mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-26 09:52:11 +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>
240 lines
9.3 KiB
TypeScript
240 lines
9.3 KiB
TypeScript
/**
|
|
* In-memory request/token counters for Gemini models — tracks both RPD (daily),
|
|
* RPM (sliding 60s window), and TPM (sliding 60s token window) so that 429
|
|
* responses can be classified as either quota_exhausted (RPD hit),
|
|
* rate_limit_exceeded (RPM hit), or token_rate_exceeded (TPM hit).
|
|
*
|
|
* Gemini returns identical error bodies for all three, so we rely on
|
|
* published per-model limits from geminiRateLimits.json to distinguish them.
|
|
*
|
|
* Counters are incremented on every Gemini request so that once usage
|
|
* reaches the published limit, subsequent 429s are correctly classified.
|
|
*/
|
|
|
|
import geminiLimits from "../config/geminiRateLimits.json";
|
|
|
|
// ── RPD (daily) state ────────────────────────────────────────────────────────
|
|
|
|
interface DailyCount {
|
|
date: string; // "YYYY-MM-DD"
|
|
count: number;
|
|
}
|
|
|
|
const dailyCounts = new Map<string, DailyCount>();
|
|
|
|
// ── RPM (sliding 60s window) state ───────────────────────────────────────────
|
|
|
|
const minuteWindows = new Map<string, number[]>();
|
|
|
|
// ── TPM (sliding 60s token window) state ─────────────────────────────────────
|
|
|
|
const tokenWindows = new Map<string, number[]>();
|
|
|
|
// ── Helpers ──────────────────────────────────────────────────────────────────
|
|
|
|
function toDateKey(): string {
|
|
return new Date().toISOString().slice(0, 10);
|
|
}
|
|
|
|
function stripModelPrefix(modelId: string): string {
|
|
// Only strip the "gemini/" provider prefix, never "gemini-" which is part
|
|
// of the actual model name (e.g. "gemini-2.5-flash", "gemini-3.5-live-translate").
|
|
return modelId.replace(/^gemini\//, "").trim();
|
|
}
|
|
|
|
function lookupValue(modelId: string, field: "rpm" | "rpd" | "tpm"): number {
|
|
if (!modelId) return 0;
|
|
const key = stripModelPrefix(modelId);
|
|
const entry = (geminiLimits as Record<string, Record<string, number>>)[key];
|
|
if (!entry) {
|
|
for (const [knownKey, knownEntry] of Object.entries(geminiLimits)) {
|
|
if (key.endsWith(knownKey) || knownKey.endsWith(key)) {
|
|
const val = knownEntry[field];
|
|
return typeof val === "number" && val > 0 ? val : 0;
|
|
}
|
|
}
|
|
return 0;
|
|
}
|
|
const val = entry[field];
|
|
return typeof val === "number" && val > 0 ? val : 0;
|
|
}
|
|
|
|
// ── RPD exports ──────────────────────────────────────────────────────────────
|
|
|
|
export function getModelRpd(modelId: string): number {
|
|
return lookupValue(modelId, "rpd");
|
|
}
|
|
|
|
export function incrementDailyRequestCount(modelId: string): void {
|
|
if (!modelId) return;
|
|
const key = stripModelPrefix(modelId);
|
|
const today = toDateKey();
|
|
const existing = dailyCounts.get(key);
|
|
if (existing && existing.date === today) {
|
|
existing.count++;
|
|
} else {
|
|
dailyCounts.set(key, { date: today, count: 1 });
|
|
}
|
|
}
|
|
|
|
export function getDailyRequestCount(modelId: string): number {
|
|
if (!modelId) return 0;
|
|
const key = stripModelPrefix(modelId);
|
|
const today = toDateKey();
|
|
const entry = dailyCounts.get(key);
|
|
if (entry && entry.date === today) return entry.count;
|
|
return 0;
|
|
}
|
|
|
|
export function isRpdExhausted(modelId: string): boolean {
|
|
const rpd = getModelRpd(modelId);
|
|
if (rpd <= 0) return false;
|
|
return getDailyRequestCount(modelId) >= rpd;
|
|
}
|
|
|
|
// ── RPM exports ──────────────────────────────────────────────────────────────
|
|
|
|
export function getModelRpm(modelId: string): number {
|
|
return lookupValue(modelId, "rpm");
|
|
}
|
|
|
|
/** Prune timestamps older than 60 seconds from a model's window. */
|
|
function pruneMinuteWindow(key: string): void {
|
|
const now = Date.now();
|
|
const cutoff = now - 60_000;
|
|
const timestamps = minuteWindows.get(key);
|
|
if (!timestamps) return;
|
|
let i = 0;
|
|
while (i < timestamps.length && timestamps[i] < cutoff) i++;
|
|
if (i > 0) {
|
|
minuteWindows.set(key, timestamps.slice(i));
|
|
}
|
|
}
|
|
|
|
function pruneTokenWindow(key: string): void {
|
|
const now = Date.now();
|
|
const cutoff = now - 60_000;
|
|
const entries = tokenWindows.get(key);
|
|
if (!entries) return;
|
|
let i = 0;
|
|
while (i < entries.length && entries[i] < cutoff) i += 2;
|
|
if (i > 0) {
|
|
tokenWindows.set(key, entries.slice(i));
|
|
}
|
|
}
|
|
|
|
export function incrementMinuteRequestCount(modelId: string): void {
|
|
if (!modelId) return;
|
|
const key = stripModelPrefix(modelId);
|
|
pruneMinuteWindow(key);
|
|
const timestamps = minuteWindows.get(key) ?? [];
|
|
timestamps.push(Date.now());
|
|
minuteWindows.set(key, timestamps);
|
|
}
|
|
|
|
export function getMinuteRequestCount(modelId: string): number {
|
|
if (!modelId) return 0;
|
|
const key = stripModelPrefix(modelId);
|
|
pruneMinuteWindow(key);
|
|
return minuteWindows.get(key)?.length ?? 0;
|
|
}
|
|
|
|
export function isRpmExhausted(modelId: string): boolean {
|
|
const rpm = getModelRpm(modelId);
|
|
if (rpm <= 0) return false;
|
|
return getMinuteRequestCount(modelId) >= rpm;
|
|
}
|
|
|
|
// ── TPM exports ──────────────────────────────────────────────────────────────
|
|
|
|
export function getModelTpm(modelId: string): number {
|
|
return lookupValue(modelId, "tpm");
|
|
}
|
|
|
|
/**
|
|
* Record prompt token consumption for a Gemini model.
|
|
* Allows the per-minute token pre-check to avoid 429s.
|
|
*/
|
|
export function incrementTokenUsage(modelId: string, promptTokens: number): void {
|
|
if (!modelId || !Number.isFinite(promptTokens) || promptTokens <= 0) return;
|
|
const key = stripModelPrefix(modelId);
|
|
pruneTokenWindow(key);
|
|
const entries = tokenWindows.get(key) ?? [];
|
|
entries.push(Date.now(), promptTokens);
|
|
tokenWindows.set(key, entries);
|
|
}
|
|
|
|
export function getMinuteTokenCount(modelId: string): number {
|
|
if (!modelId) return 0;
|
|
const key = stripModelPrefix(modelId);
|
|
pruneTokenWindow(key);
|
|
const entries = tokenWindows.get(key);
|
|
if (!entries) return 0;
|
|
let total = 0;
|
|
for (let i = 1; i < entries.length; i += 2) {
|
|
total += entries[i];
|
|
}
|
|
return total;
|
|
}
|
|
|
|
export function isTpmExhausted(modelId: string): boolean {
|
|
const tpm = getModelTpm(modelId);
|
|
if (tpm <= 0) return false;
|
|
return getMinuteTokenCount(modelId) >= tpm;
|
|
}
|
|
|
|
// ── Text-based metric classification ─────────────────────────────────────────
|
|
|
|
/**
|
|
* Extract which quota class ("rpd" | "rpm" | "tpm") a Gemini 429 error text
|
|
* names, directly from Google's own metric identifier — e.g.:
|
|
* "Quota exceeded for metric: generativelanguage.googleapis.com/
|
|
* generate_content_free_tier_input_token_count, limit: 16000"
|
|
*
|
|
* This is authoritative (Google's own signal) and must be checked BEFORE the
|
|
* local usage counters (isRpdExhausted/isRpmExhausted/isTpmExhausted): those
|
|
* counters only increment via `incrementTokenUsage`/`incrementRequestCount`,
|
|
* which fire AFTER a request completes successfully. A request that gets
|
|
* REJECTED — especially the first of several concurrent requests that all
|
|
* trip the same per-minute limit before any of them completes — never
|
|
* contributes to the local counter, so `isTpmExhausted` reads 0 at the exact
|
|
* moment it needs to return true, and the generic "quota exceeded" text
|
|
* classifier (which matches ALL Gemini 429 bodies, per the file header)
|
|
* mis-classifies a genuine TPM/RPM burst as QUOTA_EXHAUSTED (midnight lockout)
|
|
* instead of RATE_LIMIT_EXCEEDED (short cooldown).
|
|
*/
|
|
export function classifyGeminiQuotaMetricFromText(
|
|
errorText: string | null | undefined
|
|
): "rpd" | "rpm" | "tpm" | null {
|
|
if (!errorText) return null;
|
|
const lower = errorText.toLowerCase();
|
|
if (!lower.includes("generativelanguage.googleapis.com")) return null;
|
|
if (lower.includes("_per_day") || lower.includes("per day")) return "rpd";
|
|
if (lower.includes("input_token_count") || lower.includes("token_count")) return "tpm";
|
|
if (lower.includes("_requests")) return "rpm";
|
|
return null;
|
|
}
|
|
|
|
// ── Increment both (convenience) ─────────────────────────────────────────────
|
|
|
|
/** Increment both daily and minute counters for a Gemini request. */
|
|
export function incrementRequestCount(modelId: string): void {
|
|
incrementDailyRequestCount(modelId);
|
|
incrementMinuteRequestCount(modelId);
|
|
}
|
|
|
|
// ── Composite check ──────────────────────────────────────────────────────────
|
|
|
|
/** Returns true if either RPM or TPM is exhausted for this model. */
|
|
export function isMinuteRateExhausted(modelId: string): boolean {
|
|
return isRpmExhausted(modelId) || isTpmExhausted(modelId);
|
|
}
|
|
|
|
// ── Reset (testing) ──────────────────────────────────────────────────────────
|
|
|
|
export function resetCounters(): void {
|
|
dailyCounts.clear();
|
|
minuteWindows.clear();
|
|
tokenWindows.clear();
|
|
}
|