mirror of
https://github.com/dtzp555-max/olp.git
synced 2026-07-21 21:15:10 +00:00
feat(phase-1): D10 P1 hardening — providers.enabled wiring + real streaming + spawn timeout
Folds in three production-blocking defects from external Codex review
round-3 of Phase 1 (D5+D6+D8+D9 already merged). Without these, OLP
returns 503 on every request even when `npm start` succeeds, streams
arrive as a single buffered burst after the spawn completes, and hung
CLIs block the engine forever despite ADR 0004 declaring spawn-timeout
a hard trigger.
P1.1 providers.enabled config wiring (ADR 0002 § Disable model):
- loadFallbackConfigSync() returns tri-field {chains, soft_triggers,
providersEnabled}; server.mjs reads _startupConfig.providersEnabled
and passes to loadProviders() at startup
- Empty / missing config → 0 enabled providers → 503 no_enabled_provider
(matches v0.1 0-Enabled posture per ALIGNMENT.md § Provider Inventory)
- __setProvidersEnabled / __resetProvidersEnabled test seams; in-place
Map mutation preserves existing direct-mutation patterns in Suite 13
P1.2 Real SSE streaming on single-hop cache-miss (ADR 0003 entry adapter
pattern, OpenAI /v1/chat/completions stream=true contract):
- New handleChatCompletions branch when ir.stream === true && chain.length
=== 1 && !bypassCache && !preCheckHit
- for await (const irChunk of provider.spawn(...)) writes SSE per chunk
via res.write(irChunkToOpenAISSE(...)); accumulates streamedChunks for
cacheStore.set on stop
- First-chunk rule preserved: error-before-first-chunk → sendError(502);
error-after-first-chunk → truncated res.end(), no fallback
- Multi-hop chains (chain.length > 1) continue to use buffered
executeWithFallback to keep fallback safety semantics
P1.3 Spawn timeout hard trigger (ADR 0004 § Trigger taxonomy bullet 4):
- SPAWN_TIMEOUT added to PROVIDER_ERROR_CODES (lib/providers/base.mjs)
and HARD_TRIGGER_CODES (lib/fallback/engine.mjs)
- All three plugins (anthropic.mjs / codex.mjs / mistral.mjs) wrap drain
loop with setTimeout (default 600_000ms, configurable via
hints.maxSpawnTimeMs); on fire: proc.kill('SIGTERM') + reject pending
drain promise with ProviderError(..., 'SPAWN_TIMEOUT')
- Timer cleared in finally; resolveNext/rejectNext atomically nulled in
push() + timer-fire path to prevent late-fire double-settle
Tests 277 → 288 (+11). Suite 14 (4 providers.enabled), Suite 15
(3 streaming cache-miss real-time, including arrival-count >= 2
assertion that architecturally proves real streaming), Suite 16
(4 spawn timeout, including 2-hop chain advancement from timed-out
primary). 288/288 pass on Node 20.20.2 + Node 25.8.0.
Authorities:
- ADR 0002 § Disable model — config toggle, not plugin-removal
https://github.com/dtzp555-max/olp/blob/main/docs/adr/0002-plugin-architecture.md
- ADR 0003 § Translation direction model — entry adapter for await pattern
https://github.com/dtzp555-max/olp/blob/main/docs/adr/0003-intermediate-representation.md
- ADR 0004 § Trigger taxonomy + § Fallback safety (first-chunk rule)
https://github.com/dtzp555-max/olp/blob/main/docs/adr/0004-fallback-engine.md
- OpenAI /v1/chat/completions stream=true (server-sent events,
data: {chunk} per delta, terminator data: [DONE])
https://platform.openai.com/docs/api-reference/chat/streaming
Reviewer (Iron Rule 10): fresh-context opus, independent of drafter.
Verdict: APPROVE_WITH_MINOR. Folded the one cheap minor before commit
(Suite 15a arrival-count assertion strengthened from chunks.length > 0
to arrivalTimestamps.length >= 2 — the prior assertion would have
admitted a buffered impl). Two remaining non-blocking notes deferred:
optional writeHead deferral (low value; single-hop guard makes pre-
content 200 + empty body safe), and version bump (Phase 1 ships as
v0.1.0 aggregate when D11–D16 land).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
+63
-20
@@ -50,7 +50,7 @@ import { execFileSync, execSync } from 'node:child_process';
|
||||
import { existsSync, readFileSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
import { homedir } from 'node:os';
|
||||
import { ProviderError } from './base.mjs';
|
||||
import { ProviderError, PROVIDER_ERROR_CODES } from './base.mjs';
|
||||
|
||||
// ── Binary resolution ─────────────────────────────────────────────────────
|
||||
// OLP_CLAUDE_BIN env takes priority, then falls back to 'claude' from PATH.
|
||||
@@ -256,12 +256,15 @@ async function* _spawnAndStream(irRequest, authContext, spawnImpl) {
|
||||
let exitCode = null;
|
||||
let exitSignal = null;
|
||||
let resolveNext = null;
|
||||
// timeout: tracks a pending rejectNext for spawn timeout
|
||||
let rejectNext = null;
|
||||
|
||||
function push(item) {
|
||||
chunks.push(item);
|
||||
if (resolveNext) {
|
||||
const r = resolveNext;
|
||||
resolveNext = null;
|
||||
rejectNext = null;
|
||||
r();
|
||||
}
|
||||
}
|
||||
@@ -286,40 +289,77 @@ async function* _spawnAndStream(irRequest, authContext, spawnImpl) {
|
||||
push({ type: 'close' });
|
||||
});
|
||||
|
||||
// ADR 0004 § Trigger taxonomy bullet 4: spawn timeout is a hard trigger.
|
||||
// maxSpawnTimeMs: from hints field so tests can lower it without changing the plugin.
|
||||
// Default: 600 000 ms (10 minutes) — reasonable for long Claude outputs.
|
||||
const maxSpawnTimeMs = anthropic.hints?.maxSpawnTimeMs ?? 600_000;
|
||||
|
||||
// Overall wall-clock deadline — fires if the process hasn't closed in time.
|
||||
let spawnTimedOut = false;
|
||||
const spawnDeadlineTimer = setTimeout(() => {
|
||||
spawnTimedOut = true;
|
||||
// Kill the process and wake up the drain loop via a rejection.
|
||||
try { proc.kill('SIGTERM'); } catch { /* ignore */ }
|
||||
if (rejectNext) {
|
||||
const r = rejectNext;
|
||||
rejectNext = null;
|
||||
resolveNext = null;
|
||||
r(new ProviderError(
|
||||
`claude spawn timed out after ${maxSpawnTimeMs}ms`,
|
||||
'SPAWN_TIMEOUT',
|
||||
));
|
||||
}
|
||||
}, maxSpawnTimeMs);
|
||||
|
||||
// Drain the chunk buffer
|
||||
while (true) {
|
||||
if (chunks.length === 0) {
|
||||
if (done) break;
|
||||
// Wait for the next event
|
||||
await new Promise((resolve) => { resolveNext = resolve; });
|
||||
continue;
|
||||
}
|
||||
try {
|
||||
while (true) {
|
||||
if (chunks.length === 0) {
|
||||
if (done) break;
|
||||
if (spawnTimedOut) {
|
||||
throw new ProviderError(
|
||||
`claude spawn timed out after ${maxSpawnTimeMs}ms`,
|
||||
'SPAWN_TIMEOUT',
|
||||
);
|
||||
}
|
||||
// Wait for the next event (or timeout rejection)
|
||||
await new Promise((resolve, reject) => {
|
||||
resolveNext = resolve;
|
||||
rejectNext = reject;
|
||||
});
|
||||
continue;
|
||||
}
|
||||
|
||||
const item = chunks.shift();
|
||||
const item = chunks.shift();
|
||||
|
||||
if (item.type === 'error') {
|
||||
throw new ProviderError(`claude spawn error: ${item.err.message}`, 'SPAWN_FAILED');
|
||||
}
|
||||
if (item.type === 'error') {
|
||||
throw new ProviderError(`claude spawn error: ${item.err.message}`, 'SPAWN_FAILED');
|
||||
}
|
||||
|
||||
if (item.type === 'close') {
|
||||
break;
|
||||
}
|
||||
if (item.type === 'close') {
|
||||
break;
|
||||
}
|
||||
|
||||
if (item.type === 'data') {
|
||||
yield anthropicChunkToIR(item.text, isFirstChunk);
|
||||
isFirstChunk = false;
|
||||
if (item.type === 'data') {
|
||||
yield anthropicChunkToIR(item.text, isFirstChunk);
|
||||
isFirstChunk = false;
|
||||
}
|
||||
}
|
||||
} finally {
|
||||
clearTimeout(spawnDeadlineTimer);
|
||||
}
|
||||
|
||||
// Process close
|
||||
if (exitCode !== 0) {
|
||||
if (exitCode !== 0 && !spawnTimedOut) {
|
||||
const errMsg = accumulatedStderr.slice(0, 300) || `claude exit ${exitCode}`;
|
||||
// Map known exit patterns to IR error chunk, then throw
|
||||
throw new ProviderError(errMsg, 'SPAWN_FAILED');
|
||||
}
|
||||
|
||||
// Normal exit: emit stop chunk
|
||||
yield anthropicStopToIR('stop');
|
||||
if (!spawnTimedOut) {
|
||||
yield anthropicStopToIR('stop');
|
||||
}
|
||||
}
|
||||
|
||||
// ── spawn (public, contract method) ──────────────────────────────────────
|
||||
@@ -447,6 +487,9 @@ const anthropic = {
|
||||
requiresTTY: false,
|
||||
concurrentSpawnSafe: true,
|
||||
maxConcurrent: 4,
|
||||
// ADR 0004 § Trigger taxonomy bullet 4: spawn timeout is a hard trigger.
|
||||
// 600_000ms = 10 minutes. Tests can lower this by mutating anthropic.hints.maxSpawnTimeMs.
|
||||
maxSpawnTimeMs: 600_000,
|
||||
},
|
||||
};
|
||||
|
||||
|
||||
Reference in New Issue
Block a user