Use trimmed transcript for session recap

README.md

@@ -101,7 +101,7 @@ scriptorium:
 
       inputs:
         transcript:
-          source: "processed_transcript"
+          source: "trimmed_transcript"
           required: true
 
         previous_recap:
@@ -133,7 +133,8 @@ For the initial implementation, only `session_recap` generation is supported.
 
 Analyze-stage session recap behavior:
 
-- uses processed transcript input (`transcripts/processed.json`)
+- defaults to trimmed transcript input (`transcripts/trimmed.json`) when configured with `source: trimmed_transcript`
+- still supports full polished transcript input (`transcripts/processed.json`) when configured with `source: processed_transcript`
 - optionally includes `previous_recap` when configured and resolvable
 - omits optional previous recap when unavailable
 - fails if required inputs are missing