fix(mem0-plugin): remove noisy session-state dumps, match openclaw pattern

- Remove all background REST API transcript dumps (on_pre_compact.py,
  capture_compact_summary.py, on_pre_commit.py calls) that were creating
  noisy session_state and commit_context memories automatically
- Rewrite pre-compaction prompt to extract individual durable facts
  (decisions, learnings, anti-patterns) instead of session summary blobs
- Agent now decides what to store, matching openclaw's triage pattern:
  "Most sessions produce zero memory operations. That is correct."
- Fix auto_import.py to search git repo root for CLAUDE.md/AGENTS.md
  (was only searching plugin cwd, missing files in parent directory)
- Fix health check session tracker to check stats file directly instead
  of depending on CLAUDE_PLUGIN_ROOT env var
- Fix session-end report to print in SessionEnd hook (Stop hook output
  doesn't render on /exit)
- Update v2 API endpoint to v3 in git commit capture search
- Keep auto_import.py as only direct REST write path (project profiles,
  idempotent, hash-gated)

mem0-plugin/scripts/on_post_compact.sh

@@ -40,9 +40,8 @@ You lost most conversation history. Recover context NOW:
 
 1. \`search_memories(query="session state current task", filters={"AND": [{"user_id": "$USER_ID"}, {"app_id": "$PROJECT_ID"}, {"metadata": {"type": "session_state"}}]})\`
 2. \`search_memories(query="recent decisions and learnings", filters={"AND": [{"user_id": "$USER_ID"}, {"app_id": "$PROJECT_ID"}, {"metadata": {"type": "decision"}}]})\`
-3. \`search_memories(query="compact summary", filters={"AND": [{"user_id": "$USER_ID"}, {"app_id": "$PROJECT_ID"}, {"metadata": {"type": "compact_summary"}}]})\`
 
-Run all 3 in parallel. Use results to resume work without asking user to repeat context.
+Run both in parallel. Use results to resume work without asking user to repeat context.
 EOF
 
 exit 0