This release improves GitHub Copilot integration with better API routing and error handling, along with enhanced conversation state management and expanded documentation.
Bug Fixes
- Fixes GitHub Copilot Responses API auto-selection and error preservation to properly route models to correct endpoints
- Prevents X-Conversation-Id from mutating cached session on retry by making continuations transactional
- Preserves item value fields and Ask permission in Session.Clone operations
- Implements deep-copy for Evals, EvalResult, and ToolDefinitions in session clones
- Updates github-copilot model from gpt-4o to gpt-4.1 to match available models
Technical Changes
- Freezes configuration schema v9 and starts v10 as latest version
- Adds comprehensive documentation for coding harnesses, caching, lifecycle, defer, and fetch filtering
- Adds end-to-end tests for conversation state handling across failed turns
What's Changed
- docs: update CHANGELOG.md for v1.70.2 by @docker-read-write[bot] in #2951
- docs: document coding harnesses and fill P0/P1/P2 documentation gaps by @aheritier in #2950
- fix: keep failed chat continuations out of conversation cache by @dgageot in #2947
- fix: github-copilot Responses API auto-selection and error preservation by @dgageot in #2942
- fix: update github-copilot model from gpt-4o to gpt-4.1 by @dgageot in #2961
- chore(config): freeze v9 and bump latest to v10 by @dgageot in #2960
Full Changelog: v1.70.2...v1.71.0