utility inference cleanup

2026-08-17 23:48:15 -07:00
parent a223b753e5
commit 551c7f03ec
7 changed files with 53 additions and 52 deletions
@@ -78,6 +78,13 @@ const SUMMARIES = {
    MIN_EPISODES_SINCE: 5,      // don't resummarize until N new episodes since last summary
    MAX_SUMMARY_CHARS:  8000,   // max chars to include from recent episodes when generating summary (to control prompt size)
    MAX_PROJECT_EPISODE_LIMIT: 200, // max number of episodes to consider from the entire project when generating summary (to control prompt size)
+
+    // Generation params for the utility model (passed to utilityInference).
+    // Distinct from MAX_SUMMARY_TOKENS above, which gates STORED summary size;
+    // these two cap GENERATION length (num_predict) per summary type.
+    TEMPERATURE:            0.2,    // slightly higher than entities (0.1) — summaries benefit from some fluency
+    SESSION_GEN_MAX_TOKENS: 500,    // num_predict for a session summary (3-5 sentences)
+    PROJECT_GEN_MAX_TOKENS: 1200,   // num_predict for a project overview (multi-paragraph)
 }

 const ENTITIES = {