5ae4ea4c84
* feat(#1105): add external-job capability (SLURM scheduler-adapter producer half) The async external-job consumer half (#1165) shipped long ago: the core loop reads .planning/async-jobs/<job>.json manifests and treats a non-terminal one as the legal external_job_waiting half-state. The PRODUCER half (#1164) was the remaining unimplemented piece of #1105. This adds the producer as a default-off capability: - capabilities/external-job/ — capability.json (execute:wave:post -> executor, plan:post -> planner contributions, external_job.* config keys, default-off) + fragments teaching runtime-budget classification and externalization. - src/external-job.cts -> gsd-core/bin/lib/external-job.cjs — pure producer module: SLURM state -> manifest-status map (no guessing), manifest build/validate (versioned stability contract), sbatch/squeue/sacct parsers, and a fail-closed manifest writer (refuses a second non-terminal job for a plan_id already in flight; refuses to clobber a malformed manifest). fs/clock seams for deterministic tests. - scripts/slurm-adapter.cjs — operator CLI (submit/poll/show) wrapping bounded sbatch/squeue/sacct subprocesses; surfaces manifest commands for confirmation and never auto-runs them (trust boundary). - tests/external-job.test.cjs — 23 behavioral + fast-check property tests. - docs/reference/long-running-operations.md + docs/how-to/async-external-jobs.md. - CONTEXT.md glossary entry for the External-job Capability. - Regenerated capability-registry.cjs; pruned the now-stale test-file-count allowlist entry (external-job is at the 2-file cap). * chore(#1105): backfill PR number in changeset * fix(#1105): sync capability artifacts + update registry shape-pin tests gsd-test caught that adding the external-job capability requires its dependent artifacts regenerated and its registry-shape drift absorbed: - sync-manifest-versions: stamp 1.7.0-rc.2 into capability.json (was 1.0.0). - gen-capability-matrix --write: regenerate docs/reference/capability-matrix.md. - gen-inventory-manifest --write: regenerate docs/INVENTORY-MANIFEST.json. - check-gap-analysis-plan-post-e2e: plan:post now has 1 contribution (external-job planner fragment) instead of 0. - execute-wave-post-gate-pipeline-e2e: execute:wave:post now has 2 contributions (mempalace + external-job) instead of 1. * fix(#1105): regenerate capability-registry after version stamp sync-manifest-versions re-stamped external-job/capability.json from 1.0.0 to 1.7.0-rc.2 after the last registry regeneration, leaving the committed capability-registry.cjs stale (CI gen-capability-registry --check failed). gsd-test masked this because its setup runs the full 'npm run build' (which regenerates the registry); CI's 'npm test' pretest only runs build:lib.
82 lines
2.6 KiB
JSON
82 lines
2.6 KiB
JSON
{
|
|
"id": "external-job",
|
|
"role": "feature",
|
|
"version": "1.7.0-rc.2",
|
|
"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.",
|
|
"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."
|
|
},
|
|
"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."
|
|
},
|
|
"external_job.poll_timeout_ms": {
|
|
"type": "number",
|
|
"default": 15000,
|
|
"description": "Hard timeout (ms) for the scheduler poll subprocess (squeue, with sacct fallback)."
|
|
}
|
|
},
|
|
"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": []
|
|
}
|