mirror of
https://github.com/dtzp555-max/olp.git
synced 2026-07-21 21:15:10 +00:00
taodengandClaude Opus 4.7
994568a8fb
ADR 0002 Amendment 1 declared `hints.maxConcurrent` declarative-only at
v0.1 — type-validated at startup but with no runtime enforcement.
D38 wires the runtime enforcement via a per-provider in-flight spawn
counter with immediate-advancement on saturation.
Design choice: **immediate-advancement via fallback engine** (queue +
timeout DEFERRED). When a provider is at its maxConcurrent limit, the
spawn call synchronously fails with a new `CONCURRENCY_LIMIT` error
code; the fallback engine treats this as a hard trigger and advances
to the next chain hop. If the entire chain is saturated, the user
sees a chain-exhausted error (existing path).
Rationale for immediate-advancement over queue+timeout:
1. The fallback chain exists precisely for this kind of overflow —
adding a queue layer would duplicate the advancement semantics.
2. Queue + timeout adds new config surface (timeout duration, queue
depth bounds, queue eviction policy) that isn't needed at the
personal/family scale OLP serves.
3. Head-of-line blocking risk: a long-running spawn would stall
queued requests behind it even though other providers in the chain
could serve them immediately.
4. Fail-fast latency aligns with the multi-provider proxy philosophy
("spread risk across providers, not within a provider").
Queue + timeout is deferred to a v1.x design ADR if real usage shows
demand. ADR 0002 Amendment 6 and ADR 0004 Amendment 4 capture the
decision explicitly.
Changes (8 files, +<delta>):
**Code**
1. **lib/providers/base.mjs** — add `CONCURRENCY_LIMIT` to
`PROVIDER_ERROR_CODES`. JSDoc clarifies the code is synthesised by
the orchestration layer, not thrown by provider plugins themselves.
2. **lib/providers/index.mjs** — new semaphore primitives:
- `tryAcquireSpawn(providerName, maxConcurrent)` — atomic
check-then-increment. Returns `true` on success, `false` if at
limit. Atomicity rests on the JS single-threaded invariant
(read + write synchronous, NO `await` between them); module-level
comment block warns future maintainers against breaking this.
- `releaseSpawn(providerName)` — decrement; throws on
under-decrement (defensive bug guard for missing acquire / double
release). Map.delete at zero for clean memory footprint.
- `getActiveSpawnCount(providerName)` — returns current count
(0 for unseen providers). For diagnostics + tests.
- `DEFAULT_MAX_CONCURRENT_SPAWNS = 4` — defense-in-depth fallback
matching the v0.1 plugin defaults (anthropic/codex/mistral all
declare hints.maxConcurrent: 4). Also coerces non-integer / NaN
/ negative inputs to the default.
- `__resetSpawnCounters()` — internal test seam.
3. **lib/fallback/engine.mjs** — `CONCURRENCY_LIMIT: true` added to
`HARD_TRIGGER_CODES`. `classifyTrigger` and `evaluateHardTriggers`
both pick it up via the same lookup. v0.1 live hard-trigger codes
are now 5 (was 4 post-D34): SPAWN_FAILED, CLI_NOT_FOUND,
AUTH_MISSING:false, SPAWN_TIMEOUT, CONCURRENCY_LIMIT.
4. **server.mjs** — gate the spawn call in handleChatCompletions at
BOTH spawn call sites:
- **Buffered path** (executeHopFn → collectAllChunks): acquire
before provider.spawn; on failure synthesise
`ProviderError(CONCURRENCY_LIMIT)` with providerName /
maxConcurrent / activeSpawns diagnostic fields and throw —
fallback engine catches and advances. On success, outer try/
finally wraps the inner D16 truncation-salvage try/catch so
releaseSpawn fires on EVERY exit path (return, D16 salvage
return, re-throw).
- **Streaming path** (single-hop real-SSE branch): acquire BEFORE
the streaming branch entry. If acquire fails, branch is skipped
and request falls through to buffered path (whose own gate
surfaces chain-exhausted for single-hop chains). If acquire
succeeds, existing streaming try/catch gains
`finally { releaseSpawn(streamProvider) }` — slot releases on
stop-chunk completion, generator exhaustion, abort, or any
exception path. `releaseSpawn` fires at END of stream
consumption, not when spawn() returns.
**Tests** (test-features.mjs): 431 → 447 (+16):
Suite 18 — D38 — maxConcurrent runtime enforcement:
- 18a: PROVIDER_ERROR_CODES.CONCURRENCY_LIMIT exists
- 18b: evaluateHardTriggers true for CONCURRENCY_LIMIT
- 18c: AUTH_MISSING regression guard (D38 did NOT flip it to hard)
- 18d.1-18d.4: semaphore unit (increment / saturate-no-increment /
release / map-delete-at-zero)
- 18e: tryAcquireSpawn returns false without side-effect when at limit
- 18f: releaseSpawn throws on under-decrement
- 18g.1-18g.2: DEFAULT_MAX_CONCURRENT_SPAWNS applied for invalid
inputs (undefined / NaN / negative / non-integer)
- 18h: __resetSpawnCounters clears state
- 18i: HTTP integration — 5 concurrent requests to single-hop
chain w/ maxConcurrent=2 → peak in-flight exactly 2, 2 succeed,
3 fail
- 18j: counter releases after buffered request (sequential test)
- 18k: 2-hop chain — saturated primary advances to fallback
- 18l: streaming counter releases at END of stream (not at spawn)
**ADR amendments**
5. **docs/adr/0002-plugin-architecture.md** — Amendment 6 added.
Removes "Declarative hint only at v0.1" caveat from the
`maxConcurrent` description in the Provider contract section.
Adds implementation reference + design-choice rationale (4 points).
Lists all exported symbols.
6. **docs/adr/0004-fallback-engine.md** — Amendment 4 added.
CONCURRENCY_LIMIT added to v0.1 hard-trigger taxonomy. Documents
synthesis-vs-plugin-thrown distinction. Documents first-chunk
safety (acquire before any res.write). v1.x re-evaluation triggers
named.
**CHANGELOG**
7. **CHANGELOG.md** — Unreleased sentinel replaced with proper D38
entry. Per CLAUDE.md release_kit phase_rolling_mode, this lands
under Unreleased; promotion to ## v0.1.1 happens at the v0.1.1
release. The D37 phase_rolling_mode gate now correctly fires if
anyone tags v0.1.x with this content present without promotion —
intentional.
Pre-commit fold-ins (per evidence-first checkpoint #4):
- **Reviewer Suggestion #1 (test 18c name mismatch)**: 18c is named
"classifyTrigger returns hard for CONCURRENCY_LIMIT" but body tests
AUTH_MISSING regression. Renamed header comment to
"AUTH_MISSING regression guard" and clarified that
CONCURRENCY_LIMIT classification is covered by 18b.
- **Reviewer Suggestion #3 (activeSpawns diagnostic field)**: server
.mjs:532 set `concurrencyErr.activeSpawns = maxConcurrent` (the
limit). Technically correct (since acquire just failed, live
count == limit) but confuses future readers. Changed to query
`getActiveSpawnCount(hopProvider)` directly. Added import of the
new symbol to the lib/providers/index.mjs import block.
- **Reviewer Suggestion #5 (ADR overstatement)**: ADR 0002 Amendment 6
said getActiveSpawnCount is "exported for /health, diagnostics,
and tests" but /health integration is not wired at D38. Reworded to
"exported for diagnostics and tests" + "/health integration
deferred — when surfaced there will land at providers.status.<name>
.activeSpawns; not wired at D38." Avoids overstating current state.
Two reviewer suggestions not folded:
- Suggestion #2 (streaming test 18l comment about branch entry
conditions) — low priority; the test passes and the branch is
taken (verified by reviewer). Future polish if confusion arises.
- Suggestion #4 (additional test for streaming-saturation → chain-
exhausted) — code path is straightforward and intentional; 18i
covers the buffered-path version directly. Defer.
Authority:
- ADR 0002 Amendment 1 (declarative-only caveat) — superseded by
Amendment 6
- ADR 0002 Amendment 6 (this commit) — runtime enforcement landed
- ADR 0004 Amendment 4 (this commit) — CONCURRENCY_LIMIT added to
v0.1 hard-trigger taxonomy
- GitHub issue #1 — closed by this commit
- CC 开发铁律 v1.6 § 10.x — independent fresh-context reviewer
- CLAUDE.md release_kit_overlay phase_rolling_mode — no version
bump; Unreleased entry written
Reviewer (Iron Rule v1.6 § 10.x Mode A, fresh-context opus,
independent of drafter): APPROVE. Critical depth checks:
- Atomicity in tryAcquireSpawn (lines 285-290 read+set with no
intervening await) — confirmed; module-level invariant comment
warns future maintainers
- Release on every exit path: buffered (outer finally wraps inner
try/catch covering D16 salvage return + normal return + re-throw);
streaming (try/finally covers stop-chunk return + loop exhaustion +
catch paths). No double-release path identified.
- Streaming release timing: fires in finally after res.end() at all
exit paths, never before stream consumption completes
- Counter leak: every code path traced — no orphan acquire identified
- 447/447 tests pass in reviewer's independent npm test run
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
157 lines
17 KiB
Markdown
157 lines
17 KiB
Markdown
# Changelog
|
||
|
||
All notable changes to OLP land here. Per `CLAUDE.md` release_kit overlay, this file is the source of truth for GitHub release notes.
|
||
|
||
## Unreleased
|
||
|
||
### D38 — maxConcurrent runtime enforcement (issue #1)
|
||
|
||
- **Spawn lifecycle gate** — `hints.maxConcurrent` is now enforced at runtime per ADR 0002 Amendment 6: `lib/providers/index.mjs` exports a per-provider `tryAcquireSpawn` / `releaseSpawn` / `getActiveSpawnCount` semaphore; `server.mjs` gates both the buffered and streaming spawn call sites in `handleChatCompletions` with a try/finally release. Saturation surfaces as `ProviderError(CONCURRENCY_LIMIT)` which the fallback engine treats as a hard trigger (ADR 0004 Amendment 4) — the chain advances to the next hop instead of queueing. If the entire chain is saturated, the user receives a chain-exhausted error via the existing exhaustion path. Closes #1. Queue+timeout deferred (see ADR 0002 Amendment 6 § Design choice). Test count 431 → 447.
|
||
|
||
## v0.1.0 — 2026-05-24
|
||
|
||
### Phase 1 Close — Multi-provider proxy core
|
||
|
||
**Overview.** Phase 1 delivers the OLP minimum-viable multi-provider proxy: OpenAI-compatible HTTP entry surface, plugin architecture for 3 Tier-D providers (Anthropic Claude / OpenAI Codex / Mistral Vibe), cache layer (D1 per-key isolation + D4 buffered-path singleflight + size cap + cacheable opt-out), fallback engine with first-chunk safety + spawn-timeout hard trigger + structured per-hop log observability, IR↔OpenAI translation honoring the Rule 2(b) no-invention constraint, and a 416-test suite covering all of it.
|
||
|
||
Released under `phase_rolling_mode` (CLAUDE.md release_kit overlay): 25 D-day commits accumulated on `main` between 2026-05-23 and 2026-05-24 before this version bump + tag.
|
||
|
||
**Provider posture.** Three Tier D plugins ship as **Candidate** (per ALIGNMENT.md § Provider Inventory) — runnable via `providers.enabled` config but not Enabled by default. Five additional Tier B/C plugin slots exist in `models-registry.json` as Speculative-Candidate / candidate stubs awaiting CLI authority pins. Zero Enabled providers at v0.1; transition to Enabled requires Phase audit + primary-source pin per ADR 0002.
|
||
|
||
### What landed (D10–D34 commit index)
|
||
|
||
The per-commit detail is in the git log; this index summarizes the deliverables.
|
||
|
||
**Phase 1 core hardening:**
|
||
- **D10** (`2cfd0b1`) — P1 round-3: providers.enabled config wiring + real SSE streaming on single-hop cache-miss + spawn-timeout hard trigger across all 3 plugins.
|
||
|
||
**Round-1 fold-in batch (cold audit caught 17 findings):**
|
||
- **D11** (`f659e29`) — ADR 0002 Amendment 1: `maxSpawnTimeMs` ratified into Provider contract hints.
|
||
- **D12** (`4b1a9c8`) — IR translator Rule 2(b) compliance: removed invented top-level `error` field on `chat.completion` shapes.
|
||
- **D13** (`f34b690`) — Per-hop `cache_control` bypass evaluation (was request-global).
|
||
- **D14** (`a7085d9`) — Defer `res.writeHead(200)` until first chunk; early-error returns 502 JSON instead of 200 empty SSE.
|
||
- **D15** (`8ae77c3`) — ADR 0005 Amendment 2: cache key includes `max_tokens` / `top_p` / `stop` / `tool_choice`.
|
||
- **D16** (`bafa6d1`) — ADR 0004 Amendment 1: SPAWN_FAILED-with-chunks salvage (don't discard partial responses).
|
||
- **D17** (`cb86807`) — Alias routing SPOT via `models-registry.json`; `getProviderForModel` canonicalizes.
|
||
- **D18** (`82ff007`) — `/v1/models` populated from registry; 5 standard X-OLP-* headers on error responses.
|
||
- **D19** (`ed82e65`) — Cleanup batch: finish_reason validator, dead alignment.yml KNOWN_PROVIDERS removal, unused imports.
|
||
- **D20** (`d85a2dc`) — Docs drift: README/AGENTS/ADR forward-references annotated `📋 Planned`.
|
||
|
||
**Round-2 fold-in batch (13 findings):**
|
||
- **D21** (`1466d3a`) — `validateProvider` enforces `maxSpawnTimeMs` contract field.
|
||
- **D22** (`e10b7d7`) — ADR 0004 Amendment 2: soft triggers deferred to v1.x.
|
||
- **D23** (`7ef5510`) — `hints.cacheable` opt-out + 10MB cache entry size cap (ADR 0002 Amendment 3, ADR 0005 Amendment 3).
|
||
- **D24** (`f8348ad`) — Spawn-timeout race fix: post-loop `if (spawnTimedOut) throw SPAWN_TIMEOUT` closes the rejectNext-null window across all 3 plugins.
|
||
- **D25** (`cd391b1`) — Round-2 P3 docs batch.
|
||
|
||
**Round-3 fold-in batch (13 findings):**
|
||
- **D26** (`a281d3e`) — Soft-trigger startup warning, stderr propagation on error-chunk SPAWN_FAILED (codex+mistral), anthropic D4-observation header, streaming truncation marker.
|
||
- **D27** (`c3ba751`) — IR validator response_format + tool_choice checks, ADR 0005 Amendment 4 (cache_control IR vs body), `/v1/models` alias surfacing.
|
||
- **D28** (`4a238c9`) — Per-hop log observability: `chain_id`, `trigger_type`, `ir_request_hash`, `next_provider` on all 8 fallback log events.
|
||
- **D29** (`de9f3ca`) — Suite 17 port-collision flake fix: 16 test sites switched to OS-assigned `listen(0)`.
|
||
- **D30** (`5119b42`) — README env vars correctness, `docs/openai-spec-pin.md` v0.1 baseline.
|
||
- **D31** (`d6347e3`) — ADR amendment trio: F5 (ADR 0003 Amendment 1 substitute test strategy), F11 (ADR 0005 Amendment 5 Anthropic wire limitation), F13+F14 (ALIGNMENT.md Speculative-Candidate exception class).
|
||
|
||
**Round-4 fold-in batch (10 findings):**
|
||
- **D32** (`30de965`) — Provider auth env vars in README, X-OLP-* on early-return paths, ADR 0002 Amendment 4 ratifying `contractVersion`, dead OUTPUT_PARSE_ERROR removal, codex parser inline assumption labels.
|
||
|
||
**Round-5 fold-in batch (12 findings):**
|
||
- **D33** (`f784fdb`) — ALIGNMENT mistral `--output streaming` pin correction, deterministic `function_call` ID (cache key stability), `/health` per-provider snapshot, fallback-hop cache-hit X-OLP-Cache correctness, `CLAUDE.md` `phase_rolling_mode` policy formalization, `/v1/models` stable `created` timestamps.
|
||
|
||
**Round-6 final batch (14 findings; 4 closed, 9 filed as issues):**
|
||
- **D34** (`60570ef`) — ADR 0005 Amendment 6 (streaming singleflight v1.x deferral), array-field cache key normalization (`tools:[]` / `stop:[]` now collide with omitted), QUOTA_EXHAUSTED + RATE_LIMITED dead code removal (ADR 0004 Amendment 3), ADR 0005 Amendment 7 (conservative cache-key v0.1 trade-off).
|
||
|
||
### ADRs in scope
|
||
|
||
- **ADR 0001** — Project founding (Phase 1 founding doc; no amendments)
|
||
- **ADR 0002** — Plugin architecture (4 amendments — `maxSpawnTimeMs`, `cacheable`, `contractVersion` ratifications)
|
||
- **ADR 0003** — IR design (1 amendment — `__irRoundTripTest` removal + substitute test strategy)
|
||
- **ADR 0004** — Fallback engine (3 amendments — SPAWN_FAILED salvage, soft trigger deferral, hard-trigger taxonomy narrowing)
|
||
- **ADR 0005** — Cache layer (7 amendments — cache key expansions, cache_control IR-vs-body, cacheable + size cap, Anthropic wire limitation, streaming singleflight deferral, conservative cache-key v0.1 trade-off)
|
||
- **ADR 0006** — Provider inclusion (Tier framework; no amendments)
|
||
- **ALIGNMENT.md** — Speculative-Candidate plugin Rule 4 exception class added (D31)
|
||
- **CLAUDE.md** — `phase_rolling_mode` overlay added (D33)
|
||
- **`docs/openai-spec-pin.md`** — v0.1 baseline pinned (D30)
|
||
|
||
### Test growth
|
||
|
||
277 (pre-D10) → 416 (post-D34). 6 cold audit rounds reviewed code against ADR claims. Iron Rule v1.6 § 10.x dual-mode review discipline (Diff Review + Cold Audit) caught 78+ findings of which ~50 closed via implementation and ~28 deferred to GitHub issues.
|
||
|
||
### Known limitations carried to v1.x
|
||
|
||
17 GitHub issues filed for follow-up. Notably:
|
||
- **Streaming singleflight** (#16) — multi-concurrent identical streaming requests each spawn fresh CLI; buffered path participates in D4, streaming path doesn't (deferred via ADR 0005 Amendment 6).
|
||
- **maxConcurrent runtime enforcement** (#1) — declarative-only at v0.1.
|
||
- **X-OLP-Fallback-Detail debug header** (#7) — documented in ADR 0004, never emitted.
|
||
- **Soft triggers** (per ADR 0004 Amendment 2) — evaluation code exists but `quotaStatus()` polling not wired; configured thresholds inert at v0.1.
|
||
|
||
### Migration from OCP
|
||
|
||
OLP supersedes OCP per ADR 0001. The `scripts/migrate-from-ocp.mjs` migration tool is 📋 Planned (Phase 7).
|
||
|
||
## v0.1.0-bootstrap — 2026-05-23
|
||
|
||
### Phase 0 — Repo bootstrap (founding + post-codex-review hardening)
|
||
|
||
This is the founding commit set of OLP (Open LLM Proxy), a personal- and family-scale multi-provider LLM proxy that supersedes OCP. The trigger was Anthropic's 2026-05-14 announcement (effective 2026-06-15) splitting `claude -p` / Agent SDK / third-party agent traffic out of the Pro/Max subscription pool into a separate fixed monthly Agent SDK Credit pool.
|
||
|
||
**What lands at v0.1.0-bootstrap (final state on `main` as of 2026-05-23):**
|
||
|
||
- `ALIGNMENT.md` — OLP constitution. Three concurrent authorities (per-provider CLI / OpenAI spec / IR contract), 5 Rules, 4-tier Risk Tier Framework, Candidate-vs-Enabled provider inventory, one-shot triggered audits (2026-06-16 Anthropic post-split; 90-day Antigravity primary-source pin).
|
||
- `AGENTS.md` — multi-tool agent guidelines (inherits `~/.cc-rules/AGENTS.md`).
|
||
- `CLAUDE.md` — Claude-Code-specific session instructions + machine-readable `release_kit` overlay (Iron Rule 5.5).
|
||
- `README.md` — phase-aware skeleton with Candidate-vs-Enabled provider tables, API endpoint table, environment-variables table, response-headers spec, architecture overview, phase plan, migration-from-OCP outline. Placeholder content marked as such per phase.
|
||
- `docs/adr/` — 6 founding ADRs:
|
||
- `0001-project-founding.md` — Mission, non-mission, narrow-scope supersession of OCP ADR 0005 (single-provider-sufficiency premise only; BYOK / no-spawn parts of ADR 0005 not inherited).
|
||
- `0002-plugin-architecture.md` — `lib/providers/<name>.mjs` plug-in model with the Provider contract (name / models / auth / spawn / estimateCost / quotaStatus / healthCheck / hints). 8 candidate providers declared, 0 Enabled at v0.1.
|
||
- `0003-intermediate-representation.md` — OLP-internal canonical IR between OpenAI-compat entry and provider plugins.
|
||
- `0004-fallback-engine.md` — Trigger taxonomy (Hard / Soft / Deterministic-deferred / Cost-aware-deferred), idempotent-failure safety (first-chunk rule), chain advancement one-at-a-time, observability headers.
|
||
- `0005-cache-cross-provider.md` — Cache key composition over `(provider, model, messages, ...)`, D1+D2+D3+D4 port from OCP v3.13.0.
|
||
- `0006-provider-inclusion.md` — 4-tier Risk Framework, Candidate-vs-Enabled distinction, 8-provider candidate classification, Antigravity Tier A (evidence-backed, pending primary-source pin) — exclusion rests on (named prohibition + no cost advantage + reinstatement friction) combination; primary-source URL not yet pinned, follow-up tracked.
|
||
- `.github/PULL_REQUEST_TEMPLATE.md` — 8-radio Change Type taxonomy + per-type Authority Evidence sections + Iron Rule 10 reviewer checklist.
|
||
- `.github/workflows/alignment.yml` — CI blacklist (transitive `api.anthropic.com/api/oauth/usage` from OCP 2026-04-11 drift; Antigravity provider exclusion enforcement) + `models-registry.json` validator + commit-citation soft check (process-substitution form, no Bash subshell trap).
|
||
- `.github/workflows/release.yml` — Auto-release on tag push with `package.json`-vs-tag version match check (Iron Rule 5).
|
||
- `.github/workflows/test.yml` — Node 20/24 matrix; tolerates bootstrap-phase absence of `test-features.mjs` AND `scripts.test`.
|
||
- `models-registry.json` — minimal v0.1 stub with empty `providers: {}`, matching the 0-Enabled posture; populated by Phase audits as providers transition Candidate → Enabled.
|
||
- `package.json` — minimal: no `main`, no `scripts.test`, no `scripts.start` (those entries land alongside the real files in Phase 1).
|
||
- `.gitignore`, `LICENSE` (MIT), `CHANGELOG.md` — standard project boilerplate.
|
||
|
||
**Provider posture at v0.1.0-bootstrap (per ALIGNMENT.md § Provider Inventory):**
|
||
|
||
| Tier | Anticipated providers | v0.1 default state |
|
||
|---|---|---|
|
||
| D (eligible-for-default-enabled) | Anthropic, OpenAI Codex, Mistral Vibe | Candidate (transition gate: authority pin + plugin + Phase audit) |
|
||
| C (opt-in) | xAI Grok, Moonshot Kimi | Candidate |
|
||
| B (opt-in + consent) | MiniMax, Zhipu GLM, Alibaba Qwen | Candidate |
|
||
| A (excluded by default; constitutional-amendment-only re-inclusion) | Google Antigravity | Excluded; pending primary-source pin |
|
||
|
||
**Total Enabled at v0.1.0-bootstrap: 0.** Enablement is a Phase audit deliverable, not a bootstrap claim. This explicit zero is intentional and codified — a constitution that names providers as "default-enabled" while their CLI versions, output shapes, auth artifacts, and exit-code semantics are still TBD would violate Rules 1 (Cite First) and 3 (Match the Implementation).
|
||
|
||
**Review history for this version:**
|
||
|
||
1. **Initial internal review (Claude Opus, fresh-context, Iron Rule 10).** Verdict: APPROVE_WITH_MINOR — 2 minor items (alignment.yml heredoc indent breaking bash parse on failure path; AGENTS.md cross-reference to ADR 0003 imprecise). Both folded in before the founding commit.
|
||
|
||
2. **External review #1 (OpenAI Codex CLI, no spec framing).** Verdict: 6 substantive findings beyond internal review.
|
||
- Provider Inventory split into Candidate vs Enabled (the v0.1 constitution had declared `anthropic` / `openai` / `mistral` as Tier D default-enabled while their Authority pins were still `TBD at Phase N spawn` — direct violation of Rule 1 / Rule 3 against the constitution's own text).
|
||
- Antigravity Tier A downgraded to "evidence-backed, pending primary-source pin" (secondary reports disagree on blast radius; Google FAQ URL not yet primary-source-pinned).
|
||
- ADR 0001 supersession scope narrowed (OLP rejects ADR 0005's "BYOK + no spawn" qualifiers, which originally applied to a commercial pivot; OLP is non-commercial and spawn-binary by design).
|
||
- Anthropic post-2026-06-15 one-shot audit scheduled (annual May 14 audit would leave Anthropic re-eval ~year late after the split takes effect).
|
||
- Tier A "permanent" language unified across docs (constitution and ADR 0006 had disagreed).
|
||
- OpenAI Tier D wording softened ("maintainer signal indicates low risk; formal ToS pin pending" — Discussion #8338 is a posture statement, not a formal ToS blessing).
|
||
|
||
3. **External review #2 (OpenAI Codex CLI, second pass after review #1 fold-in).** Verdict: 6 additional substantive findings — the self-consistency trap recurred when fold-in of review #1 was scoped only to files codex explicitly named. Round #2 caught:
|
||
- ADR 0002 still claimed "three default-enabled" while ALIGNMENT.md said zero Enabled — accepted ADR contradicting constitution.
|
||
- `release.yml` would publish stale `## v0.1.0-bootstrap` notes that ignored the "Unreleased" amendments — fixed by consolidating amendments into the v0.1.0-bootstrap section (this entry).
|
||
- `package.json` advertised `main` / `scripts.test` / `scripts.start` for files that don't exist — `npm test` / `npm start` failed locally. Removed all three; will return in Phase 1 alongside the real files.
|
||
- `models-registry.json` documented as SPOT but missing — minimal stub added.
|
||
- `alignment.yml` commit-citation soft check had a Bash subshell trap (`while` in pipe loses `WARN=1` mutation) — fixed via process substitution `< <(...)`.
|
||
- Tier A "permanent" wording still inconsistent across `alignment.yml` workflow text, ADR 0006 Consequences section, and the rest of the docs — unified throughout.
|
||
|
||
All 6 round-#2 findings folded in this consolidated v0.1.0-bootstrap state.
|
||
|
||
**Reviewer framing learning (recorded permanently in `~/.cc-rules/memory/learnings/ai_reviewer_self_consistency_trap.md`):** Internal AI reviewers framed on a shared source-of-truth miss bugs in the source-of-truth itself. The self-consistency trap recurred during the fold-in of round #1 — when an external reviewer surfaces findings, the fold-in must grep the entire repo for the same concept, not only edit the files the reviewer named. Round #2 caught what round #1's fold-in missed for exactly this reason. Both lessons updated in the cross-machine memory.
|
||
|
||
**Iron Rule 10 status:** Satisfied. Initial reviewer = internal opus (independent from drafters). Round #1 reviewer = external codex (independent from drafters and from internal opus). Round #2 reviewer = external codex (independent from the round #1 fold-in implementer). The maintainer's role across all three reviews was approver, not author. The drafting agents and fold-in agents were never the same as the reviewers for any of the three passes.
|
||
|
||
**Next:** Phase 1 lands `server.mjs` skeleton + IR + Anthropic provider plugin + cache D1+D4 port from OCP. At that point, `package.json` regains `main` + `scripts.test` + `scripts.start`, `test-features.mjs` lands, `models-registry.json` populates its first `providers.anthropic` entry, and Anthropic transitions Candidate → Enabled. Per spec §6 phase plan.
|