This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
ReleasePort's take
Moderate signalThe v1.71.0 release fixes several bugs in GitHub Copilot integrations and session handling while updating the configuration schema to version 10.
Why it matters: Severity 70 breaking change freezes config schema v9; all systems must migrate configurations to v10 before next deployment cycle.
Summary
AI summaryUpdates Technical Changes, Bug Fixes, and fix across a mixed release.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Breaking | High |
Freezes configuration schema v9 and starts v10 as latest version Freezes configuration schema v9 and starts v10 as latest version Source: llm_adapter@2026-06-02 Confidence: high |
— |
| Feature | Low |
Adds comprehensive documentation for coding harnesses, caching, lifecycle, defer, and fetch filtering Adds comprehensive documentation for coding harnesses, caching, lifecycle, defer, and fetch filtering Source: llm_adapter@2026-06-02 Confidence: high |
— |
| Feature | Low |
Adds end-to-end tests for conversation state handling across failed turns Adds end-to-end tests for conversation state handling across failed turns Source: llm_adapter@2026-06-02 Confidence: high |
— |
| Dependency | Medium |
Updates GitHub Copilot model from gpt-4o to gpt-4.1 to match available models Updates GitHub Copilot model from gpt-4o to gpt-4.1 to match available models Source: llm_adapter@2026-06-02 Confidence: high |
— |
| Bugfix | Medium |
Fixes GitHub Copilot Responses API auto-selection and error preservation to properly route models to correct endpoints Fixes GitHub Copilot Responses API auto-selection and error preservation to properly route models to correct endpoints Source: llm_adapter@2026-06-02 Confidence: high |
— |
| Bugfix | Medium |
Prevents X-Conversation-Id from mutating cached session on retry by making continuations transactional Prevents X-Conversation-Id from mutating cached session on retry by making continuations transactional Source: llm_adapter@2026-06-02 Confidence: high |
— |
| Bugfix | Medium |
Preserves item value fields and Ask permission in Session.Clone operations Preserves item value fields and Ask permission in Session.Clone operations Source: llm_adapter@2026-06-02 Confidence: high |
— |
| Bugfix | Medium |
Implements deep-copy for Evals, EvalResult, and ToolDefinitions in session clones Implements deep-copy for Evals, EvalResult, and ToolDefinitions in session clones Source: llm_adapter@2026-06-02 Confidence: high |
— |
Full changelog
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 https://github.com/docker/docker-agent/pull/2951
- docs: document coding harnesses and fill P0/P1/P2 documentation gaps by @aheritier in https://github.com/docker/docker-agent/pull/2950
- fix: keep failed chat continuations out of conversation cache by @dgageot in https://github.com/docker/docker-agent/pull/2947
- fix: github-copilot Responses API auto-selection and error preservation by @dgageot in https://github.com/docker/docker-agent/pull/2942
- fix: update github-copilot model from gpt-4o to gpt-4.1 by @dgageot in https://github.com/docker/docker-agent/pull/2961
- chore(config): freeze v9 and bump latest to v10 by @dgageot in https://github.com/docker/docker-agent/pull/2960
Full Changelog: https://github.com/docker/docker-agent/compare/v1.70.2...v1.71.0
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
Related context
Related tools
Beta — feedback welcome: [email protected]