JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(mem0-plugin): improve auto-triggering — pre-fetch, dedup, skill enforcement v0.2.3 (#5237)

Browse Source
This commit is contained in:
Kartik
2026-05-23 17:20:54 +05:30
committed by GitHub
parent 16a7702d09
commit 99beb007ab
54 changed files with 1817 additions and 1162 deletions
Download Patch File Download Diff File Expand all files Collapse all files
mem0-plugin/scripts/on_task_completed.sh
+1 -10
View File
@@ -25,16 +25,7 @@ _PROJECT="${MEM0_PROJECT_ID:-unknown}"
cat <<EOF
Task completed: "$TASK_SUBJECT"
Extract key learnings from this completed task and store them using the mem0 \`add_memory\` tool:
1. What strategy worked well? -> Store with metadata \`{"type": "task_learning"}\`
2. Were there failed approaches before finding the solution? -> Store with metadata \`{"type": "anti_pattern"}\`
3. Were there architectural decisions? -> Store with metadata \`{"type": "decision"}\`
4. Any new conventions or patterns established? -> Store with metadata \`{"type": "convention"}\`
Memories can be as detailed as needed — include full context, reasoning, code snippets, and examples.
Only store genuinely useful learnings — skip if the task was trivial.
Include \`app_id\` = \`"$_PROJECT"\` as a top-level parameter in every \`add_memory\` call (not in metadata).
Store 0-2 key learnings via \`add_memory\` with \`app_id="$_PROJECT"\`. Use types: \`decision\`, \`task_learning\`, \`anti_pattern\`, or \`convention\`. Skip if trivial.
EOF
# Telemetry (background, fire-and-forget)