@rune-kit/rune 2.13.0 → 2.15.0

package/README.md

@@ -5,7 +5,7 @@
 <p align="center">
   <strong>Less skills. Deeper connections.</strong><br>
   A lean, interconnected skill ecosystem for AI coding assistants.<br>
-  62 skills · 215+ mesh connections · 8 platforms · MIT
+  63 skills · 215+ mesh connections · 8 platforms · MIT
 </p>
 
 <p align="center">
@@ -23,7 +23,7 @@
 
 Most skill ecosystems are either **too many isolated skills** (540+ that don't talk to each other) or **rigid pipelines** (A → B → C, if B fails everything stops).
 
-Rune is a **mesh** — 62 skills with 215+ connections across a 5-layer architecture. Skills call each other bidirectionally, forming resilient workflows that adapt when things go wrong.
+Rune is a **mesh** — 63 skills with 215+ connections across a 5-layer architecture. Skills call each other bidirectionally, forming resilient workflows that adapt when things go wrong.
 
 ```
 Pipeline:  A → B → C → D         (B fails = stuck)
@@ -83,13 +83,32 @@ _Methodology: Claude Code CLI headless mode (`claude -p --output-format json`),
 
 ---
 
-## What's New (v2.13.0 — Script Contract + Media Pack)
+## What's New (v2.15.0 — Second Opinion + Cross-Provider + Routing Clarity)
 
-- **`@rune-pro/media` pack v1.0.0** — new Pro pack: raster image generation across 5 providers (Codex CLI, DALL-E, Replicate, Stability AI, local SD), prompt engineering with 4-gate safety check (trademark, public-figure, prompt-injection, uncanny-precondition), batch asset pipeline with multi-resolution variants + WebP/AVIF conversion + EXIF strip. Fills the raster gap left by `asset-creator` (SVG/HTML only) and `video-creator` (planning only).
-- **`sentinel-env` v0.3.0** — 9-tier binary detection for hard-dependency checks. Catches desktop-app bundles (macOS `.app`), npm-global on Windows (PATH oversight), platform release archives. Eliminates the "binary installed but not detected" failure class.
-- **`skill-forge` v1.8.0** — new Phase 5.25 "Script Contract" — helper scripts must follow stdout=paths / stderr=diagnostics / `--json` opt-in / `--debug` opt-in pattern, implement semantic exit codes (including `4` timeout-partial vs `124` timeout-zero), honor OpenClaw artifact-directory fallback chain. HARD-GATE on pre-ship verification.
-- **OpenClaw adapter** — `generateManifest` now declares `artifactConvention` (output-dir fallback order, output contract, exit-code vocabulary). Formalizes the de-facto in-the-wild convention from [codex-imagen](https://github.com/darkamenosa/codex-imagen).
-- **Skill-count scaling** — OpenClaw manifest description now scales with actual skill count rather than hardcoded.
+- **`adversary` v0.2.0 — Mode: oracle** — when `agent.stuck` fires from `debug` (3 disproved hypotheses) or `fix` (2+ failed attempts), oracle-mode dispatches a stateless second-model pass with explicit "no prior context" framing. Bundle format is regex-validated (`[SYSTEM]` invariant role-priming + `[USER]` template + `### File N`), token-capped (100k bundle, 4k per file, 12 files max), citation-required reply contract. Secrets auto-redacted. Breaks the confirmation-bias loop that scout's zoom-out (structural pivot) cannot.
+- **`session-bridge` v0.8.0 — Detach Mode** — async escalation primitive. Heavy-model second-opinion calls (1-10 min wall time) no longer block the primary agent. `.rune/oracle-pending/<sessionId>.json` is the rendezvous file; idempotent dispatch (bundleHash-keyed); 10min default timeout; 24h orphan cleanup on session start. `cook` Phase 4 and `team` Phase 3 reattach via filesystem poll between adjacent tasks.
+- **`context-engine` v1.1.0 — Mode: preview** — pre-flight cost gate. Caller emits `context.preview` BEFORE bundle build with file list + estimated tokens (chars × 0.25). Per-caller thresholds: adversary 50k/100k, team 30k/80k (per worker), review 40k/100k, audit 60k/120k. Action enum `proceed | warn | block`. Override via `RUNE_CONTEXT_THRESHOLDS_<CALLER>`. Stops `team` parallel workstreams from silently blowing $20 of Opus tokens.
+- **Cross-provider model mapping** — 5 non-Anthropic adapters now translate `model: opus|sonnet|haiku` to provider-correct names. **codex** → gpt-5-pro / gpt-5 / gpt-5-mini. **antigravity** → gemini-3-pro / gemini-3-flash / gemini-3-flash-lite. **opencode / openclaw / generic** → tier:heavy / tier:mid / tier:light (provider-agnostic). claude / cursor / windsurf remain no-op (Anthropic backend understands native names).
+- **Routing clarity sweep** — all 63 SKILL.md descriptions now double-quoted (YAML safety). 13 ambiguous-name skills got explicit "Use when…" routing hints so skill-router doesn't have to guess: ba, completion-gate, constraint-check, doc-processor, integrity-check, logic-guardian, onboard, preflight, sentinel-env, watchdog, worktree, hallucination-guard, mcp-builder.
+- **4 new mesh signals** — `oracle.dispatched`, `oracle.response`, `oracle.failed`, `context.preview`. All registered in Signal Catalog with full emit/listen mapping. `agent.stuck` listeners updated to include adversary in addition to scout.
+- **1,331 tests** — +71 from v2.14.0 across 5 new test files: adapter-model-mapping (18), oracle-bundle-format (19), oracle-pending-schema (16), context-preview-signal (13), skill-description-quality (5).
+
+### Previous (v2.14.0 — Deep Modules)
+
+- **`improve-architecture` skill (NEW L2, opus)** — controlled vocabulary (Module / Interface / Implementation / Depth / Seam / Adapter / Leverage / Locality), numeric depth-leverage-locality scoring (1–5 each), 4 dependency categories, structured proposal payloads.
+- **TDD vertical-slicing HARD-GATE** — `test` v1.3.0 catches "horizontal slicing" (5 tests before any GREEN), commit-pair audit trail, shape-test smell detector.
+- **`.out-of-scope/` knowledge base** — `ba` v0.11.0 reads, `review-intake` v1.2.0 writes. Stops re-litigation of rejected features.
+- **CONTEXT.md inline-sharpen + ADR 3-criteria gate** — `journal` v0.4.0 only opens an ADR when sum ≥ 11 + each axis ≥ 3.
+- **Agent Brief durability** — `context-pack` v0.2.0 regex smell tests block stale paths/line numbers.
+- **Design-It-Twice mode** — `brainstorm` v0.6.0 with constraint-pinned parallel subagents + diversity score gate.
+- **Zoom-out + explore-first micro-utilities** — `scout` v0.4.0 listens for `agent.stuck`; `ba` Step 2.0 HARD-GATE requires tool-call evidence.
+
+### Previous (v2.13.0 — Script Contract + Media Pack)
+
+- **`@rune-pro/media` pack v1.0.0** — new Pro pack: raster image generation across 5 providers (Codex CLI, DALL-E, Replicate, Stability AI, local SD), prompt engineering with 4-gate safety check (trademark, public-figure, prompt-injection, uncanny-precondition), batch asset pipeline with multi-resolution variants + WebP/AVIF conversion + EXIF strip.
+- **`sentinel-env` v0.3.0** — 9-tier binary detection for hard-dependency checks.
+- **`skill-forge` v1.8.0** — new Phase 5.25 "Script Contract" — helper scripts must follow stdout=paths / stderr=diagnostics / `--json` opt-in / semantic exit codes. HARD-GATE on pre-ship verification.
+- **OpenClaw adapter** — `generateManifest` now declares `artifactConvention`.
 
 ### Previous (v2.12.0 — Auto-Discipline)
 
@@ -158,7 +177,7 @@ cook ───emit:phase.complete────→ session-bridge
 
 ## What Rune Is (and Isn't)
 
-Rune started as a **Claude Code plugin** and now compiles to **every major AI IDE**. Same 62 skills, same mesh connections, same workflows — zero knowledge loss across platforms.
+Rune started as a **Claude Code plugin** and now compiles to **every major AI IDE**. Same 63 skills, same mesh connections, same workflows — zero knowledge loss across platforms.
 
 | | Rune Provides | Claude Code Provides |
 |---|---|---|
@@ -210,7 +229,7 @@ npx @rune-kit/rune init --platform windsurf
 npx @rune-kit/rune init --platform antigravity
 ```
 
-This compiles all 62 skills into your IDE's rules format. Same knowledge, same workflows.
+This compiles all 63 skills into your IDE's rules format. Same knowledge, same workflows.
 
 ### Platform Comparison
 
@@ -561,7 +580,7 @@ See [docs/MULTI-PLATFORM.md](docs/MULTI-PLATFORM.md) for the full architecture.
 | Doc | What's inside |
 |-----|---------------|
 | [`docs/GETTING_STARTED.md`](docs/GETTING_STARTED.md) | Your first 5 minutes with Rune — install to first `/rune cook` |
-| [`docs/SKILLS.md`](docs/SKILLS.md) | All 62 skills, searchable by intent and layer |
+| [`docs/SKILLS.md`](docs/SKILLS.md) | All 63 skills, searchable by intent and layer |
 | [`docs/SIGNALS.md`](docs/SIGNALS.md) | Canonical signal inventory — 25 events, emit/listen graph |
 | [`docs/ARCHITECTURE.md`](docs/ARCHITECTURE.md) | 5-layer mesh architecture reference |
 | [`docs/VISION.md`](docs/VISION.md) | Philosophy — what Rune is and isn't |
@@ -577,7 +596,7 @@ See [docs/MULTI-PLATFORM.md](docs/MULTI-PLATFORM.md) for the full architecture.
 Core Skills:       62 (L0: 1 │ L1: 5 │ L2: 29 │ L3: 27)
 Extension Packs:   14 free + 5 pro + 4 business
 Mesh Connections:  215+ cross-references
-Mesh Signals:      25 signals across 62 skills (emit/listen graph)
+Mesh Signals:      25 signals across 63 skills (emit/listen graph)
 Connections/Skill: 3.4 avg
 Platforms:         8 (Claude Code, Cursor, Windsurf, Antigravity, Codex, OpenCode, OpenClaw, Generic)
 Compiler:          ~1400 LOC (parser + 8 transforms + 8 adapters + CLI)

package/compiler/__tests__/adapter-model-mapping.test.js

@@ -0,0 +1,152 @@
+/**
+ * Adapter model tier mapping (v2.15+) — verify non-Anthropic adapters
+ * translate `model: opus|sonnet|haiku` to provider-correct names while
+ * Anthropic-backed adapters (claude/cursor/windsurf) remain no-op.
+ *
+ * Validates:
+ *   - codex/antigravity emit concrete provider model names
+ *   - opencode/openclaw/generic emit semantic tier hints (provider-agnostic)
+ *   - claude/cursor/windsurf do NOT translate (no-op)
+ *   - Skills without `model:` produce no model line
+ *   - Unknown tier values pass through unchanged
+ */
+
+import assert from 'node:assert';
+import { describe, test } from 'node:test';
+import { getAdapter } from '../adapters/index.js';
+
+const baseSkill = {
+  name: 'cook',
+  description: 'Feature implementation orchestrator',
+  layer: 'L1',
+  group: 'orchestration',
+};
+
+describe('codex adapter model mapping', () => {
+  const codex = getAdapter('codex');
+
+  test('opus translates to gpt-5-pro', () => {
+    const header = codex.generateHeader({ ...baseSkill, model: 'opus' });
+    assert.match(header, /model: gpt-5-pro/);
+  });
+
+  test('sonnet translates to gpt-5', () => {
+    const header = codex.generateHeader({ ...baseSkill, model: 'sonnet' });
+    assert.match(header, /model: gpt-5(?!-)/);
+  });
+
+  test('haiku translates to gpt-5-mini', () => {
+    const header = codex.generateHeader({ ...baseSkill, model: 'haiku' });
+    assert.match(header, /model: gpt-5-mini/);
+  });
+
+  test('omitted model produces no model line', () => {
+    const header = codex.generateHeader({ ...baseSkill });
+    assert.doesNotMatch(header, /model:/);
+  });
+
+  test('unknown tier passes through unchanged', () => {
+    const header = codex.generateHeader({ ...baseSkill, model: 'custom-fine-tune' });
+    assert.match(header, /model: custom-fine-tune/);
+  });
+});
+
+describe('antigravity adapter model mapping', () => {
+  const antigravity = getAdapter('antigravity');
+
+  test('opus translates to gemini-3-pro', () => {
+    const header = antigravity.generateHeader({ ...baseSkill, model: 'opus' });
+    assert.match(header, /model: gemini-3-pro/);
+  });
+
+  test('sonnet translates to gemini-3-flash', () => {
+    const header = antigravity.generateHeader({ ...baseSkill, model: 'sonnet' });
+    assert.match(header, /model: gemini-3-flash(?!-)/);
+  });
+
+  test('haiku translates to gemini-3-flash-lite', () => {
+    const header = antigravity.generateHeader({ ...baseSkill, model: 'haiku' });
+    assert.match(header, /model: gemini-3-flash-lite/);
+  });
+});
+
+describe('opencode adapter model mapping (provider-agnostic)', () => {
+  const opencode = getAdapter('opencode');
+
+  test('opus translates to tier:heavy', () => {
+    const header = opencode.generateHeader({ ...baseSkill, model: 'opus' });
+    assert.match(header, /model: tier:heavy/);
+  });
+
+  test('sonnet translates to tier:mid', () => {
+    const header = opencode.generateHeader({ ...baseSkill, model: 'sonnet' });
+    assert.match(header, /model: tier:mid/);
+  });
+
+  test('haiku translates to tier:light', () => {
+    const header = opencode.generateHeader({ ...baseSkill, model: 'haiku' });
+    assert.match(header, /model: tier:light/);
+  });
+});
+
+describe('openclaw adapter model mapping (markdown header)', () => {
+  const openclaw = getAdapter('openclaw');
+
+  test('opus appears as tier:heavy in metadata line', () => {
+    const header = openclaw.generateHeader({ ...baseSkill, model: 'opus' });
+    assert.match(header, /model: tier:heavy/);
+  });
+
+  test('omitted model produces no model line', () => {
+    const header = openclaw.generateHeader({ ...baseSkill });
+    assert.doesNotMatch(header, /model:/);
+  });
+});
+
+describe('generic adapter model mapping (markdown header)', () => {
+  const generic = getAdapter('generic');
+
+  test('opus appears as tier:heavy in metadata line', () => {
+    const header = generic.generateHeader({ ...baseSkill, model: 'opus' });
+    assert.match(header, /model: tier:heavy/);
+  });
+});
+
+describe('Anthropic-native adapters are no-op for model field', () => {
+  test('claude generateHeader returns empty (passthrough)', () => {
+    const claude = getAdapter('claude');
+    const header = claude.generateHeader({ ...baseSkill, model: 'opus' });
+    assert.strictEqual(header, '');
+  });
+
+  test('cursor + windsurf do NOT rewrite anthropic tier names', () => {
+    const cursor = getAdapter('cursor');
+    const windsurf = getAdapter('windsurf');
+    const cursorHeader = cursor.generateHeader({ ...baseSkill, model: 'opus' });
+    const windsurfHeader = windsurf.generateHeader({ ...baseSkill, model: 'opus' });
+    assert.doesNotMatch(cursorHeader, /gpt-5/);
+    assert.doesNotMatch(cursorHeader, /gemini/);
+    assert.doesNotMatch(windsurfHeader, /gpt-5/);
+    assert.doesNotMatch(windsurfHeader, /gemini/);
+  });
+});
+
+describe('cross-adapter consistency', () => {
+  test('all 5 non-Anthropic adapters emit a model line for opus skills', () => {
+    const adapterNames = ['codex', 'antigravity', 'opencode', 'openclaw', 'generic'];
+    for (const name of adapterNames) {
+      const adapter = getAdapter(name);
+      const header = adapter.generateHeader({ ...baseSkill, model: 'opus' });
+      assert.match(header, /model: /, `${name} should emit a model line for opus skill`);
+    }
+  });
+
+  test('all 5 non-Anthropic adapters omit model line when skill has no model', () => {
+    const adapterNames = ['codex', 'antigravity', 'opencode', 'openclaw', 'generic'];
+    for (const name of adapterNames) {
+      const adapter = getAdapter(name);
+      const header = adapter.generateHeader({ ...baseSkill });
+      assert.doesNotMatch(header, /model:/, `${name} should NOT emit a model line for skill without model`);
+    }
+  });
+});

package/compiler/__tests__/adr-scoring.test.js

@@ -0,0 +1,91 @@
+/**
+ * ADR scoring gate — verify the 3-criteria threshold logic.
+ *
+ * The gate: open_adr = (sum >= 11) AND (each axis >= 3)
+ *   - Prevents single-axis cheating
+ *   - Counter-test (rejected alternative) is enforced at write time, not numerically
+ *
+ * Also validates ADR filename pattern includes the score.
+ */
+
+import assert from 'node:assert';
+import { describe, test } from 'node:test';
+
+function shouldOpenAdr({ reversibility, surprisingness, tradeoff_strength }) {
+  const sum = reversibility + surprisingness + tradeoff_strength;
+  const minAxis = Math.min(reversibility, surprisingness, tradeoff_strength);
+  return sum >= 11 && minAxis >= 3;
+}
+
+const ADR_FILENAME_PATTERN = /^ADR-\d{3}-[a-z][a-z0-9]*(-[a-z0-9]+)*-s(\d{1,2})\.md$/;
+
+describe('ADR scoring gate', () => {
+  test('opens ADR when sum >= 11 and all axes >= 3', () => {
+    assert.strictEqual(shouldOpenAdr({ reversibility: 4, surprisingness: 4, tradeoff_strength: 3 }), true);
+    assert.strictEqual(shouldOpenAdr({ reversibility: 5, surprisingness: 5, tradeoff_strength: 5 }), true);
+    assert.strictEqual(shouldOpenAdr({ reversibility: 4, surprisingness: 3, tradeoff_strength: 4 }), true);
+  });
+
+  test('blocks when sum < 11', () => {
+    assert.strictEqual(
+      shouldOpenAdr({ reversibility: 3, surprisingness: 3, tradeoff_strength: 3 }),
+      false,
+      'sum=9 should block',
+    );
+    assert.strictEqual(
+      shouldOpenAdr({ reversibility: 4, surprisingness: 4, tradeoff_strength: 2 }),
+      false,
+      'sum=10 should block (also violates min-axis rule)',
+    );
+  });
+
+  test('blocks single-axis cheating: 5+5+1 = 11 sum but axis=1 fails min-axis rule', () => {
+    assert.strictEqual(shouldOpenAdr({ reversibility: 5, surprisingness: 5, tradeoff_strength: 1 }), false);
+    assert.strictEqual(shouldOpenAdr({ reversibility: 5, surprisingness: 1, tradeoff_strength: 5 }), false);
+    assert.strictEqual(shouldOpenAdr({ reversibility: 1, surprisingness: 5, tradeoff_strength: 5 }), false);
+  });
+
+  test('boundary: sum=11 with all axes = 3 — Wait, 3+3+3 = 9, not 11. Min sum with each axis >=3 is 9. So sum=11 implies at least one axis is 4', () => {
+    // 3+3+5 = 11, all axes >= 3, should open
+    assert.strictEqual(shouldOpenAdr({ reversibility: 3, surprisingness: 3, tradeoff_strength: 5 }), true);
+  });
+
+  test('borderline cases (sum 8-10) all block — these go to conventions, not ADRs', () => {
+    for (let r = 1; r <= 5; r++) {
+      for (let s = 1; s <= 5; s++) {
+        for (let t = 1; t <= 5; t++) {
+          const sum = r + s + t;
+          const result = shouldOpenAdr({ reversibility: r, surprisingness: s, tradeoff_strength: t });
+          if (sum >= 8 && sum <= 10) {
+            assert.strictEqual(result, false, `sum=${sum} (${r}/${s}/${t}) should block`);
+          }
+        }
+      }
+    }
+  });
+});
+
+describe('ADR filename pattern', () => {
+  test('valid filenames with score', () => {
+    assert.ok(ADR_FILENAME_PATTERN.test('ADR-007-postgres-write-model-s13.md'));
+    assert.ok(ADR_FILENAME_PATTERN.test('ADR-001-monorepo-s12.md'));
+    assert.ok(ADR_FILENAME_PATTERN.test('ADR-042-event-sourced-orders-s14.md'));
+  });
+
+  test('rejects filename without score suffix', () => {
+    assert.ok(!ADR_FILENAME_PATTERN.test('ADR-007-postgres-write-model.md'));
+  });
+
+  test('rejects non-sequential ADR id format', () => {
+    assert.ok(!ADR_FILENAME_PATTERN.test('ADR-7-postgres-s11.md'));
+  });
+
+  test('rejects PascalCase slug', () => {
+    assert.ok(!ADR_FILENAME_PATTERN.test('ADR-007-PostgresWriteModel-s13.md'));
+  });
+
+  test('extracts score from filename', () => {
+    const m = 'ADR-007-postgres-write-model-s13.md'.match(ADR_FILENAME_PATTERN);
+    assert.strictEqual(parseInt(m[2], 10), 13);
+  });
+});

package/compiler/__tests__/context-md-format.test.js

@@ -0,0 +1,180 @@
+/**
+ * CONTEXT.md format — validates the project glossary structure.
+ *
+ * Lazy creation rule: empty/absent CONTEXT.md is OK; the validator only runs on existing files.
+ *
+ * Required sections: # Project Glossary heading, ## Language table, ## Relationships
+ * Optional sections: ## Example dialogue, ## Flagged ambiguities
+ */
+
+import assert from 'node:assert';
+import { describe, test } from 'node:test';
+
+function validateContextMd(content) {
+  const issues = [];
+
+  if (!/^# .+/m.test(content.split('\n')[0] || '')) {
+    issues.push('first line must be H1 (# Title)');
+  }
+
+  if (!/## Language/.test(content)) {
+    issues.push('missing ## Language section');
+  }
+
+  if (!/## Relationships/.test(content)) {
+    issues.push('missing ## Relationships section');
+  }
+
+  // Validate Language table shape if present
+  const langMatch = content.match(/## Language\s*\n([\s\S]*?)(?=\n## |\n# |$)/);
+  if (langMatch) {
+    const tableLines = langMatch[1].split('\n').filter((l) => l.trim().startsWith('|'));
+    if (tableLines.length < 3) {
+      issues.push('## Language section must contain a Markdown table with header + separator + >=1 row');
+    } else {
+      // Header should mention Term, Definition, Aliases, Status
+      const header = tableLines[0].toLowerCase();
+      const requiredColumns = [
+        { lower: 'term', label: 'Term' },
+        { lower: 'definition', label: 'Definition' },
+        { lower: 'aliases', label: 'Aliases' },
+        { lower: 'status', label: 'Status' },
+      ];
+      for (const col of requiredColumns) {
+        if (!header.includes(col.lower)) {
+          issues.push(`Language table header missing column: ${col.label}`);
+        }
+      }
+      // Each row should have a status field with valid value
+      const validStatuses = ['canonical', 'pending', 'conflicted'];
+      for (let i = 2; i < tableLines.length; i++) {
+        const row = tableLines[i];
+        const cells = row
+          .split('|')
+          .map((c) => c.trim())
+          .filter(Boolean);
+        if (cells.length >= 4) {
+          const status = cells[3].toLowerCase();
+          if (!validStatuses.includes(status)) {
+            issues.push(`row "${cells[0]}" has invalid status "${status}"`);
+          }
+        }
+      }
+    }
+  }
+
+  return issues;
+}
+
+describe('CONTEXT.md format', () => {
+  test('valid context passes', () => {
+    const content = `# Project Glossary
+
+## Language
+
+| Term | Definition | Aliases to avoid | Status |
+|------|------------|-------------------|--------|
+| **Order** | A customer's request to purchase items | Purchase, transaction | canonical |
+| **Invoice** | A request for payment | Bill | canonical |
+
+## Relationships
+
+- An **Order** produces one or more **Invoices**
+
+## Flagged ambiguities
+
+- "account" was used for both Customer and User — resolved.
+`;
+    assert.deepStrictEqual(validateContextMd(content), []);
+  });
+
+  test('rejects content without H1', () => {
+    const content = `## Language
+| Term | Definition | Aliases | Status |
+|------|------------|---------|--------|
+| **X** | y | z | canonical |
+## Relationships
+- A
+`;
+    const issues = validateContextMd(content);
+    assert.ok(
+      issues.some((i) => i.includes('H1')),
+      'should require H1',
+    );
+  });
+
+  test('rejects missing Language section', () => {
+    const content = `# Project Glossary
+## Relationships
+- A
+`;
+    const issues = validateContextMd(content);
+    assert.ok(
+      issues.some((i) => i.includes('Language')),
+      'should require Language section',
+    );
+  });
+
+  test('rejects missing Relationships section', () => {
+    const content = `# Project Glossary
+## Language
+| Term | Definition | Aliases | Status |
+|------|------------|---------|--------|
+| **X** | y | z | canonical |
+`;
+    const issues = validateContextMd(content);
+    assert.ok(
+      issues.some((i) => i.includes('Relationships')),
+      'should require Relationships section',
+    );
+  });
+
+  test('rejects invalid status value', () => {
+    const content = `# Project Glossary
+## Language
+| Term | Definition | Aliases | Status |
+|------|------------|---------|--------|
+| **Order** | y | z | provisional |
+## Relationships
+- A
+`;
+    const issues = validateContextMd(content);
+    assert.ok(
+      issues.some((i) => i.includes('invalid status')),
+      'should reject status outside canonical|pending|conflicted',
+    );
+  });
+
+  test('accepts pending and conflicted statuses', () => {
+    const content = `# Project Glossary
+## Language
+| Term | Definition | Aliases | Status |
+|------|------------|---------|--------|
+| **Order** | y | z | pending |
+| **Invoice** | y | z | conflicted |
+## Relationships
+- A
+`;
+    assert.deepStrictEqual(validateContextMd(content), []);
+  });
+
+  test('rejects table missing required columns', () => {
+    const content = `# Project Glossary
+## Language
+| Term | Definition |
+|------|------------|
+| **Order** | y |
+## Relationships
+- A
+`;
+    const issues = validateContextMd(content);
+    assert.ok(
+      issues.some((i) => i.includes('Aliases')),
+      'should require Aliases column',
+    );
+    assert.ok(
+      issues.some((i) => i.includes('Status')),
+      'should require Status column',
+    );
+  });
+});