Mgeeeek
8cb4f09ded
Six independent fixes that make hook behaviour deterministic, debuggable, and free of silent footguns. Persist session_id in stored memories on_pre_compact.py now extracts session_id from the hook input and writes it under metadata.session_id, enabling search-by-session. Skip SessionStart bootstrap when MEM0_API_KEY is missing on_session_start.sh exits 0 early instead of emitting bootstrap text that instructs the agent to call mem0 MCP tools that would all fail without a key. Tighten block_memory_write.sh regex The old `*/memory/*.md` pattern blocked legitimate paths like docs/memory/architecture.md. New pattern blocks `*/MEMORY.md` and `*/.claude/memory/*` only -- the actual surfaces we want to protect. Opt-in debug logging via MEM0_DEBUG=1 Each hook (bash + python) redirects stderr / adds a FileHandler to ~/.mem0/hooks.log when MEM0_DEBUG is set. No helper module, no rotation -- KISS. Default behaviour is unchanged. Drop the duplicate PreCompact registration hooks.json and cursor-hooks.json had on_pre_compact.sh AND on_pre_compact.py registered on PreCompact, producing duplicate session-state writes. Drop the python entry. The python script stays alive -- on_stop.sh still spawns it as a session-end safety net. CI nudge Adds a single comment line to pyproject.toml because the repo's ci.yml path filters exclude mem0-plugin/-only PRs but the build_mem0/build_embedchain status checks are required by branch protection. Track the proper fix (path-conditional CI) as a follow-up.
34 lines
1.2 KiB
Bash
Executable File
34 lines
1.2 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Hook: TaskCompleted
|
|
#
|
|
# Fires when a task is marked as completed. Reminds Claude to extract
|
|
# and store learnings via the mem0 MCP tools.
|
|
#
|
|
# Input: JSON on stdin with task_id, task_subject, task_description
|
|
# Output: Text that becomes feedback to the model (exit 0)
|
|
|
|
set -euo pipefail
|
|
|
|
if [ -n "${MEM0_DEBUG:-}" ]; then
|
|
mkdir -p "$HOME/.mem0" && exec 2>>"$HOME/.mem0/hooks.log"
|
|
fi
|
|
|
|
INPUT=$(cat)
|
|
TASK_SUBJECT=$(echo "$INPUT" | jq -r '.task_subject // "unknown task"' 2>/dev/null || echo "unknown task")
|
|
|
|
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.
|
|
EOF
|
|
|
|
exit 0
|