runtime(bash): use dedicated tmux socket to avoid inherited permission issues; initialize _closed safely

Create a fresh, uniquely named tmux socket for each BashSession via libtmux.Server(socket_name=...). This prevents connecting to a root-owned TMUX socket (e.g., /tmp/tmux-0/default) on CI, which caused interactive tests to misbehave.

Also set _closed early and reset on initialize to avoid __del__ AttributeError if initialization fails early.

Co-authored-by: OpenHands-GPT-5 openhands@all-hands.dev

evaluation/benchmarks/nocode_bench/README.md

@@ -0,0 +1,45 @@
+# Evaluate OpenHands on NoCode-bench
+
+## LLM Setup
+
+Please follow [here](../../README.md#setup).
+
+
+## Docker image download
+
+Evaluating OpenHands on NoCode-bench need instance-level docker image.
+Please follow the instructions of NoCode-bench image setup to build or download all instance-level dokcer [here](https://github.com/NoCode-bench/NoCode-bench).
+
+## Generate patch
+
+Please follow the instructions [here](../swe_bench/README.md#running-locally-with-docker)
+For example,
+```bash
+bash ./evaluation/benchmarks/nocode_bench/scripts/run_infer_nc.sh llm.claude HEAD CodeActAgent 114 100 10 NoCode-bench/NoCode-bench_Verified test
+```
+The results will be generated in evaluation/evaluation_outputs/outputs/XXX/CodeActAgent/YYY/output.jsonl.
+
+## Runing evaluation
+
+First, install [NoCode-bench](https://github.com/NoCode-bench/NoCode-bench).
+
+Second, convert the output.jsonl to patch.jsonl with [script](scripts/eval/convert.py).
+
+```bash
+python evaluation/benchmarks/multi_swe_bench/scripts/eval/convert.py
+```
+
+Finally, evaluate with NoCode-bench.
+
+```bash
+export PYTHONPATH=$PYTHONPATH:$(pwd)
+python ./evaluation/eval.py \
+    --predictions_path ./all_preds.jsonl \  # <path_to_your_predictions>
+    --log_dir ./evaluation/logs \ # <path_to_your_log_dir>
+    --bench_tasks NoCode-bench/NoCode-bench_Verified \ # <dataset_name>
+    --max_workers 110 \ # <number_of_workers>
+    --output_file eval_result.txt \ # <path_to_your_output_file>
+    --image_level repo \ # <cache_image_level>
+    --timeout 600 \ # <timeout_in_seconds>
+    --proxy None # <proxy_if_needed>
+```

evaluation/benchmarks/nocode_bench/binary_patch_utils.py

@@ -0,0 +1,52 @@
+"""
+Utilities for handling binary files and patch generation in SWE-bench evaluation.
+"""
+
+
+def remove_binary_diffs(patch_text):
+    """
+    Remove binary file diffs from a git patch.
+
+    Args:
+        patch_text (str): The git patch text
+
+    Returns:
+        str: The cleaned patch text with binary diffs removed
+    """
+    lines = patch_text.splitlines()
+    cleaned_lines = []
+    block = []
+    is_binary_block = False
+
+    for line in lines:
+        if line.startswith('diff --git '):
+            if block and not is_binary_block:
+                cleaned_lines.extend(block)
+            block = [line]
+            is_binary_block = False
+        elif 'Binary files' in line:
+            is_binary_block = True
+            block.append(line)
+        else:
+            block.append(line)
+
+    if block and not is_binary_block:
+        cleaned_lines.extend(block)
+    return '\n'.join(cleaned_lines)
+
+
+def remove_binary_files_from_git():
+    """
+    Generate a bash command to remove binary files from git staging.
+
+    Returns:
+        str: A bash command that removes binary files from git staging
+    """
+    return """
+    for file in $(git status --porcelain | grep -E "^(M| M|\\?\\?|A| A)" | cut -c4-); do
+        if [ -f "$file" ] && (file "$file" | grep -q "executable" || git check-attr binary "$file" | grep -q "binary: set"); then
+            git rm -f "$file" 2>/dev/null || rm -f "$file"
+            echo "Removed: $file"
+        fi
+    done
+    """.strip()

evaluation/benchmarks/nocode_bench/consistants.py

@@ -0,0 +1,545 @@
+DOCPATH_PATTERNS = [
+    r'docs/',
+    r'^CHANGES\.rst$',
+    r'doc/',
+    r'ChangeLog',
+    r'^changelog/',
+    r'^CHANGES$',
+]
+
+MATPLOTLIB_CONFIG = {
+    k: {
+        'python': '3.11',
+        'conda_env': 'matplotlib_35',
+        'install': 'python -m pip install -e .',
+        'test_cmd': 'pytest -rA --color=no',
+    }
+    for k in ['3.5', '3.6', '3.7', '3.8', '3.9']
+}
+MATPLOTLIB_CONFIG.update(
+    {
+        k: {
+            'python': '3.8',
+            'conda_env': 'matplotlib_31',
+            'install': 'python -m pip install -e .',
+            'test_cmd': 'pytest -rA --color=no',
+        }
+        for k in ['3.1', '3.2', '3.3', '3.4']
+    }
+)
+MATPLOTLIB_CONFIG.update(
+    {
+        k: {
+            'python': '3.5',
+            'install': 'python setup.py build; python setup.py install',
+            'conda_env': 'matplotlib_11',
+            'nonroot': True,
+            'test_cmd': 'pytest -rA --color=no',
+        }
+        for k in ['2.0', '2.1', '2.2', '1.0', '1.1', '1.2', '1.3', '1.4', '1.5']
+    }
+)
+for k in ['3.8', '3.9']:
+    MATPLOTLIB_CONFIG[k]['install'] = (
+        'python -m pip install --no-build-isolation -e ".[dev]"'
+    )
+
+
+SYMPY_CONFIG = {}
+SYMPY_CONFIG.update(
+    {
+        '1.0': {
+            'conda_env': 'sympy_10',
+            'install': 'pip install -e .',
+            'test_cmd': 'bin/test -C -v',
+            # testfile -k testname
+        }
+    }
+)
+
+REQUESTS_CONFIG = {}
+REQUESTS_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'requests_227',
+            'install': 'pip install -r requirements-dev.txt',
+            'test_cmd': 'pytest -rA',
+        }
+        for k in ['2.27']
+    }
+)
+REQUESTS_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'requests_226',
+            'install': 'pip install -e .',
+            'test_cmd': 'pytest -rA',
+        }
+        for k in ['2.26']
+    }
+)
+
+PYTEST_CONFIG = {}
+PYTEST_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'pytest_33',
+            'install': 'pip install -e .',
+            'test_cmd': 'pytest -v --color=no',
+        }
+        for k in ['4.4', '4.1', '3.7', '3.4', '3.3']
+    }
+)
+
+PYLINT_CONFIG = {}
+PYLINT_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'pylint_210',
+            'install': 'pip install -r requirements_test.txt',
+            'test_cmd': 'pytest -rA --color=no',
+        }
+        for k in [
+            '2.10',
+            '2.11',
+            '2.13',
+            '2.14',
+            '2.15',
+            '2.16',
+            '2.17',
+            '3.0',
+            '3.1',
+            '3.2',
+            '3.3',
+        ]
+    }
+)
+PYLINT_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'pylint_210',
+            'pre_install': [
+                r"sed -i 's/setuptools==[0-9.]\+/setuptools==58.0.0/' requirements_test_min.txt"
+            ],
+            'install': 'pip install -r requirements_test.txt',
+            'test_cmd': 'pytest -rA --color=no',
+        }
+        for k in ['3.0', '3.1', '3.2', '3.3']
+    }
+)
+
+ASTROPY_CONFIG = {}
+ASTROPY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'astropy_11',
+            'install': 'python -m pip install -e .[test] --verbose',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['1.1', '1.2', '1.3', '2.0']
+    }
+)
+ASTROPY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'astropy_30',
+            'pre_install': """echo '[pytest]
+filterwarnings =
+    ignore::DeprecationWarning' > pytest.ini""",
+            'install': 'python -m pip install -e .[test] --verbose',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['3.0', '3.1', '3.2']
+    }
+)
+ASTROPY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'astropy_40',
+            'pre_install': [
+                r"""sed -i 's/requires = \["setuptools",/requires = \["setuptools==68.0.0",/' pyproject.toml"""
+            ],
+            'install': 'python -m pip install -e .[test] --verbose',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['4.0']
+    }
+)
+ASTROPY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'astropy_41',
+            'pre_install': [
+                r"""sed -i 's/requires = \["setuptools",/requires = \["setuptools==68.0.0",/' pyproject.toml""",
+                """sed -i 's/^qt_no_exception_capture = 1$/; qt_no_exception_capture = 1/' setup.cfg""",
+                r"""sed -i '/setuptools==68.0.0",/a \    "markupsafe==2.0.1",' pyproject.tomlsed -i '/setuptools==68.0.0",/a \    "markupsafe==2.0.1",' pyproject.toml""",
+            ],
+            'install': 'python -m pip install -e .[test] --verbose',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['4.1']
+    }
+)
+ASTROPY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'astropy_42',
+            'pre_install': [
+                r"""sed -i 's/requires = \["setuptools",/requires = \["setuptools==68.0.0",/' pyproject.toml""",
+                r"""sed -i '/setuptools==68.0.0",/a \    "markupsafe==2.0.1",' pyproject.tomlsed -i '/setuptools==68.0.0",/a \    "markupsafe==2.0.1",' pyproject.toml""",
+            ],
+            'install': 'python -m pip install -e .[test] --verbose',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['4.2', '4.3', '5.0', '5.1']
+    }
+)
+
+ASTROPY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'astropy_52',
+            'pre_install': [
+                r"""sed -i 's/requires = \["setuptools",/requires = \["setuptools==68.0.0",/' pyproject.toml"""
+            ],
+            'install': 'python -m pip install -e .[test] --verbose',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['5.2', '5.3', '6.0', '6.1', '7.0']
+    }
+)
+
+DJANGO_CONFIG = {}
+DJANGO_CONFIG.update(
+    {
+        k: {
+            'install': 'pip install -e .',
+            'conda_env': 'django_22',
+            'test_cmd': 'python tests/runtests.py --verbosity 2',
+        }
+        for k in ['1.9', '2.2']
+    }
+)
+DJANGO_CONFIG.update(
+    {
+        '3.2': {
+            'install': 'pip install -e .',
+            'conda_env': 'django_32',
+            'test_cmd': 'python tests/runtests.py --verbosity 2',
+        },
+        '4.2': {
+            'install': 'pip install -e .',
+            'conda_env': 'django_42',
+            'test_cmd': 'python tests/runtests.py --verbosity 2',
+        },
+        '5.1': {
+            'install': 'pip install -e .',
+            'conda_env': 'django_51',
+            'test_cmd': 'python tests/runtests.py --verbosity 2',
+        },
+    }
+)
+SPHINX_CONFIG = {}
+SPHINX_CONFIG.update(
+    {  # 1.x 版本问题，实际无用
+        k: {
+            'conda_env': 'sphinx_20',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': ["sed -i 's/pytest/pytest -rA/' tox.ini"],
+            'test_cmd': 'tox --current-env -epy37 -v --',
+        }
+        for k in ['1.3', '1.4', '1.5', '1.6', '1.7', '1.8']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_20',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+                "sed -i 's/Jinja2>=2.3/Jinja2<3.0/' setup.py",
+            ],
+            'test_cmd': 'tox --current-env -epy37 -v --',
+        }
+        for k in ['2.0', '2.1', '2.2', '2.3', '2.4']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_30',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+                "sed -i 's/Jinja2>=2.3/Jinja2<3.0/' setup.py",
+                "sed -i 's/sphinxcontrib-applehelp/sphinxcontrib-applehelp<=1.0.7/' setup.py",
+                "sed -i 's/sphinxcontrib-devhelp/sphinxcontrib-devhelp<=1.0.5/' setup.py",
+                "sed -i 's/sphinxcontrib-qthelp/sphinxcontrib-qthelp<=1.0.6/' setup.py",
+                "sed -i 's/alabaster>=0.7,<0.8/alabaster>=0.7,<0.7.12/' setup.py",
+                "sed -i \"s/'packaging',/'packaging', 'markupsafe<=2.0.1',/\" setup.py",
+                "sed -i 's/sphinxcontrib-htmlhelp/sphinxcontrib-htmlhelp<=2.0.4/' setup.py",
+                "sed -i 's/sphinxcontrib-serializinghtml/sphinxcontrib-serializinghtml<=1.1.9/' setup.py",
+            ],
+            'test_cmd': 'tox --current-env -epy37 -v --',
+        }
+        for k in ['3.0', '3.1', '3.2', '3.3', '3.4', '3.5', '4.0']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_30',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+                "sed -i 's/Jinja2>=2.3/Jinja2<3.0/' setup.py",
+                "sed -i 's/sphinxcontrib-applehelp/sphinxcontrib-applehelp<=1.0.7/' setup.py",
+                "sed -i 's/sphinxcontrib-devhelp/sphinxcontrib-devhelp<=1.0.5/' setup.py",
+                "sed -i 's/sphinxcontrib-qthelp/sphinxcontrib-qthelp<=1.0.6/' setup.py",
+                "sed -i 's/alabaster>=0.7,<0.8/alabaster>=0.7,<0.7.12/' setup.py",
+                "sed -i \"s/'packaging',/'packaging', 'markupsafe<=2.0.1',/\" setup.py",
+                (
+                    "grep -q 'sphinxcontrib-htmlhelp>=2.0.0' setup.py && "
+                    "sed -i 's/sphinxcontrib-htmlhelp>=2.0.0/sphinxcontrib-htmlhelp>=2.0.0,<=2.0.4/' setup.py || "
+                    "sed -i 's/sphinxcontrib-htmlhelp/sphinxcontrib-htmlhelp<=2.0.4/' setup.py"
+                ),
+                (
+                    "grep -q 'sphinxcontrib-serializinghtml>=1.1.5' setup.py && "
+                    "sed -i 's/sphinxcontrib-serializinghtml>=1.1.5/sphinxcontrib-serializinghtml>=1.1.5,<=1.1.9/' setup.py || "
+                    "sed -i 's/sphinxcontrib-serializinghtml/sphinxcontrib-serializinghtml<=1.1.9/' setup.py"
+                ),
+            ],
+            'test_cmd': 'tox --current-env -epy37 -v --',
+        }
+        for k in ['4.1']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_30',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+                "sed -i 's/Jinja2>=2.3/Jinja2<3.0/' setup.py",
+                "sed -i 's/sphinxcontrib-applehelp/sphinxcontrib-applehelp<=1.0.7/' setup.py",
+                "sed -i 's/sphinxcontrib-devhelp/sphinxcontrib-devhelp<=1.0.5/' setup.py",
+                "sed -i 's/sphinxcontrib-qthelp/sphinxcontrib-qthelp<=1.0.6/' setup.py",
+                "sed -i 's/alabaster>=0.7,<0.8/alabaster>=0.7,<0.7.12/' setup.py",
+                "sed -i \"s/'packaging',/'packaging', 'markupsafe<=2.0.1',/\" setup.py",
+                "sed -i 's/sphinxcontrib-htmlhelp>=2.0.0/sphinxcontrib-htmlhelp>=2.0.0,<=2.0.4/' setup.py",
+                "sed -i 's/sphinxcontrib-serializinghtml>=1.1.5/sphinxcontrib-serializinghtml>=1.1.5,<=1.1.9/' setup.py",
+            ],
+            'test_cmd': 'tox --current-env -epy37 -v --',
+        }
+        for k in ['4.2', '4.3', '4.4']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_30',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+            ],
+            'test_cmd': 'tox --current-env -epy37 -v --',
+        }
+        for k in ['4.5', '5.0', '5.1', '5.2']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_60',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+            ],
+            'test_cmd': 'tox --current-env -epy39 -v --',
+        }
+        for k in ['6.0', '6.2', '7.0', '7.1']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_72',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+                'apt-get update && apt-get install -y graphviz',
+            ],
+            'test_cmd': 'tox --current-env -epy39 -v --',
+        }
+        for k in ['7.2', '7.3', '7.4']
+    }
+)
+SPHINX_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'sphinx_80',
+            'install': 'python -m pip install -e .[test]',
+            'pre_install': [
+                "sed -i 's/pytest/pytest -rA/' tox.ini",
+            ],
+            'test_cmd': 'tox --current-env -epy310 -v --',
+        }
+        for k in ['8.0', '8.1']
+    }
+)
+
+
+SKLEARN_CONFIG = {}
+SKLEARN_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'skl_020',
+            'install': 'pip install -v --no-use-pep517 --no-build-isolation -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['0.20', '0.21', '0.22']
+    }
+)
+SKLEARN_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'skl_100',
+            'install': 'pip install -v --no-use-pep517 --no-build-isolation -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['0.23', '0.24', '1.00', '1.01', '1.02']
+    }
+)
+SKLEARN_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'skl_104',
+            'install': 'pip install -v --no-use-pep517 --no-build-isolation -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['1.03', '1.04', '1.05']
+    }
+)
+
+SEABORN_CONFIG = {}
+SEABORN_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'seaborn_010',
+            'install': 'pip install -e .[dev]',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['0.3', '0.4', '0.5', '0.6', '0.11', '0.12', '0.13', '0.14']
+    }
+)
+
+XARRAY_CONFIG = {}
+XARRAY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'xarray_0014',
+            'install': 'pip install -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['0014', '0015', '0016']
+    }
+)
+XARRAY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'xarray_0017',
+            'install': 'pip install -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['0017', '0018', '0019', '0020', '0021']
+    }
+)
+XARRAY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'xarray_2203',
+            'install': 'pip install -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['2203', '2206', '2209', '2210', '2211', '2212']
+    }
+)
+XARRAY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'xarray_2303',
+            'install': 'pip install -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in [
+            '2303',
+            '2304',
+            '2305',
+            '2306',
+            '2308',
+            '2309',
+            '2310',
+            '2311',
+            '2312',
+        ]
+    }
+)
+XARRAY_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'xarray_2401',
+            'install': 'pip install -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['2401', '2402', '2403', '2405', '2407', '2409', '2410', '2411']
+    }
+)
+
+SKLEARN_CONFIG = {}
+SKLEARN_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'skl_020',
+            'install': 'pip install -v --no-use-pep517 --no-build-isolation -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['0.20', '0.21', '0.22']
+    }
+)
+SKLEARN_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'skl_100',
+            'install': 'pip install -v --no-use-pep517 --no-build-isolation -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['0.23', '0.24', '1.00', '1.01', '1.02']
+    }
+)
+SKLEARN_CONFIG.update(
+    {
+        k: {
+            'conda_env': 'skl_104',
+            'install': 'pip install -v --no-use-pep517 --no-build-isolation -e .',
+            'test_cmd': 'pytest --color=no -rA',
+        }
+        for k in ['1.03', '1.04', '1.05', '1.06', '1.07']
+    }
+)
+
+
+MAP_REPO_TO_CONFIG = {
+    'pydata/xarray': XARRAY_CONFIG,
+    'mwaskom/seaborn': SEABORN_CONFIG,
+    'scikit-learn/scikit-learn': SKLEARN_CONFIG,
+    'sphinx-doc/sphinx': SPHINX_CONFIG,
+    'django/django': DJANGO_CONFIG,
+    'astropy/astropy': ASTROPY_CONFIG,
+    'pylint-dev/pylint': PYLINT_CONFIG,
+    'pytest-dev/pytest': PYTEST_CONFIG,
+    'psf/requests': REQUESTS_CONFIG,
+    'sympy/sympy': SYMPY_CONFIG,
+    'matplotlib/matplotlib': MATPLOTLIB_CONFIG,
+}

evaluation/benchmarks/nocode_bench/prompts/nc.j2

@@ -0,0 +1,65 @@
+<uploaded_files>
+/workspace/{{ workspace_dir_name }}
+</uploaded_files>
+
+I've uploaded a python code repository in the directory {{ workspace_dir_name }}. Consider the following issue description:
+
+<doc_change>
+{{ instance.problem_statement }}
+</doc_change>
+
+Can you help me add the new features to the repository based on the changes in the <doc_change>?
+I've already taken care of all changes to any of the test files described in the <doc_change>. This means you DON'T have to modify the testing logic or any of the tests in any way!
+Also the development Python environment is already set up for you (i.e., all dependencies already installed), so you don't need to install other packages.
+Your task is to make the minimal changes to non-test files in the /workspace/{{ workspace_dir_name }} directory to implement the new features required by the documentation updates.
+
+Follow these phases to resolve the issue:
+
+Phase 1. READING: read the requirements and reword it in clearer terms
+   1.1 If there are code or config snippets. Express in words any best practices or conventions in them.
+   1.2 Hightlight method names, variables, file names, stack traces, and technical details, particularly those related to new features.
+   1.3 Explain the new feature requirements in clear terms.
+   1.4 Specify functional scope and expected behavior of new features.
+   1.5 Hightlight any best practices to take into account when developing and testing the new feature.
+
+Phase 2. RUNNING: install and run the functionality in the repository to validate the new features
+   2.1 Follow the readme.
+   2.2 Install the environment and anything needed.
+   2.2 Iterate and figure out how to validate the newly added features.
+
+Phase 3. EXPLORATION: find the files related to the new features and possible implementation solutions
+   3.1 Use `grep` to search for relevant methods, classes, keywords and feature requirements.
+   3.2 Identify all files related to the new features.
+   3.3 Propose the methods and files to implement the new features and explain why.
+   3.4 From the possible file locations, select the most likely location to implement the new features.
+
+Phase 4. TEST CREATION: before implementing any new features, create a script to validate the feature's correctness.
+   4.1 Look at existing test files in the repository to understand the test format/structure.
+   4.2 Create a minimal validation script to verify the newly added features.
+   4.3 Run the validation script to confirm the new features are successfully added and working as expected.
+   4.4 Adjust the validation script as necessary to ensure the new features fully meet the requirements.
+
+Phase 5. FEATURE ANALYSIS: state clearly the new feature and how to implement it
+   5.1 State clearly what the new feature is.
+   5.2 State clearly where the feature should be implemented.
+   5.3 State clearly how the test validates the new feature.
+   5.4 State clearly the best practices to take into account when implementing the new feature.
+   5.5 State clearly how to implement the new feature.
+
+Phase 6. FEATURE IMPLEMENTATION: edit the source code to implement your chosen solution for the new feature
+   6.1 Make minimal, focused changes to implement the new feature.
+
+Phase 7. VERIFICATION: Test your new feature thoroughly.
+   7.1 Run your validation script to verify the new feature works as expected.
+   7.2 Add edge cases to your test script to ensure comprehensive coverage of the new feature.
+   7.3 Run existing tests related to the modified code to ensure you haven't broken anything.
+
+Phase 8. FINAL REVIEW: Carefully re-read the feature requirements and compare your changes with the base commit {{ instance.base_commit }}
+   8.1 Ensure you've fully implemented all required features.
+   8.2 Run any tests in the repository related to:
+     8.2.1 The new features you are adding
+     8.2.2 The files you modified
+     8.2.3 The functions you changed
+   8.3 If any tests fail, revise your implementation until all tests pass and the new feature works as expected.
+
+Be thorough in your exploration, testing, and reasoning. It's fine if your thinking process is lengthy - quality and completeness are more important than brevity.

evaluation/benchmarks/nocode_bench/resource/mapping.py

@@ -0,0 +1,39 @@
+"""Mapping instance_id to resource_factor.
+
+Different instances may have different resource requirements.
+e.g., some instances may require more memory/CPU to run inference.
+This file tracks the resource requirements of different instances.
+"""
+
+import json
+import os
+
+from openhands.core.logger import openhands_logger as logger
+
+CUR_DIR = os.path.dirname(os.path.abspath(__file__))
+DEFAULT_RUNTIME_RESOURCE_FACTOR = int(
+    os.environ.get('DEFAULT_RUNTIME_RESOURCE_FACTOR', 1)
+)
+
+# dataset to resource mapping
+_global_resource_mapping: dict[str, dict[str, float]] = {}
+
+
+def get_resource_mapping(dataset_name: str) -> dict[str, float]:
+    if dataset_name not in _global_resource_mapping:
+        file_path = os.path.join(CUR_DIR, f'{dataset_name}.json')
+        if not os.path.exists(file_path):
+            logger.info(f'Resource mapping for {dataset_name} not found.')
+            return None
+
+        with open(file_path, 'r') as f:
+            _global_resource_mapping[dataset_name] = json.load(f)
+        logger.debug(f'Loaded resource mapping for {dataset_name}')
+    return _global_resource_mapping[dataset_name]
+
+
+def get_instance_resource_factor(dataset_name: str, instance_id: str) -> int:
+    resource_mapping = get_resource_mapping(dataset_name)
+    if resource_mapping is None:
+        return DEFAULT_RUNTIME_RESOURCE_FACTOR
+    return int(resource_mapping.get(instance_id, DEFAULT_RUNTIME_RESOURCE_FACTOR))

evaluation/benchmarks/nocode_bench/run_infer_nc.py

@@ -0,0 +1,909 @@
+import asyncio
+import copy
+import json
+import os
+import tempfile
+from typing import Any, Literal
+
+import numpy as np
+import pandas as pd
+import toml
+from datasets import load_dataset
+from jinja2 import Environment, FileSystemLoader
+
+import openhands.agenthub
+from evaluation.benchmarks.nocode_bench.binary_patch_utils import (
+    remove_binary_diffs,
+    remove_binary_files_from_git,
+)
+from evaluation.benchmarks.nocode_bench.consistants import MAP_REPO_TO_CONFIG
+from evaluation.benchmarks.nocode_bench.resource.mapping import (
+    get_instance_resource_factor,
+)
+from evaluation.benchmarks.nocode_bench.scripts.utils.evaluation_utils import (
+    run_evaluation_nocode_bench,
+)
+from evaluation.utils.shared import (
+    EvalException,
+    EvalMetadata,
+    EvalOutput,
+    assert_and_raise,
+    codeact_user_response,
+    get_default_sandbox_config_for_eval,
+    get_metrics,
+    is_fatal_evaluation_error,
+    make_metadata,
+    prepare_dataset,
+    reset_logger_for_multiprocessing,
+    update_llm_config_for_completions_logging,
+)
+from openhands.controller.state.state import State
+from openhands.core.config import (
+    AgentConfig,
+    OpenHandsConfig,
+    get_evaluation_parser,
+    get_llm_config_arg,
+)
+from openhands.core.config.condenser_config import NoOpCondenserConfig
+from openhands.core.config.utils import get_condenser_config_arg
+from openhands.core.logger import openhands_logger as logger
+from openhands.core.main import create_runtime, run_controller
+from openhands.critic import AgentFinishedCritic
+from openhands.events.action import CmdRunAction, FileReadAction, MessageAction
+from openhands.events.observation import (
+    CmdOutputObservation,
+    ErrorObservation,
+    FileReadObservation,
+)
+from openhands.events.serialization.event import event_from_dict, event_to_dict
+from openhands.runtime.base import Runtime
+from openhands.utils.async_utils import call_async_from_sync
+from openhands.utils.shutdown_listener import sleep_if_should_continue
+
+USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
+RUN_WITH_BROWSING = os.environ.get('RUN_WITH_BROWSING', 'false').lower() == 'true'
+ENABLE_LLM_EDITOR = os.environ.get('ENABLE_LLM_EDITOR', 'false').lower() == 'true'
+BenchMode = Literal['swe', 'swt', 'swt-ci']
+
+# Global variable to track dataset type
+DATASET_TYPE = 'nc_bench'
+
+
+def set_dataset_type(dataset_name: str) -> str:
+    """Set dataset type based on dataset name."""
+    global DATASET_TYPE
+    DATASET_TYPE = 'nc_bench'
+
+    logger.info(f'Dataset type set to: {DATASET_TYPE}')
+
+
+AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
+    'CodeActAgent': codeact_user_response,
+}
+
+
+def _get_swebench_workspace_dir_name(instance: pd.Series) -> str:
+    return f'{instance.repo.split("/")[-1]}'
+
+
+def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageAction:
+    workspace_dir_name = _get_swebench_workspace_dir_name(instance)
+    metadata.details['mode']
+
+    # Determine the template file based on mode and LLM
+
+    template_name = 'nc.j2'
+
+    # Set up Jinja2 environment
+    # Assuming templates are in 'evaluation/benchmarks/swe_bench/prompts' relative to this script
+    prompts_dir = os.path.join(os.path.dirname(__file__), 'prompts')
+    env = Environment(loader=FileSystemLoader(prompts_dir))
+    template = env.get_template(template_name)
+
+    # Prepare context for rendering
+    context = {
+        'instance': instance,
+        'workspace_dir_name': workspace_dir_name,
+        'metadata': metadata,  # Pass metadata if needed in templates
+    }
+
+    context['test_instructions'] = ''  # Ensure it's defined for other modes
+
+    # Render the instruction
+    instruction = template.render(context)
+
+    if RUN_WITH_BROWSING:
+        instruction += (
+            '<IMPORTANT!>\nYou SHOULD NEVER attempt to browse the web. </IMPORTANT!>\n'
+        )
+
+    if 'image_assets' in instance:
+        assets = json.loads(instance['image_assets'])
+        assert 'problem_statement' in assets, (
+            'problem_statement is required in image_assets'
+        )
+        image_urls = assets['problem_statement']
+        return MessageAction(content=instruction, image_urls=image_urls)
+    return MessageAction(content=instruction)
+
+
+DEFAULT_DOCKER_IMAGE_PREFIX = os.environ.get(
+    'EVAL_DOCKER_IMAGE_PREFIX', 'docker.io/xingyaoww/'
+)
+logger.info(f'Default docker image prefix: {DEFAULT_DOCKER_IMAGE_PREFIX}')
+
+
+def get_instance_docker_image(
+    instance_id: str,
+    swebench_official_image: bool = False,
+) -> str:
+    if swebench_official_image:
+        # Official NoCode-Bench image
+        image_name = f'ncbench_{instance_id}:latest'.lower()
+        logger.debug(f'Using official NoCode-Bench image: {image_name}')
+        return image_name
+    else:
+        raise
+
+
+def get_config(
+    instance: pd.Series,
+    metadata: EvalMetadata,
+) -> OpenHandsConfig:
+    # We use a different instance image for the each instance of NoCode-bench eval
+    use_swebench_official_image = True
+
+    base_container_image = get_instance_docker_image(
+        instance['instance_id'],
+        swebench_official_image=use_swebench_official_image,
+    )
+    logger.info(
+        f'Using instance container image: {base_container_image}. '
+        f'Please make sure this image exists. '
+        f'Submit an issue on https://github.com/All-Hands-AI/OpenHands if you run into any issues.'
+    )
+
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = base_container_image
+    sandbox_config.enable_auto_lint = True
+    sandbox_config.use_host_network = False
+    # Add platform to the sandbox config to solve issue 4401
+    sandbox_config.platform = 'linux/amd64'
+    sandbox_config.remote_runtime_resource_factor = get_instance_resource_factor(
+        dataset_name=metadata.dataset,
+        instance_id=instance['instance_id'],
+    )
+
+    config = OpenHandsConfig(
+        default_agent=metadata.agent_class,
+        run_as_openhands=False,
+        max_iterations=metadata.max_iterations,
+        runtime=os.environ.get('RUNTIME', 'docker'),
+        sandbox=sandbox_config,
+        # do not mount workspace
+        workspace_base=None,
+        workspace_mount_path=None,
+    )
+
+    config.set_llm_config(
+        update_llm_config_for_completions_logging(
+            metadata.llm_config, metadata.eval_output_dir, instance['instance_id']
+        )
+    )
+    # get 'draft_editor' config if exists
+    config.set_llm_config(get_llm_config_arg('draft_editor'), 'draft_editor')
+
+    agent_config = AgentConfig(
+        enable_jupyter=False,
+        enable_browsing=RUN_WITH_BROWSING,
+        enable_llm_editor=ENABLE_LLM_EDITOR,
+        enable_mcp=False,
+        condenser=metadata.condenser_config,
+        enable_prompt_extensions=False,
+    )
+    config.set_agent_config(agent_config)
+    return config
+
+
+def make_serializable(obj):
+    if isinstance(obj, pd.Series):
+        obj = obj.to_dict()
+    if isinstance(obj, dict):
+        return {k: make_serializable(v) for k, v in obj.items()}
+    elif isinstance(obj, list):
+        return [make_serializable(v) for v in obj]
+    elif isinstance(obj, tuple):
+        return tuple(make_serializable(v) for v in obj)
+    elif isinstance(obj, np.ndarray):
+        return obj.tolist()
+    elif isinstance(obj, pd.Timestamp):
+        return str(obj)
+    else:
+        return obj
+
+
+def initialize_runtime(
+    runtime: Runtime,
+    instance: pd.Series,  # this argument is not required
+    metadata: EvalMetadata,
+):
+    """Initialize the runtime for the agent.
+
+    This function is called before the runtime is used to run the agent.
+    """
+    logger.info('-' * 30)
+    logger.info('BEGIN Runtime Initialization Fn')
+    logger.info('-' * 30)
+    workspace_dir_name = _get_swebench_workspace_dir_name(instance)
+    obs: CmdOutputObservation
+
+    # Set instance id and git configuration
+    action = CmdRunAction(
+        command=f"""echo 'export SWE_INSTANCE_ID={instance['instance_id']}' >> ~/.bashrc && echo 'export PIP_CACHE_DIR=~/.cache/pip' >> ~/.bashrc && echo "alias git='git --no-pager'" >> ~/.bashrc && git config --global core.pager "" && git config --global diff.binary false"""
+    )
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0,
+        f'Failed to export SWE_INSTANCE_ID and configure git: {str(obs)}',
+    )
+
+    action = CmdRunAction(command="""export USER=$(whoami); echo USER=${USER} """)
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(obs.exit_code == 0, f'Failed to export USER: {str(obs)}')
+
+    # inject the init script
+    script_dir = os.path.dirname(__file__)
+
+    # inject the instance info
+    action = CmdRunAction(command='mkdir -p /swe_util/eval_data/instances')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0,
+        f'Failed to create /swe_util/eval_data/instances: {str(obs)}',
+    )
+
+    swe_instance_json_name = 'swe-bench-instance.json'
+    with tempfile.TemporaryDirectory() as temp_dir:
+        # Construct the full path for the desired file name within the temporary directory
+        temp_file_path = os.path.join(temp_dir, swe_instance_json_name)
+        # Write to the file with the desired name within the temporary directory
+
+        with open(temp_file_path, 'w') as f:
+            if not isinstance(instance, dict):
+                instance_dict = make_serializable(instance)
+            else:
+                instance_dict = dict(instance)
+
+            if DATASET_TYPE == 'nc_bench':
+                config = MAP_REPO_TO_CONFIG.get(instance['repo'], {}).get(
+                    instance['version'], []
+                )
+                docker_conda_env_name = config['conda_env']
+                instance_dict['conda_env'] = docker_conda_env_name
+
+            json.dump([instance_dict], f)
+
+        # Copy the file to the desired location
+        runtime.copy_to(temp_file_path, '/swe_util/eval_data/instances/')
+
+        # inject the instance swe entry
+        entry_script_path = 'instance_nc_entry.sh'
+
+        runtime.copy_to(
+            str(os.path.join(script_dir, f'scripts/setup/{entry_script_path}')),
+            '/swe_util/',
+        )
+
+    action = CmdRunAction(command='cat ~/.bashrc')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(obs.exit_code == 0, f'Failed to cat ~/.bashrc: {str(obs)}')
+
+    action = CmdRunAction(command='source ~/.bashrc')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    if isinstance(obs, ErrorObservation):
+        logger.error(f'Failed to source ~/.bashrc: {str(obs)}')
+    assert_and_raise(obs.exit_code == 0, f'Failed to source ~/.bashrc: {str(obs)}')
+
+    action = CmdRunAction(command=f'source /swe_util/{entry_script_path}')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0,
+        f'Failed to source /swe_util/{entry_script_path}: {str(obs)}',
+    )
+
+    action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0,
+        f'Failed to cd to /workspace/{workspace_dir_name}: {str(obs)}',
+    )
+
+    action = CmdRunAction(command='git reset --hard')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(obs.exit_code == 0, f'Failed to git reset --hard: {str(obs)}')
+
+    action = CmdRunAction(
+        command='for remote_name in $(git remote); do git remote remove "${remote_name}"; done'
+    )
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(obs.exit_code == 0, f'Failed to remove git remotes: {str(obs)}')
+
+    if DATASET_TYPE != 'Multimodal' and DATASET_TYPE != 'SWE-bench-Live':
+        # Only for non-multimodal datasets, we need to activate the testbed environment for Python
+        # SWE-Bench multimodal datasets and SWE-bench-Live are not using the testbed environment
+        action = CmdRunAction(command='which python')
+        action.set_hard_timeout(600)
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+        assert_and_raise(
+            obs.exit_code == 0,
+            f'Expected to find python interpreter, but got: {str(obs)}',
+        )
+
+    logger.info('-' * 30)
+    logger.info('END Runtime Initialization Fn')
+    logger.info('-' * 30)
+
+
+def complete_runtime(
+    runtime: Runtime,
+    instance: pd.Series,  # this argument is not required, but it is used to get the workspace_dir_name
+) -> dict[str, Any]:
+    """Complete the runtime for the agent.
+
+    This function is called before the runtime is used to run the agent.
+    If you need to do something in the sandbox to get the correctness metric after
+    the agent has run, modify this function.
+    """
+    logger.info('-' * 30)
+    logger.info('BEGIN Runtime Completion Fn')
+    logger.info('-' * 30)
+    obs: CmdOutputObservation
+    workspace_dir_name = _get_swebench_workspace_dir_name(instance)
+
+    action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+    if obs.exit_code == -1:
+        # The previous command is still running
+        # We need to kill previous command
+        logger.info('The previous command is still running, trying to kill it...')
+        action = CmdRunAction(command='C-c')
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+        # Then run the command again
+        action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
+        action.set_hard_timeout(600)
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+    if obs.exit_code == -1:
+        # The previous command is still running
+        # We need to kill previous command
+        logger.info('The previous command is still running, trying to ctrl+z it...')
+        action = CmdRunAction(command='C-z')
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+        # Then run the command again
+        action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
+        action.set_hard_timeout(600)
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to cd to /workspace/{workspace_dir_name}: {str(obs)}',
+    )
+
+    action = CmdRunAction(command='git config --global core.pager ""')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to git config --global core.pager "": {str(obs)}',
+    )
+
+    # First check for any git repositories in subdirectories
+    action = CmdRunAction(command='find . -type d -name .git -not -path "./.git"')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to find git repositories: {str(obs)}',
+    )
+
+    git_dirs = [p for p in obs.content.strip().split('\n') if p]
+    if git_dirs:
+        # Remove all .git directories in subdirectories
+        for git_dir in git_dirs:
+            action = CmdRunAction(command=f'rm -rf "{git_dir}"')
+            action.set_hard_timeout(600)
+            logger.info(action, extra={'msg_type': 'ACTION'})
+            obs = runtime.run_action(action)
+            logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+            assert_and_raise(
+                isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+                f'Failed to remove git directory {git_dir}: {str(obs)}',
+            )
+
+    # add all files
+    action = CmdRunAction(command='git add -A')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to git add -A: {str(obs)}',
+    )
+
+    # Remove binary files from git staging
+    action = CmdRunAction(command=remove_binary_files_from_git())
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
+        f'Failed to remove binary files: {str(obs)}',
+    )
+
+    n_retries = 0
+    git_patch = None
+    while n_retries < 5:
+        action = CmdRunAction(
+            command=f'git diff --no-color --cached {instance["base_commit"]} > patch.diff'
+        )
+        action.set_hard_timeout(max(300 + 100 * n_retries, 600))
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+        n_retries += 1
+        if isinstance(obs, CmdOutputObservation):
+            if obs.exit_code == 0:
+                # Read the patch file
+                action = FileReadAction(path='patch.diff')
+                action.set_hard_timeout(max(300 + 100 * n_retries, 600))
+                logger.info(action, extra={'msg_type': 'ACTION'})
+                obs = runtime.run_action(action)
+                logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+                if isinstance(obs, FileReadObservation):
+                    git_patch = obs.content
+                    break
+                elif isinstance(obs, ErrorObservation):
+                    # Fall back to cat "patch.diff" to get the patch
+                    assert 'File could not be decoded as utf-8' in obs.content
+                    action = CmdRunAction(command='cat patch.diff')
+                    action.set_hard_timeout(max(300 + 100 * n_retries, 600))
+                    logger.info(action, extra={'msg_type': 'ACTION'})
+                    obs = runtime.run_action(action)
+                    assert isinstance(obs, CmdOutputObservation) and obs.exit_code == 0
+                    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+                    git_patch = obs.content
+                    break
+                else:
+                    assert_and_raise(False, f'Unexpected observation type: {str(obs)}')
+            else:
+                logger.info('Failed to get git diff, retrying...')
+                sleep_if_should_continue(10)
+        elif isinstance(obs, ErrorObservation):
+            logger.error(f'Error occurred: {obs.content}. Retrying...')
+            sleep_if_should_continue(10)
+        else:
+            assert_and_raise(False, f'Unexpected observation type: {str(obs)}')
+
+    assert_and_raise(git_patch is not None, 'Failed to get git diff (None)')
+
+    # Remove binary diffs from the patch
+    git_patch = remove_binary_diffs(git_patch)
+
+    logger.info('-' * 30)
+    logger.info('END Runtime Completion Fn')
+    logger.info('-' * 30)
+    return {'git_patch': git_patch}
+
+
+def process_instance(
+    instance: pd.Series,
+    metadata: EvalMetadata,
+    reset_logger: bool = True,
+    runtime_failure_count: int = 0,
+) -> EvalOutput:
+    config = get_config(instance, metadata)
+
+    # Setup the logger properly, so you can run multi-processing to parallelize the evaluation
+    if reset_logger:
+        log_dir = os.path.join(metadata.eval_output_dir, 'infer_logs')
+        reset_logger_for_multiprocessing(logger, instance.instance_id, log_dir)
+    else:
+        logger.info(f'Starting evaluation for instance {instance.instance_id}.')
+
+    # Increase resource_factor with increasing attempt_id
+    if runtime_failure_count > 0:
+        config.sandbox.remote_runtime_resource_factor = min(
+            config.sandbox.remote_runtime_resource_factor * (2**runtime_failure_count),
+            8,
+        )
+        logger.warning(
+            f'This is the {runtime_failure_count + 1}th attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
+        )
+
+    metadata = copy.deepcopy(metadata)
+    metadata.details['runtime_failure_count'] = runtime_failure_count
+    metadata.details['remote_runtime_resource_factor'] = (
+        config.sandbox.remote_runtime_resource_factor
+    )
+
+    runtime = create_runtime(config)
+    call_async_from_sync(runtime.connect)
+
+    try:
+        initialize_runtime(runtime, instance, metadata)
+
+        message_action = get_instruction(instance, metadata)
+
+        # Here's how you can run the agent (similar to the `main` function) and get the final task state
+        state: State | None = asyncio.run(
+            run_controller(
+                config=config,
+                initial_user_action=message_action,
+                runtime=runtime,
+                fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN[
+                    metadata.agent_class
+                ],
+            )
+        )
+
+        # if fatal error, throw EvalError to trigger re-run
+        if is_fatal_evaluation_error(state.last_error):
+            raise EvalException('Fatal error detected: ' + state.last_error)
+
+        # ======= THIS IS SWE-Bench specific =======
+        # Get git patch
+        if DATASET_TYPE == 'SWE-bench-Live':
+            from evaluation.benchmarks.swe_bench.live_utils import (
+                complete_runtime as complete_runtime_fn,
+            )
+        else:
+            complete_runtime_fn = complete_runtime
+        return_val = complete_runtime_fn(runtime, instance)
+        git_patch = return_val['git_patch']
+        logger.info(
+            f'Got git diff for instance {instance.instance_id}:\n--------\n{git_patch}\n--------'
+        )
+    finally:
+        runtime.close()
+    # ==========================================
+
+    # ======= Attempt to evaluate the agent's edits =======
+    # we use eval_infer.sh to evaluate the agent's edits, not here
+    # because the agent may alter the environment / testcases
+    test_result = {
+        'git_patch': git_patch,
+    }
+
+    # If you are working on some simpler benchmark that only evaluates the final model output (e.g., in a MessageAction)
+    # You can simply get the LAST `MessageAction` from the returned `state.history` and parse it for evaluation.
+    if state is None:
+        raise ValueError('State should not be None.')
+
+    # NOTE: this is NO LONGER the event stream, but an agent history that includes delegate agent's events
+    histories = [event_to_dict(event) for event in state.history]
+    metrics = get_metrics(state)
+
+    # Save the output
+    instruction = message_action.content
+    if message_action.image_urls:
+        instruction += (
+            '\n\n<image_urls>' + '\n'.join(message_action.image_urls) + '</image_urls>'
+        )
+    output = EvalOutput(
+        instance_id=instance.instance_id,
+        instruction=instruction,
+        instance=instance.to_dict(),  # SWE Bench specific
+        test_result=test_result,
+        metadata=metadata,
+        history=histories,
+        metrics=metrics,
+        error=state.last_error if state and state.last_error else None,
+    )
+    return output
+
+
+def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
+    file_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'config.toml')
+    if os.path.exists(file_path):
+        with open(file_path, 'r') as file:
+            data = toml.load(file)
+            if 'selected_ids' in data:
+                selected_ids = data['selected_ids']
+                logger.info(
+                    f'Filtering {len(selected_ids)} tasks from "selected_ids"...'
+                )
+                subset = dataset[dataset[filter_column].isin(selected_ids)]
+                logger.info(f'Retained {subset.shape[0]} tasks after filtering')
+                return subset
+            if 'selected_repos' in data:
+                # repos for the swe-bench instances:
+                # ['astropy/astropy', 'django/django', 'matplotlib/matplotlib', 'mwaskom/seaborn', 'pallets/flask', 'psf/requests', 'pydata/xarray', 'pylint-dev/pylint', 'pytest-dev/pytest', 'scikit-learn/scikit-learn', 'sphinx-doc/sphinx', 'sympy/sympy']
+                selected_repos = data['selected_repos']
+                if isinstance(selected_repos, str):
+                    selected_repos = [selected_repos]
+                assert isinstance(selected_repos, list)
+                logger.info(
+                    f'Filtering {selected_repos} tasks from "selected_repos"...'
+                )
+                subset = dataset[dataset['repo'].isin(selected_repos)]
+                logger.info(f'Retained {subset.shape[0]} tasks after filtering')
+                return subset
+
+    skip_ids = os.environ.get('SKIP_IDS', '').split(',')
+    if len(skip_ids) > 0:
+        logger.info(f'Filtering {len(skip_ids)} tasks from "SKIP_IDS"...')
+        return dataset[~dataset[filter_column].isin(skip_ids)]
+    return dataset
+
+
+if __name__ == '__main__':
+    parser = get_evaluation_parser()
+    parser.add_argument(
+        '--dataset',
+        type=str,
+        default='NoCode-bench/NoCode-bench_Verified',
+        help='data set to evaluate on, either full-test or lite-test',
+    )
+    parser.add_argument(
+        '--split',
+        type=str,
+        default='test',
+        help='split to evaluate on',
+    )
+    parser.add_argument(
+        '--mode',
+        type=str,
+        default='swe',
+        choices=['swe', 'swt', 'swt-ci'],
+        help="mode to run the evaluation, either 'swe', 'swt', or 'swt-ci'",
+    )
+
+    args, _ = parser.parse_known_args()
+
+    # NOTE: It is preferable to load datasets from huggingface datasets and perform post-processing
+    # so we don't need to manage file uploading to OpenHands's repo
+
+    dataset = load_dataset(args.dataset, args.split)
+
+    # Set the global dataset type based on dataset name
+    set_dataset_type(args.dataset)
+
+    swe_bench_tests = filter_dataset(dataset.to_pandas(), 'instance_id')
+    logger.info(
+        f'Loaded dataset {args.dataset} with split {args.split}: {len(swe_bench_tests)} tasks'
+    )
+
+    llm_config = None
+    if args.llm_config:
+        llm_config = get_llm_config_arg(args.llm_config)
+        llm_config.log_completions = True
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
+
+    if llm_config is None:
+        raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
+
+    # Get condenser config from environment variable
+    condenser_name = os.environ.get('EVAL_CONDENSER')
+    if condenser_name:
+        condenser_config = get_condenser_config_arg(condenser_name)
+        if condenser_config is None:
+            raise ValueError(
+                f'Could not find Condenser config: EVAL_CONDENSER={condenser_name}'
+            )
+    else:
+        # If no specific condenser config is provided via env var, default to NoOpCondenser
+        condenser_config = NoOpCondenserConfig()
+        logger.debug(
+            'No Condenser config provided via EVAL_CONDENSER, using NoOpCondenser.'
+        )
+
+    details = {'mode': args.mode}
+    _agent_cls = openhands.agenthub.Agent.get_cls(args.agent_cls)
+
+    dataset_descrption = (
+        args.dataset.replace('/', '__') + '-' + args.split.replace('/', '__')
+    )
+    metadata = make_metadata(
+        llm_config,
+        dataset_descrption,
+        args.agent_cls,
+        args.max_iterations,
+        args.eval_note,
+        args.eval_output_dir,
+        details=details,
+        condenser_config=condenser_config,
+    )
+
+    output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
+    print(f'### OUTPUT FILE: {output_file} ###')
+
+    # Run evaluation in iterative mode:
+    # If a rollout fails to output AgentFinishAction, we will try again until it succeeds OR total 3 attempts have been made.
+    ITERATIVE_EVAL_MODE = (
+        os.environ.get('ITERATIVE_EVAL_MODE', 'false').lower() == 'true'
+    )
+    ITERATIVE_EVAL_MODE_MAX_ATTEMPTS = int(
+        os.environ.get('ITERATIVE_EVAL_MODE_MAX_ATTEMPTS', '3')
+    )
+
+    if not ITERATIVE_EVAL_MODE:
+        # load the dataset
+        instances = prepare_dataset(swe_bench_tests, output_file, args.eval_n_limit)
+        if len(instances) > 0 and not isinstance(
+            instances['PASS2PASS'][instances['PASS2PASS'].index[0]], str
+        ):
+            for col in ['PASS2PASS', 'FAIL2PASS']:
+                instances[col] = instances[col].apply(lambda x: str(x))
+
+        run_evaluation_nocode_bench(
+            instances,
+            metadata,
+            output_file,
+            args.eval_num_workers,
+            process_instance,
+            timeout_seconds=8
+            * 60
+            * 60,  # 8 hour PER instance should be more than enough
+            max_retries=5,
+        )
+    else:
+        critic = AgentFinishedCritic()
+
+        def get_cur_output_file_path(attempt: int) -> str:
+            return (
+                f'{output_file.removesuffix(".jsonl")}.critic_attempt_{attempt}.jsonl'
+            )
+
+        eval_ids = None
+        for attempt in range(1, ITERATIVE_EVAL_MODE_MAX_ATTEMPTS + 1):
+            cur_output_file = get_cur_output_file_path(attempt)
+            logger.info(
+                f'Running evaluation with critic {critic.__class__.__name__} for attempt {attempt} of {ITERATIVE_EVAL_MODE_MAX_ATTEMPTS}.'
+            )
+
+            # For deterministic eval, we set temperature to 0.1 for (>1) attempt
+            # so hopefully we get slightly different results
+            if attempt > 1 and metadata.llm_config.temperature == 0:
+                logger.info(
+                    f'Detected temperature is 0 for (>1) attempt {attempt}. Setting temperature to 0.1...'
+                )
+                metadata.llm_config.temperature = 0.1
+
+            # Load instances - at first attempt, we evaluate all instances
+            # On subsequent attempts, we only evaluate the instances that failed the previous attempt determined by critic
+            instances = prepare_dataset(
+                swe_bench_tests, cur_output_file, args.eval_n_limit, eval_ids=eval_ids
+            )
+            if len(instances) > 0 and not isinstance(
+                instances['PASS2PASS'][instances['PASS2PASS'].index[0]], str
+            ):
+                for col in ['PASS2PASS', 'FAIL2PASS']:
+                    instances[col] = instances[col].apply(lambda x: str(x))
+
+            # Run evaluation - but save them to cur_output_file
+            logger.info(
+                f'Evaluating {len(instances)} instances for attempt {attempt}...'
+            )
+            run_evaluation_nocode_bench(
+                instances,
+                metadata,
+                cur_output_file,
+                args.eval_num_workers,
+                process_instance,
+                timeout_seconds=8
+                * 60
+                * 60,  # 8 hour PER instance should be more than enough
+                max_retries=5,
+            )
+
+            # When eval is done, we update eval_ids to the instances that failed the current attempt
+            instances_failed = []
+            logger.info(
+                f'Use critic {critic.__class__.__name__} to check {len(instances)} instances for attempt {attempt}...'
+            )
+            with open(cur_output_file, 'r') as f:
+                for line in f:
+                    instance = json.loads(line)
+                    try:
+                        history = [
+                            event_from_dict(event) for event in instance['history']
+                        ]
+                        critic_result = critic.evaluate(
+                            history, instance['test_result'].get('git_patch', '')
+                        )
+                        if not critic_result.success:
+                            instances_failed.append(instance['instance_id'])
+                    except Exception as e:
+                        logger.error(
+                            f'Error loading history for instance {instance["instance_id"]}: {e}'
+                        )
+                        instances_failed.append(instance['instance_id'])
+            logger.info(
+                f'{len(instances_failed)} instances failed the current attempt {attempt}: {instances_failed}'
+            )
+            eval_ids = instances_failed
+
+            # If no instances failed, we break
+            if len(instances_failed) == 0:
+                break
+
+        # Then we should aggregate the results from all attempts into the original output file
+        # and remove the intermediate files
+        logger.info(
+            'Aggregating results from all attempts into the original output file...'
+        )
+        fout = open(output_file, 'w')
+        added_instance_ids = set()
+        for attempt in reversed(range(1, ITERATIVE_EVAL_MODE_MAX_ATTEMPTS + 1)):
+            cur_output_file = get_cur_output_file_path(attempt)
+            if not os.path.exists(cur_output_file):
+                logger.warning(
+                    f'Intermediate output file {cur_output_file} does not exist. Skipping...'
+                )
+                continue
+
+            with open(cur_output_file, 'r') as f:
+                for line in f:
+                    instance = json.loads(line)
+                    # Also make sure git_patch is not empty - otherwise we fall back to previous attempt (empty patch is worse than anything else)
+                    if (
+                        instance['instance_id'] not in added_instance_ids
+                        and instance['test_result'].get('git_patch', '').strip()
+                    ):
+                        fout.write(line)
+                        added_instance_ids.add(instance['instance_id'])
+            logger.info(
+                f'Aggregated instances from {cur_output_file}. Total instances added so far: {len(added_instance_ids)}'
+            )
+        fout.close()
+        logger.info(
+            f'Done! Total {len(added_instance_ids)} instances added to {output_file}'
+        )

evaluation/benchmarks/nocode_bench/scripts/eval/convert.py

@@ -0,0 +1,33 @@
+import argparse
+import json
+
+
+def main(output_jsonl: str):
+    with open(output_jsonl, 'r') as f:
+        for line in f:
+            try:
+                output = json.loads(line)
+                pred = {
+                    'instance_id': output['instance_id'],
+                    'model_name_or_path': output['metadata']['llm_config']['model'],
+                    'model_patch': output['test_result']['git_patch'],
+                }
+            except Exception as e:
+                print(
+                    f'Error while reading output of instance {output["instance_id"]}: {e}'
+                )
+
+            print(json.dumps(pred))
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '--output_jsonl',
+        type=str,
+        required=True,
+        help='Path to the prediction file (.../outputs.jsonl)',
+    )
+    args = parser.parse_args()
+
+    main(args.output_jsonl)

evaluation/benchmarks/nocode_bench/scripts/eval/verify_costs.py

@@ -0,0 +1,104 @@
+import argparse
+
+import pandas as pd
+
+from openhands.core.logger import openhands_logger as logger
+
+
+def verify_instance_costs(row: pd.Series) -> float:
+    """
+    Verifies that the accumulated_cost matches the sum of individual costs in metrics.
+    Also checks for duplicate consecutive costs which might indicate buggy counting.
+    If the consecutive costs are identical, the file is affected by this bug:
+    https://github.com/All-Hands-AI/OpenHands/issues/5383
+
+    Args:
+        row: DataFrame row containing instance data with metrics
+    Returns:
+        float: The verified total cost for this instance (corrected if needed)
+    """
+    try:
+        metrics = row.get('metrics')
+        if not metrics:
+            logger.warning(f'Instance {row["instance_id"]}: No metrics found')
+            return 0.0
+
+        accumulated = metrics.get('accumulated_cost')
+        costs = metrics.get('costs', [])
+
+        if accumulated is None:
+            logger.warning(
+                f'Instance {row["instance_id"]}: No accumulated_cost in metrics'
+            )
+            return 0.0
+
+        # Check for duplicate consecutive costs and systematic even-odd pairs
+        has_duplicate = False
+        all_pairs_match = True
+
+        # Check each even-odd pair (0-1, 2-3, etc.)
+        for i in range(0, len(costs) - 1, 2):
+            if abs(costs[i]['cost'] - costs[i + 1]['cost']) < 1e-6:
+                has_duplicate = True
+                logger.debug(
+                    f'Instance {row["instance_id"]}: Possible buggy double-counting detected! '
+                    f'Steps {i} and {i + 1} have identical costs: {costs[i]["cost"]:.2f}'
+                )
+            else:
+                all_pairs_match = False
+                break
+
+        # Calculate total cost, accounting for buggy double counting if detected
+        if len(costs) >= 2 and has_duplicate and all_pairs_match:
+            paired_steps_cost = sum(
+                cost_entry['cost']
+                for cost_entry in costs[: -1 if len(costs) % 2 else None]
+            )
+            real_paired_cost = paired_steps_cost / 2
+
+            unpaired_cost = costs[-1]['cost'] if len(costs) % 2 else 0
+            total_cost = real_paired_cost + unpaired_cost
+
+        else:
+            total_cost = sum(cost_entry['cost'] for cost_entry in costs)
+
+        if not abs(total_cost - accumulated) < 1e-6:
+            logger.warning(
+                f'Instance {row["instance_id"]}: Cost mismatch: '
+                f'accumulated: {accumulated:.2f}, sum of costs: {total_cost:.2f}, '
+            )
+
+        return total_cost
+
+    except Exception as e:
+        logger.error(
+            f'Error verifying costs for instance {row.get("instance_id", "UNKNOWN")}: {e}'
+        )
+        return 0.0
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description='Verify costs in SWE-bench output file'
+    )
+    parser.add_argument(
+        'input_filepath', type=str, help='Path to the output.jsonl file'
+    )
+    args = parser.parse_args()
+
+    try:
+        # Load and verify the JSONL file
+        df = pd.read_json(args.input_filepath, lines=True)
+        logger.info(f'Loaded {len(df)} instances from {args.input_filepath}')
+
+        # Verify costs for each instance and sum up total
+        total_cost = df.apply(verify_instance_costs, axis=1).sum()
+        logger.info(f'Total verified cost across all instances: ${total_cost:.2f}')
+
+    except Exception as e:
+        logger.error(f'Failed to process file: {e}')
+        raise
+
+
+if __name__ == '__main__':
+    main()

evaluation/benchmarks/nocode_bench/scripts/run_infer_nc.sh

@@ -0,0 +1,146 @@
+#!/usr/bin/env bash
+set -eo pipefail
+
+source "evaluation/utils/version_control.sh"
+
+MODEL_CONFIG=$1
+COMMIT_HASH=$2
+AGENT=$3
+EVAL_LIMIT=$4
+MAX_ITER=$5
+NUM_WORKERS=$6
+DATASET=$7
+SPLIT=$8
+N_RUNS=$9
+MODE=${10}
+
+
+if [ -z "$NUM_WORKERS" ]; then
+  NUM_WORKERS=1
+  echo "Number of workers not specified, use default $NUM_WORKERS"
+fi
+checkout_eval_branch
+
+if [ -z "$AGENT" ]; then
+  echo "Agent not specified, use default CodeActAgent"
+  AGENT="CodeActAgent"
+fi
+
+if [ -z "$MAX_ITER" ]; then
+  echo "MAX_ITER not specified, use default 100"
+  MAX_ITER=100
+fi
+
+if [ -z "$RUN_WITH_BROWSING" ]; then
+  echo "RUN_WITH_BROWSING not specified, use default false"
+  RUN_WITH_BROWSING=false
+fi
+
+
+if [ -z "$DATASET" ]; then
+  echo "DATASET not specified, use default princeton-nlp/SWE-bench_Lite"
+  DATASET="princeton-nlp/SWE-bench_Lite"
+fi
+
+if [ -z "$SPLIT" ]; then
+  echo "SPLIT not specified, use default test"
+  SPLIT="test"
+fi
+
+if [ -z "$MODE" ]; then
+  MODE="swe"
+  echo "MODE not specified, use default $MODE"
+fi
+
+if [ -n "$EVAL_CONDENSER" ]; then
+  echo "Using Condenser Config: $EVAL_CONDENSER"
+else
+  echo "No Condenser Config provided via EVAL_CONDENSER, use default (NoOpCondenser)."
+fi
+
+export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
+echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
+
+get_openhands_version
+
+echo "AGENT: $AGENT"
+echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "MODEL_CONFIG: $MODEL_CONFIG"
+echo "DATASET: $DATASET"
+echo "SPLIT: $SPLIT"
+echo "MAX_ITER: $MAX_ITER"
+echo "NUM_WORKERS: $NUM_WORKERS"
+echo "COMMIT_HASH: $COMMIT_HASH"
+echo "MODE: $MODE"
+echo "EVAL_CONDENSER: $EVAL_CONDENSER"
+
+# Default to NOT use Hint
+if [ -z "$USE_HINT_TEXT" ]; then
+  export USE_HINT_TEXT=false
+fi
+echo "USE_HINT_TEXT: $USE_HINT_TEXT"
+EVAL_NOTE="$OPENHANDS_VERSION"
+# if not using Hint, add -no-hint to the eval note
+if [ "$USE_HINT_TEXT" = false ]; then
+  EVAL_NOTE="$EVAL_NOTE-no-hint"
+fi
+
+if [ "$RUN_WITH_BROWSING" = true ]; then
+  EVAL_NOTE="$EVAL_NOTE-with-browsing"
+fi
+
+if [ -n "$EXP_NAME" ]; then
+  EVAL_NOTE="$EVAL_NOTE-$EXP_NAME"
+fi
+# if mode != swe, add mode to the eval note
+if [ "$MODE" != "swe" ]; then
+  EVAL_NOTE="${EVAL_NOTE}-${MODE}"
+fi
+# Add condenser config to eval note if provided
+if [ -n "$EVAL_CONDENSER" ]; then
+  EVAL_NOTE="${EVAL_NOTE}-${EVAL_CONDENSER}"
+fi
+
+function run_eval() {
+  local eval_note="${1}"
+  COMMAND="poetry run python evaluation/benchmarks/nocode_bench/run_infer_nc.py \
+    --agent-cls $AGENT \
+    --llm-config $MODEL_CONFIG \
+    --max-iterations $MAX_ITER \
+    --eval-num-workers $NUM_WORKERS \
+    --eval-note $eval_note \
+    --dataset $DATASET \
+    --split $SPLIT \
+    --mode $MODE"
+
+
+
+  if [ -n "$EVAL_LIMIT" ]; then
+    echo "EVAL_LIMIT: $EVAL_LIMIT"
+    COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
+  fi
+
+  # Run the command
+  eval $COMMAND
+}
+
+unset SANDBOX_ENV_GITHUB_TOKEN # prevent the agent from using the github token to push
+if [ -z "$N_RUNS" ]; then
+  N_RUNS=1
+  echo "N_RUNS not specified, use default $N_RUNS"
+fi
+
+# Skip runs if the run number is in the SKIP_RUNS list
+# read from env variable SKIP_RUNS as a comma separated list of run numbers
+SKIP_RUNS=(${SKIP_RUNS//,/ })
+for i in $(seq 1 $N_RUNS); do
+  if [[ " ${SKIP_RUNS[@]} " =~ " $i " ]]; then
+    echo "Skipping run $i"
+    continue
+  fi
+  current_eval_note="$EVAL_NOTE-run_$i"
+  echo "EVAL_NOTE: $current_eval_note"
+  run_eval $current_eval_note
+done
+
+checkout_original_branch

evaluation/benchmarks/nocode_bench/scripts/setup/compare_patch_filename.py

@@ -0,0 +1,54 @@
+"""This script compares gold patches with OpenHands-generated patches and check whether
+OpenHands found the right (set of) files to modify.
+"""
+
+import argparse
+import json
+import re
+
+
+def extract_modified_files(patch):
+    modified_files = set()
+    file_pattern = re.compile(r'^diff --git a/(.*?) b/')
+
+    for line in patch.split('\n'):
+        match = file_pattern.match(line)
+        if match:
+            modified_files.add(match.group(1))
+
+    return modified_files
+
+
+def process_report(oh_output_file):
+    succ = 0
+    fail = 0
+    for line in open(oh_output_file):
+        line = json.loads(line)
+        instance_id = line['instance_id']
+        gold_patch = line['swe_instance']['patch']
+        generated_patch = line['git_patch']
+        gold_modified_files = extract_modified_files(gold_patch)
+        # swe-bench lite only: a gold patch always contains exactly one file
+        assert len(gold_modified_files) == 1
+        generated_modified_files = extract_modified_files(generated_patch)
+
+        # Check if all files in gold_patch are also in generated_patch
+        all_files_in_generated = gold_modified_files.issubset(generated_modified_files)
+        if all_files_in_generated:
+            succ += 1
+        else:
+            fail += 1
+            print(
+                f'{instance_id}: file mismatch, gold = {gold_modified_files}, generated = {generated_modified_files}'
+            )
+    print(
+        f'\nSUMMARY: {succ} out of {succ + fail} instances found correct files to edit, success rate = {succ / float(succ + fail)}'
+    )
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--oh_output_file', help='Path to the OH output file')
+    args = parser.parse_args()
+
+    process_report(args.oh_output_file)

evaluation/benchmarks/nocode_bench/scripts/setup/instance_nc_entry.sh

@@ -0,0 +1,53 @@
+#!/usr/bin/env bash
+
+source ~/.bashrc
+SWEUTIL_DIR=/swe_util
+
+if [ -z "$SWE_INSTANCE_ID" ]; then
+    echo "Error: SWE_INSTANCE_ID is not set." >&2
+    exit 1
+fi
+
+
+item=$(jq --arg INSTANCE_ID "$SWE_INSTANCE_ID" '.[] | select(.instance_id == $INSTANCE_ID)' $SWEUTIL_DIR/eval_data/instances/swe-bench-instance.json)
+
+
+if [[ -z "$item" ]]; then
+  echo "No item found for the provided instance ID."
+  exit 1
+fi
+
+REPO_NAME=$(echo "$item" | jq -r '.repo | split("/")[-1]')
+WORKSPACE_NAME="$REPO_NAME"
+
+
+echo "WORKSPACE_NAME: $WORKSPACE_NAME"
+
+
+# Clear the workspace
+if [ -d /workspace ]; then
+    rm -rf /workspace/*
+else
+    mkdir /workspace
+fi
+# Copy repo to workspace
+if [ -d /workspace/$WORKSPACE_NAME ]; then
+    rm -rf /workspace/$WORKSPACE_NAME
+fi
+mkdir -p /workspace
+
+SRC_DIR="/root/$REPO_NAME"
+DEST_DIR="/workspace/$WORKSPACE_NAME"
+
+cp -r "$SRC_DIR" "$DEST_DIR"
+
+
+
+echo ">> Extracting conda environment name..."
+CONDA_ENV_NAME=$(echo "$item" | jq -r '.conda_env // empty')
+
+# Activate instance-specific environment
+if [ -d /opt/miniconda3 ]; then
+    . /opt/miniconda3/etc/profile.d/conda.sh
+    conda activate $CONDA_ENV_NAME
+fi

evaluation/benchmarks/nocode_bench/scripts/utils/evaluation_utils.py

@@ -0,0 +1,154 @@
+import json
+import multiprocessing as mp
+from typing import Awaitable, Callable, TextIO
+
+import numpy as np
+import pandas as pd
+from pydantic import SecretStr
+from tqdm import tqdm
+
+from evaluation.utils.shared import (
+    EvalMetadata,
+    EvalOutput,
+    _process_instance_wrapper,
+    _process_instance_wrapper_mp,
+)
+from openhands.core.logger import openhands_logger as logger
+
+
+def update_progress_nc(
+    result: EvalOutput,
+    pbar: tqdm,
+    output_fp: TextIO,
+):
+    """Update the progress bar and write the result to the output file."""
+    pbar.update(1)
+    pbar.set_description(f'Instance {result.instance_id}')
+    pbar.set_postfix_str(f'Test Result: {str(result.test_result)[:300]}...')
+    logger.info(
+        f'Finished evaluation for instance {result.instance_id}: '
+        f'{str(result.test_result)[:300]}...\n'
+    )
+
+    def make_serializable(obj):
+        if isinstance(obj, pd.Series):
+            return make_serializable(obj.to_dict())
+
+        if isinstance(obj, dict):
+            return {k: make_serializable(v) for k, v in obj.items()}
+
+        elif isinstance(obj, (list, tuple, set)):
+            converted = [make_serializable(v) for v in obj]
+            if isinstance(obj, list):
+                return converted
+            elif isinstance(obj, tuple):
+                return tuple(converted)
+            else:  # set
+                return converted
+
+        elif isinstance(obj, np.ndarray):
+            return obj.tolist()
+
+        elif isinstance(obj, np.generic):
+            return obj.item()
+
+        elif isinstance(obj, pd.Timestamp):
+            return obj.isoformat()
+
+        elif SecretStr is not None and isinstance(obj, SecretStr):
+            return str(obj)
+
+        else:
+            return obj
+
+    try:
+        raw_data = result.model_dump(mode='python', round_trip=False)
+        safe_data = make_serializable(raw_data)
+        output_fp.write(json.dumps(safe_data, ensure_ascii=False) + '\n')
+        output_fp.flush()
+
+    except Exception as e:
+        logger.error(f'Failed to write full result: {e}')
+
+        fallback = {
+            'instance_id': result.instance_id,
+            'model_patch': result.test_result.get('git_patch', ''),
+        }
+        try:
+            output_fp.write(json.dumps(fallback, ensure_ascii=False) + '\n')
+            output_fp.flush()
+            logger.info(
+                f'Wrote fallback result for instance {result.instance_id}: only instance_id and model_patch.'
+            )
+        except Exception as e2:
+            logger.error(f'Failed to write fallback result: {e2}')
+
+
+def cleanup():
+    print('Cleaning up child processes...')
+    for process in mp.active_children():
+        print(f'Terminating child process: {process.name}')
+        process.terminate()
+        process.join()
+
+
+def run_evaluation_nocode_bench(
+    dataset: pd.DataFrame,
+    metadata: EvalMetadata | None,
+    output_file: str,
+    num_workers: int,
+    process_instance_func: Callable[
+        [pd.Series, EvalMetadata, bool], Awaitable[EvalOutput]
+    ],
+    max_retries: int = 5,  # number of retries for each instance
+    timeout_seconds: int | None = None,
+):
+    use_multiprocessing = num_workers > 1
+
+    if metadata is not None:
+        logger.info(
+            f'Evaluation started with Agent {metadata.agent_class}:\n'
+            f'model {metadata.llm_config.model}, max iterations {metadata.max_iterations}.\n'
+        )
+    else:
+        logger.warning('Running evaluation without metadata.')
+        logger.info(f'Evaluation started with {num_workers} workers.')
+
+    total_instances = len(dataset)
+    pbar = tqdm(total=total_instances, desc='Instances processed')
+    output_fp = open(output_file, 'a')
+
+    try:
+        if use_multiprocessing:
+            with mp.Pool(num_workers) as pool:
+                args_iter = (
+                    (
+                        process_instance_func,
+                        instance,
+                        metadata,
+                        True,
+                        max_retries,
+                        timeout_seconds,
+                    )
+                    for _, instance in dataset.iterrows()
+                )
+                results = pool.imap_unordered(_process_instance_wrapper_mp, args_iter)
+                for result in results:
+                    update_progress_nc(result, pbar, output_fp)
+        else:
+            for _, instance in dataset.iterrows():
+                result = _process_instance_wrapper(
+                    process_instance_func=process_instance_func,
+                    instance=instance,
+                    metadata=metadata,
+                    use_mp=False,
+                    max_retries=max_retries,
+                )
+                update_progress_nc(result, pbar, output_fp)
+
+    except KeyboardInterrupt:
+        print('\nKeyboardInterrupt received. Cleaning up...\n')
+        cleanup()
+
+    output_fp.close()
+    logger.info('\nEvaluation finished.\n')

evaluation/regression/.gitignore

@@ -1,2 +0,0 @@
-node_modules
-outputs

evaluation/regression/README.md

@@ -1,70 +0,0 @@
-# OpenHands - Regression Test Framework
-
-OpenHands project is an open-source software engineering AI that can solve various software engineering tasks. This repository contains the regression test framework for OpenHands project.
-
-## Running the Tests
-
-To run the tests for OpenHands project, you can use the provided test runner script. Follow these steps:
-
-1. Ensure you have Python 3.6 or higher installed on your system.
-2. Install the required dependencies by running the following command in your terminal:
-   ```
-   pip install -r requirements.txt
-   ```
-3. Navigate to the root directory of the project.
-4. Run the test suite using the test runner script with the required arguments:
-   ```
-   python evaluation/regression/run_tests.py --OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxx --model=gpt-4o
-   ```
-   Replace `sk-xxxxxxxxxxxxxxxxxxxxxx` with your actual OpenAI API key. The default model is `gpt-4o`, but you can specify a different model if needed.
-
-The test runner will discover and execute all the test cases in the `cases/` directory, and display the results of the test suite, including the status of each individual test case and the overall summary.
-
-## Test Case Structure
-
-The test cases for OpenHands project are organized in the `cases/` directory. Each test case has the following structure:
-
-```
-cases/
-├── hello-world/
-│   ├── task.txt
-│   ├── outputs/
-│   │   └── codeact_agent/
-│   │       └── workspace/
-│   │           ├── hello_world.sh
-│   └── test_hello_world.py
-├── create_web_app/
-│   ├── task.txt
-│   ├── outputs/
-│   │   └── codeact_agent/
-│   │       └── workspace/
-│   │           ├── app.py
-│   │           ├── requirements.txt
-│   │           ├── static/
-│   │           └── templates/
-│   └── test_create_web_app.py
-└── ...
-```
-
-- `task.txt`: This file contains the task description provided by the user.
-- `outputs/`: This directory contains the output generated by OpenHands for each agent.
-- `outputs/*/workspace/`: This directory contains the actual output files generated by OpenHands.
-- `test_*.py`: These are the test scripts that validate the output of OpenHands.
-
-## Adding New Test Cases
-
-To add a new test case to the regression test framework, follow the same steps as described in the previous sections.
-
-## Customizing the Test Cases
-
-The test cases can be customized by modifying the fixtures defined in the `conftest.py` file. The available fixtures are:
-
-- `test_cases_dir`: The directory containing the test cases.
-- `task_file`: The path to the `task.txt` file for the current test case.
-- `workspace_dir`: The path to the `workspace/` directory for the current test case.
-- `model`: The model selected start the generation.
-- `run_test_case`: A fixture that runs OpenHands and generates the workspace for the current test case.
-
-You can modify these fixtures to change the behavior of the test cases or add new ones as needed.
-
-If you have any questions or need further assistance, feel free to reach out to the project maintainers.

evaluation/regression/cases/client-server/task.txt

@@ -1 +0,0 @@
-Write an API server in node express which responds with a random number, and a frontend in React that displays the next number from the API

evaluation/regression/cases/express/task.txt

@@ -1 +0,0 @@
-Write a simple hello world server in node Express

evaluation/regression/cases/hello-name/start/hello_world.sh

@@ -1,2 +0,0 @@
-#!/usr/bin/env bash
-echo "hello world"

evaluation/regression/cases/hello-name/task.txt

@@ -1 +0,0 @@
-Rewrite the script so that it prints the user's name, using the first argument. If there's no name, default to "world"

evaluation/regression/cases/hello-world/task.txt

@@ -1 +0,0 @@
-Write a bash script named "hello_world.sh" that prints "Hello, World!"

evaluation/regression/cases/hello-world/test_hello_world.py

@@ -1,20 +0,0 @@
-import os
-
-import pytest
-from conftest import agents
-
-
-@pytest.mark.parametrize('agent', agents())
-def test_hello_world(task_file, run_test_case, agent):
-    """Test case for the "Hello, World!" Bash script using different agents."""
-    # Run the test case for the specified agent
-    workspace_dir = run_test_case(agent, 'hello-world')
-
-    # Validate the generated workspace
-    assert os.path.exists(workspace_dir)
-    assert os.path.isfile(os.path.join(workspace_dir, 'hello_world.sh'))
-
-    # Execute the hello_world.sh script
-    os.chdir(workspace_dir)
-    output = os.popen('bash hello_world.sh').read()
-    assert output == 'Hello, World!\n'

evaluation/regression/cases/node-cli-rewrite/start/commands/length.py

@@ -1,2 +0,0 @@
-def string_length(s):
-    return len(s)

evaluation/regression/cases/node-cli-rewrite/start/commands/lowercase.py

@@ -1,2 +0,0 @@
-def to_lowercase(s):
-    return s.lower()

evaluation/regression/cases/node-cli-rewrite/start/commands/reverse.py

@@ -1,2 +0,0 @@
-def reverse_string(s):
-    return s[::-1]

evaluation/regression/cases/node-cli-rewrite/start/commands/scramble.py

@@ -1,7 +0,0 @@
-import random
-
-
-def scramble_string(s):
-    s_list = list(s)
-    random.shuffle(s_list)
-    return ''.join(s_list)

evaluation/regression/cases/node-cli-rewrite/start/commands/spongebob.py

@@ -1,8 +0,0 @@
-def spongebob_case(s):
-    result = ''
-    for i, char in enumerate(s):
-        if i % 2 == 0:
-            result += char.lower()
-        else:
-            result += char.upper()
-    return result

evaluation/regression/cases/node-cli-rewrite/start/commands/uppercase.py

@@ -1,2 +0,0 @@
-def to_uppercase(s):
-    return s.upper()

evaluation/regression/cases/node-cli-rewrite/start/string_cli.py

@@ -1,55 +0,0 @@
-import sys
-
-
-def print_help():
-    help_text = """
-Usage: python string_cli.py <command> <string>
-
-Commands:
-    reverse - Reverses the input string.
-    uppercase - Converts the input string to uppercase.
-    lowercase - Converts the input string to lowercase.
-    spongebob - Converts the input string to spongebob case.
-    length - Returns the length of the input string.
-    scramble - Randomly scrambles the characters in the input string.
-"""
-    print(help_text)
-
-
-if __name__ == '__main__':
-    if len(sys.argv) == 2 and sys.argv[1] == '--help':
-        print_help()
-        sys.exit(0)
-    elif len(sys.argv) < 3:
-        print('Usage: python string_cli.py <command> <string>')
-        sys.exit(1)
-
-    command = sys.argv[1]
-    input_string = sys.argv[2]
-
-    if command == 'reverse':
-        from commands.reverse import reverse_string
-
-        print(reverse_string(input_string))
-    elif command == 'uppercase':
-        from commands.uppercase import to_uppercase
-
-        print(to_uppercase(input_string))
-    elif command == 'lowercase':
-        from commands.lowercase import to_lowercase
-
-        print(to_lowercase(input_string))
-    elif command == 'spongebob':
-        from commands.spongebob import spongebob_case
-
-        print(spongebob_case(input_string))
-    elif command == 'length':
-        from commands.length import string_length
-
-        print(string_length(input_string))
-    elif command == 'scramble':
-        from commands.scramble import scramble_string
-
-        print(scramble_string(input_string))
-    else:
-        print('Invalid command!')

evaluation/regression/cases/node-cli-rewrite/task.txt

@@ -1 +0,0 @@
-Please rewrite the entire CLI in node.js

evaluation/regression/cases/python-cli-help/start/commands/length.py

@@ -1,2 +0,0 @@
-def string_length(s):
-    return len(s)

evaluation/regression/cases/python-cli-help/start/commands/lowercase.py

@@ -1,2 +0,0 @@
-def to_lowercase(s):
-    return s.lower()

evaluation/regression/cases/python-cli-help/start/commands/reverse.py

@@ -1,2 +0,0 @@
-def reverse_string(s):
-    return s[::-1]

evaluation/regression/cases/python-cli-help/start/commands/scramble.py

@@ -1,7 +0,0 @@
-import random
-
-
-def scramble_string(s):
-    s_list = list(s)
-    random.shuffle(s_list)
-    return ''.join(s_list)

evaluation/regression/cases/python-cli-help/start/commands/spongebob.py

@@ -1,8 +0,0 @@
-def spongebob_case(s):
-    result = ''
-    for i, char in enumerate(s):
-        if i % 2 == 0:
-            result += char.lower()
-        else:
-            result += char.upper()
-    return result

evaluation/regression/cases/python-cli-help/start/commands/uppercase.py

@@ -1,2 +0,0 @@
-def to_uppercase(s):
-    return s.upper()

evaluation/regression/cases/python-cli-help/start/string_cli.py

@@ -1,36 +0,0 @@
-import sys
-
-if __name__ == '__main__':
-    if len(sys.argv) < 3:
-        print('Usage: python string_cli.py <command> <string>')
-        sys.exit(1)
-
-    command = sys.argv[1]
-    input_string = sys.argv[2]
-
-    if command == 'reverse':
-        from commands.reverse import reverse_string
-
-        print(reverse_string(input_string))
-    elif command == 'uppercase':
-        from commands.uppercase import to_uppercase
-
-        print(to_uppercase(input_string))
-    elif command == 'lowercase':
-        from commands.lowercase import to_lowercase
-
-        print(to_lowercase(input_string))
-    elif command == 'spongebob':
-        from commands.spongebob import spongebob_case
-
-        print(spongebob_case(input_string))
-    elif command == 'length':
-        from commands.length import string_length
-
-        print(string_length(input_string))
-    elif command == 'scramble':
-        from commands.scramble import scramble_string
-
-        print(scramble_string(input_string))
-    else:
-        print('Invalid command!')

evaluation/regression/cases/python-cli-help/task.txt

@@ -1 +0,0 @@
-Please add a --help option to the CLI, with a detailed description of each command

evaluation/regression/cases/python-cli/task.txt

@@ -1 +0,0 @@
-Write a python CLI for string manipulation. The CLI should accept a command, and a string. The commands should include `reverse`, `uppercase`, `lowercase`, `spongebob`, `length`, and `scramble`. The logic for each command should live in its own file.

evaluation/regression/cases/react-todo/task.txt

@@ -1 +0,0 @@
-Write a simple TODO list application in React

evaluation/regression/cases/server-test/start/server.py

@@ -1,21 +0,0 @@
-from http.server import BaseHTTPRequestHandler, HTTPServer
-
-
-class HelloWorldHandler(BaseHTTPRequestHandler):
-    def do_GET(self):
-        self.send_response(200)
-        self.send_header('Content-type', 'text/plain')
-        self.end_headers()
-        self.wfile.write(b'Hello World\n')
-
-
-def run(server_class=HTTPServer, handler_class=HelloWorldHandler, port=8000):
-    server_address = ('', port)
-    httpd = server_class(server_address, handler_class)
-    print(f'Starting httpd on port {port}...')
-    httpd.serve_forever()
-
-
-if __name__ == '__main__':
-    print('starting server...')
-    run()

evaluation/regression/cases/server-test/task.txt

@@ -1 +0,0 @@
-Make sure the server works and responds appropriately

evaluation/regression/conftest.py

@@ -1,171 +0,0 @@
-import datetime
-import logging
-import os
-import shutil
-import subprocess
-
-import pytest
-
-SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
-CASES_DIR = os.path.join(SCRIPT_DIR, 'cases')
-AGENTHUB_DIR = os.path.join(SCRIPT_DIR, '../', 'agenthub')
-
-
-def agents():
-    """Retrieves a list of available agents.
-
-    Returns:
-        A list of agent names.
-    """
-    agents = []
-    for agent in os.listdir(AGENTHUB_DIR):
-        if os.path.isdir(os.path.join(AGENTHUB_DIR, agent)) and agent.endswith(
-            '_agent'
-        ):
-            agents.append(agent)
-    return agents
-
-
-@pytest.fixture(scope='session')
-def test_cases_dir():
-    """Fixture that provides the directory path for test cases.
-
-    Returns:
-        The directory path for test cases.
-    """
-    return CASES_DIR
-
-
-@pytest.fixture
-def task_file(test_cases_dir, request):
-    """Fixture that provides the path to the task file for a test case.
-
-    Args:
-        test_cases_dir: The directory path for test cases.
-        request: The pytest request object.
-
-    Returns:
-        The path to the task file for the test case.
-    """
-    test_case_dir = os.path.dirname(request.module.__file__)
-    task_file_path = os.path.join(test_case_dir, 'task.txt')
-    return task_file_path
-
-
-@pytest.fixture
-def workspace_dir(test_cases_dir, request):
-    """Fixture that provides the workspace directory for a test case.
-
-    Args:
-        test_cases_dir: The directory path for test cases.
-        request: The pytest request object.
-
-    Returns:
-        The workspace directory for the test case.
-    """
-    test_case_dir = os.path.dirname(request.module.__file__)
-    workspace_dir = os.path.join(test_case_dir, 'workspace')
-    return workspace_dir
-
-
-@pytest.fixture
-def model(request):
-    """Fixture that provides the model name.
-
-    Args:
-        request: The pytest request object.
-
-    Returns:
-        The model name, defaulting to "gpt-3.5-turbo".
-    """
-    return request.config.getoption('model', default='gpt-3.5-turbo')
-
-
-@pytest.fixture
-def run_test_case(test_cases_dir, workspace_dir, request):
-    """Fixture that provides a function to run a test case.
-
-    Args:
-        test_cases_dir: The directory path for test cases.
-        workspace_dir: The workspace directory for the test case.
-        request: The pytest request object.
-
-    Returns:
-        A function that runs a test case for a given agent and case.
-    """
-
-    def _run_test_case(agent, case):
-        """Runs a test case for a given agent.
-
-        Args:
-            agent: The name of the agent to run the test case for.
-            case: The name of the test case to run.
-
-        Returns:
-            The path to the workspace directory for the agent and test case.
-
-        Raises:
-            AssertionError: If the test case execution fails (non-zero return code).
-
-        Steps:
-        """
-        case_dir = os.path.join(test_cases_dir, case)
-        task = open(os.path.join(case_dir, 'task.txt'), 'r').read().strip()
-        outputs_dir = os.path.join(case_dir, 'outputs')
-        agent_dir = os.path.join(outputs_dir, agent)
-
-        if not os.path.exists(agent_dir):
-            os.makedirs(agent_dir)
-
-        shutil.rmtree(os.path.join(agent_dir, 'workspace'), ignore_errors=True)
-        if os.path.isdir(os.path.join(case_dir, 'start')):
-            os.copytree(
-                os.path.join(case_dir, 'start'), os.path.join(agent_dir, 'workspace')
-            )
-        else:
-            os.makedirs(os.path.join(agent_dir, 'workspace'))
-        agents_ref = {
-            'codeact_agent': 'CodeActAgent',
-        }
-        process = subprocess.Popen(
-            [
-                'python3',
-                f'{SCRIPT_DIR}/../../openhands/main.py',
-                '-d',
-                f'{os.path.join(agent_dir, "workspace")}',
-                '-c',
-                f'{agents_ref[agent]}',
-                '-t',
-                f'{task}',
-                '-m',
-                'gpt-3.5-turbo',
-            ],
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE,
-            universal_newlines=True,
-        )
-        stdout, stderr = process.communicate()
-        logging.info(f'Stdout: {stdout}')
-        logging.error(f'Stderr: {stderr}')
-
-        assert process.returncode == 0
-        return os.path.join(agent_dir, 'workspace')
-
-    return _run_test_case
-
-
-def pytest_configure(config):
-    """Configuration hook for pytest.
-
-    Args:
-        config: The pytest configuration object.
-    """
-    now = datetime.datetime.now()
-    logging.basicConfig(
-        level=logging.INFO,
-        format='%(asctime)s [%(levelname)s] %(message)s',
-        handlers=[
-            logging.FileHandler(f'test_results_{now.strftime("%Y%m%d_%H%M%S")}.log'),
-            logging.StreamHandler(),
-        ],
-    )

evaluation/regression/run_tests.py

@@ -1,32 +0,0 @@
-import argparse
-
-import pytest
-
-from openhands.config import load_openhands_config
-
-config = load_openhands_config()
-
-if __name__ == '__main__':
-    """Main entry point of the script.
-
-    This script runs pytest with specific arguments and configuration.
-
-    Usage:
-        python script_name.py [--OPENAI_API_KEY=<api_key>] [--model=<model_name>]
-
-    """
-    parser = argparse.ArgumentParser(
-        description='This script runs pytest with specific arguments and configuration.'
-    )
-    parser.add_argument(
-        '--OPENAI_API_KEY', type=str, required=True, help='Your OpenAI API key'
-    )
-    parser.add_argument(
-        '--model', type=str, required=True, help='The model name to use'
-    )
-
-    parser_args = parser.parse_args()
-    config.config['OPENAI_API_KEY'] = parser_args.OPENAI_API_KEY
-    args = ['-v', 'evaluation/regression/cases', f'-o model={parser_args.model}']
-
-    pytest.main(args)

frontend/__tests__/components/features/chat/task-tracking-observation-content.test.tsx

@@ -0,0 +1,135 @@
+import { render, screen } from "@testing-library/react";
+import { describe, it, expect, vi } from "vitest";
+import { TaskTrackingObservationContent } from "#/components/features/chat/task-tracking-observation-content";
+import { TaskTrackingObservation } from "#/types/core/observations";
+
+// Mock the translation hook
+vi.mock("react-i18next", () => ({
+  useTranslation: () => ({
+    t: (key: string) => {
+      const translations: Record<string, string> = {
+        "TASK_TRACKING_OBSERVATION$TASK_LIST": "Task List",
+        "TASK_TRACKING_OBSERVATION$TASK_ID": "ID",
+        "TASK_TRACKING_OBSERVATION$TASK_NOTES": "Notes",
+        "TASK_TRACKING_OBSERVATION$RESULT": "Result",
+      };
+      return translations[key] || key;
+    },
+  }),
+}));
+
+describe("TaskTrackingObservationContent", () => {
+  const mockEvent: TaskTrackingObservation = {
+    id: 123,
+    timestamp: "2024-01-01T00:00:00Z",
+    source: "agent",
+    observation: "task_tracking",
+    content: "Task tracking operation completed successfully",
+    cause: 122,
+    message: "Task tracking operation completed successfully",
+    extras: {
+      command: "plan",
+      task_list: [
+        {
+          id: "task-1",
+          title: "Implement feature A",
+          status: "todo",
+          notes: "This is a test task",
+        },
+        {
+          id: "task-2",
+          title: "Fix bug B",
+          status: "in_progress",
+        },
+        {
+          id: "task-3",
+          title: "Deploy to production",
+          status: "done",
+          notes: "Completed successfully",
+        },
+      ],
+    },
+  };
+
+  it("does not render command section", () => {
+    render(<TaskTrackingObservationContent event={mockEvent} />);
+
+    expect(screen.queryByText("Command")).not.toBeInTheDocument();
+    expect(screen.queryByText("plan")).not.toBeInTheDocument();
+  });
+
+  it("renders task list when command is 'plan' and tasks exist", () => {
+    render(<TaskTrackingObservationContent event={mockEvent} />);
+
+    expect(screen.getByText("Task List (3 items)")).toBeInTheDocument();
+    expect(screen.getByText("Implement feature A")).toBeInTheDocument();
+    expect(screen.getByText("Fix bug B")).toBeInTheDocument();
+    expect(screen.getByText("Deploy to production")).toBeInTheDocument();
+  });
+
+  it("displays correct status icons and badges", () => {
+    render(<TaskTrackingObservationContent event={mockEvent} />);
+
+    // Check for status text (the icons are emojis)
+    expect(screen.getByText("todo")).toBeInTheDocument();
+    expect(screen.getByText("in progress")).toBeInTheDocument();
+    expect(screen.getByText("done")).toBeInTheDocument();
+  });
+
+  it("displays task IDs and notes", () => {
+    render(<TaskTrackingObservationContent event={mockEvent} />);
+
+    expect(screen.getByText("ID: task-1")).toBeInTheDocument();
+    expect(screen.getByText("ID: task-2")).toBeInTheDocument();
+    expect(screen.getByText("ID: task-3")).toBeInTheDocument();
+
+    expect(screen.getByText("Notes: This is a test task")).toBeInTheDocument();
+    expect(screen.getByText("Notes: Completed successfully")).toBeInTheDocument();
+  });
+
+  it("renders result section when content exists", () => {
+    render(<TaskTrackingObservationContent event={mockEvent} />);
+
+    expect(screen.getByText("Result")).toBeInTheDocument();
+    expect(screen.getByText("Task tracking operation completed successfully")).toBeInTheDocument();
+  });
+
+  it("does not render task list when command is not 'plan'", () => {
+    const eventWithoutPlan = {
+      ...mockEvent,
+      extras: {
+        ...mockEvent.extras,
+        command: "view",
+      },
+    };
+
+    render(<TaskTrackingObservationContent event={eventWithoutPlan} />);
+
+    expect(screen.queryByText("Task List")).not.toBeInTheDocument();
+  });
+
+  it("does not render task list when task list is empty", () => {
+    const eventWithEmptyTasks = {
+      ...mockEvent,
+      extras: {
+        ...mockEvent.extras,
+        task_list: [],
+      },
+    };
+
+    render(<TaskTrackingObservationContent event={eventWithEmptyTasks} />);
+
+    expect(screen.queryByText("Task List")).not.toBeInTheDocument();
+  });
+
+  it("does not render result section when content is empty", () => {
+    const eventWithoutContent = {
+      ...mockEvent,
+      content: "",
+    };
+
+    render(<TaskTrackingObservationContent event={eventWithoutContent} />);
+
+    expect(screen.queryByText("Result")).not.toBeInTheDocument();
+  });
+});

frontend/__tests__/components/likert-scale.test.tsx

@@ -42,6 +42,8 @@ describe("LikertScale", () => {
     expect(screen.getByText(I18nKey.FEEDBACK$REASON_MISUNDERSTOOD_INSTRUCTION)).toBeInTheDocument();
     expect(screen.getByText(I18nKey.FEEDBACK$REASON_FORGOT_CONTEXT)).toBeInTheDocument();
     expect(screen.getByText(I18nKey.FEEDBACK$REASON_UNNECESSARY_CHANGES)).toBeInTheDocument();
+    expect(screen.getByText(I18nKey.FEEDBACK$REASON_SHOULD_ASK_FIRST)).toBeInTheDocument();
+    expect(screen.getByText(I18nKey.FEEDBACK$REASON_DIDNT_FINISH_JOB)).toBeInTheDocument();
     expect(screen.getByText(I18nKey.FEEDBACK$REASON_OTHER)).toBeInTheDocument();
   });
 

frontend/__tests__/utils/browser-tab.test.ts

@@ -0,0 +1,51 @@
+import { describe, it, expect, beforeEach, afterEach, vi } from "vitest";
+
+import { browserTab } from "#/utils/browser-tab";
+
+// These tests exercise the browser-tab notification flasher behavior.
+// Specifically we verify that when the document title changes externally
+// while a notification is active, the flasher updates its internal
+// baseline so it restores/toggles to the new title instead of an old one.
+
+describe("browserTab notifications", () => {
+  const MESSAGE = "Agent ready";
+  const INITIAL = "Conversation 123 | OpenHands";
+  const RENAMED = "My renamed title | OpenHands";
+
+  beforeEach(() => {
+    vi.useFakeTimers();
+    // reset title for each test
+    document.title = INITIAL;
+  });
+
+  afterEach(() => {
+    browserTab.stopNotification();
+    vi.runOnlyPendingTimers();
+    vi.useRealTimers();
+  });
+
+  it("updates baseline when title changes during an active notification and restores to the new title", () => {
+    // Start flashing
+    browserTab.startNotification(MESSAGE);
+
+    // Tick once: should switch to the message
+    vi.advanceTimersByTime(1000);
+    expect(document.title).toBe(MESSAGE);
+
+    // Simulate an external rename while flashing (e.g., user edits title)
+    document.title = RENAMED;
+
+    // Next tick: flasher observes the external change and updates baseline
+    vi.advanceTimersByTime(1000);
+    // On this tick, we toggle back to the message
+    expect(document.title).toBe(MESSAGE);
+
+    // Next tick should toggle to the updated baseline (renamed title)
+    vi.advanceTimersByTime(1000);
+    expect(document.title).toBe(RENAMED);
+
+    // Stop flashing: title should remain the updated baseline
+    browserTab.stopNotification();
+    expect(document.title).toBe(RENAMED);
+  });
+});

frontend/src/components/features/chat/event-content-helpers/get-action-content.ts

@@ -9,6 +9,7 @@ import {
   ThinkAction,
   OpenHandsAction,
   FinishAction,
+  TaskTrackingAction,
 } from "#/types/core/actions";
 import { getDefaultEventContent, MAX_CONTENT_LENGTH } from "./shared";
 import i18n from "#/i18n";
@@ -79,6 +80,38 @@ const getThinkActionContent = (event: ThinkAction): string =>
 
 const getFinishActionContent = (event: FinishAction): string =>
   event.args.final_thought.trim();
+
+const getTaskTrackingActionContent = (event: TaskTrackingAction): string => {
+  let content = `**Command:** \`${event.args.command}\``;
+
+  if (
+    event.args.command === "plan" &&
+    event.args.task_list &&
+    event.args.task_list.length > 0
+  ) {
+    content += `\n\n**Task List (${event.args.task_list.length} ${event.args.task_list.length === 1 ? "item" : "items"}):**\n`;
+
+    event.args.task_list.forEach((task, index) => {
+      const statusIcon =
+        {
+          todo: "⏳",
+          in_progress: "🔄",
+          done: "✅",
+        }[task.status] || "❓";
+
+      content += `\n${index + 1}. ${statusIcon} **[${task.status.toUpperCase().replace("_", " ")}]** ${task.title}`;
+      content += `\n   *ID: ${task.id}*`;
+      if (task.notes) {
+        content += `\n   *Notes: ${task.notes}*`;
+      }
+    });
+  } else if (event.args.command === "plan") {
+    content += "\n\n**Task List:** Empty";
+  }
+
+  return content;
+};
+
 const getNoContentActionContent = (): string => "";
 
 export const getActionContent = (event: OpenHandsAction): string => {
@@ -102,6 +135,8 @@ export const getActionContent = (event: OpenHandsAction): string => {
       return getThinkActionContent(event);
     case "finish":
       return getFinishActionContent(event);
+    case "task_tracking":
+      return getTaskTrackingActionContent(event);
     default:
       return getDefaultEventContent(event);
   }

frontend/src/components/features/chat/event-content-helpers/get-observation-content.ts

@@ -6,6 +6,7 @@ import {
   BrowseObservation,
   OpenHandsObservation,
   RecallObservation,
+  TaskTrackingObservation,
 } from "#/types/core/observations";
 import { getObservationResult } from "./get-observation-result";
 import { getDefaultEventContent, MAX_CONTENT_LENGTH } from "./shared";
@@ -102,6 +103,40 @@ const getRecallObservationContent = (event: RecallObservation): string => {
   return content;
 };
 
+const getTaskTrackingObservationContent = (
+  event: TaskTrackingObservation,
+): string => {
+  const { command, task_list: taskList } = event.extras;
+  let content = `**Command:** \`${command}\``;
+
+  if (command === "plan" && taskList.length > 0) {
+    content += `\n\n**Task List (${taskList.length} ${taskList.length === 1 ? "item" : "items"}):**\n`;
+
+    taskList.forEach((task, index) => {
+      const statusIcon =
+        {
+          todo: "⏳",
+          in_progress: "🔄",
+          done: "✅",
+        }[task.status] || "❓";
+
+      content += `\n${index + 1}. ${statusIcon} **[${task.status.toUpperCase().replace("_", " ")}]** ${task.title}`;
+      content += `\n   *ID: ${task.id}*`;
+      if (task.notes) {
+        content += `\n   *Notes: ${task.notes}*`;
+      }
+    });
+  } else if (command === "plan") {
+    content += "\n\n**Task List:** Empty";
+  }
+
+  if (event.content && event.content.trim()) {
+    content += `\n\n**Result:** ${event.content.trim()}`;
+  }
+
+  return content;
+};
+
 export const getObservationContent = (event: OpenHandsObservation): string => {
   switch (event.observation) {
     case "read":
@@ -118,6 +153,8 @@ export const getObservationContent = (event: OpenHandsObservation): string => {
       return getBrowseObservationContent(event);
     case "recall":
       return getRecallObservationContent(event);
+    case "task_tracking":
+      return getTaskTrackingObservationContent(event);
     default:
       return getDefaultEventContent(event);
   }

frontend/src/components/features/chat/event-content-helpers/should-render-event.ts

@@ -16,6 +16,8 @@ const COMMON_NO_RENDER_LIST: OpenHandsEventType[] = [
 
 const ACTION_NO_RENDER_LIST: OpenHandsEventType[] = ["recall"];
 
+const OBSERVATION_NO_RENDER_LIST: OpenHandsEventType[] = ["think"];
+
 export const shouldRenderEvent = (
   event: OpenHandsAction | OpenHandsObservation,
 ) => {
@@ -35,7 +37,10 @@ export const shouldRenderEvent = (
       return false;
     }
 
-    return !COMMON_NO_RENDER_LIST.includes(event.observation);
+    const noRenderList = COMMON_NO_RENDER_LIST.concat(
+      OBSERVATION_NO_RENDER_LIST,
+    );
+    return !noRenderList.includes(event.observation);
   }
 
   return true;

frontend/src/components/features/chat/event-message.tsx

@@ -1,4 +1,5 @@
 import React from "react";
+import { useTranslation } from "react-i18next";
 import { ConfirmationButtons } from "#/components/shared/buttons/confirmation-buttons";
 import { OpenHandsAction } from "#/types/core/actions";
 import {
@@ -10,12 +11,14 @@ import {
   isFinishAction,
   isRejectObservation,
   isMcpObservation,
+  isTaskTrackingObservation,
 } from "#/types/core/guards";
 import { OpenHandsObservation } from "#/types/core/observations";
 import { ImageCarousel } from "../images/image-carousel";
 import { ChatMessage } from "./chat-message";
 import { ErrorMessage } from "./error-message";
 import { MCPObservationContent } from "./mcp-observation-content";
+import { TaskTrackingObservationContent } from "./task-tracking-observation-content";
 import { getObservationResult } from "./event-content-helpers/get-observation-result";
 import { getEventContent } from "./event-content-helpers/get-event-content";
 import { GenericEventMessage } from "./generic-event-message";
@@ -58,6 +61,7 @@ export function EventMessage({
   actions,
   isInLast10Actions,
 }: EventMessageProps) {
+  const { t } = useTranslation();
   const shouldShowConfirmationButtons =
     isLastMessage && event.source === "agent" && isAwaitingUserConfirmation;
 
@@ -113,7 +117,7 @@ export function EventMessage({
   }
 
   if (hasObservationPair && isOpenHandsAction(event)) {
-    if (hasThoughtProperty(event.args)) {
+    if (hasThoughtProperty(event.args) && event.action !== "think") {
       return (
         <div>
           <ChatMessage
@@ -209,11 +213,41 @@ export function EventMessage({
     );
   }
 
+  if (isTaskTrackingObservation(event)) {
+    const { command } = event.extras;
+    let title: React.ReactNode;
+    let initiallyExpanded = false;
+
+    // Determine title and expansion state based on command
+    if (command === "plan") {
+      title = t("OBSERVATION_MESSAGE$TASK_TRACKING_PLAN");
+      initiallyExpanded = true;
+    } else {
+      // command === "view"
+      title = t("OBSERVATION_MESSAGE$TASK_TRACKING_VIEW");
+      initiallyExpanded = false;
+    }
+
+    return (
+      <div>
+        <GenericEventMessage
+          title={title}
+          details={<TaskTrackingObservationContent event={event} />}
+          success={getObservationResult(event)}
+          initiallyExpanded={initiallyExpanded}
+        />
+        {shouldShowConfirmationButtons && <ConfirmationButtons />}
+      </div>
+    );
+  }
+
   return (
     <div>
-      {isOpenHandsAction(event) && hasThoughtProperty(event.args) && (
-        <ChatMessage type="agent" message={event.args.thought} />
-      )}
+      {isOpenHandsAction(event) &&
+        hasThoughtProperty(event.args) &&
+        event.action !== "think" && (
+          <ChatMessage type="agent" message={event.args.thought} />
+        )}
 
       <GenericEventMessage
         title={getEventContent(event).title}

frontend/src/components/features/chat/generic-event-message.tsx

@@ -13,14 +13,16 @@ interface GenericEventMessageProps {
   title: React.ReactNode;
   details: string | React.ReactNode;
   success?: ObservationResultStatus;
+  initiallyExpanded?: boolean;
 }
 
 export function GenericEventMessage({
   title,
   details,
   success,
+  initiallyExpanded = false,
 }: GenericEventMessageProps) {
-  const [showDetails, setShowDetails] = React.useState(false);
+  const [showDetails, setShowDetails] = React.useState(initiallyExpanded);
 
   return (
     <div className="flex flex-col gap-2 border-l-2 pl-2 my-2 py-2 border-neutral-300 text-sm w-full">

frontend/src/components/features/chat/task-tracking-observation-content.tsx

@@ -0,0 +1,110 @@
+import React from "react";
+import { useTranslation } from "react-i18next";
+import { TaskTrackingObservation } from "#/types/core/observations";
+
+interface TaskTrackingObservationContentProps {
+  event: TaskTrackingObservation;
+}
+
+export function TaskTrackingObservationContent({
+  event,
+}: TaskTrackingObservationContentProps) {
+  const { t } = useTranslation();
+
+  const { command, task_list: taskList } = event.extras;
+  const shouldShowTaskList = command === "plan" && taskList.length > 0;
+
+  const getStatusIcon = (status: string) => {
+    switch (status) {
+      case "todo":
+        return "⏳";
+      case "in_progress":
+        return "🔄";
+      case "done":
+        return "✅";
+      default:
+        return "❓";
+    }
+  };
+
+  const getStatusClassName = (status: string) => {
+    if (status === "done") {
+      return "bg-green-800 text-green-200";
+    }
+    if (status === "in_progress") {
+      return "bg-yellow-800 text-yellow-200";
+    }
+    return "bg-gray-700 text-gray-300";
+  };
+
+  return (
+    <div className="flex flex-col gap-4">
+      {/* Task List section - only show for 'plan' command */}
+      {shouldShowTaskList && (
+        <div className="flex flex-col gap-2">
+          <div className="flex items-center justify-between">
+            <h3 className="text-sm font-semibold text-gray-300">
+              {t("TASK_TRACKING_OBSERVATION$TASK_LIST")} ({taskList.length}{" "}
+              {taskList.length === 1 ? "item" : "items"})
+            </h3>
+          </div>
+          <div className="p-3 bg-gray-900 rounded-md overflow-auto text-gray-300 max-h-[400px] shadow-inner">
+            <div className="space-y-3">
+              {taskList.map((task, index) => (
+                <div key={task.id} className="border-l-2 border-gray-600 pl-3">
+                  <div className="flex items-start gap-2">
+                    <span className="text-lg">
+                      {getStatusIcon(task.status)}
+                    </span>
+                    <div className="flex-1">
+                      <div className="flex items-center gap-2 mb-1">
+                        <span className="text-sm text-gray-400">
+                          {index + 1}.
+                        </span>
+                        <span
+                          className={`text-xs px-2 py-1 rounded uppercase font-semibold ${getStatusClassName(
+                            task.status,
+                          )}`}
+                        >
+                          {task.status.replace("_", " ")}
+                        </span>
+                      </div>
+                      <h4 className="font-medium text-white mb-1">
+                        {task.title}
+                      </h4>
+                      <p className="text-xs text-gray-400 mb-1">
+                        {t("TASK_TRACKING_OBSERVATION$TASK_ID")}: {task.id}
+                      </p>
+                      {task.notes && (
+                        <p className="text-sm text-gray-300 italic">
+                          {t("TASK_TRACKING_OBSERVATION$TASK_NOTES")}:{" "}
+                          {task.notes}
+                        </p>
+                      )}
+                    </div>
+                  </div>
+                </div>
+              ))}
+            </div>
+          </div>
+        </div>
+      )}
+
+      {/* Result message - only show if there's meaningful content */}
+      {event.content && event.content.trim() && (
+        <div className="flex flex-col gap-2">
+          <div className="flex items-center justify-between">
+            <h3 className="text-sm font-semibold text-gray-300">
+              {t("TASK_TRACKING_OBSERVATION$RESULT")}
+            </h3>
+          </div>
+          <div className="p-3 bg-gray-900 rounded-md overflow-auto text-gray-300 shadow-inner">
+            <pre className="whitespace-pre-wrap text-sm">
+              {event.content.trim()}
+            </pre>
+          </div>
+        </div>
+      )}
+    </div>
+  );
+}

frontend/src/components/features/feedback/likert-scale.tsx

@@ -46,6 +46,7 @@ export function LikertScale({
     t(I18nKey.FEEDBACK$REASON_FORGOT_CONTEXT),
     t(I18nKey.FEEDBACK$REASON_UNNECESSARY_CHANGES),
     t(I18nKey.FEEDBACK$REASON_SHOULD_ASK_FIRST),
+    t(I18nKey.FEEDBACK$REASON_DIDNT_FINISH_JOB),
     t(I18nKey.FEEDBACK$REASON_OTHER),
   ];
 

frontend/src/i18n/declaration.ts

@@ -37,8 +37,14 @@ export enum I18nKey {
   EVENT$UNKNOWN_EVENT = "EVENT$UNKNOWN_EVENT",
   OBSERVATION$COMMAND_NO_OUTPUT = "OBSERVATION$COMMAND_NO_OUTPUT",
   OBSERVATION$MCP_NO_OUTPUT = "OBSERVATION$MCP_NO_OUTPUT",
+  OBSERVATION$TASK_TRACKING_NO_OUTPUT = "OBSERVATION$TASK_TRACKING_NO_OUTPUT",
   MCP_OBSERVATION$ARGUMENTS = "MCP_OBSERVATION$ARGUMENTS",
   MCP_OBSERVATION$OUTPUT = "MCP_OBSERVATION$OUTPUT",
+  TASK_TRACKING_OBSERVATION$TASK_LIST = "TASK_TRACKING_OBSERVATION$TASK_LIST",
+  TASK_TRACKING_OBSERVATION$OUTPUT = "TASK_TRACKING_OBSERVATION$OUTPUT",
+  TASK_TRACKING_OBSERVATION$TASK_ID = "TASK_TRACKING_OBSERVATION$TASK_ID",
+  TASK_TRACKING_OBSERVATION$TASK_NOTES = "TASK_TRACKING_OBSERVATION$TASK_NOTES",
+  TASK_TRACKING_OBSERVATION$RESULT = "TASK_TRACKING_OBSERVATION$RESULT",
   OBSERVATION$ERROR_PREFIX = "OBSERVATION$ERROR_PREFIX",
   TASK$ADDRESSING_TASK = "TASK$ADDRESSING_TASK",
   SECRETS$SECRET_VALUE_REQUIRED = "SECRETS$SECRET_VALUE_REQUIRED",
@@ -483,6 +489,7 @@ export enum I18nKey {
   ACTION_MESSAGE$THINK = "ACTION_MESSAGE$THINK",
   ACTION_MESSAGE$SYSTEM = "ACTION_MESSAGE$SYSTEM",
   ACTION_MESSAGE$CONDENSATION = "ACTION_MESSAGE$CONDENSATION",
+  ACTION_MESSAGE$TASK_TRACKING = "ACTION_MESSAGE$TASK_TRACKING",
   OBSERVATION_MESSAGE$RUN = "OBSERVATION_MESSAGE$RUN",
   OBSERVATION_MESSAGE$RUN_IPYTHON = "OBSERVATION_MESSAGE$RUN_IPYTHON",
   OBSERVATION_MESSAGE$READ = "OBSERVATION_MESSAGE$READ",
@@ -492,6 +499,8 @@ export enum I18nKey {
   OBSERVATION_MESSAGE$MCP = "OBSERVATION_MESSAGE$MCP",
   OBSERVATION_MESSAGE$RECALL = "OBSERVATION_MESSAGE$RECALL",
   OBSERVATION_MESSAGE$THINK = "OBSERVATION_MESSAGE$THINK",
+  OBSERVATION_MESSAGE$TASK_TRACKING_PLAN = "OBSERVATION_MESSAGE$TASK_TRACKING_PLAN",
+  OBSERVATION_MESSAGE$TASK_TRACKING_VIEW = "OBSERVATION_MESSAGE$TASK_TRACKING_VIEW",
   EXPANDABLE_MESSAGE$SHOW_DETAILS = "EXPANDABLE_MESSAGE$SHOW_DETAILS",
   EXPANDABLE_MESSAGE$HIDE_DETAILS = "EXPANDABLE_MESSAGE$HIDE_DETAILS",
   AI_SETTINGS$TITLE = "AI_SETTINGS$TITLE",
@@ -651,6 +660,7 @@ export enum I18nKey {
   FEEDBACK$REASON_FORGOT_CONTEXT = "FEEDBACK$REASON_FORGOT_CONTEXT",
   FEEDBACK$REASON_UNNECESSARY_CHANGES = "FEEDBACK$REASON_UNNECESSARY_CHANGES",
   FEEDBACK$REASON_SHOULD_ASK_FIRST = "FEEDBACK$REASON_SHOULD_ASK_FIRST",
+  FEEDBACK$REASON_DIDNT_FINISH_JOB = "FEEDBACK$REASON_DIDNT_FINISH_JOB",
   FEEDBACK$REASON_OTHER = "FEEDBACK$REASON_OTHER",
   FEEDBACK$THANK_YOU_FOR_FEEDBACK = "FEEDBACK$THANK_YOU_FOR_FEEDBACK",
   FEEDBACK$FAILED_TO_SUBMIT = "FEEDBACK$FAILED_TO_SUBMIT",

frontend/src/i18n/translation.json

@@ -591,6 +591,22 @@
         "de": "[MCP-Tool wurde ohne Ausgabe ausgeführt]",
         "uk": "[Інструмент MCP завершив виконання без виводу]"
     },
+    "OBSERVATION$TASK_TRACKING_NO_OUTPUT": {
+        "en": "[Task tracking completed with no output]",
+        "ja": "[タスクトラッキングは出力なしで完了しました]",
+        "zh-CN": "[任务跟踪完成，没有输出]",
+        "zh-TW": "[任務跟踪完成，沒有輸出]",
+        "ko-KR": "[작업 추적이 출력 없이 완료되었습니다]",
+        "no": "[Oppgavesporing fullført uten utdata]",
+        "it": "[Tracciamento attività completato senza output]",
+        "pt": "[Rastreamento de tarefas concluído sem saída]",
+        "es": "[Seguimiento de tareas completado sin salida]",
+        "ar": "[اكتمل تتبع المهام بدون مخرجات]",
+        "fr": "[Suivi des tâches terminé sans sortie]",
+        "tr": "[Görev takibi çıktı olmadan tamamlandı]",
+        "de": "[Aufgabenverfolgung ohne Ausgabe abgeschlossen]",
+        "uk": "[Відстеження завдань завершено без виводу]"
+    },
     "MCP_OBSERVATION$ARGUMENTS": {
         "en": "Arguments",
         "ja": "引数",
@@ -623,6 +639,86 @@
         "de": "Ausgabe",
         "uk": "Вивід"
     },
+    "TASK_TRACKING_OBSERVATION$TASK_LIST": {
+        "en": "Task List",
+        "ja": "タスクリスト",
+        "zh-CN": "任务列表",
+        "zh-TW": "任務列表",
+        "ko-KR": "작업 목록",
+        "no": "Oppgaveliste",
+        "it": "Elenco attività",
+        "pt": "Lista de tarefas",
+        "es": "Lista de tareas",
+        "ar": "قائمة المهام",
+        "fr": "Liste des tâches",
+        "tr": "Görev listesi",
+        "de": "Aufgabenliste",
+        "uk": "Список завдань"
+    },
+    "TASK_TRACKING_OBSERVATION$OUTPUT": {
+        "en": "Output",
+        "ja": "出力",
+        "zh-CN": "输出",
+        "zh-TW": "輸出",
+        "ko-KR": "출력",
+        "no": "Utdata",
+        "it": "Output",
+        "pt": "Saída",
+        "es": "Salida",
+        "ar": "المخرجات",
+        "fr": "Sortie",
+        "tr": "Çıktı",
+        "de": "Ausgabe",
+        "uk": "Вивід"
+    },
+    "TASK_TRACKING_OBSERVATION$TASK_ID": {
+        "en": "ID",
+        "ja": "ID",
+        "zh-CN": "ID",
+        "zh-TW": "ID",
+        "ko-KR": "ID",
+        "no": "ID",
+        "it": "ID",
+        "pt": "ID",
+        "es": "ID",
+        "ar": "المعرف",
+        "fr": "ID",
+        "tr": "ID",
+        "de": "ID",
+        "uk": "ID"
+    },
+    "TASK_TRACKING_OBSERVATION$TASK_NOTES": {
+        "en": "Notes",
+        "ja": "メモ",
+        "zh-CN": "备注",
+        "zh-TW": "備註",
+        "ko-KR": "메모",
+        "no": "Notater",
+        "it": "Note",
+        "pt": "Notas",
+        "es": "Notas",
+        "ar": "ملاحظات",
+        "fr": "Notes",
+        "tr": "Notlar",
+        "de": "Notizen",
+        "uk": "Примітки"
+    },
+    "TASK_TRACKING_OBSERVATION$RESULT": {
+        "en": "Result",
+        "ja": "結果",
+        "zh-CN": "结果",
+        "zh-TW": "結果",
+        "ko-KR": "결과",
+        "no": "Resultat",
+        "it": "Risultato",
+        "pt": "Resultado",
+        "es": "Resultado",
+        "ar": "النتيجة",
+        "fr": "Résultat",
+        "tr": "Sonuç",
+        "de": "Ergebnis",
+        "uk": "Результат"
+    },
     "OBSERVATION$ERROR_PREFIX": {
         "en": "error:",
         "ja": "エラー:",
@@ -7727,6 +7823,22 @@
         "tr": "Yoğunlaşma",
         "uk": "Конденсація"
     },
+    "ACTION_MESSAGE$TASK_TRACKING": {
+        "en": "Managing tasks",
+        "zh-CN": "管理任务",
+        "zh-TW": "管理任務",
+        "ko-KR": "작업 관리",
+        "ja": "タスク管理",
+        "no": "Administrerer oppgaver",
+        "ar": "إدارة المهام",
+        "de": "Aufgaben verwalten",
+        "fr": "Gestion des tâches",
+        "it": "Gestione delle attività",
+        "pt": "Gerenciando tarefas",
+        "es": "Gestionando tareas",
+        "tr": "Görevleri yönetiyor",
+        "uk": "Керування завданнями"
+    },
     "OBSERVATION_MESSAGE$RUN": {
         "en": "Ran <cmd>{{command}}</cmd>",
         "zh-CN": "运行 <cmd>{{command}}</cmd>",
@@ -7871,6 +7983,38 @@
         "de": "Gedanke",
         "uk": "Думка"
     },
+    "OBSERVATION_MESSAGE$TASK_TRACKING_PLAN": {
+        "en": "Agent updated the plan",
+        "zh-CN": "代理更新了计划",
+        "zh-TW": "代理更新了計劃",
+        "ko-KR": "에이전트가 계획을 업데이트했습니다",
+        "ja": "エージェントがプランを更新しました",
+        "no": "Agent oppdaterte planen",
+        "ar": "قام الوكيل بتحديث الخطة",
+        "de": "Agent hat den Plan aktualisiert",
+        "fr": "L'agent a mis à jour le plan",
+        "it": "L'agente ha aggiornato il piano",
+        "pt": "O agente atualizou o plano",
+        "es": "El agente actualizó el plan",
+        "tr": "Ajan planı güncelledi",
+        "uk": "Агент оновив план"
+    },
+    "OBSERVATION_MESSAGE$TASK_TRACKING_VIEW": {
+        "en": "Agent checked the current plan",
+        "zh-CN": "代理检查了当前计划",
+        "zh-TW": "代理檢查了當前計劃",
+        "ko-KR": "에이전트가 현재 계획을 확인했습니다",
+        "ja": "エージェントが現在のプランを確認しました",
+        "no": "Agent sjekket gjeldende plan",
+        "ar": "تحقق الوكيل من الخطة الحالية",
+        "de": "Agent hat den aktuellen Plan überprüft",
+        "fr": "L'agent a vérifié le plan actuel",
+        "it": "L'agente ha controllato il piano attuale",
+        "pt": "O agente verificou o plano atual",
+        "es": "El agente verificó el plan actual",
+        "tr": "Ajan mevcut planı kontrol etti",
+        "uk": "Агент перевірив поточний план"
+    },
     "EXPANDABLE_MESSAGE$SHOW_DETAILS": {
         "en": "Show details",
         "zh-CN": "显示详情",
@@ -10415,6 +10559,22 @@
         "de": "Der Agent hätte mich vorher fragen sollen!",
         "uk": "Агент повинен був спочатку запитати мене, перш ніж це робити!"
     },
+    "FEEDBACK$REASON_DIDNT_FINISH_JOB": {
+        "en": "The agent didn't finish the job",
+        "ja": "エージェントは作業を完了しませんでした",
+        "zh-CN": "代理没有完成工作",
+        "zh-TW": "代理沒有完成工作",
+        "ko-KR": "에이전트가 작업을 완료하지 않았습니다",
+        "no": "Agenten fullførte ikke jobben",
+        "it": "L'agente non ha completato il lavoro",
+        "pt": "O agente não terminou o trabalho",
+        "es": "El agente no terminó el trabajo",
+        "ar": "لم يكمل الوكيل المهمة",
+        "fr": "L'agent n'a pas terminé le travail",
+        "tr": "Ajan işi bitirmedi",
+        "de": "Der Agent hat die Aufgabe nicht beendet",
+        "uk": "Агент не завершив роботу"
+    },
     "FEEDBACK$REASON_OTHER": {
         "en": "Other",
         "ja": "その他",

frontend/src/services/observations.ts

@@ -52,6 +52,7 @@ export function handleObservationMessage(message: ObservationMessage) {
     case ObservationType.RECALL:
     case ObservationType.ERROR:
     case ObservationType.MCP:
+    case ObservationType.TASK_TRACKING:
       break; // We don't display the default message for these observations
     default:
       break;

frontend/src/types/action-type.tsx

@@ -44,6 +44,9 @@ enum ActionType {
 
   // Interact with the MCP server.
   MCP = "call_tool_mcp",
+
+  // Views or updates the task list for task management.
+  TASK_TRACKING = "task_tracking",
 }
 
 export default ActionType;

frontend/src/types/core/actions.ts

@@ -162,6 +162,21 @@ export interface MCPAction extends OpenHandsActionEvent<"call_tool_mcp"> {
   };
 }
 
+export interface TaskTrackingAction
+  extends OpenHandsActionEvent<"task_tracking"> {
+  source: "agent";
+  args: {
+    command: string;
+    task_list: Array<{
+      id: string;
+      title: string;
+      status: "todo" | "in_progress" | "done";
+      notes?: string;
+    }>;
+    thought: string;
+  };
+}
+
 export type OpenHandsAction =
   | UserMessageAction
   | AssistantMessageAction
@@ -178,4 +193,5 @@ export type OpenHandsAction =
   | FileWriteAction
   | RejectAction
   | RecallAction
-  | MCPAction;
+  | MCPAction
+  | TaskTrackingAction;

frontend/src/types/core/base.ts

@@ -18,6 +18,7 @@ export type OpenHandsEventType =
   | "recall"
   | "mcp"
   | "call_tool_mcp"
+  | "task_tracking"
   | "user_rejected";
 
 export type OpenHandsSourceType = "agent" | "user" | "environment";

frontend/src/types/core/guards.ts

@@ -6,6 +6,7 @@ import {
   SystemMessageAction,
   CommandAction,
   FinishAction,
+  TaskTrackingAction,
 } from "./actions";
 import {
   AgentStateChangeObservation,
@@ -13,6 +14,7 @@ import {
   ErrorObservation,
   MCPObservation,
   OpenHandsObservation,
+  TaskTrackingObservation,
 } from "./observations";
 import { StatusUpdate } from "./variances";
 
@@ -87,6 +89,16 @@ export const isMcpObservation = (
 ): event is MCPObservation =>
   isOpenHandsObservation(event) && event.observation === "mcp";
 
+export const isTaskTrackingAction = (
+  event: OpenHandsParsedEvent,
+): event is TaskTrackingAction =>
+  isOpenHandsAction(event) && event.action === "task_tracking";
+
+export const isTaskTrackingObservation = (
+  event: OpenHandsParsedEvent,
+): event is TaskTrackingObservation =>
+  isOpenHandsObservation(event) && event.observation === "task_tracking";
+
 export const isStatusUpdate = (event: unknown): event is StatusUpdate =>
   typeof event === "object" &&
   event !== null &&

frontend/src/types/core/observations.ts

@@ -146,6 +146,20 @@ export interface UserRejectedObservation
   extras: Record<string, unknown>;
 }
 
+export interface TaskTrackingObservation
+  extends OpenHandsObservationEvent<"task_tracking"> {
+  source: "agent";
+  extras: {
+    command: string;
+    task_list: Array<{
+      id: string;
+      title: string;
+      status: "todo" | "in_progress" | "done";
+      notes?: string;
+    }>;
+  };
+}
+
 export type OpenHandsObservation =
   | AgentStateChangeObservation
   | AgentThinkObservation
@@ -160,4 +174,5 @@ export type OpenHandsObservation =
   | ErrorObservation
   | RecallObservation
   | MCPObservation
-  | UserRejectedObservation;
+  | UserRejectedObservation
+  | TaskTrackingObservation;

frontend/src/types/observation-type.tsx

@@ -40,6 +40,9 @@ enum ObservationType {
 
   // A no-op observation
   NULL = "null",
+
+  // Result of a task tracking operation
+  TASK_TRACKING = "task_tracking",
 }
 
 export default ObservationType;

frontend/src/utils/browser-tab.ts

@@ -11,20 +11,23 @@ export const browserTab = {
   startNotification(message: string) {
     if (!isBrowser) return;
 
-    // Store original title if not already stored
-    if (!originalTitle) {
-      originalTitle = document.title;
-    }
+    // Always capture the current title as the baseline to restore to
+    originalTitle = document.title;
 
     // Clear any existing interval
     if (titleInterval) {
       this.stopNotification();
     }
 
-    // Alternate between original title and notification message
+    // Alternate between the latest baseline title and the notification message.
+    // If the title changes externally (e.g., user renames conversation),
+    // update the baseline so we restore to the new value when stopping.
     titleInterval = window.setInterval(() => {
-      document.title =
-        document.title === originalTitle ? message : originalTitle;
+      const current = document.title;
+      if (current !== originalTitle && current !== message) {
+        originalTitle = current;
+      }
+      document.title = current === message ? originalTitle : message;
     }, 1000);
 
     // Set favicon to indicate notification

microagents/code-review.md

@@ -47,8 +47,8 @@ Then, for each issue you find:
 - Suggest a concrete improvement
 
 Use the following structure in your output:
-[Line 42] :hammer_and_wrench: Unused import: The 'os' module is imported but never used. Remove it to clean up the code.
-[Lines 78–85] :mag: Readability: This nested if-else block is hard to follow. Consider refactoring into smaller functions or using early returns.
-[Line 102] :closed_lock_with_key: Security Risk: User input is directly concatenated into an SQL query. This could allow SQL injection. Use parameterized queries instead.
+[src/utils.py, Line 42] :hammer_and_wrench: Unused import: The 'os' module is imported but never used. Remove it to clean up the code.
+[src/database.py, Lines 78–85] :mag: Readability: This nested if-else block is hard to follow. Consider refactoring into smaller functions or using early returns.
+[src/auth.py, Line 102] :closed_lock_with_key: Security Risk: User input is directly concatenated into an SQL query. This could allow SQL injection. Use parameterized queries instead.
 
 REMEMBER, DO NOT MODIFY THE CODE. ONLY PROVIDE FEEDBACK IN YOUR RESPONSE.

microagents/codereview-roasted.md

@@ -0,0 +1,104 @@
+---
+triggers:
+- /codereview-roasted
+---
+
+PERSONA:
+You are a critical code reviewer with the engineering mindset of Linus Torvalds. Apply 30+ years of experience maintaining robust, scalable systems to analyze code quality risks and ensure solid technical foundations. You prioritize simplicity, pragmatism, and "good taste" over theoretical perfection.
+
+CORE PHILOSOPHY:
+1. **"Good Taste" - First Principle**: Look for elegant solutions that eliminate special cases rather than adding conditional checks. Good code has no edge cases.
+2. **"Never Break Userspace" - Iron Law**: Any change that breaks existing functionality is unacceptable, regardless of theoretical correctness.
+3. **Pragmatism**: Solve real problems, not imaginary ones. Reject over-engineering and "theoretically perfect" but practically complex solutions.
+4. **Simplicity Obsession**: If it needs more than 3 levels of indentation, it's broken and needs redesign.
+
+CRITICAL ANALYSIS FRAMEWORK:
+
+Before reviewing, ask Linus's Three Questions:
+1. Is this solving a real problem or an imagined one?
+2. Is there a simpler way?
+3. What will this break?
+
+TASK:
+Provide brutally honest, technically rigorous feedback on code changes. Be direct and critical while remaining constructive. Focus on fundamental engineering principles over style preferences. DO NOT modify the code; only provide specific, actionable feedback.
+
+CODE REVIEW SCENARIOS:
+
+1. **Data Structure Analysis** (Highest Priority)
+"Bad programmers worry about the code. Good programmers worry about data structures."
+Check for:
+- Poor data structure choices that create unnecessary complexity
+- Data copying/transformation that could be eliminated
+- Unclear data ownership and flow
+- Missing abstractions that would simplify the logic
+- Data structures that force special case handling
+
+2. **Complexity and "Good Taste" Assessment**
+"If you need more than 3 levels of indentation, you're screwed."
+Identify:
+- Functions with >3 levels of nesting (immediate red flag)
+- Special cases that could be eliminated with better design
+- Functions doing multiple things (violating single responsibility)
+- Complex conditional logic that obscures the core algorithm
+- Code that could be 3 lines instead of 10
+
+3. **Pragmatic Problem Analysis**
+"Theory and practice sometimes clash. Theory loses. Every single time."
+Evaluate:
+- Is this solving a problem that actually exists in production?
+- Does the solution's complexity match the problem's severity?
+- Are we over-engineering for theoretical edge cases?
+- Could this be solved with existing, simpler mechanisms?
+
+4. **Breaking Change Risk Assessment**
+"We don't break user space!"
+Watch for:
+- Changes that could break existing APIs or behavior
+- Modifications to public interfaces without deprecation
+- Assumptions about backward compatibility
+- Dependencies that could affect existing users
+
+5. **Security and Correctness** (Critical Issues Only)
+Focus on real security risks, not theoretical ones:
+- Actual input validation failures with exploit potential
+- Real privilege escalation or data exposure risks
+- Memory safety issues in unsafe languages
+- Concurrency bugs that cause data corruption
+
+CRITICAL REVIEW OUTPUT FORMAT:
+
+Start with a **Taste Rating**:
+🟢 **Good taste** - Elegant, simple solution
+🟡 **Acceptable** - Works but could be cleaner
+🔴 **Needs improvement** - Violates fundamental principles
+
+Then provide **Linus-Style Analysis**:
+
+**[CRITICAL ISSUES]** (Must fix - these break fundamental principles)
+- [src/core.py, Line X] **Data Structure**: Wrong choice creates unnecessary complexity
+- [src/handler.py, Line Y] **Complexity**: >3 levels of nesting - redesign required
+- [src/api.py, Line Z] **Breaking Change**: This will break existing functionality
+
+**[IMPROVEMENT OPPORTUNITIES]** (Should fix - violates good taste)
+- [src/utils.py, Line A] **Special Case**: Can be eliminated with better design
+- [src/processor.py, Line B] **Simplification**: These 10 lines can be 3
+- [src/feature.py, Line C] **Pragmatism**: Solving imaginary problem, focus on real issues
+
+**[STYLE NOTES]** (Minor - only mention if genuinely important)
+- [src/models.py, Line D] **Naming**: Unclear intent, affects maintainability
+
+**VERDICT:**
+✅ **Worth merging**: Core logic is sound, minor improvements suggested
+❌ **Needs rework**: Fundamental design issues must be addressed first
+
+**KEY INSIGHT:**
+[One sentence summary of the most important architectural observation]
+
+COMMUNICATION STYLE:
+- Be direct and technically precise
+- Focus on engineering fundamentals, not personal preferences
+- Explain the "why" behind each criticism
+- Suggest concrete, actionable improvements
+- Prioritize issues that affect real users over theoretical concerns
+
+REMEMBER: DO NOT MODIFY THE CODE. PROVIDE CRITICAL BUT CONSTRUCTIVE FEEDBACK ONLY.

openhands/agenthub/codeact_agent/codeact_agent.py

@@ -10,7 +10,7 @@ if TYPE_CHECKING:
     from openhands.llm.llm import ModelResponse
 
 import openhands.agenthub.codeact_agent.function_calling as codeact_function_calling
-from openhands.agenthub.codeact_agent.tools.bash import create_cmd_run_tool
+from openhands.agenthub.codeact_agent.tools.bash import CmdRunTool
 from openhands.agenthub.codeact_agent.tools.browser import BrowserTool
 from openhands.agenthub.codeact_agent.tools.condensation_request import (
     CondensationRequestTool,
@@ -21,6 +21,9 @@ from openhands.agenthub.codeact_agent.tools.llm_based_edit import LLMBasedFileEd
 from openhands.agenthub.codeact_agent.tools.str_replace_editor import (
     create_str_replace_editor_tool,
 )
+from openhands.agenthub.codeact_agent.tools.task_tracker import (
+    create_task_tracker_tool,
+)
 from openhands.agenthub.codeact_agent.tools.think import ThinkTool
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
@@ -98,7 +101,7 @@ class CodeActAgent(Agent):
         if self._prompt_manager is None:
             self._prompt_manager = PromptManager(
                 prompt_dir=os.path.join(os.path.dirname(__file__), 'prompts'),
-                system_prompt_filename=self.config.system_prompt_filename,
+                system_prompt_filename=self.config.resolved_system_prompt_filename,
             )
 
         return self._prompt_manager
@@ -122,7 +125,9 @@ class CodeActAgent(Agent):
 
         tools = []
         if self.config.enable_cmd:
-            tools.append(create_cmd_run_tool(use_short_description=use_short_tool_desc))
+            tools.append(
+                CmdRunTool(use_short_description=use_short_tool_desc).to_param()
+            )
         if self.config.enable_think:
             tools.append(ThinkTool)
         if self.config.enable_finish:
@@ -136,6 +141,9 @@ class CodeActAgent(Agent):
                 tools.append(BrowserTool)
         if self.config.enable_jupyter:
             tools.append(IPythonTool)
+        if self.config.enable_plan_mode:
+            # In plan mode, we use the task_tracker tool for task management
+            tools.append(create_task_tracker_tool(use_short_tool_desc))
         if self.config.enable_llm_editor:
             tools.append(LLMBasedFileEditTool)
         elif self.config.enable_editor:

openhands/agenthub/codeact_agent/function_calling.py

@@ -16,9 +16,10 @@ from openhands.agenthub.codeact_agent.tools import (
     IPythonTool,
     LLMBasedFileEditTool,
     ThinkTool,
-    create_cmd_run_tool,
     create_str_replace_editor_tool,
+    execute_bash,
 )
+from openhands.agenthub.codeact_agent.tools.bash import CmdRunTool
 from openhands.core.exceptions import (
     FunctionCallNotExistsError,
     FunctionCallValidationError,
@@ -30,16 +31,22 @@ from openhands.events.action import (
     AgentFinishAction,
     AgentThinkAction,
     BrowseInteractiveAction,
-    CmdRunAction,
     FileEditAction,
     FileReadAction,
     IPythonRunCellAction,
     MessageAction,
+    TaskTrackingAction,
 )
 from openhands.events.action.agent import CondensationRequestAction
 from openhands.events.action.mcp import MCPAction
 from openhands.events.event import FileEditSource, FileReadSource
 from openhands.events.tool import ToolCallMetadata
+from openhands.llm.tool_names import TASK_TRACKER_TOOL_NAME
+
+# Tool handlers registry for class-based tools
+_TOOL_HANDLERS = {
+    execute_bash.name: CmdRunTool(),
+}
 
 
 def combine_thought(action: Action, thought: str) -> Action:
@@ -84,23 +91,8 @@ def response_to_actions(
             # CmdRunTool (Bash)
             # ================================================
 
-            if tool_call.function.name == create_cmd_run_tool()['function']['name']:
-                if 'command' not in arguments:
-                    raise FunctionCallValidationError(
-                        f'Missing required argument "command" in tool call {tool_call.function.name}'
-                    )
-                # convert is_input to boolean
-                is_input = arguments.get('is_input', 'false') == 'true'
-                action = CmdRunAction(command=arguments['command'], is_input=is_input)
-
-                # Set hard timeout if provided
-                if 'timeout' in arguments:
-                    try:
-                        action.set_hard_timeout(float(arguments['timeout']))
-                    except ValueError as e:
-                        raise FunctionCallValidationError(
-                            f"Invalid float passed to 'timeout' argument: {arguments['timeout']}"
-                        ) from e
+            if tool_call.function.name == execute_bash.name:
+                action = _TOOL_HANDLERS[execute_bash.name].to_action(arguments)
 
             # ================================================
             # IPythonTool (Jupyter)
@@ -220,6 +212,24 @@ def response_to_actions(
                     )
                 action = BrowseInteractiveAction(browser_actions=arguments['code'])
 
+            # ================================================
+            # TaskTrackingAction
+            # ================================================
+            elif tool_call.function.name == TASK_TRACKER_TOOL_NAME:
+                if 'command' not in arguments:
+                    raise FunctionCallValidationError(
+                        f'Missing required argument "command" in tool call {tool_call.function.name}'
+                    )
+                if arguments['command'] == 'plan' and 'task_list' not in arguments:
+                    raise FunctionCallValidationError(
+                        f'Missing required argument "task_list" for "plan" command in tool call {tool_call.function.name}'
+                    )
+
+                action = TaskTrackingAction(
+                    command=arguments['command'],
+                    task_list=arguments.get('task_list', []),
+                )
+
             # ================================================
             # MCPAction (MCP)
             # ================================================

openhands/agenthub/codeact_agent/prompts/system_prompt_long_horizon.j2

@@ -1,39 +1,40 @@
 {% include "system_prompt.j2" %}
 
 <TASK_MANAGEMENT>
-* For complex, long-horizon tasks, create a TODO.md file to track progress:
-  1. Start by creating a detailed plan in TODO.md with clear steps
-  2. Check TODO.md before each new action to maintain context and track progress
-  3. Update TODO.md as you complete steps or discover new requirements
-  4. Mark completed items with ✓ or [x] to maintain a clear record of progress
-  5. For each major step, add sub-tasks as needed to break down complex work
-  6. If you discover the plan needs significant changes, propose updates and confirm with the user before proceeding and update TODO.md
-  7. IMPORTANT: Do NOT add TODO.md to git commits or version control systems
-
-* Example TODO.md format:
-```markdown
-# Task: [Brief description of the overall task]
-
-## Plan
-- [ ] Step 1: [Description]
-  - [ ] Sub-task 1.1
-  - [ ] Sub-task 1.2
-- [ ] Step 2: [Description]
-- [x] Step 3: [Description] (Completed)
-
-## Notes
-- Important discovery: [Details about something you learned]
-- Potential issue: [Description of a potential problem]
-```
-
-* When working on a task:
-  - Read the README to understand how the system works
-  - Create TODO.md with every major step unchecked
-  - Add TODO.md to .gitignore if it's not already ignored
-  - Until every item in TODO.md is checked:
-    a. Pick the next unchecked item and work on it
-    b. Run appropriate tests to verify your work
-    c. If issues arise, fix them until tests pass
-    d. Once complete, check off the item in TODO.md
-    e. Proceed to the next unchecked item
+* You have access to the `task_tracker` tool to help you organize and monitor development work. Use this tool REGULARLY to maintain task visibility and provide users with clear progress updates. This tool is ESSENTIAL for systematic planning and decomposing complex development work into manageable components. Failing to use this tool for planning may result in overlooked requirements - which is unacceptable.
+* It is crucial that you update task status to "done" immediately upon completion of each work item. Do not accumulate multiple finished tasks before updating their status.
+* For complex, multi-phase development work, use `task_tracker` to establish a comprehensive plan with well-defined steps:
+  1. Begin by decomposing the overall objective into primary phases using `task_tracker`
+  2. Include detailed work items as necessary to break complex activities into actionable units
+  3. Update tasks to "in_progress" status when commencing work on them
+  4. Update tasks to "done" status immediately after completing each item
+  5. For each primary phase, incorporate additional work items as you identify new requirements
+  6. If you determine the plan requires substantial modifications, suggest revisions and obtain user confirmation before proceeding
+* Example workflow for debugging and resolution:
+  ```
+  User: "Execute the test suite and resolve any validation failures"
+  Assistant: I'm going to use the task_tracker tool to organize the following work items:
+  - Execute the test suite
+  - Resolve any validation failures
+  I'm now going to run the test suite using the terminal.
+  [After running tests and discovering 8 validation failures]
+  I found 8 validation failures that need attention. I'm going to use the task_tracker tool to add 8 specific items to the task list.
+  [Updating first task to in_progress]
+  Let me begin addressing the first validation issue...
+  [After resolving first failure]
+  The first validation issue has been resolved, let me mark that task as done and proceed to the second item...
+  ```
+* Example workflow for component development:
+  ```
+  User: "Build a dashboard component that displays analytics data with interactive charts and filtering options"
+  Assistant: I'll help you create an analytics dashboard with interactive charts and filtering. Let me first use the task_tracker tool to organize this development work.
+  Adding the following tasks to the tracker:
+  1. Analyze existing analytics data structure and requirements
+  2. Design dashboard layout and component architecture
+  3. Implement data visualization charts with interactivity
+  4. Create filtering and search functionality
+  5. Integrate components and perform testing
+  Let me start by examining the current analytics data structure to understand what we're working with...
+  [Assistant proceeds with implementation step by step, updating tasks to in_progress and done as work progresses]
+  ```
 </TASK_MANAGEMENT>

openhands/agenthub/codeact_agent/prompts/system_prompt_tech_philosophy.j2

@@ -0,0 +1,122 @@
+{% include "system_prompt.j2" %}
+
+<TECHNICAL_PHILOSOPHY>
+
+Adopt the engineering mindset of Linus Torvalds, creator and chief architect of the Linux kernel. Apply his 30+ years of experience maintaining the world's most successful open-source project to analyze code quality risks and ensure solid technical foundations.
+
+# My Core Philosophy
+
+1. "Good Taste" – My First Principle
+"Sometimes you can look at the problem from a different angle, rewrite it so that special cases disappear and become normal cases."
+    • Classic case: linked list deletion — optimized from 10 lines with if checks to 4 lines with unconditional branches
+    • Good taste is an intuition built from experience
+    • Eliminating edge cases is always better than adding conditional checks
+
+2. "Never break userspace" – My Iron Law
+"We don't break user space!"
+    • Any change that causes existing programs to crash is a bug, no matter how "theoretically correct"
+    • The kernel's job is to serve users, not to educate them
+    • Backward compatibility is sacred and inviolable
+
+3. Pragmatism – My Belief
+"I'm a damn pragmatist."
+    • Solve real problems, not imaginary threats
+    • Reject "theoretically perfect" but practically complex solutions like microkernels
+    • Code should serve reality, not academic papers
+
+4. Obsession with Simplicity – My Standard
+"If you need more than three levels of indentation, you're screwed and should fix your program."
+    • Functions must be short and do one thing well
+    • C is a Spartan language, naming should be equally concise
+    • Complexity is the root of all evil
+
+# Communication Principles
+
+Basic Communication Rules
+    • Style: Direct, clear, and constructive. Focus on technical improvements rather than judgmental language.
+    • Technical Priority: Provide specific, actionable feedback on technical issues. Maintain high standards while being respectful and educational.
+
+# Requirement Confirmation Process
+
+## 0. Premise Thinking – Linus's Three Questions
+
+Before any analysis, ask yourself:
+
+1. Is this a real problem or an imagined one? – Reject over-engineering
+2. Is there a simpler way? – Always seek the simplest solution
+3. What will it break? – Backward compatibility is law
+
+## 1. Requirement Understanding Confirmation
+
+Once you understand the user’s requirement, reply it in Linus’s style to confirm:
+	> Based on current information, my understanding of your requirement is: [Restate the requirement using Linus’s thinking and communication style]
+	> Please confirm if my understanding is correct.
+
+## 2. Linus-Style Problem Decomposition
+
+### First Layer: Data Structure Analysis
+"Bad programmers worry about the code. Good programmers worry about data structures."
+    • What are the core data elements? How are they related?
+    • Where does the data flow? Who owns it? Who modifies it?
+    • Any unnecessary data copying or transformation?
+
+### Second Layer: Special Case Identification
+"Good code has no special cases"
+    • Identify all if/else branches
+    • Which are real business logic? Which are patches for bad design?
+    • Can the data structure be redesigned to remove these branches?
+
+### Third Layer: Complexity Review
+"If it needs more than 3 levels of indentation, redesign it"
+    • What is the essence of the feature? (One sentence)
+    • How many concepts does the current solution use?
+    • Can it be reduced by half? Then by half again?
+
+### Fourth Layer: Breaking Change Analysis
+"Never break userspace" – backward compatibility is the law
+    • List all existing features that could be affected
+    • Which dependencies would break?
+    • How can we improve without breaking anything?
+
+### Fifth Layer: Practicality Verification
+"Theory and practice sometimes clash. Theory loses. Every single time."
+    • Does this problem actually exist in production?
+    • How many users are truly affected?
+    • Does the solution's complexity match the problem's severity?
+
+## 3. Decision Output Format
+After the 5-layer analysis, output must include:
+
+[Core Judgment]
+✅ Worth doing: [reason] / ❌ Not worth doing: [reason]
+
+[Key Insights]
+- Data Structure: [most critical data relationship]
+- Complexity: [complexity that can be eliminated]
+- Risk: [biggest breaking change risk]
+
+[Linus-Style Plan]
+If worth doing:
+1. Always start by simplifying the data structure
+2. Eliminate all special cases
+3. Implement in the dumbest but clearest way
+4. Ensure zero breaking changes
+
+If not worth doing, explain to the user:
+"This is solving a problem that doesn’t exist. The real problem is [XXX]."
+
+## 4. Code Review Output
+When seeing code, make three quick judgments:
+
+[Taste Rating]
+🟢 Good taste / 🟡 Acceptable / 🔴 Needs improvement
+
+[Critical Issue]
+- [If any, directly point out the worst part]
+
+[Improvement Direction]
+"Eliminate this special case"
+"These 10 lines can be 3"
+"Wrong data structure, should be..."
+
+</TECHNICAL_PHILOSOPHY>

openhands/agenthub/codeact_agent/tools/__init__.py

@@ -1,4 +1,9 @@
-from .bash import create_cmd_run_tool
+from .bash import create_cmd_run_tool, execute_bash
+
+# NOTE: This module currently exposes schema-only tools. As part of #10441 we are
+# gradually encapsulating tools as classes that own schema and validation. See
+# bash.CmdRunTool for the first example. Existing code remains backward
+# compatible by exporting ChatCompletionToolParam for now.
 from .browser import BrowserTool
 from .condensation_request import CondensationRequestTool
 from .finish import FinishTool
@@ -11,6 +16,7 @@ __all__ = [
     'BrowserTool',
     'CondensationRequestTool',
     'create_cmd_run_tool',
+    'execute_bash',
     'FinishTool',
     'IPythonTool',
     'LLMBasedFileEditTool',

openhands/agenthub/codeact_agent/tools/base.py

@@ -0,0 +1,43 @@
+from __future__ import annotations
+
+import json
+from abc import ABC, abstractmethod
+from typing import Any
+
+from litellm import ChatCompletionToolParam
+
+from openhands.core.exceptions import FunctionCallValidationError
+
+
+class Tool(ABC):
+    """Base class for CodeAct tools.
+
+    Subclasses should encapsulate schema, descriptions and validation.
+    They must implement to_param() and to_action().
+    """
+
+    @abstractmethod
+    def to_param(self) -> ChatCompletionToolParam:
+        """Return the ChatCompletionToolParam schema for this tool."""
+        raise NotImplementedError
+
+    def parse_arguments(self, raw_arguments: str) -> dict[str, Any]:
+        """Parse the raw JSON string from the model into a dict.
+
+        Raises FunctionCallValidationError on failure.
+        """
+        try:
+            return json.loads(raw_arguments) if raw_arguments else {}
+        except json.decoder.JSONDecodeError as e:
+            raise FunctionCallValidationError(
+                f'Failed to parse tool call arguments: {raw_arguments}'
+            ) from e
+
+    @abstractmethod
+    def to_action(self, arguments: dict[str, Any]):  # -> Action
+        """Convert validated arguments to an Action.
+
+        Implementations should raise FunctionCallValidationError for
+        missing/invalid parameters.
+        """
+        raise NotImplementedError

openhands/agenthub/codeact_agent/tools/bash.py

@@ -1,8 +1,22 @@
+from __future__ import annotations
+
 from litellm import ChatCompletionToolParam, ChatCompletionToolParamFunctionChunk
 
+from openhands.agenthub.codeact_agent.tools.base import Tool
 from openhands.agenthub.codeact_agent.tools.prompt import refine_prompt
+from openhands.core.exceptions import FunctionCallValidationError
+from openhands.events.action import CmdRunAction
 from openhands.llm.tool_names import EXECUTE_BASH_TOOL_NAME
 
+
+class _ToolRef:
+    def __init__(self, name: str) -> None:
+        self.name = name
+
+
+# Lightweight reference so callers can compare against execute_bash.name
+execute_bash = _ToolRef(EXECUTE_BASH_TOOL_NAME)
+
 _DETAILED_BASH_DESCRIPTION = """Execute a bash command in the terminal within a persistent shell session.
 
 
@@ -28,6 +42,65 @@ _DETAILED_BASH_DESCRIPTION = """Execute a bash command in the terminal within a
 * Output truncation: If the output exceeds a maximum length, it will be truncated before being returned.
 """
 
+
+class CmdRunTool(Tool):
+    def __init__(self, use_short_description: bool = False) -> None:
+        self.use_short_description = use_short_description
+
+    def to_param(self) -> ChatCompletionToolParam:
+        description = (
+            _SHORT_BASH_DESCRIPTION
+            if self.use_short_description
+            else _DETAILED_BASH_DESCRIPTION
+        )
+        return ChatCompletionToolParam(
+            type='function',
+            function=ChatCompletionToolParamFunctionChunk(
+                name=EXECUTE_BASH_TOOL_NAME,
+                description=refine_prompt(description),
+                parameters={
+                    'type': 'object',
+                    'properties': {
+                        'command': {
+                            'type': 'string',
+                            'description': refine_prompt(
+                                'The bash command to execute. Can be empty string to view additional logs when previous exit code is `-1`. Can be `C-c` (Ctrl+C) to interrupt the currently running process. Note: You can only execute one bash command at a time. If you need to run multiple commands sequentially, you can use `&&` or `;` to chain them together.'
+                            ),
+                        },
+                        'is_input': {
+                            'type': 'string',
+                            'description': refine_prompt(
+                                'If True, the command is an input to the running process. If False, the command is a bash command to be executed in the terminal. Default is False.'
+                            ),
+                            'enum': ['true', 'false'],
+                        },
+                        'timeout': {
+                            'type': 'number',
+                            'description': 'Optional. Sets a hard timeout in seconds for the command execution. If not provided, the command will use the default soft timeout behavior.',
+                        },
+                    },
+                    'required': ['command'],
+                },
+            ),
+        )
+
+    def to_action(self, arguments: dict[str, str]) -> CmdRunAction:
+        if 'command' not in arguments:
+            raise FunctionCallValidationError(
+                'Missing required argument "command" in tool call execute_bash'
+            )
+        is_input = arguments.get('is_input', 'false') == 'true'
+        action = CmdRunAction(command=arguments['command'], is_input=is_input)
+        if 'timeout' in arguments:
+            try:
+                action.set_hard_timeout(float(arguments['timeout']))
+            except ValueError as e:
+                raise FunctionCallValidationError(
+                    f"Invalid float passed to 'timeout' argument: {arguments['timeout']}"
+                ) from e
+        return action
+
+
 _SHORT_BASH_DESCRIPTION = """Execute a bash command in the terminal.
 * Long running commands: For commands that may run indefinitely, it should be run in the background and the output should be redirected to a file, e.g. command = `python3 app.py > server.log 2>&1 &`. For commands that need to run for a specific duration, you can set the "timeout" argument to specify a hard timeout in seconds.
 * Interact with running process: If a bash command returns exit code `-1`, this means the process is not yet finished. By setting `is_input` to `true`, the assistant can interact with the running process and send empty `command` to retrieve any additional logs, or send additional text (set `command` to the text) to STDIN of the running process, or send command like `C-c` (Ctrl+C), `C-d` (Ctrl+D), `C-z` (Ctrl+Z) to interrupt the process.

openhands/agenthub/codeact_agent/tools/task_tracker.py

@@ -0,0 +1,203 @@
+from litellm import ChatCompletionToolParam, ChatCompletionToolParamFunctionChunk
+
+from openhands.llm.tool_names import TASK_TRACKER_TOOL_NAME
+
+_DETAILED_TASK_TRACKER_DESCRIPTION = """This tool provides structured task management capabilities for development workflows.
+It enables systematic tracking of work items, progress monitoring, and efficient
+organization of complex development activities.
+
+The tool maintains visibility into project status and helps communicate
+progress effectively to users.
+
+## Application Guidelines
+
+Utilize this tool in the following situations:
+
+1. Multi-phase development work - When projects involve multiple sequential or
+   parallel activities
+2. Complex implementation tasks - Work requiring systematic planning and
+   coordination across multiple components
+3. Explicit user request for task organization - When users specifically ask
+   for structured task management
+4. Multiple concurrent requirements - When users present several work items
+   that need coordination
+5. Project initiation - Capture and organize user requirements at project start
+6. Work commencement - Update task status to in_progress before beginning
+   implementation. Maintain focus by limiting active work to one task
+7. Task completion - Update status to done and identify any additional work
+   that emerged during implementation
+
+## Situations Where Tool Usage Is Unnecessary
+
+Avoid using this tool when:
+
+1. Single atomic tasks that require no decomposition
+2. Trivial operations where tracking adds no organizational value
+3. Simple activities completable in minimal steps
+4. Pure information exchange or discussion
+
+Note: For single straightforward tasks, proceed with direct implementation
+rather than creating tracking overhead.
+
+## Usage Scenarios
+
+**Scenario A: Feature Development with Validation**
+User request: "Build a user authentication system with login/logout functionality.
+Don't forget to include input validation and error handling!"
+
+Response approach: I'll implement a user authentication system with comprehensive
+validation. Let me organize this work systematically.
+
+*Task breakdown includes:*
+1. Design authentication API endpoints and data models
+2. Implement user login/logout controllers with session management
+3. Add client-side form validation and error display
+4. Create backend input sanitization and security checks
+5. Implement comprehensive error handling for edge cases
+6. Perform integration testing and fix any issues
+
+**Scenario B: Codebase Refactoring**
+User request: "I need to update all instances of the method 'fetchData' to
+'retrieveInformation' throughout the entire project"
+
+Response approach: Let me first analyze your codebase to identify all locations
+where 'fetchData' appears.
+
+*After code analysis*
+
+I've located 12 occurrences of 'fetchData' across 6 files in your project.
+I'll create a systematic plan to update these references.
+
+*Organized task list includes specific file-by-file updates*
+
+**Scenario C: Multi-feature Development**
+User request: "Set up a blog platform with these components: admin dashboard,
+article management, comment system, and user profiles."
+
+Response approach: I'll help build your blog platform. Let me break down these
+components into manageable implementation phases.
+
+*Creates structured plan with each feature decomposed into specific development tasks*
+
+## Counter-examples - Direct Implementation Preferred
+
+**Counter-example A: Simple inquiry**
+User request: "What's the syntax for a for loop in JavaScript?"
+
+Response approach: Here's how to write a for loop in JavaScript:
+
+```javascript
+for (let i = 0; i < array.length; i++) {
+    console.log(array[i]);
+}
+```
+
+*No task tracking needed - single informational response*
+
+**Counter-example B: Minor modification**
+User request: "Please add a docstring to the processPayment function explaining
+its parameters."
+
+Response approach: I'll add a docstring to explain the processPayment function.
+
+*Direct edit without task tracking for simple modification*
+
+## Status Management and Workflow
+
+1. **Status Values**: Track work using these states:
+   - todo: Not yet initiated
+   - in_progress: Currently active (maintain single focus)
+   - done: Successfully completed
+
+2. **Workflow Practices**:
+   - Update status dynamically as work progresses
+   - Mark completion immediately upon task finish
+   - Limit active work to ONE task at any given time
+   - Complete current activities before initiating new ones
+   - Remove obsolete tasks from tracking entirely
+
+3. **Completion Criteria**:
+   - Mark tasks as done only when fully achieved
+   - Keep status as in_progress if errors, blocks, or partial completion exist
+   - Create new tasks for discovered issues or dependencies
+   - Never mark done when:
+       - Test suites are failing
+       - Implementation remains incomplete
+       - Unresolved errors persist
+       - Required resources are unavailable
+
+4. **Task Organization**:
+   - Write precise, actionable descriptions
+   - Decompose complex work into manageable units
+   - Use descriptive, clear naming conventions
+
+When uncertain, favor using this tool. Proactive task management demonstrates
+systematic approach and ensures comprehensive requirement fulfillment.
+"""
+
+_SHORT_TASK_TRACKER_DESCRIPTION = """Provides structured task management for development workflows, enabling progress
+tracking and systematic organization of complex coding activities.
+
+* Apply to multi-phase projects (3+ distinct steps) or when managing multiple user requirements
+* Update status (todo/in_progress/done) dynamically throughout work
+* Maintain single active task focus at any time
+* Mark completion immediately upon task finish
+* Decompose complex work into manageable, actionable units
+"""
+
+
+def create_task_tracker_tool(
+    use_short_description: bool = False,
+) -> ChatCompletionToolParam:
+    description = (
+        _SHORT_TASK_TRACKER_DESCRIPTION
+        if use_short_description
+        else _DETAILED_TASK_TRACKER_DESCRIPTION
+    )
+    return ChatCompletionToolParam(
+        type='function',
+        function=ChatCompletionToolParamFunctionChunk(
+            name=TASK_TRACKER_TOOL_NAME,
+            description=description,
+            parameters={
+                'type': 'object',
+                'properties': {
+                    'command': {
+                        'type': 'string',
+                        'enum': ['view', 'plan'],
+                        'description': 'The command to execute. `view` shows the current task list. `plan` creates or updates the task list based on provided requirements and progress. Always `view` the current list before making changes.',
+                    },
+                    'task_list': {
+                        'type': 'array',
+                        'description': 'The full task list. Required parameter of `plan` command.',
+                        'items': {
+                            'type': 'object',
+                            'properties': {
+                                'id': {
+                                    'type': 'string',
+                                    'description': 'Unique task identifier',
+                                },
+                                'title': {
+                                    'type': 'string',
+                                    'description': 'Brief task description',
+                                },
+                                'status': {
+                                    'type': 'string',
+                                    'description': 'Current task status',
+                                    'enum': ['todo', 'in_progress', 'done'],
+                                },
+                                'notes': {
+                                    'type': 'string',
+                                    'description': 'Optional additional context or details',
+                                },
+                            },
+                            'required': ['title', 'status', 'id'],
+                            'additionalProperties': False,
+                        },
+                    },
+                },
+                'required': ['command'],
+                'additionalProperties': False,
+            },
+        ),
+    )

openhands/cli/main.py

@@ -360,12 +360,12 @@ async def run_session(
             # Check if it's an authentication error
             if 'ERROR_LLM_AUTHENTICATION' in error_message:
                 # Start with base authentication error message
-                initial_message = 'Authentication error with the LLM provider. Please check your API key.'
+                welcome_message = 'Authentication error with the LLM provider. Please check your API key.'
 
                 # Add OpenHands-specific guidance if using an OpenHands model
                 llm_config = config.get_llm_config()
                 if llm_config.model.startswith('openhands/'):
-                    initial_message += " If you're using OpenHands models, get a new API key from https://app.all-hands.dev/settings/api-keys"
+                    welcome_message += "\nIf you're using OpenHands models, get a new API key from https://app.all-hands.dev/settings/api-keys"
             else:
                 # For other errors, use the standard message
                 initial_message = (

openhands/cli/tui.py

@@ -41,6 +41,7 @@ from openhands.events.action import (
     CmdRunAction,
     MCPAction,
     MessageAction,
+    TaskTrackingAction,
 )
 from openhands.events.event import Event
 from openhands.events.observation import (
@@ -50,6 +51,7 @@ from openhands.events.observation import (
     FileEditObservation,
     FileReadObservation,
     MCPObservation,
+    TaskTrackingObservation,
 )
 from openhands.llm.metrics import Metrics
 from openhands.mcp.error_collector import mcp_error_collector
@@ -273,6 +275,8 @@ def display_event(event: Event, config: OpenHandsConfig) -> None:
                 initialize_streaming_output()
         elif isinstance(event, MCPAction):
             display_mcp_action(event)
+        elif isinstance(event, TaskTrackingAction):
+            display_task_tracking_action(event)
         elif isinstance(event, Action):
             # For other actions, display thoughts normally
             if hasattr(event, 'thought') and event.thought:
@@ -293,6 +297,8 @@ def display_event(event: Event, config: OpenHandsConfig) -> None:
             display_file_read(event)
         elif isinstance(event, MCPObservation):
             display_mcp_observation(event)
+        elif isinstance(event, TaskTrackingObservation):
+            display_task_tracking_observation(event)
         elif isinstance(event, AgentStateChangedObservation):
             display_agent_state_change_message(event.agent_state)
         elif isinstance(event, ErrorObservation):
@@ -521,6 +527,74 @@ def display_mcp_observation(event: MCPObservation) -> None:
     print_container(container)
 
 
+def display_task_tracking_action(event: TaskTrackingAction) -> None:
+    """Display a TaskTracking action in the CLI."""
+    # Display thought first if present
+    if hasattr(event, 'thought') and event.thought:
+        display_message(event.thought)
+
+    # Format the command and task list for display
+    display_text = f'Command: {event.command}'
+
+    if event.command == 'plan':
+        if event.task_list:
+            display_text += f'\n\nTask List ({len(event.task_list)} items):'
+            for i, task in enumerate(event.task_list, 1):
+                status = task.get('status', 'unknown')
+                title = task.get('title', 'Untitled task')
+                task_id = task.get('id', f'task-{i}')
+                notes = task.get('notes', '')
+
+                # Add status indicator with color
+                status_indicator = {
+                    'todo': '⏳',
+                    'in_progress': '🔄',
+                    'done': '✅',
+                }.get(status, '❓')
+
+                display_text += f'\n  {i}. {status_indicator} [{status.upper()}] {title} (ID: {task_id})'
+                if notes:
+                    display_text += f'\n     Notes: {notes}'
+        else:
+            display_text += '\n\nTask List: Empty'
+
+    container = Frame(
+        TextArea(
+            text=display_text,
+            read_only=True,
+            style='ansigreen',
+            wrap_lines=True,
+        ),
+        title='Task Tracking Action',
+        style='ansigreen',
+    )
+    print_formatted_text('')
+    print_container(container)
+
+
+def display_task_tracking_observation(event: TaskTrackingObservation) -> None:
+    """Display a TaskTracking observation in the CLI."""
+    # Format the content and task list for display
+    content = (
+        event.content.strip() if event.content else 'Task tracking operation completed'
+    )
+
+    display_text = f'Result: {content}'
+
+    container = Frame(
+        TextArea(
+            text=display_text,
+            read_only=True,
+            style=COLOR_GREY,
+            wrap_lines=True,
+        ),
+        title='Task Tracking Result',
+        style=f'fg:{COLOR_GREY}',
+    )
+    print_formatted_text('')
+    print_container(container)
+
+
 def initialize_streaming_output():
     """Initialize the streaming output TextArea."""
     if not ENABLE_STREAMING:

openhands/core/config/agent_config.py

@@ -46,6 +46,8 @@ class AgentConfig(BaseModel):
     """Whether history should be truncated to continue the session when hitting LLM context length limit."""
     enable_som_visual_browsing: bool = Field(default=True)
     """Whether to enable SoM (Set of Marks) visual browsing."""
+    enable_plan_mode: bool = Field(default=True)
+    """Whether to enable plan mode, which uses the long horizon system message and add the new tool - task_tracker - for planning, tracking and executing complex tasks."""
     condenser: CondenserConfig = Field(
         # The default condenser is set to the conversation window condenser -- if
         # we use NoOp and the conversation hits the LLM context length limit,
@@ -58,6 +60,17 @@ class AgentConfig(BaseModel):
 
     model_config = ConfigDict(extra='forbid')
 
+    @property
+    def resolved_system_prompt_filename(self) -> str:
+        """
+        Returns the appropriate system prompt filename based on the agent configuration.
+        When enable_plan_mode is True, automatically uses the long horizon system prompt
+        unless a custom system_prompt_filename was explicitly set (not the default).
+        """
+        if self.enable_plan_mode and self.system_prompt_filename == 'system_prompt.j2':
+            return 'system_prompt_long_horizon.j2'
+        return self.system_prompt_filename
+
     @classmethod
     def from_toml_section(cls, data: dict) -> dict[str, AgentConfig]:
         """Create a mapping of AgentConfig instances from a toml dictionary representing the [agent] section.

openhands/core/schema/action.py

@@ -94,3 +94,6 @@ class ActionType(str, Enum):
 
     CONDENSATION_REQUEST = 'condensation_request'
     """Request for condensation of a list of events."""
+
+    TASK_TRACKING = 'task_tracking'
+    """Views or updates the task list for task management."""

openhands/core/schema/observation.py

@@ -55,3 +55,6 @@ class ObservationType(str, Enum):
 
     DOWNLOAD = 'download'
     """Result of downloading/opening a file via the browser"""
+
+    TASK_TRACKING = 'task_tracking'
+    """Result of a task tracking operation"""

openhands/events/action/__init__.py

@@ -6,6 +6,7 @@ from openhands.events.action.agent import (
     AgentThinkAction,
     ChangeAgentStateAction,
     RecallAction,
+    TaskTrackingAction,
 )
 from openhands.events.action.browse import BrowseInteractiveAction, BrowseURLAction
 from openhands.events.action.commands import CmdRunAction, IPythonRunCellAction
@@ -38,4 +39,5 @@ __all__ = [
     'AgentThinkAction',
     'RecallAction',
     'MCPAction',
+    'TaskTrackingAction',
 ]

openhands/events/action/agent.py

@@ -201,3 +201,28 @@ class CondensationRequestAction(Action):
     @property
     def message(self) -> str:
         return 'Requesting a condensation of the conversation history.'
+
+
+@dataclass
+class TaskTrackingAction(Action):
+    """An action where the agent writes or updates a task list for task management.
+    Attributes:
+        task_list (list): The list of task items with their status and metadata.
+        thought (str): The agent's explanation of its actions.
+        action (str): The action type, namely ActionType.TASK_TRACKING.
+    """
+
+    command: str = 'view'
+    task_list: list[dict[str, Any]] = field(default_factory=list)
+    thought: str = ''
+    action: str = ActionType.TASK_TRACKING
+
+    @property
+    def message(self) -> str:
+        num_tasks = len(self.task_list)
+        if num_tasks == 0:
+            return 'Clearing the task list.'
+        elif num_tasks == 1:
+            return 'Managing 1 task item.'
+        else:
+            return f'Managing {num_tasks} task items.'

openhands/events/nested_event_store.py

@@ -28,16 +28,22 @@ class NestedEventStore(EventStoreABC):
         filter: EventFilter | None = None,
         limit: int | None = None,
     ) -> Iterable[Event]:
+        # Maintain explicit cursors for pagination to avoid accidental mutation.
+        start_cursor = start_id
+        end_cursor: int | None = None  # Used only for reverse pagination
         while True:
-            search_params = {
-                'start_id': start_id,
+            search_params: dict[str, int | bool] = {
+                'start_id': start_cursor,
                 'reverse': reverse,
             }
+            if reverse and end_cursor is not None:
+                # Bound the upper end when scanning backwards to avoid duplicates
+                search_params['end_id'] = end_cursor
             if limit is not None:
                 search_params['limit'] = min(100, limit)
             search_str = urlencode(search_params)
             url = f'{self.base_url}/events?{search_str}'
-            headers = {}
+            headers: dict[str, str] = {}
             if self.session_api_key:
                 headers['X-Session-API-Key'] = self.session_api_key
             response = httpx.get(url, headers=headers)
@@ -45,9 +51,17 @@ class NestedEventStore(EventStoreABC):
                 # Follow pattern of event store not throwing errors on not found
                 return
             result_set = response.json()
+
+            page_min_id: int | None = None
+            forward_next_start = start_cursor
             for result in result_set['events']:
                 event = event_from_dict(result)
-                start_id = max(start_id, event.id + 1)
+                if reverse:
+                    page_min_id = (
+                        event.id if page_min_id is None else min(page_min_id, event.id)
+                    )
+                else:
+                    forward_next_start = max(forward_next_start, event.id + 1)
                 if end_id == event.id:
                     if not filter or filter.include(event):
                         yield event
@@ -59,6 +73,14 @@ class NestedEventStore(EventStoreABC):
                     limit -= 1
                     if limit <= 0:
                         return
+
+            # Update pagination cursor for next request
+            if reverse and page_min_id is not None:
+                # Next page should end strictly before the smallest ID we just saw
+                end_cursor = page_min_id - 1
+            elif not reverse:
+                start_cursor = forward_next_start
+
             if not result_set['has_more']:
                 return
 

openhands/events/observation/__init__.py

@@ -26,6 +26,7 @@ from openhands.events.observation.mcp import MCPObservation
 from openhands.events.observation.observation import Observation
 from openhands.events.observation.reject import UserRejectObservation
 from openhands.events.observation.success import SuccessObservation
+from openhands.events.observation.task_tracking import TaskTrackingObservation
 
 __all__ = [
     'Observation',
@@ -48,4 +49,5 @@ __all__ = [
     'RecallType',
     'MCPObservation',
     'FileDownloadObservation',
+    'TaskTrackingObservation',
 ]

openhands/events/observation/task_tracking.py

@@ -0,0 +1,18 @@
+from dataclasses import dataclass, field
+from typing import Any
+
+from openhands.core.schema import ObservationType
+from openhands.events.observation.observation import Observation
+
+
+@dataclass
+class TaskTrackingObservation(Observation):
+    """This data class represents the result of a task tracking operation."""
+
+    observation: str = ObservationType.TASK_TRACKING
+    command: str = ''
+    task_list: list[dict[str, Any]] = field(default_factory=list)
+
+    @property
+    def message(self) -> str:
+        return self.content

openhands/events/serialization/action.py

@@ -11,6 +11,7 @@ from openhands.events.action.agent import (
     CondensationAction,
     CondensationRequestAction,
     RecallAction,
+    TaskTrackingAction,
 )
 from openhands.events.action.browse import BrowseInteractiveAction, BrowseURLAction
 from openhands.events.action.commands import (
@@ -46,6 +47,7 @@ actions = (
     CondensationAction,
     CondensationRequestAction,
     MCPAction,
+    TaskTrackingAction,
 )
 
 ACTION_TYPE_TO_CLASS = {action_class.action: action_class for action_class in actions}  # type: ignore[attr-defined]

openhands/events/serialization/observation.py

@@ -30,6 +30,7 @@ from openhands.events.observation.mcp import MCPObservation
 from openhands.events.observation.observation import Observation
 from openhands.events.observation.reject import UserRejectObservation
 from openhands.events.observation.success import SuccessObservation
+from openhands.events.observation.task_tracking import TaskTrackingObservation
 
 observations = (
     NullObservation,
@@ -49,6 +50,7 @@ observations = (
     RecallObservation,
     MCPObservation,
     FileDownloadObservation,
+    TaskTrackingObservation,
 )
 
 OBSERVATION_TYPE_TO_CLASS = {

openhands/integrations/gitlab/gitlab_service.py

@@ -1,4 +1,5 @@
 import os
+from datetime import datetime
 from typing import Any
 
 import httpx
@@ -7,6 +8,7 @@ from pydantic import SecretStr
 from openhands.integrations.service_types import (
     BaseGitService,
     Branch,
+    Comment,
     GitService,
     OwnerType,
     ProviderType,
@@ -673,6 +675,80 @@ class GitLabService(BaseGitService, GitService):
         # Parse the content to extract triggers from frontmatter
         return self._parse_microagent_content(response, file_path)
 
+    async def get_issue_comments(
+        self, project_id: str, issue_iid: int, limit: int = 100
+    ) -> list[Comment]:
+        """Get the last n comments for a specific issue.
+
+        Args:
+            project_id: The GitLab project ID (can be numeric ID or URL-encoded path)
+            issue_iid: The issue internal ID (iid) in GitLab
+            limit: Maximum number of comments to retrieve (default: 100)
+
+        Returns:
+            List of Comment objects, ordered by creation date (newest first)
+
+        Raises:
+            UnknownException: If the request fails or the issue is not found
+        """
+        # URL-encode the project_id if it contains special characters
+        if '/' in str(project_id):
+            encoded_project_id = str(project_id).replace('/', '%2F')
+        else:
+            encoded_project_id = str(project_id)
+
+        url = f'{self.BASE_URL}/projects/{encoded_project_id}/issues/{issue_iid}/notes'
+
+        all_comments: list[Comment] = []
+        page = 1
+        per_page = min(limit, 100)  # GitLab API max per_page is 100
+
+        while len(all_comments) < limit:
+            # Get comments with pagination, ordered by creation date descending
+            params = {
+                'per_page': per_page,
+                'page': page,
+                'order_by': 'created_at',
+                'sort': 'desc',  # Get newest comments first
+            }
+
+            response, headers = await self._make_request(url, params)
+
+            if not response:  # No more comments
+                break
+
+            # Filter out system comments and convert to Comment objects
+            for comment_data in response:
+                if len(all_comments) >= limit:
+                    break
+
+                # Skip system-generated comments unless explicitly requested
+                if comment_data.get('system', False):
+                    continue
+
+                comment = Comment(
+                    id=comment_data['id'],
+                    body=comment_data['body'],
+                    author=comment_data.get('author', {}).get('username', 'unknown'),
+                    created_at=datetime.fromisoformat(
+                        comment_data['created_at'].replace('Z', '+00:00')
+                    ),
+                    updated_at=datetime.fromisoformat(
+                        comment_data['updated_at'].replace('Z', '+00:00')
+                    ),
+                    system=comment_data.get('system', False),
+                )
+                all_comments.append(comment)
+
+            # Check if we have more pages
+            link_header = headers.get('Link', '')
+            if 'rel="next"' not in link_header or len(all_comments) >= limit:
+                break
+
+            page += 1
+
+        return all_comments
+
 
 gitlab_service_cls = os.environ.get(
     'OPENHANDS_GITLAB_SERVICE_CLS',

openhands/integrations/service_types.py

@@ -140,6 +140,15 @@ class Repository(BaseModel):
     main_branch: str | None = None  # The main/default branch of the repository
 
 
+class Comment(BaseModel):
+    id: int
+    body: str
+    author: str
+    created_at: datetime
+    updated_at: datetime
+    system: bool = False  # Whether this is a system-generated comment
+
+
 class AuthenticationError(ValueError):
     """Raised when there is an issue with GitHub authentication."""
 

openhands/llm/tool_names.py

@@ -5,3 +5,4 @@ STR_REPLACE_EDITOR_TOOL_NAME = 'str_replace_editor'
 BROWSER_TOOL_NAME = 'browser'
 FINISH_TOOL_NAME = 'finish'
 LLM_BASED_EDIT_TOOL_NAME = 'edit_file'
+TASK_TRACKER_TOOL_NAME = 'task_tracker'

openhands/memory/conversation_memory.py

@@ -18,6 +18,7 @@ from openhands.events.action import (
     FileReadAction,
     IPythonRunCellAction,
     MessageAction,
+    TaskTrackingAction,
 )
 from openhands.events.action.mcp import MCPAction
 from openhands.events.action.message import SystemMessageAction
@@ -32,6 +33,7 @@ from openhands.events.observation import (
     FileEditObservation,
     FileReadObservation,
     IPythonRunCellObservation,
+    TaskTrackingObservation,
     UserRejectObservation,
 )
 from openhands.events.observation.agent import (
@@ -228,11 +230,27 @@ class ConversationMemory:
                 BrowseInteractiveAction,
                 BrowseURLAction,
                 MCPAction,
+                TaskTrackingAction,
             ),
         ) or (isinstance(action, CmdRunAction) and action.source == 'agent'):
             tool_metadata = action.tool_call_metadata
+
+            # Allow user actions to skip tool metadata validation
+            if action.source == 'user' and tool_metadata is None:
+                # For user-initiated actions without tool metadata, create a simple message
+                return [
+                    Message(
+                        role='user',
+                        content=[
+                            TextContent(
+                                text=f'User requested to read file: {str(action)}'
+                            )
+                        ],
+                    )
+                ]
+
             assert tool_metadata is not None, (
-                'Tool call metadata should NOT be None when function calling is enabled. Action: '
+                'Tool call metadata should NOT be None when function calling is enabled for agent actions. Action: '
                 + str(action)
             )
 
@@ -487,6 +505,9 @@ class ConversationMemory:
         elif isinstance(obs, AgentThinkObservation):
             text = truncate_content(obs.content, max_message_chars)
             message = Message(role='user', content=[TextContent(text=text)])
+        elif isinstance(obs, TaskTrackingObservation):
+            text = truncate_content(obs.content, max_message_chars)
+            message = Message(role='user', content=[TextContent(text=text)])
         elif isinstance(obs, ErrorObservation):
             text = truncate_content(obs.content, max_message_chars)
             text += '\n[Error occurred in processing last action]'

openhands/runtime/base.py

@@ -33,6 +33,7 @@ from openhands.events.action import (
     FileReadAction,
     FileWriteAction,
     IPythonRunCellAction,
+    TaskTrackingAction,
 )
 from openhands.events.action.mcp import MCPAction
 from openhands.events.event import Event
@@ -43,6 +44,7 @@ from openhands.events.observation import (
     FileReadObservation,
     NullObservation,
     Observation,
+    TaskTrackingObservation,
     UserRejectObservation,
 )
 from openhands.events.serialization.action import ACTION_TYPE_TO_CLASS
@@ -869,6 +871,46 @@ fi
         if not action.runnable:
             if isinstance(action, AgentThinkAction):
                 return AgentThinkObservation('Your thought has been logged.')
+            elif isinstance(action, TaskTrackingAction):
+                # If `command` is `plan`, write the serialized task list to the file TASKS.md under `.openhands/`
+                if action.command == 'plan':
+                    content = '# Task List\n\n'
+                    for i, task in enumerate(action.task_list, 1):
+                        status_icon = {
+                            'todo': '⏳',
+                            'in_progress': '🔄',
+                            'done': '✅',
+                        }.get(task.get('status', 'todo'), '⏳')
+                        content += f'{i}. {status_icon} {task.get("title", "")}\n{task.get("notes", "")}\n'
+                    write_obs = self.write(
+                        FileWriteAction(path='.openhands/TASKS.md', content=content)
+                    )
+                    if isinstance(write_obs, ErrorObservation):
+                        return ErrorObservation(
+                            f'Failed to write task list to .openhands/TASKS.md: {write_obs.content}'
+                        )
+
+                    return TaskTrackingObservation(
+                        content=f'Task list has been updated with {len(action.task_list)} items.',
+                        command=action.command,
+                        task_list=action.task_list,
+                    )
+                elif action.command == 'view':
+                    # If `command` is `view`, read the TASKS.md file and return its content
+                    read_obs = self.read(FileReadAction(path='.openhands/TASKS.md'))
+                    if isinstance(read_obs, FileReadObservation):
+                        return TaskTrackingObservation(
+                            content=read_obs.content,
+                            command=action.command,
+                            task_list=[],  # Empty for view command
+                        )
+                    else:
+                        return TaskTrackingObservation(  # Return observation if error occurs because file might not exist yet
+                            command=action.command,
+                            task_list=[],
+                            content=f'Failed to read the task list. Error: {read_obs.content}',
+                        )
+
             return NullObservation('')
         if (
             hasattr(action, 'confirmation_state')

openhands/runtime/utils/bash.py

@@ -189,9 +189,13 @@ class BashSession:
         self.username = username
         self._initialized = False
         self.max_memory_mb = max_memory_mb
+        # Ensure a safe default for cleanup even if initialization fails early
+        self._closed: bool = True
 
     def initialize(self) -> None:
-        self.server = libtmux.Server()
+        # Use a dedicated tmux socket name to avoid inheriting an existing TMUX session
+        # which may be owned by a different user and cause permission issues.
+        self.server = libtmux.Server(socket_name=f'openhands-{uuid.uuid4()}')
         _shell_command = '/bin/bash'
         if self.username in ['root', 'openhands']:
             # This starts a non-login (new) shell for the given user
@@ -241,7 +245,7 @@ class BashSession:
         # Store the last command for interactive input handling
         self.prev_status: BashCommandStatus | None = None
         self.prev_output: str = ''
-        self._closed: bool = False
+        self._closed = False
         logger.debug(f'Bash session initialized with work dir: {self.work_dir}')
 
         # Maintain the current working directory

openhands/storage/batched_web_hook.py

@@ -1,9 +1,10 @@
 import threading
-from typing import Optional, Union
+from typing import Optional
 
 import httpx
 import tenacity
 
+from openhands.core.logger import openhands_logger as logger
 from openhands.storage.files import FileStore
 from openhands.utils.async_utils import EXECUTOR
 
@@ -17,8 +18,8 @@ class BatchedWebHookFileStore(FileStore):
 
     This class wraps another FileStore implementation and sends HTTP requests
     to a specified URL when files are written or deleted. Updates are batched
-    and sent together after a certain amount of time passes or if the content
-    size exceeds a threshold.
+    and sent together after a certain amount of time or size exceeds a threshold.
+    Time is counted from the last insert.
 
     Attributes:
         file_store: The underlying FileStore implementation
@@ -38,7 +39,7 @@ class BatchedWebHookFileStore(FileStore):
     batch_timeout_seconds: float
     batch_size_limit_bytes: int
     _batch_lock: threading.Lock
-    _batch: dict[str, tuple[str, Optional[Union[str, bytes]]]]
+    _batch: dict[str, tuple[str, str | bytes | None]]
     _batch_timer: Optional[threading.Timer]
     _batch_size: int
 
@@ -81,7 +82,7 @@ class BatchedWebHookFileStore(FileStore):
         self._batch_timer = None
         self._batch_size = 0
 
-    def write(self, path: str, contents: Union[str, bytes]) -> None:
+    def write(self, path: str, contents: str | bytes) -> None:
         """Write contents to a file and queue a webhook update.
 
         Args:
@@ -123,7 +124,7 @@ class BatchedWebHookFileStore(FileStore):
         self._queue_update(path, 'delete', None)
 
     def _queue_update(
-        self, path: str, operation: str, contents: Optional[Union[str, bytes]]
+        self, path: str, operation: str, contents: str | bytes | None
     ) -> None:
         """Queue an update to be sent to the webhook.
 
@@ -159,8 +160,7 @@ class BatchedWebHookFileStore(FileStore):
 
             # Check if we need to send the batch due to size limit
             if self._batch_size >= self.batch_size_limit_bytes:
-                # Submit to executor to avoid blocking
-                EXECUTOR.submit(self._send_batch)
+                self._enqueue_batch_from_lock()
                 return
 
             # Start or reset the timer for sending the batch
@@ -169,52 +169,55 @@ class BatchedWebHookFileStore(FileStore):
                 self._batch_timer = None
 
             timer = threading.Timer(
-                self.batch_timeout_seconds, self._send_batch_from_timer
+                self.batch_timeout_seconds, self._enqueue_batch_from_timer
             )
             timer.daemon = True
             timer.start()
             self._batch_timer = timer
 
-    def _send_batch_from_timer(self) -> None:
+    def _enqueue_batch_from_timer(self) -> None:
         """Send the batch from the timer thread.
         This method is called by the timer and submits the actual sending to the executor.
         """
-        EXECUTOR.submit(self._send_batch)
+        with self._batch_lock:
+            self._enqueue_batch_from_lock()
 
-    def _send_batch(self) -> None:
+    def _enqueue_batch_from_lock(self, background=True) -> None:
+        """
+        Must have lock before calling. Will reset the batch state and send the current one.
+        Uses executor by default, but can perform synchronously by setting background=False
+        """
+        batch_to_send = self._batch
+        self._batch = {}
+        self._batch_size = 0
+        if background:
+            EXECUTOR.submit(self._send_batch, batch_to_send)
+        else:
+            self._send_batch(batch_to_send)
+        # Cancel any pending timer
+        if self._batch_timer is not None:
+            self._batch_timer.cancel()
+            self._batch_timer = None
+
+    def _send_batch(
+        self, batch_to_send: dict[str, tuple[str, str | bytes | None]]
+    ) -> None:
         """Send the current batch of updates to the webhook as a single request.
         This method acquires the batch lock and processes all pending updates in one batch.
         """
-        batch_to_send: dict[str, tuple[str, Optional[Union[str, bytes]]]] = {}
-
-        with self._batch_lock:
-            if not self._batch:
-                return
-
-            # Copy the batch and clear the current one
-            batch_to_send = self._batch.copy()
-            self._batch.clear()
-            self._batch_size = 0
-
-            # Cancel any pending timer
-            if self._batch_timer is not None:
-                self._batch_timer.cancel()
-                self._batch_timer = None
-
         # Process the entire batch in a single request
         if batch_to_send:
             try:
                 self._send_batch_request(batch_to_send)
-            except Exception as e:
-                # Log the error
-                print(f'Error sending webhook batch: {e}')
+            except Exception:
+                logger.exception('Error sending webhook batch')
 
     @tenacity.retry(
         wait=tenacity.wait_fixed(1),
         stop=tenacity.stop_after_attempt(3),
     )
     def _send_batch_request(
-        self, batch: dict[str, tuple[str, Optional[Union[str, bytes]]]]
+        self, batch: dict[str, tuple[str, str | bytes | None]]
     ) -> None:
         """Send a single batch request to the webhook URL with all updates.
 
@@ -260,4 +263,5 @@ class BatchedWebHookFileStore(FileStore):
         """Immediately send any pending updates to the webhook.
         This can be called to ensure all updates are sent before shutting down.
         """
-        self._send_batch()
+        with self._batch_lock:
+            self._enqueue_batch_from_lock(background=False)

tests/unit/test_nested_event_store.py

@@ -372,3 +372,66 @@ class TestNestedEventStore:
             'http://test-api.example.com/events?start_id=0&reverse=False',
             headers={'X-Session-API-Key': 'test-api-key'},
         )
+
+    @patch('httpx.get')
+    def test_search_events_reverse_pagination_multiple_pages(
+        self, mock_get, event_store
+    ):
+        """Ensure reverse pagination works across multiple server pages.
+
+        We emulate the remote /events endpoint by using an in-memory EventStream as the
+        backing store and having httpx.get return paginated JSON responses derived from it.
+        """
+        from urllib.parse import parse_qs, urlparse
+
+        from openhands.events.event import EventSource
+        from openhands.events.observation import NullObservation
+        from openhands.events.serialization.event import event_to_dict
+        from openhands.events.stream import EventStream
+        from openhands.storage.memory import InMemoryFileStore
+
+        # Build a fake server-side store with many events so that server pagination kicks in
+        fs = InMemoryFileStore()
+        server_stream = EventStream('test-session', fs, user_id='test-user')
+        total_events = 50
+        for i in range(total_events):
+            server_stream.add_event(NullObservation(f'e{i}'), EventSource.AGENT)
+
+        def server_side_get(url: str, headers: dict | None = None):
+            # Parse query params like the FastAPI layer would receive
+            parsed = urlparse(url)
+            qs = parse_qs(parsed.query)
+            start_id = int(qs.get('start_id', ['0'])[0])
+            reverse = qs.get('reverse', ['False'])[0] == 'True'
+            end_id = int(qs['end_id'][0]) if 'end_id' in qs else None
+            limit = int(qs.get('limit', ['20'])[0])  # server default = 20
+
+            # Emulate server route logic: request limit+1 to compute has_more
+            events = list(
+                server_stream.search_events(
+                    start_id=start_id, end_id=end_id, reverse=reverse, limit=limit + 1
+                )
+            )
+            has_more = len(events) > limit
+            if has_more:
+                events = events[:limit]
+
+            mock_response = MagicMock()
+            mock_response.status_code = 200
+            mock_response.json.return_value = {
+                'events': [event_to_dict(e) for e in events],
+                'has_more': has_more,
+            }
+            return mock_response
+
+        mock_get.side_effect = server_side_get
+
+        # Execute the nested search in reverse without a client-side limit
+        results = list(event_store.search_events(reverse=True))
+
+        # Verify we received all events in descending order
+        assert len(results) == total_events
+        assert [e.id for e in results] == list(range(total_events - 1, -1, -1))
+
+        # Ensure multiple HTTP calls were made due to pagination
+        assert mock_get.call_count >= 2