wise-workflow-status

# /wise-workflow-status Before asking any user question, read and follow the [question lifecycle](../../references/workflow-host-control.md#keep-asynchronous-questions-open). Keep asynchronous prompts open until answered; this rule does not authorize questions in autonomous or otherwise prompt-free procedures. First read [host control](../../references/workflow-host-control.md). Resolve the loaded installation, set `WISE_HOST` to this conductor and `WISE_PLUGIN_ROOT` to that installation. Use its managed launcher for shell commands. Follow the reference's diagnostics and explicit-answer fallback when MCP or a native picker is unavailable. Conductor host and child provider are independent. `wise_status` comes from the managed `wise-engine` MCP server. On `DAEMON_UNAVAILABLE`, follow host-control diagnostics before retrying. ## No argument `wise_status {}` returns `RunSummary[]`, newest activity first. Render one table: run id | workflow | status | started | cwd | children. The children column lists each live child as `<step> turn <n> <tool>`, or `-`. Empty list: `No engine runs yet.` If legacy history is requested, get the canonical root with `python3 "${WISE_PLUGIN_ROOT}/scripts/wise-helpers.py" runs-root`, then use that helper's `list-runs <root>` command. It reports v1 entries as read-only legacy notices; they cannot resume. Keep all history files unchanged. ## With a run id `wise_status {run_id}` returns one `RunSummary`. Print run id, workflow, status, s...