mirror of
https://github.com/affaan-m/everything-claude-code.git
synced 2026-06-10 10:13:49 +08:00
Compare commits
4 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
c802c33abc | ||
|
|
0e66c838c7 | ||
|
|
cb9702ca99 | ||
|
|
f9384427b8 |
@@ -171,6 +171,24 @@ As of 2026-05-13:
|
||||
head, scores their artifacts and findings against evaluator/RAG corpus
|
||||
expectations, and treats matching hosted artifacts as promotion evidence
|
||||
before reporting a gap.
|
||||
- ECC-Tools PR #70 merged as `7001d805ac981fe220b4575159f469fbea9dbb76`
|
||||
and added retrieval planning for hosted promotion:
|
||||
the check now emits ranked retrieval candidates from cached hosted artifacts,
|
||||
hosted findings, expected evidence paths, and changed source paths, plus a
|
||||
model prompt seed that tells the later hosted judge not to promote from
|
||||
changed paths alone.
|
||||
- ECC-Tools PR #71 merged as `d41e59ff00fe1bd0b0c96386e56bc5269d7b9c15`
|
||||
and added the first model-backed hosted promotion judge contract:
|
||||
the check now emits a provider-neutral `hosted-promotion-judge.v1` request
|
||||
contract and fails closed unless hosted retrieval evidence, entitlement,
|
||||
remaining budget, and provider configuration are present. It still does not
|
||||
make live model calls.
|
||||
- ECC-Tools PR #72 merged as `973bc51e5436dd279ae5a890cce9811485eef0b5`
|
||||
and executes the hosted promotion model judge behind explicit gates:
|
||||
`PR_HOSTED_PROMOTION_MODEL_JUDGE_MODE=execute` now calls the configured
|
||||
provider only after hosted retrieval evidence, entitlement, budget, provider,
|
||||
and executor gates pass; the check remains non-blocking, strict-JSON-only,
|
||||
and rejects uncited or non-hosted model output without echoing raw responses.
|
||||
- Handoff `ecc-supply-chain-audit-20260513-0645.md` under
|
||||
`~/.cluster-swarm/handoffs/`
|
||||
records the May 13 supply-chain sweep: no active lockfile/manifest hit for
|
||||
@@ -467,10 +485,10 @@ is not complete unless the evidence column exists and has been freshly verified.
|
||||
| Claude and Codex plugin publication | Contact/submission path with required artifacts and status | Publication readiness, naming matrix, and May 12 dry-run evidence document plugin validation, clean-checkout Claude tag/install smoke, and Codex marketplace CLI shape | Needs explicit approval for real tag/push and marketplace submission |
|
||||
| Articles, tweets, and announcements | X thread, LinkedIn copy, GitHub release copy, push checklist | Draft launch collateral exists under rc.1 release docs | Needs URL-backed refresh |
|
||||
| AgentShield enterprise iteration | Policy gates, SARIF, packs, provenance, corpus, HTML reports, exception lifecycle audit, baseline drift Action/CLI surfaces, evidence-pack redaction, harness adapter registry, enterprise research roadmap, supply-chain hardened release path, CI-safe baseline fingerprints, corpus accuracy recommendations, remediation workflow phases, env proxy hijack corpus coverage | PRs #53, #55-#64, #67-#69, and #78-#82 landed with test evidence; native PDF export deferred in favor of self-contained HTML plus print-to-PDF until explicit enterprise demand appears; `docs/architecture/agentshield-enterprise-research-roadmap.md` now has baseline drift, evidence-pack bundle, redaction, adapter-registry, supply-chain hardening, hashed baseline fingerprints, corpus accuracy recommendation, remediation workflow, and env proxy hijack corpus slices landed | Next hosted evidence-pack workflow depth |
|
||||
| ECC Tools next-level app | Billing audit, PR checks, deep analyzer, sync backlog, evaluator/RAG corpus, analysis-depth readiness, hosted execution planning, hosted CI diagnostics, hosted security evidence review, hosted harness compatibility audit, hosted reference-set evaluation, hosted AI routing/cost review, hosted team backlog routing, hosted depth-plan check-run, PR-comment hosted job dispatch, hosted job result history/check-runs, hosted result status command, status-aware depth-plan recommendations, hosted promotion readiness, hosted promotion output scoring | PRs #26-#43 plus #53-#69 landed with test evidence, including AgentShield evidence-pack gap routing, canonical bundle recognition, supply-chain signature gates, PR draft follow-up Linear tracking, evidence-backed/deep-ready repository classification, the `/api/analysis/depth-plan` hosted job plan, `/api/analysis/jobs/ci-diagnostics`, `/api/analysis/jobs/security-evidence-review`, `/api/analysis/jobs/harness-compatibility-audit`, `/api/analysis/jobs/reference-set-evaluation`, `/api/analysis/jobs/ai-routing-cost-review`, `/api/analysis/jobs/team-backlog-routing`, the `ECC Tools / Hosted Depth Plan` check-run, `/ecc-tools analyze --job ...` PR-comment dispatch, non-blocking per-hosted-job result check-runs backed by 30-day result cache records, `/ecc-tools analyze --job status` cache lookup, cache-aware next-job recommendations in the depth-plan check-run, the `ECC Tools / Hosted Promotion Readiness` corpus-backed PR check-run, and deterministic hosted-output scoring against cached completed job artifacts/findings | Next work is retrieval/model-backed hosted promotion after deterministic output scoring |
|
||||
| ECC Tools next-level app | Billing audit, PR checks, deep analyzer, sync backlog, evaluator/RAG corpus, analysis-depth readiness, hosted execution planning, hosted CI diagnostics, hosted security evidence review, hosted harness compatibility audit, hosted reference-set evaluation, hosted AI routing/cost review, hosted team backlog routing, hosted depth-plan check-run, PR-comment hosted job dispatch, hosted job result history/check-runs, hosted result status command, status-aware depth-plan recommendations, hosted promotion readiness, hosted promotion output scoring, hosted promotion retrieval planning, hosted promotion judge contract, gated hosted promotion judge execution | PRs #26-#43 plus #53-#72 landed with test evidence, including AgentShield evidence-pack gap routing, canonical bundle recognition, supply-chain signature gates, PR draft follow-up Linear tracking, evidence-backed/deep-ready repository classification, the `/api/analysis/depth-plan` hosted job plan, `/api/analysis/jobs/ci-diagnostics`, `/api/analysis/jobs/security-evidence-review`, `/api/analysis/jobs/harness-compatibility-audit`, `/api/analysis/jobs/reference-set-evaluation`, `/api/analysis/jobs/ai-routing-cost-review`, `/api/analysis/jobs/team-backlog-routing`, the `ECC Tools / Hosted Depth Plan` check-run, `/ecc-tools analyze --job ...` PR-comment dispatch, non-blocking per-hosted-job result check-runs backed by 30-day result cache records, `/ecc-tools analyze --job status` cache lookup, cache-aware next-job recommendations in the depth-plan check-run, the `ECC Tools / Hosted Promotion Readiness` corpus-backed PR check-run, deterministic hosted-output scoring against cached completed job artifacts/findings, ranked retrieval/model-prompt planning, the fail-closed `hosted-promotion-judge.v1` request contract, and opt-in live model-judge execution behind hosted evidence, entitlement, budget, provider, executor, strict JSON, and citation gates | Next work is hosted promotion telemetry and operator review UX |
|
||||
| GitGuardian/Dependabot/CodeRabbit-style checks | Non-blocking taxonomy, deterministic follow-up checks, and local supply-chain gates | ECC-Tools risk taxonomy check plus follow-up signals landed, including Skill Quality, Deep Analyzer Evidence, Analyzer Corpus Evidence, RAG/Evaluator Evidence, PR Review/Salvage Evidence, and AgentShield evidence-pack evidence; #1846 added npm registry signature gates; #1848 added the supply-chain incident-response playbook and `pull_request_target` cache-poisoning validator guard; #1851 added the privileged checkout credential-persistence guard; AgentShield #78, JARVIS #13, and ECC-Tools #53 applied the same hardening outside trunk | Current supply-chain gate complete; deeper hosted review features remain future |
|
||||
| Harness-agnostic learning system | Audit, adapter matrix, observability, traces, promotion loop | Audit/adapters/observability gates plus `docs/architecture/evaluator-rag-prototype.md`, `examples/evaluator-rag-prototype/`, and ECC-Tools PR #40 define read-only stale-salvage, billing-readiness, CI-failure-diagnosis, harness-config-quality, AgentShield policy-exception, skill-quality evidence, deep-analyzer evidence, and RAG/evaluator comparison scenarios with trace, report, playbook, verifier, and predictive-check artifacts; ECC-Tools PRs #68/#69 now turn that corpus into a deterministic PR check-run gate with cached hosted-output scoring | Deterministic hosted PR check and cached output scoring integrated; hosted retrieval remains future |
|
||||
| Linear roadmap is detailed | Linear project status plus repo mirror | Repo mirror exists; issue creation was retried on 2026-05-12 and remains blocked by the workspace free issue limit; this May 13 sync adds ECC #1860, AgentShield #78-#82, JARVIS #13, ECC-Tools #53-#69, resolved queue/discussion counts, and Linear project status updates through ECC-Tools #69 | Needs recurring status updates after each merge batch |
|
||||
| Harness-agnostic learning system | Audit, adapter matrix, observability, traces, promotion loop | Audit/adapters/observability gates plus `docs/architecture/evaluator-rag-prototype.md`, `examples/evaluator-rag-prototype/`, and ECC-Tools PR #40 define read-only stale-salvage, billing-readiness, CI-failure-diagnosis, harness-config-quality, AgentShield policy-exception, skill-quality evidence, deep-analyzer evidence, and RAG/evaluator comparison scenarios with trace, report, playbook, verifier, and predictive-check artifacts; ECC-Tools PRs #68-#72 now turn that corpus into a deterministic PR check-run gate with cached hosted-output scoring, ranked retrieval candidates, a model prompt seed, a fail-closed hosted model-judge request contract, and opt-in live model execution behind strict hosted-evidence gates | Deterministic hosted PR check, cached output scoring, retrieval planning, judge contract, and gated model execution integrated |
|
||||
| Linear roadmap is detailed | Linear project status plus repo mirror | Repo mirror exists; issue creation was retried on 2026-05-12 and remains blocked by the workspace free issue limit; this May 13 sync adds ECC #1860, AgentShield #78-#82, JARVIS #13, ECC-Tools #53-#72, resolved queue/discussion counts, and notes that Linear connector status updates after ECC-Tools #68 remain blocked by a connector secret-owner error | Needs recurring status updates after connector recovery |
|
||||
| Flow separation and progress tracking | Flow lanes with owner artifacts and update cadence | This roadmap defines lanes below and `docs/architecture/progress-sync-contract.md` makes GitHub/Linear/handoff/roadmap sync part of the readiness gate | Active |
|
||||
| Realtime Linear sync | Project updates while issue limit is blocked; issues later | ECC-Tools #39 implements opt-in Linear API sync for deferred follow-up backlog items, and ECC-Tools #54 adds copy-ready PR drafts to that backlog when draft PR shells are not opened; `docs/architecture/progress-sync-contract.md` defines the local file-backed realtime boundary while issue capacity is blocked | Needs workspace capacity/config rollout |
|
||||
| Observability for self-use | Local readiness gate, traces, status snapshots, HUD/status contract, risk ledger, progress-sync contract | `npm run observability:ready` reports 21/21 | Complete for local gate |
|
||||
@@ -489,9 +507,9 @@ repo evidence and merge commits.
|
||||
| Queue hygiene and salvage | GitHub PR/issue state, salvage ledger | Append ledger entries for any future stale closures | Every cleanup batch |
|
||||
| Release and publication | rc.1 release docs, publication readiness doc | Naming matrix and plugin submission/contact checklist | Before any tag |
|
||||
| Harness OS core | Audit, adapter matrix, observability docs, `ecc2/` | HUD/session-control acceptance spec | Weekly until GA |
|
||||
| Evaluation and RAG | Reference-set validation, harness audit, traces, ECC-Tools corpus | Read-only evaluator/RAG prototype plus stale-salvage, billing-readiness, CI-failure-diagnosis, harness-config-quality, AgentShield policy-exception, skill-quality evidence, deep-analyzer evidence, and RAG/evaluator comparison fixtures; ECC-Tools #68 publishes the corpus as a hosted promotion readiness check-run, and #69 scores cached hosted job outputs against the same corpus | Hosted retrieval/model-backed promotion plan |
|
||||
| Evaluation and RAG | Reference-set validation, harness audit, traces, ECC-Tools corpus | Read-only evaluator/RAG prototype plus stale-salvage, billing-readiness, CI-failure-diagnosis, harness-config-quality, AgentShield policy-exception, skill-quality evidence, deep-analyzer evidence, and RAG/evaluator comparison fixtures; ECC-Tools #68 publishes the corpus as a hosted promotion readiness check-run, #69 scores cached hosted job outputs against the same corpus, #70 emits ranked retrieval candidates plus a model prompt seed, #71 adds a fail-closed hosted model-judge request contract, and #72 executes that judge only when explicitly enabled and backed by hosted retrieval citations | Hosted promotion telemetry and operator review UX |
|
||||
| AgentShield enterprise | AgentShield PR evidence and roadmap notes | Remediation workflow depth or corpus expansion follow-up | Next implementation batch |
|
||||
| ECC Tools app | ECC-Tools PR evidence, billing audit, risk taxonomy, evaluator/RAG corpus | ECC-Tools #53 published the supply-chain workflow hardening branch, #54 tracks copy-ready PR drafts in the Linear/project backlog, #55 classifies analysis-depth readiness, #56 exposes the hosted execution plan, #57 executes the first hosted CI diagnostics job, #58 executes the hosted security evidence review job, #59 executes the hosted harness compatibility audit, #60 executes the hosted reference-set evaluation, #61 executes the hosted AI routing/cost review, #62 executes hosted team backlog routing, #63 publishes the hosted depth-plan check-run, #64 dispatches hosted jobs from PR comments, #65 persists hosted result history/check-runs, #66 exposes hosted job status from PR comments, #67 makes depth-plan recommendations cache-aware, #68 publishes hosted promotion readiness from the evaluator/RAG corpus, and #69 scores cached hosted job outputs against that corpus; next work is retrieval/model-backed hosted promotion | Next implementation batch |
|
||||
| ECC Tools app | ECC-Tools PR evidence, billing audit, risk taxonomy, evaluator/RAG corpus | ECC-Tools #53 published the supply-chain workflow hardening branch, #54 tracks copy-ready PR drafts in the Linear/project backlog, #55 classifies analysis-depth readiness, #56 exposes the hosted execution plan, #57 executes the first hosted CI diagnostics job, #58 executes the hosted security evidence review job, #59 executes the hosted harness compatibility audit, #60 executes the hosted reference-set evaluation, #61 executes the hosted AI routing/cost review, #62 executes hosted team backlog routing, #63 publishes the hosted depth-plan check-run, #64 dispatches hosted jobs from PR comments, #65 persists hosted result history/check-runs, #66 exposes hosted job status from PR comments, #67 makes depth-plan recommendations cache-aware, #68 publishes hosted promotion readiness from the evaluator/RAG corpus, #69 scores cached hosted job outputs against that corpus, #70 emits ranked retrieval candidates plus a model prompt seed, #71 emits the gated `hosted-promotion-judge.v1` contract without live model calls, and #72 adds opt-in live model-judge execution behind hosted-evidence and strict JSON/citation gates | Next implementation batch |
|
||||
| Linear progress | Linear project status updates, `docs/architecture/progress-sync-contract.md`, and this mirror | Status update with queue/evidence/missing gates | Every significant merge batch |
|
||||
|
||||
The project status update should always include:
|
||||
@@ -708,12 +726,12 @@ Acceptance:
|
||||
PR #82 expanded corpus coverage for env proxy hijacks and out-of-band
|
||||
exfiltration; and ECC-Tools PRs #42/#43 now route and recognize evidence
|
||||
packs. The next slice is hosted evidence-pack workflow depth.
|
||||
2. Plan retrieval/model-backed hosted promotion on top of the #69 deterministic
|
||||
hosted output scoring contract, keeping vector/model judgment behind fixture
|
||||
evaluation until the retrieval contract is stable.
|
||||
2. Add hosted promotion telemetry and operator review UX on top of the #72
|
||||
gated model execution path so live judgments can be audited before any
|
||||
promotion policy becomes enforceable.
|
||||
3. Enable/configure the merged Linear backlog sync path after workspace issue
|
||||
capacity clears or the Linear workspace is upgraded, then verify PR-draft
|
||||
salvage items land in the expected project.
|
||||
4. Use the ECC-Tools evaluator/RAG corpus as the promotion gate before adding
|
||||
hosted retrieval, vector storage, model-backed judging, or automated
|
||||
hosted retrieval, vector storage, live model-backed judging, or automated
|
||||
check-run promotion.
|
||||
|
||||
@@ -7,13 +7,12 @@
|
||||
* the actual code. This hook steers the agent back to fixing the source.
|
||||
*
|
||||
* Exit codes:
|
||||
* 0 = allow (not a config file, or first-time creation of one)
|
||||
* 2 = block (existing config file modification attempted)
|
||||
* 0 = allow (not a config file)
|
||||
* 2 = block (config file modification attempted)
|
||||
*/
|
||||
|
||||
'use strict';
|
||||
|
||||
const fs = require('fs');
|
||||
const path = require('path');
|
||||
|
||||
const MAX_STDIN = 1024 * 1024;
|
||||
@@ -59,7 +58,7 @@ const PROTECTED_FILES = new Set([
|
||||
'.stylelintrc.yml',
|
||||
'.markdownlint.json',
|
||||
'.markdownlint.yaml',
|
||||
'.markdownlintrc'
|
||||
'.markdownlintrc',
|
||||
]);
|
||||
|
||||
function parseInput(inputOrRaw) {
|
||||
@@ -95,41 +94,13 @@ function run(inputOrRaw, options = {}) {
|
||||
|
||||
const basename = path.basename(filePath);
|
||||
if (PROTECTED_FILES.has(basename)) {
|
||||
// Allow first-time creation — there's no existing config to weaken.
|
||||
// The hook's purpose is blocking modifications; writing a brand-new
|
||||
// config file in a project that has none is a legitimate bootstrap
|
||||
// path (e.g. scaffolding ESLint into a fresh repo).
|
||||
//
|
||||
// Fail closed on any stat error other than ENOENT. Use lstatSync so a
|
||||
// symlink at the protected path is treated as present even if its target
|
||||
// is missing — a dangling symlink at e.g. .eslintrc.js still represents
|
||||
// an existing config entry that an agent should not silently replace.
|
||||
// fs.existsSync would swallow EACCES/EPERM as false; lstatSync exposes
|
||||
// the error code so we can treat only genuine "path not found" (ENOENT)
|
||||
// as absent.
|
||||
let exists = true;
|
||||
try {
|
||||
fs.lstatSync(filePath);
|
||||
// lstat succeeded — something (file, dir, or symlink) exists here.
|
||||
} catch (err) {
|
||||
if (err && err.code === 'ENOENT') {
|
||||
exists = false;
|
||||
}
|
||||
// Any other error (EACCES, EPERM, ELOOP, etc.) leaves exists=true
|
||||
// so the guard is never silently weakened.
|
||||
}
|
||||
|
||||
if (!exists) {
|
||||
return { exitCode: 0 };
|
||||
}
|
||||
|
||||
return {
|
||||
exitCode: 2,
|
||||
stderr:
|
||||
`BLOCKED: Modifying ${basename} is not allowed. ` +
|
||||
'Fix the source code to satisfy linter/formatter rules instead of ' +
|
||||
'weakening the config. If this is a legitimate config change, ' +
|
||||
'disable the config-protection hook temporarily.'
|
||||
'disable the config-protection hook temporarily.',
|
||||
};
|
||||
}
|
||||
|
||||
@@ -154,7 +125,7 @@ process.stdin.on('data', chunk => {
|
||||
process.stdin.on('end', () => {
|
||||
const result = run(raw, {
|
||||
truncated,
|
||||
maxStdin: Number(process.env.ECC_HOOK_INPUT_MAX_BYTES) || MAX_STDIN
|
||||
maxStdin: Number(process.env.ECC_HOOK_INPUT_MAX_BYTES) || MAX_STDIN,
|
||||
});
|
||||
|
||||
if (result.stderr) {
|
||||
|
||||
@@ -19,7 +19,8 @@ const {
|
||||
getTempDir,
|
||||
writeFile,
|
||||
readStdinJson,
|
||||
log
|
||||
log,
|
||||
output
|
||||
} = require('../lib/utils');
|
||||
|
||||
async function resolveSessionId() {
|
||||
@@ -77,14 +78,25 @@ async function main() {
|
||||
writeFile(counterFile, String(count));
|
||||
}
|
||||
|
||||
// Suggest compact after threshold tool calls
|
||||
// Suggest compact after threshold tool calls.
|
||||
//
|
||||
// log() writes to stderr (debug log). Per the Claude Code hooks guide,
|
||||
// non-blocking PreToolUse stderr (exit 0) is only written to the debug log;
|
||||
// it does not reach the model. To inject a user-facing suggestion without
|
||||
// blocking the tool call, emit structured JSON to stdout with
|
||||
// hookSpecificOutput.additionalContext — the documented mechanism for
|
||||
// PreToolUse hooks to add context to the next model turn.
|
||||
if (count === threshold) {
|
||||
log(`[StrategicCompact] ${threshold} tool calls reached - consider /compact if transitioning phases`);
|
||||
const msg = `[StrategicCompact] ${threshold} tool calls reached - consider /compact if transitioning phases`;
|
||||
log(msg);
|
||||
output({ hookSpecificOutput: { hookEventName: 'PreToolUse', additionalContext: msg } });
|
||||
}
|
||||
|
||||
// Suggest at regular intervals after threshold (every 25 calls from threshold)
|
||||
if (count > threshold && (count - threshold) % 25 === 0) {
|
||||
log(`[StrategicCompact] ${count} tool calls - good checkpoint for /compact if context is stale`);
|
||||
const msg = `[StrategicCompact] ${count} tool calls - good checkpoint for /compact if context is stale`;
|
||||
log(msg);
|
||||
output({ hookSpecificOutput: { hookEventName: 'PreToolUse', additionalContext: msg } });
|
||||
}
|
||||
|
||||
process.exit(0);
|
||||
|
||||
@@ -135,7 +135,7 @@ test('roadmap points to the evaluator RAG prototype and hosted PR check', () =>
|
||||
|
||||
assert.ok(roadmap.includes('docs/architecture/evaluator-rag-prototype.md'));
|
||||
assert.ok(roadmap.includes('examples/evaluator-rag-prototype/'));
|
||||
assert.ok(roadmap.includes('Deterministic hosted PR check and cached output scoring integrated; hosted retrieval remains future'));
|
||||
assert.ok(roadmap.includes('Deterministic hosted PR check, cached output scoring, retrieval planning, judge contract, and gated model execution integrated'));
|
||||
});
|
||||
|
||||
test('billing readiness scenario rejects launch copy overclaims', () => {
|
||||
|
||||
@@ -4,7 +4,6 @@
|
||||
|
||||
const assert = require('assert');
|
||||
const fs = require('fs');
|
||||
const os = require('os');
|
||||
const path = require('path');
|
||||
const { spawnSync } = require('child_process');
|
||||
|
||||
@@ -71,249 +70,85 @@ function runTests() {
|
||||
let passed = 0;
|
||||
let failed = 0;
|
||||
|
||||
if (
|
||||
test('blocks protected config file edits through run-with-flags', () => {
|
||||
const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'ecc-config-protect-'));
|
||||
try {
|
||||
const absPath = path.join(tmpDir, '.eslintrc.js');
|
||||
fs.writeFileSync(absPath, 'module.exports = {};');
|
||||
|
||||
const input = {
|
||||
tool_name: 'Write',
|
||||
tool_input: {
|
||||
file_path: absPath,
|
||||
content: 'module.exports = {};'
|
||||
}
|
||||
};
|
||||
|
||||
const result = runHook(input);
|
||||
assert.strictEqual(result.code, 2, 'Expected protected config edit to be blocked');
|
||||
assert.strictEqual(result.stdout, '', 'Blocked hook should not echo raw input');
|
||||
assert.ok(result.stderr.includes('BLOCKED: Modifying .eslintrc.js is not allowed.'), `Expected block message, got: ${result.stderr}`);
|
||||
} finally {
|
||||
try {
|
||||
fs.rmSync(tmpDir, { recursive: true, force: true });
|
||||
} catch {
|
||||
// best-effort cleanup
|
||||
}
|
||||
if (test('blocks protected config file edits through run-with-flags', () => {
|
||||
const input = {
|
||||
tool_name: 'Write',
|
||||
tool_input: {
|
||||
file_path: '.eslintrc.js',
|
||||
content: 'module.exports = {};'
|
||||
}
|
||||
})
|
||||
)
|
||||
passed++;
|
||||
else failed++;
|
||||
};
|
||||
|
||||
if (
|
||||
test('passes through safe file edits unchanged', () => {
|
||||
const input = {
|
||||
tool_name: 'Write',
|
||||
tool_input: {
|
||||
file_path: 'src/index.js',
|
||||
content: 'console.log("ok");'
|
||||
}
|
||||
};
|
||||
const result = runHook(input);
|
||||
assert.strictEqual(result.code, 2, 'Expected protected config edit to be blocked');
|
||||
assert.strictEqual(result.stdout, '', 'Blocked hook should not echo raw input');
|
||||
assert.ok(result.stderr.includes('BLOCKED: Modifying .eslintrc.js is not allowed.'), `Expected block message, got: ${result.stderr}`);
|
||||
})) passed++; else failed++;
|
||||
|
||||
const rawInput = JSON.stringify(input);
|
||||
const result = runHook(input);
|
||||
assert.strictEqual(result.code, 0, 'Expected safe file edit to pass');
|
||||
assert.strictEqual(result.stdout, rawInput, 'Expected exact raw JSON passthrough');
|
||||
assert.strictEqual(result.stderr, '', 'Expected no stderr for safe edits');
|
||||
})
|
||||
)
|
||||
passed++;
|
||||
else failed++;
|
||||
if (test('passes through safe file edits unchanged', () => {
|
||||
const input = {
|
||||
tool_name: 'Write',
|
||||
tool_input: {
|
||||
file_path: 'src/index.js',
|
||||
content: 'console.log("ok");'
|
||||
}
|
||||
};
|
||||
|
||||
const rawInput = JSON.stringify(input);
|
||||
const result = runHook(input);
|
||||
assert.strictEqual(result.code, 0, 'Expected safe file edit to pass');
|
||||
assert.strictEqual(result.stdout, rawInput, 'Expected exact raw JSON passthrough');
|
||||
assert.strictEqual(result.stderr, '', 'Expected no stderr for safe edits');
|
||||
})) passed++; else failed++;
|
||||
|
||||
if (test('blocks truncated protected config payloads instead of failing open', () => {
|
||||
const rawInput = JSON.stringify({
|
||||
tool_name: 'Write',
|
||||
tool_input: {
|
||||
file_path: '.eslintrc.js',
|
||||
content: 'x'.repeat(1024 * 1024 + 2048)
|
||||
}
|
||||
});
|
||||
|
||||
const result = runHook(rawInput);
|
||||
assert.strictEqual(result.code, 2, 'Expected truncated protected payload to be blocked');
|
||||
assert.strictEqual(result.stdout, '', 'Blocked truncated payload should not echo raw input');
|
||||
assert.ok(result.stderr.includes('Hook input exceeded 1048576 bytes'), `Expected size warning, got: ${result.stderr}`);
|
||||
assert.ok(result.stderr.includes('truncated payload'), `Expected truncated payload warning, got: ${result.stderr}`);
|
||||
})) passed++; else failed++;
|
||||
|
||||
if (test('legacy hooks do not echo raw input when they fail without stdout', () => {
|
||||
const pluginRoot = path.join(__dirname, '..', `tmp-runner-plugin-${Date.now()}`);
|
||||
const scriptDir = path.join(pluginRoot, 'scripts', 'hooks');
|
||||
const scriptPath = path.join(scriptDir, 'legacy-block.js');
|
||||
|
||||
try {
|
||||
fs.mkdirSync(scriptDir, { recursive: true });
|
||||
fs.writeFileSync(
|
||||
scriptPath,
|
||||
'#!/usr/bin/env node\nprocess.stderr.write("blocked by legacy hook\\n");\nprocess.exit(2);\n'
|
||||
);
|
||||
|
||||
if (
|
||||
test('blocks truncated protected config payloads instead of failing open', () => {
|
||||
const rawInput = JSON.stringify({
|
||||
tool_name: 'Write',
|
||||
tool_input: {
|
||||
file_path: '.eslintrc.js',
|
||||
content: 'x'.repeat(1024 * 1024 + 2048)
|
||||
content: 'module.exports = {};'
|
||||
}
|
||||
});
|
||||
|
||||
const result = runHook(rawInput);
|
||||
assert.strictEqual(result.code, 2, 'Expected truncated protected payload to be blocked');
|
||||
assert.strictEqual(result.stdout, '', 'Blocked truncated payload should not echo raw input');
|
||||
assert.ok(result.stderr.includes('Hook input exceeded 1048576 bytes'), `Expected size warning, got: ${result.stderr}`);
|
||||
assert.ok(result.stderr.includes('truncated payload'), `Expected truncated payload warning, got: ${result.stderr}`);
|
||||
})
|
||||
)
|
||||
passed++;
|
||||
else failed++;
|
||||
|
||||
if (
|
||||
test('allows first-time creation of a protected config file', () => {
|
||||
const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'ecc-config-protect-'));
|
||||
const result = runCustomHook(pluginRoot, 'pre:legacy-block', 'scripts/hooks/legacy-block.js', rawInput);
|
||||
assert.strictEqual(result.code, 2, 'Expected failing legacy hook exit code to propagate');
|
||||
assert.strictEqual(result.stdout, '', 'Expected failing legacy hook to avoid raw passthrough');
|
||||
assert.ok(result.stderr.includes('blocked by legacy hook'), `Expected legacy hook stderr, got: ${result.stderr}`);
|
||||
} finally {
|
||||
try {
|
||||
const absPath = path.join(tmpDir, 'eslint.config.mjs');
|
||||
const input = {
|
||||
tool_name: 'Write',
|
||||
tool_input: {
|
||||
file_path: absPath,
|
||||
content: 'export default [];'
|
||||
}
|
||||
};
|
||||
|
||||
const rawInput = JSON.stringify(input);
|
||||
const result = runHook(input);
|
||||
assert.strictEqual(result.code, 0, `Expected exit 0 for first-time creation, got ${result.code}; stderr: ${result.stderr}`);
|
||||
assert.strictEqual(result.stdout, rawInput, 'Expected raw passthrough when creation is allowed');
|
||||
assert.strictEqual(result.stderr, '', `Expected no stderr for first-time creation, got: ${result.stderr}`);
|
||||
} finally {
|
||||
try {
|
||||
fs.rmSync(tmpDir, { recursive: true, force: true });
|
||||
} catch {
|
||||
// best-effort cleanup
|
||||
}
|
||||
fs.rmSync(pluginRoot, { recursive: true, force: true });
|
||||
} catch {
|
||||
// best-effort cleanup
|
||||
}
|
||||
})
|
||||
)
|
||||
passed++;
|
||||
else failed++;
|
||||
|
||||
if (
|
||||
test('allows first-time creation when the parent directory does not exist yet', () => {
|
||||
const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'ecc-config-protect-'));
|
||||
try {
|
||||
// Path under a non-existent subdirectory — statSync returns ENOENT
|
||||
// on the final segment, which should be treated as "does not exist"
|
||||
// and allow the write. (Agent or CLI is expected to create parents
|
||||
// during the Write itself; this hook does not need to.)
|
||||
const absPath = path.join(tmpDir, 'no-such-parent', '.prettierrc');
|
||||
const input = {
|
||||
tool_name: 'Write',
|
||||
tool_input: {
|
||||
file_path: absPath,
|
||||
content: '{}'
|
||||
}
|
||||
};
|
||||
|
||||
const rawInput = JSON.stringify(input);
|
||||
const result = runHook(input);
|
||||
assert.strictEqual(result.code, 0, `Expected exit 0 for ENOENT path, got ${result.code}; stderr: ${result.stderr}`);
|
||||
assert.strictEqual(result.stdout, rawInput, 'Expected raw passthrough when path does not exist');
|
||||
} finally {
|
||||
try {
|
||||
fs.rmSync(tmpDir, { recursive: true, force: true });
|
||||
} catch {
|
||||
// best-effort cleanup
|
||||
}
|
||||
}
|
||||
})
|
||||
)
|
||||
passed++;
|
||||
else failed++;
|
||||
|
||||
if (
|
||||
test('blocks protected paths that exist as a dangling symlink', () => {
|
||||
const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'ecc-config-protect-'));
|
||||
try {
|
||||
const missingTarget = path.join(tmpDir, 'nowhere.js');
|
||||
const linkPath = path.join(tmpDir, '.eslintrc.js');
|
||||
try {
|
||||
fs.symlinkSync(missingTarget, linkPath);
|
||||
} catch (err) {
|
||||
// Windows without Developer Mode or certain sandboxes disallow
|
||||
// symlinks. Skip cleanly rather than fail the suite.
|
||||
if (err.code === 'EPERM' || err.code === 'EACCES') {
|
||||
console.log(' (skipped: symlink creation not permitted here)');
|
||||
return;
|
||||
}
|
||||
throw err;
|
||||
}
|
||||
|
||||
const input = {
|
||||
tool_name: 'Write',
|
||||
tool_input: {
|
||||
file_path: linkPath,
|
||||
content: 'module.exports = {};'
|
||||
}
|
||||
};
|
||||
|
||||
const result = runHook(input);
|
||||
assert.strictEqual(result.code, 2, `Expected exit 2 for dangling symlink, got ${result.code}; stderr: ${result.stderr}`);
|
||||
assert.strictEqual(result.stdout, '', 'Blocked hook should not echo raw input');
|
||||
assert.ok(
|
||||
result.stderr.includes('BLOCKED: Modifying .eslintrc.js is not allowed.'),
|
||||
`Expected block message, got: ${result.stderr}`
|
||||
);
|
||||
} finally {
|
||||
try {
|
||||
fs.rmSync(tmpDir, { recursive: true, force: true });
|
||||
} catch {
|
||||
// best-effort cleanup
|
||||
}
|
||||
}
|
||||
})
|
||||
)
|
||||
passed++;
|
||||
else failed++;
|
||||
|
||||
if (
|
||||
test('still blocks writes to an existing protected config file', () => {
|
||||
const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'ecc-config-protect-'));
|
||||
try {
|
||||
const absPath = path.join(tmpDir, '.eslintrc.js');
|
||||
fs.writeFileSync(absPath, 'module.exports = { rules: {} };');
|
||||
|
||||
const input = {
|
||||
tool_name: 'Edit',
|
||||
tool_input: {
|
||||
file_path: absPath,
|
||||
content: 'module.exports = { rules: { "no-console": "off" } };'
|
||||
}
|
||||
};
|
||||
|
||||
const result = runHook(input);
|
||||
assert.strictEqual(result.code, 2, 'Expected exit 2 when modifying an existing protected config');
|
||||
assert.strictEqual(result.stdout, '', 'Blocked hook should not echo raw input');
|
||||
assert.ok(result.stderr.includes('BLOCKED: Modifying .eslintrc.js is not allowed.'), `Expected block message, got: ${result.stderr}`);
|
||||
} finally {
|
||||
try {
|
||||
fs.rmSync(tmpDir, { recursive: true, force: true });
|
||||
} catch {
|
||||
// best-effort cleanup
|
||||
}
|
||||
}
|
||||
})
|
||||
)
|
||||
passed++;
|
||||
else failed++;
|
||||
|
||||
if (
|
||||
test('legacy hooks do not echo raw input when they fail without stdout', () => {
|
||||
const pluginRoot = path.join(__dirname, '..', `tmp-runner-plugin-${Date.now()}`);
|
||||
const scriptDir = path.join(pluginRoot, 'scripts', 'hooks');
|
||||
const scriptPath = path.join(scriptDir, 'legacy-block.js');
|
||||
|
||||
try {
|
||||
fs.mkdirSync(scriptDir, { recursive: true });
|
||||
fs.writeFileSync(scriptPath, '#!/usr/bin/env node\nprocess.stderr.write("blocked by legacy hook\\n");\nprocess.exit(2);\n');
|
||||
|
||||
const rawInput = JSON.stringify({
|
||||
tool_name: 'Write',
|
||||
tool_input: {
|
||||
file_path: '.eslintrc.js',
|
||||
content: 'module.exports = {};'
|
||||
}
|
||||
});
|
||||
|
||||
const result = runCustomHook(pluginRoot, 'pre:legacy-block', 'scripts/hooks/legacy-block.js', rawInput);
|
||||
assert.strictEqual(result.code, 2, 'Expected failing legacy hook exit code to propagate');
|
||||
assert.strictEqual(result.stdout, '', 'Expected failing legacy hook to avoid raw passthrough');
|
||||
assert.ok(result.stderr.includes('blocked by legacy hook'), `Expected legacy hook stderr, got: ${result.stderr}`);
|
||||
} finally {
|
||||
try {
|
||||
fs.rmSync(pluginRoot, { recursive: true, force: true });
|
||||
} catch {
|
||||
// best-effort cleanup
|
||||
}
|
||||
}
|
||||
})
|
||||
)
|
||||
passed++;
|
||||
else failed++;
|
||||
}
|
||||
})) passed++; else failed++;
|
||||
|
||||
console.log(`\nResults: Passed: ${passed}, Failed: ${failed}`);
|
||||
process.exit(failed > 0 ? 1 : 0);
|
||||
|
||||
@@ -366,6 +366,66 @@ function runTests() {
|
||||
})) passed++;
|
||||
else failed++;
|
||||
|
||||
// ── hookSpecificOutput JSON on stdout ──
|
||||
// Claude Code 2.1+ drops non-blocking PreToolUse stderr; the suggestion has
|
||||
// to ride on stdout as { hookSpecificOutput: { additionalContext } } to reach
|
||||
// the model. These tests pin that contract.
|
||||
console.log('\nhookSpecificOutput stdout JSON:');
|
||||
|
||||
if (test('emits hookSpecificOutput.additionalContext on stdout at threshold', () => {
|
||||
const { sessionId, counterFile, cleanup } = createCounterContext();
|
||||
cleanup();
|
||||
fs.writeFileSync(counterFile, '49');
|
||||
const result = runCompact({ CLAUDE_SESSION_ID: sessionId });
|
||||
assert.strictEqual(result.code, 0, 'Should exit 0');
|
||||
assert.ok(result.stdout.trim().length > 0, `Expected stdout payload at threshold. Got: "${result.stdout}"`);
|
||||
const parsed = JSON.parse(result.stdout);
|
||||
assert.strictEqual(parsed.hookSpecificOutput.hookEventName, 'PreToolUse',
|
||||
`hookEventName should be PreToolUse. Got: ${JSON.stringify(parsed)}`);
|
||||
assert.ok(parsed.hookSpecificOutput.additionalContext.includes('50 tool calls reached'),
|
||||
`additionalContext should include threshold text. Got: ${parsed.hookSpecificOutput.additionalContext}`);
|
||||
cleanup();
|
||||
})) passed++;
|
||||
else failed++;
|
||||
|
||||
if (test('emits hookSpecificOutput.additionalContext on stdout at +25 interval', () => {
|
||||
const { sessionId, counterFile, cleanup } = createCounterContext();
|
||||
cleanup();
|
||||
// threshold=3, set counter to 27 → next run = 28 → 28-3=25 → interval hit
|
||||
fs.writeFileSync(counterFile, '27');
|
||||
const result = runCompact({ CLAUDE_SESSION_ID: sessionId, COMPACT_THRESHOLD: '3' });
|
||||
assert.strictEqual(result.code, 0, 'Should exit 0');
|
||||
assert.ok(result.stdout.trim().length > 0, `Expected stdout payload at interval. Got: "${result.stdout}"`);
|
||||
const parsed = JSON.parse(result.stdout);
|
||||
assert.strictEqual(parsed.hookSpecificOutput.hookEventName, 'PreToolUse');
|
||||
assert.ok(parsed.hookSpecificOutput.additionalContext.includes('28 tool calls'),
|
||||
`additionalContext should include count. Got: ${parsed.hookSpecificOutput.additionalContext}`);
|
||||
cleanup();
|
||||
})) passed++;
|
||||
else failed++;
|
||||
|
||||
if (test('emits no stdout below threshold (silent)', () => {
|
||||
const { sessionId, cleanup } = createCounterContext();
|
||||
cleanup();
|
||||
const result = runCompact({ CLAUDE_SESSION_ID: sessionId, COMPACT_THRESHOLD: '5' });
|
||||
assert.strictEqual(result.code, 0);
|
||||
assert.strictEqual(result.stdout.trim(), '',
|
||||
`Expected empty stdout below threshold. Got: "${result.stdout}"`);
|
||||
cleanup();
|
||||
})) passed++;
|
||||
else failed++;
|
||||
|
||||
if (test('still writes [StrategicCompact] to stderr (debug log retained)', () => {
|
||||
const { sessionId, counterFile, cleanup } = createCounterContext();
|
||||
cleanup();
|
||||
fs.writeFileSync(counterFile, '49');
|
||||
const result = runCompact({ CLAUDE_SESSION_ID: sessionId });
|
||||
assert.ok(result.stderr.includes('[StrategicCompact]'),
|
||||
`stderr should retain [StrategicCompact] for debug log capture. Got: "${result.stderr}"`);
|
||||
cleanup();
|
||||
})) passed++;
|
||||
else failed++;
|
||||
|
||||
// ── Round 64: default session ID fallback ──
|
||||
console.log('\nDefault session ID fallback (Round 64):');
|
||||
|
||||
|
||||
Reference in New Issue
Block a user