feat(issue-30): a stall watcher that only notifies

lib_py/stall_watch.py runs beside the wrapper's subscriber for a local herdr
job (started after delivery, stopped when the subscriber ends; MAM_STALL_WATCH=0
turns it off). It follows `herdr agent wait` transitions and publishes only
`progress` events through one publisher; it has no path that closes a job.

- blocked: `stalled:blocked <detection line>` once per episode, never answered.
- idle for MAM_STALL_IDLE_S (600) with no background descendants of the agent
  pid (pane process-info + /proc; adapter resident_children and the heartbeat
  timer excluded) and an empty input box: `stalled:idle` and one nudge.
- input box judged from adapter facts measured on herdr 0.9.1 (codex '›',
  grok frame '│', opencode '┃' block + stop pattern); the whole-pane fallback
  is gone. No facts: withheld + `stall_watch:input_check_unavailable` once;
  never empty for 3 x S: `stall_watch:input_never_empty` once.
- herdr failures are not "no event": warning + `stall_watch:herdr_unavailable:
  <code>` (or agent_not_found), backoff, rc 2 after MAM_STALL_HERDR_FAIL_S
  (120); the wrapper prints the watcher's last lines.
- remote and human jobs are skipped with one log line.
- agent_status_reliable is an adapter field; false turns idle judgement off.
- the loop runner relays stalled:/stall_watch: notices once each.
- scoped_env drops a pane-inherited workspace scope for name lookups (#34 rule).

The module sits at the top of lib_py: delegation and loop may not import the
agent adapters (their sibling-import rules). Idle pane captures of the five
CLIs are fixtures; the mock herdr answers process-info in the real shape.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

.agents/skills/lib_py/loop/runner.py

@@ -106,6 +106,7 @@ class LoopRunner:
         self.round_roots: List[str] = []
         self.wait_open_jobs = False
         self.failed_submit_jobs: Set[str] = set()
+        self._stall_seen: Dict[str, Tuple[int, Set[str]]] = {}
         self.current_plan = ""
         self.plan_job_id: Optional[str] = None
         self.base_commit = ""
@@ -637,6 +638,7 @@ class LoopRunner:
                     log_error(f"Job '{job_id}' record unreadable / status unknown; aborting wait.")
                     return False
 
+            self._relay_stall_warnings(job_id)
             if status == "completed":
                 if self.verbose:
                     log_success(f"Job '{job_id}' completed successfully.")
@@ -650,6 +652,30 @@ class LoopRunner:
         log_error(f"Job '{job_id}' timed out after {max_wait}s.")
         return False
 
+    def _relay_stall_warnings(self, job_id: str) -> None:
+        """Issue #30: surface the stall watcher's progress events (detail
+        `stalled:...` / `stall_watch:...`) in the loop log, once per detail.
+        Reads events.log incrementally; never closes the job."""
+        offset, seen = self._stall_seen.get(job_id, (0, set()))
+        try:
+            with open(self.jobs_dir / f"{job_id}.events.log", "r", encoding="utf-8") as fh:
+                fh.seek(offset)
+                lines = fh.readlines()
+                offset = fh.tell()
+        except OSError:
+            return
+        for line in lines:
+            try:
+                ev = json.loads(line)
+            except ValueError:
+                continue
+            detail = str(ev.get("detail") or "")
+            if ev.get("event") == "progress" and detail.startswith(("stalled:", "stall_watch:")) \
+                    and detail not in seen:
+                seen.add(detail)
+                log_warn(f"job {job_id}: {detail}")
+        self._stall_seen[job_id] = (offset, seen)
+
     # ------------------------------------------------------------------
     # Issue #34: a creator job's sub-jobs (registered with --parent-job)
     # ------------------------------------------------------------------

.agents/skills/lib_py/loop/watcher.py

@@ -74,21 +74,39 @@ def caller_server(environ=None):
     return ""
 
 
-def scoped_env(session=None, environ=None):
-    """The environment for a wait aimed at `session`.
+def _names_agent(argv) -> bool:
+    """True for a herdr call that looks an agent up by name (lib.sh
+    _herdr_scope_is_pane_inherited): `agent ...`, has-session, kill-session."""
+    args = list(argv or [])
+    if args and os.path.basename(args[0]) == "herdr":
+        args = args[1:]
+    while len(args) >= 2 and args[0] in ("-L", "--session"):
+        args = args[2:]
+    return bool(args) and args[0] in ("agent", "has-session", "kill-session")
 
-    Unchanged unless this process runs inside a pane of another server: only
-    then are the caller's own workspace/pane/tab ids meaningless for the call
-    and dropped. No pane and same-server keep every value.
+
+def scoped_env(session=None, environ=None, argv=None):
+    """The environment for a herdr call aimed at `session`.
+
+    Inside a pane of another server the caller's own workspace/pane/tab ids are
+    meaningless for the call and dropped (#23). On the same server, a call that
+    looks an agent up by name (`argv`) drops a HERDR_WORKSPACE_ID that is just
+    the caller pane's own workspace (#34, as mam_herdr does): agent names are
+    unique per server, and a worktree pane must reach an agent of mam-agent.
+    An id that disagrees with the pane, or one set outside a pane, still scopes.
     """
     src = os.environ if environ is None else environ
     caller = caller_server(src)
     target = (session or "").strip()
     # `default` is the same sentinel build_argv reads: no --session flag, so
     # herdr answers on the ambient server - the caller's own.
-    if not caller or not target or target == "default" or caller == target:
-        return dict(src)
-    return dict((k, v) for k, v in src.items() if k not in CALLER_SCOPE_VARS)
+    if caller and target and target != "default" and caller != target:
+        return dict((k, v) for k, v in src.items() if k not in CALLER_SCOPE_VARS)
+    ws = src.get("HERDR_WORKSPACE_ID") or ""
+    pane = src.get("HERDR_PANE_ID") or ""
+    if ws and pane and pane.split(":", 1)[0] == ws and _names_agent(argv):
+        return dict((k, v) for k, v in src.items() if k != "HERDR_WORKSPACE_ID")
+    return dict(src)
 
 
 class WaitOutcome(object):
@@ -144,7 +162,7 @@ def wait_once(target: str, until: Sequence[str] = DEFAULT_UNTIL,
     """One barrier call. `run` is injectable so tests never touch a real herdr."""
     argv = build_argv(target, until, timeout_ms, session=session)
     try:
-        proc = run(argv, capture_output=True, text=True, env=scoped_env(session))
+        proc = run(argv, capture_output=True, text=True, env=scoped_env(session, argv=argv))
     except Exception as exc:
         return WaitOutcome(TRANSPORT_ERROR, detail="herdr could not be executed: {}".format(exc))