taodengandClaude Opus 4.7
a7085d9718
cold-audit catch from 2026-05-23
Cold-audit Finding 1 (P2 correctness). Pre-D14 the D10 real-streaming
branch called `res.writeHead(200, ...)` unconditionally before any
provider chunk arrived. If `streamPlugin.spawn(...)` threw or yielded
an error chunk before the first content chunk, the catch block found
`firstChunkEmitted === false` AND `res.headersSent === true` (because
writeHead had already fired), so the `!res.headersSent` branch was
dead code and the path fell through to bare `res.end()`. Result:
HTTP 200 + Content-Type: text/event-stream + zero bytes of body + no
`[DONE]` terminator. The client saw a "successful" empty response.
Compare the buffered path: identical upstream failure returns
HTTP 502 + Content-Type: application/json + `{error: {message, type}}`
body via `sendError(res, 502, ...)`. Inconsistent client-visible
outcomes across paths, with the streaming variant being silently lossy.
Changes (server.mjs +14/-7, test-features.mjs +66):
1. Removed the unconditional pre-loop `res.writeHead(200, ...)` block.
Replaced with a D14 explanatory comment block.
2. Added a deferred writeHead inside the for-await loop, just before
the first `res.write`, guarded by `if (!res.headersSent)`:
```
if (!res.headersSent) {
res.writeHead(200, { Content-Type, Cache-Control, Connection,
X-Accel-Buffering, ...streamHeaders });
}
streamedChunks.push(irChunk);
res.write(irChunkToOpenAISSE(...));
firstChunkEmitted = true;
```
After the first iteration the guard becomes a no-op for subsequent
chunks. Order inside the loop body is fully synchronous (no await
between writeHead, write, and the flag assignment), so the
`firstChunkEmitted` and `res.headersSent` predicates become
equivalent in steady state.
3. The catch block was NOT touched. Its existing branching was correct
but the `!res.headersSent → sendError(502)` arm was dead code
pre-D14; post-D14 it becomes live. This makes the streaming path's
pre-first-chunk error behavior identical to the buffered path's.
Tests: 291 → 292 (+1):
- Test 15d "streaming early error → 502 JSON not 200 empty body":
Injects a mock anthropic provider via the `loadedProviders` test
seam; mock's `spawn` is an async generator that throws ProviderError
immediately (no yields). Asserts r.status === 502, Content-Type
includes application/json, body parses to `{error: {message, type}}`
with type === 'provider_error', and message contains the original
error string. This test would FAIL on pre-D14 code (would have seen
200 + empty SSE body).
Scope explicitly excludes:
- Finding #5 (streaming bypasses D4 singleflight) — deferred to D14.5
with ADR 0005 § D4 amendment pinning the tee-vs-buffer-replay design
choice. Verified no inflight map, no singleflight machinery, no
Promise tracking added.
- No ADR change. ADR 0004 § Fallback safety first-chunk rule already
governs the post-first-chunk behavior (truncated `res.end()`, no
fallback, no in-band error); D14 preserves that semantics exactly.
Authority:
- OpenAI Chat Completions streaming spec: a failed completion before
the first byte should be an HTTP error response, not a 200 with empty
body
https://platform.openai.com/docs/api-reference/chat/streaming
- ALIGNMENT.md Rule 2(b): no invented response shapes (200 with empty
body when error occurred is an implicit invention since OpenAI spec
does not define this as a success shape)
- ADR 0004 § Fallback safety — first-chunk rule (preserved unchanged)
https://github.com/dtzp555-max/olp/blob/main/docs/adr/0004-fallback-engine.md
Reviewer (Iron Rule v1.6 § 10.x Mode A, fresh-context opus, independent
of drafter): APPROVE. Reviewer stashed the diff to trace pre-D14
control flow manually and confirmed the defect existed exactly as
described (writeHead unconditional → catch with firstChunkEmitted=false
and res.headersSent=true → bare res.end() → silent 200 + empty body).
Verified order inside loop body is correct, headers passed to writeHead
are unchanged, sendError signature matches, stop-as-first-chunk edge
case handled correctly, no singleflight introduced, hygiene clean.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
OLP — Open LLM Proxy
A personal- and family-scale multi-provider LLM proxy. One HTTP endpoint, many subscriptions behind it, automatic routing, automatic fallback, content-addressed caching — so your IDEs and family clients keep working as long as any of your subscriptions has quota left.
Status: v0.1 — bootstrap. Most of this README is a skeleton; sections marked placeholder land alongside the relevant phase of work (see phase plan).
Why OLP
On 2026-05-14, Anthropic announced (effective 2026-06-15) that claude -p, the Agent SDK, and third-party agent traffic move out of the Pro/Max subscription pool into a separate fixed monthly Agent SDK Credit pool. OCP, OLP's predecessor, was a proxy around a single CLI — its core assumption was "subscription = unlimited within rate limits". That assumption breaks for Anthropic on the effective date.
The structural response is to stop relying on one provider's subscription terms remaining favourable. OLP spreads risk across multiple providers whose subscriptions still include CLI/programmatic use, routes intelligently between them, and caches aggressively so every request that does spawn a CLI counts.
OLP is not: a commercial multi-tenant SaaS; an enterprise gateway competing with LiteLLM / OpenCode / CLIProxyAPI on breadth; a model-capability router ("route to the smartest model" — you pick the model); a conversation-state store (your client handles that).
See ALIGNMENT.md for OLP's constitution and docs/adr/ for the founding ADRs.
Quick Start
placeholder — lands with Phase 1.
Anticipated shape:
# install
npm install -g @dtzp555-max/olp
# run setup (writes ~/.olp/config.json, asks which providers to enable)
olp setup
# start the proxy (default port 3456 — same as OCP if you migrate)
olp start
# point your IDE at http://localhost:3456/v1/chat/completions with the OLP API key from `olp keys list`.
Supported Providers
Source of truth: models-registry.json. This table is regenerated from the registry per the release_kit overlay; do not edit it out of sync.
OLP distinguishes Candidate Providers (declared as intended, not yet pinned) from Enabled Providers (authority pin filled + plugin landed + Phase audit passed). The v0.1 founding commit ships zero Enabled Providers — enablement is a Phase audit deliverable, not a bootstrap claim. See ALIGNMENT.md § Provider Inventory for the transition gate.
Candidate Providers
| Provider key | CLI | Subscription / auth | Anticipated Tier | Anticipated Phase |
|---|---|---|---|---|
anthropic |
claude -p |
Pro / Max OAuth (pre-2026-06-15); Agent SDK Credit pool after | D (re-eval post-2026-06-15) | Phase 1 |
openai |
codex exec --json |
ChatGPT Pro OAuth or API key | D | Phase 2 |
mistral |
vibe --prompt --output json |
Le Chat Pro API key | D | Phase 3 |
grok |
grok -p --output-format streaming-json |
xAI Build xai-... API key |
C | Phase 8+ |
kimi |
kimi -p --output-format stream-json |
Moonshot Kimi API key | C | Phase 8+ |
minimax |
TBD | MiniMax Token Plan (¥29+/mo) | B | Phase 8+ |
glm |
TBD | Zhipu Coding Plan ($10+/mo) | B | Phase 8+ |
qwen |
TBD | Alibaba Coding Plan ($50/mo) | B | Phase 8+ |
Risk tier guide. D = permissive / safe (eligible for default-enabled); C = tightening signal, no enforcement history (opt-in); B = service-level key revocation risk (opt-in + consent); A = excluded by default (cannot be opt-in enabled). Tier B providers prompt for explicit consent on first enable and record consent in ~/.olp/config.json. See ALIGNMENT.md § Risk Tier Framework.
Excluded by default (Tier A — evidence-backed, pending primary-source pin). Google Antigravity. See ADR 0006 for the named-prohibition + no-cost-advantage + reinstatement-friction rationale, and for the primary-source pinning follow-up that may force a Tier reconsideration if the Google FAQ language cannot be sourced within 90 days of 2026-05-23.
Configuration
placeholder — full configuration reference lands with Phase 4 (fallback engine).
OLP reads its config from ~/.olp/config.json. The minimum useful shape:
{
"routing": {
"chains": {
"<requested-model>": [
{ "provider": "<key>", "model": "<provider-model-id>" },
{ "provider": "<key>", "model": "<provider-model-id>" }
]
},
"soft_triggers": {
"<provider-key>": { "<trigger>": <threshold> }
}
}
}
Trigger types, fallback safety, idempotency rules, and the full example config land here when Phase 4 ships. See ADR 0004 (Fallback Engine Semantics & Safety) for the design.
API Endpoints
placeholder — full table lands as each endpoint lands.
| Endpoint | Method | Phase | Description |
|---|---|---|---|
/v1/chat/completions |
POST | 1 | OpenAI-compatible Chat Completions entry. Internally normalized to IR, dispatched to a provider plugin, response shape converted back. |
/v1/models |
GET | 1 | Lists models from models-registry.json. |
/health |
GET | 1 | Per-provider health snapshot (owner-only). |
/cache/stats |
GET | 5 | Cache hit rate, by-provider breakdown. |
/v0/management/quota |
GET | 6 | Per-provider quota / credit pool status (best-effort). |
/dashboard |
GET | 6 | Owner-only dashboard (localhost-bound by default). |
Environment Variables
placeholder — full table lands per-phase as variables are introduced.
| Variable | Default | Description |
|---|---|---|
OLP_PORT |
3456 |
HTTP listener port. |
OLP_HOME |
~/.olp |
Config, providers, keys, cache, logs root. |
OLP_LOG_LEVEL |
info |
One of error, warn, info, debug. |
Further variables (per-provider auth path overrides, cache size limits, fallback-engine knobs) land with the relevant phase.
Response Headers
Every response served through OLP carries:
X-OLP-Provider-Used: <provider-key>— which provider's plugin served the request.X-OLP-Model-Used: <model-id>— which model the served provider used.X-OLP-Fallback-Hops: <n>— number of fallback hops (0if served by the primary chain entry).X-OLP-Cache: hit | miss | bypass— cache layer outcome.X-OLP-Latency-Ms: <ms>— end-to-end latency observed at the proxy.
If a fallback chain is exhausted, X-OLP-Fallback-Exhausted lists the tried providers in order.
Architecture
OLP is a Node.js (ESM, .mjs) HTTP proxy with no build step and minimal dependencies. The high-level shape:
- Entry surface —
server.mjshandles/v1/chat/completionsand the administrative endpoints. Governed by OpenAI's/v1/chat/completionsspecification as the wire authority. SeeALIGNMENT.md§ Authorities. - Intermediate Representation (IR) —
lib/ir/normalizes between the entry surface and provider-native shapes. The IR is the lingua franca; any extension is an ADR 0003 amendment. - Provider plugins —
lib/providers/<name>.mjs. Each plugin implements the contract in ADR 0002 (Plugin Architecture for Providers), spawns its CLI, and translates between IR and provider-native IO. - Cache layer —
lib/cache/is a content-addressed cache keyed on(provider, model, messages, tools, temperature, response_format, cache_control). Per-key isolation, prompt-caching bypass, chunked stream replay, and singleflight. See ADR 0005 (Cache Layer Cross-Provider Design). - Fallback engine —
lib/fallback/advances a configured chain one provider at a time on configured triggers, never retrying after the first response chunk has been emitted to the client. See ADR 0004. - Multi-key auth —
lib/keys.mjscarries OCP's per-OLP-key namespace isolation forward. Each OLP API key has independent quota, cache namespace, and audit log; each key declares which providers it can access.
Read the ADRs in docs/adr/ in order before proposing structural changes.
Phase plan
OLP lands in phases. Each phase has its own PR series and Iron-Rule-10 reviewer; this README's placeholders are filled per-phase via the release_kit overlay.
- Phase 0 — Repo bootstrap,
ALIGNMENT.md, founding ADRs, CI workflows, PR template. (current) - Phase 1 —
server.mjsskeleton, IR, Anthropic plugin, cache D1+D4. Port from OCP. - Phase 2 — OpenAI Codex plugin.
- Phase 3 — Mistral Vibe plugin.
- Phase 4 — Fallback engine + routing chains config + quota poll worker.
- Phase 5 — Cache cross-provider hardening (D2+D3).
- Phase 6 — Dashboard + observability (
/v0/management/quota). - Phase 7 — Release v0.1, OCP enters maintenance.
- Phase 8+ — Optional Grok / Kimi / tier-2 plugins; provider-native protocol endpoints; deterministic triggers.
Full spec (decision rationale, open questions, risks): ~/.cc-rules/memory/projects/olp_v0_1_spec.md on the maintainer's workstations.
Migration from OCP
placeholder — scripts/migrate-from-ocp.mjs lands with Phase 7.
Anticipated user-facing flow (target: <5 minutes):
- Stop OCP (
launchctl bootoutthe OCP service orocp stop). - Install OLP.
- Run
olp migrate-from-ocp— copies~/.ocp/keys/to~/.olp/keys/and points provider plugins at OCP's existing auth artifacts where applicable. - Start OLP. Clients pointing at port 3456 keep working; their existing OLP API keys remain valid.
OCP's cache directory is not migrated: OLP's cache key format includes provider+model and warms cold naturally. OCP enters maintenance mode (stability fixes only) when OLP v0.1 ships; new development happens in OLP.
License
MIT.
Acknowledgements
OLP evolved from OCP (Open Claude Proxy). OCP's per-key isolation model, cache-layer design (D1–D4), dashboard, and alignment-constitution discipline are all carried forward. The structural generalization from single-CLI to multi-provider is what makes this a new project rather than an OCP minor version — see ALIGNMENT.md § Reference: How OCP's cli.js discipline maps to OLP.
Authors: project maintainer (with AI drafting assistance).