- Implemented `test_adapter_verification.py` to verify correct usage of browser adapters.
- Created `test_all_features.py` for a comprehensive suite covering URL seeding, adaptive crawling, browser adapters, proxy rotation, and dispatchers.
- Developed `test_anti_bot_strategy.py` to validate the functionality of various anti-bot strategies.
- Added `test_antibot_simple.py` for simple testing of anti-bot strategies using async web crawling.
- Introduced `test_bot_detection.py` to assess adapter performance against bot detection mechanisms.
- Compiled `test_final_summary.py` to provide a detailed summary of all tests and their results.
- Implemented demo_proxy_rotation.py to showcase various proxy rotation strategies and their integration with the API.
- Included multiple demos demonstrating round robin, random, least used, failure-aware, and streaming strategies.
- Added error handling and real-world scenario examples for e-commerce price monitoring.
- Created quick_proxy_test.py to validate API integration without real proxies, testing parameter acceptance, invalid strategy rejection, and optional parameters.
- Ensured both scripts provide informative output and usage instructions.
Implement hierarchical configuration for LLM parameters with support for:
- Temperature control (0.0-2.0) to adjust response creativity
- Custom base_url for proxy servers and alternative endpoints
- 4-tier priority: request params > provider env > global env > defaults
Add helper functions in utils.py, update API schemas and handlers,
support environment variables (LLM_TEMPERATURE, OPENAI_TEMPERATURE, etc.),
and provide comprehensive documentation with examples.
- Support LLM_PROVIDER env var to override default provider (openai/gpt-4o-mini)
- Add optional 'provider' parameter to API endpoints for per-request overrides
- Implement provider validation to ensure API keys exist
- Update documentation and examples with new configuration options
Closes the need to hardcode providers in config.yml
Revised the description for the `f` parameter in the `/mcp/md` tool schema to use lowercase enum values
(`raw`, `fit`, `bm25`, `llm`) for consistency with the actual `enum` definition. This change prevents
LLM-based clients (e.g., Gemini via LibreChat) from generating uppercase values like `"FIT"`, which
caused 422 validation errors due to strict case-sensitive matching.
Implements new asynchronous endpoints for handling long-running crawl and LLM tasks:
- POST /crawl/job and GET /crawl/job/{task_id} for crawl operations
- POST /llm/job and GET /llm/job/{task_id} for LLM operations
- Added Redis-based task management with configurable TTL
- Moved schema definitions to dedicated schemas.py
- Added example polling client demo_docker_polling.py
This change allows clients to handle long-running operations asynchronously through a polling pattern rather than holding connections open.
