Merge branch 'main' into mh/rel0210

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -71,7 +71,7 @@ def process_git_patch(patch):
     return patch
 
 
-def get_config(instance: pd.Series) -> AppConfig:
+def get_config(metadata: EvalMetadata, instance: pd.Series) -> AppConfig:
     # We use a different instance image for the each instance of swe-bench eval
     base_container_image = get_instance_docker_image(instance['instance_id'])
     logger.info(
@@ -132,7 +132,7 @@ def process_instance(
     else:
         logger.info(f'Starting evaluation for instance {instance.instance_id}.')
 
-    config = get_config(instance)
+    config = get_config(metadata, instance)
     instance_id = instance.instance_id
     model_patch = instance['model_patch']
     test_spec: TestSpec = instance['test_spec']

openhands/agenthub/codeact_agent/codeact_agent.py

@@ -277,16 +277,11 @@ def get_observation_message(
             # if it doesn't have tool call metadata, it was triggered by a user action
             if obs.tool_call_metadata is None:
                 text = truncate_content(
-                    f'\nObserved result of command executed by user:\n{obs.content}',
+                    f'\nObserved result of command executed by user:\n{obs.to_agent_observation()}',
                     max_message_chars,
                 )
             else:
-                text = truncate_content(
-                    obs.content
-                    + f'\n[Python Interpreter: {obs.metadata.py_interpreter_path}]',
-                    max_message_chars,
-                )
-            text += f'\n[Command finished with exit code {obs.exit_code}]'
+                text = truncate_content(obs.to_agent_observation(), max_message_chars)
             message = Message(role='user', content=[TextContent(text=text)])
         elif isinstance(obs, IPythonRunCellObservation):
             text = obs.content

openhands/events/observation/commands.py

@@ -149,16 +149,18 @@ def __str__(self) -> str:
             f'**CmdOutputObservation (source={self.source}, exit code={self.exit_code}, '
             f'metadata={json.dumps(self.metadata.model_dump(), indent=2)})**\n'
             '--BEGIN AGENT OBSERVATION--\n'
-            f'{self._to_agent_observation()}\n'
+            f'{self.to_agent_observation()}\n'
             '--END AGENT OBSERVATION--'
         )
 
-    def _to_agent_observation(self) -> str:
+    def to_agent_observation(self) -> str:
         ret = f'{self.metadata.prefix}{self.content}{self.metadata.suffix}'
         if self.metadata.working_dir:
             ret += f'\n[Current working directory: {self.metadata.working_dir}]'
         if self.metadata.py_interpreter_path:
             ret += f'\n[Python interpreter: {self.metadata.py_interpreter_path}]'
+        if self.metadata.exit_code != -1:
+            ret += f'\n[Command finished with exit code {self.metadata.exit_code}]'
         return ret
 
 

openhands/runtime/impl/docker/docker_runtime.py

@@ -66,7 +66,7 @@ def __init__(
         headless_mode: bool = True,
     ):
         global _atexit_registered
-        if not _atexit_registered:
+        if not _atexit_registered and not config.sandbox.keep_runtime_alive:
             _atexit_registered = True
             atexit.register(remove_all_runtime_containers)
 

tests/unit/test_codeact_agent.py

@@ -46,7 +46,7 @@ def agent() -> CodeActAgent:
     agent = CodeActAgent(llm=LLM(LLMConfig()), config=config)
     agent.llm = Mock()
     agent.llm.config = Mock()
-    agent.llm.config.max_message_chars = 100
+    agent.llm.config.max_message_chars = 1000
     return agent
 
 
@@ -65,19 +65,26 @@ def test_cmd_output_observation_message(agent: CodeActAgent):
         content='Command output',
         metadata=CmdOutputMetadata(
             exit_code=0,
+            prefix='[THIS IS PREFIX]',
+            suffix='[THIS IS SUFFIX]',
         ),
     )
 
-    results = agent.get_observation_message(obs, tool_call_id_to_message={})
+    tool_call_id_to_message = {}
+    results = agent.get_observation_message(
+        obs, tool_call_id_to_message=tool_call_id_to_message
+    )
     assert len(results) == 1
 
     result = results[0]
     assert result is not None
     assert result.role == 'user'
     assert len(result.content) == 1
     assert isinstance(result.content[0], TextContent)
-    assert 'Command output' in result.content[0].text
+    assert 'Observed result of command executed by user:' in result.content[0].text
     assert '[Command finished with exit code 0]' in result.content[0].text
+    assert '[THIS IS PREFIX]' in result.content[0].text
+    assert '[THIS IS SUFFIX]' in result.content[0].text
 
 
 def test_ipython_run_cell_observation_message(agent: CodeActAgent):