Sending a message while the agent is working used to queue it for the next turn by default. It now steers the running turn by default on web, desktop, and mobile.
The contracts default for followUpBehavior and the mobile DEFAULT_FOLLOW_UP_BEHAVIOR both flip from queue to steer. mod+Enter still queues for one message. Web and desktop persist the full client settings object, so anyone who has saved any client setting keeps the stored queue; new installs and mobile users who never picked a value get steer.
Verified with vp run check:changed (format, lint, knip, typecheck of 30 packages, tests). The composer and Settings were not exercised in a running client.
Opus 5.5 via Claude Code in T3 Code.
🤖 Generated with Claude Code
Added 1 commit
Verdict: Needs Human Approval
Macroscope's review found this PR requires human approval — This changes the default follow-up action from queuing to steering in both mobile fallback logic and shared settings decoding, altering normal user-facing behavior for users without an explicit preference. The product-default change warrants human review.
You can add or adjust custom eligibility rules. Learn more.
No actionable comments were generated in the recent review.
c91f17ba-f761-43b6-8369-6b2e773878afReviewing files that changed from the base of the PR and between 90c455ff8fceef426bafc64c0b755ef864a353ab and 3f0e31802487612d5fcf1836fb5f3b1377c825dd.
apps/mobile/src/lib/followUpBehavior.tspackages/contracts/src/settings.tsIncluded review availability: This review used your included allowance. Your plan provides up to 10 included reviews per hour; 7 remain after this review.
The mobile default and settings-schema default for follow-up behavior change from queue to steer. Explicitly supplied queue and steer values remain accepted by the schema.
Changes: Follow-up behavior
| Layer / File(s) | Summary |
|---|---|
Align follow-up defaults apps/mobile/src/lib/followUpBehavior.ts, packages/contracts/src/settings.ts | Both the mobile default and the default used when the setting is omitted change from queue to steer. The schema continues to accept explicitly supplied queue and steer values. |
Priority: External image Normal
Estimated code review effort: 1 (Trivial) | ~3 minutes
Change: Feature
Possibly related PRs
Suggested reviewers: macroscopeapp, juliusmarminge
3f0e3The follow-up behavior default changes consistently to steering without affecting saved preferences.
Failed Failed checks: 1 warning
| Check name | Status | Explanation | Resolution |
|---|---|---|---|
| Description check | Warning | The description explains the previous behavior, the new defaults, persistence behavior, the mod+Enter exception, verification results, and untested client areas. It does not include the required Scope… | Add a Scope and approval section. Link the triaged issue or maintainer approval with the approval comment, or explain why this focused change qualifies for an exemption. Keep the existing verification details and state the client testing li… |
| Check name | Status | Explanation |
|---|---|---|
| Title check | Passed | The title clearly and concisely describes the primary change: follow-up messages now steer the running turn by default. |
| Linked Issues check | Passed | Check skipped because no linked issues were found for this pull request. |
| Out of Scope Changes check | Passed | Check skipped because no linked issues were found for this pull request. |
Explanation
The description explains the previous behavior, the new defaults, persistence behavior, the mod+Enter exception, verification results, and untested client areas. It does not include the required Scope and approval information for this broader workflow behavior change.
Resolution
Add a Scope and approval section. Link the triaged issue or maintainer approval with the approval comment, or explain why this focused change qualifies for an exemption. Keep the existing verification details and state the client testing limitation explicitly under Verification; use the template section headings for clarity when updating the description。该响应不应包含中文。
Comment @coderabbitai help to get the list of available commands.
✅ Thread transfer remains within every enforced ceiling.
ℹ️ The exact PR base did not have a successful artifact. Baseline uses the latest successful
mainmeasurement shown below.
| Provider | Metric | Main baseline | This PR | Impact | PR ceiling | |
|---|---|---|---|---|---|---|
| Codex | Total thread wire | 5.0 KiB | 4.9 KiB | −23 B (−0.5%) | 6.8 KiB | ✅ |
| Codex | Thread snapshot wire | 3.8 KiB | 3.8 KiB | 0 B (0.0%) | 4.9 KiB | ✅ |
| Codex | Live turn WebSocket wire | 1.2 KiB | 1.2 KiB | −23 B (−1.9%) | 2.0 KiB | ✅ |
| Codex | Live turn WebSocket decoded | 20.9 KiB | 20.8 KiB | −41 B (−0.2%) | 29.3 KiB | ✅ |
| Codex | Live turn messages | 2 | 1 | −1 (−50.0%) | 8 | ✅ |
| Claude | Total thread wire | 5.0 KiB | 5.0 KiB | 0 B (0.0%) | 6.8 KiB | ✅ |
| Claude | Thread snapshot wire | 3.8 KiB | 3.8 KiB | 0 B (0.0%) | 4.9 KiB | ✅ |
| Claude | Live turn WebSocket wire | 1.2 KiB | 1.2 KiB | 0 B (0.0%) | 2.0 KiB | ✅ |
| Claude | Live turn WebSocket decoded | 21.2 KiB | 21.2 KiB | 0 B (0.0%) | 29.3 KiB | ✅ |
| Claude | Live turn messages | 2 | 2 | 0 (0.0%) | 8 | ✅ |
Baseline: e666c01 · PR result: 3f0e318 · Source CI: success
10 historical turns, 5 command tools per turn, 878.9 KiB retained MCP result per historical turn, and a 1.05 MiB retained result in the measured turn.
Updated in place by a trusted workflow. PR artifacts are strictly validated and never executed.
