basemind-doctor

# basemind-doctor — diagnose and recover basemind Use this when basemind isn't behaving: MCP tools aren't available or return errors, the statusline says **no index**, queries come back empty when they shouldn't, or the `basemind serve` MCP server appears dead. Every step here uses the **CLI**, so it works even when the MCP server is down. Important: a stdio MCP server (what `basemind serve` is) **cannot be restarted by an agent or by basemind itself** — a fresh process can't resume the client's MCP `initialize` handshake. Reconnecting the server is the **MCP client's** job (see step 4). What you _can_ do from here is make sure the index is healthy and clear anything blocking a restart. ## 1. Is there an index? ```sh basemind query status ``` - Errors / "no index" / `file_count: 0` with blobs present → the index is missing or lost. Build it: `basemind scan` (see the `basemind-scan` skill / `/bm-scan`). - Healthy `file_count` → the index is fine; the problem is the server connection (step 4). ## 2. Is a server already running (holding the lock)? If `basemind scan` fails with a lock error, a `basemind serve` (or `watch`) already owns the index for this repo. The lock-contention error itself names the live holder (command + pid) — it reads that from the `.lock.meta` sidecar next to the workspace `.lock`. Both live in this workspace's directory under the machine-global cache (Linux `~/.local/share/basemind/`, macOS `~/Library/Application Support/basemind/`; override `BAS...