fix(dashboard): reset model state on agent switch

[Premshay]

Problem / Motivation

Switching a dashboard slot to another agent retained the previous agent's model pin and fallback recovery state. A replacement session could therefore send a model identifier that belongs to the old binding.

Why it matters

The next turn can start with an incompatible model instead of the target agent's default configuration.

What changed (motivation → approach → change)

Agent switches already reset their session before the next turn. The transaction now joins the existing model-pick lock, clears model and fallback state only when the agent changes, persists the blank model, and restores the prior state only for a proven pre-pop rollback. Same-agent resets leave model state unchanged.

Tests

• Added coverage for clearing and persisting model/fallback state on an agent change.
• Added coverage for preserving model state on a same-agent reset and restoring it after a pre-pop reset failure.
• �[1m============================= test session starts ==============================�[0m
  platform linux -- Python 3.14.4, pytest-8.4.2, pluggy-1.6.0
  rootdir: /home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset
  configfile: setup.cfg
  plugins: xdist-3.8.0, cov-6.3.0, timeout-2.4.0, hypothesis-6.165.2, asyncio-1.4.0, testmon-2.2.0
  timeout: 120.0s
  timeout method: signal
  timeout func_only: False
  asyncio: mode=Mode.STRICT, debug=False, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function
  created: 13/13 workers
  13 workers [769 items]

�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[33m [ 9%]
�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[33m [ 18%]
�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[33m [ 28%]
�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[33m [ 37%]
�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[33m [ 46%]
�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[33m [ 56%]
�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[33m [ 65%]
�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[33m [ 74%]
�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[33m [ 84%]
�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[33m [ 93%]
�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[32m.�[0m�[33m [100%]�[0m
�[33m=============================== warnings summary ===============================�[0m
../../KiroCrew/.venv/lib/python3.14/site-packages/xdist/plugin.py:289: 14 warnings
/home/prems/dev/repos/premshay/KiroCrew/.venv/lib/python3.14/site-packages/xdist/plugin.py:289: DeprecationWarning: The --looponfail command line argument and looponfailroots config variable are deprecated.
The loop-on-fail feature will be removed in pytest-xdist 4.0.
config.issue_config_time_warning(warning, 2)

test/test_dashboard_chat.py: 263 warnings
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/test/chat_test_helpers.py:231: NotAppKeyWarning: It is recommended to use web.AppKey instances for keys.
https://docs.aiohttp.org/en/stable/web_advanced.html#application-s-config
app["state"] = state

test/test_dashboard_chat.py: 13 warnings
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/test/chat_test_helpers.py:225: NotAppKeyWarning: It is recommended to use web.RequestKey instances for keys.
https://docs.aiohttp.org/en/stable/web_advanced.html#request-s-storage
request["app"] = "" # dashboard user, not an app

test/test_dashboard_chat.py: 13 warnings
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/test/chat_test_helpers.py:227: NotAppKeyWarning: It is recommended to use web.RequestKey instances for keys.
https://docs.aiohttp.org/en/stable/web_advanced.html#request-s-storage
request["user"] = "local-app" # recognized as owner

test/test_dashboard_chat.py: 96 warnings
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/src/kiro_crew/dashboard/chat_runner.py:2127: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
report = _session_mcp_report(provider)
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py: 71 warnings
/home/prems/dev/repos/premshay/KiroCrew/.venv/lib/python3.14/site-packages/_pytest/stash.py:108: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
del self._storage[key]
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py: 26 warnings
/usr/lib/python3.14/unittest/mock.py:2259: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
def init(self, name, parent):
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py: 12 warnings
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/src/kiro_crew/dashboard/handlers/usage.py:1049: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
return (int(used_fn()), int(window_fn()))
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py: 30 warnings
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/test/chat_test_helpers.py:267: NotAppKeyWarning: It is recommended to use web.AppKey instances for keys.
https://docs.aiohttp.org/en/stable/web_advanced.html#application-s-config
app["state"] = state

test/test_dashboard_chat.py::TestPythonStageLoop::test_queued_receipt_carries_the_entry_queue_id
/usr/lib/python3.14/contextlib.py:450: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
def exit(self, exctype, excinst, exctb):
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py: 61 warnings
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/test/chat_test_helpers.py:294: NotAppKeyWarning: It is recommended to use web.AppKey instances for keys.
https://docs.aiohttp.org/en/stable/web_advanced.html#application-s-config
app["state"] = state

test/test_dashboard_chat.py::TestRegenerateAndVariants::test_edit_resend_non_dict_body_is_400_not_500
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/test/test_dashboard_chat.py:13526: NotAppKeyWarning: It is recommended to use web.AppKey instances for keys.
https://docs.aiohttp.org/en/stable/web_advanced.html#application-s-config
app["state"] = state

test/test_dashboard_chat.py::TestRegenerateAndVariants::test_restore_preserves_variants
test/test_dashboard_chat.py::TestForkSlot::test_fork_copies_all_messages
/usr/lib/python3.14/collections/init.py:455: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
result = tuple_new(cls, iterable)
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py::TestForkSlot::test_fork_with_prompt
/usr/lib/python3.14/unittest/mock.py:2608: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
return tuple.new(cls, (name, args, kwargs))
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py::TestForkSlot::test_fork_reads_full_history_from_disk_when_memory_capped
test/test_dashboard_chat.py::TestBulkModelSwitch::test_switches_all_differing_slots_and_resets_each
:2: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py::TestStopReasonCancelled::test_monitor_wake_turn_does_not_write_user_memory
/usr/lib/python3.14/threading.py:290: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
def init(self, lock=None):
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py::TestStopReasonCancelled::test_cancelled_turn_restores_the_reinjection_flag
:53: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py::TestStopReasonCancelled::test_cancelled_turn_restores_the_reinjection_flag
test/test_dashboard_chat.py::TestStopReasonCancelled::test_landed_turn_does_not_restore_the_reinjection_flag
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/src/kiro_crew/dashboard/chat_runner.py:7179: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
model_window = window_for_provider_client(client)
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py::TestStopTurnSlotState::test_stop_turn_slot_state_transitions_soft
/usr/lib/python3.14/unittest/mock.py:455: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
if not issubclass(cls, AsyncMockMixin):
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py::TestRunChatTransientRetry::test_first_exhausted_cycle_never_discards
test/test_dashboard_chat.py::TestRunChatTransientRetry::test_canary_empty_reply_is_not_positive_evidence
test/test_dashboard_chat.py::TestRunChatTransientRetry::test_stop_during_canary_vetoes_discard_and_requeue
test/test_dashboard_chat.py::TestRunChatTransientRetry::test_transient_budget_refreshed_after_terminal_error
test/test_dashboard_chat.py::TestRunChatTransientRetry::test_poisoned_discard_is_one_shot_until_a_turn_lands
test/test_dashboard_chat.py::TestRunChatTransientRetry::test_unreadable_session_model_skips_canary_and_discard
test/test_dashboard_chat.py::TestRunChatTransientRetry::test_thinking_only_failures_never_accrue_discard_streak
test/test_dashboard_chat.py::TestRunChatTransientRetry::test_canary_failure_blocks_discard_and_preserves_one_shot
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/src/kiro_crew/llm_helpers.py:610: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
return advertised_model_ids(getter())
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py::TestStopTurnSlotState::test_single_press_empty_queue_goes_idle
/usr/lib/python3.14/unittest/mock.py:460: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
new = type(cls.name, bases, {'doc': cls.doc})
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py::TestRunChatTransientRetry::test_poisoned_conversation_discarded_on_second_exhausted_cycle
/usr/lib/python3.14/unittest/mock.py:430: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
def init(self, /, *args, **kwargs):
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py::TestRunChatTransientRetry::test_poisoned_conversation_discarded_on_second_exhausted_cycle
/usr/lib/python3.14/json/encoder.py:263: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
return _iterencode(o, 0)
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py::TestRunChatTransientRetry::test_cancelled_turn_does_not_rearm_poisoned_one_shot
/usr/lib/python3.14/ast.py:46: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
return compile(source, filename, mode, flags,
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py::TestRunChatTransientRetry::test_posttoken_suppressed_leaves_allowance_for_later_turn
/usr/lib/python3.14/unittest/mock.py:496: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
dict['_mock_mock_calls'] = _CallList()
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py::TestStopTurnSlotState::test_stop_event_replace_in_place
/usr/lib/python3.14/asyncio/selector_events.py:673: RuntimeWarning: coroutine 'AsyncMockMixin._execute_mock_call' was never awaited
def _sock_write_done(self, fd, fut, handle=None):
Enable tracemalloc to get traceback where the object was allocated.
See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

test/test_dashboard_chat.py::TestBulkModelSwitch::test_switches_all_differing_slots_and_resets_each
test/test_dashboard_chat.py::TestBulkModelSwitch::test_already_on_target_is_unchanged_not_reset
test/test_dashboard_chat.py::TestBulkModelSwitch::test_reset_failure_is_isolated_and_reported
test/test_dashboard_chat.py::TestBulkModelSwitch::test_skips_running_slot_by_default
test/test_dashboard_chat.py::TestBulkModelSwitch::test_skip_running_false_forces_running_slot
test/test_dashboard_chat.py::TestBulkModelSwitch::test_app_caller_only_switches_own_slots
test/test_dashboard_chat.py::TestBulkModelSwitch::test_non_boolean_skip_running_is_rejected
test/test_dashboard_chat.py::TestBulkModelSwitch::test_canonical_key_rejected_no_slot_touched
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/test/test_dashboard_chat.py:19088: NotAppKeyWarning: It is recommended to use web.AppKey instances for keys.
https://docs.aiohttp.org/en/stable/web_advanced.html#application-s-config
app["state"] = state

test/test_dashboard_chat.py::TestSlotsGetWarmsGitLabAllowlist::test_cold_get_returns_the_authorized_self_hosted_link
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/test/test_dashboard_chat.py:19007: NotAppKeyWarning: It is recommended to use web.AppKey instances for keys.
https://docs.aiohttp.org/en/stable/web_advanced.html#application-s-config
app["state"] = state

test/test_dashboard_chat.py::TestSlotModelGuard::test_canonical_key_rejected_slot_unchanged
test/test_dashboard_chat.py::TestSlotModelGuard::test_valid_kiro_alias_is_allowed
test/test_dashboard_chat.py::TestSlotModelGuard::test_auto_literal_is_allowed
test/test_dashboard_chat.py::TestSlotModelGuard::test_empty_string_auto_default_is_allowed
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/test/test_dashboard_chat.py:19323: NotAppKeyWarning: It is recommended to use web.AppKey instances for keys.
https://docs.aiohttp.org/en/stable/web_advanced.html#application-s-config
app["state"] = state

test/test_dashboard_chat.py: 25 warnings
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/test/test_dashboard_chat.py:19406: NotAppKeyWarning: It is recommended to use web.AppKey instances for keys.
https://docs.aiohttp.org/en/stable/web_advanced.html#application-s-config
app["state"] = state

test/test_dashboard_chat.py::TestBulkModelSwitch::test_falsy_non_string_marker_fails_closed
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/test/test_dashboard_chat.py:19270: NotAppKeyWarning: It is recommended to use web.AppKey instances for keys.
https://docs.aiohttp.org/en/stable/web_advanced.html#application-s-config
app_obj["state"] = state

test/test_dashboard_chat.py::TestBulkModelSwitch::test_missing_auth_marker_is_denied
/home/prems/dev/repos/premshay/.worktrees/kc-upstream-dashboard-agent-model-reset/test/test_dashboard_chat.py:19243: NotAppKeyWarning: It is recommended to use web.AppKey instances for keys.
https://docs.aiohttp.org/en/stable/web_advanced.html#application-s-config
bare_app["state"] = state

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
============================= slowest 5 durations ==============================
1.00s call test/test_dashboard_chat.py::TestOrchestratorPlanGateArming::test_stage_loop_times_out_a_stage_that_swallows_cancellation
0.45s call test/test_dashboard_chat.py::TestFullPaginationWalk::test_walk_all_pages
0.39s call test/test_dashboard_chat.py::TestSlotModelLiveSwitch::test_refused_pick_rollback_spares_a_newer_concurrent_pick
0.39s call test/test_dashboard_chat.py::TestSlotModelLiveSwitch::test_two_refused_picks_leave_the_slot_untouched
0.38s call test/test_dashboard_chat.py::TestResumeDedupe::test_resume_from_disk_sends_the_older_history_cursor
�[33m====================== �[32m769 passed�[0m, �[33m�[1m665 warnings�[0m�[33m in 10.78s�[0m�[33m ======================�[0m — 769 passed.

• Black, isort, flake8, diff validation, and documentation lint passed.

Manual verification

N/A — handler transaction, persistence, and rollback paths are covered by the dashboard suite.

Related Issues

N/A — identified during reconciliation of the fork's portable dashboard fixes.

Pattern harvest

Rule candidate: review-prompt

Pattern: Any binding switch that retains provider-specific state must clear or revalidate that state before the next provider session starts.

Checklist

• At most two commits (one is the norm), with a Conventional Commits title
• Existing tests pass and new tests added for new functionality
• Self-review completed; code follows project style guidelines
• Documentation updated
• No secrets, credentials, or internal references in the diff

Contribution License Agreement

From https://github.com/kirodotdev/KiroCrew

[github-actions]

Design Review (Fable 5.1, fork) — ✅ PASS

Design-level review of f481b7097338d01d51ba722eeeaaf937df9601bb via the fork AI-review pipeline — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS/CONCERNS are advisory.

Design is sound. Lock ordering (slot._lock → session lock → _model_pick_lock) matches the existing model handler, rollback is symmetric and identity-scoped, both local and remote paths are covered with tests, and the spec is updated in the same commit.

The change targets a real problem: on an agent switch the slot kept the old agent's provider-specific model id and fallback recovery state, which the replacement session would then send — producing a failed or wrong-model turn. Clearing to "" (provider default) is the proportionate fix; preserving the model only when providers happen to match would add resolution complexity for no guaranteed validity. Contract evolution is safe (persisted model="" resumes on default), and the failure path rolls back on commit-token identity so concurrent explicit picks keep their win.

Design-Verdict: PASS

Clearing provider-bound model/fallback state on agent switch is the right fix at the right layer, with rollback and lock discipline consistent with the existing model handler.

[DESIGN-REVIEWED] f481b70

[github-actions]

GPT 5.6 Review (fork) — 🔴 changes requested (blocking)

Reviewed f481b7097338d01d51ba722eeeaaf937df9601bb via the fork AI-review pipeline; updated in place on each push.

1 of 1 blocking finding(s) are security-class and were withheld from adjudication, so the blocking verdict stands.

BLOCKING -- src/kiro_crew/dashboard/chat_handlers.py:5684 -- Model reset occurs after an await (origin: validation)
if agent_changed: slot.model = _CommitToken("")
Agent switch + concurrent send during binding resolution -> _run_chat reads the old model -> replacement session starts with an incompatible model.
Anchor: residual/crash-data-loss-corruption
Fix: Clear model/fallback state alongside slot.agent, before the first await, retaining rollback tokens.
[BLOCK-MERGE] f481b70
[GPT-REVIEWED] f481b70

Adjudication (Fable 5.1) — is blocking on each finding proportionate?

API Error: 400 Claude Code 2.1.240 does not support this model; version 2.1.255 or newer is required. Run 'claude update', or update the Claude desktop app, then try again.

[github-actions]

Opus 4.8 Review (fork) — ✅ no blocking findings

Reviewed f481b7097338d01d51ba722eeeaaf937df9601bb via the fork AI-review pipeline; updated in place on each push.

Review details

Both candidates are self-rated low-confidence, and both fail the falsification bar.

Candidate 2 (same-agent write of model to metadata) requires slot.model="" while transcript metadata carries a stale non-empty "X". But model is a SLOT_OWNED_META_KEY (history.py:176) reconstructed from slot.model by the periodic slot save (chat_persistence.py:2783), and no other writer ever puts model into transcript metadata — the model handler (api_chat_slot_model) never calls update_metadata. Metadata therefore tracks slot.model; the divergence the candidate needs does not occur in practice, and writing str(slot.model) on a same-agent switch converges metadata to the authoritative slot value rather than corrupting it. No observable wrong outcome. Dies.

Candidate 1 (agent rollback restores OLD agent while a broken model-token identity leaves a NEW-agent model) requires a concurrent unlocked slot.model write during the failing reset await. The switch now holds slot._model_pick_lock for its whole body (chat_handlers.py:5599), the same lock every model-pick transaction and the fallback-recovery swap take (chat_runner.py:1112, chat_handlers.py:6200/6849); the pre-turn busy/skip_if_busy guards exclude an in-flight turn. The candidate's own (a) is stated as "could"/"if", and the identity-token design deliberately treats a concurrent writer's value as truth — so standing the model rollback down is intended. Fails concrete input; dies.

Nothing grounded to add in Step 2.

No findings.

[OPUS-REVIEWED] f481b70

[github-actions]

First Principles Review (Fable 5.1, fork) — 🟡 CONCERNS

Premise-level review of f481b7097338d01d51ba722eeeaaf937df9601bb via the fork AI-review pipeline — why this exists and whether the shipped surface is the smallest honest version. Updated in place on each push. A BLOCK verdict blocks PR readiness; PASS/CONCERNS are advisory.

First-Principles-Verdict: CONCERNS

A real, well-targeted fix, but the same root cause (agent changes → session reset → stale provider-bound model) is left unfixed at the in-turn /agent switch in chat_runner.

What this change ships

Intent: after switching a dashboard slot to a different agent, the next turn starts on the new agent's default model, not an incompatible model id from the old agent's provider. FIX.

1. Local agent switch to a different agent clears model pin + fallback recovery state before reset — justified.
2. Blank model persisted to conversation metadata so a post-restart resume doesn't revert — justified (consumed by chat_persistence.py:942).
3. Remote/peer agent switch clears + persists the same in its mirror after acceptance — justified.
4. Same-agent reset leaves model state untouched — justified guard against over-clearing.
5. Pre-pop reset failure rolls model/fallback state back to prior — justified (mirrors existing _rollback_switch).
6. api_chat_slot_agent now takes a third lock (_model_pick_lock) — justified (serializes vs the model-pick/bulk handlers that mutate _model_pick_gen).

Watch

• Counted unfixed sibling of the root cause. Grepped slot.agent = across dashboard/: 2 agent-change-with-reset sites are fixed here; chat_runner.py:9660 (the in-turn kiro-cli /agent directive) sets slot.agent = new_agent and needs_session_reset = True but never clears model/fallback state — so an in-turn switch resumes the new agent on the old provider's pinned model (slot.model is re-sent as a set_model override per state.py:3737), the exact defect this PR fixes. openai_compat.py:552 is a weaker candidate. A shared clear covering the in-turn path is the general fix; deferring it is acceptable, but it should be a named follow-up, not silent.

[FIRST-PRINCIPLES-REVIEWED] f481b70