@jambonz/llm 0.5.0 → 0.5.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/index.cjs +14 -0
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.cts +2 -2
- package/dist/index.d.ts +2 -2
- package/dist/index.js +14 -0
- package/dist/index.js.map +1 -1
- package/dist/test-kit/index.cjs +14 -0
- package/dist/test-kit/index.cjs.map +1 -1
- package/dist/test-kit/index.d.cts +1 -1
- package/dist/test-kit/index.d.ts +1 -1
- package/dist/test-kit/index.js +14 -0
- package/dist/test-kit/index.js.map +1 -1
- package/dist/{types-BWsmVtXv.d.cts → types-BEgQaQIb.d.cts} +23 -0
- package/dist/{types-BWsmVtXv.d.ts → types-BEgQaQIb.d.ts} +23 -0
- package/package.json +1 -1
package/dist/index.cjs
CHANGED
|
@@ -130,6 +130,9 @@ async function* streamFromOpenAI(client, req, options) {
|
|
|
130
130
|
const param = options.tokensParam ?? (needsMaxCompletionTokens(req.model) ? "max_completion_tokens" : "max_tokens");
|
|
131
131
|
body[param] = effectiveMaxTokens;
|
|
132
132
|
}
|
|
133
|
+
const t0 = process.hrtime.bigint();
|
|
134
|
+
let t1;
|
|
135
|
+
let t2;
|
|
133
136
|
let stream;
|
|
134
137
|
let responseHeaders;
|
|
135
138
|
try {
|
|
@@ -142,6 +145,7 @@ async function* streamFromOpenAI(client, req, options) {
|
|
|
142
145
|
} else {
|
|
143
146
|
stream = await apiPromise;
|
|
144
147
|
}
|
|
148
|
+
t1 = process.hrtime.bigint();
|
|
145
149
|
} catch (err) {
|
|
146
150
|
if (isAbortError(err)) {
|
|
147
151
|
yield { type: "end", finishReason: "aborted" };
|
|
@@ -173,6 +177,7 @@ async function* streamFromOpenAI(client, req, options) {
|
|
|
173
177
|
const delta = choice.delta;
|
|
174
178
|
const finishReason = choice.finish_reason;
|
|
175
179
|
if (delta?.content) {
|
|
180
|
+
if (t2 === void 0) t2 = process.hrtime.bigint();
|
|
176
181
|
yield { type: "token", text: delta.content };
|
|
177
182
|
}
|
|
178
183
|
if (delta?.tool_calls) {
|
|
@@ -242,6 +247,14 @@ async function* streamFromOpenAI(client, req, options) {
|
|
|
242
247
|
endEvent.vendorMetadata = metadata;
|
|
243
248
|
}
|
|
244
249
|
}
|
|
250
|
+
if (t1 !== void 0) {
|
|
251
|
+
const t3 = process.hrtime.bigint();
|
|
252
|
+
endEvent.clientTiming = {
|
|
253
|
+
requestToHeadersMs: Number(t1 - t0) / 1e6,
|
|
254
|
+
...t2 !== void 0 ? { headersToFirstTokenMs: Number(t2 - t1) / 1e6 } : {},
|
|
255
|
+
totalMs: Number(t3 - t0) / 1e6
|
|
256
|
+
};
|
|
257
|
+
}
|
|
245
258
|
yield endEvent;
|
|
246
259
|
}
|
|
247
260
|
function appendOpenAIAssistantToolCall(history, toolCalls) {
|
|
@@ -2673,6 +2686,7 @@ var groqManifest = {
|
|
|
2673
2686
|
var GROQ_METADATA_EXTRACTOR = makeMetadataExtractor([
|
|
2674
2687
|
{ header: "x-request-id", key: "request_id" },
|
|
2675
2688
|
{ header: "x-groq-region", key: "region" },
|
|
2689
|
+
{ header: "openai-processing-ms", key: "processing_ms", numeric: true },
|
|
2676
2690
|
{ header: "x-ratelimit-remaining-requests", key: "requests_remaining", numeric: true },
|
|
2677
2691
|
{ header: "x-ratelimit-remaining-tokens", key: "tokens_remaining", numeric: true }
|
|
2678
2692
|
]);
|