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).

src/tool_security.py

@@ -14,6 +14,7 @@ logger = logging.getLogger(__name__)
 NON_ADMIN_BLOCKED_TOOLS = {
     "bash",
     "python",
+    "manage_bg_jobs",
     "read_file",
     "write_file",
     "edit_file",
@@ -114,6 +115,8 @@ _PLAN_MODE_KNOWN_MUTATORS = {
     # Shell is never read-only-safe; block it explicitly so it stays out of plan
     # mode even if the schema list fails to load.
     "bash", "python",
+    # Controls shell processes (kill); plan mode can't run bash anyway.
+    "manage_bg_jobs",
 }