fix: add disk cleanup step to Docker workflow

announcement: add application form for cloud API closed beta

.github/workflows/docker-release.yml

@@ -0,0 +1,100 @@
+name: Docker Release
+on:
+  release:
+    types: [published]
+  push:
+    tags:
+      - 'docker-rebuild-v*'  # Allow manual Docker rebuilds via tags
+
+jobs:
+  docker:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Free up disk space
+        run: |
+          echo "=== Disk space before cleanup ==="
+          df -h
+
+          # Remove unnecessary tools and libraries (frees ~25GB)
+          sudo rm -rf /usr/share/dotnet
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /opt/ghc
+          sudo rm -rf /opt/hostedtoolcache/CodeQL
+          sudo rm -rf /usr/local/share/boost
+          sudo rm -rf /usr/share/swift
+
+          # Clean apt cache
+          sudo apt-get clean
+
+          echo "=== Disk space after cleanup ==="
+          df -h
+
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Extract version from release or tag
+        id: get_version
+        run: |
+          if [ "${{ github.event_name }}" == "release" ]; then
+            # Triggered by release event
+            VERSION="${{ github.event.release.tag_name }}"
+            VERSION=${VERSION#v}  # Remove 'v' prefix
+          else
+            # Triggered by docker-rebuild-v* tag
+            VERSION=${GITHUB_REF#refs/tags/docker-rebuild-v}
+          fi
+          echo "VERSION=$VERSION" >> $GITHUB_OUTPUT
+          echo "Building Docker images for version: $VERSION"
+
+      - name: Extract major and minor versions
+        id: versions
+        run: |
+          VERSION=${{ steps.get_version.outputs.VERSION }}
+          MAJOR=$(echo $VERSION | cut -d. -f1)
+          MINOR=$(echo $VERSION | cut -d. -f1-2)
+          echo "MAJOR=$MAJOR" >> $GITHUB_OUTPUT
+          echo "MINOR=$MINOR" >> $GITHUB_OUTPUT
+          echo "Semantic versions - Major: $MAJOR, Minor: $MINOR"
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      - name: Build and push Docker images
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: true
+          tags: |
+            unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}
+            unclecode/crawl4ai:${{ steps.versions.outputs.MINOR }}
+            unclecode/crawl4ai:${{ steps.versions.outputs.MAJOR }}
+            unclecode/crawl4ai:latest
+          platforms: linux/amd64,linux/arm64
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+      - name: Summary
+        run: |
+          echo "## 🐳 Docker Release Complete!" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### Published Images" >> $GITHUB_STEP_SUMMARY
+          echo "- \`unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- \`unclecode/crawl4ai:${{ steps.versions.outputs.MINOR }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- \`unclecode/crawl4ai:${{ steps.versions.outputs.MAJOR }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- \`unclecode/crawl4ai:latest\`" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### Platforms" >> $GITHUB_STEP_SUMMARY
+          echo "- linux/amd64" >> $GITHUB_STEP_SUMMARY
+          echo "- linux/arm64" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### 🚀 Pull Command" >> $GITHUB_STEP_SUMMARY
+          echo "\`\`\`bash" >> $GITHUB_STEP_SUMMARY
+          echo "docker pull unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}" >> $GITHUB_STEP_SUMMARY
+          echo "\`\`\`" >> $GITHUB_STEP_SUMMARY

.github/workflows/docs/ARCHITECTURE.md

@@ -0,0 +1,917 @@
+# Workflow Architecture Documentation
+
+## Overview
+
+This document describes the technical architecture of the split release pipeline for Crawl4AI.
+
+---
+
+## Architecture Diagram
+
+```
+┌─────────────────────────────────────────────────────────────────┐
+│                         Developer                                │
+│                              │                                   │
+│                              ▼                                   │
+│                    git tag v1.2.3                               │
+│                    git push --tags                              │
+└──────────────────────────────┬──────────────────────────────────┘
+                               │
+                               ▼
+┌─────────────────────────────────────────────────────────────────┐
+│                      GitHub Repository                           │
+│                                                                  │
+│  ┌────────────────────────────────────────────────────────┐   │
+│  │                  Tag Event: v1.2.3                      │   │
+│  └────────────────────────────────────────────────────────┘   │
+│                              │                                   │
+│                              ▼                                   │
+│  ┌────────────────────────────────────────────────────────┐   │
+│  │           release.yml (Release Pipeline)               │   │
+│  │  ┌──────────────────────────────────────────────┐     │   │
+│  │  │ 1. Extract Version                            │     │   │
+│  │  │    v1.2.3 → 1.2.3                            │     │   │
+│  │  └──────────────────────────────────────────────┘     │   │
+│  │  ┌──────────────────────────────────────────────┐     │   │
+│  │  │ 2. Validate Version                           │     │   │
+│  │  │    Tag == __version__.py                      │     │   │
+│  │  └──────────────────────────────────────────────┘     │   │
+│  │  ┌──────────────────────────────────────────────┐     │   │
+│  │  │ 3. Build Python Package                       │     │   │
+│  │  │    - Source dist (.tar.gz)                    │     │   │
+│  │  │    - Wheel (.whl)                             │     │   │
+│  │  └──────────────────────────────────────────────┘     │   │
+│  │  ┌──────────────────────────────────────────────┐     │   │
+│  │  │ 4. Upload to PyPI                             │     │   │
+│  │  │    - Authenticate with token                  │     │   │
+│  │  │    - Upload dist/*                            │     │   │
+│  │  └──────────────────────────────────────────────┘     │   │
+│  │  ┌──────────────────────────────────────────────┐     │   │
+│  │  │ 5. Create GitHub Release                      │     │   │
+│  │  │    - Tag: v1.2.3                              │     │   │
+│  │  │    - Body: Install instructions               │     │   │
+│  │  │    - Status: Published                        │     │   │
+│  │  └──────────────────────────────────────────────┘     │   │
+│  └────────────────────────────────────────────────────────┘   │
+│                              │                                   │
+│                              ▼                                   │
+│  ┌────────────────────────────────────────────────────────┐   │
+│  │         Release Event: published (v1.2.3)              │   │
+│  └────────────────────────────────────────────────────────┘   │
+│                              │                                   │
+│                              ▼                                   │
+│  ┌────────────────────────────────────────────────────────┐   │
+│  │         docker-release.yml (Docker Pipeline)           │   │
+│  │  ┌──────────────────────────────────────────────┐     │   │
+│  │  │ 1. Extract Version from Release               │     │   │
+│  │  │    github.event.release.tag_name → 1.2.3     │     │   │
+│  │  └──────────────────────────────────────────────┘     │   │
+│  │  ┌──────────────────────────────────────────────┐     │   │
+│  │  │ 2. Parse Semantic Versions                    │     │   │
+│  │  │    1.2.3 → Major: 1, Minor: 1.2              │     │   │
+│  │  └──────────────────────────────────────────────┘     │   │
+│  │  ┌──────────────────────────────────────────────┐     │   │
+│  │  │ 3. Setup Multi-Arch Build                     │     │   │
+│  │  │    - Docker Buildx                            │     │   │
+│  │  │    - QEMU emulation                           │     │   │
+│  │  └──────────────────────────────────────────────┘     │   │
+│  │  ┌──────────────────────────────────────────────┐     │   │
+│  │  │ 4. Authenticate Docker Hub                    │     │   │
+│  │  │    - Username: DOCKER_USERNAME                │     │   │
+│  │  │    - Token: DOCKER_TOKEN                      │     │   │
+│  │  └──────────────────────────────────────────────┘     │   │
+│  │  ┌──────────────────────────────────────────────┐     │   │
+│  │  │ 5. Build Multi-Arch Images                    │     │   │
+│  │  │    ┌────────────────┬────────────────┐       │     │   │
+│  │  │    │  linux/amd64   │  linux/arm64   │       │     │   │
+│  │  │    └────────────────┴────────────────┘       │     │   │
+│  │  │    Cache: GitHub Actions (type=gha)          │     │   │
+│  │  └──────────────────────────────────────────────┘     │   │
+│  │  ┌──────────────────────────────────────────────┐     │   │
+│  │  │ 6. Push to Docker Hub                         │     │   │
+│  │  │    Tags:                                      │     │   │
+│  │  │    - unclecode/crawl4ai:1.2.3                │     │   │
+│  │  │    - unclecode/crawl4ai:1.2                  │     │   │
+│  │  │    - unclecode/crawl4ai:1                    │     │   │
+│  │  │    - unclecode/crawl4ai:latest               │     │   │
+│  │  └──────────────────────────────────────────────┘     │   │
+│  └────────────────────────────────────────────────────────┘   │
+└─────────────────────────────────────────────────────────────────┘
+                               │
+                               ▼
+┌─────────────────────────────────────────────────────────────────┐
+│                     External Services                            │
+│                                                                  │
+│  ┌──────────────┐  ┌──────────────┐  ┌──────────────┐         │
+│  │    PyPI      │  │  Docker Hub  │  │   GitHub     │         │
+│  │              │  │              │  │              │         │
+│  │  crawl4ai    │  │ unclecode/   │  │  Releases    │         │
+│  │  1.2.3       │  │ crawl4ai     │  │  v1.2.3      │         │
+│  └──────────────┘  └──────────────┘  └──────────────┘         │
+└─────────────────────────────────────────────────────────────────┘
+```
+
+---
+
+## Component Details
+
+### 1. Release Pipeline (release.yml)
+
+#### Purpose
+Fast publication of Python package and GitHub release.
+
+#### Input
+- **Trigger**: Git tag matching `v*` (excluding `test-v*`)
+- **Example**: `v1.2.3`
+
+#### Processing Stages
+
+##### Stage 1: Version Extraction
+```bash
+Input:  refs/tags/v1.2.3
+Output: VERSION=1.2.3
+```
+
+**Implementation**:
+```bash
+TAG_VERSION=${GITHUB_REF#refs/tags/v}  # Remove 'refs/tags/v' prefix
+echo "VERSION=$TAG_VERSION" >> $GITHUB_OUTPUT
+```
+
+##### Stage 2: Version Validation
+```bash
+Input:  TAG_VERSION=1.2.3
+Check:  crawl4ai/__version__.py contains __version__ = "1.2.3"
+Output: Pass/Fail
+```
+
+**Implementation**:
+```bash
+PACKAGE_VERSION=$(python -c "from crawl4ai.__version__ import __version__; print(__version__)")
+if [ "$TAG_VERSION" != "$PACKAGE_VERSION" ]; then
+  exit 1
+fi
+```
+
+##### Stage 3: Package Build
+```bash
+Input:  Source code + pyproject.toml
+Output: dist/crawl4ai-1.2.3.tar.gz
+        dist/crawl4ai-1.2.3-py3-none-any.whl
+```
+
+**Implementation**:
+```bash
+python -m build
+# Uses build backend defined in pyproject.toml
+```
+
+##### Stage 4: PyPI Upload
+```bash
+Input:  dist/*.{tar.gz,whl}
+Auth:   PYPI_TOKEN
+Output: Package published to PyPI
+```
+
+**Implementation**:
+```bash
+twine upload dist/*
+# Environment:
+#   TWINE_USERNAME: __token__
+#   TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
+```
+
+##### Stage 5: GitHub Release Creation
+```bash
+Input:  Tag: v1.2.3
+        Body: Markdown content
+Output: Published GitHub release
+```
+
+**Implementation**:
+```yaml
+uses: softprops/action-gh-release@v2
+with:
+  tag_name: v1.2.3
+  name: Release v1.2.3
+  body: |
+    Installation instructions and changelog
+  draft: false
+  prerelease: false
+```
+
+#### Output
+- **PyPI Package**: https://pypi.org/project/crawl4ai/1.2.3/
+- **GitHub Release**: Published release on repository
+- **Event**: `release.published` (triggers Docker workflow)
+
+#### Timeline
+```
+0:00 - Tag pushed
+0:01 - Checkout + Python setup
+0:02 - Version validation
+0:03 - Package build
+0:04 - PyPI upload starts
+0:06 - PyPI upload complete
+0:07 - GitHub release created
+0:08 - Workflow complete
+```
+
+---
+
+### 2. Docker Release Pipeline (docker-release.yml)
+
+#### Purpose
+Build and publish multi-architecture Docker images.
+
+#### Inputs
+
+##### Input 1: Release Event (Automatic)
+```yaml
+Event: release.published
+Data:  github.event.release.tag_name = "v1.2.3"
+```
+
+##### Input 2: Docker Rebuild Tag (Manual)
+```yaml
+Tag: docker-rebuild-v1.2.3
+```
+
+#### Processing Stages
+
+##### Stage 1: Version Detection
+```bash
+# From release event:
+VERSION = github.event.release.tag_name.strip("v")
+# Result: "1.2.3"
+
+# From rebuild tag:
+VERSION = GITHUB_REF.replace("refs/tags/docker-rebuild-v", "")
+# Result: "1.2.3"
+```
+
+##### Stage 2: Semantic Version Parsing
+```bash
+Input:  VERSION=1.2.3
+Output: MAJOR=1
+        MINOR=1.2
+        PATCH=3 (implicit)
+```
+
+**Implementation**:
+```bash
+MAJOR=$(echo $VERSION | cut -d. -f1)    # Extract first component
+MINOR=$(echo $VERSION | cut -d. -f1-2)  # Extract first two components
+```
+
+##### Stage 3: Multi-Architecture Setup
+```yaml
+Setup:
+  - Docker Buildx (multi-platform builder)
+  - QEMU (ARM emulation on x86)
+
+Platforms:
+  - linux/amd64 (x86_64)
+  - linux/arm64 (aarch64)
+```
+
+**Architecture**:
+```
+GitHub Runner (linux/amd64)
+  ├─ Buildx Builder
+  │   ├─ Native: Build linux/amd64 image
+  │   └─ QEMU: Emulate ARM to build linux/arm64 image
+  └─ Generate manifest list (points to both images)
+```
+
+##### Stage 4: Docker Hub Authentication
+```bash
+Input:  DOCKER_USERNAME
+        DOCKER_TOKEN
+Output: Authenticated Docker client
+```
+
+##### Stage 5: Build with Cache
+```yaml
+Cache Configuration:
+  cache-from: type=gha           # Read from GitHub Actions cache
+  cache-to: type=gha,mode=max    # Write all layers
+
+Cache Key Components:
+  - Workflow file path
+  - Branch name
+  - Architecture (amd64/arm64)
+```
+
+**Cache Hierarchy**:
+```
+Cache Entry: main/docker-release.yml/linux-amd64
+  ├─ Layer: sha256:abc123... (FROM python:3.12)
+  ├─ Layer: sha256:def456... (RUN apt-get update)
+  ├─ Layer: sha256:ghi789... (COPY requirements.txt)
+  ├─ Layer: sha256:jkl012... (RUN pip install)
+  └─ Layer: sha256:mno345... (COPY . /app)
+
+Cache Hit/Miss Logic:
+  - If layer input unchanged → cache hit → skip build
+  - If layer input changed → cache miss → rebuild + all subsequent layers
+```
+
+##### Stage 6: Tag Generation
+```bash
+Input:  VERSION=1.2.3, MAJOR=1, MINOR=1.2
+
+Output Tags:
+  - unclecode/crawl4ai:1.2.3    (exact version)
+  - unclecode/crawl4ai:1.2      (minor version)
+  - unclecode/crawl4ai:1        (major version)
+  - unclecode/crawl4ai:latest   (latest stable)
+```
+
+**Tag Strategy**:
+- All tags point to same image SHA
+- Users can pin to desired stability level
+- Pushing new version updates `1`, `1.2`, and `latest` automatically
+
+##### Stage 7: Push to Registry
+```bash
+For each tag:
+  For each platform (amd64, arm64):
+    Push image to Docker Hub
+
+Create manifest list:
+  Manifest: unclecode/crawl4ai:1.2.3
+    ├─ linux/amd64: sha256:abc...
+    └─ linux/arm64: sha256:def...
+
+Docker CLI automatically selects correct platform on pull
+```
+
+#### Output
+- **Docker Images**: 4 tags × 2 platforms = 8 image variants + 4 manifests
+- **Docker Hub**: https://hub.docker.com/r/unclecode/crawl4ai/tags
+
+#### Timeline
+
+**Cold Cache (First Build)**:
+```
+0:00 - Release event received
+0:01 - Checkout + Buildx setup
+0:02 - Docker Hub auth
+0:03 - Start build (amd64)
+0:08 - Complete amd64 build
+0:09 - Start build (arm64)
+0:14 - Complete arm64 build
+0:15 - Generate manifests
+0:16 - Push all tags
+0:17 - Workflow complete
+```
+
+**Warm Cache (Code Change Only)**:
+```
+0:00 - Release event received
+0:01 - Checkout + Buildx setup
+0:02 - Docker Hub auth
+0:03 - Start build (amd64) - cache hit for layers 1-4
+0:04 - Complete amd64 build (only layer 5 rebuilt)
+0:05 - Start build (arm64) - cache hit for layers 1-4
+0:06 - Complete arm64 build (only layer 5 rebuilt)
+0:07 - Generate manifests
+0:08 - Push all tags
+0:09 - Workflow complete
+```
+
+---
+
+## Data Flow
+
+### Version Information Flow
+
+```
+Developer
+  │
+  ▼
+crawl4ai/__version__.py
+  __version__ = "1.2.3"
+  │
+  ├─► Git Tag
+  │     v1.2.3
+  │       │
+  │       ▼
+  │     release.yml
+  │       │
+  │       ├─► Validation
+  │       │     ✓ Match
+  │       │
+  │       ├─► PyPI Package
+  │       │     crawl4ai==1.2.3
+  │       │
+  │       └─► GitHub Release
+  │             v1.2.3
+  │               │
+  │               ▼
+  │           docker-release.yml
+  │               │
+  │               └─► Docker Tags
+  │                     1.2.3, 1.2, 1, latest
+  │
+  └─► Package Metadata
+        pyproject.toml
+          version = "1.2.3"
+```
+
+### Secrets Flow
+
+```
+GitHub Secrets (Encrypted at Rest)
+  │
+  ├─► PYPI_TOKEN
+  │     │
+  │     ▼
+  │   release.yml
+  │     │
+  │     ▼
+  │   TWINE_PASSWORD env var (masked in logs)
+  │     │
+  │     ▼
+  │   PyPI API (HTTPS)
+  │
+  ├─► DOCKER_USERNAME
+  │     │
+  │     ▼
+  │   docker-release.yml
+  │     │
+  │     ▼
+  │   docker/login-action (masked in logs)
+  │     │
+  │     ▼
+  │   Docker Hub API (HTTPS)
+  │
+  └─► DOCKER_TOKEN
+        │
+        ▼
+      docker-release.yml
+        │
+        ▼
+      docker/login-action (masked in logs)
+        │
+        ▼
+      Docker Hub API (HTTPS)
+```
+
+### Artifact Flow
+
+```
+Source Code
+  │
+  ├─► release.yml
+  │     │
+  │     ▼
+  │   python -m build
+  │     │
+  │     ├─► crawl4ai-1.2.3.tar.gz
+  │     │     │
+  │     │     ▼
+  │     │   PyPI Storage
+  │     │     │
+  │     │     ▼
+  │     │   pip install crawl4ai
+  │     │
+  │     └─► crawl4ai-1.2.3-py3-none-any.whl
+  │           │
+  │           ▼
+  │         PyPI Storage
+  │           │
+  │           ▼
+  │         pip install crawl4ai
+  │
+  └─► docker-release.yml
+        │
+        ▼
+      docker build
+        │
+        ├─► Image: linux/amd64
+        │     │
+        │     └─► Docker Hub
+        │           unclecode/crawl4ai:1.2.3-amd64
+        │
+        └─► Image: linux/arm64
+              │
+              └─► Docker Hub
+                    unclecode/crawl4ai:1.2.3-arm64
+```
+
+---
+
+## State Machines
+
+### Release Pipeline State Machine
+
+```
+┌─────────┐
+│  START  │
+└────┬────┘
+     │
+     ▼
+┌──────────────┐
+│ Extract      │
+│ Version      │
+└──────┬───────┘
+       │
+       ▼
+┌──────────────┐      ┌─────────┐
+│ Validate     │─────►│ FAILED  │
+│ Version      │ No   │ (Exit 1)│
+└──────┬───────┘      └─────────┘
+       │ Yes
+       ▼
+┌──────────────┐
+│ Build        │
+│ Package      │
+└──────┬───────┘
+       │
+       ▼
+┌──────────────┐      ┌─────────┐
+│ Upload       │─────►│ FAILED  │
+│ to PyPI      │ Error│ (Exit 1)│
+└──────┬───────┘      └─────────┘
+       │ Success
+       ▼
+┌──────────────┐
+│ Create       │
+│ GH Release   │
+└──────┬───────┘
+       │
+       ▼
+┌──────────────┐
+│  SUCCESS     │
+│ (Emit Event) │
+└──────────────┘
+```
+
+### Docker Pipeline State Machine
+
+```
+┌─────────┐
+│  START  │
+│ (Event) │
+└────┬────┘
+     │
+     ▼
+┌──────────────┐
+│ Detect       │
+│ Version      │
+│ Source       │
+└──────┬───────┘
+       │
+       ▼
+┌──────────────┐
+│ Parse        │
+│ Semantic     │
+│ Versions     │
+└──────┬───────┘
+       │
+       ▼
+┌──────────────┐      ┌─────────┐
+│ Authenticate │─────►│ FAILED  │
+│ Docker Hub   │ Error│ (Exit 1)│
+└──────┬───────┘      └─────────┘
+       │ Success
+       ▼
+┌──────────────┐
+│ Build        │
+│ amd64        │
+└──────┬───────┘
+       │
+       ▼
+┌──────────────┐      ┌─────────┐
+│ Build        │─────►│ FAILED  │
+│ arm64        │ Error│ (Exit 1)│
+└──────┬───────┘      └─────────┘
+       │ Success
+       ▼
+┌──────────────┐
+│ Push All     │
+│ Tags         │
+└──────┬───────┘
+       │
+       ▼
+┌──────────────┐
+│  SUCCESS     │
+└──────────────┘
+```
+
+---
+
+## Security Architecture
+
+### Threat Model
+
+#### Threats Mitigated
+
+1. **Secret Exposure**
+   - Mitigation: GitHub Actions secret masking
+   - Evidence: Secrets never appear in logs
+
+2. **Unauthorized Package Upload**
+   - Mitigation: Scoped PyPI tokens
+   - Evidence: Token limited to `crawl4ai` project
+
+3. **Man-in-the-Middle**
+   - Mitigation: HTTPS for all API calls
+   - Evidence: PyPI, Docker Hub, GitHub all use TLS
+
+4. **Supply Chain Tampering**
+   - Mitigation: Immutable artifacts, content checksums
+   - Evidence: PyPI stores SHA256, Docker uses content-addressable storage
+
+#### Trust Boundaries
+
+```
+┌─────────────────────────────────────────┐
+│         Trusted Zone                     │
+│  ┌────────────────────────────────┐    │
+│  │  GitHub Actions Runner         │    │
+│  │  - Ephemeral VM                │    │
+│  │  - Isolated environment        │    │
+│  │  - Access to secrets           │    │
+│  └────────────────────────────────┘    │
+│                │                         │
+│                │ HTTPS (TLS 1.2+)       │
+│                ▼                         │
+└─────────────────────────────────────────┘
+                 │
+    ┌────────────┼────────────┐
+    │            │            │
+    ▼            ▼            ▼
+┌────────┐  ┌─────────┐  ┌──────────┐
+│  PyPI  │  │  Docker │  │  GitHub  │
+│  API   │  │  Hub    │  │  API     │
+└────────┘  └─────────┘  └──────────┘
+ External     External     External
+  Service      Service      Service
+```
+
+### Secret Management
+
+#### Secret Lifecycle
+
+```
+Creation (Developer)
+  │
+  ├─► PyPI: Create API token (scoped to project)
+  ├─► Docker Hub: Create access token (read/write)
+  │
+  ▼
+Storage (GitHub)
+  │
+  ├─► Encrypted at rest (AES-256)
+  ├─► Access controlled (repo-scoped)
+  │
+  ▼
+Usage (Workflow)
+  │
+  ├─► Injected as env vars
+  ├─► Masked in logs (GitHub redacts on output)
+  ├─► Never persisted to disk (in-memory only)
+  │
+  ▼
+Transmission (API Call)
+  │
+  ├─► HTTPS only
+  ├─► TLS 1.2+ with strong ciphers
+  │
+  ▼
+Rotation (Manual)
+  │
+  └─► Regenerate on PyPI/Docker Hub
+      Update GitHub secret
+```
+
+---
+
+## Performance Characteristics
+
+### Release Pipeline Performance
+
+| Metric | Value | Notes |
+|--------|-------|-------|
+| Cold start | ~2-3 min | First run on new runner |
+| Warm start | ~2-3 min | Minimal caching benefit |
+| PyPI upload | ~30-60 sec | Network-bound |
+| Package build | ~30 sec | CPU-bound |
+| Parallelization | None | Sequential by design |
+
+### Docker Pipeline Performance
+
+| Metric | Cold Cache | Warm Cache (code) | Warm Cache (deps) |
+|--------|-----------|-------------------|-------------------|
+| Total time | 10-15 min | 1-2 min | 3-5 min |
+| amd64 build | 5-7 min | 30-60 sec | 1-2 min |
+| arm64 build | 5-7 min | 30-60 sec | 1-2 min |
+| Push time | 1-2 min | 30 sec | 30 sec |
+| Cache hit rate | 0% | 85% | 60% |
+
+### Cache Performance Model
+
+```python
+def estimate_build_time(changes):
+    base_time = 60  # seconds (setup + push)
+
+    if "Dockerfile" in changes:
+        return base_time + (10 * 60)  # Full rebuild: ~11 min
+    elif "requirements.txt" in changes:
+        return base_time + (3 * 60)   # Deps rebuild: ~4 min
+    elif any(f.endswith(".py") for f in changes):
+        return base_time + 60          # Code only: ~2 min
+    else:
+        return base_time               # No changes: ~1 min
+```
+
+---
+
+## Scalability Considerations
+
+### Current Limits
+
+| Resource | Limit | Impact |
+|----------|-------|--------|
+| Workflow concurrency | 20 (default) | Max 20 releases in parallel |
+| Artifact storage | 500 MB/artifact | PyPI packages small (<10 MB) |
+| Cache storage | 10 GB/repo | Docker layers fit comfortably |
+| Workflow run time | 6 hours | Plenty of headroom |
+
+### Scaling Strategies
+
+#### Horizontal Scaling (Multiple Repos)
+```
+crawl4ai (main)
+  ├─ release.yml
+  └─ docker-release.yml
+
+crawl4ai-plugins (separate)
+  ├─ release.yml
+  └─ docker-release.yml
+
+Each repo has independent:
+  - Secrets
+  - Cache (10 GB each)
+  - Concurrency limits (20 each)
+```
+
+#### Vertical Scaling (Larger Runners)
+```yaml
+jobs:
+  docker:
+    runs-on: ubuntu-latest-8-cores  # GitHub-hosted larger runner
+    # 4x faster builds for CPU-bound layers
+```
+
+---
+
+## Disaster Recovery
+
+### Failure Scenarios
+
+#### Scenario 1: Release Pipeline Fails
+
+**Failure Point**: PyPI upload fails (network error)
+
+**State**:
+- ✓ Version validated
+- ✓ Package built
+- ✗ PyPI upload
+- ✗ GitHub release
+
+**Recovery**:
+```bash
+# Manual upload
+twine upload dist/*
+
+# Retry workflow (re-run from GitHub Actions UI)
+```
+
+**Prevention**: Add retry logic to PyPI upload
+
+#### Scenario 2: Docker Pipeline Fails
+
+**Failure Point**: ARM build fails (dependency issue)
+
+**State**:
+- ✓ PyPI published
+- ✓ GitHub release created
+- ✓ amd64 image built
+- ✗ arm64 image build
+
+**Recovery**:
+```bash
+# Fix Dockerfile
+git commit -am "fix: ARM build dependency"
+
+# Trigger rebuild
+git tag docker-rebuild-v1.2.3
+git push origin docker-rebuild-v1.2.3
+```
+
+**Impact**: PyPI package available, only Docker ARM users affected
+
+#### Scenario 3: Partial Release
+
+**Failure Point**: GitHub release creation fails
+
+**State**:
+- ✓ PyPI published
+- ✗ GitHub release
+- ✗ Docker images
+
+**Recovery**:
+```bash
+# Create release manually
+gh release create v1.2.3 \
+  --title "Release v1.2.3" \
+  --notes "..."
+
+# This triggers docker-release.yml automatically
+```
+
+---
+
+## Monitoring and Observability
+
+### Metrics to Track
+
+#### Release Pipeline
+- Success rate (target: >99%)
+- Duration (target: <3 min)
+- PyPI upload time (target: <60 sec)
+
+#### Docker Pipeline
+- Success rate (target: >95%)
+- Duration (target: <15 min cold, <2 min warm)
+- Cache hit rate (target: >80% for code changes)
+
+### Alerting
+
+**Critical Alerts**:
+- Release pipeline failure (blocks release)
+- PyPI authentication failure (expired token)
+
+**Warning Alerts**:
+- Docker build >15 min (performance degradation)
+- Cache hit rate <50% (cache issue)
+
+### Logging
+
+**GitHub Actions Logs**:
+- Retention: 90 days
+- Downloadable: Yes
+- Searchable: Limited
+
+**Recommended External Logging**:
+```yaml
+- name: Send logs to external service
+  if: failure()
+  run: |
+    curl -X POST https://logs.example.com/api/v1/logs \
+      -H "Content-Type: application/json" \
+      -d "{\"workflow\": \"${{ github.workflow }}\", \"status\": \"failed\"}"
+```
+
+---
+
+## Future Enhancements
+
+### Planned Improvements
+
+1. **Automated Changelog Generation**
+   - Use conventional commits
+   - Generate CHANGELOG.md automatically
+
+2. **Pre-release Testing**
+   - Test builds on `test-v*` tags
+   - Upload to TestPyPI
+
+3. **Notification System**
+   - Slack/Discord notifications on release
+   - Email on failure
+
+4. **Performance Optimization**
+   - Parallel Docker builds (amd64 + arm64 simultaneously)
+   - Persistent runners for better caching
+
+5. **Enhanced Validation**
+   - Smoke tests after PyPI upload
+   - Container security scanning
+
+---
+
+## References
+
+- [GitHub Actions Architecture](https://docs.github.com/en/actions/learn-github-actions/understanding-github-actions)
+- [Docker Build Cache](https://docs.docker.com/build/cache/)
+- [PyPI API Documentation](https://warehouse.pypa.io/api-reference/)
+
+---
+
+**Last Updated**: 2025-01-21
+**Version**: 2.0

.github/workflows/docs/WORKFLOW_REFERENCE.md

@@ -0,0 +1,287 @@
+# Workflow Quick Reference
+
+## Quick Commands
+
+### Standard Release
+```bash
+# 1. Update version
+vim crawl4ai/__version__.py  # Set to "1.2.3"
+
+# 2. Commit and tag
+git add crawl4ai/__version__.py
+git commit -m "chore: bump version to 1.2.3"
+git tag v1.2.3
+git push origin main
+git push origin v1.2.3
+
+# 3. Monitor
+# - PyPI: ~2-3 minutes
+# - Docker: ~1-15 minutes
+```
+
+### Docker Rebuild Only
+```bash
+git tag docker-rebuild-v1.2.3
+git push origin docker-rebuild-v1.2.3
+```
+
+### Delete Tag (Undo Release)
+```bash
+# Local
+git tag -d v1.2.3
+
+# Remote
+git push --delete origin v1.2.3
+
+# GitHub Release
+gh release delete v1.2.3
+```
+
+---
+
+## Workflow Triggers
+
+### release.yml
+| Event | Pattern | Example |
+|-------|---------|---------|
+| Tag push | `v*` | `v1.2.3` |
+| Excludes | `test-v*` | `test-v1.2.3` |
+
+### docker-release.yml
+| Event | Pattern | Example |
+|-------|---------|---------|
+| Release published | `release.published` | Automatic |
+| Tag push | `docker-rebuild-v*` | `docker-rebuild-v1.2.3` |
+
+---
+
+## Environment Variables
+
+### release.yml
+| Variable | Source | Example |
+|----------|--------|---------|
+| `VERSION` | Git tag | `1.2.3` |
+| `TWINE_USERNAME` | Static | `__token__` |
+| `TWINE_PASSWORD` | Secret | `pypi-Ag...` |
+| `GITHUB_TOKEN` | Auto | `ghp_...` |
+
+### docker-release.yml
+| Variable | Source | Example |
+|----------|--------|---------|
+| `VERSION` | Release/Tag | `1.2.3` |
+| `MAJOR` | Computed | `1` |
+| `MINOR` | Computed | `1.2` |
+| `DOCKER_USERNAME` | Secret | `unclecode` |
+| `DOCKER_TOKEN` | Secret | `dckr_pat_...` |
+
+---
+
+## Docker Tags Generated
+
+| Version | Tags Created |
+|---------|-------------|
+| v1.0.0 | `1.0.0`, `1.0`, `1`, `latest` |
+| v1.1.0 | `1.1.0`, `1.1`, `1`, `latest` |
+| v1.2.3 | `1.2.3`, `1.2`, `1`, `latest` |
+| v2.0.0 | `2.0.0`, `2.0`, `2`, `latest` |
+
+---
+
+## Workflow Outputs
+
+### release.yml
+| Output | Location | Time |
+|--------|----------|------|
+| PyPI Package | https://pypi.org/project/crawl4ai/ | ~2-3 min |
+| GitHub Release | Repository → Releases | ~2-3 min |
+| Workflow Summary | Actions → Run → Summary | Immediate |
+
+### docker-release.yml
+| Output | Location | Time |
+|--------|----------|------|
+| Docker Images | https://hub.docker.com/r/unclecode/crawl4ai | ~1-15 min |
+| Workflow Summary | Actions → Run → Summary | Immediate |
+
+---
+
+## Common Issues
+
+| Issue | Solution |
+|-------|----------|
+| Version mismatch | Update `crawl4ai/__version__.py` to match tag |
+| PyPI 403 Forbidden | Check `PYPI_TOKEN` secret |
+| PyPI 400 File exists | Version already published, increment version |
+| Docker auth failed | Regenerate `DOCKER_TOKEN` |
+| Docker build timeout | Check Dockerfile, review build logs |
+| Cache not working | First build on branch always cold |
+
+---
+
+## Secrets Checklist
+
+- [ ] `PYPI_TOKEN` - PyPI API token (project or account scope)
+- [ ] `DOCKER_USERNAME` - Docker Hub username
+- [ ] `DOCKER_TOKEN` - Docker Hub access token (read/write)
+- [ ] `GITHUB_TOKEN` - Auto-provided (no action needed)
+
+---
+
+## Workflow Dependencies
+
+### release.yml Dependencies
+```yaml
+Python: 3.12
+Actions:
+  - actions/checkout@v4
+  - actions/setup-python@v5
+  - softprops/action-gh-release@v2
+PyPI Packages:
+  - build
+  - twine
+```
+
+### docker-release.yml Dependencies
+```yaml
+Actions:
+  - actions/checkout@v4
+  - docker/setup-buildx-action@v3
+  - docker/login-action@v3
+  - docker/build-push-action@v5
+Docker:
+  - Buildx
+  - QEMU (for multi-arch)
+```
+
+---
+
+## Cache Information
+
+### Type
+- GitHub Actions Cache (`type=gha`)
+
+### Storage
+- **Limit**: 10GB per repository
+- **Retention**: 7 days for unused entries
+- **Cleanup**: Automatic LRU eviction
+
+### Performance
+| Scenario | Cache Hit | Build Time |
+|----------|-----------|------------|
+| First build | 0% | 10-15 min |
+| Code change only | 85% | 1-2 min |
+| Dependency update | 60% | 3-5 min |
+| No changes | 100% | 30-60 sec |
+
+---
+
+## Build Platforms
+
+| Platform | Architecture | Devices |
+|----------|--------------|---------|
+| linux/amd64 | x86_64 | Intel/AMD servers, AWS EC2, GCP |
+| linux/arm64 | aarch64 | Apple Silicon, AWS Graviton, Raspberry Pi |
+
+---
+
+## Version Validation
+
+### Pre-Tag Checklist
+```bash
+# Check current version
+python -c "from crawl4ai.__version__ import __version__; print(__version__)"
+
+# Verify it matches intended tag
+# If tag is v1.2.3, version should be "1.2.3"
+```
+
+### Post-Release Verification
+```bash
+# PyPI
+pip install crawl4ai==1.2.3
+python -c "import crawl4ai; print(crawl4ai.__version__)"
+
+# Docker
+docker pull unclecode/crawl4ai:1.2.3
+docker run unclecode/crawl4ai:1.2.3 python -c "import crawl4ai; print(crawl4ai.__version__)"
+```
+
+---
+
+## Monitoring URLs
+
+| Service | URL |
+|---------|-----|
+| GitHub Actions | `https://github.com/{owner}/{repo}/actions` |
+| PyPI Project | `https://pypi.org/project/crawl4ai/` |
+| Docker Hub | `https://hub.docker.com/r/unclecode/crawl4ai` |
+| GitHub Releases | `https://github.com/{owner}/{repo}/releases` |
+
+---
+
+## Rollback Strategy
+
+### PyPI (Cannot Delete)
+```bash
+# Increment patch version
+git tag v1.2.4
+git push origin v1.2.4
+```
+
+### Docker (Can Overwrite)
+```bash
+# Rebuild with fix
+git tag docker-rebuild-v1.2.3
+git push origin docker-rebuild-v1.2.3
+```
+
+### GitHub Release
+```bash
+# Delete release
+gh release delete v1.2.3
+
+# Delete tag
+git push --delete origin v1.2.3
+```
+
+---
+
+## Status Badge Markdown
+
+```markdown
+[![Release Pipeline](https://github.com/{owner}/{repo}/actions/workflows/release.yml/badge.svg)](https://github.com/{owner}/{repo}/actions/workflows/release.yml)
+
+[![Docker Release](https://github.com/{owner}/{repo}/actions/workflows/docker-release.yml/badge.svg)](https://github.com/{owner}/{repo}/actions/workflows/docker-release.yml)
+```
+
+---
+
+## Timeline Example
+
+```
+0:00 - Push tag v1.2.3
+0:01 - release.yml starts
+0:02 - Version validation passes
+0:03 - Package built
+0:04 - PyPI upload starts
+0:06 - PyPI upload complete ✓
+0:07 - GitHub release created ✓
+0:08 - release.yml complete
+0:08 - docker-release.yml triggered
+0:10 - Docker build starts
+0:12 - amd64 image built (cache hit)
+0:14 - arm64 image built (cache hit)
+0:15 - Images pushed to Docker Hub ✓
+0:16 - docker-release.yml complete
+
+Total: ~16 minutes
+Critical path (PyPI + GitHub): ~8 minutes
+```
+
+---
+
+## Contact
+
+For workflow issues:
+1. Check Actions tab for logs
+2. Review this reference
+3. See [README.md](./README.md) for detailed docs

.github/workflows/release.yml

@@ -10,53 +10,53 @@ jobs:
     runs-on: ubuntu-latest
     permissions:
       contents: write  # Required for creating releases
-    
+
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
-      
+
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
           python-version: '3.12'
-      
+
       - name: Extract version from tag
         id: get_version
         run: |
           TAG_VERSION=${GITHUB_REF#refs/tags/v}
           echo "VERSION=$TAG_VERSION" >> $GITHUB_OUTPUT
           echo "Releasing version: $TAG_VERSION"
-      
+
       - name: Install package dependencies
         run: |
           pip install -e .
-      
+
       - name: Check version consistency
         run: |
           TAG_VERSION=${{ steps.get_version.outputs.VERSION }}
           PACKAGE_VERSION=$(python -c "from crawl4ai.__version__ import __version__; print(__version__)")
-          
+
           echo "Tag version: $TAG_VERSION"
           echo "Package version: $PACKAGE_VERSION"
-          
+
           if [ "$TAG_VERSION" != "$PACKAGE_VERSION" ]; then
             echo "❌ Version mismatch! Tag: $TAG_VERSION, Package: $PACKAGE_VERSION"
             echo "Please update crawl4ai/__version__.py to match the tag version"
             exit 1
           fi
           echo "✅ Version check passed: $TAG_VERSION"
-      
+
       - name: Install build dependencies
         run: |
           python -m pip install --upgrade pip
           pip install build twine
-      
+
       - name: Build package
         run: python -m build
-      
+
       - name: Check package
         run: twine check dist/*
-      
+
       - name: Upload to PyPI
         env:
           TWINE_USERNAME: __token__
@@ -65,37 +65,7 @@ jobs:
           echo "📦 Uploading to PyPI..."
           twine upload dist/*
           echo "✅ Package uploaded to https://pypi.org/project/crawl4ai/"
-      
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      
-      - name: Log in to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
-      
-      - name: Extract major and minor versions
-        id: versions
-        run: |
-          VERSION=${{ steps.get_version.outputs.VERSION }}
-          MAJOR=$(echo $VERSION | cut -d. -f1)
-          MINOR=$(echo $VERSION | cut -d. -f1-2)
-          echo "MAJOR=$MAJOR" >> $GITHUB_OUTPUT
-          echo "MINOR=$MINOR" >> $GITHUB_OUTPUT
-      
-      - name: Build and push Docker images
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          push: true
-          tags: |
-            unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}
-            unclecode/crawl4ai:${{ steps.versions.outputs.MINOR }}
-            unclecode/crawl4ai:${{ steps.versions.outputs.MAJOR }}
-            unclecode/crawl4ai:latest
-          platforms: linux/amd64,linux/arm64
-      
+
       - name: Create GitHub Release
         uses: softprops/action-gh-release@v2
         with:
@@ -103,26 +73,29 @@ jobs:
           name: Release v${{ steps.get_version.outputs.VERSION }}
           body: |
             ## 🎉 Crawl4AI v${{ steps.get_version.outputs.VERSION }} Released!
-            
+
             ### 📦 Installation
-            
+
             **PyPI:**
             ```bash
             pip install crawl4ai==${{ steps.get_version.outputs.VERSION }}
             ```
-            
+
             **Docker:**
             ```bash
             docker pull unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}
             docker pull unclecode/crawl4ai:latest
             ```
-            
+
+            **Note:** Docker images are being built and will be available shortly.
+            Check the [Docker Release workflow](https://github.com/${{ github.repository }}/actions/workflows/docker-release.yml) for build status.
+
             ### 📝 What's Changed
             See [CHANGELOG.md](https://github.com/${{ github.repository }}/blob/main/CHANGELOG.md) for details.
           draft: false
           prerelease: false
           token: ${{ secrets.GITHUB_TOKEN }}
-      
+
       - name: Summary
         run: |
           echo "## 🚀 Release Complete!" >> $GITHUB_STEP_SUMMARY
@@ -132,11 +105,9 @@ jobs:
           echo "- URL: https://pypi.org/project/crawl4ai/" >> $GITHUB_STEP_SUMMARY
           echo "- Install: \`pip install crawl4ai==${{ steps.get_version.outputs.VERSION }}\`" >> $GITHUB_STEP_SUMMARY
           echo "" >> $GITHUB_STEP_SUMMARY
-          echo "### 🐳 Docker Images" >> $GITHUB_STEP_SUMMARY
-          echo "- \`unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}\`" >> $GITHUB_STEP_SUMMARY
-          echo "- \`unclecode/crawl4ai:${{ steps.versions.outputs.MINOR }}\`" >> $GITHUB_STEP_SUMMARY
-          echo "- \`unclecode/crawl4ai:${{ steps.versions.outputs.MAJOR }}\`" >> $GITHUB_STEP_SUMMARY
-          echo "- \`unclecode/crawl4ai:latest\`" >> $GITHUB_STEP_SUMMARY
-          echo "" >> $GITHUB_STEP_SUMMARY
           echo "### 📋 GitHub Release" >> $GITHUB_STEP_SUMMARY
-          echo "https://github.com/${{ github.repository }}/releases/tag/v${{ steps.get_version.outputs.VERSION }}" >> $GITHUB_STEP_SUMMARY
+          echo "- https://github.com/${{ github.repository }}/releases/tag/v${{ steps.get_version.outputs.VERSION }}" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### 🐳 Docker Images" >> $GITHUB_STEP_SUMMARY
+          echo "Docker images are being built in a separate workflow." >> $GITHUB_STEP_SUMMARY
+          echo "Check: https://github.com/${{ github.repository }}/actions/workflows/docker-release.yml" >> $GITHUB_STEP_SUMMARY

.github/workflows/release.yml.backup

@@ -0,0 +1,142 @@
+name: Release Pipeline
+on:
+  push:
+    tags:
+      - 'v*'
+      - '!test-v*'  # Exclude test tags
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write  # Required for creating releases
+    
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      
+      - name: Extract version from tag
+        id: get_version
+        run: |
+          TAG_VERSION=${GITHUB_REF#refs/tags/v}
+          echo "VERSION=$TAG_VERSION" >> $GITHUB_OUTPUT
+          echo "Releasing version: $TAG_VERSION"
+      
+      - name: Install package dependencies
+        run: |
+          pip install -e .
+      
+      - name: Check version consistency
+        run: |
+          TAG_VERSION=${{ steps.get_version.outputs.VERSION }}
+          PACKAGE_VERSION=$(python -c "from crawl4ai.__version__ import __version__; print(__version__)")
+          
+          echo "Tag version: $TAG_VERSION"
+          echo "Package version: $PACKAGE_VERSION"
+          
+          if [ "$TAG_VERSION" != "$PACKAGE_VERSION" ]; then
+            echo "❌ Version mismatch! Tag: $TAG_VERSION, Package: $PACKAGE_VERSION"
+            echo "Please update crawl4ai/__version__.py to match the tag version"
+            exit 1
+          fi
+          echo "✅ Version check passed: $TAG_VERSION"
+      
+      - name: Install build dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install build twine
+      
+      - name: Build package
+        run: python -m build
+      
+      - name: Check package
+        run: twine check dist/*
+      
+      - name: Upload to PyPI
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
+        run: |
+          echo "📦 Uploading to PyPI..."
+          twine upload dist/*
+          echo "✅ Package uploaded to https://pypi.org/project/crawl4ai/"
+      
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+      
+      - name: Extract major and minor versions
+        id: versions
+        run: |
+          VERSION=${{ steps.get_version.outputs.VERSION }}
+          MAJOR=$(echo $VERSION | cut -d. -f1)
+          MINOR=$(echo $VERSION | cut -d. -f1-2)
+          echo "MAJOR=$MAJOR" >> $GITHUB_OUTPUT
+          echo "MINOR=$MINOR" >> $GITHUB_OUTPUT
+      
+      - name: Build and push Docker images
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: true
+          tags: |
+            unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}
+            unclecode/crawl4ai:${{ steps.versions.outputs.MINOR }}
+            unclecode/crawl4ai:${{ steps.versions.outputs.MAJOR }}
+            unclecode/crawl4ai:latest
+          platforms: linux/amd64,linux/arm64
+      
+      - name: Create GitHub Release
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: v${{ steps.get_version.outputs.VERSION }}
+          name: Release v${{ steps.get_version.outputs.VERSION }}
+          body: |
+            ## 🎉 Crawl4AI v${{ steps.get_version.outputs.VERSION }} Released!
+            
+            ### 📦 Installation
+            
+            **PyPI:**
+            ```bash
+            pip install crawl4ai==${{ steps.get_version.outputs.VERSION }}
+            ```
+            
+            **Docker:**
+            ```bash
+            docker pull unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}
+            docker pull unclecode/crawl4ai:latest
+            ```
+            
+            ### 📝 What's Changed
+            See [CHANGELOG.md](https://github.com/${{ github.repository }}/blob/main/CHANGELOG.md) for details.
+          draft: false
+          prerelease: false
+          token: ${{ secrets.GITHUB_TOKEN }}
+      
+      - name: Summary
+        run: |
+          echo "## 🚀 Release Complete!" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### 📦 PyPI Package" >> $GITHUB_STEP_SUMMARY
+          echo "- Version: ${{ steps.get_version.outputs.VERSION }}" >> $GITHUB_STEP_SUMMARY
+          echo "- URL: https://pypi.org/project/crawl4ai/" >> $GITHUB_STEP_SUMMARY
+          echo "- Install: \`pip install crawl4ai==${{ steps.get_version.outputs.VERSION }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### 🐳 Docker Images" >> $GITHUB_STEP_SUMMARY
+          echo "- \`unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- \`unclecode/crawl4ai:${{ steps.versions.outputs.MINOR }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- \`unclecode/crawl4ai:${{ steps.versions.outputs.MAJOR }}\`" >> $GITHUB_STEP_SUMMARY
+          echo "- \`unclecode/crawl4ai:latest\`" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "### 📋 GitHub Release" >> $GITHUB_STEP_SUMMARY
+          echo "https://github.com/${{ github.repository }}/releases/tag/v${{ steps.get_version.outputs.VERSION }}" >> $GITHUB_STEP_SUMMARY

.gitignore

@@ -266,6 +266,8 @@ continue_config.json
 .llm.env
 .private/
 
+.claude/
+
 CLAUDE_MONITOR.md
 CLAUDE.md
 

Dockerfile

@@ -1,7 +1,7 @@
 FROM python:3.12-slim-bookworm AS build
 
 # C4ai version
-ARG C4AI_VER=0.7.0-r1
+ARG C4AI_VER=0.7.8
 ENV C4AI_VERSION=$C4AI_VER
 LABEL c4ai.version=$C4AI_VER
 
@@ -167,6 +167,11 @@ RUN mkdir -p /home/appuser/.cache/ms-playwright \
 
 RUN crawl4ai-doctor
 
+# Ensure all cache directories belong to appuser
+# This fixes permission issues with .cache/url_seeder and other runtime cache dirs
+RUN mkdir -p /home/appuser/.cache \
+    && chown -R appuser:appuser /home/appuser/.cache
+
 # Copy application code
 COPY deploy/docker/* ${APP_HOME}/
 

README.md

@@ -12,6 +12,16 @@
 [![Downloads](https://static.pepy.tech/badge/crawl4ai/month)](https://pepy.tech/project/crawl4ai)
 [![GitHub Sponsors](https://img.shields.io/github/sponsors/unclecode?style=flat&logo=GitHub-Sponsors&label=Sponsors&color=pink)](https://github.com/sponsors/unclecode)
 
+---
+#### 🚀 Crawl4AI Cloud API — Closed Beta (Launching Soon)
+Reliable, large-scale web extraction, now built to be _**drastically more cost-effective**_ than any of the existing solutions.
+
+👉 **Apply [here](https://forms.gle/E9MyPaNXACnAMaqG7) for early access**  
+_We’ll be onboarding in phases and working closely with early users.
+Limited slots._
+
+---
+
 <p align="center">
     <a href="https://x.com/crawl4ai">
       <img src="https://img.shields.io/badge/Follow%20on%20X-000000?style=for-the-badge&logo=x&logoColor=white" alt="Follow on X" />
@@ -27,11 +37,13 @@
 
 Crawl4AI turns the web into clean, LLM ready Markdown for RAG, agents, and data pipelines. Fast, controllable, battle tested by a 50k+ star community.
 
-[✨ Check out latest update v0.7.4](#-recent-updates)
+[✨ Check out latest update v0.7.8](#-recent-updates)
 
-✨ New in v0.7.4: Revolutionary LLM Table Extraction with intelligent chunking, enhanced concurrency fixes, memory management refactor, and critical stability improvements. [Release notes →](https://github.com/unclecode/crawl4ai/blob/main/docs/blog/release-v0.7.4.md)
+✨ **New in v0.7.8**: Stability & Bug Fix Release! 11 bug fixes addressing Docker API issues (ContentRelevanceFilter, ProxyConfig, cache permissions), LLM extraction improvements (configurable backoff, HTML input format), URL handling fixes, and dependency updates (pypdf, Pydantic v2). [Release notes →](https://github.com/unclecode/crawl4ai/blob/main/docs/blog/release-v0.7.8.md)
 
-✨ Recent v0.7.3: Undetected Browser Support, Multi-URL Configurations, Memory Monitoring, Enhanced Table Extraction, GitHub Sponsors. [Release notes →](https://github.com/unclecode/crawl4ai/blob/main/docs/blog/release-v0.7.3.md)
+✨ Recent v0.7.7: Complete Self-Hosting Platform with Real-time Monitoring! Enterprise-grade monitoring dashboard, comprehensive REST API, WebSocket streaming, smart browser pool management, and production-ready observability. [Release notes →](https://github.com/unclecode/crawl4ai/blob/main/docs/blog/release-v0.7.7.md)
+
+✨ Previous v0.7.6: Complete Webhook Infrastructure for Docker Job Queue API! Real-time notifications for both `/crawl/job` and `/llm/job` endpoints with exponential backoff retry, custom headers, and flexible delivery modes. [Release notes →](https://github.com/unclecode/crawl4ai/blob/main/docs/blog/release-v0.7.6.md)
 
 <details>
   <summary>🤓 <strong>My Personal Story</strong></summary>
@@ -177,7 +189,7 @@ No rate-limited APIs. No lock-in. Build and own your data pipeline with direct g
 - 📸 **Screenshots**: Capture page screenshots during crawling for debugging or analysis.
 - 📂 **Raw Data Crawling**: Directly process raw HTML (`raw:`) or local files (`file://`).
 - 🔗 **Comprehensive Link Extraction**: Extracts internal, external links, and embedded iframe content.
-- 🛠️ **Customizable Hooks**: Define hooks at every step to customize crawling behavior.
+- 🛠️ **Customizable Hooks**: Define hooks at every step to customize crawling behavior (supports both string and function-based APIs).
 - 💾 **Caching**: Cache data for improved speed and to avoid redundant fetches.
 - 📄 **Metadata Extraction**: Retrieve structured metadata from web pages.
 - 📡 **IFrame Content Extraction**: Seamless extraction from embedded iframe content.
@@ -294,6 +306,7 @@ pip install -e ".[all]"             # Install all optional features
 ### New Docker Features
 
 The new Docker implementation includes:
+- **Real-time Monitoring Dashboard** with live system metrics and browser pool visibility
 - **Browser pooling** with page pre-warming for faster response times
 - **Interactive playground** to test and generate request code
 - **MCP integration** for direct connection to AI tools like Claude Code
@@ -308,7 +321,8 @@ The new Docker implementation includes:
 docker pull unclecode/crawl4ai:latest
 docker run -d -p 11235:11235 --name crawl4ai --shm-size=1g unclecode/crawl4ai:latest
 
-# Visit the playground at http://localhost:11235/playground
+# Visit the monitoring dashboard at http://localhost:11235/dashboard
+# Or the playground at http://localhost:11235/playground
 ```
 
 ### Quick Test
@@ -337,7 +351,7 @@ else:
     result = requests.get(f"http://localhost:11235/task/{task_id}")
 ```
 
-For more examples, see our [Docker Examples](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/docker_example.py). For advanced configuration, environment variables, and usage examples, see our [Docker Deployment Guide](https://docs.crawl4ai.com/basic/docker-deployment/).
+For more examples, see our [Docker Examples](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/docker_example.py). For advanced configuration, monitoring features, and production deployment, see our [Self-Hosting Guide](https://docs.crawl4ai.com/core/self-hosting/).
 
 </details>
 
@@ -542,8 +556,160 @@ async def test_news_crawl():
 
 </details>
 
+---
+
+> **💡 Tip:** Some websites may use **CAPTCHA** based verification mechanisms to prevent automated access. If your workflow encounters such challenges, you may optionally integrate a third-party CAPTCHA-handling service such as <strong>[CapSolver](https://www.capsolver.com/blog/Partners/crawl4ai-capsolver/?utm_source=crawl4ai&utm_medium=github_pr&utm_campaign=crawl4ai_integration)</strong>. They support reCAPTCHA v2/v3, Cloudflare Turnstile, Challenge, AWS WAF, and more. Please ensure that your usage complies with the target website’s terms of service and applicable laws.
+
 ## ✨ Recent Updates
 
+<details>
+<summary><strong>Version 0.7.8 Release Highlights - Stability & Bug Fix Release</strong></summary>
+
+This release focuses on stability with 11 bug fixes addressing issues reported by the community. No new features, but significant improvements to reliability.
+
+- **🐳 Docker API Fixes**:
+  - Fixed `ContentRelevanceFilter` deserialization in deep crawl requests (#1642)
+  - Fixed `ProxyConfig` JSON serialization in `BrowserConfig.to_dict()` (#1629)
+  - Fixed `.cache` folder permissions in Docker image (#1638)
+
+- **🤖 LLM Extraction Improvements**:
+  - Configurable rate limiter backoff with new `LLMConfig` parameters (#1269):
+    ```python
+    from crawl4ai import LLMConfig
+
+    config = LLMConfig(
+        provider="openai/gpt-4o-mini",
+        backoff_base_delay=5,           # Wait 5s on first retry
+        backoff_max_attempts=5,          # Try up to 5 times
+        backoff_exponential_factor=3     # Multiply delay by 3 each attempt
+    )
+    ```
+  - HTML input format support for `LLMExtractionStrategy` (#1178):
+    ```python
+    from crawl4ai import LLMExtractionStrategy
+
+    strategy = LLMExtractionStrategy(
+        llm_config=config,
+        instruction="Extract table data",
+        input_format="html"  # Now supports: "html", "markdown", "fit_markdown"
+    )
+    ```
+  - Fixed raw HTML URL variable - extraction strategies now receive `"Raw HTML"` instead of HTML blob (#1116)
+
+- **🔗 URL Handling**:
+  - Fixed relative URL resolution after JavaScript redirects (#1268)
+  - Fixed import statement formatting in extracted code (#1181)
+
+- **📦 Dependency Updates**:
+  - Replaced deprecated PyPDF2 with pypdf (#1412)
+  - Pydantic v2 ConfigDict compatibility - no more deprecation warnings (#678)
+
+- **🧠 AdaptiveCrawler**:
+  - Fixed query expansion to actually use LLM instead of hardcoded mock data (#1621)
+
+[Full v0.7.8 Release Notes →](https://github.com/unclecode/crawl4ai/blob/main/docs/blog/release-v0.7.8.md)
+
+</details>
+
+<details>
+<summary><strong>Version 0.7.7 Release Highlights - The Self-Hosting & Monitoring Update</strong></summary>
+
+- **📊 Real-time Monitoring Dashboard**: Interactive web UI with live system metrics and browser pool visibility
+  ```python
+  # Access the monitoring dashboard
+  # Visit: http://localhost:11235/dashboard
+
+  # Real-time metrics include:
+  # - System health (CPU, memory, network, uptime)
+  # - Active and completed request tracking
+  # - Browser pool management (permanent/hot/cold)
+  # - Janitor cleanup events
+  # - Error monitoring with full context
+  ```
+
+- **🔌 Comprehensive Monitor API**: Complete REST API for programmatic access to all monitoring data
+  ```python
+  import httpx
+
+  async with httpx.AsyncClient() as client:
+      # System health
+      health = await client.get("http://localhost:11235/monitor/health")
+
+      # Request tracking
+      requests = await client.get("http://localhost:11235/monitor/requests")
+
+      # Browser pool status
+      browsers = await client.get("http://localhost:11235/monitor/browsers")
+
+      # Endpoint statistics
+      stats = await client.get("http://localhost:11235/monitor/endpoints/stats")
+  ```
+
+- **⚡ WebSocket Streaming**: Real-time updates every 2 seconds for custom dashboards
+- **🔥 Smart Browser Pool**: 3-tier architecture (permanent/hot/cold) with automatic promotion and cleanup
+- **🧹 Janitor System**: Automatic resource management with event logging
+- **🎮 Control Actions**: Manual browser management (kill, restart, cleanup) via API
+- **📈 Production Metrics**: 6 critical metrics for operational excellence with Prometheus integration
+- **🐛 Critical Bug Fixes**:
+  - Fixed async LLM extraction blocking issue (#1055)
+  - Enhanced DFS deep crawl strategy (#1607)
+  - Fixed sitemap parsing in AsyncUrlSeeder (#1598)
+  - Resolved browser viewport configuration (#1495)
+  - Fixed CDP timing with exponential backoff (#1528)
+  - Security update for pyOpenSSL (>=25.3.0)
+
+[Full v0.7.7 Release Notes →](https://github.com/unclecode/crawl4ai/blob/main/docs/blog/release-v0.7.7.md)
+
+</details>
+
+<details>
+<summary><strong>Version 0.7.5 Release Highlights - The Docker Hooks & Security Update</strong></summary>
+
+- **🔧 Docker Hooks System**: Complete pipeline customization with user-provided Python functions at 8 key points
+- **✨ Function-Based Hooks API (NEW)**: Write hooks as regular Python functions with full IDE support:
+  ```python
+  from crawl4ai import hooks_to_string
+  from crawl4ai.docker_client import Crawl4aiDockerClient
+
+  # Define hooks as regular Python functions
+  async def on_page_context_created(page, context, **kwargs):
+      """Block images to speed up crawling"""
+      await context.route("**/*.{png,jpg,jpeg,gif,webp}", lambda route: route.abort())
+      await page.set_viewport_size({"width": 1920, "height": 1080})
+      return page
+
+  async def before_goto(page, context, url, **kwargs):
+      """Add custom headers"""
+      await page.set_extra_http_headers({'X-Crawl4AI': 'v0.7.5'})
+      return page
+
+  # Option 1: Use hooks_to_string() utility for REST API
+  hooks_code = hooks_to_string({
+      "on_page_context_created": on_page_context_created,
+      "before_goto": before_goto
+  })
+
+  # Option 2: Docker client with automatic conversion (Recommended)
+  client = Crawl4aiDockerClient(base_url="http://localhost:11235")
+  results = await client.crawl(
+      urls=["https://httpbin.org/html"],
+      hooks={
+          "on_page_context_created": on_page_context_created,
+          "before_goto": before_goto
+      }
+  )
+  # ✓ Full IDE support, type checking, and reusability!
+  ```
+
+- **🤖 Enhanced LLM Integration**: Custom providers with temperature control and base_url configuration
+- **🔒 HTTPS Preservation**: Secure internal link handling with `preserve_https_for_internal_links=True`
+- **🐍 Python 3.10+ Support**: Modern language features and enhanced performance
+- **🛠️ Bug Fixes**: Resolved multiple community-reported issues including URL processing, JWT authentication, and proxy configuration
+
+[Full v0.7.5 Release Notes →](https://github.com/unclecode/crawl4ai/blob/main/docs/blog/release-v0.7.5.md)
+
+</details>
+
 <details>
 <summary><strong>Version 0.7.4 Release Highlights - The Intelligent Table Extraction & Performance Update</strong></summary>
 
@@ -919,6 +1085,40 @@ We envision a future where AI is powered by real human knowledge, ensuring data
 For more details, see our [full mission statement](./MISSION.md).
 </details>
 
+## 🌟 Current Sponsors
+
+### 🏢 Enterprise Sponsors & Partners
+
+Our enterprise sponsors and technology partners help scale Crawl4AI to power production-grade data pipelines.
+
+| Company | About | Sponsorship Tier |
+|------|------|----------------------------|
+| <a href="https://app.nstproxy.com/register?i=ecOqW9" target="_blank"><picture><source width="250" media="(prefers-color-scheme: dark)" srcset="https://gist.github.com/aravindkarnam/62f82bd4818d3079d9dd3c31df432cf8/raw/nst-light.svg"><source width="250" media="(prefers-color-scheme: light)" srcset="https://www.nstproxy.com/logo.svg"><img alt="nstproxy" src="ttps://www.nstproxy.com/logo.svg"></picture></a>  | NstProxy is a trusted proxy provider with over 110M+ real residential IPs, city-level targeting, 99.99% uptime, and low pricing at $0.1/GB, it delivers unmatched stability, scale, and cost-efficiency. | 🥈 Silver |
+| <a href="https://app.scrapeless.com/passport/register?utm_source=official&utm_term=crawl4ai" target="_blank"><picture><source width="250" media="(prefers-color-scheme: dark)" srcset="https://gist.githubusercontent.com/aravindkarnam/0d275b942705604263e5c32d2db27bc1/raw/Scrapeless-light-logo.svg"><source width="250" media="(prefers-color-scheme: light)" srcset="https://gist.githubusercontent.com/aravindkarnam/22d0525cc0f3021bf19ebf6e11a69ccd/raw/Scrapeless-dark-logo.svg"><img alt="Scrapeless" src="https://gist.githubusercontent.com/aravindkarnam/22d0525cc0f3021bf19ebf6e11a69ccd/raw/Scrapeless-dark-logo.svg"></picture></a>  | Scrapeless provides production-grade infrastructure for Crawling, Automation, and AI Agents, offering Scraping Browser, 4 Proxy Types and Universal Scraping API. | 🥈 Silver |
+| <a href="https://dashboard.capsolver.com/passport/register?inviteCode=ESVSECTX5Q23" target="_blank"><picture><source width="120" media="(prefers-color-scheme: dark)" srcset="https://docs.crawl4ai.com/uploads/sponsors/20251013045338_72a71fa4ee4d2f40.png"><source width="120" media="(prefers-color-scheme: light)" srcset="https://www.capsolver.com/assets/images/logo-text.png"><img alt="Capsolver" src="https://www.capsolver.com/assets/images/logo-text.png"></picture></a> | AI-powered Captcha solving service. Supports all major Captcha types, including reCAPTCHA, Cloudflare, and more | 🥉 Bronze |
+| <a href="https://kipo.ai" target="_blank"><img src="https://docs.crawl4ai.com/uploads/sponsors/20251013045751_2d54f57f117c651e.png" alt="DataSync" width="120"/></a> | Helps engineers and buyers find, compare, and source electronic & industrial parts in seconds, with specs, pricing, lead times & alternatives.| 🥇 Gold |
+| <a href="https://www.kidocode.com/" target="_blank"><img src="https://docs.crawl4ai.com/uploads/sponsors/20251013045045_bb8dace3f0440d65.svg" alt="Kidocode" width="120"/><p align="center">KidoCode</p></a> | Kidocode is a hybrid technology and entrepreneurship school for kids aged 5–18, offering both online and on-campus education. | 🥇 Gold |
+| <a href="https://www.alephnull.sg/" target="_blank"><img src="https://docs.crawl4ai.com/uploads/sponsors/20251013050323_a9e8e8c4c3650421.svg" alt="Aleph null" width="120"/></a> | Singapore-based  Aleph Null is Asia’s leading edtech hub, dedicated to student-centric, AI-driven education—empowering learners with the tools to thrive in a fast-changing world. | 🥇 Gold |
+
+
+
+### 🧑‍🤝 Individual Sponsors
+
+A heartfelt thanks to our individual supporters! Every contribution helps us keep our opensource mission alive and thriving!
+
+<p align="left">
+  <a href="https://github.com/hafezparast"><img src="https://avatars.githubusercontent.com/u/14273305?s=60&v=4" style="border-radius:50%;" width="64px;"/></a>
+  <a href="https://github.com/ntohidi"><img src="https://avatars.githubusercontent.com/u/17140097?s=60&v=4" style="border-radius:50%;"width="64px;"/></a>
+  <a href="https://github.com/Sjoeborg"><img src="https://avatars.githubusercontent.com/u/17451310?s=60&v=4" style="border-radius:50%;"width="64px;"/></a>
+  <a href="https://github.com/romek-rozen"><img src="https://avatars.githubusercontent.com/u/30595969?s=60&v=4" style="border-radius:50%;"width="64px;"/></a>
+  <a href="https://github.com/Kourosh-Kiyani"><img src="https://avatars.githubusercontent.com/u/34105600?s=60&v=4" style="border-radius:50%;"width="64px;"/></a>
+  <a href="https://github.com/Etherdrake"><img src="https://avatars.githubusercontent.com/u/67021215?s=60&v=4" style="border-radius:50%;"width="64px;"/></a>
+  <a href="https://github.com/shaman247"><img src="https://avatars.githubusercontent.com/u/211010067?s=60&v=4" style="border-radius:50%;"width="64px;"/></a>
+  <a href="https://github.com/work-flow-manager"><img src="https://avatars.githubusercontent.com/u/217665461?s=60&v=4" style="border-radius:50%;"width="64px;"/></a>
+</p>
+
+> Want to join them? [Sponsor Crawl4AI →](https://github.com/sponsors/unclecode)
+
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=unclecode/crawl4ai&type=Date)](https://star-history.com/#unclecode/crawl4ai&Date)

crawl4ai/__init__.py

@@ -72,6 +72,8 @@ from .deep_crawling import (
     BestFirstCrawlingStrategy,
     DFSDeepCrawlStrategy,
     DeepCrawlDecorator,
+    ContentRelevanceFilter,
+    ContentTypeScorer,
 )
 # NEW: Import AsyncUrlSeeder
 from .async_url_seeder import AsyncUrlSeeder
@@ -103,7 +105,8 @@ from .browser_adapter import (
 
 from .utils import (
     start_colab_display_server,
-    setup_colab_environment
+    setup_colab_environment,
+    hooks_to_string
 )
 
 __all__ = [
@@ -183,6 +186,7 @@ __all__ = [
     "ProxyConfig",
     "start_colab_display_server",
     "setup_colab_environment",
+    "hooks_to_string",
     # C4A Script additions
     "c4a_compile",
     "c4a_validate", 

crawl4ai/__version__.py

@@ -1,7 +1,7 @@
 # crawl4ai/__version__.py
 
 # This is the version that will be used for stable releases
-__version__ = "0.7.4"
+__version__ = "0.7.8"
 
 # For nightly builds, this gets set during build process
 __nightly_version__ = None

crawl4ai/adaptive_crawler.py

@@ -728,18 +728,18 @@ class EmbeddingStrategy(CrawlStrategy):
         provider = llm_config_dict.get('provider', 'openai/gpt-4o-mini') if llm_config_dict else 'openai/gpt-4o-mini'
         api_token = llm_config_dict.get('api_token') if llm_config_dict else None
         
-        # response = perform_completion_with_backoff(
-        #     provider=provider,
-        #     prompt_with_variables=prompt,
-        #     api_token=api_token,
-        #     json_response=True
-        # )
+        response = perform_completion_with_backoff(
+            provider=provider,
+            prompt_with_variables=prompt,
+            api_token=api_token,
+            json_response=True
+        )
         
-        # variations = json.loads(response.choices[0].message.content)
+        variations = json.loads(response.choices[0].message.content)
         
         
         # # Mock data with more variations for split
-        variations ={'queries': ['what are the best vegetables to use in fried rice?', 'how do I make vegetable fried rice from scratch?', 'can you provide a quick recipe for vegetable fried rice?', 'what cooking techniques are essential for perfect fried rice with vegetables?', 'how to add flavor to vegetable fried rice?', 'are there any tips for making healthy fried rice with vegetables?']}
+        # variations ={'queries': ['what are the best vegetables to use in fried rice?', 'how do I make vegetable fried rice from scratch?', 'can you provide a quick recipe for vegetable fried rice?', 'what cooking techniques are essential for perfect fried rice with vegetables?', 'how to add flavor to vegetable fried rice?', 'are there any tips for making healthy fried rice with vegetables?']}
         
         
         # variations = {'queries': [

crawl4ai/async_configs.py

@@ -1,6 +1,7 @@
+import importlib
 import os
-from typing import Union
 import warnings
+import requests
 from .config import (
     DEFAULT_PROVIDER,
     DEFAULT_PROVIDER_API_KEY,
@@ -26,14 +27,14 @@ from .table_extraction import TableExtractionStrategy, DefaultTableExtraction
 from .cache_context import CacheMode
 from .proxy_strategy import ProxyRotationStrategy
 
-from typing import Union, List, Callable
 import inspect
-from typing import Any, Dict, Optional
+from typing import Any, Callable, Dict, List, Optional, Union
 from enum import Enum
 
 # Type alias for URL matching
 UrlMatcher = Union[str, Callable[[str], bool], List[Union[str, Callable[[str], bool]]]]
 
+
 class MatchMode(Enum):
     OR = "or"
     AND = "and"
@@ -41,8 +42,7 @@ class MatchMode(Enum):
 # from .proxy_strategy import ProxyConfig
 
 
-
-def to_serializable_dict(obj: Any, ignore_default_value : bool = False) -> Dict:
+def to_serializable_dict(obj: Any, ignore_default_value : bool = False):
     """
     Recursively convert an object to a serializable dictionary using {type, params} structure
     for complex objects.
@@ -109,8 +109,6 @@ def to_serializable_dict(obj: Any, ignore_default_value : bool = False) -> Dict:
         #             if value is not None:
         #                 current_values[attr_name] = to_serializable_dict(value)
 
-            
-        
         return {
             "type": obj.__class__.__name__,
             "params": current_values
@@ -136,12 +134,20 @@ def from_serializable_dict(data: Any) -> Any:
         if data["type"] == "dict" and "value" in data:
             return {k: from_serializable_dict(v) for k, v in data["value"].items()}
 
-        # Import from crawl4ai for class instances
-        import crawl4ai
-
-        if hasattr(crawl4ai, data["type"]):
-            cls = getattr(crawl4ai, data["type"])
+        cls = None
+        # If you are receiving an error while trying to convert a dict to an object:
+        # Either add a module to `modules_paths` list, or add the `data["type"]` to the crawl4ai __init__.py file
+        module_paths = ["crawl4ai"]
+        for module_path in module_paths:
+            try:
+                mod = importlib.import_module(module_path)
+                if hasattr(mod, data["type"]):
+                    cls = getattr(mod, data["type"])
+                    break
+            except (ImportError, AttributeError):
+                continue
 
+        if cls is not None:
             # Handle Enum
             if issubclass(cls, Enum):
                 return cls(data["params"])
@@ -597,7 +603,7 @@ class BrowserConfig:
             "chrome_channel": self.chrome_channel,
             "channel": self.channel,
             "proxy": self.proxy,
-            "proxy_config": self.proxy_config,
+            "proxy_config": self.proxy_config.to_dict() if self.proxy_config else None,
             "viewport_width": self.viewport_width,
             "viewport_height": self.viewport_height,
             "accept_downloads": self.accept_downloads,
@@ -649,6 +655,85 @@ class BrowserConfig:
             return config
         return BrowserConfig.from_kwargs(config)
 
+    def set_nstproxy(
+        self,
+        token: str,
+        channel_id: str,
+        country: str = "ANY",
+        state: str = "",
+        city: str = "",
+        protocol: str = "http",
+        session_duration: int = 10,
+    ):
+        """
+        Fetch a proxy from NSTProxy API and automatically assign it to proxy_config.
+
+        Get your NSTProxy token from: https://app.nstproxy.com/profile
+
+        Args:
+            token (str): NSTProxy API token.
+            channel_id (str): NSTProxy channel ID.
+            country (str, optional): Country code (default: "ANY").
+            state (str, optional): State code (default: "").
+            city (str, optional): City name (default: "").
+            protocol (str, optional): Proxy protocol ("http" or "socks5"). Defaults to "http".
+            session_duration (int, optional): Session duration in minutes (0 = rotate each request). Defaults to 10.
+
+        Raises:
+            ValueError: If the API response format is invalid.
+            PermissionError: If the API returns an error message.
+        """
+
+        # --- Validate input early ---
+        if not token or not channel_id:
+            raise ValueError("[NSTProxy] token and channel_id are required")
+
+        if protocol not in ("http", "socks5"):
+            raise ValueError(f"[NSTProxy] Invalid protocol: {protocol}")
+
+        # --- Build NSTProxy API URL ---
+        params = {
+            "fType": 2,
+            "count": 1,
+            "channelId": channel_id,
+            "country": country,
+            "protocol": protocol,
+            "sessionDuration": session_duration,
+            "token": token,
+        }
+        if state:
+            params["state"] = state
+        if city:
+            params["city"] = city
+
+        url = "https://api.nstproxy.com/api/v1/generate/apiproxies"
+
+        try:
+            response = requests.get(url, params=params, timeout=10)
+            response.raise_for_status()
+
+            data = response.json()
+
+            # --- Handle API error response ---
+            if isinstance(data, dict) and data.get("err"):
+                raise PermissionError(f"[NSTProxy] API Error: {data.get('msg', 'Unknown error')}")
+
+            if not isinstance(data, list) or not data:
+                raise ValueError("[NSTProxy] Invalid API response — expected a non-empty list")
+
+            proxy_info = data[0]
+
+            # --- Apply proxy config ---
+            self.proxy_config = ProxyConfig(
+                server=f"{protocol}://{proxy_info['ip']}:{proxy_info['port']}",
+                username=proxy_info["username"],
+                password=proxy_info["password"],
+            )
+
+        except Exception as e:
+            print(f"[NSTProxy] ❌ Failed to set proxy: {e}")
+            raise
+
 class VirtualScrollConfig:
     """Configuration for virtual scroll handling.
     
@@ -1712,7 +1797,10 @@ class LLMConfig:
         frequency_penalty: Optional[float] = None,
         presence_penalty: Optional[float] = None,
         stop: Optional[List[str]] = None,
-        n: Optional[int] = None,    
+        n: Optional[int] = None,
+        backoff_base_delay: Optional[int] = None,
+        backoff_max_attempts: Optional[int] = None,
+        backoff_exponential_factor: Optional[int] = None,
     ):
         """Configuaration class for LLM provider and API token."""
         self.provider = provider
@@ -1741,6 +1829,9 @@ class LLMConfig:
         self.presence_penalty = presence_penalty
         self.stop = stop
         self.n = n
+        self.backoff_base_delay = backoff_base_delay if backoff_base_delay is not None else 2
+        self.backoff_max_attempts = backoff_max_attempts if backoff_max_attempts is not None else 3
+        self.backoff_exponential_factor = backoff_exponential_factor if backoff_exponential_factor is not None else 2
 
     @staticmethod
     def from_kwargs(kwargs: dict) -> "LLMConfig":
@@ -1754,7 +1845,10 @@ class LLMConfig:
             frequency_penalty=kwargs.get("frequency_penalty"),
             presence_penalty=kwargs.get("presence_penalty"),
             stop=kwargs.get("stop"),
-            n=kwargs.get("n")
+            n=kwargs.get("n"),
+            backoff_base_delay=kwargs.get("backoff_base_delay"),
+            backoff_max_attempts=kwargs.get("backoff_max_attempts"),
+            backoff_exponential_factor=kwargs.get("backoff_exponential_factor")
         )
 
     def to_dict(self):
@@ -1768,7 +1862,10 @@ class LLMConfig:
             "frequency_penalty": self.frequency_penalty,
             "presence_penalty": self.presence_penalty,
             "stop": self.stop,
-            "n": self.n
+            "n": self.n,
+            "backoff_base_delay": self.backoff_base_delay,
+            "backoff_max_attempts": self.backoff_max_attempts,
+            "backoff_exponential_factor": self.backoff_exponential_factor
         }
 
     def clone(self, **kwargs):

crawl4ai/async_crawler_strategy.py

@@ -1023,6 +1023,12 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                 final_messages = await self.adapter.retrieve_console_messages(page)
                 captured_console.extend(final_messages)
 
+            ###
+            # This ensures we capture the current page URL at the time we return the response, 
+            # which correctly reflects any JavaScript navigation that occurred.
+            ###
+            redirected_url = page.url  # Use current page URL to capture JS redirects
+            
             # Return complete response
             return AsyncCrawlResponse(
                 html=html,
@@ -1383,9 +1389,10 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
         try:
             await self.adapter.evaluate(page,
                 f"""
-                (() => {{
+                (async () => {{
                     try {{
-                        {remove_overlays_js}
+                        const removeOverlays = {remove_overlays_js};
+                        await removeOverlays();
                         return {{ success: true }};
                     }} catch (error) {{
                         return {{

crawl4ai/async_url_seeder.py

@@ -845,6 +845,15 @@ class AsyncUrlSeeder:
             return
 
         data = gzip.decompress(r.content) if url.endswith(".gz") else r.content
+        base_url = str(r.url)
+
+        def _normalize_loc(raw: Optional[str]) -> Optional[str]:
+            if not raw:
+                return None
+            normalized = urljoin(base_url, raw.strip())
+            if not normalized:
+                return None
+            return normalized
 
         # Detect if this is a sitemap index by checking for <sitemapindex> or presence of <sitemap> elements
         is_sitemap_index = False
@@ -857,25 +866,42 @@ class AsyncUrlSeeder:
                 # Use XML parser for sitemaps, not HTML parser
                 parser = etree.XMLParser(recover=True)
                 root = etree.fromstring(data, parser=parser)
+                # Namespace-agnostic lookups using local-name() so we honor custom or missing namespaces
+                sitemap_loc_nodes = root.xpath("//*[local-name()='sitemap']/*[local-name()='loc']")
+                url_loc_nodes = root.xpath("//*[local-name()='url']/*[local-name()='loc']")
 
-                # Define namespace for sitemap
-                ns = {'s': 'http://www.sitemaps.org/schemas/sitemap/0.9'}
+                self._log(
+                    "debug",
+                    "Parsed sitemap {url}: {sitemap_count} sitemap entries, {url_count} url entries discovered",
+                    params={
+                        "url": url,
+                        "sitemap_count": len(sitemap_loc_nodes),
+                        "url_count": len(url_loc_nodes),
+                    },
+                    tag="URL_SEED",
+                )
 
                 # Check for sitemap index entries
-                sitemap_locs = root.xpath('//s:sitemap/s:loc', namespaces=ns)
-                if sitemap_locs:
+                if sitemap_loc_nodes:
                     is_sitemap_index = True
-                    for sitemap_elem in sitemap_locs:
-                        loc = sitemap_elem.text.strip() if sitemap_elem.text else ""
+                    for sitemap_elem in sitemap_loc_nodes:
+                        loc = _normalize_loc(sitemap_elem.text)
                         if loc:
                             sub_sitemaps.append(loc)
 
                 # If not a sitemap index, get regular URLs
                 if not is_sitemap_index:
-                    for loc_elem in root.xpath('//s:url/s:loc', namespaces=ns):
-                        loc = loc_elem.text.strip() if loc_elem.text else ""
+                    for loc_elem in url_loc_nodes:
+                        loc = _normalize_loc(loc_elem.text)
                         if loc:
                             regular_urls.append(loc)
+                    if not regular_urls:
+                        self._log(
+                            "warning",
+                            "No <loc> entries found inside <url> tags for sitemap {url}. The sitemap might be empty or use an unexpected structure.",
+                            params={"url": url},
+                            tag="URL_SEED",
+                        )
             except Exception as e:
                 self._log("error", "LXML parsing error for sitemap {url}: {error}",
                           params={"url": url, "error": str(e)}, tag="URL_SEED")
@@ -892,19 +918,39 @@ class AsyncUrlSeeder:
 
                 # Check for sitemap index entries
                 sitemaps = root.findall('.//sitemap')
+                url_entries = root.findall('.//url')
+                self._log(
+                    "debug",
+                    "ElementTree parsed sitemap {url}: {sitemap_count} sitemap entries, {url_count} url entries discovered",
+                    params={
+                        "url": url,
+                        "sitemap_count": len(sitemaps),
+                        "url_count": len(url_entries),
+                    },
+                    tag="URL_SEED",
+                )
                 if sitemaps:
                     is_sitemap_index = True
                     for sitemap in sitemaps:
                         loc_elem = sitemap.find('loc')
-                        if loc_elem is not None and loc_elem.text:
-                            sub_sitemaps.append(loc_elem.text.strip())
+                        loc = _normalize_loc(loc_elem.text if loc_elem is not None else None)
+                        if loc:
+                            sub_sitemaps.append(loc)
 
                 # If not a sitemap index, get regular URLs
                 if not is_sitemap_index:
-                    for url_elem in root.findall('.//url'):
+                    for url_elem in url_entries:
                         loc_elem = url_elem.find('loc')
-                        if loc_elem is not None and loc_elem.text:
-                            regular_urls.append(loc_elem.text.strip())
+                        loc = _normalize_loc(loc_elem.text if loc_elem is not None else None)
+                        if loc:
+                            regular_urls.append(loc)
+                    if not regular_urls:
+                        self._log(
+                            "warning",
+                            "No <loc> entries found inside <url> tags for sitemap {url}. The sitemap might be empty or use an unexpected structure.",
+                            params={"url": url},
+                            tag="URL_SEED",
+                        )
             except Exception as e:
                 self._log("error", "ElementTree parsing error for sitemap {url}: {error}",
                           params={"url": url, "error": str(e)}, tag="URL_SEED")

crawl4ai/async_webcrawler.py

@@ -617,7 +617,17 @@ class AsyncWebCrawler:
                 else config.chunking_strategy
             )
             sections = chunking.chunk(content)
-            extracted_content = config.extraction_strategy.run(url, sections)
+            # extracted_content = config.extraction_strategy.run(_url, sections)
+
+            # Use async version if available for better parallelism
+            if hasattr(config.extraction_strategy, 'arun'):
+                extracted_content = await config.extraction_strategy.arun(_url, sections)
+            else:
+                # Fallback to sync version run in thread pool to avoid blocking
+                extracted_content = await asyncio.to_thread(
+                    config.extraction_strategy.run, url, sections
+                )
+                
             extracted_content = json.dumps(
                 extracted_content, indent=4, default=str, ensure_ascii=False
             )

crawl4ai/browser_manager.py

@@ -369,6 +369,9 @@ class ManagedBrowser:
             ]
             if self.headless:
                 flags.append("--headless=new")
+            # Add viewport flag if specified in config
+            if self.browser_config.viewport_height and self.browser_config.viewport_width:
+                flags.append(f"--window-size={self.browser_config.viewport_width},{self.browser_config.viewport_height}")
             # merge common launch flags
             flags.extend(self.build_browser_flags(self.browser_config))
         elif self.browser_type == "firefox":
@@ -658,6 +661,11 @@ class BrowserManager:
         if self.config.cdp_url or self.config.use_managed_browser:
             self.config.use_managed_browser = True
             cdp_url = await self.managed_browser.start() if not self.config.cdp_url else self.config.cdp_url
+            
+            # Add CDP endpoint verification before connecting
+            if not await self._verify_cdp_ready(cdp_url):
+                raise Exception(f"CDP endpoint at {cdp_url} is not ready after startup")
+            
             self.browser = await self.playwright.chromium.connect_over_cdp(cdp_url)
             contexts = self.browser.contexts
             if contexts:
@@ -678,6 +686,24 @@ class BrowserManager:
 
             self.default_context = self.browser
 
+    async def _verify_cdp_ready(self, cdp_url: str) -> bool:
+        """Verify CDP endpoint is ready with exponential backoff"""
+        import aiohttp
+        self.logger.debug(f"Starting CDP verification for {cdp_url}", tag="BROWSER")
+        for attempt in range(5):
+            try:
+                async with aiohttp.ClientSession() as session:
+                    async with session.get(f"{cdp_url}/json/version", timeout=aiohttp.ClientTimeout(total=2)) as response:
+                        if response.status == 200:
+                            self.logger.debug(f"CDP endpoint ready after {attempt + 1} attempts", tag="BROWSER")
+                            return True
+            except Exception as e:
+                self.logger.debug(f"CDP check attempt {attempt + 1} failed: {e}", tag="BROWSER")
+            delay = 0.5 * (1.4 ** attempt)
+            self.logger.debug(f"Waiting {delay:.2f}s before next CDP check...", tag="BROWSER")
+            await asyncio.sleep(delay)
+        self.logger.debug(f"CDP verification failed after 5 attempts", tag="BROWSER")
+        return False
 
     def _build_browser_args(self) -> dict:
         """Build browser launch arguments from config."""

crawl4ai/content_filter_strategy.py

@@ -980,6 +980,9 @@ class LLMContentFilter(RelevantContentFilter):
                         prompt,
                         api_token,
                         base_url=base_url,
+                        base_delay=self.llm_config.backoff_base_delay,
+                        max_attempts=self.llm_config.backoff_max_attempts,
+                        exponential_factor=self.llm_config.backoff_exponential_factor,
                         extra_args=extra_args,
                     )
 

crawl4ai/content_scraping_strategy.py

@@ -542,6 +542,19 @@ class LXMLWebScrapingStrategy(ContentScrapingStrategy):
             if el.tag in bypass_tags:
                 continue
 
+            # Skip elements inside <pre> or <code> tags where whitespace is significant
+            # This preserves whitespace-only spans (e.g., <span class="w"> </span>) in code blocks
+            is_in_code_block = False
+            ancestor = el.getparent()
+            while ancestor is not None:
+                if ancestor.tag in ("pre", "code"):
+                    is_in_code_block = True
+                    break
+                ancestor = ancestor.getparent()
+
+            if is_in_code_block:
+                continue
+
             text_content = (el.text_content() or "").strip()
             if (
                 len(text_content.split()) < word_count_threshold

crawl4ai/deep_crawling/dfs_strategy.py

@@ -4,14 +4,26 @@ from typing import AsyncGenerator, Optional, Set, Dict, List, Tuple
 from ..models import CrawlResult
 from .bfs_strategy import BFSDeepCrawlStrategy  # noqa
 from ..types import AsyncWebCrawler, CrawlerRunConfig
+from ..utils import normalize_url_for_deep_crawl
 
 class DFSDeepCrawlStrategy(BFSDeepCrawlStrategy):
     """
-    Depth-First Search (DFS) deep crawling strategy.
+    Depth-first deep crawling with familiar BFS rules.
 
-    Inherits URL validation and link discovery from BFSDeepCrawlStrategy.
-    Overrides _arun_batch and _arun_stream to use a stack (LIFO) for DFS traversal.
+    We reuse the same filters, scoring, and page limits from :class:`BFSDeepCrawlStrategy`,
+    but walk the graph with a stack so we fully explore one branch before hopping to the
+    next. DFS also keeps its own ``_dfs_seen`` set so we can drop duplicate links at
+    discovery time without accidentally marking them as “already crawled”.
     """
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self._dfs_seen: Set[str] = set()
+
+    def _reset_seen(self, start_url: str) -> None:
+        """Start each crawl with a clean dedupe set seeded with the root URL."""
+        self._dfs_seen = {start_url}
+
     async def _arun_batch(
         self,
         start_url: str,
@@ -19,14 +31,19 @@ class DFSDeepCrawlStrategy(BFSDeepCrawlStrategy):
         config: CrawlerRunConfig,
     ) -> List[CrawlResult]:
         """
-        Batch (non-streaming) DFS mode.
-        Uses a stack to traverse URLs in DFS order, aggregating CrawlResults into a list.
+        Crawl level-by-level but emit results at the end.
+
+        We keep a stack of ``(url, parent, depth)`` tuples, pop one at a time, and
+        hand it to ``crawler.arun_many`` with deep crawling disabled so we remain
+        in control of traversal. Every successful page bumps ``_pages_crawled`` and
+        seeds new stack items discovered via :meth:`link_discovery`.
         """
         visited: Set[str] = set()
         # Stack items: (url, parent_url, depth)
         stack: List[Tuple[str, Optional[str], int]] = [(start_url, None, 0)]
         depths: Dict[str, int] = {start_url: 0}
         results: List[CrawlResult] = []
+        self._reset_seen(start_url)
 
         while stack and not self._cancel_event.is_set():
             url, parent, depth = stack.pop()
@@ -71,12 +88,16 @@ class DFSDeepCrawlStrategy(BFSDeepCrawlStrategy):
         config: CrawlerRunConfig,
     ) -> AsyncGenerator[CrawlResult, None]:
         """
-        Streaming DFS mode.
-        Uses a stack to traverse URLs in DFS order and yields CrawlResults as they become available.
+        Same traversal as :meth:`_arun_batch`, but yield pages immediately.
+
+        Each popped URL is crawled, its metadata annotated, then the result gets
+        yielded before we even look at the next stack entry. Successful crawls
+        still feed :meth:`link_discovery`, keeping DFS order intact.
         """
         visited: Set[str] = set()
         stack: List[Tuple[str, Optional[str], int]] = [(start_url, None, 0)]
         depths: Dict[str, int] = {start_url: 0}
+        self._reset_seen(start_url)
 
         while stack and not self._cancel_event.is_set():
             url, parent, depth = stack.pop()
@@ -108,3 +129,92 @@ class DFSDeepCrawlStrategy(BFSDeepCrawlStrategy):
                     for new_url, new_parent in reversed(new_links):
                         new_depth = depths.get(new_url, depth + 1)
                         stack.append((new_url, new_parent, new_depth))
+
+    async def link_discovery(
+        self,
+        result: CrawlResult,
+        source_url: str,
+        current_depth: int,
+        _visited: Set[str],
+        next_level: List[Tuple[str, Optional[str]]],
+        depths: Dict[str, int],
+    ) -> None:
+        """
+        Find the next URLs we should push onto the DFS stack.
+
+        Parameters
+        ----------
+        result : CrawlResult
+            Output of the page we just crawled; its ``links`` block is our raw material.
+        source_url : str
+            URL of the parent page; stored so callers can track ancestry.
+        current_depth : int
+            Depth of the parent; children naturally sit at ``current_depth + 1``.
+        _visited : Set[str]
+            Present to match the BFS signature, but we rely on ``_dfs_seen`` instead.
+        next_level : list of tuples
+            The stack buffer supplied by the caller; we append new ``(url, parent)`` items here.
+        depths : dict
+            Shared depth map so future metadata tagging knows how deep each URL lives.
+
+        Notes
+        -----
+        - ``_dfs_seen`` keeps us from pushing duplicates without touching the traversal guard.
+        - Validation, scoring, and capacity trimming mirror the BFS version so behaviour stays consistent.
+        """
+        next_depth = current_depth + 1
+        if next_depth > self.max_depth:
+            return
+
+        remaining_capacity = self.max_pages - self._pages_crawled
+        if remaining_capacity <= 0:
+            self.logger.info(
+                f"Max pages limit ({self.max_pages}) reached, stopping link discovery"
+            )
+            return
+
+        links = result.links.get("internal", [])
+        if self.include_external:
+            links += result.links.get("external", [])
+
+        seen = self._dfs_seen
+        valid_links: List[Tuple[str, float]] = []
+
+        for link in links:
+            raw_url = link.get("href")
+            if not raw_url:
+                continue
+
+            normalized_url = normalize_url_for_deep_crawl(raw_url, source_url)
+            if not normalized_url or normalized_url in seen:
+                continue
+
+            if not await self.can_process_url(raw_url, next_depth):
+                self.stats.urls_skipped += 1
+                continue
+
+            score = self.url_scorer.score(normalized_url) if self.url_scorer else 0
+            if score < self.score_threshold:
+                self.logger.debug(
+                    f"URL {normalized_url} skipped: score {score} below threshold {self.score_threshold}"
+                )
+                self.stats.urls_skipped += 1
+                continue
+
+            seen.add(normalized_url)
+            valid_links.append((normalized_url, score))
+
+        if len(valid_links) > remaining_capacity:
+            if self.url_scorer:
+                valid_links.sort(key=lambda x: x[1], reverse=True)
+            valid_links = valid_links[:remaining_capacity]
+            self.logger.info(
+                f"Limiting to {remaining_capacity} URLs due to max_pages limit"
+            )
+
+        for url, score in valid_links:
+            if score:
+                result.metadata = result.metadata or {}
+                result.metadata["score"] = score
+            next_level.append((url, source_url))
+            depths[url] = next_depth

crawl4ai/deep_crawling/filters.py

@@ -509,18 +509,22 @@ class DomainFilter(URLFilter):
 class ContentRelevanceFilter(URLFilter):
     """BM25-based relevance filter using head section content"""
 
-    __slots__ = ("query_terms", "threshold", "k1", "b", "avgdl")
+    __slots__ = ("query_terms", "threshold", "k1", "b", "avgdl", "query")
 
     def __init__(
         self,
-        query: str,
+        query: Union[str, List[str]],
         threshold: float,
         k1: float = 1.2,
         b: float = 0.75,
         avgdl: int = 1000,
     ):
         super().__init__(name="BM25RelevanceFilter")
-        self.query_terms = self._tokenize(query)
+        if isinstance(query, list):
+            self.query = " ".join(query)
+        else:
+            self.query = query
+        self.query_terms = self._tokenize(self.query)
         self.threshold = threshold
         self.k1 = k1  # TF saturation parameter
         self.b = b  # Length normalization parameter

crawl4ai/docker_client.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, Union, AsyncGenerator, Dict, Any
+from typing import List, Optional, Union, AsyncGenerator, Dict, Any, Callable
 import httpx
 import json
 from urllib.parse import urljoin
@@ -7,6 +7,7 @@ import asyncio
 from .async_configs import BrowserConfig, CrawlerRunConfig
 from .models import CrawlResult
 from .async_logger import AsyncLogger, LogLevel
+from .utils import hooks_to_string
 
 
 class Crawl4aiClientError(Exception):
@@ -70,17 +71,41 @@ class Crawl4aiDockerClient:
             self.logger.error(f"Server unreachable: {str(e)}", tag="ERROR")
             raise ConnectionError(f"Cannot connect to server: {str(e)}")
 
-    def _prepare_request(self, urls: List[str], browser_config: Optional[BrowserConfig] = None, 
-                       crawler_config: Optional[CrawlerRunConfig] = None) -> Dict[str, Any]:
+    def _prepare_request(
+        self,
+        urls: List[str],
+        browser_config: Optional[BrowserConfig] = None,
+        crawler_config: Optional[CrawlerRunConfig] = None,
+        hooks: Optional[Union[Dict[str, Callable], Dict[str, str]]] = None,
+        hooks_timeout: int = 30
+    ) -> Dict[str, Any]:
         """Prepare request data from configs."""
         if self._token:
             self._http_client.headers["Authorization"] = f"Bearer {self._token}"
-        return {
+
+        request_data = {
             "urls": urls,
             "browser_config": browser_config.dump() if browser_config else {},
             "crawler_config": crawler_config.dump() if crawler_config else {}
         }
 
+        # Handle hooks if provided
+        if hooks:
+            # Check if hooks are already strings or need conversion
+            if any(callable(v) for v in hooks.values()):
+                # Convert function objects to strings
+                hooks_code = hooks_to_string(hooks)
+            else:
+                # Already in string format
+                hooks_code = hooks
+
+            request_data["hooks"] = {
+                "code": hooks_code,
+                "timeout": hooks_timeout
+            }
+
+        return request_data
+
     async def _request(self, method: str, endpoint: str, **kwargs) -> httpx.Response:
         """Make an HTTP request with error handling."""
         url = urljoin(self.base_url, endpoint)
@@ -102,16 +127,42 @@ class Crawl4aiDockerClient:
         self,
         urls: List[str],
         browser_config: Optional[BrowserConfig] = None,
-        crawler_config: Optional[CrawlerRunConfig] = None
+        crawler_config: Optional[CrawlerRunConfig] = None,
+        hooks: Optional[Union[Dict[str, Callable], Dict[str, str]]] = None,
+        hooks_timeout: int = 30
     ) -> Union[CrawlResult, List[CrawlResult], AsyncGenerator[CrawlResult, None]]:
-        """Execute a crawl operation."""
+        """
+        Execute a crawl operation.
+
+        Args:
+            urls: List of URLs to crawl
+            browser_config: Browser configuration
+            crawler_config: Crawler configuration
+            hooks: Optional hooks - can be either:
+                   - Dict[str, Callable]: Function objects that will be converted to strings
+                   - Dict[str, str]: Already stringified hook code
+            hooks_timeout: Timeout in seconds for each hook execution (1-120)
+
+        Returns:
+            Single CrawlResult, list of results, or async generator for streaming
+
+        Example with function hooks:
+            >>> async def my_hook(page, context, **kwargs):
+            ...     await page.set_viewport_size({"width": 1920, "height": 1080})
+            ...     return page
+            >>>
+            >>> result = await client.crawl(
+            ...     ["https://example.com"],
+            ...     hooks={"on_page_context_created": my_hook}
+            ... )
+        """
         await self._check_server()
-        
-        data = self._prepare_request(urls, browser_config, crawler_config)
+
+        data = self._prepare_request(urls, browser_config, crawler_config, hooks, hooks_timeout)
         is_streaming = crawler_config and crawler_config.stream
-        
+
         self.logger.info(f"Crawling {len(urls)} URLs {'(streaming)' if is_streaming else ''}", tag="CRAWL")
-        
+
         if is_streaming:
             async def stream_results() -> AsyncGenerator[CrawlResult, None]:
                 async with self._http_client.stream("POST", f"{self.base_url}/crawl/stream", json=data) as response:
@@ -128,12 +179,12 @@ class Crawl4aiDockerClient:
                             else:
                                 yield CrawlResult(**result)
             return stream_results()
-        
-        response = await self._request("POST", "/crawl", json=data)
+
+        response = await self._request("POST", "/crawl", json=data, timeout=hooks_timeout)
         result_data = response.json()
         if not result_data.get("success", False):
             raise RequestError(f"Crawl failed: {result_data.get('msg', 'Unknown error')}")
-        
+
         results = [CrawlResult(**r) for r in result_data.get("results", [])]
         self.logger.success(f"Crawl completed with {len(results)} results", tag="CRAWL")
         return results[0] if len(results) == 1 else results

crawl4ai/extraction_strategy.py

@@ -94,6 +94,20 @@ class ExtractionStrategy(ABC):
                 extracted_content.extend(future.result())
         return extracted_content
 
+    async def arun(self, url: str, sections: List[str], *q, **kwargs) -> List[Dict[str, Any]]:
+        """
+        Async version: Process sections of text in parallel using asyncio.
+
+        Default implementation runs the sync version in a thread pool.
+        Subclasses can override this for true async processing.
+
+        :param url: The URL of the webpage.
+        :param sections: List of sections (strings) to process.
+        :return: A list of processed JSON blocks.
+        """
+        import asyncio
+        return await asyncio.to_thread(self.run, url, sections, *q, **kwargs)
+
 
 class NoExtractionStrategy(ExtractionStrategy):
     """
@@ -635,6 +649,9 @@ class LLMExtractionStrategy(ExtractionStrategy):
                 base_url=self.llm_config.base_url,
                 json_response=self.force_json_response,
                 extra_args=self.extra_args,
+                base_delay=self.llm_config.backoff_base_delay,
+                max_attempts=self.llm_config.backoff_max_attempts,
+                exponential_factor=self.llm_config.backoff_exponential_factor
             )  # , json_response=self.extract_type == "schema")
             # Track usage
             usage = TokenUsage(
@@ -780,6 +797,180 @@ class LLMExtractionStrategy(ExtractionStrategy):
 
         return extracted_content
 
+    async def aextract(self, url: str, ix: int, html: str) -> List[Dict[str, Any]]:
+        """
+        Async version: Extract meaningful blocks or chunks from the given HTML using an LLM.
+
+        How it works:
+        1. Construct a prompt with variables.
+        2. Make an async request to the LLM using the prompt.
+        3. Parse the response and extract blocks or chunks.
+
+        Args:
+            url: The URL of the webpage.
+            ix: Index of the block.
+            html: The HTML content of the webpage.
+
+        Returns:
+            A list of extracted blocks or chunks.
+        """
+        from .utils import aperform_completion_with_backoff
+
+        if self.verbose:
+            print(f"[LOG] Call LLM for {url} - block index: {ix}")
+
+        variable_values = {
+            "URL": url,
+            "HTML": escape_json_string(sanitize_html(html)),
+        }
+
+        prompt_with_variables = PROMPT_EXTRACT_BLOCKS
+        if self.instruction:
+            variable_values["REQUEST"] = self.instruction
+            prompt_with_variables = PROMPT_EXTRACT_BLOCKS_WITH_INSTRUCTION
+
+        if self.extract_type == "schema" and self.schema:
+            variable_values["SCHEMA"] = json.dumps(self.schema, indent=2)
+            prompt_with_variables = PROMPT_EXTRACT_SCHEMA_WITH_INSTRUCTION
+
+        if self.extract_type == "schema" and not self.schema:
+            prompt_with_variables = PROMPT_EXTRACT_INFERRED_SCHEMA
+
+        for variable in variable_values:
+            prompt_with_variables = prompt_with_variables.replace(
+                "{" + variable + "}", variable_values[variable]
+            )
+
+        try:
+            response = await aperform_completion_with_backoff(
+                self.llm_config.provider,
+                prompt_with_variables,
+                self.llm_config.api_token,
+                base_url=self.llm_config.base_url,
+                json_response=self.force_json_response,
+                extra_args=self.extra_args,
+                base_delay=self.llm_config.backoff_base_delay,
+                max_attempts=self.llm_config.backoff_max_attempts,
+                exponential_factor=self.llm_config.backoff_exponential_factor
+            )
+            # Track usage
+            usage = TokenUsage(
+                completion_tokens=response.usage.completion_tokens,
+                prompt_tokens=response.usage.prompt_tokens,
+                total_tokens=response.usage.total_tokens,
+                completion_tokens_details=response.usage.completion_tokens_details.__dict__
+                if response.usage.completion_tokens_details
+                else {},
+                prompt_tokens_details=response.usage.prompt_tokens_details.__dict__
+                if response.usage.prompt_tokens_details
+                else {},
+            )
+            self.usages.append(usage)
+
+            # Update totals
+            self.total_usage.completion_tokens += usage.completion_tokens
+            self.total_usage.prompt_tokens += usage.prompt_tokens
+            self.total_usage.total_tokens += usage.total_tokens
+
+            try:
+                content = response.choices[0].message.content
+                blocks = None
+
+                if self.force_json_response:
+                    blocks = json.loads(content)
+                    if isinstance(blocks, dict):
+                        if len(blocks) == 1 and isinstance(list(blocks.values())[0], list):
+                            blocks = list(blocks.values())[0]
+                        else:
+                            blocks = [blocks]
+                    elif isinstance(blocks, list):
+                        blocks = blocks
+                else:
+                    blocks = extract_xml_data(["blocks"], content)["blocks"]
+                    blocks = json.loads(blocks)
+
+                for block in blocks:
+                    block["error"] = False
+            except Exception:
+                parsed, unparsed = split_and_parse_json_objects(
+                    response.choices[0].message.content
+                )
+                blocks = parsed
+                if unparsed:
+                    blocks.append(
+                        {"index": 0, "error": True, "tags": ["error"], "content": unparsed}
+                    )
+
+            if self.verbose:
+                print(
+                    "[LOG] Extracted",
+                    len(blocks),
+                    "blocks from URL:",
+                    url,
+                    "block index:",
+                    ix,
+                )
+            return blocks
+        except Exception as e:
+            if self.verbose:
+                print(f"[LOG] Error in LLM extraction: {e}")
+            return [
+                {
+                    "index": ix,
+                    "error": True,
+                    "tags": ["error"],
+                    "content": str(e),
+                }
+            ]
+
+    async def arun(self, url: str, sections: List[str]) -> List[Dict[str, Any]]:
+        """
+        Async version: Process sections with true parallelism using asyncio.gather.
+
+        Args:
+            url: The URL of the webpage.
+            sections: List of sections (strings) to process.
+
+        Returns:
+            A list of extracted blocks or chunks.
+        """
+        import asyncio
+
+        merged_sections = self._merge(
+            sections,
+            self.chunk_token_threshold,
+            overlap=int(self.chunk_token_threshold * self.overlap_rate),
+        )
+
+        extracted_content = []
+
+        # Create tasks for all sections to run in parallel
+        tasks = [
+            self.aextract(url, ix, sanitize_input_encode(section))
+            for ix, section in enumerate(merged_sections)
+        ]
+
+        # Execute all tasks concurrently
+        results = await asyncio.gather(*tasks, return_exceptions=True)
+
+        # Process results
+        for result in results:
+            if isinstance(result, Exception):
+                if self.verbose:
+                    print(f"Error in async extraction: {result}")
+                extracted_content.append(
+                    {
+                        "index": 0,
+                        "error": True,
+                        "tags": ["error"],
+                        "content": str(result),
+                    }
+                )
+            else:
+                extracted_content.extend(result)
+
+        return extracted_content
+
     def show_usage(self) -> None:
         """Print a detailed token usage report showing total and per-request usage."""
         print("\n=== Token Usage Summary ===")

crawl4ai/models.py

@@ -1,4 +1,4 @@
-from pydantic import BaseModel, HttpUrl, PrivateAttr, Field
+from pydantic import BaseModel, HttpUrl, PrivateAttr, Field, ConfigDict
 from typing import List, Dict, Optional, Callable, Awaitable, Union, Any
 from typing import AsyncGenerator
 from typing import Generic, TypeVar
@@ -153,8 +153,7 @@ class CrawlResult(BaseModel):
     console_messages: Optional[List[Dict[str, Any]]] = None
     tables: List[Dict] = Field(default_factory=list)  # NEW – [{headers,rows,caption,summary}]
 
-    class Config:
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
 # NOTE: The StringCompatibleMarkdown class, custom __init__ method, property getters/setters,
 # and model_dump override all exist to support a smooth transition from markdown as a string
@@ -332,8 +331,7 @@ class AsyncCrawlResponse(BaseModel):
     network_requests: Optional[List[Dict[str, Any]]] = None
     console_messages: Optional[List[Dict[str, Any]]] = None
 
-    class Config:
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
 ###############################
 # Scraping Models

crawl4ai/processors/pdf/processor.py

@@ -15,9 +15,9 @@ from .utils import (
     clean_pdf_text_to_html,
 )
 
-# Remove direct PyPDF2 imports from the top
-# import PyPDF2
-# from PyPDF2 import PdfReader
+# Remove direct pypdf imports from the top
+# import pypdf
+# from pypdf import PdfReader
 
 logger = logging.getLogger(__name__)
 
@@ -59,9 +59,9 @@ class NaivePDFProcessorStrategy(PDFProcessorStrategy):
                  save_images_locally: bool = False, image_save_dir: Optional[Path] = None, batch_size: int = 4):
         # Import check at initialization time
         try:
-            import PyPDF2
+            import pypdf
         except ImportError:
-            raise ImportError("PyPDF2 is required for PDF processing. Install with 'pip install crawl4ai[pdf]'")
+            raise ImportError("pypdf is required for PDF processing. Install with 'pip install crawl4ai[pdf]'")
             
         self.image_dpi = image_dpi
         self.image_quality = image_quality
@@ -75,9 +75,9 @@ class NaivePDFProcessorStrategy(PDFProcessorStrategy):
     def process(self, pdf_path: Path) -> PDFProcessResult:
         # Import inside method to allow dependency to be optional
         try:
-            from PyPDF2 import PdfReader
+            from pypdf import PdfReader
         except ImportError:
-            raise ImportError("PyPDF2 is required for PDF processing. Install with 'pip install crawl4ai[pdf]'")
+            raise ImportError("pypdf is required for PDF processing. Install with 'pip install crawl4ai[pdf]'")
             
         start_time = time()
         result = PDFProcessResult(
@@ -125,15 +125,15 @@ class NaivePDFProcessorStrategy(PDFProcessorStrategy):
         """Like process() but processes PDF pages in parallel batches"""
         # Import inside method to allow dependency to be optional
         try:
-            from PyPDF2 import PdfReader
-            import PyPDF2  # For type checking
+            from pypdf import PdfReader
+            import pypdf  # For type checking
         except ImportError:
-            raise ImportError("PyPDF2 is required for PDF processing. Install with 'pip install crawl4ai[pdf]'")
+            raise ImportError("pypdf is required for PDF processing. Install with 'pip install crawl4ai[pdf]'")
             
         import concurrent.futures
         import threading
         
-        # Initialize PyPDF2 thread support
+        # Initialize pypdf thread support
         if not hasattr(threading.current_thread(), "_children"): 
             threading.current_thread()._children = set()
         
@@ -232,11 +232,11 @@ class NaivePDFProcessorStrategy(PDFProcessorStrategy):
         return pdf_page
 
     def _extract_images(self, page, image_dir: Optional[Path]) -> List[Dict]:
-        # Import PyPDF2 for type checking only when needed
+        # Import pypdf for type checking only when needed
         try:
-            import PyPDF2
+            from pypdf.generic import IndirectObject
         except ImportError:
-            raise ImportError("PyPDF2 is required for PDF processing. Install with 'pip install crawl4ai[pdf]'")
+            raise ImportError("pypdf is required for PDF processing. Install with 'pip install crawl4ai[pdf]'")
             
         if not self.extract_images:
             return []
@@ -266,7 +266,7 @@ class NaivePDFProcessorStrategy(PDFProcessorStrategy):
                                     width = xobj.get('/Width', 0)
                                     height = xobj.get('/Height', 0)
                                     color_space = xobj.get('/ColorSpace', '/DeviceRGB')
-                                    if isinstance(color_space, PyPDF2.generic.IndirectObject):
+                                    if isinstance(color_space, IndirectObject):
                                         color_space = color_space.get_object()
 
                                     # Handle different image encodings
@@ -277,7 +277,7 @@ class NaivePDFProcessorStrategy(PDFProcessorStrategy):
                                     if '/FlateDecode' in filters:
                                         try:
                                             decode_parms = xobj.get('/DecodeParms', {})
-                                            if isinstance(decode_parms, PyPDF2.generic.IndirectObject):
+                                            if isinstance(decode_parms, IndirectObject):
                                                 decode_parms = decode_parms.get_object()
                                             
                                             predictor = decode_parms.get('/Predictor', 1)
@@ -416,10 +416,10 @@ class NaivePDFProcessorStrategy(PDFProcessorStrategy):
         # Import inside method to allow dependency to be optional 
         if reader is None:
             try:
-                from PyPDF2 import PdfReader
+                from pypdf import PdfReader
                 reader = PdfReader(pdf_path)
             except ImportError:
-                raise ImportError("PyPDF2 is required for PDF processing. Install with 'pip install crawl4ai[pdf]'")
+                raise ImportError("pypdf is required for PDF processing. Install with 'pip install crawl4ai[pdf]'")
 
         meta = reader.metadata or {}
         created = self._parse_pdf_date(meta.get('/CreationDate', ''))
@@ -459,11 +459,11 @@ if __name__ == "__main__":
     from pathlib import Path
     
     try:
-        # Import PyPDF2 only when running the file directly
-        import PyPDF2
-        from PyPDF2 import PdfReader
+        # Import pypdf only when running the file directly
+        import pypdf
+        from pypdf import PdfReader
     except ImportError:
-        print("PyPDF2 is required for PDF processing. Install with 'pip install crawl4ai[pdf]'")
+        print("pypdf is required for PDF processing. Install with 'pip install crawl4ai[pdf]'")
         exit(1)
         
     current_dir = Path(__file__).resolve().parent

crawl4ai/table_extraction.py

@@ -795,6 +795,9 @@ Return only a JSON array of extracted tables following the specified format."""
                     api_token=self.llm_config.api_token,
                     base_url=self.llm_config.base_url,
                     json_response=True,
+                    base_delay=self.llm_config.backoff_base_delay,
+                    max_attempts=self.llm_config.backoff_max_attempts,
+                    exponential_factor=self.llm_config.backoff_exponential_factor,
                     extra_args=self.extra_args
                 )
                 
@@ -1116,6 +1119,9 @@ Return only a JSON array of extracted tables following the specified format."""
                     api_token=self.llm_config.api_token,
                     base_url=self.llm_config.base_url,
                     json_response=True,
+                    base_delay=self.llm_config.backoff_base_delay,
+                    max_attempts=self.llm_config.backoff_max_attempts,
+                    exponential_factor=self.llm_config.backoff_exponential_factor,
                     extra_args=self.extra_args
                 )
                 

crawl4ai/utils.py

@@ -47,6 +47,7 @@ from urllib.parse import (
     urljoin, urlparse, urlunparse,
     parse_qsl, urlencode, quote, unquote
 )
+import inspect
 
 
 # Monkey patch to fix wildcard handling in urllib.robotparser
@@ -1744,6 +1745,9 @@ def perform_completion_with_backoff(
     api_token,
     json_response=False,
     base_url=None,
+    base_delay=2,
+    max_attempts=3,
+    exponential_factor=2,
     **kwargs,
 ):
     """
@@ -1760,6 +1764,9 @@ def perform_completion_with_backoff(
         api_token (str): The API token for authentication.
         json_response (bool): Whether to request a JSON response. Defaults to False.
         base_url (Optional[str]): The base URL for the API. Defaults to None.
+        base_delay (int): The base delay in seconds. Defaults to 2.
+        max_attempts (int): The maximum number of attempts. Defaults to 3.
+        exponential_factor (int): The exponential factor. Defaults to 2.
         **kwargs: Additional arguments for the API request.
 
     Returns:
@@ -1769,9 +1776,6 @@ def perform_completion_with_backoff(
     from litellm import completion
     from litellm.exceptions import RateLimitError
 
-    max_attempts = 3
-    base_delay = 2  # Base delay in seconds, you can adjust this based on your needs
-
     extra_args = {"temperature": 0.01, "api_key": api_token, "base_url": base_url}
     if json_response:
         extra_args["response_format"] = {"type": "json_object"}
@@ -1797,7 +1801,7 @@ def perform_completion_with_backoff(
             # Check if we have exhausted our max attempts
             if attempt < max_attempts - 1:
                 # Calculate the delay and wait
-                delay = base_delay * (2**attempt)  # Exponential backoff formula
+                delay = base_delay * (exponential_factor**attempt)  # Exponential backoff formula
                 print(f"Waiting for {delay} seconds before retrying...")
                 time.sleep(delay)
             else:
@@ -1824,6 +1828,85 @@ def perform_completion_with_backoff(
             # ]
 
 
+async def aperform_completion_with_backoff(
+    provider,
+    prompt_with_variables,
+    api_token,
+    json_response=False,
+    base_url=None,
+    base_delay=2,
+    max_attempts=3,
+    exponential_factor=2,
+    **kwargs,
+):
+    """
+    Async version: Perform an API completion request with exponential backoff.
+
+    How it works:
+    1. Sends an async completion request to the API.
+    2. Retries on rate-limit errors with exponential delays (async).
+    3. Returns the API response or an error after all retries.
+
+    Args:
+        provider (str): The name of the API provider.
+        prompt_with_variables (str): The input prompt for the completion request.
+        api_token (str): The API token for authentication.
+        json_response (bool): Whether to request a JSON response. Defaults to False.
+        base_url (Optional[str]): The base URL for the API. Defaults to None.
+        base_delay (int): The base delay in seconds. Defaults to 2.
+        max_attempts (int): The maximum number of attempts. Defaults to 3.
+        exponential_factor (int): The exponential factor. Defaults to 2.
+        **kwargs: Additional arguments for the API request.
+
+    Returns:
+        dict: The API response or an error message after all retries.
+    """
+
+    from litellm import acompletion
+    from litellm.exceptions import RateLimitError
+    import asyncio
+
+    extra_args = {"temperature": 0.01, "api_key": api_token, "base_url": base_url}
+    if json_response:
+        extra_args["response_format"] = {"type": "json_object"}
+
+    if kwargs.get("extra_args"):
+        extra_args.update(kwargs["extra_args"])
+
+    for attempt in range(max_attempts):
+        try:
+            response = await acompletion(
+                model=provider,
+                messages=[{"role": "user", "content": prompt_with_variables}],
+                **extra_args,
+            )
+            return response  # Return the successful response
+        except RateLimitError as e:
+            print("Rate limit error:", str(e))
+
+            if attempt == max_attempts - 1:
+                # Last attempt failed, raise the error.
+                raise
+
+            # Check if we have exhausted our max attempts
+            if attempt < max_attempts - 1:
+                # Calculate the delay and wait
+                delay = base_delay * (exponential_factor**attempt)  # Exponential backoff formula
+                print(f"Waiting for {delay} seconds before retrying...")
+                await asyncio.sleep(delay)
+            else:
+                # Return an error response after exhausting all retries
+                return [
+                    {
+                        "index": 0,
+                        "tags": ["error"],
+                        "content": ["Rate limit error. Please try again later."],
+                    }
+                ]
+        except Exception as e:
+            raise e  # Raise any other exceptions immediately
+
+
 def extract_blocks(url, html, provider=DEFAULT_PROVIDER, api_token=None, base_url=None):
     """
     Extract content blocks from website HTML using an AI provider.
@@ -3529,4 +3612,52 @@ def get_memory_stats() -> Tuple[float, float, float]:
     available_gb = get_true_available_memory_gb()
     used_percent = get_true_memory_usage_percent()
     
-    return used_percent, available_gb, total_gb
+    return used_percent, available_gb, total_gb
+
+
+# Hook utilities for Docker API
+def hooks_to_string(hooks: Dict[str, Callable]) -> Dict[str, str]:
+    """
+    Convert hook function objects to string representations for Docker API.
+
+    This utility simplifies the process of using hooks with the Docker API by converting
+    Python function objects into the string format required by the API.
+
+    Args:
+        hooks: Dictionary mapping hook point names to Python function objects.
+               Functions should be async and follow hook signature requirements.
+
+    Returns:
+        Dictionary mapping hook point names to string representations of the functions.
+
+    Example:
+        >>> async def my_hook(page, context, **kwargs):
+        ...     await page.set_viewport_size({"width": 1920, "height": 1080})
+        ...     return page
+        >>>
+        >>> hooks_dict = {"on_page_context_created": my_hook}
+        >>> api_hooks = hooks_to_string(hooks_dict)
+        >>> # api_hooks is now ready to use with Docker API
+
+    Raises:
+        ValueError: If a hook is not callable or source cannot be extracted
+    """
+    result = {}
+
+    for hook_name, hook_func in hooks.items():
+        if not callable(hook_func):
+            raise ValueError(f"Hook '{hook_name}' must be a callable function, got {type(hook_func)}")
+
+        try:
+            # Get the source code of the function
+            source = inspect.getsource(hook_func)
+            # Remove any leading indentation to get clean source
+            source = textwrap.dedent(source)
+            result[hook_name] = source
+        except (OSError, TypeError) as e:
+            raise ValueError(
+                f"Cannot extract source code for hook '{hook_name}'. "
+                f"Make sure the function is defined in a file (not interactively). Error: {e}"
+            )
+
+    return result

deploy/docker/README.md

@@ -12,6 +12,7 @@
   - [Python SDK](#python-sdk)
   - [Understanding Request Schema](#understanding-request-schema)
   - [REST API Examples](#rest-api-examples)
+  - [Asynchronous Jobs with Webhooks](#asynchronous-jobs-with-webhooks)
 - [Additional API Endpoints](#additional-api-endpoints)
   - [HTML Extraction Endpoint](#html-extraction-endpoint)
   - [Screenshot Endpoint](#screenshot-endpoint)
@@ -58,15 +59,13 @@ Pull and run images directly from Docker Hub without building locally.
 
 #### 1. Pull the Image
 
-Our latest release candidate is `0.7.0-r1`. Images are built with multi-arch manifests, so Docker automatically pulls the correct version for your system.
-
-> ⚠️ **Important Note**: The `latest` tag currently points to the stable `0.6.0` version. After testing and validation, `0.7.0` (without -r1) will be released and `latest` will be updated. For now, please use `0.7.0-r1` to test the new features.
+Our latest stable release is `0.7.7`. Images are built with multi-arch manifests, so Docker automatically pulls the correct version for your system.
 
 ```bash
-# Pull the release candidate (for testing new features)
-docker pull unclecode/crawl4ai:0.7.0-r1
+# Pull the latest stable version (0.7.7)
+docker pull unclecode/crawl4ai:0.7.7
 
-# Or pull the current stable version (0.6.0)
+# Or use the latest tag (points to 0.7.7)
 docker pull unclecode/crawl4ai:latest
 ```
 
@@ -101,7 +100,7 @@ EOL
       -p 11235:11235 \
       --name crawl4ai \
       --shm-size=1g \
-      unclecode/crawl4ai:0.7.0-r1
+      unclecode/crawl4ai:0.7.7
     ```
 
 *   **With LLM support:**
@@ -112,7 +111,7 @@ EOL
       --name crawl4ai \
       --env-file .llm.env \
       --shm-size=1g \
-      unclecode/crawl4ai:0.7.0-r1
+      unclecode/crawl4ai:0.7.7
     ```
 
 > The server will be available at `http://localhost:11235`. Visit `/playground` to access the interactive testing interface.
@@ -185,7 +184,7 @@ The `docker-compose.yml` file in the project root provides a simplified approach
     ```bash
     # Pulls and runs the release candidate from Docker Hub
     # Automatically selects the correct architecture
-    IMAGE=unclecode/crawl4ai:0.7.0-r1 docker compose up -d
+    IMAGE=unclecode/crawl4ai:0.7.7 docker compose up -d
     ```
 
 *   **Build and Run Locally:**
@@ -648,6 +647,194 @@ async def test_stream_crawl(token: str = None): # Made token optional
 # asyncio.run(test_stream_crawl())
 ```
 
+### Asynchronous Jobs with Webhooks
+
+For long-running crawls or when you want to avoid keeping connections open, use the job queue endpoints. Instead of polling for results, configure a webhook to receive notifications when jobs complete.
+
+#### Why Use Jobs & Webhooks?
+
+- **No Polling Required** - Get notified when crawls complete instead of constantly checking status
+- **Better Resource Usage** - Free up client connections while jobs run in the background
+- **Scalable Architecture** - Ideal for high-volume crawling with TypeScript/Node.js clients or microservices
+- **Reliable Delivery** - Automatic retry with exponential backoff (5 attempts: 1s → 2s → 4s → 8s → 16s)
+
+#### How It Works
+
+1. **Submit Job** → POST to `/crawl/job` with optional `webhook_config`
+2. **Get Task ID** → Receive a `task_id` immediately
+3. **Job Runs** → Crawl executes in the background
+4. **Webhook Fired** → Server POSTs completion notification to your webhook URL
+5. **Fetch Results** → If data wasn't included in webhook, GET `/crawl/job/{task_id}`
+
+#### Quick Example
+
+```bash
+# Submit a crawl job with webhook notification
+curl -X POST http://localhost:11235/crawl/job \
+  -H "Content-Type: application/json" \
+  -d '{
+    "urls": ["https://example.com"],
+    "webhook_config": {
+      "webhook_url": "https://myapp.com/webhooks/crawl-complete",
+      "webhook_data_in_payload": false
+    }
+  }'
+
+# Response: {"task_id": "crawl_a1b2c3d4"}
+```
+
+**Your webhook receives:**
+```json
+{
+  "task_id": "crawl_a1b2c3d4",
+  "task_type": "crawl",
+  "status": "completed",
+  "timestamp": "2025-10-21T10:30:00.000000+00:00",
+  "urls": ["https://example.com"]
+}
+```
+
+Then fetch the results:
+```bash
+curl http://localhost:11235/crawl/job/crawl_a1b2c3d4
+```
+
+#### Include Data in Webhook
+
+Set `webhook_data_in_payload: true` to receive the full crawl results directly in the webhook:
+
+```bash
+curl -X POST http://localhost:11235/crawl/job \
+  -H "Content-Type: application/json" \
+  -d '{
+    "urls": ["https://example.com"],
+    "webhook_config": {
+      "webhook_url": "https://myapp.com/webhooks/crawl-complete",
+      "webhook_data_in_payload": true
+    }
+  }'
+```
+
+**Your webhook receives the complete data:**
+```json
+{
+  "task_id": "crawl_a1b2c3d4",
+  "task_type": "crawl",
+  "status": "completed",
+  "timestamp": "2025-10-21T10:30:00.000000+00:00",
+  "urls": ["https://example.com"],
+  "data": {
+    "markdown": "...",
+    "html": "...",
+    "links": {...},
+    "metadata": {...}
+  }
+}
+```
+
+#### Webhook Authentication
+
+Add custom headers for authentication:
+
+```json
+{
+  "urls": ["https://example.com"],
+  "webhook_config": {
+    "webhook_url": "https://myapp.com/webhooks/crawl",
+    "webhook_data_in_payload": false,
+    "webhook_headers": {
+      "X-Webhook-Secret": "your-secret-token",
+      "X-Service-ID": "crawl4ai-prod"
+    }
+  }
+}
+```
+
+#### Global Default Webhook
+
+Configure a default webhook URL in `config.yml` for all jobs:
+
+```yaml
+webhooks:
+  enabled: true
+  default_url: "https://myapp.com/webhooks/default"
+  data_in_payload: false
+  retry:
+    max_attempts: 5
+    initial_delay_ms: 1000
+    max_delay_ms: 32000
+    timeout_ms: 30000
+```
+
+Now jobs without `webhook_config` automatically use the default webhook.
+
+#### Job Status Polling (Without Webhooks)
+
+If you prefer polling instead of webhooks, just omit `webhook_config`:
+
+```bash
+# Submit job
+curl -X POST http://localhost:11235/crawl/job \
+  -H "Content-Type: application/json" \
+  -d '{"urls": ["https://example.com"]}'
+# Response: {"task_id": "crawl_xyz"}
+
+# Poll for status
+curl http://localhost:11235/crawl/job/crawl_xyz
+```
+
+The response includes `status` field: `"processing"`, `"completed"`, or `"failed"`.
+
+#### LLM Extraction Jobs with Webhooks
+
+The same webhook system works for LLM extraction jobs via `/llm/job`:
+
+```bash
+# Submit LLM extraction job with webhook
+curl -X POST http://localhost:11235/llm/job \
+  -H "Content-Type: application/json" \
+  -d '{
+    "url": "https://example.com/article",
+    "q": "Extract the article title, author, and main points",
+    "provider": "openai/gpt-4o-mini",
+    "webhook_config": {
+      "webhook_url": "https://myapp.com/webhooks/llm-complete",
+      "webhook_data_in_payload": true,
+      "webhook_headers": {
+        "X-Webhook-Secret": "your-secret-token"
+      }
+    }
+  }'
+
+# Response: {"task_id": "llm_1234567890"}
+```
+
+**Your webhook receives:**
+```json
+{
+  "task_id": "llm_1234567890",
+  "task_type": "llm_extraction",
+  "status": "completed",
+  "timestamp": "2025-10-22T12:30:00.000000+00:00",
+  "urls": ["https://example.com/article"],
+  "data": {
+    "extracted_content": {
+      "title": "Understanding Web Scraping",
+      "author": "John Doe",
+      "main_points": ["Point 1", "Point 2", "Point 3"]
+    }
+  }
+}
+```
+
+**Key Differences for LLM Jobs:**
+- Task type is `"llm_extraction"` instead of `"crawl"`
+- Extracted data is in `data.extracted_content`
+- Single URL only (not an array)
+- Supports schema-based extraction with `schema` parameter
+
+> 💡 **Pro tip**: See [WEBHOOK_EXAMPLES.md](./WEBHOOK_EXAMPLES.md) for detailed examples including TypeScript client code, Flask webhook handlers, and failure handling.
+
 ---
 
 ## Metrics & Monitoring
@@ -826,10 +1013,11 @@ We're here to help you succeed with Crawl4AI! Here's how to get support:
 
 In this guide, we've covered everything you need to get started with Crawl4AI's Docker deployment:
 - Building and running the Docker container
-- Configuring the environment  
+- Configuring the environment
 - Using the interactive playground for testing
 - Making API requests with proper typing
 - Using the Python SDK
+- Asynchronous job queues with webhook notifications
 - Leveraging specialized endpoints for screenshots, PDFs, and JavaScript execution
 - Connecting via the Model Context Protocol (MCP)
 - Monitoring your deployment

deploy/docker/WEBHOOK_EXAMPLES.md

@@ -0,0 +1,378 @@
+# Webhook Feature Examples
+
+This document provides examples of how to use the webhook feature for crawl jobs in Crawl4AI.
+
+## Overview
+
+The webhook feature allows you to receive notifications when crawl jobs complete, eliminating the need for polling. Webhooks are sent with exponential backoff retry logic to ensure reliable delivery.
+
+## Configuration
+
+### Global Configuration (config.yml)
+
+You can configure default webhook settings in `config.yml`:
+
+```yaml
+webhooks:
+  enabled: true
+  default_url: null  # Optional: default webhook URL for all jobs
+  data_in_payload: false  # Optional: default behavior for including data
+  retry:
+    max_attempts: 5
+    initial_delay_ms: 1000  # 1s, 2s, 4s, 8s, 16s exponential backoff
+    max_delay_ms: 32000
+    timeout_ms: 30000  # 30s timeout per webhook call
+  headers:  # Optional: default headers to include
+    User-Agent: "Crawl4AI-Webhook/1.0"
+```
+
+## API Usage Examples
+
+### Example 1: Basic Webhook (Notification Only)
+
+Send a webhook notification without including the crawl data in the payload.
+
+**Request:**
+```bash
+curl -X POST http://localhost:11235/crawl/job \
+  -H "Content-Type: application/json" \
+  -d '{
+    "urls": ["https://example.com"],
+    "webhook_config": {
+      "webhook_url": "https://myapp.com/webhooks/crawl-complete",
+      "webhook_data_in_payload": false
+    }
+  }'
+```
+
+**Response:**
+```json
+{
+  "task_id": "crawl_a1b2c3d4"
+}
+```
+
+**Webhook Payload Received:**
+```json
+{
+  "task_id": "crawl_a1b2c3d4",
+  "task_type": "crawl",
+  "status": "completed",
+  "timestamp": "2025-10-21T10:30:00.000000+00:00",
+  "urls": ["https://example.com"]
+}
+```
+
+Your webhook handler should then fetch the results:
+```bash
+curl http://localhost:11235/crawl/job/crawl_a1b2c3d4
+```
+
+### Example 2: Webhook with Data Included
+
+Include the full crawl results in the webhook payload.
+
+**Request:**
+```bash
+curl -X POST http://localhost:11235/crawl/job \
+  -H "Content-Type: application/json" \
+  -d '{
+    "urls": ["https://example.com"],
+    "webhook_config": {
+      "webhook_url": "https://myapp.com/webhooks/crawl-complete",
+      "webhook_data_in_payload": true
+    }
+  }'
+```
+
+**Webhook Payload Received:**
+```json
+{
+  "task_id": "crawl_a1b2c3d4",
+  "task_type": "crawl",
+  "status": "completed",
+  "timestamp": "2025-10-21T10:30:00.000000+00:00",
+  "urls": ["https://example.com"],
+  "data": {
+    "markdown": "...",
+    "html": "...",
+    "links": {...},
+    "metadata": {...}
+  }
+}
+```
+
+### Example 3: Webhook with Custom Headers
+
+Include custom headers for authentication or identification.
+
+**Request:**
+```bash
+curl -X POST http://localhost:11235/crawl/job \
+  -H "Content-Type: application/json" \
+  -d '{
+    "urls": ["https://example.com"],
+    "webhook_config": {
+      "webhook_url": "https://myapp.com/webhooks/crawl-complete",
+      "webhook_data_in_payload": false,
+      "webhook_headers": {
+        "X-Webhook-Secret": "my-secret-token",
+        "X-Service-ID": "crawl4ai-production"
+      }
+    }
+  }'
+```
+
+The webhook will be sent with these additional headers plus the default headers from config.
+
+### Example 4: Failure Notification
+
+When a crawl job fails, a webhook is sent with error details.
+
+**Webhook Payload on Failure:**
+```json
+{
+  "task_id": "crawl_a1b2c3d4",
+  "task_type": "crawl",
+  "status": "failed",
+  "timestamp": "2025-10-21T10:30:00.000000+00:00",
+  "urls": ["https://example.com"],
+  "error": "Connection timeout after 30s"
+}
+```
+
+### Example 5: Using Global Default Webhook
+
+If you set a `default_url` in config.yml, jobs without webhook_config will use it:
+
+**config.yml:**
+```yaml
+webhooks:
+  enabled: true
+  default_url: "https://myapp.com/webhooks/default"
+  data_in_payload: false
+```
+
+**Request (no webhook_config needed):**
+```bash
+curl -X POST http://localhost:11235/crawl/job \
+  -H "Content-Type: application/json" \
+  -d '{
+    "urls": ["https://example.com"]
+  }'
+```
+
+The webhook will be sent to the default URL configured in config.yml.
+
+### Example 6: LLM Extraction Job with Webhook
+
+Use webhooks with the LLM extraction endpoint for asynchronous processing.
+
+**Request:**
+```bash
+curl -X POST http://localhost:11235/llm/job \
+  -H "Content-Type: application/json" \
+  -d '{
+    "url": "https://example.com/article",
+    "q": "Extract the article title, author, and publication date",
+    "schema": "{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"author\": {\"type\": \"string\"}, \"date\": {\"type\": \"string\"}}}",
+    "cache": false,
+    "provider": "openai/gpt-4o-mini",
+    "webhook_config": {
+      "webhook_url": "https://myapp.com/webhooks/llm-complete",
+      "webhook_data_in_payload": true
+    }
+  }'
+```
+
+**Response:**
+```json
+{
+  "task_id": "llm_1698765432_12345"
+}
+```
+
+**Webhook Payload Received:**
+```json
+{
+  "task_id": "llm_1698765432_12345",
+  "task_type": "llm_extraction",
+  "status": "completed",
+  "timestamp": "2025-10-21T10:30:00.000000+00:00",
+  "urls": ["https://example.com/article"],
+  "data": {
+    "extracted_content": {
+      "title": "Understanding Web Scraping",
+      "author": "John Doe",
+      "date": "2025-10-21"
+    }
+  }
+}
+```
+
+## Webhook Handler Example
+
+Here's a simple Python Flask webhook handler that supports both crawl and LLM extraction jobs:
+
+```python
+from flask import Flask, request, jsonify
+import requests
+
+app = Flask(__name__)
+
+@app.route('/webhooks/crawl-complete', methods=['POST'])
+def handle_crawl_webhook():
+    payload = request.json
+
+    task_id = payload['task_id']
+    task_type = payload['task_type']
+    status = payload['status']
+
+    if status == 'completed':
+        # If data not in payload, fetch it
+        if 'data' not in payload:
+            # Determine endpoint based on task type
+            endpoint = 'crawl' if task_type == 'crawl' else 'llm'
+            response = requests.get(f'http://localhost:11235/{endpoint}/job/{task_id}')
+            data = response.json()
+        else:
+            data = payload['data']
+
+        # Process based on task type
+        if task_type == 'crawl':
+            print(f"Processing crawl results for {task_id}")
+            # Handle crawl results
+            results = data.get('results', [])
+            for result in results:
+                print(f"  - {result.get('url')}: {len(result.get('markdown', ''))} chars")
+
+        elif task_type == 'llm_extraction':
+            print(f"Processing LLM extraction for {task_id}")
+            # Handle LLM extraction
+            # Note: Webhook sends 'extracted_content', API returns 'result'
+            extracted = data.get('extracted_content', data.get('result', {}))
+            print(f"  - Extracted: {extracted}")
+
+        # Your business logic here...
+
+    elif status == 'failed':
+        error = payload.get('error', 'Unknown error')
+        print(f"{task_type} job {task_id} failed: {error}")
+        # Handle failure...
+
+    return jsonify({"status": "received"}), 200
+
+if __name__ == '__main__':
+    app.run(port=8080)
+```
+
+## Retry Logic
+
+The webhook delivery service uses exponential backoff retry logic:
+
+- **Attempts:** Up to 5 attempts by default
+- **Delays:** 1s → 2s → 4s → 8s → 16s
+- **Timeout:** 30 seconds per attempt
+- **Retry Conditions:**
+  - Server errors (5xx status codes)
+  - Network errors
+  - Timeouts
+- **No Retry:**
+  - Client errors (4xx status codes)
+  - Successful delivery (2xx status codes)
+
+## Benefits
+
+1. **No Polling Required** - Eliminates constant API calls to check job status
+2. **Real-time Notifications** - Immediate notification when jobs complete
+3. **Reliable Delivery** - Exponential backoff ensures webhooks are delivered
+4. **Flexible** - Choose between notification-only or full data delivery
+5. **Secure** - Support for custom headers for authentication
+6. **Configurable** - Global defaults or per-job configuration
+7. **Universal Support** - Works with both `/crawl/job` and `/llm/job` endpoints
+
+## TypeScript Client Example
+
+```typescript
+interface WebhookConfig {
+  webhook_url: string;
+  webhook_data_in_payload?: boolean;
+  webhook_headers?: Record<string, string>;
+}
+
+interface CrawlJobRequest {
+  urls: string[];
+  browser_config?: Record<string, any>;
+  crawler_config?: Record<string, any>;
+  webhook_config?: WebhookConfig;
+}
+
+interface LLMJobRequest {
+  url: string;
+  q: string;
+  schema?: string;
+  cache?: boolean;
+  provider?: string;
+  webhook_config?: WebhookConfig;
+}
+
+async function createCrawlJob(request: CrawlJobRequest) {
+  const response = await fetch('http://localhost:11235/crawl/job', {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify(request)
+  });
+
+  const { task_id } = await response.json();
+  return task_id;
+}
+
+async function createLLMJob(request: LLMJobRequest) {
+  const response = await fetch('http://localhost:11235/llm/job', {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify(request)
+  });
+
+  const { task_id } = await response.json();
+  return task_id;
+}
+
+// Usage - Crawl Job
+const crawlTaskId = await createCrawlJob({
+  urls: ['https://example.com'],
+  webhook_config: {
+    webhook_url: 'https://myapp.com/webhooks/crawl-complete',
+    webhook_data_in_payload: false,
+    webhook_headers: {
+      'X-Webhook-Secret': 'my-secret'
+    }
+  }
+});
+
+// Usage - LLM Extraction Job
+const llmTaskId = await createLLMJob({
+  url: 'https://example.com/article',
+  q: 'Extract the main points from this article',
+  provider: 'openai/gpt-4o-mini',
+  webhook_config: {
+    webhook_url: 'https://myapp.com/webhooks/llm-complete',
+    webhook_data_in_payload: true,
+    webhook_headers: {
+      'X-Webhook-Secret': 'my-secret'
+    }
+  }
+});
+```
+
+## Monitoring and Debugging
+
+Webhook delivery attempts are logged at INFO level:
+- Successful deliveries
+- Retry attempts with delays
+- Final failures after max attempts
+
+Check the application logs for webhook delivery status:
+```bash
+docker logs crawl4ai-container | grep -i webhook
+```

deploy/docker/api.py

@@ -46,6 +46,7 @@ from utils import (
     get_llm_temperature,
     get_llm_base_url
 )
+from webhook import WebhookDeliveryService
 
 import psutil, time
 
@@ -107,7 +108,10 @@ async def handle_llm_qa(
             prompt_with_variables=prompt,
             api_token=get_llm_api_key(config),  # Returns None to let litellm handle it
             temperature=get_llm_temperature(config),
-            base_url=get_llm_base_url(config)
+            base_url=get_llm_base_url(config),
+            base_delay=config["llm"].get("backoff_base_delay", 2),
+            max_attempts=config["llm"].get("backoff_max_attempts", 3),
+            exponential_factor=config["llm"].get("backoff_exponential_factor", 2)
         )
 
         return response.choices[0].message.content
@@ -127,10 +131,14 @@ async def process_llm_extraction(
     schema: Optional[str] = None,
     cache: str = "0",
     provider: Optional[str] = None,
+    webhook_config: Optional[Dict] = None,
     temperature: Optional[float] = None,
     base_url: Optional[str] = None
 ) -> None:
     """Process LLM extraction in background."""
+    # Initialize webhook service
+    webhook_service = WebhookDeliveryService(config)
+
     try:
         # Validate provider
         is_valid, error_msg = validate_llm_provider(config, provider)
@@ -139,6 +147,16 @@ async def process_llm_extraction(
                 "status": TaskStatus.FAILED,
                 "error": error_msg
             })
+
+            # Send webhook notification on failure
+            await webhook_service.notify_job_completion(
+                task_id=task_id,
+                task_type="llm_extraction",
+                status="failed",
+                urls=[url],
+                webhook_config=webhook_config,
+                error=error_msg
+            )
             return
         api_key = get_llm_api_key(config, provider)  # Returns None to let litellm handle it
         llm_strategy = LLMExtractionStrategy(
@@ -169,17 +187,40 @@ async def process_llm_extraction(
                 "status": TaskStatus.FAILED,
                 "error": result.error_message
             })
+
+            # Send webhook notification on failure
+            await webhook_service.notify_job_completion(
+                task_id=task_id,
+                task_type="llm_extraction",
+                status="failed",
+                urls=[url],
+                webhook_config=webhook_config,
+                error=result.error_message
+            )
             return
 
         try:
             content = json.loads(result.extracted_content)
         except json.JSONDecodeError:
             content = result.extracted_content
+
+        result_data = {"extracted_content": content}
+
         await redis.hset(f"task:{task_id}", mapping={
             "status": TaskStatus.COMPLETED,
             "result": json.dumps(content)
         })
 
+        # Send webhook notification on successful completion
+        await webhook_service.notify_job_completion(
+            task_id=task_id,
+            task_type="llm_extraction",
+            status="completed",
+            urls=[url],
+            webhook_config=webhook_config,
+            result=result_data
+        )
+
     except Exception as e:
         logger.error(f"LLM extraction error: {str(e)}", exc_info=True)
         await redis.hset(f"task:{task_id}", mapping={
@@ -187,6 +228,16 @@ async def process_llm_extraction(
             "error": str(e)
         })
 
+        # Send webhook notification on failure
+        await webhook_service.notify_job_completion(
+            task_id=task_id,
+            task_type="llm_extraction",
+            status="failed",
+            urls=[url],
+            webhook_config=webhook_config,
+            error=str(e)
+        )
+
 async def handle_markdown_request(
     url: str,
     filter_type: FilterType,
@@ -275,6 +326,7 @@ async def handle_llm_request(
     cache: str = "0",
     config: Optional[dict] = None,
     provider: Optional[str] = None,
+    webhook_config: Optional[Dict] = None,
     temperature: Optional[float] = None,
     api_base_url: Optional[str] = None
 ) -> JSONResponse:
@@ -308,6 +360,7 @@ async def handle_llm_request(
             base_url,
             config,
             provider,
+            webhook_config,
             temperature,
             api_base_url
         )
@@ -355,6 +408,7 @@ async def create_new_task(
     base_url: str,
     config: dict,
     provider: Optional[str] = None,
+    webhook_config: Optional[Dict] = None,
     temperature: Optional[float] = None,
     api_base_url: Optional[str] = None
 ) -> JSONResponse:
@@ -365,12 +419,18 @@ async def create_new_task(
 
     from datetime import datetime
     task_id = f"llm_{int(datetime.now().timestamp())}_{id(background_tasks)}"
-    
-    await redis.hset(f"task:{task_id}", mapping={
+
+    task_data = {
         "status": TaskStatus.PROCESSING,
         "created_at": datetime.now().isoformat(),
         "url": decoded_url
-    })
+    }
+
+    # Store webhook config if provided
+    if webhook_config:
+        task_data["webhook_config"] = json.dumps(webhook_config)
+
+    await redis.hset(f"task:{task_id}", mapping=task_data)
 
     background_tasks.add_task(
         process_llm_extraction,
@@ -382,6 +442,7 @@ async def create_new_task(
         schema,
         cache,
         provider,
+        webhook_config,
         temperature,
         api_base_url
     )
@@ -723,6 +784,7 @@ async def handle_crawl_job(
     browser_config: Dict,
     crawler_config: Dict,
     config: Dict,
+    webhook_config: Optional[Dict] = None,
 ) -> Dict:
     """
     Fire-and-forget version of handle_crawl_request.
@@ -730,13 +792,24 @@ async def handle_crawl_job(
     lets /crawl/job/{task_id} polling fetch the result.
     """
     task_id = f"crawl_{uuid4().hex[:8]}"
-    await redis.hset(f"task:{task_id}", mapping={
+
+    # Store task data in Redis
+    task_data = {
         "status": TaskStatus.PROCESSING,         # <-- keep enum values consistent
         "created_at": datetime.now(timezone.utc).replace(tzinfo=None).isoformat(),
         "url": json.dumps(urls),                 # store list as JSON string
         "result": "",
         "error": "",
-    })
+    }
+
+    # Store webhook config if provided
+    if webhook_config:
+        task_data["webhook_config"] = json.dumps(webhook_config)
+
+    await redis.hset(f"task:{task_id}", mapping=task_data)
+
+    # Initialize webhook service
+    webhook_service = WebhookDeliveryService(config)
 
     async def _runner():
         try:
@@ -750,6 +823,17 @@ async def handle_crawl_job(
                 "status": TaskStatus.COMPLETED,
                 "result": json.dumps(result),
             })
+
+            # Send webhook notification on successful completion
+            await webhook_service.notify_job_completion(
+                task_id=task_id,
+                task_type="crawl",
+                status="completed",
+                urls=urls,
+                webhook_config=webhook_config,
+                result=result
+            )
+
             await asyncio.sleep(5)  # Give Redis time to process the update
         except Exception as exc:
             await redis.hset(f"task:{task_id}", mapping={
@@ -757,5 +841,15 @@ async def handle_crawl_job(
                 "error": str(exc),
             })
 
+            # Send webhook notification on failure
+            await webhook_service.notify_job_completion(
+                task_id=task_id,
+                task_type="crawl",
+                status="failed",
+                urls=urls,
+                webhook_config=webhook_config,
+                error=str(exc)
+            )
+
     background_tasks.add_task(_runner)
     return {"task_id": task_id}

deploy/docker/config.yml

@@ -87,4 +87,17 @@ observability:
     enabled: True
     endpoint: "/metrics"
   health_check:
-    endpoint: "/health"
+    endpoint: "/health"
+
+# Webhook Configuration
+webhooks:
+  enabled: true
+  default_url: null  # Optional: default webhook URL for all jobs
+  data_in_payload: false  # Optional: default behavior for including data
+  retry:
+    max_attempts: 5
+    initial_delay_ms: 1000  # 1s, 2s, 4s, 8s, 16s exponential backoff
+    max_delay_ms: 32000
+    timeout_ms: 30000  # 30s timeout per webhook call
+  headers:  # Optional: default headers to include
+    User-Agent: "Crawl4AI-Webhook/1.0"

deploy/docker/job.py

@@ -12,6 +12,7 @@ from api import (
     handle_crawl_job,
     handle_task_status,
 )
+from schemas import WebhookConfig
 
 # ------------- dependency placeholders -------------
 _redis = None        # will be injected from server.py
@@ -37,6 +38,7 @@ class LlmJobPayload(BaseModel):
     schema: Optional[str] = None
     cache:  bool = False
     provider: Optional[str] = None
+    webhook_config: Optional[WebhookConfig] = None
     temperature: Optional[float] = None
     base_url: Optional[str] = None
 
@@ -45,6 +47,7 @@ class CrawlJobPayload(BaseModel):
     urls:           list[HttpUrl]
     browser_config: Dict = {}
     crawler_config: Dict = {}
+    webhook_config: Optional[WebhookConfig] = None
 
 
 # ---------- LL​M job ---------------------------------------------------------
@@ -55,6 +58,10 @@ async def llm_job_enqueue(
         request: Request,
         _td: Dict = Depends(lambda: _token_dep()),   # late-bound dep
 ):
+    webhook_config = None
+    if payload.webhook_config:
+        webhook_config = payload.webhook_config.model_dump(mode='json')
+
     return await handle_llm_request(
         _redis,
         background_tasks,
@@ -65,6 +72,7 @@ async def llm_job_enqueue(
         cache=payload.cache,
         config=_config,
         provider=payload.provider,
+        webhook_config=webhook_config,
         temperature=payload.temperature,
         api_base_url=payload.base_url,
     )
@@ -86,6 +94,10 @@ async def crawl_job_enqueue(
         background_tasks: BackgroundTasks,
         _td: Dict = Depends(lambda: _token_dep()),
 ):
+    webhook_config = None
+    if payload.webhook_config:
+        webhook_config = payload.webhook_config.model_dump(mode='json')
+
     return await handle_crawl_job(
         _redis,
         background_tasks,
@@ -93,6 +105,7 @@ async def crawl_job_enqueue(
         payload.browser_config,
         payload.crawler_config,
         config=_config,
+        webhook_config=webhook_config,
     )
 
 

deploy/docker/requirements.txt

@@ -12,6 +12,6 @@ pydantic>=2.11
 rank-bm25==0.2.2
 anyio==4.9.0
 PyJWT==2.10.1
-mcp>=1.6.0
+mcp>=1.18.0
 websockets>=15.0.1
 httpx[http2]>=0.27.2

deploy/docker/schemas.py

@@ -1,6 +1,6 @@
 from typing import List, Optional, Dict
 from enum import Enum
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, HttpUrl
 from utils import FilterType
 
 
@@ -85,4 +85,22 @@ class JSEndpointRequest(BaseModel):
     scripts: List[str] = Field(
         ...,
         description="List of separated JavaScript snippets to execute"
-    )
+    )
+
+
+class WebhookConfig(BaseModel):
+    """Configuration for webhook notifications."""
+    webhook_url: HttpUrl
+    webhook_data_in_payload: bool = False
+    webhook_headers: Optional[Dict[str, str]] = None
+
+
+class WebhookPayload(BaseModel):
+    """Payload sent to webhook endpoints."""
+    task_id: str
+    task_type: str  # "crawl", "llm_extraction", etc.
+    status: str  # "completed" or "failed"
+    timestamp: str  # ISO 8601 format
+    urls: List[str]
+    error: Optional[str] = None
+    data: Optional[Dict] = None  # Included only if webhook_data_in_payload=True

deploy/docker/webhook.py

@@ -0,0 +1,159 @@
+"""
+Webhook delivery service for Crawl4AI.
+
+This module provides webhook notification functionality with exponential backoff retry logic.
+"""
+import asyncio
+import httpx
+import logging
+from typing import Dict, Optional
+from datetime import datetime, timezone
+
+logger = logging.getLogger(__name__)
+
+
+class WebhookDeliveryService:
+    """Handles webhook delivery with exponential backoff retry logic."""
+
+    def __init__(self, config: Dict):
+        """
+        Initialize the webhook delivery service.
+
+        Args:
+            config: Application configuration dictionary containing webhook settings
+        """
+        self.config = config.get("webhooks", {})
+        self.max_attempts = self.config.get("retry", {}).get("max_attempts", 5)
+        self.initial_delay = self.config.get("retry", {}).get("initial_delay_ms", 1000) / 1000
+        self.max_delay = self.config.get("retry", {}).get("max_delay_ms", 32000) / 1000
+        self.timeout = self.config.get("retry", {}).get("timeout_ms", 30000) / 1000
+
+    async def send_webhook(
+        self,
+        webhook_url: str,
+        payload: Dict,
+        headers: Optional[Dict[str, str]] = None
+    ) -> bool:
+        """
+        Send webhook with exponential backoff retry logic.
+
+        Args:
+            webhook_url: The URL to send the webhook to
+            payload: The JSON payload to send
+            headers: Optional custom headers
+
+        Returns:
+            bool: True if delivered successfully, False otherwise
+        """
+        default_headers = self.config.get("headers", {})
+        merged_headers = {**default_headers, **(headers or {})}
+        merged_headers["Content-Type"] = "application/json"
+
+        async with httpx.AsyncClient(timeout=self.timeout) as client:
+            for attempt in range(self.max_attempts):
+                try:
+                    logger.info(
+                        f"Sending webhook (attempt {attempt + 1}/{self.max_attempts}) to {webhook_url}"
+                    )
+
+                    response = await client.post(
+                        webhook_url,
+                        json=payload,
+                        headers=merged_headers
+                    )
+
+                    # Success or client error (don't retry client errors)
+                    if response.status_code < 500:
+                        if 200 <= response.status_code < 300:
+                            logger.info(f"Webhook delivered successfully to {webhook_url}")
+                            return True
+                        else:
+                            logger.warning(
+                                f"Webhook rejected with status {response.status_code}: {response.text[:200]}"
+                            )
+                            return False  # Client error - don't retry
+
+                    # Server error - retry with backoff
+                    logger.warning(
+                        f"Webhook failed with status {response.status_code}, will retry"
+                    )
+
+                except httpx.TimeoutException as exc:
+                    logger.error(f"Webhook timeout (attempt {attempt + 1}): {exc}")
+                except httpx.RequestError as exc:
+                    logger.error(f"Webhook request error (attempt {attempt + 1}): {exc}")
+                except Exception as exc:
+                    logger.error(f"Webhook delivery error (attempt {attempt + 1}): {exc}")
+
+                # Calculate exponential backoff delay
+                if attempt < self.max_attempts - 1:
+                    delay = min(self.initial_delay * (2 ** attempt), self.max_delay)
+                    logger.info(f"Retrying in {delay}s...")
+                    await asyncio.sleep(delay)
+
+        logger.error(
+            f"Webhook delivery failed after {self.max_attempts} attempts to {webhook_url}"
+        )
+        return False
+
+    async def notify_job_completion(
+        self,
+        task_id: str,
+        task_type: str,
+        status: str,
+        urls: list,
+        webhook_config: Optional[Dict],
+        result: Optional[Dict] = None,
+        error: Optional[str] = None
+    ):
+        """
+        Notify webhook of job completion.
+
+        Args:
+            task_id: The task identifier
+            task_type: Type of task (e.g., "crawl", "llm_extraction")
+            status: Task status ("completed" or "failed")
+            urls: List of URLs that were crawled
+            webhook_config: Webhook configuration from the job request
+            result: Optional crawl result data
+            error: Optional error message if failed
+        """
+        # Determine webhook URL
+        webhook_url = None
+        data_in_payload = self.config.get("data_in_payload", False)
+        custom_headers = None
+
+        if webhook_config:
+            webhook_url = webhook_config.get("webhook_url")
+            data_in_payload = webhook_config.get("webhook_data_in_payload", data_in_payload)
+            custom_headers = webhook_config.get("webhook_headers")
+
+        if not webhook_url:
+            webhook_url = self.config.get("default_url")
+
+        if not webhook_url:
+            logger.debug("No webhook URL configured, skipping notification")
+            return
+
+        # Check if webhooks are enabled
+        if not self.config.get("enabled", True):
+            logger.debug("Webhooks are disabled, skipping notification")
+            return
+
+        # Build payload
+        payload = {
+            "task_id": task_id,
+            "task_type": task_type,
+            "status": status,
+            "timestamp": datetime.now(timezone.utc).isoformat(),
+            "urls": urls
+        }
+
+        if error:
+            payload["error"] = error
+
+        if data_in_payload and result:
+            payload["data"] = result
+
+        # Send webhook (fire and forget - don't block on completion)
+        await self.send_webhook(webhook_url, payload, custom_headers)

docker-compose.yml

@@ -6,15 +6,16 @@ x-base-config: &base-config
     - "11235:11235"  # Gunicorn port
   env_file:
     - .llm.env       # API keys (create from .llm.env.example)
-  environment:
-    - OPENAI_API_KEY=${OPENAI_API_KEY:-}
-    - DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY:-}
-    - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-}
-    - GROQ_API_KEY=${GROQ_API_KEY:-}
-    - TOGETHER_API_KEY=${TOGETHER_API_KEY:-}
-    - MISTRAL_API_KEY=${MISTRAL_API_KEY:-}
-    - GEMINI_API_TOKEN=${GEMINI_API_TOKEN:-}
-    - LLM_PROVIDER=${LLM_PROVIDER:-}  # Optional: Override default provider (e.g., "anthropic/claude-3-opus")
+  # Uncomment to set default environment variables (will overwrite .llm.env)
+  # environment:
+  #   - OPENAI_API_KEY=${OPENAI_API_KEY:-}
+  #   - DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY:-}
+  #   - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-}
+  #   - GROQ_API_KEY=${GROQ_API_KEY:-}
+  #   - TOGETHER_API_KEY=${TOGETHER_API_KEY:-}
+  #   - MISTRAL_API_KEY=${MISTRAL_API_KEY:-}
+  #   - GEMINI_API_KEY=${GEMINI_API_KEY:-}
+  #   - LLM_PROVIDER=${LLM_PROVIDER:-}  # Optional: Override default provider (e.g., "anthropic/claude-3-opus")
   volumes:
     - /dev/shm:/dev/shm  # Chromium performance
   deploy:

docs/blog/release-v0.7.4.md

@@ -10,7 +10,6 @@ Today I'm releasing Crawl4AI v0.7.4—the Intelligent Table Extraction & Perform
 
 - **🚀 LLMTableExtraction**: Revolutionary table extraction with intelligent chunking for massive tables
 - **⚡ Enhanced Concurrency**: True concurrency improvements for fast-completing tasks in batch operations
-- **🧹 Memory Management Refactor**: Streamlined memory utilities and better resource management
 - **🔧 Browser Manager Fixes**: Resolved race conditions in concurrent page creation
 - **⌨️ Cross-Platform Browser Profiler**: Improved keyboard handling and quit mechanisms
 - **🔗 Advanced URL Processing**: Better handling of raw URLs and base tag link resolution
@@ -158,40 +157,6 @@ async with AsyncWebCrawler() as crawler:
 - **Monitoring Systems**: Faster health checks and status page monitoring
 - **Data Aggregation**: Improved performance for real-time data collection
 
-## 🧹 Memory Management Refactor: Cleaner Architecture
-
-**The Problem:** Memory utilities were scattered and difficult to maintain, with potential import conflicts and unclear organization.
-
-**My Solution:** I consolidated all memory-related utilities into the main `utils.py` module, creating a cleaner, more maintainable architecture.
-
-### Improved Memory Handling
-
-```python
-# All memory utilities now consolidated
-from crawl4ai.utils import get_true_memory_usage_percent, MemoryMonitor
-
-# Enhanced memory monitoring
-monitor = MemoryMonitor()
-monitor.start_monitoring()
-
-async with AsyncWebCrawler() as crawler:
-    # Memory-efficient batch processing
-    results = await crawler.arun_many(large_url_list)
-    
-    # Get accurate memory metrics
-    memory_usage = get_true_memory_usage_percent()
-    memory_report = monitor.get_report()
-    
-    print(f"Memory efficiency: {memory_report['efficiency']:.1f}%")
-    print(f"Peak usage: {memory_report['peak_mb']:.1f} MB")
-```
-
-**Expected Real-World Impact:**
-- **Production Stability**: More reliable memory tracking and management
-- **Code Maintainability**: Cleaner architecture for easier debugging
-- **Import Clarity**: Resolved potential conflicts and import issues
-- **Developer Experience**: Simpler API for memory monitoring
-
 ## 🔧 Critical Stability Fixes
 
 ### Browser Manager Race Condition Resolution

docs/blog/release-v0.7.5.md

@@ -0,0 +1,318 @@
+# 🚀 Crawl4AI v0.7.5: The Docker Hooks & Security Update
+
+*September 29, 2025 • 8 min read*
+
+---
+
+Today I'm releasing Crawl4AI v0.7.5—focused on extensibility and security. This update introduces the Docker Hooks System for pipeline customization, enhanced LLM integration, and important security improvements.
+
+## 🎯 What's New at a Glance
+
+- **Docker Hooks System**: Custom Python functions at key pipeline points with function-based API
+- **Function-Based Hooks**: New `hooks_to_string()` utility with Docker client auto-conversion
+- **Enhanced LLM Integration**: Custom providers with temperature control
+- **HTTPS Preservation**: Secure internal link handling
+- **Bug Fixes**: Resolved multiple community-reported issues
+- **Improved Docker Error Handling**: Better debugging and reliability
+
+## 🔧 Docker Hooks System: Pipeline Customization
+
+Every scraping project needs custom logic—authentication, performance optimization, content processing. Traditional solutions require forking or complex workarounds. Docker Hooks let you inject custom Python functions at 8 key points in the crawling pipeline.
+
+### Real Example: Authentication & Performance
+
+```python
+import requests
+
+# Real working hooks for httpbin.org
+hooks_config = {
+    "on_page_context_created": """
+async def hook(page, context, **kwargs):
+    print("Hook: Setting up page context")
+    # Block images to speed up crawling
+    await context.route("**/*.{png,jpg,jpeg,gif,webp}", lambda route: route.abort())
+    print("Hook: Images blocked")
+    return page
+""",
+
+    "before_retrieve_html": """
+async def hook(page, context, **kwargs):
+    print("Hook: Before retrieving HTML")
+    # Scroll to bottom to load lazy content
+    await page.evaluate("window.scrollTo(0, document.body.scrollHeight)")
+    await page.wait_for_timeout(1000)
+    print("Hook: Scrolled to bottom")
+    return page
+""",
+
+    "before_goto": """
+async def hook(page, context, url, **kwargs):
+    print(f"Hook: About to navigate to {url}")
+    # Add custom headers
+    await page.set_extra_http_headers({
+        'X-Test-Header': 'crawl4ai-hooks-test'
+    })
+    return page
+"""
+}
+
+# Test with Docker API
+payload = {
+    "urls": ["https://httpbin.org/html"],
+    "hooks": {
+        "code": hooks_config,
+        "timeout": 30
+    }
+}
+
+response = requests.post("http://localhost:11235/crawl", json=payload)
+result = response.json()
+
+if result.get('success'):
+    print("✅ Hooks executed successfully!")
+    print(f"Content length: {len(result.get('markdown', ''))} characters")
+```
+
+**Available Hook Points:**
+- `on_browser_created`: Browser setup
+- `on_page_context_created`: Page context configuration
+- `before_goto`: Pre-navigation setup
+- `after_goto`: Post-navigation processing
+- `on_user_agent_updated`: User agent changes
+- `on_execution_started`: Crawl initialization
+- `before_retrieve_html`: Pre-extraction processing
+- `before_return_html`: Final HTML processing
+
+### Function-Based Hooks API
+
+Writing hooks as strings works, but lacks IDE support and type checking. v0.7.5 introduces a function-based approach with automatic conversion!
+
+**Option 1: Using the `hooks_to_string()` Utility**
+
+```python
+from crawl4ai import hooks_to_string
+import requests
+
+# Define hooks as regular Python functions (with full IDE support!)
+async def on_page_context_created(page, context, **kwargs):
+    """Block images to speed up crawling"""
+    await context.route("**/*.{png,jpg,jpeg,gif,webp}", lambda route: route.abort())
+    await page.set_viewport_size({"width": 1920, "height": 1080})
+    return page
+
+async def before_goto(page, context, url, **kwargs):
+    """Add custom headers"""
+    await page.set_extra_http_headers({
+        'X-Crawl4AI': 'v0.7.5',
+        'X-Custom-Header': 'my-value'
+    })
+    return page
+
+# Convert functions to strings
+hooks_code = hooks_to_string({
+    "on_page_context_created": on_page_context_created,
+    "before_goto": before_goto
+})
+
+# Use with REST API
+payload = {
+    "urls": ["https://httpbin.org/html"],
+    "hooks": {"code": hooks_code, "timeout": 30}
+}
+response = requests.post("http://localhost:11235/crawl", json=payload)
+```
+
+**Option 2: Docker Client with Automatic Conversion (Recommended!)**
+
+```python
+from crawl4ai.docker_client import Crawl4aiDockerClient
+
+# Define hooks as functions (same as above)
+async def on_page_context_created(page, context, **kwargs):
+    await context.route("**/*.{png,jpg,jpeg,gif,webp}", lambda route: route.abort())
+    return page
+
+async def before_retrieve_html(page, context, **kwargs):
+    # Scroll to load lazy content
+    await page.evaluate("window.scrollTo(0, document.body.scrollHeight)")
+    await page.wait_for_timeout(1000)
+    return page
+
+# Use Docker client - conversion happens automatically!
+client = Crawl4aiDockerClient(base_url="http://localhost:11235")
+
+results = await client.crawl(
+    urls=["https://httpbin.org/html"],
+    hooks={
+        "on_page_context_created": on_page_context_created,
+        "before_retrieve_html": before_retrieve_html
+    },
+    hooks_timeout=30
+)
+
+if results and results.success:
+    print(f"✅ Hooks executed! HTML length: {len(results.html)}")
+```
+
+**Benefits of Function-Based Hooks:**
+- ✅ Full IDE support (autocomplete, syntax highlighting)
+- ✅ Type checking and linting
+- ✅ Easier to test and debug
+- ✅ Reusable across projects
+- ✅ Automatic conversion in Docker client
+- ✅ No breaking changes - string hooks still work!
+
+## 🤖 Enhanced LLM Integration
+
+Enhanced LLM integration with custom providers, temperature control, and base URL configuration.
+
+### Multi-Provider Support
+
+```python
+from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
+from crawl4ai.extraction_strategy import LLMExtractionStrategy
+
+# Test with different providers
+async def test_llm_providers():
+    # OpenAI with custom temperature
+    openai_strategy = LLMExtractionStrategy(
+        provider="gemini/gemini-2.5-flash-lite",
+        api_token="your-api-token",
+        temperature=0.7,  # New in v0.7.5
+        instruction="Summarize this page in one sentence"
+    )
+
+    async with AsyncWebCrawler() as crawler:
+        result = await crawler.arun(
+            "https://example.com",
+            config=CrawlerRunConfig(extraction_strategy=openai_strategy)
+        )
+
+        if result.success:
+            print("✅ LLM extraction completed")
+            print(result.extracted_content)
+
+# Docker API with enhanced LLM config
+llm_payload = {
+    "url": "https://example.com",
+    "f": "llm",
+    "q": "Summarize this page in one sentence.",
+    "provider": "gemini/gemini-2.5-flash-lite",
+    "temperature": 0.7
+}
+
+response = requests.post("http://localhost:11235/md", json=llm_payload)
+```
+
+**New Features:**
+- Custom `temperature` parameter for creativity control
+- `base_url` for custom API endpoints
+- Multi-provider environment variable support
+- Docker API integration
+
+## 🔒 HTTPS Preservation
+
+**The Problem:** Modern web apps require HTTPS everywhere. When crawlers downgrade internal links from HTTPS to HTTP, authentication breaks and security warnings appear.
+
+**Solution:** HTTPS preservation maintains secure protocols throughout crawling.
+
+```python
+from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, FilterChain, URLPatternFilter, BFSDeepCrawlStrategy
+
+async def test_https_preservation():
+    # Enable HTTPS preservation
+    url_filter = URLPatternFilter(
+        patterns=["^(https:\/\/)?quotes\.toscrape\.com(\/.*)?$"]
+    )
+
+    config = CrawlerRunConfig(
+        exclude_external_links=True,
+        preserve_https_for_internal_links=True,  # New in v0.7.5
+        deep_crawl_strategy=BFSDeepCrawlStrategy(
+            max_depth=2,
+            max_pages=5,
+            filter_chain=FilterChain([url_filter])
+        )
+    )
+
+    async with AsyncWebCrawler() as crawler:
+        async for result in await crawler.arun(
+            url="https://quotes.toscrape.com",
+            config=config
+        ):
+            # All internal links maintain HTTPS
+            internal_links = [link['href'] for link in result.links['internal']]
+            https_links = [link for link in internal_links if link.startswith('https://')]
+
+            print(f"HTTPS links preserved: {len(https_links)}/{len(internal_links)}")
+            for link in https_links[:3]:
+                print(f"  → {link}")
+```
+
+## 🛠️ Bug Fixes and Improvements
+
+### Major Fixes
+- **URL Processing**: Fixed '+' sign preservation in query parameters (#1332)
+- **Proxy Configuration**: Enhanced proxy string parsing (old `proxy` parameter deprecated)
+- **Docker Error Handling**: Comprehensive error messages with status codes
+- **Memory Management**: Fixed leaks in long-running sessions
+- **JWT Authentication**: Fixed Docker JWT validation issues (#1442)
+- **Playwright Stealth**: Fixed stealth features for Playwright integration (#1481)
+- **API Configuration**: Fixed config handling to prevent overriding user-provided settings (#1505)
+- **Docker Filter Serialization**: Resolved JSON encoding errors in deep crawl strategy (#1419)
+- **LLM Provider Support**: Fixed custom LLM provider integration for adaptive crawler (#1291)
+- **Performance Issues**: Resolved backoff strategy failures and timeout handling (#989)
+
+### Community-Reported Issues Fixed
+This release addresses multiple issues reported by the community through GitHub issues and Discord discussions:
+- Fixed browser configuration reference errors
+- Resolved dependency conflicts with cssselect
+- Improved error messaging for failed authentications
+- Enhanced compatibility with various proxy configurations
+- Fixed edge cases in URL normalization
+
+### Configuration Updates
+```python
+# Old proxy config (deprecated)
+# browser_config = BrowserConfig(proxy="http://proxy:8080")
+
+# New enhanced proxy config
+browser_config = BrowserConfig(
+    proxy_config={
+        "server": "http://proxy:8080",
+        "username": "optional-user",
+        "password": "optional-pass"
+    }
+)
+```
+
+## 🔄 Breaking Changes
+
+1. **Python 3.10+ Required**: Upgrade from Python 3.9
+2. **Proxy Parameter Deprecated**: Use new `proxy_config` structure
+3. **New Dependency**: Added `cssselect` for better CSS handling
+
+## 🚀 Get Started
+
+```bash
+# Install latest version
+pip install crawl4ai==0.7.5
+
+# Docker deployment
+docker pull unclecode/crawl4ai:latest
+docker run -p 11235:11235 unclecode/crawl4ai:latest
+```
+
+**Try the Demo:**
+```bash
+# Run working examples
+python docs/releases_review/demo_v0.7.5.py
+```
+
+**Resources:**
+- 📖 Documentation: [docs.crawl4ai.com](https://docs.crawl4ai.com)
+- 🐙 GitHub: [github.com/unclecode/crawl4ai](https://github.com/unclecode/crawl4ai)
+- 💬 Discord: [discord.gg/crawl4ai](https://discord.gg/jP8KfhDhyN)
+- 🐦 Twitter: [@unclecode](https://x.com/unclecode)
+
+Happy crawling! 🕷️

docs/blog/release-v0.7.6.md

@@ -0,0 +1,314 @@
+# Crawl4AI v0.7.6 Release Notes
+
+*Release Date: October 22, 2025*
+
+I'm excited to announce Crawl4AI v0.7.6, featuring a complete webhook infrastructure for the Docker job queue API! This release eliminates polling and brings real-time notifications to both crawling and LLM extraction workflows.
+
+## 🎯 What's New
+
+### Webhook Support for Docker Job Queue API
+
+The headline feature of v0.7.6 is comprehensive webhook support for asynchronous job processing. No more constant polling to check if your jobs are done - get instant notifications when they complete!
+
+**Key Capabilities:**
+
+- ✅ **Universal Webhook Support**: Both `/crawl/job` and `/llm/job` endpoints now support webhooks
+- ✅ **Flexible Delivery Modes**: Choose notification-only or include full data in the webhook payload
+- ✅ **Reliable Delivery**: Exponential backoff retry mechanism (5 attempts: 1s → 2s → 4s → 8s → 16s)
+- ✅ **Custom Authentication**: Add custom headers for webhook authentication
+- ✅ **Global Configuration**: Set default webhook URL in `config.yml` for all jobs
+- ✅ **Task Type Identification**: Distinguish between `crawl` and `llm_extraction` tasks
+
+### How It Works
+
+Instead of constantly checking job status:
+
+**OLD WAY (Polling):**
+```python
+# Submit job
+response = requests.post("http://localhost:11235/crawl/job", json=payload)
+task_id = response.json()['task_id']
+
+# Poll until complete
+while True:
+    status = requests.get(f"http://localhost:11235/crawl/job/{task_id}")
+    if status.json()['status'] == 'completed':
+        break
+    time.sleep(5)  # Wait and try again
+```
+
+**NEW WAY (Webhooks):**
+```python
+# Submit job with webhook
+payload = {
+    "urls": ["https://example.com"],
+    "webhook_config": {
+        "webhook_url": "https://myapp.com/webhook",
+        "webhook_data_in_payload": True
+    }
+}
+response = requests.post("http://localhost:11235/crawl/job", json=payload)
+
+# Done! Webhook will notify you when complete
+# Your webhook handler receives the results automatically
+```
+
+### Crawl Job Webhooks
+
+```bash
+curl -X POST http://localhost:11235/crawl/job \
+  -H "Content-Type: application/json" \
+  -d '{
+    "urls": ["https://example.com"],
+    "browser_config": {"headless": true},
+    "crawler_config": {"cache_mode": "bypass"},
+    "webhook_config": {
+      "webhook_url": "https://myapp.com/webhooks/crawl-complete",
+      "webhook_data_in_payload": false,
+      "webhook_headers": {
+        "X-Webhook-Secret": "your-secret-token"
+      }
+    }
+  }'
+```
+
+### LLM Extraction Job Webhooks (NEW!)
+
+```bash
+curl -X POST http://localhost:11235/llm/job \
+  -H "Content-Type: application/json" \
+  -d '{
+    "url": "https://example.com/article",
+    "q": "Extract the article title, author, and publication date",
+    "schema": "{\"type\":\"object\",\"properties\":{\"title\":{\"type\":\"string\"}}}",
+    "provider": "openai/gpt-4o-mini",
+    "webhook_config": {
+      "webhook_url": "https://myapp.com/webhooks/llm-complete",
+      "webhook_data_in_payload": true
+    }
+  }'
+```
+
+### Webhook Payload Structure
+
+**Success (with data):**
+```json
+{
+  "task_id": "llm_1698765432",
+  "task_type": "llm_extraction",
+  "status": "completed",
+  "timestamp": "2025-10-22T10:30:00.000000+00:00",
+  "urls": ["https://example.com/article"],
+  "data": {
+    "extracted_content": {
+      "title": "Understanding Web Scraping",
+      "author": "John Doe",
+      "date": "2025-10-22"
+    }
+  }
+}
+```
+
+**Failure:**
+```json
+{
+  "task_id": "crawl_abc123",
+  "task_type": "crawl",
+  "status": "failed",
+  "timestamp": "2025-10-22T10:30:00.000000+00:00",
+  "urls": ["https://example.com"],
+  "error": "Connection timeout after 30s"
+}
+```
+
+### Simple Webhook Handler Example
+
+```python
+from flask import Flask, request, jsonify
+
+app = Flask(__name__)
+
+@app.route('/webhook', methods=['POST'])
+def handle_webhook():
+    payload = request.json
+
+    task_id = payload['task_id']
+    task_type = payload['task_type']
+    status = payload['status']
+
+    if status == 'completed':
+        if 'data' in payload:
+            # Process data directly
+            data = payload['data']
+        else:
+            # Fetch from API
+            endpoint = 'crawl' if task_type == 'crawl' else 'llm'
+            response = requests.get(f'http://localhost:11235/{endpoint}/job/{task_id}')
+            data = response.json()
+
+        # Your business logic here
+        print(f"Job {task_id} completed!")
+
+    elif status == 'failed':
+        error = payload.get('error', 'Unknown error')
+        print(f"Job {task_id} failed: {error}")
+
+    return jsonify({"status": "received"}), 200
+
+app.run(port=8080)
+```
+
+## 📊 Performance Improvements
+
+- **Reduced Server Load**: Eliminates constant polling requests
+- **Lower Latency**: Instant notification vs. polling interval delay
+- **Better Resource Usage**: Frees up client connections while jobs run in background
+- **Scalable Architecture**: Handles high-volume crawling workflows efficiently
+
+## 🐛 Bug Fixes
+
+- Fixed webhook configuration serialization for Pydantic HttpUrl fields
+- Improved error handling in webhook delivery service
+- Enhanced Redis task storage for webhook config persistence
+
+## 🌍 Expected Real-World Impact
+
+### For Web Scraping Workflows
+- **Reduced Costs**: Less API calls = lower bandwidth and server costs
+- **Better UX**: Instant notifications improve user experience
+- **Scalability**: Handle 100s of concurrent jobs without polling overhead
+
+### For LLM Extraction Pipelines
+- **Async Processing**: Submit LLM extraction jobs and move on
+- **Batch Processing**: Queue multiple extractions, get notified as they complete
+- **Integration**: Easy integration with workflow automation tools (Zapier, n8n, etc.)
+
+### For Microservices
+- **Event-Driven**: Perfect for event-driven microservice architectures
+- **Decoupling**: Decouple job submission from result processing
+- **Reliability**: Automatic retries ensure webhooks are delivered
+
+## 🔄 Breaking Changes
+
+**None!** This release is fully backward compatible.
+
+- Webhook configuration is optional
+- Existing code continues to work without modification
+- Polling is still supported for jobs without webhook config
+
+## 📚 Documentation
+
+### New Documentation
+- **[WEBHOOK_EXAMPLES.md](../deploy/docker/WEBHOOK_EXAMPLES.md)** - Comprehensive webhook usage guide
+- **[docker_webhook_example.py](../docs/examples/docker_webhook_example.py)** - Working code examples
+
+### Updated Documentation
+- **[Docker README](../deploy/docker/README.md)** - Added webhook sections
+- API documentation with webhook examples
+
+## 🛠️ Migration Guide
+
+No migration needed! Webhooks are opt-in:
+
+1. **To use webhooks**: Add `webhook_config` to your job payload
+2. **To keep polling**: Continue using your existing code
+
+### Quick Start
+
+```python
+# Just add webhook_config to your existing payload
+payload = {
+    # Your existing configuration
+    "urls": ["https://example.com"],
+    "browser_config": {...},
+    "crawler_config": {...},
+
+    # NEW: Add webhook configuration
+    "webhook_config": {
+        "webhook_url": "https://myapp.com/webhook",
+        "webhook_data_in_payload": True
+    }
+}
+```
+
+## 🔧 Configuration
+
+### Global Webhook Configuration (config.yml)
+
+```yaml
+webhooks:
+  enabled: true
+  default_url: "https://myapp.com/webhooks/default"  # Optional
+  data_in_payload: false
+  retry:
+    max_attempts: 5
+    initial_delay_ms: 1000
+    max_delay_ms: 32000
+    timeout_ms: 30000
+  headers:
+    User-Agent: "Crawl4AI-Webhook/1.0"
+```
+
+## 🚀 Upgrade Instructions
+
+### Docker
+
+```bash
+# Pull the latest image
+docker pull unclecode/crawl4ai:0.7.6
+
+# Or use latest tag
+docker pull unclecode/crawl4ai:latest
+
+# Run with webhook support
+docker run -d \
+  -p 11235:11235 \
+  --env-file .llm.env \
+  --name crawl4ai \
+  unclecode/crawl4ai:0.7.6
+```
+
+### Python Package
+
+```bash
+pip install --upgrade crawl4ai
+```
+
+## 💡 Pro Tips
+
+1. **Use notification-only mode** for large results - fetch data separately to avoid large webhook payloads
+2. **Set custom headers** for webhook authentication and request tracking
+3. **Configure global default webhook** for consistent handling across all jobs
+4. **Implement idempotent webhook handlers** - same webhook may be delivered multiple times on retry
+5. **Use structured schemas** with LLM extraction for predictable webhook data
+
+## 🎬 Demo
+
+Try the release demo:
+
+```bash
+python docs/releases_review/demo_v0.7.6.py
+```
+
+This comprehensive demo showcases:
+- Crawl job webhooks (notification-only and with data)
+- LLM extraction webhooks (with JSON schema support)
+- Custom headers for authentication
+- Webhook retry mechanism
+- Real-time webhook receiver
+
+## 🙏 Acknowledgments
+
+Thank you to the community for the feedback that shaped this feature! Special thanks to everyone who requested webhook support for asynchronous job processing.
+
+## 📞 Support
+
+- **Documentation**: https://docs.crawl4ai.com
+- **GitHub Issues**: https://github.com/unclecode/crawl4ai/issues
+- **Discord**: https://discord.gg/crawl4ai
+
+---
+
+**Happy crawling with webhooks!** 🕷️🪝
+
+*- unclecode*

docs/blog/release-v0.7.7.md

@@ -0,0 +1,626 @@
+# 🚀 Crawl4AI v0.7.7: The Self-Hosting & Monitoring Update
+
+*November 14, 2025 • 10 min read*
+
+---
+
+Today I'm releasing Crawl4AI v0.7.7—the Self-Hosting & Monitoring Update. This release transforms Crawl4AI Docker from a simple containerized crawler into a complete self-hosting platform with enterprise-grade real-time monitoring, full operational transparency, and production-ready observability.
+
+## 🎯 What's New at a Glance
+
+- **📊 Real-time Monitoring Dashboard**: Interactive web UI with live system metrics and browser pool status
+- **🔌 Comprehensive Monitor API**: Complete REST API for programmatic access to all monitoring data
+- **⚡ WebSocket Streaming**: Real-time updates every 2 seconds for custom dashboards
+- **🎮 Control Actions**: Manual browser management (kill, restart, cleanup)
+- **🔥 Smart Browser Pool**: 3-tier architecture (permanent/hot/cold) with automatic promotion
+- **🧹 Janitor Cleanup System**: Automatic resource management with event logging
+- **📈 Production Metrics**: 6 critical metrics for operational excellence
+- **🏭 Integration Ready**: Prometheus, alerting, and log aggregation examples
+- **🐛 Critical Bug Fixes**: Async LLM extraction, DFS crawling, viewport config, and more
+
+## 📊 Real-time Monitoring Dashboard: Complete Visibility
+
+**The Problem:** Running Crawl4AI in Docker was like flying blind. Users had no visibility into what was happening inside the container—memory usage, active requests, browser pools, or errors. Troubleshooting required checking logs, and there was no way to monitor performance or manually intervene when issues occurred.
+
+**My Solution:** I built a complete real-time monitoring system with an interactive dashboard, comprehensive REST API, WebSocket streaming, and manual control actions. Now you have full transparency and control over your crawling infrastructure.
+
+### The Self-Hosting Value Proposition
+
+Before v0.7.7, Docker was just a containerized crawler. After v0.7.7, it's a complete self-hosting platform that gives you:
+
+- **🔒 Data Privacy**: Your data never leaves your infrastructure
+- **💰 Cost Control**: No per-request pricing or rate limits
+- **🎯 Full Customization**: Complete control over configurations and strategies
+- **📊 Complete Transparency**: Real-time visibility into every aspect
+- **⚡ Performance**: Direct access without network overhead
+- **🛡️ Enterprise Security**: Keep workflows behind your firewall
+
+### Interactive Monitoring Dashboard
+
+Access the dashboard at `http://localhost:11235/dashboard` to see:
+
+- **System Health Overview**: CPU, memory, network, and uptime in real-time
+- **Live Request Tracking**: Active and completed requests with full details
+- **Browser Pool Management**: Interactive table with permanent/hot/cold browsers
+- **Janitor Events Log**: Automatic cleanup activities
+- **Error Monitoring**: Full context error logs
+
+The dashboard updates every 2 seconds via WebSocket, giving you live visibility into your crawling operations.
+
+## 🔌 Monitor API: Programmatic Access
+
+**The Problem:** Monitoring dashboards are great for humans, but automation and integration require programmatic access.
+
+**My Solution:** A comprehensive REST API that exposes all monitoring data for integration with your existing infrastructure.
+
+### System Health Endpoint
+
+```python
+import httpx
+import asyncio
+
+async def monitor_system_health():
+    async with httpx.AsyncClient() as client:
+        response = await client.get("http://localhost:11235/monitor/health")
+        health = response.json()
+
+        print(f"Container Metrics:")
+        print(f"  CPU: {health['container']['cpu_percent']:.1f}%")
+        print(f"  Memory: {health['container']['memory_percent']:.1f}%")
+        print(f"  Uptime: {health['container']['uptime_seconds']}s")
+
+        print(f"\nBrowser Pool:")
+        print(f"  Permanent: {health['pool']['permanent']['active']} active")
+        print(f"  Hot Pool: {health['pool']['hot']['count']} browsers")
+        print(f"  Cold Pool: {health['pool']['cold']['count']} browsers")
+
+        print(f"\nStatistics:")
+        print(f"  Total Requests: {health['stats']['total_requests']}")
+        print(f"  Success Rate: {health['stats']['success_rate_percent']:.1f}%")
+        print(f"  Avg Latency: {health['stats']['avg_latency_ms']:.0f}ms")
+
+asyncio.run(monitor_system_health())
+```
+
+### Request Tracking
+
+```python
+async def track_requests():
+    async with httpx.AsyncClient() as client:
+        response = await client.get("http://localhost:11235/monitor/requests")
+        requests_data = response.json()
+
+        print(f"Active Requests: {len(requests_data['active'])}")
+        print(f"Completed Requests: {len(requests_data['completed'])}")
+
+        # See details of recent requests
+        for req in requests_data['completed'][:5]:
+            status_icon = "✅" if req['success'] else "❌"
+            print(f"{status_icon} {req['endpoint']} - {req['latency_ms']:.0f}ms")
+```
+
+### Browser Pool Management
+
+```python
+async def monitor_browser_pool():
+    async with httpx.AsyncClient() as client:
+        response = await client.get("http://localhost:11235/monitor/browsers")
+        browsers = response.json()
+
+        print(f"Pool Summary:")
+        print(f"  Total Browsers: {browsers['summary']['total_count']}")
+        print(f"  Total Memory: {browsers['summary']['total_memory_mb']} MB")
+        print(f"  Reuse Rate: {browsers['summary']['reuse_rate_percent']:.1f}%")
+
+        # List all browsers
+        for browser in browsers['permanent']:
+            print(f"🔥 Permanent: {browser['browser_id'][:8]}... | "
+                  f"Requests: {browser['request_count']} | "
+                  f"Memory: {browser['memory_mb']:.0f} MB")
+```
+
+### Endpoint Performance Statistics
+
+```python
+async def get_endpoint_stats():
+    async with httpx.AsyncClient() as client:
+        response = await client.get("http://localhost:11235/monitor/endpoints/stats")
+        stats = response.json()
+
+        print("Endpoint Analytics:")
+        for endpoint, data in stats.items():
+            print(f"  {endpoint}:")
+            print(f"    Requests: {data['count']}")
+            print(f"    Avg Latency: {data['avg_latency_ms']:.0f}ms")
+            print(f"    Success Rate: {data['success_rate_percent']:.1f}%")
+```
+
+### Complete API Reference
+
+The Monitor API includes these endpoints:
+
+- `GET /monitor/health` - System health with pool statistics
+- `GET /monitor/requests` - Active and completed request tracking
+- `GET /monitor/browsers` - Browser pool details and efficiency
+- `GET /monitor/endpoints/stats` - Per-endpoint performance analytics
+- `GET /monitor/timeline?minutes=5` - Time-series data for charts
+- `GET /monitor/logs/janitor?limit=10` - Cleanup activity logs
+- `GET /monitor/logs/errors?limit=10` - Error logs with context
+- `POST /monitor/actions/cleanup` - Force immediate cleanup
+- `POST /monitor/actions/kill_browser` - Kill specific browser
+- `POST /monitor/actions/restart_browser` - Restart browser
+- `POST /monitor/stats/reset` - Reset accumulated statistics
+
+## ⚡ WebSocket Streaming: Real-time Updates
+
+**The Problem:** Polling the API every few seconds wastes resources and adds latency. Real-time dashboards need instant updates.
+
+**My Solution:** WebSocket streaming with 2-second update intervals for building custom real-time dashboards.
+
+### WebSocket Integration Example
+
+```python
+import websockets
+import json
+import asyncio
+
+async def monitor_realtime():
+    uri = "ws://localhost:11235/monitor/ws"
+
+    async with websockets.connect(uri) as websocket:
+        print("Connected to real-time monitoring stream")
+
+        while True:
+            # Receive update every 2 seconds
+            data = await websocket.recv()
+            update = json.loads(data)
+
+            # Access all monitoring data
+            print(f"\n--- Update at {update['timestamp']} ---")
+            print(f"Memory: {update['health']['container']['memory_percent']:.1f}%")
+            print(f"Active Requests: {len(update['requests']['active'])}")
+            print(f"Total Browsers: {update['browsers']['summary']['total_count']}")
+
+            if update['errors']:
+                print(f"⚠️  Recent Errors: {len(update['errors'])}")
+
+asyncio.run(monitor_realtime())
+```
+
+**Expected Real-World Impact:**
+- **Custom Dashboards**: Build tailored monitoring UIs for your team
+- **Real-time Alerting**: Trigger alerts instantly when metrics exceed thresholds
+- **Integration**: Feed live data into monitoring tools like Grafana
+- **Automation**: React to events in real-time without polling
+
+## 🔥 Smart Browser Pool: 3-Tier Architecture
+
+**The Problem:** Creating a new browser for every request is slow and memory-intensive. Traditional browser pools are static and inefficient.
+
+**My Solution:** A smart 3-tier browser pool that automatically adapts to usage patterns.
+
+### How It Works
+
+```python
+import httpx
+
+async def demonstrate_browser_pool():
+    async with httpx.AsyncClient() as client:
+        # Request 1-3: Default config → Uses permanent browser
+        print("Phase 1: Using permanent browser")
+        for i in range(3):
+            await client.post(
+                "http://localhost:11235/crawl",
+                json={"urls": [f"https://httpbin.org/html?req={i}"]}
+            )
+            print(f"  Request {i+1}: Reused permanent browser")
+
+        # Request 4-6: Custom viewport → Cold pool (first use)
+        print("\nPhase 2: Custom config creates cold pool browser")
+        viewport_config = {"viewport": {"width": 1280, "height": 720}}
+        for i in range(4):
+            await client.post(
+                "http://localhost:11235/crawl",
+                json={
+                    "urls": [f"https://httpbin.org/json?v={i}"],
+                    "browser_config": viewport_config
+                }
+            )
+            if i < 2:
+                print(f"  Request {i+1}: Cold pool browser")
+            else:
+                print(f"  Request {i+1}: Promoted to hot pool! (after 3 uses)")
+
+        # Check pool status
+        response = await client.get("http://localhost:11235/monitor/browsers")
+        browsers = response.json()
+
+        print(f"\nPool Status:")
+        print(f"  Permanent: {len(browsers['permanent'])} (always active)")
+        print(f"  Hot: {len(browsers['hot'])} (frequently used configs)")
+        print(f"  Cold: {len(browsers['cold'])} (on-demand)")
+        print(f"  Reuse Rate: {browsers['summary']['reuse_rate_percent']:.1f}%")
+
+asyncio.run(demonstrate_browser_pool())
+```
+
+**Pool Tiers:**
+
+- **🔥 Permanent Browser**: Always-on, default configuration, instant response
+- **♨️ Hot Pool**: Browsers promoted after 3+ uses, kept warm for quick access
+- **❄️ Cold Pool**: On-demand browsers for variant configs, cleaned up when idle
+
+**Expected Real-World Impact:**
+- **Memory Efficiency**: 10x reduction in memory usage vs creating browsers per request
+- **Performance**: Instant access to frequently-used configurations
+- **Automatic Optimization**: Pool adapts to your usage patterns
+- **Resource Management**: Janitor automatically cleans up idle browsers
+
+## 🧹 Janitor System: Automatic Cleanup
+
+**The Problem:** Long-running crawlers accumulate idle browsers and consume memory over time.
+
+**My Solution:** An automatic janitor system that monitors and cleans up idle resources.
+
+```python
+async def monitor_janitor_activity():
+    async with httpx.AsyncClient() as client:
+        response = await client.get("http://localhost:11235/monitor/logs/janitor?limit=5")
+        logs = response.json()
+
+        print("Recent Cleanup Activities:")
+        for log in logs:
+            print(f"  {log['timestamp']}: {log['message']}")
+
+# Example output:
+# 2025-11-14 10:30:00: Cleaned up 2 cold pool browsers (idle > 5min)
+# 2025-11-14 10:25:00: Browser reuse rate: 85.3%
+# 2025-11-14 10:20:00: Hot pool browser promoted (10 requests)
+```
+
+## 🎮 Control Actions: Manual Management
+
+**The Problem:** Sometimes you need to manually intervene—kill a stuck browser, force cleanup, or restart resources.
+
+**My Solution:** Manual control actions via the API for operational troubleshooting.
+
+### Force Cleanup
+
+```python
+async def force_cleanup():
+    async with httpx.AsyncClient() as client:
+        response = await client.post("http://localhost:11235/monitor/actions/cleanup")
+        result = response.json()
+
+        print(f"Cleanup completed:")
+        print(f"  Browsers cleaned: {result.get('cleaned_count', 0)}")
+        print(f"  Memory freed: {result.get('memory_freed_mb', 0):.1f} MB")
+```
+
+### Kill Specific Browser
+
+```python
+async def kill_stuck_browser(browser_id: str):
+    async with httpx.AsyncClient() as client:
+        response = await client.post(
+            "http://localhost:11235/monitor/actions/kill_browser",
+            json={"browser_id": browser_id}
+        )
+
+        if response.status_code == 200:
+            print(f"✅ Browser {browser_id} killed successfully")
+```
+
+### Reset Statistics
+
+```python
+async def reset_stats():
+    async with httpx.AsyncClient() as client:
+        response = await client.post("http://localhost:11235/monitor/stats/reset")
+        print("📊 Statistics reset for fresh monitoring")
+```
+
+## 📈 Production Integration Patterns
+
+### Prometheus Integration
+
+```python
+# Export metrics for Prometheus scraping
+async def export_prometheus_metrics():
+    async with httpx.AsyncClient() as client:
+        health = await client.get("http://localhost:11235/monitor/health")
+        data = health.json()
+
+        # Export in Prometheus format
+        metrics = f"""
+# HELP crawl4ai_memory_usage_percent Memory usage percentage
+# TYPE crawl4ai_memory_usage_percent gauge
+crawl4ai_memory_usage_percent {data['container']['memory_percent']}
+
+# HELP crawl4ai_request_success_rate Request success rate
+# TYPE crawl4ai_request_success_rate gauge
+crawl4ai_request_success_rate {data['stats']['success_rate_percent']}
+
+# HELP crawl4ai_browser_pool_count Total browsers in pool
+# TYPE crawl4ai_browser_pool_count gauge
+crawl4ai_browser_pool_count {data['pool']['permanent']['active'] + data['pool']['hot']['count'] + data['pool']['cold']['count']}
+"""
+        return metrics
+```
+
+### Alerting Example
+
+```python
+async def check_alerts():
+    async with httpx.AsyncClient() as client:
+        health = await client.get("http://localhost:11235/monitor/health")
+        data = health.json()
+
+        # Memory alert
+        if data['container']['memory_percent'] > 80:
+            print("🚨 ALERT: Memory usage above 80%")
+            # Trigger cleanup
+            await client.post("http://localhost:11235/monitor/actions/cleanup")
+
+        # Success rate alert
+        if data['stats']['success_rate_percent'] < 90:
+            print("🚨 ALERT: Success rate below 90%")
+            # Check error logs
+            errors = await client.get("http://localhost:11235/monitor/logs/errors")
+            print(f"Recent errors: {len(errors.json())}")
+
+        # Latency alert
+        if data['stats']['avg_latency_ms'] > 5000:
+            print("🚨 ALERT: Average latency above 5s")
+```
+
+### Key Metrics to Track
+
+```python
+CRITICAL_METRICS = {
+    "memory_usage": {
+        "current": "container.memory_percent",
+        "target": "<80%",
+        "alert_threshold": ">80%",
+        "action": "Force cleanup or scale"
+    },
+    "success_rate": {
+        "current": "stats.success_rate_percent",
+        "target": ">95%",
+        "alert_threshold": "<90%",
+        "action": "Check error logs"
+    },
+    "avg_latency": {
+        "current": "stats.avg_latency_ms",
+        "target": "<2000ms",
+        "alert_threshold": ">5000ms",
+        "action": "Investigate slow requests"
+    },
+    "browser_reuse_rate": {
+        "current": "browsers.summary.reuse_rate_percent",
+        "target": ">80%",
+        "alert_threshold": "<60%",
+        "action": "Check pool configuration"
+    },
+    "total_browsers": {
+        "current": "browsers.summary.total_count",
+        "target": "<15",
+        "alert_threshold": ">20",
+        "action": "Check for browser leaks"
+    },
+    "error_frequency": {
+        "current": "len(errors)",
+        "target": "<5/hour",
+        "alert_threshold": ">10/hour",
+        "action": "Review error patterns"
+    }
+}
+```
+
+## 🐛 Critical Bug Fixes
+
+This release includes significant bug fixes that improve stability and performance:
+
+### Async LLM Extraction (#1590)
+
+**The Problem:** LLM extraction was blocking async execution, causing URLs to be processed sequentially instead of in parallel (issue #1055).
+
+**The Fix:** Resolved the blocking issue to enable true parallel processing for LLM extraction.
+
+```python
+# Before v0.7.7: Sequential processing
+# After v0.7.7: True parallel processing
+
+async with AsyncWebCrawler() as crawler:
+    urls = ["url1", "url2", "url3", "url4"]
+
+    # Now processes truly in parallel with LLM extraction
+    results = await crawler.arun_many(
+        urls,
+        config=CrawlerRunConfig(
+            extraction_strategy=LLMExtractionStrategy(...)
+        )
+    )
+    # 4x faster for parallel LLM extraction!
+```
+
+**Expected Impact:** Major performance improvement for batch LLM extraction workflows.
+
+### DFS Deep Crawling (#1607)
+
+**The Problem:** DFS (Depth-First Search) deep crawl strategy had implementation issues.
+
+**The Fix:** Enhanced DFSDeepCrawlStrategy with proper seen URL tracking and improved documentation.
+
+### Browser & Crawler Config Documentation (#1609)
+
+**The Problem:** Documentation didn't match the actual `async_configs.py` implementation.
+
+**The Fix:** Updated all configuration documentation to accurately reflect the current implementation.
+
+### Sitemap Seeder (#1598)
+
+**The Problem:** Sitemap parsing and URL normalization issues in AsyncUrlSeeder (issue #1559).
+
+**The Fix:** Added comprehensive tests and fixes for sitemap namespace parsing and URL normalization.
+
+### Remove Overlay Elements (#1529)
+
+**The Problem:** The `remove_overlay_elements` functionality wasn't working (issue #1396).
+
+**The Fix:** Fixed by properly calling the injected JavaScript function.
+
+### Viewport Configuration (#1495)
+
+**The Problem:** Viewport configuration wasn't working in managed browsers (issue #1490).
+
+**The Fix:** Added proper viewport size configuration support for browser launch.
+
+### Managed Browser CDP Timing (#1528)
+
+**The Problem:** CDP (Chrome DevTools Protocol) endpoint verification had timing issues causing connection failures (issue #1445).
+
+**The Fix:** Added exponential backoff for CDP endpoint verification to handle timing variations.
+
+### Security Updates
+
+- **pyOpenSSL**: Updated from >=24.3.0 to >=25.3.0 to address security vulnerability
+- Added verification tests for the security update
+
+### Docker Fixes
+
+- **Port Standardization**: Fixed inconsistent port usage (11234 vs 11235) - now standardized to 11235
+- **LLM Environment**: Fixed LLM API key handling for multi-provider support (PR #1537)
+- **Error Handling**: Improved Docker API error messages with comprehensive status codes
+- **Serialization**: Fixed `fit_html` property serialization in `/crawl` and `/crawl/stream` endpoints
+
+### Other Important Fixes
+
+- **arun_many Returns**: Fixed function to always return a list, even on exception (PR #1530)
+- **Webhook Serialization**: Properly serialize Pydantic HttpUrl in webhook config
+- **LLMConfig Documentation**: Fixed casing and variable name consistency (issue #1551)
+- **Python Version**: Dropped Python 3.9 support, now requires Python >=3.10
+
+## 📊 Expected Real-World Impact
+
+### For DevOps & Infrastructure Teams
+- **Full Visibility**: Know exactly what's happening inside your crawling infrastructure
+- **Proactive Monitoring**: Catch issues before they become problems
+- **Resource Optimization**: Identify memory leaks and performance bottlenecks
+- **Operational Control**: Manual intervention when automated systems need help
+
+### For Production Deployments
+- **Enterprise Observability**: Prometheus, Grafana, and alerting integration
+- **Debugging**: Real-time logs and error tracking
+- **Capacity Planning**: Historical metrics for scaling decisions
+- **SLA Monitoring**: Track success rates and latency against targets
+
+### For Development Teams
+- **Local Monitoring**: Understand crawler behavior during development
+- **Performance Testing**: Measure impact of configuration changes
+- **Troubleshooting**: Quickly identify and fix issues
+- **Learning**: See exactly how the browser pool works
+
+## 🔄 Breaking Changes
+
+**None!** This release is fully backward compatible.
+
+- All existing Docker configurations continue to work
+- No API changes to existing endpoints
+- Monitoring is additive functionality
+- No migration required
+
+## 🚀 Upgrade Instructions
+
+### Docker
+
+```bash
+# Pull the latest version
+docker pull unclecode/crawl4ai:0.7.7
+
+# Or use the latest tag
+docker pull unclecode/crawl4ai:latest
+
+# Run with monitoring enabled (default)
+docker run -d \
+  -p 11235:11235 \
+  --shm-size=1g \
+  --name crawl4ai \
+  unclecode/crawl4ai:0.7.7
+
+# Access the monitoring dashboard
+open http://localhost:11235/dashboard
+```
+
+### Python Package
+
+```bash
+# Upgrade to latest version
+pip install --upgrade crawl4ai
+
+# Or install specific version
+pip install crawl4ai==0.7.7
+```
+
+## 🎬 Try the Demo
+
+Run the comprehensive demo that showcases all monitoring features:
+
+```bash
+python docs/releases_review/demo_v0.7.7.py
+```
+
+**The demo includes:**
+1. System health overview with live metrics
+2. Request tracking with active/completed monitoring
+3. Browser pool management (permanent/hot/cold)
+4. Complete Monitor API endpoint examples
+5. WebSocket streaming demonstration
+6. Control actions (cleanup, kill, restart)
+7. Production metrics and alerting patterns
+8. Self-hosting value proposition
+
+## 📚 Documentation
+
+### New Documentation
+- **[Self-Hosting Guide](https://docs.crawl4ai.com/core/self-hosting/)** - Complete self-hosting documentation with monitoring
+- **Demo Script**: `docs/releases_review/demo_v0.7.7.py` - Working examples
+
+### Updated Documentation
+- **Docker Deployment** → **Self-Hosting** (renamed for better positioning)
+- Added comprehensive monitoring sections
+- Production integration patterns
+- WebSocket streaming examples
+
+## 💡 Pro Tips
+
+1. **Start with the dashboard** - Visit `/dashboard` to get familiar with the monitoring system
+2. **Track the 6 key metrics** - Memory, success rate, latency, reuse rate, browser count, errors
+3. **Set up alerting early** - Use the Monitor API to build alerts before issues occur
+4. **Monitor browser pool efficiency** - Aim for >80% reuse rate for optimal performance
+5. **Use WebSocket for custom dashboards** - Build tailored monitoring UIs for your team
+6. **Leverage Prometheus integration** - Export metrics for long-term storage and analysis
+7. **Check janitor logs** - Understand automatic cleanup patterns
+8. **Use control actions judiciously** - Manual interventions are for exceptional cases
+
+## 🙏 Acknowledgments
+
+Thank you to our community for the feedback, bug reports, and feature requests that shaped this release. Special thanks to everyone who contributed to the issues that were fixed in this version.
+
+The monitoring system was built based on real user needs for production deployments, and your input made it comprehensive and practical.
+
+## 📞 Support & Resources
+
+- **📖 Documentation**: [docs.crawl4ai.com](https://docs.crawl4ai.com)
+- **🐙 GitHub**: [github.com/unclecode/crawl4ai](https://github.com/unclecode/crawl4ai)
+- **💬 Discord**: [discord.gg/crawl4ai](https://discord.gg/jP8KfhDhyN)
+- **🐦 Twitter**: [@unclecode](https://x.com/unclecode)
+- **📊 Dashboard**: `http://localhost:11235/dashboard` (when running)
+
+---
+
+**Crawl4AI v0.7.7 delivers complete self-hosting with enterprise-grade monitoring. You now have full visibility and control over your web crawling infrastructure. The monitoring dashboard, comprehensive API, and WebSocket streaming give you everything needed for production deployments. Try the self-hosting platform—it's a game changer for operational excellence!**
+
+**Happy crawling with full visibility!** 🕷️📊
+
+*- unclecode*

docs/blog/release-v0.7.8.md

@@ -0,0 +1,327 @@
+# Crawl4AI v0.7.8: Stability & Bug Fix Release
+
+*December 2025*
+
+---
+
+I'm releasing Crawl4AI v0.7.8—a focused stability release that addresses 11 bugs reported by the community. While there are no new features in this release, these fixes resolve important issues affecting Docker deployments, LLM extraction, URL handling, and dependency compatibility.
+
+## What's Fixed at a Glance
+
+- **Docker API**: Fixed ContentRelevanceFilter deserialization, ProxyConfig serialization, and cache folder permissions
+- **LLM Extraction**: Configurable rate limiter backoff, HTML input format support, and proper URL handling for raw HTML
+- **URL Handling**: Correct relative URL resolution after JavaScript redirects
+- **Dependencies**: Replaced deprecated PyPDF2 with pypdf, Pydantic v2 ConfigDict compatibility
+- **AdaptiveCrawler**: Fixed query expansion to actually use LLM instead of hardcoded mock data
+
+## Bug Fixes
+
+### Docker & API Fixes
+
+#### ContentRelevanceFilter Deserialization (#1642)
+
+**The Problem:** When sending deep crawl requests to the Docker API with `ContentRelevanceFilter`, the server failed to deserialize the filter, causing requests to fail.
+
+**The Fix:** I added `ContentRelevanceFilter` to the public exports and enhanced the deserialization logic with dynamic imports.
+
+```python
+# This now works correctly in Docker API
+import httpx
+
+request = {
+    "urls": ["https://docs.example.com"],
+    "crawler_config": {
+        "deep_crawl_strategy": {
+            "type": "BFSDeepCrawlStrategy",
+            "max_depth": 2,
+            "filter_chain": [
+                {
+                    "type": "ContentRelevanceFilter",
+                    "query": "API documentation",
+                    "threshold": 0.3
+                }
+            ]
+        }
+    }
+}
+
+async with httpx.AsyncClient() as client:
+    response = await client.post("http://localhost:11235/crawl", json=request)
+    # Previously failed, now works!
+```
+
+#### ProxyConfig JSON Serialization (#1629)
+
+**The Problem:** `BrowserConfig.to_dict()` failed when `proxy_config` was set because `ProxyConfig` wasn't being serialized to a dictionary.
+
+**The Fix:** `ProxyConfig.to_dict()` is now called during serialization.
+
+```python
+from crawl4ai import BrowserConfig
+from crawl4ai.async_configs import ProxyConfig
+
+proxy = ProxyConfig(
+    server="http://proxy.example.com:8080",
+    username="user",
+    password="pass"
+)
+
+config = BrowserConfig(headless=True, proxy_config=proxy)
+
+# Previously raised TypeError, now works
+config_dict = config.to_dict()
+json.dumps(config_dict)  # Valid JSON
+```
+
+#### Docker Cache Folder Permissions (#1638)
+
+**The Problem:** The `.cache` folder in the Docker image had incorrect permissions, causing crawling to fail when caching was enabled.
+
+**The Fix:** Corrected ownership and permissions during image build.
+
+```bash
+# Cache now works correctly in Docker
+docker run -d -p 11235:11235 \
+    --shm-size=1g \
+    -v ./my-cache:/app/.cache \
+    unclecode/crawl4ai:0.7.8
+```
+
+---
+
+### LLM & Extraction Fixes
+
+#### Configurable Rate Limiter Backoff (#1269)
+
+**The Problem:** The LLM rate limiting backoff parameters were hardcoded, making it impossible to adjust retry behavior for different API rate limits.
+
+**The Fix:** `LLMConfig` now accepts three new parameters for complete control over retry behavior.
+
+```python
+from crawl4ai import LLMConfig
+
+# Default behavior (unchanged)
+default_config = LLMConfig(provider="openai/gpt-4o-mini")
+# backoff_base_delay=2, backoff_max_attempts=3, backoff_exponential_factor=2
+
+# Custom configuration for APIs with strict rate limits
+custom_config = LLMConfig(
+    provider="openai/gpt-4o-mini",
+    backoff_base_delay=5,           # Wait 5 seconds on first retry
+    backoff_max_attempts=5,          # Try up to 5 times
+    backoff_exponential_factor=3     # Multiply delay by 3 each attempt
+)
+
+# Retry sequence: 5s -> 15s -> 45s -> 135s -> 405s
+```
+
+#### LLM Strategy HTML Input Support (#1178)
+
+**The Problem:** `LLMExtractionStrategy` always sent markdown to the LLM, but some extraction tasks work better with HTML structure preserved.
+
+**The Fix:** Added `input_format` parameter supporting `"markdown"`, `"html"`, `"fit_markdown"`, `"cleaned_html"`, and `"fit_html"`.
+
+```python
+from crawl4ai import LLMExtractionStrategy, LLMConfig
+
+# Default: markdown input (unchanged)
+markdown_strategy = LLMExtractionStrategy(
+    llm_config=LLMConfig(provider="openai/gpt-4o-mini"),
+    instruction="Extract product information"
+)
+
+# NEW: HTML input - preserves table/list structure
+html_strategy = LLMExtractionStrategy(
+    llm_config=LLMConfig(provider="openai/gpt-4o-mini"),
+    instruction="Extract the data table preserving structure",
+    input_format="html"
+)
+
+# NEW: Filtered markdown - only relevant content
+fit_strategy = LLMExtractionStrategy(
+    llm_config=LLMConfig(provider="openai/gpt-4o-mini"),
+    instruction="Summarize the main content",
+    input_format="fit_markdown"
+)
+```
+
+#### Raw HTML URL Variable (#1116)
+
+**The Problem:** When using `url="raw:<html>..."`, the entire HTML content was being passed to extraction strategies as the URL parameter, polluting LLM prompts.
+
+**The Fix:** The URL is now correctly set to `"Raw HTML"` for raw HTML inputs.
+
+```python
+from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
+
+html = "<html><body><h1>Test</h1></body></html>"
+
+async with AsyncWebCrawler() as crawler:
+    result = await crawler.arun(
+        url=f"raw:{html}",
+        config=CrawlerRunConfig(extraction_strategy=my_strategy)
+    )
+    # extraction_strategy receives url="Raw HTML" instead of the HTML blob
+```
+
+---
+
+### URL Handling Fix
+
+#### Relative URLs After Redirects (#1268)
+
+**The Problem:** When JavaScript caused a page redirect, relative links were resolved against the original URL instead of the final URL.
+
+**The Fix:** `redirected_url` now captures the actual page URL after all JavaScript execution completes.
+
+```python
+from crawl4ai import AsyncWebCrawler
+
+async with AsyncWebCrawler() as crawler:
+    # Page at /old-page redirects via JS to /new-page
+    result = await crawler.arun(url="https://example.com/old-page")
+
+    # BEFORE: redirected_url = "https://example.com/old-page"
+    # AFTER:  redirected_url = "https://example.com/new-page"
+
+    # Links are now correctly resolved against the final URL
+    for link in result.links['internal']:
+        print(link['href'])  # Relative links resolved correctly
+```
+
+---
+
+### Dependency & Compatibility Fixes
+
+#### PyPDF2 Replaced with pypdf (#1412)
+
+**The Problem:** PyPDF2 was deprecated in 2022 and is no longer maintained.
+
+**The Fix:** Replaced with the actively maintained `pypdf` library.
+
+```python
+# Installation (unchanged)
+pip install crawl4ai[pdf]
+
+# The PDF processor now uses pypdf internally
+# No code changes required - API remains the same
+```
+
+#### Pydantic v2 ConfigDict Compatibility (#678)
+
+**The Problem:** Using the deprecated `class Config` syntax caused deprecation warnings with Pydantic v2.
+
+**The Fix:** Migrated to `model_config = ConfigDict(...)` syntax.
+
+```python
+# No more deprecation warnings when importing crawl4ai models
+from crawl4ai.models import CrawlResult
+from crawl4ai import CrawlerRunConfig, BrowserConfig
+
+# All models are now Pydantic v2 compatible
+```
+
+---
+
+### AdaptiveCrawler Fix
+
+#### Query Expansion Using LLM (#1621)
+
+**The Problem:** The `EmbeddingStrategy` in AdaptiveCrawler had commented-out LLM code and was using hardcoded mock query variations instead.
+
+**The Fix:** Uncommented and activated the LLM call for actual query expansion.
+
+```python
+# AdaptiveCrawler query expansion now actually uses the LLM
+# Instead of hardcoded variations like:
+# variations = {'queries': ['what are the best vegetables...']}
+
+# The LLM generates relevant query variations based on your actual query
+```
+
+---
+
+### Code Formatting Fix
+
+#### Import Statement Formatting (#1181)
+
+**The Problem:** When extracting code from web pages, import statements were sometimes concatenated without proper line separation.
+
+**The Fix:** Import statements now maintain proper newline separation.
+
+```python
+# BEFORE: "import osimport sysfrom pathlib import Path"
+# AFTER:
+# import os
+# import sys
+# from pathlib import Path
+```
+
+---
+
+## Breaking Changes
+
+**None!** This release is fully backward compatible.
+
+- All existing code continues to work without modification
+- New parameters have sensible defaults matching previous behavior
+- No API changes to existing functionality
+
+---
+
+## Upgrade Instructions
+
+### Python Package
+
+```bash
+pip install --upgrade crawl4ai
+# or
+pip install crawl4ai==0.7.8
+```
+
+### Docker
+
+```bash
+# Pull the latest version
+docker pull unclecode/crawl4ai:0.7.8
+
+# Run
+docker run -d -p 11235:11235 --shm-size=1g unclecode/crawl4ai:0.7.8
+```
+
+---
+
+## Verification
+
+Run the verification tests to confirm all fixes are working:
+
+```bash
+python docs/releases_review/demo_v0.7.8.py
+```
+
+This runs actual tests that verify each bug fix is properly implemented.
+
+---
+
+## Acknowledgments
+
+Thank you to everyone who reported these issues and provided detailed reproduction steps. Your bug reports make Crawl4AI better for everyone.
+
+Issues fixed: #1642, #1638, #1629, #1621, #1412, #1269, #1268, #1181, #1178, #1116, #678
+
+---
+
+## Support & Resources
+
+- **Documentation**: [docs.crawl4ai.com](https://docs.crawl4ai.com)
+- **GitHub**: [github.com/unclecode/crawl4ai](https://github.com/unclecode/crawl4ai)
+- **Discord**: [discord.gg/crawl4ai](https://discord.gg/jP8KfhDhyN)
+- **Twitter**: [@unclecode](https://x.com/unclecode)
+
+---
+
+**This stability release ensures Crawl4AI works reliably across Docker deployments, LLM extraction workflows, and various edge cases. Thank you for your continued support and feedback!**
+
+**Happy crawling!**
+
+*- unclecode*

docs/examples/c4a_script/tutorial/README.md

@@ -18,7 +18,7 @@ A comprehensive web-based tutorial for learning and experimenting with C4A-Scrip
 
 2. **Install Dependencies**
    ```bash
-   pip install flask
+   pip install -r requirements.txt
    ```
 
 3. **Launch the Server**
@@ -28,7 +28,7 @@ A comprehensive web-based tutorial for learning and experimenting with C4A-Scrip
 
 4. **Open in Browser**
    ```
-   http://localhost:8080
+   http://localhost:8000
    ```
 
 **🌐 Try Online**: [Live Demo](https://docs.crawl4ai.com/c4a-script/demo)
@@ -325,7 +325,7 @@ Powers the recording functionality:
 ### Configuration
 ```python
 # server.py configuration
-PORT = 8080
+PORT = 8000
 DEBUG = True
 THREADED = True
 ```
@@ -343,9 +343,9 @@ THREADED = True
 **Port Already in Use**
 ```bash
 # Kill existing process
-lsof -ti:8080 | xargs kill -9
+lsof -ti:8000 | xargs kill -9
 # Or use different port
-python server.py --port 8081
+python server.py --port 8001
 ```
 
 **Blockly Not Loading**

docs/examples/c4a_script/tutorial/server.py

@@ -216,7 +216,7 @@ def get_examples():
             'name': 'Handle Cookie Banner',
             'description': 'Accept cookies and close newsletter popup',
             'script': '''# Handle cookie banner and newsletter
-GO http://127.0.0.1:8080/playground/
+GO http://127.0.0.1:8000/playground/
 WAIT `body` 2
 IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
 IF (EXISTS `.newsletter-popup`) THEN CLICK `.close`'''

docs/examples/capsolver_captcha_solver/capsolver_api_integration/solve_aws_waf.py

@@ -0,0 +1,62 @@
+import asyncio
+import capsolver
+from crawl4ai import *
+
+
+# TODO: set your config
+# Docs: https://docs.capsolver.com/guide/captcha/awsWaf/
+api_key = "CAP-xxxxxxxxxxxxxxxxxxxxx"              # your api key of capsolver
+site_url = "https://nft.porsche.com/onboarding@6"  # page url of your target site
+cookie_domain = ".nft.porsche.com"                 # the domain name to which you want to apply the cookie
+captcha_type = "AntiAwsWafTaskProxyLess"           # type of your target captcha
+capsolver.api_key = api_key
+
+
+async def main():
+    browser_config = BrowserConfig(
+        verbose=True,
+        headless=False,
+        use_persistent_context=True,
+    )
+
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        await crawler.arun(
+            url=site_url,
+            cache_mode=CacheMode.BYPASS,
+            session_id="session_captcha_test"
+        )
+
+        # get aws waf cookie using capsolver sdk
+        solution = capsolver.solve({
+            "type": captcha_type,
+            "websiteURL": site_url,
+        })
+        cookie = solution["cookie"]
+        print("aws waf cookie:", cookie)
+
+        js_code = """
+            document.cookie = \'aws-waf-token=""" + cookie + """;domain=""" + cookie_domain + """;path=/\';
+            location.reload();
+        """
+
+        wait_condition = """() => {
+            return document.title === \'Join Porsche’s journey into Web3\';
+        }"""
+
+        run_config = CrawlerRunConfig(
+            cache_mode=CacheMode.BYPASS,
+            session_id="session_captcha_test",
+            js_code=js_code,
+            js_only=True,
+            wait_for=f"js:{wait_condition}"
+        )
+
+        result_next = await crawler.arun(
+            url=site_url,
+            config=run_config,
+        )
+        print(result_next.markdown)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/capsolver_captcha_solver/capsolver_api_integration/solve_cloudflare_challenge.py

@@ -0,0 +1,60 @@
+import asyncio
+import capsolver
+from crawl4ai import *
+
+
+# TODO: set your config
+# Docs: https://docs.capsolver.com/guide/captcha/cloudflare_challenge/
+api_key = "CAP-xxxxxxxxxxxxxxxxxxxxx"          # your api key of capsolver
+site_url = "https://gitlab.com/users/sign_in"  # page url of your target site
+captcha_type = "AntiCloudflareTask"            # type of your target captcha
+# your http proxy to solve cloudflare challenge
+proxy_server = "proxy.example.com:8080"
+proxy_username = "myuser"
+proxy_password = "mypass"
+capsolver.api_key = api_key
+
+
+async def main():
+    # get challenge cookie using capsolver sdk
+    solution = capsolver.solve({
+        "type": captcha_type,
+        "websiteURL": site_url,
+        "proxy": f"{proxy_server}:{proxy_username}:{proxy_password}",
+    })
+    cookies = solution["cookies"]
+    user_agent = solution["userAgent"]
+    print("challenge cookies:", cookies)
+
+    cookies_list = []
+    for name, value in cookies.items():
+        cookies_list.append({
+            "name": name,
+            "value": value,
+            "url": site_url,
+        })
+
+    browser_config = BrowserConfig(
+        verbose=True,
+        headless=False,
+        use_persistent_context=True,
+        user_agent=user_agent,
+        cookies=cookies_list,
+        proxy_config={
+            "server": f"http://{proxy_server}",
+            "username": proxy_username,
+            "password": proxy_password,
+        },
+    )
+
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result = await crawler.arun(
+            url=site_url,
+            cache_mode=CacheMode.BYPASS,
+            session_id="session_captcha_test"
+        )
+        print(result.markdown)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/capsolver_captcha_solver/capsolver_api_integration/solve_cloudflare_turnstile.py

@@ -0,0 +1,64 @@
+import asyncio
+import capsolver
+from crawl4ai import *
+
+
+# TODO: set your config
+# Docs: https://docs.capsolver.com/guide/captcha/cloudflare_turnstile/
+api_key = "CAP-xxxxxxxxxxxxxxxxxxxxx"                       # your api key of capsolver
+site_key = "0x4AAAAAAAGlwMzq_9z6S9Mh"                       # site key of your target site
+site_url = "https://clifford.io/demo/cloudflare-turnstile"  # page url of your target site
+captcha_type = "AntiTurnstileTaskProxyLess"                 # type of your target captcha
+capsolver.api_key = api_key
+
+
+async def main():
+    browser_config = BrowserConfig(
+        verbose=True,
+        headless=False,
+        use_persistent_context=True,
+    )
+
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        await crawler.arun(
+            url=site_url,
+            cache_mode=CacheMode.BYPASS,
+            session_id="session_captcha_test"
+        )
+
+        # get turnstile token using capsolver sdk
+        solution = capsolver.solve({
+            "type": captcha_type,
+            "websiteURL": site_url,
+            "websiteKey": site_key,
+        })
+        token = solution["token"]
+        print("turnstile token:", token)
+
+        js_code = """
+            document.querySelector(\'input[name="cf-turnstile-response"]\').value = \'"""+token+"""\';
+            document.querySelector(\'button[type="submit"]\').click();
+        """
+
+        wait_condition = """() => {
+            const items = document.querySelectorAll(\'h1\');
+            return items.length === 0;
+        }"""
+
+        run_config = CrawlerRunConfig(
+            cache_mode=CacheMode.BYPASS,
+            session_id="session_captcha_test",
+            js_code=js_code,
+            js_only=True,
+            wait_for=f"js:{wait_condition}"
+        )
+
+        result_next = await crawler.arun(
+            url=site_url,
+            config=run_config,
+        )
+        print(result_next.markdown)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/capsolver_captcha_solver/capsolver_api_integration/solve_recaptcha_v2.py

@@ -0,0 +1,67 @@
+import asyncio
+import capsolver
+from crawl4ai import *
+
+
+# TODO: set your config
+# Docs: https://docs.capsolver.com/guide/captcha/ReCaptchaV2/
+api_key = "CAP-xxxxxxxxxxxxxxxxxxxxx"                                      # your api key of capsolver
+site_key = "6LfW6wATAAAAAHLqO2pb8bDBahxlMxNdo9g947u9"                      # site key of your target site
+site_url = "https://recaptcha-demo.appspot.com/recaptcha-v2-checkbox.php"  # page url of your target site
+captcha_type = "ReCaptchaV2TaskProxyLess"                                  # type of your target captcha
+capsolver.api_key = api_key
+
+
+async def main():
+    browser_config = BrowserConfig(
+        verbose=True,
+        headless=False,
+        use_persistent_context=True,
+    )
+
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        await crawler.arun(
+            url=site_url,
+            cache_mode=CacheMode.BYPASS,
+            session_id="session_captcha_test"
+        )
+
+        # get recaptcha token using capsolver sdk
+        solution = capsolver.solve({
+            "type": captcha_type,
+            "websiteURL": site_url,
+            "websiteKey": site_key,
+        })
+        token = solution["gRecaptchaResponse"]
+        print("recaptcha token:", token)
+
+        js_code = """
+            const textarea = document.getElementById(\'g-recaptcha-response\');
+            if (textarea) {
+                textarea.value = \"""" + token + """\";
+                document.querySelector(\'button.form-field[type="submit"]\').click();
+            }
+        """
+
+        wait_condition = """() => {
+            const items = document.querySelectorAll(\'h2\');
+            return items.length > 1;
+        }"""
+
+        run_config = CrawlerRunConfig(
+            cache_mode=CacheMode.BYPASS,
+            session_id="session_captcha_test",
+            js_code=js_code,
+            js_only=True,
+            wait_for=f"js:{wait_condition}"
+        )
+
+        result_next = await crawler.arun(
+            url=site_url,
+            config=run_config,
+        )
+        print(result_next.markdown)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/capsolver_captcha_solver/capsolver_api_integration/solve_recaptcha_v3.py

@@ -0,0 +1,75 @@
+import asyncio
+import capsolver
+from crawl4ai import *
+
+
+# TODO: set your config
+# Docs: https://docs.capsolver.com/guide/captcha/ReCaptchaV3/
+api_key = "CAP-xxxxxxxxxxxxxxxxxxxxx"                                            # your api key of capsolver
+site_key = "6LdKlZEpAAAAAAOQjzC2v_d36tWxCl6dWsozdSy9"                            # site key of your target site
+site_url = "https://recaptcha-demo.appspot.com/recaptcha-v3-request-scores.php"  # page url of your target site
+page_action = "examples/v3scores"                                                # page action of your target site
+captcha_type = "ReCaptchaV3TaskProxyLess"                                        # type of your target captcha
+capsolver.api_key = api_key
+
+
+async def main():
+    browser_config = BrowserConfig(
+        verbose=True,
+        headless=False,
+        use_persistent_context=True,
+    )
+
+    # get recaptcha token using capsolver sdk
+    solution = capsolver.solve({
+        "type": captcha_type,
+        "websiteURL": site_url,
+        "websiteKey": site_key,
+        "pageAction": page_action,
+    })
+    token = solution["gRecaptchaResponse"]
+    print("recaptcha token:", token)
+
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        await crawler.arun(
+            url=site_url,
+            cache_mode=CacheMode.BYPASS,
+            session_id="session_captcha_test"
+        )
+
+        js_code = """
+            const originalFetch = window.fetch;
+
+            window.fetch = function(...args) {
+              if (typeof args[0] === 'string' && args[0].includes('/recaptcha-v3-verify.php')) {
+                const url = new URL(args[0], window.location.origin);
+                url.searchParams.set('action', '""" + token + """');
+                args[0] = url.toString();
+                document.querySelector('.token').innerHTML = "fetch('/recaptcha-v3-verify.php?action=examples/v3scores&token=""" + token + """')";
+                console.log('Fetch URL hooked:', args[0]);
+              }
+              return originalFetch.apply(this, args);
+            };
+        """
+
+        wait_condition = """() => {
+            return document.querySelector('.step3:not(.hidden)');
+        }"""
+
+        run_config = CrawlerRunConfig(
+            cache_mode=CacheMode.BYPASS,
+            session_id="session_captcha_test",
+            js_code=js_code,
+            js_only=True,
+            wait_for=f"js:{wait_condition}"
+        )
+
+        result_next = await crawler.arun(
+            url=site_url,
+            config=run_config,
+        )
+        print(result_next.markdown)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/capsolver_captcha_solver/capsolver_extension_integration/solve_aws_waf.py

@@ -0,0 +1,36 @@
+import time
+import asyncio
+from crawl4ai import *
+
+
+# TODO: the user data directory that includes the capsolver extension
+user_data_dir = "/browser-profile/Default1"
+
+"""
+The capsolver extension supports more features, such as:
+    - Telling the extension when to start solving captcha.
+    - Calling functions to check whether the captcha has been solved, etc.
+Reference blog: https://docs.capsolver.com/guide/automation-tool-integration/
+"""
+
+browser_config = BrowserConfig(
+    verbose=True,
+    headless=False,
+    user_data_dir=user_data_dir,
+    use_persistent_context=True,
+)
+
+async def main():
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result_initial = await crawler.arun(
+            url="https://nft.porsche.com/onboarding@6",
+            cache_mode=CacheMode.BYPASS,
+            session_id="session_captcha_test"
+        )
+
+        # do something later
+        time.sleep(300)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/capsolver_captcha_solver/capsolver_extension_integration/solve_cloudflare_challenge.py

@@ -0,0 +1,36 @@
+import time
+import asyncio
+from crawl4ai import *
+
+
+# TODO: the user data directory that includes the capsolver extension
+user_data_dir = "/browser-profile/Default1"
+
+"""
+The capsolver extension supports more features, such as:
+    - Telling the extension when to start solving captcha.
+    - Calling functions to check whether the captcha has been solved, etc.
+Reference blog: https://docs.capsolver.com/guide/automation-tool-integration/
+"""
+
+browser_config = BrowserConfig(
+    verbose=True,
+    headless=False,
+    user_data_dir=user_data_dir,
+    use_persistent_context=True,
+)
+
+async def main():
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result_initial = await crawler.arun(
+            url="https://gitlab.com/users/sign_in",
+            cache_mode=CacheMode.BYPASS,
+            session_id="session_captcha_test"
+        )
+
+        # do something later
+        time.sleep(300)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/capsolver_captcha_solver/capsolver_extension_integration/solve_cloudflare_turnstile.py

@@ -0,0 +1,36 @@
+import time
+import asyncio
+from crawl4ai import *
+
+
+# TODO: the user data directory that includes the capsolver extension
+user_data_dir = "/browser-profile/Default1"
+
+"""
+The capsolver extension supports more features, such as:
+    - Telling the extension when to start solving captcha.
+    - Calling functions to check whether the captcha has been solved, etc.
+Reference blog: https://docs.capsolver.com/guide/automation-tool-integration/
+"""
+
+browser_config = BrowserConfig(
+    verbose=True,
+    headless=False,
+    user_data_dir=user_data_dir,
+    use_persistent_context=True,
+)
+
+async def main():
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result_initial = await crawler.arun(
+            url="https://clifford.io/demo/cloudflare-turnstile",
+            cache_mode=CacheMode.BYPASS,
+            session_id="session_captcha_test"
+        )
+
+        # do something later
+        time.sleep(300)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/capsolver_captcha_solver/capsolver_extension_integration/solve_recaptcha_v2.py

@@ -0,0 +1,36 @@
+import time
+import asyncio
+from crawl4ai import *
+
+
+# TODO: the user data directory that includes the capsolver extension
+user_data_dir = "/browser-profile/Default1"
+
+"""
+The capsolver extension supports more features, such as:
+    - Telling the extension when to start solving captcha.
+    - Calling functions to check whether the captcha has been solved, etc.
+Reference blog: https://docs.capsolver.com/guide/automation-tool-integration/
+"""
+
+browser_config = BrowserConfig(
+    verbose=True,
+    headless=False,
+    user_data_dir=user_data_dir,
+    use_persistent_context=True,
+)
+
+async def main():
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result_initial = await crawler.arun(
+            url="https://recaptcha-demo.appspot.com/recaptcha-v2-checkbox.php",
+            cache_mode=CacheMode.BYPASS,
+            session_id="session_captcha_test"
+        )
+
+        # do something later
+        time.sleep(300)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/capsolver_captcha_solver/capsolver_extension_integration/solve_recaptcha_v3.py

@@ -0,0 +1,36 @@
+import time
+import asyncio
+from crawl4ai import *
+
+
+# TODO: the user data directory that includes the capsolver extension
+user_data_dir = "/browser-profile/Default1"
+
+"""
+The capsolver extension supports more features, such as:
+    - Telling the extension when to start solving captcha.
+    - Calling functions to check whether the captcha has been solved, etc.
+Reference blog: https://docs.capsolver.com/guide/automation-tool-integration/
+"""
+
+browser_config = BrowserConfig(
+    verbose=True,
+    headless=False,
+    user_data_dir=user_data_dir,
+    use_persistent_context=True,
+)
+
+async def main():
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result_initial = await crawler.arun(
+            url="https://recaptcha-demo.appspot.com/recaptcha-v3-request-scores.php",
+            cache_mode=CacheMode.BYPASS,
+            session_id="session_captcha_test"
+        )
+
+        # do something later
+        time.sleep(300)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/cloud_browser/scrapeless_browser.py

@@ -0,0 +1,61 @@
+import json
+import asyncio
+from urllib.parse import quote, urlencode
+from crawl4ai import CrawlerRunConfig, BrowserConfig, AsyncWebCrawler
+
+# Scrapeless provides a free anti-detection fingerprint browser client and cloud browsers:
+# https://www.scrapeless.com/en/blog/scrapeless-nstbrowser-strategic-integration
+
+async def main():
+    # customize browser fingerprint
+    fingerprint = {
+        "userAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.1.2.3 Safari/537.36",
+        "platform": "Windows",
+        "screen": {
+            "width": 1280, "height": 1024
+        },
+        "localization": {
+            "languages": ["zh-HK", "en-US", "en"], "timezone": "Asia/Hong_Kong",
+        }
+    }
+
+    fingerprint_json = json.dumps(fingerprint)
+    encoded_fingerprint = quote(fingerprint_json)
+
+    scrapeless_params = {
+        "token": "your token",
+        "sessionTTL": 1000,
+        "sessionName": "Demo",
+        "fingerprint": encoded_fingerprint,
+        # Sets the target country/region for the proxy, sending requests via an IP address from that region. You can specify a country code (e.g., US for the United States, GB for the United Kingdom, ANY for any country). See country codes for all supported options.
+        # "proxyCountry": "ANY",
+        # create profile on scrapeless
+        # "profileId": "your profileId",
+        # For more usage details, please refer to https://docs.scrapeless.com/en/scraping-browser/quickstart/getting-started
+    }
+    query_string = urlencode(scrapeless_params)
+    scrapeless_connection_url = f"wss://browser.scrapeless.com/api/v2/browser?{query_string}"
+    async with AsyncWebCrawler(
+        config=BrowserConfig(
+            headless=False,
+            browser_mode="cdp",
+            cdp_url=scrapeless_connection_url,
+        )
+    ) as crawler:
+        result = await crawler.arun(
+            url="https://www.scrapeless.com/en",
+            config=CrawlerRunConfig(
+                wait_for="css:.content",
+                scan_full_page=True,
+            ),
+        )
+        print("-" * 20)
+        print(f'Status Code: {result.status_code}')
+        print("-" * 20)
+        print(f'Title: {result.metadata["title"]}')
+        print(f'Description: {result.metadata["description"]}')
+        print("-" * 20)
+
+if __name__ == "__main__":
+    asyncio.run(main())
+    

docs/examples/dfs_crawl_demo.py

@@ -0,0 +1,39 @@
+"""
+Simple demonstration of the DFS deep crawler visiting multiple pages.
+
+Run with:  python docs/examples/dfs_crawl_demo.py
+"""
+import asyncio
+
+from crawl4ai.async_configs import BrowserConfig, CrawlerRunConfig
+from crawl4ai.async_webcrawler import AsyncWebCrawler
+from crawl4ai.cache_context import CacheMode
+from crawl4ai.deep_crawling.dfs_strategy import DFSDeepCrawlStrategy
+from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
+
+
+async def main() -> None:
+    dfs_strategy = DFSDeepCrawlStrategy(
+        max_depth=3,
+        max_pages=50,
+        include_external=False,
+    )
+
+    config = CrawlerRunConfig(
+        deep_crawl_strategy=dfs_strategy,
+        cache_mode=CacheMode.BYPASS,
+        markdown_generator=DefaultMarkdownGenerator(),
+        stream=True,
+    )
+
+    seed_url = "https://docs.python.org/3/"  # Plenty of internal links
+
+    async with AsyncWebCrawler(config=BrowserConfig(headless=True)) as crawler:
+        async for result in await crawler.arun(url=seed_url, config=config):
+            depth = result.metadata.get("depth")
+            status = "SUCCESS" if result.success else "FAILED"
+            print(f"[{status}] depth={depth} url={result.url}")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/docker_client_hooks_example.py

@@ -0,0 +1,522 @@
+#!/usr/bin/env python3
+"""
+Comprehensive hooks examples using Docker Client with function objects.
+
+This approach is recommended because:
+- Write hooks as regular Python functions
+- Full IDE support (autocomplete, type checking)
+- Automatic conversion to API format
+- Reusable and testable code
+- Clean, readable syntax
+"""
+
+import asyncio
+from crawl4ai import Crawl4aiDockerClient
+
+# API_BASE_URL = "http://localhost:11235"
+API_BASE_URL = "http://localhost:11234"
+
+
+# ============================================================================
+# Hook Function Definitions
+# ============================================================================
+
+# --- All Hooks Demo ---
+async def browser_created_hook(browser, **kwargs):
+    """Called after browser is created"""
+    print("[HOOK] Browser created and ready")
+    return browser
+
+
+async def page_context_hook(page, context, **kwargs):
+    """Setup page environment"""
+    print("[HOOK] Setting up page environment")
+
+    # Set viewport
+    await page.set_viewport_size({"width": 1920, "height": 1080})
+
+    # Add cookies
+    await context.add_cookies([{
+        "name": "test_session",
+        "value": "abc123xyz",
+        "domain": ".httpbin.org",
+        "path": "/"
+    }])
+
+    # Block resources
+    await context.route("**/*.{png,jpg,jpeg,gif}", lambda route: route.abort())
+    await context.route("**/analytics/*", lambda route: route.abort())
+
+    print("[HOOK] Environment configured")
+    return page
+
+
+async def user_agent_hook(page, context, user_agent, **kwargs):
+    """Called when user agent is updated"""
+    print(f"[HOOK] User agent: {user_agent[:50]}...")
+    return page
+
+
+async def before_goto_hook(page, context, url, **kwargs):
+    """Called before navigating to URL"""
+    print(f"[HOOK] Navigating to: {url}")
+
+    await page.set_extra_http_headers({
+        "X-Custom-Header": "crawl4ai-test",
+        "Accept-Language": "en-US"
+    })
+
+    return page
+
+
+async def after_goto_hook(page, context, url, response, **kwargs):
+    """Called after page loads"""
+    print(f"[HOOK] Page loaded: {url}")
+
+    await page.wait_for_timeout(1000)
+
+    try:
+        await page.wait_for_selector("body", timeout=2000)
+        print("[HOOK] Body element ready")
+    except:
+        print("[HOOK] Timeout, continuing")
+
+    return page
+
+
+async def execution_started_hook(page, context, **kwargs):
+    """Called when custom JS execution starts"""
+    print("[HOOK] JS execution started")
+    await page.evaluate("console.log('[HOOK] Custom JS');")
+    return page
+
+
+async def before_retrieve_hook(page, context, **kwargs):
+    """Called before retrieving HTML"""
+    print("[HOOK] Preparing HTML retrieval")
+
+    # Scroll for lazy content
+    await page.evaluate("window.scrollTo(0, document.body.scrollHeight);")
+    await page.wait_for_timeout(500)
+    await page.evaluate("window.scrollTo(0, 0);")
+
+    print("[HOOK] Scrolling complete")
+    return page
+
+
+async def before_return_hook(page, context, html, **kwargs):
+    """Called before returning HTML"""
+    print(f"[HOOK] HTML ready: {len(html)} chars")
+
+    metrics = await page.evaluate('''() => ({
+        images: document.images.length,
+        links: document.links.length,
+        scripts: document.scripts.length
+    })''')
+
+    print(f"[HOOK] Metrics - Images: {metrics['images']}, Links: {metrics['links']}")
+    return page
+
+
+# --- Authentication Hooks ---
+async def auth_context_hook(page, context, **kwargs):
+    """Setup authentication context"""
+    print("[HOOK] Setting up authentication")
+
+    # Add auth cookies
+    await context.add_cookies([{
+        "name": "auth_token",
+        "value": "fake_jwt_token",
+        "domain": ".httpbin.org",
+        "path": "/",
+        "httpOnly": True
+    }])
+
+    # Set localStorage
+    await page.evaluate('''
+        localStorage.setItem('user_id', '12345');
+        localStorage.setItem('auth_time', new Date().toISOString());
+    ''')
+
+    print("[HOOK] Auth context ready")
+    return page
+
+
+async def auth_headers_hook(page, context, url, **kwargs):
+    """Add authentication headers"""
+    print(f"[HOOK] Adding auth headers for {url}")
+
+    import base64
+    credentials = base64.b64encode(b"user:passwd").decode('ascii')
+
+    await page.set_extra_http_headers({
+        'Authorization': f'Basic {credentials}',
+        'X-API-Key': 'test-key-123'
+    })
+
+    return page
+
+
+# --- Performance Optimization Hooks ---
+async def performance_hook(page, context, **kwargs):
+    """Optimize page for performance"""
+    print("[HOOK] Optimizing for performance")
+
+    # Block resource-heavy content
+    await context.route("**/*.{png,jpg,jpeg,gif,webp,svg}", lambda r: r.abort())
+    await context.route("**/*.{woff,woff2,ttf}", lambda r: r.abort())
+    await context.route("**/*.{mp4,webm,ogg}", lambda r: r.abort())
+    await context.route("**/googletagmanager.com/*", lambda r: r.abort())
+    await context.route("**/google-analytics.com/*", lambda r: r.abort())
+    await context.route("**/facebook.com/*", lambda r: r.abort())
+
+    # Disable animations
+    await page.add_style_tag(content='''
+        *, *::before, *::after {
+            animation-duration: 0s !important;
+            transition-duration: 0s !important;
+        }
+    ''')
+
+    print("[HOOK] Optimizations applied")
+    return page
+
+
+async def cleanup_hook(page, context, **kwargs):
+    """Clean page before extraction"""
+    print("[HOOK] Cleaning page")
+
+    await page.evaluate('''() => {
+        const selectors = [
+            '.ad', '.ads', '.advertisement',
+            '.popup', '.modal', '.overlay',
+            '.cookie-banner', '.newsletter'
+        ];
+
+        selectors.forEach(sel => {
+            document.querySelectorAll(sel).forEach(el => el.remove());
+        });
+
+        document.querySelectorAll('script, style').forEach(el => el.remove());
+    }''')
+
+    print("[HOOK] Page cleaned")
+    return page
+
+
+# --- Content Extraction Hooks ---
+async def wait_dynamic_content_hook(page, context, url, response, **kwargs):
+    """Wait for dynamic content to load"""
+    print(f"[HOOK] Waiting for dynamic content on {url}")
+
+    await page.wait_for_timeout(2000)
+
+    # Click "Load More" if exists
+    try:
+        load_more = await page.query_selector('[class*="load-more"], button:has-text("Load More")')
+        if load_more:
+            await load_more.click()
+            await page.wait_for_timeout(1000)
+            print("[HOOK] Clicked 'Load More'")
+    except:
+        pass
+
+    return page
+
+
+async def extract_metadata_hook(page, context, **kwargs):
+    """Extract page metadata"""
+    print("[HOOK] Extracting metadata")
+
+    metadata = await page.evaluate('''() => {
+        const getMeta = (name) => {
+            const el = document.querySelector(`meta[name="${name}"], meta[property="${name}"]`);
+            return el ? el.getAttribute('content') : null;
+        };
+
+        return {
+            title: document.title,
+            description: getMeta('description'),
+            author: getMeta('author'),
+            keywords: getMeta('keywords'),
+        };
+    }''')
+
+    print(f"[HOOK] Metadata: {metadata}")
+
+    # Infinite scroll
+    for i in range(3):
+        await page.evaluate("window.scrollTo(0, document.body.scrollHeight);")
+        await page.wait_for_timeout(1000)
+        print(f"[HOOK] Scroll {i+1}/3")
+
+    return page
+
+
+# --- Multi-URL Hooks ---
+async def url_specific_hook(page, context, url, **kwargs):
+    """Apply URL-specific logic"""
+    print(f"[HOOK] Processing URL: {url}")
+
+    # URL-specific headers
+    if 'html' in url:
+        await page.set_extra_http_headers({"X-Type": "HTML"})
+    elif 'json' in url:
+        await page.set_extra_http_headers({"X-Type": "JSON"})
+
+    return page
+
+
+async def track_progress_hook(page, context, url, response, **kwargs):
+    """Track crawl progress"""
+    status = response.status if response else 'unknown'
+    print(f"[HOOK] Loaded {url} - Status: {status}")
+    return page
+
+
+# ============================================================================
+# Test Functions
+# ============================================================================
+
+async def test_all_hooks_comprehensive():
+    """Test all 8 hook types"""
+    print("=" * 70)
+    print("Test 1: All Hooks Comprehensive Demo (Docker Client)")
+    print("=" * 70)
+
+    async with Crawl4aiDockerClient(base_url=API_BASE_URL, verbose=False) as client:
+        print("\nCrawling with all 8 hooks...")
+
+        # Define hooks with function objects
+        hooks = {
+            "on_browser_created": browser_created_hook,
+            "on_page_context_created": page_context_hook,
+            "on_user_agent_updated": user_agent_hook,
+            "before_goto": before_goto_hook,
+            "after_goto": after_goto_hook,
+            "on_execution_started": execution_started_hook,
+            "before_retrieve_html": before_retrieve_hook,
+            "before_return_html": before_return_hook
+        }
+
+        result = await client.crawl(
+            ["https://httpbin.org/html"],
+            hooks=hooks,
+            hooks_timeout=30
+        )
+
+        print("\n✅ Success!")
+        print(f"   URL: {result.url}")
+        print(f"   Success: {result.success}")
+        print(f"   HTML: {len(result.html)} chars")
+
+
+async def test_authentication_workflow():
+    """Test authentication with hooks"""
+    print("\n" + "=" * 70)
+    print("Test 2: Authentication Workflow (Docker Client)")
+    print("=" * 70)
+
+    async with Crawl4aiDockerClient(base_url=API_BASE_URL, verbose=False) as client:
+        print("\nTesting authentication...")
+
+        hooks = {
+            "on_page_context_created": auth_context_hook,
+            "before_goto": auth_headers_hook
+        }
+
+        result = await client.crawl(
+            ["https://httpbin.org/basic-auth/user/passwd"],
+            hooks=hooks,
+            hooks_timeout=15
+        )
+
+        print("\n✅ Authentication completed")
+
+        if result.success:
+            if '"authenticated"' in result.html and 'true' in result.html:
+                print("   ✅ Basic auth successful!")
+            else:
+                print("   ⚠️ Auth status unclear")
+        else:
+            print(f"   ❌ Failed: {result.error_message}")
+
+
+async def test_performance_optimization():
+    """Test performance optimization"""
+    print("\n" + "=" * 70)
+    print("Test 3: Performance Optimization (Docker Client)")
+    print("=" * 70)
+
+    async with Crawl4aiDockerClient(base_url=API_BASE_URL, verbose=False) as client:
+        print("\nTesting performance hooks...")
+
+        hooks = {
+            "on_page_context_created": performance_hook,
+            "before_retrieve_html": cleanup_hook
+        }
+
+        result = await client.crawl(
+            ["https://httpbin.org/html"],
+            hooks=hooks,
+            hooks_timeout=10
+        )
+
+        print("\n✅ Optimization completed")
+        print(f"   HTML size: {len(result.html):,} chars")
+        print("   Resources blocked, ads removed")
+
+
+async def test_content_extraction():
+    """Test content extraction"""
+    print("\n" + "=" * 70)
+    print("Test 4: Content Extraction (Docker Client)")
+    print("=" * 70)
+
+    async with Crawl4aiDockerClient(base_url=API_BASE_URL, verbose=False) as client:
+        print("\nTesting extraction hooks...")
+
+        hooks = {
+            "after_goto": wait_dynamic_content_hook,
+            "before_retrieve_html": extract_metadata_hook
+        }
+
+        result = await client.crawl(
+            ["https://www.kidocode.com/"],
+            hooks=hooks,
+            hooks_timeout=20
+        )
+
+        print("\n✅ Extraction completed")
+        print(f"   URL: {result.url}")
+        print(f"   Success: {result.success}")
+        print(f"   Metadata: {result.metadata}")
+
+
+async def test_multi_url_crawl():
+    """Test hooks with multiple URLs"""
+    print("\n" + "=" * 70)
+    print("Test 5: Multi-URL Crawl (Docker Client)")
+    print("=" * 70)
+
+    async with Crawl4aiDockerClient(base_url=API_BASE_URL, verbose=False) as client:
+        print("\nCrawling multiple URLs...")
+
+        hooks = {
+            "before_goto": url_specific_hook,
+            "after_goto": track_progress_hook
+        }
+
+        results = await client.crawl(
+            [
+                "https://httpbin.org/html",
+                "https://httpbin.org/json",
+                "https://httpbin.org/xml"
+            ],
+            hooks=hooks,
+            hooks_timeout=15
+        )
+
+        print("\n✅ Multi-URL crawl completed")
+        print(f"\n   Crawled {len(results)} URLs:")
+        for i, result in enumerate(results, 1):
+            status = "✅" if result.success else "❌"
+            print(f"   {status} {i}. {result.url}")
+
+
+async def test_reusable_hook_library():
+    """Test using reusable hook library"""
+    print("\n" + "=" * 70)
+    print("Test 6: Reusable Hook Library (Docker Client)")
+    print("=" * 70)
+
+    # Create a library of reusable hooks
+    class HookLibrary:
+        @staticmethod
+        async def block_images(page, context, **kwargs):
+            """Block all images"""
+            await context.route("**/*.{png,jpg,jpeg,gif}", lambda r: r.abort())
+            print("[LIBRARY] Images blocked")
+            return page
+
+        @staticmethod
+        async def block_analytics(page, context, **kwargs):
+            """Block analytics"""
+            await context.route("**/analytics/*", lambda r: r.abort())
+            await context.route("**/google-analytics.com/*", lambda r: r.abort())
+            print("[LIBRARY] Analytics blocked")
+            return page
+
+        @staticmethod
+        async def scroll_infinite(page, context, **kwargs):
+            """Handle infinite scroll"""
+            for i in range(5):
+                prev = await page.evaluate("document.body.scrollHeight")
+                await page.evaluate("window.scrollTo(0, document.body.scrollHeight);")
+                await page.wait_for_timeout(1000)
+                curr = await page.evaluate("document.body.scrollHeight")
+                if curr == prev:
+                    break
+            print("[LIBRARY] Infinite scroll complete")
+            return page
+
+    async with Crawl4aiDockerClient(base_url=API_BASE_URL, verbose=False) as client:
+        print("\nUsing hook library...")
+
+        hooks = {
+            "on_page_context_created": HookLibrary.block_images,
+            "before_retrieve_html": HookLibrary.scroll_infinite
+        }
+
+        result = await client.crawl(
+            ["https://www.kidocode.com/"],
+            hooks=hooks,
+            hooks_timeout=20
+        )
+
+        print("\n✅ Library hooks completed")
+        print(f"   Success: {result.success}")
+
+
+# ============================================================================
+# Main
+# ============================================================================
+
+async def main():
+    """Run all Docker client hook examples"""
+    print("🔧 Crawl4AI Docker Client - Hooks Examples (Function-Based)")
+    print("Using Python function objects with automatic conversion")
+    print("=" * 70)
+
+    tests = [
+        ("All Hooks Demo", test_all_hooks_comprehensive),
+        ("Authentication", test_authentication_workflow),
+        ("Performance", test_performance_optimization),
+        ("Extraction", test_content_extraction),
+        ("Multi-URL", test_multi_url_crawl),
+        ("Hook Library", test_reusable_hook_library)
+    ]
+
+    for i, (name, test_func) in enumerate(tests, 1):
+        try:
+            await test_func()
+            print(f"\n✅ Test {i}/{len(tests)}: {name} completed\n")
+        except Exception as e:
+            print(f"\n❌ Test {i}/{len(tests)}: {name} failed: {e}\n")
+            import traceback
+            traceback.print_exc()
+
+    print("=" * 70)
+    print("🎉 All Docker client hook examples completed!")
+    print("\n💡 Key Benefits of Function-Based Hooks:")
+    print("   • Write as regular Python functions")
+    print("   • Full IDE support (autocomplete, types)")
+    print("   • Automatic conversion to API format")
+    print("   • Reusable across projects")
+    print("   • Clean, readable code")
+    print("   • Easy to test and debug")
+    print("=" * 70)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/docker_webhook_example.py

@@ -0,0 +1,461 @@
+"""
+Docker Webhook Example for Crawl4AI
+
+This example demonstrates how to use webhooks with the Crawl4AI job queue API.
+Instead of polling for results, webhooks notify your application when jobs complete.
+
+Supports both:
+- /crawl/job - Raw crawling with markdown extraction
+- /llm/job - LLM-powered content extraction
+
+Prerequisites:
+1. Crawl4AI Docker container running on localhost:11235
+2. Flask installed: pip install flask requests
+3. LLM API key configured in .llm.env (for LLM extraction examples)
+
+Usage:
+1. Run this script: python docker_webhook_example.py
+2. The webhook server will start on http://localhost:8080
+3. Jobs will be submitted and webhooks will be received automatically
+"""
+
+import requests
+import json
+import time
+from flask import Flask, request, jsonify
+from threading import Thread
+
+# Configuration
+CRAWL4AI_BASE_URL = "http://localhost:11235"
+WEBHOOK_BASE_URL = "http://localhost:8080"  # Your webhook receiver URL
+
+# Initialize Flask app for webhook receiver
+app = Flask(__name__)
+
+# Store received webhook data for demonstration
+received_webhooks = []
+
+
+@app.route('/webhooks/crawl-complete', methods=['POST'])
+def handle_crawl_webhook():
+    """
+    Webhook handler that receives notifications when crawl jobs complete.
+
+    Payload structure:
+    {
+        "task_id": "crawl_abc123",
+        "task_type": "crawl",
+        "status": "completed" or "failed",
+        "timestamp": "2025-10-21T10:30:00.000000+00:00",
+        "urls": ["https://example.com"],
+        "error": "error message" (only if failed),
+        "data": {...} (only if webhook_data_in_payload=True)
+    }
+    """
+    payload = request.json
+    print(f"\n{'='*60}")
+    print(f"📬 Webhook received for task: {payload['task_id']}")
+    print(f"   Status: {payload['status']}")
+    print(f"   Timestamp: {payload['timestamp']}")
+    print(f"   URLs: {payload['urls']}")
+
+    if payload['status'] == 'completed':
+        # If data is in payload, process it directly
+        if 'data' in payload:
+            print(f"   ✅ Data included in webhook")
+            data = payload['data']
+            # Process the crawl results here
+            for result in data.get('results', []):
+                print(f"      - Crawled: {result.get('url')}")
+                print(f"      - Markdown length: {len(result.get('markdown', ''))}")
+        else:
+            # Fetch results from API if not included
+            print(f"   📥 Fetching results from API...")
+            task_id = payload['task_id']
+            result_response = requests.get(f"{CRAWL4AI_BASE_URL}/crawl/job/{task_id}")
+            if result_response.ok:
+                data = result_response.json()
+                print(f"   ✅ Results fetched successfully")
+                # Process the crawl results here
+                for result in data['result'].get('results', []):
+                    print(f"      - Crawled: {result.get('url')}")
+                    print(f"      - Markdown length: {len(result.get('markdown', ''))}")
+
+    elif payload['status'] == 'failed':
+        print(f"   ❌ Job failed: {payload.get('error', 'Unknown error')}")
+
+    print(f"{'='*60}\n")
+
+    # Store webhook for demonstration
+    received_webhooks.append(payload)
+
+    # Return 200 OK to acknowledge receipt
+    return jsonify({"status": "received"}), 200
+
+
+@app.route('/webhooks/llm-complete', methods=['POST'])
+def handle_llm_webhook():
+    """
+    Webhook handler that receives notifications when LLM extraction jobs complete.
+
+    Payload structure:
+    {
+        "task_id": "llm_1698765432_12345",
+        "task_type": "llm_extraction",
+        "status": "completed" or "failed",
+        "timestamp": "2025-10-21T10:30:00.000000+00:00",
+        "urls": ["https://example.com/article"],
+        "error": "error message" (only if failed),
+        "data": {"extracted_content": {...}} (only if webhook_data_in_payload=True)
+    }
+    """
+    payload = request.json
+    print(f"\n{'='*60}")
+    print(f"🤖 LLM Webhook received for task: {payload['task_id']}")
+    print(f"   Task Type: {payload['task_type']}")
+    print(f"   Status: {payload['status']}")
+    print(f"   Timestamp: {payload['timestamp']}")
+    print(f"   URL: {payload['urls'][0]}")
+
+    if payload['status'] == 'completed':
+        # If data is in payload, process it directly
+        if 'data' in payload:
+            print(f"   ✅ Data included in webhook")
+            data = payload['data']
+            # Webhook wraps extracted content in 'extracted_content' field
+            extracted = data.get('extracted_content', {})
+            print(f"      - Extracted content:")
+            print(f"        {json.dumps(extracted, indent=8)}")
+        else:
+            # Fetch results from API if not included
+            print(f"   📥 Fetching results from API...")
+            task_id = payload['task_id']
+            result_response = requests.get(f"{CRAWL4AI_BASE_URL}/llm/job/{task_id}")
+            if result_response.ok:
+                data = result_response.json()
+                print(f"   ✅ Results fetched successfully")
+                # API returns unwrapped content in 'result' field
+                extracted = data['result']
+                print(f"      - Extracted content:")
+                print(f"        {json.dumps(extracted, indent=8)}")
+
+    elif payload['status'] == 'failed':
+        print(f"   ❌ Job failed: {payload.get('error', 'Unknown error')}")
+
+    print(f"{'='*60}\n")
+
+    # Store webhook for demonstration
+    received_webhooks.append(payload)
+
+    # Return 200 OK to acknowledge receipt
+    return jsonify({"status": "received"}), 200
+
+
+def start_webhook_server():
+    """Start the Flask webhook server in a separate thread"""
+    app.run(host='0.0.0.0', port=8080, debug=False, use_reloader=False)
+
+
+def submit_crawl_job_with_webhook(urls, webhook_url, include_data=False):
+    """
+    Submit a crawl job with webhook notification.
+
+    Args:
+        urls: List of URLs to crawl
+        webhook_url: URL to receive webhook notifications
+        include_data: Whether to include full results in webhook payload
+
+    Returns:
+        task_id: The job's task identifier
+    """
+    payload = {
+        "urls": urls,
+        "browser_config": {"headless": True},
+        "crawler_config": {"cache_mode": "bypass"},
+        "webhook_config": {
+            "webhook_url": webhook_url,
+            "webhook_data_in_payload": include_data,
+            # Optional: Add custom headers for authentication
+            # "webhook_headers": {
+            #     "X-Webhook-Secret": "your-secret-token"
+            # }
+        }
+    }
+
+    print(f"\n🚀 Submitting crawl job...")
+    print(f"   URLs: {urls}")
+    print(f"   Webhook: {webhook_url}")
+    print(f"   Include data: {include_data}")
+
+    response = requests.post(
+        f"{CRAWL4AI_BASE_URL}/crawl/job",
+        json=payload,
+        headers={"Content-Type": "application/json"}
+    )
+
+    if response.ok:
+        data = response.json()
+        task_id = data['task_id']
+        print(f"   ✅ Job submitted successfully")
+        print(f"   Task ID: {task_id}")
+        return task_id
+    else:
+        print(f"   ❌ Failed to submit job: {response.text}")
+        return None
+
+
+def submit_llm_job_with_webhook(url, query, webhook_url, include_data=False, schema=None, provider=None):
+    """
+    Submit an LLM extraction job with webhook notification.
+
+    Args:
+        url: URL to extract content from
+        query: Instruction for the LLM (e.g., "Extract article title and author")
+        webhook_url: URL to receive webhook notifications
+        include_data: Whether to include full results in webhook payload
+        schema: Optional JSON schema for structured extraction
+        provider: Optional LLM provider (e.g., "openai/gpt-4o-mini")
+
+    Returns:
+        task_id: The job's task identifier
+    """
+    payload = {
+        "url": url,
+        "q": query,
+        "cache": False,
+        "webhook_config": {
+            "webhook_url": webhook_url,
+            "webhook_data_in_payload": include_data,
+            # Optional: Add custom headers for authentication
+            # "webhook_headers": {
+            #     "X-Webhook-Secret": "your-secret-token"
+            # }
+        }
+    }
+
+    if schema:
+        payload["schema"] = schema
+
+    if provider:
+        payload["provider"] = provider
+
+    print(f"\n🤖 Submitting LLM extraction job...")
+    print(f"   URL: {url}")
+    print(f"   Query: {query}")
+    print(f"   Webhook: {webhook_url}")
+    print(f"   Include data: {include_data}")
+    if provider:
+        print(f"   Provider: {provider}")
+
+    response = requests.post(
+        f"{CRAWL4AI_BASE_URL}/llm/job",
+        json=payload,
+        headers={"Content-Type": "application/json"}
+    )
+
+    if response.ok:
+        data = response.json()
+        task_id = data['task_id']
+        print(f"   ✅ Job submitted successfully")
+        print(f"   Task ID: {task_id}")
+        return task_id
+    else:
+        print(f"   ❌ Failed to submit job: {response.text}")
+        return None
+
+
+def submit_job_without_webhook(urls):
+    """
+    Submit a job without webhook (traditional polling approach).
+
+    Args:
+        urls: List of URLs to crawl
+
+    Returns:
+        task_id: The job's task identifier
+    """
+    payload = {
+        "urls": urls,
+        "browser_config": {"headless": True},
+        "crawler_config": {"cache_mode": "bypass"}
+    }
+
+    print(f"\n🚀 Submitting crawl job (without webhook)...")
+    print(f"   URLs: {urls}")
+
+    response = requests.post(
+        f"{CRAWL4AI_BASE_URL}/crawl/job",
+        json=payload
+    )
+
+    if response.ok:
+        data = response.json()
+        task_id = data['task_id']
+        print(f"   ✅ Job submitted successfully")
+        print(f"   Task ID: {task_id}")
+        return task_id
+    else:
+        print(f"   ❌ Failed to submit job: {response.text}")
+        return None
+
+
+def poll_job_status(task_id, timeout=60):
+    """
+    Poll for job status (used when webhook is not configured).
+
+    Args:
+        task_id: The job's task identifier
+        timeout: Maximum time to wait in seconds
+    """
+    print(f"\n⏳ Polling for job status...")
+    start_time = time.time()
+
+    while time.time() - start_time < timeout:
+        response = requests.get(f"{CRAWL4AI_BASE_URL}/crawl/job/{task_id}")
+
+        if response.ok:
+            data = response.json()
+            status = data.get('status', 'unknown')
+
+            if status == 'completed':
+                print(f"   ✅ Job completed!")
+                return data
+            elif status == 'failed':
+                print(f"   ❌ Job failed: {data.get('error', 'Unknown error')}")
+                return data
+            else:
+                print(f"   ⏳ Status: {status}, waiting...")
+                time.sleep(2)
+        else:
+            print(f"   ❌ Failed to get status: {response.text}")
+            return None
+
+    print(f"   ⏰ Timeout reached")
+    return None
+
+
+def main():
+    """Run the webhook demonstration"""
+
+    # Check if Crawl4AI is running
+    try:
+        health = requests.get(f"{CRAWL4AI_BASE_URL}/health", timeout=5)
+        print(f"✅ Crawl4AI is running: {health.json()}")
+    except:
+        print(f"❌ Cannot connect to Crawl4AI at {CRAWL4AI_BASE_URL}")
+        print("   Please make sure Docker container is running:")
+        print("   docker run -d -p 11235:11235 --name crawl4ai unclecode/crawl4ai:latest")
+        return
+
+    # Start webhook server in background thread
+    print(f"\n🌐 Starting webhook server at {WEBHOOK_BASE_URL}...")
+    webhook_thread = Thread(target=start_webhook_server, daemon=True)
+    webhook_thread.start()
+    time.sleep(2)  # Give server time to start
+
+    # Example 1: Job with webhook (notification only, fetch data separately)
+    print(f"\n{'='*60}")
+    print("Example 1: Webhook Notification Only")
+    print(f"{'='*60}")
+    task_id_1 = submit_crawl_job_with_webhook(
+        urls=["https://example.com"],
+        webhook_url=f"{WEBHOOK_BASE_URL}/webhooks/crawl-complete",
+        include_data=False
+    )
+
+    # Example 2: Job with webhook (data included in payload)
+    time.sleep(5)  # Wait a bit between requests
+    print(f"\n{'='*60}")
+    print("Example 2: Webhook with Full Data")
+    print(f"{'='*60}")
+    task_id_2 = submit_crawl_job_with_webhook(
+        urls=["https://www.python.org"],
+        webhook_url=f"{WEBHOOK_BASE_URL}/webhooks/crawl-complete",
+        include_data=True
+    )
+
+    # Example 3: LLM extraction with webhook (notification only)
+    time.sleep(5)  # Wait a bit between requests
+    print(f"\n{'='*60}")
+    print("Example 3: LLM Extraction with Webhook (Notification Only)")
+    print(f"{'='*60}")
+    task_id_3 = submit_llm_job_with_webhook(
+        url="https://www.example.com",
+        query="Extract the main heading and description from this page.",
+        webhook_url=f"{WEBHOOK_BASE_URL}/webhooks/llm-complete",
+        include_data=False,
+        provider="openai/gpt-4o-mini"
+    )
+
+    # Example 4: LLM extraction with webhook (data included + schema)
+    time.sleep(5)  # Wait a bit between requests
+    print(f"\n{'='*60}")
+    print("Example 4: LLM Extraction with Schema and Full Data")
+    print(f"{'='*60}")
+
+    # Define a schema for structured extraction
+    schema = json.dumps({
+        "type": "object",
+        "properties": {
+            "title": {"type": "string", "description": "Page title"},
+            "description": {"type": "string", "description": "Page description"}
+        },
+        "required": ["title"]
+    })
+
+    task_id_4 = submit_llm_job_with_webhook(
+        url="https://www.python.org",
+        query="Extract the title and description of this website",
+        webhook_url=f"{WEBHOOK_BASE_URL}/webhooks/llm-complete",
+        include_data=True,
+        schema=schema,
+        provider="openai/gpt-4o-mini"
+    )
+
+    # Example 5: Traditional polling (no webhook)
+    time.sleep(5)  # Wait a bit between requests
+    print(f"\n{'='*60}")
+    print("Example 5: Traditional Polling (No Webhook)")
+    print(f"{'='*60}")
+    task_id_5 = submit_job_without_webhook(
+        urls=["https://github.com"]
+    )
+    if task_id_5:
+        result = poll_job_status(task_id_5)
+        if result and result.get('status') == 'completed':
+            print(f"   ✅ Results retrieved via polling")
+
+    # Wait for webhooks to arrive
+    print(f"\n⏳ Waiting for webhooks to be received...")
+    time.sleep(30)  # Give jobs time to complete and webhooks to arrive (longer for LLM)
+
+    # Summary
+    print(f"\n{'='*60}")
+    print("Summary")
+    print(f"{'='*60}")
+    print(f"Total webhooks received: {len(received_webhooks)}")
+
+    crawl_webhooks = [w for w in received_webhooks if w['task_type'] == 'crawl']
+    llm_webhooks = [w for w in received_webhooks if w['task_type'] == 'llm_extraction']
+
+    print(f"\n📊 Breakdown:")
+    print(f"   - Crawl webhooks: {len(crawl_webhooks)}")
+    print(f"   - LLM extraction webhooks: {len(llm_webhooks)}")
+
+    print(f"\n📋 Details:")
+    for i, webhook in enumerate(received_webhooks, 1):
+        task_type = webhook['task_type']
+        icon = "🕷️" if task_type == "crawl" else "🤖"
+        print(f"{i}. {icon} Task {webhook['task_id']}: {webhook['status']} ({task_type})")
+
+    print(f"\n✅ Demo completed!")
+    print(f"\n💡 Pro tips:")
+    print(f"   - In production, your webhook URL should be publicly accessible")
+    print(f"     (e.g., https://myapp.com/webhooks) or use ngrok for testing")
+    print(f"   - Both /crawl/job and /llm/job support the same webhook configuration")
+    print(f"   - Use webhook_data_in_payload=true to get results directly in the webhook")
+    print(f"   - LLM jobs may take longer, adjust timeouts accordingly")
+
+
+if __name__ == "__main__":
+    main()

docs/examples/nst_proxy/api_proxy_example.py

@@ -0,0 +1,48 @@
+"""
+NSTProxy Integration Examples for crawl4ai
+------------------------------------------
+
+NSTProxy is a premium residential proxy provider.
+👉 Purchase Proxies: https://nstproxy.com
+💰 Use coupon code "crawl4ai" for 10% off your plan.
+
+"""
+import asyncio, requests
+from crawl4ai import AsyncWebCrawler, BrowserConfig
+
+
+async def main():
+    """
+    Example: Dynamically fetch a proxy from NSTProxy API before crawling.
+    """
+    NST_TOKEN = "YOUR_NST_PROXY_TOKEN"  # Get from https://app.nstproxy.com/profile
+    CHANNEL_ID = "YOUR_NST_PROXY_CHANNEL_ID"  # Your NSTProxy Channel ID
+    country = "ANY"  # e.g. "ANY", "US", "DE"
+
+    # Fetch proxy from NSTProxy API
+    api_url = (
+        f"https://api.nstproxy.com/api/v1/generate/apiproxies"
+        f"?fType=2&channelId={CHANNEL_ID}&country={country}"
+        f"&protocol=http&sessionDuration=10&count=1&token={NST_TOKEN}"
+    )
+    response = requests.get(api_url, timeout=10).json()
+    proxy = response[0]
+
+    ip = proxy.get("ip")
+    port = proxy.get("port")
+    username = proxy.get("username", "")
+    password = proxy.get("password", "")
+
+    browser_config = BrowserConfig(proxy_config={
+        "server": f"http://{ip}:{port}",
+        "username": username,
+        "password": password,
+    })
+
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result = await crawler.arun(url="https://example.com")
+        print("[API Proxy] Status:", result.status_code)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/nst_proxy/auth_proxy_example.py

@@ -0,0 +1,31 @@
+"""
+NSTProxy Integration Examples for crawl4ai
+------------------------------------------
+
+NSTProxy is a premium residential proxy provider.
+👉 Purchase Proxies: https://nstproxy.com
+💰 Use coupon code "crawl4ai" for 10% off your plan.
+
+"""
+import asyncio
+from crawl4ai import AsyncWebCrawler, BrowserConfig
+
+
+async def main():
+    """
+    Example: Use NSTProxy with manual username/password authentication.
+    """
+
+    browser_config = BrowserConfig(proxy_config={
+        "server": "http://gate.nstproxy.io:24125",
+        "username": "your_username",
+        "password": "your_password",
+    })
+
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result = await crawler.arun(url="https://example.com")
+        print("[Auth Proxy] Status:", result.status_code)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/nst_proxy/basic_proxy_example.py

@@ -0,0 +1,29 @@
+"""
+NSTProxy Integration Examples for crawl4ai
+------------------------------------------
+
+NSTProxy is a premium residential proxy provider.
+👉 Purchase Proxies: https://nstproxy.com
+💰 Use coupon code "crawl4ai" for 10% off your plan.
+
+"""
+import asyncio
+from crawl4ai import AsyncWebCrawler, BrowserConfig
+
+
+async def main():
+    # Using HTTP proxy
+    browser_config = BrowserConfig(proxy_config={"server": "http://gate.nstproxy.io:24125"})
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result = await crawler.arun(url="https://example.com")
+        print("[HTTP Proxy] Status:", result.status_code)
+
+    # Using SOCKS proxy
+    browser_config = BrowserConfig(proxy_config={"server": "socks5://gate.nstproxy.io:24125"})
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result = await crawler.arun(url="https://example.com")
+        print("[SOCKS5 Proxy] Status:", result.status_code)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/examples/nst_proxy/nstproxy_example.py

@@ -0,0 +1,39 @@
+"""
+NSTProxy Integration Examples for crawl4ai
+------------------------------------------
+
+NSTProxy is a premium residential proxy provider.
+👉 Purchase Proxies: https://nstproxy.com
+💰 Use coupon code "crawl4ai" for 10% off your plan.
+
+"""
+import asyncio
+from crawl4ai import AsyncWebCrawler, BrowserConfig
+
+
+async def main():
+    """
+    Example: Using NSTProxy with AsyncWebCrawler.
+    """
+
+    NST_TOKEN = "YOUR_NST_PROXY_TOKEN"  # Get from https://app.nstproxy.com/profile
+    CHANNEL_ID = "YOUR_NST_PROXY_CHANNEL_ID"  # Your NSTProxy Channel ID
+
+    browser_config = BrowserConfig()
+    browser_config.set_nstproxy(
+        token=NST_TOKEN,
+        channel_id=CHANNEL_ID,
+        country="ANY",  # e.g. "US", "JP", or "ANY"
+        state="",  # optional, leave empty if not needed
+        city="",  # optional, leave empty if not needed
+        session_duration=0  # Session duration in minutes,0 = rotate on every request
+    )
+
+    # === Run crawler ===
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result = await crawler.arun(url="https://example.com")
+        print("[Nstproxy] Status:", result.status_code)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/md_v2/advanced/identity-based-crawling.md

@@ -82,6 +82,42 @@ If you installed Crawl4AI (which installs Playwright under the hood), you alread
 
 ---
 
+### Creating a Profile Using the Crawl4AI CLI (Easiest)
+
+If you prefer a guided, interactive setup, use the built-in CLI to create and manage persistent browser profiles.
+
+1.⠀Launch the profile manager:
+   ```bash
+   crwl profiles
+   ```
+
+2.⠀Choose "Create new profile" and enter a profile name. A Chromium window opens so you can log in to sites and configure settings. When finished, return to the terminal and press `q` to save the profile.
+
+3.⠀Profiles are saved under `~/.crawl4ai/profiles/<profile_name>` (for example: `/home/<you>/.crawl4ai/profiles/test_profile_1`) along with a `storage_state.json` for cookies and session data.
+
+4.⠀Optionally, choose "List profiles" in the CLI to view available profiles and their paths.
+
+5.⠀Use the saved path with `BrowserConfig.user_data_dir`:
+   ```python
+   from crawl4ai import AsyncWebCrawler, BrowserConfig
+
+   profile_path = "/home/<you>/.crawl4ai/profiles/test_profile_1"
+
+   browser_config = BrowserConfig(
+       headless=True,
+       use_managed_browser=True,
+       user_data_dir=profile_path,
+       browser_type="chromium",
+   )
+
+   async with AsyncWebCrawler(config=browser_config) as crawler:
+       result = await crawler.arun(url="https://example.com/private")
+   ```
+
+The CLI also supports listing and deleting profiles, and even testing a crawl directly from the menu.
+
+---
+
 ## 3. Using Managed Browsers in Crawl4AI
 
 Once you have a data directory with your session data, pass it to **`BrowserConfig`**:

docs/md_v2/advanced/proxy-security.md

@@ -1,98 +1,304 @@
-# Proxy 
+# Proxy & Security
+
+This guide covers proxy configuration and security features in Crawl4AI, including SSL certificate analysis and proxy rotation strategies.
+
+## Understanding Proxy Configuration
+
+Crawl4AI recommends configuring proxies per request through `CrawlerRunConfig.proxy_config`. This gives you precise control, enables rotation strategies, and keeps examples simple enough to copy, paste, and run.
 
 ## Basic Proxy Setup
 
-Simple proxy configuration with `BrowserConfig`:
+Configure proxies that apply to each crawl operation:
 
 ```python
-from crawl4ai.async_configs import BrowserConfig
-
-# Using HTTP proxy
-browser_config = BrowserConfig(proxy_config={"server": "http://proxy.example.com:8080"})
-async with AsyncWebCrawler(config=browser_config) as crawler:
-    result = await crawler.arun(url="https://example.com")
-
-# Using SOCKS proxy
-browser_config = BrowserConfig(proxy_config={"server": "socks5://proxy.example.com:1080"})
-async with AsyncWebCrawler(config=browser_config) as crawler:
-    result = await crawler.arun(url="https://example.com")
-```
-
-## Authenticated Proxy
-
-Use an authenticated proxy with `BrowserConfig`:
-
-```python
-from crawl4ai.async_configs import BrowserConfig
-
-browser_config = BrowserConfig(proxy_config={
-    "server": "http://[host]:[port]",
-    "username": "[username]",
-    "password": "[password]",
-})
-async with AsyncWebCrawler(config=browser_config) as crawler:
-    result = await crawler.arun(url="https://example.com")
-```
-
-
-## Rotating Proxies 
-
-Example using a proxy rotation service dynamically:
-
-```python
-import re
-from crawl4ai import (
-    AsyncWebCrawler,
-    BrowserConfig,
-    CrawlerRunConfig,
-    CacheMode,
-    RoundRobinProxyStrategy,
-)
 import asyncio
-from crawl4ai import ProxyConfig
+from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, ProxyConfig
+
+run_config = CrawlerRunConfig(proxy_config=ProxyConfig(server="http://proxy.example.com:8080"))
+# run_config = CrawlerRunConfig(proxy_config={"server": "http://proxy.example.com:8080"})
+# run_config = CrawlerRunConfig(proxy_config="http://proxy.example.com:8080")
+
+
 async def main():
-    # Load proxies and create rotation strategy
+    browser_config = BrowserConfig()
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result = await crawler.arun(url="https://example.com", config=run_config)
+        print(f"Success: {result.success} -> {result.url}")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+!!! note "Why request-level?"
+    `CrawlerRunConfig.proxy_config` keeps each request self-contained, so swapping proxies or rotation strategies is just a matter of building a new run configuration.
+
+## Supported Proxy Formats
+
+The `ProxyConfig.from_string()` method supports multiple formats:
+
+```python
+from crawl4ai import ProxyConfig
+
+# HTTP proxy with authentication
+proxy1 = ProxyConfig.from_string("http://user:pass@192.168.1.1:8080")
+
+# HTTPS proxy
+proxy2 = ProxyConfig.from_string("https://proxy.example.com:8080")
+
+# SOCKS5 proxy
+proxy3 = ProxyConfig.from_string("socks5://proxy.example.com:1080")
+
+# Simple IP:port format
+proxy4 = ProxyConfig.from_string("192.168.1.1:8080")
+
+# IP:port:user:pass format
+proxy5 = ProxyConfig.from_string("192.168.1.1:8080:user:pass")
+```
+
+## Authenticated Proxies
+
+For proxies requiring authentication:
+
+```python
+import asyncio
+from crawl4ai import AsyncWebCrawler,BrowserConfig, CrawlerRunConfig, ProxyConfig
+
+run_config = CrawlerRunConfig(
+    proxy_config=ProxyConfig(
+        server="http://proxy.example.com:8080",
+        username="your_username",
+        password="your_password",
+    )
+)
+# Or dictionary style:
+# run_config = CrawlerRunConfig(proxy_config={
+#     "server": "http://proxy.example.com:8080",
+#     "username": "your_username",
+#     "password": "your_password",
+# })
+
+
+async def main():
+    browser_config = BrowserConfig()
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result = await crawler.arun(url="https://example.com", config=run_config)
+        print(f"Success: {result.success} -> {result.url}")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+## Environment Variable Configuration
+
+Load proxies from environment variables for easy configuration:
+
+```python
+import os
+from crawl4ai import ProxyConfig, CrawlerRunConfig
+
+# Set environment variable
+os.environ["PROXIES"] = "ip1:port1:user1:pass1,ip2:port2:user2:pass2,ip3:port3"
+
+# Load all proxies
+proxies = ProxyConfig.from_env()
+print(f"Loaded {len(proxies)} proxies")
+
+# Use first proxy
+if proxies:
+    run_config = CrawlerRunConfig(proxy_config=proxies[0])
+```
+
+## Rotating Proxies
+
+Crawl4AI supports automatic proxy rotation to distribute requests across multiple proxy servers. Rotation is applied per request using a rotation strategy on `CrawlerRunConfig`.
+
+### Proxy Rotation (recommended)
+```python
+import asyncio
+import re
+from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode, ProxyConfig
+from crawl4ai.proxy_strategy import RoundRobinProxyStrategy
+
+async def main():
+    # Load proxies from environment
     proxies = ProxyConfig.from_env()
-    #eg: export PROXIES="ip1:port1:username1:password1,ip2:port2:username2:password2"
     if not proxies:
-        print("No proxies found in environment. Set PROXIES env variable!")
+        print("No proxies found! Set PROXIES environment variable.")
         return
 
+    # Create rotation strategy
     proxy_strategy = RoundRobinProxyStrategy(proxies)
 
-    # Create configs
+    # Configure per-request with proxy rotation
     browser_config = BrowserConfig(headless=True, verbose=False)
     run_config = CrawlerRunConfig(
         cache_mode=CacheMode.BYPASS,
-        proxy_rotation_strategy=proxy_strategy
+        proxy_rotation_strategy=proxy_strategy,
     )
 
     async with AsyncWebCrawler(config=browser_config) as crawler:
         urls = ["https://httpbin.org/ip"] * (len(proxies) * 2)  # Test each proxy twice
 
-        print("\n📈 Initializing crawler with proxy rotation...")
-        async with AsyncWebCrawler(config=browser_config) as crawler:
-            print("\n🚀 Starting batch crawl with proxy rotation...")
-            results = await crawler.arun_many(
-                urls=urls,
-                config=run_config
-            )
-            for result in results:
-                if result.success:
-                    ip_match = re.search(r'(?:[0-9]{1,3}\.){3}[0-9]{1,3}', result.html)
-                    current_proxy = run_config.proxy_config if run_config.proxy_config else None
+        print(f"🚀 Testing {len(proxies)} proxies with rotation...")
+        results = await crawler.arun_many(urls=urls, config=run_config)
 
-                    if current_proxy and ip_match:
-                        print(f"URL {result.url}")
-                        print(f"Proxy {current_proxy.server} -> Response IP: {ip_match.group(0)}")
-                        verified = ip_match.group(0) == current_proxy.ip
-                        if verified:
-                            print(f"✅ Proxy working! IP matches: {current_proxy.ip}")
-                        else:
-                            print("❌ Proxy failed or IP mismatch!")
-                    print("---")
+        for i, result in enumerate(results):
+            if result.success:
+                # Extract IP from response
+                ip_match = re.search(r'(?:[0-9]{1,3}\.){3}[0-9]{1,3}', result.html)
+                if ip_match:
+                    detected_ip = ip_match.group(0)
+                    proxy_index = i % len(proxies)
+                    expected_ip = proxies[proxy_index].ip
 
-asyncio.run(main())
+                    print(f"✅ Request {i+1}: Proxy {proxy_index+1} -> IP {detected_ip}")
+                    if detected_ip == expected_ip:
+                        print("   🎯 IP matches proxy configuration")
+                    else:
+                        print(f"   ⚠️  IP mismatch (expected {expected_ip})")
+                else:
+                    print(f"❌ Request {i+1}: Could not extract IP from response")
+            else:
+                print(f"❌ Request {i+1}: Failed - {result.error_message}")
 
+if __name__ == "__main__":
+    asyncio.run(main())
 ```
 
+## SSL Certificate Analysis
+
+Combine proxy usage with SSL certificate inspection for enhanced security analysis. SSL certificate fetching is configured per request via `CrawlerRunConfig`.
+
+### Per-Request SSL Certificate Analysis
+```python
+import asyncio
+from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig
+
+run_config = CrawlerRunConfig(
+    proxy_config={
+        "server": "http://proxy.example.com:8080",
+        "username": "user",
+        "password": "pass",
+    },
+    fetch_ssl_certificate=True,  # Enable SSL certificate analysis for this request
+)
+
+
+async def main():
+    browser_config = BrowserConfig()
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        result = await crawler.arun(url="https://example.com", config=run_config)
+
+        if result.success:
+            print(f"✅ Crawled via proxy: {result.url}")
+
+            # Analyze SSL certificate
+            if result.ssl_certificate:
+                cert = result.ssl_certificate
+                print("🔒 SSL Certificate Info:")
+                print(f"   Issuer: {cert.issuer}")
+                print(f"   Subject: {cert.subject}")
+                print(f"   Valid until: {cert.valid_until}")
+                print(f"   Fingerprint: {cert.fingerprint}")
+
+                # Export certificate
+                cert.to_json("certificate.json")
+                print("💾 Certificate exported to certificate.json")
+            else:
+                print("⚠️  No SSL certificate information available")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+## Security Best Practices
+
+### 1. Proxy Rotation for Anonymity
+```python
+from crawl4ai import CrawlerRunConfig, ProxyConfig
+from crawl4ai.proxy_strategy import RoundRobinProxyStrategy
+
+# Use multiple proxies to avoid IP blocking
+proxies = ProxyConfig.from_env("PROXIES")
+strategy = RoundRobinProxyStrategy(proxies)
+
+# Configure rotation per request (recommended)
+run_config = CrawlerRunConfig(proxy_rotation_strategy=strategy)
+
+# For a fixed proxy across all requests, just reuse the same run_config instance
+static_run_config = run_config
+```
+
+### 2. SSL Certificate Verification
+```python
+from crawl4ai import CrawlerRunConfig
+
+# Always verify SSL certificates when possible
+# Per-request (affects specific requests)
+run_config = CrawlerRunConfig(fetch_ssl_certificate=True)
+```
+
+### 3. Environment Variable Security
+```bash
+# Use environment variables for sensitive proxy credentials
+# Avoid hardcoding usernames/passwords in code
+export PROXIES="ip1:port1:user1:pass1,ip2:port2:user2:pass2"
+```
+
+### 4. SOCKS5 for Enhanced Security
+```python
+from crawl4ai import CrawlerRunConfig
+
+# Prefer SOCKS5 proxies for better protocol support
+run_config = CrawlerRunConfig(proxy_config="socks5://proxy.example.com:1080")
+```
+
+## Migration from Deprecated `proxy` Parameter
+
+- "Deprecation Notice"
+    The legacy `proxy` argument on `BrowserConfig` is deprecated. Configure proxies through `CrawlerRunConfig.proxy_config` so each request fully describes its network settings.
+
+```python
+# Old (deprecated) approach
+# from crawl4ai import BrowserConfig
+# browser_config = BrowserConfig(proxy="http://proxy.example.com:8080")
+
+# New (preferred) approach
+from crawl4ai import CrawlerRunConfig
+run_config = CrawlerRunConfig(proxy_config="http://proxy.example.com:8080")
+```
+
+### Safe Logging of Proxies
+```python
+from crawl4ai import ProxyConfig
+
+def safe_proxy_repr(proxy: ProxyConfig):
+    if getattr(proxy, "username", None):
+        return f"{proxy.server} (auth: ****)"
+    return proxy.server
+```
+
+## Troubleshooting
+
+### Common Issues
+
+- "Proxy connection failed"
+    - Verify the proxy server is reachable from your network.
+    - Double-check authentication credentials.
+    - Ensure the protocol matches (`http`, `https`, or `socks5`).
+
+- "SSL certificate errors"
+    - Some proxies break SSL inspection; switch proxies if you see repeated failures.
+    - Consider temporarily disabling certificate fetching to isolate the issue.
+
+- "Environment variables not loading"
+    - Confirm `PROXIES` (or your custom env var) is set before running the script.
+    - Check formatting: `ip:port:user:pass,ip:port:user:pass`.
+
+- "Proxy rotation not working"
+    - Ensure `ProxyConfig.from_env()` actually loaded entries (`len(proxies) > 0`).
+    - Attach `proxy_rotation_strategy` to `CrawlerRunConfig`.
+    - Validate the proxy definitions you pass into the strategy.

docs/md_v2/api/parameters.md

@@ -21,21 +21,35 @@ browser_cfg = BrowserConfig(
 |-----------------------|----------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------|
 | **`browser_type`**    | `"chromium"`, `"firefox"`, `"webkit"`<br/>*(default: `"chromium"`)* | Which browser engine to use. `"chromium"` is typical for many sites, `"firefox"` or `"webkit"` for specialized tests.                 |
 | **`headless`**        | `bool` (default: `True`)               | Headless means no visible UI. `False` is handy for debugging.                                                                         |
+| **`browser_mode`**    | `str` (default: `"dedicated"`)         | How browser is initialized: `"dedicated"` (new instance), `"builtin"` (CDP background), `"custom"` (explicit CDP), `"docker"` (container). |
+| **`use_managed_browser`** | `bool` (default: `False`)          | Launch browser via CDP for advanced control. Set automatically based on `browser_mode`.                  |
+| **`cdp_url`**         | `str` (default: `None`)                | Chrome DevTools Protocol endpoint URL (e.g., `"ws://localhost:9222/devtools/browser/"`). Set automatically based on `browser_mode`.   |
+| **`debugging_port`**  | `int` (default: `9222`)                | Port for browser debugging protocol.                                                                                                   |
+| **`host`**            | `str` (default: `"localhost"`)         | Host for browser connection.                                                                                                           |
 | **`viewport_width`**  | `int` (default: `1080`)                | Initial page width (in px). Useful for testing responsive layouts.                                                                    |
 | **`viewport_height`** | `int` (default: `600`)                 | Initial page height (in px).                                                                                                          |
+| **`viewport`**        | `dict` (default: `None`)               | Viewport dimensions dict. If set, overrides `viewport_width` and `viewport_height`.                                                   |
 | **`proxy`**           | `str` (deprecated)                      | Deprecated. Use `proxy_config` instead. If set, it will be auto-converted internally. |
-| **`proxy_config`**    | `dict` (default: `None`)               | For advanced or multi-proxy needs, specify details like `{"server": "...", "username": "...", ...}`.                                  |
+| **`proxy_config`**    | `ProxyConfig or dict` (default: `None`)| For advanced or multi-proxy needs, specify `ProxyConfig` object or dict like `{"server": "...", "username": "...", "password": "..."}`.  |
 | **`use_persistent_context`** | `bool` (default: `False`)       | If `True`, uses a **persistent** browser context (keep cookies, sessions across runs). Also sets `use_managed_browser=True`.          |
 | **`user_data_dir`**   | `str or None` (default: `None`)        | Directory to store user data (profiles, cookies). Must be set if you want permanent sessions.                                         |
+| **`chrome_channel`**  | `str` (default: `"chromium"`)          | Chrome channel to launch (e.g., "chrome", "msedge"). Only for `browser_type="chromium"`. Auto-set to empty for Firefox/WebKit.       |
+| **`channel`**         | `str` (default: `"chromium"`)          | Alias for `chrome_channel`.                                                                                                           |
+| **`accept_downloads`** | `bool` (default: `False`)             | Whether to allow file downloads. Requires `downloads_path` if `True`.                                                                 |
+| **`downloads_path`**  | `str or None` (default: `None`)        | Directory to store downloaded files.                                                                                                  |
+| **`storage_state`**   | `str or dict or None` (default: `None`)| In-memory storage state (cookies, localStorage) to restore browser state.                                                             |
 | **`ignore_https_errors`** | `bool` (default: `True`)           | If `True`, continues despite invalid certificates (common in dev/staging).                                                            |
 | **`java_script_enabled`** | `bool` (default: `True`)           | Disable if you want no JS overhead, or if only static content is needed.                                                              |
+| **`sleep_on_close`**  | `bool` (default: `False`)              | Add a small delay when closing browser (can help with cleanup issues).                                                                |
 | **`cookies`**         | `list` (default: `[]`)                 | Pre-set cookies, each a dict like `{"name": "session", "value": "...", "url": "..."}`.                                                |
 | **`headers`**         | `dict` (default: `{}`)                 | Extra HTTP headers for every request, e.g. `{"Accept-Language": "en-US"}`.                                                            |
-| **`user_agent`**      | `str` (default: Chrome-based UA)       | Your custom or random user agent. `user_agent_mode="random"` can shuffle it.                                                          |
-| **`light_mode`**      | `bool` (default: `False`)              | Disables some background features for performance gains.                                                                              |
+| **`user_agent`**      | `str` (default: Chrome-based UA)       | Your custom user agent string.                                                                                                        |
+| **`user_agent_mode`** | `str` (default: `""`)                  | Set to `"random"` to randomize user agent from a pool (helps with bot detection).                                                     |
+| **`user_agent_generator_config`** | `dict` (default: `{}`)     | Configuration dict for user agent generation when `user_agent_mode="random"`.                                                         |
 | **`text_mode`**       | `bool` (default: `False`)              | If `True`, tries to disable images/other heavy content for speed.                                                                     |
-| **`use_managed_browser`** | `bool` (default: `False`)          | For advanced “managed” interactions (debugging, CDP usage). Typically set automatically if persistent context is on.                  |
+| **`light_mode`**      | `bool` (default: `False`)              | Disables some background features for performance gains.                                                                              |
 | **`extra_args`**      | `list` (default: `[]`)                 | Additional flags for the underlying browser process, e.g. `["--disable-extensions"]`.                                                |
+| **`enable_stealth`**  | `bool` (default: `False`)              | Enable playwright-stealth mode to bypass bot detection. Cannot be used with `browser_mode="builtin"`.                                |
 
 **Tips**:
 - Set `headless=False` to visually **debug** how pages load or how interactions proceed.  
@@ -70,6 +84,7 @@ We group them by category.
 |------------------------------|--------------------------------------|-------------------------------------------------------------------------------------------------|
 | **`word_count_threshold`**   | `int` (default: ~200)                | Skips text blocks below X words. Helps ignore trivial sections.                                 |
 | **`extraction_strategy`**    | `ExtractionStrategy` (default: None) | If set, extracts structured data (CSS-based, LLM-based, etc.).                                  |
+| **`chunking_strategy`**      | `ChunkingStrategy` (default: RegexChunking()) | Strategy to chunk content before extraction. Can be customized for different chunking approaches. |
 | **`markdown_generator`**     | `MarkdownGenerationStrategy` (None)  | If you want specialized markdown output (citations, filtering, chunking, etc.). Can be customized with options such as `content_source` parameter to select the HTML input source ('cleaned_html', 'raw_html', or 'fit_html').                 |
 | **`css_selector`**           | `str` (None)                         | Retains only the part of the page matching this selector. Affects the entire extraction process. |
 | **`target_elements`**        | `List[str]` (None)                   | List of CSS selectors for elements to focus on for markdown generation and data extraction, while still processing the entire page for links, media, etc. Provides more flexibility than `css_selector`. |
@@ -78,32 +93,50 @@ We group them by category.
 | **`only_text`**              | `bool` (False)                       | If `True`, tries to extract text-only content.                                                  |
 | **`prettiify`**              | `bool` (False)                       | If `True`, beautifies final HTML (slower, purely cosmetic).                                      |
 | **`keep_data_attributes`**   | `bool` (False)                       | If `True`, preserve `data-*` attributes in cleaned HTML.                                         |
+| **`keep_attrs`**             | `list` (default: [])                 | List of HTML attributes to keep during processing (e.g., `["id", "class", "data-value"]`).      |
 | **`remove_forms`**           | `bool` (False)                       | If `True`, remove all `<form>` elements.                                                        |
+| **`parser_type`**            | `str` (default: "lxml")              | HTML parser to use (e.g., "lxml", "html.parser").                                               |
+| **`scraping_strategy`**      | `ContentScrapingStrategy` (default: LXMLWebScrapingStrategy()) | Strategy to use for content scraping. Can be customized for different scraping needs (e.g., PDF extraction). |
 
 ---
 
-### B) **Caching & Session**
+### B) **Browser Location and Identity**
+
+| **Parameter**          | **Type / Default**        | **What It Does**                                                                                       |
+|------------------------|---------------------------|--------------------------------------------------------------------------------------------------------|
+| **`locale`**           | `str or None` (None)      | Browser's locale (e.g., "en-US", "fr-FR") for language preferences.                                   |
+| **`timezone_id`**      | `str or None` (None)      | Browser's timezone (e.g., "America/New_York", "Europe/Paris").                                         |
+| **`geolocation`**      | `GeolocationConfig or None` (None) | GPS coordinates configuration. Use `GeolocationConfig(latitude=..., longitude=..., accuracy=...)`. |
+| **`fetch_ssl_certificate`** | `bool` (False)       | If `True`, fetches and includes SSL certificate information in the result.                             |
+| **`proxy_config`**           | `ProxyConfig or dict or None` (None) | Proxy configuration for this specific crawl. Can override browser-level proxy settings.          |
+| **`proxy_rotation_strategy`** | `ProxyRotationStrategy` (None)      | Strategy for rotating proxies during crawl operations.                                           |
+
+---
+
+### C) **Caching & Session**
 
 | **Parameter**           | **Type / Default**     | **What It Does**                                                                                                              |
 |-------------------------|------------------------|------------------------------------------------------------------------------------------------------------------------------|
 | **`cache_mode`**        | `CacheMode or None`    | Controls how caching is handled (`ENABLED`, `BYPASS`, `DISABLED`, etc.). If `None`, typically defaults to `ENABLED`.          |
 | **`session_id`**        | `str or None`          | Assign a unique ID to reuse a single browser session across multiple `arun()` calls.                                          |
-| **`bypass_cache`**      | `bool` (False)         | If `True`, acts like `CacheMode.BYPASS`.                                                                                     |
-| **`disable_cache`**     | `bool` (False)         | If `True`, acts like `CacheMode.DISABLED`.                                                                                   |
-| **`no_cache_read`**     | `bool` (False)         | If `True`, acts like `CacheMode.WRITE_ONLY` (writes cache but never reads).                                                  |
-| **`no_cache_write`**    | `bool` (False)         | If `True`, acts like `CacheMode.READ_ONLY` (reads cache but never writes).                                                   |
+| **`bypass_cache`**      | `bool` (False)         | **Deprecated.** If `True`, acts like `CacheMode.BYPASS`. Use `cache_mode` instead.                                           |
+| **`disable_cache`**     | `bool` (False)         | **Deprecated.** If `True`, acts like `CacheMode.DISABLED`. Use `cache_mode` instead.                                         |
+| **`no_cache_read`**     | `bool` (False)         | **Deprecated.** If `True`, acts like `CacheMode.WRITE_ONLY` (writes cache but never reads). Use `cache_mode` instead.        |
+| **`no_cache_write`**    | `bool` (False)         | **Deprecated.** If `True`, acts like `CacheMode.READ_ONLY` (reads cache but never writes). Use `cache_mode` instead.         |
+| **`shared_data`**       | `dict or None` (None)  | Shared data to be passed between hooks and accessible across crawl operations.                                                |
 
 Use these for controlling whether you read or write from a local content cache. Handy for large batch crawls or repeated site visits.
 
 ---
 
-### C) **Page Navigation & Timing**
+### D) **Page Navigation & Timing**
 
 | **Parameter**              | **Type / Default**      | **What It Does**                                                                                                    |
 |----------------------------|-------------------------|----------------------------------------------------------------------------------------------------------------------|
-| **`wait_until`**           | `str` (domcontentloaded)| Condition for navigation to “complete”. Often `"networkidle"` or `"domcontentloaded"`.                               |
+| **`wait_until`**           | `str` (domcontentloaded)| Condition for navigation to "complete". Often `"networkidle"` or `"domcontentloaded"`.                               |
 | **`page_timeout`**         | `int` (60000 ms)        | Timeout for page navigation or JS steps. Increase for slow sites.                                                    |
 | **`wait_for`**             | `str or None`           | Wait for a CSS (`"css:selector"`) or JS (`"js:() => bool"`) condition before content extraction.                     |
+| **`wait_for_timeout`**     | `int or None` (None)    | Specific timeout in ms for the `wait_for` condition. If None, uses `page_timeout`.                                   |
 | **`wait_for_images`**      | `bool` (False)          | Wait for images to load before finishing. Slows down if you only want text.                                          |
 | **`delay_before_return_html`** | `float` (0.1)       | Additional pause (seconds) before final HTML is captured. Good for last-second updates.                               |
 | **`check_robots_txt`**     | `bool` (False)          | Whether to check and respect robots.txt rules before crawling. If True, caches robots.txt for efficiency.            |
@@ -112,15 +145,17 @@ Use these for controlling whether you read or write from a local content cache.
 
 ---
 
-### D) **Page Interaction**
+### E) **Page Interaction**
 
 | **Parameter**              | **Type / Default**            | **What It Does**                                                                                                                       |
 |----------------------------|--------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------|
 | **`js_code`**              | `str or list[str]` (None)      | JavaScript to run after load. E.g. `"document.querySelector('button')?.click();"`.                                                     |
-| **`js_only`**              | `bool` (False)                 | If `True`, indicates we’re reusing an existing session and only applying JS. No full reload.                                           |
+| **`c4a_script`**           | `str or list[str]` (None)      | C4A script that compiles to JavaScript. Alternative to writing raw JS.                                                                 |
+| **`js_only`**              | `bool` (False)                 | If `True`, indicates we're reusing an existing session and only applying JS. No full reload.                                           |
 | **`ignore_body_visibility`** | `bool` (True)                | Skip checking if `<body>` is visible. Usually best to keep `True`.                                                                     |
 | **`scan_full_page`**       | `bool` (False)                 | If `True`, auto-scroll the page to load dynamic content (infinite scroll).                                                              |
 | **`scroll_delay`**         | `float` (0.2)                  | Delay between scroll steps if `scan_full_page=True`.                                                                                   |
+| **`max_scroll_steps`**     | `int or None` (None)           | Maximum number of scroll steps during full page scan. If None, scrolls until entire page is loaded.                                     |
 | **`process_iframes`**      | `bool` (False)                 | Inlines iframe content for single-page extraction.                                                                                     |
 | **`remove_overlay_elements`** | `bool` (False)              | Removes potential modals/popups blocking the main content.                                                                              |
 | **`simulate_user`**        | `bool` (False)                 | Simulate user interactions (mouse movements) to avoid bot detection.                                                                    |
@@ -132,7 +167,7 @@ If your page is a single-page app with repeated JS updates, set `js_only=True` i
 
 ---
 
-### E) **Media Handling**
+### F) **Media Handling**
 
 | **Parameter**                              | **Type / Default**  | **What It Does**                                                                                         |
 |--------------------------------------------|---------------------|-----------------------------------------------------------------------------------------------------------|
@@ -141,13 +176,16 @@ If your page is a single-page app with repeated JS updates, set `js_only=True` i
 | **`screenshot_height_threshold`**          | `int` (~20000)      | If the page is taller than this, alternate screenshot strategies are used.                                |
 | **`pdf`**                                  | `bool` (False)      | If `True`, returns a PDF in `result.pdf`.                                                                 |
 | **`capture_mhtml`**                        | `bool` (False)      | If `True`, captures an MHTML snapshot of the page in `result.mhtml`. MHTML includes all page resources (CSS, images, etc.) in a single file. |
-| **`image_description_min_word_threshold`** | `int` (~50)         | Minimum words for an image’s alt text or description to be considered valid.                              |
+| **`image_description_min_word_threshold`** | `int` (~50)         | Minimum words for an image's alt text or description to be considered valid.                              |
 | **`image_score_threshold`**                | `int` (~3)          | Filter out low-scoring images. The crawler scores images by relevance (size, context, etc.).              |
 | **`exclude_external_images`**              | `bool` (False)      | Exclude images from other domains.                                                                        |
+| **`exclude_all_images`**                   | `bool` (False)      | If `True`, excludes all images from processing (both internal and external).                              |
+| **`table_score_threshold`**                | `int` (7)           | Minimum score threshold for processing a table. Lower values include more tables.                         |
+| **`table_extraction`**                     | `TableExtractionStrategy` (DefaultTableExtraction) | Strategy for table extraction. Defaults to DefaultTableExtraction with configured threshold. |
 
 ---
 
-### F) **Link/Domain Handling**
+### G) **Link/Domain Handling**
 
 | **Parameter**                | **Type / Default**      | **What It Does**                                                                                                             |
 |------------------------------|-------------------------|-----------------------------------------------------------------------------------------------------------------------------|
@@ -155,23 +193,39 @@ If your page is a single-page app with repeated JS updates, set `js_only=True` i
 | **`exclude_external_links`** | `bool` (False)          | Removes all links pointing outside the current domain.                                                                      |
 | **`exclude_social_media_links`** | `bool` (False)      | Strips links specifically to social sites (like Facebook or Twitter).                                                      |
 | **`exclude_domains`**        | `list` ([])             | Provide a custom list of domains to exclude (like `["ads.com", "trackers.io"]`).                                            |
+| **`exclude_internal_links`** | `bool` (False)          | If `True`, excludes internal links from the results.                                                                        |
+| **`score_links`**            | `bool` (False)          | If `True`, calculates intrinsic quality scores for all links using URL structure, text quality, and contextual metrics.     |
 | **`preserve_https_for_internal_links`** | `bool` (False) | If `True`, preserves HTTPS scheme for internal links even when the server redirects to HTTP. Useful for security-conscious crawling. |
 
 Use these for link-level content filtering (often to keep crawls “internal” or to remove spammy domains).
 
 ---
 
-### G) **Debug & Logging**
+### H) **Debug, Logging & Network Monitoring**
 
 | **Parameter**  | **Type / Default** | **What It Does**                                                         |
 |----------------|--------------------|---------------------------------------------------------------------------|
 | **`verbose`**  | `bool` (True)     | Prints logs detailing each step of crawling, interactions, or errors.    |
-| **`log_console`** | `bool` (False) | Logs the page’s JavaScript console output if you want deeper JS debugging.|
+| **`log_console`** | `bool` (False) | Logs the page's JavaScript console output if you want deeper JS debugging.|
+| **`capture_network_requests`** | `bool` (False) | If `True`, captures network requests made by the page in `result.captured_requests`. |
+| **`capture_console_messages`** | `bool` (False) | If `True`, captures console messages from the page in `result.console_messages`. |
 
 ---
 
+### I) **Connection & HTTP Parameters**
 
-### H) **Virtual Scroll Configuration**
+| **Parameter**               | **Type / Default**      | **What It Does**                                                                                                    |
+|-----------------------------|-------------------------|----------------------------------------------------------------------------------------------------------------------|
+| **`method`**                | `str` ("GET")          | HTTP method to use when using AsyncHTTPCrawlerStrategy (e.g., "GET", "POST").                                       |
+| **`stream`**                | `bool` (False)         | If `True`, enables streaming mode for `arun_many()` to process URLs as they complete rather than waiting for all.   |
+| **`url`**                   | `str or None` (None)   | URL for this specific config. Not typically set directly but used internally for URL-specific configurations.       |
+| **`user_agent`**            | `str or None` (None)   | Custom User-Agent string for this crawl. Can override browser-level user agent.                                     |
+| **`user_agent_mode`**       | `str or None` (None)   | Set to `"random"` to randomize user agent. Can override browser-level setting.                                      |
+| **`user_agent_generator_config`** | `dict` ({})      | Configuration for user agent generation when `user_agent_mode="random"`.                                            |
+
+---
+
+### J) **Virtual Scroll Configuration**
 
 | **Parameter**                | **Type / Default**           | **What It Does**                                                                                                                    |
 |------------------------------|------------------------------|-------------------------------------------------------------------------------------------------------------------------------------|
@@ -211,7 +265,7 @@ See [Virtual Scroll documentation](../../advanced/virtual-scroll.md) for detaile
 
 ---
 
-### I) **URL Matching Configuration**
+### K) **URL Matching Configuration**
 
 | **Parameter**          | **Type / Default**           | **What It Does**                                                                                                                    |
 |------------------------|------------------------------|-------------------------------------------------------------------------------------------------------------------------------------|
@@ -274,7 +328,25 @@ default_config = CrawlerRunConfig()  # No url_matcher = matches everything
 - If no config matches a URL and there's no default config (one without `url_matcher`), the URL will fail with "No matching configuration found"
 - Always include a default config as the last item if you want to handle all URLs
 
----## 2.2 Helper Methods
+---
+
+### L) **Advanced Crawling Features**
+
+| **Parameter**               | **Type / Default**           | **What It Does**                                                                                                                    |
+|-----------------------------|------------------------------|-------------------------------------------------------------------------------------------------------------------------------------|
+| **`deep_crawl_strategy`**   | `DeepCrawlStrategy or None` (None) | Strategy for deep/recursive crawling. Enables automatic link following and multi-level site crawling.                     |
+| **`link_preview_config`**   | `LinkPreviewConfig or dict or None` (None) | Configuration for link head extraction and scoring. Fetches and scores link metadata without full page loads.  |
+| **`experimental`**          | `dict or None` (None)       | Dictionary for experimental/beta features not yet integrated into main parameters. Use with caution.                                |
+
+**Deep Crawl Strategy** enables automatic site exploration by following links according to defined rules. Useful for sitemap generation or comprehensive site archiving.
+
+**Link Preview Config** allows efficient link discovery and scoring by fetching only the `<head>` section of linked pages, enabling smart crawl prioritization without the overhead of full page loads.
+
+**Experimental** parameters are features in beta testing. They may change or be removed in future versions. Check documentation for currently available experimental features.
+
+---
+
+## 2.2 Helper Methods
 
 Both `BrowserConfig` and `CrawlerRunConfig` provide a `clone()` method to create modified copies:
 
@@ -367,10 +439,19 @@ LLMConfig is useful to pass LLM provider config to strategies and functions that
 | **`provider`**    | `"ollama/llama3","groq/llama3-70b-8192","groq/llama3-8b-8192", "openai/gpt-4o-mini" ,"openai/gpt-4o","openai/o1-mini","openai/o1-preview","openai/o3-mini","openai/o3-mini-high","anthropic/claude-3-haiku-20240307","anthropic/claude-3-opus-20240229","anthropic/claude-3-sonnet-20240229","anthropic/claude-3-5-sonnet-20240620","gemini/gemini-pro","gemini/gemini-1.5-pro","gemini/gemini-2.0-flash","gemini/gemini-2.0-flash-exp","gemini/gemini-2.0-flash-lite-preview-02-05","deepseek/deepseek-chat"`<br/>*(default: `"openai/gpt-4o-mini"`)* | Which LLM provider to use. 
 | **`api_token`**         |1.Optional. When not provided explicitly, api_token will be read from environment variables based on provider. For example: If a gemini model is passed as provider then,`"GEMINI_API_KEY"` will be read from environment variables  <br/> 2. API token of LLM provider <br/> eg: `api_token = "gsk_1ClHGGJ7Lpn4WGybR7vNWGdyb3FY7zXEw3SCiy0BAVM9lL8CQv"` <br/> 3. Environment variable - use with prefix "env:" <br/> eg:`api_token = "env: GROQ_API_KEY"`              | API token to use for the given provider 
 | **`base_url`**         |Optional. Custom API endpoint | If your provider has a custom endpoint
+| **`backoff_base_delay`** |Optional. `int` *(default: `2`)* | Seconds to wait before the first retry when the provider throttles a request.
+| **`backoff_max_attempts`** |Optional. `int` *(default: `3`)* | Total tries (initial call + retries) before surfacing an error.
+| **`backoff_exponential_factor`** |Optional. `int` *(default: `2`)* | Multiplier that increases the wait time for each retry (`delay = base_delay * factor^attempt`).
 
 ## 3.2 Example Usage
 ```python
-llm_config = LLMConfig(provider="openai/gpt-4o-mini", api_token=os.getenv("OPENAI_API_KEY"))
+llm_config = LLMConfig(
+    provider="openai/gpt-4o-mini",
+    api_token=os.getenv("OPENAI_API_KEY"),
+    backoff_base_delay=1, # optional
+    backoff_max_attempts=5, # optional
+    backoff_exponential_factor=3, # optional
+)
 ```
 
 ## 4. Putting It All Together

docs/md_v2/apps/c4a-script/README.md

@@ -18,7 +18,7 @@ A comprehensive web-based tutorial for learning and experimenting with C4A-Scrip
 
 2. **Install Dependencies**
    ```bash
-   pip install flask
+   pip install -r requirements.txt
    ```
 
 3. **Launch the Server**
@@ -28,7 +28,7 @@ A comprehensive web-based tutorial for learning and experimenting with C4A-Scrip
 
 4. **Open in Browser**
    ```
-   http://localhost:8080
+   http://localhost:8000
    ```
 
 **🌐 Try Online**: [Live Demo](https://docs.crawl4ai.com/c4a-script/demo)
@@ -325,7 +325,7 @@ Powers the recording functionality:
 ### Configuration
 ```python
 # server.py configuration
-PORT = 8080
+PORT = 8000
 DEBUG = True
 THREADED = True
 ```
@@ -343,9 +343,9 @@ THREADED = True
 **Port Already in Use**
 ```bash
 # Kill existing process
-lsof -ti:8080 | xargs kill -9
+lsof -ti:8000 | xargs kill -9
 # Or use different port
-python server.py --port 8081
+python server.py --port 8001
 ```
 
 **Blockly Not Loading**

docs/md_v2/apps/c4a-script/server.py

@@ -216,7 +216,7 @@ def get_examples():
             'name': 'Handle Cookie Banner',
             'description': 'Accept cookies and close newsletter popup',
             'script': '''# Handle cookie banner and newsletter
-GO http://127.0.0.1:8080/playground/
+GO http://127.0.0.1:8000/playground/
 WAIT `body` 2
 IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
 IF (EXISTS `.newsletter-popup`) THEN CLICK `.close`'''
@@ -283,7 +283,7 @@ WAIT `.success-message` 5'''
     return jsonify(examples)
 
 if __name__ == '__main__':
-    port = int(os.environ.get('PORT', 8080))
+    port = int(os.environ.get('PORT', 8000))
     print(f"""
 ╔══════════════════════════════════════════════════════════╗
 ║          C4A-Script Interactive Tutorial Server          ║

docs/md_v2/blog/index.md

@@ -20,22 +20,73 @@ Ever wondered why your AI coding assistant struggles with your library despite c
 
 ## Latest Release
 
-### [Crawl4AI v0.7.4 – The Intelligent Table Extraction & Performance Update](../blog/release-v0.7.4.md)
-*August 17, 2025*
+### [Crawl4AI v0.7.8 – Stability & Bug Fix Release](../blog/release-v0.7.8.md)
+*December 2025*
 
-Crawl4AI v0.7.4 introduces revolutionary LLM-powered table extraction with intelligent chunking, performance improvements for concurrent crawling, enhanced browser management, and critical stability fixes that make Crawl4AI more robust for production workloads.
+Crawl4AI v0.7.8 is a focused stability release addressing 11 bugs reported by the community. While there are no new features, these fixes resolve important issues affecting Docker deployments, LLM extraction, URL handling, and dependency compatibility.
 
 Key highlights:
-- **🚀 LLMTableExtraction**: Revolutionary table extraction with intelligent chunking for massive tables
-- **⚡ Dispatcher Bug Fix**: Fixed sequential processing issue in arun_many for fast-completing tasks
-- **🧹 Memory Management Refactor**: Streamlined memory utilities and better resource management
-- **🔧 Browser Manager Fixes**: Resolved race conditions in concurrent page creation
-- **🔗 Advanced URL Processing**: Better handling of raw URLs and base tag link resolution
+- **🐳 Docker API Fixes**: ContentRelevanceFilter deserialization, ProxyConfig serialization, cache folder permissions
+- **🤖 LLM Improvements**: Configurable rate limiter backoff, HTML input format support, raw HTML URL handling
+- **🔗 URL Handling**: Correct relative URL resolution after JavaScript redirects
+- **📦 Dependencies**: Replaced deprecated PyPDF2 with pypdf, Pydantic v2 ConfigDict compatibility
+- **🧠 AdaptiveCrawler**: Fixed query expansion to actually use LLM instead of mock data
 
-[Read full release notes →](../blog/release-v0.7.4.md)
+[Read full release notes →](../blog/release-v0.7.8.md)
+
+## Recent Releases
+
+### [Crawl4AI v0.7.7 – The Self-Hosting & Monitoring Update](../blog/release-v0.7.7.md)
+*November 14, 2025*
+
+Crawl4AI v0.7.7 transforms Docker into a complete self-hosting platform with enterprise-grade real-time monitoring, comprehensive observability, and full operational control.
+
+Key highlights:
+- **📊 Real-time Monitoring Dashboard**: Interactive web UI with live system metrics
+- **🔌 Comprehensive Monitor API**: Complete REST API for programmatic access
+- **⚡ WebSocket Streaming**: Real-time updates every 2 seconds
+- **🔥 Smart Browser Pool**: 3-tier architecture with automatic promotion and cleanup
+
+[Read full release notes →](../blog/release-v0.7.7.md)
+
+### [Crawl4AI v0.7.6 – The Webhook Infrastructure Update](../blog/release-v0.7.6.md)
+*October 22, 2025*
+
+Crawl4AI v0.7.6 introduces comprehensive webhook support for the Docker job queue API, bringing real-time notifications to both crawling and LLM extraction workflows. No more polling!
+
+Key highlights:
+- **🪝 Complete Webhook Support**: Real-time notifications for both `/crawl/job` and `/llm/job` endpoints
+- **🔄 Reliable Delivery**: Exponential backoff retry mechanism (5 attempts: 1s → 2s → 4s → 8s → 16s)
+- **🔐 Custom Authentication**: Add custom headers for webhook authentication
+- **📊 Flexible Delivery**: Choose notification-only or include full data in payload
+- **⚙️ Global Configuration**: Set default webhook URL in config.yml for all jobs
+
+[Read full release notes →](../blog/release-v0.7.6.md)
+
+### [Crawl4AI v0.7.5 – The Docker Hooks & Security Update](../blog/release-v0.7.5.md)
+*September 29, 2025*
+
+Crawl4AI v0.7.5 introduces the powerful Docker Hooks System for complete pipeline customization, enhanced LLM integration with custom providers, HTTPS preservation for modern web security, and resolves multiple community-reported issues.
+
+Key highlights:
+- **🔧 Docker Hooks System**: Custom Python functions at 8 key pipeline points for unprecedented customization
+- **🤖 Enhanced LLM Integration**: Custom providers with temperature control and base_url configuration
+- **🔒 HTTPS Preservation**: Secure internal link handling for modern web applications
+- **🐍 Python 3.10+ Support**: Modern language features and enhanced performance
+
+[Read full release notes →](../blog/release-v0.7.5.md)
 
 ---
 
+## Older Releases
+
+| Version | Date | Highlights |
+|---------|------|------------|
+| [v0.7.4](../blog/release-v0.7.4.md) | August 2025 | LLM-powered table extraction, performance improvements |
+| [v0.7.3](../blog/release-v0.7.3.md) | July 2025 | Undetected browser, multi-URL config, memory monitoring |
+| [v0.7.1](../blog/release-v0.7.1.md) | June 2025 | Bug fixes and stability improvements |
+| [v0.7.0](../blog/release-v0.7.0.md) | May 2025 | Adaptive crawling, virtual scroll, link analysis |
+
 ## Project History
 
 Curious about how Crawl4AI has evolved? Check out our [complete changelog](https://github.com/unclecode/crawl4ai/blob/main/CHANGELOG.md) for a detailed history of all versions and updates.

docs/md_v2/blog/releases/0.7.6.md

@@ -0,0 +1,314 @@
+# Crawl4AI v0.7.6 Release Notes
+
+*Release Date: October 22, 2025*
+
+I'm excited to announce Crawl4AI v0.7.6, featuring a complete webhook infrastructure for the Docker job queue API! This release eliminates polling and brings real-time notifications to both crawling and LLM extraction workflows.
+
+## 🎯 What's New
+
+### Webhook Support for Docker Job Queue API
+
+The headline feature of v0.7.6 is comprehensive webhook support for asynchronous job processing. No more constant polling to check if your jobs are done - get instant notifications when they complete!
+
+**Key Capabilities:**
+
+- ✅ **Universal Webhook Support**: Both `/crawl/job` and `/llm/job` endpoints now support webhooks
+- ✅ **Flexible Delivery Modes**: Choose notification-only or include full data in the webhook payload
+- ✅ **Reliable Delivery**: Exponential backoff retry mechanism (5 attempts: 1s → 2s → 4s → 8s → 16s)
+- ✅ **Custom Authentication**: Add custom headers for webhook authentication
+- ✅ **Global Configuration**: Set default webhook URL in `config.yml` for all jobs
+- ✅ **Task Type Identification**: Distinguish between `crawl` and `llm_extraction` tasks
+
+### How It Works
+
+Instead of constantly checking job status:
+
+**OLD WAY (Polling):**
+```python
+# Submit job
+response = requests.post("http://localhost:11235/crawl/job", json=payload)
+task_id = response.json()['task_id']
+
+# Poll until complete
+while True:
+    status = requests.get(f"http://localhost:11235/crawl/job/{task_id}")
+    if status.json()['status'] == 'completed':
+        break
+    time.sleep(5)  # Wait and try again
+```
+
+**NEW WAY (Webhooks):**
+```python
+# Submit job with webhook
+payload = {
+    "urls": ["https://example.com"],
+    "webhook_config": {
+        "webhook_url": "https://myapp.com/webhook",
+        "webhook_data_in_payload": True
+    }
+}
+response = requests.post("http://localhost:11235/crawl/job", json=payload)
+
+# Done! Webhook will notify you when complete
+# Your webhook handler receives the results automatically
+```
+
+### Crawl Job Webhooks
+
+```bash
+curl -X POST http://localhost:11235/crawl/job \
+  -H "Content-Type: application/json" \
+  -d '{
+    "urls": ["https://example.com"],
+    "browser_config": {"headless": true},
+    "crawler_config": {"cache_mode": "bypass"},
+    "webhook_config": {
+      "webhook_url": "https://myapp.com/webhooks/crawl-complete",
+      "webhook_data_in_payload": false,
+      "webhook_headers": {
+        "X-Webhook-Secret": "your-secret-token"
+      }
+    }
+  }'
+```
+
+### LLM Extraction Job Webhooks (NEW!)
+
+```bash
+curl -X POST http://localhost:11235/llm/job \
+  -H "Content-Type: application/json" \
+  -d '{
+    "url": "https://example.com/article",
+    "q": "Extract the article title, author, and publication date",
+    "schema": "{\"type\":\"object\",\"properties\":{\"title\":{\"type\":\"string\"}}}",
+    "provider": "openai/gpt-4o-mini",
+    "webhook_config": {
+      "webhook_url": "https://myapp.com/webhooks/llm-complete",
+      "webhook_data_in_payload": true
+    }
+  }'
+```
+
+### Webhook Payload Structure
+
+**Success (with data):**
+```json
+{
+  "task_id": "llm_1698765432",
+  "task_type": "llm_extraction",
+  "status": "completed",
+  "timestamp": "2025-10-22T10:30:00.000000+00:00",
+  "urls": ["https://example.com/article"],
+  "data": {
+    "extracted_content": {
+      "title": "Understanding Web Scraping",
+      "author": "John Doe",
+      "date": "2025-10-22"
+    }
+  }
+}
+```
+
+**Failure:**
+```json
+{
+  "task_id": "crawl_abc123",
+  "task_type": "crawl",
+  "status": "failed",
+  "timestamp": "2025-10-22T10:30:00.000000+00:00",
+  "urls": ["https://example.com"],
+  "error": "Connection timeout after 30s"
+}
+```
+
+### Simple Webhook Handler Example
+
+```python
+from flask import Flask, request, jsonify
+
+app = Flask(__name__)
+
+@app.route('/webhook', methods=['POST'])
+def handle_webhook():
+    payload = request.json
+
+    task_id = payload['task_id']
+    task_type = payload['task_type']
+    status = payload['status']
+
+    if status == 'completed':
+        if 'data' in payload:
+            # Process data directly
+            data = payload['data']
+        else:
+            # Fetch from API
+            endpoint = 'crawl' if task_type == 'crawl' else 'llm'
+            response = requests.get(f'http://localhost:11235/{endpoint}/job/{task_id}')
+            data = response.json()
+
+        # Your business logic here
+        print(f"Job {task_id} completed!")
+
+    elif status == 'failed':
+        error = payload.get('error', 'Unknown error')
+        print(f"Job {task_id} failed: {error}")
+
+    return jsonify({"status": "received"}), 200
+
+app.run(port=8080)
+```
+
+## 📊 Performance Improvements
+
+- **Reduced Server Load**: Eliminates constant polling requests
+- **Lower Latency**: Instant notification vs. polling interval delay
+- **Better Resource Usage**: Frees up client connections while jobs run in background
+- **Scalable Architecture**: Handles high-volume crawling workflows efficiently
+
+## 🐛 Bug Fixes
+
+- Fixed webhook configuration serialization for Pydantic HttpUrl fields
+- Improved error handling in webhook delivery service
+- Enhanced Redis task storage for webhook config persistence
+
+## 🌍 Expected Real-World Impact
+
+### For Web Scraping Workflows
+- **Reduced Costs**: Less API calls = lower bandwidth and server costs
+- **Better UX**: Instant notifications improve user experience
+- **Scalability**: Handle 100s of concurrent jobs without polling overhead
+
+### For LLM Extraction Pipelines
+- **Async Processing**: Submit LLM extraction jobs and move on
+- **Batch Processing**: Queue multiple extractions, get notified as they complete
+- **Integration**: Easy integration with workflow automation tools (Zapier, n8n, etc.)
+
+### For Microservices
+- **Event-Driven**: Perfect for event-driven microservice architectures
+- **Decoupling**: Decouple job submission from result processing
+- **Reliability**: Automatic retries ensure webhooks are delivered
+
+## 🔄 Breaking Changes
+
+**None!** This release is fully backward compatible.
+
+- Webhook configuration is optional
+- Existing code continues to work without modification
+- Polling is still supported for jobs without webhook config
+
+## 📚 Documentation
+
+### New Documentation
+- **[WEBHOOK_EXAMPLES.md](../deploy/docker/WEBHOOK_EXAMPLES.md)** - Comprehensive webhook usage guide
+- **[docker_webhook_example.py](../docs/examples/docker_webhook_example.py)** - Working code examples
+
+### Updated Documentation
+- **[Docker README](../deploy/docker/README.md)** - Added webhook sections
+- API documentation with webhook examples
+
+## 🛠️ Migration Guide
+
+No migration needed! Webhooks are opt-in:
+
+1. **To use webhooks**: Add `webhook_config` to your job payload
+2. **To keep polling**: Continue using your existing code
+
+### Quick Start
+
+```python
+# Just add webhook_config to your existing payload
+payload = {
+    # Your existing configuration
+    "urls": ["https://example.com"],
+    "browser_config": {...},
+    "crawler_config": {...},
+
+    # NEW: Add webhook configuration
+    "webhook_config": {
+        "webhook_url": "https://myapp.com/webhook",
+        "webhook_data_in_payload": True
+    }
+}
+```
+
+## 🔧 Configuration
+
+### Global Webhook Configuration (config.yml)
+
+```yaml
+webhooks:
+  enabled: true
+  default_url: "https://myapp.com/webhooks/default"  # Optional
+  data_in_payload: false
+  retry:
+    max_attempts: 5
+    initial_delay_ms: 1000
+    max_delay_ms: 32000
+    timeout_ms: 30000
+  headers:
+    User-Agent: "Crawl4AI-Webhook/1.0"
+```
+
+## 🚀 Upgrade Instructions
+
+### Docker
+
+```bash
+# Pull the latest image
+docker pull unclecode/crawl4ai:0.7.6
+
+# Or use latest tag
+docker pull unclecode/crawl4ai:latest
+
+# Run with webhook support
+docker run -d \
+  -p 11235:11235 \
+  --env-file .llm.env \
+  --name crawl4ai \
+  unclecode/crawl4ai:0.7.6
+```
+
+### Python Package
+
+```bash
+pip install --upgrade crawl4ai
+```
+
+## 💡 Pro Tips
+
+1. **Use notification-only mode** for large results - fetch data separately to avoid large webhook payloads
+2. **Set custom headers** for webhook authentication and request tracking
+3. **Configure global default webhook** for consistent handling across all jobs
+4. **Implement idempotent webhook handlers** - same webhook may be delivered multiple times on retry
+5. **Use structured schemas** with LLM extraction for predictable webhook data
+
+## 🎬 Demo
+
+Try the release demo:
+
+```bash
+python docs/releases_review/demo_v0.7.6.py
+```
+
+This comprehensive demo showcases:
+- Crawl job webhooks (notification-only and with data)
+- LLM extraction webhooks (with JSON schema support)
+- Custom headers for authentication
+- Webhook retry mechanism
+- Real-time webhook receiver
+
+## 🙏 Acknowledgments
+
+Thank you to the community for the feedback that shaped this feature! Special thanks to everyone who requested webhook support for asynchronous job processing.
+
+## 📞 Support
+
+- **Documentation**: https://docs.crawl4ai.com
+- **GitHub Issues**: https://github.com/unclecode/crawl4ai/issues
+- **Discord**: https://discord.gg/crawl4ai
+
+---
+
+**Happy crawling with webhooks!** 🕷️🪝
+
+*- unclecode*

docs/md_v2/blog/releases/v0.7.5.md

@@ -0,0 +1,318 @@
+# 🚀 Crawl4AI v0.7.5: The Docker Hooks & Security Update
+
+*September 29, 2025 • 8 min read*
+
+---
+
+Today I'm releasing Crawl4AI v0.7.5—focused on extensibility and security. This update introduces the Docker Hooks System for pipeline customization, enhanced LLM integration, and important security improvements.
+
+## 🎯 What's New at a Glance
+
+- **Docker Hooks System**: Custom Python functions at key pipeline points with function-based API
+- **Function-Based Hooks**: New `hooks_to_string()` utility with Docker client auto-conversion
+- **Enhanced LLM Integration**: Custom providers with temperature control
+- **HTTPS Preservation**: Secure internal link handling
+- **Bug Fixes**: Resolved multiple community-reported issues
+- **Improved Docker Error Handling**: Better debugging and reliability
+
+## 🔧 Docker Hooks System: Pipeline Customization
+
+Every scraping project needs custom logic—authentication, performance optimization, content processing. Traditional solutions require forking or complex workarounds. Docker Hooks let you inject custom Python functions at 8 key points in the crawling pipeline.
+
+### Real Example: Authentication & Performance
+
+```python
+import requests
+
+# Real working hooks for httpbin.org
+hooks_config = {
+    "on_page_context_created": """
+async def hook(page, context, **kwargs):
+    print("Hook: Setting up page context")
+    # Block images to speed up crawling
+    await context.route("**/*.{png,jpg,jpeg,gif,webp}", lambda route: route.abort())
+    print("Hook: Images blocked")
+    return page
+""",
+
+    "before_retrieve_html": """
+async def hook(page, context, **kwargs):
+    print("Hook: Before retrieving HTML")
+    # Scroll to bottom to load lazy content
+    await page.evaluate("window.scrollTo(0, document.body.scrollHeight)")
+    await page.wait_for_timeout(1000)
+    print("Hook: Scrolled to bottom")
+    return page
+""",
+
+    "before_goto": """
+async def hook(page, context, url, **kwargs):
+    print(f"Hook: About to navigate to {url}")
+    # Add custom headers
+    await page.set_extra_http_headers({
+        'X-Test-Header': 'crawl4ai-hooks-test'
+    })
+    return page
+"""
+}
+
+# Test with Docker API
+payload = {
+    "urls": ["https://httpbin.org/html"],
+    "hooks": {
+        "code": hooks_config,
+        "timeout": 30
+    }
+}
+
+response = requests.post("http://localhost:11235/crawl", json=payload)
+result = response.json()
+
+if result.get('success'):
+    print("✅ Hooks executed successfully!")
+    print(f"Content length: {len(result.get('markdown', ''))} characters")
+```
+
+**Available Hook Points:**
+- `on_browser_created`: Browser setup
+- `on_page_context_created`: Page context configuration
+- `before_goto`: Pre-navigation setup
+- `after_goto`: Post-navigation processing
+- `on_user_agent_updated`: User agent changes
+- `on_execution_started`: Crawl initialization
+- `before_retrieve_html`: Pre-extraction processing
+- `before_return_html`: Final HTML processing
+
+### Function-Based Hooks API
+
+Writing hooks as strings works, but lacks IDE support and type checking. v0.7.5 introduces a function-based approach with automatic conversion!
+
+**Option 1: Using the `hooks_to_string()` Utility**
+
+```python
+from crawl4ai import hooks_to_string
+import requests
+
+# Define hooks as regular Python functions (with full IDE support!)
+async def on_page_context_created(page, context, **kwargs):
+    """Block images to speed up crawling"""
+    await context.route("**/*.{png,jpg,jpeg,gif,webp}", lambda route: route.abort())
+    await page.set_viewport_size({"width": 1920, "height": 1080})
+    return page
+
+async def before_goto(page, context, url, **kwargs):
+    """Add custom headers"""
+    await page.set_extra_http_headers({
+        'X-Crawl4AI': 'v0.7.5',
+        'X-Custom-Header': 'my-value'
+    })
+    return page
+
+# Convert functions to strings
+hooks_code = hooks_to_string({
+    "on_page_context_created": on_page_context_created,
+    "before_goto": before_goto
+})
+
+# Use with REST API
+payload = {
+    "urls": ["https://httpbin.org/html"],
+    "hooks": {"code": hooks_code, "timeout": 30}
+}
+response = requests.post("http://localhost:11235/crawl", json=payload)
+```
+
+**Option 2: Docker Client with Automatic Conversion (Recommended!)**
+
+```python
+from crawl4ai.docker_client import Crawl4aiDockerClient
+
+# Define hooks as functions (same as above)
+async def on_page_context_created(page, context, **kwargs):
+    await context.route("**/*.{png,jpg,jpeg,gif,webp}", lambda route: route.abort())
+    return page
+
+async def before_retrieve_html(page, context, **kwargs):
+    # Scroll to load lazy content
+    await page.evaluate("window.scrollTo(0, document.body.scrollHeight)")
+    await page.wait_for_timeout(1000)
+    return page
+
+# Use Docker client - conversion happens automatically!
+client = Crawl4aiDockerClient(base_url="http://localhost:11235")
+
+results = await client.crawl(
+    urls=["https://httpbin.org/html"],
+    hooks={
+        "on_page_context_created": on_page_context_created,
+        "before_retrieve_html": before_retrieve_html
+    },
+    hooks_timeout=30
+)
+
+if results and results.success:
+    print(f"✅ Hooks executed! HTML length: {len(results.html)}")
+```
+
+**Benefits of Function-Based Hooks:**
+- ✅ Full IDE support (autocomplete, syntax highlighting)
+- ✅ Type checking and linting
+- ✅ Easier to test and debug
+- ✅ Reusable across projects
+- ✅ Automatic conversion in Docker client
+- ✅ No breaking changes - string hooks still work!
+
+## 🤖 Enhanced LLM Integration
+
+Enhanced LLM integration with custom providers, temperature control, and base URL configuration.
+
+### Multi-Provider Support
+
+```python
+from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
+from crawl4ai.extraction_strategy import LLMExtractionStrategy
+
+# Test with different providers
+async def test_llm_providers():
+    # OpenAI with custom temperature
+    openai_strategy = LLMExtractionStrategy(
+        provider="gemini/gemini-2.5-flash-lite",
+        api_token="your-api-token",
+        temperature=0.7,  # New in v0.7.5
+        instruction="Summarize this page in one sentence"
+    )
+
+    async with AsyncWebCrawler() as crawler:
+        result = await crawler.arun(
+            "https://example.com",
+            config=CrawlerRunConfig(extraction_strategy=openai_strategy)
+        )
+
+        if result.success:
+            print("✅ LLM extraction completed")
+            print(result.extracted_content)
+
+# Docker API with enhanced LLM config
+llm_payload = {
+    "url": "https://example.com",
+    "f": "llm",
+    "q": "Summarize this page in one sentence.",
+    "provider": "gemini/gemini-2.5-flash-lite",
+    "temperature": 0.7
+}
+
+response = requests.post("http://localhost:11235/md", json=llm_payload)
+```
+
+**New Features:**
+- Custom `temperature` parameter for creativity control
+- `base_url` for custom API endpoints
+- Multi-provider environment variable support
+- Docker API integration
+
+## 🔒 HTTPS Preservation
+
+**The Problem:** Modern web apps require HTTPS everywhere. When crawlers downgrade internal links from HTTPS to HTTP, authentication breaks and security warnings appear.
+
+**Solution:** HTTPS preservation maintains secure protocols throughout crawling.
+
+```python
+from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, FilterChain, URLPatternFilter, BFSDeepCrawlStrategy
+
+async def test_https_preservation():
+    # Enable HTTPS preservation
+    url_filter = URLPatternFilter(
+        patterns=["^(https:\/\/)?quotes\.toscrape\.com(\/.*)?$"]
+    )
+
+    config = CrawlerRunConfig(
+        exclude_external_links=True,
+        preserve_https_for_internal_links=True,  # New in v0.7.5
+        deep_crawl_strategy=BFSDeepCrawlStrategy(
+            max_depth=2,
+            max_pages=5,
+            filter_chain=FilterChain([url_filter])
+        )
+    )
+
+    async with AsyncWebCrawler() as crawler:
+        async for result in await crawler.arun(
+            url="https://quotes.toscrape.com",
+            config=config
+        ):
+            # All internal links maintain HTTPS
+            internal_links = [link['href'] for link in result.links['internal']]
+            https_links = [link for link in internal_links if link.startswith('https://')]
+
+            print(f"HTTPS links preserved: {len(https_links)}/{len(internal_links)}")
+            for link in https_links[:3]:
+                print(f"  → {link}")
+```
+
+## 🛠️ Bug Fixes and Improvements
+
+### Major Fixes
+- **URL Processing**: Fixed '+' sign preservation in query parameters (#1332)
+- **Proxy Configuration**: Enhanced proxy string parsing (old `proxy` parameter deprecated)
+- **Docker Error Handling**: Comprehensive error messages with status codes
+- **Memory Management**: Fixed leaks in long-running sessions
+- **JWT Authentication**: Fixed Docker JWT validation issues (#1442)
+- **Playwright Stealth**: Fixed stealth features for Playwright integration (#1481)
+- **API Configuration**: Fixed config handling to prevent overriding user-provided settings (#1505)
+- **Docker Filter Serialization**: Resolved JSON encoding errors in deep crawl strategy (#1419)
+- **LLM Provider Support**: Fixed custom LLM provider integration for adaptive crawler (#1291)
+- **Performance Issues**: Resolved backoff strategy failures and timeout handling (#989)
+
+### Community-Reported Issues Fixed
+This release addresses multiple issues reported by the community through GitHub issues and Discord discussions:
+- Fixed browser configuration reference errors
+- Resolved dependency conflicts with cssselect
+- Improved error messaging for failed authentications
+- Enhanced compatibility with various proxy configurations
+- Fixed edge cases in URL normalization
+
+### Configuration Updates
+```python
+# Old proxy config (deprecated)
+# browser_config = BrowserConfig(proxy="http://proxy:8080")
+
+# New enhanced proxy config
+browser_config = BrowserConfig(
+    proxy_config={
+        "server": "http://proxy:8080",
+        "username": "optional-user",
+        "password": "optional-pass"
+    }
+)
+```
+
+## 🔄 Breaking Changes
+
+1. **Python 3.10+ Required**: Upgrade from Python 3.9
+2. **Proxy Parameter Deprecated**: Use new `proxy_config` structure
+3. **New Dependency**: Added `cssselect` for better CSS handling
+
+## 🚀 Get Started
+
+```bash
+# Install latest version
+pip install crawl4ai==0.7.5
+
+# Docker deployment
+docker pull unclecode/crawl4ai:latest
+docker run -p 11235:11235 unclecode/crawl4ai:latest
+```
+
+**Try the Demo:**
+```bash
+# Run working examples
+python docs/releases_review/demo_v0.7.5.py
+```
+
+**Resources:**
+- 📖 Documentation: [docs.crawl4ai.com](https://docs.crawl4ai.com)
+- 🐙 GitHub: [github.com/unclecode/crawl4ai](https://github.com/unclecode/crawl4ai)
+- 💬 Discord: [discord.gg/crawl4ai](https://discord.gg/jP8KfhDhyN)
+- 🐦 Twitter: [@unclecode](https://x.com/unclecode)
+
+Happy crawling! 🕷️

docs/md_v2/blog/releases/v0.7.7.md

@@ -0,0 +1,626 @@
+# 🚀 Crawl4AI v0.7.7: The Self-Hosting & Monitoring Update
+
+*November 14, 2025 • 10 min read*
+
+---
+
+Today I'm releasing Crawl4AI v0.7.7—the Self-Hosting & Monitoring Update. This release transforms Crawl4AI Docker from a simple containerized crawler into a complete self-hosting platform with enterprise-grade real-time monitoring, full operational transparency, and production-ready observability.
+
+## 🎯 What's New at a Glance
+
+- **📊 Real-time Monitoring Dashboard**: Interactive web UI with live system metrics and browser pool status
+- **🔌 Comprehensive Monitor API**: Complete REST API for programmatic access to all monitoring data
+- **⚡ WebSocket Streaming**: Real-time updates every 2 seconds for custom dashboards
+- **🎮 Control Actions**: Manual browser management (kill, restart, cleanup)
+- **🔥 Smart Browser Pool**: 3-tier architecture (permanent/hot/cold) with automatic promotion
+- **🧹 Janitor Cleanup System**: Automatic resource management with event logging
+- **📈 Production Metrics**: 6 critical metrics for operational excellence
+- **🏭 Integration Ready**: Prometheus, alerting, and log aggregation examples
+- **🐛 Critical Bug Fixes**: Async LLM extraction, DFS crawling, viewport config, and more
+
+## 📊 Real-time Monitoring Dashboard: Complete Visibility
+
+**The Problem:** Running Crawl4AI in Docker was like flying blind. Users had no visibility into what was happening inside the container—memory usage, active requests, browser pools, or errors. Troubleshooting required checking logs, and there was no way to monitor performance or manually intervene when issues occurred.
+
+**My Solution:** I built a complete real-time monitoring system with an interactive dashboard, comprehensive REST API, WebSocket streaming, and manual control actions. Now you have full transparency and control over your crawling infrastructure.
+
+### The Self-Hosting Value Proposition
+
+Before v0.7.7, Docker was just a containerized crawler. After v0.7.7, it's a complete self-hosting platform that gives you:
+
+- **🔒 Data Privacy**: Your data never leaves your infrastructure
+- **💰 Cost Control**: No per-request pricing or rate limits
+- **🎯 Full Customization**: Complete control over configurations and strategies
+- **📊 Complete Transparency**: Real-time visibility into every aspect
+- **⚡ Performance**: Direct access without network overhead
+- **🛡️ Enterprise Security**: Keep workflows behind your firewall
+
+### Interactive Monitoring Dashboard
+
+Access the dashboard at `http://localhost:11235/dashboard` to see:
+
+- **System Health Overview**: CPU, memory, network, and uptime in real-time
+- **Live Request Tracking**: Active and completed requests with full details
+- **Browser Pool Management**: Interactive table with permanent/hot/cold browsers
+- **Janitor Events Log**: Automatic cleanup activities
+- **Error Monitoring**: Full context error logs
+
+The dashboard updates every 2 seconds via WebSocket, giving you live visibility into your crawling operations.
+
+## 🔌 Monitor API: Programmatic Access
+
+**The Problem:** Monitoring dashboards are great for humans, but automation and integration require programmatic access.
+
+**My Solution:** A comprehensive REST API that exposes all monitoring data for integration with your existing infrastructure.
+
+### System Health Endpoint
+
+```python
+import httpx
+import asyncio
+
+async def monitor_system_health():
+    async with httpx.AsyncClient() as client:
+        response = await client.get("http://localhost:11235/monitor/health")
+        health = response.json()
+
+        print(f"Container Metrics:")
+        print(f"  CPU: {health['container']['cpu_percent']:.1f}%")
+        print(f"  Memory: {health['container']['memory_percent']:.1f}%")
+        print(f"  Uptime: {health['container']['uptime_seconds']}s")
+
+        print(f"\nBrowser Pool:")
+        print(f"  Permanent: {health['pool']['permanent']['active']} active")
+        print(f"  Hot Pool: {health['pool']['hot']['count']} browsers")
+        print(f"  Cold Pool: {health['pool']['cold']['count']} browsers")
+
+        print(f"\nStatistics:")
+        print(f"  Total Requests: {health['stats']['total_requests']}")
+        print(f"  Success Rate: {health['stats']['success_rate_percent']:.1f}%")
+        print(f"  Avg Latency: {health['stats']['avg_latency_ms']:.0f}ms")
+
+asyncio.run(monitor_system_health())
+```
+
+### Request Tracking
+
+```python
+async def track_requests():
+    async with httpx.AsyncClient() as client:
+        response = await client.get("http://localhost:11235/monitor/requests")
+        requests_data = response.json()
+
+        print(f"Active Requests: {len(requests_data['active'])}")
+        print(f"Completed Requests: {len(requests_data['completed'])}")
+
+        # See details of recent requests
+        for req in requests_data['completed'][:5]:
+            status_icon = "✅" if req['success'] else "❌"
+            print(f"{status_icon} {req['endpoint']} - {req['latency_ms']:.0f}ms")
+```
+
+### Browser Pool Management
+
+```python
+async def monitor_browser_pool():
+    async with httpx.AsyncClient() as client:
+        response = await client.get("http://localhost:11235/monitor/browsers")
+        browsers = response.json()
+
+        print(f"Pool Summary:")
+        print(f"  Total Browsers: {browsers['summary']['total_count']}")
+        print(f"  Total Memory: {browsers['summary']['total_memory_mb']} MB")
+        print(f"  Reuse Rate: {browsers['summary']['reuse_rate_percent']:.1f}%")
+
+        # List all browsers
+        for browser in browsers['permanent']:
+            print(f"🔥 Permanent: {browser['browser_id'][:8]}... | "
+                  f"Requests: {browser['request_count']} | "
+                  f"Memory: {browser['memory_mb']:.0f} MB")
+```
+
+### Endpoint Performance Statistics
+
+```python
+async def get_endpoint_stats():
+    async with httpx.AsyncClient() as client:
+        response = await client.get("http://localhost:11235/monitor/endpoints/stats")
+        stats = response.json()
+
+        print("Endpoint Analytics:")
+        for endpoint, data in stats.items():
+            print(f"  {endpoint}:")
+            print(f"    Requests: {data['count']}")
+            print(f"    Avg Latency: {data['avg_latency_ms']:.0f}ms")
+            print(f"    Success Rate: {data['success_rate_percent']:.1f}%")
+```
+
+### Complete API Reference
+
+The Monitor API includes these endpoints:
+
+- `GET /monitor/health` - System health with pool statistics
+- `GET /monitor/requests` - Active and completed request tracking
+- `GET /monitor/browsers` - Browser pool details and efficiency
+- `GET /monitor/endpoints/stats` - Per-endpoint performance analytics
+- `GET /monitor/timeline?minutes=5` - Time-series data for charts
+- `GET /monitor/logs/janitor?limit=10` - Cleanup activity logs
+- `GET /monitor/logs/errors?limit=10` - Error logs with context
+- `POST /monitor/actions/cleanup` - Force immediate cleanup
+- `POST /monitor/actions/kill_browser` - Kill specific browser
+- `POST /monitor/actions/restart_browser` - Restart browser
+- `POST /monitor/stats/reset` - Reset accumulated statistics
+
+## ⚡ WebSocket Streaming: Real-time Updates
+
+**The Problem:** Polling the API every few seconds wastes resources and adds latency. Real-time dashboards need instant updates.
+
+**My Solution:** WebSocket streaming with 2-second update intervals for building custom real-time dashboards.
+
+### WebSocket Integration Example
+
+```python
+import websockets
+import json
+import asyncio
+
+async def monitor_realtime():
+    uri = "ws://localhost:11235/monitor/ws"
+
+    async with websockets.connect(uri) as websocket:
+        print("Connected to real-time monitoring stream")
+
+        while True:
+            # Receive update every 2 seconds
+            data = await websocket.recv()
+            update = json.loads(data)
+
+            # Access all monitoring data
+            print(f"\n--- Update at {update['timestamp']} ---")
+            print(f"Memory: {update['health']['container']['memory_percent']:.1f}%")
+            print(f"Active Requests: {len(update['requests']['active'])}")
+            print(f"Total Browsers: {update['browsers']['summary']['total_count']}")
+
+            if update['errors']:
+                print(f"⚠️  Recent Errors: {len(update['errors'])}")
+
+asyncio.run(monitor_realtime())
+```
+
+**Expected Real-World Impact:**
+- **Custom Dashboards**: Build tailored monitoring UIs for your team
+- **Real-time Alerting**: Trigger alerts instantly when metrics exceed thresholds
+- **Integration**: Feed live data into monitoring tools like Grafana
+- **Automation**: React to events in real-time without polling
+
+## 🔥 Smart Browser Pool: 3-Tier Architecture
+
+**The Problem:** Creating a new browser for every request is slow and memory-intensive. Traditional browser pools are static and inefficient.
+
+**My Solution:** A smart 3-tier browser pool that automatically adapts to usage patterns.
+
+### How It Works
+
+```python
+import httpx
+
+async def demonstrate_browser_pool():
+    async with httpx.AsyncClient() as client:
+        # Request 1-3: Default config → Uses permanent browser
+        print("Phase 1: Using permanent browser")
+        for i in range(3):
+            await client.post(
+                "http://localhost:11235/crawl",
+                json={"urls": [f"https://httpbin.org/html?req={i}"]}
+            )
+            print(f"  Request {i+1}: Reused permanent browser")
+
+        # Request 4-6: Custom viewport → Cold pool (first use)
+        print("\nPhase 2: Custom config creates cold pool browser")
+        viewport_config = {"viewport": {"width": 1280, "height": 720}}
+        for i in range(4):
+            await client.post(
+                "http://localhost:11235/crawl",
+                json={
+                    "urls": [f"https://httpbin.org/json?v={i}"],
+                    "browser_config": viewport_config
+                }
+            )
+            if i < 2:
+                print(f"  Request {i+1}: Cold pool browser")
+            else:
+                print(f"  Request {i+1}: Promoted to hot pool! (after 3 uses)")
+
+        # Check pool status
+        response = await client.get("http://localhost:11235/monitor/browsers")
+        browsers = response.json()
+
+        print(f"\nPool Status:")
+        print(f"  Permanent: {len(browsers['permanent'])} (always active)")
+        print(f"  Hot: {len(browsers['hot'])} (frequently used configs)")
+        print(f"  Cold: {len(browsers['cold'])} (on-demand)")
+        print(f"  Reuse Rate: {browsers['summary']['reuse_rate_percent']:.1f}%")
+
+asyncio.run(demonstrate_browser_pool())
+```
+
+**Pool Tiers:**
+
+- **🔥 Permanent Browser**: Always-on, default configuration, instant response
+- **♨️ Hot Pool**: Browsers promoted after 3+ uses, kept warm for quick access
+- **❄️ Cold Pool**: On-demand browsers for variant configs, cleaned up when idle
+
+**Expected Real-World Impact:**
+- **Memory Efficiency**: 10x reduction in memory usage vs creating browsers per request
+- **Performance**: Instant access to frequently-used configurations
+- **Automatic Optimization**: Pool adapts to your usage patterns
+- **Resource Management**: Janitor automatically cleans up idle browsers
+
+## 🧹 Janitor System: Automatic Cleanup
+
+**The Problem:** Long-running crawlers accumulate idle browsers and consume memory over time.
+
+**My Solution:** An automatic janitor system that monitors and cleans up idle resources.
+
+```python
+async def monitor_janitor_activity():
+    async with httpx.AsyncClient() as client:
+        response = await client.get("http://localhost:11235/monitor/logs/janitor?limit=5")
+        logs = response.json()
+
+        print("Recent Cleanup Activities:")
+        for log in logs:
+            print(f"  {log['timestamp']}: {log['message']}")
+
+# Example output:
+# 2025-11-14 10:30:00: Cleaned up 2 cold pool browsers (idle > 5min)
+# 2025-11-14 10:25:00: Browser reuse rate: 85.3%
+# 2025-11-14 10:20:00: Hot pool browser promoted (10 requests)
+```
+
+## 🎮 Control Actions: Manual Management
+
+**The Problem:** Sometimes you need to manually intervene—kill a stuck browser, force cleanup, or restart resources.
+
+**My Solution:** Manual control actions via the API for operational troubleshooting.
+
+### Force Cleanup
+
+```python
+async def force_cleanup():
+    async with httpx.AsyncClient() as client:
+        response = await client.post("http://localhost:11235/monitor/actions/cleanup")
+        result = response.json()
+
+        print(f"Cleanup completed:")
+        print(f"  Browsers cleaned: {result.get('cleaned_count', 0)}")
+        print(f"  Memory freed: {result.get('memory_freed_mb', 0):.1f} MB")
+```
+
+### Kill Specific Browser
+
+```python
+async def kill_stuck_browser(browser_id: str):
+    async with httpx.AsyncClient() as client:
+        response = await client.post(
+            "http://localhost:11235/monitor/actions/kill_browser",
+            json={"browser_id": browser_id}
+        )
+
+        if response.status_code == 200:
+            print(f"✅ Browser {browser_id} killed successfully")
+```
+
+### Reset Statistics
+
+```python
+async def reset_stats():
+    async with httpx.AsyncClient() as client:
+        response = await client.post("http://localhost:11235/monitor/stats/reset")
+        print("📊 Statistics reset for fresh monitoring")
+```
+
+## 📈 Production Integration Patterns
+
+### Prometheus Integration
+
+```python
+# Export metrics for Prometheus scraping
+async def export_prometheus_metrics():
+    async with httpx.AsyncClient() as client:
+        health = await client.get("http://localhost:11235/monitor/health")
+        data = health.json()
+
+        # Export in Prometheus format
+        metrics = f"""
+# HELP crawl4ai_memory_usage_percent Memory usage percentage
+# TYPE crawl4ai_memory_usage_percent gauge
+crawl4ai_memory_usage_percent {data['container']['memory_percent']}
+
+# HELP crawl4ai_request_success_rate Request success rate
+# TYPE crawl4ai_request_success_rate gauge
+crawl4ai_request_success_rate {data['stats']['success_rate_percent']}
+
+# HELP crawl4ai_browser_pool_count Total browsers in pool
+# TYPE crawl4ai_browser_pool_count gauge
+crawl4ai_browser_pool_count {data['pool']['permanent']['active'] + data['pool']['hot']['count'] + data['pool']['cold']['count']}
+"""
+        return metrics
+```
+
+### Alerting Example
+
+```python
+async def check_alerts():
+    async with httpx.AsyncClient() as client:
+        health = await client.get("http://localhost:11235/monitor/health")
+        data = health.json()
+
+        # Memory alert
+        if data['container']['memory_percent'] > 80:
+            print("🚨 ALERT: Memory usage above 80%")
+            # Trigger cleanup
+            await client.post("http://localhost:11235/monitor/actions/cleanup")
+
+        # Success rate alert
+        if data['stats']['success_rate_percent'] < 90:
+            print("🚨 ALERT: Success rate below 90%")
+            # Check error logs
+            errors = await client.get("http://localhost:11235/monitor/logs/errors")
+            print(f"Recent errors: {len(errors.json())}")
+
+        # Latency alert
+        if data['stats']['avg_latency_ms'] > 5000:
+            print("🚨 ALERT: Average latency above 5s")
+```
+
+### Key Metrics to Track
+
+```python
+CRITICAL_METRICS = {
+    "memory_usage": {
+        "current": "container.memory_percent",
+        "target": "<80%",
+        "alert_threshold": ">80%",
+        "action": "Force cleanup or scale"
+    },
+    "success_rate": {
+        "current": "stats.success_rate_percent",
+        "target": ">95%",
+        "alert_threshold": "<90%",
+        "action": "Check error logs"
+    },
+    "avg_latency": {
+        "current": "stats.avg_latency_ms",
+        "target": "<2000ms",
+        "alert_threshold": ">5000ms",
+        "action": "Investigate slow requests"
+    },
+    "browser_reuse_rate": {
+        "current": "browsers.summary.reuse_rate_percent",
+        "target": ">80%",
+        "alert_threshold": "<60%",
+        "action": "Check pool configuration"
+    },
+    "total_browsers": {
+        "current": "browsers.summary.total_count",
+        "target": "<15",
+        "alert_threshold": ">20",
+        "action": "Check for browser leaks"
+    },
+    "error_frequency": {
+        "current": "len(errors)",
+        "target": "<5/hour",
+        "alert_threshold": ">10/hour",
+        "action": "Review error patterns"
+    }
+}
+```
+
+## 🐛 Critical Bug Fixes
+
+This release includes significant bug fixes that improve stability and performance:
+
+### Async LLM Extraction (#1590)
+
+**The Problem:** LLM extraction was blocking async execution, causing URLs to be processed sequentially instead of in parallel (issue #1055).
+
+**The Fix:** Resolved the blocking issue to enable true parallel processing for LLM extraction.
+
+```python
+# Before v0.7.7: Sequential processing
+# After v0.7.7: True parallel processing
+
+async with AsyncWebCrawler() as crawler:
+    urls = ["url1", "url2", "url3", "url4"]
+
+    # Now processes truly in parallel with LLM extraction
+    results = await crawler.arun_many(
+        urls,
+        config=CrawlerRunConfig(
+            extraction_strategy=LLMExtractionStrategy(...)
+        )
+    )
+    # 4x faster for parallel LLM extraction!
+```
+
+**Expected Impact:** Major performance improvement for batch LLM extraction workflows.
+
+### DFS Deep Crawling (#1607)
+
+**The Problem:** DFS (Depth-First Search) deep crawl strategy had implementation issues.
+
+**The Fix:** Enhanced DFSDeepCrawlStrategy with proper seen URL tracking and improved documentation.
+
+### Browser & Crawler Config Documentation (#1609)
+
+**The Problem:** Documentation didn't match the actual `async_configs.py` implementation.
+
+**The Fix:** Updated all configuration documentation to accurately reflect the current implementation.
+
+### Sitemap Seeder (#1598)
+
+**The Problem:** Sitemap parsing and URL normalization issues in AsyncUrlSeeder (issue #1559).
+
+**The Fix:** Added comprehensive tests and fixes for sitemap namespace parsing and URL normalization.
+
+### Remove Overlay Elements (#1529)
+
+**The Problem:** The `remove_overlay_elements` functionality wasn't working (issue #1396).
+
+**The Fix:** Fixed by properly calling the injected JavaScript function.
+
+### Viewport Configuration (#1495)
+
+**The Problem:** Viewport configuration wasn't working in managed browsers (issue #1490).
+
+**The Fix:** Added proper viewport size configuration support for browser launch.
+
+### Managed Browser CDP Timing (#1528)
+
+**The Problem:** CDP (Chrome DevTools Protocol) endpoint verification had timing issues causing connection failures (issue #1445).
+
+**The Fix:** Added exponential backoff for CDP endpoint verification to handle timing variations.
+
+### Security Updates
+
+- **pyOpenSSL**: Updated from >=24.3.0 to >=25.3.0 to address security vulnerability
+- Added verification tests for the security update
+
+### Docker Fixes
+
+- **Port Standardization**: Fixed inconsistent port usage (11234 vs 11235) - now standardized to 11235
+- **LLM Environment**: Fixed LLM API key handling for multi-provider support (PR #1537)
+- **Error Handling**: Improved Docker API error messages with comprehensive status codes
+- **Serialization**: Fixed `fit_html` property serialization in `/crawl` and `/crawl/stream` endpoints
+
+### Other Important Fixes
+
+- **arun_many Returns**: Fixed function to always return a list, even on exception (PR #1530)
+- **Webhook Serialization**: Properly serialize Pydantic HttpUrl in webhook config
+- **LLMConfig Documentation**: Fixed casing and variable name consistency (issue #1551)
+- **Python Version**: Dropped Python 3.9 support, now requires Python >=3.10
+
+## 📊 Expected Real-World Impact
+
+### For DevOps & Infrastructure Teams
+- **Full Visibility**: Know exactly what's happening inside your crawling infrastructure
+- **Proactive Monitoring**: Catch issues before they become problems
+- **Resource Optimization**: Identify memory leaks and performance bottlenecks
+- **Operational Control**: Manual intervention when automated systems need help
+
+### For Production Deployments
+- **Enterprise Observability**: Prometheus, Grafana, and alerting integration
+- **Debugging**: Real-time logs and error tracking
+- **Capacity Planning**: Historical metrics for scaling decisions
+- **SLA Monitoring**: Track success rates and latency against targets
+
+### For Development Teams
+- **Local Monitoring**: Understand crawler behavior during development
+- **Performance Testing**: Measure impact of configuration changes
+- **Troubleshooting**: Quickly identify and fix issues
+- **Learning**: See exactly how the browser pool works
+
+## 🔄 Breaking Changes
+
+**None!** This release is fully backward compatible.
+
+- All existing Docker configurations continue to work
+- No API changes to existing endpoints
+- Monitoring is additive functionality
+- No migration required
+
+## 🚀 Upgrade Instructions
+
+### Docker
+
+```bash
+# Pull the latest version
+docker pull unclecode/crawl4ai:0.7.7
+
+# Or use the latest tag
+docker pull unclecode/crawl4ai:latest
+
+# Run with monitoring enabled (default)
+docker run -d \
+  -p 11235:11235 \
+  --shm-size=1g \
+  --name crawl4ai \
+  unclecode/crawl4ai:0.7.7
+
+# Access the monitoring dashboard
+open http://localhost:11235/dashboard
+```
+
+### Python Package
+
+```bash
+# Upgrade to latest version
+pip install --upgrade crawl4ai
+
+# Or install specific version
+pip install crawl4ai==0.7.7
+```
+
+## 🎬 Try the Demo
+
+Run the comprehensive demo that showcases all monitoring features:
+
+```bash
+python docs/releases_review/demo_v0.7.7.py
+```
+
+**The demo includes:**
+1. System health overview with live metrics
+2. Request tracking with active/completed monitoring
+3. Browser pool management (permanent/hot/cold)
+4. Complete Monitor API endpoint examples
+5. WebSocket streaming demonstration
+6. Control actions (cleanup, kill, restart)
+7. Production metrics and alerting patterns
+8. Self-hosting value proposition
+
+## 📚 Documentation
+
+### New Documentation
+- **[Self-Hosting Guide](https://docs.crawl4ai.com/core/self-hosting/)** - Complete self-hosting documentation with monitoring
+- **Demo Script**: `docs/releases_review/demo_v0.7.7.py` - Working examples
+
+### Updated Documentation
+- **Docker Deployment** → **Self-Hosting** (renamed for better positioning)
+- Added comprehensive monitoring sections
+- Production integration patterns
+- WebSocket streaming examples
+
+## 💡 Pro Tips
+
+1. **Start with the dashboard** - Visit `/dashboard` to get familiar with the monitoring system
+2. **Track the 6 key metrics** - Memory, success rate, latency, reuse rate, browser count, errors
+3. **Set up alerting early** - Use the Monitor API to build alerts before issues occur
+4. **Monitor browser pool efficiency** - Aim for >80% reuse rate for optimal performance
+5. **Use WebSocket for custom dashboards** - Build tailored monitoring UIs for your team
+6. **Leverage Prometheus integration** - Export metrics for long-term storage and analysis
+7. **Check janitor logs** - Understand automatic cleanup patterns
+8. **Use control actions judiciously** - Manual interventions are for exceptional cases
+
+## 🙏 Acknowledgments
+
+Thank you to our community for the feedback, bug reports, and feature requests that shaped this release. Special thanks to everyone who contributed to the issues that were fixed in this version.
+
+The monitoring system was built based on real user needs for production deployments, and your input made it comprehensive and practical.
+
+## 📞 Support & Resources
+
+- **📖 Documentation**: [docs.crawl4ai.com](https://docs.crawl4ai.com)
+- **🐙 GitHub**: [github.com/unclecode/crawl4ai](https://github.com/unclecode/crawl4ai)
+- **💬 Discord**: [discord.gg/crawl4ai](https://discord.gg/jP8KfhDhyN)
+- **🐦 Twitter**: [@unclecode](https://x.com/unclecode)
+- **📊 Dashboard**: `http://localhost:11235/dashboard` (when running)
+
+---
+
+**Crawl4AI v0.7.7 delivers complete self-hosting with enterprise-grade monitoring. You now have full visibility and control over your web crawling infrastructure. The monitoring dashboard, comprehensive API, and WebSocket streaming give you everything needed for production deployments. Try the self-hosting platform—it's a game changer for operational excellence!**
+
+**Happy crawling with full visibility!** 🕷️📊
+
+*- unclecode*

docs/md_v2/blog/releases/v0.7.8.md

@@ -0,0 +1,327 @@
+# Crawl4AI v0.7.8: Stability & Bug Fix Release
+
+*December 2025*
+
+---
+
+I'm releasing Crawl4AI v0.7.8—a focused stability release that addresses 11 bugs reported by the community. While there are no new features in this release, these fixes resolve important issues affecting Docker deployments, LLM extraction, URL handling, and dependency compatibility.
+
+## What's Fixed at a Glance
+
+- **Docker API**: Fixed ContentRelevanceFilter deserialization, ProxyConfig serialization, and cache folder permissions
+- **LLM Extraction**: Configurable rate limiter backoff, HTML input format support, and proper URL handling for raw HTML
+- **URL Handling**: Correct relative URL resolution after JavaScript redirects
+- **Dependencies**: Replaced deprecated PyPDF2 with pypdf, Pydantic v2 ConfigDict compatibility
+- **AdaptiveCrawler**: Fixed query expansion to actually use LLM instead of hardcoded mock data
+
+## Bug Fixes
+
+### Docker & API Fixes
+
+#### ContentRelevanceFilter Deserialization (#1642)
+
+**The Problem:** When sending deep crawl requests to the Docker API with `ContentRelevanceFilter`, the server failed to deserialize the filter, causing requests to fail.
+
+**The Fix:** I added `ContentRelevanceFilter` to the public exports and enhanced the deserialization logic with dynamic imports.
+
+```python
+# This now works correctly in Docker API
+import httpx
+
+request = {
+    "urls": ["https://docs.example.com"],
+    "crawler_config": {
+        "deep_crawl_strategy": {
+            "type": "BFSDeepCrawlStrategy",
+            "max_depth": 2,
+            "filter_chain": [
+                {
+                    "type": "ContentRelevanceFilter",
+                    "query": "API documentation",
+                    "threshold": 0.3
+                }
+            ]
+        }
+    }
+}
+
+async with httpx.AsyncClient() as client:
+    response = await client.post("http://localhost:11235/crawl", json=request)
+    # Previously failed, now works!
+```
+
+#### ProxyConfig JSON Serialization (#1629)
+
+**The Problem:** `BrowserConfig.to_dict()` failed when `proxy_config` was set because `ProxyConfig` wasn't being serialized to a dictionary.
+
+**The Fix:** `ProxyConfig.to_dict()` is now called during serialization.
+
+```python
+from crawl4ai import BrowserConfig
+from crawl4ai.async_configs import ProxyConfig
+
+proxy = ProxyConfig(
+    server="http://proxy.example.com:8080",
+    username="user",
+    password="pass"
+)
+
+config = BrowserConfig(headless=True, proxy_config=proxy)
+
+# Previously raised TypeError, now works
+config_dict = config.to_dict()
+json.dumps(config_dict)  # Valid JSON
+```
+
+#### Docker Cache Folder Permissions (#1638)
+
+**The Problem:** The `.cache` folder in the Docker image had incorrect permissions, causing crawling to fail when caching was enabled.
+
+**The Fix:** Corrected ownership and permissions during image build.
+
+```bash
+# Cache now works correctly in Docker
+docker run -d -p 11235:11235 \
+    --shm-size=1g \
+    -v ./my-cache:/app/.cache \
+    unclecode/crawl4ai:0.7.8
+```
+
+---
+
+### LLM & Extraction Fixes
+
+#### Configurable Rate Limiter Backoff (#1269)
+
+**The Problem:** The LLM rate limiting backoff parameters were hardcoded, making it impossible to adjust retry behavior for different API rate limits.
+
+**The Fix:** `LLMConfig` now accepts three new parameters for complete control over retry behavior.
+
+```python
+from crawl4ai import LLMConfig
+
+# Default behavior (unchanged)
+default_config = LLMConfig(provider="openai/gpt-4o-mini")
+# backoff_base_delay=2, backoff_max_attempts=3, backoff_exponential_factor=2
+
+# Custom configuration for APIs with strict rate limits
+custom_config = LLMConfig(
+    provider="openai/gpt-4o-mini",
+    backoff_base_delay=5,           # Wait 5 seconds on first retry
+    backoff_max_attempts=5,          # Try up to 5 times
+    backoff_exponential_factor=3     # Multiply delay by 3 each attempt
+)
+
+# Retry sequence: 5s -> 15s -> 45s -> 135s -> 405s
+```
+
+#### LLM Strategy HTML Input Support (#1178)
+
+**The Problem:** `LLMExtractionStrategy` always sent markdown to the LLM, but some extraction tasks work better with HTML structure preserved.
+
+**The Fix:** Added `input_format` parameter supporting `"markdown"`, `"html"`, `"fit_markdown"`, `"cleaned_html"`, and `"fit_html"`.
+
+```python
+from crawl4ai import LLMExtractionStrategy, LLMConfig
+
+# Default: markdown input (unchanged)
+markdown_strategy = LLMExtractionStrategy(
+    llm_config=LLMConfig(provider="openai/gpt-4o-mini"),
+    instruction="Extract product information"
+)
+
+# NEW: HTML input - preserves table/list structure
+html_strategy = LLMExtractionStrategy(
+    llm_config=LLMConfig(provider="openai/gpt-4o-mini"),
+    instruction="Extract the data table preserving structure",
+    input_format="html"
+)
+
+# NEW: Filtered markdown - only relevant content
+fit_strategy = LLMExtractionStrategy(
+    llm_config=LLMConfig(provider="openai/gpt-4o-mini"),
+    instruction="Summarize the main content",
+    input_format="fit_markdown"
+)
+```
+
+#### Raw HTML URL Variable (#1116)
+
+**The Problem:** When using `url="raw:<html>..."`, the entire HTML content was being passed to extraction strategies as the URL parameter, polluting LLM prompts.
+
+**The Fix:** The URL is now correctly set to `"Raw HTML"` for raw HTML inputs.
+
+```python
+from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
+
+html = "<html><body><h1>Test</h1></body></html>"
+
+async with AsyncWebCrawler() as crawler:
+    result = await crawler.arun(
+        url=f"raw:{html}",
+        config=CrawlerRunConfig(extraction_strategy=my_strategy)
+    )
+    # extraction_strategy receives url="Raw HTML" instead of the HTML blob
+```
+
+---
+
+### URL Handling Fix
+
+#### Relative URLs After Redirects (#1268)
+
+**The Problem:** When JavaScript caused a page redirect, relative links were resolved against the original URL instead of the final URL.
+
+**The Fix:** `redirected_url` now captures the actual page URL after all JavaScript execution completes.
+
+```python
+from crawl4ai import AsyncWebCrawler
+
+async with AsyncWebCrawler() as crawler:
+    # Page at /old-page redirects via JS to /new-page
+    result = await crawler.arun(url="https://example.com/old-page")
+
+    # BEFORE: redirected_url = "https://example.com/old-page"
+    # AFTER:  redirected_url = "https://example.com/new-page"
+
+    # Links are now correctly resolved against the final URL
+    for link in result.links['internal']:
+        print(link['href'])  # Relative links resolved correctly
+```
+
+---
+
+### Dependency & Compatibility Fixes
+
+#### PyPDF2 Replaced with pypdf (#1412)
+
+**The Problem:** PyPDF2 was deprecated in 2022 and is no longer maintained.
+
+**The Fix:** Replaced with the actively maintained `pypdf` library.
+
+```python
+# Installation (unchanged)
+pip install crawl4ai[pdf]
+
+# The PDF processor now uses pypdf internally
+# No code changes required - API remains the same
+```
+
+#### Pydantic v2 ConfigDict Compatibility (#678)
+
+**The Problem:** Using the deprecated `class Config` syntax caused deprecation warnings with Pydantic v2.
+
+**The Fix:** Migrated to `model_config = ConfigDict(...)` syntax.
+
+```python
+# No more deprecation warnings when importing crawl4ai models
+from crawl4ai.models import CrawlResult
+from crawl4ai import CrawlerRunConfig, BrowserConfig
+
+# All models are now Pydantic v2 compatible
+```
+
+---
+
+### AdaptiveCrawler Fix
+
+#### Query Expansion Using LLM (#1621)
+
+**The Problem:** The `EmbeddingStrategy` in AdaptiveCrawler had commented-out LLM code and was using hardcoded mock query variations instead.
+
+**The Fix:** Uncommented and activated the LLM call for actual query expansion.
+
+```python
+# AdaptiveCrawler query expansion now actually uses the LLM
+# Instead of hardcoded variations like:
+# variations = {'queries': ['what are the best vegetables...']}
+
+# The LLM generates relevant query variations based on your actual query
+```
+
+---
+
+### Code Formatting Fix
+
+#### Import Statement Formatting (#1181)
+
+**The Problem:** When extracting code from web pages, import statements were sometimes concatenated without proper line separation.
+
+**The Fix:** Import statements now maintain proper newline separation.
+
+```python
+# BEFORE: "import osimport sysfrom pathlib import Path"
+# AFTER:
+# import os
+# import sys
+# from pathlib import Path
+```
+
+---
+
+## Breaking Changes
+
+**None!** This release is fully backward compatible.
+
+- All existing code continues to work without modification
+- New parameters have sensible defaults matching previous behavior
+- No API changes to existing functionality
+
+---
+
+## Upgrade Instructions
+
+### Python Package
+
+```bash
+pip install --upgrade crawl4ai
+# or
+pip install crawl4ai==0.7.8
+```
+
+### Docker
+
+```bash
+# Pull the latest version
+docker pull unclecode/crawl4ai:0.7.8
+
+# Run
+docker run -d -p 11235:11235 --shm-size=1g unclecode/crawl4ai:0.7.8
+```
+
+---
+
+## Verification
+
+Run the verification tests to confirm all fixes are working:
+
+```bash
+python docs/releases_review/demo_v0.7.8.py
+```
+
+This runs actual tests that verify each bug fix is properly implemented.
+
+---
+
+## Acknowledgments
+
+Thank you to everyone who reported these issues and provided detailed reproduction steps. Your bug reports make Crawl4AI better for everyone.
+
+Issues fixed: #1642, #1638, #1629, #1621, #1412, #1269, #1268, #1181, #1178, #1116, #678
+
+---
+
+## Support & Resources
+
+- **Documentation**: [docs.crawl4ai.com](https://docs.crawl4ai.com)
+- **GitHub**: [github.com/unclecode/crawl4ai](https://github.com/unclecode/crawl4ai)
+- **Discord**: [discord.gg/crawl4ai](https://discord.gg/jP8KfhDhyN)
+- **Twitter**: [@unclecode](https://x.com/unclecode)
+
+---
+
+**This stability release ensures Crawl4AI works reliably across Docker deployments, LLM extraction workflows, and various edge cases. Thank you for your continued support and feedback!**
+
+**Happy crawling!**
+
+*- unclecode*

docs/md_v2/core/browser-crawler-config.md

@@ -17,6 +17,11 @@ class BrowserConfig:
     def __init__(
         browser_type="chromium",
         headless=True,
+        browser_mode="dedicated",
+        use_managed_browser=False,
+        cdp_url=None,
+        debugging_port=9222,
+        host="localhost",
         proxy_config=None,
         viewport_width=1080,
         viewport_height=600,
@@ -25,7 +30,13 @@ class BrowserConfig:
         user_data_dir=None,
         cookies=None,
         headers=None,
-        user_agent=None,
+        user_agent=(
+            # "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:109.0) AppleWebKit/537.36 "
+            # "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 "
+            # "(KHTML, like Gecko) Chrome/116.0.5845.187 Safari/604.1 Edg/117.0.2045.47"
+            "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 Chrome/116.0.0.0 Safari/537.36"
+        ),
+        user_agent_mode="",
         text_mode=False,
         light_mode=False,
         extra_args=None,
@@ -37,17 +48,33 @@ class BrowserConfig:
 
 ### Key Fields to Note
 
-1. **`browser_type`**  
-- Options: `"chromium"`, `"firefox"`, or `"webkit"`.  
-- Defaults to `"chromium"`.  
-- If you need a different engine, specify it here.
+1.⠀**`browser_type`**  
+   - Options: `"chromium"`, `"firefox"`, or `"webkit"`.  
+   - Defaults to `"chromium"`.  
+   - If you need a different engine, specify it here.
 
-2. **`headless`**  
+2.⠀**`headless`**  
    - `True`: Runs the browser in headless mode (invisible browser).  
    - `False`: Runs the browser in visible mode, which helps with debugging.
 
-3. **`proxy_config`**  
-   - A dictionary with fields like:  
+3.⠀**`browser_mode`**  
+   - Determines how the browser should be initialized:
+     - `"dedicated"` (default): Creates a new browser instance each time
+     - `"builtin"`: Uses the builtin CDP browser running in background
+     - `"custom"`: Uses explicit CDP settings provided in `cdp_url`
+     - `"docker"`: Runs browser in Docker container with isolation
+
+4.⠀**`use_managed_browser`** & **`cdp_url`**  
+   - `use_managed_browser=True`: Launch browser using Chrome DevTools Protocol (CDP) for advanced control
+   - `cdp_url`: URL for CDP endpoint (e.g., `"ws://localhost:9222/devtools/browser/"`)
+   - Automatically set based on `browser_mode`
+
+5.⠀**`debugging_port`** & **`host`**  
+   - `debugging_port`: Port for browser debugging protocol (default: 9222)
+   - `host`: Host for browser connection (default: "localhost")
+
+6.⠀**`proxy_config`**  
+   - A `ProxyConfig` object or dictionary with fields like:  
 ```json
 {
     "server": "http://proxy.example.com:8080", 
@@ -57,35 +84,35 @@ class BrowserConfig:
 ```
    - Leave as `None` if a proxy is not required.
 
-4. **`viewport_width` & `viewport_height`**:  
+7.⠀**`viewport_width` & `viewport_height`**  
    - The initial window size.  
    - Some sites behave differently with smaller or bigger viewports.
 
-5. **`verbose`**:  
+8.⠀**`verbose`**  
    - If `True`, prints extra logs.  
    - Handy for debugging.
 
-6. **`use_persistent_context`**:  
+9.⠀**`use_persistent_context`**  
    - If `True`, uses a **persistent** browser profile, storing cookies/local storage across runs.  
    - Typically also set `user_data_dir` to point to a folder.
 
-7. **`cookies`** & **`headers`**:  
-   - If you want to start with specific cookies or add universal HTTP headers, set them here.  
-   - E.g. `cookies=[{"name": "session", "value": "abc123", "domain": "example.com"}]`.
+10.⠀**`cookies`** & **`headers`**  
+    - If you want to start with specific cookies or add universal HTTP headers to the browser context, set them here.  
+    - E.g. `cookies=[{"name": "session", "value": "abc123", "domain": "example.com"}]`.
 
-8. **`user_agent`**:  
-   - Custom User-Agent string. If `None`, a default is used.  
-   - You can also set `user_agent_mode="random"` for randomization (if you want to fight bot detection).
+11.⠀**`user_agent`** & **`user_agent_mode`**  
+    - `user_agent`: Custom User-Agent string. If `None`, a default is used.  
+    - `user_agent_mode`: Set to `"random"` for randomization (helps fight bot detection).
 
-9. **`text_mode`** & **`light_mode`**:  
-   - `text_mode=True` disables images, possibly speeding up text-only crawls.  
-   - `light_mode=True` turns off certain background features for performance.  
+12.⠀**`text_mode`** & **`light_mode`**  
+    - `text_mode=True` disables images, possibly speeding up text-only crawls.  
+    - `light_mode=True` turns off certain background features for performance.  
 
-10. **`extra_args`**:  
+13.⠀**`extra_args`**  
     - Additional flags for the underlying browser.  
     - E.g. `["--disable-extensions"]`.
 
-11. **`enable_stealth`**:  
+14.⠀**`enable_stealth`**  
     - If `True`, enables stealth mode using playwright-stealth.  
     - Modifies browser fingerprints to avoid basic bot detection.  
     - Default is `False`. Recommended for sites with bot protection.
@@ -134,9 +161,11 @@ class CrawlerRunConfig:
     def __init__(
         word_count_threshold=200,
         extraction_strategy=None,
+        chunking_strategy=RegexChunking(),
         markdown_generator=None,
-        cache_mode=None,
+        cache_mode=CacheMode.BYPASS,
         js_code=None,
+        c4a_script=None,
         wait_for=None,
         screenshot=False,
         pdf=False,
@@ -145,13 +174,18 @@ class CrawlerRunConfig:
         locale=None,            # e.g. "en-US", "fr-FR"
         timezone_id=None,       # e.g. "America/New_York"
         geolocation=None,       # GeolocationConfig object
-        # Resource Management
-        enable_rate_limiting=False,
-        rate_limit_config=None,
-        memory_threshold_percent=70.0,
-        check_interval=1.0,
-        max_session_permit=20,
-        display_mode=None,
+        # Proxy Configuration
+        proxy_config=None,
+        proxy_rotation_strategy=None,
+        # Page Interaction Parameters
+        scan_full_page=False,
+        scroll_delay=0.2,
+        wait_until="domcontentloaded",
+        page_timeout=60000,
+        delay_before_return_html=0.1,
+        # URL Matching Parameters
+        url_matcher=None,       # For URL-specific configurations
+        match_mode=MatchMode.OR,
         verbose=True,
         stream=False,  # Enable streaming for arun_many()
         # ... other advanced parameters omitted
@@ -161,69 +195,68 @@ class CrawlerRunConfig:
 
 ### Key Fields to Note
 
-1. **`word_count_threshold`**:  
+1.⠀**`word_count_threshold`**:  
    - The minimum word count before a block is considered.  
    - If your site has lots of short paragraphs or items, you can lower it.
 
-2. **`extraction_strategy`**:  
+2.⠀**`extraction_strategy`**:  
    - Where you plug in JSON-based extraction (CSS, LLM, etc.).  
    - If `None`, no structured extraction is done (only raw/cleaned HTML + markdown).
 
-3. **`markdown_generator`**:  
+3.⠀**`chunking_strategy`**:  
+   - Strategy to chunk content before extraction.  
+   - Defaults to `RegexChunking()`. Can be customized for different chunking approaches.
+
+4.⠀**`markdown_generator`**:  
    - E.g., `DefaultMarkdownGenerator(...)`, controlling how HTML→Markdown conversion is done.  
    - If `None`, a default approach is used.
 
-4. **`cache_mode`**:  
+5.⠀**`cache_mode`**:  
    - Controls caching behavior (`ENABLED`, `BYPASS`, `DISABLED`, etc.).  
-   - If `None`, defaults to some level of caching or you can specify `CacheMode.ENABLED`.
+   - Defaults to `CacheMode.BYPASS`.
 
-5. **`js_code`**:  
-   - A string or list of JS strings to execute.  
+6.⠀**`js_code`** & **`c4a_script`**:  
+   - `js_code`: A string or list of JavaScript strings to execute.  
+   - `c4a_script`: C4A script that compiles to JavaScript.
    - Great for "Load More" buttons or user interactions.  
 
-6. **`wait_for`**:  
+7.⠀**`wait_for`**:  
    - A CSS or JS expression to wait for before extracting content.  
    - Common usage: `wait_for="css:.main-loaded"` or `wait_for="js:() => window.loaded === true"`.
 
-7. **`screenshot`**, **`pdf`**, & **`capture_mhtml`**:  
+8.⠀**`screenshot`**, **`pdf`**, & **`capture_mhtml`**:  
    - If `True`, captures a screenshot, PDF, or MHTML snapshot after the page is fully loaded.  
    - The results go to `result.screenshot` (base64), `result.pdf` (bytes), or `result.mhtml` (string).
 
-8. **Location Parameters**:  
+9.⠀**Location Parameters**:  
    - **`locale`**: Browser's locale (e.g., `"en-US"`, `"fr-FR"`) for language preferences
    - **`timezone_id`**: Browser's timezone (e.g., `"America/New_York"`, `"Europe/Paris"`)
    - **`geolocation`**: GPS coordinates via `GeolocationConfig(latitude=48.8566, longitude=2.3522)`
    - See [Identity Based Crawling](../advanced/identity-based-crawling.md#7-locale-timezone-and-geolocation-control)
 
-9. **`verbose`**:  
-   - Logs additional runtime details.  
-   - Overlaps with the browser's verbosity if also set to `True` in `BrowserConfig`.
+10.⠀**Proxy Configuration**:  
+    - **`proxy_config`**: Proxy server configuration (ProxyConfig object or dict) e.g. {"server": "...", "username": "...", "password"}
+    - **`proxy_rotation_strategy`**: Strategy for rotating proxies during crawls
 
-10. **`enable_rate_limiting`**:  
-   - If `True`, enables rate limiting for batch processing.  
-   - Requires `rate_limit_config` to be set.
+11.⠀**Page Interaction Parameters**:  
+    - **`scan_full_page`**: If `True`, scroll through the entire page to load all content
+    - **`wait_until`**: Condition to wait for when navigating (e.g., "domcontentloaded", "networkidle")
+    - **`page_timeout`**: Timeout in milliseconds for page operations (default: 60000)
+    - **`delay_before_return_html`**: Delay in seconds before retrieving final HTML.
 
-11. **`memory_threshold_percent`**:  
-    - The memory threshold (as a percentage) to monitor.  
-    - If exceeded, the crawler will pause or slow down.
-
-12. **`check_interval`**:  
-    - The interval (in seconds) to check system resources.  
-    - Affects how often memory and CPU usage are monitored.
-
-13. **`max_session_permit`**:  
-    - The maximum number of concurrent crawl sessions.  
-    - Helps prevent overwhelming the system.
-
-14. **`url_matcher`** & **`match_mode`**:  
+12.⠀**`url_matcher`** & **`match_mode`**:  
     - Enable URL-specific configurations when used with `arun_many()`.
     - Set `url_matcher` to patterns (glob, function, or list) to match specific URLs.
     - Use `match_mode` (OR/AND) to control how multiple patterns combine.
     - See [URL-Specific Configurations](../api/arun_many.md#url-specific-configurations) for examples.
 
-15. **`display_mode`**:  
-    - The display mode for progress information (`DETAILED`, `BRIEF`, etc.).  
-    - Affects how much information is printed during the crawl.
+13.⠀**`verbose`**:  
+    - Logs additional runtime details.  
+    - Overlaps with the browser's verbosity if also set to `True` in `BrowserConfig`.
+
+14.⠀**`stream`**:  
+    - If `True`, enables streaming mode for `arun_many()` to process URLs as they complete.
+    - Allows handling results incrementally instead of waiting for all URLs to finish.
 
 
 ### Helper Methods
@@ -263,20 +296,32 @@ The `clone()` method:
 
 ### Key fields to note
 
-1. **`provider`**:  
+1.⠀**`provider`**:  
 - Which LLM provider to use. 
 - Possible values are `"ollama/llama3","groq/llama3-70b-8192","groq/llama3-8b-8192", "openai/gpt-4o-mini" ,"openai/gpt-4o","openai/o1-mini","openai/o1-preview","openai/o3-mini","openai/o3-mini-high","anthropic/claude-3-haiku-20240307","anthropic/claude-3-opus-20240229","anthropic/claude-3-sonnet-20240229","anthropic/claude-3-5-sonnet-20240620","gemini/gemini-pro","gemini/gemini-1.5-pro","gemini/gemini-2.0-flash","gemini/gemini-2.0-flash-exp","gemini/gemini-2.0-flash-lite-preview-02-05","deepseek/deepseek-chat"`<br/>*(default: `"openai/gpt-4o-mini"`)*
 
-2. **`api_token`**:  
+2.⠀**`api_token`**:  
     - Optional. When not provided explicitly, api_token will be read from environment variables based on provider. For example: If a gemini model is passed as provider then,`"GEMINI_API_KEY"` will be read from environment variables  
     - API token of LLM provider <br/> eg: `api_token = "gsk_1ClHGGJ7Lpn4WGybR7vNWGdyb3FY7zXEw3SCiy0BAVM9lL8CQv"`
     - Environment variable - use with prefix "env:" <br/> eg:`api_token = "env: GROQ_API_KEY"`            
 
-3. **`base_url`**:  
+3.⠀**`base_url`**:  
    - If your provider has a custom endpoint
 
+4.⠀**Retry/backoff controls** *(optional)*:  
+   - `backoff_base_delay` *(default `2` seconds)* – base delay inserted before the first retry when the provider returns a rate-limit response.  
+   - `backoff_max_attempts` *(default `3`)* – total number of attempts (initial call plus retries) before the request is surfaced as an error.  
+   - `backoff_exponential_factor` *(default `2`)* – growth rate for the retry delay (`delay = base_delay * factor^attempt`).  
+   - These values are forwarded to the shared `perform_completion_with_backoff` helper, ensuring every strategy that consumes your `LLMConfig` honors the same throttling policy.
+
 ```python
-llm_config = LLMConfig(provider="openai/gpt-4o-mini", api_token=os.getenv("OPENAI_API_KEY"))
+llm_config = LLMConfig(
+    provider="openai/gpt-4o-mini",
+    api_token=os.getenv("OPENAI_API_KEY"),
+    backoff_base_delay=1, # optional
+    backoff_max_attempts=5, # optional
+    backoff_exponential_factor=3, #optional
+)
 ```
 
 ## 4. Putting It All Together

docs/md_v2/core/c4a-script.md

@@ -69,12 +69,12 @@ The tutorial includes a Flask-based web interface with:
 cd docs/examples/c4a_script/tutorial/
 
 # Install dependencies
-pip install flask
+pip install -r requirements.txt
 
 # Launch the tutorial server
-python app.py
+python server.py
 
-# Open http://localhost:5000 in your browser
+# Open http://localhost:8000 in your browser
 ```
 
 ## Core Concepts
@@ -111,8 +111,8 @@ CLICK `.submit-btn`
 # By attribute
 CLICK `button[type="submit"]`
 
-# By text content
-CLICK `button:contains("Sign In")`
+# By accessible attributes
+CLICK `button[aria-label="Search"][title="Search"]`
 
 # Complex selectors
 CLICK `.form-container input[name="email"]`

docs/md_v2/core/examples.md

@@ -11,6 +11,12 @@ This page provides a comprehensive list of example scripts that demonstrate vari
 | Quickstart Set 1 | Basic examples for getting started with Crawl4AI. | [View Code](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/quickstart_examples_set_1.py) |
 | Quickstart Set 2 | More advanced examples for working with Crawl4AI. | [View Code](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/quickstart_examples_set_2.py) |
 
+## Proxies
+
+| Example  | Description | Link |
+|----------|--------------|------|
+| **NSTProxy** | [NSTProxy](https://www.nstproxy.com/?utm_source=crawl4ai) Seamlessly integrates with crawl4ai — no setup required. Access high-performance residential, datacenter, ISP, and IPv6 proxies with smart rotation and anti-blocking technology. Starts from $0.1/GB. Use code crawl4ai for 10% off. | [View Code](https://github.com/unclecode/crawl4ai/tree/main/docs/examples/proxy) |
+
 ## Browser & Crawling Features
 
 | Example | Description | Link |
@@ -56,13 +62,14 @@ This page provides a comprehensive list of example scripts that demonstrate vari
 
 ## Anti-Bot & Stealth Features
 
-| Example | Description | Link |
-|---------|-------------|------|
-| Stealth Mode Quick Start | Five practical examples showing how to use stealth mode for bypassing basic bot detection. | [View Code](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/stealth_mode_quick_start.py) |
+| Example                    | Description | Link |
+|----------------------------|-------------|------|
+| Stealth Mode Quick Start   | Five practical examples showing how to use stealth mode for bypassing basic bot detection. | [View Code](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/stealth_mode_quick_start.py) |
 | Stealth Mode Comprehensive | Comprehensive demonstration of stealth mode features with bot detection testing and comparisons. | [View Code](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/stealth_mode_example.py) |
-| Undetected Browser | Simple example showing how to use the undetected browser adapter. | [View Code](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/hello_world_undetected.py) |
-| Undetected Browser Demo | Basic demo comparing regular and undetected browser modes. | [View Code](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/undetected_simple_demo.py) |
-| Undetected Tests | Advanced tests comparing regular vs undetected browsers on various bot detection services. | [View Folder](https://github.com/unclecode/crawl4ai/tree/main/docs/examples/undetectability/) |
+| Undetected Browser         | Simple example showing how to use the undetected browser adapter. | [View Code](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/hello_world_undetected.py) |
+| Undetected Browser Demo    | Basic demo comparing regular and undetected browser modes. | [View Code](https://github.com/unclecode/crawl4ai/blob/main/docs/examples/undetected_simple_demo.py) |
+| Undetected Tests           | Advanced tests comparing regular vs undetected browsers on various bot detection services. | [View Folder](https://github.com/unclecode/crawl4ai/tree/main/docs/examples/undetectability/) |
+| CapSolver Captcha Solver   | Seamlessly integrate with [CapSolver](https://www.capsolver.com/?utm_source=crawl4ai&utm_medium=github_pr&utm_campaign=crawl4ai_integration) to automatically solve reCAPTCHA v2/v3, Cloudflare Turnstile / Challenges, AWS WAF and more for uninterrupted scraping and automation. | [View Folder](https://github.com/unclecode/crawl4ai/tree/main/docs/examples/capsolver_captcha_solver/) |
 
 ## Customization & Security
 

docs/md_v2/core/self-hosting.md

@@ -22,18 +22,6 @@ When you self-host, you can scale from a single container to a full browser infr
   - [Option 1: Using Pre-built Docker Hub Images (Recommended)](#option-1-using-pre-built-docker-hub-images-recommended)
   - [Option 2: Using Docker Compose](#option-2-using-docker-compose)
   - [Option 3: Manual Local Build & Run](#option-3-manual-local-build--run)
-- [Dockerfile Parameters](#dockerfile-parameters)
-- [Using the API](#using-the-api)
-  - [Playground Interface](#playground-interface)
-  - [Python SDK](#python-sdk)
-  - [Understanding Request Schema](#understanding-request-schema)
-  - [REST API Examples](#rest-api-examples)
-- [Additional API Endpoints](#additional-api-endpoints)
-  - [HTML Extraction Endpoint](#html-extraction-endpoint)
-  - [Screenshot Endpoint](#screenshot-endpoint)
-  - [PDF Export Endpoint](#pdf-export-endpoint)
-  - [JavaScript Execution Endpoint](#javascript-execution-endpoint)
-  - [Library Context Endpoint](#library-context-endpoint)
 - [MCP (Model Context Protocol) Support](#mcp-model-context-protocol-support)
   - [What is MCP?](#what-is-mcp)
   - [Connecting via MCP](#connecting-via-mcp)
@@ -79,13 +67,13 @@ Pull and run images directly from Docker Hub without building locally.
 
 #### 1. Pull the Image
 
-Our latest release is `0.7.3`. Images are built with multi-arch manifests, so Docker automatically pulls the correct version for your system.
+Our latest release is `0.7.6`. Images are built with multi-arch manifests, so Docker automatically pulls the correct version for your system.
 
-> 💡 **Note**: The `latest` tag points to the stable `0.7.3` version.
+> 💡 **Note**: The `latest` tag points to the stable `0.7.6` version.
 
 ```bash
 # Pull the latest version
-docker pull unclecode/crawl4ai:0.7.3
+docker pull unclecode/crawl4ai:0.7.6
 
 # Or pull using the latest tag
 docker pull unclecode/crawl4ai:latest
@@ -157,7 +145,7 @@ docker stop crawl4ai && docker rm crawl4ai
 #### Docker Hub Versioning Explained
 
 *   **Image Name:** `unclecode/crawl4ai`
-*   **Tag Format:** `LIBRARY_VERSION[-SUFFIX]` (e.g., `0.7.3`)
+*   **Tag Format:** `LIBRARY_VERSION[-SUFFIX]` (e.g., `0.7.6`)
     *   `LIBRARY_VERSION`: The semantic version of the core `crawl4ai` Python library
     *   `SUFFIX`: Optional tag for release candidates (``) and revisions (`r1`)
 *   **`latest` Tag:** Points to the most recent stable version
@@ -853,6 +841,733 @@ else:
 
 > 💡 **Remember**: Always test your hooks on safe, known websites first before using them on production sites. Never crawl sites that you don't have permission to access or that might be malicious.
 
+### Hooks Utility: Function-Based Approach (Python)
+
+For Python developers, Crawl4AI provides a more convenient way to work with hooks using the `hooks_to_string()` utility function and Docker client integration.
+
+#### Why Use Function-Based Hooks?
+
+**String-Based Approach (shown above)**:
+```python
+hooks_code = {
+    "on_page_context_created": """
+async def hook(page, context, **kwargs):
+    await page.set_viewport_size({"width": 1920, "height": 1080})
+    return page
+"""
+}
+```
+
+**Function-Based Approach (recommended for Python)**:
+```python
+from crawl4ai import Crawl4aiDockerClient
+
+async def my_hook(page, context, **kwargs):
+    await page.set_viewport_size({"width": 1920, "height": 1080})
+    return page
+
+async with Crawl4aiDockerClient(base_url="http://localhost:11235") as client:
+    result = await client.crawl(
+        ["https://example.com"],
+        hooks={"on_page_context_created": my_hook}
+    )
+```
+
+**Benefits**:
+- ✅ Write hooks as regular Python functions
+- ✅ Full IDE support (autocomplete, syntax highlighting, type checking)
+- ✅ Easy to test and debug
+- ✅ Reusable hook libraries
+- ✅ Automatic conversion to API format
+
+#### Using the Hooks Utility
+
+The `hooks_to_string()` utility converts Python function objects to the string format required by the API:
+
+```python
+from crawl4ai import hooks_to_string
+
+# Define your hooks as functions
+async def setup_hook(page, context, **kwargs):
+    await page.set_viewport_size({"width": 1920, "height": 1080})
+    await context.add_cookies([{
+        "name": "session",
+        "value": "token",
+        "domain": ".example.com"
+    }])
+    return page
+
+async def scroll_hook(page, context, **kwargs):
+    await page.evaluate("window.scrollTo(0, document.body.scrollHeight)")
+    return page
+
+# Convert to string format
+hooks_dict = {
+    "on_page_context_created": setup_hook,
+    "before_retrieve_html": scroll_hook
+}
+hooks_string = hooks_to_string(hooks_dict)
+
+# Now use with REST API or Docker client
+# hooks_string contains the string representations
+```
+
+#### Docker Client with Automatic Conversion
+
+The Docker client automatically detects and converts function objects:
+
+```python
+from crawl4ai import Crawl4aiDockerClient
+
+async def auth_hook(page, context, **kwargs):
+    """Add authentication cookies"""
+    await context.add_cookies([{
+        "name": "auth_token",
+        "value": "your_token",
+        "domain": ".example.com"
+    }])
+    return page
+
+async def performance_hook(page, context, **kwargs):
+    """Block unnecessary resources"""
+    await context.route("**/*.{png,jpg,gif}", lambda r: r.abort())
+    await context.route("**/analytics/*", lambda r: r.abort())
+    return page
+
+async with Crawl4aiDockerClient(base_url="http://localhost:11235") as client:
+    # Pass functions directly - automatic conversion!
+    result = await client.crawl(
+        ["https://example.com"],
+        hooks={
+            "on_page_context_created": performance_hook,
+            "before_goto": auth_hook
+        },
+        hooks_timeout=30  # Optional timeout in seconds (1-120)
+    )
+
+    print(f"Success: {result.success}")
+    print(f"HTML: {len(result.html)} chars")
+```
+
+#### Creating Reusable Hook Libraries
+
+Build collections of reusable hooks:
+
+```python
+# hooks_library.py
+class CrawlHooks:
+    """Reusable hook collection for common crawling tasks"""
+
+    @staticmethod
+    async def block_images(page, context, **kwargs):
+        """Block all images to speed up crawling"""
+        await context.route("**/*.{png,jpg,jpeg,gif,webp}", lambda r: r.abort())
+        return page
+
+    @staticmethod
+    async def block_analytics(page, context, **kwargs):
+        """Block analytics and tracking scripts"""
+        tracking_domains = [
+            "**/google-analytics.com/*",
+            "**/googletagmanager.com/*",
+            "**/facebook.com/tr/*",
+            "**/doubleclick.net/*"
+        ]
+        for domain in tracking_domains:
+            await context.route(domain, lambda r: r.abort())
+        return page
+
+    @staticmethod
+    async def scroll_infinite(page, context, **kwargs):
+        """Handle infinite scroll to load more content"""
+        previous_height = 0
+        for i in range(5):  # Max 5 scrolls
+            current_height = await page.evaluate("document.body.scrollHeight")
+            if current_height == previous_height:
+                break
+            await page.evaluate("window.scrollTo(0, document.body.scrollHeight)")
+            await page.wait_for_timeout(1000)
+            previous_height = current_height
+        return page
+
+    @staticmethod
+    async def wait_for_dynamic_content(page, context, url, response, **kwargs):
+        """Wait for dynamic content to load"""
+        await page.wait_for_timeout(2000)
+        try:
+            # Click "Load More" if present
+            load_more = await page.query_selector('[class*="load-more"]')
+            if load_more:
+                await load_more.click()
+                await page.wait_for_timeout(1000)
+        except:
+            pass
+        return page
+
+# Use in your application
+from hooks_library import CrawlHooks
+from crawl4ai import Crawl4aiDockerClient
+
+async def crawl_with_optimizations(url):
+    async with Crawl4aiDockerClient() as client:
+        result = await client.crawl(
+            [url],
+            hooks={
+                "on_page_context_created": CrawlHooks.block_images,
+                "before_retrieve_html": CrawlHooks.scroll_infinite
+            }
+        )
+        return result
+```
+
+#### Choosing the Right Approach
+
+| Approach | Best For | IDE Support | Language |
+|----------|----------|-------------|----------|
+| **String-based** | Non-Python clients, REST APIs, other languages | ❌ None | Any |
+| **Function-based** | Python applications, local development | ✅ Full | Python only |
+| **Docker Client** | Python apps with automatic conversion | ✅ Full | Python only |
+
+**Recommendation**:
+- **Python applications**: Use Docker client with function objects (easiest)
+- **Non-Python or REST API**: Use string-based hooks (most flexible)
+- **Manual control**: Use `hooks_to_string()` utility (middle ground)
+
+#### Complete Example with Function Hooks
+
+```python
+from crawl4ai import Crawl4aiDockerClient, BrowserConfig, CrawlerRunConfig, CacheMode
+
+# Define hooks as regular Python functions
+async def setup_environment(page, context, **kwargs):
+    """Setup crawling environment"""
+    # Set viewport
+    await page.set_viewport_size({"width": 1920, "height": 1080})
+
+    # Block resources for speed
+    await context.route("**/*.{png,jpg,gif}", lambda r: r.abort())
+
+    # Add custom headers
+    await page.set_extra_http_headers({
+        "Accept-Language": "en-US",
+        "X-Custom-Header": "Crawl4AI"
+    })
+
+    print("[HOOK] Environment configured")
+    return page
+
+async def extract_content(page, context, **kwargs):
+    """Extract and prepare content"""
+    # Scroll to load lazy content
+    await page.evaluate("window.scrollTo(0, document.body.scrollHeight)")
+    await page.wait_for_timeout(1000)
+
+    # Extract metadata
+    metadata = await page.evaluate('''() => ({
+        title: document.title,
+        links: document.links.length,
+        images: document.images.length
+    })''')
+
+    print(f"[HOOK] Page metadata: {metadata}")
+    return page
+
+async def main():
+    async with Crawl4aiDockerClient(base_url="http://localhost:11235", verbose=True) as client:
+        # Configure crawl
+        browser_config = BrowserConfig(headless=True)
+        crawler_config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS)
+
+        # Crawl with hooks
+        result = await client.crawl(
+            ["https://httpbin.org/html"],
+            browser_config=browser_config,
+            crawler_config=crawler_config,
+            hooks={
+                "on_page_context_created": setup_environment,
+                "before_retrieve_html": extract_content
+            },
+            hooks_timeout=30
+        )
+
+        if result.success:
+            print(f"✅ Crawl successful!")
+            print(f"   URL: {result.url}")
+            print(f"   HTML: {len(result.html)} chars")
+            print(f"   Markdown: {len(result.markdown)} chars")
+        else:
+            print(f"❌ Crawl failed: {result.error_message}")
+
+if __name__ == "__main__":
+    import asyncio
+    asyncio.run(main())
+```
+
+#### Additional Resources
+
+- **Comprehensive Examples**: See `/docs/examples/hooks_docker_client_example.py` for Python function-based examples
+- **REST API Examples**: See `/docs/examples/hooks_rest_api_example.py` for string-based examples
+- **Comparison Guide**: See `/docs/examples/README_HOOKS.md` for detailed comparison
+- **Utility Documentation**: See `/docs/hooks-utility-guide.md` for complete guide
+
+---
+
+## Job Queue & Webhook API
+
+The Docker deployment includes a powerful asynchronous job queue system with webhook support for both crawling and LLM extraction tasks. Instead of waiting for long-running operations to complete, submit jobs and receive real-time notifications via webhooks when they finish.
+
+### Why Use the Job Queue API?
+
+**Traditional Synchronous API (`/crawl`):**
+- Client waits for entire crawl to complete
+- Timeout issues with long-running crawls
+- Resource blocking during execution
+- Constant polling required for status updates
+
+**Asynchronous Job Queue API (`/crawl/job`, `/llm/job`):**
+- ✅ Submit job and continue immediately
+- ✅ No timeout concerns for long operations
+- ✅ Real-time webhook notifications on completion
+- ✅ Better resource utilization
+- ✅ Perfect for batch processing
+- ✅ Ideal for microservice architectures
+
+### Available Endpoints
+
+#### 1. Crawl Job Endpoint
+
+```
+POST /crawl/job
+```
+
+Submit an asynchronous crawl job with optional webhook notification.
+
+**Request Body:**
+```json
+{
+  "urls": ["https://example.com"],
+  "cache_mode": "bypass",
+  "extraction_strategy": {
+    "type": "JsonCssExtractionStrategy",
+    "schema": {
+      "title": "h1",
+      "content": ".article-body"
+    }
+  },
+  "webhook_config": {
+    "webhook_url": "https://your-app.com/webhook/crawl-complete",
+    "webhook_data_in_payload": true,
+    "webhook_headers": {
+      "X-Webhook-Secret": "your-secret-token",
+      "X-Custom-Header": "value"
+    }
+  }
+}
+```
+
+**Response:**
+```json
+{
+  "task_id": "crawl_1698765432",
+  "message": "Crawl job submitted"
+}
+```
+
+#### 2. LLM Extraction Job Endpoint
+
+```
+POST /llm/job
+```
+
+Submit an asynchronous LLM extraction job with optional webhook notification.
+
+**Request Body:**
+```json
+{
+  "url": "https://example.com/article",
+  "q": "Extract the article title, author, publication date, and main points",
+  "provider": "openai/gpt-4o-mini",
+  "schema": "{\"title\": \"string\", \"author\": \"string\", \"date\": \"string\", \"points\": [\"string\"]}",
+  "cache": false,
+  "webhook_config": {
+    "webhook_url": "https://your-app.com/webhook/llm-complete",
+    "webhook_data_in_payload": true,
+    "webhook_headers": {
+      "X-Webhook-Secret": "your-secret-token"
+    }
+  }
+}
+```
+
+**Response:**
+```json
+{
+  "task_id": "llm_1698765432",
+  "message": "LLM job submitted"
+}
+```
+
+#### 3. Job Status Endpoint
+
+```
+GET /job/{task_id}
+```
+
+Check the status and retrieve results of a submitted job.
+
+**Response (In Progress):**
+```json
+{
+  "task_id": "crawl_1698765432",
+  "status": "processing",
+  "message": "Job is being processed"
+}
+```
+
+**Response (Completed):**
+```json
+{
+  "task_id": "crawl_1698765432",
+  "status": "completed",
+  "result": {
+    "markdown": "# Page Title\n\nContent...",
+    "extracted_content": {...},
+    "links": {...}
+  }
+}
+```
+
+### Webhook Configuration
+
+Webhooks provide real-time notifications when your jobs complete, eliminating the need for constant polling.
+
+#### Webhook Config Parameters
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `webhook_url` | string | Yes | Your HTTP(S) endpoint to receive notifications |
+| `webhook_data_in_payload` | boolean | No | Include full result data in webhook payload (default: false) |
+| `webhook_headers` | object | No | Custom headers for authentication/identification |
+
+#### Webhook Payload Format
+
+**Success Notification (Crawl Job):**
+```json
+{
+  "task_id": "crawl_1698765432",
+  "task_type": "crawl",
+  "status": "completed",
+  "timestamp": "2025-10-22T12:30:00.000000+00:00",
+  "urls": ["https://example.com"],
+  "data": {
+    "markdown": "# Page content...",
+    "extracted_content": {...},
+    "links": {...}
+  }
+}
+```
+
+**Success Notification (LLM Job):**
+```json
+{
+  "task_id": "llm_1698765432",
+  "task_type": "llm_extraction",
+  "status": "completed",
+  "timestamp": "2025-10-22T12:30:00.000000+00:00",
+  "urls": ["https://example.com/article"],
+  "data": {
+    "extracted_content": {
+      "title": "Understanding Web Scraping",
+      "author": "John Doe",
+      "date": "2025-10-22",
+      "points": ["Point 1", "Point 2"]
+    }
+  }
+}
+```
+
+**Failure Notification:**
+```json
+{
+  "task_id": "crawl_1698765432",
+  "task_type": "crawl",
+  "status": "failed",
+  "timestamp": "2025-10-22T12:30:00.000000+00:00",
+  "urls": ["https://example.com"],
+  "error": "Connection timeout after 30 seconds"
+}
+```
+
+#### Webhook Delivery & Retry
+
+- **Delivery Method:** HTTP POST to your `webhook_url`
+- **Content-Type:** `application/json`
+- **Retry Policy:** Exponential backoff with 5 attempts
+  - Attempt 1: Immediate
+  - Attempt 2: 1 second delay
+  - Attempt 3: 2 seconds delay
+  - Attempt 4: 4 seconds delay
+  - Attempt 5: 8 seconds delay
+- **Success Status Codes:** 200-299
+- **Custom Headers:** Your `webhook_headers` are included in every request
+
+### Usage Examples
+
+#### Example 1: Python with Webhook Handler (Flask)
+
+```python
+from flask import Flask, request, jsonify
+import requests
+
+app = Flask(__name__)
+
+# Webhook handler
+@app.route('/webhook/crawl-complete', methods=['POST'])
+def handle_crawl_webhook():
+    payload = request.json
+
+    if payload['status'] == 'completed':
+        print(f"✅ Job {payload['task_id']} completed!")
+        print(f"Task type: {payload['task_type']}")
+
+        # Access the crawl results
+        if 'data' in payload:
+            markdown = payload['data'].get('markdown', '')
+            extracted = payload['data'].get('extracted_content', {})
+            print(f"Extracted {len(markdown)} characters")
+            print(f"Structured data: {extracted}")
+    else:
+        print(f"❌ Job {payload['task_id']} failed: {payload.get('error')}")
+
+    return jsonify({"status": "received"}), 200
+
+# Submit a crawl job with webhook
+def submit_crawl_job():
+    response = requests.post(
+        "http://localhost:11235/crawl/job",
+        json={
+            "urls": ["https://example.com"],
+            "extraction_strategy": {
+                "type": "JsonCssExtractionStrategy",
+                "schema": {
+                    "name": "Example Schema",
+                    "baseSelector": "body",
+                    "fields": [
+                        {"name": "title", "selector": "h1", "type": "text"},
+                        {"name": "description", "selector": "meta[name='description']", "type": "attribute", "attribute": "content"}
+                    ]
+                }
+            },
+            "webhook_config": {
+                "webhook_url": "https://your-app.com/webhook/crawl-complete",
+                "webhook_data_in_payload": True,
+                "webhook_headers": {
+                    "X-Webhook-Secret": "your-secret-token"
+                }
+            }
+        }
+    )
+
+    task_id = response.json()['task_id']
+    print(f"Job submitted: {task_id}")
+    return task_id
+
+if __name__ == '__main__':
+    app.run(port=5000)
+```
+
+#### Example 2: LLM Extraction with Webhooks
+
+```python
+import requests
+
+def submit_llm_job_with_webhook():
+    response = requests.post(
+        "http://localhost:11235/llm/job",
+        json={
+            "url": "https://example.com/article",
+            "q": "Extract the article title, author, and main points",
+            "provider": "openai/gpt-4o-mini",
+            "webhook_config": {
+                "webhook_url": "https://your-app.com/webhook/llm-complete",
+                "webhook_data_in_payload": True,
+                "webhook_headers": {
+                    "X-Webhook-Secret": "your-secret-token"
+                }
+            }
+        }
+    )
+
+    task_id = response.json()['task_id']
+    print(f"LLM job submitted: {task_id}")
+    return task_id
+
+# Webhook handler for LLM jobs
+@app.route('/webhook/llm-complete', methods=['POST'])
+def handle_llm_webhook():
+    payload = request.json
+
+    if payload['status'] == 'completed':
+        extracted = payload['data']['extracted_content']
+        print(f"✅ LLM extraction completed!")
+        print(f"Results: {extracted}")
+    else:
+        print(f"❌ LLM extraction failed: {payload.get('error')}")
+
+    return jsonify({"status": "received"}), 200
+```
+
+#### Example 3: Without Webhooks (Polling)
+
+If you don't use webhooks, you can poll for results:
+
+```python
+import requests
+import time
+
+# Submit job
+response = requests.post(
+    "http://localhost:11235/crawl/job",
+    json={"urls": ["https://example.com"]}
+)
+task_id = response.json()['task_id']
+
+# Poll for results
+while True:
+    result = requests.get(f"http://localhost:11235/job/{task_id}")
+    data = result.json()
+
+    if data['status'] == 'completed':
+        print("Job completed!")
+        print(data['result'])
+        break
+    elif data['status'] == 'failed':
+        print(f"Job failed: {data.get('error')}")
+        break
+
+    print("Still processing...")
+    time.sleep(2)
+```
+
+#### Example 4: Global Webhook Configuration
+
+Set a default webhook URL in your `config.yml` to avoid repeating it in every request:
+
+```yaml
+# config.yml
+api:
+  crawler:
+    # ... other settings ...
+    webhook:
+      default_url: "https://your-app.com/webhook/default"
+      default_headers:
+        X-Webhook-Secret: "your-secret-token"
+```
+
+Then submit jobs without webhook config:
+
+```python
+# Uses the global webhook configuration
+response = requests.post(
+    "http://localhost:11235/crawl/job",
+    json={"urls": ["https://example.com"]}
+)
+```
+
+### Webhook Best Practices
+
+1. **Authentication:** Always use custom headers for webhook authentication
+   ```json
+   "webhook_headers": {
+     "X-Webhook-Secret": "your-secret-token"
+   }
+   ```
+
+2. **Idempotency:** Design your webhook handler to be idempotent (safe to receive duplicate notifications)
+
+3. **Fast Response:** Return HTTP 200 quickly; process data asynchronously if needed
+   ```python
+   @app.route('/webhook', methods=['POST'])
+   def webhook():
+       payload = request.json
+       # Queue for background processing
+       queue.enqueue(process_webhook, payload)
+       return jsonify({"status": "received"}), 200
+   ```
+
+4. **Error Handling:** Handle both success and failure notifications
+   ```python
+   if payload['status'] == 'completed':
+       # Process success
+   elif payload['status'] == 'failed':
+       # Log error, retry, or alert
+   ```
+
+5. **Validation:** Verify webhook authenticity using custom headers
+   ```python
+   secret = request.headers.get('X-Webhook-Secret')
+   if secret != os.environ['EXPECTED_SECRET']:
+       return jsonify({"error": "Unauthorized"}), 401
+   ```
+
+6. **Logging:** Log webhook deliveries for debugging
+   ```python
+   logger.info(f"Webhook received: {payload['task_id']} - {payload['status']}")
+   ```
+
+### Use Cases
+
+**1. Batch Processing**
+Submit hundreds of URLs and get notified as each completes:
+```python
+urls = ["https://site1.com", "https://site2.com", ...]
+for url in urls:
+    submit_crawl_job(url, webhook_url="https://app.com/webhook")
+```
+
+**2. Microservice Integration**
+Integrate with event-driven architectures:
+```python
+# Service A submits job
+task_id = submit_crawl_job(url)
+
+# Service B receives webhook and triggers next step
+@app.route('/webhook')
+def webhook():
+    process_result(request.json)
+    trigger_next_service()
+    return "OK", 200
+```
+
+**3. Long-Running Extractions**
+Handle complex LLM extractions without timeouts:
+```python
+submit_llm_job(
+    url="https://long-article.com",
+    q="Comprehensive summary with key points and analysis",
+    webhook_url="https://app.com/webhook/llm"
+)
+```
+
+### Troubleshooting
+
+**Webhook not receiving notifications?**
+- Check your webhook URL is publicly accessible
+- Verify firewall/security group settings
+- Use webhook testing tools like webhook.site for debugging
+- Check server logs for delivery attempts
+- Ensure your handler returns 200-299 status code
+
+**Job stuck in processing?**
+- Check Redis connection: `docker logs <container_name> | grep redis`
+- Verify worker processes: `docker exec <container_name> ps aux | grep worker`
+- Check server logs: `docker logs <container_name>`
+
+**Need to cancel a job?**
+Jobs are processed asynchronously. If you need to cancel:
+- Delete the task from Redis (requires Redis CLI access)
+- Or implement a cancellation endpoint in your webhook handler
+
 ---
 
 ## Dockerfile Parameters
@@ -913,10 +1628,12 @@ This is the easiest way to translate Python configuration to JSON requests when
 
 Install the SDK: `pip install crawl4ai`
 
+The Python SDK provides a convenient way to interact with the Docker API, including **automatic hook conversion** when using function objects.
+
 ```python
 import asyncio
 from crawl4ai.docker_client import Crawl4aiDockerClient
-from crawl4ai import BrowserConfig, CrawlerRunConfig, CacheMode # Assuming you have crawl4ai installed
+from crawl4ai import BrowserConfig, CrawlerRunConfig, CacheMode
 
 async def main():
     # Point to the correct server port
@@ -928,23 +1645,22 @@ async def main():
         print("--- Running Non-Streaming Crawl ---")
         results = await client.crawl(
             ["https://httpbin.org/html"],
-            browser_config=BrowserConfig(headless=True), # Use library classes for config aid
+            browser_config=BrowserConfig(headless=True),
             crawler_config=CrawlerRunConfig(cache_mode=CacheMode.BYPASS)
         )
-        if results: # client.crawl returns None on failure
-          print(f"Non-streaming results success: {results.success}")
-          if results.success:
-              for result in results: # Iterate through the CrawlResultContainer
-                  print(f"URL: {result.url}, Success: {result.success}")
+        if results:
+            print(f"Non-streaming results success: {results.success}")
+            if results.success:
+                for result in results:
+                    print(f"URL: {result.url}, Success: {result.success}")
         else:
             print("Non-streaming crawl failed.")
 
-
         # Example Streaming crawl
         print("\n--- Running Streaming Crawl ---")
         stream_config = CrawlerRunConfig(stream=True, cache_mode=CacheMode.BYPASS)
         try:
-            async for result in await client.crawl( # client.crawl returns an async generator for streaming
+            async for result in await client.crawl(
                 ["https://httpbin.org/html", "https://httpbin.org/links/5/0"],
                 browser_config=BrowserConfig(headless=True),
                 crawler_config=stream_config
@@ -953,17 +1669,56 @@ async def main():
         except Exception as e:
             print(f"Streaming crawl failed: {e}")
 
+        # Example with hooks (Python function objects)
+        print("\n--- Crawl with Hooks ---")
+
+        async def my_hook(page, context, **kwargs):
+            """Custom hook to optimize performance"""
+            await page.set_viewport_size({"width": 1920, "height": 1080})
+            await context.route("**/*.{png,jpg}", lambda r: r.abort())
+            print("[HOOK] Page optimized")
+            return page
+
+        result = await client.crawl(
+            ["https://httpbin.org/html"],
+            browser_config=BrowserConfig(headless=True),
+            crawler_config=CrawlerRunConfig(cache_mode=CacheMode.BYPASS),
+            hooks={"on_page_context_created": my_hook},  # Pass function directly!
+            hooks_timeout=30
+        )
+        print(f"Crawl with hooks success: {result.success}")
 
         # Example Get schema
         print("\n--- Getting Schema ---")
         schema = await client.get_schema()
-        print(f"Schema received: {bool(schema)}") # Print whether schema was received
+        print(f"Schema received: {bool(schema)}")
 
 if __name__ == "__main__":
     asyncio.run(main())
 ```
 
-*(SDK parameters like timeout, verify_ssl etc. remain the same)*
+#### SDK Parameters
+
+The Docker client supports the following parameters:
+
+**Client Initialization**:
+- `base_url` (str): URL of the Docker server (default: `http://localhost:8000`)
+- `timeout` (float): Request timeout in seconds (default: 30.0)
+- `verify_ssl` (bool): Verify SSL certificates (default: True)
+- `verbose` (bool): Enable verbose logging (default: True)
+- `log_file` (Optional[str]): Path to log file (default: None)
+
+**crawl() Method**:
+- `urls` (List[str]): List of URLs to crawl
+- `browser_config` (Optional[BrowserConfig]): Browser configuration
+- `crawler_config` (Optional[CrawlerRunConfig]): Crawler configuration
+- `hooks` (Optional[Dict]): Hook functions or strings - **automatically converts function objects!**
+- `hooks_timeout` (int): Timeout for each hook execution in seconds (default: 30)
+
+**Returns**:
+- Single URL: `CrawlResult` object
+- Multiple URLs: `List[CrawlResult]`
+- Streaming: `AsyncGenerator[CrawlResult]`
 
 ### Second Approach: Direct API Calls
 

docs/md_v2/extraction/llm-strategies.md

@@ -20,10 +20,10 @@ In some cases, you need to extract **complex or unstructured** information from
 
 ## 2. Provider-Agnostic via LiteLLM
 
-You can use LlmConfig, to quickly configure multiple variations of LLMs and experiment with them to find the optimal one for your use case. You can read more about LlmConfig [here](/api/parameters).
+You can use LLMConfig, to quickly configure multiple variations of LLMs and experiment with them to find the optimal one for your use case. You can read more about LLMConfig [here](/api/parameters).
 
 ```python
-llmConfig = LlmConfig(provider="openai/gpt-4o-mini", api_token=os.getenv("OPENAI_API_KEY"))
+llm_config = LLMConfig(provider="openai/gpt-4o-mini", api_token=os.getenv("OPENAI_API_KEY"))
 ```
 
 Crawl4AI uses a “provider string” (e.g., `"openai/gpt-4o"`, `"ollama/llama2.0"`, `"aws/titan"`) to identify your LLM. **Any** model that LiteLLM supports is fair game. You just provide:
@@ -58,7 +58,7 @@ For structured data, `"schema"` is recommended. You provide `schema=YourPydantic
 
 Below is an overview of important LLM extraction parameters. All are typically set inside `LLMExtractionStrategy(...)`. You then put that strategy in your `CrawlerRunConfig(..., extraction_strategy=...)`.
 
-1. **`llmConfig`** (LlmConfig): e.g., `"openai/gpt-4"`, `"ollama/llama2"`.    
+1. **`llm_config`** (LLMConfig): e.g., `"openai/gpt-4"`, `"ollama/llama2"`.
 2. **`schema`** (dict): A JSON schema describing the fields you want. Usually generated by `YourModel.model_json_schema()`.  
 3. **`extraction_type`** (str): `"schema"` or `"block"`.  
 4. **`instruction`** (str): Prompt text telling the LLM what you want extracted. E.g., “Extract these fields as a JSON array.”  
@@ -112,7 +112,7 @@ async def main():
     # 1. Define the LLM extraction strategy
     llm_strategy = LLMExtractionStrategy(
         llm_config = LLMConfig(provider="openai/gpt-4o-mini", api_token=os.getenv('OPENAI_API_KEY')),
-        schema=Product.schema_json(), # Or use model_json_schema()
+        schema=Product.model_json_schema(), # Or use model_json_schema()
         extraction_type="schema",
         instruction="Extract all product objects with 'name' and 'price' from the content.",
         chunk_token_threshold=1000,
@@ -238,7 +238,7 @@ class KnowledgeGraph(BaseModel):
 async def main():
     # LLM extraction strategy
     llm_strat = LLMExtractionStrategy(
-        llmConfig = LLMConfig(provider="openai/gpt-4", api_token=os.getenv('OPENAI_API_KEY')),
+        llm_config = LLMConfig(provider="openai/gpt-4", api_token=os.getenv('OPENAI_API_KEY')),
         schema=KnowledgeGraph.model_json_schema(),
         extraction_type="schema",
         instruction="Extract entities and relationships from the content. Return valid JSON.",

docs/md_v2/index.md

@@ -55,9 +55,40 @@
   
 </div>
 
+---
+#### 🚀 Crawl4AI Cloud API — Closed Beta (Launching Soon)
+Reliable, large-scale web extraction, now built to be _**drastically more cost-effective**_ than any of the existing solutions.
+
+👉 **Apply [here](https://forms.gle/E9MyPaNXACnAMaqG7) for early access**  
+_We’ll be onboarding in phases and working closely with early users.
+Limited slots._
+
+---
+
 Crawl4AI is the #1 trending GitHub repository, actively maintained by a vibrant community. It delivers blazing-fast, AI-ready web crawling tailored for large language models, AI agents, and data pipelines. Fully open source, flexible, and built for real-time performance, **Crawl4AI** empowers developers with unmatched speed, precision, and deployment ease.
 
-> **Note**: If you're looking for the old documentation, you can access it [here](https://old.docs.crawl4ai.com).
+> Enjoy using Crawl4AI? Consider **[becoming a sponsor](https://github.com/sponsors/unclecode)** to support ongoing development and community growth!
+
+## 🆕 AI Assistant Skill Now Available!
+
+<div style="background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); padding: 20px; border-radius: 10px; margin: 20px 0; box-shadow: 0 4px 6px rgba(0,0,0,0.1);">
+  <h3 style="color: white; margin: 0 0 10px 0;">🤖 Crawl4AI Skill for Claude & AI Assistants</h3>
+  <p style="color: white; margin: 10px 0;">Supercharge your AI coding assistant with complete Crawl4AI knowledge! Download our comprehensive skill package that includes:</p>
+  <ul style="color: white; margin: 10px 0;">
+    <li>📚 Complete SDK reference (23K+ words)</li>
+    <li>🚀 Ready-to-use extraction scripts</li>
+    <li>⚡ Schema generation for efficient scraping</li>
+    <li>🔧 Version 0.7.4 compatible</li>
+  </ul>
+  <div style="text-align: center; margin-top: 15px;">
+    <a href="assets/crawl4ai-skill.zip" download style="background: white; color: #667eea; padding: 12px 30px; border-radius: 5px; text-decoration: none; font-weight: bold; display: inline-block; transition: transform 0.2s;">
+      📦 Download Skill Package
+    </a>
+  </div>
+  <p style="color: white; margin: 15px 0 0 0; font-size: 0.9em; text-align: center;">
+    Works with Claude, Cursor, Windsurf, and other AI coding assistants. Import the .zip file into your AI assistant's skill/knowledge system.
+  </p>
+</div>
 
 ## 🎯 New: Adaptive Web Crawling
 

docs/md_v2/marketplace/admin/admin.js

@@ -529,8 +529,19 @@ class AdminDashboard {
                     </label>
                 </div>
                 <div class="form-group full-width">
-                    <label>Integration Guide</label>
-                    <textarea id="form-integration" rows="10">${app?.integration_guide || ''}</textarea>
+                    <label>Long Description (Markdown - Overview tab)</label>
+                    <textarea id="form-long-description" rows="10" placeholder="Enter detailed description with markdown formatting...">${app?.long_description || ''}</textarea>
+                    <small>Markdown support: **bold**, *italic*, [links](url), # headers, code blocks, lists</small>
+                </div>
+                <div class="form-group full-width">
+                    <label>Integration Guide (Markdown - Integration tab)</label>
+                    <textarea id="form-integration" rows="20" placeholder="Enter integration guide with installation, examples, and code snippets using markdown...">${app?.integration_guide || ''}</textarea>
+                    <small>Single markdown field with installation, examples, and complete guide. Code blocks get auto copy buttons.</small>
+                </div>
+                <div class="form-group full-width">
+                    <label>Documentation (Markdown - Documentation tab)</label>
+                    <textarea id="form-documentation" rows="20" placeholder="Enter documentation with API reference, examples, and best practices using markdown...">${app?.documentation || ''}</textarea>
+                    <small>Full documentation with API reference, examples, best practices, etc.</small>
                 </div>
             </div>
         `;
@@ -712,7 +723,9 @@ class AdminDashboard {
             data.contact_email = document.getElementById('form-email').value;
             data.featured = document.getElementById('form-featured').checked ? 1 : 0;
             data.sponsored = document.getElementById('form-sponsored').checked ? 1 : 0;
+            data.long_description = document.getElementById('form-long-description').value;
             data.integration_guide = document.getElementById('form-integration').value;
+            data.documentation = document.getElementById('form-documentation').value;
         } else if (type === 'articles') {
             data.title = document.getElementById('form-title').value;
             data.slug = this.generateSlug(data.title);

docs/md_v2/marketplace/app-detail.css

@@ -278,12 +278,12 @@
 }
 
 .tab-content {
-    display: none;
+    display: none !important;
     padding: 2rem;
 }
 
 .tab-content.active {
-    display: block;
+    display: block !important;
 }
 
 /* Overview Layout */
@@ -510,6 +510,31 @@
     line-height: 1.5;
 }
 
+/* Markdown rendered code blocks */
+.integration-content pre,
+.docs-content pre {
+    background: var(--bg-dark);
+    border: 1px solid var(--border-color);
+    margin: 1rem 0;
+    padding: 1rem;
+    padding-top: 2.5rem; /* Space for copy button */
+    overflow-x: auto;
+    position: relative;
+    max-height: none; /* Remove any height restrictions */
+    height: auto; /* Allow content to expand */
+}
+
+.integration-content pre code,
+.docs-content pre code {
+    background: transparent;
+    padding: 0;
+    color: var(--text-secondary);
+    font-size: 0.875rem;
+    line-height: 1.5;
+    white-space: pre; /* Preserve whitespace and line breaks */
+    display: block;
+}
+
 /* Feature Grid */
 .feature-grid {
     display: grid;

docs/md_v2/marketplace/app-detail.html

@@ -73,27 +73,14 @@
                 <div class="tabs">
                     <button class="tab-btn active" data-tab="overview">Overview</button>
                     <button class="tab-btn" data-tab="integration">Integration</button>
-                    <button class="tab-btn" data-tab="docs">Documentation</button>
-                    <button class="tab-btn" data-tab="support">Support</button>
+                    <!-- <button class="tab-btn" data-tab="docs">Documentation</button>
+                    <button class="tab-btn" data-tab="support">Support</button> -->
                 </div>
 
                 <section id="overview-tab" class="tab-content active">
                     <div class="overview-columns">
                         <div class="overview-main">
-                            <h2>Overview</h2>
                             <div id="app-overview">Overview content goes here.</div>
-
-                            <h3>Key Features</h3>
-                            <ul id="app-features" class="features-list">
-                                <li>Feature 1</li>
-                                <li>Feature 2</li>
-                                <li>Feature 3</li>
-                            </ul>
-
-                            <h3>Use Cases</h3>
-                            <div id="app-use-cases" class="use-cases">
-                                <p>Describe how this app can help your workflow.</p>
-                            </div>
                         </div>
 
                         <aside class="sidebar">
@@ -142,37 +129,16 @@
                 </section>
 
                 <section id="integration-tab" class="tab-content">
-                    <div class="integration-content">
-                        <h2>Integration Guide</h2>
-
-                        <h3>Installation</h3>
-                        <div class="code-block">
-                            <pre><code id="install-code"># Installation instructions will appear here</code></pre>
-                        </div>
-
-                        <h3>Basic Usage</h3>
-                        <div class="code-block">
-                            <pre><code id="usage-code"># Usage example will appear here</code></pre>
-                        </div>
-
-                        <h3>Complete Integration Example</h3>
-                        <div class="code-block">
-                            <button class="copy-btn" id="copy-integration">Copy</button>
-                            <pre><code id="integration-code"># Complete integration guide will appear here</code></pre>
-                        </div>
+                    <div class="integration-content" id="app-integration">
                     </div>
                 </section>
 
-                <section id="docs-tab" class="tab-content">
-                    <div class="docs-content">
-                        <h2>Documentation</h2>
-                        <div id="app-docs" class="doc-sections">
-                            <p>Documentation coming soon.</p>
-                        </div>
+                <!-- <section id="docs-tab" class="tab-content">
+                    <div class="docs-content" id="app-docs">
                     </div>
-                </section>
+                </section> -->
 
-                <section id="support-tab" class="tab-content">
+                <!-- <section id="support-tab" class="tab-content">
                     <div class="docs-content">
                         <h2>Support</h2>
                         <div class="support-grid">
@@ -190,7 +156,7 @@
                             </div>
                         </div>
                     </div>
-                </section>
+                </section> -->
             </div>
 
         </main>

docs/md_v2/marketplace/app-detail.js

@@ -112,7 +112,7 @@ class AppDetailPage {
         }
 
         // Contact
-        document.getElementById('app-contact').textContent = this.appData.contact_email || 'Not available';
+        document.getElementById('app-contact') && (document.getElementById('app-contact').textContent = this.appData.contact_email || 'Not available');
 
         // Sidebar info
         document.getElementById('sidebar-downloads').textContent = this.formatNumber(this.appData.downloads || 0);
@@ -123,144 +123,132 @@ class AppDetailPage {
         document.getElementById('sidebar-pricing').textContent = this.appData.pricing || 'Free';
         document.getElementById('sidebar-contact').textContent = this.appData.contact_email || 'contact@example.com';
 
-        // Integration guide
-        this.renderIntegrationGuide();
+        // Render tab contents from database fields
+        this.renderTabContents();
     }
 
-    renderIntegrationGuide() {
-        // Installation code
-        const installCode = document.getElementById('install-code');
-        if (installCode) {
-            if (this.appData.type === 'Open Source' && this.appData.github_url) {
-                installCode.textContent = `# Clone from GitHub
-git clone ${this.appData.github_url}
-
-# Install dependencies
-pip install -r requirements.txt`;
-            } else if (this.appData.name.toLowerCase().includes('api')) {
-                installCode.textContent = `# Install via pip
-pip install ${this.appData.slug}
-
-# Or install from source
-pip install git+${this.appData.github_url || 'https://github.com/example/repo'}`;
+    renderTabContents() {
+        // Overview tab - use long_description from database
+        const overviewDiv = document.getElementById('app-overview');
+        if (overviewDiv) {
+            if (this.appData.long_description) {
+                overviewDiv.innerHTML = this.renderMarkdown(this.appData.long_description);
+            } else {
+                overviewDiv.innerHTML = `<p>${this.appData.description || 'No overview available.'}</p>`;
             }
         }
 
-        // Usage code - customize based on category
-        const usageCode = document.getElementById('usage-code');
-        if (usageCode) {
-            if (this.appData.category === 'Browser Automation') {
-                usageCode.textContent = `from crawl4ai import AsyncWebCrawler
-from ${this.appData.slug.replace(/-/g, '_')} import ${this.appData.name.replace(/\s+/g, '')}
-
-async def main():
-    # Initialize ${this.appData.name}
-    automation = ${this.appData.name.replace(/\s+/g, '')}()
-
-    async with AsyncWebCrawler() as crawler:
-        result = await crawler.arun(
-            url="https://example.com",
-            browser_config=automation.config,
-            wait_for="css:body"
-        )
-        print(result.markdown)`;
-        } else if (this.appData.category === 'Proxy Services') {
-            usageCode.textContent = `from crawl4ai import AsyncWebCrawler
-import ${this.appData.slug.replace(/-/g, '_')}
-
-# Configure proxy
-proxy_config = {
-    "server": "${this.appData.website_url || 'https://proxy.example.com'}",
-    "username": "your_username",
-    "password": "your_password"
-}
-
-async with AsyncWebCrawler(proxy=proxy_config) as crawler:
-    result = await crawler.arun(
-        url="https://example.com",
-        bypass_cache=True
-    )
-    print(result.status_code)`;
-        } else if (this.appData.category === 'LLM Integration') {
-            usageCode.textContent = `from crawl4ai import AsyncWebCrawler
-from crawl4ai.extraction_strategy import LLMExtractionStrategy
-
-# Configure LLM extraction
-strategy = LLMExtractionStrategy(
-    provider="${this.appData.name.toLowerCase().includes('gpt') ? 'openai' : 'anthropic'}",
-    api_key="your-api-key",
-    model="${this.appData.name.toLowerCase().includes('gpt') ? 'gpt-4' : 'claude-3'}",
-    instruction="Extract structured data"
-)
-
-async with AsyncWebCrawler() as crawler:
-    result = await crawler.arun(
-        url="https://example.com",
-        extraction_strategy=strategy
-    )
-    print(result.extracted_content)`;
+        // Integration tab - use integration_guide field from database
+        const integrationDiv = document.getElementById('app-integration');
+        if (integrationDiv) {
+            if (this.appData.integration_guide) {
+                integrationDiv.innerHTML = this.renderMarkdown(this.appData.integration_guide);
+                // Add copy buttons to all code blocks
+                this.addCopyButtonsToCodeBlocks(integrationDiv);
+            } else {
+                integrationDiv.innerHTML = '<p>Integration guide not yet available. Please check the official website for details.</p>';
             }
         }
 
-        // Integration example
-        const integrationCode = document.getElementById('integration-code');
-        if (integrationCode) {
-            integrationCode.textContent = this.appData.integration_guide ||
-`# Complete ${this.appData.name} Integration Example
-
-from crawl4ai import AsyncWebCrawler
-from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
-import json
-
-async def crawl_with_${this.appData.slug.replace(/-/g, '_')}():
-    """
-    Complete example showing how to use ${this.appData.name}
-    with Crawl4AI for production web scraping
-    """
-
-    # Define extraction schema
-    schema = {
-        "name": "ProductList",
-        "baseSelector": "div.product",
-        "fields": [
-            {"name": "title", "selector": "h2", "type": "text"},
-            {"name": "price", "selector": ".price", "type": "text"},
-            {"name": "image", "selector": "img", "type": "attribute", "attribute": "src"},
-            {"name": "link", "selector": "a", "type": "attribute", "attribute": "href"}
-        ]
+        // Documentation tab - use documentation field from database
+        const docsDiv = document.getElementById('app-docs');
+        if (docsDiv) {
+            if (this.appData.documentation) {
+                docsDiv.innerHTML = this.renderMarkdown(this.appData.documentation);
+                // Add copy buttons to all code blocks
+                this.addCopyButtonsToCodeBlocks(docsDiv);
+            } else {
+                docsDiv.innerHTML = '<p>Documentation coming soon.</p>';
+            }
+        }
     }
 
-    # Initialize crawler with ${this.appData.name}
-    async with AsyncWebCrawler(
-        browser_type="chromium",
-        headless=True,
-        verbose=True
-    ) as crawler:
+    addCopyButtonsToCodeBlocks(container) {
+        // Find all code blocks and add copy buttons
+        const codeBlocks = container.querySelectorAll('pre code');
+        codeBlocks.forEach(codeBlock => {
+            const pre = codeBlock.parentElement;
 
-        # Crawl with extraction
-        result = await crawler.arun(
-            url="https://example.com/products",
-            extraction_strategy=JsonCssExtractionStrategy(schema),
-            cache_mode="bypass",
-            wait_for="css:.product",
-            screenshot=True
-        )
+            // Skip if already has a copy button
+            if (pre.querySelector('.copy-btn')) return;
 
-        # Process results
-        if result.success:
-            products = json.loads(result.extracted_content)
-            print(f"Found {len(products)} products")
+            // Create copy button
+            const copyBtn = document.createElement('button');
+            copyBtn.className = 'copy-btn';
+            copyBtn.textContent = 'Copy';
+            copyBtn.onclick = () => {
+                navigator.clipboard.writeText(codeBlock.textContent).then(() => {
+                    copyBtn.textContent = '✓ Copied!';
+                    setTimeout(() => {
+                        copyBtn.textContent = 'Copy';
+                    }, 2000);
+                });
+            };
 
-            for product in products[:5]:
-                print(f"- {product['title']}: {product['price']}")
+            // Add button to pre element
+            pre.style.position = 'relative';
+            pre.insertBefore(copyBtn, codeBlock);
+        });
+    }
 
-        return products
+    renderMarkdown(text) {
+        if (!text) return '';
 
-# Run the crawler
-if __name__ == "__main__":
-    import asyncio
-    asyncio.run(crawl_with_${this.appData.slug.replace(/-/g, '_')}())`;
-        }
+        // Store code blocks temporarily to protect them from processing
+        const codeBlocks = [];
+        let processed = text.replace(/```(\w+)?\n([\s\S]*?)```/g, (match, lang, code) => {
+            const placeholder = `___CODE_BLOCK_${codeBlocks.length}___`;
+            codeBlocks.push(`<pre><code class="language-${lang || ''}">${this.escapeHtml(code)}</code></pre>`);
+            return placeholder;
+        });
+
+        // Store inline code temporarily
+        const inlineCodes = [];
+        processed = processed.replace(/`([^`]+)`/g, (match, code) => {
+            const placeholder = `___INLINE_CODE_${inlineCodes.length}___`;
+            inlineCodes.push(`<code>${this.escapeHtml(code)}</code>`);
+            return placeholder;
+        });
+
+        // Now process the rest of the markdown
+        processed = processed
+            // Headers
+            .replace(/^### (.*$)/gim, '<h3>$1</h3>')
+            .replace(/^## (.*$)/gim, '<h2>$1</h2>')
+            .replace(/^# (.*$)/gim, '<h1>$1</h1>')
+            // Bold
+            .replace(/\*\*(.*?)\*\*/g, '<strong>$1</strong>')
+            // Italic
+            .replace(/\*(.*?)\*/g, '<em>$1</em>')
+            // Links
+            .replace(/\[([^\]]+)\]\(([^)]+)\)/g, '<a href="$2" target="_blank">$1</a>')
+            // Line breaks
+            .replace(/\n\n/g, '</p><p>')
+            .replace(/\n/g, '<br>')
+            // Lists
+            .replace(/^\* (.*)$/gim, '<li>$1</li>')
+            .replace(/^- (.*)$/gim, '<li>$1</li>')
+            // Wrap in paragraphs
+            .replace(/^(?!<[h|p|pre|ul|ol|li])/gim, '<p>')
+            .replace(/(?<![>])$/gim, '</p>');
+
+        // Restore inline code
+        inlineCodes.forEach((code, i) => {
+            processed = processed.replace(`___INLINE_CODE_${i}___`, code);
+        });
+
+        // Restore code blocks
+        codeBlocks.forEach((block, i) => {
+            processed = processed.replace(`___CODE_BLOCK_${i}___`, block);
+        });
+
+        return processed;
+    }
+
+    escapeHtml(text) {
+        const div = document.createElement('div');
+        div.textContent = text;
+        return div.innerHTML;
     }
 
     formatNumber(num) {
@@ -275,45 +263,27 @@ if __name__ == "__main__":
     setupEventListeners() {
         // Tab switching
         const tabs = document.querySelectorAll('.tab-btn');
+
         tabs.forEach(tab => {
             tab.addEventListener('click', () => {
-                // Update active tab
+                // Update active tab button
                 tabs.forEach(t => t.classList.remove('active'));
                 tab.classList.add('active');
 
                 // Show corresponding content
                 const tabName = tab.dataset.tab;
-                document.querySelectorAll('.tab-content').forEach(content => {
+
+                // Hide all tab contents
+                const allTabContents = document.querySelectorAll('.tab-content');
+                allTabContents.forEach(content => {
                     content.classList.remove('active');
                 });
-                document.getElementById(`${tabName}-tab`).classList.add('active');
-            });
-        });
 
-        // Copy integration code
-        document.getElementById('copy-integration').addEventListener('click', () => {
-            const code = document.getElementById('integration-code').textContent;
-            navigator.clipboard.writeText(code).then(() => {
-                const btn = document.getElementById('copy-integration');
-                const originalText = btn.innerHTML;
-                btn.innerHTML = '<span>✓</span> Copied!';
-                setTimeout(() => {
-                    btn.innerHTML = originalText;
-                }, 2000);
-            });
-        });
-
-        // Copy code buttons
-        document.querySelectorAll('.copy-btn').forEach(btn => {
-            btn.addEventListener('click', (e) => {
-                const codeBlock = e.target.closest('.code-block');
-                const code = codeBlock.querySelector('code').textContent;
-                navigator.clipboard.writeText(code).then(() => {
-                    btn.textContent = 'Copied!';
-                    setTimeout(() => {
-                        btn.textContent = 'Copy';
-                    }, 2000);
-                });
+                // Show the selected tab content
+                const targetTab = document.getElementById(`${tabName}-tab`);
+                if (targetTab) {
+                    targetTab.classList.add('active');
+                }
             });
         });
     }

docs/md_v2/marketplace/backend/server.py

@@ -471,13 +471,17 @@ async def delete_sponsor(sponsor_id: int):
 
 app.include_router(router)
 
+# Version info
+VERSION = "1.1.0"
+BUILD_DATE = "2025-10-26"
 
 @app.get("/")
 async def root():
     """API info"""
     return {
         "name": "Crawl4AI Marketplace API",
-        "version": "1.0.0",
+        "version": VERSION,
+        "build_date": BUILD_DATE,
         "endpoints": [
             "/marketplace/api/apps",
             "/marketplace/api/articles",

docs/releases_review/demo_v0.7.5.py

@@ -0,0 +1,338 @@
+"""
+🚀 Crawl4AI v0.7.5 Release Demo - Working Examples
+==================================================
+This demo showcases key features introduced in v0.7.5 with real, executable examples.
+
+Featured Demos:
+1. ✅ Docker Hooks System - Real API calls with custom hooks (string & function-based)
+2. ✅ Enhanced LLM Integration - Working LLM configurations
+3. ✅ HTTPS Preservation - Live crawling with HTTPS maintenance
+
+Requirements:
+- crawl4ai v0.7.5 installed
+- Docker running with crawl4ai image (optional for Docker demos)
+- Valid API keys for LLM demos (optional)
+"""
+
+import asyncio
+import requests
+import time
+import sys
+
+from crawl4ai import (AsyncWebCrawler, CrawlerRunConfig, BrowserConfig,
+                      CacheMode, FilterChain, URLPatternFilter, BFSDeepCrawlStrategy,
+                      hooks_to_string)
+from crawl4ai.docker_client import Crawl4aiDockerClient
+    
+
+def print_section(title: str, description: str = ""):
+    """Print a section header"""
+    print(f"\n{'=' * 60}")
+    print(f"{title}")
+    if description:
+        print(f"{description}")
+    print(f"{'=' * 60}\n")
+
+
+async def demo_1_docker_hooks_system():
+    """Demo 1: Docker Hooks System - Real API calls with custom hooks"""
+    print_section(
+        "Demo 1: Docker Hooks System",
+        "Testing both string-based and function-based hooks (NEW in v0.7.5!)"
+    )
+
+    # Check Docker service availability
+    def check_docker_service():
+        try:
+            response = requests.get("http://localhost:11235/", timeout=3)
+            return response.status_code == 200
+        except:
+            return False
+
+    print("Checking Docker service...")
+    docker_running = check_docker_service()
+
+    if not docker_running:
+        print("⚠️  Docker service not running on localhost:11235")
+        print("To test Docker hooks:")
+        print("1. Run: docker run -p 11235:11235 unclecode/crawl4ai:latest")
+        print("2. Wait for service to start")
+        print("3. Re-run this demo\n")
+        return
+
+    print("✓ Docker service detected!")
+
+    # ============================================================================
+    # PART 1: Traditional String-Based Hooks (Works with REST API)
+    # ============================================================================
+    print("\n" + "─" * 60)
+    print("Part 1: String-Based Hooks (REST API)")
+    print("─" * 60)
+
+    hooks_config_string = {
+        "on_page_context_created": """
+async def hook(page, context, **kwargs):
+    print("[String Hook] Setting up page context")
+    await context.route("**/*.{png,jpg,jpeg,gif,webp}", lambda route: route.abort())
+    return page
+""",
+        "before_retrieve_html": """
+async def hook(page, context, **kwargs):
+    print("[String Hook] Before retrieving HTML")
+    await page.evaluate("window.scrollTo(0, document.body.scrollHeight)")
+    await page.wait_for_timeout(1000)
+    return page
+"""
+    }
+
+    payload = {
+        "urls": ["https://httpbin.org/html"],
+        "hooks": {
+            "code": hooks_config_string,
+            "timeout": 30
+        }
+    }
+
+    print("🔧 Using string-based hooks for REST API...")
+    try:
+        start_time = time.time()
+        response = requests.post("http://localhost:11235/crawl", json=payload, timeout=60)
+        execution_time = time.time() - start_time
+
+        if response.status_code == 200:
+            result = response.json()
+            print(f"✅ String-based hooks executed in {execution_time:.2f}s")
+            if result.get('results') and result['results'][0].get('success'):
+                html_length = len(result['results'][0].get('html', ''))
+                print(f"   📄 HTML length: {html_length} characters")
+        else:
+            print(f"❌ Request failed: {response.status_code}")
+    except Exception as e:
+        print(f"❌ Error: {str(e)}")
+
+    # ============================================================================
+    # PART 2: NEW Function-Based Hooks with Docker Client (v0.7.5)
+    # ============================================================================
+    print("\n" + "─" * 60)
+    print("Part 2: Function-Based Hooks with Docker Client (✨ NEW!)")
+    print("─" * 60)
+
+    # Define hooks as regular Python functions
+    async def on_page_context_created_func(page, context, **kwargs):
+        """Block images to speed up crawling"""
+        print("[Function Hook] Setting up page context")
+        await context.route("**/*.{png,jpg,jpeg,gif,webp}", lambda route: route.abort())
+        await page.set_viewport_size({"width": 1920, "height": 1080})
+        return page
+
+    async def before_goto_func(page, context, url, **kwargs):
+        """Add custom headers before navigation"""
+        print(f"[Function Hook] About to navigate to {url}")
+        await page.set_extra_http_headers({
+            'X-Crawl4AI': 'v0.7.5-function-hooks',
+            'X-Test-Header': 'demo'
+        })
+        return page
+
+    async def before_retrieve_html_func(page, context, **kwargs):
+        """Scroll to load lazy content"""
+        print("[Function Hook] Scrolling page for lazy-loaded content")
+        await page.evaluate("window.scrollTo(0, document.body.scrollHeight)")
+        await page.wait_for_timeout(500)
+        await page.evaluate("window.scrollTo(0, 0)")
+        return page
+
+    # Use the hooks_to_string utility (can be used standalone)
+    print("\n📦 Converting functions to strings with hooks_to_string()...")
+    hooks_as_strings = hooks_to_string({
+        "on_page_context_created": on_page_context_created_func,
+        "before_goto": before_goto_func,
+        "before_retrieve_html": before_retrieve_html_func
+    })
+    print(f"   ✓ Converted {len(hooks_as_strings)} hooks to string format")
+
+    # OR use Docker Client which does conversion automatically!
+    print("\n🐳 Using Docker Client with automatic conversion...")
+    try:
+        client = Crawl4aiDockerClient(base_url="http://localhost:11235")
+
+        # Pass function objects directly - conversion happens automatically!
+        results = await client.crawl(
+            urls=["https://httpbin.org/html"],
+            hooks={
+                "on_page_context_created": on_page_context_created_func,
+                "before_goto": before_goto_func,
+                "before_retrieve_html": before_retrieve_html_func
+            },
+            hooks_timeout=30
+        )
+
+        if results and results.success:
+            print(f"✅ Function-based hooks executed successfully!")
+            print(f"   📄 HTML length: {len(results.html)} characters")
+            print(f"   🎯 URL: {results.url}")
+        else:
+            print("⚠️ Crawl completed but may have warnings")
+
+    except Exception as e:
+        print(f"❌ Docker client error: {str(e)}")
+
+    # Show the benefits
+    print("\n" + "=" * 60)
+    print("✨ Benefits of Function-Based Hooks:")
+    print("=" * 60)
+    print("✓ Full IDE support (autocomplete, syntax highlighting)")
+    print("✓ Type checking and linting")
+    print("✓ Easier to test and debug")
+    print("✓ Reusable across projects")
+    print("✓ Automatic conversion in Docker client")
+    print("=" * 60)
+
+
+async def demo_2_enhanced_llm_integration():
+    """Demo 2: Enhanced LLM Integration - Working LLM configurations"""
+    print_section(
+        "Demo 2: Enhanced LLM Integration",
+        "Testing custom LLM providers and configurations"
+    )
+
+    print("🤖 Testing Enhanced LLM Integration Features")
+
+    provider = "gemini/gemini-2.5-flash-lite"
+    payload = {
+        "url": "https://example.com",
+        "f": "llm",
+        "q": "Summarize this page in one sentence.",
+        "provider": provider,  # Explicitly set provider
+        "temperature": 0.7
+    }
+    try:
+        response = requests.post(
+            "http://localhost:11235/md",
+            json=payload,
+            timeout=60
+        )
+        if response.status_code == 200:
+            result = response.json()
+            print(f"✓ Request successful with provider: {provider}")
+            print(f"  - Response keys: {list(result.keys())}")
+            print(f"  - Content length: {len(result.get('markdown', ''))} characters")
+            print(f"  - Note: Actual LLM call may fail without valid API key")
+        else:
+            print(f"❌ Request failed: {response.status_code}")
+            print(f"  - Response: {response.text[:500]}")
+            
+    except Exception as e:
+        print(f"[red]Error: {e}[/]")
+
+
+async def demo_3_https_preservation():
+    """Demo 3: HTTPS Preservation - Live crawling with HTTPS maintenance"""
+    print_section(
+        "Demo 3: HTTPS Preservation",
+        "Testing HTTPS preservation for internal links"
+    )
+
+    print("🔒 Testing HTTPS Preservation Feature")
+
+    # Test with HTTPS preservation enabled
+    print("\nTest 1: HTTPS Preservation ENABLED")
+
+    url_filter = URLPatternFilter(
+        patterns=["^(https:\/\/)?quotes\.toscrape\.com(\/.*)?$"]
+    )
+    config = CrawlerRunConfig(
+        exclude_external_links=True, 
+        stream=True, 
+        verbose=False,
+        preserve_https_for_internal_links=True,
+        deep_crawl_strategy=BFSDeepCrawlStrategy(
+            max_depth=2, 
+            max_pages=5,
+            filter_chain=FilterChain([url_filter])
+        )
+    )
+
+    test_url = "https://quotes.toscrape.com"
+    print(f"🎯 Testing URL: {test_url}")
+
+    async with AsyncWebCrawler() as crawler:
+        async for result in await crawler.arun(url=test_url, config=config):
+            print("✓ HTTPS Preservation Test Completed")
+            internal_links = [i['href'] for i in result.links['internal']]
+            for link in internal_links:
+                print(f"  → {link}")
+
+
+async def main():
+    """Run all demos"""
+    print("\n" + "=" * 60)
+    print("🚀 Crawl4AI v0.7.5 Working Demo")
+    print("=" * 60)
+
+    # Check system requirements
+    print("🔍 System Requirements Check:")
+    print(f"  - Python version: {sys.version.split()[0]} {'✓' if sys.version_info >= (3, 10) else '❌ (3.10+ required)'}")
+
+    try:
+        import requests
+        print(f"  - Requests library: ✓")
+    except ImportError:
+        print(f"  - Requests library: ❌")
+
+    print()
+
+    demos = [
+        ("Docker Hooks System", demo_1_docker_hooks_system),
+        ("Enhanced LLM Integration", demo_2_enhanced_llm_integration),
+        ("HTTPS Preservation", demo_3_https_preservation),
+    ]
+
+    for i, (name, demo_func) in enumerate(demos, 1):
+        try:
+            print(f"\n📍 Starting Demo {i}/{len(demos)}: {name}")
+            await demo_func()
+
+            if i < len(demos):
+                print(f"\n✨ Demo {i} complete! Press Enter for next demo...")
+                input()
+
+        except KeyboardInterrupt:
+            print(f"\n⏹️  Demo interrupted by user")
+            break
+        except Exception as e:
+            print(f"❌ Demo {i} error: {str(e)}")
+            print("Continuing to next demo...")
+            continue
+
+    print("\n" + "=" * 60)
+    print("🎉 Demo Complete!")
+    print("=" * 60)
+    print("You've experienced the power of Crawl4AI v0.7.5!")
+    print("")
+    print("Key Features Demonstrated:")
+    print("🔧 Docker Hooks - String-based & function-based (NEW!)")
+    print("   • hooks_to_string() utility for function conversion")
+    print("   • Docker client with automatic conversion")
+    print("   • Full IDE support and type checking")
+    print("🤖 Enhanced LLM - Better AI integration")
+    print("🔒 HTTPS Preservation - Secure link handling")
+    print("")
+    print("Ready to build something amazing? 🚀")
+    print("")
+    print("📖 Docs: https://docs.crawl4ai.com/")
+    print("🐙 GitHub: https://github.com/unclecode/crawl4ai")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    print("🚀 Crawl4AI v0.7.5 Live Demo Starting...")
+    print("Press Ctrl+C anytime to exit\n")
+
+    try:
+        asyncio.run(main())
+    except KeyboardInterrupt:
+        print("\n👋 Demo stopped by user. Thanks for trying Crawl4AI v0.7.5!")
+    except Exception as e:
+        print(f"\n❌ Demo error: {str(e)}")
+        print("Make sure you have the required dependencies installed.")

docs/releases_review/demo_v0.7.6.py

@@ -0,0 +1,359 @@
+#!/usr/bin/env python3
+"""
+Crawl4AI v0.7.6 Release Demo
+============================
+
+This demo showcases the major feature in v0.7.6:
+**Webhook Support for Docker Job Queue API**
+
+Features Demonstrated:
+1. Asynchronous job processing with webhook notifications
+2. Webhook support for /crawl/job endpoint
+3. Webhook support for /llm/job endpoint
+4. Notification-only vs data-in-payload modes
+5. Custom webhook headers for authentication
+6. Structured extraction with JSON schemas
+7. Exponential backoff retry for reliable delivery
+
+Prerequisites:
+- Crawl4AI Docker container running on localhost:11235
+- Flask installed: pip install flask requests
+- LLM API key configured (for LLM examples)
+
+Usage:
+python docs/releases_review/demo_v0.7.6.py
+"""
+
+import requests
+import json
+import time
+from flask import Flask, request, jsonify
+from threading import Thread
+
+# Configuration
+CRAWL4AI_BASE_URL = "http://localhost:11235"
+WEBHOOK_BASE_URL = "http://localhost:8080"
+
+# Flask app for webhook receiver
+app = Flask(__name__)
+received_webhooks = []
+
+
+@app.route('/webhook', methods=['POST'])
+def webhook_handler():
+    """Universal webhook handler for both crawl and LLM extraction jobs."""
+    payload = request.json
+    task_id = payload['task_id']
+    task_type = payload['task_type']
+    status = payload['status']
+
+    print(f"\n{'='*70}")
+    print(f"📬 Webhook Received!")
+    print(f"   Task ID: {task_id}")
+    print(f"   Task Type: {task_type}")
+    print(f"   Status: {status}")
+    print(f"   Timestamp: {payload['timestamp']}")
+
+    if status == 'completed':
+        if 'data' in payload:
+            print(f"   ✅ Data included in webhook")
+            if task_type == 'crawl':
+                results = payload['data'].get('results', [])
+                print(f"   📊 Crawled {len(results)} URL(s)")
+            elif task_type == 'llm_extraction':
+                extracted = payload['data'].get('extracted_content', {})
+                print(f"   🤖 Extracted: {json.dumps(extracted, indent=6)}")
+        else:
+            print(f"   📥 Notification only (fetch data separately)")
+    elif status == 'failed':
+        print(f"   ❌ Error: {payload.get('error', 'Unknown')}")
+
+    print(f"{'='*70}\n")
+    received_webhooks.append(payload)
+
+    return jsonify({"status": "received"}), 200
+
+
+def start_webhook_server():
+    """Start Flask webhook server in background."""
+    app.run(host='0.0.0.0', port=8080, debug=False, use_reloader=False)
+
+
+def demo_1_crawl_webhook_notification_only():
+    """Demo 1: Crawl job with webhook notification (data fetched separately)."""
+    print("\n" + "="*70)
+    print("DEMO 1: Crawl Job - Webhook Notification Only")
+    print("="*70)
+    print("Submitting crawl job with webhook notification...")
+
+    payload = {
+        "urls": ["https://example.com"],
+        "browser_config": {"headless": True},
+        "crawler_config": {"cache_mode": "bypass"},
+        "webhook_config": {
+            "webhook_url": f"{WEBHOOK_BASE_URL}/webhook",
+            "webhook_data_in_payload": False,
+            "webhook_headers": {
+                "X-Demo": "v0.7.6",
+                "X-Type": "crawl"
+            }
+        }
+    }
+
+    response = requests.post(f"{CRAWL4AI_BASE_URL}/crawl/job", json=payload)
+    if response.ok:
+        task_id = response.json()['task_id']
+        print(f"✅ Job submitted: {task_id}")
+        print("⏳ Webhook will notify when complete...")
+        return task_id
+    else:
+        print(f"❌ Failed: {response.text}")
+        return None
+
+
+def demo_2_crawl_webhook_with_data():
+    """Demo 2: Crawl job with full data in webhook payload."""
+    print("\n" + "="*70)
+    print("DEMO 2: Crawl Job - Webhook with Full Data")
+    print("="*70)
+    print("Submitting crawl job with data included in webhook...")
+
+    payload = {
+        "urls": ["https://www.python.org"],
+        "browser_config": {"headless": True},
+        "crawler_config": {"cache_mode": "bypass"},
+        "webhook_config": {
+            "webhook_url": f"{WEBHOOK_BASE_URL}/webhook",
+            "webhook_data_in_payload": True,
+            "webhook_headers": {
+                "X-Demo": "v0.7.6",
+                "X-Type": "crawl-with-data"
+            }
+        }
+    }
+
+    response = requests.post(f"{CRAWL4AI_BASE_URL}/crawl/job", json=payload)
+    if response.ok:
+        task_id = response.json()['task_id']
+        print(f"✅ Job submitted: {task_id}")
+        print("⏳ Webhook will include full results...")
+        return task_id
+    else:
+        print(f"❌ Failed: {response.text}")
+        return None
+
+
+def demo_3_llm_webhook_notification_only():
+    """Demo 3: LLM extraction with webhook notification (NEW in v0.7.6!)."""
+    print("\n" + "="*70)
+    print("DEMO 3: LLM Extraction - Webhook Notification Only (NEW!)")
+    print("="*70)
+    print("Submitting LLM extraction job with webhook notification...")
+
+    payload = {
+        "url": "https://www.example.com",
+        "q": "Extract the main heading and description from this page",
+        "provider": "openai/gpt-4o-mini",
+        "cache": False,
+        "webhook_config": {
+            "webhook_url": f"{WEBHOOK_BASE_URL}/webhook",
+            "webhook_data_in_payload": False,
+            "webhook_headers": {
+                "X-Demo": "v0.7.6",
+                "X-Type": "llm"
+            }
+        }
+    }
+
+    response = requests.post(f"{CRAWL4AI_BASE_URL}/llm/job", json=payload)
+    if response.ok:
+        task_id = response.json()['task_id']
+        print(f"✅ Job submitted: {task_id}")
+        print("⏳ Webhook will notify when LLM extraction completes...")
+        return task_id
+    else:
+        print(f"❌ Failed: {response.text}")
+        return None
+
+
+def demo_4_llm_webhook_with_schema():
+    """Demo 4: LLM extraction with JSON schema and data in webhook (NEW in v0.7.6!)."""
+    print("\n" + "="*70)
+    print("DEMO 4: LLM Extraction - Schema + Full Data in Webhook (NEW!)")
+    print("="*70)
+    print("Submitting LLM extraction with JSON schema...")
+
+    schema = {
+        "type": "object",
+        "properties": {
+            "title": {"type": "string", "description": "Page title"},
+            "description": {"type": "string", "description": "Page description"},
+            "main_topics": {
+                "type": "array",
+                "items": {"type": "string"},
+                "description": "Main topics covered"
+            }
+        },
+        "required": ["title"]
+    }
+
+    payload = {
+        "url": "https://www.python.org",
+        "q": "Extract the title, description, and main topics from this website",
+        "schema": json.dumps(schema),
+        "provider": "openai/gpt-4o-mini",
+        "cache": False,
+        "webhook_config": {
+            "webhook_url": f"{WEBHOOK_BASE_URL}/webhook",
+            "webhook_data_in_payload": True,
+            "webhook_headers": {
+                "X-Demo": "v0.7.6",
+                "X-Type": "llm-with-schema"
+            }
+        }
+    }
+
+    response = requests.post(f"{CRAWL4AI_BASE_URL}/llm/job", json=payload)
+    if response.ok:
+        task_id = response.json()['task_id']
+        print(f"✅ Job submitted: {task_id}")
+        print("⏳ Webhook will include structured extraction results...")
+        return task_id
+    else:
+        print(f"❌ Failed: {response.text}")
+        return None
+
+
+def demo_5_global_webhook_config():
+    """Demo 5: Using global webhook configuration from config.yml."""
+    print("\n" + "="*70)
+    print("DEMO 5: Global Webhook Configuration")
+    print("="*70)
+    print("💡 You can configure a default webhook URL in config.yml:")
+    print("""
+    webhooks:
+      enabled: true
+      default_url: "https://myapp.com/webhooks/default"
+      data_in_payload: false
+      retry:
+        max_attempts: 5
+        initial_delay_ms: 1000
+        max_delay_ms: 32000
+        timeout_ms: 30000
+    """)
+    print("Then submit jobs WITHOUT webhook_config - they'll use the default!")
+    print("This is useful for consistent webhook handling across all jobs.")
+
+
+def demo_6_webhook_retry_logic():
+    """Demo 6: Webhook retry mechanism with exponential backoff."""
+    print("\n" + "="*70)
+    print("DEMO 6: Webhook Retry Logic")
+    print("="*70)
+    print("🔄 Webhook delivery uses exponential backoff retry:")
+    print("   • Max attempts: 5")
+    print("   • Delays: 1s → 2s → 4s → 8s → 16s")
+    print("   • Timeout: 30s per attempt")
+    print("   • Retries on: 5xx errors, network errors, timeouts")
+    print("   • No retry on: 4xx client errors")
+    print("\nThis ensures reliable webhook delivery even with temporary failures!")
+
+
+def print_summary():
+    """Print demo summary and results."""
+    print("\n" + "="*70)
+    print("📊 DEMO SUMMARY")
+    print("="*70)
+    print(f"Total webhooks received: {len(received_webhooks)}")
+
+    crawl_webhooks = [w for w in received_webhooks if w['task_type'] == 'crawl']
+    llm_webhooks = [w for w in received_webhooks if w['task_type'] == 'llm_extraction']
+
+    print(f"\nBreakdown:")
+    print(f"  🕷️  Crawl jobs: {len(crawl_webhooks)}")
+    print(f"  🤖 LLM extraction jobs: {len(llm_webhooks)}")
+
+    print(f"\nDetails:")
+    for i, webhook in enumerate(received_webhooks, 1):
+        icon = "🕷️" if webhook['task_type'] == 'crawl' else "🤖"
+        print(f"  {i}. {icon} {webhook['task_id']}: {webhook['status']}")
+
+    print("\n" + "="*70)
+    print("✨ v0.7.6 KEY FEATURES DEMONSTRATED:")
+    print("="*70)
+    print("✅ Webhook support for /crawl/job")
+    print("✅ Webhook support for /llm/job (NEW!)")
+    print("✅ Notification-only mode (fetch data separately)")
+    print("✅ Data-in-payload mode (get full results in webhook)")
+    print("✅ Custom headers for authentication")
+    print("✅ JSON schema for structured LLM extraction")
+    print("✅ Exponential backoff retry for reliable delivery")
+    print("✅ Global webhook configuration support")
+    print("✅ Universal webhook handler for both job types")
+    print("\n💡 Benefits:")
+    print("   • No more polling - get instant notifications")
+    print("   • Better resource utilization")
+    print("   • Reliable delivery with automatic retries")
+    print("   • Consistent API across crawl and LLM jobs")
+    print("   • Production-ready webhook infrastructure")
+
+
+def main():
+    """Run all demos."""
+    print("\n" + "="*70)
+    print("🚀 Crawl4AI v0.7.6 Release Demo")
+    print("="*70)
+    print("Feature: Webhook Support for Docker Job Queue API")
+    print("="*70)
+
+    # Check if server is running
+    try:
+        health = requests.get(f"{CRAWL4AI_BASE_URL}/health", timeout=5)
+        print(f"✅ Crawl4AI server is running")
+    except:
+        print(f"❌ Cannot connect to Crawl4AI at {CRAWL4AI_BASE_URL}")
+        print("Please start Docker container:")
+        print("  docker run -d -p 11235:11235 --env-file .llm.env unclecode/crawl4ai:0.7.6")
+        return
+
+    # Start webhook server
+    print(f"\n🌐 Starting webhook server at {WEBHOOK_BASE_URL}...")
+    webhook_thread = Thread(target=start_webhook_server, daemon=True)
+    webhook_thread.start()
+    time.sleep(2)
+
+    # Run demos
+    demo_1_crawl_webhook_notification_only()
+    time.sleep(5)
+
+    demo_2_crawl_webhook_with_data()
+    time.sleep(5)
+
+    demo_3_llm_webhook_notification_only()
+    time.sleep(5)
+
+    demo_4_llm_webhook_with_schema()
+    time.sleep(5)
+
+    demo_5_global_webhook_config()
+    demo_6_webhook_retry_logic()
+
+    # Wait for webhooks
+    print("\n⏳ Waiting for all webhooks to arrive...")
+    time.sleep(30)
+
+    # Print summary
+    print_summary()
+
+    print("\n" + "="*70)
+    print("✅ Demo completed!")
+    print("="*70)
+    print("\n📚 Documentation:")
+    print("   • deploy/docker/WEBHOOK_EXAMPLES.md")
+    print("   • docs/examples/docker_webhook_example.py")
+    print("\n🔗 Upgrade:")
+    print("   docker pull unclecode/crawl4ai:0.7.6")
+
+
+if __name__ == "__main__":
+    main()

docs/releases_review/demo_v0.7.7.py

@@ -0,0 +1,628 @@
+#!/usr/bin/env python3
+"""
+Crawl4AI v0.7.7 Release Demo
+============================
+
+This demo showcases the major feature in v0.7.7:
+**Self-Hosting with Real-time Monitoring Dashboard**
+
+Features Demonstrated:
+1. System health monitoring with live metrics
+2. Real-time request tracking (active & completed)
+3. Browser pool management (permanent/hot/cold pools)
+4. Monitor API endpoints for programmatic access
+5. WebSocket streaming for real-time updates
+6. Control actions (kill browser, cleanup, restart)
+7. Production metrics (efficiency, reuse rates, memory)
+
+Prerequisites:
+- Crawl4AI Docker container running on localhost:11235
+- Python packages: pip install httpx websockets
+
+Usage:
+python docs/releases_review/demo_v0.7.7.py
+"""
+
+import asyncio
+import httpx
+import json
+import time
+from datetime import datetime
+from typing import Dict, Any
+
+# Configuration
+CRAWL4AI_BASE_URL = "http://localhost:11235"
+MONITOR_DASHBOARD_URL = f"{CRAWL4AI_BASE_URL}/dashboard"
+
+
+def print_section(title: str, description: str = ""):
+    """Print a formatted section header"""
+    print(f"\n{'=' * 70}")
+    print(f"📊 {title}")
+    if description:
+        print(f"{description}")
+    print(f"{'=' * 70}\n")
+
+
+def print_subsection(title: str):
+    """Print a formatted subsection header"""
+    print(f"\n{'-' * 70}")
+    print(f"{title}")
+    print(f"{'-' * 70}")
+
+
+async def check_server_health():
+    """Check if Crawl4AI server is running"""
+    try:
+        async with httpx.AsyncClient(timeout=5.0) as client:
+            response = await client.get(f"{CRAWL4AI_BASE_URL}/health")
+            return response.status_code == 200
+    except:
+        return False
+
+
+async def demo_1_system_health_overview():
+    """Demo 1: System Health Overview - Live metrics and pool status"""
+    print_section(
+        "Demo 1: System Health Overview",
+        "Real-time monitoring of system resources and browser pool"
+    )
+
+    async with httpx.AsyncClient(timeout=30.0) as client:
+        print("🔍 Fetching system health metrics...")
+
+        try:
+            response = await client.get(f"{CRAWL4AI_BASE_URL}/monitor/health")
+            health = response.json()
+
+            print("\n✅ System Health Report:")
+            print(f"\n🖥️  Container Metrics:")
+            print(f"   • CPU Usage: {health['container']['cpu_percent']:.1f}%")
+            print(f"   • Memory Usage: {health['container']['memory_percent']:.1f}% "
+                  f"({health['container']['memory_mb']:.0f} MB)")
+            print(f"   • Network RX: {health['container']['network_rx_mb']:.2f} MB")
+            print(f"   • Network TX: {health['container']['network_tx_mb']:.2f} MB")
+            print(f"   • Uptime: {health['container']['uptime_seconds']:.0f}s")
+
+            print(f"\n🌐 Browser Pool Status:")
+            print(f"   Permanent Browser:")
+            print(f"   • Active: {health['pool']['permanent']['active']}")
+            print(f"   • Total Requests: {health['pool']['permanent']['total_requests']}")
+
+            print(f"   Hot Pool (Frequently Used Configs):")
+            print(f"   • Count: {health['pool']['hot']['count']}")
+            print(f"   • Total Requests: {health['pool']['hot']['total_requests']}")
+
+            print(f"   Cold Pool (On-Demand Configs):")
+            print(f"   • Count: {health['pool']['cold']['count']}")
+            print(f"   • Total Requests: {health['pool']['cold']['total_requests']}")
+
+            print(f"\n📈 Overall Statistics:")
+            print(f"   • Total Requests: {health['stats']['total_requests']}")
+            print(f"   • Success Rate: {health['stats']['success_rate_percent']:.1f}%")
+            print(f"   • Avg Latency: {health['stats']['avg_latency_ms']:.0f}ms")
+
+            print(f"\n💡 Dashboard URL: {MONITOR_DASHBOARD_URL}")
+
+        except Exception as e:
+            print(f"❌ Error fetching health: {e}")
+
+
+async def demo_2_request_tracking():
+    """Demo 2: Real-time Request Tracking - Generate and monitor requests"""
+    print_section(
+        "Demo 2: Real-time Request Tracking",
+        "Submit crawl jobs and watch them in real-time"
+    )
+
+    async with httpx.AsyncClient(timeout=60.0) as client:
+        print("🚀 Submitting crawl requests...")
+
+        # Submit multiple requests
+        urls_to_crawl = [
+            "https://httpbin.org/html",
+            "https://httpbin.org/json",
+            "https://example.com"
+        ]
+
+        tasks = []
+        for url in urls_to_crawl:
+            task = client.post(
+                f"{CRAWL4AI_BASE_URL}/crawl",
+                json={"urls": [url], "crawler_config": {}}
+            )
+            tasks.append(task)
+
+        print(f"   • Submitting {len(urls_to_crawl)} requests in parallel...")
+        results = await asyncio.gather(*tasks, return_exceptions=True)
+
+        successful = sum(1 for r in results if not isinstance(r, Exception) and r.status_code == 200)
+        print(f"   ✅ {successful}/{len(urls_to_crawl)} requests submitted")
+
+        # Check request tracking
+        print("\n📊 Checking request tracking...")
+        await asyncio.sleep(2)  # Wait for requests to process
+
+        response = await client.get(f"{CRAWL4AI_BASE_URL}/monitor/requests")
+        requests_data = response.json()
+
+        print(f"\n📋 Request Status:")
+        print(f"   • Active Requests: {len(requests_data['active'])}")
+        print(f"   • Completed Requests: {len(requests_data['completed'])}")
+
+        if requests_data['completed']:
+            print(f"\n📝 Recent Completed Requests:")
+            for req in requests_data['completed'][:3]:
+                status_icon = "✅" if req['success'] else "❌"
+                print(f"   {status_icon} {req['endpoint']} - {req['latency_ms']:.0f}ms")
+
+
+async def demo_3_browser_pool_management():
+    """Demo 3: Browser Pool Management - 3-tier architecture in action"""
+    print_section(
+        "Demo 3: Browser Pool Management",
+        "Understanding permanent, hot, and cold browser pools"
+    )
+
+    async with httpx.AsyncClient(timeout=60.0) as client:
+        print("🌊 Testing browser pool with different configurations...")
+
+        # Test 1: Default config (permanent browser)
+        print("\n🔥 Test 1: Default Config → Permanent Browser")
+        for i in range(3):
+            await client.post(
+                f"{CRAWL4AI_BASE_URL}/crawl",
+                json={"urls": [f"https://httpbin.org/html?req={i}"], "crawler_config": {}}
+            )
+            print(f"   • Request {i+1}/3 sent (should use permanent browser)")
+
+        await asyncio.sleep(2)
+
+        # Test 2: Custom viewport (cold → hot promotion after 3 uses)
+        print("\n♨️  Test 2: Custom Viewport → Cold Pool (promoting to Hot)")
+        viewport_config = {"viewport": {"width": 1280, "height": 720}}
+        for i in range(4):
+            await client.post(
+                f"{CRAWL4AI_BASE_URL}/crawl",
+                json={
+                    "urls": [f"https://httpbin.org/json?viewport={i}"],
+                    "browser_config": viewport_config,
+                    "crawler_config": {}
+                }
+            )
+            print(f"   • Request {i+1}/4 sent (cold→hot promotion after 3rd use)")
+
+        await asyncio.sleep(2)
+
+        # Check browser pool status
+        print("\n📊 Browser Pool Report:")
+        response = await client.get(f"{CRAWL4AI_BASE_URL}/monitor/browsers")
+        browsers = response.json()
+
+        print(f"\n🎯 Pool Summary:")
+        print(f"   • Total Browsers: {browsers['summary']['total_count']}")
+        print(f"   • Total Memory: {browsers['summary']['total_memory_mb']} MB")
+        print(f"   • Reuse Rate: {browsers['summary']['reuse_rate_percent']:.1f}%")
+
+        print(f"\n📋 Browser Pool Details:")
+        if browsers['permanent']:
+            for browser in browsers['permanent']:
+                print(f"   🔥 Permanent: {browser['browser_id'][:8]}... | "
+                      f"Requests: {browser['request_count']} | "
+                      f"Memory: {browser['memory_mb']:.0f} MB")
+
+        if browsers['hot']:
+            for browser in browsers['hot']:
+                print(f"   ♨️  Hot: {browser['browser_id'][:8]}... | "
+                      f"Requests: {browser['request_count']} | "
+                      f"Memory: {browser['memory_mb']:.0f} MB")
+
+        if browsers['cold']:
+            for browser in browsers['cold']:
+                print(f"   ❄️  Cold: {browser['browser_id'][:8]}... | "
+                      f"Requests: {browser['request_count']} | "
+                      f"Memory: {browser['memory_mb']:.0f} MB")
+
+
+async def demo_4_monitor_api_endpoints():
+    """Demo 4: Monitor API Endpoints - Complete API surface"""
+    print_section(
+        "Demo 4: Monitor API Endpoints",
+        "Programmatic access to all monitoring data"
+    )
+
+    async with httpx.AsyncClient(timeout=30.0) as client:
+        print("🔌 Testing Monitor API endpoints...")
+
+        # Endpoint performance statistics
+        print_subsection("Endpoint Performance Statistics")
+        response = await client.get(f"{CRAWL4AI_BASE_URL}/monitor/endpoints/stats")
+        endpoint_stats = response.json()
+
+        print("\n📊 Per-Endpoint Analytics:")
+        for endpoint, stats in endpoint_stats.items():
+            print(f"   {endpoint}:")
+            print(f"      • Requests: {stats['count']}")
+            print(f"      • Avg Latency: {stats['avg_latency_ms']:.0f}ms")
+            print(f"      • Success Rate: {stats['success_rate_percent']:.1f}%")
+
+        # Timeline data for charts
+        print_subsection("Timeline Data (for Charts)")
+        response = await client.get(f"{CRAWL4AI_BASE_URL}/monitor/timeline?minutes=5")
+        timeline = response.json()
+
+        print(f"\n📈 Timeline Metrics (last 5 minutes):")
+        print(f"   • Data Points: {len(timeline['memory'])}")
+        if timeline['memory']:
+            latest = timeline['memory'][-1]
+            print(f"   • Latest Memory: {latest['value']:.1f}%")
+            print(f"   • Timestamp: {latest['timestamp']}")
+
+        # Janitor logs
+        print_subsection("Janitor Cleanup Events")
+        response = await client.get(f"{CRAWL4AI_BASE_URL}/monitor/logs/janitor?limit=3")
+        janitor_logs = response.json()
+
+        print(f"\n🧹 Recent Cleanup Activities:")
+        if janitor_logs:
+            for log in janitor_logs[:3]:
+                print(f"   • {log['timestamp']}: {log['message']}")
+        else:
+            print("   (No cleanup events yet - janitor runs periodically)")
+
+        # Error logs
+        print_subsection("Error Monitoring")
+        response = await client.get(f"{CRAWL4AI_BASE_URL}/monitor/logs/errors?limit=3")
+        error_logs = response.json()
+
+        print(f"\n❌ Recent Errors:")
+        if error_logs:
+            for log in error_logs[:3]:
+                print(f"   • {log['timestamp']}: {log['error_type']}")
+                print(f"     {log['message'][:100]}...")
+        else:
+            print("   ✅ No recent errors!")
+
+
+async def demo_5_websocket_streaming():
+    """Demo 5: WebSocket Streaming - Real-time updates"""
+    print_section(
+        "Demo 5: WebSocket Streaming",
+        "Live monitoring with 2-second update intervals"
+    )
+
+    print("⚡ WebSocket Streaming Demo")
+    print("\n💡 The monitoring dashboard uses WebSocket for real-time updates")
+    print(f"   • Connection: ws://localhost:11235/monitor/ws")
+    print(f"   • Update Interval: 2 seconds")
+    print(f"   • Data: Health, requests, browsers, memory, errors")
+
+    print("\n📝 Sample WebSocket Integration Code:")
+    print("""
+    import websockets
+    import json
+
+    async def monitor_realtime():
+        uri = "ws://localhost:11235/monitor/ws"
+        async with websockets.connect(uri) as websocket:
+            while True:
+                data = await websocket.recv()
+                update = json.loads(data)
+
+                print(f"Memory: {update['health']['container']['memory_percent']:.1f}%")
+                print(f"Active Requests: {len(update['requests']['active'])}")
+                print(f"Browser Pool: {update['health']['pool']['permanent']['active']}")
+    """)
+
+    print("\n🌐 Open the dashboard to see WebSocket in action:")
+    print(f"   {MONITOR_DASHBOARD_URL}")
+
+
+async def demo_6_control_actions():
+    """Demo 6: Control Actions - Manual browser management"""
+    print_section(
+        "Demo 6: Control Actions",
+        "Manual control over browser pool and cleanup"
+    )
+
+    async with httpx.AsyncClient(timeout=30.0) as client:
+        print("🎮 Testing control actions...")
+
+        # Force cleanup
+        print_subsection("Force Immediate Cleanup")
+        print("🧹 Triggering manual cleanup...")
+        try:
+            response = await client.post(f"{CRAWL4AI_BASE_URL}/monitor/actions/cleanup")
+            if response.status_code == 200:
+                result = response.json()
+                print(f"   ✅ Cleanup completed")
+                print(f"   • Browsers cleaned: {result.get('cleaned_count', 0)}")
+                print(f"   • Memory freed: {result.get('memory_freed_mb', 0):.1f} MB")
+            else:
+                print(f"   ⚠️  Response: {response.status_code}")
+        except Exception as e:
+            print(f"   ℹ️  Cleanup action: {e}")
+
+        # Get browser list for potential kill/restart
+        print_subsection("Browser Management")
+        response = await client.get(f"{CRAWL4AI_BASE_URL}/monitor/browsers")
+        browsers = response.json()
+
+        cold_browsers = browsers.get('cold', [])
+        if cold_browsers:
+            browser_id = cold_browsers[0]['browser_id']
+            print(f"\n🎯 Example: Kill specific browser")
+            print(f"   POST /monitor/actions/kill_browser")
+            print(f"   JSON: {{'browser_id': '{browser_id[:16]}...'}}")
+            print(f"   → Kills the browser and frees resources")
+
+        print(f"\n🔄 Example: Restart browser")
+        print(f"   POST /monitor/actions/restart_browser")
+        print(f"   JSON: {{'browser_id': 'browser_id_here'}}")
+        print(f"   → Restart a specific browser instance")
+
+        # Reset statistics
+        print_subsection("Reset Statistics")
+        print("📊 Statistics can be reset for fresh monitoring:")
+        print(f"   POST /monitor/stats/reset")
+        print(f"   → Clears all accumulated statistics")
+
+
+async def demo_7_production_metrics():
+    """Demo 7: Production Metrics - Key indicators for operations"""
+    print_section(
+        "Demo 7: Production Metrics",
+        "Critical metrics for production monitoring"
+    )
+
+    async with httpx.AsyncClient(timeout=30.0) as client:
+        print("📊 Key Production Metrics:")
+
+        # Overall health
+        response = await client.get(f"{CRAWL4AI_BASE_URL}/monitor/health")
+        health = response.json()
+
+        # Browser efficiency
+        response = await client.get(f"{CRAWL4AI_BASE_URL}/monitor/browsers")
+        browsers = response.json()
+
+        print("\n🎯 Critical Metrics to Track:")
+
+        print(f"\n1️⃣  Memory Usage Trends")
+        print(f"   • Current: {health['container']['memory_percent']:.1f}%")
+        print(f"   • Alert if: >80%")
+        print(f"   • Action: Trigger cleanup or scale")
+
+        print(f"\n2️⃣  Request Success Rate")
+        print(f"   • Current: {health['stats']['success_rate_percent']:.1f}%")
+        print(f"   • Target: >95%")
+        print(f"   • Alert if: <90%")
+
+        print(f"\n3️⃣  Average Latency")
+        print(f"   • Current: {health['stats']['avg_latency_ms']:.0f}ms")
+        print(f"   • Target: <2000ms")
+        print(f"   • Alert if: >5000ms")
+
+        print(f"\n4️⃣  Browser Pool Efficiency")
+        print(f"   • Reuse Rate: {browsers['summary']['reuse_rate_percent']:.1f}%")
+        print(f"   • Target: >80%")
+        print(f"   • Indicates: Effective browser pooling")
+
+        print(f"\n5️⃣  Total Browsers")
+        print(f"   • Current: {browsers['summary']['total_count']}")
+        print(f"   • Alert if: >20 (possible leak)")
+        print(f"   • Check: Janitor is running correctly")
+
+        print(f"\n6️⃣  Error Frequency")
+        response = await client.get(f"{CRAWL4AI_BASE_URL}/monitor/logs/errors?limit=10")
+        errors = response.json()
+        print(f"   • Recent Errors: {len(errors)}")
+        print(f"   • Alert if: >10 in last hour")
+        print(f"   • Action: Review error patterns")
+
+        print("\n💡 Integration Examples:")
+        print("   • Prometheus: Scrape /monitor/health")
+        print("   • Alerting: Monitor memory, success rate, latency")
+        print("   • Dashboards: WebSocket streaming to custom UI")
+        print("   • Log Aggregation: Collect /monitor/logs/* endpoints")
+
+
+async def demo_8_self_hosting_value():
+    """Demo 8: Self-Hosting Value Proposition"""
+    print_section(
+        "Demo 8: Why Self-Host Crawl4AI?",
+        "The value proposition of owning your infrastructure"
+    )
+
+    print("🎯 Self-Hosting Benefits:\n")
+
+    print("🔒 Data Privacy & Security")
+    print("   • Your data never leaves your infrastructure")
+    print("   • No third-party access to crawled content")
+    print("   • Keep sensitive workflows behind your firewall")
+
+    print("\n💰 Cost Control")
+    print("   • No per-request pricing or rate limits")
+    print("   • Predictable infrastructure costs")
+    print("   • Scale based on your actual needs")
+
+    print("\n🎯 Full Customization")
+    print("   • Complete control over browser configs")
+    print("   • Custom hooks and strategies")
+    print("   • Tailored monitoring and alerting")
+
+    print("\n📊 Complete Transparency")
+    print("   • Real-time monitoring dashboard")
+    print("   • Full visibility into system performance")
+    print("   • Detailed request and error tracking")
+
+    print("\n⚡ Performance & Flexibility")
+    print("   • Direct access, no network overhead")
+    print("   • Integrate with existing infrastructure")
+    print("   • Custom resource allocation")
+
+    print("\n🛡️ Enterprise-Grade Operations")
+    print("   • Prometheus integration ready")
+    print("   • WebSocket for real-time dashboards")
+    print("   • Full API for automation")
+    print("   • Manual controls for troubleshooting")
+
+    print(f"\n🌐 Get Started:")
+    print(f"   docker pull unclecode/crawl4ai:0.7.7")
+    print(f"   docker run -d -p 11235:11235 --shm-size=1g unclecode/crawl4ai:0.7.7")
+    print(f"   # Visit: {MONITOR_DASHBOARD_URL}")
+
+
+def print_summary():
+    """Print comprehensive demo summary"""
+    print("\n" + "=" * 70)
+    print("📊 DEMO SUMMARY - Crawl4AI v0.7.7")
+    print("=" * 70)
+
+    print("\n✨ Features Demonstrated:")
+    print("=" * 70)
+    print("✅ System Health Overview")
+    print("   → Real-time CPU, memory, network, and uptime monitoring")
+
+    print("\n✅ Request Tracking")
+    print("   → Active and completed request monitoring with full details")
+
+    print("\n✅ Browser Pool Management")
+    print("   → 3-tier architecture: Permanent, Hot, and Cold pools")
+    print("   → Automatic promotion and cleanup")
+
+    print("\n✅ Monitor API Endpoints")
+    print("   → Complete REST API for programmatic access")
+    print("   → Health, requests, browsers, timeline, logs, errors")
+
+    print("\n✅ WebSocket Streaming")
+    print("   → Real-time updates every 2 seconds")
+    print("   → Build custom dashboards with live data")
+
+    print("\n✅ Control Actions")
+    print("   → Manual browser management (kill, restart)")
+    print("   → Force cleanup and statistics reset")
+
+    print("\n✅ Production Metrics")
+    print("   → 6 critical metrics for operational excellence")
+    print("   → Prometheus integration patterns")
+
+    print("\n✅ Self-Hosting Value")
+    print("   → Data privacy, cost control, full customization")
+    print("   → Enterprise-grade transparency and control")
+
+    print("\n" + "=" * 70)
+    print("🎯 What's New in v0.7.7?")
+    print("=" * 70)
+    print("• 📊 Complete Real-time Monitoring System")
+    print("• 🌐 Interactive Web Dashboard (/dashboard)")
+    print("• 🔌 Comprehensive Monitor API")
+    print("• ⚡ WebSocket Streaming (2-second updates)")
+    print("• 🎮 Manual Control Actions")
+    print("• 📈 Production Integration Examples")
+    print("• 🏭 Prometheus, Alerting, Log Aggregation")
+    print("• 🔥 Smart Browser Pool (Permanent/Hot/Cold)")
+    print("• 🧹 Automatic Janitor Cleanup")
+    print("• 📋 Full Request & Error Tracking")
+
+    print("\n" + "=" * 70)
+    print("💡 Why This Matters")
+    print("=" * 70)
+    print("Before v0.7.7: Docker was just a containerized crawler")
+    print("After v0.7.7: Complete self-hosting platform with enterprise monitoring")
+    print("\nYou now have:")
+    print("  • Full visibility into what's happening inside")
+    print("  • Real-time operational dashboards")
+    print("  • Complete control over browser resources")
+    print("  • Production-ready observability")
+    print("  • Zero external dependencies")
+
+    print("\n" + "=" * 70)
+    print("📚 Next Steps")
+    print("=" * 70)
+    print(f"1. Open the dashboard: {MONITOR_DASHBOARD_URL}")
+    print("2. Read the docs: https://docs.crawl4ai.com/basic/self-hosting/")
+    print("3. Try the Monitor API endpoints yourself")
+    print("4. Set up Prometheus integration for production")
+    print("5. Build custom dashboards with WebSocket streaming")
+
+    print("\n" + "=" * 70)
+    print("🔗 Resources")
+    print("=" * 70)
+    print(f"• Dashboard: {MONITOR_DASHBOARD_URL}")
+    print(f"• Health API: {CRAWL4AI_BASE_URL}/monitor/health")
+    print(f"• Documentation: https://docs.crawl4ai.com/")
+    print(f"• GitHub: https://github.com/unclecode/crawl4ai")
+
+    print("\n" + "=" * 70)
+    print("🎉 You're now in control of your web crawling destiny!")
+    print("=" * 70)
+
+
+async def main():
+    """Run all demos"""
+    print("\n" + "=" * 70)
+    print("🚀 Crawl4AI v0.7.7 Release Demo")
+    print("=" * 70)
+    print("Feature: Self-Hosting with Real-time Monitoring Dashboard")
+    print("=" * 70)
+
+    # Check if server is running
+    print("\n🔍 Checking Crawl4AI server...")
+    server_running = await check_server_health()
+
+    if not server_running:
+        print(f"❌ Cannot connect to Crawl4AI at {CRAWL4AI_BASE_URL}")
+        print("\nPlease start the Docker container:")
+        print("  docker pull unclecode/crawl4ai:0.7.7")
+        print("  docker run -d -p 11235:11235 --shm-size=1g unclecode/crawl4ai:0.7.7")
+        print("\nThen re-run this demo.")
+        return
+
+    print(f"✅ Crawl4AI server is running!")
+    print(f"📊 Dashboard available at: {MONITOR_DASHBOARD_URL}")
+
+    # Run all demos
+    demos = [
+        demo_1_system_health_overview,
+        demo_2_request_tracking,
+        demo_3_browser_pool_management,
+        demo_4_monitor_api_endpoints,
+        demo_5_websocket_streaming,
+        demo_6_control_actions,
+        demo_7_production_metrics,
+        demo_8_self_hosting_value,
+    ]
+
+    for i, demo_func in enumerate(demos, 1):
+        try:
+            await demo_func()
+
+            if i < len(demos):
+                await asyncio.sleep(2)  # Brief pause between demos
+
+        except KeyboardInterrupt:
+            print(f"\n\n⚠️  Demo interrupted by user")
+            return
+        except Exception as e:
+            print(f"\n❌ Demo {i} error: {e}")
+            print("Continuing to next demo...\n")
+            continue
+
+    # Print comprehensive summary
+    print_summary()
+
+    print("\n" + "=" * 70)
+    print("✅ Demo completed!")
+    print("=" * 70)
+
+
+if __name__ == "__main__":
+    try:
+        asyncio.run(main())
+    except KeyboardInterrupt:
+        print("\n\n👋 Demo stopped by user. Thanks for trying Crawl4AI v0.7.7!")
+    except Exception as e:
+        print(f"\n\n❌ Demo failed: {e}")
+        print("Make sure the Docker container is running:")
+        print("  docker run -d -p 11235:11235 --shm-size=1g unclecode/crawl4ai:0.7.7")

docs/releases_review/demo_v0.7.8.py

@@ -0,0 +1,910 @@
+#!/usr/bin/env python3
+"""
+Crawl4AI v0.7.8 Release Demo - Verification Tests
+==================================================
+
+This demo ACTUALLY RUNS and VERIFIES the bug fixes in v0.7.8.
+Each test executes real code and validates the fix is working.
+
+Bug Fixes Verified:
+1. ProxyConfig JSON serialization (#1629)
+2. Configurable backoff parameters (#1269)
+3. LLM Strategy input_format support (#1178)
+4. Raw HTML URL variable (#1116)
+5. Relative URLs after redirects (#1268)
+6. pypdf migration (#1412)
+7. Pydantic v2 ConfigDict (#678)
+8. Docker ContentRelevanceFilter (#1642) - requires Docker
+9. Docker .cache permissions (#1638) - requires Docker
+10. AdaptiveCrawler query expansion (#1621) - requires LLM API key
+11. Import statement formatting (#1181)
+
+Usage:
+    python docs/releases_review/demo_v0.7.8.py
+
+For Docker tests:
+    docker run -d -p 11235:11235 --shm-size=1g unclecode/crawl4ai:0.7.8
+    python docs/releases_review/demo_v0.7.8.py
+"""
+
+import asyncio
+import json
+import sys
+import warnings
+import os
+import tempfile
+from typing import Tuple, Optional
+from dataclasses import dataclass
+
+# Test results tracking
+@dataclass
+class TestResult:
+    name: str
+    issue: str
+    passed: bool
+    message: str
+    skipped: bool = False
+
+
+results: list[TestResult] = []
+
+
+def print_header(title: str):
+    print(f"\n{'=' * 70}")
+    print(f"{title}")
+    print(f"{'=' * 70}")
+
+
+def print_test(name: str, issue: str):
+    print(f"\n[TEST] {name} ({issue})")
+    print("-" * 50)
+
+
+def record_result(name: str, issue: str, passed: bool, message: str, skipped: bool = False):
+    results.append(TestResult(name, issue, passed, message, skipped))
+    if skipped:
+        print(f"  SKIPPED: {message}")
+    elif passed:
+        print(f"  PASSED: {message}")
+    else:
+        print(f"  FAILED: {message}")
+
+
+# =============================================================================
+# TEST 1: ProxyConfig JSON Serialization (#1629)
+# =============================================================================
+async def test_proxy_config_serialization():
+    """
+    Verify BrowserConfig.to_dict() properly serializes ProxyConfig to JSON.
+
+    BEFORE: ProxyConfig was included as object, causing JSON serialization to fail
+    AFTER: ProxyConfig.to_dict() is called, producing valid JSON
+    """
+    print_test("ProxyConfig JSON Serialization", "#1629")
+
+    try:
+        from crawl4ai import BrowserConfig
+        from crawl4ai.async_configs import ProxyConfig
+
+        # Create config with ProxyConfig
+        proxy = ProxyConfig(
+            server="http://proxy.example.com:8080",
+            username="testuser",
+            password="testpass"
+        )
+        browser_config = BrowserConfig(headless=True, proxy_config=proxy)
+
+        # Test 1: to_dict() should return dict for proxy_config
+        config_dict = browser_config.to_dict()
+        proxy_dict = config_dict.get('proxy_config')
+
+        if not isinstance(proxy_dict, dict):
+            record_result("ProxyConfig Serialization", "#1629", False,
+                         f"proxy_config is {type(proxy_dict)}, expected dict")
+            return
+
+        # Test 2: Should be JSON serializable
+        try:
+            json_str = json.dumps(config_dict)
+            json.loads(json_str)  # Verify valid JSON
+        except (TypeError, json.JSONDecodeError) as e:
+            record_result("ProxyConfig Serialization", "#1629", False,
+                         f"JSON serialization failed: {e}")
+            return
+
+        # Test 3: Verify proxy data is preserved
+        if proxy_dict.get('server') != "http://proxy.example.com:8080":
+            record_result("ProxyConfig Serialization", "#1629", False,
+                         "Proxy server not preserved in serialization")
+            return
+
+        record_result("ProxyConfig Serialization", "#1629", True,
+                     "BrowserConfig with ProxyConfig serializes to valid JSON")
+
+    except Exception as e:
+        record_result("ProxyConfig Serialization", "#1629", False, f"Exception: {e}")
+
+
+# =============================================================================
+# TEST 2: Configurable Backoff Parameters (#1269)
+# =============================================================================
+async def test_configurable_backoff():
+    """
+    Verify LLMConfig accepts and stores backoff configuration parameters.
+
+    BEFORE: Backoff was hardcoded (delay=2, attempts=3, factor=2)
+    AFTER: LLMConfig accepts backoff_base_delay, backoff_max_attempts, backoff_exponential_factor
+    """
+    print_test("Configurable Backoff Parameters", "#1269")
+
+    try:
+        from crawl4ai import LLMConfig
+
+        # Test 1: Default values
+        default_config = LLMConfig(provider="openai/gpt-4o-mini")
+
+        if default_config.backoff_base_delay != 2:
+            record_result("Configurable Backoff", "#1269", False,
+                         f"Default base_delay is {default_config.backoff_base_delay}, expected 2")
+            return
+
+        if default_config.backoff_max_attempts != 3:
+            record_result("Configurable Backoff", "#1269", False,
+                         f"Default max_attempts is {default_config.backoff_max_attempts}, expected 3")
+            return
+
+        if default_config.backoff_exponential_factor != 2:
+            record_result("Configurable Backoff", "#1269", False,
+                         f"Default exponential_factor is {default_config.backoff_exponential_factor}, expected 2")
+            return
+
+        # Test 2: Custom values
+        custom_config = LLMConfig(
+            provider="openai/gpt-4o-mini",
+            backoff_base_delay=5,
+            backoff_max_attempts=10,
+            backoff_exponential_factor=3
+        )
+
+        if custom_config.backoff_base_delay != 5:
+            record_result("Configurable Backoff", "#1269", False,
+                         f"Custom base_delay is {custom_config.backoff_base_delay}, expected 5")
+            return
+
+        if custom_config.backoff_max_attempts != 10:
+            record_result("Configurable Backoff", "#1269", False,
+                         f"Custom max_attempts is {custom_config.backoff_max_attempts}, expected 10")
+            return
+
+        if custom_config.backoff_exponential_factor != 3:
+            record_result("Configurable Backoff", "#1269", False,
+                         f"Custom exponential_factor is {custom_config.backoff_exponential_factor}, expected 3")
+            return
+
+        # Test 3: to_dict() includes backoff params
+        config_dict = custom_config.to_dict()
+        if 'backoff_base_delay' not in config_dict:
+            record_result("Configurable Backoff", "#1269", False,
+                         "backoff_base_delay missing from to_dict()")
+            return
+
+        record_result("Configurable Backoff", "#1269", True,
+                     "LLMConfig accepts and stores custom backoff parameters")
+
+    except Exception as e:
+        record_result("Configurable Backoff", "#1269", False, f"Exception: {e}")
+
+
+# =============================================================================
+# TEST 3: LLM Strategy Input Format (#1178)
+# =============================================================================
+async def test_llm_input_format():
+    """
+    Verify LLMExtractionStrategy accepts input_format parameter.
+
+    BEFORE: Always used markdown input
+    AFTER: Supports "markdown", "html", "fit_markdown", "cleaned_html", "fit_html"
+    """
+    print_test("LLM Strategy Input Format", "#1178")
+
+    try:
+        from crawl4ai import LLMExtractionStrategy, LLMConfig
+
+        llm_config = LLMConfig(provider="openai/gpt-4o-mini")
+
+        # Test 1: Default is markdown
+        default_strategy = LLMExtractionStrategy(
+            llm_config=llm_config,
+            instruction="Extract data"
+        )
+
+        if default_strategy.input_format != "markdown":
+            record_result("LLM Input Format", "#1178", False,
+                         f"Default input_format is '{default_strategy.input_format}', expected 'markdown'")
+            return
+
+        # Test 2: Can set to html
+        html_strategy = LLMExtractionStrategy(
+            llm_config=llm_config,
+            instruction="Extract data",
+            input_format="html"
+        )
+
+        if html_strategy.input_format != "html":
+            record_result("LLM Input Format", "#1178", False,
+                         f"HTML input_format is '{html_strategy.input_format}', expected 'html'")
+            return
+
+        # Test 3: Can set to fit_markdown
+        fit_strategy = LLMExtractionStrategy(
+            llm_config=llm_config,
+            instruction="Extract data",
+            input_format="fit_markdown"
+        )
+
+        if fit_strategy.input_format != "fit_markdown":
+            record_result("LLM Input Format", "#1178", False,
+                         f"fit_markdown input_format is '{fit_strategy.input_format}'")
+            return
+
+        record_result("LLM Input Format", "#1178", True,
+                     "LLMExtractionStrategy accepts all input_format options")
+
+    except Exception as e:
+        record_result("LLM Input Format", "#1178", False, f"Exception: {e}")
+
+
+# =============================================================================
+# TEST 4: Raw HTML URL Variable (#1116)
+# =============================================================================
+async def test_raw_html_url_variable():
+    """
+    Verify that raw: prefix URLs pass "Raw HTML" to extraction strategy.
+
+    BEFORE: Entire HTML blob was passed as URL parameter
+    AFTER: "Raw HTML" string is passed as URL parameter
+    """
+    print_test("Raw HTML URL Variable", "#1116")
+
+    try:
+        from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
+        from crawl4ai.extraction_strategy import ExtractionStrategy
+
+        # Custom strategy to capture what URL is passed
+        class URLCapturingStrategy(ExtractionStrategy):
+            captured_url = None
+
+            def extract(self, url: str, html: str, *args, **kwargs):
+                URLCapturingStrategy.captured_url = url
+                return [{"content": "test"}]
+
+        html_content = "<html><body><h1>Test</h1></body></html>"
+        strategy = URLCapturingStrategy()
+
+        async with AsyncWebCrawler() as crawler:
+            result = await crawler.arun(
+                url=f"raw:{html_content}",
+                config=CrawlerRunConfig(
+                    extraction_strategy=strategy
+                )
+            )
+
+        captured = URLCapturingStrategy.captured_url
+
+        if captured is None:
+            record_result("Raw HTML URL Variable", "#1116", False,
+                         "Extraction strategy was not called")
+            return
+
+        if captured == html_content or captured.startswith("<html"):
+            record_result("Raw HTML URL Variable", "#1116", False,
+                         f"URL contains HTML content instead of 'Raw HTML': {captured[:50]}...")
+            return
+
+        if captured != "Raw HTML":
+            record_result("Raw HTML URL Variable", "#1116", False,
+                         f"URL is '{captured}', expected 'Raw HTML'")
+            return
+
+        record_result("Raw HTML URL Variable", "#1116", True,
+                     "Extraction strategy receives 'Raw HTML' as URL for raw: prefix")
+
+    except Exception as e:
+        record_result("Raw HTML URL Variable", "#1116", False, f"Exception: {e}")
+
+
+# =============================================================================
+# TEST 5: Relative URLs After Redirects (#1268)
+# =============================================================================
+async def test_redirect_url_handling():
+    """
+    Verify that redirected_url reflects the final URL after JS navigation.
+
+    BEFORE: redirected_url was the original URL, not the final URL
+    AFTER: redirected_url is captured after JS execution completes
+    """
+    print_test("Relative URLs After Redirects", "#1268")
+
+    try:
+        from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
+
+        # Test with a URL that we know the final state of
+        # We'll use httpbin which doesn't redirect, but verify the mechanism works
+        test_url = "https://httpbin.org/html"
+
+        async with AsyncWebCrawler() as crawler:
+            result = await crawler.arun(
+                url=test_url,
+                config=CrawlerRunConfig()
+            )
+
+        # Verify redirected_url is populated
+        if not result.redirected_url:
+            record_result("Redirect URL Handling", "#1268", False,
+                         "redirected_url is empty")
+            return
+
+        # For non-redirecting URL, should match original or be the final URL
+        if not result.redirected_url.startswith("https://httpbin.org"):
+            record_result("Redirect URL Handling", "#1268", False,
+                         f"redirected_url is unexpected: {result.redirected_url}")
+            return
+
+        # Verify links are present and resolved
+        if result.links:
+            # Check that internal links have full URLs
+            internal_links = result.links.get('internal', [])
+            external_links = result.links.get('external', [])
+            all_links = internal_links + external_links
+
+            for link in all_links[:5]:  # Check first 5 links
+                href = link.get('href', '')
+                if href and not href.startswith(('http://', 'https://', 'mailto:', 'tel:', '#', 'javascript:')):
+                    record_result("Redirect URL Handling", "#1268", False,
+                                 f"Link not resolved to absolute URL: {href}")
+                    return
+
+        record_result("Redirect URL Handling", "#1268", True,
+                     f"redirected_url correctly captured: {result.redirected_url}")
+
+    except Exception as e:
+        record_result("Redirect URL Handling", "#1268", False, f"Exception: {e}")
+
+
+# =============================================================================
+# TEST 6: pypdf Migration (#1412)
+# =============================================================================
+async def test_pypdf_migration():
+    """
+    Verify pypdf is used instead of deprecated PyPDF2.
+
+    BEFORE: Used PyPDF2 (deprecated since 2022)
+    AFTER: Uses pypdf (actively maintained)
+    """
+    print_test("pypdf Migration", "#1412")
+
+    try:
+        # Test 1: pypdf should be importable (if pdf extra is installed)
+        try:
+            import pypdf
+            pypdf_available = True
+            pypdf_version = pypdf.__version__
+        except ImportError:
+            pypdf_available = False
+            pypdf_version = None
+
+        # Test 2: PyPDF2 should NOT be imported by crawl4ai
+        # Check if the processor uses pypdf
+        try:
+            from crawl4ai.processors.pdf import processor
+            processor_source = open(processor.__file__).read()
+
+            uses_pypdf = 'from pypdf' in processor_source or 'import pypdf' in processor_source
+            uses_pypdf2 = 'from PyPDF2' in processor_source or 'import PyPDF2' in processor_source
+
+            if uses_pypdf2 and not uses_pypdf:
+                record_result("pypdf Migration", "#1412", False,
+                             "PDF processor still uses PyPDF2")
+                return
+
+            if uses_pypdf:
+                record_result("pypdf Migration", "#1412", True,
+                             f"PDF processor uses pypdf{' v' + pypdf_version if pypdf_version else ''}")
+                return
+            else:
+                record_result("pypdf Migration", "#1412", True,
+                             "PDF processor found, pypdf dependency updated", skipped=not pypdf_available)
+                return
+
+        except ImportError:
+            # PDF processor not available
+            if pypdf_available:
+                record_result("pypdf Migration", "#1412", True,
+                             f"pypdf v{pypdf_version} is installed (PDF processor not loaded)")
+            else:
+                record_result("pypdf Migration", "#1412", True,
+                             "PDF support not installed (optional feature)", skipped=True)
+            return
+
+    except Exception as e:
+        record_result("pypdf Migration", "#1412", False, f"Exception: {e}")
+
+
+# =============================================================================
+# TEST 7: Pydantic v2 ConfigDict (#678)
+# =============================================================================
+async def test_pydantic_configdict():
+    """
+    Verify no Pydantic deprecation warnings for Config class.
+
+    BEFORE: Used deprecated 'class Config' syntax
+    AFTER: Uses ConfigDict for Pydantic v2 compatibility
+    """
+    print_test("Pydantic v2 ConfigDict", "#678")
+
+    try:
+        import pydantic
+        from pydantic import __version__ as pydantic_version
+
+        # Capture warnings during import
+        with warnings.catch_warnings(record=True) as w:
+            warnings.simplefilter("always", DeprecationWarning)
+
+            # Import models that might have Config classes
+            from crawl4ai.models import CrawlResult, MarkdownGenerationResult
+            from crawl4ai.async_configs import CrawlerRunConfig, BrowserConfig
+
+            # Filter for Pydantic-related deprecation warnings
+            pydantic_warnings = [
+                warning for warning in w
+                if 'pydantic' in str(warning.message).lower()
+                or 'config' in str(warning.message).lower()
+            ]
+
+            if pydantic_warnings:
+                warning_msgs = [str(w.message) for w in pydantic_warnings[:3]]
+                record_result("Pydantic ConfigDict", "#678", False,
+                             f"Deprecation warnings: {warning_msgs}")
+                return
+
+        # Verify models work correctly
+        try:
+            # Test that models can be instantiated without issues
+            config = CrawlerRunConfig()
+            browser = BrowserConfig()
+
+            record_result("Pydantic ConfigDict", "#678", True,
+                         f"No deprecation warnings with Pydantic v{pydantic_version}")
+        except Exception as e:
+            record_result("Pydantic ConfigDict", "#678", False,
+                         f"Model instantiation failed: {e}")
+
+    except Exception as e:
+        record_result("Pydantic ConfigDict", "#678", False, f"Exception: {e}")
+
+
+# =============================================================================
+# TEST 8: Docker ContentRelevanceFilter (#1642)
+# =============================================================================
+async def test_docker_content_filter():
+    """
+    Verify ContentRelevanceFilter deserializes correctly in Docker API.
+
+    BEFORE: Docker API failed to import/instantiate ContentRelevanceFilter
+    AFTER: Filter is properly exported and deserializable
+    """
+    print_test("Docker ContentRelevanceFilter", "#1642")
+
+    # First verify the fix in local code
+    try:
+        # Test 1: ContentRelevanceFilter should be importable from crawl4ai
+        from crawl4ai import ContentRelevanceFilter
+
+        # Test 2: Should be instantiable
+        filter_instance = ContentRelevanceFilter(
+            query="test query",
+            threshold=0.3
+        )
+
+        if not hasattr(filter_instance, 'query'):
+            record_result("Docker ContentRelevanceFilter", "#1642", False,
+                         "ContentRelevanceFilter missing query attribute")
+            return
+
+    except ImportError as e:
+        record_result("Docker ContentRelevanceFilter", "#1642", False,
+                     f"ContentRelevanceFilter not exported: {e}")
+        return
+    except Exception as e:
+        record_result("Docker ContentRelevanceFilter", "#1642", False,
+                     f"ContentRelevanceFilter instantiation failed: {e}")
+        return
+
+    # Test Docker API if available
+    try:
+        import httpx
+
+        async with httpx.AsyncClient(timeout=5.0) as client:
+            response = await client.get("http://localhost:11235/health")
+            if response.status_code != 200:
+                raise Exception("Docker not available")
+
+        # Docker is running, test the API
+        async with httpx.AsyncClient(timeout=30.0) as client:
+            request = {
+                "urls": ["https://httpbin.org/html"],
+                "crawler_config": {
+                    "deep_crawl_strategy": {
+                        "type": "BFSDeepCrawlStrategy",
+                        "max_depth": 1,
+                        "filter_chain": [
+                            {
+                                "type": "ContentTypeFilter",
+                                "allowed_types": ["text/html"]
+                            }
+                        ]
+                    }
+                }
+            }
+
+            response = await client.post(
+                "http://localhost:11235/crawl",
+                json=request
+            )
+
+            if response.status_code == 200:
+                record_result("Docker ContentRelevanceFilter", "#1642", True,
+                             "Filter deserializes correctly in Docker API")
+            else:
+                record_result("Docker ContentRelevanceFilter", "#1642", False,
+                             f"Docker API returned {response.status_code}: {response.text[:100]}")
+
+    except ImportError:
+        record_result("Docker ContentRelevanceFilter", "#1642", True,
+                     "ContentRelevanceFilter exportable (Docker test skipped - httpx not installed)",
+                     skipped=True)
+    except Exception as e:
+        record_result("Docker ContentRelevanceFilter", "#1642", True,
+                     f"ContentRelevanceFilter exportable (Docker test skipped: {e})",
+                     skipped=True)
+
+
+# =============================================================================
+# TEST 9: Docker Cache Permissions (#1638)
+# =============================================================================
+async def test_docker_cache_permissions():
+    """
+    Verify Docker image has correct .cache folder permissions.
+
+    This test requires Docker container to be running.
+    """
+    print_test("Docker Cache Permissions", "#1638")
+
+    try:
+        import httpx
+
+        async with httpx.AsyncClient(timeout=5.0) as client:
+            response = await client.get("http://localhost:11235/health")
+            if response.status_code != 200:
+                raise Exception("Docker not available")
+
+        # Test by making a crawl request with caching
+        async with httpx.AsyncClient(timeout=60.0) as client:
+            request = {
+                "urls": ["https://httpbin.org/html"],
+                "crawler_config": {
+                    "cache_mode": "enabled"
+                }
+            }
+
+            response = await client.post(
+                "http://localhost:11235/crawl",
+                json=request
+            )
+
+            if response.status_code == 200:
+                result = response.json()
+                # Check if there were permission errors
+                if "permission" in str(result).lower() and "denied" in str(result).lower():
+                    record_result("Docker Cache Permissions", "#1638", False,
+                                 "Permission denied error in response")
+                else:
+                    record_result("Docker Cache Permissions", "#1638", True,
+                                 "Crawl with caching succeeded in Docker")
+            else:
+                error_text = response.text[:200]
+                if "permission" in error_text.lower():
+                    record_result("Docker Cache Permissions", "#1638", False,
+                                 f"Permission error: {error_text}")
+                else:
+                    record_result("Docker Cache Permissions", "#1638", False,
+                                 f"Request failed: {response.status_code}")
+
+    except ImportError:
+        record_result("Docker Cache Permissions", "#1638", True,
+                     "Skipped - httpx not installed", skipped=True)
+    except Exception as e:
+        record_result("Docker Cache Permissions", "#1638", True,
+                     f"Skipped - Docker not available: {e}", skipped=True)
+
+
+# =============================================================================
+# TEST 10: AdaptiveCrawler Query Expansion (#1621)
+# =============================================================================
+async def test_adaptive_crawler_embedding():
+    """
+    Verify EmbeddingStrategy LLM code is uncommented and functional.
+
+    BEFORE: LLM call was commented out, using hardcoded mock data
+    AFTER: Actually calls LLM for query expansion
+    """
+    print_test("AdaptiveCrawler Query Expansion", "#1621")
+
+    try:
+        # Read the source file to verify the fix
+        import crawl4ai.adaptive_crawler as adaptive_module
+        source_file = adaptive_module.__file__
+
+        with open(source_file, 'r') as f:
+            source_code = f.read()
+
+        # Check that the LLM call is NOT commented out
+        # Look for the perform_completion_with_backoff call
+
+        # Find the EmbeddingStrategy section
+        if 'class EmbeddingStrategy' not in source_code:
+            record_result("AdaptiveCrawler Query Expansion", "#1621", True,
+                         "EmbeddingStrategy not in adaptive_crawler (may have moved)",
+                         skipped=True)
+            return
+
+        # Check if the mock data line is commented out
+        # and the actual LLM call is NOT commented out
+        lines = source_code.split('\n')
+        in_embedding_strategy = False
+        found_llm_call = False
+        mock_data_commented = False
+
+        for i, line in enumerate(lines):
+            if 'class EmbeddingStrategy' in line:
+                in_embedding_strategy = True
+            elif in_embedding_strategy and line.strip().startswith('class '):
+                in_embedding_strategy = False
+
+            if in_embedding_strategy:
+                # Check for uncommented LLM call
+                if 'perform_completion_with_backoff' in line and not line.strip().startswith('#'):
+                    found_llm_call = True
+                # Check for commented mock data
+                if "variations ={'queries'" in line or 'variations = {\'queries\'' in line:
+                    if line.strip().startswith('#'):
+                        mock_data_commented = True
+
+        if found_llm_call:
+            record_result("AdaptiveCrawler Query Expansion", "#1621", True,
+                         "LLM call is active in EmbeddingStrategy")
+        else:
+            # Check if the entire embedding strategy exists but might be structured differently
+            if 'perform_completion_with_backoff' in source_code:
+                record_result("AdaptiveCrawler Query Expansion", "#1621", True,
+                             "perform_completion_with_backoff found in module")
+            else:
+                record_result("AdaptiveCrawler Query Expansion", "#1621", False,
+                             "LLM call not found or still commented out")
+
+    except Exception as e:
+        record_result("AdaptiveCrawler Query Expansion", "#1621", False, f"Exception: {e}")
+
+
+# =============================================================================
+# TEST 11: Import Statement Formatting (#1181)
+# =============================================================================
+async def test_import_formatting():
+    """
+    Verify code extraction properly formats import statements.
+
+    BEFORE: Import statements were concatenated without newlines
+    AFTER: Import statements have proper newline separation
+    """
+    print_test("Import Statement Formatting", "#1181")
+
+    try:
+        from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
+
+        # Create HTML with code containing imports
+        html_with_code = """
+        <html>
+        <body>
+        <pre><code>
+import os
+import sys
+from pathlib import Path
+from typing import List, Dict
+
+def main():
+    pass
+        </code></pre>
+        </body>
+        </html>
+        """
+
+        async with AsyncWebCrawler() as crawler:
+            result = await crawler.arun(
+                url=f"raw:{html_with_code}",
+                config=CrawlerRunConfig()
+            )
+
+        markdown = result.markdown.raw_markdown if result.markdown else ""
+
+        # Check that imports are not concatenated on the same line
+        # Bad: "import osimport sys" (no newline between statements)
+        # This is the actual bug - statements getting merged on same line
+        bad_patterns = [
+            "import os import sys",      # Space but no newline
+            "import osimport sys",       # No space or newline
+            "import os from pathlib",    # Space but no newline
+            "import osfrom pathlib",     # No space or newline
+        ]
+
+        markdown_single_line = markdown.replace('\n', ' ')  # Convert newlines to spaces
+
+        for pattern in bad_patterns:
+            # Check if pattern exists without proper line separation
+            if pattern.replace(' ', '') in markdown_single_line.replace(' ', ''):
+                # Verify it's actually on same line (not just adjacent after newline removal)
+                lines = markdown.split('\n')
+                for line in lines:
+                    if 'import' in line.lower():
+                        # Count import statements on this line
+                        import_count = line.lower().count('import ')
+                        if import_count > 1:
+                            record_result("Import Formatting", "#1181", False,
+                                         f"Multiple imports on same line: {line[:60]}...")
+                            return
+
+        # Verify imports are present
+        if "import" in markdown.lower():
+            record_result("Import Formatting", "#1181", True,
+                         "Import statements are properly line-separated")
+        else:
+            record_result("Import Formatting", "#1181", True,
+                         "No import statements found to verify (test HTML may have changed)")
+
+    except Exception as e:
+        record_result("Import Formatting", "#1181", False, f"Exception: {e}")
+
+
+# =============================================================================
+# COMPREHENSIVE CRAWL TEST
+# =============================================================================
+async def test_comprehensive_crawl():
+    """
+    Run a comprehensive crawl to verify overall stability.
+    """
+    print_test("Comprehensive Crawl Test", "Overall")
+
+    try:
+        from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, BrowserConfig
+
+        async with AsyncWebCrawler(config=BrowserConfig(headless=True)) as crawler:
+            result = await crawler.arun(
+                url="https://httpbin.org/html",
+                config=CrawlerRunConfig()
+            )
+
+        # Verify result
+        checks = []
+
+        if result.success:
+            checks.append("success=True")
+        else:
+            record_result("Comprehensive Crawl", "Overall", False,
+                         f"Crawl failed: {result.error_message}")
+            return
+
+        if result.html and len(result.html) > 100:
+            checks.append(f"html={len(result.html)} chars")
+
+        if result.markdown and result.markdown.raw_markdown:
+            checks.append(f"markdown={len(result.markdown.raw_markdown)} chars")
+
+        if result.redirected_url:
+            checks.append("redirected_url present")
+
+        record_result("Comprehensive Crawl", "Overall", True,
+                     f"All checks passed: {', '.join(checks)}")
+
+    except Exception as e:
+        record_result("Comprehensive Crawl", "Overall", False, f"Exception: {e}")
+
+
+# =============================================================================
+# MAIN
+# =============================================================================
+
+def print_summary():
+    """Print test results summary"""
+    print_header("TEST RESULTS SUMMARY")
+
+    passed = sum(1 for r in results if r.passed and not r.skipped)
+    failed = sum(1 for r in results if not r.passed and not r.skipped)
+    skipped = sum(1 for r in results if r.skipped)
+
+    print(f"\nTotal: {len(results)} tests")
+    print(f"  Passed:  {passed}")
+    print(f"  Failed:  {failed}")
+    print(f"  Skipped: {skipped}")
+
+    if failed > 0:
+        print("\nFailed Tests:")
+        for r in results:
+            if not r.passed and not r.skipped:
+                print(f"  - {r.name} ({r.issue}): {r.message}")
+
+    if skipped > 0:
+        print("\nSkipped Tests:")
+        for r in results:
+            if r.skipped:
+                print(f"  - {r.name} ({r.issue}): {r.message}")
+
+    print("\n" + "=" * 70)
+    if failed == 0:
+        print("All tests passed! v0.7.8 bug fixes verified.")
+    else:
+        print(f"WARNING: {failed} test(s) failed!")
+    print("=" * 70)
+
+    return failed == 0
+
+
+async def main():
+    """Run all verification tests"""
+    print_header("Crawl4AI v0.7.8 - Bug Fix Verification Tests")
+    print("Running actual tests to verify bug fixes...")
+
+    # Run all tests
+    tests = [
+        test_proxy_config_serialization,       # #1629
+        test_configurable_backoff,             # #1269
+        test_llm_input_format,                 # #1178
+        test_raw_html_url_variable,            # #1116
+        test_redirect_url_handling,            # #1268
+        test_pypdf_migration,                  # #1412
+        test_pydantic_configdict,              # #678
+        test_docker_content_filter,            # #1642
+        test_docker_cache_permissions,         # #1638
+        test_adaptive_crawler_embedding,       # #1621
+        test_import_formatting,                # #1181
+        test_comprehensive_crawl,              # Overall
+    ]
+
+    for test_func in tests:
+        try:
+            await test_func()
+        except Exception as e:
+            print(f"\nTest {test_func.__name__} crashed: {e}")
+            results.append(TestResult(
+                test_func.__name__,
+                "Unknown",
+                False,
+                f"Crashed: {e}"
+            ))
+
+    # Print summary
+    all_passed = print_summary()
+
+    return 0 if all_passed else 1
+
+
+if __name__ == "__main__":
+    try:
+        exit_code = asyncio.run(main())
+        sys.exit(exit_code)
+    except KeyboardInterrupt:
+        print("\n\nTests interrupted by user.")
+        sys.exit(1)
+    except Exception as e:
+        print(f"\n\nTest suite failed: {e}")
+        import traceback
+        traceback.print_exc()
+        sys.exit(1)

docs/releases_review/v0.7.5_docker_hooks_demo.py

@@ -0,0 +1,655 @@
+#!/usr/bin/env python3
+"""
+🚀 Crawl4AI v0.7.5 - Docker Hooks System Complete Demonstration
+================================================================
+
+This file demonstrates the NEW Docker Hooks System introduced in v0.7.5.
+
+The Docker Hooks System is a completely NEW feature that provides pipeline
+customization through user-provided Python functions. It offers three approaches:
+
+1. String-based hooks for REST API
+2. hooks_to_string() utility to convert functions
+3. Docker Client with automatic conversion (most convenient)
+
+All three approaches are part of this NEW v0.7.5 feature!
+
+Perfect for video recording and demonstration purposes.
+
+Requirements:
+- Docker container running: docker run -p 11235:11235 unclecode/crawl4ai:latest
+- crawl4ai v0.7.5 installed: pip install crawl4ai==0.7.5
+"""
+
+import asyncio
+import requests
+import json
+import time
+from typing import Dict, Any
+
+# Import Crawl4AI components
+from crawl4ai import hooks_to_string
+from crawl4ai.docker_client import Crawl4aiDockerClient
+
+# Configuration
+DOCKER_URL = "http://localhost:11235"
+# DOCKER_URL = "http://localhost:11234"
+TEST_URLS = [
+    # "https://httpbin.org/html",
+    "https://www.kidocode.com",
+    "https://quotes.toscrape.com",
+]
+
+
+def print_section(title: str, description: str = ""):
+    """Print a formatted section header"""
+    print("\n" + "=" * 70)
+    print(f"  {title}")
+    if description:
+        print(f"  {description}")
+    print("=" * 70 + "\n")
+
+
+def check_docker_service() -> bool:
+    """Check if Docker service is running"""
+    try:
+        response = requests.get(f"{DOCKER_URL}/health", timeout=3)
+        return response.status_code == 200
+    except:
+        return False
+
+
+# ============================================================================
+# REUSABLE HOOK LIBRARY (NEW in v0.7.5)
+# ============================================================================
+
+async def performance_optimization_hook(page, context, **kwargs):
+    """
+    Performance Hook: Block unnecessary resources to speed up crawling
+    """
+    print("  [Hook] 🚀 Optimizing performance - blocking images and ads...")
+
+    # Block images
+    await context.route(
+        "**/*.{png,jpg,jpeg,gif,webp,svg,ico}",
+        lambda route: route.abort()
+    )
+
+    # Block ads and analytics
+    await context.route("**/analytics/*", lambda route: route.abort())
+    await context.route("**/ads/*", lambda route: route.abort())
+    await context.route("**/google-analytics.com/*", lambda route: route.abort())
+
+    print("  [Hook] ✓ Performance optimization applied")
+    return page
+
+
+async def viewport_setup_hook(page, context, **kwargs):
+    """
+    Viewport Hook: Set consistent viewport size for rendering
+    """
+    print("  [Hook] 🖥️  Setting viewport to 1920x1080...")
+    await page.set_viewport_size({"width": 1920, "height": 1080})
+    print("  [Hook] ✓ Viewport configured")
+    return page
+
+
+async def authentication_headers_hook(page, context, url, **kwargs):
+    """
+    Headers Hook: Add custom authentication and tracking headers
+    """
+    print(f"  [Hook] 🔐 Adding custom headers for {url[:50]}...")
+
+    await page.set_extra_http_headers({
+        'X-Crawl4AI-Version': '0.7.5',
+        'X-Custom-Hook': 'function-based-demo',
+        'Accept-Language': 'en-US,en;q=0.9',
+        'User-Agent': 'Crawl4AI/0.7.5 (Educational Demo)'
+    })
+
+    print("  [Hook] ✓ Custom headers added")
+    return page
+
+
+async def lazy_loading_handler_hook(page, context, **kwargs):
+    """
+    Content Hook: Handle lazy-loaded content by scrolling
+    """
+    print("  [Hook] 📜 Scrolling to load lazy content...")
+
+    # Scroll to bottom
+    await page.evaluate("window.scrollTo(0, document.body.scrollHeight)")
+    await page.wait_for_timeout(1000)
+
+    # Scroll to middle
+    await page.evaluate("window.scrollTo(0, document.body.scrollHeight / 2)")
+    await page.wait_for_timeout(500)
+
+    # Scroll back to top
+    await page.evaluate("window.scrollTo(0, 0)")
+    await page.wait_for_timeout(500)
+
+    print("  [Hook] ✓ Lazy content loaded")
+    return page
+
+
+async def page_analytics_hook(page, context, **kwargs):
+    """
+    Analytics Hook: Log page metrics before extraction
+    """
+    print("  [Hook] 📊 Collecting page analytics...")
+
+    metrics = await page.evaluate('''
+        () => ({
+            title: document.title,
+            images: document.images.length,
+            links: document.links.length,
+            scripts: document.scripts.length,
+            headings: document.querySelectorAll('h1, h2, h3').length,
+            paragraphs: document.querySelectorAll('p').length
+        })
+    ''')
+
+    print(f"  [Hook] 📈 Page: {metrics['title'][:50]}...")
+    print(f"         Links: {metrics['links']}, Images: {metrics['images']}, "
+          f"Headings: {metrics['headings']}, Paragraphs: {metrics['paragraphs']}")
+
+    return page
+
+
+# ============================================================================
+# DEMO 1: String-Based Hooks (NEW Docker Hooks System)
+# ============================================================================
+
+def demo_1_string_based_hooks():
+    """
+    Demonstrate string-based hooks with REST API (part of NEW Docker Hooks System)
+    """
+    print_section(
+        "DEMO 1: String-Based Hooks (REST API)",
+        "Part of the NEW Docker Hooks System - hooks as strings"
+    )
+
+    # Define hooks as strings
+    hooks_config = {
+        "on_page_context_created": """
+async def hook(page, context, **kwargs):
+    print("  [String Hook] Setting up page context...")
+    # Block images for performance
+    await context.route("**/*.{png,jpg,jpeg,gif,webp}", lambda route: route.abort())
+    await page.set_viewport_size({"width": 1920, "height": 1080})
+    return page
+""",
+
+        "before_goto": """
+async def hook(page, context, url, **kwargs):
+    print(f"  [String Hook] Navigating to {url[:50]}...")
+    await page.set_extra_http_headers({
+        'X-Crawl4AI': 'string-based-hooks',
+        'X-Demo': 'v0.7.5'
+    })
+    return page
+""",
+
+        "before_retrieve_html": """
+async def hook(page, context, **kwargs):
+    print("  [String Hook] Scrolling page...")
+    await page.evaluate("window.scrollTo(0, document.body.scrollHeight)")
+    await page.wait_for_timeout(1000)
+    return page
+"""
+    }
+
+    # Prepare request payload
+    payload = {
+        "urls": [TEST_URLS[0]],
+        "hooks": {
+            "code": hooks_config,
+            "timeout": 30
+        },
+        "crawler_config": {
+            "cache_mode": "bypass"
+        }
+    }
+
+    print(f"🎯 Target URL: {TEST_URLS[0]}")
+    print(f"🔧 Configured {len(hooks_config)} string-based hooks")
+    print(f"📡 Sending request to Docker API...\n")
+
+    try:
+        start_time = time.time()
+        response = requests.post(f"{DOCKER_URL}/crawl", json=payload, timeout=60)
+        execution_time = time.time() - start_time
+
+        if response.status_code == 200:
+            result = response.json()
+
+            print(f"\n✅ Request successful! (took {execution_time:.2f}s)")
+
+            # Display results
+            if result.get('results') and result['results'][0].get('success'):
+                crawl_result = result['results'][0]
+                html_length = len(crawl_result.get('html', ''))
+                markdown_length = len(crawl_result.get('markdown', ''))
+
+                print(f"\n📊 Results:")
+                print(f"   • HTML length: {html_length:,} characters")
+                print(f"   • Markdown length: {markdown_length:,} characters")
+                print(f"   • URL: {crawl_result.get('url')}")
+
+                # Check hooks execution
+                if 'hooks' in result:
+                    hooks_info = result['hooks']
+                    print(f"\n🎣 Hooks Execution:")
+                    print(f"   • Status: {hooks_info['status']['status']}")
+                    print(f"   • Attached hooks: {len(hooks_info['status']['attached_hooks'])}")
+
+                    if 'summary' in hooks_info:
+                        summary = hooks_info['summary']
+                        print(f"   • Total executions: {summary['total_executions']}")
+                        print(f"   • Successful: {summary['successful']}")
+                        print(f"   • Success rate: {summary['success_rate']:.1f}%")
+            else:
+                print(f"⚠️ Crawl completed but no results")
+
+        else:
+            print(f"❌ Request failed with status {response.status_code}")
+            print(f"   Error: {response.text[:200]}")
+
+    except requests.exceptions.Timeout:
+        print("⏰ Request timed out after 60 seconds")
+    except Exception as e:
+        print(f"❌ Error: {str(e)}")
+
+    print("\n" + "─" * 70)
+    print("✓ String-based hooks demo complete\n")
+
+
+# ============================================================================
+# DEMO 2: Function-Based Hooks with hooks_to_string() Utility
+# ============================================================================
+
+def demo_2_hooks_to_string_utility():
+    """
+    Demonstrate the new hooks_to_string() utility for converting functions
+    """
+    print_section(
+        "DEMO 2: hooks_to_string() Utility (NEW! ✨)",
+        "Convert Python functions to strings for REST API"
+    )
+
+    print("📦 Creating hook functions...")
+    print("   • performance_optimization_hook")
+    print("   • viewport_setup_hook")
+    print("   • authentication_headers_hook")
+    print("   • lazy_loading_handler_hook")
+
+    # Convert function objects to strings using the NEW utility
+    print("\n🔄 Converting functions to strings with hooks_to_string()...")
+
+    hooks_dict = {
+        "on_page_context_created": performance_optimization_hook,
+        "before_goto": authentication_headers_hook,
+        "before_retrieve_html": lazy_loading_handler_hook,
+    }
+
+    hooks_as_strings = hooks_to_string(hooks_dict)
+
+    print(f"✅ Successfully converted {len(hooks_as_strings)} functions to strings")
+
+    # Show a preview
+    print("\n📝 Sample converted hook (first 250 characters):")
+    print("─" * 70)
+    sample_hook = list(hooks_as_strings.values())[0]
+    print(sample_hook[:250] + "...")
+    print("─" * 70)
+
+    # Use the converted hooks with REST API
+    print("\n📡 Using converted hooks with REST API...")
+
+    payload = {
+        "urls": [TEST_URLS[0]],
+        "hooks": {
+            "code": hooks_as_strings,
+            "timeout": 30
+        }
+    }
+
+    try:
+        start_time = time.time()
+        response = requests.post(f"{DOCKER_URL}/crawl", json=payload, timeout=60)
+        execution_time = time.time() - start_time
+
+        if response.status_code == 200:
+            result = response.json()
+            print(f"\n✅ Request successful! (took {execution_time:.2f}s)")
+
+            if result.get('results') and result['results'][0].get('success'):
+                crawl_result = result['results'][0]
+                print(f"   • HTML length: {len(crawl_result.get('html', '')):,} characters")
+                print(f"   • Hooks executed successfully!")
+        else:
+            print(f"❌ Request failed: {response.status_code}")
+
+    except Exception as e:
+        print(f"❌ Error: {str(e)}")
+
+    print("\n💡 Benefits of hooks_to_string():")
+    print("   ✓ Write hooks as regular Python functions")
+    print("   ✓ Full IDE support (autocomplete, syntax highlighting)")
+    print("   ✓ Type checking and linting")
+    print("   ✓ Easy to test and debug")
+    print("   ✓ Reusable across projects")
+    print("   ✓ Works with any REST API client")
+
+    print("\n" + "─" * 70)
+    print("✓ hooks_to_string() utility demo complete\n")
+
+
+# ============================================================================
+# DEMO 3: Docker Client with Automatic Conversion (RECOMMENDED! 🌟)
+# ============================================================================
+
+async def demo_3_docker_client_auto_conversion():
+    """
+    Demonstrate Docker Client with automatic hook conversion (RECOMMENDED)
+    """
+    print_section(
+        "DEMO 3: Docker Client with Auto-Conversion (RECOMMENDED! 🌟)",
+        "Pass function objects directly - conversion happens automatically!"
+    )
+
+    print("🐳 Initializing Crawl4AI Docker Client...")
+    client = Crawl4aiDockerClient(base_url=DOCKER_URL)
+
+    print("✅ Client ready!\n")
+
+    # Use our reusable hook library - just pass the function objects!
+    print("📚 Using reusable hook library:")
+    print("   • performance_optimization_hook")
+    print("   • viewport_setup_hook")
+    print("   • authentication_headers_hook")
+    print("   • lazy_loading_handler_hook")
+    print("   • page_analytics_hook")
+
+    print("\n🎯 Target URL: " + TEST_URLS[1])
+    print("🚀 Starting crawl with automatic hook conversion...\n")
+
+    try:
+        start_time = time.time()
+
+        # Pass function objects directly - NO manual conversion needed! ✨
+        results = await client.crawl(
+            urls=[TEST_URLS[0]],
+            hooks={
+                "on_page_context_created": performance_optimization_hook,
+                "before_goto": authentication_headers_hook,
+                "before_retrieve_html": lazy_loading_handler_hook,
+                "before_return_html": page_analytics_hook,
+            },
+            hooks_timeout=30
+        )
+
+        execution_time = time.time() - start_time
+
+        print(f"\n✅ Crawl completed! (took {execution_time:.2f}s)\n")
+
+        # Display results
+        if results and results.success:
+            result = results
+            print(f"📊 Results:")
+            print(f"   • URL: {result.url}")
+            print(f"   • Success: {result.success}")
+            print(f"   • HTML length: {len(result.html):,} characters")
+            print(f"   • Markdown length: {len(result.markdown):,} characters")
+
+            # Show metadata
+            if result.metadata:
+                print(f"\n📋 Metadata:")
+                print(f"   • Title: {result.metadata.get('title', 'N/A')}")
+                print(f"   • Description: {result.metadata.get('description', 'N/A')}")
+
+            # Show links
+            if result.links:
+                internal_count = len(result.links.get('internal', []))
+                external_count = len(result.links.get('external', []))
+                print(f"\n🔗 Links Found:")
+                print(f"   • Internal: {internal_count}")
+                print(f"   • External: {external_count}")
+        else:
+            print(f"⚠️ Crawl completed but no successful results")
+            if results:
+                print(f"   Error: {results.error_message}")
+
+    except Exception as e:
+        print(f"❌ Error: {str(e)}")
+        import traceback
+        traceback.print_exc()
+
+    print("\n🌟 Why Docker Client is RECOMMENDED:")
+    print("   ✓ Automatic function-to-string conversion")
+    print("   ✓ No manual hooks_to_string() calls needed")
+    print("   ✓ Cleaner, more Pythonic code")
+    print("   ✓ Full type hints and IDE support")
+    print("   ✓ Built-in error handling")
+    print("   ✓ Async/await support")
+
+    print("\n" + "─" * 70)
+    print("✓ Docker Client auto-conversion demo complete\n")
+
+
+# ============================================================================
+# DEMO 4: Advanced Use Case - Complete Hook Pipeline
+# ============================================================================
+
+async def demo_4_complete_hook_pipeline():
+    """
+    Demonstrate a complete hook pipeline using all 8 hook points
+    """
+    print_section(
+        "DEMO 4: Complete Hook Pipeline",
+        "Using all 8 available hook points for comprehensive control"
+    )
+
+    # Define all 8 hooks
+    async def on_browser_created_hook(browser, **kwargs):
+        """Hook 1: Called after browser is created"""
+        print("  [Pipeline] 1/8 Browser created")
+        return browser
+
+    async def on_page_context_created_hook(page, context, **kwargs):
+        """Hook 2: Called after page context is created"""
+        print("  [Pipeline] 2/8 Page context created - setting up...")
+        await page.set_viewport_size({"width": 1920, "height": 1080})
+        return page
+
+    async def on_user_agent_updated_hook(page, context, user_agent, **kwargs):
+        """Hook 3: Called when user agent is updated"""
+        print(f"  [Pipeline] 3/8 User agent updated: {user_agent[:50]}...")
+        return page
+
+    async def before_goto_hook(page, context, url, **kwargs):
+        """Hook 4: Called before navigating to URL"""
+        print(f"  [Pipeline] 4/8 Before navigation to: {url[:60]}...")
+        return page
+
+    async def after_goto_hook(page, context, url, response, **kwargs):
+        """Hook 5: Called after navigation completes"""
+        print(f"  [Pipeline] 5/8 After navigation - Status: {response.status if response else 'N/A'}")
+        await page.wait_for_timeout(1000)
+        return page
+
+    async def on_execution_started_hook(page, context, **kwargs):
+        """Hook 6: Called when JavaScript execution starts"""
+        print("  [Pipeline] 6/8 JavaScript execution started")
+        return page
+
+    async def before_retrieve_html_hook(page, context, **kwargs):
+        """Hook 7: Called before retrieving HTML"""
+        print("  [Pipeline] 7/8 Before HTML retrieval - scrolling...")
+        await page.evaluate("window.scrollTo(0, document.body.scrollHeight)")
+        return page
+
+    async def before_return_html_hook(page, context, html, **kwargs):
+        """Hook 8: Called before returning HTML"""
+        print(f"  [Pipeline] 8/8 Before return - HTML length: {len(html):,} chars")
+        return page
+
+    print("🎯 Target URL: " + TEST_URLS[0])
+    print("🔧 Configured ALL 8 hook points for complete pipeline control\n")
+
+    client = Crawl4aiDockerClient(base_url=DOCKER_URL)
+
+    try:
+        print("🚀 Starting complete pipeline crawl...\n")
+        start_time = time.time()
+
+        results = await client.crawl(
+            urls=[TEST_URLS[0]],
+            hooks={
+                "on_browser_created": on_browser_created_hook,
+                "on_page_context_created": on_page_context_created_hook,
+                "on_user_agent_updated": on_user_agent_updated_hook,
+                "before_goto": before_goto_hook,
+                "after_goto": after_goto_hook,
+                "on_execution_started": on_execution_started_hook,
+                "before_retrieve_html": before_retrieve_html_hook,
+                "before_return_html": before_return_html_hook,
+            },
+            hooks_timeout=45
+        )
+
+        execution_time = time.time() - start_time
+
+        if results and results.success:
+            print(f"\n✅ Complete pipeline executed successfully! (took {execution_time:.2f}s)")
+            print(f"   • All 8 hooks executed in sequence")
+            print(f"   • HTML length: {len(results.html):,} characters")
+        else:
+            print(f"⚠️ Pipeline completed with warnings")
+
+    except Exception as e:
+        print(f"❌ Error: {str(e)}")
+
+    print("\n📚 Available Hook Points:")
+    print("   1. on_browser_created - Browser initialization")
+    print("   2. on_page_context_created - Page context setup")
+    print("   3. on_user_agent_updated - User agent configuration")
+    print("   4. before_goto - Pre-navigation setup")
+    print("   5. after_goto - Post-navigation processing")
+    print("   6. on_execution_started - JavaScript execution start")
+    print("   7. before_retrieve_html - Pre-extraction processing")
+    print("   8. before_return_html - Final HTML processing")
+
+    print("\n" + "─" * 70)
+    print("✓ Complete hook pipeline demo complete\n")
+
+
+# ============================================================================
+# MAIN EXECUTION
+# ============================================================================
+
+async def main():
+    """
+    Run all demonstrations
+    """
+    print("\n" + "=" * 70)
+    print("  🚀 Crawl4AI v0.7.5 - Docker Hooks Complete Demonstration")
+    print("=" * 70)
+
+    # Check Docker service
+    print("\n🔍 Checking Docker service status...")
+    if not check_docker_service():
+        print("❌ Docker service is not running!")
+        print("\n📋 To start the Docker service:")
+        print("   docker run -p 11235:11235 unclecode/crawl4ai:latest")
+        print("\nPlease start the service and run this demo again.")
+        return
+
+    print("✅ Docker service is running!\n")
+
+    # Run all demos
+    demos = [
+        ("String-Based Hooks (REST API)", demo_1_string_based_hooks, False),
+        ("hooks_to_string() Utility", demo_2_hooks_to_string_utility, False),
+        ("Docker Client Auto-Conversion", demo_3_docker_client_auto_conversion, True),
+        # ("Complete Hook Pipeline", demo_4_complete_hook_pipeline, True),
+    ]
+
+    for i, (name, demo_func, is_async) in enumerate(demos, 1):
+        print(f"\n{'🔷' * 35}")
+        print(f"Starting Demo {i}/{len(demos)}: {name}")
+        print(f"{'🔷' * 35}\n")
+
+        try:
+            if is_async:
+                await demo_func()
+            else:
+                demo_func()
+
+            print(f"✅ Demo {i} completed successfully!")
+
+            # Pause between demos (except the last one)
+            if i < len(demos):
+                print("\n⏸️  Press Enter to continue to next demo...")
+                # input()
+
+        except KeyboardInterrupt:
+            print(f"\n⏹️  Demo interrupted by user")
+            break
+        except Exception as e:
+            print(f"\n❌ Demo {i} failed: {str(e)}")
+            import traceback
+            traceback.print_exc()
+            print("\nContinuing to next demo...\n")
+            continue
+
+    # Final summary
+    print("\n" + "=" * 70)
+    print("  🎉 All Demonstrations Complete!")
+    print("=" * 70)
+
+    print("\n📊 Summary of v0.7.5 Docker Hooks System:")
+    print("\n🆕 COMPLETELY NEW FEATURE in v0.7.5:")
+    print("   The Docker Hooks System lets you customize the crawling pipeline")
+    print("   with user-provided Python functions at 8 strategic points.")
+
+    print("\n✨ Three Ways to Use Docker Hooks (All NEW!):")
+    print("   1. String-based - Write hooks as strings for REST API")
+    print("   2. hooks_to_string() - Convert Python functions to strings")
+    print("   3. Docker Client - Automatic conversion (RECOMMENDED)")
+
+    print("\n💡 Key Benefits:")
+    print("   ✓ Full IDE support (autocomplete, syntax highlighting)")
+    print("   ✓ Type checking and linting")
+    print("   ✓ Easy to test and debug")
+    print("   ✓ Reusable across projects")
+    print("   ✓ Complete pipeline control")
+
+    print("\n🎯 8 Hook Points Available:")
+    print("   • on_browser_created, on_page_context_created")
+    print("   • on_user_agent_updated, before_goto, after_goto")
+    print("   • on_execution_started, before_retrieve_html, before_return_html")
+
+    print("\n📚 Resources:")
+    print("   • Docs: https://docs.crawl4ai.com")
+    print("   • GitHub: https://github.com/unclecode/crawl4ai")
+    print("   • Discord: https://discord.gg/jP8KfhDhyN")
+
+    print("\n" + "=" * 70)
+    print("  Happy Crawling with v0.7.5! 🕷️")
+    print("=" * 70 + "\n")
+
+
+if __name__ == "__main__":
+    print("\n🎬 Starting Crawl4AI v0.7.5 Docker Hooks Demonstration...")
+    print("Press Ctrl+C anytime to exit\n")
+
+    try:
+        asyncio.run(main())
+    except KeyboardInterrupt:
+        print("\n\n👋 Demo stopped by user. Thanks for exploring Crawl4AI v0.7.5!")
+    except Exception as e:
+        print(f"\n\n❌ Demo error: {str(e)}")
+        import traceback
+        traceback.print_exc()

mkdocs.yml

@@ -7,6 +7,7 @@ docs_dir: docs/md_v2
 
 nav:
   - Home: 'index.md'
+  - "📚 Complete SDK Reference": "complete-sdk-reference.md"
   - "Ask AI": "core/ask-ai.md"
   - "Quick Start": "core/quickstart.md"
   - "Code Examples": "core/examples.md"

pyproject.toml

@@ -31,7 +31,7 @@ dependencies = [
     "rank-bm25~=0.2",
     "snowballstemmer~=2.2",
     "pydantic>=2.10",
-    "pyOpenSSL>=24.3.0",
+    "pyOpenSSL>=25.3.0",
     "psutil>=6.1.1",
     "PyYAML>=6.0",
     "nltk>=3.9.1",
@@ -59,13 +59,13 @@ classifiers = [
 ]
 
 [project.optional-dependencies]
-pdf = ["PyPDF2"]  
+pdf = ["pypdf"]  
 torch = ["torch", "nltk", "scikit-learn"]
 transformer = ["transformers", "tokenizers", "sentence-transformers"]
 cosine = ["torch", "transformers", "nltk", "sentence-transformers"]
 sync = ["selenium"]
 all = [
-    "PyPDF2",
+    "pypdf",
     "torch",
     "nltk",
     "scikit-learn",

requirements.txt

@@ -19,7 +19,7 @@ rank-bm25~=0.2
 colorama~=0.4
 snowballstemmer~=2.2
 pydantic>=2.10
-pyOpenSSL>=24.3.0
+pyOpenSSL>=25.3.0
 psutil>=6.1.1
 PyYAML>=6.0
 nltk>=3.9.1
@@ -33,4 +33,4 @@ shapely>=2.0.0
 
 fake-useragent>=2.2.0
 pdf2image>=1.17.0
-PyPDF2>=3.0.1
+pypdf>=6.0.0

test_llm_webhook_feature.py

@@ -0,0 +1,401 @@
+#!/usr/bin/env python3
+"""
+Test script to validate webhook implementation for /llm/job endpoint.
+
+This tests that the /llm/job endpoint now supports webhooks
+following the same pattern as /crawl/job.
+"""
+
+import sys
+import os
+
+# Add deploy/docker to path
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'deploy', 'docker'))
+
+def test_llm_job_payload_model():
+    """Test that LlmJobPayload includes webhook_config field"""
+    print("=" * 60)
+    print("TEST 1: LlmJobPayload Model")
+    print("=" * 60)
+
+    try:
+        from job import LlmJobPayload
+        from schemas import WebhookConfig
+        from pydantic import ValidationError
+
+        # Test with webhook_config
+        payload_dict = {
+            "url": "https://example.com",
+            "q": "Extract main content",
+            "schema": None,
+            "cache": False,
+            "provider": None,
+            "webhook_config": {
+                "webhook_url": "https://myapp.com/webhook",
+                "webhook_data_in_payload": True,
+                "webhook_headers": {"X-Secret": "token"}
+            }
+        }
+
+        payload = LlmJobPayload(**payload_dict)
+
+        print(f"✅ LlmJobPayload accepts webhook_config")
+        print(f"   - URL: {payload.url}")
+        print(f"   - Query: {payload.q}")
+        print(f"   - Webhook URL: {payload.webhook_config.webhook_url}")
+        print(f"   - Data in payload: {payload.webhook_config.webhook_data_in_payload}")
+
+        # Test without webhook_config (should be optional)
+        minimal_payload = {
+            "url": "https://example.com",
+            "q": "Extract content"
+        }
+
+        payload2 = LlmJobPayload(**minimal_payload)
+        assert payload2.webhook_config is None, "webhook_config should be optional"
+        print(f"✅ LlmJobPayload works without webhook_config (optional)")
+
+        return True
+    except Exception as e:
+        print(f"❌ Failed: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+def test_handle_llm_request_signature():
+    """Test that handle_llm_request accepts webhook_config parameter"""
+    print("\n" + "=" * 60)
+    print("TEST 2: handle_llm_request Function Signature")
+    print("=" * 60)
+
+    try:
+        from api import handle_llm_request
+        import inspect
+
+        sig = inspect.signature(handle_llm_request)
+        params = list(sig.parameters.keys())
+
+        print(f"Function parameters: {params}")
+
+        if 'webhook_config' in params:
+            print(f"✅ handle_llm_request has webhook_config parameter")
+
+            # Check that it's optional with default None
+            webhook_param = sig.parameters['webhook_config']
+            if webhook_param.default is None or webhook_param.default == inspect.Parameter.empty:
+                print(f"✅ webhook_config is optional (default: {webhook_param.default})")
+            else:
+                print(f"⚠️  webhook_config default is: {webhook_param.default}")
+
+            return True
+        else:
+            print(f"❌ handle_llm_request missing webhook_config parameter")
+            return False
+
+    except Exception as e:
+        print(f"❌ Failed: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+def test_process_llm_extraction_signature():
+    """Test that process_llm_extraction accepts webhook_config parameter"""
+    print("\n" + "=" * 60)
+    print("TEST 3: process_llm_extraction Function Signature")
+    print("=" * 60)
+
+    try:
+        from api import process_llm_extraction
+        import inspect
+
+        sig = inspect.signature(process_llm_extraction)
+        params = list(sig.parameters.keys())
+
+        print(f"Function parameters: {params}")
+
+        if 'webhook_config' in params:
+            print(f"✅ process_llm_extraction has webhook_config parameter")
+
+            webhook_param = sig.parameters['webhook_config']
+            if webhook_param.default is None or webhook_param.default == inspect.Parameter.empty:
+                print(f"✅ webhook_config is optional (default: {webhook_param.default})")
+            else:
+                print(f"⚠️  webhook_config default is: {webhook_param.default}")
+
+            return True
+        else:
+            print(f"❌ process_llm_extraction missing webhook_config parameter")
+            return False
+
+    except Exception as e:
+        print(f"❌ Failed: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+def test_webhook_integration_in_api():
+    """Test that api.py properly integrates webhook notifications"""
+    print("\n" + "=" * 60)
+    print("TEST 4: Webhook Integration in process_llm_extraction")
+    print("=" * 60)
+
+    try:
+        api_file = os.path.join(os.path.dirname(__file__), 'deploy', 'docker', 'api.py')
+
+        with open(api_file, 'r') as f:
+            api_content = f.read()
+
+        # Check for WebhookDeliveryService initialization
+        if 'webhook_service = WebhookDeliveryService(config)' in api_content:
+            print("✅ process_llm_extraction initializes WebhookDeliveryService")
+        else:
+            print("❌ Missing WebhookDeliveryService initialization in process_llm_extraction")
+            return False
+
+        # Check for notify_job_completion calls with llm_extraction
+        if 'task_type="llm_extraction"' in api_content:
+            print("✅ Uses correct task_type='llm_extraction' for notifications")
+        else:
+            print("❌ Missing task_type='llm_extraction' in webhook notifications")
+            return False
+
+        # Count webhook notification calls (should have at least 3: success + 2 failure paths)
+        notification_count = api_content.count('await webhook_service.notify_job_completion')
+        # Find only in process_llm_extraction function
+        llm_func_start = api_content.find('async def process_llm_extraction')
+        llm_func_end = api_content.find('\nasync def ', llm_func_start + 1)
+        if llm_func_end == -1:
+            llm_func_end = len(api_content)
+
+        llm_func_content = api_content[llm_func_start:llm_func_end]
+        llm_notification_count = llm_func_content.count('await webhook_service.notify_job_completion')
+
+        print(f"✅ Found {llm_notification_count} webhook notification calls in process_llm_extraction")
+
+        if llm_notification_count >= 3:
+            print(f"✅ Sufficient notification points (success + failure paths)")
+        else:
+            print(f"⚠️  Expected at least 3 notification calls, found {llm_notification_count}")
+
+        return True
+    except Exception as e:
+        print(f"❌ Failed: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+def test_job_endpoint_integration():
+    """Test that /llm/job endpoint extracts and passes webhook_config"""
+    print("\n" + "=" * 60)
+    print("TEST 5: /llm/job Endpoint Integration")
+    print("=" * 60)
+
+    try:
+        job_file = os.path.join(os.path.dirname(__file__), 'deploy', 'docker', 'job.py')
+
+        with open(job_file, 'r') as f:
+            job_content = f.read()
+
+        # Find the llm_job_enqueue function
+        llm_job_start = job_content.find('async def llm_job_enqueue')
+        llm_job_end = job_content.find('\n\n@router', llm_job_start + 1)
+        if llm_job_end == -1:
+            llm_job_end = job_content.find('\n\nasync def', llm_job_start + 1)
+
+        llm_job_func = job_content[llm_job_start:llm_job_end]
+
+        # Check for webhook_config extraction
+        if 'webhook_config = None' in llm_job_func:
+            print("✅ llm_job_enqueue initializes webhook_config variable")
+        else:
+            print("❌ Missing webhook_config initialization")
+            return False
+
+        if 'if payload.webhook_config:' in llm_job_func:
+            print("✅ llm_job_enqueue checks for payload.webhook_config")
+        else:
+            print("❌ Missing webhook_config check")
+            return False
+
+        if 'webhook_config = payload.webhook_config.model_dump(mode=\'json\')' in llm_job_func:
+            print("✅ llm_job_enqueue converts webhook_config to dict")
+        else:
+            print("❌ Missing webhook_config.model_dump conversion")
+            return False
+
+        if 'webhook_config=webhook_config' in llm_job_func:
+            print("✅ llm_job_enqueue passes webhook_config to handle_llm_request")
+        else:
+            print("❌ Missing webhook_config parameter in handle_llm_request call")
+            return False
+
+        return True
+    except Exception as e:
+        print(f"❌ Failed: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+def test_create_new_task_integration():
+    """Test that create_new_task stores webhook_config in Redis"""
+    print("\n" + "=" * 60)
+    print("TEST 6: create_new_task Webhook Storage")
+    print("=" * 60)
+
+    try:
+        api_file = os.path.join(os.path.dirname(__file__), 'deploy', 'docker', 'api.py')
+
+        with open(api_file, 'r') as f:
+            api_content = f.read()
+
+        # Find create_new_task function
+        create_task_start = api_content.find('async def create_new_task')
+        create_task_end = api_content.find('\nasync def ', create_task_start + 1)
+        if create_task_end == -1:
+            create_task_end = len(api_content)
+
+        create_task_func = api_content[create_task_start:create_task_end]
+
+        # Check for webhook_config storage
+        if 'if webhook_config:' in create_task_func:
+            print("✅ create_new_task checks for webhook_config")
+        else:
+            print("❌ Missing webhook_config check in create_new_task")
+            return False
+
+        if 'task_data["webhook_config"] = json.dumps(webhook_config)' in create_task_func:
+            print("✅ create_new_task stores webhook_config in Redis task data")
+        else:
+            print("❌ Missing webhook_config storage in task_data")
+            return False
+
+        # Check that webhook_config is passed to process_llm_extraction
+        if 'webhook_config' in create_task_func and 'background_tasks.add_task' in create_task_func:
+            print("✅ create_new_task passes webhook_config to background task")
+        else:
+            print("⚠️  Could not verify webhook_config passed to background task")
+
+        return True
+    except Exception as e:
+        print(f"❌ Failed: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+def test_pattern_consistency():
+    """Test that /llm/job follows the same pattern as /crawl/job"""
+    print("\n" + "=" * 60)
+    print("TEST 7: Pattern Consistency with /crawl/job")
+    print("=" * 60)
+
+    try:
+        api_file = os.path.join(os.path.dirname(__file__), 'deploy', 'docker', 'api.py')
+
+        with open(api_file, 'r') as f:
+            api_content = f.read()
+
+        # Find handle_crawl_job to compare pattern
+        crawl_job_start = api_content.find('async def handle_crawl_job')
+        crawl_job_end = api_content.find('\nasync def ', crawl_job_start + 1)
+        if crawl_job_end == -1:
+            crawl_job_end = len(api_content)
+        crawl_job_func = api_content[crawl_job_start:crawl_job_end]
+
+        # Find process_llm_extraction
+        llm_extract_start = api_content.find('async def process_llm_extraction')
+        llm_extract_end = api_content.find('\nasync def ', llm_extract_start + 1)
+        if llm_extract_end == -1:
+            llm_extract_end = len(api_content)
+        llm_extract_func = api_content[llm_extract_start:llm_extract_end]
+
+        print("Checking pattern consistency...")
+
+        # Both should initialize WebhookDeliveryService
+        crawl_has_service = 'webhook_service = WebhookDeliveryService(config)' in crawl_job_func
+        llm_has_service = 'webhook_service = WebhookDeliveryService(config)' in llm_extract_func
+
+        if crawl_has_service and llm_has_service:
+            print("✅ Both initialize WebhookDeliveryService")
+        else:
+            print(f"❌ Service initialization mismatch (crawl: {crawl_has_service}, llm: {llm_has_service})")
+            return False
+
+        # Both should call notify_job_completion on success
+        crawl_notifies_success = 'status="completed"' in crawl_job_func and 'notify_job_completion' in crawl_job_func
+        llm_notifies_success = 'status="completed"' in llm_extract_func and 'notify_job_completion' in llm_extract_func
+
+        if crawl_notifies_success and llm_notifies_success:
+            print("✅ Both notify on success")
+        else:
+            print(f"❌ Success notification mismatch (crawl: {crawl_notifies_success}, llm: {llm_notifies_success})")
+            return False
+
+        # Both should call notify_job_completion on failure
+        crawl_notifies_failure = 'status="failed"' in crawl_job_func and 'error=' in crawl_job_func
+        llm_notifies_failure = 'status="failed"' in llm_extract_func and 'error=' in llm_extract_func
+
+        if crawl_notifies_failure and llm_notifies_failure:
+            print("✅ Both notify on failure")
+        else:
+            print(f"❌ Failure notification mismatch (crawl: {crawl_notifies_failure}, llm: {llm_notifies_failure})")
+            return False
+
+        print("✅ /llm/job follows the same pattern as /crawl/job")
+        return True
+
+    except Exception as e:
+        print(f"❌ Failed: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+def main():
+    """Run all tests"""
+    print("\n🧪 LLM Job Webhook Feature Validation")
+    print("=" * 60)
+    print("Testing that /llm/job now supports webhooks like /crawl/job")
+    print("=" * 60 + "\n")
+
+    results = []
+
+    # Run all tests
+    results.append(("LlmJobPayload Model", test_llm_job_payload_model()))
+    results.append(("handle_llm_request Signature", test_handle_llm_request_signature()))
+    results.append(("process_llm_extraction Signature", test_process_llm_extraction_signature()))
+    results.append(("Webhook Integration", test_webhook_integration_in_api()))
+    results.append(("/llm/job Endpoint", test_job_endpoint_integration()))
+    results.append(("create_new_task Storage", test_create_new_task_integration()))
+    results.append(("Pattern Consistency", test_pattern_consistency()))
+
+    # Print summary
+    print("\n" + "=" * 60)
+    print("TEST SUMMARY")
+    print("=" * 60)
+
+    passed = sum(1 for _, result in results if result)
+    total = len(results)
+
+    for test_name, result in results:
+        status = "✅ PASS" if result else "❌ FAIL"
+        print(f"{status} - {test_name}")
+
+    print(f"\n{'=' * 60}")
+    print(f"Results: {passed}/{total} tests passed")
+    print(f"{'=' * 60}")
+
+    if passed == total:
+        print("\n🎉 All tests passed! /llm/job webhook feature is correctly implemented.")
+        print("\n📝 Summary of changes:")
+        print("  1. LlmJobPayload model includes webhook_config field")
+        print("  2. /llm/job endpoint extracts and passes webhook_config")
+        print("  3. handle_llm_request accepts webhook_config parameter")
+        print("  4. create_new_task stores webhook_config in Redis")
+        print("  5. process_llm_extraction sends webhook notifications")
+        print("  6. Follows the same pattern as /crawl/job")
+        return 0
+    else:
+        print(f"\n⚠️  {total - passed} test(s) failed. Please review the output above.")
+        return 1
+
+if __name__ == "__main__":
+    exit(main())

test_webhook_implementation.py

@@ -0,0 +1,307 @@
+"""
+Simple test script to validate webhook implementation without running full server.
+
+This script tests:
+1. Webhook module imports and syntax
+2. WebhookDeliveryService initialization
+3. Payload construction logic
+4. Configuration parsing
+"""
+
+import sys
+import os
+import json
+from datetime import datetime, timezone
+
+# Add deploy/docker to path to import modules
+# sys.path.insert(0, '/home/user/crawl4ai/deploy/docker')
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'deploy', 'docker'))
+
+def test_imports():
+    """Test that all webhook-related modules can be imported"""
+    print("=" * 60)
+    print("TEST 1: Module Imports")
+    print("=" * 60)
+
+    try:
+        from webhook import WebhookDeliveryService
+        print("✅ webhook.WebhookDeliveryService imported successfully")
+    except Exception as e:
+        print(f"❌ Failed to import webhook module: {e}")
+        return False
+
+    try:
+        from schemas import WebhookConfig, WebhookPayload
+        print("✅ schemas.WebhookConfig imported successfully")
+        print("✅ schemas.WebhookPayload imported successfully")
+    except Exception as e:
+        print(f"❌ Failed to import schemas: {e}")
+        return False
+
+    return True
+
+def test_webhook_service_init():
+    """Test WebhookDeliveryService initialization"""
+    print("\n" + "=" * 60)
+    print("TEST 2: WebhookDeliveryService Initialization")
+    print("=" * 60)
+
+    try:
+        from webhook import WebhookDeliveryService
+
+        # Test with default config
+        config = {
+            "webhooks": {
+                "enabled": True,
+                "default_url": None,
+                "data_in_payload": False,
+                "retry": {
+                    "max_attempts": 5,
+                    "initial_delay_ms": 1000,
+                    "max_delay_ms": 32000,
+                    "timeout_ms": 30000
+                },
+                "headers": {
+                    "User-Agent": "Crawl4AI-Webhook/1.0"
+                }
+            }
+        }
+
+        service = WebhookDeliveryService(config)
+
+        print(f"✅ Service initialized successfully")
+        print(f"   - Max attempts: {service.max_attempts}")
+        print(f"   - Initial delay: {service.initial_delay}s")
+        print(f"   - Max delay: {service.max_delay}s")
+        print(f"   - Timeout: {service.timeout}s")
+
+        # Verify calculations
+        assert service.max_attempts == 5, "Max attempts should be 5"
+        assert service.initial_delay == 1.0, "Initial delay should be 1.0s"
+        assert service.max_delay == 32.0, "Max delay should be 32.0s"
+        assert service.timeout == 30.0, "Timeout should be 30.0s"
+
+        print("✅ All configuration values correct")
+
+        return True
+    except Exception as e:
+        print(f"❌ Service initialization failed: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+def test_webhook_config_model():
+    """Test WebhookConfig Pydantic model"""
+    print("\n" + "=" * 60)
+    print("TEST 3: WebhookConfig Model Validation")
+    print("=" * 60)
+
+    try:
+        from schemas import WebhookConfig
+        from pydantic import ValidationError
+
+        # Test valid config
+        valid_config = {
+            "webhook_url": "https://example.com/webhook",
+            "webhook_data_in_payload": True,
+            "webhook_headers": {"X-Secret": "token123"}
+        }
+
+        config = WebhookConfig(**valid_config)
+        print(f"✅ Valid config accepted:")
+        print(f"   - URL: {config.webhook_url}")
+        print(f"   - Data in payload: {config.webhook_data_in_payload}")
+        print(f"   - Headers: {config.webhook_headers}")
+
+        # Test minimal config
+        minimal_config = {
+            "webhook_url": "https://example.com/webhook"
+        }
+
+        config2 = WebhookConfig(**minimal_config)
+        print(f"✅ Minimal config accepted (defaults applied):")
+        print(f"   - URL: {config2.webhook_url}")
+        print(f"   - Data in payload: {config2.webhook_data_in_payload}")
+        print(f"   - Headers: {config2.webhook_headers}")
+
+        # Test invalid URL
+        try:
+            invalid_config = {
+                "webhook_url": "not-a-url"
+            }
+            config3 = WebhookConfig(**invalid_config)
+            print(f"❌ Invalid URL should have been rejected")
+            return False
+        except ValidationError as e:
+            print(f"✅ Invalid URL correctly rejected")
+
+        return True
+    except Exception as e:
+        print(f"❌ Model validation test failed: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+def test_payload_construction():
+    """Test webhook payload construction logic"""
+    print("\n" + "=" * 60)
+    print("TEST 4: Payload Construction")
+    print("=" * 60)
+
+    try:
+        # Simulate payload construction from notify_job_completion
+        task_id = "crawl_abc123"
+        task_type = "crawl"
+        status = "completed"
+        urls = ["https://example.com"]
+
+        payload = {
+            "task_id": task_id,
+            "task_type": task_type,
+            "status": status,
+            "timestamp": datetime.now(timezone.utc).isoformat(),
+            "urls": urls
+        }
+
+        print(f"✅ Basic payload constructed:")
+        print(json.dumps(payload, indent=2))
+
+        # Test with error
+        error_payload = {
+            "task_id": "crawl_xyz789",
+            "task_type": "crawl",
+            "status": "failed",
+            "timestamp": datetime.now(timezone.utc).isoformat(),
+            "urls": ["https://example.com"],
+            "error": "Connection timeout"
+        }
+
+        print(f"\n✅ Error payload constructed:")
+        print(json.dumps(error_payload, indent=2))
+
+        # Test with data
+        data_payload = {
+            "task_id": "crawl_def456",
+            "task_type": "crawl",
+            "status": "completed",
+            "timestamp": datetime.now(timezone.utc).isoformat(),
+            "urls": ["https://example.com"],
+            "data": {
+                "results": [
+                    {"url": "https://example.com", "markdown": "# Example"}
+                ]
+            }
+        }
+
+        print(f"\n✅ Data payload constructed:")
+        print(json.dumps(data_payload, indent=2))
+
+        return True
+    except Exception as e:
+        print(f"❌ Payload construction failed: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+def test_exponential_backoff():
+    """Test exponential backoff calculation"""
+    print("\n" + "=" * 60)
+    print("TEST 5: Exponential Backoff Calculation")
+    print("=" * 60)
+
+    try:
+        initial_delay = 1.0  # 1 second
+        max_delay = 32.0     # 32 seconds
+
+        print("Backoff delays for 5 attempts:")
+        for attempt in range(5):
+            delay = min(initial_delay * (2 ** attempt), max_delay)
+            print(f"  Attempt {attempt + 1}: {delay}s")
+
+        # Verify the sequence: 1s, 2s, 4s, 8s, 16s
+        expected = [1.0, 2.0, 4.0, 8.0, 16.0]
+        actual = [min(initial_delay * (2 ** i), max_delay) for i in range(5)]
+
+        assert actual == expected, f"Expected {expected}, got {actual}"
+        print("✅ Exponential backoff sequence correct")
+
+        return True
+    except Exception as e:
+        print(f"❌ Backoff calculation failed: {e}")
+        return False
+
+def test_api_integration():
+    """Test that api.py imports webhook module correctly"""
+    print("\n" + "=" * 60)
+    print("TEST 6: API Integration")
+    print("=" * 60)
+
+    try:
+        # Check if api.py can import webhook module
+        api_path = os.path.join(os.path.dirname(__file__), 'deploy', 'docker', 'api.py')
+        with open(api_path, 'r') as f:
+            api_content = f.read()
+
+        if 'from webhook import WebhookDeliveryService' in api_content:
+            print("✅ api.py imports WebhookDeliveryService")
+        else:
+            print("❌ api.py missing webhook import")
+            return False
+
+        if 'WebhookDeliveryService(config)' in api_content:
+            print("✅ api.py initializes WebhookDeliveryService")
+        else:
+            print("❌ api.py doesn't initialize WebhookDeliveryService")
+            return False
+
+        if 'notify_job_completion' in api_content:
+            print("✅ api.py calls notify_job_completion")
+        else:
+            print("❌ api.py doesn't call notify_job_completion")
+            return False
+
+        return True
+    except Exception as e:
+        print(f"❌ API integration check failed: {e}")
+        return False
+
+def main():
+    """Run all tests"""
+    print("\n🧪 Webhook Implementation Validation Tests")
+    print("=" * 60)
+
+    results = []
+
+    # Run tests
+    results.append(("Module Imports", test_imports()))
+    results.append(("Service Initialization", test_webhook_service_init()))
+    results.append(("Config Model", test_webhook_config_model()))
+    results.append(("Payload Construction", test_payload_construction()))
+    results.append(("Exponential Backoff", test_exponential_backoff()))
+    results.append(("API Integration", test_api_integration()))
+
+    # Print summary
+    print("\n" + "=" * 60)
+    print("TEST SUMMARY")
+    print("=" * 60)
+
+    passed = sum(1 for _, result in results if result)
+    total = len(results)
+
+    for test_name, result in results:
+        status = "✅ PASS" if result else "❌ FAIL"
+        print(f"{status} - {test_name}")
+
+    print(f"\n{'=' * 60}")
+    print(f"Results: {passed}/{total} tests passed")
+    print(f"{'=' * 60}")
+
+    if passed == total:
+        print("\n🎉 All tests passed! Webhook implementation is valid.")
+        return 0
+    else:
+        print(f"\n⚠️  {total - passed} test(s) failed. Please review the output above.")
+        return 1
+
+if __name__ == "__main__":
+    exit(main())

tests/WEBHOOK_TEST_README.md

@@ -0,0 +1,251 @@
+# Webhook Feature Test Script
+
+This directory contains a comprehensive test script for the webhook feature implementation.
+
+## Overview
+
+The `test_webhook_feature.sh` script automates the entire process of testing the webhook feature:
+
+1. ✅ Fetches and switches to the webhook feature branch
+2. ✅ Activates the virtual environment
+3. ✅ Installs all required dependencies
+4. ✅ Starts Redis server in background
+5. ✅ Starts Crawl4AI server in background
+6. ✅ Runs webhook integration test
+7. ✅ Verifies job completion via webhook
+8. ✅ Cleans up and returns to original branch
+
+## Prerequisites
+
+- Python 3.10+
+- Virtual environment already created (`venv/` in project root)
+- Git repository with the webhook feature branch
+- `redis-server` (script will attempt to install if missing)
+- `curl` and `lsof` commands available
+
+## Usage
+
+### Quick Start
+
+From the project root:
+
+```bash
+./tests/test_webhook_feature.sh
+```
+
+Or from the tests directory:
+
+```bash
+cd tests
+./test_webhook_feature.sh
+```
+
+### What the Script Does
+
+#### Step 1: Branch Management
+- Saves your current branch
+- Fetches the webhook feature branch from remote
+- Switches to the webhook feature branch
+
+#### Step 2: Environment Setup
+- Activates your existing virtual environment
+- Installs dependencies from `deploy/docker/requirements.txt`
+- Installs Flask for the webhook receiver
+
+#### Step 3: Service Startup
+- Starts Redis server on port 6379
+- Starts Crawl4AI server on port 11235
+- Waits for server health check to pass
+
+#### Step 4: Webhook Test
+- Creates a webhook receiver on port 8080
+- Submits a crawl job for `https://example.com` with webhook config
+- Waits for webhook notification (60s timeout)
+- Verifies webhook payload contains expected data
+
+#### Step 5: Cleanup
+- Stops webhook receiver
+- Stops Crawl4AI server
+- Stops Redis server
+- Returns to your original branch
+
+## Expected Output
+
+```
+[INFO] Starting webhook feature test script
+[INFO] Project root: /path/to/crawl4ai
+[INFO] Step 1: Fetching PR branch...
+[INFO] Current branch: develop
+[SUCCESS] Branch fetched
+[INFO] Step 2: Switching to branch: claude/implement-webhook-crawl-feature-011CULZY1Jy8N5MUkZqXkRVp
+[SUCCESS] Switched to webhook feature branch
+[INFO] Step 3: Activating virtual environment...
+[SUCCESS] Virtual environment activated
+[INFO] Step 4: Installing server dependencies...
+[SUCCESS] Dependencies installed
+[INFO] Step 5a: Starting Redis...
+[SUCCESS] Redis started (PID: 12345)
+[INFO] Step 5b: Starting server on port 11235...
+[INFO] Server started (PID: 12346)
+[INFO] Waiting for server to be ready...
+[SUCCESS] Server is ready!
+[INFO] Step 6: Creating webhook test script...
+[INFO] Running webhook test...
+
+🚀 Submitting crawl job with webhook...
+✅ Job submitted successfully, task_id: crawl_abc123
+⏳ Waiting for webhook notification...
+
+✅ Webhook received: {
+  "task_id": "crawl_abc123",
+  "task_type": "crawl",
+  "status": "completed",
+  "timestamp": "2025-10-22T00:00:00.000000+00:00",
+  "urls": ["https://example.com"],
+  "data": { ... }
+}
+
+✅ Webhook received!
+   Task ID: crawl_abc123
+   Status: completed
+   URLs: ['https://example.com']
+   ✅ Data included in webhook payload
+   📄 Crawled 1 URL(s)
+      - https://example.com: 1234 chars
+
+🎉 Webhook test PASSED!
+
+[INFO] Step 7: Verifying test results...
+[SUCCESS] ✅ Webhook test PASSED!
+[SUCCESS] All tests completed successfully! 🎉
+[INFO] Cleanup will happen automatically...
+[INFO] Starting cleanup...
+[INFO] Stopping webhook receiver...
+[INFO] Stopping server...
+[INFO] Stopping Redis...
+[INFO] Switching back to branch: develop
+[SUCCESS] Cleanup complete
+```
+
+## Troubleshooting
+
+### Server Failed to Start
+
+If the server fails to start, check the logs:
+
+```bash
+tail -100 /tmp/crawl4ai_server.log
+```
+
+Common issues:
+- Port 11235 already in use: `lsof -ti:11235 | xargs kill -9`
+- Missing dependencies: Check that all packages are installed
+
+### Redis Connection Failed
+
+Check if Redis is running:
+
+```bash
+redis-cli ping
+# Should return: PONG
+```
+
+If not running:
+
+```bash
+redis-server --port 6379 --daemonize yes
+```
+
+### Webhook Not Received
+
+The script has a 60-second timeout for webhook delivery. If the webhook isn't received:
+
+1. Check server logs: `/tmp/crawl4ai_server.log`
+2. Verify webhook receiver is running on port 8080
+3. Check network connectivity between components
+
+### Script Interruption
+
+If the script is interrupted (Ctrl+C), cleanup happens automatically via trap. The script will:
+- Kill all background processes
+- Stop Redis
+- Return to your original branch
+
+To manually cleanup if needed:
+
+```bash
+# Kill processes by port
+lsof -ti:11235 | xargs kill -9  # Server
+lsof -ti:8080 | xargs kill -9   # Webhook receiver
+lsof -ti:6379 | xargs kill -9   # Redis
+
+# Return to your branch
+git checkout develop  # or your branch name
+```
+
+## Testing Different URLs
+
+To test with a different URL, modify the script or create a custom test:
+
+```python
+payload = {
+    "urls": ["https://your-url-here.com"],
+    "browser_config": {"headless": True},
+    "crawler_config": {"cache_mode": "bypass"},
+    "webhook_config": {
+        "webhook_url": "http://localhost:8080/webhook",
+        "webhook_data_in_payload": True
+    }
+}
+```
+
+## Files Generated
+
+The script creates temporary files:
+
+- `/tmp/crawl4ai_server.log` - Server output logs
+- `/tmp/test_webhook.py` - Webhook test Python script
+
+These are not cleaned up automatically so you can review them after the test.
+
+## Exit Codes
+
+- `0` - All tests passed successfully
+- `1` - Test failed (check output for details)
+
+## Safety Features
+
+- ✅ Automatic cleanup on exit, interrupt, or error
+- ✅ Returns to original branch on completion
+- ✅ Kills all background processes
+- ✅ Comprehensive error handling
+- ✅ Colored output for easy reading
+- ✅ Detailed logging at each step
+
+## Notes
+
+- The script uses `set -e` to exit on any command failure
+- All background processes are tracked and cleaned up
+- The virtual environment must exist before running
+- Redis must be available (installed or installable via apt-get/brew)
+
+## Integration with CI/CD
+
+This script can be integrated into CI/CD pipelines:
+
+```yaml
+# Example GitHub Actions
+- name: Test Webhook Feature
+  run: |
+    chmod +x tests/test_webhook_feature.sh
+    ./tests/test_webhook_feature.sh
+```
+
+## Support
+
+If you encounter issues:
+
+1. Check the troubleshooting section above
+2. Review server logs at `/tmp/crawl4ai_server.log`
+3. Ensure all prerequisites are met
+4. Open an issue with the full output of the script

tests/async/test_redirect_url_resolution.py

@@ -0,0 +1,118 @@
+"""Test delayed redirect WITH wait_for - does link resolution use correct URL?"""
+import asyncio
+import threading
+from http.server import HTTPServer, SimpleHTTPRequestHandler
+
+class RedirectTestHandler(SimpleHTTPRequestHandler):
+    def log_message(self, format, *args):
+        pass
+
+    def do_GET(self):
+        if self.path == "/page-a":
+            self.send_response(200)
+            self.send_header("Content-type", "text/html")
+            self.end_headers()
+            content = """
+            <!DOCTYPE html>
+            <html>
+            <head><title>Page A</title></head>
+            <body>
+                <h1>Page A - Will redirect after 200ms</h1>
+                <script>
+                    setTimeout(function() {
+                        window.location.href = '/redirect-target/';
+                    }, 200);
+                </script>
+            </body>
+            </html>
+            """
+            self.wfile.write(content.encode())
+        elif self.path.startswith("/redirect-target"):
+            self.send_response(200)
+            self.send_header("Content-type", "text/html")
+            self.end_headers()
+            content = """
+            <!DOCTYPE html>
+            <html>
+            <head><title>Redirect Target</title></head>
+            <body>
+                <h1>Redirect Target</h1>
+                <nav id="target-nav">
+                    <a href="subpage-1">Subpage 1</a>
+                    <a href="subpage-2">Subpage 2</a>
+                </nav>
+            </body>
+            </html>
+            """
+            self.wfile.write(content.encode())
+        else:
+            self.send_response(404)
+            self.end_headers()
+
+async def main():
+    import socket
+    class ReuseAddrHTTPServer(HTTPServer):
+        allow_reuse_address = True
+    
+    server = ReuseAddrHTTPServer(("localhost", 8769), RedirectTestHandler)
+    thread = threading.Thread(target=server.serve_forever)
+    thread.daemon = True
+    thread.start()
+    
+    try:
+        import sys
+        sys.path.insert(0, '/Users/nasrin/vscode/c4ai-uc/develop')
+        from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig
+        
+        print("=" * 60)
+        print("TEST: Delayed JS redirect WITH wait_for='css:#target-nav'")
+        print("This waits for the redirect to complete")
+        print("=" * 60)
+        
+        browser_config = BrowserConfig(headless=True, verbose=False)
+        crawl_config = CrawlerRunConfig(
+            cache_mode="bypass",
+            wait_for="css:#target-nav"  # Wait for element on redirect target
+        )
+        
+        async with AsyncWebCrawler(config=browser_config) as crawler:
+            result = await crawler.arun(
+                url="http://localhost:8769/page-a",
+                config=crawl_config
+            )
+            
+            print(f"Original URL: http://localhost:8769/page-a")
+            print(f"Redirected URL returned: {result.redirected_url}")
+            print(f"HTML contains 'Redirect Target': {'Redirect Target' in result.html}")
+            print()
+            
+            if "/redirect-target" in (result.redirected_url or ""):
+                print("✓ redirected_url is CORRECT")
+            else:
+                print("✗ BUG #1: redirected_url is WRONG - still shows original URL!")
+                
+            # Check links
+            all_links = []
+            if isinstance(result.links, dict):
+                all_links = result.links.get("internal", []) + result.links.get("external", [])
+            
+            print(f"\nLinks found ({len(all_links)} total):")
+            bug_found = False
+            for link in all_links:
+                href = link.get("href", "") if isinstance(link, dict) else getattr(link, 'href', "")
+                if "subpage" in href:
+                    print(f"  {href}")
+                    if "/page-a/" in href:
+                        print("    ^^^ BUG #2: Link resolved with WRONG base URL!")
+                        bug_found = True
+                    elif "/redirect-target/" in href:
+                        print("    ^^^ CORRECT")
+            
+            if not bug_found and all_links:
+                print("\n✓ Link resolution is CORRECT")
+                        
+    finally:
+        server.shutdown()
+
+if __name__ == "__main__":
+    asyncio.run(main())

tests/browser/test_cdp_strategy.py

@@ -7,12 +7,13 @@ and serve as functional tests.
 import asyncio
 import os
 import sys
+import time
 
 # Add the project root to Python path if running directly
 if __name__ == "__main__":
     sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../..')))
 
-from crawl4ai.browser import BrowserManager
+from crawl4ai.browser_manager import BrowserManager
 from crawl4ai.async_configs import BrowserConfig, CrawlerRunConfig
 from crawl4ai.async_logger import AsyncLogger
 
@@ -24,8 +25,8 @@ async def test_cdp_launch_connect():
     logger.info("Testing launch and connect via CDP", tag="TEST")
     
     browser_config = BrowserConfig(
-        use_managed_browser=True,
         browser_mode="cdp",
+        use_managed_browser=True,
         headless=True
     )
     
@@ -62,17 +63,18 @@ async def test_cdp_launch_connect():
         return False
 
 async def test_cdp_with_user_data_dir():
-    """Test CDP browser with a user data directory."""
+    """Test CDP browser with a user data directory and storage state."""
     logger.info("Testing CDP browser with user data directory", tag="TEST")
     
     # Create a temporary user data directory
     import tempfile
     user_data_dir = tempfile.mkdtemp(prefix="crawl4ai-test-")
+    storage_state_file = os.path.join(user_data_dir, "storage_state.json")
     logger.info(f"Created temporary user data directory: {user_data_dir}", tag="TEST")
     
     browser_config = BrowserConfig(
         headless=True,
-        browser_mode="cdp",
+        use_managed_browser=True,
         user_data_dir=user_data_dir
     )
     
@@ -86,38 +88,59 @@ async def test_cdp_with_user_data_dir():
         crawler_config = CrawlerRunConfig()
         page, context = await manager.get_page(crawler_config)
         
-        # Set a cookie
+        # Visit the site first
+        await page.goto("https://example.com", wait_until="domcontentloaded")
+        
+        # Set a cookie via JavaScript (more reliable for persistence)
+        await page.evaluate("""
+            document.cookie = 'test_cookie=test_value; path=/; max-age=86400';
+        """)
+        
+        # Also set via context API for double coverage
         await context.add_cookies([{
-            "name": "test_cookie",
-            "value": "test_value",
-            "url": "https://example.com"
+            "name": "test_cookie_api",
+            "value": "test_value_api",
+            "domain": "example.com",
+            "path": "/"
         }])
         
-        # Visit the site
-        await page.goto("https://example.com")
-        
-        # Verify cookie was set
+        # Verify cookies were set
         cookies = await context.cookies(["https://example.com"])
-        has_test_cookie = any(cookie["name"] == "test_cookie" for cookie in cookies)
+        has_test_cookie = any(cookie["name"] in ["test_cookie", "test_cookie_api"] for cookie in cookies)
         logger.info(f"Cookie set successfully: {has_test_cookie}", tag="TEST")
         
+        # Save storage state before closing
+        await context.storage_state(path=storage_state_file)
+        logger.info(f"Storage state saved to: {storage_state_file}", tag="TEST")
+        
         # Close the browser
         await manager.close()
         logger.info("First browser session closed", tag="TEST")
         
-        # Start a new browser with the same user data directory
+        # Wait a moment for clean shutdown
+        await asyncio.sleep(1.0)
+        
+        # Start a new browser with the same user data directory and storage state
         logger.info("Starting second browser session with same user data directory", tag="TEST")
-        manager2 = BrowserManager(browser_config=browser_config, logger=logger)
+        browser_config2 = BrowserConfig(
+            headless=True,
+            use_managed_browser=True,
+            user_data_dir=user_data_dir,
+            storage_state=storage_state_file
+        )
+        
+        manager2 = BrowserManager(browser_config=browser_config2, logger=logger)
         await manager2.start()
         
         # Get a new page and check if the cookie persists
         page2, context2 = await manager2.get_page(crawler_config)
-        await page2.goto("https://example.com")
+        await page2.goto("https://example.com", wait_until="domcontentloaded")
         
         # Verify cookie persisted
         cookies2 = await context2.cookies(["https://example.com"])
-        has_test_cookie2 = any(cookie["name"] == "test_cookie" for cookie in cookies2)
+        has_test_cookie2 = any(cookie["name"] in ["test_cookie", "test_cookie_api"] for cookie in cookies2)
         logger.info(f"Cookie persisted across sessions: {has_test_cookie2}", tag="TEST")
+        logger.info(f"Cookies found: {[c['name'] for c in cookies2]}", tag="TEST")
         
         # Clean up
         await manager2.close()
@@ -134,6 +157,10 @@ async def test_cdp_with_user_data_dir():
             await manager.close()
         except:
             pass
+        try:
+            await manager2.close()
+        except:
+            pass
             
         # Clean up temporary directory
         try:
@@ -145,7 +172,7 @@ async def test_cdp_with_user_data_dir():
         return False
 
 async def test_cdp_session_management():
-    """Test session management with CDP browser."""
+    """Test session management with CDP browser - focused on session tracking."""
     logger.info("Testing session management with CDP browser", tag="TEST")
     
     browser_config = BrowserConfig(
@@ -159,45 +186,104 @@ async def test_cdp_session_management():
         await manager.start()
         logger.info("Browser launched successfully", tag="TEST")
         
-        # Create two sessions
+        # Test session tracking and lifecycle management
         session1_id = "test_session_1"
         session2_id = "test_session_2"
         
         # Set up first session
         crawler_config1 = CrawlerRunConfig(session_id=session1_id)
         page1, context1 = await manager.get_page(crawler_config1)
-        await page1.goto("https://example.com")
-        await page1.evaluate("localStorage.setItem('session1_data', 'test_value')")
-        logger.info(f"Set up session 1 with ID: {session1_id}", tag="TEST")
+        await page1.goto("https://example.com", wait_until="domcontentloaded")
         
-        # Set up second session
+        # Get page URL and title for verification
+        page1_url = page1.url
+        page1_title = await page1.title()
+        logger.info(f"Session 1 setup - URL: {page1_url}, Title: {page1_title}", tag="TEST")
+        
+        # Set up second session  
         crawler_config2 = CrawlerRunConfig(session_id=session2_id)
         page2, context2 = await manager.get_page(crawler_config2)
-        await page2.goto("https://example.org")
-        await page2.evaluate("localStorage.setItem('session2_data', 'test_value2')")
-        logger.info(f"Set up session 2 with ID: {session2_id}", tag="TEST")
+        await page2.goto("https://httpbin.org/html", wait_until="domcontentloaded")
         
-        # Get first session again
-        page1_again, _ = await manager.get_page(crawler_config1)
+        page2_url = page2.url
+        page2_title = await page2.title()
+        logger.info(f"Session 2 setup - URL: {page2_url}, Title: {page2_title}", tag="TEST")
         
-        # Verify it's the same page and data persists
+        # Verify sessions exist in manager
+        session1_exists = session1_id in manager.sessions
+        session2_exists = session2_id in manager.sessions
+        logger.info(f"Sessions in manager - S1: {session1_exists}, S2: {session2_exists}", tag="TEST")
+        
+        # Test session reuse
+        page1_again, context1_again = await manager.get_page(crawler_config1)
         is_same_page = page1 == page1_again
-        data1 = await page1_again.evaluate("localStorage.getItem('session1_data')")
-        logger.info(f"Session 1 reuse successful: {is_same_page}, data: {data1}", tag="TEST")
+        is_same_context = context1 == context1_again
         
-        # Kill first session
+        logger.info(f"Session 1 reuse - Same page: {is_same_page}, Same context: {is_same_context}", tag="TEST")
+        
+        # Test that sessions are properly tracked with timestamps
+        session1_info = manager.sessions.get(session1_id)
+        session2_info = manager.sessions.get(session2_id)
+        
+        session1_has_timestamp = session1_info and len(session1_info) == 3
+        session2_has_timestamp = session2_info and len(session2_info) == 3
+        
+        logger.info(f"Session tracking - S1 complete: {session1_has_timestamp}, S2 complete: {session2_has_timestamp}", tag="TEST")
+        
+        # In managed browser mode, pages might be shared. Let's test what actually happens
+        pages_same_or_different = page1 == page2
+        logger.info(f"Pages same object: {pages_same_or_different}", tag="TEST")
+        
+        # Test that we can distinguish sessions by their stored info
+        session1_context, session1_page, session1_time = session1_info
+        session2_context, session2_page, session2_time = session2_info
+        
+        sessions_have_different_timestamps = session1_time != session2_time
+        logger.info(f"Sessions have different timestamps: {sessions_have_different_timestamps}", tag="TEST")
+        
+        # Test session killing
         await manager.kill_session(session1_id)
         logger.info(f"Killed session 1", tag="TEST")
         
-        # Verify second session still works
-        data2 = await page2.evaluate("localStorage.getItem('session2_data')")
-        logger.info(f"Session 2 still functional after killing session 1, data: {data2}", tag="TEST")
+        # Verify session was removed
+        session1_removed = session1_id not in manager.sessions
+        session2_still_exists = session2_id in manager.sessions
+        logger.info(f"After kill - S1 removed: {session1_removed}, S2 exists: {session2_still_exists}", tag="TEST")
+        
+        # Test page state after killing session
+        page1_closed = page1.is_closed()
+        logger.info(f"Page1 closed after kill: {page1_closed}", tag="TEST")
+        
+        # Clean up remaining session
+        try:
+            await manager.kill_session(session2_id)
+            logger.info("Killed session 2", tag="TEST")
+            session2_removed = session2_id not in manager.sessions
+        except Exception as e:
+            logger.info(f"Session 2 cleanup: {e}", tag="TEST")
+            session2_removed = False
         
         # Clean up
         await manager.close()
         logger.info("Browser closed successfully", tag="TEST")
         
-        return is_same_page and data1 == "test_value" and data2 == "test_value2"
+        # Success criteria for managed browser sessions:
+        # 1. Sessions can be created and tracked with proper info
+        # 2. Same page/context returned for same session ID  
+        # 3. Sessions have proper timestamp tracking
+        # 4. Sessions can be killed and removed from tracking
+        # 5. Session cleanup works properly
+        success = (session1_exists and 
+                  session2_exists and 
+                  is_same_page and 
+                  session1_has_timestamp and 
+                  session2_has_timestamp and
+                  sessions_have_different_timestamps and
+                  session1_removed and 
+                  session2_removed)
+        
+        logger.info(f"Test success: {success}", tag="TEST")
+        return success
     except Exception as e:
         logger.error(f"Test failed: {str(e)}", tag="TEST")
         try:
@@ -206,14 +292,170 @@ async def test_cdp_session_management():
             pass
         return False
 
+async def test_cdp_timing_fix_fast_startup():
+    """
+    Test that the CDP timing fix handles fast browser startup correctly.
+    This should work without any delays or retries.
+    """
+    logger.info("Testing CDP timing fix with fast startup", tag="TEST")
+    
+    browser_config = BrowserConfig(
+        use_managed_browser=True,
+        browser_mode="cdp",
+        headless=True,
+        debugging_port=9223,  # Use different port to avoid conflicts
+        verbose=True
+    )
+    
+    manager = BrowserManager(browser_config=browser_config, logger=logger)
+    
+    try:
+        start_time = time.time()
+        await manager.start()
+        startup_time = time.time() - start_time
+        
+        logger.info(f"Browser started successfully in {startup_time:.2f}s", tag="TEST")
+        
+        # Test basic functionality
+        crawler_config = CrawlerRunConfig(url="https://example.com")
+        page, context = await manager.get_page(crawler_config)
+        
+        await page.goto("https://example.com", wait_until="domcontentloaded")
+        title = await page.title()
+        
+        logger.info(f"Successfully navigated to page: {title}", tag="TEST")
+        
+        await manager.close()
+        logger.success("test_cdp_timing_fix_fast_startup completed successfully", tag="TEST")
+        return True
+        
+    except Exception as e:
+        logger.error(f"test_cdp_timing_fix_fast_startup failed: {str(e)}", tag="TEST")
+        try:
+            await manager.close()
+        except:
+            pass
+        return False
+
+
+async def test_cdp_timing_fix_delayed_browser_start():
+    """
+    Test CDP timing fix by actually delaying the browser startup process.
+    This simulates a real scenario where the browser takes time to expose CDP.
+    """
+    logger.info("Testing CDP timing fix with delayed browser startup", tag="TEST")
+    
+    browser_config = BrowserConfig(
+        use_managed_browser=True,
+        browser_mode="cdp",
+        headless=True,
+        debugging_port=9224,
+        verbose=True
+    )
+    
+    # Start the managed browser separately to control timing
+    from crawl4ai.browser_manager import ManagedBrowser
+    managed_browser = ManagedBrowser(browser_config=browser_config, logger=logger)
+    
+    try:
+        # Start browser process but it will take time for CDP to be ready
+        cdp_url = await managed_browser.start()
+        logger.info(f"Managed browser started at {cdp_url}", tag="TEST")
+        
+        # Small delay to simulate the browser needing time to fully initialize CDP
+        await asyncio.sleep(1.0)
+        
+        # Now create BrowserManager and connect - this should use the CDP verification fix
+        manager = BrowserManager(browser_config=browser_config, logger=logger)
+        manager.config.cdp_url = cdp_url  # Use the CDP URL from managed browser
+        
+        start_time = time.time()
+        await manager.start()
+        startup_time = time.time() - start_time
+        
+        logger.info(f"BrowserManager connected successfully in {startup_time:.2f}s", tag="TEST")
+        
+        # Test basic functionality
+        crawler_config = CrawlerRunConfig(url="https://example.com")
+        page, context = await manager.get_page(crawler_config)
+        await page.goto("https://example.com", wait_until="domcontentloaded")
+        title = await page.title()
+        
+        logger.info(f"Successfully navigated to page: {title}", tag="TEST")
+        
+        # Clean up
+        await manager.close()
+        await managed_browser.cleanup()
+        
+        logger.success("test_cdp_timing_fix_delayed_browser_start completed successfully", tag="TEST")
+        return True
+        
+    except Exception as e:
+        logger.error(f"test_cdp_timing_fix_delayed_browser_start failed: {str(e)}", tag="TEST")
+        try:
+            await manager.close()
+            await managed_browser.cleanup()
+        except:
+            pass
+        return False
+
+
+async def test_cdp_verification_backoff_behavior():
+    """
+    Test the exponential backoff behavior of CDP verification in isolation.
+    """
+    logger.info("Testing CDP verification exponential backoff behavior", tag="TEST")
+    
+    browser_config = BrowserConfig(
+        use_managed_browser=True,
+        debugging_port=9225,  # Use different port
+        verbose=True
+    )
+    
+    manager = BrowserManager(browser_config=browser_config, logger=logger)
+    
+    try:
+        # Test with a non-existent CDP URL to trigger retries
+        fake_cdp_url = "http://localhost:19999"  # This should not exist
+        
+        start_time = time.time()
+        result = await manager._verify_cdp_ready(fake_cdp_url)
+        elapsed_time = time.time() - start_time
+        
+        # Should return False after all retries
+        assert result is False, "Expected CDP verification to fail with non-existent endpoint"
+        
+        # Should take some time due to retries and backoff
+        assert elapsed_time > 2.0, f"Expected backoff delays, but took only {elapsed_time:.2f}s"
+        
+        logger.info(f"CDP verification correctly failed after {elapsed_time:.2f}s with exponential backoff", tag="TEST")
+        logger.success("test_cdp_verification_backoff_behavior completed successfully", tag="TEST")
+        return True
+        
+    except Exception as e:
+        logger.error(f"test_cdp_verification_backoff_behavior failed: {str(e)}", tag="TEST")
+        return False
+
+
+
 async def run_tests():
     """Run all tests sequentially."""
+    import time
+    
     results = []
     
+    # Original CDP strategy tests
+    logger.info("Running original CDP strategy tests", tag="SUITE")
     # results.append(await test_cdp_launch_connect())
     results.append(await test_cdp_with_user_data_dir())
     results.append(await test_cdp_session_management())
     
+    # CDP timing fix tests
+    logger.info("Running CDP timing fix tests", tag="SUITE")
+    results.append(await test_cdp_timing_fix_fast_startup())
+    results.append(await test_cdp_timing_fix_delayed_browser_start())
+    results.append(await test_cdp_verification_backoff_behavior())
+    
     # Print summary
     total = len(results)
     passed = sum(results)

tests/check_dependencies.py

@@ -71,7 +71,7 @@ PACKAGE_MAPPINGS = {
     'sentence_transformers': 'sentence-transformers',
     'rank_bm25': 'rank-bm25',
     'snowballstemmer': 'snowballstemmer',
-    'PyPDF2': 'PyPDF2',
+    'pypdf': 'pypdf',
     'pdf2image': 'pdf2image',
 }