@zilliz/memsearch-opencode 0.2.1 → 0.3.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +19 -5
- package/index.ts +25 -8
- package/package.json +1 -1
- package/scripts/capture-daemon.py +352 -144
- package/scripts/opencode_turns.py +449 -0
- package/scripts/parse-transcript.py +61 -148
- package/skills/memory-recall/SKILL.md +2 -1
|
@@ -25,7 +25,8 @@ Search for memories relevant to: $ARGUMENTS
|
|
|
25
25
|
3. **Expand**: For each relevant result, run `memsearch expand <chunk_hash> --collection <collection name above>` to get the full markdown section with surrounding context.
|
|
26
26
|
|
|
27
27
|
4. **Deep drill (optional)**: If an expanded chunk contains transcript anchors (HTML comments with session info), and the original conversation seems critical:
|
|
28
|
-
- If the anchor contains `
|
|
28
|
+
- If the anchor contains `turn:`, run `python3 __INSTALL_DIR__/scripts/parse-transcript.py <session_id> --turn <turn_id> --context 3` to retrieve the original conversation around that turn.
|
|
29
|
+
- If the anchor only contains `db:` / `session:` with no turn cursor, run `python3 __INSTALL_DIR__/scripts/parse-transcript.py <session_id> --limit 10` to retrieve the most recent turns from the SQLite database.
|
|
29
30
|
- If the anchor format is unfamiliar (e.g. `transcript:`, `rollout:` instead of `db:`), try reading the referenced file directly to explore its structure and locate the relevant conversation by the session or turn identifiers in the anchor.
|
|
30
31
|
|
|
31
32
|
5. **Return results**: Output a curated summary of the most relevant memories. Be concise — only include information that is genuinely useful for the user's current question.
|