fix(agent-core-v2): don't record turn.steer when an unconsumed steer …

[liruifengv]

Related Issue

N/A — internal bug, reproduced from a live desktop session (no tracking issue).

Problem

When a user steers a message while the agent is running, and the running turn then ends before the steer is consumed (cancelled via Esc, or completed before the next step boundary), the unconsumed steered prompt seeds the next turn as its opening prompt. The engine recorded both turn.prompt (the turn's opening) and turn.steer (steer consumption) for the same message, so the live transcript projected it twice — the chat showed the steered message as two identical user bubbles.

The cold transcript rebuild already deduplicates this case (a message whose id opened a turn is not folded as a steer), so reloading the session showed a single bubble — confirming the turn.steer record is spurious when the steered message itself opens the new turn.

What changed

• In AgentLoopService.consumeDrainedNudges, skip dispatching TurnSteer when the nudge being consumed is the message that opened the active turn (nudge.contextMessage.id === active.prompt.message.id). The message is still materialized into context exactly once; only the durable turn.steer record is no longer written for it.
• turn.steer now only fires when a steer is actually injected mid-turn into an already-running turn, which is the only case that needs a separate steer frame in the transcript. Live rendering then matches the cold rebuild: one user bubble (the turn's opening prompt).
• Tests:
  • New loop-level test: steer during a held step, Esc-cancel the turn, let the steered prompt seed the next turn — asserts no turn.steer is published and the message lands in context exactly once.
  • Two existing steer-metadata tests covered the same seeded-turn path and asserted the spurious turn.steer; they now assert on the materialized context message (merged content, FIFO client metadata, reserved message id), which is the more direct seam for what they guard.

Checklist

• I have read the CONTRIBUTING document.
• I have linked a related issue (external PRs: the issue must have a maintainer's /approve). — N/A, internal bug
• I have added tests that prove my feature works.
• Ran gen-changesets skill, or this PR needs no changeset.
• Ran gen-docs skill, or this PR needs no doc update.

[changeset-bot]

🦋 Changeset detected

Latest commit: c7cfc8b

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 1 package

Name	Type
@moonshot-ai/kimi-code	Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

[pkg-pr-new]

pnpm dlx https://pkg.pr.new/@moonshot-ai/kimi-code@c7cfc8b

npx https://pkg.pr.new/@moonshot-ai/kimi-code@c7cfc8b

commit: c7cfc8b

[Copilot]

Copilot review overview

🟢 Approval recommended

The targeted condition fixes duplicate transcript rendering and is covered by focused regression tests.

Review effort: Balanced
Findings: None

What changed in this PR

Prevents seeded post-cancellation prompts from being recorded as duplicate in-turn steer messages.

Changes:

• Suppresses redundant turn.steer events for prompts seeding a new turn.
• Updates regression coverage and adds a CLI patch changeset.

File	Description
packages/​agent-core-v2/​src/​agent/​loop/​loopService.ts	Avoids redundant steer dispatch.
packages/​agent-core-v2/​test/​agent/​prompt/​promptService.test.ts	Verifies correct event and message materialization behavior.
.changeset/​steer-seeded-turn-duplicate-message.md	Documents the user-visible fix.

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.