rungate 0.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude/agents/aditi.md +47 -0
- package/.claude/agents/marcus.md +50 -0
- package/.claude/agents/quinn.md +58 -0
- package/.claude/agents/rook.md +47 -0
- package/.claude/agents/serena.md +46 -0
- package/.claude/rungate.json +11 -0
- package/.fallowrc.json +28 -0
- package/.github/copilot-instructions.md +20 -0
- package/.rungate/conformity-findings.json +648 -0
- package/AGENTS.md +106 -0
- package/CODE-MAP.md +50 -0
- package/HARNESS.md +88 -0
- package/bun.lock +26 -0
- package/bunfig.toml +2 -0
- package/config/brief-policies.json +28 -0
- package/config/ceremony-profiles.json +212 -0
- package/config/consumer-cascade-map.json +24 -0
- package/config/doc-cascade-map.json +24 -0
- package/config/eval.json +84 -0
- package/config/profiles/account-plan.yaml +36 -0
- package/config/profiles/campaign.yaml +94 -0
- package/config/prove-evidence.schema.json +65 -0
- package/config/spec-policies.json +36 -0
- package/config/workflow-schema.json +281 -0
- package/gates/SCHEMA-GUIDE.md +121 -0
- package/gates/ac-quality.test.ts +106 -0
- package/gates/adversarial.test.ts +274 -0
- package/gates/brief-assembler.test.ts +429 -0
- package/gates/brief-assembler.ts +334 -0
- package/gates/bunfig.toml +2 -0
- package/gates/chain.test.ts +91 -0
- package/gates/e2e-smoke.test.ts +234 -0
- package/gates/error-classifier.test.ts +249 -0
- package/gates/error-classifier.ts +89 -0
- package/gates/orchestrator.test.ts +950 -0
- package/gates/orchestrator.ts +569 -0
- package/gates/preload.ts +77 -0
- package/gates/prompts/ac-adversary.md +20 -0
- package/gates/prompts/evidence-validator.md +22 -0
- package/gates/prompts/prove-reproducer.md +53 -0
- package/gates/prove.test.ts +164 -0
- package/gates/run-gate.ts +936 -0
- package/gates/schema-parity.test.ts +197 -0
- package/gates/schema.ts +362 -0
- package/gates/self-heal.test.ts +511 -0
- package/gates/self-heal.ts +121 -0
- package/gates/ship-orchestrator.test.ts +379 -0
- package/gates/ship-orchestrator.ts +363 -0
- package/gates/test-fixtures/broken-no-environments.json +60 -0
- package/gates/test-fixtures/valid-standard.json +54 -0
- package/gates/test-utils.ts +43 -0
- package/gates/witness.ts +220 -0
- package/gates/workflow.test.ts +1053 -0
- package/hooks/AgentBriefGuard.hook.ts +586 -0
- package/hooks/AgentVerdictCapture.hook.ts +134 -0
- package/hooks/AutoVerifyGate.hook.ts +76 -0
- package/hooks/GateEnforcement.hook.ts +273 -0
- package/hooks/IssueCloseGuard.hook.ts +116 -0
- package/hooks/MergeGuard.hook.ts +55 -0
- package/hooks/StaleTTLCleanup.hook.ts +133 -0
- package/hooks/VerifyPhaseLock.hook.ts +81 -0
- package/hooks/WorkflowStateGuard.hook.ts +37 -0
- package/hooks/lib/agentDetection.ts +70 -0
- package/hooks/lib/findWorkflow.ts +101 -0
- package/hooks/lib/parseStdin.ts +37 -0
- package/hooks/lib/paths.ts +111 -0
- package/hooks/lib/utils.ts +81 -0
- package/lib/conformity.ts +959 -0
- package/lib/paths.ts +23 -0
- package/lib/rungate-schema.ts +60 -0
- package/lib/signal-phrases.ts +7 -0
- package/package.json +20 -0
- package/prompts/ac-adversary.md +20 -0
- package/prompts/ac-format.md +34 -0
- package/prompts/aditi.md +29 -0
- package/prompts/blast-radius.md +29 -0
- package/prompts/coding-principles.md +34 -0
- package/prompts/container-rebuild.md +29 -0
- package/prompts/container-verify.md +28 -0
- package/prompts/discovery.md +27 -0
- package/prompts/environment.md +28 -0
- package/prompts/escalation-decision-tree.md +38 -0
- package/prompts/evidence-hierarchy.md +31 -0
- package/prompts/evidence-validator.md +22 -0
- package/prompts/marcus.md +29 -0
- package/prompts/prevention.md +26 -0
- package/prompts/prove-reproducer.md +43 -0
- package/prompts/quinn-decision-tree.md +31 -0
- package/prompts/quinn-ui-brief.md +106 -0
- package/prompts/quinn.md +29 -0
- package/prompts/rca.md +28 -0
- package/prompts/read-before-write.md +30 -0
- package/prompts/regression.md +26 -0
- package/prompts/rook.md +29 -0
- package/prompts/serena.md +28 -0
- package/prompts/testing-strategy.md +34 -0
- package/reference/migration-manifest.json +554 -0
- package/reference/prompts/agent-aditi.md +38 -0
- package/reference/prompts/agent-marcus.md +38 -0
- package/reference/prompts/agent-quinn.md +38 -0
- package/reference/prompts/agent-rook.md +37 -0
- package/reference/prompts/agent-serena.md +37 -0
- package/reference/prompts/council-skill.md +170 -0
- package/reference/prompts/goal-skill.md +235 -0
- package/reference/prompts/prove-skill.md +283 -0
- package/reference/prompts/quinn-standard.md +246 -0
- package/reference/prompts/ship-convergence.md +65 -0
- package/reference/prompts/ship-escalation.md +43 -0
- package/reference/prompts/ship-iteration.md +382 -0
- package/reference/prompts/ship-pending-patches.md +246 -0
- package/reference/prompts/ship-reference.md +250 -0
- package/reference/prompts/ship-skill.md +347 -0
- package/reference/prompts/ship-templates.md +215 -0
- package/reference/scripts/batch-status.sh +68 -0
- package/reference/scripts/chain-compat-check.sh +67 -0
- package/reference/scripts/context-audit.sh +314 -0
- package/reference/scripts/dead-export-check.sh +61 -0
- package/reference/scripts/generate-qc-tables.sh +92 -0
- package/reference/scripts/harness-init.sh +111 -0
- package/reference/scripts/pai-054-baseline-check.sh +40 -0
- package/reference/scripts/prove-smoke-test.sh +112 -0
- package/reference/scripts/setup-keychain-salt.sh +12 -0
- package/reference/scripts/skill-optimizer-friday.sh +88 -0
- package/reference/scripts/skill-qc-test.sh +351 -0
- package/reference/scripts/skill-synthesize-tonight.sh +66 -0
- package/reference/specs/HARNESS-EXTRACTION-SPEC.md +263 -0
- package/reference/specs/harness-v3-bash-deletion-plan.md +65 -0
- package/reference/specs/harness-v3-migration-plan.md +188 -0
- package/scripts/decision-reconcile.sh +74 -0
- package/scripts/decision-reconcile.ts +152 -0
- package/scripts/extract-constraints.ts +260 -0
- package/scripts/generate-code-map.ts +339 -0
- package/scripts/git-hooks/pre-commit +76 -0
- package/scripts/git-hooks/pre-push +271 -0
- package/scripts/harness-skill-check.sh +52 -0
- package/scripts/lib/gap-emit.sh +65 -0
- package/scripts/lib/jq-update.sh +30 -0
- package/scripts/lib/resolve-slug.sh +30 -0
- package/scripts/lib/verify-spec-compliance.sh +102 -0
- package/scripts/prove-backfill.sh +87 -0
- package/scripts/scaffold-project.ts +1488 -0
- package/scripts/scaffold-rungate-config.ts +91 -0
- package/scripts/self-containment-check.sh +109 -0
- package/scripts/skill-qc-validator.sh +402 -0
- package/scripts/slug-resolver.sh +14 -0
- package/scripts/sync-spec-tests.ts +236 -0
- package/specs/BOOTSTRAP-DATA-FLOW-SPEC.md +2493 -0
- package/specs/BOOTSTRAP-TEST-PLAN.md +571 -0
- package/specs/HARNESS-GATES.md +256 -0
- package/specs/HARNESS-SKILL-CHAIN.md +286 -0
- package/specs/HARNESS-SKILL-CONTRACT.md +93 -0
- package/specs/HARNESS-STANDARD.md +488 -0
- package/specs/SPEC-TEMPLATE.md +53 -0
- package/specs/bootstrap-data-flow.png +0 -0
- package/specs/harness-automation-matrix.md +314 -0
- package/specs/harness-automation-matrix.rules.json +64 -0
- package/test/anti.test.ts +80 -0
- package/test/contract-negative.test.ts +86 -0
- package/test/contract.test.ts +158 -0
- package/test/external-deps.test.ts +48 -0
- package/test/fixtures/golden-project/.env.example +3 -0
- package/test/fixtures/golden-project/Makefile +7 -0
- package/test/fixtures/golden-project/docs/adr/ADR-001-framework.md +23 -0
- package/test/fixtures/golden-project/docs/setup-guide.md +10 -0
- package/test/fixtures/golden-project/package.json +10 -0
- package/test/fixtures/golden-project/specs/api-spec.md +20 -0
- package/test/fixtures/golden-project/src/auth.ts +8 -0
- package/test/fixtures/golden-project/src/db.ts +11 -0
- package/test/fixtures/golden-project/src/index.ts +19 -0
- package/test/fixtures/golden-project/src/utils/format.ts +3 -0
- package/test/fixtures/golden-project/test/auth.test.ts +15 -0
- package/test/fixtures/golden-project/tsconfig.json +12 -0
- package/test/meta-sc-coverage.test.ts +159 -0
- package/test/phase-0.test.ts +846 -0
- package/test/phase-1.test.ts +617 -0
- package/test/phase-2.test.ts +620 -0
- package/test/phase-3.test.ts +99 -0
- package/test/scaffold-conformity.test.ts +8 -0
- package/test/schema-canary.test.ts +51 -0
- package/test/spec-compliance-auto.test.ts +64 -0
- package/test/spec-compliance.test.ts +295 -0
- package/test/spec-discovery.test.ts +68 -0
- package/test/spec-drift.test.ts +5 -0
- package/test/structure.test.ts +165 -0
- package/test/unit/agent-brief-guard-ship.test.ts +293 -0
- package/test/unit/extract-constraints.test.ts +145 -0
- package/test/unit/issue-close-guard.test.ts +204 -0
- package/test/unit/scaffold-project.test.ts +417 -0
- package/test/unit/skill-cooccurrence.test.ts +177 -0
- package/test/unit/skill-sequence-logger.test.ts +244 -0
- package/test/unit/workflow-state-guard.test.ts +95 -0
- package/workflows/batch-ship.js +295 -0
- package/workflows/council.js +481 -0
- package/workflows/prove.js +560 -0
- package/workflows/ship.js +789 -0
- package/workflows/verify.js +236 -0
|
@@ -0,0 +1,177 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* skill-cooccurrence.test.ts
|
|
3
|
+
*
|
|
4
|
+
* Test suite for SkillCooccurrence.ts CLI tool
|
|
5
|
+
*
|
|
6
|
+
* COVERAGE:
|
|
7
|
+
* - Matrix building from skill-sequences.jsonl
|
|
8
|
+
* - Pair counting within same session
|
|
9
|
+
* - JSON output format
|
|
10
|
+
* - Empty input handling
|
|
11
|
+
*/
|
|
12
|
+
|
|
13
|
+
import { describe, test, expect, beforeEach, afterEach } from 'bun:test';
|
|
14
|
+
import { mkdtempSync, rmSync, writeFileSync, readFileSync, existsSync } from 'fs';
|
|
15
|
+
import { join } from 'path';
|
|
16
|
+
import { tmpdir } from 'os';
|
|
17
|
+
import { execSync } from 'child_process';
|
|
18
|
+
|
|
19
|
+
describe('SkillCooccurrence.ts', () => {
|
|
20
|
+
let tempDir: string;
|
|
21
|
+
let sequencesPath: string;
|
|
22
|
+
let outputPath: string;
|
|
23
|
+
|
|
24
|
+
beforeEach(() => {
|
|
25
|
+
tempDir = mkdtempSync(join(tmpdir(), 'cooccur-test-'));
|
|
26
|
+
sequencesPath = join(tempDir, 'skill-sequences.jsonl');
|
|
27
|
+
outputPath = join(tempDir, 'skill-cooccurrence.json');
|
|
28
|
+
});
|
|
29
|
+
|
|
30
|
+
afterEach(() => {
|
|
31
|
+
if (existsSync(tempDir)) {
|
|
32
|
+
rmSync(tempDir, { recursive: true, force: true });
|
|
33
|
+
}
|
|
34
|
+
});
|
|
35
|
+
|
|
36
|
+
test('builds co-occurrence matrix from skill sequences', () => {
|
|
37
|
+
// Session 1: dev-loop + testing
|
|
38
|
+
// Session 2: dev-loop + testing (again)
|
|
39
|
+
// Session 3: debugging + research
|
|
40
|
+
const sequences = [
|
|
41
|
+
{ session_id: 's1', timestamp: '2026-05-10T10:00:00Z', skill_name: 'dev-loop', args: '', rating: 8 },
|
|
42
|
+
{ session_id: 's1', timestamp: '2026-05-10T10:05:00Z', skill_name: 'testing-and-qa-validation', args: '', rating: 8 },
|
|
43
|
+
{ session_id: 's2', timestamp: '2026-05-10T11:00:00Z', skill_name: 'dev-loop', args: '', rating: 9 },
|
|
44
|
+
{ session_id: 's2', timestamp: '2026-05-10T11:05:00Z', skill_name: 'testing-and-qa-validation', args: '', rating: 9 },
|
|
45
|
+
{ session_id: 's3', timestamp: '2026-05-10T12:00:00Z', skill_name: 'debugging-and-bug-fixes', args: '', rating: 7 },
|
|
46
|
+
{ session_id: 's3', timestamp: '2026-05-10T12:05:00Z', skill_name: 'research-and-api-investigation', args: '', rating: 7 }
|
|
47
|
+
];
|
|
48
|
+
|
|
49
|
+
writeFileSync(sequencesPath, sequences.map(s => JSON.stringify(s)).join('\n'));
|
|
50
|
+
|
|
51
|
+
const toolPath = join(process.env.HOME!, '.claude', 'PAI', 'Tools', 'SkillCooccurrence.ts');
|
|
52
|
+
|
|
53
|
+
execSync(`bun ${toolPath}`, {
|
|
54
|
+
env: {
|
|
55
|
+
...process.env,
|
|
56
|
+
SEQUENCES_FILE: sequencesPath,
|
|
57
|
+
OUTPUT_FILE: outputPath
|
|
58
|
+
}
|
|
59
|
+
});
|
|
60
|
+
|
|
61
|
+
expect(existsSync(outputPath)).toBe(true);
|
|
62
|
+
const matrix = JSON.parse(readFileSync(outputPath, 'utf-8'));
|
|
63
|
+
|
|
64
|
+
// dev-loop + testing occurred together 2 times
|
|
65
|
+
expect(matrix['dev-loop']['testing-and-qa-validation']).toBe(2);
|
|
66
|
+
expect(matrix['testing-and-qa-validation']['dev-loop']).toBe(2);
|
|
67
|
+
|
|
68
|
+
// debugging + research occurred together 1 time
|
|
69
|
+
expect(matrix['debugging-and-bug-fixes']['research-and-api-investigation']).toBe(1);
|
|
70
|
+
expect(matrix['research-and-api-investigation']['debugging-and-bug-fixes']).toBe(1);
|
|
71
|
+
|
|
72
|
+
// dev-loop and debugging never occurred together
|
|
73
|
+
expect(matrix['dev-loop']['debugging-and-bug-fixes']).toBeUndefined();
|
|
74
|
+
});
|
|
75
|
+
|
|
76
|
+
test('handles single-skill sessions (no pairs)', () => {
|
|
77
|
+
const sequences = [
|
|
78
|
+
{ session_id: 's1', timestamp: '2026-05-10T10:00:00Z', skill_name: 'dev-loop', args: '', rating: 8 },
|
|
79
|
+
{ session_id: 's2', timestamp: '2026-05-10T11:00:00Z', skill_name: 'testing-and-qa-validation', args: '', rating: 9 }
|
|
80
|
+
];
|
|
81
|
+
|
|
82
|
+
writeFileSync(sequencesPath, sequences.map(s => JSON.stringify(s)).join('\n'));
|
|
83
|
+
|
|
84
|
+
const toolPath = join(process.env.HOME!, '.claude', 'PAI', 'Tools', 'SkillCooccurrence.ts');
|
|
85
|
+
|
|
86
|
+
execSync(`bun ${toolPath}`, {
|
|
87
|
+
env: {
|
|
88
|
+
...process.env,
|
|
89
|
+
SEQUENCES_FILE: sequencesPath,
|
|
90
|
+
OUTPUT_FILE: outputPath
|
|
91
|
+
}
|
|
92
|
+
});
|
|
93
|
+
|
|
94
|
+
const matrix = JSON.parse(readFileSync(outputPath, 'utf-8'));
|
|
95
|
+
|
|
96
|
+
// Each skill appears but has no co-occurrences
|
|
97
|
+
expect(matrix['dev-loop']).toEqual({});
|
|
98
|
+
expect(matrix['testing-and-qa-validation']).toEqual({});
|
|
99
|
+
});
|
|
100
|
+
|
|
101
|
+
test('handles empty input file', () => {
|
|
102
|
+
writeFileSync(sequencesPath, '');
|
|
103
|
+
|
|
104
|
+
const toolPath = join(process.env.HOME!, '.claude', 'PAI', 'Tools', 'SkillCooccurrence.ts');
|
|
105
|
+
|
|
106
|
+
execSync(`bun ${toolPath}`, {
|
|
107
|
+
env: {
|
|
108
|
+
...process.env,
|
|
109
|
+
SEQUENCES_FILE: sequencesPath,
|
|
110
|
+
OUTPUT_FILE: outputPath
|
|
111
|
+
}
|
|
112
|
+
});
|
|
113
|
+
|
|
114
|
+
const matrix = JSON.parse(readFileSync(outputPath, 'utf-8'));
|
|
115
|
+
expect(Object.keys(matrix).length).toBe(0);
|
|
116
|
+
});
|
|
117
|
+
|
|
118
|
+
test('counts multiple occurrences in same session as one', () => {
|
|
119
|
+
// Same skill called twice in one session — should count as 1 for pairs
|
|
120
|
+
const sequences = [
|
|
121
|
+
{ session_id: 's1', timestamp: '2026-05-10T10:00:00Z', skill_name: 'dev-loop', args: '', rating: 8 },
|
|
122
|
+
{ session_id: 's1', timestamp: '2026-05-10T10:01:00Z', skill_name: 'dev-loop', args: '', rating: 8 },
|
|
123
|
+
{ session_id: 's1', timestamp: '2026-05-10T10:05:00Z', skill_name: 'testing-and-qa-validation', args: '', rating: 8 }
|
|
124
|
+
];
|
|
125
|
+
|
|
126
|
+
writeFileSync(sequencesPath, sequences.map(s => JSON.stringify(s)).join('\n'));
|
|
127
|
+
|
|
128
|
+
const toolPath = join(process.env.HOME!, '.claude', 'PAI', 'Tools', 'SkillCooccurrence.ts');
|
|
129
|
+
|
|
130
|
+
execSync(`bun ${toolPath}`, {
|
|
131
|
+
env: {
|
|
132
|
+
...process.env,
|
|
133
|
+
SEQUENCES_FILE: sequencesPath,
|
|
134
|
+
OUTPUT_FILE: outputPath
|
|
135
|
+
}
|
|
136
|
+
});
|
|
137
|
+
|
|
138
|
+
const matrix = JSON.parse(readFileSync(outputPath, 'utf-8'));
|
|
139
|
+
|
|
140
|
+
// dev-loop + testing co-occurred once (same session)
|
|
141
|
+
expect(matrix['dev-loop']['testing-and-qa-validation']).toBe(1);
|
|
142
|
+
});
|
|
143
|
+
|
|
144
|
+
test('JSON output format validation', () => {
|
|
145
|
+
const sequences = [
|
|
146
|
+
{ session_id: 's1', timestamp: '2026-05-10T10:00:00Z', skill_name: 'dev-loop', args: '', rating: 8 },
|
|
147
|
+
{ session_id: 's1', timestamp: '2026-05-10T10:05:00Z', skill_name: 'testing-and-qa-validation', args: '', rating: 8 }
|
|
148
|
+
];
|
|
149
|
+
|
|
150
|
+
writeFileSync(sequencesPath, sequences.map(s => JSON.stringify(s)).join('\n'));
|
|
151
|
+
|
|
152
|
+
const toolPath = join(process.env.HOME!, '.claude', 'PAI', 'Tools', 'SkillCooccurrence.ts');
|
|
153
|
+
|
|
154
|
+
execSync(`bun ${toolPath}`, {
|
|
155
|
+
env: {
|
|
156
|
+
...process.env,
|
|
157
|
+
SEQUENCES_FILE: sequencesPath,
|
|
158
|
+
OUTPUT_FILE: outputPath
|
|
159
|
+
}
|
|
160
|
+
});
|
|
161
|
+
|
|
162
|
+
const content = readFileSync(outputPath, 'utf-8');
|
|
163
|
+
const matrix = JSON.parse(content); // Must be valid JSON
|
|
164
|
+
|
|
165
|
+
// Top-level keys are skill names
|
|
166
|
+
Object.keys(matrix).forEach(skill => {
|
|
167
|
+
expect(typeof skill).toBe('string');
|
|
168
|
+
expect(typeof matrix[skill]).toBe('object');
|
|
169
|
+
|
|
170
|
+
// Nested values are counts
|
|
171
|
+
Object.values(matrix[skill]).forEach(count => {
|
|
172
|
+
expect(typeof count).toBe('number');
|
|
173
|
+
expect(count).toBeGreaterThan(0);
|
|
174
|
+
});
|
|
175
|
+
});
|
|
176
|
+
});
|
|
177
|
+
});
|
|
@@ -0,0 +1,244 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* skill-sequence-logger.test.ts
|
|
3
|
+
*
|
|
4
|
+
* Test suite for SkillSequenceLogger hook (SessionEnd trigger)
|
|
5
|
+
*
|
|
6
|
+
* COVERAGE:
|
|
7
|
+
* - Transcript parsing for Skill() tool calls
|
|
8
|
+
* - JSONL format validation
|
|
9
|
+
* - Rating join logic (session_id match)
|
|
10
|
+
* - Non-blocking behavior (always exit 0)
|
|
11
|
+
*/
|
|
12
|
+
|
|
13
|
+
import { describe, test, expect, beforeEach, afterEach } from 'bun:test';
|
|
14
|
+
import { mkdtempSync, rmSync, writeFileSync, readFileSync, existsSync } from 'fs';
|
|
15
|
+
import { join } from 'path';
|
|
16
|
+
import { tmpdir } from 'os';
|
|
17
|
+
import { execSync } from 'child_process';
|
|
18
|
+
|
|
19
|
+
describe('SkillSequenceLogger.hook.ts', () => {
|
|
20
|
+
let tempDir: string;
|
|
21
|
+
let ratingsPath: string;
|
|
22
|
+
let sequencesPath: string;
|
|
23
|
+
let transcriptPath: string;
|
|
24
|
+
|
|
25
|
+
beforeEach(() => {
|
|
26
|
+
tempDir = mkdtempSync(join(tmpdir(), 'skill-seq-test-'));
|
|
27
|
+
ratingsPath = join(tempDir, 'ratings.jsonl');
|
|
28
|
+
sequencesPath = join(tempDir, 'skill-sequences.jsonl');
|
|
29
|
+
transcriptPath = join(tempDir, 'transcript.jsonl');
|
|
30
|
+
});
|
|
31
|
+
|
|
32
|
+
afterEach(() => {
|
|
33
|
+
if (existsSync(tempDir)) {
|
|
34
|
+
rmSync(tempDir, { recursive: true, force: true });
|
|
35
|
+
}
|
|
36
|
+
});
|
|
37
|
+
|
|
38
|
+
test('parses Skill() tool calls from transcript', () => {
|
|
39
|
+
// Red phase — hook doesn't exist yet
|
|
40
|
+
const transcript = [
|
|
41
|
+
{
|
|
42
|
+
type: 'assistant',
|
|
43
|
+
message: {
|
|
44
|
+
content: [
|
|
45
|
+
{ type: 'text', text: 'Let me use a skill' },
|
|
46
|
+
{ type: 'tool_use', name: 'Skill', input: { skill: 'dev-loop', args: 'BKL-042' } }
|
|
47
|
+
]
|
|
48
|
+
}
|
|
49
|
+
},
|
|
50
|
+
{
|
|
51
|
+
type: 'tool_result',
|
|
52
|
+
message: { content: [{ type: 'text', text: 'Skill completed successfully' }] }
|
|
53
|
+
},
|
|
54
|
+
{
|
|
55
|
+
type: 'assistant',
|
|
56
|
+
message: {
|
|
57
|
+
content: [
|
|
58
|
+
{ type: 'tool_use', name: 'Skill', input: { skill: 'testing-and-qa-validation' } }
|
|
59
|
+
]
|
|
60
|
+
}
|
|
61
|
+
}
|
|
62
|
+
];
|
|
63
|
+
|
|
64
|
+
writeFileSync(transcriptPath, transcript.map(t => JSON.stringify(t)).join('\n'));
|
|
65
|
+
writeFileSync(ratingsPath, JSON.stringify({
|
|
66
|
+
session_id: 'test-123',
|
|
67
|
+
rating: 8,
|
|
68
|
+
timestamp: '2026-05-10T10:00:00Z'
|
|
69
|
+
}) + '\n');
|
|
70
|
+
|
|
71
|
+
const input = JSON.stringify({
|
|
72
|
+
session_id: 'test-123',
|
|
73
|
+
transcript_path: transcriptPath
|
|
74
|
+
});
|
|
75
|
+
|
|
76
|
+
const hookPath = join(process.env.HOME!, '.pai', 'hooks', 'SkillSequenceLogger.hook.ts');
|
|
77
|
+
|
|
78
|
+
// This will fail until we implement the hook
|
|
79
|
+
execSync(`bun ${hookPath}`, {
|
|
80
|
+
input: input,
|
|
81
|
+
env: {
|
|
82
|
+
...process.env,
|
|
83
|
+
RATINGS_FILE: ratingsPath,
|
|
84
|
+
SEQUENCES_FILE: sequencesPath
|
|
85
|
+
}
|
|
86
|
+
});
|
|
87
|
+
|
|
88
|
+
expect(existsSync(sequencesPath)).toBe(true);
|
|
89
|
+
const lines = readFileSync(sequencesPath, 'utf-8').trim().split('\n');
|
|
90
|
+
expect(lines.length).toBe(2); // Two Skill() calls
|
|
91
|
+
|
|
92
|
+
const first = JSON.parse(lines[0]);
|
|
93
|
+
expect(first.skill_name).toBe('dev-loop');
|
|
94
|
+
expect(first.args).toBe('BKL-042');
|
|
95
|
+
expect(first.session_id).toBe('test-123');
|
|
96
|
+
expect(first.rating).toBe(8);
|
|
97
|
+
|
|
98
|
+
const second = JSON.parse(lines[1]);
|
|
99
|
+
expect(second.skill_name).toBe('testing-and-qa-validation');
|
|
100
|
+
expect(second.session_id).toBe('test-123');
|
|
101
|
+
expect(second.rating).toBe(8);
|
|
102
|
+
});
|
|
103
|
+
|
|
104
|
+
test('joins with ratings.jsonl on session_id', () => {
|
|
105
|
+
const transcript = [
|
|
106
|
+
{
|
|
107
|
+
type: 'assistant',
|
|
108
|
+
message: {
|
|
109
|
+
content: [
|
|
110
|
+
{ type: 'tool_use', name: 'Skill', input: { skill: 'debugging-and-bug-fixes' } }
|
|
111
|
+
]
|
|
112
|
+
}
|
|
113
|
+
}
|
|
114
|
+
];
|
|
115
|
+
|
|
116
|
+
writeFileSync(transcriptPath, transcript.map(t => JSON.stringify(t)).join('\n'));
|
|
117
|
+
writeFileSync(ratingsPath, JSON.stringify({
|
|
118
|
+
session_id: 'test-456',
|
|
119
|
+
rating: 3,
|
|
120
|
+
timestamp: '2026-05-10T11:00:00Z'
|
|
121
|
+
}) + '\n');
|
|
122
|
+
|
|
123
|
+
const input = JSON.stringify({
|
|
124
|
+
session_id: 'test-456',
|
|
125
|
+
transcript_path: transcriptPath
|
|
126
|
+
});
|
|
127
|
+
|
|
128
|
+
const hookPath = join(process.env.HOME!, '.pai', 'hooks', 'SkillSequenceLogger.hook.ts');
|
|
129
|
+
|
|
130
|
+
execSync(`bun ${hookPath}`, {
|
|
131
|
+
input: input,
|
|
132
|
+
env: {
|
|
133
|
+
...process.env,
|
|
134
|
+
RATINGS_FILE: ratingsPath,
|
|
135
|
+
SEQUENCES_FILE: sequencesPath
|
|
136
|
+
}
|
|
137
|
+
});
|
|
138
|
+
|
|
139
|
+
const lines = readFileSync(sequencesPath, 'utf-8').trim().split('\n');
|
|
140
|
+
const entry = JSON.parse(lines[0]);
|
|
141
|
+
expect(entry.rating).toBe(3);
|
|
142
|
+
});
|
|
143
|
+
|
|
144
|
+
test('handles missing rating gracefully (rating=null)', () => {
|
|
145
|
+
const transcript = [
|
|
146
|
+
{
|
|
147
|
+
type: 'assistant',
|
|
148
|
+
message: {
|
|
149
|
+
content: [
|
|
150
|
+
{ type: 'tool_use', name: 'Skill', input: { skill: 'research-and-api-investigation' } }
|
|
151
|
+
]
|
|
152
|
+
}
|
|
153
|
+
}
|
|
154
|
+
];
|
|
155
|
+
|
|
156
|
+
writeFileSync(transcriptPath, transcript.map(t => JSON.stringify(t)).join('\n'));
|
|
157
|
+
// No ratings.jsonl file created — missing rating scenario
|
|
158
|
+
|
|
159
|
+
const input = JSON.stringify({
|
|
160
|
+
session_id: 'test-789',
|
|
161
|
+
transcript_path: transcriptPath
|
|
162
|
+
});
|
|
163
|
+
|
|
164
|
+
const hookPath = join(process.env.HOME!, '.pai', 'hooks', 'SkillSequenceLogger.hook.ts');
|
|
165
|
+
|
|
166
|
+
execSync(`bun ${hookPath}`, {
|
|
167
|
+
input: input,
|
|
168
|
+
env: {
|
|
169
|
+
...process.env,
|
|
170
|
+
RATINGS_FILE: ratingsPath,
|
|
171
|
+
SEQUENCES_FILE: sequencesPath
|
|
172
|
+
}
|
|
173
|
+
});
|
|
174
|
+
|
|
175
|
+
const lines = readFileSync(sequencesPath, 'utf-8').trim().split('\n');
|
|
176
|
+
const entry = JSON.parse(lines[0]);
|
|
177
|
+
expect(entry.rating).toBeNull();
|
|
178
|
+
});
|
|
179
|
+
|
|
180
|
+
test('always exits 0 (non-blocking)', () => {
|
|
181
|
+
const input = JSON.stringify({
|
|
182
|
+
session_id: 'test-exit',
|
|
183
|
+
transcript_path: '/nonexistent/path'
|
|
184
|
+
});
|
|
185
|
+
|
|
186
|
+
const hookPath = join(process.env.HOME!, '.pai', 'hooks', 'SkillSequenceLogger.hook.ts');
|
|
187
|
+
|
|
188
|
+
// Even with invalid input, should exit 0
|
|
189
|
+
const result = execSync(`bun ${hookPath}; echo $?`, {
|
|
190
|
+
input: input,
|
|
191
|
+
encoding: 'utf-8',
|
|
192
|
+
env: {
|
|
193
|
+
...process.env,
|
|
194
|
+
RATINGS_FILE: ratingsPath,
|
|
195
|
+
SEQUENCES_FILE: sequencesPath
|
|
196
|
+
}
|
|
197
|
+
});
|
|
198
|
+
|
|
199
|
+
expect(result.trim().endsWith('0')).toBe(true);
|
|
200
|
+
});
|
|
201
|
+
|
|
202
|
+
test('JSONL format validation', () => {
|
|
203
|
+
const transcript = [
|
|
204
|
+
{
|
|
205
|
+
type: 'assistant',
|
|
206
|
+
message: {
|
|
207
|
+
content: [
|
|
208
|
+
{ type: 'tool_use', name: 'Skill', input: { skill: 'product-feature-development' } }
|
|
209
|
+
]
|
|
210
|
+
}
|
|
211
|
+
}
|
|
212
|
+
];
|
|
213
|
+
|
|
214
|
+
writeFileSync(transcriptPath, transcript.map(t => JSON.stringify(t)).join('\n'));
|
|
215
|
+
|
|
216
|
+
const input = JSON.stringify({
|
|
217
|
+
session_id: 'test-format',
|
|
218
|
+
transcript_path: transcriptPath
|
|
219
|
+
});
|
|
220
|
+
|
|
221
|
+
const hookPath = join(process.env.HOME!, '.pai', 'hooks', 'SkillSequenceLogger.hook.ts');
|
|
222
|
+
|
|
223
|
+
execSync(`bun ${hookPath}`, {
|
|
224
|
+
input: input,
|
|
225
|
+
env: {
|
|
226
|
+
...process.env,
|
|
227
|
+
RATINGS_FILE: ratingsPath,
|
|
228
|
+
SEQUENCES_FILE: sequencesPath
|
|
229
|
+
}
|
|
230
|
+
});
|
|
231
|
+
|
|
232
|
+
const content = readFileSync(sequencesPath, 'utf-8');
|
|
233
|
+
const lines = content.trim().split('\n');
|
|
234
|
+
|
|
235
|
+
// Each line must be valid JSON
|
|
236
|
+
lines.forEach(line => {
|
|
237
|
+
const entry = JSON.parse(line);
|
|
238
|
+
expect(entry).toHaveProperty('session_id');
|
|
239
|
+
expect(entry).toHaveProperty('timestamp');
|
|
240
|
+
expect(entry).toHaveProperty('skill_name');
|
|
241
|
+
expect(entry).toHaveProperty('rating');
|
|
242
|
+
});
|
|
243
|
+
});
|
|
244
|
+
});
|
|
@@ -0,0 +1,95 @@
|
|
|
1
|
+
import { test, expect, describe } from "bun:test";
|
|
2
|
+
import { readFileSync, existsSync } from "fs";
|
|
3
|
+
import { join } from "path";
|
|
4
|
+
|
|
5
|
+
const HOOK_PATH = join(__dirname, "..", "..", "hooks", "WorkflowStateGuard.hook.ts");
|
|
6
|
+
|
|
7
|
+
describe("WorkflowStateGuard.hook.ts", () => {
|
|
8
|
+
test("hook file exists", () => {
|
|
9
|
+
expect(existsSync(HOOK_PATH)).toBe(true);
|
|
10
|
+
});
|
|
11
|
+
|
|
12
|
+
const hookSource = readFileSync(HOOK_PATH, "utf-8");
|
|
13
|
+
|
|
14
|
+
test("blocks Write tool when path contains workflow-state.json", () => {
|
|
15
|
+
expect(hookSource).toContain("Write");
|
|
16
|
+
expect(hookSource).toContain("workflow-state.json");
|
|
17
|
+
expect(hookSource).toContain("block");
|
|
18
|
+
});
|
|
19
|
+
|
|
20
|
+
test("blocks Edit tool when path contains workflow-state.json", () => {
|
|
21
|
+
expect(hookSource).toContain("Edit");
|
|
22
|
+
expect(hookSource).toContain("workflow-state.json");
|
|
23
|
+
});
|
|
24
|
+
|
|
25
|
+
test("block message includes writeWorkflowState() function name", () => {
|
|
26
|
+
expect(hookSource).toContain("writeWorkflowState()");
|
|
27
|
+
});
|
|
28
|
+
|
|
29
|
+
test("block message includes bun -e example command", () => {
|
|
30
|
+
expect(hookSource).toContain("bun -e");
|
|
31
|
+
});
|
|
32
|
+
|
|
33
|
+
test("outputs JSON decision block format", () => {
|
|
34
|
+
expect(hookSource).toContain("decision");
|
|
35
|
+
expect(hookSource).toContain("block");
|
|
36
|
+
// Verify it outputs JSON.stringify with decision: 'block'
|
|
37
|
+
expect(hookSource).toContain("JSON.stringify");
|
|
38
|
+
});
|
|
39
|
+
|
|
40
|
+
test("reads file_path from tool_input", () => {
|
|
41
|
+
expect(hookSource).toContain("file_path");
|
|
42
|
+
});
|
|
43
|
+
});
|
|
44
|
+
|
|
45
|
+
describe("schema strictness parity (GI-8)", () => {
|
|
46
|
+
const orchestratorSource = readFileSync(join(__dirname, "..", "..", "gates", "orchestrator.ts"), "utf-8");
|
|
47
|
+
const workflowTestSource = readFileSync(join(__dirname, "..", "..", "gates", "workflow.test.ts"), "utf-8");
|
|
48
|
+
|
|
49
|
+
test("writeWorkflowState uses passthrough parse", () => {
|
|
50
|
+
// writeWorkflowState should use .passthrough().parse()
|
|
51
|
+
expect(orchestratorSource).toContain("WorkflowStateSchema.passthrough().parse(state)");
|
|
52
|
+
});
|
|
53
|
+
|
|
54
|
+
test("workflow.test.ts uses passthrough safeParse", () => {
|
|
55
|
+
// workflow.test.ts should use .passthrough().safeParse()
|
|
56
|
+
expect(workflowTestSource).toContain("WorkflowStateSchema.passthrough().safeParse(raw)");
|
|
57
|
+
});
|
|
58
|
+
|
|
59
|
+
test("both use identical passthrough strictness", () => {
|
|
60
|
+
const orchestratorUsesPassthrough = orchestratorSource.includes("WorkflowStateSchema.passthrough().parse");
|
|
61
|
+
const testUsesPassthrough = workflowTestSource.includes("WorkflowStateSchema.passthrough().safeParse");
|
|
62
|
+
expect(orchestratorUsesPassthrough).toBe(true);
|
|
63
|
+
expect(testUsesPassthrough).toBe(true);
|
|
64
|
+
});
|
|
65
|
+
});
|
|
66
|
+
|
|
67
|
+
describe("ship.js Write tool instructions eliminated", () => {
|
|
68
|
+
const shipSource = readFileSync(join(__dirname, "..", "..", "workflows", "ship.js"), "utf-8");
|
|
69
|
+
|
|
70
|
+
test("zero agent prompts instruct using Write tool for workflow-state.json", () => {
|
|
71
|
+
// Count occurrences of "Write tool" or "Write the COMPLETE" in agent prompts
|
|
72
|
+
const writeToolPattern = /(?:using Write tool|Write the COMPLETE)/g;
|
|
73
|
+
const matches = shipSource.match(writeToolPattern) || [];
|
|
74
|
+
expect(matches.length, `Found ${matches.length} Write tool instructions in ship.js: ${matches.join(", ")}`).toBe(0);
|
|
75
|
+
});
|
|
76
|
+
|
|
77
|
+
test("heal prompts route through writeWorkflowState", () => {
|
|
78
|
+
// All agent prompts that modify workflow-state.json should reference writeWorkflowState
|
|
79
|
+
expect(shipSource).toContain("writeWorkflowState");
|
|
80
|
+
});
|
|
81
|
+
});
|
|
82
|
+
|
|
83
|
+
describe("checkIntegrity has production caller", () => {
|
|
84
|
+
const selfHealSource = readFileSync(join(__dirname, "..", "..", "gates", "self-heal.ts"), "utf-8");
|
|
85
|
+
|
|
86
|
+
test("checkIntegrity is called in runWithHeal", () => {
|
|
87
|
+
// checkIntegrity should be called after gate execution
|
|
88
|
+
const callPattern = /checkIntegrity\(beforeSnapshot,\s*afterSnapshot\)/;
|
|
89
|
+
expect(callPattern.test(selfHealSource)).toBe(true);
|
|
90
|
+
});
|
|
91
|
+
|
|
92
|
+
test("snapshotProtectedFields called before gate execution", () => {
|
|
93
|
+
expect(selfHealSource).toContain("snapshotProtectedFields(preState)");
|
|
94
|
+
});
|
|
95
|
+
});
|