@boyingliu01/xp-gate 0.15.5 → 0.18.0

package/scripts/migrate-audit-anomalies.mjs

@@ -0,0 +1,78 @@
+#!/usr/bin/env node
+/**
+ * Issue #370: One-time migration to mark existing anomalous audit records.
+ *
+ * Scans .xp-gate/audit.jsonl for entries where duration_ms > max_duration_ms
+ * (default 7200000ms = 2h, configurable via .xp-gate-config.json audit.max_duration_ms)
+ * and adds `duration_anomaly: true` to those entries.
+ *
+ * Original duration_ms values are PRESERVED — never clamped or modified.
+ *
+ * Usage: node src/npm-package/scripts/migrate-audit-anomalies.mjs [--dry-run]
+ */
+import { readFileSync, writeFileSync, existsSync } from 'fs';
+import { join } from 'path';
+
+const repoRoot = process.cwd();
+const auditPath = join(repoRoot, '.xp-gate', 'audit.jsonl');
+const configPath = join(repoRoot, '.xp-gate-config.json');
+const dryRun = process.argv.includes('--dry-run');
+
+// Read max_duration_ms from config (default 7200000)
+let maxDurationMs = 7200000;
+if (existsSync(configPath)) {
+  try {
+    const config = JSON.parse(readFileSync(configPath, 'utf8'));
+    if (config.audit && typeof config.audit.max_duration_ms === 'number') {
+      maxDurationMs = config.audit.max_duration_ms;
+    }
+  } catch {
+    // Use default
+  }
+}
+
+if (!existsSync(auditPath)) {
+  console.log(`No audit log found at ${auditPath} — nothing to migrate.`);
+  process.exit(0);
+}
+
+const content = readFileSync(auditPath, 'utf8');
+const lines = content.split('\n');
+let markedCount = 0;
+let alreadyMarked = 0;
+const updatedLines = [];
+
+for (const line of lines) {
+  if (!line.trim()) {
+    updatedLines.push(line);
+    continue;
+  }
+  try {
+    const entry = JSON.parse(line);
+    if (entry.duration_ms > maxDurationMs) {
+      if (entry.duration_anomaly === true) {
+        alreadyMarked++;
+      } else {
+        entry.duration_anomaly = true;
+        markedCount++;
+      }
+    }
+    updatedLines.push(JSON.stringify(entry));
+  } catch {
+    // Preserve malformed lines as-is
+    updatedLines.push(line);
+  }
+}
+
+if (dryRun) {
+  console.log(`[DRY RUN] Would mark ${markedCount} records with duration_anomaly: true`);
+  console.log(`[DRY RUN] Already marked: ${alreadyMarked}`);
+  console.log(`[DRY RUN] Threshold: duration_ms > ${maxDurationMs}`);
+} else {
+  writeFileSync(auditPath, updatedLines.join('\n'), 'utf8');
+  console.log(`Migration complete:`);
+  console.log(`  Marked ${markedCount} records with duration_anomaly: true`);
+  console.log(`  Already marked: ${alreadyMarked}`);
+  console.log(`  Threshold: duration_ms > ${maxDurationMs}`);
+  console.log(`  File: ${auditPath}`);
+}

package/scripts/sync-package-content.js

@@ -9,7 +9,11 @@ const REPO_ROOT = path.resolve(PKG_ROOT, '..', '..');
 
 const CORE_SKILLS = [
   'admin-template-guidelines',
+  'batch-grill-me',
   'delphi-review',
+  'domain-modeling',
+  'grill-with-docs',
+  'grilling',
   'improve-codebase-architecture',
   'ralph-loop',
   'sprint-flow',
@@ -172,6 +176,48 @@ function syncAdapters() {
   return copied + gateFiles.length;
 }
 
+function syncHooks() {
+  const SRC = path.join(REPO_ROOT, 'githooks');
+  const DST = path.join(PKG_ROOT, 'hooks');
+  // In-place copy (no rmrf) to avoid race condition with parallel test readers.
+  fs.mkdirSync(DST, { recursive: true });
+
+  const HOOK_FILES = ['pre-commit', 'pre-push', 'adapter-common.sh'];
+  let copied = 0;
+
+  for (const name of HOOK_FILES) {
+    const srcPath = path.join(SRC, name);
+    const dstPath = path.join(DST, name);
+    if (fs.existsSync(srcPath)) {
+      fs.copyFileSync(srcPath, dstPath);
+      copied += 1;
+    }
+  }
+
+  // Copy lib/ subdirectory recursively
+  const libSrc = path.join(SRC, 'lib');
+  const libDst = path.join(DST, 'lib');
+  if (fs.existsSync(libSrc)) {
+    copyDir(libSrc, libDst);
+    copied += 1;
+  }
+
+  // Copy gate-*.sh files from githooks root to hooks/
+  const gateFiles = fs.readdirSync(SRC).filter(f =>
+    f.endsWith('.sh') && (f.startsWith('gate-') || f === 'sprint-gate.sh')
+  );
+  for (const f of gateFiles) {
+    fs.copyFileSync(path.join(SRC, f), path.join(DST, f));
+  }
+  if (gateFiles.length > 0) {
+    console.error(`[sync] hooks/ gate scripts: ${gateFiles.join(', ')}`);
+    copied += gateFiles.length;
+  }
+
+  console.error(`[sync] hooks/ (${copied} entries)`);
+  return copied;
+}
+
 function syncModules(moduleName) {
   const src = path.join(REPO_ROOT, 'src', moduleName);
   const dest = path.join(PKG_ROOT, moduleName);
@@ -406,11 +452,12 @@ function main() {
   const plugins = syncPlugins();
   const scripts = syncScripts();
   const adapters = syncAdapters();
-const principles = syncModules('principles');
-const mutation = syncModules('mutation');
-const mockPolicy = syncModules('mock-policy');
-const buildIntegrity = syncModules('build-integrity');
-console.error(`[sync] done: ${skills} skill(s), ${plugins} plugin(s), ${scripts} script(s), ${adapters} adapter entries, ${principles + mutation + mockPolicy + buildIntegrity} module(s)`);
+  const hooks = syncHooks();
+  const principles = syncModules('principles');
+  const mutation = syncModules('mutation');
+  const mockPolicy = syncModules('mock-policy');
+  const buildIntegrity = syncModules('build-integrity');
+  console.error(`[sync] done: ${skills} skill(s), ${plugins} plugin(s), ${scripts} script(s), ${adapters} adapter entries, ${hooks} hook entries, ${principles + mutation + mockPolicy + buildIntegrity} module(s)`);
   if (skills !== CORE_SKILLS.length) {
     console.error(`[sync] ERROR: expected ${CORE_SKILLS.length} skills, copied ${skills}`);
     process.exit(1);

package/skills/batch-grill-me/SKILL.md

@@ -0,0 +1,15 @@
+---
+name: batch-grill-me
+description: A relentless interview that asks every frontier question at once, round by round.
+disable-model-invocation: true
+---
+
+Interview the user relentlessly until you reach a shared understanding. Map this as a **design tree**: every decision branches into the decisions that hang off it.
+
+Work the tree in **rounds**. The **frontier** is every decision whose prerequisites are already settled — the questions you can ask *now* without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.
+
+Each round the user answers reshapes the tree — settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a *later* round, not this one.
+
+Finding *facts* is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it — don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report — ask the rest of the frontier now. The *decisions* are the user's — put each to them and wait.
+
+The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.

package/skills/delphi-review/AGENTS.md

@@ -1,9 +1,9 @@
 # SKILLS/DELPHI-REVIEW KNOWLEDGE BASE
 
-**Generated:** 2026-07-23
-**Commit:** 766602e
+**Generated:** 2026-07-25
+**Commit:** 3150b22
 **Branch:** main
-**Version:** 0.15.5.0
+**Version:** 0.18.0.0
 
 ## OVERVIEW
 Delphi Consensus Review — multi-round anonymous expert review (≥90% threshold, 3 experts from ≥2 providers, domestic models only). Supports design + code-walkthrough modes.

package/skills/delphi-review/SKILL.md

@@ -3,8 +3,9 @@ name: delphi-review
 version: 1.1.0
 description: >
   Performs multi-round anonymous expert consensus review using the Delphi method. Supports
-  design review (default) and code-walkthrough (--mode code-walkthrough) modes. Uses 2-3 experts
-  from at least 2 different domestic model providers with a >=90% statistical consensus threshold.
+  design review (default), code-walkthrough (--mode code-walkthrough), and requirements
+  (lightweight, --mode requirements) modes. Uses 2-3 experts from at least 2 different domestic
+  model providers with a >=90% statistical consensus threshold.
   Outputs structured verdict (APPROVED/PASS_WITH_CAVEATS/REQUEST_CHANGES/BLOCKED).
 
   WHAT: Anonymous multi-expert review with iterative consensus building for designs, plans,
@@ -20,12 +21,13 @@ description: >
   "多专家评审", "consensus review", "code walkthrough", "push review", "architecture review",
   "delphi review", "run delphi", "start delphi", "评审这个架构", "review this architecture",
   "评审PR", "review this PR with delphi", "delphi评审", "delphi 评审", "run delphi review",
-  "执行delphi", "启动delphi评审".
+  "执行delphi", "启动delphi评审", "review the requirements", "评审需求", "requirements review",
+  "/requirements-review".
   NEGATIVE TRIGGERS: "how does delphi work", "what is delphi review", "code review checklist",
   "review my code quickly", "can you review this", "peer review", "I need a review",
   "explain the review process", "review guidelines", "how to review a design",
   "code review template", "review format", "PR review", "帮我review一下",
-  "just review this", "quick review", "review steps".
+  "just review this", "quick review", "review steps", "review my requirements document".
 maturity: beta
 auto_continue: true
 triggers:
@@ -51,6 +53,10 @@ triggers:
   - "run delphi review"
   - "执行delphi"
   - "启动delphi评审"
+  - "review the requirements"
+  - "评审需求"
+  - "requirements review"
+  - "/requirements-review"
 triggers_negative_examples:
   - "how does delphi work"       # educational question about the process
   - "what is delphi review"      # asking for explanation, not execution
@@ -72,6 +78,7 @@ triggers_negative_examples:
   - "review format"              # asking about format, not executing
   - "show me how to review"      # educational request about reviewing
   - "review checklist example"   # asking for examples, not running review
+  - "review my requirements document"  # educational discussion about requirements, not executing review
 triggers_negative_test_cases:
   - input: "how does delphi work"
     expect: "NOT triggered"
@@ -129,6 +136,16 @@ triggers_negative_test_cases:
     expect: "NOT triggered"
   - input: "run delphi"
     expect: "triggered"
+  - input: "review the requirements"
+    expect: "triggered"
+  - input: "评审需求"
+    expect: "triggered"
+  - input: "requirements review"
+    expect: "triggered"
+  - input: "/requirements-review"
+    expect: "triggered"
+  - input: "review my requirements document"
+    expect: "NOT triggered"
 workflow_steps:
   - "Step 0: Input Validation → Output: [DelphiReview] or [DelphiReview:BLOCKED]"
   - "Round 1: Anonymous Independent Review → Output: [DelphiReview Round 1] expert JSON verdicts"
@@ -203,6 +220,10 @@ tools_denied:
 - run delphi review
 - 执行delphi
 - 启动delphi评审
+- review the requirements
+- 评审需求
+- requirements review
+- /requirements-review
 
 **NOT triggered by:**
 - "how does delphi work" (educational)
@@ -222,6 +243,7 @@ tools_denied:
 - "code review template" (asking for template)
 - "review format" (asking about format)
 - "show me how to review" (educational)
+- "review my requirements document" (educational discussion, not execution)
 
 ## Workflow
 
@@ -280,9 +302,12 @@ Each round MUST output a structured round marker:
 |------|------|------|------|
 | `design`（默认） | `/delphi-review` | 需求/设计/架构/PR 评审 | 共识报告 + specification.yaml |
 | `code-walkthrough` | `--mode code-walkthrough` | git push 前代码走查 | `.code-walkthrough-result.json` |
+| `requirements` | `--mode requirements` | Phase 2 THINK 阶段需求评审 | `.sprint-state/phase-outputs/requirements-reviewed.json` |
 
 **Code Walkthrough 模式**的完整规范 → 详见 `references/code-walkthrough.md`
 
+**Requirements 模式**的完整规范 → 详见 `references/requirements.md`
+
 ---
 
 ## 参数配置
@@ -419,6 +444,28 @@ Phase 0: 准备 → Round 1: 匿名独立评审 → 共识检查
 
 **For code-walkthrough mode**, output follows `.code-walkthrough-result.json` schema (see `references/code-walkthrough.md`).
 
+**For requirements mode**, output follows `requirements-reviewed.json` schema (see `references/requirements.md`):
+
+```json
+{
+  "mode": "requirements",
+  "verdict": "APPROVED|GAPS_FOUND",
+  "timestamp": "2026-07-25T10:30:00Z",
+  "requirements_hash": "<SHA-256 hex digest>",
+  "head_commit": "<git rev-parse HEAD>",
+  "context_file_used": "CONTEXT.md",
+  "round": 1,
+  "expert_verdicts": [
+    { "role": "architecture", "verdict": "APPROVED", "confidence": 9 },
+    { "role": "feasibility", "verdict": "APPROVED", "confidence": 8 }
+  ],
+  "requirements_statement": "<short summary of what was reviewed>",
+  "gaps_found": [],
+  "rounds_used": 1,
+  "escalation_needed": false
+}
+```
+
 **Anti-patterns mapping:**
 - `Round 1 → "评审完成"` → MUST NOT have `verdict: APPROVED` if `critical_issues` exist
 - `只处理 Critical，忽略 Major` → MUST include `major_concerns` array
@@ -452,6 +499,11 @@ Phase 0: 准备 → Round 1: 匿名独立评审 → 共识检查
 {"mode":"code-walkthrough","commit":"abc123...","timestamp":"...","verdict":"APPROVED","consensus_ratio":1.0}
 ```
 
+**Requirements mode APPROVED** → `.sprint-state/delphi-reviewed.json`:
+```json
+{"mode":"requirements","timestamp":"...","verdict":"APPROVED","consensus_ratio":1.0}
+```
+
 ---
 
 ## Anti-Patterns
@@ -468,6 +520,8 @@ Phase 0: 准备 → Round 1: 匿名独立评审 → 共识检查
 
 **Code-walkthrough 专属 Anti-Patterns** → 详见 `references/code-walkthrough.md`
 
+**Requirements 专属 Anti-Patterns** → 详见 `references/requirements.md`
+
 ---
 
 ## Red Flags
@@ -499,5 +553,6 @@ Phase 0: 准备 → Round 1: 匿名独立评审 → 共识检查
 | File | Content |
 |------|---------|
 | `@references/code-walkthrough.md` | Code-walkthrough mode specification |
+| `@references/requirements.md` | Requirements mode specification |
 | `@references/orchestrator-dispatch.md` | Orchestrator auto-dispatch rules (#218 subagent multi-round loop) |
 | `@references/round-templates.md` | Round templates (anonymous/exchange/final/fix report formats) |