Fix TOOL-12: one line on every dev hand-back, by the model that ran

An Opus-run dev got no verification and no message, so silence meant
both "still verifying" and "will never verify" (SAFETY-135 waited
overnight, SAFETY-126 8 h). Verdicts were also labelled with the
routing choice, not the model the run used.

- Every dev hand-back posts one line at once:
  "[model-router] Tn verifying on Opus..." (a verdict follows), or
  "[model-router] Tn no verification: dev ran on Opus. Go straight to
  review." A run that ends with an error or names no clone says so.
- Each round is decided and labelled by the model the run reported
  (its end usage), the routing choice only as fallback. A difference
  is shown as "(routed to X, ran on Y)", also on later rounds.
- 8 new tests; each new rule was also broken on purpose and caught,
  apart from one equivalent change.

Version 0.4.6.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MdqPWvuDpbpRvDEdURoAwo

hooks/register.ts

@@ -19,6 +19,8 @@ import {
   parseBrief,
   parsePatterns,
   parseVerdict,
+  handBackLine,
+  ranTier,
   safetyHit,
   skipReason,
   validTimeout,
@@ -32,7 +34,10 @@ import {
 /** One agent the router started, kept from spawn to its last verified round. */
 type AgentRec = {
   taskId: string
+  /** The model the last round actually ran on (the routing choice until a round reports one). */
   tier: Tier
+  /** The model the router chose at spawn; tier can differ when the run used another. */
+  routed?: Tier
   role?: Role
   clone?: string
   baseBranch?: string
@@ -124,7 +129,7 @@ The model-router mod picks each subagent's model and verifies dev work before it
 - Every dev, review and test brief carries one line \`Clone: <path>\` (add \`(Role: dev|review|test)\` if the path does not end in the role). The router reads the role from that line only; a brief naming several clones without it runs on Opus, unverified.
 - Dev agents are routed: Sonnet when the brief decides the approach (Expected / acceptance criteria), Opus when the design is still open. Naming a model on a dev brief has no effect. Give each dev brief its clone path and base branch.
 - Review and test agents keep the model you name (Opus when you name none).
-- When a dev agent below Opus finishes a round, the router verifies its clone's diff on Opus and posts a "[model-router]" verdict. Wait for that verdict before opening or advancing the PR.
+- Every dev hand-back gets one "[model-router] Tn" line at once. "verifying on Opus...": wait for the verdict before advancing the PR. "no verification: dev ran on Opus. Go straight to review.": no verdict will come. Lines are decided by the model the dev actually ran on.
 - On "[model-router] ... FAIL ... resume agent", resume that same agent with SendMessage, passing the issues. On "start a new agent ... [router-rewrite Tn]", stop the old agent and call Agent with exactly that prompt. On "handed back", stop and show the issues to the person. Do not fix rejected work yourself.`
 
 // ---------- store helpers (top-level, as the engine requires for `$`) ----------
@@ -501,14 +506,21 @@ async function skipRound($: EngineInterface, agentId: string, rec: AgentRec, out
     reason: outcome,
     outcome,
   })
-  if (rec.role === 'dev' && outcome === 'no-clone')
-    await tell($, `[model-router] ${rec.taskId} (agent ${agentId}): NOT VERIFIED - the brief names no clone path.`)
 }
 
-async function runRound($: EngineInterface, agentId: string, rec: AgentRec, ended: string, cfg: Settings) {
-  const skip = skipReason(rec, ended)
-  if (skip) await skipRound($, agentId, rec, skip)
-  else await verifyRound($, agentId, rec, cfg)
+/**
+ * One finished run of a tracked agent. Decides on the model that actually ran,
+ * says at once what happens next for a dev, then verifies or logs the skip.
+ */
+async function runRound($: EngineInterface, agentId: string, rec: AgentRec, ended: string, reported: string | undefined, cfg: Settings) {
+  const routed = rec.routed ?? rec.tier
+  const ran = ranTier(reported, routed)
+  const round: AgentRec = { ...rec, routed, tier: ran.tier }
+  const skip = skipReason(round, ended)
+  const line = handBackLine({ taskId: rec.taskId, role: rec.role, ran: ran.tier, routed, skip, ended })
+  if (line) await tell($, line)
+  if (skip) await skipRound($, agentId, round, skip)
+  else await verifyRound($, agentId, round, cfg)
 }
 
 // ---------- the hooks ----------
@@ -612,6 +624,7 @@ export const register: Register = (on, options) => {
       await putIn<AgentRec>($, S.agents, ran.agentId, {
         taskId,
         tier,
+        routed: tier,
         role: brief.role,
         clone: brief.clone,
         baseBranch: brief.baseBranch,
@@ -656,7 +669,8 @@ export const register: Register = (on, options) => {
     const rec = (await getMap<AgentRec>($, S.agents))[agentId]
     if (!rec) return out
     // Verification takes minutes: run it after this event has gone on.
-    $.clock.after(0, () => void runRound($, agentId, rec, e.reason, cfg))
+    const reported = e.usage?.model
+    $.clock.after(0, () => void runRound($, agentId, rec, e.reason, reported, cfg))
     return out
   })
 

hooks/router.ts

@@ -262,3 +262,39 @@ export function validTimeout(raw: unknown): number {
   return Number.isFinite(n) && n >= 1 ? Math.round(n) : 1800
 }
 
+
+// ---------- the hand-back line (TOOL-12) ----------
+
+const LABEL: Record<Tier, string> = { haiku: 'Haiku', sonnet: 'Sonnet', opus: 'Opus', fable: 'Fable' }
+
+/**
+ * The model a run actually used, from the model id its end reports; the
+ * routing choice only when the run reported none.
+ */
+export const ranTier = (reportedModel: string | undefined, routed: Tier): { tier: Tier; isMismatch: boolean } => {
+  const seen = asTier(reportedModel)
+  return seen ? { tier: seen, isMismatch: seen !== routed } : { tier: routed, isMismatch: false }
+}
+
+/**
+ * The one line every dev hand-back gets at once, so silence never stands for
+ * both "still verifying" and "will never verify". Undefined: no line (not a dev).
+ */
+export const handBackLine = (args: {
+  taskId: string
+  role?: Role
+  ran: Tier
+  routed: Tier
+  skip?: Skip
+  ended: string
+}): string | undefined => {
+  const { taskId, role, ran, routed, skip, ended } = args
+  if (role !== 'dev') return undefined
+  const note = ran !== routed ? ` (routed to ${LABEL[routed]}, ran on ${LABEL[ran]})` : ''
+  const head = `[model-router] ${taskId}`
+  if (!skip) return `${head} verifying on ${LABEL[verifierFor(ran)]}...${note}`
+  if (skip === 'opus-unverified') return `${head} no verification: dev ran on ${LABEL[ran]}. Go straight to review.${note}`
+  if (skip === 'agent-ended') return `${head} no verification: the dev run ended without an answer (${ended}).${note}`
+  if (skip === 'no-clone') return `${head} no verification: the brief names no clone path.${note}`
+  return undefined
+}