Factor out ActionExecutionClient (#5796)

2026-01-10 07:18:10 -05:00 · 2024-12-30 10:32:13 -05:00
parent 37363a0a8d
commit 0e4e1b3316
34 changed files with 475 additions and 735 deletions
--- a/evaluation/benchmarks/EDA/run_infer.py
+++ b/evaluation/benchmarks/EDA/run_infer.py
@@ -63,7 +63,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
--- a/evaluation/benchmarks/agent_bench/run_infer.py
+++ b/evaluation/benchmarks/agent_bench/run_infer.py
@@ -43,7 +43,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-slim',
--- a/evaluation/benchmarks/aider_bench/run_infer.py
+++ b/evaluation/benchmarks/aider_bench/run_infer.py
@@ -50,7 +50,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.11-bookworm',
--- a/evaluation/benchmarks/biocoder/run_infer.py
+++ b/evaluation/benchmarks/biocoder/run_infer.py
@@ -61,7 +61,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image=BIOCODER_BENCH_CONTAINER_IMAGE,
--- a/evaluation/benchmarks/bird/run_infer.py
+++ b/evaluation/benchmarks/bird/run_infer.py
@@ -74,7 +74,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
--- a/evaluation/benchmarks/browsing_delegation/run_infer.py
+++ b/evaluation/benchmarks/browsing_delegation/run_infer.py
@@ -39,7 +39,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
--- a/evaluation/benchmarks/commit0_bench/run_infer.py
+++ b/evaluation/benchmarks/commit0_bench/run_infer.py
@@ -124,7 +124,7 @@ def get_config(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        max_iterations=metadata.max_iterations,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        sandbox=SandboxConfig(
            base_container_image=base_container_image,
            enable_auto_lint=True,
--- a/evaluation/benchmarks/discoverybench/run_infer.py
+++ b/evaluation/benchmarks/discoverybench/run_infer.py
@@ -65,7 +65,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
--- a/evaluation/benchmarks/gaia/run_infer.py
+++ b/evaluation/benchmarks/gaia/run_infer.py
@@ -50,7 +50,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
--- a/evaluation/benchmarks/gorilla/run_infer.py
+++ b/evaluation/benchmarks/gorilla/run_infer.py
@@ -43,7 +43,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
--- a/evaluation/benchmarks/gpqa/run_infer.py
+++ b/evaluation/benchmarks/gpqa/run_infer.py
@@ -64,7 +64,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
--- a/evaluation/benchmarks/humanevalfix/run_infer.py
+++ b/evaluation/benchmarks/humanevalfix/run_infer.py
@@ -85,7 +85,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
--- a/evaluation/benchmarks/logic_reasoning/run_infer.py
+++ b/evaluation/benchmarks/logic_reasoning/run_infer.py
@@ -48,7 +48,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='xingyaoww/od-eval-logic-reasoning:v1.0',
--- a/evaluation/benchmarks/miniwob/run_infer.py
+++ b/evaluation/benchmarks/miniwob/run_infer.py
@@ -58,7 +58,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='xingyaoww/od-eval-miniwob:v1.0',
--- a/evaluation/benchmarks/mint/run_infer.py
+++ b/evaluation/benchmarks/mint/run_infer.py
@@ -106,7 +106,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='xingyaoww/od-eval-mint:v1.0',
--- a/evaluation/benchmarks/ml_bench/run_infer.py
+++ b/evaluation/benchmarks/ml_bench/run_infer.py
@@ -80,7 +80,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='public.ecr.aws/i5g0m1f6/ml-bench',
--- a/evaluation/benchmarks/scienceagentbench/run_infer.py
+++ b/evaluation/benchmarks/scienceagentbench/run_infer.py
@@ -62,7 +62,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        max_budget_per_task=4,
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
--- a/evaluation/benchmarks/swe_bench/eval_infer.py
+++ b/evaluation/benchmarks/swe_bench/eval_infer.py
@@ -76,7 +76,7 @@ def get_config(instance: pd.Series) -> AppConfig:
    )
    config = AppConfig(
        run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        sandbox=SandboxConfig(
            base_container_image=base_container_image,
            use_host_network=False,
--- a/evaluation/benchmarks/swe_bench/run_infer.py
+++ b/evaluation/benchmarks/swe_bench/run_infer.py
@@ -121,7 +121,7 @@ def get_config(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        max_iterations=metadata.max_iterations,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        sandbox=SandboxConfig(
            base_container_image=base_container_image,
            enable_auto_lint=True,
--- a/evaluation/benchmarks/toolqa/run_infer.py
+++ b/evaluation/benchmarks/toolqa/run_infer.py
@@ -44,7 +44,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
--- a/evaluation/benchmarks/webarena/run_infer.py
+++ b/evaluation/benchmarks/webarena/run_infer.py
@@ -53,7 +53,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime='eventstream',
+        runtime='docker',
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            base_container_image='python:3.12-bookworm',
--- a/evaluation/integration_tests/run_infer.py
+++ b/evaluation/integration_tests/run_infer.py
@@ -42,7 +42,7 @@ def get_config(
    config = AppConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
-        runtime=os.environ.get('RUNTIME', 'eventstream'),
+        runtime=os.environ.get('RUNTIME', 'docker'),
        max_iterations=metadata.max_iterations,
        sandbox=SandboxConfig(
            # use default base_container_image