feat(agent): add manage_bg_jobs tool to inspect and kill background bash jobs (#4577)

Detached bash jobs (#!bg) could be launched and auto-reported on completion,
but the agent had no way to act on a running one: no on-demand output read and
no kill (it blocked until the 1h max-runtime). bg_jobs had the pieces
(_read_output, list_for_session, internal _kill) but none was exposed.

Adds:
- bg_jobs.kill(job_id): tears down the process tree, marks the job killed, and
  sets followed_up so the monitor does not also auto-continue a deliberate kill.
- manage_bg_jobs registry tool with actions list / output / kill, scoped to the
  chat that launched the job (cross-session access reads as not found).
- Wiring: TOOL_HANDLERS/TAGS, function schema, RAG index + keyword hints, parser
  name map, dispatch (threads session_id via _direct_fallback). Gated like bash
  (NON_ADMIN_BLOCKED_TOOLS; plan-mode mutator).
- agent_loop: background-job intent regex maps to the files domain (and the tool
  joins _DOMAIN_TOOL_MAP[files]) so short commands like 'kill that job' are not
  dropped by the low-signal gate that skips tool retrieval.
- bg launch message tells the model to call manage_bg_jobs itself for check/stop
  rather than printing raw tool syntax to the user.

Tests: tests/test_bg_job_tools.py (kill semantics, per-chat scoping, actions,
and the intent classifier).
This commit is contained in:
Kenny Van de Maele
2026-06-19 09:28:22 +02:00
committed by GitHub
parent 39a802bea2
commit cdae9879f2
10 changed files with 347 additions and 5 deletions
+23 -1
View File
@@ -263,10 +263,32 @@ def list_for_session(session_id: str) -> List[Dict[str, Any]]:
return [r for r in refresh().values() if r.get("session_id") == session_id]
def kill(job_id: str) -> Optional[Dict[str, Any]]:
"""Terminate a running job's process tree and mark it killed. Returns the
updated record, or None if the id is unknown. Idempotent: a job that already
finished is returned unchanged. Sets followed_up so the monitor does not also
fire an auto-continue for a job the agent deliberately stopped."""
jobs = _load()
rec = jobs.get(job_id)
if rec is None:
return None
if rec.get("status") == "running":
_kill(rec.get("pid"))
rec["status"] = "failed"
rec["exit_code"] = -1
rec["ended_at"] = time.time()
rec["killed"] = True
rec["followed_up"] = True
_save(jobs)
return rec
def result_text(rec: Dict[str, Any]) -> str:
"""Human/agent-readable summary of a finished job, for the follow-up."""
out = _read_output(rec)
if rec.get("timed_out"):
if rec.get("killed"):
head = "Background job was killed."
elif rec.get("timed_out"):
head = f"Background job timed out after {rec.get('max_runtime_s')}s."
elif rec.get("died"):
head = "Background job process died unexpectedly (no exit code)."