copilot-api-plus 1.0.46 → 1.0.48

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}/${maxPromptTokens}). Auto-truncating context...`);
+	console.log(`Context too long (${tokenCount.input}/${maxPromptTokens} tokens), truncating...`);
 	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} msgs. Tokens: ${tokenCount.input} -> ${newTokenCount.input}`);
 			}
 			return truncatedPayload;
 		}
@@ -3048,12 +3048,13 @@ async function handleCompletion$1(c) {
 				if (sseChunk.data && sseChunk.data !== "[DONE]") {
 					const parsed = JSON.parse(sseChunk.data);
 					if (parsed.usage) {
-						setTokenUsage({
+						const usage = {
 							inputTokens: parsed.usage.prompt_tokens ?? 0,
 							outputTokens: parsed.usage.completion_tokens ?? 0,
 							cacheReadTokens: parsed.usage.prompt_tokens_details?.cached_tokens
-						});
-						consola.info(`Token usage: in:${parsed.usage.prompt_tokens ?? 0} out:${parsed.usage.completion_tokens ?? 0}` + (parsed.usage.prompt_tokens_details?.cached_tokens ? ` cache_read:${parsed.usage.prompt_tokens_details.cached_tokens}` : ""));
+						};
+						setTokenUsage(usage);
+						console.log(`[${formatTokenUsage(usage)}]`);
 					}
 				}
 			} catch {}
@@ -3524,12 +3525,13 @@ async function handleCompletion(c) {
 			const chunk = JSON.parse(rawEvent.data);
 			const events$1 = translateChunkToAnthropicEvents(chunk, streamState);
 			if (chunk.usage) {
-				setTokenUsage({
+				const usage = {
 					inputTokens: chunk.usage.prompt_tokens - (chunk.usage.prompt_tokens_details?.cached_tokens ?? 0),
 					outputTokens: chunk.usage.completion_tokens,
 					cacheReadTokens: chunk.usage.prompt_tokens_details?.cached_tokens
-				});
-				consola.info(`Token usage: in:${chunk.usage.prompt_tokens - (chunk.usage.prompt_tokens_details?.cached_tokens ?? 0)} out:${chunk.usage.completion_tokens}` + (chunk.usage.prompt_tokens_details?.cached_tokens ? ` cache_read:${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,