utility inference cleanup

packages/memory-service/src/summarization/project.js

@@ -60,12 +60,20 @@ function buildProjectSummaryFromEpisodesPrompt(projectName, episodes) {
 
 async function generateProjectSummaryFromEpisodes(projectName, episodes) {
     const user = buildProjectSummaryFromEpisodesPrompt(projectName, episodes);
-    return utilityInference({ user, temperature: 0.2, maxTokens: 1200 });
+    return utilityInference({
+        user,
+        temperature: SUMMARIES.TEMPERATURE,
+        maxTokens: SUMMARIES.PROJECT_GEN_MAX_TOKENS,
+    });
 }
 
 async function generateProjectSummary(projectName, sessionSummaries) {
     const user = buildProjectSummaryPrompt(projectName, sessionSummaries);
-    return utilityInference({ user, temperature: 0.2, maxTokens: 1200 });
+    return utilityInference({
+        user,
+        temperature: SUMMARIES.TEMPERATURE,
+        maxTokens: SUMMARIES.PROJECT_GEN_MAX_TOKENS,
+    });
 }
 
 // Main entry point — called by the route handler

packages/orchestration-service/src/services/summarization.js

@@ -43,8 +43,8 @@ async function generateSummary(episodes, existingSummary = null) {
 
     const content = await utilityInference({
         user,
-        temperature: 0.2,   // slightly higher than entities — summaries benefit from some fluency
-        maxTokens: 500,     // generous but bounded — keeps summaries from running long
+        temperature: SUMMARIES.TEMPERATURE,
+        maxTokens: SUMMARIES.SESSION_GEN_MAX_TOKENS,
     });
 
     return content;

packages/shared/src/config/constants.js

@@ -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 = {