msd-core/capabilities/external-job/capability.json

{
  "id": "external-job",
  "role": "feature",
  "version": "1.12.0",
  "title": "Async external-job scheduler adapter",
  "description": "Default-off producer of the async external-job manifest (#1164). At execute:wave:post an executor can externalize long-running compute (SLURM first, scheduler-pluggable), commit a .planning/async-jobs/<job>.json manifest, defer SUMMARY.md, and return external_job_waiting. The core loop (#1165) consumes the manifest; this capability is the only thing that writes it. NOTE on contribution point: #1164 specifies classification at execute:wave:pre and recording at execute:wave:post. This capability still contributes executor guidance at wave:post; execute-phase now renders wave:pre entries and dispatches generic step hooks there independently. Moving external-job classification to wave:pre is a separate capability change, not part of #4148. The adapter (scripts/slurm-adapter.cjs) reads external_job.submit_timeout_ms / poll_timeout_ms / artifact_dir through the canonical capability-config seam (env override > config > registry default).",
  "tier": "full",
  "requires": [],
  "engines": {
    "gsd": ">=1.7.0"
  },
  "runtimeCompat": {
    "supported": [
      "*"
    ],
    "unsupported": []
  },
  "skills": [],
  "agents": [],
  "hooks": [],
  "config": {
    "external_job.enabled": {
      "type": "boolean",
      "default": false,
      "description": "Master toggle for the async external-job producer capability. Default-off: the core loop consumes manifests whether or not this is on, but no manifest is ever written unless an executor opts in here."
    },
    "external_job.backend": {
      "type": "enum",
      "values": [
        "slurm"
      ],
      "default": "slurm",
      "description": "Scheduler backend. SLURM is the first adapter; the field is the pluggability seam for future backends (LSF, PBS, Kubernetes batch). Core never interprets this value."
    },
    "external_job.artifact_dir": {
      "type": "string",
      "default": "Artifacts/jobs",
      "description": "Root for per-job artifact directories (e.g. Artifacts/jobs/<jobid>/). Avoids fixed log paths and hardcoding a cluster/project layout. Surfaced by the adapter (`slurm-adapter.cjs submit` prints the resolved value); override via GSD_EXTERNAL_JOB_ARTIFACT_DIR."
    },
    "external_job.submit_timeout_ms": {
      "type": "number",
      "default": 30000,
      "description": "Hard timeout (ms) for the scheduler submit subprocess (e.g. sbatch). Bounded per CLAUDE.md unbounded-subprocess policy. Read by the adapter (env GSD_SLURM_SUBMIT_TIMEOUT_MS overrides)."
    },
    "external_job.poll_timeout_ms": {
      "type": "number",
      "default": 15000,
      "description": "Hard timeout (ms) for the scheduler poll subprocess (squeue, with sacct fallback). Read by the adapter (env GSD_SLURM_POLL_TIMEOUT_MS overrides)."
    }
  },
  "steps": [],
  "contributions": [
    {
      "point": "execute:wave:post",
      "into": "executor",
      "fragment": {
        "path": "fragments/execute-wave-post.md"
      },
      "produces": [
        ".planning/async-jobs/<job>.json"
      ],
      "consumes": [
        "PLAN.md"
      ],
      "when": "external_job.enabled",
      "onError": "skip"
    },
    {
      "point": "plan:post",
      "into": "planner",
      "fragment": {
        "path": "fragments/plan-post.md"
      },
      "produces": [],
      "consumes": [],
      "when": "external_job.enabled",
      "onError": "skip"
    }
  ],
  "gates": []
}