CICD / test_out.txt
printf-sourav's picture
Expose independent grader scores in the reward calculator component models
05feb67
Raw
History Blame Contribute Delete
16.9 kB
.............EEEE.EEEF.....E.
======================================================================
ERROR: test_action_space_rejects_alias_tools (test_env.EnvironmentContractTests.test_action_space_rejects_alias_tools)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/home/sourav/Documents/DEployment/cicd-debugger-env/tests/test_env.py", line 48, in test_action_space_rejects_alias_tools
_, _, done, info = asyncio.run(env.step("read: workflow file"))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/env/environment.py", line 284, in step
reward_model = Reward(value=float(reward), components={"total": float(reward)})
^^^^^^^^^^^^^
TypeError: float() argument must be a string or a real number, not 'tuple'
======================================================================
ERROR: test_action_space_rejects_extra_tools (test_env.EnvironmentContractTests.test_action_space_rejects_extra_tools)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/home/sourav/Documents/DEployment/cicd-debugger-env/tests/test_env.py", line 36, in test_action_space_rejects_extra_tools
observation, reward, done, info = asyncio.run(env.step("propose_fix: force deploy"))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/env/environment.py", line 284, in step
reward_model = Reward(value=float(reward), components={"total": float(reward)})
^^^^^^^^^^^^^
TypeError: float() argument must be a string or a real number, not 'tuple'
======================================================================
ERROR: test_hard_needs_order_edit_updates_deploy_dependency (test_env.EnvironmentContractTests.test_hard_needs_order_edit_updates_deploy_dependency)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/home/sourav/Documents/DEployment/cicd-debugger-env/tests/test_env.py", line 106, in test_hard_needs_order_edit_updates_deploy_dependency
observation, _, _, _ = asyncio.run(env.step("edit_config: fix deploy dependency ordering"))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/env/environment.py", line 284, in step
reward_model = Reward(value=float(reward), components={"total": float(reward)})
^^^^^^^^^^^^^
TypeError: float() argument must be a string or a real number, not 'tuple'
======================================================================
ERROR: test_internal_state_tracks_required_fields (test_env.EnvironmentContractTests.test_internal_state_tracks_required_fields)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/home/sourav/Documents/DEployment/cicd-debugger-env/tests/test_env.py", line 74, in test_internal_state_tracks_required_fields
asyncio.run(env.step("read_logs: inspect logs"))
File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/env/environment.py", line 284, in step
reward_model = Reward(value=float(reward), components={"total": float(reward)})
^^^^^^^^^^^^^
TypeError: float() argument must be a string or a real number, not 'tuple'
======================================================================
ERROR: test_step_returns_obs_reward_done_info (test_env.EnvironmentContractTests.test_step_returns_obs_reward_done_info)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/home/sourav/Documents/DEployment/cicd-debugger-env/tests/test_env.py", line 24, in test_step_returns_obs_reward_done_info
observation, reward, done, info = asyncio.run(env.step("read_logs: inspect failing stage logs"))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/env/environment.py", line 284, in step
reward_model = Reward(value=float(reward), components={"total": float(reward)})
^^^^^^^^^^^^^
TypeError: float() argument must be a string or a real number, not 'tuple'
======================================================================
ERROR: test_submit_solution_path (test_env.EnvironmentContractTests.test_submit_solution_path)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/home/sourav/Documents/DEployment/cicd-debugger-env/tests/test_env.py", line 58, in test_submit_solution_path
asyncio.run(env.step("read_logs: inspect logs"))
File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/env/environment.py", line 284, in step
reward_model = Reward(value=float(reward), components={"total": float(reward)})
^^^^^^^^^^^^^
TypeError: float() argument must be a string or a real number, not 'tuple'
======================================================================
ERROR: test_yaml_task_is_fixable_via_edit_flow (test_env.EnvironmentContractTests.test_yaml_task_is_fixable_via_edit_flow)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/home/sourav/Documents/DEployment/cicd-debugger-env/tests/test_env.py", line 88, in test_yaml_task_is_fixable_via_edit_flow
asyncio.run(env.step("read_logs: inspect logs"))
File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/asyncio/base_events.py", line 687, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/env/environment.py", line 284, in step
reward_model = Reward(value=float(reward), components={"total": float(reward)})
^^^^^^^^^^^^^
TypeError: float() argument must be a string or a real number, not 'tuple'
======================================================================
ERROR: test_reset_state_step_flow (test_server_api.ServerApiTests.test_reset_state_step_flow)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/home/sourav/Documents/DEployment/cicd-debugger-env/tests/test_server_api.py", line 32, in test_reset_state_step_flow
step_response = self.client.post(
^^^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/testclient.py", line 546, in post
return super().post(
^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/httpx/_client.py", line 1144, in post
return self.request(
^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/testclient.py", line 445, in request
return super().request(
^^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/httpx/_client.py", line 825, in request
return self.send(request, auth=auth, follow_redirects=follow_redirects)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/httpx/_client.py", line 914, in send
response = self._send_handling_auth(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/httpx/_client.py", line 942, in _send_handling_auth
response = self._send_handling_redirects(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/httpx/_client.py", line 979, in _send_handling_redirects
response = self._send_single_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/httpx/_client.py", line 1014, in _send_single_request
response = transport.handle_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/testclient.py", line 348, in handle_request
raise exc
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/testclient.py", line 345, in handle_request
portal.call(self.app, scope, receive, send)
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/anyio/from_thread.py", line 334, in call
return cast(T_Retval, self.start_task_soon(func, *args).result())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/concurrent/futures/_base.py", line 456, in result
return self.__get_result()
^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result
raise self._exception
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/anyio/from_thread.py", line 259, in _call_func
retval = await retval_or_awaitable
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/fastapi/applications.py", line 1163, in __call__
await super().__call__(scope, receive, send)
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/applications.py", line 90, in __call__
await self.middleware_stack(scope, receive, send)
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/middleware/errors.py", line 186, in __call__
raise exc
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/middleware/errors.py", line 164, in __call__
await self.app(scope, receive, _send)
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/middleware/exceptions.py", line 63, in __call__
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
raise exc
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
await app(scope, receive, sender)
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/fastapi/middleware/asyncexitstack.py", line 18, in __call__
await self.app(scope, receive, send)
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/routing.py", line 660, in __call__
await self.middleware_stack(scope, receive, send)
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/routing.py", line 680, in app
await route.handle(scope, receive, send)
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/routing.py", line 276, in handle
await self.app(scope, receive, send)
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/fastapi/routing.py", line 134, in app
await wrap_app_handling_exceptions(app, request)(scope, receive, send)
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
raise exc
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
await app(scope, receive, sender)
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/fastapi/routing.py", line 120, in app
response = await f(request)
^^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/fastapi/routing.py", line 674, in app
raw_response = await run_endpoint_function(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/venv/lib/python3.12/site-packages/fastapi/routing.py", line 328, in run_endpoint_function
return await dependant.call(**values)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/server/app.py", line 138, in step
observation, reward, done, info = await runtime_session.env.step(payload.action)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/sourav/Documents/DEployment/cicd-debugger-env/env/environment.py", line 284, in step
reward_model = Reward(value=float(reward), components={"total": float(reward)})
^^^^^^^^^^^^^
TypeError: float() argument must be a string or a real number, not 'tuple'
======================================================================
FAIL: test_inference_prints_required_markers (test_inference.InferenceOutputFormatTests.test_inference_prints_required_markers)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/home/sourav/Documents/DEployment/cicd-debugger-env/tests/test_inference.py", line 25, in test_inference_prints_required_markers
self.assertGreaterEqual(len(lines), 3)
AssertionError: 2 not greater than or equal to 3
----------------------------------------------------------------------
Ran 29 tests in 1.321s
FAILED (failures=1, errors=8)