fix(kanban): suppress dispatcher stuck-warn when ready queue holds only non-spawnable assignees

After PR #20105 (dispatcher skips ready tasks whose assignee fails
``profile_exists()`` to prevent the orion-cc/orion-research crash
loop), the gateway and CLI emit a spurious "kanban dispatcher stuck:
ready queue non-empty for N consecutive ticks but 0 workers spawned"
warning every 5 minutes on multi-lane setups where the queue is
steadily full of human-pulled work assigned to terminal lanes.

The warn is intended to catch real failure modes (broken PATH,
missing venv, credential loss for a real Hermes profile). On a
multi-lane host it fires forever even though everything is healthy:
the dispatcher correctly chose not to spawn, and there is nothing
for the operator to fix.

Changes:

* ``DispatchResult`` gains a ``skipped_nonspawnable`` field
  (separate from ``skipped_unassigned``) so callers can distinguish
  "task missing an owner — operator should route it" from "task
  owned by a control-plane lane — terminal will pull it".
* ``dispatch_once`` routes the ``not profile_exists(assignee)`` skip
  into the new bucket (was lumped into ``skipped_unassigned``).
* New helper ``has_spawnable_ready(conn)`` returns True iff at least
  one ready+assigned+unclaimed task in the DB has an assignee that
  maps to a real Hermes profile. Falls back to legacy "any
  ready+assigned" when ``profile_exists`` is unimportable so degraded
  installs still surface the original warn.
* The gateway dispatcher (``gateway/run.py``) and the CLI standalone
  daemon (``hermes_cli/kanban.py``) both swap their cheap
  ``ready_nonempty`` probe to use ``has_spawnable_ready``. Stuck-warn
  now fires only when there is genuine spawnable work the dispatcher
  failed to start.
* CLI dispatch output prints ``Skipped (non-spawnable assignee —
  terminal lane, OK)`` for visibility without alarm.

Tests:

* New ``has_spawnable_ready`` cases (empty queue, terminal-lane
  only, mixed real+terminal).
* New ``test_dispatch_skips_nonspawnable_into_separate_bucket``
  verifies the bucketing change.
* Updated ``test_dispatch_skips_unassigned`` to assert no
  cross-leak.
* Added ``all_assignees_spawnable`` fixture in
  ``tests/hermes_cli/conftest.py`` and threaded it through dispatcher
  tests that use synthetic assignees ("alice", "bob"). PR #20105
  (the parent commit) silently broke 8 such tests by routing those
  assignees into ``skipped_nonspawnable`` instead of spawning; this
  PR repairs them as part of the same code area.

Verified locally: 246/246 kanban-suite tests pass.

Stacks on top of fix/kanban-dispatcher-skip-missing-profile-2026-05-05
(PR #20105). Reviewer: this PR is meant to merge AFTER #20105.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

tests/hermes_cli/conftest.py

@@ -0,0 +1,19 @@
+"""Fixtures shared across hermes_cli kanban tests."""
+
+from __future__ import annotations
+
+import pytest
+
+
+@pytest.fixture
+def all_assignees_spawnable(monkeypatch):
+    """Pretend every assignee maps to a real Hermes profile.
+
+    Most dispatcher tests use synthetic assignees ("alice", "bob") that
+    don't correspond to actual profile directories on disk. Without this
+    patch, the dispatcher's profile-exists guard (PR #20105) routes
+    those tasks into ``skipped_nonspawnable`` instead of spawning, which
+    would break tests that assert spawn behavior.
+    """
+    from hermes_cli import profiles
+    monkeypatch.setattr(profiles, "profile_exists", lambda name: True)

tests/hermes_cli/test_kanban_core_functionality.py

@@ -80,7 +80,7 @@ def test_no_idempotency_key_never_collides(kanban_home):
 # Spawn-failure circuit breaker
 # ---------------------------------------------------------------------------
 
-def test_spawn_failure_auto_blocks_after_limit(kanban_home):
+def test_spawn_failure_auto_blocks_after_limit(kanban_home, all_assignees_spawnable):
     """N consecutive spawn failures on the same task → auto_blocked."""
     def _bad_spawn(task, ws):
         raise RuntimeError("no PATH")
@@ -109,7 +109,7 @@ def test_spawn_failure_auto_blocks_after_limit(kanban_home):
         conn.close()
 
 
-def test_successful_spawn_resets_failure_counter(kanban_home):
+def test_successful_spawn_resets_failure_counter(kanban_home, all_assignees_spawnable):
     """A successful spawn clears the counter so past failures don't count
     against future retries of the same task."""
     calls = [0]
@@ -138,7 +138,7 @@ def test_successful_spawn_resets_failure_counter(kanban_home):
         conn.close()
 
 
-def test_workspace_resolution_failure_also_counts(kanban_home):
+def test_workspace_resolution_failure_also_counts(kanban_home, all_assignees_spawnable):
     """`dir:` workspace with no path should fail workspace resolution AND
     count against the failure budget — not just crash the tick."""
     conn = kb.connect()
@@ -824,7 +824,7 @@ def test_recompute_ready_emits_promoted_not_ready(kanban_home):
         conn.close()
 
 
-def test_spawn_failure_circuit_breaker_emits_gave_up(kanban_home):
+def test_spawn_failure_circuit_breaker_emits_gave_up(kanban_home, all_assignees_spawnable):
     def _bad(task, ws):
         raise RuntimeError("nope")
     conn = kb.connect()
@@ -840,7 +840,7 @@ def test_spawn_failure_circuit_breaker_emits_gave_up(kanban_home):
         conn.close()
 
 
-def test_spawned_event_emitted_with_pid(kanban_home):
+def test_spawned_event_emitted_with_pid(kanban_home, all_assignees_spawnable):
     """Successful spawn must append a ``spawned`` event with the pid in
     the payload so humans tailing events see pid tracking."""
     def _spawn_returns_pid(task, ws):
@@ -1154,7 +1154,7 @@ def test_run_on_block_with_reason(kanban_home):
         conn.close()
 
 
-def test_run_on_spawn_failure_records_failed_runs(kanban_home):
+def test_run_on_spawn_failure_records_failed_runs(kanban_home, all_assignees_spawnable):
     """Each spawn_failed event closes a run with outcome='spawn_failed',
     and the Nth failure closes a run with outcome='gave_up'."""
     def _bad(task, ws):

tests/hermes_cli/test_kanban_db.py

@@ -327,7 +327,7 @@ def test_worker_context_includes_parent_results_and_comments(kanban_home):
 # Dispatcher
 # ---------------------------------------------------------------------------
 
-def test_dispatch_dry_run_does_not_claim(kanban_home):
+def test_dispatch_dry_run_does_not_claim(kanban_home, all_assignees_spawnable):
     with kb.connect() as conn:
         t1 = kb.create_task(conn, title="a", assignee="alice")
         t2 = kb.create_task(conn, title="b", assignee="bob")
@@ -344,10 +344,58 @@ def test_dispatch_skips_unassigned(kanban_home):
         t = kb.create_task(conn, title="floater")
         res = kb.dispatch_once(conn, dry_run=True)
     assert t in res.skipped_unassigned
+    assert t not in res.skipped_nonspawnable
     assert not res.spawned
 
 
-def test_dispatch_promotes_ready_and_spawns(kanban_home):
+def test_dispatch_skips_nonspawnable_into_separate_bucket(kanban_home, monkeypatch):
+    """Tasks whose assignee fails profile_exists() must NOT land in
+    ``skipped_unassigned`` (which is operator-actionable) — they go in
+    the dedicated ``skipped_nonspawnable`` bucket so health telemetry
+    can suppress false-positive "stuck" warnings."""
+    from hermes_cli import profiles
+    monkeypatch.setattr(profiles, "profile_exists", lambda name: False)
+    with kb.connect() as conn:
+        t = kb.create_task(conn, title="for-terminal", assignee="orion-cc")
+        res = kb.dispatch_once(conn, dry_run=True)
+    assert t in res.skipped_nonspawnable
+    assert t not in res.skipped_unassigned
+    assert not res.spawned
+
+
+def test_has_spawnable_ready_false_when_only_terminal_lanes(kanban_home, monkeypatch):
+    """``has_spawnable_ready`` returns False when every ready task is
+    assigned to a control-plane lane — used by gateway/CLI dispatchers
+    to silence the stuck-warn while terminals still have queued work."""
+    from hermes_cli import profiles
+    monkeypatch.setattr(profiles, "profile_exists", lambda name: False)
+    with kb.connect() as conn:
+        kb.create_task(conn, title="t1", assignee="orion-cc")
+        kb.create_task(conn, title="t2", assignee="orion-research")
+        assert kb.has_spawnable_ready(conn) is False
+
+
+def test_has_spawnable_ready_true_when_real_profile_present(kanban_home, monkeypatch):
+    """``has_spawnable_ready`` returns True as soon as ANY ready task
+    has an assignee that maps to a real Hermes profile — preserves the
+    real "stuck" signal when a daily/agent task is queued."""
+    from hermes_cli import profiles
+    monkeypatch.setattr(
+        profiles, "profile_exists", lambda name: name == "daily"
+    )
+    with kb.connect() as conn:
+        kb.create_task(conn, title="terminal-task", assignee="orion-cc")
+        kb.create_task(conn, title="hermes-task", assignee="daily")
+        assert kb.has_spawnable_ready(conn) is True
+
+
+def test_has_spawnable_ready_false_on_empty_queue(kanban_home):
+    """Empty queue is the trivial false case — no ready tasks at all."""
+    with kb.connect() as conn:
+        assert kb.has_spawnable_ready(conn) is False
+
+
+def test_dispatch_promotes_ready_and_spawns(kanban_home, all_assignees_spawnable):
     spawns = []
 
     def fake_spawn(task, workspace):
@@ -368,7 +416,7 @@ def test_dispatch_promotes_ready_and_spawns(kanban_home):
         assert kb.get_task(conn, c).status == "running"
 
 
-def test_dispatch_spawn_failure_releases_claim(kanban_home):
+def test_dispatch_spawn_failure_releases_claim(kanban_home, all_assignees_spawnable):
     def boom(task, workspace):
         raise RuntimeError("spawn failed")