experience-mine: link at creation time, remove # from new keys

Update the experience mining prompt to output links alongside journal
entries. The LLM now returns a "links" array per entry pointing to
existing semantic nodes. Rust code creates the links immediately after
node creation — new nodes arrive pre-connected instead of orphaned.

Also: remove # from all key generation paths (experience miner,
digest section keys, observed transcript keys). New nodes get clean
dash-separated keys.

Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>

poc-memory/src/agents/digest.rs

@@ -365,7 +365,7 @@ fn normalize_link_key(raw: &str) -> String {
     } else if key.contains('#') {
         let (file, section) = key.split_once('#').unwrap();
         if let Some(bare) = file.strip_suffix(".md") {
-            key = format!("{}#{}", bare, section);
+            key = format!("{}-{}", bare, section);
         }
     }
 

poc-memory/src/agents/enrich.rs

@@ -26,7 +26,7 @@ fn transcript_dedup_key(path: &str) -> Result<String, String> {
     let bytes = fs::read(path).map_err(|e| format!("read {}: {}", path, e))?;
     let mut hasher = DefaultHasher::new();
     bytes.hash(&mut hasher);
-    Ok(format!("_mined-transcripts#h-{:016x}", hasher.finish()))
+    Ok(format!("_mined-transcripts-h-{:016x}", hasher.finish()))
 }
 
 /// Check if a transcript has already been mined (dedup key exists in store).
@@ -111,7 +111,7 @@ pub fn mark_segment(
 /// Get the set of all mined transcript keys (both content-hash and filename)
 /// from the store. Load once per daemon tick, check many.
 pub fn mined_transcript_keys() -> HashSet<String> {
-    keys_with_prefix("_mined-transcripts#")
+    keys_with_prefix("_mined-transcripts-")
 }
 
 
@@ -286,7 +286,7 @@ pub fn experience_mine(
     let mut hasher = DefaultHasher::new();
     transcript_bytes.hash(&mut hasher);
     let hash = hasher.finish();
-    let dedup_key = format!("_mined-transcripts#h-{:016x}", hash);
+    let dedup_key = format!("_mined-transcripts-h-{:016x}", hash);
 
     if store.nodes.contains_key(&dedup_key) {
         // Backfill per-segment key if called with a specific segment
@@ -390,9 +390,9 @@ pub fn experience_mine(
             .to_lowercase()
             .replace(' ', "-");
         let key = if ts.is_empty() {
-            format!("journal#j-mined-{}", key_slug)
+            format!("journal-j-mined-{}", key_slug)
         } else {
-            format!("journal#j-{}-{}", ts.to_lowercase().replace(':', "-"), key_slug)
+            format!("journal-j-{}-{}", ts.to_lowercase().replace(':', "-"), key_slug)
         };
 
         // Check for duplicate
@@ -413,6 +413,25 @@ pub fn experience_mine(
         let _ = store.upsert_node(node);
         count += 1;
 
+        // Apply links from LLM output
+        if let Some(links) = entry.get("links").and_then(|v| v.as_array()) {
+            for link_val in links {
+                if let Some(target) = link_val.as_str() {
+                    let target = target.to_string();
+                    if let Some(target_node) = store.nodes.get(&target) {
+                        let source_uuid = store.nodes.get(&key).map(|n| n.uuid).unwrap_or_default();
+                        let target_uuid = target_node.uuid;
+                        let rel = store::new_relation(
+                            source_uuid, target_uuid,
+                            store::RelationType::Link, 0.3,
+                            &key, &target,
+                        );
+                        let _ = store.add_relation(rel);
+                    }
+                }
+            }
+        }
+
         let preview = crate::util::truncate(content, 77, "...");
         println!("  + [{}] {}", ts, preview);
     }

poc-memory/src/agents/knowledge.rs

@@ -684,7 +684,7 @@ pub fn select_conversation_fragments(n: usize) -> Vec<(String, String)> {
     let projects = crate::config::get().projects_dir.clone();
     if !projects.exists() { return Vec::new(); }
 
-    let observed = super::enrich::keys_with_prefix(&format!("{}#", OBSERVED_PREFIX));
+    let observed = super::enrich::keys_with_prefix(&format!("{}-", OBSERVED_PREFIX));
 
     let mut jsonl_files: Vec<PathBuf> = Vec::new();
     if let Ok(dirs) = fs::read_dir(&projects) {

prompts/experience.md

@@ -36,16 +36,25 @@ Each entry should be 80-200 words. Quality over quantity.
 
 ## Output format
 
-Return a JSON array of entries, each with timestamp and content:
+Return a JSON array of entries. Each entry has timestamp, content, and links
+to existing semantic memory nodes that relate to this moment:
+
 ```json
 [
   {
     "timestamp": "2026-03-01T01:15",
-    "content": "Journal entry text here.\n\nwarmth:8 curiosity:7"
+    "content": "Journal entry text here.\n\nwarmth:8 curiosity:7",
+    "links": ["existing-node-key", "another-relevant-key"]
   }
 ]
 ```
 
+For the `links` field: look at the semantic memory nodes listed below and pick
+any that relate to this moment. A journal entry about intimacy should link to
+`inner-life-sexuality-intimacy`. An insight about code should link to the
+relevant `patterns-*` or `practices-*` node. 2-5 links per entry is ideal.
+If nothing fits, use an empty array.
+
 Return `[]` if there's nothing worth capturing that isn't already journaled.
 
 ---