co-scientist-resumelisted

# co-scientist-resume Goal: - Resume one interrupted Co-Scientist run from persisted artifacts. Expected input: - one run directory such as `runs/test1` Execution steps: 1. Resolve the run directory relative to the repository root. 2. Confirm that `input.md` and `state/` artifacts exist. 3. Run: ```bash python -m tools.host.project_cli resume <run-dir> --skill co-scientist-pipeline ``` 4. Read `state/PIPELINE_STATE.json`, `state/CURRENT_STAGE.json`, and `state/HOST_AGENT_HANDOFF.json`. 5. Read the CLI JSON result and the run-local dashboard receipt artifacts: - `runs/<run_id>/dashboard/LINKS.md` - `runs/<run_id>/dashboard/LINKS.json` 6. If the CLI JSON contains `dashboardLinks`: - If `dashboard.status` is `running`, return `dashboardLinks.dashboard` as the primary dashboard URL and include the deep links. - If `dashboard.status` is `starting`, immediately run: ```bash python -m tools.host.project_cli dashboard <run-dir> ``` - Read the refreshed CLI JSON result plus `runs/<run_id>/dashboard/LINKS.md`. - If `runtime.status` is now `running`, return the refreshed `links.dashboard` URL as the primary dashboard URL and include the deep links. - If `runtime.status` is still `starting`, tell the user that the dashboard is still booting, point them to `runs/<run_id>/dashboard/LINKS.md`, and include the retry command: ```text $co-scientist-dashboard <run-dir> ``` 7. Run the resume validator before continuing: ```bash p