mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-11-22 04:19:40 +00:00
fix(usage): count speech and transcription once after the tip merge
The tip already writes a usage_history row for every speech and transcription call (recordMediaRequest), and the per-key USD limits count that row. Tagging those calls with the modal ledger tier as well would count each call twice. Only rerank, which writes no usage_history row, keeps the modal tier. The tests now check the speech ledger row keeps its own tier and that a transcription with no reported duration adds no spend.
This commit is contained in:
@@ -1 +1 @@
|
||||
- **fix(usage):** text-to-speech, speech-to-text and rerank spend now counts toward a key's daily, weekly and 5-hour USD limits. Transcription is priced per second from the duration the provider reports. ([#19754](https://github.com/cheaper-inference/OmniRoute/pull/19754))
|
||||
- **fix(usage):** rerank spend now counts toward a key's daily, weekly and 5-hour USD limits. Speech and transcription already count through their usage history rows and are counted once. ([#19754](https://github.com/cheaper-inference/OmniRoute/pull/19754))
|
||||
|
||||
@@ -221,15 +221,14 @@ export function aggregateLedger(
|
||||
export const SEARCH_LEDGER_SERVICE_TIER = "search";
|
||||
|
||||
/**
|
||||
* `service_tier` marker on speech, transcription and rerank ledger rows. Those calls write no
|
||||
* usage_history row, so per-key USD limits read their spend from the ledger. Image calls are not
|
||||
* tagged: the ones that report usage already have a usage_history row, and counting both would
|
||||
* charge them twice.
|
||||
* `service_tier` marker on rerank ledger rows. Rerank writes no usage_history row, so per-key USD
|
||||
* limits read its spend from the ledger. Speech, transcription and image calls are not tagged: they
|
||||
* already have a usage_history row, and counting both would charge them twice.
|
||||
*/
|
||||
export const MODAL_LEDGER_SERVICE_TIER = "modal";
|
||||
|
||||
/**
|
||||
* Total web-search and modal (speech, transcription, rerank) spend for an api key since an ISO
|
||||
* Total web-search and modal (rerank) spend for an api key since an ISO
|
||||
* timestamp, failed calls included (a provider that reports a cost on an error status still
|
||||
* charged).
|
||||
*/
|
||||
|
||||
@@ -1,8 +1,9 @@
|
||||
// Per-key USD limits (daily / weekly / 5 h) re-price usage_history and add the
|
||||
// search ledger tier. Speech, transcription and rerank calls write no
|
||||
// usage_history row, so their spend never moved a limit. They now write a
|
||||
// request_cost_ledger row tagged with the "modal" tier, and the limit readers
|
||||
// add that tier next to "search".
|
||||
// search ledger tier. Rerank calls write no usage_history row, so their spend
|
||||
// never moved a limit. They now write a request_cost_ledger row tagged with the
|
||||
// "modal" tier, and the limit readers add that tier next to "search". Speech and
|
||||
// transcription already write a usage_history row; their ledger row keeps its
|
||||
// own tier, so each call is counted exactly once.
|
||||
//
|
||||
// Every route test drives the public handler with a real key and a mocked
|
||||
// upstream, then reads the result through getApiKeyUsageLimitStatus, the code
|
||||
@@ -155,7 +156,11 @@ test("a $2 TTS call flips weeklyExceeded on a $1 weekly limit, and the next call
|
||||
const status = await statusOf(key.key);
|
||||
assert.ok(Math.abs(status.weeklySpentUsd - 2) < 1e-9, `weekly spend ${status.weeklySpentUsd}`);
|
||||
assert.equal(status.weeklyExceeded, true);
|
||||
assert.deepEqual(ledgerTiers(key.id), ["modal"]);
|
||||
assert.deepEqual(
|
||||
ledgerTiers(key.id),
|
||||
["standard"],
|
||||
"speech counts from usage_history, not twice"
|
||||
);
|
||||
|
||||
const blocked = await speak();
|
||||
assert.equal(blocked.status, 429);
|
||||
@@ -254,7 +259,7 @@ test("a transcription call priced per second flips weeklyExceeded on a $1 weekly
|
||||
assert.equal(status.weeklyExceeded, true);
|
||||
});
|
||||
|
||||
test("a transcription whose upstream reports no duration charges nothing", async () => {
|
||||
test("a transcription whose upstream reports no duration adds no spend", async () => {
|
||||
saveSyncedPricing({
|
||||
openai: { "whisper-1": { input: 0, output: 0, input_cost_per_second: 0.02 } },
|
||||
});
|
||||
@@ -276,7 +281,8 @@ test("a transcription whose upstream reports no duration charges nothing", async
|
||||
await new Promise((resolve) => setTimeout(resolve, 100));
|
||||
|
||||
assert.deepEqual(ledgerTiers(key.id), []);
|
||||
assert.equal((await statusOf(key.key)).weeklyExceeded, false);
|
||||
// The call is unpriced, so `weeklyExceeded` follows the unpriced-usage policy (fail closed by default).
|
||||
assert.equal((await statusOf(key.key)).weeklySpentUsd, 0);
|
||||
});
|
||||
|
||||
test("modal ledger spend counts in the daily, weekly and 5h windows; the 5h reset follows its timestamp", async () => {
|
||||
|
||||
Reference in New Issue
Block a user