@lcv-ideas-software/cross-review 4.2.2 → 4.2.4

package/CHANGELOG.md

@@ -7,6 +7,48 @@ standard `v00.00.00`; npm package versions remain SemVer.
 
 ## [Unreleased]
 
+## [v04.02.04] — 2026-06-05
+
+**Patch — truthfulness preflight auditability.** This release tightens the
+guardrails added after the v4.2.x session audit so unsupported runtime/history
+claims fail with clearer classes and can be retested after evidence is attached.
+
+### Added
+
+- Added `session_truthfulness_preflight_check`, a read-only MCP tool that
+  re-runs the local truthfulness preflight for an existing session without
+  calling providers.
+- Added `issue_classes` to truthfulness preflight results and abort events for
+  `runtime_contradiction`, `unsupported_current_state_claim`,
+  `unsupported_historical_claim`, and `fabrication_pattern`.
+- Added durable `failed_attempts` metadata for `run_until_unanimous` preflight
+  aborts that happen before a peer-review round is appended.
+
+### Changed
+
+- Re-runs truthfulness preflight on lead-generated initial drafts and revisions
+  before dispatching reviewer peer calls, blocking unsupported generated
+  runtime claims before they propagate through the panel.
+- Parser diagnostics now distinguish empty verified `evidence_sources` from
+  non-empty but generic evidence sources, and recognize attached-evidence
+  labels, `evidence/` paths, log lines, line labels, and command/test-output
+  citations as concrete evidence markers.
+
+## [v04.02.03] — 2026-06-03
+
+**Patch — Gemini replacement pin and rate-card refresh.** This release follows
+Google's deprecation schedule for Gemini 2.5 Pro by making Gemini 3.1 Pro Preview
+the active canonical Gemini pin.
+
+### Changed
+
+- Promoted the Google/Gemini canonical default from `gemini-2.5-pro` to
+  `gemini-3.1-pro-preview` after Google's deprecation schedule listed the
+  former for shutdown on 2026-10-16.
+- Updated the active local Gemini rate card from Gemini 2.5 Pro pricing to
+  Gemini 3.1 Pro Preview pricing, including the >200K extended tier and
+  cached-input rates.
+
 ## [v04.02.02] — 2026-06-02
 
 **Patch — provider-doc refresh and Perplexity probe repair.** This release

package/README.md

@@ -24,7 +24,7 @@ npm install -g @lcv-ideas-software/cross-review
 npm install -g @lcv-ideas-software/cross-review --registry=https://npm.pkg.github.com
 ```
 
-**Status.** Stable. Current release: **v04.02.02** (npm package `4.2.2`). See [CHANGELOG.md](./CHANGELOG.md) for the full release history.
+**Status.** Stable. Current release: **v04.02.04** (npm package `4.2.4`). See [CHANGELOG.md](./CHANGELOG.md) for the full release history.
 
 > **Project renamed 2026-05-15.** This project was previously published as
 > [`@lcv-ideas-software/cross-review-v2`](https://www.npmjs.com/package/@lcv-ideas-software/cross-review-v2)
@@ -38,6 +38,8 @@ The version history at a glance:
 
 | Release              | Scope                                                                                                                                                                                                              |
 | -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| **`v04.02.04`**      | Patch — harden truthfulness preflight auditability, add a read-only preflight retest tool, and reduce false parser warnings for attached/log evidence.                                                             |
+| **`v04.02.03`**      | Patch — promote the Gemini canonical default to `gemini-3.1-pro-preview` and refresh the active local Gemini rate card.                                                                                            |
 | **`v04.02.02`**      | Patch — provider-doc refresh, Perplexity probe repair, current model pins, and rate-card guidance.                                                                                                                 |
 | **`v04.02.01`**      | Patch — publish the workspace hard-gate cleanup as a package release.                                                                                                                                              |
 | **`v04.02.00`**      | Minor — bounded MCP session listing and cancellation semantics cleanup.                                                                                                                                            |
@@ -209,6 +211,7 @@ these environment variables before running real sessions (example):
 - `session_doctor`
 - `session_report`
 - `session_check_convergence`
+- `session_truthfulness_preflight_check`
 - `session_attach_evidence`
 - `session_evidence_checklist_update`
 - `session_evidence_judge_pass`

package/dist/scripts/provider-refresh-smoke.js

@@ -32,6 +32,11 @@ const config = loadConfig();
     assert.equal(claude.selected, "claude-opus-4-8");
     assert.equal(claude.confidence, "verified");
 }
+{
+    const gemini = selectFromCandidates("gemini", [{ id: "gemini-3.1-pro-preview", source: "api" }], "gemini-3.1-pro-preview");
+    assert.equal(gemini.selected, "gemini-3.1-pro-preview");
+    assert.equal(gemini.confidence, "verified");
+}
 {
     const grok = selectFromCandidates("grok", [{ id: "grok-4.3", source: "api" }], "grok-4.3");
     assert.equal(grok.selected, "grok-4.3");
@@ -41,8 +46,10 @@ const config = loadConfig();
     const configSource = fs.readFileSync("src/core/config.ts", "utf8");
     const modelSelectionSource = fs.readFileSync("src/peers/model-selection.ts", "utf8");
     assert.ok(configSource.includes('claude: envValue("CROSS_REVIEW_ANTHROPIC_MODEL") || "claude-opus-4-8"'));
+    assert.ok(configSource.includes('gemini: envValue("CROSS_REVIEW_GEMINI_MODEL") || "gemini-3.1-pro-preview"'));
     assert.ok(configSource.includes('grok: envValue("CROSS_REVIEW_GROK_MODEL") || "grok-4.3"'));
     assert.ok(modelSelectionSource.includes('claude: ["claude-opus-4-8"]'));
+    assert.ok(modelSelectionSource.includes('gemini: ["gemini-3.1-pro-preview"]'));
     assert.ok(modelSelectionSource.includes('grok: ["grok-4.3"]'));
 }
 console.log("[provider-refresh-smoke] PASS");

package/dist/scripts/provider-refresh-smoke.js.map

@@ -1 +1 @@
-{"version":3,"file":"provider-refresh-smoke.js","sourceRoot":"","sources":["../../scripts/provider-refresh-smoke.ts"],"names":[],"mappings":"AAAA,OAAO,MAAM,MAAM,oBAAoB,CAAC;AACxC,OAAO,EAAE,MAAM,SAAS,CAAC;AACzB,OAAO,EAAE,MAAM,SAAS,CAAC;AACzB,OAAO,IAAI,MAAM,WAAW,CAAC;AAE7B,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAC;AACnD,OAAO,EAAE,oBAAoB,EAAE,MAAM,iCAAiC,CAAC;AACvE,OAAO,EAAE,iBAAiB,EAAE,MAAM,4BAA4B,CAAC;AAE/D,OAAO,CAAC,GAAG,CAAC,iBAAiB,GAAG,GAAG,CAAC;AACpC,OAAO,CAAC,GAAG,CAAC,2BAA2B,GAAG,GAAG,CAAC;AAC9C,OAAO,CAAC,GAAG,CAAC,kBAAkB,GAAG,qBAAqB,CAAC;AACvD,OAAO,CAAC,GAAG,CAAC,qBAAqB,GAAG,EAAE,CAAC,WAAW,CAChD,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,MAAM,EAAE,EAAE,gCAAgC,CAAC,CACzD,CAAC;AAEF,MAAM,MAAM,GAAG,UAAU,EAAE,CAAC;AAE5B,CAAC;IACC,MAAM,OAAO,GAAG,IAAI,iBAAiB,CAAC,MAAM,CAAC,CAAC;IAC9C,IAAI,eAA8E,CAAC;IAEjF,OASD,CAAC,MAAM,GAAG,KAAK,IAAI,EAAE,CAAC,CAAC;QACtB,IAAI,EAAE;YACJ,WAAW,EAAE;gBACX,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE;oBACxB,eAAe,GAAG,OAAO,CAAC;gBAC5B,CAAC;aACF;SACF;KACF,CAAC,CAAC;IAEH,MAAM,KAAK,GAAG,MAAM,OAAO,CAAC,KAAK,EAAE,CAAC;IACpC,MAAM,CAAC,KAAK,CAAC,KAAK,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;IACpC,MAAM,CAAC,KAAK,CAAC,eAAe,EAAE,cAAc,EAAE,IAAI,CAAC,CAAC;IACpD,MAAM,CAAC,EAAE,CACP,OAAO,eAAe,EAAE,UAAU,KAAK,QAAQ,IAAI,eAAe,CAAC,UAAU,IAAI,EAAE,EACnF,+EAA+E,CAChF,CAAC;AACJ,CAAC;AAED,CAAC;IACC,MAAM,MAAM,GAAG,oBAAoB,CACjC,QAAQ,EACR,CAAC,EAAE,EAAE,EAAE,iBAAiB,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,EAC1C,iBAAiB,CAClB,CAAC;IACF,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,QAAQ,EAAE,iBAAiB,CAAC,CAAC;IACjD,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,UAAU,EAAE,UAAU,CAAC,CAAC;AAC9C,CAAC;AAED,CAAC;IACC,MAAM,IAAI,GAAG,oBAAoB,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,EAAE,UAAU,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,EAAE,UAAU,CAAC,CAAC;IAC3F,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,QAAQ,EAAE,UAAU,CAAC,CAAC;IACxC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,UAAU,EAAE,UAAU,CAAC,CAAC;AAC5C,CAAC;AAED,CAAC;IACC,MAAM,YAAY,GAAG,EAAE,CAAC,YAAY,CAAC,oBAAoB,EAAE,MAAM,CAAC,CAAC;IACnE,MAAM,oBAAoB,GAAG,EAAE,CAAC,YAAY,CAAC,8BAA8B,EAAE,MAAM,CAAC,CAAC;IACrF,MAAM,CAAC,EAAE,CACP,YAAY,CAAC,QAAQ,CAAC,uEAAuE,CAAC,CAC/F,CAAC;IACF,MAAM,CAAC,EAAE,CAAC,YAAY,CAAC,QAAQ,CAAC,yDAAyD,CAAC,CAAC,CAAC;IAC5F,MAAM,CAAC,EAAE,CAAC,oBAAoB,CAAC,QAAQ,CAAC,6BAA6B,CAAC,CAAC,CAAC;IACxE,MAAM,CAAC,EAAE,CAAC,oBAAoB,CAAC,QAAQ,CAAC,oBAAoB,CAAC,CAAC,CAAC;AACjE,CAAC;AAED,OAAO,CAAC,GAAG,CAAC,+BAA+B,CAAC,CAAC"}
+{"version":3,"file":"provider-refresh-smoke.js","sourceRoot":"","sources":["../../scripts/provider-refresh-smoke.ts"],"names":[],"mappings":"AAAA,OAAO,MAAM,MAAM,oBAAoB,CAAC;AACxC,OAAO,EAAE,MAAM,SAAS,CAAC;AACzB,OAAO,EAAE,MAAM,SAAS,CAAC;AACzB,OAAO,IAAI,MAAM,WAAW,CAAC;AAE7B,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAC;AACnD,OAAO,EAAE,oBAAoB,EAAE,MAAM,iCAAiC,CAAC;AACvE,OAAO,EAAE,iBAAiB,EAAE,MAAM,4BAA4B,CAAC;AAE/D,OAAO,CAAC,GAAG,CAAC,iBAAiB,GAAG,GAAG,CAAC;AACpC,OAAO,CAAC,GAAG,CAAC,2BAA2B,GAAG,GAAG,CAAC;AAC9C,OAAO,CAAC,GAAG,CAAC,kBAAkB,GAAG,qBAAqB,CAAC;AACvD,OAAO,CAAC,GAAG,CAAC,qBAAqB,GAAG,EAAE,CAAC,WAAW,CAChD,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,MAAM,EAAE,EAAE,gCAAgC,CAAC,CACzD,CAAC;AAEF,MAAM,MAAM,GAAG,UAAU,EAAE,CAAC;AAE5B,CAAC;IACC,MAAM,OAAO,GAAG,IAAI,iBAAiB,CAAC,MAAM,CAAC,CAAC;IAC9C,IAAI,eAA8E,CAAC;IAEjF,OASD,CAAC,MAAM,GAAG,KAAK,IAAI,EAAE,CAAC,CAAC;QACtB,IAAI,EAAE;YACJ,WAAW,EAAE;gBACX,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE;oBACxB,eAAe,GAAG,OAAO,CAAC;gBAC5B,CAAC;aACF;SACF;KACF,CAAC,CAAC;IAEH,MAAM,KAAK,GAAG,MAAM,OAAO,CAAC,KAAK,EAAE,CAAC;IACpC,MAAM,CAAC,KAAK,CAAC,KAAK,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;IACpC,MAAM,CAAC,KAAK,CAAC,eAAe,EAAE,cAAc,EAAE,IAAI,CAAC,CAAC;IACpD,MAAM,CAAC,EAAE,CACP,OAAO,eAAe,EAAE,UAAU,KAAK,QAAQ,IAAI,eAAe,CAAC,UAAU,IAAI,EAAE,EACnF,+EAA+E,CAChF,CAAC;AACJ,CAAC;AAED,CAAC;IACC,MAAM,MAAM,GAAG,oBAAoB,CACjC,QAAQ,EACR,CAAC,EAAE,EAAE,EAAE,iBAAiB,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,EAC1C,iBAAiB,CAClB,CAAC;IACF,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,QAAQ,EAAE,iBAAiB,CAAC,CAAC;IACjD,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,UAAU,EAAE,UAAU,CAAC,CAAC;AAC9C,CAAC;AAED,CAAC;IACC,MAAM,MAAM,GAAG,oBAAoB,CACjC,QAAQ,EACR,CAAC,EAAE,EAAE,EAAE,wBAAwB,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,EACjD,wBAAwB,CACzB,CAAC;IACF,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,QAAQ,EAAE,wBAAwB,CAAC,CAAC;IACxD,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,UAAU,EAAE,UAAU,CAAC,CAAC;AAC9C,CAAC;AAED,CAAC;IACC,MAAM,IAAI,GAAG,oBAAoB,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,EAAE,UAAU,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,EAAE,UAAU,CAAC,CAAC;IAC3F,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,QAAQ,EAAE,UAAU,CAAC,CAAC;IACxC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,UAAU,EAAE,UAAU,CAAC,CAAC;AAC5C,CAAC;AAED,CAAC;IACC,MAAM,YAAY,GAAG,EAAE,CAAC,YAAY,CAAC,oBAAoB,EAAE,MAAM,CAAC,CAAC;IACnE,MAAM,oBAAoB,GAAG,EAAE,CAAC,YAAY,CAAC,8BAA8B,EAAE,MAAM,CAAC,CAAC;IACrF,MAAM,CAAC,EAAE,CACP,YAAY,CAAC,QAAQ,CAAC,uEAAuE,CAAC,CAC/F,CAAC;IACF,MAAM,CAAC,EAAE,CACP,YAAY,CAAC,QAAQ,CACnB,2EAA2E,CAC5E,CACF,CAAC;IACF,MAAM,CAAC,EAAE,CAAC,YAAY,CAAC,QAAQ,CAAC,yDAAyD,CAAC,CAAC,CAAC;IAC5F,MAAM,CAAC,EAAE,CAAC,oBAAoB,CAAC,QAAQ,CAAC,6BAA6B,CAAC,CAAC,CAAC;IACxE,MAAM,CAAC,EAAE,CAAC,oBAAoB,CAAC,QAAQ,CAAC,oCAAoC,CAAC,CAAC,CAAC;IAC/E,MAAM,CAAC,EAAE,CAAC,oBAAoB,CAAC,QAAQ,CAAC,oBAAoB,CAAC,CAAC,CAAC;AACjE,CAAC;AAED,OAAO,CAAC,GAAG,CAAC,+BAA+B,CAAC,CAAC"}

package/dist/scripts/smoke.js

@@ -209,6 +209,7 @@ for (const { file, field } of adapterExpectations) {
 const modelSelectionSource = fs.readFileSync("src/peers/model-selection.ts", "utf8");
 for (const deprecatedOrWeakModel of [
     "claude-haiku-4-5",
+    "gemini-2.5-pro",
     "gemini-3-pro-preview",
     "deepseek-reasoner",
     "deepseek-chat",
@@ -221,7 +222,7 @@ for (const deprecatedOrWeakModel of [
 for (const canonicalPin of [
     "gpt-5.5",
     "claude-opus-4-8",
-    "gemini-2.5-pro",
+    "gemini-3.1-pro-preview",
     "deepseek-v4-pro",
     "grok-4.3",
     "sonar-reasoning-pro",
@@ -1373,6 +1374,19 @@ assert.equal(Object.hasOwn(metrics.decision_quality, "undefined"), false);
         follow_ups: [],
     }));
     assert.ok(!grounded.parser_warnings.includes("verified_without_evidence_sources"), "v4.2.2 / truthfulness_guardrails: concrete evidence_sources must satisfy verified confidence");
+    const attachedEvidenceGrounded = parseStatusForTruth(JSON.stringify({
+        status: "READY",
+        summary: "The raw gate proves the fix.",
+        confidence: "verified",
+        evidence_sources: [
+            "Attachment: RAW clean-room CI-equivalent gate (Node 24.14.0): npm ci exit 0; npm test 22 passed.",
+            "evidence/2026-06-05T09-55-29-249Z-RAW-clean-room-CI-equivalent-gate.txt: Test Files 4 passed (4)",
+            "L7001 jsdom dependency undici ^7.25.0; L9544 resolved undici 6.24.0",
+        ],
+        caller_requests: [],
+        follow_ups: [],
+    }));
+    assert.ok(!attachedEvidenceGrounded.parser_warnings.includes("verified_without_evidence_sources"), "v4.2.4 / truthfulness_guardrails: attachment paths, raw gate logs, and line-number labels are evidence_sources, not empty-evidence warnings");
     assert.ok(/confidence.*verified[\s\S]+evidence_sources/i.test(statusInstruction()), "v4.2.2 / truthfulness_guardrails: statusInstruction must tie verified confidence to concrete evidence_sources");
     console.log("[smoke] verified_requires_evidence_sources_test: PASS");
 }
@@ -5739,6 +5753,7 @@ assert.equal(Object.hasOwn(metrics.decision_quality, "undefined"), false);
     });
     assert.equal(contradictedByRuntime.pass, false, "v4.2.2 / truthfulness_preflight: current-runtime version claim contradicting runtime facts must trip even when server_info text is present");
     assert.ok(contradictedByRuntime.contradictions.some((item) => item.includes("4.2.0")), "v4.2.2 / truthfulness_preflight: mismatch diagnostics must include the contradicted version token");
+    assert.ok(contradictedByRuntime.issue_classes?.includes("runtime_contradiction"), "v4.2.4 / truthfulness_preflight: runtime contradictions must surface issue_classes=runtime_contradiction");
     const backedByRuntime = truthfulnessPreflight({
         task: "Audit all sessions generated with the current cross-review version.",
         initialDraft: 'Live server_info: {"version":"4.2.1","release_date":"2026-05-21"}\nAudit report for cross-review v4.2.1 current production, released 2026-05-21.',
@@ -5753,6 +5768,7 @@ assert.equal(Object.hasOwn(metrics.decision_quality, "undefined"), false);
         attachmentsPresent: false,
     });
     assert.equal(unsupportedCurrentState.pass, false, "v4.2.2 / truthfulness_preflight: current-runtime claim without runtime facts or source evidence must trip");
+    assert.ok(unsupportedCurrentState.issue_classes?.includes("unsupported_current_state_claim"), "v4.2.4 / truthfulness_preflight: unsupported current-state claims must have their own issue class");
     const historicalChangelog = truthfulnessPreflight({
         task: "Review this changelog text.",
         initialDraft: "v4.2.0 was released on 2026-05-17. v4.2.1 was released on 2026-05-21.",
@@ -5767,6 +5783,17 @@ assert.equal(Object.hasOwn(metrics.decision_quality, "undefined"), false);
         attachmentsPresent: false,
     });
     assert.equal(fabricatedTiming.pass, false, "v4.2.2 / truthfulness_preflight: historical runtime timing narrative without snapshot evidence must trip");
+    assert.ok(fabricatedTiming.issue_classes?.includes("unsupported_historical_claim"), "v4.2.4 / truthfulness_preflight: historical timing claims without snapshot evidence must surface unsupported_historical_claim");
+    assert.ok(/attachments_present=false/.test(fabricatedTiming.reason) &&
+        /session_attach_evidence/.test(fabricatedTiming.reason), "v4.2.4 / truthfulness_preflight: failure reason must tell operators that no attachment was visible and how to fix it");
+    const fabricatedWorkflowClaim = truthfulnessPreflight({
+        task: "Summarize the release closure.",
+        initialDraft: "I triggered the workflow dispatch after operator authorization and confirmed the remote deployment succeeded.",
+        runtimeFacts,
+        attachmentsPresent: false,
+    });
+    assert.equal(fabricatedWorkflowClaim.pass, false, "v4.2.4 / truthfulness_preflight: fabricated workflow or authorization claims must trip before paid calls");
+    assert.ok(fabricatedWorkflowClaim.issue_classes?.includes("fabrication_pattern"), "v4.2.4 / truthfulness_preflight: fabricated workflow/authorization claims must surface issue_classes=fabrication_pattern");
     const withStructuredEvidence = truthfulnessPreflight({
         task: "Explain why the report said v4.2.0.",
         initialDraft: "When the workflow began, cross-review was running v4.2.0. It was bumped to v4.2.1 between R1 and R3.",
@@ -5781,9 +5808,36 @@ assert.equal(Object.hasOwn(metrics.decision_quality, "undefined"), false);
     assert.ok(/truthfulness_preflight_enabled/.test(orchSrcTruth) &&
         /askPeers[\s\S]+truthfulnessPreflight/.test(orchSrcTruth) &&
         /runUntilUnanimous[\s\S]+truthfulnessPreflight/.test(orchSrcTruth), "v4.2.2 / truthfulness_preflight: both askPeers and runUntilUnanimous must gate on config.truthfulness_preflight_enabled");
+    assert.ok(/recordPreflightFailure/.test(orchSrcTruth), "v4.2.4 / truthfulness_preflight: preflight aborts without rounds must still persist failed_attempts metadata");
     assert.ok(/boolEnv\("CROSS_REVIEW_TRUTHFULNESS_PREFLIGHT", true\)/.test(configSrcTruth), "v4.2.2 / truthfulness_preflight: CROSS_REVIEW_TRUTHFULNESS_PREFLIGHT env var must default ON");
     console.log("[smoke] truthfulness_preflight_test: PASS");
 }
+// v4.2.4 — truthfulness_preflight_runtime_contract_test.
+// A failed preflight should be inspectable without scraping events, and
+// operators should be able to re-run the same read-only preflight after
+// attaching evidence instead of starting duplicate sessions.
+{
+    const orchSrcTruth = fs.readFileSync(new URL("../src/core/orchestrator.ts", import.meta.url), "utf8");
+    const storeSrcTruth = fs.readFileSync(new URL("../src/core/session-store.ts", import.meta.url), "utf8");
+    const serverSrcTruth = fs.readFileSync(new URL("../src/mcp/server.ts", import.meta.url), "utf8");
+    assert.ok(/recordPreflightFailure/.test(storeSrcTruth) &&
+        /failed_attempts/.test(storeSrcTruth) &&
+        /truthfulness_preflight/.test(storeSrcTruth), "v4.2.4 / truthfulness_preflight: SessionStore must persist preflight failed_attempts even when no round is appended");
+    const runUntilIndex = orchSrcTruth.indexOf("async runUntilUnanimous");
+    const truthfulnessIndex = orchSrcTruth.indexOf("const truthfulness = truthfulnessPreflight", runUntilIndex);
+    const evidenceIndex = orchSrcTruth.indexOf("const preflight = evidencePreflight", runUntilIndex);
+    const leadGenerationIndex = orchSrcTruth.indexOf("const generation = await adapters[leadPeer].generate", runUntilIndex);
+    assert.ok(runUntilIndex >= 0 &&
+        truthfulnessIndex > runUntilIndex &&
+        evidenceIndex > truthfulnessIndex &&
+        leadGenerationIndex > evidenceIndex, "v4.2.4 / truthfulness_preflight: runUntilUnanimous must run truthfulness/evidence preflight before paid lead generation");
+    assert.ok(/"session_truthfulness_preflight_check"/.test(serverSrcTruth) &&
+        /readEvidenceAttachments/.test(serverSrcTruth) &&
+        /truthfulnessPreflight/.test(serverSrcTruth), "v4.2.4 / truthfulness_preflight: MCP must expose a read-only session_truthfulness_preflight_check retest tool");
+    assert.ok(/"session_truthfulness_preflight_check"/.test(serverSrcTruth) &&
+        /TOOL_NAMES[\s\S]*session_truthfulness_preflight_check/.test(serverSrcTruth), "v4.2.4 / truthfulness_preflight: server_info tool list must include session_truthfulness_preflight_check");
+    console.log("[smoke] truthfulness_preflight_runtime_contract_test: PASS");
+}
 // v3.5.0 (CRV2-1 + CRV2-6) — budget + max_rounds traceability.
 //
 // setSessionTraceability persists requested-vs-effective max_rounds and
@@ -6129,13 +6183,13 @@ assert.equal(Object.hasOwn(metrics.decision_quality, "undefined"), false);
     // SINGLE canonical pin. Negative pins (off-policy models that must never
     // appear) + positive pins (the exact lone-entry shape per peer).
     const a3ModelSrc = fs.readFileSync(new URL("../src/peers/model-selection.ts", import.meta.url), "utf8");
-    for (const offPolicyModel of ["deepseek-v4-flash", "gemini-3.1-pro-preview"]) {
+    for (const offPolicyModel of ["deepseek-v4-flash", "gemini-2.5-pro"]) {
         assert.ok(!a3ModelSrc.includes(`"${offPolicyModel}"`), `v3.7.2 / AUDIT-3: ${offPolicyModel} must not appear in the PRIORITY lists`);
     }
     for (const [peer, pin] of [
         ["codex", "gpt-5.5"],
         ["claude", "claude-opus-4-8"],
-        ["gemini", "gemini-2.5-pro"],
+        ["gemini", "gemini-3.1-pro-preview"],
         ["deepseek", "deepseek-v4-pro"],
         ["grok", "grok-4.3"],
         ["perplexity", "sonar-reasoning-pro"],