Skip to content

feat(voice): add scoped Live Voice work sessions - #1161

Open
vastsa wants to merge 5 commits into
mainfrom
codex/live-voice-v1
Open

vastsa wants to merge 5 commits into
mainfrom
codex/live-voice-v1

Conversation

@vastsa

@vastsa vastsa commented Sep 28, 2026 •

Copy link
Copy Markdown
Owner

Summary

  • Bind a Live call to an explicitly selected local Desktop work session, with recent-context sharing disabled by default and limited to eligible plain-text messages when the user opts in.
  • Route accepted voice requests through the existing Host and AgentHost session lifecycle, including durable queue admission, scoped steering, exact-turn stop, and queue cancellation.
  • Preserve provider request, operation, user-message, queue, and turn identities; display bounded work status and terminal summaries in the Live panel.
  • Add English and Chinese work-session specifications, delivery evidence, migration coverage, and focused tests.

Validation

  • Passed: pnpm build:js (with existing chunk-size and documentation highlighter warnings), desktop typecheck, pnpm lint, pnpm docs:check, node scripts/check-architecture.mjs, pnpm check:agent-policy, and pnpm check:pr-base.
  • Passed targeted suites: host-runtime (67), agent-host (49), voice-runtime (48), agent-runtime exact-turn guard (2), Live Voice Node user-path tests (12), and cargo test -p host-core --locked (659), plus cargo fmt --check and cargo clippy -p host-core --all-targets --locked.
  • Task candidate: 1ec74701f1c2; base main: 2387fa6d4d96.

Remaining acceptance work

  • Live work result summaries are visible in the panel and can be queried, but automatic spoken completion/error announcements are not implemented.
  • Model-driven session listing, opening, and creation through selectionRef are not implemented; the flow requires explicit Desktop selection.
  • The full W2 acceptance matrix and E2E-LIVE-WORK M01–M16 real desktop journeys have not been completed. No real provider account or live desktop instance was used.

This is an incomplete v2 candidate; the remaining acceptance work is recorded in docs/implementation/live-work-evidence.md. No merge was performed.

Add a main-process-owned Live Voice lifecycle with provider adapters,
scoped microphone access, media transport, and renderer controls.

Persist compatible settings and document the protocol so sessions
can be configured without changing dictation behavior.
Copilot AI lite review requested due to automatic review settings September 28, 2026 00:38

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

Replace the Composer Dictation surface with Live Voice while preserving stored Dictation settings. Align the call panel with shared surfaces and connect the existing configurable voice shortcuts to the call lifecycle.

Escape now cancels only an in-progress startup, and the shortcut settings and specs describe the Live Voice behavior.
Include the current main base in the Live Voice candidate before updating its pull request.
Refresh the shared Live Voice branch against the current target before the remote update, preserving the public PR history.

This brings the candidate forward without rewriting the existing branch.
Keep spoken work inside the selected Desktop session and Host queue rather than creating a parallel agent path. Preserve request and turn identity so admission, cancellation, and stop controls stay scoped to the originating call.
@vastsa vastsa changed the title feat(voice): add Live Voice sessions feat(voice): add scoped Live Voice work sessions Sep 28, 2026

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants