docker-agent

This release improves error handling for model context overflow, adds external coding harness support, and includes numerous TUI fixes and performance optimizations.

What's New

• Adds external coding harness agents that delegate coding tasks to external coding CLIs
• Adds support for running context: fork slash commands as sub-sessions instead of inlining them
• Adds docker-agent kit staging in sandbox with skills and prompt files

Improvements

• Classifies overflow errors by kind to provide more specific error messages for different types of context window issues
• Optimizes session browser rendering to only render visible window rows for better performance with large session histories
• Improves shutdown safety by racing Wait() against deadline and calling ReleaseTerminal on timeout
• Updates Gemini adapter to forward stream chunks that carry only UsageMetadata for accurate token counting

Bug Fixes

• Fixes URL clicks in TUI by properly handling mouse events
• Fixes crash prevention by not notifying on click if the agent didn't change
• Fixes deadlock in TUI exit safety net and race conditions in shutdown handling
• Fixes auto-scroll blocking user scroll in long elicitation dialogs
• Fixes MCP tool name prefix stripping in callTool functionality
• Fixes OpenAI strict mode support for Notion and Jira MCP tools with gpt-5
• Fixes user_prompt dialog to open scrolled to top and respect user scrolling
• Fixes keychain prompts in tests by using in-memory token store
• Fixes MCP OAuth handler to drop stray callbacks and respond with proper HTTP status codes

Technical Changes

• Bounds three previously-unbounded caches to prevent memory growth on long sessions
• Uses SSRF-safe HTTP client for remote skills registry
• Honors Cache-Control headers properly in skills caching
• Extracts lrucache package and bounds unbounded caches
• Refactors model override into runAgent request body for atomic model selection
• Updates Grok example to use grok-4.3 model
• Treats wezterm as a terminal that handles shift+enter properly
• Adds clean task to remove generated binary
• Updates various dependencies including Anthropic SDK, AWS Bedrock runtime, and Docker CLI

What's Changed

• docs: update CHANGELOG.md for v1.61.0 by @docker-read-write[bot] in https://github.com/docker/docker-agent/pull/2822
• modelerrors: make overflow errors more specific by @trungutt in https://github.com/docker/docker-agent/pull/2818
• Add .cache to .gitignore by @rumpl in https://github.com/docker/docker-agent/pull/2827
• Treat wezterm as a terminal that knows how to handle shift+enter by @rumpl in https://github.com/docker/docker-agent/pull/2825
• Don't notify on click if the agent didn't change by @rumpl in https://github.com/docker/docker-agent/pull/2824
• tui: Fix URL clicks by @vvoland in https://github.com/docker/docker-agent/pull/2823
• feat: add external coding harness agents by @rumpl in https://github.com/docker/docker-agent/pull/2826
• perf(tui): only render visible session rows in /sessions dialog by @dgageot in https://github.com/docker/docker-agent/pull/2830
• docs: document allow_private_ips option and SSRF protection in fetch tool by @dgageot in https://github.com/docker/docker-agent/pull/2833
• fix(tui): bound previously-unbounded caches to prevent OOM on long sessions by @dgageot in https://github.com/docker/docker-agent/pull/2831
• Misc Security fixes by @dgageot in https://github.com/docker/docker-agent/pull/2820
• fix: use in-memory token store in tests to avoid OS keychain prompt by @dgageot in https://github.com/docker/docker-agent/pull/2836
• fix MCP tool name prefix stripping in callTool by @dgageot in https://github.com/docker/docker-agent/pull/2837
• chore(examples): remove shebang lines and executable bits by @dgageot in https://github.com/docker/docker-agent/pull/2838
• docs(memory): fix incorrect default database path placeholder by @kenijkawada in https://github.com/docker/docker-agent/pull/2835
• fix(tui): user_prompt dialog opens scrolled to top and respects user scrolling by @dgageot in https://github.com/docker/docker-agent/pull/2843
• feat(mcpcatalog): hide disable / reset_auth tools when no server is enabled by @dgageot in https://github.com/docker/docker-agent/pull/2840
• fix(tui): restore terminal on Ctrl-C when bubbletea shutdown stalls by @dgageot in https://github.com/docker/docker-agent/pull/2842
• fix(examples): update grok example to use grok-4.3 by @dgageot in https://github.com/docker/docker-agent/pull/2846
• chore: add clean task to remove generated binary by @dgageot in https://github.com/docker/docker-agent/pull/2847
• test(server): make TestAttachedServer_DeleteSessionStopsEventStream more robust by @dgageot in https://github.com/docker/docker-agent/pull/2845
• chore: bump direct Go dependencies by @dgageot in https://github.com/docker/docker-agent/pull/2849
• fix(openai): support Notion and Jira MCP tools with gpt-5 strict mode by @dgageot in https://github.com/docker/docker-agent/pull/2839
• fix(gemini): forward stream chunks that carry only UsageMetadata by @kenijkawada in https://github.com/docker/docker-agent/pull/2848
• docs+config: surface the two env-variable expansion syntaxes (#2615) by @dgageot in https://github.com/docker/docker-agent/pull/2851
• feat(skills): run context: fork slash commands as sub-sessions by @dgageot in https://github.com/docker/docker-agent/pull/2850
• refactor(api): fold model override into runAgent request body by @dgageot in https://github.com/docker/docker-agent/pull/2852
• feat(sandbox): docker-agent kit, gateway allowlist, and assorted --sandbox fixes by @dgageot in https://github.com/docker/docker-agent/pull/2844

New Contributors

• @kenijkawada made their first contribution in https://github.com/docker/docker-agent/pull/2835

Full Changelog: https://github.com/docker/docker-agent/compare/v1.61.0...v1.62.0