Turtle
38c7a9fbf4
* feat(release): publish package source, declaration maps, and documentation Every release member publishes its TypeScript source and the declaration maps that resolve into it, and @deepseek-ai/dsh publishes the repository Markdown documentation staged from docs/ at prepack time. The ./src/* export most members already declared now resolves for an installed consumer, and a consumer editor follows a declaration to the implementation. Bundled JavaScript maps stay unpublished; the vendored family and the Desktop runtime file policy are unchanged. Rationale: .agents/notes/implemented/process/2026-10-08-published-source-and-docs.md * feat(release): publish JavaScript maps and compress bundles Every emitted JavaScript map ships beside the bundle it describes, and the workspace build and the client preset compress bundles without mangling identifiers. The documentation payload now mirrors the website publication manifest and is removed again by `postpack`; Desktop and the Python executable exclude the published source, documentation, and maps; `clean` removes a staged copy. Typert's publication contract gains the Remote declaration map. * fix(release): keep node bundles readable for the worker image The browser worker image lowers `yield*` only as a whole statement and rewrites `for await` loops by their source layout, so compressed node-side entries either fail that lowering or lower to unparseable code. Only the browser bundles keep compression, which removes about a third of their text. The bundle-purity assertion now matches the module-loader call regardless of the quote style compression picks, and the release-pack fixture exercises the installed package's new documentation requirement. * feat(release): publish the whole documentation tree `@deepseek-ai/dsh` copies `docs/` in full instead of the website's page set: the maintainer documents, the generated migration records, the translation guidelines, and the `*.i18n.yaml` consistency records ship with the installed package, so the documentation's own links resolve without a checkout. * feat(release): publish the upgrade guides with the documentation The staged documentation keeps the website's page set and adds every `docs/upgrade-guide/` document, which is what an installed reader consults when a released change breaks something. The rest of the maintainer tree stays out. * test(release): expect source and maps in master's new payload cases * feat(release): keep installed docs and source readable in Desktop Desktop keeps the published src/ and docs/ trees inside app.asar, and every model shell call receives DSH_INSTALL_DIR and DSH_NODE_EXECUTABLE so an agent can read them through Electron's Node mode. Staging also generates docs/upgrade-guide/README.md, an index of the upgrade guides grouped by the release they upgrade from. Minified client bundles print string literals with backticks: the worker image packer now recognizes those chunk requests, client license banners are prepended after minification so their text survives, and the affected artifact tests accept either quote. * test(desktop): read archived docs through the Windows PowerShell form Regenerate the config catalog for the shifted shell-env source line. * test(desktop): wait for the GUI-subsystem Electron process from PowerShell * build(release): publish source and maps from the message-quotes package * build(release): publish source and maps from packages new on master * build(release): publish source and maps from the tool-office package
description, kind
| description | kind |
|---|---|
| Package map for the human-collaboration capability family: slash commands, one-shot approvals, permission presets, and the question/answer seam that lets a running agent pause for a human decision. | package-group |
interaction/ — the human-collaboration plane
English | 中文
Summary
The interaction/ group covers the ways a person can guide a running agent. Use slash commands for immediate actions that do not require a model round trip, one-shot approvals for sensitive operations, permission presets to choose sandbox and approval behavior together, and questions when the agent needs information or a decision. Interactive applications expose these capabilities to people; automation handles its own approvals through ACP. The package map below distinguishes each capability and links to its full behavior and configuration.
Table of Contents
Packages
Each package README and its subsystem reference own the exhaustive contracts.
| Package | Role | ctx key |
|---|---|---|
commands/ |
Lets users type slash commands that run directly against an agent without a model round trip | ctx.commands |
user-approval/ |
Asks composed answerers for one-shot allow/reject decisions and fails closed without one | ctx.approval |
permission-presets/ |
Bundles sandbox mode with an approval policy into one user-facing Permissions selector | ctx.permissionPresets |
user-questions/ |
Defines the validated question schema and scoped answerer waterfall an agent pauses on | ctx.userQuestions |
tool-ask-user/ |
Exposes the ask_user_question tool so the model can ask the human for a decision |
registers on ctx.tools |
Related documentation
Start with the subsystem references for the shared vocabularies, then the neighboring automation and composition surfaces.
- Commands subsystem — command registry semantics and the
ctx.commandsCordis surface. - Approval subsystem — request/outcome vocabulary, the answerer waterfall, and per-session policy.
- Permission presets subsystem — the preset table and the knob write-through.
- User interaction subsystem — question vocabulary, answerer waterfall, and pending-question lifecycle.
- ACP group — the automation-only transport that answers approval requests for its own agents.
Dev Note
Working context for maintainers — click to expand
None.