docker-agent

This release adds XML tool call parsing for better model compatibility, performance improvements for TUI rendering, and enhanced remote runtime capabilities.

What's New

• Adds XML tool call fallback parsing for models that return <tool_call>...</tool_call> text instead of using OpenAI function-calling API
• Adds fd:// scheme support to server.Listen for parent process socket passing
• Adds per-code-block copy affordance with clickable copy glyphs in TUI
• Adds session persistence and resumption for A2A (agent-to-agent) interactions using SQLite
• Adds comprehensive remote runtime API with SSE event streaming, session management, and graceful degradation

Improvements

• Improves TUI rendering performance with cached output, targeted invalidation, and incremental markdown rendering
• Improves ACP support with session management, event handling, and structured error codes
• Preserves user input across tab switches in TUI dialogs

Bug Fixes

• Fixes crash during tool auto-install by adding panic recovery
• Fixes SSE stream cancellation and IPv6 address binding issues
• Fixes Vertex AI Model Garden provider capability lookups by rewriting provider to publisher mapping

Technical Changes

• Replaces internal secretsscan with github.com/docker/portcullis library
• Centralizes modelsdev.Store creation via RuntimeConfig with lazy initialization
• Merges modelcaps into modelinfo and introduces strongly-typed modelsdev.ID
• Refactors event handling to use EventSink interface instead of channel threading
• Removes experimental send, watch, and proto subcommands

What's Changed

• docs: update CHANGELOG.md for v1.58.0 by @docker-read-write[bot] in https://github.com/docker/docker-agent/pull/2745
• feat: add fd:// scheme support to server.Listen by @dgageot in https://github.com/docker/docker-agent/pull/2744
• refactor: replace internal secretsscan with github.com/docker/portcullis by @dgageot in https://github.com/docker/docker-agent/pull/2747
• refactor: centralize modelsdev.Store creation and inject via RuntimeConfig by @dgageot in https://github.com/docker/docker-agent/pull/2746
• docs: Docker-branded redesign with dark-mode-first theme and improved homepage by @dgageot in https://github.com/docker/docker-agent/pull/2750
• feat(modelsdev): add WithCache option to override cache file path by @rumpl in https://github.com/docker/docker-agent/pull/2753
• feat: wire TUI/CLI to emit Document parts and render attachments by @simonferquel-clanker in https://github.com/docker/docker-agent/pull/2751
• fix: avoid sub-agent terminology in skill instructions to prevent transfer_task confusion by @dgageot in https://github.com/docker/docker-agent/pull/2748
• refactor: merge modelcaps into modelinfo and simplify by @dgageot in https://github.com/docker/docker-agent/pull/2755
• refactor: simplify RuntimeConfig by removing dead field and caching env provider by @dgageot in https://github.com/docker/docker-agent/pull/2754
• refactor: extract loopState struct to bundle runTurn parameters by @dgageot in https://github.com/docker/docker-agent/pull/2759
• feat: add docs preview workflow for PRs by @dgageot in https://github.com/docker/docker-agent/pull/2752
• feat(runtime): remote runtime with full TUI parity and production readiness by @dgageot in https://github.com/docker/docker-agent/pull/2749
• feat(a2a): allow session to be resumed interactively by @maxcleme in https://github.com/docker/docker-agent/pull/2762
• feat: improve TUI control plane API for external consumers by @dgageot in https://github.com/docker/docker-agent/pull/2757
• perf: TUI rendering performance improvements by @dgageot in https://github.com/docker/docker-agent/pull/2756
• drop send, watch and proto subcommands by @dgageot in https://github.com/docker/docker-agent/pull/2763
• xml fallback for llama.cpp models by @areebahmeddd in https://github.com/docker/docker-agent/pull/2732
• refactor: replace chan Event threading with EventSink interface by @dgageot in https://github.com/docker/docker-agent/pull/2760
• Improve ACP support: session management, event handling, and code simplification by @dgageot in https://github.com/docker/docker-agent/pull/2758
• refactor: introduce modelsdev.ID for provider-qualified model identity by @dgageot in https://github.com/docker/docker-agent/pull/2766
• fix(toolinstall): recover from panics during auto-install by @dgageot in https://github.com/docker/docker-agent/pull/2768
• fix: rewrite Vertex AI Model Garden provider to publisher for capability lookups by @dgageot in https://github.com/docker/docker-agent/pull/2767
• bump direct go dependencies by @dgageot in https://github.com/docker/docker-agent/pull/2771
• Fix linter by @dgageot in https://github.com/docker/docker-agent/pull/2772
• fix(tui): preserve user_prompt input across tab switches by @dgageot in https://github.com/docker/docker-agent/pull/2774
• perf(tui): make streaming chunk rendering linear by @dgageot in https://github.com/docker/docker-agent/pull/2773
• fix: two TUI control-plane bugs (SSE cancel, IPv6 listen) by @dgageot in https://github.com/docker/docker-agent/pull/2775
• set working dir properly by @krissetto in https://github.com/docker/docker-agent/pull/2777
• feat(tui): add per-code-block copy affordance by @rumpl in https://github.com/docker/docker-agent/pull/2778

New Contributors

• @areebahmeddd made their first contribution in https://github.com/docker/docker-agent/pull/2732

Full Changelog: https://github.com/docker/docker-agent/compare/v1.58.0...v1.59.0