deepagents

# Deep Agents docs release skill Use this skill when the product is Deep Agents Python (`langchain-ai/deepagents`, tags `deepagents==...`). For TypeScript releases from `langchain-ai/deepagentsjs`, use the `deepagentsjs` skill. For Deep Agents Code, use `deepagents-code`. Do not use this skill for Managed Deep Agents. ## Sources of truth - Releases: GitHub `langchain-ai/deepagents` via `get_eligible_release` / `get_release_notes` - Important: that repo publishes several packages. For this product, only tags that start with `deepagents==` count (not `deepagents-code==`, `deepagents-acp==`, or `langchain-quickjs==`). - Docs paths in `langchain-ai/docs`: - `src/oss/deepagents/` library pages - Exclude `src/oss/deepagents/code/` (Deep Agents Code is a separate product) - Navigation for Deep Agents in `src/docs.json` - Shared guidance in root `AGENTS.md` - Changelog entry pages: - `src/oss/deepagents/changelog-py.mdx` - `src/oss/deepagents/changelog-js.mdx` ## What usually needs docs Prioritize user-facing changes: - New public APIs, middleware, backends, tools, or config options - New or changed CLI / SDK behavior that readers rely on - New capabilities (subagents, sandboxes, streaming, HITL, skills, memory) - Behavior changes that make existing docs wrong - New minimum package versions that docs should call out Usually skip docs for: - Internal refactors with no user-visible change - Dependency bumps with no behavior change - Pure bug fixes that do not change documented behavior - Changes that belong only to Deep Agents Code (`deepagents-code==...` releases) When a release note is Python-only or JS-only, edit the matching language-fenced sections (`:::python` / `:::js`) rather than inventing parity. When unsure, open a small clarifying ticket/PR only if a reader of the current docs would be misled. ## Workflow for one Deep Agents release 1. Call `get_eligible_release` with `product="deepagents"` and `min_age_days=7`. 2. Read `/memories/agent/deepagents-releases.md` (create it if missing). Skip features already recorded for that tag. 3. Load the release notes. Split the notes into discrete features (one user-facing capability each). 4. In the sandbox, clone or refresh `https://github.com/langchain-ai/docs.git` and read the Deep Agents pages that might be affected. Stay out of `src/oss/deepagents/code/` unless the feature clearly belongs there and you are explicitly covering Deep Agents Code. 5. For each feature that needs a docs change: - Draft the MDX edits (follow `AGENTS.md`: frontmatter, no markdown in `description`, Tabler icons only, sentence-case headings, no contractions, no first person). - Prefer updating the owning page over creating a new page. If a new page is required, also plan the `src/docs.json` navigation update. - Load the `ship-docs-update` skill and ship that feature alone. 6. After shipping, append the release tag, feature name, Linear URL, and PR URL to `/memories/agent/deepagents-releases.md`. 7. Keep `/memories/agent/AGENTS.md` short: last processed Deep Agents tag and date, alongside other products. ## Memory format Use cold memory file `/memories/agent/deepagents-releases.md`: ```md # Deep Agents release tracking ## deepagents==0.7.24 - feature: async subagent fork mode - linear: https://linear.app/... - pr: https://github.com/langchain-ai/docs/pull/... ```