wogiflow 2.25.0 → 2.25.1

package/.claude/commands/wogi-debug-hypothesis.md

@@ -176,7 +176,7 @@ After all agents complete, display the consolidated results:
 
 ### Step 4: Hypothesis Adversary (v2.23.0+ — MANDATORY unless `--no-adversary`)
 
-After consolidation, spawn a single Agent (different `model` param if `config.hybrid.enabled`, else same) with this prompt:
+After consolidation, spawn a single Agent on a DIFFERENT model (default `sonnet` via `config.researchReasoningGate.tier3.adversaryModel` — canonical cross-command adversary key, same as `/wogi-peer-review`, `/wogi-learn`, `/wogi-decide`) with this prompt:
 
 ```
 You are the hypothesis adversary.

package/.claude/commands/wogi-peer-review.md

@@ -47,9 +47,11 @@ Models are selected once per session and remembered for subsequent runs.
 ├─────────────────────────────────────────────────────────┤
 │  1. Collect code changes (git diff or specified files)   │
 │  2. Classify change size → effort tier:                  │
-│     L0/L1 (>10 files)  → opus-4-7 xhigh                  │
+│     L0/L1 (>10 files)  → opus (latest) xhigh             │
 │     L2 (3-10 files)    → sonnet medium                   │
 │     L3 (<3 files)      → haiku medium                    │
+│     (Model IDs resolve from config.models — avoid        │
+│      hardcoding model version in this doc.)              │
 │  3. Generate improvement-focused prompt                  │
 │  4. If includeClaude enabled:                            │
 │     - Launch Claude review (Task agent, Explore type)    │
@@ -96,7 +98,7 @@ analysis, EACH carrying an explicit evidence tier.
 
 ## Synthesis Adversary (v2.23.0+ — MANDATORY unless `--no-adversary`)
 
-After initial synthesis, spawn a single adversary agent on a DIFFERENT model from the synthesizer (default: if synthesizer is Opus, adversary is Sonnet; config via `peerReview.adversaryModel`). Prompt:
+After initial synthesis, spawn a single adversary agent on a DIFFERENT model from the synthesizer (default `sonnet`; override via the canonical `config.researchReasoningGate.tier3.adversaryModel` — same key used by `/wogi-debug-hypothesis`, `/wogi-learn`, `/wogi-decide`). Prompt:
 
 ```
 You are the synthesis adversary.
@@ -199,7 +201,7 @@ For manual review (no API keys needed): `/wogi-peer-review --manual`
 | `--verbose` | Show full model responses |
 | `--create-tasks` | Auto-create tasks for strong agreements |
 | `--no-adversary` | Skip the v2.23.0 synthesis adversary (not recommended for L0/L1 diffs) |
-| `--adversary-model <id>` | Override adversary model (default: cross-model from synthesizer) |
+| `--adversary-model <id>` | Override adversary model (default: `config.researchReasoningGate.tier3.adversaryModel`, usually `sonnet`) |
 | `--effort <level>` | Override effort tier (low/medium/high/xhigh/max) — otherwise derived from diff size |
 
 ARGUMENTS: {args}

package/.claude/commands/wogi-triage.md

@@ -357,33 +357,45 @@ Each finding is displayed using these fields from `last-review.json`:
 | Issue | `finding.issue` | "Raw JSON.parse without try-catch" |
 | Recommendation | `finding.recommendation` | "Use safeJsonParse from flow-utils.js" |
 
-## Anti-Deferral Enforcement (v2.25.0+ — MANDATORY)
+## Anti-Deferral Enforcement (v2.25.0+ — two layers)
 
-The **Review-Findings Anti-Deferral Rule** (`.workflow/state/decisions.md`, 2026-04-15) extends to `/wogi-triage` mechanically in v2.25.0+. Prevents the rubber-stamp pattern where the AI silently drops findings from "fix all" requests.
+The **Review-Findings Anti-Deferral Rule** (`.workflow/state/decisions.md`, 2026-04-15) gets two complementary enforcement layers. One mechanical (an actual gate in the codebase), one AI-followed (a protocol documented here that the triage flow honors).
 
-**Enforcement rules**:
+### Layer 1 — Mechanical gate (v2.25.1+)
 
-1. **"Defer" / "skip" requires explicit user confirmation with a reason.** When the AI or user proposes to defer a finding, the triage flow MUST prompt:
+`scripts/flow-completion-truth-gate.js` exports `parseCommitMessageClaims()` and `verifyCommitMessageAgainstDiff()`. Callers pass a commit message and the staged diff (or changed-files list); the function parses finding IDs (`F1`/`M1`/`SEC-001`), task IDs (`wf-XXXXXXXX` after fix/close/resolve verbs), and file-path mentions, then checks each against the diff. Any unverified claim surfaces as a blocking prompt with three remediation options. This is real code, callable from pre-commit hooks, `flow-done.js`, or the triage flow itself.
+
+Example usage:
+```javascript
+const { verifyCommitMessageAgainstDiff, formatMissingClaimsMessage } =
+  require('wogiflow/scripts/flow-completion-truth-gate');
+
+const result = verifyCommitMessageAgainstDiff(commitMsg, { diffText, changedFiles });
+if (!result.ok) {
+  console.error(formatMissingClaimsMessage(result));
+  // Block + remediate
+}
+```
+
+### Layer 2 — AI-followed protocol (documentation)
+
+The rest of the triage flow is a protocol the AI follows. It is NOT automatically enforced by a hook — the historical v2.17.4 incident showed that doc-only protocols can be violated. The mechanical gate above closes the most damaging failure mode (commit message / diff mismatch). The AI-followed rules below cover the earlier stages:
+
+1. **Defer requires explicit user confirmation + reason.** The triage flow prompts when proposing to defer:
    ```
    Defer finding wf-review-XXXX?
      Severity: HIGH
      Reason required: [user input]
      [Confirm defer] [Cancel — fix now]
    ```
-   Auto-defer without reason is FORBIDDEN.
+   Auto-defer without reason is forbidden by this protocol.
 
-2. **"Fix all" / "Option 1" / equivalent means fix ALL.** If the user requests bulk processing:
+2. **"Fix all" / "Option 1" means fix ALL.** If the user requests bulk processing:
    - Ship a fix for every finding with evidence-tier ≥ 1
    - If any finding is too large, STOP and ask: "Finding X requires ~Y minutes of work. Ship now, split to its own release, or defer (needs reason)?"
    - Never silently convert a finding to "deferred" in commit messages or release notes
 
-3. **Commit/release consistency check.** Before finalizing, scan the commit message / release notes against the findings list. If the message claims "fixes F1, F2, F3, M1" but M1 isn't in the diff, BLOCK with:
-   ```
-   Commit message claims M1 is fixed, but M1 does not appear in the diff.
-   Options: [Fix M1 now] [Remove M1 from message] [Acknowledge + proceed]
-   ```
-
-4. **Triage output includes a Deferral Audit Trail**:
+3. **Triage output includes a Deferral Audit Trail**:
    ```
    ━━━ TRIAGE SUMMARY ━━━
    Fixed: 12
@@ -394,6 +406,10 @@ The **Review-Findings Anti-Deferral Rule** (`.workflow/state/decisions.md`, 2026
    ━━━━━━━━━━━━━━━━━━━━━━
    ```
 
-Historical incident (v2.17.4 release, 2026-04-15): commit message claimed "fix all findings" but M1 and M3 were silently dropped. The v2.25.0+ mechanical enforcement makes that failure mode architecturally impossible — the flow stops and asks rather than letting the AI make an autonomous defer decision.
+### Honest tradeoff
+
+Layer 1 is genuinely mechanical — impossible for an AI to bypass without explicitly disabling the gate. Layer 2 is a protocol the AI can fail to follow if prompted poorly, distracted, or confused about priorities. Both matter; calling the whole system "architecturally impossible to bypass" would be inaccurate. The mechanical gate at least ensures that WHEN the AI writes a commit message, claimed fixes must actually appear in the diff.
+
+Historical incident (v2.17.4 release, 2026-04-15): commit claimed "fix all findings" but M1 and M3 were silently dropped. Layer 1 would have caught that — the commit message mentioned M1 + M3 but the diff didn't. Layer 2 is the human-protocol reinforcement.
 
-Skip only if `config.triage.antiDeferralEnforcement.enabled` is explicitly `false` (default: true).
+Skip via `config.triage.antiDeferralEnforcement.enabled: false` — note that this is currently a surface flag only (read by AI-followed protocol, not by the Layer 1 gate); to disable Layer 1 set `config.commitClaimsGate.enabled: false`.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "wogiflow",
-  "version": "2.25.0",
+  "version": "2.25.1",
   "description": "AI-powered development workflow management system with multi-model support",
   "main": "lib/index.js",
   "bin": {
@@ -10,7 +10,7 @@
   },
   "scripts": {
     "flow": "./scripts/flow",
-    "test": "NODE_ENV=test node --test tests/auto-compact-prompt.test.js tests/flow-paths.test.js tests/flow-io.test.js tests/flow-config-loader.test.js tests/flow-damage-control.test.js tests/flow-output.test.js tests/flow-constants.test.js tests/flow-session-state.test.js tests/flow-hooks-integration.test.js tests/flow-utils.test.js tests/flow-security.test.js tests/flow-memory-db.test.js tests/flow-durable-session.test.js tests/flow-skill-matcher.test.js tests/flow-bridge.test.js tests/flow-proactive-compact.test.js tests/flow-cascade-completion.test.js tests/flow-capture-gate.test.js tests/flow-correction-detector-hybrid.test.js tests/flow-promote.test.js tests/flow-archive-runs.test.js tests/flow-memory.test.js tests/flow-hooks-pre-tool-helpers.test.js tests/flow-hooks-bugfix-scope-gate.test.js tests/flow-hooks-routing-gate.test.js tests/flow-hooks-phase-read-gate.test.js tests/flow-hooks-commit-log-gate.test.js tests/flow-hooks-deploy-gate.test.js tests/flow-hooks-todowrite-gate.test.js tests/flow-hooks-git-safety-gate.test.js tests/flow-hooks-scope-mutation-gate.test.js tests/flow-hooks-strike-gate.test.js tests/flow-hooks-component-check.test.js tests/flow-hooks-scope-gate.test.js tests/flow-hooks-implementation-gate.test.js tests/flow-hooks-research-gate.test.js tests/flow-hooks-loop-check.test.js tests/flow-hooks-manager-boundary-gate.test.js tests/flow-hooks-phase-gate.test.js tests/flow-hooks-pre-tool-orchestrator.test.js tests/flow-hooks-observation-capture.test.js tests/flow-hooks-task-gate.test.js tests/flow-durable-session-suspension.test.js tests/flow-health-mcp-scopes.test.js tests/flow-lean-config.test.js tests/flow-workspace-autopickup.test.js tests/flow-worker-boundary-gate.test.js tests/flow-worker-question-classifier.test.js tests/flow-completion-truth-gate-contradictions.test.js tests/flow-structure-sensor.test.js tests/flow-workspace-dispatch-tracking.test.js tests/flow-story-gates.test.js tests/flow-workspace-restart-handoff.test.js tests/flow-wogi-claude-wrapper.test.js tests/flow-wave1-integrations.test.js tests/flow-wave2-integrations.test.js tests/flow-wave3-integrations.test.js && NODE_ENV=test node tests/run-quality-gates.test.js",
+    "test": "NODE_ENV=test node --test tests/auto-compact-prompt.test.js tests/flow-paths.test.js tests/flow-io.test.js tests/flow-config-loader.test.js tests/flow-damage-control.test.js tests/flow-output.test.js tests/flow-constants.test.js tests/flow-session-state.test.js tests/flow-hooks-integration.test.js tests/flow-utils.test.js tests/flow-security.test.js tests/flow-memory-db.test.js tests/flow-durable-session.test.js tests/flow-skill-matcher.test.js tests/flow-bridge.test.js tests/flow-proactive-compact.test.js tests/flow-cascade-completion.test.js tests/flow-capture-gate.test.js tests/flow-correction-detector-hybrid.test.js tests/flow-promote.test.js tests/flow-archive-runs.test.js tests/flow-memory.test.js tests/flow-hooks-pre-tool-helpers.test.js tests/flow-hooks-bugfix-scope-gate.test.js tests/flow-hooks-routing-gate.test.js tests/flow-hooks-phase-read-gate.test.js tests/flow-hooks-commit-log-gate.test.js tests/flow-hooks-deploy-gate.test.js tests/flow-hooks-todowrite-gate.test.js tests/flow-hooks-git-safety-gate.test.js tests/flow-hooks-scope-mutation-gate.test.js tests/flow-hooks-strike-gate.test.js tests/flow-hooks-component-check.test.js tests/flow-hooks-scope-gate.test.js tests/flow-hooks-implementation-gate.test.js tests/flow-hooks-research-gate.test.js tests/flow-hooks-loop-check.test.js tests/flow-hooks-manager-boundary-gate.test.js tests/flow-hooks-phase-gate.test.js tests/flow-hooks-pre-tool-orchestrator.test.js tests/flow-hooks-observation-capture.test.js tests/flow-hooks-task-gate.test.js tests/flow-durable-session-suspension.test.js tests/flow-health-mcp-scopes.test.js tests/flow-lean-config.test.js tests/flow-workspace-autopickup.test.js tests/flow-worker-boundary-gate.test.js tests/flow-worker-question-classifier.test.js tests/flow-completion-truth-gate-contradictions.test.js tests/flow-structure-sensor.test.js tests/flow-workspace-dispatch-tracking.test.js tests/flow-story-gates.test.js tests/flow-workspace-restart-handoff.test.js tests/flow-wogi-claude-wrapper.test.js tests/flow-wave1-integrations.test.js tests/flow-wave2-integrations.test.js tests/flow-wave3-integrations.test.js tests/flow-commit-claims-gate.test.js && NODE_ENV=test node tests/run-quality-gates.test.js",
     "test:syntax": "find scripts/ lib/ -name '*.js' -not -path '*/node_modules/*' -exec node --check {} +",
     "lint": "eslint scripts/ lib/ tests/",
     "lint:ci": "eslint scripts/ lib/ tests/ --max-warnings 0",

package/scripts/flow-completion-truth-gate.js

@@ -614,6 +614,133 @@ function collectArrayEntries(obj, keys) {
   return out;
 }
 
+// ============================================================
+// Commit-vs-diff consistency scanner (v2.25.1 — H2b from Waves 1-3 review)
+// ============================================================
+
+/**
+ * Parse a commit message for "fixes X" / "closes X" / "F1, F2, M1" style claims
+ * that should be verifiable against the diff.
+ *
+ * Heuristics — conservative to avoid false positives:
+ *   1. Bracketed finding IDs: `F1`, `F2`, `M1`, `H3`, `L5`, or `SEC-001`/`PERF-002`
+ *   2. Task IDs: `wf-XXXXXXXX` that appear as "fixes wf-...", "closes wf-...", etc.
+ *   3. File paths mentioned in fix-context: "fixes `path/to/file.js`"
+ *
+ * Returns the structured claims a diff-consistency check can verify.
+ *
+ * @param {string} commitMessage
+ * @returns {{claims: Array<{kind: 'finding-id'|'task-id'|'file', value: string, raw: string}>}}
+ */
+function parseCommitMessageClaims(commitMessage) {
+  const claims = [];
+  if (typeof commitMessage !== 'string' || commitMessage.trim().length === 0) {
+    return { claims };
+  }
+
+  // Finding IDs: F1, F2, M1, H3, L5, SEC-001, PERF-002, etc.
+  //   - Single-letter + digits: match on word boundary
+  //   - ALLCAPS-dashnum: SEC-001, PERF-002
+  const findingRe = /\b(?:F\d+|H\d+|M\d+|L\d+|[A-Z]{2,6}-\d+)\b/g;
+  for (const m of commitMessage.matchAll(findingRe)) {
+    claims.push({ kind: 'finding-id', value: m[0], raw: m[0] });
+  }
+
+  // Task IDs (wf-XXXXXXXX) — only count if preceded by fix/close/resolve verb
+  const taskRe = /\b(?:fix(?:es|ed)?|clos(?:es|ed)?|resolv(?:es|ed)?|address(?:es|ed)?)\s+(wf-[0-9a-f]{8})\b/gi;
+  for (const m of commitMessage.matchAll(taskRe)) {
+    claims.push({ kind: 'task-id', value: m[1], raw: m[0] });
+  }
+
+  // File paths in backticks after fix/address verbs: `fixes \`path/to/file.js\``
+  const fileRe = /(?:fix(?:es|ed)?|address(?:es|ed)?|updat(?:es|ed)?)\s+`([^`\n]{3,120})`/gi;
+  for (const m of commitMessage.matchAll(fileRe)) {
+    // Only count values that look like file paths (have an extension or a slash)
+    const val = m[1];
+    if (/[./]/.test(val) && !val.includes(' ')) {
+      claims.push({ kind: 'file', value: val, raw: m[0] });
+    }
+  }
+
+  // Dedup
+  const seen = new Set();
+  return {
+    claims: claims.filter(c => {
+      const k = `${c.kind}::${c.value.toLowerCase()}`;
+      if (seen.has(k)) return false;
+      seen.add(k);
+      return true;
+    })
+  };
+}
+
+/**
+ * Check commit message claims against the staged diff. Each claim must appear
+ * somewhere in the diff (a file path in the changed-files list OR the token
+ * appearing as-is in the diff body).
+ *
+ * @param {string} commitMessage
+ * @param {Object} [opts]
+ * @param {string} [opts.diffText] — raw `git diff --staged` output
+ * @param {string[]} [opts.changedFiles] — staged file list (alternative input)
+ * @returns {{ok: boolean, totalClaims: number, missingClaims: Array, verifiedClaims: Array}}
+ */
+function verifyCommitMessageAgainstDiff(commitMessage, opts = {}) {
+  const { claims } = parseCommitMessageClaims(commitMessage);
+  if (claims.length === 0) return { ok: true, totalClaims: 0, missingClaims: [], verifiedClaims: [] };
+
+  const diffText = typeof opts.diffText === 'string' ? opts.diffText : '';
+  const changedFiles = Array.isArray(opts.changedFiles) ? opts.changedFiles : [];
+  const haystack = [diffText, ...changedFiles].join('\n');
+
+  const missingClaims = [];
+  const verifiedClaims = [];
+
+  for (const claim of claims) {
+    let found = false;
+    if (claim.kind === 'file') {
+      // File claims verify by exact path match (or suffix) in changed-files list
+      found = changedFiles.some(f => f === claim.value || f.endsWith('/' + claim.value) || f.endsWith(claim.value));
+      if (!found) found = diffText.includes(claim.value);
+    } else {
+      // finding-id + task-id: plain substring search in the haystack
+      found = haystack.includes(claim.value);
+    }
+    (found ? verifiedClaims : missingClaims).push(claim);
+  }
+
+  return {
+    ok: missingClaims.length === 0,
+    totalClaims: claims.length,
+    missingClaims,
+    verifiedClaims
+  };
+}
+
+/**
+ * Human-readable message when claims are missing from the diff.
+ *
+ * @param {Object} result — from verifyCommitMessageAgainstDiff
+ * @returns {string|null}
+ */
+function formatMissingClaimsMessage(result) {
+  if (!result || result.ok || !Array.isArray(result.missingClaims) || result.missingClaims.length === 0) {
+    return null;
+  }
+  const lines = [
+    `Commit message claims ${result.missingClaims.length} item(s) that do not appear in the staged diff:`
+  ];
+  for (const c of result.missingClaims) {
+    lines.push(`  • ${c.kind === 'finding-id' ? 'Finding' : c.kind === 'task-id' ? 'Task' : 'File'} "${c.value}" — not found`);
+  }
+  lines.push('');
+  lines.push('Options:');
+  lines.push('  1. Add the missing fix to the commit now (git add + amend)');
+  lines.push('  2. Remove the unverified claim from the commit message');
+  lines.push('  3. Acknowledge + proceed (use --force-commit-claims if blocking from a gate)');
+  return lines.join('\n');
+}
+
 // ============================================================
 // Exports
 // ============================================================
@@ -627,6 +754,9 @@ module.exports = {
   isTruthGateDisabled,
   getMinTierForDone,
   scanForClaimContradictions,
+  parseCommitMessageClaims,
+  verifyCommitMessageAgainstDiff,
+  formatMissingClaimsMessage,
   TIER_NAMES,
   DONE_WORDS,
   DISAGREEMENT_WORDS,

package/scripts/flow-config-defaults.js

@@ -818,6 +818,31 @@ const CONFIG_DEFAULTS = {
   // --- Gate Confidence ---
   gateConfidence: { enabled: false },
 
+  // --- Intent-Grounded Reasoning (IGR) ---
+  // Master flag for the IGR pipeline: Intent Framing (Step 1.15), Architect
+  // Pass (Step 1.55), Logic Adversary (Step 1.57), Scope-Confidence Audit
+  // (Step 1.45), Completion Truth Gate (Step 3.9). Default-on so new projects
+  // inherit the full reasoning pipeline. See .claude/docs/intent-grounded-reasoning.md.
+  intentGroundedReasoning: {
+    enabled: true,
+    _comment: 'IGR pipeline: architect + logic adversary + truth gate. See .claude/docs/intent-grounded-reasoning.md'
+  },
+
+  // --- Research Reasoning Gate ---
+  // Tiered classification for conversation-mode questions. Tier 1 = factual,
+  // direct answer. Tier 2 = domain/recommendation, surface assumptions and
+  // wait for user confirmation. Tier 3 = architecture, tier 2 flow + spawn
+  // cross-model adversary. See wogi-start.md § Research Reasoning Gate.
+  researchReasoningGate: {
+    enabled: true,
+    tier2: { enabled: true },
+    tier3: {
+      enabled: true,
+      adversaryModel: 'sonnet',
+      _comment_adversaryModel: 'Model used for Tier-3 cross-model adversary. Reused by /wogi-peer-review, /wogi-debug-hypothesis, /wogi-learn, /wogi-decide — single canonical key.'
+    }
+  },
+
   // --- Long Input Gate ---
   longInputGate: {
     enabled: true,

package/scripts/flow-extraction-review.js

@@ -104,8 +104,13 @@ function loadReviewSession() {
       return null;
     }
 
-    // Check for prototype pollution keys
-    if ('__proto__' in parsed || 'constructor' in parsed || 'prototype' in parsed) {
+    // Check for prototype pollution keys. Use Object.prototype.hasOwnProperty
+    // rather than `key in parsed` — the latter also returns true for inherited
+    // properties, and EVERY plain object inherits `constructor` from
+    // Object.prototype, which made this guard falsely trip on every valid
+    // session file (pre-existing bug, found via v2.25.1 wave2 test).
+    const hasOwn = Object.prototype.hasOwnProperty;
+    if (hasOwn.call(parsed, '__proto__') || hasOwn.call(parsed, 'constructor') || hasOwn.call(parsed, 'prototype')) {
       console.error('Review session file contains unsafe keys');
       return null;
     }
@@ -414,11 +419,21 @@ function exportAsItemManifest() {
   // Coordinate with Intent Bootstrap (see flow-story-gates.coordinateIntentBootstrap)
   // so /wogi-start doesn't re-prompt if the user already scheduled bootstrap via
   // /wogi-story during this session.
+  //
+  // v2.25.1: Semantics corrected (nit from Waves 1-3 review). The flag
+  // represents "is IGR bootstrap active/scheduled for this session?", NOT
+  // "did THIS call schedule it?". `result.active` is true when IGR is enabled
+  // and bootstrap has been scheduled — whether by this call or a prior one.
   let intentBootstrapScheduled = false;
   try {
     const gates = require('./flow-story-gates');
     const result = gates.coordinateIntentBootstrap();
-    intentBootstrapScheduled = !!(result && result.scheduled);
+    if (result && result.active) {
+      // Scheduled in this call OR already-scheduled from a prior call = active
+      intentBootstrapScheduled = result.scheduled === true ||
+                                 result.reason === 'already-scheduled' ||
+                                 result.reason === 'artifacts-exist';
+    }
   } catch (_err) { /* non-critical */ }
 
   return {

package/scripts/flow-morning.js

@@ -385,22 +385,31 @@ function collectBriefingData() {
   // v2.23.0 — Workspace dispatch surfacing (manager mode only).
   // If the user is working inside a workspace manager session, surface any
   // overdue or restart-gap-lost dispatches so the morning briefing catches
-  // what the last manager turn would have caught. Fail-open.
+  // what the last manager turn would have caught. Fail-open; DEBUG-logged.
   try {
     if (process.env.WOGI_WORKSPACE_ROOT) {
       const { buildOverdueContext } = require('./hooks/core/overdue-dispatches');
       const ctx = buildOverdueContext();
       if (ctx) briefing.workspaceOverdue = ctx;
     }
-  } catch (_err) { /* non-critical */ }
+  } catch (err) {
+    if (process.env.DEBUG) {
+      console.error(`[morning] Workspace overdue check failed (fail-open): ${err.message}`);
+    }
+  }
 
   // v2.23.0 — Completion-claim honesty scan.
   // Catches done-word-in-notes-while-status-partial and similar
   // contradictions across ready.json (uses the honesty-infra from 2026-04-16).
+  // Fail-open; DEBUG-logged.
   try {
     const { checkCompletionClaimHonesty } = require('./flow-health');
     briefing.honestyHits = checkCompletionClaimHonesty();
-  } catch (_err) { /* non-critical */ }
+  } catch (err) {
+    if (process.env.DEBUG) {
+      console.error(`[morning] Honesty scan failed (fail-open): ${err.message}`);
+    }
+  }
 
   // Generate suggested prompt if enabled
   if (morningConfig.generatePrompt !== false) {

package/scripts/flow-session-end.js

@@ -596,9 +596,18 @@ function writeWorkspaceSessionEndMessage() {
   const workspaceRoot = process.env.WOGI_WORKSPACE_ROOT;
   if (!workspaceRoot) return;
   const repo = process.env.WOGI_REPO_NAME;
-  // Only manager-mode sessions emit this signal. Workers use their own
-  // Stop-hook worker-stopped message (see lib/workspace-messages.js).
-  if (repo && repo !== 'manager') return;
+  // Only emit this signal from EXPLICIT manager-mode sessions.
+  // v2.25.1 (M2 from Waves 1-3 review): tightened to require
+  // WOGI_REPO_NAME === 'manager' explicitly. Previously we let
+  // unset-repo sessions fall through, which could emit a spurious
+  // "manager session ended" broadcast from a mis-env'd worker shell.
+  // Workers use their own Stop-hook worker-stopped message.
+  if (repo !== 'manager') {
+    if (repo && process.env.DEBUG) {
+      console.error(`[session-end] Skipping workspace message — WOGI_REPO_NAME is '${repo}', not 'manager'`);
+    }
+    return;
+  }
 
   try {
     const messagesLib = path.resolve(__dirname, '..', 'lib', 'workspace-messages.js');