From b889070fb965807004fb40f018d312bb3b9cf4b7 Mon Sep 17 00:00:00 2001
From: garrytan <garrytan@gmail.com>
Date: Thu, 29 Oct 2026 04:45:05 +0000
Subject: [PATCH] fix: a cost-only record never sets the trial model

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---
 scripts/harness-version.json  | 2 +-
 scripts/lib/paid-report.ts    | 2 +-
 test/paid-report-cost.test.ts | 5 +++++
 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/scripts/harness-version.json b/scripts/harness-version.json
index 22c6c416b..d2993d593 100644
--- a/scripts/harness-version.json
+++ b/scripts/harness-version.json
@@ -13,7 +13,7 @@
   "files": {
     "scripts/lib/paid-cases.ts": {"blob":"f862cf5241580c7593b9ee62eacf5ef046248d26","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"},
     "scripts/lib/paid-plan.ts": {"blob":"e8ce3cb98474dded38c5128a631d283b0ca35b63","since":6,"nonBehavioral":"F1 rule-16 flaky rerun: report aggregation, rerun planning and the gate slice exit code; no case's execution, trial outcome, trial record or panel verdict changes, so no pass-rate series resets"},
-    "scripts/lib/paid-report.ts": {"blob":"6adbde198309328bae17c3b17d199963e19a4c7e","since":6,"nonBehavioral":"the paid report headline adds session cost no collector record carries; cost fields only, no verdict or failure class changes"},
+    "scripts/lib/paid-report.ts": {"blob":"a4ef799c233c65e9209a4b654360476fdbf51802","since":6,"nonBehavioral":"the trial model comes from the named records only, as before cost_case_id; cost fields only, no verdict, failure class or series key changes"},
     "scripts/lib/published-text.ts": {"blob":"3f2e4d616b5dd0204035710c66b64d49055c5714","since":6},
     "scripts/lib/shard-engine.ts": {"blob":"dc714d7d897aed185c0ec3d2c92ad22d954039e5","since":6,"nonBehavioral":"createShardSandbox drops the Capy launch markers (GSTACK_SESSION_KIND, GSTACK_CAPY, GSTACK_EPHEMERAL, GSTACK_INSTALL_VERDICT) from shard environments; CI never sets them, so no case's input or verdict changes there, and on a Capy machine fixtures now see the session kind they set themselves instead of the installer's"},
     "scripts/test-paid-shards.ts": {"blob":"5439d0a8f6e1569fa7c924af20d67c30c81d5d30","since":6,"nonBehavioral":"credential rejections are classed infra instead of assertion: no case's pass or fail changes; only failed trials whose provider rejected the run's key move class, so no rerun spends on a rejected key"},
diff --git a/scripts/lib/paid-report.ts b/scripts/lib/paid-report.ts
index 6adbde198..a4ef799c2 100644
--- a/scripts/lib/paid-report.ts
+++ b/scripts/lib/paid-report.ts
@@ -334,7 +334,7 @@ export function junitCensus(manifest: PaidRunManifest, artifacts: ReportArtifact
           ...(failureClass ? { failure_class: failureClass } : {}), ...(failedRecord?.exit_reason ? { exit_reason: String(failedRecord.exit_reason) } : {}),
           ...(error && failed ? { error } : {}), ...diagnosis, ...trialSessions(sessions), duration_ms: Math.min(cases.reduce((sum, tc) => sum + tc.timeMs, 0), outcome.elapsedMs),
           ...cost,
-          ...(typeof mine[0]?.model === 'string' ? { model: mine[0].model } : {}), ...(cliVersion ? { cli_version: cliVersion } : {}),
+          ...(typeof named[0]?.model === 'string' ? { model: named[0].model } : {}), ...(cliVersion ? { cli_version: cliVersion } : {}),
           quarantined: false, execution: outcome.reused ? 'reused' : 'executed', source: 'junit' } as TrialOutcomeRecord);
       }
       census.shardSkipReasons.set(key, reasons);
diff --git a/test/paid-report-cost.test.ts b/test/paid-report-cost.test.ts
index 7ceb8af1b..073949b7c 100644
--- a/test/paid-report-cost.test.ts
+++ b/test/paid-report-cost.test.ts
@@ -102,4 +102,9 @@ describe('junitCensus cost binding', () => {
       .toEqual({ failureClass: unbound.failureClass, error: unbound.error, line: unbound.line?.replace(/ {2}\[slice.*$/, '') });
     expect(bound.failureClass).toBe('assertion');
   });
+
+  test('a cost-only record never sets the trial\'s model, which keys its pass-rate series', () => {
+    const history = census(labelled.map(r => ({ ...r, model: 'claude-opus-5-5' }))).history;
+    expect(history.map(h => [h.case, h.model])).toEqual([['browse-basic', undefined], ['browse-snapshot', undefined]]);
+  });
 });