Commit Graph

2 Commits

Author SHA1 Message Date
Diego Rodrigues de Sa e Souza
3d4f3e4960 test(infra): retry recursive temp-dir removal instead of failing a shard on ENOTEMPTY (#11966) (#11968)
* test(infra): retry recursive temp-dir removal instead of failing a shard on ENOTEMPTY (#11966)

Two shards on release/v3.8.51 went red in one day with the same signature —
"ENOTEMPTY, Directory not empty: /tmp/omniroute-<test>-XXXXXX" — from
combo-same-provider-cascade (Unit Tests fast-path 4/4, on a PR that touches only
.github/) and auth-policy-embeddings-webfetch-7785 (the 20k-test TIA step). Both pass
alone and on re-run: the cleanup races something still writing into the directory
(SQLite WAL/-shm checkpoint, a worker, the backup) and under a loaded hosted runner
the window opens. 1154 test files do their own cleanup with
fs.rmSync(dir, { recursive: true, force: true }); 57 already asked for retries.

One-shot codemod (scripts/ad-hoc/codemod-rm-maxretries.mjs, kept for the record):
every rm / rmSync / rmdirSync option object with `recursive: true` and no
`maxRetries` gains `maxRetries: 5, retryDelay: 100` — Node itself then retries
ENOTEMPTY/EBUSY/EPERM for up to ~0.5 s before giving up. 2243 call sites in 1292
files under tests/, the shared tests/_setup/isolateDataDir.ts exit hook included.
Only the option object changes: no call site, assertion or import is touched.

Validation: prettier and ESLint (with the frozen suppressions) clean on all 1292
files; a random 20-file sample runs green (quota-redis-store hangs identically on
the untouched tree — it needs a Redis on localhost, an environment matter). The
four unit shards on this PR are the full run.

* fix(quality): let check-forgotten-sibling-tests read a 1,000-file diff

The gate shells out to `git diff` through execFileSync with Node's default 1 MB
maxBuffer; the 1,292-file codemod in this PR is the first diff large enough to
overflow it, and the gate died with `spawnSync git ENOBUFS` before comparing
anything. 64 MB is far above any real PR and costs nothing when unused.
2026-08-29 01:17:40 -03:00
Moseyuh333
eeec4d9e87 feat(chaos): big update - optimize, fix bugs, add features, enhance UX (#6728)
* feat(chaos): add Chaos Mode — multi-model parallel/collaborative execution

- New DB column chaos_mode_enabled on api_keys table
- API key create/PATCH routes support chaosModeEnabled toggle
- Core library src/lib/chaos/chaosConfig.ts for persistent config
- API routes: GET/PUT/DELETE /api/chaos/config
- Chaos execution POST /api/skills/collect/chaos with key auth
- Dashboard page at /dashboard/chaos with full config UI
- Sidebar entry in Agentic Features section
- Chaos mode toggle in API Key editor permissions panel
- i18n keys for chaos config (en.json)

* feat(chaos): big update — optimize, fix bugs, add features

=== Changes ===

1. NEW: src/lib/chaos/chaosExecutor.ts — shared execution engine
   - Removed ~150 lines of duplicate dispatch logic between two API routes
   - Single executeChaosRun() function used by both endpoints
   - Added concurrency limit (max 10 parallel requests)
   - Added proper TypeScript interfaces (ChaosRunInput, ChaosRunResult)
   - Added error logging throughout

2. FIX: src/app/api/skills/collect/chaos/route.ts
   - Was MISSING logger import (log.error was undefined at runtime)
   - Reduced from 388 lines → 142 lines by delegating to shared executor
   - Added maxTokens support in schema validation

3. REFACTOR: src/app/api/chaos/run/route.ts
   - Simplified to thin wrapper: auth + validate + delegate to executor
   - Added maxTokens support

4. ENHANCE: src/lib/chaos/chaosConfig.ts
   - Added maxTokens config field (256-128k, default 4096)
   - Persisted per-instance via settings table

5. ENHANCE: UI — ChaosConfigPageClient.tsx
   - Loads available providers from /api/models for dropdown autocomplete
   - Added datalist-based provider selector in overrides section
   - Added Max Tokens configuration input
   - Added expandable provider list showing all detected providers
   - Fixed duplicate override detection

* fix(chaos): fetch providers from /api/providers instead of /api/keys

* fix(chaos): remove dead code isOverrideDuplicate, fix maxTokens fallback to include global config

* fix(chaos): resetConfig now shows error on HTTP failure (was silent)

* feat(dashboard): Chaos Mode — multi-model parallel/collaborative execution

Splits the PR down to only the genuinely new Chaos Mode feature (drops the
duplicate Skill Collector/GitHub-discovery portion already shipped via
#6186). Replaces the loopback fetch() dispatch (hardcoded to the wrong port)
with the established in-process synthetic-Request/route-handler pattern used
by src/lib/batches/dispatch.ts, moves settings persistence off raw SQL, and
adds unit test coverage for chaosConfig, chaosExecutor and the 3 chaos API
routes.

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

* fix(chaos): fix external Bearer-auth bypass and stale config cache in tests

validateApiKey() returns a plain boolean for both the deployment-time env key
and a DB-backed key, so branching on `keyInfo === true` in
verifyChaosKey() (src/app/api/skills/collect/chaos/route.ts) treated every
valid API key as having full env-key access, silently skipping the
chaosModeEnabled permission check entirely. Now always resolves through
getApiKeyMetadata() and only bypasses the per-key check for the synthesized
env-key record (id: "env-key").

Also exports invalidateChaosConfigCache() from chaosConfig.ts and wires it
into the route tests' resetStorage() — the in-process config cache was
surviving DB resets between tests, causing state to leak across cases.

Fixes CHANGELOG-eat from the release merge (re-inserted the Chaos Mode
bullet against the base CHANGELOG.md, verified additive via
check-changelog-integrity.mjs) and re-syncs against release/v3.8.47 tip.

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

* docs(changelog): Chaos Mode overhaul bullet referencing #6728 after release sync

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

* fix(merge): restore #6126 clinepass files reverted by release auto-resolve + baseline re-merge

The release sync's auto-resolve reverted sibling PR #6126's clinepass work
(registry, catalog, oauth constants, clineAuth.ts, token-refresh case, tests)
and the file-size baseline — all outside this PR's scope. Restored to the
release versions, re-applied only this PR's own baseline entries, restored the
#6126 CHANGELOG bullet (re-inserting only this PR's own).

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

* fix(dashboard): chaos client hook must not import the server Pino logger

useChaosConfigData ("use client") pulled @/sse/utils/logger → shared Pino →
logRotation/dataPaths → node:fs into the browser bundle, breaking next build
(Turbopack: Can't resolve 'fs') — caught by the DAST smoke's isolated build.
console.error matches every other dashboard client component.

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

* test(api-manager): align switch-count invariant with the extracted toggle components

The Self-service block now renders 4 inline switches; the #5731 quota-bypass
and #6728 chaos-access toggles were extracted into dedicated components. The
type="button" invariant is preserved AND extended: the test now also asserts
each extracted component's switches declare type="button".

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

* chore(sync): merge release tip + restore own CHANGELOG bullet

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

---------

Co-authored-by: Moseyuh333 <Moseyuh333@users.noreply.github.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com>
2026-07-09 23:49:48 -03:00