copilot-api-plus 1.0.45 → 1.0.47

package/dist/main.js

@@ -2875,7 +2875,7 @@ const truncateMessages = async (payload, model) => {
 	const tokenCount = await getTokenCount(payload, model);
 	const safeLimit = Math.floor(maxPromptTokens * .95);
 	if (tokenCount.input <= safeLimit) return payload;
-	consola.warn(`Prompt tokens (${tokenCount.input}) exceed safe limit (${safeLimit}/${maxPromptTokens}). Auto-truncating context...`);
+	console.log(`WARN  Prompt tokens (${tokenCount.input}) exceed safe limit (${safeLimit}/${maxPromptTokens}). Auto-truncating context...`);
 	const groups = groupMessages(payload.messages);
 	const systemGroups = groups.filter((g) => g.isSystem);
 	const conversationGroups = groups.filter((g) => !g.isSystem);
@@ -2902,7 +2902,7 @@ const truncateMessages = async (payload, model) => {
 		if (newTokenCount.input <= safeLimit) {
 			if (dropCount > 0) {
 				const droppedMessages = conversationGroups.slice(0, dropCount).reduce((sum, g) => sum + g.messages.length, 0);
-				consola.info(`Truncated ${droppedMessages} messages (${dropCount} conversation groups). Tokens: ${tokenCount.input} -> ${newTokenCount.input} (limit: ${maxPromptTokens})`);
+				console.log(`Truncated ${droppedMessages} messages (${dropCount} groups). Tokens: ${tokenCount.input} -> ${newTokenCount.input} (limit: ${maxPromptTokens})`);
 			}
 			return truncatedPayload;
 		}
@@ -2954,10 +2954,14 @@ const createChatCompletions = async (payload) => {
 		endpoint: `${copilotBaseUrl(state)}/chat/completions`
 	});
 	const url = `${copilotBaseUrl(state)}/chat/completions`;
+	const body = payload.stream ? {
+		...payload,
+		stream_options: { include_usage: true }
+	} : payload;
 	const fetchOptions = {
 		method: "POST",
 		headers,
-		body: JSON.stringify(payload)
+		body: JSON.stringify(body)
 	};
 	const maxRetries = 2;
 	let lastError;
@@ -3043,11 +3047,15 @@ async function handleCompletion$1(c) {
 				const sseChunk = chunk;
 				if (sseChunk.data && sseChunk.data !== "[DONE]") {
 					const parsed = JSON.parse(sseChunk.data);
-					if (parsed.usage) setTokenUsage({
-						inputTokens: parsed.usage.prompt_tokens ?? 0,
-						outputTokens: parsed.usage.completion_tokens ?? 0,
-						cacheReadTokens: parsed.usage.prompt_tokens_details?.cached_tokens
-					});
+					if (parsed.usage) {
+						const usage = {
+							inputTokens: parsed.usage.prompt_tokens ?? 0,
+							outputTokens: parsed.usage.completion_tokens ?? 0,
+							cacheReadTokens: parsed.usage.prompt_tokens_details?.cached_tokens
+						};
+						setTokenUsage(usage);
+						console.log(`[${formatTokenUsage(usage)}]`);
+					}
 				}
 			} catch {}
 			await stream.writeSSE(chunk);
@@ -3516,11 +3524,15 @@ async function handleCompletion(c) {
 			if (!rawEvent.data) continue;
 			const chunk = JSON.parse(rawEvent.data);
 			const events$1 = translateChunkToAnthropicEvents(chunk, streamState);
-			if (chunk.usage) setTokenUsage({
-				inputTokens: chunk.usage.prompt_tokens - (chunk.usage.prompt_tokens_details?.cached_tokens ?? 0),
-				outputTokens: chunk.usage.completion_tokens,
-				cacheReadTokens: chunk.usage.prompt_tokens_details?.cached_tokens
-			});
+			if (chunk.usage) {
+				const usage = {
+					inputTokens: chunk.usage.prompt_tokens - (chunk.usage.prompt_tokens_details?.cached_tokens ?? 0),
+					outputTokens: chunk.usage.completion_tokens,
+					cacheReadTokens: chunk.usage.prompt_tokens_details?.cached_tokens
+				};
+				setTokenUsage(usage);
+				console.log(`[${formatTokenUsage(usage)}]`);
+			}
 			for (const event of events$1) await stream.writeSSE({
 				event: event.type,
 				data: JSON.stringify(event)