docker-agent 1.112.0

[BrewTestBot]

Created by brew bump

---

Created with brew bump-formula-pr.

Details

release notes

This release adds several new built-in toolsets (git, webhook), budget limits, `.agentsignore` support, expanded Mermaid rendering, image rendering in the TUI, and numerous TUI improvements including per-agent usage details, session browser enhancements, and argument auto-completion for slash commands.
What's New

Adds a read-only git toolset (git_status, git_log, git_branches, git_show, git_blame) giving agents structured access to the working repository without requiring a git binary
Adds a webhook toolset with a send_webhook tool that lets agents send outbound notifications to a configured chat service without exposing the URL or secret to the model
Adds budget configuration (budget / budgets) to cap what an agent may spend in cost, tokens, or working time, with live tracking in the TUI sidebar
Adds .agentsignore support — a .gitignore-syntax file that prevents the agent from listing, reading, or writing matched files
Adds image rendering in the TUI for tool result images and markdown images in agent responses (using the Kitty graphics protocol, with a setting to disable)
Adds an image rendering preference to settings
Adds Mermaid flowchart direction support and subgraph rendering
Adds argument auto-completion for /toolset-restart, /drop, and /effort slash commands
Adds per-agent usage details to the TUI sidebar, with a new sidebar info mode selector in /settings
Adds fuzzy search matching for tool discovery via search_tool in the deferred toolset
Adds Claude Code harness setup and diagnostics as a new docker agent setup path
Adds explicit prompt cache breakpoint support for OpenAI (GPT-5.6+)
Extends session browser search to match session IDs in addition to titles
Groups the session browser by git repository root (worktree-aware)
Allows configuring compaction_model directly on an agent as a sibling to compaction_threshold
Opens the /cost dialog when clicking the sidebar cost/token usage reading
Adds a self-maintaining llms.txt generated from nav.yml at Hugo build time

Improvements

Fixes severe scrolling performance on very large sessions by caching rendered lines in the cost dialog and stopping message-list render cache thrashing
Keeps the /cost dialog cache fresh on live updates and theme changes
Shows usage and team roster in the collapsed sidebar band from startup
Adds sidebar agent info modes

Bug Fixes

Fixes RAG query embedding usage tracking so tokens are correctly attributed and emitted to the active session
Fixes telemetry model dimension pollution and captures partial usage in RAG
Fixes Anthropic system cache breakpoints being exceeded by capping them so requests never exceed the limit
Fixes transcripts carrying cache checkpoint marks after compaction
Fixes slash command inline completion to match on command value, not just label (e.g. typing /settings now surfaces the Settings command)
Fixes TUI panic when the terminal reports a degenerate (0×0 or 1×1) size
Fixes the /cost dialog cache not refreshing on live updates and theme changes
Fixes the sidebar scrollbar clicks registering in content click zones
Fixes the settings command label to display consistently as Settings
Fixes right-to-left Mermaid connector rendering
Fixes HTTP error statuses (4xx/5xx) being swallowed and treated as success in the API tool
Fixes webhook tool to sanitize *url.Error to prevent secret URL leakage
Fixes MCP OAuth clients with allow-private-ips to use a private connection pool instead of sharing http.DefaultTransport
Fixes flaky OAuth tests by not sharing http.DefaultTransport across parallel tests
Fixes the template Docker build stage to use COPY --from instead of an unauthenticated GitHub API call that hit rate limits
Removes macOS Keychain and pass secret providers from DefaultSources

Technical Changes

Freezes config schema v12 and opens v13 as the new latest
Refactors Anthropic prompt-cache checkpoint handling into consolidated owners, making known failure modes structurally impossible
Refreshes the embedded models.dev snapshot
Drops the unused benchmarks/ folder
Exposes the current agent's supported thinking levels from the runtime


What's Changed

Render images by @rumpl in Render images docker/docker-agent#3699
feat(docs): self-maintaining llms.txt generated from nav.yml by @aheritier in feat(docs): self-maintaining llms.txt generated from nav.yml docker/docker-agent#3695
fix(docs): constrain content images and shrink demo GIF by @aheritier in fix(docs): constrain content images and shrink demo GIF docker/docker-agent#3696
docs: update CHANGELOG.md for v1.111.0 by @docker-read-write[bot] in docs: update CHANGELOG.md for v1.111.0 docker/docker-agent#3703
docs: sync documentation with recent main merges by @aheritier in docs: sync documentation with recent main merges docker/docker-agent#3700
test(mcp): fix flaky OAuth tests by not sharing http.DefaultTransport by @dgageot in test(mcp): fix flaky OAuth tests by not sharing http.DefaultTransport docker/docker-agent#3704
feat(tools): add read-only "git" toolset for structured repository inspection by @dwin-gharibi in feat(tools): add read-only "git" toolset for structured repository inspection docker/docker-agent#3637
chore: bump direct Go dependencies by @dgageot in chore: bump direct Go dependencies docker/docker-agent#3706
fix(mcp): give allow-private-ips OAuth clients a private connection pool by @dgageot in fix(mcp): give allow-private-ips OAuth clients a private connection pool docker/docker-agent#3707
docs: add Sessions, Code Mode, headless/CI guide, and expand the CLI reference by @aheritier in docs: add Sessions, Code Mode, headless/CI guide, and expand the CLI reference docker/docker-agent#3694
feat(tui): extend session browser search to match session IDs by @dgageot in feat(tui): extend session browser search to match session IDs docker/docker-agent#3708
chore: drop benchmarks folder by @dgageot in chore: drop benchmarks folder docker/docker-agent#3709
docs: add tour pointer, prompt-files subsection, and product-naming consistency by @aheritier in docs: add tour pointer, prompt-files subsection, and product-naming consistency docker/docker-agent#3698
perf(tui): fix horrendous scrolling on very large sessions by @dgageot in perf(tui): fix horrendous scrolling on very large sessions docker/docker-agent#3710
refactor: consolidate and harden Anthropic prompt-cache checkpoint handling by @dgageot in refactor: consolidate and harden Anthropic prompt-cache checkpoint handling docker/docker-agent#3712
feat(env): remove macOS keychain and pass secret providers by @dgageot in feat(env): remove macOS keychain and pass secret providers docker/docker-agent#3713
Mermaid flowchart directions by @rumpl in Mermaid flowchart directions docker/docker-agent#3715
Mermaid flowchart subgraphs by @rumpl in Mermaid flowchart subgraphs docker/docker-agent#3716
fix: address Mermaid subgraph review findings by @rumpl in fix: address Mermaid subgraph review findings docker/docker-agent#3717
Use golden files for Mermaid renders by @rumpl in Use golden files for Mermaid renders docker/docker-agent#3718
fix(rag): correctly attribute and track query embedding usage for active sessions by @Piyush0049 in fix(rag): correctly attribute and track query embedding usage for active sessions docker/docker-agent#3603
Render markdown images in agent responses by @rumpl in Render markdown images in agent responses docker/docker-agent#3720
feat(tui): show usage details per agent by @Sayt-0 in feat(tui): show usage details per agent docker/docker-agent#3714
fix(tui): address PR #3720 review feedback on markdown image rendering by @dgageot in fix(tui): address PR #3720 review feedback on markdown image rendering docker/docker-agent#3721
feat(openai): support explicit prompt cache breakpoints by @Sayt-0 in feat(openai): support explicit prompt cache breakpoints docker/docker-agent#3719
fix(tui): match slash command value, not just label, in inline completion by @aheritier in fix(tui): match slash command value, not just label, in inline completion docker/docker-agent#3723
fix(tui): hide no-op slash commands (/settings) in lean mode by @aheritier in fix(tui): hide no-op slash commands (/settings) in lean mode docker/docker-agent#3724
fix(tui): label settings command consistently by @Sayt-0 in fix(tui): label settings command consistently docker/docker-agent#3726
fix(tui): show usage and team roster in the collapsed sidebar band from startup by @Sayt-0 in fix(tui): show usage and team roster in the collapsed sidebar band from startup docker/docker-agent#3727
revert: pkg/tui lean-mode machinery from #3724 by @aheritier in revert: pkg/tui lean-mode machinery from #3724 docker/docker-agent#3729
feat(tui): argument auto-completion for /toolset-restart by @aheritier in feat(tui): argument auto-completion for /toolset-restart docker/docker-agent#3728
feat: add Claude Code harness setup and diagnostics by @Sayt-0 in feat: add Claude Code harness setup and diagnostics docker/docker-agent#3722
docs: update documentation for recent merged PRs by @aheritier in docs: update documentation for recent merged PRs docker/docker-agent#3735
fix(tui): don't panic when the terminal reports a degenerate size by @dgageot in fix(tui): don't panic when the terminal reports a degenerate size docker/docker-agent#3736
feat: group session browser by git repo root (worktree-aware) by @dgageot in feat: group session browser by git repo root (worktree-aware) docker/docker-agent#3737
feat(deferred): add fuzzy search matching for tool discovery by @Piyush0049 in feat(deferred): add fuzzy search matching for tool discovery docker/docker-agent#3738
feat(tui): argument auto-completion for /effort by @aheritier in feat(tui): argument auto-completion for /effort docker/docker-agent#3734
feat(tui): argument auto-completion for /drop by @aheritier in feat(tui): argument auto-completion for /drop docker/docker-agent#3733
fix: use COPY --from for mcp-gateway in template stage by @aheritier in fix: use COPY --from for mcp-gateway in template stage docker/docker-agent#3744
docs: sync documentation with recent code changes by @aheritier in docs: sync documentation with recent code changes docker/docker-agent#3741
chore(deps): bump mcp from 1.23.0 to 1.28.1 in /examples/dhi/dhi_mcp_server in the pip group across 1 directory by @dependabot[bot] in chore(deps): bump mcp from 1.23.0 to 1.28.1 in /examples/dhi/dhi_mcp_server in the pip group across 1 directory docker/docker-agent#3740
fix: propagate HTTP error statuses in API tool by @Piyush0049 in fix: propagate HTTP error statuses in API tool docker/docker-agent#3739
feat(filesystem): add .agentsignore to keep files out of the agent's reach by @dwin-gharibi in feat(filesystem): add .agentsignore to keep files out of the agent's reach docker/docker-agent#3743
feat(budget): cap what an agent may spend in money, tokens, or working time by @dwin-gharibi in feat(budget): cap what an agent may spend in money, tokens, or working time docker/docker-agent#3702
chore: refresh embedded models.dev snapshot by @github-actions[bot] in chore: refresh embedded models.dev snapshot docker/docker-agent#3747
feat(tools): add "webhook" toolset for outbound notifications by @dwin-gharibi in feat(tools): add "webhook" toolset for outbound notifications docker/docker-agent#3641
feat: allow configuring compaction_model on agents by @dgageot in feat: allow configuring compaction_model on agents docker/docker-agent#3752
feat(tui): open the /cost dialog when clicking the sidebar cost reading by @dgageot in feat(tui): open the /cost dialog when clicking the sidebar cost reading docker/docker-agent#3754
chore: freeze config v12 and open v13 as latest by @dgageot in chore: freeze config v12 and open v13 as latest docker/docker-agent#3753

New Contributors

@github-actions[bot] made their first contribution in chore: refresh embedded models.dev snapshot docker/docker-agent#3747

Full Changelog: docker/docker-agent@v1.111.0...v1.112.0

View the full release notes at https://github.com/docker/docker-agent/releases/tag/v1.112.0.

---

[github-actions]

🤖 An automated task has requested bottles to be published to this PR.

Caution

Please do not push to this PR branch before the bottle commits have been pushed, as this results in a state that is difficult to recover from. If you need to resolve a merge conflict, please use a merge commit. Do not force-push to this PR branch.