O-series (o1, o3) and GPT-5 models only support temperature=1.
Setting litellm.drop_params=True auto-drops unsupported parameters
instead of throwing UnsupportedParamsError.
Fixes temperature=0.01 error for these models in LLM extraction.
- Extract prompt building to shared _build_schema_prompt() method
- Add agenerate_schema() async version using aperform_completion_with_backoff
- Refactor generate_schema() to use shared prompt builder
- Fixes Gemini/Vertex AI compatibility in async contexts (FastAPI)
Security fixes for vulnerabilities reported by ProjectDiscovery:
1. Remote Code Execution via Hooks (CVE pending)
- Remove __import__ from allowed_builtins in hook_manager.py
- Prevents arbitrary module imports (os, subprocess, etc.)
- Hooks now disabled by default via CRAWL4AI_HOOKS_ENABLED env var
2. Local File Inclusion via file:// URLs (CVE pending)
- Add URL scheme validation to /execute_js, /screenshot, /pdf, /html
- Block file://, javascript:, data: and other dangerous schemes
- Only allow http://, https://, and raw: (where appropriate)
3. Security hardening
- Add CRAWL4AI_HOOKS_ENABLED=false as default (opt-in for hooks)
- Add security warning comments in config.yml
- Add validate_url_scheme() helper for consistent validation
Testing:
- Add unit tests (test_security_fixes.py) - 16 tests
- Add integration tests (run_security_tests.py) for live server
Affected endpoints:
- POST /crawl (hooks disabled by default)
- POST /crawl/stream (hooks disabled by default)
- POST /execute_js (URL validation added)
- POST /screenshot (URL validation added)
- POST /pdf (URL validation added)
- POST /html (URL validation added)
Breaking changes:
- Hooks require CRAWL4AI_HOOKS_ENABLED=true to function
- file:// URLs no longer work on API endpoints (use library directly)
Add documentation explaining how to pass multiple HTML samples
to generate_schema() for stable selectors that work across pages
with varying DOM structures.
Includes:
- Problem explanation (fragile nth-child selectors)
- Solution with code example
- Key points for multi-sample queries
- Comparison table of fragile vs stable selectors
- Add cache_ttl_hours and validate_sitemap_lastmod params to SeedingConfig
- New JSON cache format with metadata (version, created_at, lastmod, url_count)
- Cache validation by TTL expiry and sitemap lastmod comparison
- Auto-migration from old .jsonl to new .json format
- Fixes bug where incomplete cache was used indefinitely
- Add process_in_browser parameter to CrawlerRunConfig
- Route raw:/file:// URLs through _crawl_web() when browser operations needed
- Use page.set_content() instead of goto() for local content
- Fix cookie handling for non-HTTP URLs in browser_manager
- Auto-detect browser requirements: js_code, wait_for, screenshot, etc.
- Maintain fast path for raw:/file:// without browser params
Fixes#310
- Add `prefetch` parameter to CrawlerRunConfig
- Add `quick_extract_links()` function for fast link extraction
- Add short-circuit in aprocess_html() for prefetch mode
- Add 42 tests (unit, integration, regression)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When processing raw: HTML (e.g., from cache), the URL parameter is meaningless
for markdown link resolution. This adds a base_url parameter that can be set
explicitly to provide proper URL resolution context.
Changes:
- Add base_url parameter to CrawlerRunConfig.__init__
- Add base_url to CrawlerRunConfig.from_kwargs
- Update aprocess_html to use base_url for markdown generation
Usage:
config = CrawlerRunConfig(base_url='https://example.com')
result = await crawler.arun(url='raw:{html}', config=config)
The AsyncHTTPCrawlerStrategy.crawl() method used urlparse() to extract
content from raw: URLs. This caused HTML with CSS color codes like #eee
to be truncated because # is treated as a URL fragment delimiter.
Before: raw:body{background:#eee} -> parsed.path = 'body{background:'
After: raw:body{background:#eee} -> raw_content = 'body{background:#eee'
Fix: Strip the raw: or raw:// prefix directly instead of using urlparse,
matching how the browser strategy handles it.
Add optional resume_state and on_state_change parameters to all deep
crawl strategies (BFS, DFS, Best-First) for cloud deployment crash
recovery.
Features:
- resume_state: Pass saved state to resume from checkpoint
- on_state_change: Async callback fired after each URL for real-time
state persistence to external storage (Redis, DB, etc.)
- export_state(): Get last captured state manually
- Zero overhead when features are disabled (None defaults)
State includes visited URLs, pending queue/stack, depths, and
pages_crawled count. All state is JSON-serializable.
- Replace _generate_screenshot_from_html with _generate_media_from_html
- New method handles screenshot, PDF, and MHTML in one browser session
- Update raw: and file:// URL handlers to use new method
- Enables cached HTML to generate all media types
Implements the missing method that was being called but never defined.
Now raw: and file:// URLs can generate screenshots by:
1. Loading HTML into a browser page via page.set_content()
2. Taking screenshot using existing take_screenshot() method
3. Cleaning up the page afterward
This enables cached HTML to be rendered with screenshots in crawl4ai-cloud.
Changes to browser_manager.py:
1. _verify_cdp_ready(): Support multiple URL formats
- WebSocket URLs (ws://, wss://): Skip HTTP verification, Playwright handles directly
- HTTP URLs with query params: Properly parse with urlparse to preserve query string
- Fixes issue where naive f"{cdp_url}/json/version" broke WS URLs and query params
2. close(): Proper cleanup when cdp_cleanup_on_close=True
- Close all sessions (pages)
- Close all contexts
- Call browser.close() to disconnect (doesn't terminate browser, just releases connection)
- Wait 1 second for CDP connection to fully release
- Stop Playwright instance to prevent memory leaks
This enables:
- Connecting to specific browsers via WS URL
- Reusing the same browser with multiple sequential connections
- No user wait needed between connections (internal 1s delay handles it)
Added tests/browser/test_cdp_cleanup_reuse.py with comprehensive tests.
This adds the ability to inject JavaScript that runs before any page loads,
useful for stealth evasions (canvas/audio fingerprinting, userAgentData).
- Add init_scripts parameter to BrowserConfig (list of JS strings)
- Apply init_scripts in setup_context() via context.add_init_script()
- Update from_kwargs() and to_dict() for serialization
Uses contexts_by_config cache (same as non-CDP mode) to reuse contexts
for multiple URLs with same config. Still creates new page per crawl
for navigation isolation. Benefits batch/deep crawls.
When True, forces creation of a new browser context instead of reusing
the default context. Essential for concurrent crawls on the same browser
to prevent navigation conflicts.
Enable Crawl4AI to connect to pre-created CDP browser contexts, which is
essential for cloud browser services that pre-create isolated contexts.
Changes:
- Add browser_context_id and target_id parameters to BrowserConfig
- Update from_kwargs() and to_dict() methods
- Modify BrowserManager.start() to use existing context when provided
- Add _get_page_by_target_id() helper method
- Update get_page() to handle pre-existing targets
- Add test for browser_context_id functionality
This enables cloud services to:
1. Create isolated CDP contexts before Crawl4AI connects
2. Pass context/target IDs to BrowserConfig
3. Have Crawl4AI reuse existing contexts instead of creating new ones
* Fix: Use correct URL variable for raw HTML extraction (#1116)
- Prevents full HTML content from being passed as URL to extraction strategies
- Added unit tests to verify raw HTML and regular URL processing
Fix: Wrong URL variable used for extraction of raw html
* Fix#1181: Preserve whitespace in code blocks during HTML scraping
The remove_empty_elements_fast() method was removing whitespace-only
span elements inside <pre> and <code> tags, causing import statements
like "import torch" to become "importtorch". Now skips elements inside
code blocks where whitespace is significant.
* Refactor Pydantic model configuration to use ConfigDict for arbitrary types
* Fix EmbeddingStrategy: Uncomment response handling for the variations and clean up mock data. ref #1621
* Fix: permission issues with .cache/url_seeder and other runtime cache dirs. ref #1638
* fix: ensure BrowserConfig.to_dict serializes proxy_config
* feat: make LLM backoff configurable end-to-end
- extend LLMConfig with backoff delay/attempt/factor fields and thread them
through LLMExtractionStrategy, LLMContentFilter, table extraction, and
Docker API handlers
- expose the backoff parameter knobs on perform_completion_with_backoff/aperform_completion_with_backoff
and document them in the md_v2 guides
* reproduced AttributeError from #1642
* pass timeout parameter to docker client request
* added missing deep crawling objects to init
* generalized query in ContentRelevanceFilter to be a str or list
* import modules from enhanceable deserialization
* parameterized tests
* Fix: capture current page URL to reflect JavaScript navigation and add test for delayed redirects. ref #1268
* refactor: replace PyPDF2 with pypdf across the codebase. ref #1412
* announcement: add application form for cloud API closed beta
* Release v0.7.8: Stability & Bug Fix Release
- Updated version to 0.7.8
- Introduced focused stability release addressing 11 community-reported bugs.
- Key fixes include Docker API improvements, LLM extraction enhancements, URL handling corrections, and dependency updates.
- Added detailed release notes for v0.7.8 in the blog and created a dedicated verification script to ensure all fixes are functioning as intended.
- Updated documentation to reflect recent changes and improvements.
* docs: add section for Crawl4AI Cloud API closed beta with application link
* fix: add disk cleanup step to Docker workflow
---------
Co-authored-by: rbushria <rbushri@gmail.com>
Co-authored-by: AHMET YILMAZ <tawfik@kidocode.com>
Co-authored-by: Soham Kukreti <kukretisoham@gmail.com>
Co-authored-by: Chris Murphy <chris.murphy@klaviyo.com>
Co-authored-by: Aravind Karnam <aravind.karanam@gmail.com>
