12c9dd599e
* feat(approval): localize prompts and allow consent for one turn * test(approval): update cast baseline and Web PTC prompt pin * fix(approval): cover PTC language and clarify turn consent * fix(approval): group turn consent under allow menu * fix(approval): keep turn consent in memory only * test(snapshot): refresh owners for merged justification guidance * fix(approval): drop duplicate allow-once from the allow menu * refactor(approval): derive turn consent expiry from one check Replace the turn approval bookkeeping (revocation state, incremental log cursor, and turn-signal listeners) with one side-effect-free expiry check over the log and lifetime flags. Events now only withdraw open presentations early; the expiry check decides whether an answer or turn consent still applies, including for Sessions without event publication. * refactor(approval): drop one-turn consent and keep localization only Remove the allowed-turn answer, the live turn-consent state, the allow menu, and their tests, notes, and recorded Web scenario. The approval service returns to the master request path; the request keeps the localized displayReason for presentation, and the card resolves it in the active UI language. * test(snapshots): record the localized justification schema text in new scenarios --------- Co-authored-by: Turtle <[email protected]> Co-authored-by: Kaige-Gao <[email protected]>
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 presentation intent.
- ACP group — the automation-only transport that answers approval requests for its own agents.
Dev Note
Working context for maintainers — click to expand
None.