taodeng/olp
1
0
Fork 0
mirror of https://github.com/dtzp555-max/olp.git synced 2026-07-21 21:15:10 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
06f619120d0fb4b4bc4f4965862d4ad19e6753a8
olp/AGENTS.md
T
dtzp555-maxGitHubtaodengClaude Opus 4.7
 06f619120d feat+test+docs: D46 — owner-vs-guest gating for /health + X-OLP-Fallback-Detail (Phase 2) (#22) 
* feat+test+docs: D46 — owner-vs-guest gating for /health + X-OLP-Fallback-Detail (Phase 2)

Third Phase 2 implementation D-day. Closes ADR 0007 § 10 acceptance
criteria #4 (/health payload trimming for non-owner) + #5
(X-OLP-Fallback-Detail emission gating per fallback_detail_header_policy).
Phase 2 server surface now fully gated end-to-end; remaining D-days
are keygen CLI surface (D47+) and Phase 2 close (v0.2.0, maintainer-
triggered).

server.mjs handleHealth identity-aware payload per § 7.1:

  - Auth gate at top — 401 for unauth + allow_anonymous=false; 200
    with trimmed { ok, version } for non-owner; 200 with full payload
    for owner.
  - Trim controlled by _authConfig.owner_only_endpoints — operator
    removing /health from the list reverts to v0.1.1 full-payload-to-
    everyone (opt-out knob).
  - touchLastUsed fires on res.on('finish') for filesystem identities;
    no audit row on /health (high-volume monitoring; out of scope at
    Phase 2 per § 8).

server.mjs withFallbackDetailHeader identity-aware emission per § 7.2:

  - New shouldEmitFallbackDetailHeader(olpIdentity) helper reads
    _authConfig.fallback_detail_header_policy:
      'owner_only' (default) → emit only to owner
      'all'                  → emit unconditionally (v0.1.1 opt-back-in)
      'none'                 → suppress unconditionally
  - olpIdentity null on pre-auth paths → emit (preserves D40 v0.1.1
    behaviour for pre-auth errors where identity is unknown).
  - withFallbackDetailHeader signature gains 3rd `olpIdentity` arg;
    both call sites in handleChatCompletions updated.

Test surface — Suite 21, +9 tests; +1 in Suite 20 (20m); 515 → 524:

  20m: /health with no auth + allow_anonymous=false → 401
       (consistency with /v1/*)
  21a-d: /health payload trimming (criterion #4): anonymous trimmed;
         guest trimmed; owner full; owner_only_endpoints: [] opts out
  21e-h: X-OLP-Fallback-Detail emission gating (criterion #5):
         owner_only + guest → header absent
         owner_only + owner → header present + valid JSON
         'all' + guest → header present (v0.1.1 opt-back)
         'none' + owner → header absent (full suppression)
       Tests use 2-hop chain anthropic→openai with anthropic primary
       failing to produce non-empty fallbackDetail for header content.

Test-mode setup updated:

  Global __setAuthConfig({ allow_anonymous: true }) extended to also
  pass owner_only_endpoints: [] + fallback_detail_header_policy: 'all'
  so pre-D46 tests (Suite 18, F5 /health tests, D40 fallback-detail
  tests, etc.) continue to pass; Suite 21 overrides per-case.

DOCS:

  - AGENTS.md: lib/keys.mjs marker updated to reflect D46 ship; impl-
    status-note + shipped-set updated.
  - README.md: Implementation Status row + Known limitations "Multi-key
    auth" note rewritten to reflect D46 ship + remaining keygen CLI.
  - CHANGELOG.md: D46 entry under Unreleased per release_kit overlay.

AUTHORITY:

  - ADR 0007 §§ 7.1 + 7.2 implementation contracts + § 10 criteria
    #4 + #5 covered.
  - ADR 0004 Amendment 5 (D40 — "Phase 2 will re-introduce owner-vs-
    non-owner gating when lib/keys.mjs lands"): this D-day fulfils the
    deferral.
  - CLAUDE.md release_kit overlay phase_rolling_mode — under Unreleased.
  - Standing autopilot grant (~/.cc-rules/memory/auto/
    standing_autopilot_phase_2.md in cc-rules bf0ed9a).

Verified: 524/524 pass via npm test (no regression in 515 pre-D46
tests; 9 new Suite 21 tests + 1 new Suite 20m test all green).

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

* docs: D46 fold-in — opus reviewer P3 polish (constant import + comment tighten)

Fresh-context opus reviewer (PR #22) returned APPROVE_WITH_MINOR with 2 P3
findings, both trivial polish.

- server.mjs imports gain ENV_OWNER_KEY_ID from lib/keys.mjs (already
  used the namesake ANONYMOUS_KEY_ID import). handleHealth touchLastUsed
  guard now uses the imported constant for SPOT discipline.
- handleHealth audit-deferral comment tightened: removed the "§ 8 schema
  doesn't mandate auditing" phrasing (overstates the ADR — § 8 doesn't
  enumerate paths); replaced with the operational rationale (high-volume
  noise, no observability value until Phase 3 Dashboard).

No behaviour change. 524/524 tests pass (verified locally).

Authority: PR #22 fresh-context opus reviewer findings.

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>
2026-05-25 14:42:24 +10:00

89 lines
8.6 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
Inherits: @~/.cc-rules/AGENTS.md
# OLP — Open LLM Proxy — Agent Guidelines
**Scope**: the `dtzp555-max/olp` repository.
**Audience**: any AI coding agent (Claude Code / Cursor / OpenCode / Copilot / Codex / Gemini) touching OLP source.
---
## What this project is
OLP (Open LLM Proxy) is a personal- and family-scale multi-provider LLM proxy. It exposes a single OpenAI-compatible HTTP endpoint (`/v1/chat/completions`) and routes each request to one of N provider plugins, each of which spawns the corresponding provider CLI (e.g. `claude -p`, `codex exec --json`, `vibe --prompt`). An IR (Intermediate Representation) normalizes between the entry surface and each provider's native shape. Intelligent fallback chains advance one provider at a time on configured triggers; content-addressed caching minimizes quota consumption.
OLP supersedes OCP (Open Claude Proxy) as of v1.0. The trigger was the 2026-05-14 Anthropic announcement (effective 2026-06-15) splitting CLI/Agent SDK traffic out of the Pro/Max subscription pool — OCP's foundational assumption ("subscription = unlimited within rate limits") broke for Anthropic on that date. Spreading risk across multiple providers is the structural response.
OLP is **not** a commercial multi-tenant SaaS, **not** an enterprise gateway competing with LiteLLM/OpenCode/CLIProxyAPI on breadth, **not** a model-capability router ("route to the smartest model"), and **not** a conversation-state store (clients manage their own state). See `ALIGNMENT.md` Core Principle and `docs/adr/0001-project-founding.md`.
Runtime: Node.js (ESM, `.mjs` throughout). No build step. No bundler. `server.mjs` is the single executable entrypoint. The architecture is spawn-binary: OLP spawns the real provider CLI for every uncached request.
---
## Stack
- Node.js >=18, native ESM modules
- `http`/`https` built-ins for the proxy core (no Express, no Fastify)
- `models-registry.json` as the single source of truth for `(provider, model) → metadata` mappings (analogous to OCP's `models.json`; SPOT discipline will be codified in a Phase 1 ADR — OLP ADR 0003 is currently the IR design, not the SPOT codification)
- GitHub Actions for CI (`alignment.yml`, `release.yml`, `test.yml`)
- `gh` CLI assumed for PR creation and release automation
- No TypeScript. No test framework beyond `test-features.mjs` (run via `npm test`; CI workflow `.github/workflows/test.yml`). Keep dependencies minimal.
---
## Key files to know
- `server.mjs` — HTTP listener, entry surface (`/v1/chat/completions`, `/health`, `/v1/models`, etc.), plugin loader, request dispatch. Governed by `ALIGNMENT.md`.
- `lib/providers/` — per-provider plugins. Each file (`anthropic.mjs`, `openai.mjs`, `mistral.mjs`, …) implements the Provider contract documented in ADR 0002.
- `lib/ir/` — Intermediate Representation definition + serializers. Governed by ADR 0003.
- `lib/cache/` — content-addressed cache layer (per-key isolation, `cache_control` bypass, chunked stream replay, singleflight). Governed by ADR 0005.
- `lib/fallback/` — fallback engine (trigger detection, chain advancement, idempotent-failure safety, header annotation). Governed by ADR 0004.
- `lib/keys.mjs` — multi-key auth, per-key namespacing, identity layer. Carries OCP's per-key isolation model into OLP. **🟡 Phase 2 — D44 core + D45 server integration + D46 owner gating shipped (validateKey on every /v1/* + /health; chain filtered by providers_enabled; touchLastUsed fires post-response; /health payload trimmed for non-owner; X-OLP-Fallback-Detail gated by fallback_detail_header_policy). Remaining: keygen CLI bootstrap surface; Phase 2 close → v0.2.0.**
- `lib/audit.mjs` — append-only ndjson audit per ADR 0007 § 6.2 + § 8. **🟡 D45 — appendAuditEvent + getAuditDropCount shipped. Fires per /v1/chat/completions + /v1/models request including 401/403/5xx paths. Warn+1-retry on append failure; no memory buffer at Phase 2 (forward path).**
- `dashboard.html` — owner-only multi-provider dashboard (quota panels, fallback rate, cache hit rate). **📋 Planned (Phase 6) — not yet authored.**
- `models-registry.json` — single source of truth for `(provider, model) → metadata`. SPOT.
- `ALIGNMENT.md` — the constitution. Binding for any plugin / entry-surface / IR change.
- `docs/adr/` — Architecture Decision Records. Read the index in `docs/adr/README.md` before proposing governance, SPOT, or contract changes.
- `.github/workflows/alignment.yml` — CI blacklist grep + per-provider citation soft check; fails the build on known-hallucinated tokens.
- `CLAUDE.md` — Claude-Code-specific session instructions + `release_kit` overlay (Iron Rule 5.5).
**Implementation status note (as of 2026-05-25):** Files marked 📋 above are designed and documented but not yet on disk; files marked 🟡 are partially shipped (specific components landed; others scheduled). For the full status table see `README.md § "Implementation status"`. The shipped set as of D46 is: `server.mjs` (with Phase 2 auth middleware + audit wire + owner-vs-non-owner gating), `lib/ir/`, `lib/providers/{anthropic,codex,mistral}.mjs`, `lib/cache/{keys,store}.mjs`, `lib/fallback/engine.mjs`, `lib/keys.mjs` (core + loadAuthConfigSync — D44 + D45), `lib/audit.mjs` (D45), `models-registry.json`, `test-features.mjs` (Suites 19 + 20 + 21). Phase 2 in progress: keygen CLI bootstrap surface; Phase 2 close → v0.2.0 (maintainer-triggered).
---
## Project-specific constraints
- **`ALIGNMENT.md` is binding.** Any PR touching a provider plugin, the entry surface, or the IR must cite the relevant authority (provider CLI documentation / OpenAI spec URL / ADR number) in the commit body and PR description. See `CLAUDE.md` § "Hard requirements for plugin / server.mjs changes" and `ALIGNMENT.md` Rules 1, 2, 5.
- **Alignment CI is not suppressible.** The `alignment.yml` workflow greps for known-hallucinated tokens (currently carrying OCP's `api.anthropic.com/api/oauth/usage` as a transitive guardrail) and runs per-provider sanity checks. Adding new blacklist tokens is done via PR amendment to `alignment.yml`; removing entries requires an `ALIGNMENT.md` amendment PR.
- **No self-approval.** Implementation author cannot merge their own PR (Iron Rule 10). A fresh-context reviewer must open the cited authority and confirm in the review comment.
- **`models-registry.json` is the only place to add/edit `(provider, model)` metadata.** Do not touch hardcoded model maps in `server.mjs`, `lib/providers/*.mjs`, or `setup.mjs` (📋 `setup.mjs` is planned, not yet authored). The OLP ADR that codifies this SPOT discipline lands in Phase 1 (OCP's ADR 0003 — `models.json` SPOT — is the precedent; OLP needs its own SPOT ADR because the registry shape differs).
- **Provider plugins follow the contract in ADR 0002.** A new provider plugin must implement every method on the Provider contract (`name`, `displayName`, `models`, `auth`, `spawn`, `estimateCost`, `quotaStatus`, `healthCheck`, `hints`). Partial implementations are unalignable per `ALIGNMENT.md` Rule 4.
- **No anti-fingerprinting.** OLP is honest about spawning the real CLI. If a provider detects subscription-spawn proxying and bans it, the response is to drop the provider per ADR 0006, not to mask the spawn.
- **No conversation state.** OLP is a stateless proxy. Memory / continuity is the client's responsibility (see ADR 0001 § Non-mission).
---
## Release protocol
OLP follows the machine-readable `release_kit:` overlay in `CLAUDE.md` (Iron Rule 5.5). Before any version bump or tag push, re-read that YAML block and walk every item in `new_feature_doc_expectations` and `bootstrap_quirk_policy`. Tag push triggers `.github/workflows/release.yml`, which creates the GitHub Release automatically — do not create the release manually.
Version is sourced from `package.json`; changelog from `CHANGELOG.md`; user-facing docs from `README.md`. The Supported Providers table in `README.md` is sourced from `models-registry.json` per the overlay; do not hand-edit it out of sync.
---
## Handoff expectations
A fresh session picking up OLP work should read, in order:
1. This file (`AGENTS.md`).
2. `ALIGNMENT.md` — constitution; non-optional.
3. `CLAUDE.md` — tool-specific instructions and `release_kit` overlay.
4. `docs/adr/` — most recent ADRs first; they explain why the current structure exists. Founding ADRs 0001–0006 are the OLP-bootstrap set.
5. `~/.cc-rules/memory/projects/olp_v0_1_spec.md` — the v0.1 spec (authoritative for OLP scope until v1.0 ships).
6. `~/.cc-rules/memory/auto/MEMORY.md` — cross-machine memory index.
Only after these should the session touch code.
---
**Authors:** project maintainer (with AI drafting assistance).
Reference in New Issue View Git Blame Copy Permalink