remove dead transcript mining pipeline

Delete enrich.rs (conversation extraction), select_conversation_fragments,
mark_observation_done, format_segment, and the {{conversations}} placeholder.
Transcript processing is handled by observe/journal agents now.

Co-Authored-By: Proof of Concept <poc@bcachefs.org>

src/subconscious/defs.rs

@@ -333,18 +333,6 @@ fn resolve(
             Some(Resolved { text, keys: result_keys })
         }
 
-        "conversations" => {
-            let fragments = super::knowledge::select_conversation_fragments(count);
-            let fragment_ids: Vec<String> = fragments.iter()
-                .map(|(id, _)| id.clone())
-                .collect();
-            let text = fragments.iter()
-                .map(|(id, text)| format!("### Session {}\n\n{}", id, text))
-                .collect::<Vec<_>>()
-                .join("\n\n---\n\n");
-            Some(Resolved { text, keys: fragment_ids })
-        }
-
         "siblings" | "neighborhood" => {
             let mut out = String::new();
             let mut all_keys: Vec<String> = Vec::new();