Merge pull request #1 from yana1205/toolkit

feat: provide bench runner and agent harness as a toolkit (ported from agent-bench-automation)

Author: yana1205

.dockerignore

@@ -0,0 +1,4 @@
+**/__pycache__
+**/*.egg-info/
+**/.venv
+**/*Dockerfile

.gitignore

@@ -0,0 +1,132 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+.vscode
+
+.DS_Store

.pre-commit-config.yaml

@@ -0,0 +1,21 @@
+# This is an example configuration to enable detect-secrets in the pre-commit hook.
+# Add this file to the root folder of your repository.
+#
+# Read pre-commit hook framework https://pre-commit.com/ for more details about the structure of config yaml file and how git pre-commit would invoke each hook.
+#
+# This line indicates we will use the hook from ibm/detect-secrets to run scan during committing phase.
+repos:
+  - repo: https://github.com/ibm/detect-secrets
+    # If you desire to use a specific version of detect-secrets, you can replace `master` with other git revisions such as branch, tag or commit sha.
+    # You are encouraged to use static refs such as tags, instead of branch name
+    #
+    # Running "pre-commit autoupdate" automatically updates rev to latest tag
+    rev: 0.13.1+ibm.62.dss
+    hooks:
+      - id: detect-secrets # pragma: whitelist secret
+        # Add options for detect-secrets-hook binary. You can run `detect-secrets-hook --help` to list out all possible options.
+        # You may also run `pre-commit run detect-secrets` to preview the scan result.
+        # when "--baseline" without "--use-all-plugins", pre-commit scan with just plugins in baseline file
+        # when "--baseline" with "--use-all-plugins", pre-commit scan with all available plugins
+        # add "--fail-on-unaudited" to fail pre-commit for unaudited potential secrets
+        args: [--baseline, .secrets.baseline, --use-all-plugins]

.secrets.baseline

@@ -0,0 +1,85 @@
+{
+  "exclude": {
+    "files": ".git|.venv|.pytest*|caa-agent|caa-bundle|^.secrets.baseline$",
+    "lines": null
+  },
+  "generated_at": "2025-03-21T08:44:41Z",
+  "plugins_used": [
+    {
+      "name": "AWSKeyDetector"
+    },
+    {
+      "name": "ArtifactoryDetector"
+    },
+    {
+      "name": "AzureStorageKeyDetector"
+    },
+    {
+      "base64_limit": 4.5,
+      "name": "Base64HighEntropyString"
+    },
+    {
+      "name": "BasicAuthDetector"
+    },
+    {
+      "name": "BoxDetector"
+    },
+    {
+      "name": "CloudantDetector"
+    },
+    {
+      "ghe_instance": "github.ibm.com",
+      "name": "GheDetector"
+    },
+    {
+      "name": "GitHubTokenDetector"
+    },
+    {
+      "hex_limit": 3,
+      "name": "HexHighEntropyString"
+    },
+    {
+      "name": "IbmCloudIamDetector"
+    },
+    {
+      "name": "IbmCosHmacDetector"
+    },
+    {
+      "name": "JwtTokenDetector"
+    },
+    {
+      "keyword_exclude": null,
+      "name": "KeywordDetector"
+    },
+    {
+      "name": "MailchimpDetector"
+    },
+    {
+      "name": "NpmDetector"
+    },
+    {
+      "name": "PrivateKeyDetector"
+    },
+    {
+      "name": "SlackDetector"
+    },
+    {
+      "name": "SoftlayerDetector"
+    },
+    {
+      "name": "SquareOAuthDetector"
+    },
+    {
+      "name": "StripeDetector"
+    },
+    {
+      "name": "TwilioKeyDetector"
+    }
+  ],
+  "results": {},
+  "version": "0.13.1+ibm.62.dss",
+  "word_list": {
+    "file": null,
+    "hash": null
+  }
+}

.whitesource

@@ -0,0 +1,3 @@
+{
+  "settingsInheritedFrom": "whitesource-config/whitesource-config@master"
+}

Makefile

@@ -0,0 +1,20 @@
+
+.PHONY: test
+test:
+	@echo "Running Unit Tests"
+	@pytest tests
+
+.PHONY: format
+format:
+	python -m black .
+
+# Direct dependency is not allowed for Pypi packaging even if the dependant module is defined as extra dependencies. 
+# Workaround: Move to manual installation by make
+.PHONY: install-detect-descret
+install-detect-descret:
+	python -m pip install detect-secrets@git+https://github.com/ibm/detect-secrets.git@master#egg=detect-secrets
+
+.PHONY: clean
+clean:
+	@rm -rf build *.egg-info dist
+	python -m pyclean -v .

README.md

@@ -1,2 +1,32 @@
-# ITBench-Tools
-Code repository for tools as part of ITBench
+# IT-Bench Tools
+
+This repository provides a toolkit for [ITBench](https://github.com/IBM/itbench), including the containerized components used to run and evaluate agents.
+
+## 🎞️ Components
+
+- **bench-runner**: Executes benchmark scenarios.
+- **agent-harness**: Wraps agents for interaction with IT Bench Service.
+
+## 🛠️ Build and Push (Multi-Arch)
+
+```bash
+bench_runner_name="icr.io/agent-bench/bench-runner-base:0.0.1"
+agent_harness_name="icr.io/agent-bench/agent-harness-base:0.0.1"
+
+# Build and push bench-runner base image
+docker buildx build --platform linux/amd64,linux/arm64 \
+  -f ./docker/bench-runner/Dockerfile \
+  -t ${bench_runner_name} \
+  . --push
+
+# Build and push agent-harness base image
+docker buildx build --platform linux/amd64,linux/arm64 \
+  -f ./docker/agent-harness/Dockerfile \
+  -t ${agent_harness_name} \
+  . --push
+```
+
+## 📝 Notes
+
+- Make sure `docker buildx` is installed and configured with a builder that supports multi-platform builds.
+- You need to be logged in to the container registry (`icr.io`) before pushing.

docker/agent-harness/Dockerfile

@@ -0,0 +1,15 @@
+FROM python:3.11.10-slim
+
+RUN apt update -y && apt install -y curl gnupg2
+RUN mkdir /etc/agent-benchmark
+COPY itbench_tools /etc/agent-benchmark/itbench_tools
+COPY pyproject.toml /etc/agent-benchmark/pyproject.toml
+COPY docker/agent-harness/entrypoint.sh /etc/entrypoint.sh
+RUN chmod +x /etc/entrypoint.sh
+RUN pip install --upgrade setuptools==70.0.0
+RUN pip install -e /etc/agent-benchmark --no-cache-dir
+RUN ln -sf /bin/bash /bin/sh
+
+WORKDIR /etc/agent-benchmark
+
+ENTRYPOINT ["/etc/entrypoint.sh"]

docker/agent-harness/entrypoint.sh

@@ -0,0 +1,28 @@
+#!/bin/bash
+
+cd /etc/agent-benchmark
+
+port="443"
+root_path="/bench-server"
+benchmark_timeout="300"
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --host) host="$2"; shift 2 ;;
+    --port) port="$2"; shift 2 ;;
+    --root_path) runner_id="$2"; shift 2 ;;
+    --benchmark_timeout) token="$2"; shift 2 ;;
+    *) echo "Unknown option: $1"; exit 1 ;;
+  esac
+done
+
+python itbench_tools/agent_harness/main.py \
+  --agent_directory /etc/ciso-agent \
+  -i /tmp/agent-manifest.json \
+  -c /etc/ciso-agent/agent-harness.yaml \
+  --host $host \
+  --port $port \
+  --root_path $root_path \
+  --ssl \
+  --benchmark_timeout $benchmark_timeout \
+  --single_run

docker/agent-harness/sre_agent_harness/Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.12-slim
+
+WORKDIR /app
+
+RUN apt update -y && apt install -y curl gnupg2 jq
+RUN mkdir /app/agent-benchmark
+COPY itbench_tools /app/agent-benchmark/itbench_tools
+COPY pyproject.toml /app/agent-benchmark/pyproject.toml
+RUN pip install -e /app/agent-benchmark --no-cache-dir
+RUN ln -sf /bin/bash /bin/sh
+
+WORKDIR /app/agent-benchmark