feat+test+docs: D45 — server.mjs auth integration + lib/audit.mjs (#21)

* feat+test+docs: D45 — server.mjs auth integration + lib/audit.mjs (Phase 2 wire-up)

Second Phase 2 implementation D-day. Wires the D44 lib/keys.mjs identity
layer into the request flow + lands lib/audit.mjs per ADR 0007 § 6.2
+ § 8.

Closes ADR § 10 acceptance criteria #1 (per-key cache isolation), #2
(anonymous prod-default off), #3 (anonymous dev-mode on), #6 (post-revoke
401 within next request — full coverage with D45), #8 (audit ndjson
round-trip), #10 (OLP_OWNER_TOKEN env override — full server-side
coverage), #11 (providers_enabled 403 scope). Owner-vs-guest gating for
/health + X-OLP-Fallback-Detail (criteria #4, #5) remains in D46 scope.

NEW lib/audit.mjs (~110 lines):

  - appendAuditEvent(event, opts): one JSON event per line to
    ~/.olp/logs/audit.ndjson (file 0600, dir 0700). § 6.2 retry: warn +
    1 retry; per-process drop counter + warn on second failure; NEVER
    throws. Per-call OLP_HOME env resolution (matches lib/keys.mjs).
  - getAuditDropCount(): for future /health surface.

lib/keys.mjs extended:

  - loadAuthConfigSync({ olpHome }): reads auth block from
    ~/.olp/config.json with ADR § 7.2 defaults (allow_anonymous: false,
    owner_only_endpoints: ['/health'], fallback_detail_header_policy:
    'owner_only'). Never throws; missing file / malformed JSON falls
    back to defaults.
  - _resolveOlpHome(opts): precedence opts.olpHome → process.env.OLP_HOME
    → ~/.olp. Per-call resolution so tests + operator deployments can
    redirect without code edits.

server.mjs auth middleware integration:

  - extractToken(req): parses Authorization Bearer / x-api-key.
  - authenticate(req): validateKey + 401 paths (auth_required vs
    invalid_or_revoked_key).
  - isProviderEnabled(olpIdentity, providerKey): '*' = all; else
    array allowlist.
  - _authConfig loaded at startup; warn auth_allow_anonymous_enabled
    when true. Test seams __setAuthConfig / __resetAuthConfig.
  - handleChatCompletions + handleModels both gated by authenticate at
    top. Audit ctx built throughout; res.on('finish') appends row +
    fires touchLastUsed async.
  - IDENTITY-VS-CREDENTIALS SEPARATION: olpIdentity (new validated
    identity) consumed for cache namespacing + providers_enabled +
    audit; authContext passed to provider.spawn() REMAINS null so
    providers continue their own credential discovery (env / keychain
    / file). Per-provider per-key credential mapping is Phase 3+ per
    ADR § 12.
  - handleChatCompletions chain filtered by isProviderEnabled; empty
    result returns 403 key_no_provider_access.
  - keyId = olpIdentity.keyId (replacing hardcoded '__anonymous__').
  - Audit captures fields throughout: post-auth, post-IR, post-chain
    (success or exhausted). Status + latency populated on
    res.on('finish').

TESTS — Suite 20, +15 (499 → 514):

  20a-d: header parsing + valid key happy paths (Bearer / x-api-key /
    invalid → 401)
  20e: revoked key 401 (criterion #6 end-to-end)
  20f: OLP_OWNER_TOKEN env override returns 200 (criterion #10 full)
  20g: allow_anonymous=true + no header returns 200 (criterion #3)
  20h + 20h-extra: providers_enabled=['mistral'] for anthropic model →
    403; '*' baseline returns 200 (criterion #11)
  20i: per-key cache namespace isolation (criterion #1 end-to-end)
  20j + 20j-401: audit.ndjson written with § 8 schema fields + PII
    guard; 401 path also appends (criterion #8)
  20k: filesystem key last_used_at populated post-request (D45 touch
    wire)
  20l + 20l-200: /v1/models also enforces auth

TEST-MODE SETUP (test-features.mjs):

  - process.env.OLP_HOME = mkdtempSync(...) at module load so audit +
    key writes don't pollute ~/.olp/.
  - __setAuthConfig({ allow_anonymous: true }) after server.mjs imports
    so pre-D45 HTTP integration tests (Suite 18 etc.) continue to pass.
  - Suite 20 explicitly overrides __setAuthConfig per-case to exercise
    production-default-off coverage.

DOCUMENTATION:

  - AGENTS.md: lib/keys.mjs 🟡 marker updated + NEW lib/audit.mjs entry;
    Implementation-status-note + shipped-set updated.
  - README.md: Implementation Status table gains lib/audit.mjs row +
    lib/keys.mjs row updated; Known limitations Multi-key auth note
    rewritten to reflect D45 ship + D46 follow-up; new env-vars
    (OLP_HOME, OLP_OWNER_TOKEN) and auth config block surfaced.
  - CHANGELOG.md: D45 entry under Unreleased per release_kit overlay
    phase_rolling_mode discipline.

AUTHORITY:

  - ADR 0007 (multi-key auth — §§ 5/6.2/7/9.4 implementation
    contracts + § 10 criteria #1/#2/#3/#6/#8/#10/#11 covered).
  - CLAUDE.md release_kit overlay phase_rolling_mode — under
    Unreleased.
  - Phase 2 kickoff handoff (~/.cc-rules/memory/handoffs/
    2026-05-25-phase-2-kickoff.md in cc-rules d9da966).
  - Standing autopilot grant (~/.cc-rules/memory/auto/
    standing_autopilot_phase_2.md in cc-rules bf0ed9a).

Verified: 514/514 pass via npm test (no regression in 499 existing
tests; 15 new Suite 20 tests all green).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix+test+docs: D45 fold-in — CI fail recovery + opus reviewer P1/P2/P3

Fresh-context opus reviewer (PR #21) returned APPROVE_WITH_MINOR with 4
findings; CI Node 24 separately reported 9 Suite 20 failures (all
200-expecting tests). Root cause of CI: Suite 20 setup did not stub
CLAUDE_CODE_OAUTH_TOKEN before mock spawn, so anthropic.mjs AUTH_MISSING
pre-check fired and tests 502'd. (Local Node 22 had the env from the
maintainer's claude install — masked the gap.)

CI FIX — Suite 20 OAuth env stub

  Added ensureSuite20FakeOAuth / restoreSuite20OAuth helpers in
  makeSuite20Server / teardownSuite20. Matches the existing pattern in
  Suite 9 line ~2154 (test-fake-oauth-token-for-cache-tests).

P1 — Real-streaming path audit fidelity

  Single-hop streaming success (server.mjs ~L1050, the most common
  deployed shape) did not populate auditCtx.provider / tried_providers
  / cache_status. Audit rows for streaming requests carried
  provider: null. Fixed by stamping these at the top of the streaming
  branch and amending error_code on the two streaming failure exit
  paths (streaming_error_after_first_chunk +
  streaming_error_before_first_chunk).

  New regression test 20j-stream: streaming request asserts the audit
  row's provider, cache_status, and tried_providers fields are
  populated.

P2 — Global test tmpdir cleanup

  process.env.OLP_HOME = mkdtempSync(...) at test-features.mjs module
  load left /var/folders/.../olp-test-home-* leak per npm test run.
  Fixed by process.on('exit', () => rmSync(_GLOBAL_TEST_OLP_HOME)).
  Best-effort; swallows errors so exit handler never throws.

P3 — handleModels 401 lacks OLP diagnostic headers

  handleChatCompletions 401 passes olpErrorHeaders({ startMs });
  handleModels 401 did not. Aligned.

DEFERRED — P2 tried_providers semantics on 403

  Reviewer noted that key_no_provider_access 403 stamps original chain
  in tried_providers, but the field name implies hops actually
  dispatched. Either ADR § 8 amendment or D46+ semantic fix. Marked
  in CHANGELOG; not in this fold-in scope.

Test count: 514 → 515 (+1 streaming-audit regression test 20j-stream;
14 existing Suite 20 tests still pass). Verified locally via
npm test. CI Node 24 recovery via the OAuth env stub.

Authority: PR #21 fresh-context opus reviewer findings; CI Node 24
run 26382758946 failure logs; CLAUDE.md release_kit overlay
phase_rolling_mode — under Unreleased.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

---------

Co-authored-by: dtzp555 <dtzp555@gmail.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
dtzp555-max
2026-05-25 14:28:45 +10:00
committed by GitHub
co-authored by taodeng Claude Opus 4.7
parent 4b9916341b
commit 40064955ab
7 changed files with 989 additions and 16 deletions
+7 -2
View File
@@ -182,7 +182,8 @@ Phase 1 is closed at v0.1.1 (multi-provider proxy core + pre-Phase-2 cleanup). P
| Soft trigger data path (`quotaStatus()` polling) | 📋 Planned (v1.x) | Evaluation logic shipped + tested; data ingestion deferred per ADR 0004 Amendment 2 |
| `models-registry.json` | ✅ Shipped | SPOT for `(provider, model)` metadata |
| `test-features.mjs` | ✅ Shipped | Comprehensive test suite covering IR, cache, fallback, and integration paths (CI: `test.yml`) |
| `lib/keys.mjs` | 🟡 Phase 2 — core landed (D44) | Multi-key auth core (`createKey` / `validateKey` / `listKeys` / `revokeKey` / `touchLastUsed`) per ADR 0007 §§ 5/6.1/6.3/6.3.5/6.4/9.4. Atomic manifest writes + per-key write-lock + revoke-dominates-touch + env override. `server.mjs` integration scheduled D45; audit ndjson + keygen CLI surface follow. |
| `lib/keys.mjs` | 🟡 Phase 2 — core + server integration (D44 + D45) | Multi-key auth core (`createKey` / `validateKey` / `listKeys` / `revokeKey` / `touchLastUsed`) per ADR 0007 §§ 5/6.1/6.3/6.3.5/6.4/9.4 + `loadAuthConfigSync` for `auth.allow_anonymous` (default false). Server wires `validateKey` per request, filters chain by `providers_enabled`, fires `touchLastUsed` post-response. D46 will add owner-vs-guest gating for `/health` + `X-OLP-Fallback-Detail`. |
| `lib/audit.mjs` | 🟡 Phase 2 — shipped at D45 | Append-only ndjson audit at `~/.olp/logs/audit.ndjson` per ADR 0007 § 6.2 + § 8. `appendAuditEvent` fires for every `/v1/*` request (success, 401, 403, 5xx). Warn + 1 retry on append failure; no memory buffer at Phase 2 (forward path). PII excluded (no message / response content). `OLP_HOME` env override supported for test/operator isolation. |
| `dashboard.html` | 📋 Planned (Phase 6) | Owner-only multi-provider dashboard |
| `docs/provider-caveats.md` | 📋 Planned (Phase 3+) | Lossy-translation reference; for now documented inline in each plugin header |
| `docs/openai-spec-pin.md` | ✅ Shipped (D30) | OpenAI spec snapshot for annual audit; v0.1 baseline pinned 2026-05-24 |
@@ -196,7 +197,11 @@ Behaviors that work correctly at personal/family scale but have ratified follow-
- **Streaming-path singleflight not implemented.** The cache layer's D4 singleflight (one spawn per identical concurrent request) is fully wired on the buffered path but NOT on the streaming path. N concurrent identical streaming requests at v0.1 will each spawn their own CLI process. Design ratified in [ADR 0005 Amendment 8](./docs/adr/0005-cache-cross-provider.md); implementation tracked via [issue #16](https://github.com/dtzp555-max/olp/issues/16) and [v1.x roadmap #1](./docs/v1x-roadmap.md). At family scale this is observably fine — every caller still receives the correct response; the cost is N CLI processes instead of one.
- **Soft triggers configured but inert.** `routing.soft_triggers` in `~/.olp/config.json` is honored by the engine's evaluation logic but `quotaStatus()` polling is not wired (ADR 0004 Amendment 2). A startup warning fires if the field is non-empty so the inert state is visible.
- **Multi-key auth core landed, server integration pending.** `lib/keys.mjs` core (createKey / validateKey / listKeys / revokeKey / touchLastUsed) shipped at D44 per ADR 0007. All requests at v0.1.1 / D44 still share the cache namespace `__anonymous__` because `server.mjs` integration is scheduled for D45 — until that lands, the identity layer exists in-tree but no request flow consults it. Phase 2 in progress through D45 (server wire-up), D46 (owner gating), D47 (E2E + multi-key fixtures), Phase 2 close → v0.2.0. Tracked in [v1.x roadmap #2](./docs/v1x-roadmap.md).
- **Multi-key auth shipped through server integration (D45); owner gating pending D46.** `lib/keys.mjs` core (createKey / validateKey / listKeys / revokeKey / touchLastUsed) shipped at D44; `server.mjs` now invokes `validateKey` per request, filters the chain by `providers_enabled`, fires `touchLastUsed` post-response, and appends an audit row to `~/.olp/logs/audit.ndjson` for each `/v1/*` request. The owner-vs-guest gating for `/health` payload trimming and `X-OLP-Fallback-Detail` header suppression is scheduled D46. Phase 2 in progress through D46 (owner gating), D47+ (keygen CLI surface, docs), Phase 2 close → v0.2.0. Tracked in [v1.x roadmap #2](./docs/v1x-roadmap.md).
**New env vars consumed at D45:** `OLP_HOME` (override `~/.olp/` location, used by tests + operator deployments); `OLP_OWNER_TOKEN` (synthetic env-owner identity for headless / CI deployments — bypasses filesystem manifest lookup with stable `__env_owner__` keyId).
**New config block consumed at D45:** `config.json auth.{ allow_anonymous, owner_only_endpoints, fallback_detail_header_policy }`. Default `allow_anonymous: false` (production-off); set true to accept requests without an OLP API key (development / single-user dev mode). Startup emits a warn when `allow_anonymous: true` so the relaxed posture is observable.
- **Provider-level `cacheKeyFields` mask not implemented.** Cache keys include every IR field including ones individual plugins drop at spawn (e.g., Anthropic plugin drops `temperature`). Spurious cache misses possible (extra spawn cost; never spurious hits). Conservative posture documented in [ADR 0005 Amendment 7](./docs/adr/0005-cache-cross-provider.md). Tracked in [v1.x roadmap #5](./docs/v1x-roadmap.md).
---