Skip to content

feat(hooks): add add_context builtin for dependency-free template context injection - #4206

Merged
dgageot merged 1 commit into
docker:mainfrom
dgageot:worktree-board-dd784dbfb9819a13
Sep 9, 2026
Merged

dgageot merged 1 commit into
docker:mainfrom
dgageot:worktree-board-dd784dbfb9819a13

Conversation

@dgageot

@dgageot dgageot commented Sep 9, 2026

Copy link
Copy Markdown
Member

The existing way to inject hook-derived context into the model's conversation requires an external tool such as jq to parse the JSON payload on stdin and format the output. This is fragile in environments where jq is absent, and it forces users to write shell quoting around Go template-style strings.

add_context is a new builtin hook that takes a list of Go text/template strings as args, renders each one against the typed hook input (using Go field names like .SessionID, .AgentName, .Cwd), and joins non-blank results with newlines into additional_context. No shell, no JSON parser, no external binary. Template parse and execution errors are strict: they discard the hook's output and follow the configured on_error policy. Rendered output is plain text only; it is not re-evaluated or executed.

The tips guide's session-ID example, which used a jq command hook, is updated to use add_context instead. A new standalone examples/context_hooks.yaml shows the builtin in action; examples/hooks.yaml gains a matching entry. Schema descriptions and types.go comments are updated to document the new builtin. Unit tests cover template rendering, blank-result filtering, and error propagation; a runtime integration test covers the end-to-end path through the hooks engine.

…text injection

Adds a new add_context builtin hook that renders Go text/template arguments
against hook input and joins non-blank results as additional_context. No
external dependencies (no jq, no shell) are required.

- Renders each arg as an independent text/template against the hook input
- Joins non-blank results with newlines as additional_context
- Strict: template parse and execution errors propagate and follow on_error
- Plain-text output only; no re-evaluation or command execution
- Registered alongside existing builtins in pkg/hooks/builtins

Updates schema descriptions, types.go comments, hooks reference docs,
tips guide (updates session ID tip from jq command to add_context builtin),
canonical examples/hooks.yaml, and adds standalone examples/context_hooks.yaml.
Unit and runtime test coverage included.
@dgageot
dgageot requested a review from a team as a code owner September 9, 2026 06:59
@aheritier aheritier added area/config For configuration parsing, YAML, environment variables area/docs Documentation changes area/runtime Runtime engine, agent loop execution, tool dispatch, loop detection kind/feat PR adds a new feature (maps to feat:). Use on PRs only. labels Sep 9, 2026

@docker-agent docker-agent left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🟢 No issues found — LGTM! View logs.

@dgageot
dgageot merged commit 6e2924f into docker:main Sep 9, 2026
21 of 22 checks passed
social4hyq pushed a commit to social4hyq/homebrew-core that referenced this pull request Sep 20, 2026
docker-agent 1.137.0

Created-by: HarmonybrewBot
Commit-by: HarmonybrewBot
Merged-by: HarmonybrewBot
Description: Created by `brew bump`

---

Created with `brew bump-formula-pr`.<details>
  <summary>release notes</summary>
  <pre>This release removes the `session_plan` toolset, adds audio/video/image input and output capability handling, expands hook functionality with new builtins and sequential pipelines, and includes several bug fixes and safety improvements.

## Breaking Changes
- Removes the `session_plan` toolset, including its tool handlers, stream event, plans service, TUI `/plans` browser, and `--session`/`--scope` addressing on the `plans` command

## What's New
- Adds detection and filtering of audio/video input modalities per request model, stripping unsupported media parts and preserving provider-specific fallbacks
- Adds `output_capabilities.image` model override to resolve image output capability from models.dev metadata
- Adds guard for image-output requests across Google (gateway, direct Gemini API, and Vertex) surfaces, rejecting incompatible custom tools and structured output before dispatch
- Adds `add_context` builtin hook for dependency-free Go template-based context injection into the model's conversation
- Adds sequential pipeline execution for `pre_tool_use`, `before_llm_call`, and `tool_response_transform` hooks, replacing the previous concurrent first-rewrite-wins strategy
- Adds 56 new safe and 27 new destructive shell safety patterns, covering Git read operations, GitHub CLI queries, Go tooling, `rg`/`ripgrep`, and common inspection commands

## Bug Fixes
- Fixes Gemini keepalive SSE events (`event: keepalive` with `data: {}`) being passed to the SDK parser, causing parse failures; these frames are now dropped at the transport layer
- Fixes image-output-capable models being incorrectly excluded from session title generation
- Fixes shell metacharacter detection and corrects `gh`/`rg` pattern classifications
- Fixes SQLite stores not being closed deterministically on Windows, causing `TempDir` cleanup failures in tests
- Fixes `pkg/session` importing the SQLite driver, keeping the package free of that dependency

## Technical Changes
- Adds request-shape diagnostics for Gemini image requests (excluding prompt, schema, media-payload, and credential fields)
- Adds shared UTF-8-safe display-name sanitization helpers
- Classifies Gemini API 400 errors into bounded actionable categories
- Adds documentation tip for injecting session ID into model context using a `session_start` hook
---

## What's Changed
* docs: update CHANGELOG.md for v1.136.0 by @docker-read-write[bot] in docker/docker-agent#4202
* fix: drop Gemini keepalive SSE events before SDK parsing by @dgageot in docker/docker-agent#4203
* feat(plan)!: remove the session_plan toolset by @trungutt in docker/docker-agent#4199
* docs: add tip for injecting session ID with a session_start hook by @dgageot in docker/docker-agent#4205
* feat(hooks): add add_context builtin for dependency-free template context injection by @dgageot in docker/docker-agent#4206
* feat(hooks): sequential pipeline for pre_tool_use, before_llm_call, and tool_response_transform by @dgageot in docker/docker-agent#4207
* feat(#3996): resolve and filter input media per request model by @aheritier in docker/docker-agent#4016
* fix(#3996): diagnose Gemini requests and sanitize API failures by @aheritier in docker/docker-agent#4017
* feat(#3996): resolve image output capability from models.dev by @aheritier in docker/docker-agent#4019
* feat(#3996): guard image-output requests across Google surfaces by @aheritier in docker/docker-agent#4020
* fix(#3996): keep image-output models eligible for session titles by @aheritier in docker/docker-agent#4021
* fix(#3996): filter gateway SSE keepalives and test image requests by @aheritier in docker/docker-agent#4022
* feat(safety): expand shell safety patterns and harden substitution checks by @dgageot in docker/docker-agent#4209
* fix(tui): close SQLite stores deterministically so Windows can delete t.TempDir by @aheritier in docker/docker-agent#4210


**Full Changelog**: docker/docker-agent@v1.136.0...v1.137.0
</pre>
  <p>View the full release notes at <a href="https://github.com/docker/docker-agent/releases/tag/v1.137.0">https://github.com/docker/docker-agent/releases/tag/v1.137.0</a>.</p>
</details>
<hr>

See merge request: Harmonybrew/homebrew-core!18818
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

area/config For configuration parsing, YAML, environment variables area/docs Documentation changes area/runtime Runtime engine, agent loop execution, tool dispatch, loop detection kind/feat PR adds a new feature (maps to feat:). Use on PRs only.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants