docker-agent

This release brings significant new capabilities including a safety-check hook system, TUI improvements with retry support and new slash commands, expanded hook and config features, and a large number of internal quality improvements around context threading, linting, and test performance.

What's New

• Adds usage and cost fields to the after_llm_call hook payload, exposing per-turn token usage and computed USD cost
• Adds a triage-prs skill for triaging open pull requests
• Adds a TUI e2e test harness (tuitest) with VCR cassette support, plus live/frame-dump debugging, mouse, and clipboard helpers
• Adds a retry button to TUI error messages, allowing one-click recovery after agent turn failures
• Adds key/value metadata field to tool-call confirmation events, rendered in the TUI confirmation dialog
• Adds ${env.X} expansion support in toolset env values (in addition to the existing ${X} syntax)
• Adds triage-prs skill for automated PR classification and triage
• Adds fork suffix deduplication across sibling forks so parallel forks of the same parent get unique (fork N) suffixes
• Adds tool-scoping for fork-mode skills via allowed_tools and toolsets frontmatter fields
• Adds url field support in agent /commands config, opening a URL in the user's default browser instead of sending a prompt
• Adds {{session_id}} expansion in URL commands
• Persists agent failures as first-class Error session items so errors survive session reload and appear in the TUI
• Adds instruction_file field to agent config for referencing external instruction files
• Adds open_url built-in toolset for agents to open a configured URL in the user's default browser
• Adds preempt_yolo flag on pre_tool_use hook entries and a safer_shell builtin that classifies shell commands and forces confirmation for destructive operations
• Adds file-based plan revisions, free-form status field, and optimistic locking to the plan toolset, including new export_plan_to_file and update_plan_from_file tools
• Embeds a models.dev catalog snapshot as a binary fallback for offline/air-gapped environments
• Adds timing instrumentation to the model picker pipeline
• Adds /feedback and /bug slash commands to the TUI
• Adds WrapErrors lint cop to catch fmt.Errorf calls that discard error chains
• Adds constructor side-effect lint cops preventing goroutines, command execution, and network I/O in constructors
• Adds deferred mutex unlock lint cop and converts existing terminal unlocks to deferred form
• Adds ContextConnectivity whole-program lint cop and threads context throughout the codebase
• Builtin hooks now honor working_dir and env fields

Improvements

• Returns 1,000,000-token context window for Claude Opus 4.6/4.7/4.8 families instead of the 200k fallback
• Reuses a single warmed models.dev store across runtime, server, and embedded-chat paths instead of warming independently per session
• Caps oversized tool result payloads (filesystem, shell, MCP, and A2A) at 2,000 lines / 50 KiB, saving the full output to a temp file
• Removes redundant agent-switch and thinking-level toast notifications whose results are already visible in the UI
• Speeds up Go test suite by ~37% with shared shims and offline fixtures

Bug Fixes

• Fixes per-model attachment capability override so custom/aliased OpenAI-compatible providers (Ollama, xai, mistral, etc.) can declare image/PDF support when absent from models.dev
• Fixes cycling thinking level in the lean TUI via Shift+Tab
• Fixes ctrl+1–ctrl+9 agent quick-switch shortcuts broken under the Kitty keyboard protocol
• Fixes lock-state modifiers being incorrectly applied to ctrl+N agent switch
• Fixes MCP OAuth token persistence in sandboxes by falling back to a file-backed keyring when the OS keyring is unavailable, using a per-install random passphrase
• Fixes data races in scroll state and session store updates
• Fixes suppression of re-emitted UserMessageEvent before StreamStarted on retry
• Fixes ~ expansion to respect the HOME environment variable before falling back to os.UserHomeDir()
• Fixes DMR model selection to prefer locally pulled models and surface actionable pull errors
• Fixes recovery from corrupted partial model downloads (HTTP 416)
• Fixes URL validation before handing URLs to the OS opener
• Fixes context cancellation being passed to the browser opener (strips it before launch)
• Fixes Tool.Metadata serialization to avoid duplicate/stale wire fields
• Fixes session working directory usage in TUI so /shell opens in the worktree directory rather than the process CWD
• Fixes context-cancelled errors being cached in the model picker
• Fixes branching and cloning sessions that contain error items

Technical Changes

• Freezes config schema v10 and starts v11 as latest
• Parallelizes build-image CI job across native runners
• Switches CI Task installation from source compilation to prebuilt binary (~51s → 1s)
• Adds t.Parallel() to 1,216 eligible top-level tests across 165 files
• Refactors Coordinator methods to be receiver-based, keeping package-level shims for compatibility
• Extracts buildDefaultStore for testability and adds fallback-ordering tests
• Extracts isClaudeOpus46To48 helper to deduplicate Opus matching logic
• Threads context through Runtime interface methods, RAG helpers, DB setup, memory initialization, sound playback, and other call paths
• Uses context.WithoutCancel for shutdown and flush paths
• Resolves proxy allowlist at dial time and caches it at construction
• Speeds up custom linters using new rubocop-go helpers

What's Changed

• feat(skills): add triage-prs skill by @aheritier in https://github.com/docker/docker-agent/pull/3249
• freeze config v10 and start v11 as latest by @dgageot in https://github.com/docker/docker-agent/pull/3248
• fix: cycle thinking level in lean tui by @rumpl in https://github.com/docker/docker-agent/pull/3246
• docs: update CHANGELOG.md for v1.88.1 by @docker-read-write[bot] in https://github.com/docker/docker-agent/pull/3251
• feat: add TUI e2e test harness by @dgageot in https://github.com/docker/docker-agent/pull/3252
• feat: add retry button to TUI error messages by @dgageot in https://github.com/docker/docker-agent/pull/3253
• fix(providers): add per-model attachment capability override (#2741) by @Sayt-0 in https://github.com/docker/docker-agent/pull/3205
• feat(server): bump fork suffix across sibling forks by @trungutt in https://github.com/docker/docker-agent/pull/3254
• ci: parallelize build-image across native runners by @dgageot in https://github.com/docker/docker-agent/pull/3258
• feat(config): accept ${env.X} in toolset env values (#2615) by @dgageot in https://github.com/docker/docker-agent/pull/3257
• feat: support URL-opening /commands in agent config by @dgageot in https://github.com/docker/docker-agent/pull/3261
• refactor(tui): remove redundant agent-switch and thinking-level toasts by @dgageot in https://github.com/docker/docker-agent/pull/3266
• feat: return 1M context for Claude Opus 4.6/4.7/4.8 families by @dgageot in https://github.com/docker/docker-agent/pull/3267
• feat: persist agent failures in the session by @dgageot in https://github.com/docker/docker-agent/pull/3259
• feat: add tool-scoping for fork-mode skills by @dgageot in https://github.com/docker/docker-agent/pull/3260
• fix(tui): restore ctrl+1..ctrl+9 agent quick-switch shortcuts by @dgageot in https://github.com/docker/docker-agent/pull/3265
• fix: persist MCP OAuth tokens in sandboxes via file-backed keyring fallback (#3037) by @dgageot in https://github.com/docker/docker-agent/pull/3255
• feat: add key/value metadata to tool-call confirmation events by @dgageot in https://github.com/docker/docker-agent/pull/3256
• docs: document URL-opening /commands and clean up /feedback and /bug by @dgageot in https://github.com/docker/docker-agent/pull/3270
• ci: install Task from prebuilt binary instead of compiling by @dgageot in https://github.com/docker/docker-agent/pull/3269
• fix(dmr): prefer local models and surface actionable pull errors by @Sayt-0 in https://github.com/docker/docker-agent/pull/3268
• feat(runtime): expose per-turn usage and cost in the after_llm_call hook payload by @kimizuka in https://github.com/docker/docker-agent/pull/2994
• feat(config): support external instruction files via instruction_file by @Sayt-0 in https://github.com/docker/docker-agent/pull/3272
• feat(plan): file-based revisions, free-form status, and optimistic locking by @Sayt-0 in https://github.com/docker/docker-agent/pull/3274
• docs(runtime): document StreamStopped ordering and teardown trade-offs (#3074) by @Sayt-0 in https://github.com/docker/docker-agent/pull/3275
• feat: add open_url built-in toolset by @dgageot in https://github.com/docker/docker-agent/pull/3276
• Remove thinking cycle notice by @rumpl in https://github.com/docker/docker-agent/pull/3280
• docs: document capabilities override and TUI error recovery by @aheritier in https://github.com/docker/docker-agent/pull/3283
• feat: reuse warmed model store, add picker timing, and fix discovery error caching by @dgageot in https://github.com/docker/docker-agent/pull/3285
• Add constructor side-effect lint cops by @dgageot in https://github.com/docker/docker-agent/pull/3289
• fix: open /shell in the session working directory (e.g. --worktree) by @dgageot in https://github.com/docker/docker-agent/pull/3286
• feat(modelsdev): embed models.dev catalog snapshot as binary fallback by @dgageot in https://github.com/docker/docker-agent/pull/3277
• lint: add WrapErrors cop by @dgageot in https://github.com/docker/docker-agent/pull/3287
• refactor: thread context throughout and enforce ContextConnectivity lint rule by @dgageot in https://github.com/docker/docker-agent/pull/3279
• feat(hooks): cap oversized tool result payloads by @rumpl in https://github.com/docker/docker-agent/pull/3290
• lint: enforce deferred mutex unlocks by @dgageot in https://github.com/docker/docker-agent/pull/3288
• Faster lint by @dgageot in https://github.com/docker/docker-agent/pull/3293
• test: speed up Go test suite by ~37% with shared shims and offline fixtures by @dgageot in https://github.com/docker/docker-agent/pull/3294
• feat: builtin hooks now honor working_dir and env by @dgageot in https://github.com/docker/docker-agent/pull/3295
• test: add t.Parallel() to eligible tests by @dgageot in https://github.com/docker/docker-agent/pull/3296
• feat: safety_check hook + safer_shell builtin by @melmennaoui in https://github.com/docker/docker-agent/pull/3273
• docs: replace stale safety_check references with preempt_yolo pre_tool_use by @dgageot in https://github.com/docker/docker-agent/pull/3297
• refactor: receiver-based Coordinator and parallel provider tests by @dgageot in https://github.com/docker/docker-agent/pull/3299
• fix(hooks): cap oversized mcp and a2a tool results by @Sayt-0 in https://github.com/docker/docker-agent/pull/3301
• chore: bump direct Go dependencies by @dgageot in https://github.com/docker/docker-agent/pull/3300
• fix: respect HOME env var when expanding ~ in paths by @Divyansh670 in https://github.com/docker/docker-agent/pull/3088

New Contributors

• @melmennaoui made their first contribution in https://github.com/docker/docker-agent/pull/3273
• @Divyansh670 made their first contribution in https://github.com/docker/docker-agent/pull/3088

Full Changelog: https://github.com/docker/docker-agent/compare/v1.88.1...v1.89.0