diff --git a/packages/inference-service/src/providers/llamacpp.js b/packages/inference-service/src/providers/llamacpp.js index 46db8e1..41f4fb9 100644 --- a/packages/inference-service/src/providers/llamacpp.js +++ b/packages/inference-service/src/providers/llamacpp.js @@ -90,8 +90,6 @@ async function* completeStream(prompt, options = {}) { } console.log('[llamacpp] finalTokenCount:', finalTokenCount); -yield { response: '', done: true, model: finalModel, tokenCount: finalTokenCount }; - yield { response: '', done: true, model: finalModel, tokenCount: finalTokenCount }; } diff --git a/packages/orchestration-service/src/services/summarization.js b/packages/orchestration-service/src/services/summarization.js index 0ee9088..3527145 100644 --- a/packages/orchestration-service/src/services/summarization.js +++ b/packages/orchestration-service/src/services/summarization.js @@ -59,6 +59,7 @@ async function generateSummary(episodes, existingSummary = null) { } async function maybeSummarize(session, allEpisodes) { + console.log('[summarization] MEMORY_URL:', MEMORY_URL) // 1. Sum total tokens for this session const totalTokens = allEpisodes.reduce((sum, ep) => sum + (ep.token_count || 0), 0); if (totalTokens < THRESHOLD_TOKENS) return; // under threshold — nothing to do