Release v0.7.6: The 0.7.6 Update

- Updated version to 0.7.6
- Added comprehensive demo and release notes
- Updated all documentation
- Update the veriosn in Dockerfile to 0.7.6

.github/workflows/docker-release.yml

@@ -0,0 +1,81 @@
+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: 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

@@ -266,11 +266,11 @@ continue_config.json
 .llm.env
 .private/
 
+.claude/
+
 CLAUDE_MONITOR.md
 CLAUDE.md
 
-.claude/
-
 tests/**/test_site
 tests/**/reports
 tests/**/benchmark_reports
@@ -282,14 +282,3 @@ docs/apps/linkdin/debug*/
 docs/apps/linkdin/samples/insights/*
 
 scripts/
-
-
-# Databse files
-*.sqlite3
-*.sqlite3-journal
-*.db-journal
-*.db-wal
-*.db-shm
-*.db
-*.rdb
-*.ldb

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=0.7.6
 ENV C4AI_VERSION=$C4AI_VER
 LABEL c4ai.version=$C4AI_VER
 

README.md

@@ -27,11 +27,13 @@
 
 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 v0.7.6](#-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 v0.7.6**: 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. No more polling! [Release notes →](https://github.com/unclecode/crawl4ai/blob/main/docs/blog/release-v0.7.6.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 v0.7.5: Docker Hooks System with function-based API for pipeline customization, Enhanced LLM Integration with custom providers, HTTPS Preservation, and multiple community-reported bug fixes. [Release notes →](https://github.com/unclecode/crawl4ai/blob/main/docs/blog/release-v0.7.5.md)
+
+✨ Previous 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)
 
 <details>
   <summary>🤓 <strong>My Personal Story</strong></summary>
@@ -177,7 +179,7 @@ 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.
@@ -544,6 +546,54 @@ async def test_news_crawl():
 
 ## ✨ Recent Updates
 
+<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 +969,36 @@ 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://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 | 🥈 Silver |
+| <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

@@ -103,7 +103,8 @@ from .browser_adapter import (
 
 from .utils import (
     start_colab_display_server,
-    setup_colab_environment
+    setup_colab_environment,
+    hooks_to_string
 )
 
 __all__ = [
@@ -183,6 +184,7 @@ __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__ = "0.7.6"
 
 # For nightly builds, this gets set during build process
 __nightly_version__ = None

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)
         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/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
@@ -3529,4 +3530,52 @@ 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 `0.7.6`. 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 (0.7.6)
+docker pull unclecode/crawl4ai:0.7.6
 
-# Or pull the current stable version (0.6.0)
+# Or use the latest tag (points to 0.7.6)
 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:0.7.6
     ```
 
 *   **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:0.7.6
     ```
 
 > 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:0.7.6 docker compose up -d
     ```
 
 *   **Build and Run Locally:**
@@ -648,6 +647,146 @@ 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"`.
+
+> 💡 **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 +965,11 @@ 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/STRESS_TEST_PIPELINE.md

@@ -1,241 +0,0 @@
-# Crawl4AI Docker Memory & Pool Optimization - Implementation Log
-
-## Critical Issues Identified
-
-### Memory Management
-- **Host vs Container**: `psutil.virtual_memory()` reported host memory, not container limits
-- **Browser Pooling**: No pool reuse - every endpoint created new browsers
-- **Warmup Waste**: Permanent browser sat idle with mismatched config signature
-- **Idle Cleanup**: 30min TTL too long, janitor ran every 60s
-- **Endpoint Inconsistency**: 75% of endpoints bypassed pool (`/md`, `/html`, `/screenshot`, `/pdf`, `/execute_js`, `/llm`)
-
-### Pool Design Flaws
-- **Config Mismatch**: Permanent browser used `config.yml` args, endpoints used empty `BrowserConfig()`
-- **Logging Level**: Pool hit markers at DEBUG, invisible with INFO logging
-
-## Implementation Changes
-
-### 1. Container-Aware Memory Detection (`utils.py`)
-```python
-def get_container_memory_percent() -> float:
-    # Try cgroup v2 → v1 → fallback to psutil
-    # Reads /sys/fs/cgroup/memory.{current,max} OR memory/memory.{usage,limit}_in_bytes
-```
-
-### 2. Smart Browser Pool (`crawler_pool.py`)
-**3-Tier System:**
-- **PERMANENT**: Always-ready default browser (never cleaned)
-- **HOT_POOL**: Configs used 3+ times (longer TTL)
-- **COLD_POOL**: New/rare configs (short TTL)
-
-**Key Functions:**
-- `get_crawler(cfg)`: Check permanent → hot → cold → create new
-- `init_permanent(cfg)`: Initialize permanent at startup
-- `janitor()`: Adaptive cleanup (10s/30s/60s intervals based on memory)
-- `_sig(cfg)`: SHA1 hash of config dict for pool keys
-
-**Logging Fix**: Changed `logger.debug()` → `logger.info()` for pool hits
-
-### 3. Endpoint Unification
-**Helper Function** (`server.py`):
-```python
-def get_default_browser_config() -> BrowserConfig:
-    return BrowserConfig(
-        extra_args=config["crawler"]["browser"].get("extra_args", []),
-        **config["crawler"]["browser"].get("kwargs", {}),
-    )
-```
-
-**Migrated Endpoints:**
-- `/html`, `/screenshot`, `/pdf`, `/execute_js` → use `get_default_browser_config()`
-- `handle_llm_qa()`, `handle_markdown_request()` → same
-
-**Result**: All endpoints now hit permanent browser pool
-
-### 4. Config Updates (`config.yml`)
-- `idle_ttl_sec: 1800` → `300` (30min → 5min base TTL)
-- `port: 11234` → `11235` (fixed mismatch with Gunicorn)
-
-### 5. Lifespan Fix (`server.py`)
-```python
-await init_permanent(BrowserConfig(
-    extra_args=config["crawler"]["browser"].get("extra_args", []),
-    **config["crawler"]["browser"].get("kwargs", {}),
-))
-```
-Permanent browser now matches endpoint config signatures
-
-## Test Results
-
-### Test 1: Basic Health
-- 10 requests to `/health`
-- **Result**: 100% success, avg 3ms latency
-- **Baseline**: Container starts in ~5s, 270 MB idle
-
-### Test 2: Memory Monitoring
-- 20 requests with Docker stats tracking
-- **Result**: 100% success, no memory leak (-0.2 MB delta)
-- **Baseline**: 269.7 MB container overhead
-
-### Test 3: Pool Validation
-- 30 requests to `/html` endpoint
-- **Result**: **100% permanent browser hits**, 0 new browsers created
-- **Memory**: 287 MB baseline → 396 MB active (+109 MB)
-- **Latency**: Avg 4s (includes network to httpbin.org)
-
-### Test 4: Concurrent Load
-- Light (10) → Medium (50) → Heavy (100) concurrent
-- **Total**: 320 requests
-- **Result**: 100% success, **320/320 permanent hits**, 0 new browsers
-- **Memory**: 269 MB → peak 1533 MB → final 993 MB
-- **Latency**: P99 at 100 concurrent = 34s (expected with single browser)
-
-### Test 5: Pool Stress (Mixed Configs)
-- 20 requests with 4 different viewport configs
-- **Result**: 4 new browsers, 4 cold hits, **4 promotions to hot**, 8 hot hits
-- **Reuse Rate**: 60% (12 pool hits / 20 requests)
-- **Memory**: 270 MB → 928 MB peak (+658 MB = ~165 MB per browser)
-- **Proves**: Cold → hot promotion at 3 uses working perfectly
-
-### Test 6: Multi-Endpoint
-- 10 requests each: `/html`, `/screenshot`, `/pdf`, `/crawl`
-- **Result**: 100% success across all 4 endpoints
-- **Latency**: 5-8s avg (PDF slowest at 7.2s)
-
-### Test 7: Cleanup Verification
-- 20 requests (load spike) → 90s idle
-- **Memory**: 269 MB → peak 1107 MB → final 780 MB
-- **Recovery**: 327 MB (39%) - partial cleanup
-- **Note**: Hot pool browsers persist (by design), janitor working correctly
-
-## Performance Metrics
-
-| Metric | Before | After | Improvement |
-|--------|--------|-------|-------------|
-| Pool Reuse | 0% | 100% (default config) | ∞ |
-| Memory Leak | Unknown | 0 MB/cycle | Stable |
-| Browser Reuse | No | Yes | ~3-5s saved per request |
-| Idle Memory | 500-700 MB × N | 270-400 MB | 10x reduction |
-| Concurrent Capacity | ~20 | 100+ | 5x |
-
-## Key Learnings
-
-1. **Config Signature Matching**: Permanent browser MUST match endpoint default config exactly (SHA1 hash)
-2. **Logging Levels**: Pool diagnostics need INFO level, not DEBUG
-3. **Memory in Docker**: Must read cgroup files, not host metrics
-4. **Janitor Timing**: 60s interval adequate, but TTLs should be short (5min) for cold pool
-5. **Hot Promotion**: 3-use threshold works well for production patterns
-6. **Memory Per Browser**: ~150-200 MB per Chromium instance with headless + text_mode
-
-## Test Infrastructure
-
-**Location**: `deploy/docker/tests/`
-**Dependencies**: `httpx`, `docker` (Python SDK)
-**Pattern**: Sequential build - each test adds one capability
-
-**Files**:
-- `test_1_basic.py`: Health check + container lifecycle
-- `test_2_memory.py`: + Docker stats monitoring
-- `test_3_pool.py`: + Log analysis for pool markers
-- `test_4_concurrent.py`: + asyncio.Semaphore for concurrency control
-- `test_5_pool_stress.py`: + Config variants (viewports)
-- `test_6_multi_endpoint.py`: + Multiple endpoint testing
-- `test_7_cleanup.py`: + Time-series memory tracking for janitor
-
-**Run Pattern**:
-```bash
-cd deploy/docker/tests
-pip install -r requirements.txt
-# Rebuild after code changes:
-cd /path/to/repo && docker buildx build -t crawl4ai-local:latest --load .
-# Run test:
-python test_N_name.py
-```
-
-## Architecture Decisions
-
-**Why Permanent Browser?**
-- 90% of requests use default config → single browser serves most traffic
-- Eliminates 3-5s startup overhead per request
-
-**Why 3-Tier Pool?**
-- Permanent: Zero cost for common case
-- Hot: Amortized cost for frequent variants
-- Cold: Lazy allocation for rare configs
-
-**Why Adaptive Janitor?**
-- Memory pressure triggers aggressive cleanup
-- Low memory allows longer TTLs for better reuse
-
-**Why Not Close After Each Request?**
-- Browser startup: 3-5s overhead
-- Pool reuse: <100ms overhead
-- Net: 30-50x faster
-
-## Future Optimizations
-
-1. **Request Queuing**: When at capacity, queue instead of reject
-2. **Pre-warming**: Predict common configs, pre-create browsers
-3. **Metrics Export**: Prometheus metrics for pool efficiency
-4. **Config Normalization**: Group similar viewports (e.g., 1920±50 → 1920)
-
-## Critical Code Paths
-
-**Browser Acquisition** (`crawler_pool.py:34-78`):
-```
-get_crawler(cfg) →
-  _sig(cfg) →
-  if sig == DEFAULT_CONFIG_SIG → PERMANENT
-  elif sig in HOT_POOL → HOT_POOL[sig]
-  elif sig in COLD_POOL → promote if count >= 3
-  else → create new in COLD_POOL
-```
-
-**Janitor Loop** (`crawler_pool.py:107-146`):
-```
-while True:
-  mem% = get_container_memory_percent()
-  if mem% > 80: interval=10s, cold_ttl=30s
-  elif mem% > 60: interval=30s, cold_ttl=60s
-  else: interval=60s, cold_ttl=300s
-  sleep(interval)
-  close idle browsers (COLD then HOT)
-```
-
-**Endpoint Pattern** (`server.py` example):
-```python
-@app.post("/html")
-async def generate_html(...):
-    from crawler_pool import get_crawler
-    crawler = await get_crawler(get_default_browser_config())
-    results = await crawler.arun(url=body.url, config=cfg)
-    # No crawler.close() - returned to pool
-```
-
-## Debugging Tips
-
-**Check Pool Activity**:
-```bash
-docker logs crawl4ai-test | grep -E "(🔥|♨️|❄️|🆕|⬆️)"
-```
-
-**Verify Config Signature**:
-```python
-from crawl4ai import BrowserConfig
-import json, hashlib
-cfg = BrowserConfig(...)
-sig = hashlib.sha1(json.dumps(cfg.to_dict(), sort_keys=True).encode()).hexdigest()
-print(sig[:8])  # Compare with logs
-```
-
-**Monitor Memory**:
-```bash
-docker stats crawl4ai-test
-```
-
-## Known Limitations
-
-- **Mac Docker Stats**: CPU metrics unreliable, memory works
-- **PDF Generation**: Slowest endpoint (~7s), no optimization yet
-- **Hot Pool Persistence**: May hold memory longer than needed (trade-off for performance)
-- **Janitor Lag**: Up to 60s before cleanup triggers in low-memory scenarios

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
 
@@ -66,7 +67,6 @@ async def handle_llm_qa(
     config: dict
 ) -> str:
     """Process QA using LLM with crawled content as context."""
-    from crawler_pool import get_crawler
     try:
         if not url.startswith(('http://', 'https://')) and not url.startswith(("raw:", "raw://")):
             url = 'https://' + url
@@ -75,21 +75,15 @@ async def handle_llm_qa(
         if last_q_index != -1:
             url = url[:last_q_index]
 
-        # Get markdown content (use default config)
-        from utils import load_config
-        cfg = load_config()
-        browser_cfg = BrowserConfig(
-            extra_args=cfg["crawler"]["browser"].get("extra_args", []),
-            **cfg["crawler"]["browser"].get("kwargs", {}),
-        )
-        crawler = await get_crawler(browser_cfg)
-        result = await crawler.arun(url)
-        if not result.success:
-            raise HTTPException(
-                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-                detail=result.error_message
-            )
-        content = result.markdown.fit_markdown or result.markdown.raw_markdown
+        # Get markdown content
+        async with AsyncWebCrawler() as crawler:
+            result = await crawler.arun(url)
+            if not result.success:
+                raise HTTPException(
+                    status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+                    detail=result.error_message
+                )
+            content = result.markdown.fit_markdown or result.markdown.raw_markdown
 
         # Create prompt and get LLM response
         prompt = f"""Use the following content as context to answer the question.
@@ -127,10 +121,14 @@ 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 +137,16 @@ 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 +177,40 @@ 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 +218,16 @@ 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,
@@ -231,32 +272,25 @@ async def handle_markdown_request(
 
         cache_mode = CacheMode.ENABLED if cache == "1" else CacheMode.WRITE_ONLY
 
-        from crawler_pool import get_crawler
-        from utils import load_config as _load_config
-        _cfg = _load_config()
-        browser_cfg = BrowserConfig(
-            extra_args=_cfg["crawler"]["browser"].get("extra_args", []),
-            **_cfg["crawler"]["browser"].get("kwargs", {}),
-        )
-        crawler = await get_crawler(browser_cfg)
-        result = await crawler.arun(
-            url=decoded_url,
-            config=CrawlerRunConfig(
-                markdown_generator=md_generator,
-                scraping_strategy=LXMLWebScrapingStrategy(),
-                cache_mode=cache_mode
+        async with AsyncWebCrawler() as crawler:
+            result = await crawler.arun(
+                url=decoded_url,
+                config=CrawlerRunConfig(
+                    markdown_generator=md_generator,
+                    scraping_strategy=LXMLWebScrapingStrategy(),
+                    cache_mode=cache_mode
+                )
             )
-        )
+            
+            if not result.success:
+                raise HTTPException(
+                    status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+                    detail=result.error_message
+                )
 
-        if not result.success:
-            raise HTTPException(
-                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-                detail=result.error_message
-            )
-
-        return (result.markdown.raw_markdown
-               if filter_type == FilterType.RAW
-               else result.markdown.fit_markdown)
+            return (result.markdown.raw_markdown 
+                   if filter_type == FilterType.RAW 
+                   else result.markdown.fit_markdown)
 
     except Exception as e:
         logger.error(f"Markdown error: {str(e)}", exc_info=True)
@@ -275,6 +309,7 @@ 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 +343,7 @@ async def handle_llm_request(
             base_url,
             config,
             provider,
+            webhook_config,
             temperature,
             api_base_url
         )
@@ -355,6 +391,7 @@ 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 +402,18 @@ 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 +425,7 @@ async def create_new_task(
         schema,
         cache,
         provider,
+        webhook_config,
         temperature,
         api_base_url
     )
@@ -460,22 +504,12 @@ async def handle_crawl_request(
     hooks_config: Optional[dict] = None
 ) -> dict:
     """Handle non-streaming crawl requests with optional hooks."""
-    # Track request start
-    request_id = f"req_{uuid4().hex[:8]}"
-    try:
-        from monitor import get_monitor
-        await get_monitor().track_request_start(
-            request_id, "/crawl", urls[0] if urls else "batch", browser_config
-        )
-    except:
-        pass  # Monitor not critical
-
     start_mem_mb = _get_memory_mb() # <--- Get memory before
     start_time = time.time()
     mem_delta_mb = None
     peak_mem_mb = start_mem_mb
     hook_manager = None
-
+    
     try:
         urls = [('https://' + url) if not url.startswith(('http://', 'https://')) and not url.startswith(("raw:", "raw://")) else url for url in urls]
         browser_config = BrowserConfig.load(browser_config)
@@ -580,16 +614,7 @@ async def handle_crawl_request(
             "server_memory_delta_mb": mem_delta_mb,
             "server_peak_memory_mb": peak_mem_mb
         }
-
-        # Track request completion
-        try:
-            from monitor import get_monitor
-            await get_monitor().track_request_end(
-                request_id, success=True, pool_hit=True, status_code=200
-            )
-        except:
-            pass
-
+        
         # Add hooks information if hooks were used
         if hooks_config and hook_manager:
             from hook_manager import UserHookManager
@@ -618,16 +643,6 @@ async def handle_crawl_request(
 
     except Exception as e:
         logger.error(f"Crawl error: {str(e)}", exc_info=True)
-
-        # Track request error
-        try:
-            from monitor import get_monitor
-            await get_monitor().track_request_end(
-                request_id, success=False, error=str(e), status_code=500
-            )
-        except:
-            pass
-
         if 'crawler' in locals() and crawler.ready: # Check if crawler was initialized and started
             #  try:
             #      await crawler.close()
@@ -723,6 +738,7 @@ 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 +746,24 @@ 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 +777,17 @@ 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 +795,15 @@ 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

@@ -3,7 +3,7 @@ app:
   title: "Crawl4AI API"
   version: "1.0.0"
   host: "0.0.0.0"
-  port: 11235
+  port: 11234
   reload: False
   workers: 1
   timeout_keep_alive: 300
@@ -61,7 +61,7 @@ crawler:
     batch_process: 300.0  # Timeout for batch processing
   pool:
     max_pages: 40                          # ← GLOBAL_SEM permits
-    idle_ttl_sec: 300                     # ← 30 min janitor cutoff
+    idle_ttl_sec: 1800                     # ← 30 min janitor cutoff
   browser:
     kwargs:
       headless: true
@@ -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/crawler_pool.py

@@ -1,170 +1,60 @@
-# crawler_pool.py - Smart browser pool with tiered management
-import asyncio, json, hashlib, time
+# crawler_pool.py  (new file)
+import asyncio, json, hashlib, time, psutil
 from contextlib import suppress
-from typing import Dict, Optional
+from typing import Dict
 from crawl4ai import AsyncWebCrawler, BrowserConfig
-from utils import load_config, get_container_memory_percent
-import logging
+from typing import Dict
+from utils import load_config 
 
-logger = logging.getLogger(__name__)
 CONFIG = load_config()
 
-# Pool tiers
-PERMANENT: Optional[AsyncWebCrawler] = None  # Always-ready default browser
-HOT_POOL: Dict[str, AsyncWebCrawler] = {}    # Frequent configs
-COLD_POOL: Dict[str, AsyncWebCrawler] = {}   # Rare configs
+POOL: Dict[str, AsyncWebCrawler] = {}
 LAST_USED: Dict[str, float] = {}
-USAGE_COUNT: Dict[str, int] = {}
 LOCK = asyncio.Lock()
 
-# Config
-MEM_LIMIT = CONFIG.get("crawler", {}).get("memory_threshold_percent", 95.0)
-BASE_IDLE_TTL = CONFIG.get("crawler", {}).get("pool", {}).get("idle_ttl_sec", 300)
-DEFAULT_CONFIG_SIG = None  # Cached sig for default config
+MEM_LIMIT  = CONFIG.get("crawler", {}).get("memory_threshold_percent", 95.0)   # % RAM – refuse new browsers above this
+IDLE_TTL  = CONFIG.get("crawler", {}).get("pool", {}).get("idle_ttl_sec", 1800)   # close if unused for 30 min
 
 def _sig(cfg: BrowserConfig) -> str:
-    """Generate config signature."""
     payload = json.dumps(cfg.to_dict(), sort_keys=True, separators=(",",":"))
     return hashlib.sha1(payload.encode()).hexdigest()
 
-def _is_default_config(sig: str) -> bool:
-    """Check if config matches default."""
-    return sig == DEFAULT_CONFIG_SIG
-
 async def get_crawler(cfg: BrowserConfig) -> AsyncWebCrawler:
-    """Get crawler from pool with tiered strategy."""
-    sig = _sig(cfg)
-    async with LOCK:
-        # Check permanent browser for default config
-        if PERMANENT and _is_default_config(sig):
+    try:
+        sig = _sig(cfg)
+        async with LOCK:
+            if sig in POOL:
+                LAST_USED[sig] = time.time();  
+                return POOL[sig]
+            if psutil.virtual_memory().percent >= MEM_LIMIT:
+                raise MemoryError("RAM pressure – new browser denied")
+            crawler = AsyncWebCrawler(config=cfg, thread_safe=False)
+            await crawler.start()
+            POOL[sig] = crawler; LAST_USED[sig] = time.time()
+            return crawler
+    except MemoryError as e:
+        raise MemoryError(f"RAM pressure – new browser denied: {e}")
+    except Exception as e:
+        raise RuntimeError(f"Failed to start browser: {e}")
+    finally:
+        if sig in POOL:
             LAST_USED[sig] = time.time()
-            USAGE_COUNT[sig] = USAGE_COUNT.get(sig, 0) + 1
-            logger.info("🔥 Using permanent browser")
-            return PERMANENT
-
-        # Check hot pool
-        if sig in HOT_POOL:
-            LAST_USED[sig] = time.time()
-            USAGE_COUNT[sig] = USAGE_COUNT.get(sig, 0) + 1
-            logger.info(f"♨️  Using hot pool browser (sig={sig[:8]})")
-            return HOT_POOL[sig]
-
-        # Check cold pool (promote to hot if used 3+ times)
-        if sig in COLD_POOL:
-            LAST_USED[sig] = time.time()
-            USAGE_COUNT[sig] = USAGE_COUNT.get(sig, 0) + 1
-
-            if USAGE_COUNT[sig] >= 3:
-                logger.info(f"⬆️  Promoting to hot pool (sig={sig[:8]}, count={USAGE_COUNT[sig]})")
-                HOT_POOL[sig] = COLD_POOL.pop(sig)
-
-                # Track promotion in monitor
-                try:
-                    from monitor import get_monitor
-                    await get_monitor().track_janitor_event("promote", sig, {"count": USAGE_COUNT[sig]})
-                except:
-                    pass
-
-                return HOT_POOL[sig]
-
-            logger.info(f"❄️  Using cold pool browser (sig={sig[:8]})")
-            return COLD_POOL[sig]
-
-        # Memory check before creating new
-        mem_pct = get_container_memory_percent()
-        if mem_pct >= MEM_LIMIT:
-            logger.error(f"💥 Memory pressure: {mem_pct:.1f}% >= {MEM_LIMIT}%")
-            raise MemoryError(f"Memory at {mem_pct:.1f}%, refusing new browser")
-
-        # Create new in cold pool
-        logger.info(f"🆕 Creating new browser in cold pool (sig={sig[:8]}, mem={mem_pct:.1f}%)")
-        crawler = AsyncWebCrawler(config=cfg, thread_safe=False)
-        await crawler.start()
-        COLD_POOL[sig] = crawler
-        LAST_USED[sig] = time.time()
-        USAGE_COUNT[sig] = 1
-        return crawler
-
-async def init_permanent(cfg: BrowserConfig):
-    """Initialize permanent default browser."""
-    global PERMANENT, DEFAULT_CONFIG_SIG
-    async with LOCK:
-        if PERMANENT:
-            return
-        DEFAULT_CONFIG_SIG = _sig(cfg)
-        logger.info("🔥 Creating permanent default browser")
-        PERMANENT = AsyncWebCrawler(config=cfg, thread_safe=False)
-        await PERMANENT.start()
-        LAST_USED[DEFAULT_CONFIG_SIG] = time.time()
-        USAGE_COUNT[DEFAULT_CONFIG_SIG] = 0
-
+        else:
+            # If we failed to start the browser, we should remove it from the pool
+            POOL.pop(sig, None)
+            LAST_USED.pop(sig, None)
+        # If we failed to start the browser, we should remove it from the pool
 async def close_all():
-    """Close all browsers."""
     async with LOCK:
-        tasks = []
-        if PERMANENT:
-            tasks.append(PERMANENT.close())
-        tasks.extend([c.close() for c in HOT_POOL.values()])
-        tasks.extend([c.close() for c in COLD_POOL.values()])
-        await asyncio.gather(*tasks, return_exceptions=True)
-        HOT_POOL.clear()
-        COLD_POOL.clear()
-        LAST_USED.clear()
-        USAGE_COUNT.clear()
+        await asyncio.gather(*(c.close() for c in POOL.values()), return_exceptions=True)
+        POOL.clear(); LAST_USED.clear()
 
 async def janitor():
-    """Adaptive cleanup based on memory pressure."""
     while True:
-        mem_pct = get_container_memory_percent()
-
-        # Adaptive intervals and TTLs
-        if mem_pct > 80:
-            interval, cold_ttl, hot_ttl = 10, 30, 120
-        elif mem_pct > 60:
-            interval, cold_ttl, hot_ttl = 30, 60, 300
-        else:
-            interval, cold_ttl, hot_ttl = 60, BASE_IDLE_TTL, BASE_IDLE_TTL * 2
-
-        await asyncio.sleep(interval)
-
+        await asyncio.sleep(60)
         now = time.time()
         async with LOCK:
-            # Clean cold pool
-            for sig in list(COLD_POOL.keys()):
-                if now - LAST_USED.get(sig, now) > cold_ttl:
-                    idle_time = now - LAST_USED[sig]
-                    logger.info(f"🧹 Closing cold browser (sig={sig[:8]}, idle={idle_time:.0f}s)")
-                    with suppress(Exception):
-                        await COLD_POOL[sig].close()
-                    COLD_POOL.pop(sig, None)
-                    LAST_USED.pop(sig, None)
-                    USAGE_COUNT.pop(sig, None)
-
-                    # Track in monitor
-                    try:
-                        from monitor import get_monitor
-                        await get_monitor().track_janitor_event("close_cold", sig, {"idle_seconds": int(idle_time), "ttl": cold_ttl})
-                    except:
-                        pass
-
-            # Clean hot pool (more conservative)
-            for sig in list(HOT_POOL.keys()):
-                if now - LAST_USED.get(sig, now) > hot_ttl:
-                    idle_time = now - LAST_USED[sig]
-                    logger.info(f"🧹 Closing hot browser (sig={sig[:8]}, idle={idle_time:.0f}s)")
-                    with suppress(Exception):
-                        await HOT_POOL[sig].close()
-                    HOT_POOL.pop(sig, None)
-                    LAST_USED.pop(sig, None)
-                    USAGE_COUNT.pop(sig, None)
-
-                    # Track in monitor
-                    try:
-                        from monitor import get_monitor
-                        await get_monitor().track_janitor_event("close_hot", sig, {"idle_seconds": int(idle_time), "ttl": hot_ttl})
-                    except:
-                        pass
-
-            # Log pool stats
-            if mem_pct > 60:
-                logger.info(f"📊 Pool: hot={len(HOT_POOL)}, cold={len(COLD_POOL)}, mem={mem_pct:.1f}%")
+            for sig, crawler in list(POOL.items()):
+                if now - LAST_USED[sig] > IDLE_TTL:
+                    with suppress(Exception): await crawler.close()
+                    POOL.pop(sig, None); LAST_USED.pop(sig, None)

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/monitor.py

@@ -1,382 +0,0 @@
-# monitor.py - Real-time monitoring stats with Redis persistence
-import time
-import json
-import asyncio
-from typing import Dict, List, Optional
-from datetime import datetime, timezone
-from collections import deque
-from redis import asyncio as aioredis
-from utils import get_container_memory_percent
-import psutil
-import logging
-
-logger = logging.getLogger(__name__)
-
-class MonitorStats:
-    """Tracks real-time server stats with Redis persistence."""
-
-    def __init__(self, redis: aioredis.Redis):
-        self.redis = redis
-        self.start_time = time.time()
-
-        # In-memory queues (fast reads, Redis backup)
-        self.active_requests: Dict[str, Dict] = {}  # id -> request info
-        self.completed_requests: deque = deque(maxlen=100)  # Last 100
-        self.janitor_events: deque = deque(maxlen=100)
-        self.errors: deque = deque(maxlen=100)
-
-        # Endpoint stats (persisted in Redis)
-        self.endpoint_stats: Dict[str, Dict] = {}  # endpoint -> {count, total_time, errors, ...}
-
-        # Background persistence queue (max 10 pending persist requests)
-        self._persist_queue: asyncio.Queue = asyncio.Queue(maxsize=10)
-        self._persist_worker_task: Optional[asyncio.Task] = None
-
-        # Timeline data (5min window, 5s resolution = 60 points)
-        self.memory_timeline: deque = deque(maxlen=60)
-        self.requests_timeline: deque = deque(maxlen=60)
-        self.browser_timeline: deque = deque(maxlen=60)
-
-    async def track_request_start(self, request_id: str, endpoint: str, url: str, config: Dict = None):
-        """Track new request start."""
-        req_info = {
-            "id": request_id,
-            "endpoint": endpoint,
-            "url": url[:100],  # Truncate long URLs
-            "start_time": time.time(),
-            "config_sig": config.get("sig", "default") if config else "default",
-            "mem_start": psutil.Process().memory_info().rss / (1024 * 1024)
-        }
-        self.active_requests[request_id] = req_info
-
-        # Increment endpoint counter
-        if endpoint not in self.endpoint_stats:
-            self.endpoint_stats[endpoint] = {
-                "count": 0, "total_time": 0, "errors": 0,
-                "pool_hits": 0, "success": 0
-            }
-        self.endpoint_stats[endpoint]["count"] += 1
-
-        # Queue persistence (handled by background worker)
-        try:
-            self._persist_queue.put_nowait(True)
-        except asyncio.QueueFull:
-            logger.warning("Persistence queue full, skipping")
-
-    async def track_request_end(self, request_id: str, success: bool, error: str = None,
-                               pool_hit: bool = True, status_code: int = 200):
-        """Track request completion."""
-        if request_id not in self.active_requests:
-            return
-
-        req_info = self.active_requests.pop(request_id)
-        end_time = time.time()
-        elapsed = end_time - req_info["start_time"]
-        mem_end = psutil.Process().memory_info().rss / (1024 * 1024)
-        mem_delta = mem_end - req_info["mem_start"]
-
-        # Update stats
-        endpoint = req_info["endpoint"]
-        if endpoint in self.endpoint_stats:
-            self.endpoint_stats[endpoint]["total_time"] += elapsed
-            if success:
-                self.endpoint_stats[endpoint]["success"] += 1
-            else:
-                self.endpoint_stats[endpoint]["errors"] += 1
-            if pool_hit:
-                self.endpoint_stats[endpoint]["pool_hits"] += 1
-
-        # Add to completed queue
-        completed = {
-            **req_info,
-            "end_time": end_time,
-            "elapsed": round(elapsed, 2),
-            "mem_delta": round(mem_delta, 1),
-            "success": success,
-            "error": error,
-            "status_code": status_code,
-            "pool_hit": pool_hit
-        }
-        self.completed_requests.append(completed)
-
-        # Track errors
-        if not success and error:
-            self.errors.append({
-                "timestamp": end_time,
-                "endpoint": endpoint,
-                "url": req_info["url"],
-                "error": error,
-                "request_id": request_id
-            })
-
-        await self._persist_endpoint_stats()
-
-    async def track_janitor_event(self, event_type: str, sig: str, details: Dict):
-        """Track janitor cleanup events."""
-        self.janitor_events.append({
-            "timestamp": time.time(),
-            "type": event_type,  # "close_cold", "close_hot", "promote"
-            "sig": sig[:8],
-            "details": details
-        })
-
-    def _cleanup_old_entries(self, max_age_seconds: int = 300):
-        """Remove entries older than max_age_seconds (default 5min)."""
-        now = time.time()
-        cutoff = now - max_age_seconds
-
-        # Clean completed requests
-        while self.completed_requests and self.completed_requests[0].get("end_time", 0) < cutoff:
-            self.completed_requests.popleft()
-
-        # Clean janitor events
-        while self.janitor_events and self.janitor_events[0].get("timestamp", 0) < cutoff:
-            self.janitor_events.popleft()
-
-        # Clean errors
-        while self.errors and self.errors[0].get("timestamp", 0) < cutoff:
-            self.errors.popleft()
-
-    async def update_timeline(self):
-        """Update timeline data points (called every 5s)."""
-        now = time.time()
-        mem_pct = get_container_memory_percent()
-
-        # Clean old entries (keep last 5 minutes)
-        self._cleanup_old_entries(max_age_seconds=300)
-
-        # Count requests in last 5s
-        recent_reqs = sum(1 for req in self.completed_requests
-                         if now - req.get("end_time", 0) < 5)
-
-        # Browser counts (acquire lock to prevent race conditions)
-        from crawler_pool import PERMANENT, HOT_POOL, COLD_POOL, LOCK
-        async with LOCK:
-            browser_count = {
-                "permanent": 1 if PERMANENT else 0,
-                "hot": len(HOT_POOL),
-                "cold": len(COLD_POOL)
-            }
-
-        self.memory_timeline.append({"time": now, "value": mem_pct})
-        self.requests_timeline.append({"time": now, "value": recent_reqs})
-        self.browser_timeline.append({"time": now, "browsers": browser_count})
-
-    async def _persist_endpoint_stats(self):
-        """Persist endpoint stats to Redis."""
-        try:
-            await self.redis.set(
-                "monitor:endpoint_stats",
-                json.dumps(self.endpoint_stats),
-                ex=86400  # 24h TTL
-            )
-        except Exception as e:
-            logger.warning(f"Failed to persist endpoint stats: {e}")
-
-    async def _persistence_worker(self):
-        """Background worker to persist stats to Redis."""
-        while True:
-            try:
-                await self._persist_queue.get()
-                await self._persist_endpoint_stats()
-                self._persist_queue.task_done()
-            except asyncio.CancelledError:
-                break
-            except Exception as e:
-                logger.error(f"Persistence worker error: {e}")
-
-    def start_persistence_worker(self):
-        """Start the background persistence worker."""
-        if not self._persist_worker_task:
-            self._persist_worker_task = asyncio.create_task(self._persistence_worker())
-            logger.info("Started persistence worker")
-
-    async def stop_persistence_worker(self):
-        """Stop the background persistence worker."""
-        if self._persist_worker_task:
-            self._persist_worker_task.cancel()
-            try:
-                await self._persist_worker_task
-            except asyncio.CancelledError:
-                pass
-            self._persist_worker_task = None
-            logger.info("Stopped persistence worker")
-
-    async def cleanup(self):
-        """Cleanup on shutdown - persist final stats and stop workers."""
-        logger.info("Monitor cleanup starting...")
-        try:
-            # Persist final stats before shutdown
-            await self._persist_endpoint_stats()
-            # Stop background worker
-            await self.stop_persistence_worker()
-            logger.info("Monitor cleanup completed")
-        except Exception as e:
-            logger.error(f"Monitor cleanup error: {e}")
-
-    async def load_from_redis(self):
-        """Load persisted stats from Redis."""
-        try:
-            data = await self.redis.get("monitor:endpoint_stats")
-            if data:
-                self.endpoint_stats = json.loads(data)
-                logger.info("Loaded endpoint stats from Redis")
-        except Exception as e:
-            logger.warning(f"Failed to load from Redis: {e}")
-
-    async def get_health_summary(self) -> Dict:
-        """Get current system health snapshot."""
-        mem_pct = get_container_memory_percent()
-        cpu_pct = psutil.cpu_percent(interval=0.1)
-
-        # Network I/O (delta since last call)
-        net = psutil.net_io_counters()
-
-        # Pool status (acquire lock to prevent race conditions)
-        from crawler_pool import PERMANENT, HOT_POOL, COLD_POOL, LOCK
-        async with LOCK:
-            # TODO: Track actual browser process memory instead of estimates
-            # These are conservative estimates based on typical Chromium usage
-            permanent_mem = 270 if PERMANENT else 0  # Estimate: ~270MB for permanent browser
-            hot_mem = len(HOT_POOL) * 180  # Estimate: ~180MB per hot pool browser
-            cold_mem = len(COLD_POOL) * 180  # Estimate: ~180MB per cold pool browser
-            permanent_active = PERMANENT is not None
-            hot_count = len(HOT_POOL)
-            cold_count = len(COLD_POOL)
-
-        return {
-            "container": {
-                "memory_percent": round(mem_pct, 1),
-                "cpu_percent": round(cpu_pct, 1),
-                "network_sent_mb": round(net.bytes_sent / (1024**2), 2),
-                "network_recv_mb": round(net.bytes_recv / (1024**2), 2),
-                "uptime_seconds": int(time.time() - self.start_time)
-            },
-            "pool": {
-                "permanent": {"active": permanent_active, "memory_mb": permanent_mem},
-                "hot": {"count": hot_count, "memory_mb": hot_mem},
-                "cold": {"count": cold_count, "memory_mb": cold_mem},
-                "total_memory_mb": permanent_mem + hot_mem + cold_mem
-            },
-            "janitor": {
-                "next_cleanup_estimate": "adaptive",  # Would need janitor state
-                "memory_pressure": "LOW" if mem_pct < 60 else "MEDIUM" if mem_pct < 80 else "HIGH"
-            }
-        }
-
-    def get_active_requests(self) -> List[Dict]:
-        """Get list of currently active requests."""
-        now = time.time()
-        return [
-            {
-                **req,
-                "elapsed": round(now - req["start_time"], 1),
-                "status": "running"
-            }
-            for req in self.active_requests.values()
-        ]
-
-    def get_completed_requests(self, limit: int = 50, filter_status: str = "all") -> List[Dict]:
-        """Get recent completed requests."""
-        requests = list(self.completed_requests)[-limit:]
-        if filter_status == "success":
-            requests = [r for r in requests if r.get("success")]
-        elif filter_status == "error":
-            requests = [r for r in requests if not r.get("success")]
-        return requests
-
-    async def get_browser_list(self) -> List[Dict]:
-        """Get detailed browser pool information."""
-        from crawler_pool import PERMANENT, HOT_POOL, COLD_POOL, LAST_USED, USAGE_COUNT, DEFAULT_CONFIG_SIG, LOCK
-
-        browsers = []
-        now = time.time()
-
-        # Acquire lock to prevent race conditions during iteration
-        async with LOCK:
-            if PERMANENT:
-                browsers.append({
-                    "type": "permanent",
-                    "sig": DEFAULT_CONFIG_SIG[:8] if DEFAULT_CONFIG_SIG else "unknown",
-                    "age_seconds": int(now - self.start_time),
-                    "last_used_seconds": int(now - LAST_USED.get(DEFAULT_CONFIG_SIG, now)),
-                    "memory_mb": 270,
-                    "hits": USAGE_COUNT.get(DEFAULT_CONFIG_SIG, 0),
-                    "killable": False
-                })
-
-            for sig, crawler in HOT_POOL.items():
-                browsers.append({
-                    "type": "hot",
-                    "sig": sig[:8],
-                    "age_seconds": int(now - self.start_time),  # Approximation
-                    "last_used_seconds": int(now - LAST_USED.get(sig, now)),
-                    "memory_mb": 180,  # Estimate
-                    "hits": USAGE_COUNT.get(sig, 0),
-                    "killable": True
-                })
-
-            for sig, crawler in COLD_POOL.items():
-                browsers.append({
-                    "type": "cold",
-                    "sig": sig[:8],
-                    "age_seconds": int(now - self.start_time),
-                    "last_used_seconds": int(now - LAST_USED.get(sig, now)),
-                    "memory_mb": 180,
-                    "hits": USAGE_COUNT.get(sig, 0),
-                    "killable": True
-                })
-
-        return browsers
-
-    def get_endpoint_stats_summary(self) -> Dict[str, Dict]:
-        """Get aggregated endpoint statistics."""
-        summary = {}
-        for endpoint, stats in self.endpoint_stats.items():
-            count = stats["count"]
-            avg_time = (stats["total_time"] / count) if count > 0 else 0
-            success_rate = (stats["success"] / count * 100) if count > 0 else 0
-            pool_hit_rate = (stats["pool_hits"] / count * 100) if count > 0 else 0
-
-            summary[endpoint] = {
-                "count": count,
-                "avg_latency_ms": round(avg_time * 1000, 1),
-                "success_rate_percent": round(success_rate, 1),
-                "pool_hit_rate_percent": round(pool_hit_rate, 1),
-                "errors": stats["errors"]
-            }
-        return summary
-
-    def get_timeline_data(self, metric: str, window: str = "5m") -> Dict:
-        """Get timeline data for charts."""
-        # For now, only 5m window supported
-        if metric == "memory":
-            data = list(self.memory_timeline)
-        elif metric == "requests":
-            data = list(self.requests_timeline)
-        elif metric == "browsers":
-            data = list(self.browser_timeline)
-        else:
-            return {"timestamps": [], "values": []}
-
-        return {
-            "timestamps": [int(d["time"]) for d in data],
-            "values": [d.get("value", d.get("browsers")) for d in data]
-        }
-
-    def get_janitor_log(self, limit: int = 100) -> List[Dict]:
-        """Get recent janitor events."""
-        return list(self.janitor_events)[-limit:]
-
-    def get_errors_log(self, limit: int = 100) -> List[Dict]:
-        """Get recent errors."""
-        return list(self.errors)[-limit:]
-
-# Global instance (initialized in server.py)
-monitor_stats: Optional[MonitorStats] = None
-
-def get_monitor() -> MonitorStats:
-    """Get global monitor instance."""
-    if monitor_stats is None:
-        raise RuntimeError("Monitor not initialized")
-    return monitor_stats

deploy/docker/monitor_routes.py

@@ -1,405 +0,0 @@
-# monitor_routes.py - Monitor API endpoints
-from fastapi import APIRouter, HTTPException, WebSocket, WebSocketDisconnect
-from pydantic import BaseModel
-from typing import Optional
-from monitor import get_monitor
-import logging
-import asyncio
-import json
-
-logger = logging.getLogger(__name__)
-router = APIRouter(prefix="/monitor", tags=["monitor"])
-
-
-@router.get("/health")
-async def get_health():
-    """Get current system health snapshot."""
-    try:
-        monitor = get_monitor()
-        return await monitor.get_health_summary()
-    except Exception as e:
-        logger.error(f"Error getting health: {e}")
-        raise HTTPException(500, str(e))
-
-
-@router.get("/requests")
-async def get_requests(status: str = "all", limit: int = 50):
-    """Get active and completed requests.
-
-    Args:
-        status: Filter by 'active', 'completed', 'success', 'error', or 'all'
-        limit: Max number of completed requests to return (default 50)
-    """
-    # Input validation
-    if status not in ["all", "active", "completed", "success", "error"]:
-        raise HTTPException(400, f"Invalid status: {status}. Must be one of: all, active, completed, success, error")
-    if limit < 1 or limit > 1000:
-        raise HTTPException(400, f"Invalid limit: {limit}. Must be between 1 and 1000")
-
-    try:
-        monitor = get_monitor()
-
-        if status == "active":
-            return {"active": monitor.get_active_requests(), "completed": []}
-        elif status == "completed":
-            return {"active": [], "completed": monitor.get_completed_requests(limit)}
-        elif status in ["success", "error"]:
-            return {"active": [], "completed": monitor.get_completed_requests(limit, status)}
-        else:  # "all"
-            return {
-                "active": monitor.get_active_requests(),
-                "completed": monitor.get_completed_requests(limit)
-            }
-    except Exception as e:
-        logger.error(f"Error getting requests: {e}")
-        raise HTTPException(500, str(e))
-
-
-@router.get("/browsers")
-async def get_browsers():
-    """Get detailed browser pool information."""
-    try:
-        monitor = get_monitor()
-        browsers = await monitor.get_browser_list()
-
-        # Calculate summary stats
-        total_browsers = len(browsers)
-        total_memory = sum(b["memory_mb"] for b in browsers)
-
-        # Calculate reuse rate from recent requests
-        recent = monitor.get_completed_requests(100)
-        pool_hits = sum(1 for r in recent if r.get("pool_hit", False))
-        reuse_rate = (pool_hits / len(recent) * 100) if recent else 0
-
-        return {
-            "browsers": browsers,
-            "summary": {
-                "total_count": total_browsers,
-                "total_memory_mb": total_memory,
-                "reuse_rate_percent": round(reuse_rate, 1)
-            }
-        }
-    except Exception as e:
-        logger.error(f"Error getting browsers: {e}")
-        raise HTTPException(500, str(e))
-
-
-@router.get("/endpoints/stats")
-async def get_endpoint_stats():
-    """Get aggregated endpoint statistics."""
-    try:
-        monitor = get_monitor()
-        return monitor.get_endpoint_stats_summary()
-    except Exception as e:
-        logger.error(f"Error getting endpoint stats: {e}")
-        raise HTTPException(500, str(e))
-
-
-@router.get("/timeline")
-async def get_timeline(metric: str = "memory", window: str = "5m"):
-    """Get timeline data for charts.
-
-    Args:
-        metric: 'memory', 'requests', or 'browsers'
-        window: Time window (only '5m' supported for now)
-    """
-    # Input validation
-    if metric not in ["memory", "requests", "browsers"]:
-        raise HTTPException(400, f"Invalid metric: {metric}. Must be one of: memory, requests, browsers")
-    if window != "5m":
-        raise HTTPException(400, f"Invalid window: {window}. Only '5m' is currently supported")
-
-    try:
-        monitor = get_monitor()
-        return monitor.get_timeline_data(metric, window)
-    except Exception as e:
-        logger.error(f"Error getting timeline: {e}")
-        raise HTTPException(500, str(e))
-
-
-@router.get("/logs/janitor")
-async def get_janitor_log(limit: int = 100):
-    """Get recent janitor cleanup events."""
-    # Input validation
-    if limit < 1 or limit > 1000:
-        raise HTTPException(400, f"Invalid limit: {limit}. Must be between 1 and 1000")
-
-    try:
-        monitor = get_monitor()
-        return {"events": monitor.get_janitor_log(limit)}
-    except Exception as e:
-        logger.error(f"Error getting janitor log: {e}")
-        raise HTTPException(500, str(e))
-
-
-@router.get("/logs/errors")
-async def get_errors_log(limit: int = 100):
-    """Get recent errors."""
-    # Input validation
-    if limit < 1 or limit > 1000:
-        raise HTTPException(400, f"Invalid limit: {limit}. Must be between 1 and 1000")
-
-    try:
-        monitor = get_monitor()
-        return {"errors": monitor.get_errors_log(limit)}
-    except Exception as e:
-        logger.error(f"Error getting errors log: {e}")
-        raise HTTPException(500, str(e))
-
-
-# ========== Control Actions ==========
-
-class KillBrowserRequest(BaseModel):
-    sig: str
-
-
-@router.post("/actions/cleanup")
-async def force_cleanup():
-    """Force immediate janitor cleanup (kills idle cold pool browsers)."""
-    try:
-        from crawler_pool import COLD_POOL, LAST_USED, USAGE_COUNT, LOCK
-        import time
-        from contextlib import suppress
-
-        killed_count = 0
-        now = time.time()
-
-        async with LOCK:
-            for sig in list(COLD_POOL.keys()):
-                # Kill all cold pool browsers immediately
-                logger.info(f"🧹 Force cleanup: closing cold browser (sig={sig[:8]})")
-                with suppress(Exception):
-                    await COLD_POOL[sig].close()
-                COLD_POOL.pop(sig, None)
-                LAST_USED.pop(sig, None)
-                USAGE_COUNT.pop(sig, None)
-                killed_count += 1
-
-        monitor = get_monitor()
-        await monitor.track_janitor_event("force_cleanup", "manual", {"killed": killed_count})
-
-        return {"success": True, "killed_browsers": killed_count}
-    except Exception as e:
-        logger.error(f"Error during force cleanup: {e}")
-        raise HTTPException(500, str(e))
-
-
-@router.post("/actions/kill_browser")
-async def kill_browser(req: KillBrowserRequest):
-    """Kill a specific browser by signature (hot or cold only).
-
-    Args:
-        sig: Browser config signature (first 8 chars)
-    """
-    try:
-        from crawler_pool import HOT_POOL, COLD_POOL, LAST_USED, USAGE_COUNT, LOCK, DEFAULT_CONFIG_SIG
-        from contextlib import suppress
-
-        # Find full signature matching prefix
-        target_sig = None
-        pool_type = None
-
-        async with LOCK:
-            # Check hot pool
-            for sig in HOT_POOL.keys():
-                if sig.startswith(req.sig):
-                    target_sig = sig
-                    pool_type = "hot"
-                    break
-
-            # Check cold pool
-            if not target_sig:
-                for sig in COLD_POOL.keys():
-                    if sig.startswith(req.sig):
-                        target_sig = sig
-                        pool_type = "cold"
-                        break
-
-            # Check if trying to kill permanent
-            if DEFAULT_CONFIG_SIG and DEFAULT_CONFIG_SIG.startswith(req.sig):
-                raise HTTPException(403, "Cannot kill permanent browser. Use restart instead.")
-
-            if not target_sig:
-                raise HTTPException(404, f"Browser with sig={req.sig} not found")
-
-            # Warn if there are active requests (browser might be in use)
-            monitor = get_monitor()
-            active_count = len(monitor.get_active_requests())
-            if active_count > 0:
-                logger.warning(f"Killing browser {target_sig[:8]} while {active_count} requests are active - may cause failures")
-
-            # Kill the browser
-            if pool_type == "hot":
-                browser = HOT_POOL.pop(target_sig)
-            else:
-                browser = COLD_POOL.pop(target_sig)
-
-            with suppress(Exception):
-                await browser.close()
-
-            LAST_USED.pop(target_sig, None)
-            USAGE_COUNT.pop(target_sig, None)
-
-        logger.info(f"🔪 Killed {pool_type} browser (sig={target_sig[:8]})")
-
-        monitor = get_monitor()
-        await monitor.track_janitor_event("kill_browser", target_sig, {"pool": pool_type, "manual": True})
-
-        return {"success": True, "killed_sig": target_sig[:8], "pool_type": pool_type}
-    except HTTPException:
-        raise
-    except Exception as e:
-        logger.error(f"Error killing browser: {e}")
-        raise HTTPException(500, str(e))
-
-
-@router.post("/actions/restart_browser")
-async def restart_browser(req: KillBrowserRequest):
-    """Restart a browser (kill + recreate). Works for permanent too.
-
-    Args:
-        sig: Browser config signature (first 8 chars), or "permanent"
-    """
-    try:
-        from crawler_pool import (PERMANENT, HOT_POOL, COLD_POOL, LAST_USED,
-                                  USAGE_COUNT, LOCK, DEFAULT_CONFIG_SIG, init_permanent)
-        from crawl4ai import AsyncWebCrawler, BrowserConfig
-        from contextlib import suppress
-        import time
-
-        # Handle permanent browser restart
-        if req.sig == "permanent" or (DEFAULT_CONFIG_SIG and DEFAULT_CONFIG_SIG.startswith(req.sig)):
-            async with LOCK:
-                if PERMANENT:
-                    with suppress(Exception):
-                        await PERMANENT.close()
-
-                # Reinitialize permanent
-                from utils import load_config
-                config = load_config()
-                await init_permanent(BrowserConfig(
-                    extra_args=config["crawler"]["browser"].get("extra_args", []),
-                    **config["crawler"]["browser"].get("kwargs", {}),
-                ))
-
-            logger.info("🔄 Restarted permanent browser")
-            return {"success": True, "restarted": "permanent"}
-
-        # Handle hot/cold browser restart
-        target_sig = None
-        pool_type = None
-        browser_config = None
-
-        async with LOCK:
-            # Find browser
-            for sig in HOT_POOL.keys():
-                if sig.startswith(req.sig):
-                    target_sig = sig
-                    pool_type = "hot"
-                    # Would need to reconstruct config (not stored currently)
-                    break
-
-            if not target_sig:
-                for sig in COLD_POOL.keys():
-                    if sig.startswith(req.sig):
-                        target_sig = sig
-                        pool_type = "cold"
-                        break
-
-            if not target_sig:
-                raise HTTPException(404, f"Browser with sig={req.sig} not found")
-
-            # Kill existing
-            if pool_type == "hot":
-                browser = HOT_POOL.pop(target_sig)
-            else:
-                browser = COLD_POOL.pop(target_sig)
-
-            with suppress(Exception):
-                await browser.close()
-
-            # Note: We can't easily recreate with same config without storing it
-            # For now, just kill and let new requests create fresh ones
-            LAST_USED.pop(target_sig, None)
-            USAGE_COUNT.pop(target_sig, None)
-
-        logger.info(f"🔄 Restarted {pool_type} browser (sig={target_sig[:8]})")
-
-        monitor = get_monitor()
-        await monitor.track_janitor_event("restart_browser", target_sig, {"pool": pool_type})
-
-        return {"success": True, "restarted_sig": target_sig[:8], "note": "Browser will be recreated on next request"}
-    except HTTPException:
-        raise
-    except Exception as e:
-        logger.error(f"Error restarting browser: {e}")
-        raise HTTPException(500, str(e))
-
-
-@router.post("/stats/reset")
-async def reset_stats():
-    """Reset today's endpoint counters."""
-    try:
-        monitor = get_monitor()
-        monitor.endpoint_stats.clear()
-        await monitor._persist_endpoint_stats()
-
-        return {"success": True, "message": "Endpoint stats reset"}
-    except Exception as e:
-        logger.error(f"Error resetting stats: {e}")
-        raise HTTPException(500, str(e))
-
-
-@router.websocket("/ws")
-async def websocket_endpoint(websocket: WebSocket):
-    """WebSocket endpoint for real-time monitoring updates.
-
-    Sends updates every 2 seconds with:
-    - Health stats
-    - Active/completed requests
-    - Browser pool status
-    - Timeline data
-    """
-    await websocket.accept()
-    logger.info("WebSocket client connected")
-
-    try:
-        while True:
-            try:
-                # Gather all monitoring data
-                monitor = get_monitor()
-
-                data = {
-                    "timestamp": asyncio.get_event_loop().time(),
-                    "health": await monitor.get_health_summary(),
-                    "requests": {
-                        "active": monitor.get_active_requests(),
-                        "completed": monitor.get_completed_requests(limit=10)
-                    },
-                    "browsers": await monitor.get_browser_list(),
-                    "timeline": {
-                        "memory": monitor.get_timeline_data("memory", "5m"),
-                        "requests": monitor.get_timeline_data("requests", "5m"),
-                        "browsers": monitor.get_timeline_data("browsers", "5m")
-                    },
-                    "janitor": monitor.get_janitor_log(limit=10),
-                    "errors": monitor.get_errors_log(limit=10)
-                }
-
-                # Send update to client
-                await websocket.send_json(data)
-
-                # Wait 2 seconds before next update
-                await asyncio.sleep(2)
-
-            except WebSocketDisconnect:
-                logger.info("WebSocket client disconnected")
-                break
-            except Exception as e:
-                logger.error(f"WebSocket error: {e}", exc_info=True)
-                await asyncio.sleep(2)  # Continue trying
-
-    except Exception as e:
-        logger.error(f"WebSocket connection error: {e}", exc_info=True)
-    finally:
-        logger.info("WebSocket connection closed")

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/server.py

@@ -16,7 +16,6 @@ from fastapi import Request, Depends
 from fastapi.responses import FileResponse
 import base64
 import re
-import logging
 from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig
 from api import (
     handle_markdown_request, handle_llm_qa,
@@ -79,14 +78,6 @@ __version__ = "0.5.1-d1"
 MAX_PAGES = config["crawler"]["pool"].get("max_pages", 30)
 GLOBAL_SEM = asyncio.Semaphore(MAX_PAGES)
 
-# ── default browser config helper ─────────────────────────────
-def get_default_browser_config() -> BrowserConfig:
-    """Get default BrowserConfig from config.yml."""
-    return BrowserConfig(
-        extra_args=config["crawler"]["browser"].get("extra_args", []),
-        **config["crawler"]["browser"].get("kwargs", {}),
-    )
-
 # import logging
 # page_log = logging.getLogger("page_cap")
 # orig_arun = AsyncWebCrawler.arun
@@ -112,52 +103,15 @@ AsyncWebCrawler.arun = capped_arun
 
 @asynccontextmanager
 async def lifespan(_: FastAPI):
-    from crawler_pool import init_permanent
-    from monitor import MonitorStats
-    import monitor as monitor_module
-
-    # Initialize monitor
-    monitor_module.monitor_stats = MonitorStats(redis)
-    await monitor_module.monitor_stats.load_from_redis()
-    monitor_module.monitor_stats.start_persistence_worker()
-
-    # Initialize browser pool
-    await init_permanent(BrowserConfig(
+    await get_crawler(BrowserConfig(
         extra_args=config["crawler"]["browser"].get("extra_args", []),
         **config["crawler"]["browser"].get("kwargs", {}),
-    ))
-
-    # Start background tasks
-    app.state.janitor = asyncio.create_task(janitor())
-    app.state.timeline_updater = asyncio.create_task(_timeline_updater())
-
+    ))           # warm‑up
+    app.state.janitor = asyncio.create_task(janitor())        # idle GC
     yield
-
-    # Cleanup
     app.state.janitor.cancel()
-    app.state.timeline_updater.cancel()
-
-    # Monitor cleanup (persist stats and stop workers)
-    from monitor import get_monitor
-    try:
-        await get_monitor().cleanup()
-    except Exception as e:
-        logger.error(f"Monitor cleanup failed: {e}")
-
     await close_all()
 
-async def _timeline_updater():
-    """Update timeline data every 5 seconds."""
-    from monitor import get_monitor
-    while True:
-        await asyncio.sleep(5)
-        try:
-            await asyncio.wait_for(get_monitor().update_timeline(), timeout=4.0)
-        except asyncio.TimeoutError:
-            logger.warning("Timeline update timeout after 4s")
-        except Exception as e:
-            logger.warning(f"Timeline update error: {e}")
-
 # ───────────────────── FastAPI instance ──────────────────────
 app = FastAPI(
     title=config["app"]["title"],
@@ -175,25 +129,6 @@ app.mount(
     name="play",
 )
 
-# ── static monitor dashboard ────────────────────────────────
-MONITOR_DIR = pathlib.Path(__file__).parent / "static" / "monitor"
-if not MONITOR_DIR.exists():
-    raise RuntimeError(f"Monitor assets not found at {MONITOR_DIR}")
-app.mount(
-    "/dashboard",
-    StaticFiles(directory=MONITOR_DIR, html=True),
-    name="monitor_ui",
-)
-
-# ── static assets (logo, etc) ────────────────────────────────
-ASSETS_DIR = pathlib.Path(__file__).parent / "static" / "assets"
-if ASSETS_DIR.exists():
-    app.mount(
-        "/static/assets",
-        StaticFiles(directory=ASSETS_DIR),
-        name="assets",
-    )
-
 
 @app.get("/")
 async def root():
@@ -277,12 +212,6 @@ def _safe_eval_config(expr: str) -> dict:
 # ── job router ──────────────────────────────────────────────
 app.include_router(init_job_router(redis, config, token_dep))
 
-# ── monitor router ──────────────────────────────────────────
-from monitor_routes import router as monitor_router
-app.include_router(monitor_router)
-
-logger = logging.getLogger(__name__)
-
 # ──────────────────────── Endpoints ──────────────────────────
 @app.post("/token")
 async def get_token(req: TokenRequest):
@@ -337,20 +266,27 @@ async def generate_html(
     Crawls the URL, preprocesses the raw HTML for schema extraction, and returns the processed HTML.
     Use when you need sanitized HTML structures for building schemas or further processing.
     """
-    from crawler_pool import get_crawler
     cfg = CrawlerRunConfig()
     try:
-        crawler = await get_crawler(get_default_browser_config())
-        results = await crawler.arun(url=body.url, config=cfg)
+        async with AsyncWebCrawler(config=BrowserConfig()) as crawler:
+            results = await crawler.arun(url=body.url, config=cfg)
+        # Check if the crawl was successful
         if not results[0].success:
-            raise HTTPException(500, detail=results[0].error_message or "Crawl failed")
-
+            raise HTTPException(
+                status_code=500,
+                detail=results[0].error_message or "Crawl failed"
+            )
+        
         raw_html = results[0].html
         from crawl4ai.utils import preprocess_html_for_schema
         processed_html = preprocess_html_for_schema(raw_html)
         return JSONResponse({"html": processed_html, "url": body.url, "success": True})
     except Exception as e:
-        raise HTTPException(500, detail=str(e))
+        # Log and raise as HTTP 500 for other exceptions
+        raise HTTPException(
+            status_code=500,
+            detail=str(e)
+        )
 
 # Screenshot endpoint
 
@@ -368,13 +304,16 @@ async def generate_screenshot(
     Use when you need an image snapshot of the rendered page. Its recommened to provide an output path to save the screenshot.
     Then in result instead of the screenshot you will get a path to the saved file.
     """
-    from crawler_pool import get_crawler
     try:
-        cfg = CrawlerRunConfig(screenshot=True, screenshot_wait_for=body.screenshot_wait_for)
-        crawler = await get_crawler(get_default_browser_config())
-        results = await crawler.arun(url=body.url, config=cfg)
+        cfg = CrawlerRunConfig(
+            screenshot=True, screenshot_wait_for=body.screenshot_wait_for)
+        async with AsyncWebCrawler(config=BrowserConfig()) as crawler:
+            results = await crawler.arun(url=body.url, config=cfg)
         if not results[0].success:
-            raise HTTPException(500, detail=results[0].error_message or "Crawl failed")
+            raise HTTPException(
+                status_code=500,
+                detail=results[0].error_message or "Crawl failed"
+            )
         screenshot_data = results[0].screenshot
         if body.output_path:
             abs_path = os.path.abspath(body.output_path)
@@ -384,7 +323,10 @@ async def generate_screenshot(
             return {"success": True, "path": abs_path}
         return {"success": True, "screenshot": screenshot_data}
     except Exception as e:
-        raise HTTPException(500, detail=str(e))
+        raise HTTPException(
+            status_code=500,
+            detail=str(e)
+        )
 
 # PDF endpoint
 
@@ -402,13 +344,15 @@ async def generate_pdf(
     Use when you need a printable or archivable snapshot of the page. It is recommended to provide an output path to save the PDF.
     Then in result instead of the PDF you will get a path to the saved file.
     """
-    from crawler_pool import get_crawler
     try:
         cfg = CrawlerRunConfig(pdf=True)
-        crawler = await get_crawler(get_default_browser_config())
-        results = await crawler.arun(url=body.url, config=cfg)
+        async with AsyncWebCrawler(config=BrowserConfig()) as crawler:
+            results = await crawler.arun(url=body.url, config=cfg)
         if not results[0].success:
-            raise HTTPException(500, detail=results[0].error_message or "Crawl failed")
+            raise HTTPException(
+                status_code=500,
+                detail=results[0].error_message or "Crawl failed"
+            )
         pdf_data = results[0].pdf
         if body.output_path:
             abs_path = os.path.abspath(body.output_path)
@@ -418,7 +362,10 @@ async def generate_pdf(
             return {"success": True, "path": abs_path}
         return {"success": True, "pdf": base64.b64encode(pdf_data).decode()}
     except Exception as e:
-        raise HTTPException(500, detail=str(e))
+        raise HTTPException(
+            status_code=500,
+            detail=str(e)
+        )
 
 
 @app.post("/execute_js")
@@ -474,17 +421,23 @@ async def execute_js(
         ```
 
     """
-    from crawler_pool import get_crawler
     try:
         cfg = CrawlerRunConfig(js_code=body.scripts)
-        crawler = await get_crawler(get_default_browser_config())
-        results = await crawler.arun(url=body.url, config=cfg)
+        async with AsyncWebCrawler(config=BrowserConfig()) as crawler:
+            results = await crawler.arun(url=body.url, config=cfg)
         if not results[0].success:
-            raise HTTPException(500, detail=results[0].error_message or "Crawl failed")
+            raise HTTPException(
+                status_code=500,
+                detail=results[0].error_message or "Crawl failed"
+            )
+        # Return JSON-serializable dict of the first CrawlResult
         data = results[0].model_dump()
         return JSONResponse(data)
     except Exception as e:
-        raise HTTPException(500, detail=str(e))
+        raise HTTPException(
+            status_code=500,
+            detail=str(e)
+        )
 
 
 @app.get("/llm/{url:path}")

deploy/docker/static/playground/index.html

@@ -167,14 +167,11 @@
             </a>
         </h1>
 
-        <div class="ml-auto flex items-center space-x-4">
-            <a href="/dashboard" class="text-xs text-secondary hover:text-primary underline">Monitor</a>
-            <div class="flex space-x-2">
-                <button id="play-tab"
-                    class="px-3 py-1 rounded-t bg-surface border border-b-0 border-border text-primary">Playground</button>
-                <button id="stress-tab" class="px-3 py-1 rounded-t border border-border hover:bg-surface">Stress
-                    Test</button>
-            </div>
+        <div class="ml-auto flex space-x-2">
+            <button id="play-tab"
+                class="px-3 py-1 rounded-t bg-surface border border-b-0 border-border text-primary">Playground</button>
+            <button id="stress-tab" class="px-3 py-1 rounded-t border border-border hover:bg-surface">Stress
+                Test</button>
         </div>
     </header>
 

deploy/docker/test-websocket.py

@@ -1,34 +0,0 @@
-#!/usr/bin/env python3
-"""
-Quick WebSocket test - Connect to monitor WebSocket and print updates
-"""
-import asyncio
-import websockets
-import json
-
-async def test_websocket():
-    uri = "ws://localhost:11235/monitor/ws"
-    print(f"Connecting to {uri}...")
-
-    try:
-        async with websockets.connect(uri) as websocket:
-            print("✅ Connected!")
-
-            # Receive and print 5 updates
-            for i in range(5):
-                message = await websocket.recv()
-                data = json.loads(message)
-                print(f"\n📊 Update #{i+1}:")
-                print(f"  - Health: CPU {data['health']['container']['cpu_percent']}%, Memory {data['health']['container']['memory_percent']}%")
-                print(f"  - Active Requests: {len(data['requests']['active'])}")
-                print(f"  - Browsers: {len(data['browsers'])}")
-
-    except Exception as e:
-        print(f"❌ Error: {e}")
-        return 1
-
-    print("\n✅ WebSocket test passed!")
-    return 0
-
-if __name__ == "__main__":
-    exit(asyncio.run(test_websocket()))

deploy/docker/tests/demo_monitor_dashboard.py

@@ -1,164 +0,0 @@
-#!/usr/bin/env python3
-"""
-Monitor Dashboard Demo Script
-Generates varied activity to showcase all monitoring features for video recording.
-"""
-import httpx
-import asyncio
-import time
-from datetime import datetime
-
-BASE_URL = "http://localhost:11235"
-
-async def demo_dashboard():
-    print("🎬 Monitor Dashboard Demo - Starting...\n")
-    print(f"📊 Dashboard: {BASE_URL}/dashboard")
-    print("=" * 60)
-
-    async with httpx.AsyncClient(timeout=60.0) as client:
-
-        # Phase 1: Simple requests (permanent browser)
-        print("\n🔷 Phase 1: Testing permanent browser pool")
-        print("-" * 60)
-        for i in range(5):
-            print(f"  {i+1}/5 Request to /crawl (default config)...")
-            try:
-                r = await client.post(
-                    f"{BASE_URL}/crawl",
-                    json={"urls": [f"https://httpbin.org/html?req={i}"], "crawler_config": {}}
-                )
-                print(f"     ✅ Status: {r.status_code}, Time: {r.elapsed.total_seconds():.2f}s")
-            except Exception as e:
-                print(f"     ❌ Error: {e}")
-            await asyncio.sleep(1)  # Small delay between requests
-
-        # Phase 2: Create variant browsers (different configs)
-        print("\n🔶 Phase 2: Testing cold→hot pool promotion")
-        print("-" * 60)
-        viewports = [
-            {"width": 1920, "height": 1080},
-            {"width": 1280, "height": 720},
-            {"width": 800, "height": 600}
-        ]
-
-        for idx, viewport in enumerate(viewports):
-            print(f"  Viewport {viewport['width']}x{viewport['height']}:")
-            for i in range(4):  # 4 requests each to trigger promotion at 3
-                try:
-                    r = await client.post(
-                        f"{BASE_URL}/crawl",
-                        json={
-                            "urls": [f"https://httpbin.org/json?v={idx}&r={i}"],
-                            "browser_config": {"viewport": viewport},
-                            "crawler_config": {}
-                        }
-                    )
-                    print(f"    {i+1}/4 ✅ {r.status_code} - Should see cold→hot after 3 uses")
-                except Exception as e:
-                    print(f"    {i+1}/4 ❌ {e}")
-                await asyncio.sleep(0.5)
-
-        # Phase 3: Concurrent burst (stress pool)
-        print("\n🔷 Phase 3: Concurrent burst (10 parallel)")
-        print("-" * 60)
-        tasks = []
-        for i in range(10):
-            tasks.append(
-                client.post(
-                    f"{BASE_URL}/crawl",
-                    json={"urls": [f"https://httpbin.org/delay/2?burst={i}"], "crawler_config": {}}
-                )
-            )
-
-        print("  Sending 10 concurrent requests...")
-        start = time.time()
-        results = await asyncio.gather(*tasks, return_exceptions=True)
-        elapsed = time.time() - start
-
-        successes = sum(1 for r in results if not isinstance(r, Exception) and r.status_code == 200)
-        print(f"  ✅ {successes}/10 succeeded in {elapsed:.2f}s")
-
-        # Phase 4: Multi-endpoint coverage
-        print("\n🔶 Phase 4: Testing multiple endpoints")
-        print("-" * 60)
-        endpoints = [
-            ("/md", {"url": "https://httpbin.org/html", "f": "fit", "c": "0"}),
-            ("/screenshot", {"url": "https://httpbin.org/html"}),
-            ("/pdf", {"url": "https://httpbin.org/html"}),
-        ]
-
-        for endpoint, payload in endpoints:
-            print(f"  Testing {endpoint}...")
-            try:
-                if endpoint == "/md":
-                    r = await client.post(f"{BASE_URL}{endpoint}", json=payload)
-                else:
-                    r = await client.post(f"{BASE_URL}{endpoint}", json=payload)
-                print(f"    ✅ {r.status_code}")
-            except Exception as e:
-                print(f"    ❌ {e}")
-            await asyncio.sleep(1)
-
-        # Phase 5: Intentional error (to populate errors tab)
-        print("\n🔷 Phase 5: Generating error examples")
-        print("-" * 60)
-        print("  Triggering invalid URL error...")
-        try:
-            r = await client.post(
-                f"{BASE_URL}/crawl",
-                json={"urls": ["invalid://bad-url"], "crawler_config": {}}
-            )
-            print(f"    Response: {r.status_code}")
-        except Exception as e:
-            print(f"    ✅ Error captured: {type(e).__name__}")
-
-        # Phase 6: Wait for janitor activity
-        print("\n🔶 Phase 6: Waiting for janitor cleanup...")
-        print("-" * 60)
-        print("  Idle for 40s to allow janitor to clean cold pool browsers...")
-        for i in range(40, 0, -10):
-            print(f"    {i}s remaining... (Check dashboard for cleanup events)")
-            await asyncio.sleep(10)
-
-        # Phase 7: Final stats check
-        print("\n🔷 Phase 7: Final dashboard state")
-        print("-" * 60)
-
-        r = await client.get(f"{BASE_URL}/monitor/health")
-        health = r.json()
-        print(f"  Memory: {health['container']['memory_percent']:.1f}%")
-        print(f"  Browsers: Perm={health['pool']['permanent']['active']}, "
-              f"Hot={health['pool']['hot']['count']}, Cold={health['pool']['cold']['count']}")
-
-        r = await client.get(f"{BASE_URL}/monitor/endpoints/stats")
-        stats = r.json()
-        print(f"\n  Endpoint Stats:")
-        for endpoint, data in stats.items():
-            print(f"    {endpoint}: {data['count']} req, "
-                  f"{data['avg_latency_ms']:.0f}ms avg, "
-                  f"{data['success_rate_percent']:.1f}% success")
-
-        r = await client.get(f"{BASE_URL}/monitor/browsers")
-        browsers = r.json()
-        print(f"\n  Pool Efficiency:")
-        print(f"    Total browsers: {browsers['summary']['total_count']}")
-        print(f"    Memory usage: {browsers['summary']['total_memory_mb']} MB")
-        print(f"    Reuse rate: {browsers['summary']['reuse_rate_percent']:.1f}%")
-
-    print("\n" + "=" * 60)
-    print("✅ Demo complete! Dashboard is now populated with rich data.")
-    print(f"\n📹 Recording tip: Refresh {BASE_URL}/dashboard")
-    print("   You should see:")
-    print("   • Active & completed requests")
-    print("   • Browser pool (permanent + hot/cold)")
-    print("   • Janitor cleanup events")
-    print("   • Endpoint analytics")
-    print("   • Memory timeline")
-
-if __name__ == "__main__":
-    try:
-        asyncio.run(demo_dashboard())
-    except KeyboardInterrupt:
-        print("\n\n⚠️  Demo interrupted by user")
-    except Exception as e:
-        print(f"\n\n❌ Demo failed: {e}")

deploy/docker/tests/requirements.txt

@@ -1,2 +0,0 @@
-httpx>=0.25.0
-docker>=7.0.0

deploy/docker/tests/test_1_basic.py

@@ -1,138 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test 1: Basic Container Health + Single Endpoint
-- Starts container
-- Hits /health endpoint 10 times
-- Reports success rate and basic latency
-"""
-import asyncio
-import time
-import docker
-import httpx
-
-# Config
-IMAGE = "crawl4ai-local:latest"
-CONTAINER_NAME = "crawl4ai-test"
-PORT = 11235
-REQUESTS = 10
-
-async def test_endpoint(url: str, count: int):
-    """Hit endpoint multiple times, return stats."""
-    results = []
-    async with httpx.AsyncClient(timeout=30.0) as client:
-        for i in range(count):
-            start = time.time()
-            try:
-                resp = await client.get(url)
-                elapsed = (time.time() - start) * 1000  # ms
-                results.append({
-                    "success": resp.status_code == 200,
-                    "latency_ms": elapsed,
-                    "status": resp.status_code
-                })
-                print(f"  [{i+1}/{count}] ✓ {resp.status_code} - {elapsed:.0f}ms")
-            except Exception as e:
-                results.append({
-                    "success": False,
-                    "latency_ms": None,
-                    "error": str(e)
-                })
-                print(f"  [{i+1}/{count}] ✗ Error: {e}")
-    return results
-
-def start_container(client, image: str, name: str, port: int):
-    """Start container, return container object."""
-    # Clean up existing
-    try:
-        old = client.containers.get(name)
-        print(f"🧹 Stopping existing container '{name}'...")
-        old.stop()
-        old.remove()
-    except docker.errors.NotFound:
-        pass
-
-    print(f"🚀 Starting container '{name}' from image '{image}'...")
-    container = client.containers.run(
-        image,
-        name=name,
-        ports={f"{port}/tcp": port},
-        detach=True,
-        shm_size="1g",
-        environment={"PYTHON_ENV": "production"}
-    )
-
-    # Wait for health
-    print(f"⏳ Waiting for container to be healthy...")
-    for _ in range(30):  # 30s timeout
-        time.sleep(1)
-        container.reload()
-        if container.status == "running":
-            try:
-                # Quick health check
-                import requests
-                resp = requests.get(f"http://localhost:{port}/health", timeout=2)
-                if resp.status_code == 200:
-                    print(f"✅ Container healthy!")
-                    return container
-            except:
-                pass
-    raise TimeoutError("Container failed to start")
-
-def stop_container(container):
-    """Stop and remove container."""
-    print(f"🛑 Stopping container...")
-    container.stop()
-    container.remove()
-    print(f"✅ Container removed")
-
-async def main():
-    print("="*60)
-    print("TEST 1: Basic Container Health + Single Endpoint")
-    print("="*60)
-
-    client = docker.from_env()
-    container = None
-
-    try:
-        # Start container
-        container = start_container(client, IMAGE, CONTAINER_NAME, PORT)
-
-        # Test /health endpoint
-        print(f"\n📊 Testing /health endpoint ({REQUESTS} requests)...")
-        url = f"http://localhost:{PORT}/health"
-        results = await test_endpoint(url, REQUESTS)
-
-        # Calculate stats
-        successes = sum(1 for r in results if r["success"])
-        success_rate = (successes / len(results)) * 100
-        latencies = [r["latency_ms"] for r in results if r["latency_ms"] is not None]
-        avg_latency = sum(latencies) / len(latencies) if latencies else 0
-
-        # Print results
-        print(f"\n{'='*60}")
-        print(f"RESULTS:")
-        print(f"  Success Rate: {success_rate:.1f}% ({successes}/{len(results)})")
-        print(f"  Avg Latency:  {avg_latency:.0f}ms")
-        if latencies:
-            print(f"  Min Latency:  {min(latencies):.0f}ms")
-            print(f"  Max Latency:  {max(latencies):.0f}ms")
-        print(f"{'='*60}")
-
-        # Pass/Fail
-        if success_rate >= 100:
-            print(f"✅ TEST PASSED")
-            return 0
-        else:
-            print(f"❌ TEST FAILED (expected 100% success rate)")
-            return 1
-
-    except Exception as e:
-        print(f"\n❌ TEST ERROR: {e}")
-        return 1
-    finally:
-        if container:
-            stop_container(container)
-
-if __name__ == "__main__":
-    exit_code = asyncio.run(main())
-    exit(exit_code)

deploy/docker/tests/test_2_memory.py

@@ -1,205 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test 2: Docker Stats Monitoring
-- Extends Test 1 with real-time container stats
-- Monitors memory % and CPU during requests
-- Reports baseline, peak, and final memory
-"""
-import asyncio
-import time
-import docker
-import httpx
-from threading import Thread, Event
-
-# Config
-IMAGE = "crawl4ai-local:latest"
-CONTAINER_NAME = "crawl4ai-test"
-PORT = 11235
-REQUESTS = 20  # More requests to see memory usage
-
-# Stats tracking
-stats_history = []
-stop_monitoring = Event()
-
-def monitor_stats(container):
-    """Background thread to collect container stats."""
-    for stat in container.stats(decode=True, stream=True):
-        if stop_monitoring.is_set():
-            break
-
-        try:
-            # Extract memory stats
-            mem_usage = stat['memory_stats'].get('usage', 0) / (1024 * 1024)  # MB
-            mem_limit = stat['memory_stats'].get('limit', 1) / (1024 * 1024)
-            mem_percent = (mem_usage / mem_limit * 100) if mem_limit > 0 else 0
-
-            # Extract CPU stats (handle missing fields on Mac)
-            cpu_percent = 0
-            try:
-                cpu_delta = stat['cpu_stats']['cpu_usage']['total_usage'] - \
-                           stat['precpu_stats']['cpu_usage']['total_usage']
-                system_delta = stat['cpu_stats'].get('system_cpu_usage', 0) - \
-                              stat['precpu_stats'].get('system_cpu_usage', 0)
-                if system_delta > 0:
-                    num_cpus = stat['cpu_stats'].get('online_cpus', 1)
-                    cpu_percent = (cpu_delta / system_delta * num_cpus * 100.0)
-            except (KeyError, ZeroDivisionError):
-                pass
-
-            stats_history.append({
-                'timestamp': time.time(),
-                'memory_mb': mem_usage,
-                'memory_percent': mem_percent,
-                'cpu_percent': cpu_percent
-            })
-        except Exception as e:
-            # Skip malformed stats
-            pass
-
-        time.sleep(0.5)  # Sample every 500ms
-
-async def test_endpoint(url: str, count: int):
-    """Hit endpoint, return stats."""
-    results = []
-    async with httpx.AsyncClient(timeout=30.0) as client:
-        for i in range(count):
-            start = time.time()
-            try:
-                resp = await client.get(url)
-                elapsed = (time.time() - start) * 1000
-                results.append({
-                    "success": resp.status_code == 200,
-                    "latency_ms": elapsed,
-                })
-                if (i + 1) % 5 == 0:  # Print every 5 requests
-                    print(f"  [{i+1}/{count}] ✓ {resp.status_code} - {elapsed:.0f}ms")
-            except Exception as e:
-                results.append({"success": False, "error": str(e)})
-                print(f"  [{i+1}/{count}] ✗ Error: {e}")
-    return results
-
-def start_container(client, image: str, name: str, port: int):
-    """Start container."""
-    try:
-        old = client.containers.get(name)
-        print(f"🧹 Stopping existing container '{name}'...")
-        old.stop()
-        old.remove()
-    except docker.errors.NotFound:
-        pass
-
-    print(f"🚀 Starting container '{name}'...")
-    container = client.containers.run(
-        image,
-        name=name,
-        ports={f"{port}/tcp": port},
-        detach=True,
-        shm_size="1g",
-        mem_limit="4g",  # Set explicit memory limit
-    )
-
-    print(f"⏳ Waiting for health...")
-    for _ in range(30):
-        time.sleep(1)
-        container.reload()
-        if container.status == "running":
-            try:
-                import requests
-                resp = requests.get(f"http://localhost:{port}/health", timeout=2)
-                if resp.status_code == 200:
-                    print(f"✅ Container healthy!")
-                    return container
-            except:
-                pass
-    raise TimeoutError("Container failed to start")
-
-def stop_container(container):
-    """Stop container."""
-    print(f"🛑 Stopping container...")
-    container.stop()
-    container.remove()
-
-async def main():
-    print("="*60)
-    print("TEST 2: Docker Stats Monitoring")
-    print("="*60)
-
-    client = docker.from_env()
-    container = None
-    monitor_thread = None
-
-    try:
-        # Start container
-        container = start_container(client, IMAGE, CONTAINER_NAME, PORT)
-
-        # Start stats monitoring in background
-        print(f"\n📊 Starting stats monitor...")
-        stop_monitoring.clear()
-        stats_history.clear()
-        monitor_thread = Thread(target=monitor_stats, args=(container,), daemon=True)
-        monitor_thread.start()
-
-        # Wait a bit for baseline
-        await asyncio.sleep(2)
-        baseline_mem = stats_history[-1]['memory_mb'] if stats_history else 0
-        print(f"📏 Baseline memory: {baseline_mem:.1f} MB")
-
-        # Test /health endpoint
-        print(f"\n🔄 Running {REQUESTS} requests to /health...")
-        url = f"http://localhost:{PORT}/health"
-        results = await test_endpoint(url, REQUESTS)
-
-        # Wait a bit to capture peak
-        await asyncio.sleep(1)
-
-        # Stop monitoring
-        stop_monitoring.set()
-        if monitor_thread:
-            monitor_thread.join(timeout=2)
-
-        # Calculate stats
-        successes = sum(1 for r in results if r.get("success"))
-        success_rate = (successes / len(results)) * 100
-        latencies = [r["latency_ms"] for r in results if "latency_ms" in r]
-        avg_latency = sum(latencies) / len(latencies) if latencies else 0
-
-        # Memory stats
-        memory_samples = [s['memory_mb'] for s in stats_history]
-        peak_mem = max(memory_samples) if memory_samples else 0
-        final_mem = memory_samples[-1] if memory_samples else 0
-        mem_delta = final_mem - baseline_mem
-
-        # Print results
-        print(f"\n{'='*60}")
-        print(f"RESULTS:")
-        print(f"  Success Rate: {success_rate:.1f}% ({successes}/{len(results)})")
-        print(f"  Avg Latency:  {avg_latency:.0f}ms")
-        print(f"\n  Memory Stats:")
-        print(f"    Baseline: {baseline_mem:.1f} MB")
-        print(f"    Peak:     {peak_mem:.1f} MB")
-        print(f"    Final:    {final_mem:.1f} MB")
-        print(f"    Delta:    {mem_delta:+.1f} MB")
-        print(f"{'='*60}")
-
-        # Pass/Fail
-        if success_rate >= 100 and mem_delta < 100:  # No significant memory growth
-            print(f"✅ TEST PASSED")
-            return 0
-        else:
-            if success_rate < 100:
-                print(f"❌ TEST FAILED (success rate < 100%)")
-            if mem_delta >= 100:
-                print(f"⚠️  WARNING: Memory grew by {mem_delta:.1f} MB")
-            return 1
-
-    except Exception as e:
-        print(f"\n❌ TEST ERROR: {e}")
-        return 1
-    finally:
-        stop_monitoring.set()
-        if container:
-            stop_container(container)
-
-if __name__ == "__main__":
-    exit_code = asyncio.run(main())
-    exit(exit_code)

deploy/docker/tests/test_3_pool.py

@@ -1,229 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test 3: Pool Validation - Permanent Browser Reuse
-- Tests /html endpoint (should use permanent browser)
-- Monitors container logs for pool hit markers
-- Validates browser reuse rate
-- Checks memory after browser creation
-"""
-import asyncio
-import time
-import docker
-import httpx
-from threading import Thread, Event
-
-# Config
-IMAGE = "crawl4ai-local:latest"
-CONTAINER_NAME = "crawl4ai-test"
-PORT = 11235
-REQUESTS = 30
-
-# Stats tracking
-stats_history = []
-stop_monitoring = Event()
-
-def monitor_stats(container):
-    """Background stats collector."""
-    for stat in container.stats(decode=True, stream=True):
-        if stop_monitoring.is_set():
-            break
-        try:
-            mem_usage = stat['memory_stats'].get('usage', 0) / (1024 * 1024)
-            stats_history.append({
-                'timestamp': time.time(),
-                'memory_mb': mem_usage,
-            })
-        except:
-            pass
-        time.sleep(0.5)
-
-def count_log_markers(container):
-    """Extract pool usage markers from logs."""
-    logs = container.logs().decode('utf-8')
-
-    permanent_hits = logs.count("🔥 Using permanent browser")
-    hot_hits = logs.count("♨️  Using hot pool browser")
-    cold_hits = logs.count("❄️  Using cold pool browser")
-    new_created = logs.count("🆕 Creating new browser")
-
-    return {
-        'permanent_hits': permanent_hits,
-        'hot_hits': hot_hits,
-        'cold_hits': cold_hits,
-        'new_created': new_created,
-        'total_hits': permanent_hits + hot_hits + cold_hits
-    }
-
-async def test_endpoint(url: str, count: int):
-    """Hit endpoint multiple times."""
-    results = []
-    async with httpx.AsyncClient(timeout=60.0) as client:
-        for i in range(count):
-            start = time.time()
-            try:
-                resp = await client.post(url, json={"url": "https://httpbin.org/html"})
-                elapsed = (time.time() - start) * 1000
-                results.append({
-                    "success": resp.status_code == 200,
-                    "latency_ms": elapsed,
-                })
-                if (i + 1) % 10 == 0:
-                    print(f"  [{i+1}/{count}] ✓ {resp.status_code} - {elapsed:.0f}ms")
-            except Exception as e:
-                results.append({"success": False, "error": str(e)})
-                print(f"  [{i+1}/{count}] ✗ Error: {e}")
-    return results
-
-def start_container(client, image: str, name: str, port: int):
-    """Start container."""
-    try:
-        old = client.containers.get(name)
-        print(f"🧹 Stopping existing container...")
-        old.stop()
-        old.remove()
-    except docker.errors.NotFound:
-        pass
-
-    print(f"🚀 Starting container...")
-    container = client.containers.run(
-        image,
-        name=name,
-        ports={f"{port}/tcp": port},
-        detach=True,
-        shm_size="1g",
-        mem_limit="4g",
-    )
-
-    print(f"⏳ Waiting for health...")
-    for _ in range(30):
-        time.sleep(1)
-        container.reload()
-        if container.status == "running":
-            try:
-                import requests
-                resp = requests.get(f"http://localhost:{port}/health", timeout=2)
-                if resp.status_code == 200:
-                    print(f"✅ Container healthy!")
-                    return container
-            except:
-                pass
-    raise TimeoutError("Container failed to start")
-
-def stop_container(container):
-    """Stop container."""
-    print(f"🛑 Stopping container...")
-    container.stop()
-    container.remove()
-
-async def main():
-    print("="*60)
-    print("TEST 3: Pool Validation - Permanent Browser Reuse")
-    print("="*60)
-
-    client = docker.from_env()
-    container = None
-    monitor_thread = None
-
-    try:
-        # Start container
-        container = start_container(client, IMAGE, CONTAINER_NAME, PORT)
-
-        # Wait for permanent browser initialization
-        print(f"\n⏳ Waiting for permanent browser init (3s)...")
-        await asyncio.sleep(3)
-
-        # Start stats monitoring
-        print(f"📊 Starting stats monitor...")
-        stop_monitoring.clear()
-        stats_history.clear()
-        monitor_thread = Thread(target=monitor_stats, args=(container,), daemon=True)
-        monitor_thread.start()
-
-        await asyncio.sleep(1)
-        baseline_mem = stats_history[-1]['memory_mb'] if stats_history else 0
-        print(f"📏 Baseline (with permanent browser): {baseline_mem:.1f} MB")
-
-        # Test /html endpoint (uses permanent browser for default config)
-        print(f"\n🔄 Running {REQUESTS} requests to /html...")
-        url = f"http://localhost:{PORT}/html"
-        results = await test_endpoint(url, REQUESTS)
-
-        # Wait a bit
-        await asyncio.sleep(1)
-
-        # Stop monitoring
-        stop_monitoring.set()
-        if monitor_thread:
-            monitor_thread.join(timeout=2)
-
-        # Analyze logs for pool markers
-        print(f"\n📋 Analyzing pool usage...")
-        pool_stats = count_log_markers(container)
-
-        # Calculate request stats
-        successes = sum(1 for r in results if r.get("success"))
-        success_rate = (successes / len(results)) * 100
-        latencies = [r["latency_ms"] for r in results if "latency_ms" in r]
-        avg_latency = sum(latencies) / len(latencies) if latencies else 0
-
-        # Memory stats
-        memory_samples = [s['memory_mb'] for s in stats_history]
-        peak_mem = max(memory_samples) if memory_samples else 0
-        final_mem = memory_samples[-1] if memory_samples else 0
-        mem_delta = final_mem - baseline_mem
-
-        # Calculate reuse rate
-        total_requests = len(results)
-        total_pool_hits = pool_stats['total_hits']
-        reuse_rate = (total_pool_hits / total_requests * 100) if total_requests > 0 else 0
-
-        # Print results
-        print(f"\n{'='*60}")
-        print(f"RESULTS:")
-        print(f"  Success Rate: {success_rate:.1f}% ({successes}/{len(results)})")
-        print(f"  Avg Latency:  {avg_latency:.0f}ms")
-        print(f"\n  Pool Stats:")
-        print(f"    🔥 Permanent Hits: {pool_stats['permanent_hits']}")
-        print(f"    ♨️  Hot Pool Hits:   {pool_stats['hot_hits']}")
-        print(f"    ❄️  Cold Pool Hits:  {pool_stats['cold_hits']}")
-        print(f"    🆕 New Created:    {pool_stats['new_created']}")
-        print(f"    📊 Reuse Rate:     {reuse_rate:.1f}%")
-        print(f"\n  Memory Stats:")
-        print(f"    Baseline: {baseline_mem:.1f} MB")
-        print(f"    Peak:     {peak_mem:.1f} MB")
-        print(f"    Final:    {final_mem:.1f} MB")
-        print(f"    Delta:    {mem_delta:+.1f} MB")
-        print(f"{'='*60}")
-
-        # Pass/Fail
-        passed = True
-        if success_rate < 100:
-            print(f"❌ FAIL: Success rate {success_rate:.1f}% < 100%")
-            passed = False
-        if reuse_rate < 80:
-            print(f"❌ FAIL: Reuse rate {reuse_rate:.1f}% < 80% (expected high permanent browser usage)")
-            passed = False
-        if pool_stats['permanent_hits'] < (total_requests * 0.8):
-            print(f"⚠️  WARNING: Only {pool_stats['permanent_hits']} permanent hits out of {total_requests} requests")
-        if mem_delta > 200:
-            print(f"⚠️  WARNING: Memory grew by {mem_delta:.1f} MB (possible browser leak)")
-
-        if passed:
-            print(f"✅ TEST PASSED")
-            return 0
-        else:
-            return 1
-
-    except Exception as e:
-        print(f"\n❌ TEST ERROR: {e}")
-        import traceback
-        traceback.print_exc()
-        return 1
-    finally:
-        stop_monitoring.set()
-        if container:
-            stop_container(container)
-
-if __name__ == "__main__":
-    exit_code = asyncio.run(main())
-    exit(exit_code)

deploy/docker/tests/test_4_concurrent.py

@@ -1,236 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test 4: Concurrent Load Testing
-- Tests pool under concurrent load
-- Escalates: 10 → 50 → 100 concurrent requests
-- Validates latency distribution (P50, P95, P99)
-- Monitors memory stability
-"""
-import asyncio
-import time
-import docker
-import httpx
-from threading import Thread, Event
-from collections import defaultdict
-
-# Config
-IMAGE = "crawl4ai-local:latest"
-CONTAINER_NAME = "crawl4ai-test"
-PORT = 11235
-LOAD_LEVELS = [
-    {"name": "Light", "concurrent": 10, "requests": 20},
-    {"name": "Medium", "concurrent": 50, "requests": 100},
-    {"name": "Heavy", "concurrent": 100, "requests": 200},
-]
-
-# Stats
-stats_history = []
-stop_monitoring = Event()
-
-def monitor_stats(container):
-    """Background stats collector."""
-    for stat in container.stats(decode=True, stream=True):
-        if stop_monitoring.is_set():
-            break
-        try:
-            mem_usage = stat['memory_stats'].get('usage', 0) / (1024 * 1024)
-            stats_history.append({'timestamp': time.time(), 'memory_mb': mem_usage})
-        except:
-            pass
-        time.sleep(0.5)
-
-def count_log_markers(container):
-    """Extract pool markers."""
-    logs = container.logs().decode('utf-8')
-    return {
-        'permanent': logs.count("🔥 Using permanent browser"),
-        'hot': logs.count("♨️  Using hot pool browser"),
-        'cold': logs.count("❄️  Using cold pool browser"),
-        'new': logs.count("🆕 Creating new browser"),
-    }
-
-async def hit_endpoint(client, url, payload, semaphore):
-    """Single request with concurrency control."""
-    async with semaphore:
-        start = time.time()
-        try:
-            resp = await client.post(url, json=payload, timeout=60.0)
-            elapsed = (time.time() - start) * 1000
-            return {"success": resp.status_code == 200, "latency_ms": elapsed}
-        except Exception as e:
-            return {"success": False, "error": str(e)}
-
-async def run_concurrent_test(url, payload, concurrent, total_requests):
-    """Run concurrent requests."""
-    semaphore = asyncio.Semaphore(concurrent)
-    async with httpx.AsyncClient() as client:
-        tasks = [hit_endpoint(client, url, payload, semaphore) for _ in range(total_requests)]
-        results = await asyncio.gather(*tasks)
-    return results
-
-def calculate_percentiles(latencies):
-    """Calculate P50, P95, P99."""
-    if not latencies:
-        return 0, 0, 0
-    sorted_lat = sorted(latencies)
-    n = len(sorted_lat)
-    return (
-        sorted_lat[int(n * 0.50)],
-        sorted_lat[int(n * 0.95)],
-        sorted_lat[int(n * 0.99)],
-    )
-
-def start_container(client, image, name, port):
-    """Start container."""
-    try:
-        old = client.containers.get(name)
-        print(f"🧹 Stopping existing container...")
-        old.stop()
-        old.remove()
-    except docker.errors.NotFound:
-        pass
-
-    print(f"🚀 Starting container...")
-    container = client.containers.run(
-        image, name=name, ports={f"{port}/tcp": port},
-        detach=True, shm_size="1g", mem_limit="4g",
-    )
-
-    print(f"⏳ Waiting for health...")
-    for _ in range(30):
-        time.sleep(1)
-        container.reload()
-        if container.status == "running":
-            try:
-                import requests
-                if requests.get(f"http://localhost:{port}/health", timeout=2).status_code == 200:
-                    print(f"✅ Container healthy!")
-                    return container
-            except:
-                pass
-    raise TimeoutError("Container failed to start")
-
-async def main():
-    print("="*60)
-    print("TEST 4: Concurrent Load Testing")
-    print("="*60)
-
-    client = docker.from_env()
-    container = None
-    monitor_thread = None
-
-    try:
-        container = start_container(client, IMAGE, CONTAINER_NAME, PORT)
-
-        print(f"\n⏳ Waiting for permanent browser init (3s)...")
-        await asyncio.sleep(3)
-
-        # Start monitoring
-        stop_monitoring.clear()
-        stats_history.clear()
-        monitor_thread = Thread(target=monitor_stats, args=(container,), daemon=True)
-        monitor_thread.start()
-
-        await asyncio.sleep(1)
-        baseline_mem = stats_history[-1]['memory_mb'] if stats_history else 0
-        print(f"📏 Baseline: {baseline_mem:.1f} MB\n")
-
-        url = f"http://localhost:{PORT}/html"
-        payload = {"url": "https://httpbin.org/html"}
-
-        all_results = []
-        level_stats = []
-
-        # Run load levels
-        for level in LOAD_LEVELS:
-            print(f"{'='*60}")
-            print(f"🔄 {level['name']} Load: {level['concurrent']} concurrent, {level['requests']} total")
-            print(f"{'='*60}")
-
-            start_time = time.time()
-            results = await run_concurrent_test(url, payload, level['concurrent'], level['requests'])
-            duration = time.time() - start_time
-
-            successes = sum(1 for r in results if r.get("success"))
-            success_rate = (successes / len(results)) * 100
-            latencies = [r["latency_ms"] for r in results if "latency_ms" in r]
-            p50, p95, p99 = calculate_percentiles(latencies)
-            avg_lat = sum(latencies) / len(latencies) if latencies else 0
-
-            print(f"  Duration:     {duration:.1f}s")
-            print(f"  Success:      {success_rate:.1f}% ({successes}/{len(results)})")
-            print(f"  Avg Latency:  {avg_lat:.0f}ms")
-            print(f"  P50/P95/P99:  {p50:.0f}ms / {p95:.0f}ms / {p99:.0f}ms")
-
-            level_stats.append({
-                'name': level['name'],
-                'concurrent': level['concurrent'],
-                'success_rate': success_rate,
-                'avg_latency': avg_lat,
-                'p50': p50, 'p95': p95, 'p99': p99,
-            })
-            all_results.extend(results)
-
-            await asyncio.sleep(2)  # Cool down between levels
-
-        # Stop monitoring
-        await asyncio.sleep(1)
-        stop_monitoring.set()
-        if monitor_thread:
-            monitor_thread.join(timeout=2)
-
-        # Final stats
-        pool_stats = count_log_markers(container)
-        memory_samples = [s['memory_mb'] for s in stats_history]
-        peak_mem = max(memory_samples) if memory_samples else 0
-        final_mem = memory_samples[-1] if memory_samples else 0
-
-        print(f"\n{'='*60}")
-        print(f"FINAL RESULTS:")
-        print(f"{'='*60}")
-        print(f"  Total Requests: {len(all_results)}")
-        print(f"\n  Pool Utilization:")
-        print(f"    🔥 Permanent: {pool_stats['permanent']}")
-        print(f"    ♨️  Hot:       {pool_stats['hot']}")
-        print(f"    ❄️  Cold:      {pool_stats['cold']}")
-        print(f"    🆕 New:       {pool_stats['new']}")
-        print(f"\n  Memory:")
-        print(f"    Baseline: {baseline_mem:.1f} MB")
-        print(f"    Peak:     {peak_mem:.1f} MB")
-        print(f"    Final:    {final_mem:.1f} MB")
-        print(f"    Delta:    {final_mem - baseline_mem:+.1f} MB")
-        print(f"{'='*60}")
-
-        # Pass/Fail
-        passed = True
-        for ls in level_stats:
-            if ls['success_rate'] < 99:
-                print(f"❌ FAIL: {ls['name']} success rate {ls['success_rate']:.1f}% < 99%")
-                passed = False
-            if ls['p99'] > 10000:  # 10s threshold
-                print(f"⚠️  WARNING: {ls['name']} P99 latency {ls['p99']:.0f}ms very high")
-
-        if final_mem - baseline_mem > 300:
-            print(f"⚠️  WARNING: Memory grew {final_mem - baseline_mem:.1f} MB")
-
-        if passed:
-            print(f"✅ TEST PASSED")
-            return 0
-        else:
-            return 1
-
-    except Exception as e:
-        print(f"\n❌ TEST ERROR: {e}")
-        import traceback
-        traceback.print_exc()
-        return 1
-    finally:
-        stop_monitoring.set()
-        if container:
-            print(f"🛑 Stopping container...")
-            container.stop()
-            container.remove()
-
-if __name__ == "__main__":
-    exit_code = asyncio.run(main())
-    exit(exit_code)

deploy/docker/tests/test_5_pool_stress.py

@@ -1,267 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test 5: Pool Stress - Mixed Configs
-- Tests hot/cold pool with different browser configs
-- Uses different viewports to create config variants
-- Validates cold → hot promotion after 3 uses
-- Monitors pool tier distribution
-"""
-import asyncio
-import time
-import docker
-import httpx
-from threading import Thread, Event
-import random
-
-# Config
-IMAGE = "crawl4ai-local:latest"
-CONTAINER_NAME = "crawl4ai-test"
-PORT = 11235
-REQUESTS_PER_CONFIG = 5  # 5 requests per config variant
-
-# Different viewport configs to test pool tiers
-VIEWPORT_CONFIGS = [
-    None,  # Default (permanent browser)
-    {"width": 1920, "height": 1080},  # Desktop
-    {"width": 1024, "height": 768},   # Tablet
-    {"width": 375, "height": 667},    # Mobile
-]
-
-# Stats
-stats_history = []
-stop_monitoring = Event()
-
-def monitor_stats(container):
-    """Background stats collector."""
-    for stat in container.stats(decode=True, stream=True):
-        if stop_monitoring.is_set():
-            break
-        try:
-            mem_usage = stat['memory_stats'].get('usage', 0) / (1024 * 1024)
-            stats_history.append({'timestamp': time.time(), 'memory_mb': mem_usage})
-        except:
-            pass
-        time.sleep(0.5)
-
-def analyze_pool_logs(container):
-    """Extract detailed pool stats from logs."""
-    logs = container.logs().decode('utf-8')
-
-    permanent = logs.count("🔥 Using permanent browser")
-    hot = logs.count("♨️  Using hot pool browser")
-    cold = logs.count("❄️  Using cold pool browser")
-    new = logs.count("🆕 Creating new browser")
-    promotions = logs.count("⬆️  Promoting to hot pool")
-
-    return {
-        'permanent': permanent,
-        'hot': hot,
-        'cold': cold,
-        'new': new,
-        'promotions': promotions,
-        'total': permanent + hot + cold
-    }
-
-async def crawl_with_viewport(client, url, viewport):
-    """Single request with specific viewport."""
-    payload = {
-        "urls": ["https://httpbin.org/html"],
-        "browser_config": {},
-        "crawler_config": {}
-    }
-
-    # Add viewport if specified
-    if viewport:
-        payload["browser_config"] = {
-            "type": "BrowserConfig",
-            "params": {
-                "viewport": {"type": "dict", "value": viewport},
-                "headless": True,
-                "text_mode": True,
-                "extra_args": [
-                    "--no-sandbox",
-                    "--disable-dev-shm-usage",
-                    "--disable-gpu",
-                    "--disable-software-rasterizer",
-                    "--disable-web-security",
-                    "--allow-insecure-localhost",
-                    "--ignore-certificate-errors"
-                ]
-            }
-        }
-
-    start = time.time()
-    try:
-        resp = await client.post(url, json=payload, timeout=60.0)
-        elapsed = (time.time() - start) * 1000
-        return {"success": resp.status_code == 200, "latency_ms": elapsed, "viewport": viewport}
-    except Exception as e:
-        return {"success": False, "error": str(e), "viewport": viewport}
-
-def start_container(client, image, name, port):
-    """Start container."""
-    try:
-        old = client.containers.get(name)
-        print(f"🧹 Stopping existing container...")
-        old.stop()
-        old.remove()
-    except docker.errors.NotFound:
-        pass
-
-    print(f"🚀 Starting container...")
-    container = client.containers.run(
-        image, name=name, ports={f"{port}/tcp": port},
-        detach=True, shm_size="1g", mem_limit="4g",
-    )
-
-    print(f"⏳ Waiting for health...")
-    for _ in range(30):
-        time.sleep(1)
-        container.reload()
-        if container.status == "running":
-            try:
-                import requests
-                if requests.get(f"http://localhost:{port}/health", timeout=2).status_code == 200:
-                    print(f"✅ Container healthy!")
-                    return container
-            except:
-                pass
-    raise TimeoutError("Container failed to start")
-
-async def main():
-    print("="*60)
-    print("TEST 5: Pool Stress - Mixed Configs")
-    print("="*60)
-
-    client = docker.from_env()
-    container = None
-    monitor_thread = None
-
-    try:
-        container = start_container(client, IMAGE, CONTAINER_NAME, PORT)
-
-        print(f"\n⏳ Waiting for permanent browser init (3s)...")
-        await asyncio.sleep(3)
-
-        # Start monitoring
-        stop_monitoring.clear()
-        stats_history.clear()
-        monitor_thread = Thread(target=monitor_stats, args=(container,), daemon=True)
-        monitor_thread.start()
-
-        await asyncio.sleep(1)
-        baseline_mem = stats_history[-1]['memory_mb'] if stats_history else 0
-        print(f"📏 Baseline: {baseline_mem:.1f} MB\n")
-
-        url = f"http://localhost:{PORT}/crawl"
-
-        print(f"Testing {len(VIEWPORT_CONFIGS)} different configs:")
-        for i, vp in enumerate(VIEWPORT_CONFIGS):
-            vp_str = "Default" if vp is None else f"{vp['width']}x{vp['height']}"
-            print(f"  {i+1}. {vp_str}")
-        print()
-
-        # Run requests: repeat each config REQUESTS_PER_CONFIG times
-        all_results = []
-        config_sequence = []
-
-        for _ in range(REQUESTS_PER_CONFIG):
-            for viewport in VIEWPORT_CONFIGS:
-                config_sequence.append(viewport)
-
-        # Shuffle to mix configs
-        random.shuffle(config_sequence)
-
-        print(f"🔄 Running {len(config_sequence)} requests with mixed configs...")
-
-        async with httpx.AsyncClient() as http_client:
-            for i, viewport in enumerate(config_sequence):
-                result = await crawl_with_viewport(http_client, url, viewport)
-                all_results.append(result)
-
-                if (i + 1) % 5 == 0:
-                    vp_str = "default" if result['viewport'] is None else f"{result['viewport']['width']}x{result['viewport']['height']}"
-                    status = "✓" if result.get('success') else "✗"
-                    lat = f"{result.get('latency_ms', 0):.0f}ms" if 'latency_ms' in result else "error"
-                    print(f"  [{i+1}/{len(config_sequence)}] {status} {vp_str} - {lat}")
-
-        # Stop monitoring
-        await asyncio.sleep(2)
-        stop_monitoring.set()
-        if monitor_thread:
-            monitor_thread.join(timeout=2)
-
-        # Analyze results
-        pool_stats = analyze_pool_logs(container)
-
-        successes = sum(1 for r in all_results if r.get("success"))
-        success_rate = (successes / len(all_results)) * 100
-        latencies = [r["latency_ms"] for r in all_results if "latency_ms" in r]
-        avg_lat = sum(latencies) / len(latencies) if latencies else 0
-
-        memory_samples = [s['memory_mb'] for s in stats_history]
-        peak_mem = max(memory_samples) if memory_samples else 0
-        final_mem = memory_samples[-1] if memory_samples else 0
-
-        print(f"\n{'='*60}")
-        print(f"RESULTS:")
-        print(f"{'='*60}")
-        print(f"  Requests:     {len(all_results)}")
-        print(f"  Success Rate: {success_rate:.1f}% ({successes}/{len(all_results)})")
-        print(f"  Avg Latency:  {avg_lat:.0f}ms")
-        print(f"\n  Pool Statistics:")
-        print(f"    🔥 Permanent: {pool_stats['permanent']}")
-        print(f"    ♨️  Hot:       {pool_stats['hot']}")
-        print(f"    ❄️  Cold:      {pool_stats['cold']}")
-        print(f"    🆕 New:       {pool_stats['new']}")
-        print(f"    ⬆️  Promotions: {pool_stats['promotions']}")
-        print(f"    📊 Reuse:     {(pool_stats['total'] / len(all_results) * 100):.1f}%")
-        print(f"\n  Memory:")
-        print(f"    Baseline: {baseline_mem:.1f} MB")
-        print(f"    Peak:     {peak_mem:.1f} MB")
-        print(f"    Final:    {final_mem:.1f} MB")
-        print(f"    Delta:    {final_mem - baseline_mem:+.1f} MB")
-        print(f"{'='*60}")
-
-        # Pass/Fail
-        passed = True
-
-        if success_rate < 99:
-            print(f"❌ FAIL: Success rate {success_rate:.1f}% < 99%")
-            passed = False
-
-        # Should see promotions since we repeat each config 5 times
-        if pool_stats['promotions'] < (len(VIEWPORT_CONFIGS) - 1):  # -1 for default
-            print(f"⚠️  WARNING: Only {pool_stats['promotions']} promotions (expected ~{len(VIEWPORT_CONFIGS)-1})")
-
-        # Should have created some browsers for different configs
-        if pool_stats['new'] == 0:
-            print(f"⚠️  NOTE: No new browsers created (all used default?)")
-
-        if pool_stats['permanent'] == len(all_results):
-            print(f"⚠️  NOTE: All requests used permanent browser (configs not varying enough?)")
-
-        if final_mem - baseline_mem > 500:
-            print(f"⚠️  WARNING: Memory grew {final_mem - baseline_mem:.1f} MB")
-
-        if passed:
-            print(f"✅ TEST PASSED")
-            return 0
-        else:
-            return 1
-
-    except Exception as e:
-        print(f"\n❌ TEST ERROR: {e}")
-        import traceback
-        traceback.print_exc()
-        return 1
-    finally:
-        stop_monitoring.set()
-        if container:
-            print(f"🛑 Stopping container...")
-            container.stop()
-            container.remove()
-
-if __name__ == "__main__":
-    exit_code = asyncio.run(main())
-    exit(exit_code)

deploy/docker/tests/test_6_multi_endpoint.py

@@ -1,234 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test 6: Multi-Endpoint Testing
-- Tests multiple endpoints together: /html, /screenshot, /pdf, /crawl
-- Validates each endpoint works correctly
-- Monitors success rates per endpoint
-"""
-import asyncio
-import time
-import docker
-import httpx
-from threading import Thread, Event
-
-# Config
-IMAGE = "crawl4ai-local:latest"
-CONTAINER_NAME = "crawl4ai-test"
-PORT = 11235
-REQUESTS_PER_ENDPOINT = 10
-
-# Stats
-stats_history = []
-stop_monitoring = Event()
-
-def monitor_stats(container):
-    """Background stats collector."""
-    for stat in container.stats(decode=True, stream=True):
-        if stop_monitoring.is_set():
-            break
-        try:
-            mem_usage = stat['memory_stats'].get('usage', 0) / (1024 * 1024)
-            stats_history.append({'timestamp': time.time(), 'memory_mb': mem_usage})
-        except:
-            pass
-        time.sleep(0.5)
-
-async def test_html(client, base_url, count):
-    """Test /html endpoint."""
-    url = f"{base_url}/html"
-    results = []
-    for _ in range(count):
-        start = time.time()
-        try:
-            resp = await client.post(url, json={"url": "https://httpbin.org/html"}, timeout=30.0)
-            elapsed = (time.time() - start) * 1000
-            results.append({"success": resp.status_code == 200, "latency_ms": elapsed})
-        except Exception as e:
-            results.append({"success": False, "error": str(e)})
-    return results
-
-async def test_screenshot(client, base_url, count):
-    """Test /screenshot endpoint."""
-    url = f"{base_url}/screenshot"
-    results = []
-    for _ in range(count):
-        start = time.time()
-        try:
-            resp = await client.post(url, json={"url": "https://httpbin.org/html"}, timeout=30.0)
-            elapsed = (time.time() - start) * 1000
-            results.append({"success": resp.status_code == 200, "latency_ms": elapsed})
-        except Exception as e:
-            results.append({"success": False, "error": str(e)})
-    return results
-
-async def test_pdf(client, base_url, count):
-    """Test /pdf endpoint."""
-    url = f"{base_url}/pdf"
-    results = []
-    for _ in range(count):
-        start = time.time()
-        try:
-            resp = await client.post(url, json={"url": "https://httpbin.org/html"}, timeout=30.0)
-            elapsed = (time.time() - start) * 1000
-            results.append({"success": resp.status_code == 200, "latency_ms": elapsed})
-        except Exception as e:
-            results.append({"success": False, "error": str(e)})
-    return results
-
-async def test_crawl(client, base_url, count):
-    """Test /crawl endpoint."""
-    url = f"{base_url}/crawl"
-    results = []
-    payload = {
-        "urls": ["https://httpbin.org/html"],
-        "browser_config": {},
-        "crawler_config": {}
-    }
-    for _ in range(count):
-        start = time.time()
-        try:
-            resp = await client.post(url, json=payload, timeout=30.0)
-            elapsed = (time.time() - start) * 1000
-            results.append({"success": resp.status_code == 200, "latency_ms": elapsed})
-        except Exception as e:
-            results.append({"success": False, "error": str(e)})
-    return results
-
-def start_container(client, image, name, port):
-    """Start container."""
-    try:
-        old = client.containers.get(name)
-        print(f"🧹 Stopping existing container...")
-        old.stop()
-        old.remove()
-    except docker.errors.NotFound:
-        pass
-
-    print(f"🚀 Starting container...")
-    container = client.containers.run(
-        image, name=name, ports={f"{port}/tcp": port},
-        detach=True, shm_size="1g", mem_limit="4g",
-    )
-
-    print(f"⏳ Waiting for health...")
-    for _ in range(30):
-        time.sleep(1)
-        container.reload()
-        if container.status == "running":
-            try:
-                import requests
-                if requests.get(f"http://localhost:{port}/health", timeout=2).status_code == 200:
-                    print(f"✅ Container healthy!")
-                    return container
-            except:
-                pass
-    raise TimeoutError("Container failed to start")
-
-async def main():
-    print("="*60)
-    print("TEST 6: Multi-Endpoint Testing")
-    print("="*60)
-
-    client = docker.from_env()
-    container = None
-    monitor_thread = None
-
-    try:
-        container = start_container(client, IMAGE, CONTAINER_NAME, PORT)
-
-        print(f"\n⏳ Waiting for permanent browser init (3s)...")
-        await asyncio.sleep(3)
-
-        # Start monitoring
-        stop_monitoring.clear()
-        stats_history.clear()
-        monitor_thread = Thread(target=monitor_stats, args=(container,), daemon=True)
-        monitor_thread.start()
-
-        await asyncio.sleep(1)
-        baseline_mem = stats_history[-1]['memory_mb'] if stats_history else 0
-        print(f"📏 Baseline: {baseline_mem:.1f} MB\n")
-
-        base_url = f"http://localhost:{PORT}"
-
-        # Test each endpoint
-        endpoints = {
-            "/html": test_html,
-            "/screenshot": test_screenshot,
-            "/pdf": test_pdf,
-            "/crawl": test_crawl,
-        }
-
-        all_endpoint_stats = {}
-
-        async with httpx.AsyncClient() as http_client:
-            for endpoint_name, test_func in endpoints.items():
-                print(f"🔄 Testing {endpoint_name} ({REQUESTS_PER_ENDPOINT} requests)...")
-                results = await test_func(http_client, base_url, REQUESTS_PER_ENDPOINT)
-
-                successes = sum(1 for r in results if r.get("success"))
-                success_rate = (successes / len(results)) * 100
-                latencies = [r["latency_ms"] for r in results if "latency_ms" in r]
-                avg_lat = sum(latencies) / len(latencies) if latencies else 0
-
-                all_endpoint_stats[endpoint_name] = {
-                    'success_rate': success_rate,
-                    'avg_latency': avg_lat,
-                    'total': len(results),
-                    'successes': successes
-                }
-
-                print(f"  ✓ Success: {success_rate:.1f}% ({successes}/{len(results)}), Avg: {avg_lat:.0f}ms")
-
-        # Stop monitoring
-        await asyncio.sleep(1)
-        stop_monitoring.set()
-        if monitor_thread:
-            monitor_thread.join(timeout=2)
-
-        # Final stats
-        memory_samples = [s['memory_mb'] for s in stats_history]
-        peak_mem = max(memory_samples) if memory_samples else 0
-        final_mem = memory_samples[-1] if memory_samples else 0
-
-        print(f"\n{'='*60}")
-        print(f"RESULTS:")
-        print(f"{'='*60}")
-        for endpoint, stats in all_endpoint_stats.items():
-            print(f"  {endpoint:12} Success: {stats['success_rate']:5.1f}%  Avg: {stats['avg_latency']:6.0f}ms")
-
-        print(f"\n  Memory:")
-        print(f"    Baseline: {baseline_mem:.1f} MB")
-        print(f"    Peak:     {peak_mem:.1f} MB")
-        print(f"    Final:    {final_mem:.1f} MB")
-        print(f"    Delta:    {final_mem - baseline_mem:+.1f} MB")
-        print(f"{'='*60}")
-
-        # Pass/Fail
-        passed = True
-        for endpoint, stats in all_endpoint_stats.items():
-            if stats['success_rate'] < 100:
-                print(f"❌ FAIL: {endpoint} success rate {stats['success_rate']:.1f}% < 100%")
-                passed = False
-
-        if passed:
-            print(f"✅ TEST PASSED")
-            return 0
-        else:
-            return 1
-
-    except Exception as e:
-        print(f"\n❌ TEST ERROR: {e}")
-        import traceback
-        traceback.print_exc()
-        return 1
-    finally:
-        stop_monitoring.set()
-        if container:
-            print(f"🛑 Stopping container...")
-            container.stop()
-            container.remove()
-
-if __name__ == "__main__":
-    exit_code = asyncio.run(main())
-    exit(exit_code)

deploy/docker/tests/test_7_cleanup.py

@@ -1,199 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test 7: Cleanup Verification (Janitor)
-- Creates load spike then goes idle
-- Verifies memory returns to near baseline
-- Tests janitor cleanup of idle browsers
-- Monitors memory recovery time
-"""
-import asyncio
-import time
-import docker
-import httpx
-from threading import Thread, Event
-
-# Config
-IMAGE = "crawl4ai-local:latest"
-CONTAINER_NAME = "crawl4ai-test"
-PORT = 11235
-SPIKE_REQUESTS = 20  # Create some browsers
-IDLE_TIME = 90  # Wait 90s for janitor (runs every 60s)
-
-# Stats
-stats_history = []
-stop_monitoring = Event()
-
-def monitor_stats(container):
-    """Background stats collector."""
-    for stat in container.stats(decode=True, stream=True):
-        if stop_monitoring.is_set():
-            break
-        try:
-            mem_usage = stat['memory_stats'].get('usage', 0) / (1024 * 1024)
-            stats_history.append({'timestamp': time.time(), 'memory_mb': mem_usage})
-        except:
-            pass
-        time.sleep(1)  # Sample every 1s for this test
-
-def start_container(client, image, name, port):
-    """Start container."""
-    try:
-        old = client.containers.get(name)
-        print(f"🧹 Stopping existing container...")
-        old.stop()
-        old.remove()
-    except docker.errors.NotFound:
-        pass
-
-    print(f"🚀 Starting container...")
-    container = client.containers.run(
-        image, name=name, ports={f"{port}/tcp": port},
-        detach=True, shm_size="1g", mem_limit="4g",
-    )
-
-    print(f"⏳ Waiting for health...")
-    for _ in range(30):
-        time.sleep(1)
-        container.reload()
-        if container.status == "running":
-            try:
-                import requests
-                if requests.get(f"http://localhost:{port}/health", timeout=2).status_code == 200:
-                    print(f"✅ Container healthy!")
-                    return container
-            except:
-                pass
-    raise TimeoutError("Container failed to start")
-
-async def main():
-    print("="*60)
-    print("TEST 7: Cleanup Verification (Janitor)")
-    print("="*60)
-
-    client = docker.from_env()
-    container = None
-    monitor_thread = None
-
-    try:
-        container = start_container(client, IMAGE, CONTAINER_NAME, PORT)
-
-        print(f"\n⏳ Waiting for permanent browser init (3s)...")
-        await asyncio.sleep(3)
-
-        # Start monitoring
-        stop_monitoring.clear()
-        stats_history.clear()
-        monitor_thread = Thread(target=monitor_stats, args=(container,), daemon=True)
-        monitor_thread.start()
-
-        await asyncio.sleep(2)
-        baseline_mem = stats_history[-1]['memory_mb'] if stats_history else 0
-        print(f"📏 Baseline: {baseline_mem:.1f} MB\n")
-
-        # Create load spike with different configs to populate pool
-        print(f"🔥 Creating load spike ({SPIKE_REQUESTS} requests with varied configs)...")
-        url = f"http://localhost:{PORT}/crawl"
-
-        viewports = [
-            {"width": 1920, "height": 1080},
-            {"width": 1024, "height": 768},
-            {"width": 375, "height": 667},
-        ]
-
-        async with httpx.AsyncClient(timeout=60.0) as http_client:
-            tasks = []
-            for i in range(SPIKE_REQUESTS):
-                vp = viewports[i % len(viewports)]
-                payload = {
-                    "urls": ["https://httpbin.org/html"],
-                    "browser_config": {
-                        "type": "BrowserConfig",
-                        "params": {
-                            "viewport": {"type": "dict", "value": vp},
-                            "headless": True,
-                            "text_mode": True,
-                            "extra_args": [
-                                "--no-sandbox", "--disable-dev-shm-usage",
-                                "--disable-gpu", "--disable-software-rasterizer",
-                                "--disable-web-security", "--allow-insecure-localhost",
-                                "--ignore-certificate-errors"
-                            ]
-                        }
-                    },
-                    "crawler_config": {}
-                }
-                tasks.append(http_client.post(url, json=payload))
-
-            results = await asyncio.gather(*tasks, return_exceptions=True)
-            successes = sum(1 for r in results if hasattr(r, 'status_code') and r.status_code == 200)
-            print(f"  ✓ Spike completed: {successes}/{len(results)} successful")
-
-        # Measure peak
-        await asyncio.sleep(2)
-        peak_mem = max([s['memory_mb'] for s in stats_history]) if stats_history else baseline_mem
-        print(f"  📊 Peak memory: {peak_mem:.1f} MB (+{peak_mem - baseline_mem:.1f} MB)")
-
-        # Now go idle and wait for janitor
-        print(f"\n⏸️  Going idle for {IDLE_TIME}s (janitor cleanup)...")
-        print(f"  (Janitor runs every 60s, checking for idle browsers)")
-
-        for elapsed in range(0, IDLE_TIME, 10):
-            await asyncio.sleep(10)
-            current_mem = stats_history[-1]['memory_mb'] if stats_history else 0
-            print(f"  [{elapsed+10:3d}s] Memory: {current_mem:.1f} MB")
-
-        # Stop monitoring
-        stop_monitoring.set()
-        if monitor_thread:
-            monitor_thread.join(timeout=2)
-
-        # Analyze memory recovery
-        final_mem = stats_history[-1]['memory_mb'] if stats_history else 0
-        recovery_mb = peak_mem - final_mem
-        recovery_pct = (recovery_mb / (peak_mem - baseline_mem) * 100) if (peak_mem - baseline_mem) > 0 else 0
-
-        print(f"\n{'='*60}")
-        print(f"RESULTS:")
-        print(f"{'='*60}")
-        print(f"  Memory Journey:")
-        print(f"    Baseline:  {baseline_mem:.1f} MB")
-        print(f"    Peak:      {peak_mem:.1f} MB  (+{peak_mem - baseline_mem:.1f} MB)")
-        print(f"    Final:     {final_mem:.1f} MB  (+{final_mem - baseline_mem:.1f} MB)")
-        print(f"    Recovered: {recovery_mb:.1f} MB  ({recovery_pct:.1f}%)")
-        print(f"{'='*60}")
-
-        # Pass/Fail
-        passed = True
-
-        # Should have created some memory pressure
-        if peak_mem - baseline_mem < 100:
-            print(f"⚠️  WARNING: Peak increase only {peak_mem - baseline_mem:.1f} MB (expected more browsers)")
-
-        # Should recover most memory (within 100MB of baseline)
-        if final_mem - baseline_mem > 100:
-            print(f"⚠️  WARNING: Memory didn't recover well (still +{final_mem - baseline_mem:.1f} MB above baseline)")
-        else:
-            print(f"✅ Good memory recovery!")
-
-        # Baseline + 50MB tolerance
-        if final_mem - baseline_mem < 50:
-            print(f"✅ Excellent cleanup (within 50MB of baseline)")
-
-        print(f"✅ TEST PASSED")
-        return 0
-
-    except Exception as e:
-        print(f"\n❌ TEST ERROR: {e}")
-        import traceback
-        traceback.print_exc()
-        return 1
-    finally:
-        stop_monitoring.set()
-        if container:
-            print(f"🛑 Stopping container...")
-            container.stop()
-            container.remove()
-
-if __name__ == "__main__":
-    exit_code = asyncio.run(main())
-    exit(exit_code)

deploy/docker/tests/test_monitor_demo.py

@@ -1,57 +0,0 @@
-#!/usr/bin/env python3
-"""Quick test to generate monitor dashboard activity"""
-import httpx
-import asyncio
-
-async def test_dashboard():
-    async with httpx.AsyncClient(timeout=30.0) as client:
-        print("📊 Generating dashboard activity...")
-
-        # Test 1: Simple crawl
-        print("\n1️⃣ Running simple crawl...")
-        r1 = await client.post(
-            "http://localhost:11235/crawl",
-            json={"urls": ["https://httpbin.org/html"], "crawler_config": {}}
-        )
-        print(f"   Status: {r1.status_code}")
-
-        # Test 2: Multiple URLs
-        print("\n2️⃣ Running multi-URL crawl...")
-        r2 = await client.post(
-            "http://localhost:11235/crawl",
-            json={
-                "urls": [
-                    "https://httpbin.org/html",
-                    "https://httpbin.org/json"
-                ],
-                "crawler_config": {}
-            }
-        )
-        print(f"   Status: {r2.status_code}")
-
-        # Test 3: Check monitor health
-        print("\n3️⃣ Checking monitor health...")
-        r3 = await client.get("http://localhost:11235/monitor/health")
-        health = r3.json()
-        print(f"   Memory: {health['container']['memory_percent']}%")
-        print(f"   Browsers: {health['pool']['permanent']['active']}")
-
-        # Test 4: Check requests
-        print("\n4️⃣ Checking request log...")
-        r4 = await client.get("http://localhost:11235/monitor/requests")
-        reqs = r4.json()
-        print(f"   Active: {len(reqs['active'])}")
-        print(f"   Completed: {len(reqs['completed'])}")
-
-        # Test 5: Check endpoint stats
-        print("\n5️⃣ Checking endpoint stats...")
-        r5 = await client.get("http://localhost:11235/monitor/endpoints/stats")
-        stats = r5.json()
-        for endpoint, data in stats.items():
-            print(f"   {endpoint}: {data['count']} requests, {data['avg_latency_ms']}ms avg")
-
-        print("\n✅ Dashboard should now show activity!")
-        print(f"\n🌐 Open: http://localhost:11235/dashboard")
-
-if __name__ == "__main__":
-    asyncio.run(test_dashboard())

deploy/docker/utils.py

@@ -178,29 +178,4 @@ def verify_email_domain(email: str) -> bool:
         records = dns.resolver.resolve(domain, 'MX')
         return True if records else False
     except Exception as e:
-        return False
-
-def get_container_memory_percent() -> float:
-    """Get actual container memory usage vs limit (cgroup v1/v2 aware)."""
-    try:
-        # Try cgroup v2 first
-        usage_path = Path("/sys/fs/cgroup/memory.current")
-        limit_path = Path("/sys/fs/cgroup/memory.max")
-        if not usage_path.exists():
-            # Fall back to cgroup v1
-            usage_path = Path("/sys/fs/cgroup/memory/memory.usage_in_bytes")
-            limit_path = Path("/sys/fs/cgroup/memory/memory.limit_in_bytes")
-
-        usage = int(usage_path.read_text())
-        limit = int(limit_path.read_text())
-
-        # Handle unlimited (v2: "max", v1: > 1e18)
-        if limit > 1e18:
-            import psutil
-            limit = psutil.virtual_memory().total
-
-        return (usage / limit) * 100
-    except:
-        # Non-container or unsupported: fallback to host
-        import psutil
-        return psutil.virtual_memory().percent
+        return False

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)

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/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/md_v2/blog/index.md

@@ -20,17 +20,43 @@ Ever wondered why your AI coding assistant struggles with your library despite c
 
 ## Latest Release
 
+### [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
+- **🎯 Zero Breaking Changes**: Fully backward compatible, webhooks are opt-in
+
+[Read full release notes →](../blog/release-v0.7.6.md)
+
+## Recent Releases
+
+### [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
+- **🛠️ Bug Fixes**: Resolved multiple community-reported issues including URL processing, JWT authentication, and proxy configuration
+
+[Read full release notes →](../blog/release-v0.7.5.md)
+
+## Recent Releases
+
 ### [Crawl4AI v0.7.4 – The Intelligent Table Extraction & Performance Update](../blog/release-v0.7.4.md)
 *August 17, 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.
-
-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
+Revolutionary LLM-powered table extraction with intelligent chunking, performance improvements for concurrent crawling, enhanced browser management, and critical stability fixes.
 
 [Read full release notes →](../blog/release-v0.7.4.md)
 

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/index.md

@@ -59,6 +59,27 @@ Crawl4AI is the #1 trending GitHub repository, actively maintained by a vibrant
 
 > **Note**: If you're looking for the old documentation, you can access it [here](https://old.docs.crawl4ai.com).
 
+## 🆕 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
 
 Crawl4AI now features intelligent adaptive crawling that knows when to stop! Using advanced information foraging algorithms, it determines when sufficient information has been gathered to answer your query.

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/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"
@@ -18,7 +19,7 @@ nav:
     - "Marketplace Admin": "marketplace/admin/index.html"
   - Setup & Installation:
     - "Installation": "core/installation.md"
-    - "Self-Hosting Guide": "core/self-hosting.md"
+    - "Docker Deployment": "core/docker-deployment.md"
   - "Blog & Changelog":
     - "Blog Home": "blog/index.md"
     - "Changelog": "https://github.com/unclecode/crawl4ai/blob/main/CHANGELOG.md"

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/docker/test_hooks_utility.py

@@ -0,0 +1,193 @@
+"""
+Test script demonstrating the hooks_to_string utility and Docker client integration.
+"""
+import asyncio
+from crawl4ai import Crawl4aiDockerClient, hooks_to_string
+
+
+# Define hook functions as regular Python functions
+async def auth_hook(page, context, **kwargs):
+    """Add authentication cookies."""
+    await context.add_cookies([{
+        'name': 'test_cookie',
+        'value': 'test_value',
+        'domain': '.httpbin.org',
+        'path': '/'
+    }])
+    return page
+
+
+async def scroll_hook(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
+
+
+async def viewport_hook(page, context, **kwargs):
+    """Set custom viewport."""
+    await page.set_viewport_size({"width": 1920, "height": 1080})
+    return page
+
+
+async def test_hooks_utility():
+    """Test the hooks_to_string utility function."""
+    print("=" * 60)
+    print("Testing hooks_to_string utility")
+    print("=" * 60)
+
+    # Create hooks dictionary with function objects
+    hooks_dict = {
+        "on_page_context_created": auth_hook,
+        "before_retrieve_html": scroll_hook
+    }
+
+    # Convert to string format
+    hooks_string = hooks_to_string(hooks_dict)
+
+    print("\n✓ Successfully converted function objects to strings")
+    print(f"\n✓ Converted {len(hooks_string)} hooks:")
+    for hook_name in hooks_string.keys():
+        print(f"  - {hook_name}")
+
+    print("\n✓ Preview of converted hook:")
+    print("-" * 60)
+    print(hooks_string["on_page_context_created"][:200] + "...")
+    print("-" * 60)
+
+    return hooks_string
+
+
+async def test_docker_client_with_functions():
+    """Test Docker client with function objects (automatic conversion)."""
+    print("\n" + "=" * 60)
+    print("Testing Docker Client with Function Objects")
+    print("=" * 60)
+
+    # Note: This requires a running Crawl4AI Docker server
+    # Uncomment the following to test with actual server:
+
+    async with Crawl4aiDockerClient(base_url="http://localhost:11234", verbose=True) as client:
+        # Pass function objects directly - they'll be converted automatically
+        result = await client.crawl(
+            ["https://httpbin.org/html"],
+            hooks={
+                "on_page_context_created": auth_hook,
+                "before_retrieve_html": scroll_hook
+            },
+            hooks_timeout=30
+        )
+        print(f"\n✓ Crawl successful: {result.success}")
+        print(f"✓ URL: {result.url}")
+
+    print("\n✓ Docker client accepts function objects directly")
+    print("✓ Automatic conversion happens internally")
+    print("✓ No manual string formatting needed!")
+
+
+async def test_docker_client_with_strings():
+    """Test Docker client with pre-converted strings."""
+    print("\n" + "=" * 60)
+    print("Testing Docker Client with String Hooks")
+    print("=" * 60)
+
+    # Convert hooks to strings first
+    hooks_dict = {
+        "on_page_context_created": viewport_hook,
+        "before_retrieve_html": scroll_hook
+    }
+    hooks_string = hooks_to_string(hooks_dict)
+
+    # Note: This requires a running Crawl4AI Docker server
+    # Uncomment the following to test with actual server:
+
+    async with Crawl4aiDockerClient(base_url="http://localhost:11234", verbose=True) as client:
+        # Pass string hooks - they'll be used as-is
+        result = await client.crawl(
+            ["https://httpbin.org/html"],
+            hooks=hooks_string,
+            hooks_timeout=30
+        )
+        print(f"\n✓ Crawl successful: {result.success}")
+
+    print("\n✓ Docker client also accepts pre-converted strings")
+    print("✓ Backward compatible with existing code")
+
+
+async def show_usage_patterns():
+    """Show different usage patterns."""
+    print("\n" + "=" * 60)
+    print("Usage Patterns")
+    print("=" * 60)
+
+    print("\n1. Direct function usage (simplest):")
+    print("-" * 60)
+    print("""
+    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}
+    )
+    """)
+
+    print("\n2. Convert then use:")
+    print("-" * 60)
+    print("""
+    hooks_dict = {"on_page_context_created": my_hook}
+    hooks_string = hooks_to_string(hooks_dict)
+
+    result = await client.crawl(
+        ["https://example.com"],
+        hooks=hooks_string
+    )
+    """)
+
+    print("\n3. Manual string (backward compatible):")
+    print("-" * 60)
+    print("""
+    hooks_string = {
+        "on_page_context_created": '''
+async def hook(page, context, **kwargs):
+    await page.set_viewport_size({"width": 1920, "height": 1080})
+    return page
+'''
+    }
+
+    result = await client.crawl(
+        ["https://example.com"],
+        hooks=hooks_string
+    )
+    """)
+
+
+async def main():
+    """Run all tests."""
+    print("\n🚀 Crawl4AI Hooks Utility Test Suite\n")
+
+    # Test the utility function
+    # await test_hooks_utility()
+
+    # Show usage with Docker client
+    # await test_docker_client_with_functions()
+    await test_docker_client_with_strings()
+
+    # Show different patterns
+    # await show_usage_patterns()
+
+    # print("\n" + "=" * 60)
+    # print("✓ All tests completed successfully!")
+    # print("=" * 60)
+    # print("\nKey Benefits:")
+    # print("  • Write hooks as regular Python functions")
+    # print("  • IDE support with autocomplete and type checking")
+    # print("  • Automatic conversion to API format")
+    # print("  • Backward compatible with string hooks")
+    # print("  • Same utility used everywhere")
+    # print("\n")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

tests/test_webhook_feature.sh

@@ -0,0 +1,305 @@
+#!/bin/bash
+
+#############################################################################
+# Webhook Feature Test Script
+#
+# This script tests the webhook feature implementation by:
+# 1. Switching to the webhook feature branch
+# 2. Installing dependencies
+# 3. Starting the server
+# 4. Running webhook tests
+# 5. Cleaning up and returning to original branch
+#
+# Usage: ./test_webhook_feature.sh
+#############################################################################
+
+set -e  # Exit on error
+
+# Colors for output
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# Configuration
+BRANCH_NAME="claude/implement-webhook-crawl-feature-011CULZY1Jy8N5MUkZqXkRVp"
+VENV_PATH="venv"
+SERVER_PORT=11235
+WEBHOOK_PORT=8080
+PROJECT_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
+
+# PID files for cleanup
+REDIS_PID=""
+SERVER_PID=""
+WEBHOOK_PID=""
+
+#############################################################################
+# Utility Functions
+#############################################################################
+
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+cleanup() {
+    log_info "Starting cleanup..."
+
+    # Kill webhook receiver if running
+    if [ ! -z "$WEBHOOK_PID" ] && kill -0 $WEBHOOK_PID 2>/dev/null; then
+        log_info "Stopping webhook receiver (PID: $WEBHOOK_PID)..."
+        kill $WEBHOOK_PID 2>/dev/null || true
+    fi
+
+    # Kill server if running
+    if [ ! -z "$SERVER_PID" ] && kill -0 $SERVER_PID 2>/dev/null; then
+        log_info "Stopping server (PID: $SERVER_PID)..."
+        kill $SERVER_PID 2>/dev/null || true
+    fi
+
+    # Kill Redis if running
+    if [ ! -z "$REDIS_PID" ] && kill -0 $REDIS_PID 2>/dev/null; then
+        log_info "Stopping Redis (PID: $REDIS_PID)..."
+        kill $REDIS_PID 2>/dev/null || true
+    fi
+
+    # Also kill by port if PIDs didn't work
+    lsof -ti:$SERVER_PORT | xargs kill -9 2>/dev/null || true
+    lsof -ti:$WEBHOOK_PORT | xargs kill -9 2>/dev/null || true
+    lsof -ti:6379 | xargs kill -9 2>/dev/null || true
+
+    # Return to original branch
+    if [ ! -z "$ORIGINAL_BRANCH" ]; then
+        log_info "Switching back to branch: $ORIGINAL_BRANCH"
+        git checkout $ORIGINAL_BRANCH 2>/dev/null || true
+    fi
+
+    log_success "Cleanup complete"
+}
+
+# Set trap to cleanup on exit
+trap cleanup EXIT INT TERM
+
+#############################################################################
+# Main Script
+#############################################################################
+
+log_info "Starting webhook feature test script"
+log_info "Project root: $PROJECT_ROOT"
+
+cd "$PROJECT_ROOT"
+
+# Step 1: Save current branch and fetch PR
+log_info "Step 1: Fetching PR branch..."
+ORIGINAL_BRANCH=$(git rev-parse --abbrev-ref HEAD)
+log_info "Current branch: $ORIGINAL_BRANCH"
+
+git fetch origin $BRANCH_NAME
+log_success "Branch fetched"
+
+# Step 2: Switch to new branch
+log_info "Step 2: Switching to branch: $BRANCH_NAME"
+git checkout $BRANCH_NAME
+log_success "Switched to webhook feature branch"
+
+# Step 3: Activate virtual environment
+log_info "Step 3: Activating virtual environment..."
+if [ ! -d "$VENV_PATH" ]; then
+    log_error "Virtual environment not found at $VENV_PATH"
+    log_info "Creating virtual environment..."
+    python3 -m venv $VENV_PATH
+fi
+
+source $VENV_PATH/bin/activate
+log_success "Virtual environment activated: $(which python)"
+
+# Step 4: Install server dependencies
+log_info "Step 4: Installing server dependencies..."
+pip install -q -r deploy/docker/requirements.txt
+log_success "Dependencies installed"
+
+# Check if Redis is available
+log_info "Checking Redis availability..."
+if ! command -v redis-server &> /dev/null; then
+    log_warning "Redis not found, attempting to install..."
+    if command -v apt-get &> /dev/null; then
+        sudo apt-get update && sudo apt-get install -y redis-server
+    elif command -v brew &> /dev/null; then
+        brew install redis
+    else
+        log_error "Cannot install Redis automatically. Please install Redis manually."
+        exit 1
+    fi
+fi
+
+# Step 5: Start Redis in background
+log_info "Step 5a: Starting Redis..."
+redis-server --port 6379 --daemonize yes
+sleep 2
+REDIS_PID=$(pgrep redis-server)
+log_success "Redis started (PID: $REDIS_PID)"
+
+# Step 5b: Start server in background
+log_info "Step 5b: Starting server on port $SERVER_PORT..."
+cd deploy/docker
+
+# Start server in background
+python3 -m uvicorn server:app --host 0.0.0.0 --port $SERVER_PORT > /tmp/crawl4ai_server.log 2>&1 &
+SERVER_PID=$!
+cd "$PROJECT_ROOT"
+
+log_info "Server started (PID: $SERVER_PID)"
+
+# Wait for server to be ready
+log_info "Waiting for server to be ready..."
+for i in {1..30}; do
+    if curl -s http://localhost:$SERVER_PORT/health > /dev/null 2>&1; then
+        log_success "Server is ready!"
+        break
+    fi
+    if [ $i -eq 30 ]; then
+        log_error "Server failed to start within 30 seconds"
+        log_info "Server logs:"
+        tail -50 /tmp/crawl4ai_server.log
+        exit 1
+    fi
+    echo -n "."
+    sleep 1
+done
+echo ""
+
+# Step 6: Create and run webhook test
+log_info "Step 6: Creating webhook test script..."
+
+cat > /tmp/test_webhook.py << 'PYTHON_SCRIPT'
+import requests
+import json
+import time
+from flask import Flask, request, jsonify
+from threading import Thread, Event
+
+# Configuration
+CRAWL4AI_BASE_URL = "http://localhost:11235"
+WEBHOOK_BASE_URL = "http://localhost:8080"
+
+# Flask app for webhook receiver
+app = Flask(__name__)
+webhook_received = Event()
+webhook_data = {}
+
+@app.route('/webhook', methods=['POST'])
+def handle_webhook():
+    global webhook_data
+    webhook_data = request.json
+    webhook_received.set()
+    print(f"\n✅ Webhook received: {json.dumps(webhook_data, indent=2)}")
+    return jsonify({"status": "received"}), 200
+
+def start_webhook_server():
+    app.run(host='0.0.0.0', port=8080, debug=False, use_reloader=False)
+
+# Start webhook server in background
+webhook_thread = Thread(target=start_webhook_server, daemon=True)
+webhook_thread.start()
+time.sleep(2)
+
+print("🚀 Submitting crawl job with webhook...")
+
+# Submit job with webhook
+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": True
+    }
+}
+
+response = requests.post(
+    f"{CRAWL4AI_BASE_URL}/crawl/job",
+    json=payload,
+    headers={"Content-Type": "application/json"}
+)
+
+if not response.ok:
+    print(f"❌ Failed to submit job: {response.text}")
+    exit(1)
+
+task_id = response.json()['task_id']
+print(f"✅ Job submitted successfully, task_id: {task_id}")
+
+# Wait for webhook (with timeout)
+print("⏳ Waiting for webhook notification...")
+if webhook_received.wait(timeout=60):
+    print(f"✅ Webhook received!")
+    print(f"   Task ID: {webhook_data.get('task_id')}")
+    print(f"   Status: {webhook_data.get('status')}")
+    print(f"   URLs: {webhook_data.get('urls')}")
+
+    if webhook_data.get('status') == 'completed':
+        if 'data' in webhook_data:
+            print(f"   ✅ Data included in webhook payload")
+            results = webhook_data['data'].get('results', [])
+            if results:
+                print(f"   📄 Crawled {len(results)} URL(s)")
+                for result in results:
+                    print(f"      - {result.get('url')}: {len(result.get('markdown', ''))} chars")
+        print("\n🎉 Webhook test PASSED!")
+        exit(0)
+    else:
+        print(f"   ❌ Job failed: {webhook_data.get('error')}")
+        exit(1)
+else:
+    print("❌ Webhook not received within 60 seconds")
+    # Try polling as fallback
+    print("⏳ Trying to poll job status...")
+    for i in range(10):
+        status_response = requests.get(f"{CRAWL4AI_BASE_URL}/crawl/job/{task_id}")
+        if status_response.ok:
+            status = status_response.json()
+            print(f"   Status: {status.get('status')}")
+            if status.get('status') in ['completed', 'failed']:
+                break
+        time.sleep(2)
+    exit(1)
+PYTHON_SCRIPT
+
+# Install Flask for webhook receiver
+pip install -q flask
+
+# Run the webhook test
+log_info "Running webhook test..."
+python3 /tmp/test_webhook.py &
+WEBHOOK_PID=$!
+
+# Wait for test to complete
+wait $WEBHOOK_PID
+TEST_EXIT_CODE=$?
+
+# Step 7: Verify results
+log_info "Step 7: Verifying test results..."
+if [ $TEST_EXIT_CODE -eq 0 ]; then
+    log_success "✅ Webhook test PASSED!"
+else
+    log_error "❌ Webhook test FAILED (exit code: $TEST_EXIT_CODE)"
+    log_info "Server logs:"
+    tail -100 /tmp/crawl4ai_server.log
+    exit 1
+fi
+
+# Step 8: Cleanup happens automatically via trap
+log_success "All tests completed successfully! 🎉"
+log_info "Cleanup will happen automatically..."