fix(mem0-plugin): v0.2.2 (#5234)

2026-05-22 21:47:14 +05:30
parent 53a3998873
commit 16a7702d09
41 changed files with 889 additions and 675 deletions
@@ -98,6 +98,87 @@ If any failed:
 Imported <N>/<total> memories into project <project_id> (<failed> failed)
 ```

+## Importing from competing AI tools (`--tools`)
+
+When invoked with `--tools` (e.g., `/mem0:import --tools`), detect and import
+from competing AI tool configuration files:
+
+### Supported tools
+
+| Tool | File/directory |
+|------|---------------|
+| Cursor | `.cursorrules` |
+| GitHub Copilot | `.github/copilot-instructions.md` |
+| Cline | `memory-bank/` (directory of `.md` files) |
+| Continue | `.continue/rules.md` |
+
+### T1: Detect
+
+```bash
+test -f .cursorrules && echo "cursor: .cursorrules"
+test -f .github/copilot-instructions.md && echo "copilot: .github/copilot-instructions.md"
+test -d memory-bank/ && echo "cline: memory-bank/"
+test -f .continue/rules.md && echo "continue: .continue/rules.md"
+```
+
+### T2: Ask user
+
+List found files, ask which to import (numbers, comma-separated, or "all").
+If none found:
+```
+No competing tool configuration files found.
+Checked: .cursorrules, .github/copilot-instructions.md, memory-bank/, .continue/rules.md
+```
+
+### T3: Run import
+
+For each selected tool:
+```bash
+python3 "<PLUGIN_ROOT>/scripts/import_competing_tools.py" <tool> --path <file>
+```
+
+Tools: `cursorrules`, `copilot`, `cline`, `continue`.
+
+### T4: Report
+
+```
+Import complete.
+  Cursor:  <N> memories
+  Copilot: <N> memories
+  Total:   <N> memories imported into project <project_id>
+```
+
+Notes: `infer=False`, tagged `metadata.source=<tool>-import`, sections <50 chars
+skipped, chunks >10k chars truncated, safe to re-run (deduplication handles it).
+
+---
+
+## Importing Claude Code's native MEMORY.md
+
+When invoked with a path to Claude Code's native `MEMORY.md` file (typically
+`~/.claude/projects/<proj-key>/memory/MEMORY.md`), or when `on_session_start.sh`
+detects native auto-memory and the user chooses to import:
+
+1. Read the file. It contains newline-separated memory entries (one fact per line,
+   sometimes with `- ` bullet prefix).
+2. Split by non-empty lines. Each line becomes one memory.
+3. Skip lines shorter than 20 characters or lines that are just headers (`#`).
+4. For each line, call `add_memory` with:
+   - `messages=[{"role": "user", "content": "<line>"}]`
+   - `user_id=<active_user_id>`
+   - `app_id=<active_project_id>`
+   - `metadata={"type": "task_learning", "source": "memory-md-import", "confidence": 0.8}`
+   - `infer=False`
+5. Report: `Imported <N> memories from MEMORY.md into project <project_id>`
+6. Suggest disabling native auto-memory:
+   ```
+   To avoid duplicate memory systems, add to ~/.claude/settings.json:
+     "autoMemoryEnabled": false
+   ```
+
+This handles the cold-start gap when a user has been using Claude Code's native
+memory and switches to mem0.
+
 ## Error Handling

 - If the parser script is not found at `<PLUGIN_ROOT>/scripts/parse_export_file.py`, print an error and stop.