mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-31 04:12:10 +03:00
* fix(sse): Gemini TPM classification, combo-cooldown-wait for auto/quota-share, and target-timeout floor
Gemini TPM/RPM 429s were misclassified as QUOTA_EXHAUSTED because
sanitizeErrorMessage() truncates to the first line, hiding Google's
metric name and retry hint on lines 2-3. Added a rawMessage field
(internal-only, never reaches the client) and classifyGeminiQuotaMetricFromText()
to classify from the untruncated text, reordered ahead of the generic
credits/daily-quota checks.
Widened comboCooldownWaitEnabled (wait out a short transient cooldown
instead of crystallizing a 429/503) from quota-share-only to also cover
auto-strategy combos, and raised the wait ceiling to 65s/130s-budget/90s-cap
to match Gemini's ~60s TPM/RPM windows.
The per-target timeout (DEFAULT_COMBO_TARGET_TIMEOUT_MS, 120s) was shorter
than the new 130s cooldown-wait budget, so a target could get cut off
mid-wait with a synthetic 524 instead of completing the retry. Added
resolveComboTargetTimeoutMsForCombo()/isComboCooldownWaitEligible() in
comboConfig.ts to raise the per-target floor to budgetMs+buffer only for
wait-eligible strategies (auto/quota-share), verified live: a 12-request
concurrent burst against a TPM-exhausted combo went from 2/12 succeeding
(10 x 524) to 12/12 succeeding with zero 503/524.
Also: liveGeminiShared.ts's sendAndValidate now fails fast on a 503
instead of retrying past it, and the health dashboard + request logger
surface TPM stats alongside RPM/RPD.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): combo-exhausted rejection logs now capture request body + attempted models
recordRejectedRequestUsage() (the fast path for combo requests that never
reach handleChatCore, e.g. all targets locked by resilience cooldown)
hardcoded provider: "-" and never passed a request body to saveCallLog(),
so /dashboard/logs entries for these failures were nearly useless for
debugging: no way to see the client's request or which models were tried.
- recordRejectedRequestUsage() now accepts requestBody and persists it
through the existing saveCallLog() artifact mechanism (same path
handleChatCore's own logging uses).
- Added summarizeComboAttemptedModels(), which reads the combo's own model
list (always available, unlike the response's combo-diagnostics headers —
a model-level resilience-lockout skip never touches the
exhaustedProviders/exhaustedConnections sets those headers are built
from) to populate a real "provider" value instead of "-".
- Wired both into the call site in src/sse/handlers/chat.ts.
NOTE: unrelated to the Gemini TPM/combo-cooldown-wait fix on this branch —
landed here per operator request, to be split into its own branch/PR.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* feat(sse): synthetic streaming keep-alive event + 5-minute Gemini cooldown-wait ceiling
Many clients enforce a first-SSE-byte timeout, which made it unsafe to wait
out a longer upstream rate-limit cooldown on a streaming request — the
client would abandon the connection before any bytes arrived. This landed
in two parts:
1. Synthetic startup "thinking" event (OpenAI chat/completions format):
the already-existing withEarlyStreamKeepalive wrapper (open-sse/utils/
earlyStreamKeepalive.ts, wired into /v1/chat/completions, /v1/messages,
/v1/responses since #2544) opens the SSE stream immediately once a
request runs past its threshold, but only ever sent empty/no-op
keepalive frames. Added a `startupFrame` option (defaults to
`keepaliveFrame` — zero behavior change unless a route opts in) so the
very first frame can carry real content instead. Wired
OPENAI_STARTUP_THINKING_FRAME (a reasoning_content delta: "OmniRoute:
got request, sending to provider") into /v1/chat/completions only —
Claude Messages and Responses API formats both require a preceding
envelope event (message_start / response.created) that a synthetic
pre-dispatch frame can't safely fabricate without risking a duplicate
envelope once the real stream arrives, so those two routes keep their
existing (safe, proven) keepalive frames unchanged.
2. Raised the "wait out a known cooldown, then retry" ceiling to 5 minutes
for both retry mechanisms, now that a client-side first-byte timeout is
no longer a risk on the (opted-in) route:
- comboCooldownWait (auto/quota-share combos, open-sse/services/combo.ts):
maxWaitMs hard clamp raised 90s -> 300s (src/lib/resilience/settings/
normalize.ts); defaults raised to maxWaitMs:90s/maxAttempts:5/
budgetMs:300s. comboConfig.ts's resolveComboTargetTimeoutMsForCombo
already derives the per-target timeout floor from budgetMs, so it
tracks the new ceiling with no further changes.
- waitForCooldown (direct, non-combo model requests, src/sse/handlers/
chat.ts): this mechanism had NO cumulative cap before — only a
per-wait cap (maxRetryWaitMs) and a retry count (maxRetries), so
maxRetries x maxRetryWaitMs could exceed 5 minutes with no ceiling.
Added a budgetMs field (mirrors comboCooldownWait) to
WaitForCooldownSettings/CooldownAwareRetrySettings, threaded a
requestRetryBudgetLeftMs tracker through chat.ts's requestAttemptLoop
(mirrors combo.ts's comboCooldownBudgetLeftMs), and made
getCooldownAwareRetryDecision refuse to wait once the cumulative
budget is exhausted even if the single wait is under maxRetryWaitMs.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): extend the synthetic keep-alive thinking event to /v1/responses
Live incident (OpenClaw, log id 1784407081908-cbc24f): a /v1/responses
request to gemini/gemma-4-31b-it took 56s to produce a first byte and the
client disconnected (499 request_signal_aborted) — the same client-first-byte-
timeout problem the previous commit fixed for /v1/chat/completions, but
/v1/responses only had the generic bare-comment keepalive (no content), so it
wasn't covered.
Added RESPONSES_STARTUP_THINKING_FRAME: a self-contained synthetic reasoning
item (response.output_item.added -> reasoning_summary_part.added ->
reasoning_summary_text.delta -> reasoning_summary_part.done), opened AND
closed within this one frame rather than left dangling — it never carries a
response_id, so it can't collide with the real upstream response's own
independent response.created lifecycle that follows. Mirrors the abbreviated
delta+part.done close pattern open-sse/utils/stream.ts's own
emitSyntheticResponsesReasoningSummary already uses for real mid-stream
reasoning content.
Wired into src/app/api/v1/responses/route.ts via the startupFrame option
added in the previous commit.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): combo cooldown-wait vars reset every setTry, crystallizing a bogus 503 instead of waiting
Live incident (log id 1784416706646-51): a request to the "default" combo
(strategy=auto, maxSetRetries=3) hit a real Gemini TPM 429 on both gemma-4
targets, correctly classified as a short 40s rate_limit lockout — then
crystallized a 503 "all upstream accounts are inactive" in 6.9s instead of
ever reaching the cooldown-aware wait.
Root cause: `lastError`/`earliestRetryAfter`/`lastStatus` were declared with
`let` INSIDE the `for (setTry...)` loop body, so they reset to null at the
start of every set-try. When both targets lock out on setTry 0, every
subsequent setTry (1..maxSetRetries) pre-skips both targets via the
isModelLocked check with no real dispatch — so on the FINAL setTry (the only
one whose values the post-loop decision reads, since it's gated behind
`if (setTry < maxSetRetries) continue`), lastStatus was null, hitting the
"!lastStatus" branch (ALL_ACCOUNTS_INACTIVE 503) and completely bypassing the
comboCooldownWaitEnabled / earliestRetryAfter wait logic — even though a
real 429 with a known ~40s retry-after WAS observed on setTry 0.
This bug predates today's Gemini TPM work (any combo with maxSetRetries > 0
whose targets all lock out on the first pass was affected) but was masked in
existing tests: the "auto strategy (2 models...)" regression test uses
maxSetRetries: 0, so it only ever runs ONE setTry iteration and never
exercises the reset-on-retry path. It also explains why the dedicated
12-concurrent-request burst test passed cleanly — with concurrent requests,
timing variance meant some request's FINAL setTry iteration still had a live
target to dispatch to, giving lastStatus/earliestRetryAfter fresh data. A
single isolated request has no such luck.
Fix: hoist lastError/earliestRetryAfter/lastStatus to just inside
dispatchWithCooldownRetry, before the setTry loop, so they persist across
set-tries (still reset fresh on each recursive dispatchWithCooldownRetry()
call after a wait, which is correct). recordedAttempts/fallbackCount/
exhaustedProviders etc. are intentionally left per-iteration (unrelated to
this bug).
New regression test in tests/unit/combo-quota-share-cooldown-wait.test.ts
reproduces the exact live scenario (2 targets, both lock out on setTry 0,
maxSetRetries: 3) — confirmed red (503) against the pre-fix code, green
(200, waits and retries) against the fix.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* test(sse): extend live Gemini workload to Responses API + add large-context TPM test
Two additions to the live Gemini test suite, both live-verified against the
dev instance:
1. sendAndValidate() (tests/integration/liveGeminiShared.ts) now accepts an
apiFormat: "chat" | "responses" parameter, building the Responses-API
request shape (input array, max_output_tokens) and parsing its SSE events
(response.output_text.delta / response.reasoning_summary_text.delta /
response.completed) via the new readResponsesSSEStream(). Wired into two
new tests in live-gemini-workload.test.ts ([30]/[31]), mirroring the
existing Chat Completions streaming coverage. Verified live: 24/25 + 5/5
payloads succeeded end-to-end through the new code path (the one failure
was a ~300s test-client fetch timeout unrelated to the Responses API code
itself — a separate, not-yet-addressed test-harness limitation).
2. genHugeContextMessage() builds a single message large enough (~4
chars/token estimate) to approach or exceed Gemini's free-tier TPM ceiling
(16000 input tokens/min for gemma-4) by itself. Every other prompt
generator in this file tops out around 1-2k tokens — nowhere near that
ceiling — so none of the existing workload tests ever exercised a REAL TPM
429, only RPM-style rate limiting. tests/integration/gemini-large-context-tpm.test.ts
sends two ~12-13k-token requests back-to-back (comfortably exceeding
16000/min together) to exercise the full path against production Gemini:
TPM classification, the comboCooldownWait retry, and the synthetic
keep-alive frame on a genuinely slow request.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): abandoned combo target dispatch now observes its own per-target timeout, fixing a permanent "pending" dashboard leak
Live incident (dashboard log id 1784418258231-14961a, reported as "an ongoing
request even though there's already a 200"): a combo target dispatch
abandoned by comboTargetTimeoutMs (open-sse/services/combo/targetTimeoutRunner.ts)
left a permanent phantom "pending" entry in the dashboard, even after the
overall combo request had already succeeded via a different retry.
Root cause: chatCore.ts's createStreamController — and everything downstream
that depends on it (withRateLimit's Promise.race against Bottleneck,
acquireAccountSemaphore) — only ever watches clientRawRequest.signal, which
is the ORIGINAL client's request signal (set once via buildClientRawRequest
and reused unchanged across every target dispatch in a combo). It has no
connection to targetTimeoutRunner.ts's OWN AbortController
(target.modelAbortSignal), which is what actually fires when
comboTargetTimeoutMs (300s) elapses. src/sse/handlers/chat.ts's
handleSingleModel bridge between combo.ts and handleSingleModelChat received
`target.modelAbortSignal` but silently dropped it — never forwarded it
anywhere. So when a target got abandoned (e.g. stuck inside a wedged
Bottleneck rate-limiter queue, see the WEDGED force-reset log line from the
same incident), its per-target timeout fired and let the COMBO move on and
retry successfully elsewhere — but the abandoned dispatch's own promise
chain never learned it had been superseded, so it hung forever waiting on a
signal that was never going to fire, and trackPendingRequest(false) (the
finalize call) never ran.
Fix: thread target.modelAbortSignal through as a new modelAbortSignal
runtimeOption, and merge it into clientRawRequest.signal (via the existing
mergeAbortSignals helper from open-sse/executors/base.ts) right before
dispatch, so an abandoned target's own promise chain now observes its abort
and can reach its cleanup path — new resolveDispatchClientRawRequest() makes
this mechanically testable in isolation.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): combo cooldown-wait state recording, rate-limit wedge recovery, OpenAI-format SSE error frames
Five related fixes surfaced by live incidents (dashboard log ids 1784457764961-73,
1784465227489-a2cbc0, 1784504040241-6f8b9a) while validating the Gemini TPM/cooldown-wait
work on this branch against real OpenClaw traffic:
- combo.ts: the model-lockout bail-out branches in dispatchWithCooldownRetry never
recorded lastStatus, so once every target in a set hit an existing lockout the final
check crystallized a bogus ALL_ACCOUNTS_INACTIVE 503 instead of reaching the
cooldown-wait decision, even with a real 429 + short retry-after observed.
- combo.ts/combo/types.ts: the "all credentials cooling down" pre-dispatch rejection
(buildModelCooldownBody) nests its retry hint as error.retry_after/reset_seconds, not
the top-level retryAfter every other 429 shape uses — combo's extraction only read the
latter, so earliestRetryAfter stayed null for this shape even after lastStatus was fixed.
- rateLimitManager.ts: the wedge-recovery watchdog used disconnect(), which releases the
heartbeat timer but never rejects jobs already QUEUED on that instance — orphaned
dispatches hung until the outer ~300s per-target timeout, well past real clients'
patience. Switched to stop({ dropWaitingJobs: true }), safe because the wedge condition
already requires RUNNING===0 && EXECUTING===0.
- earlyStreamKeepalive.ts: the in-band error frame emitted after committing to a 200 SSE
stream was hardcoded to Anthropic's `event: error` convention for every route, including
the OpenAI-format ones (/v1/chat/completions, /v1/responses) where that framing is
either invisible or malformed to a plain data-line parser. Added per-route
OPENAI_CHAT_ERROR_FRAME / OPENAI_RESPONSES_ERROR_FRAME and wired them in.
- chatCore.ts: persisted a synthetic clientResponse error body even when the client had
already disconnected (AbortError) before that body was ever computed — misleading the
dashboard into showing "what the client received" for a response that was never sent.
Also: RequestLoggerDetail.tsx — Provider/Client Event Stream panes lost their collapse
toggle when StreamSection replaced the collapsible PayloadSection (692d6be80, unifying
active/finished request views) without carrying the toggle over.
Each fix has a TDD regression test with a confirmed red-before-green cycle.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* test(sse): free-tier model + gemma-4 TPM-ceiling benchmark harness
Adds a live benchmark comparing free models OmniRoute exposes across
configured providers plus previously-unexercised no-auth providers
(felo-web, aihorde, opencode, duckduckgo-web — none need a connection
row, they were just never tried). Reuses liveGeminiShared.ts's SSE
parsers and CASE_BUILDERS instead of duplicating them.
Also adds a targeted TPM-stress test firing back-to-back large-context
prompts at the gemma-4-31b model across its 3 free hosts (Gemini,
NVIDIA, AI Horde) to isolate whether the documented 16k-tokens/minute
free-tier ceiling is Gemini-specific enforcement or an inherent
model property.
FORCE_TOOL_CHOICE_REQUIRED is a test-only, default-off env flag added
to liveGeminiShared.ts and live-gemini-agentic-loop.test.ts for an
earlier live A/B comparison of tool_choice: required vs unset — kept
as a reusable knob for future runs.
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* test(sse): benchmark for the 2026-07-22 newly-enabled provider batch
Adds NEWLY_ENABLED_MODELS to freeModelBenchmarkShared.ts (Mistral
Leanstral, OpenRouter's live "free"-tagged roster, OpenCode Zen's
current free models — refetched live from
https://opencode.ai/zen/v1/models since the static catalog had
drifted) and a dedicated workload benchmark test for them.
Co-Authored-By: Markus Hartung <markus.hartung@gmail.com>
* test(sse): sync geminiRateLimitTracker tests with e74a1722b's corrected Gemma 4 limits
e74a1722b updated geminiRateLimits.json's gemma-4-* entries from the stale
15/1500/-1 (rpm/rpd/tpm) to the real published free-tier values
16000/14400/16000, but never updated the tests asserting the old numbers.
Surfaced by running the full test:unit suite as a post-rebase sanity check.
Co-Authored-By: Markus Hartung <markus.hartream@gmail.com>
* chore(quality): file-size baseline for own-growth (#8213)
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
---------
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
Co-authored-by: Markus Hartung <markus.hartream@gmail.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
300 lines
9.8 KiB
TypeScript
300 lines
9.8 KiB
TypeScript
/**
|
||
* tests/integration/live-gemini-workload.test.ts
|
||
*
|
||
* Streaming live Gemini workload test. Reuses shared generators from
|
||
* liveGeminiShared.ts. For non-streaming, see live-gemini-nonstream.test.ts.
|
||
*/
|
||
import test from "node:test";
|
||
import assert from "node:assert/strict";
|
||
|
||
import {
|
||
skip,
|
||
randomInt,
|
||
sendAndValidate,
|
||
CASE_BUILDERS,
|
||
ensureTestEnvironment,
|
||
DELAY_BETWEEN_REQUESTS_MS,
|
||
type Message,
|
||
} from "./liveGeminiShared.ts";
|
||
|
||
test.before(async () => {
|
||
await ensureTestEnvironment();
|
||
});
|
||
|
||
// --------------------------------------------------------------------------
|
||
// Concurrent load — 5 parallel threads × 15 iterations
|
||
// --------------------------------------------------------------------------
|
||
|
||
test("[26] concurrent load — 2 threads × 2 iterations", { skip }, async () => {
|
||
const THREAD_COUNT = 2;
|
||
const SET_COUNT = 2;
|
||
const TOTAL_REQUESTS = THREAD_COUNT * SET_COUNT;
|
||
|
||
console.log(
|
||
`\n Concurrent load: ${THREAD_COUNT} threads × ${SET_COUNT} iterations = ${TOTAL_REQUESTS} requests`
|
||
);
|
||
|
||
const start = performance.now();
|
||
|
||
// Shared state for parallel-request detection across threads
|
||
const requestWindows: { cid: string; start: number; end: number }[] = [];
|
||
let parallelViolation: string | null = null;
|
||
|
||
const threadResults = await Promise.allSettled(
|
||
Array.from({ length: THREAD_COUNT }, (_, threadIdx) =>
|
||
(async () => {
|
||
const results: {
|
||
status: number;
|
||
duration: number;
|
||
tokens: number;
|
||
contentLength: number;
|
||
correlationId: string;
|
||
}[] = [];
|
||
for (let set = 1; set <= SET_COUNT; set++) {
|
||
if (parallelViolation) break; // another thread detected a violation
|
||
|
||
const idx = randomInt(0, CASE_BUILDERS.length - 1);
|
||
const tc = CASE_BUILDERS[idx];
|
||
const label = `t${threadIdx + 1}-i${set}: ${tc.name}`;
|
||
const requestStart = Date.now();
|
||
const r = await sendAndValidate(label, tc.build);
|
||
const requestEnd = Date.now();
|
||
|
||
// Check for parallel requests with the same correlationId
|
||
const cid = r.correlationId;
|
||
const myWindow = { cid, start: requestStart, end: requestEnd };
|
||
const siblings = requestWindows.filter((w) => w.cid === cid);
|
||
for (const s of siblings) {
|
||
if (myWindow.start < s.end && s.start < myWindow.end) {
|
||
parallelViolation =
|
||
`PARALLEL REQUEST DETECTED: cid=${cid.slice(0, 12)}… ` +
|
||
`window [${new Date(myWindow.start).toISOString().slice(11, 23)}–${new Date(myWindow.end).toISOString().slice(11, 23)}] ` +
|
||
`overlaps with [${new Date(s.start).toISOString().slice(11, 23)}–${new Date(s.end).toISOString().slice(11, 23)}]`;
|
||
break;
|
||
}
|
||
}
|
||
requestWindows.push(myWindow);
|
||
results.push({ ...r } as any);
|
||
}
|
||
return results;
|
||
})()
|
||
)
|
||
);
|
||
|
||
const totalDuration = performance.now() - start;
|
||
|
||
const fulfilled = threadResults.filter((r) => r.status === "fulfilled") as PromiseFulfilledResult<
|
||
{
|
||
status: number;
|
||
duration: number;
|
||
tokens: number;
|
||
contentLength: number;
|
||
correlationId: string;
|
||
}[]
|
||
>[];
|
||
const rejected = threadResults.filter((r) => r.status === "rejected") as PromiseRejectedResult[];
|
||
|
||
const allResults = fulfilled.flatMap((r) => r.value);
|
||
const totalTokens = allResults.reduce((sum, r) => sum + r.tokens, 0);
|
||
const avgDuration =
|
||
allResults.length > 0
|
||
? Math.round(allResults.reduce((s, r) => s + r.duration, 0) / allResults.length)
|
||
: 0;
|
||
|
||
console.log(
|
||
`\n Concurrent summary: ${fulfilled.length}/${THREAD_COUNT} threads completed | ` +
|
||
`${allResults.length}/${TOTAL_REQUESTS} requests succeeded | ` +
|
||
`${Math.round(totalDuration)}ms wall clock | ` +
|
||
`${avgDuration}ms avg per request | ` +
|
||
`${totalTokens} total tokens`
|
||
);
|
||
|
||
if (rejected.length > 0) {
|
||
for (const r of rejected) {
|
||
const msg = r.reason instanceof Error ? r.message : String(r.reason);
|
||
console.log(` THREAD FAILED: ${msg}`);
|
||
}
|
||
}
|
||
|
||
if (parallelViolation) {
|
||
console.log(`\n !! ${parallelViolation}`);
|
||
}
|
||
|
||
assert.ok(
|
||
fulfilled.length === THREAD_COUNT,
|
||
`expected all ${THREAD_COUNT} threads to complete, ${rejected.length} failed`
|
||
);
|
||
assert.ok(
|
||
allResults.length === TOTAL_REQUESTS,
|
||
`expected ${TOTAL_REQUESTS} total requests, got ${allResults.length}`
|
||
);
|
||
assert.ok(!parallelViolation, parallelViolation);
|
||
});
|
||
|
||
// --------------------------------------------------------------------------
|
||
// Single-thread sequential — 1 thread × 5 iterations
|
||
// --------------------------------------------------------------------------
|
||
|
||
test("[27] single-thread sequential — 1 thread × 5 iterations", { skip }, async () => {
|
||
const SET_COUNT = 5;
|
||
|
||
console.log(`\n Single-thread sequential: 1 thread × ${SET_COUNT} iterations`);
|
||
|
||
const start = performance.now();
|
||
const results: {
|
||
status: number;
|
||
duration: number;
|
||
tokens: number;
|
||
contentLength: number;
|
||
correlationId: string;
|
||
}[] = [];
|
||
|
||
for (let i = 1; i <= SET_COUNT; i++) {
|
||
const idx = randomInt(0, CASE_BUILDERS.length - 1);
|
||
const tc = CASE_BUILDERS[idx];
|
||
const label = `seq-i${i}: ${tc.name}`;
|
||
try {
|
||
if (i > 1) await new Promise((r) => setTimeout(r, DELAY_BETWEEN_REQUESTS_MS));
|
||
const r = await sendAndValidate(label, tc.build);
|
||
results.push(r);
|
||
} catch (err) {
|
||
const msg = err instanceof Error ? err.message : String(err);
|
||
const ts = new Date().toISOString().slice(11, 23);
|
||
console.log(`${ts} ${label.padEnd(45)} FAILED: ${msg}`);
|
||
assert.fail(`iteration ${i} failed: ${msg}`);
|
||
}
|
||
}
|
||
|
||
const totalDuration = performance.now() - start;
|
||
const totalTokens = results.reduce((sum, r) => sum + r.tokens, 0);
|
||
const avgDuration =
|
||
results.length > 0
|
||
? Math.round(results.reduce((s, r) => s + r.duration, 0) / results.length)
|
||
: 0;
|
||
|
||
console.log(
|
||
`\n Sequential summary: ${results.length}/${SET_COUNT} succeeded | ` +
|
||
`${Math.round(totalDuration)}ms wall clock | ` +
|
||
`${avgDuration}ms avg per request | ` +
|
||
`${totalTokens} total tokens`
|
||
);
|
||
|
||
// Verify no duplicate correlation IDs (no retries created parallel entries)
|
||
const cids = results.map((r) => r.correlationId);
|
||
const uniqueCids = new Set(cids);
|
||
assert.equal(
|
||
uniqueCids.size,
|
||
cids.length,
|
||
`expected ${cids.length} unique correlation IDs, got ${uniqueCids.size} — duplicates detected`
|
||
);
|
||
assert.equal(results.length, SET_COUNT, `expected ${SET_COUNT} results, got ${results.length}`);
|
||
});
|
||
|
||
// ── Streaming-specific tests ────────────────────────────────────────────
|
||
|
||
test("[28] streaming: all payloads return content", { skip }, async () => {
|
||
const failures: string[] = [];
|
||
|
||
for (let i = 0; i < CASE_BUILDERS.length; i++) {
|
||
const tc = CASE_BUILDERS[i];
|
||
const label = `stream-${String(i + 1).padStart(2, "0")}: ${tc.name}`;
|
||
try {
|
||
const r = await sendAndValidate(label, tc.build);
|
||
if (r.contentLength === 0) {
|
||
failures.push(`${tc.name}: 0 bytes content`);
|
||
}
|
||
if (r.status !== 200) {
|
||
failures.push(`${tc.name}: HTTP ${r.status}`);
|
||
}
|
||
} catch (err) {
|
||
failures.push(`${tc.name}: ${err instanceof Error ? err.message : String(err)}`);
|
||
}
|
||
}
|
||
|
||
if (failures.length > 0) {
|
||
console.log(`\n Streaming failures (${failures.length}):`);
|
||
for (const f of failures) console.log(` ${f}`);
|
||
}
|
||
|
||
assert.equal(
|
||
failures.length,
|
||
0,
|
||
`${failures.length}/${CASE_BUILDERS.length} streaming payloads failed`
|
||
);
|
||
});
|
||
|
||
test("[29] streaming: correlation IDs are unique per request", { skip }, async () => {
|
||
const cids: string[] = [];
|
||
const count = 5;
|
||
|
||
for (let i = 0; i < count; i++) {
|
||
const tc = CASE_BUILDERS[i % CASE_BUILDERS.length];
|
||
const r = await sendAndValidate(`cid-${i + 1}: ${tc.name}`, tc.build);
|
||
cids.push(r.correlationId);
|
||
}
|
||
|
||
const unique = new Set(cids);
|
||
assert.equal(
|
||
unique.size,
|
||
count,
|
||
`expected ${count} unique CIDs, got ${unique.size}: ${cids.join(", ")}`
|
||
);
|
||
});
|
||
|
||
// ── Responses API — same coverage as the Chat Completions streaming tests
|
||
// above, but against /v1/responses (#7360 follow-up) ─────────────────────
|
||
|
||
test("[30] responses API: streaming payloads return content", { skip }, async () => {
|
||
const failures: string[] = [];
|
||
|
||
for (let i = 0; i < CASE_BUILDERS.length; i++) {
|
||
const tc = CASE_BUILDERS[i];
|
||
const label = `responses-${String(i + 1).padStart(2, "0")}: ${tc.name}`;
|
||
try {
|
||
const r = await sendAndValidate(label, tc.build, true, "responses");
|
||
if (r.contentLength === 0) {
|
||
failures.push(`${tc.name}: 0 bytes content`);
|
||
}
|
||
if (r.status !== 200) {
|
||
failures.push(`${tc.name}: HTTP ${r.status}`);
|
||
}
|
||
} catch (err) {
|
||
failures.push(`${tc.name}: ${err instanceof Error ? err.message : String(err)}`);
|
||
}
|
||
}
|
||
|
||
if (failures.length > 0) {
|
||
console.log(`\n Responses API streaming failures (${failures.length}):`);
|
||
for (const f of failures) console.log(` ${f}`);
|
||
}
|
||
|
||
assert.equal(
|
||
failures.length,
|
||
0,
|
||
`${failures.length}/${CASE_BUILDERS.length} Responses API streaming payloads failed`
|
||
);
|
||
});
|
||
|
||
test("[31] responses API: correlation IDs are unique per request", { skip }, async () => {
|
||
const cids: string[] = [];
|
||
const count = 5;
|
||
|
||
for (let i = 0; i < count; i++) {
|
||
const tc = CASE_BUILDERS[i % CASE_BUILDERS.length];
|
||
const r = await sendAndValidate(
|
||
`responses-cid-${i + 1}: ${tc.name}`,
|
||
tc.build,
|
||
true,
|
||
"responses"
|
||
);
|
||
cids.push(r.correlationId);
|
||
}
|
||
|
||
const unique = new Set(cids);
|
||
assert.equal(
|
||
unique.size,
|
||
count,
|
||
`expected ${count} unique CIDs, got ${unique.size}: ${cids.join(", ")}`
|
||
);
|
||
});
|