Fix issue #5234: [Bug]: [Resolver] Error when parsing the JSON response on success

.github/workflows/eval-runner.yml

@@ -1,4 +1,4 @@
-name: Run SWE-Bench Evaluation
+name: Run Evaluation
 
 on:
   pull_request:
@@ -58,6 +58,24 @@ jobs:
           echo "api_key = \"$DEEPSEEK_API_KEY\"" >> config.toml
           echo "temperature = 0.0" >> config.toml
 
+      - name: Run integration test evaluation
+        env:
+          ALLHANDS_API_KEY: ${{ secrets.ALLHANDS_EVAL_RUNTIME_API_KEY }}
+          RUNTIME: remote
+          SANDBOX_REMOTE_RUNTIME_API_URL: https://runtime.eval.all-hands.dev
+          EVAL_DOCKER_IMAGE_PREFIX: us-central1-docker.pkg.dev/evaluation-092424/swe-bench-images
+
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' $N_PROCESSES
+
+          # get evaluation report
+          REPORT_FILE=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/deepseek-chat_maxiter_10_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE: $REPORT_FILE"
+          echo "INTEGRATION_TEST_REPORT<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
       - name: Run SWE-Bench evaluation
         env:
           ALLHANDS_API_KEY: ${{ secrets.ALLHANDS_EVAL_RUNTIME_API_KEY }}
@@ -125,6 +143,9 @@ jobs:
               **SWE-Bench Evaluation Report**
               ${{ env.SWEBENCH_REPORT }}
               ---
+              **Integration Tests Evaluation Report**
+              ${{ env.INTEGRATION_TEST_REPORT }}
+              ---
               You can download the full evaluation outputs [here](${{ env.ARTIFACT_URL }}).
 
       - name: Post to a Slack channel

.github/workflows/fe-unit-tests.yml

@@ -35,9 +35,6 @@ jobs:
       - name: Install dependencies
         working-directory: ./frontend
         run: npm ci
-      - name: Run TypeScript compilation
-        working-directory: ./frontend
-        run: npm run make-i18n && tsc
       - name: Run tests and collect coverage
         working-directory: ./frontend
         run: npm run test:coverage

.github/workflows/ghcr-build.yml

@@ -291,7 +291,7 @@ jobs:
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
           TEST_IN_CI=true \
           RUN_AS_OPENHANDS=false \
-          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py
+          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4
         env:
@@ -368,7 +368,7 @@ jobs:
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
           TEST_IN_CI=true \
           RUN_AS_OPENHANDS=true \
-          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime --ignore=tests/runtime/test_browsergym_envs.py
+          poetry run pytest -n 3 -raRs --reruns 2 --reruns-delay 5 --cov=openhands --cov-report=xml -s ./tests/runtime
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4
         env:

.github/workflows/integration-runner.yml

@@ -1,158 +0,0 @@
-name: Run Integration Tests
-
-on:
-  pull_request:
-    types: [labeled]
-  workflow_dispatch:
-    inputs:
-      reason:
-        description: 'Reason for manual trigger'
-        required: true
-        default: ''
-  schedule:
-    - cron: '30 22 * * *'  # Runs at 10:30pm UTC every day
-
-env:
-  N_PROCESSES: 10 # Global configuration for number of parallel processes for evaluation
-
-jobs:
-  run-integration-tests:
-    if: github.event.label.name == 'integration-test' || github.event_name == 'workflow_dispatch' || github.event_name == 'schedule'
-    runs-on: ubuntu-latest
-    permissions:
-      contents: "read"
-      id-token: "write"
-      pull-requests: "write"
-      issues: "write"
-    strategy:
-      matrix:
-        python-version: ["3.12"]
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-          cache: "poetry"
-
-      - name: Comment on PR if 'integration-test' label is present
-        if: github.event_name == 'pull_request' && github.event.label.name == 'integration-test'
-        uses: KeisukeYamashita/create-comment@v1
-        with:
-          unique: false
-          comment: |
-            Hi! I started running the integration tests on your PR. You will receive a comment with the results shortly.
-
-      - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation,llama-index
-
-      - name: Configure config.toml for testing with Haiku
-        env:
-          LLM_MODEL: "litellm_proxy/claude-3-5-haiku-20241022"
-          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
-          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-        run: |
-          echo "[llm.eval]" > config.toml
-          echo "model = \"$LLM_MODEL\"" >> config.toml
-          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
-          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
-          echo "temperature = 0.0" >> config.toml
-
-      - name: Build environment
-        run: make build
-
-      - name: Run integration test evaluation for Haiku
-        env:
-          SANDBOX_FORCE_REBUILD_RUNTIME: True
-        run: |
-          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' $N_PROCESSES '' 'haiku_run'
-
-          # get integration tests report
-          REPORT_FILE_HAIKU=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/*haiku*_maxiter_10_N* -name "report.md" -type f | head -n 1)
-          echo "REPORT_FILE: $REPORT_FILE_HAIKU"
-          echo "INTEGRATION_TEST_REPORT_HAIKU<<EOF" >> $GITHUB_ENV
-          cat $REPORT_FILE_HAIKU >> $GITHUB_ENV
-          echo >> $GITHUB_ENV
-          echo "EOF" >> $GITHUB_ENV
-
-      - name: Wait a little bit
-        run: sleep 10
-
-      - name: Configure config.toml for testing with DeepSeek
-        env:
-          LLM_MODEL: "litellm_proxy/deepseek-chat"
-          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
-          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-        run: |
-          echo "[llm.eval]" > config.toml
-          echo "model = \"$LLM_MODEL\"" >> config.toml
-          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
-          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
-          echo "temperature = 0.0" >> config.toml
-
-      - name: Run integration test evaluation for DeepSeek
-        env:
-          SANDBOX_FORCE_REBUILD_RUNTIME: True
-        run: |
-          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' $N_PROCESSES '' 'deepseek_run'
-
-          # get integration tests report
-          REPORT_FILE_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/deepseek*_maxiter_10_N* -name "report.md" -type f | head -n 1)
-          echo "REPORT_FILE: $REPORT_FILE_DEEPSEEK"
-          echo "INTEGRATION_TEST_REPORT_DEEPSEEK<<EOF" >> $GITHUB_ENV
-          cat $REPORT_FILE_DEEPSEEK >> $GITHUB_ENV
-          echo >> $GITHUB_ENV
-          echo "EOF" >> $GITHUB_ENV
-
-      - name: Create archive of evaluation outputs
-        run: |
-          TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
-          cd evaluation/evaluation_outputs/outputs  # Change to the outputs directory
-          tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/*  # Only include the actual result directories
-
-      - name: Upload evaluation results as artifact
-        uses: actions/upload-artifact@v4
-        id: upload_results_artifact
-        with:
-          name: integration-test-outputs-${{ github.run_id }}-${{ github.run_attempt }}
-          path: integration_tests_*.tar.gz
-
-      - name: Get artifact URLs
-        run: |
-          echo "ARTIFACT_URL=${{ steps.upload_results_artifact.outputs.artifact-url }}" >> $GITHUB_ENV
-
-      - name: Set timestamp and trigger reason
-        run: |
-          echo "TIMESTAMP=$(date +'%Y-%m-%d-%H-%M')" >> $GITHUB_ENV
-          if [[ "${{ github.event_name }}" == "pull_request" ]]; then
-            echo "TRIGGER_REASON=pr-${{ github.event.pull_request.number }}" >> $GITHUB_ENV
-          elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
-            echo "TRIGGER_REASON=manual-${{ github.event.inputs.reason }}" >> $GITHUB_ENV
-          else
-            echo "TRIGGER_REASON=nightly-scheduled" >> $GITHUB_ENV
-          fi
-
-      - name: Comment with results and artifact link
-        id: create_comment
-        uses: KeisukeYamashita/create-comment@v1
-        with:
-          # if triggered by PR, use PR number, otherwise use 5318 as fallback issue number for manual triggers
-          number: ${{ github.event_name == 'pull_request' && github.event.pull_request.number || 5318 }}
-          unique: false
-          comment: |
-              Trigger by: ${{ github.event_name == 'pull_request' && format('Pull Request (integration-test label on PR #{0})', github.event.pull_request.number) || (github.event_name == 'workflow_dispatch' && format('Manual Trigger: {0}', github.event.inputs.reason)) || 'Nightly Scheduled Run' }}
-              Commit: ${{ github.sha }}
-              **Integration Tests Report (Haiku)**
-              Haiku LLM Test Results:
-              ${{ env.INTEGRATION_TEST_REPORT_HAIKU }}
-              ---
-              **Integration Tests Report (DeepSeek)**
-              DeepSeek LLM Test Results:
-              ${{ env.INTEGRATION_TEST_REPORT_DEEPSEEK }}
-              ---
-              Download testing outputs (includes both Haiku and DeepSeek results): [Download](${{ steps.upload_results_artifact.outputs.artifact-url }})

.github/workflows/lint-fix.yml

@@ -5,10 +5,9 @@ on:
     types: [labeled]
 
 jobs:
-  # Frontend lint fixes
-  lint-fix-frontend:
+  lint-fix:
     if: github.event.label.name == 'lint-fix'
-    name: Fix frontend linting issues
+    name: Fix linting issues
     runs-on: ubuntu-latest
     permissions:
       contents: write
@@ -21,6 +20,7 @@ jobs:
           fetch-depth: 0
           token: ${{ secrets.GITHUB_TOKEN }}
 
+      # Frontend lint fixes
       - name: Install Node.js 20
         uses: actions/setup-node@v4
         with:
@@ -34,36 +34,7 @@ jobs:
           cd frontend
           npm run lint:fix
 
-      # Commit and push changes if any
-      - name: Check for changes
-        id: git-check
-        run: |
-          git diff --quiet || echo "changes=true" >> $GITHUB_OUTPUT
-      - name: Commit and push if there are changes
-        if: steps.git-check.outputs.changes == 'true'
-        run: |
-          git config --local user.email "openhands@all-hands.dev"
-          git config --local user.name "OpenHands Bot"
-          git add -A
-          git commit -m "🤖 Auto-fix frontend linting issues"
-          git push
-
-  # Python lint fixes
-  lint-fix-python:
-    if: github.event.label.name == 'lint-fix'
-    name: Fix Python linting issues
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-      pull-requests: write
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ github.head_ref }}
-          repository: ${{ github.event.pull_request.head.repo.full_name }}
-          fetch-depth: 0
-          token: ${{ secrets.GITHUB_TOKEN }}
-
+      # Python lint fixes
       - name: Set up python
         uses: actions/setup-python@v5
         with:
@@ -87,5 +58,5 @@ jobs:
           git config --local user.email "openhands@all-hands.dev"
           git config --local user.name "OpenHands Bot"
           git add -A
-          git commit -m "🤖 Auto-fix Python linting issues"
+          git commit -m "🤖 Auto-fix linting issues"
           git push

.github/workflows/lint.yml

@@ -30,11 +30,10 @@ jobs:
         run: |
           cd frontend
           npm install --frozen-lockfile
-      - name: Lint and TypeScript compilation
+      - name: Lint
         run: |
           cd frontend
           npm run lint
-          npm run make-i18n && tsc
 
   # Run lint on the python code
   lint-python:

.github/workflows/openhands-resolver.yml

@@ -16,11 +16,6 @@ on:
         type: string
         default: "main"
         description: "Target branch to pull and create PR against"
-      base_container_image:
-        required: false
-        type: string
-        default: ""
-        description: "Custom sandbox env"
     secrets:
       LLM_MODEL:
         required: true
@@ -144,7 +139,6 @@ jobs:
 
           echo "MAX_ITERATIONS=${{ inputs.max_iterations || 50 }}" >> $GITHUB_ENV
           echo "SANDBOX_ENV_GITHUB_TOKEN=${{ secrets.GITHUB_TOKEN }}" >> $GITHUB_ENV
-          echo "SANDBOX_ENV_BASE_CONTAINER_IMAGE=${{ inputs.base_container_image }}" >> $GITHUB_ENV
 
           # Set branch variables
           echo "TARGET_BRANCH=${{ inputs.target_branch }}" >> $GITHUB_ENV

CONTRIBUTING.md

@@ -21,14 +21,14 @@ There are many ways that you can contribute:
 
 1. **Download and use** OpenHands, and send [issues](https://github.com/All-Hands-AI/OpenHands/issues) when you encounter something that isn't working or a feature that you'd like to see.
 2. **Send feedback** after each session by [clicking the thumbs-up thumbs-down buttons](https://docs.all-hands.dev/modules/usage/feedback), so we can see where things are working and failing, and also build an open dataset for training code agents.
-3. **Improve the Codebase** by sending [PRs](#sending-pull-requests-to-openhands) (see details below). In particular, we have some [good first issues](https://github.com/All-Hands-AI/OpenHands/labels/good%20first%20issue) that may be ones to start on.
+3. **Improve the Codebase** by sending PRs (see details below). In particular, we have some [good first issues](https://github.com/All-Hands-AI/OpenHands/labels/good%20first%20issue) that may be ones to start on.
 
 ## What can I build?
 Here are a few ways you can help improve the codebase.
 
 #### UI/UX
 We're always looking to improve the look and feel of the application. If you've got a small fix
-for something that's bugging you, feel free to open up a PR that changes the [`./frontend`](./frontend) directory.
+for something that's bugging you, feel free to open up a PR that changes the `./frontend` directory.
 
 If you're looking to make a bigger change, add a new UI element, or significantly alter the style
 of the application, please open an issue first, or better, join the #frontend channel in our Slack
@@ -46,7 +46,7 @@ We use the [SWE-bench](https://www.swebench.com/) benchmark to test our agent. Y
 channel in Slack to learn more.
 
 #### Adding a new agent
-You may want to experiment with building new types of agents. You can add an agent to [`openhands/agenthub`](./openhands/agenthub)
+You may want to experiment with building new types of agents. You can add an agent to `openhands/agenthub`
 to help expand the capabilities of OpenHands.
 
 #### Adding a new runtime
@@ -57,8 +57,8 @@ If you work for a company that provides a cloud-based runtime, you could help us
 by implementing the [interface specified here](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/base.py).
 
 #### Testing
-When you write code, it is also good to write tests. Please navigate to the [`./tests`](./tests) folder to see existing test suites.
-At the moment, we have two kinds of tests: [`unit`](./tests/unit) and [`integration`](./evaluation/integration_tests). Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
+When you write code, it is also good to write tests. Please navigate to the `tests` folder to see existing test suites.
+At the moment, we have two kinds of tests: `unit` and `integration`. Please refer to the README for each test suite. These tests also run on GitHub's continuous integration to ensure quality of the project.
 
 ## Sending Pull Requests to OpenHands
 
@@ -103,7 +103,7 @@ Further, if you see an issue you like, please leave a "thumbs-up" or a comment,
 
 ### Making Pull Requests
 
-We're generally happy to consider all [PRs](https://github.com/All-Hands-AI/OpenHands/pulls), with the evaluation process varying based on the type of change:
+We're generally happy to consider all PRs, with the evaluation process varying based on the type of change:
 
 #### For Small Improvements
 

Makefile

@@ -133,7 +133,7 @@ install-python-dependencies:
 		export HNSWLIB_NO_NATIVE=1; \
 		poetry run pip install chroma-hnswlib; \
 	fi
-	@poetry install --without llama-index,evaluation
+	@poetry install --without llama-index
 	@if [ -f "/etc/manjaro-release" ]; then \
 		echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
 		poetry run pip install playwright; \

README.md

@@ -12,7 +12,7 @@
   <a href="https://codecov.io/github/All-Hands-AI/OpenHands?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/All-Hands-AI/OpenHands?style=for-the-badge&color=blue"></a>
   <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/github/license/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="MIT License"></a>
   <br/>
-  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2vbfigwev-G03twSpXaErwzYVD4CFiBg"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
+  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2tom0er4l-JeNUGHt_AxpEfIBstbLPiw"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
   <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
   <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="Credits"></a>
   <br/>
@@ -82,7 +82,7 @@ troubleshooting resources, and advanced configuration options.
 OpenHands is a community-driven project, and we welcome contributions from everyone. We do most of our communication
 through Slack, so this is the best place to start, but we also are happy to have you contact us on Discord or Github:
 
-- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-2vbfigwev-G03twSpXaErwzYVD4CFiBg) - Here we talk about research, architecture, and future development.
+- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-2tom0er4l-JeNUGHt_AxpEfIBstbLPiw) - Here we talk about research, architecture, and future development.
 - [Join our Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
 - [Read or post Github Issues](https://github.com/All-Hands-AI/OpenHands/issues) - Check out the issues we're working on, or add your own ideas.
 

containers/dev/Dockerfile

@@ -5,24 +5,24 @@ FROM ubuntu:22.04 AS dind
 
 # https://docs.docker.com/engine/install/ubuntu/
 RUN apt-get update && apt-get install -y \
-        ca-certificates \
-        curl \
-        && install -m 0755 -d /etc/apt/keyrings \
-        && curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc \
-        && chmod a+r /etc/apt/keyrings/docker.asc \
-        && echo \
-                "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
-                $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null
+	ca-certificates \
+	curl \
+	&& install -m 0755 -d /etc/apt/keyrings \
+	&& curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc \
+	&& chmod a+r /etc/apt/keyrings/docker.asc \
+	&& echo \
+		"deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
+		$(. /etc/os-release && echo "$VERSION_CODENAME") stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null
 
 RUN apt-get update && apt-get install -y \
-        docker-ce \
-        docker-ce-cli \
-        containerd.io \
-        docker-buildx-plugin \
-        docker-compose-plugin \
-        && rm -rf /var/lib/apt/lists/* \
-        && apt-get clean \
-        && apt-get autoremove -y
+	docker-ce \
+	docker-ce-cli \
+	containerd.io \
+	docker-buildx-plugin \
+	docker-compose-plugin \
+	&& rm -rf /var/lib/apt/lists/* \
+	&& apt-get clean \
+	&& apt-get autoremove -y
 
 ###
 FROM dind AS openhands
@@ -31,25 +31,25 @@ ENV DEBIAN_FRONTEND=noninteractive
 
 #
 RUN apt-get update && apt-get install -y \
-        bash \
+	bash \
     build-essential \
     curl \
-        git \
-        git-lfs \
-        software-properties-common \
-        make \
+	git \
+	git-lfs \
+	software-properties-common \
+	make \
     netcat \
     sudo \
-        wget \
-        && rm -rf /var/lib/apt/lists/* \
-        && apt-get clean \
-        && apt-get autoremove -y
+	wget \
+	&& rm -rf /var/lib/apt/lists/* \
+	&& apt-get clean \
+	&& apt-get autoremove -y
 
 # https://github.com/cli/cli/blob/trunk/docs/install_linux.md
 RUN curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg | dd of=/usr/share/keyrings/githubcli-archive-keyring.gpg \
-        && chmod go+r /usr/share/keyrings/githubcli-archive-keyring.gpg \
-        && echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" | tee /etc/apt/sources.list.d/github-cli.list > /dev/null \
-        && apt-get update && apt-get -y install \
+	&& chmod go+r /usr/share/keyrings/githubcli-archive-keyring.gpg \
+	&& echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" | tee /etc/apt/sources.list.d/github-cli.list > /dev/null \
+	&& apt-get update && apt-get -y install \
     gh \
   && rm -rf /var/lib/apt/lists/* \
   && apt-get clean \
@@ -92,17 +92,17 @@ EOF
 FROM openhands AS dev
 
 RUN apt-get update && apt-get install -y \
-        dnsutils \
-        file \
-        iproute2 \
-        jq \
-        lsof \
-        ripgrep \
-        silversearcher-ag \
-        vim \
-        && rm -rf /var/lib/apt/lists/* \
-        && apt-get clean \
-        && apt-get autoremove -y
+	dnsutils \
+	file \
+	iproute2 \
+	jq \
+	lsof \
+	ripgrep \
+	silversearcher-ag \
+	vim \
+	&& rm -rf /var/lib/apt/lists/* \
+	&& apt-get clean \
+	&& apt-get autoremove -y
 
 WORKDIR /app
 

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/about.md

@@ -27,7 +27,7 @@ Pour plus de détails, veuillez consulter [ce document](https://github.com/All-H
 
 Nous avons à la fois un espace de travail Slack pour la collaboration sur la construction d'OpenHands et un serveur Discord pour discuter de tout ce qui est lié, par exemple, à ce projet, LLM, agent, etc.
 
-- [Espace de travail Slack](https://join.slack.com/t/openhands-ai/shared_invite/zt-2vbfigwev-G03twSpXaErwzYVD4CFiBg)
+- [Espace de travail Slack](https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA)
 - [Serveur Discord](https://discord.gg/ESHStjSjD4)
 
 Si vous souhaitez contribuer, n'hésitez pas à rejoindre notre communauté. Simplifions ensemble l'ingénierie logicielle !

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/about.md

@@ -27,7 +27,7 @@ OpenHands 是一个社区驱动的项目，我们欢迎每个人的贡献。无
 
 我们有 Slack 工作区用于协作构建 OpenHands，也有 Discord 服务器用于讨论任何相关的内容，例如此项目、大语言模型、代理等。
 
-- [Slack 工作区](https://join.slack.com/t/openhands-ai/shared_invite/zt-2vbfigwev-G03twSpXaErwzYVD4CFiBg)
+- [Slack 工作区](https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA)
 - [Discord 服务器](https://discord.gg/ESHStjSjD4)
 
 如果你想做出贡献，欢迎加入我们的社区。让我们一起简化软件工程！

docs/modules/usage/configuration-options.md

@@ -1,12 +1,13 @@
+---
+id: configuration-options
+title: Configuration Options
+sidebar_label: Configuration Options
+---
+
 # Configuration Options
 
 This guide details all configuration options available for OpenHands, helping you customize its behavior and integrate it with other services.
 
-:::note
-If you are running in [GUI Mode](https://docs.all-hands.dev/modules/usage/how-to/gui-mode), the settings available in the Settings UI will always
-take precedence.
-:::
-
 ---
 
 # Table of Contents
@@ -47,10 +48,10 @@ take precedence.
    - [Confirmation Mode](#confirmation-mode)
    - [Security Analyzer](#security-analyzer)
 
+
 ---
 
 ## Core Configuration
-
 The core configuration options are defined in the `[core]` section of the `config.toml` file.
 
 **API Keys**
@@ -177,11 +178,8 @@ The core configuration options are defined in the `[core]` section of the `confi
   - Description: JWT secret for authentication. Please set it to your own value.
 
 ## LLM Configuration
-
 The LLM (Large Language Model) configuration options are defined in the `[llm]` section of the `config.toml` file.
 
-To use these with the docker command, pass in `-e LLM_<option>`. Example: `-e LLM_NUM_RETRIES`.
-
 **AWS Credentials**
 - `aws_access_key_id`
   - Type: `str`
@@ -326,7 +324,6 @@ To use these with the docker command, pass in `-e LLM_<option>`. Example: `-e LL
   - Description: If model is vision capable, this option allows to disable image processing (useful for cost reduction)
 
 ## Agent Configuration
-
 The agent configuration options are defined in the `[agent]` and `[agent.<agent_name>]` sections of the `config.toml` file.
 
 **Microagent Configuration**
@@ -385,11 +382,8 @@ The agent configuration options are defined in the `[agent]` and `[agent.<agent_
   - Description: A list of microagents to disable
 
 ## Sandbox Configuration
-
 The sandbox configuration options are defined in the `[sandbox]` section of the `config.toml` file.
 
-To use these with the docker command, pass in `-e SANDBOX_<option>`. Example: `-e SANDBOX_TIMEOUT`.
-
 **Execution**
 - `timeout`
   - Type: `int`
@@ -442,11 +436,8 @@ To use these with the docker command, pass in `-e SANDBOX_<option>`. Example: `-
   - Description: BrowserGym environment to use for evaluation
 
 ## Security Configuration
-
 The security configuration options are defined in the `[security]` section of the `config.toml` file.
 
-To use these with the docker command, pass in `-e SECURITY_<option>`. Example: `-e SECURITY_CONFIRMATION_MODE`.
-
 **Confirmation Mode**
 - `confirmation_mode`
   - Type: `bool`
@@ -459,6 +450,7 @@ To use these with the docker command, pass in `-e SECURITY_<option>`. Example: `
   - Default: `""`
   - Description: The security analyzer to use
 
+
 ---
 
 > **Note**: Adjust configurations carefully, especially for memory, security, and network-related settings to ensure optimal performance and security.

docs/modules/usage/how-to/github-action.md

@@ -37,15 +37,12 @@ the [README for the OpenHands Resolver](https://github.com/All-Hands-AI/OpenHand
 
 You can provide custom directions for OpenHands by following the [README for the resolver](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/resolver/README.md#providing-custom-instructions).
 
-### Custom configurations
+### Configure custom macro
 
-Github resolver will automatically check for valid [repository secrets](https://docs.github.com/en/actions/security-for-github-actions/security-guides/using-secrets-in-github-actions?tool=webui#creating-secrets-for-a-repository) or [repository variables](https://docs.github.com/en/actions/writing-workflows/choosing-what-your-workflow-does/store-information-in-variables#creating-configuration-variables-for-a-repository) to customize its behavior. The customization options you can set are:
+To customize the default macro (`@openhands-agent`):
 
-| **Attribute name**               | **Type** | **Purpose**                                                                                         | **Example**                                     |
-| -------------------------------- | -------- | --------------------------------------------------------------------------------------------------- | ----------------------------------------------- |
-| `OPENHANDS_MAX_ITER`             | Variable | Set max limit for agent iterations                                                                  | `OPENHANDS_MAX_ITER=10`                         |
-| `OPENHANDS_MACRO`                | Variable | Customize default macro for invoking the resolver                                                   | `OPENHANDS_MACRO=@resolveit`                    |
-| `OPENHANDS_BASE_CONTAINER_IMAGE` | Variable | Custom Sandbox ([learn more](https://docs.all-hands.dev/modules/usage/how-to/custom-sandbox-guide)) | `OPENHANDS_BASE_CONTAINER_IMAGE="custom_image"` |
+1. [Create a repository variable](https://docs.github.com/en/actions/writing-workflows/choosing-what-your-workflow-does/store-information-in-variables#creating-configuration-variables-for-a-repository) named `OPENHANDS_MACRO`
+2. Assign the variable a custom value
 
 ## Writing Effective .openhands_instructions Files
 
@@ -58,7 +55,6 @@ The `.openhands_instructions` file is a file that you can put in the root direct
 2. **Repository Structure**: Explain the key directories and their purposes, especially highlighting where different types of code (e.g., frontend, backend) are located.
 
 3. **Development Workflows**: Document the essential commands for:
-
    - Building and setting up the project
    - Running tests
    - Linting and code quality checks
@@ -73,29 +69,24 @@ The `.openhands_instructions` file is a file that you can put in the root direct
 
 ```markdown
 # Repository Overview
-
 [Brief description of the project]
 
 ## General Setup
-
 - Main build command
 - Development environment setup
 - Pre-commit checks
 
 ## Backend
-
 - Location and structure
 - Testing instructions
 - Environment requirements
 
 ## Frontend
-
 - Setup prerequisites
 - Build and test commands
 - Environment variables
 
 ## Additional Guidelines
-
 - Code style requirements
 - Special considerations
 - Common workflows

docs/package-lock.json

@@ -24,7 +24,7 @@
         "@docusaurus/module-type-aliases": "^3.5.1",
         "@docusaurus/tsconfig": "^3.6.3",
         "@docusaurus/types": "^3.5.1",
-        "typescript": "~5.7.2"
+        "typescript": "~5.6.3"
       },
       "engines": {
         "node": ">=18.0"
@@ -16985,10 +16985,9 @@
       }
     },
     "node_modules/typescript": {
-      "version": "5.7.2",
-      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.7.2.tgz",
-      "integrity": "sha512-i5t66RHxDvVN40HfDd1PsEThGNnlMCMT3jMUuoh9/0TaqWevNontacunWyN02LA9/fIbEWlcHZcgTKb9QoaLfg==",
-      "license": "Apache-2.0",
+      "version": "5.6.3",
+      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.6.3.tgz",
+      "integrity": "sha512-hjcS1mhfuyi4WW8IWtjP7brDrG2cuDZukyrYrSauoXGNgx0S7zceP07adYkJycEr56BOUTNPzbInooiN3fn1qw==",
       "bin": {
         "tsc": "bin/tsc",
         "tsserver": "bin/tsserver"

docs/package.json

@@ -31,7 +31,7 @@
     "@docusaurus/module-type-aliases": "^3.5.1",
     "@docusaurus/tsconfig": "^3.6.3",
     "@docusaurus/types": "^3.5.1",
-    "typescript": "~5.7.2"
+    "typescript": "~5.6.3"
   },
   "browserslist": {
     "production": [

docs/sidebars.ts

@@ -44,6 +44,17 @@ const sidebars: SidebarsConfig = {
         },
       ],
     },
+    {
+      type: 'category',
+      label: 'Configuration Options',
+      items: [
+        {
+          type: 'doc',
+          label: 'Overview',
+          id: 'usage/configuration-options',
+        },
+      ],
+    },
     {
       type: 'category',
       label: 'Advanced Configuration',
@@ -100,11 +111,6 @@ const sidebars: SidebarsConfig = {
           label: 'Runtime Configuration',
           id: 'usage/runtimes',
         },
-        {
-          type: 'doc',
-          label: 'Configuration Options',
-          id: 'usage/configuration-options',
-        },
         {
           type: 'doc',
           label: 'Custom Sandbox',

docs/src/components/CustomFooter.tsx

@@ -8,7 +8,7 @@ function CustomFooter() {
     <footer className="custom-footer">
       <div className="footer-content">
         <div className="footer-icons">
-          <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2vbfigwev-G03twSpXaErwzYVD4CFiBg" target="_blank" rel="noopener noreferrer">
+          <a href="https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA" target="_blank" rel="noopener noreferrer">
             <FaSlack />
           </a>
           <a href="https://discord.gg/ESHStjSjD4" target="_blank" rel="noopener noreferrer">

docs/src/components/HomepageHeader/HomepageHeader.tsx

@@ -23,7 +23,7 @@ export function HomepageHeader() {
           <a href="https://codecov.io/github/All-Hands-AI/OpenHands?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" /></a>
           <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/github/license/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="MIT License" /></a>
           <br/>
-          <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2vbfigwev-G03twSpXaErwzYVD4CFiBg"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community" /></a>
+          <a href="https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community" /></a>
           <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community" /></a>
           <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="Credits" /></a>
           <br/>

evaluation/README.md

@@ -6,9 +6,9 @@ This folder contains code and resources to run experiments and evaluations.
 
 ### Setup
 
-Before starting evaluation, follow the instructions [here](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) to setup your local development environment and LLM.
+Before starting evaluation, follow the instructions here [here](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) to setup your local development environment and LLM.
 
-Once you are done with setup, you can follow the benchmark-specific instructions in each subdirectory of the [evaluation directory](#supported-benchmarks).
+Once you are done with setup, you can follow the benchmark-specific instructions in each subdirectory of the evaluation directory.
 Generally these will involve running `run_infer.py` to perform inference with the agents.
 
 ### Implementing and Evaluating an Agent
@@ -42,7 +42,7 @@ temperature = 0.0
 
 ## Supported Benchmarks
 
-The OpenHands evaluation harness supports a wide variety of benchmarks across [software engineering](#software-engineering), [web browsing](#web-browsing), and [miscellaneous assistance](#misc-assistance) tasks.
+The OpenHands evaluation harness supports a wide variety of benchmarks across software engineering, web browsing, and miscellaneous assistance tasks.
 
 ### Software Engineering
 
@@ -83,7 +83,7 @@ You can start your own fork of [our huggingface evaluation outputs](https://hugg
 
 To learn more about how to integrate your benchmark into OpenHands, check out [tutorial here](https://docs.all-hands.dev/modules/usage/how-to/evaluation-harness). Briefly,
 
-- Each subfolder contains a specific benchmark or experiment. For example, [`evaluation/benchmarks/swe_bench`](./benchmarks/swe_bench) should contain
+- Each subfolder contains a specific benchmark or experiment. For example, `evaluation/benchmarks/swe_bench` should contain
 all the preprocessing/evaluation/analysis scripts.
 - Raw data and experimental records should not be stored within this repo.
 - For model outputs, they should be stored at [this huggingface space](https://huggingface.co/spaces/OpenHands/evaluation) for visualization.

evaluation/benchmarks/EDA/scripts/run_infer.sh

@@ -21,7 +21,7 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 if [ -z "$DATASET" ]; then
   echo "Dataset not specified, use default 'things'"
@@ -34,9 +34,12 @@ if [ -z "$OPENAI_API_KEY" ]; then
   exit 1
 fi
 
+# IMPORTANT: Because Agent's prompt changes fairly often in the rapidly evolving codebase of OpenHands
+# We need to track the version of Agent in the evaluation to make sure results are comparable
+AGENT_VERSION=v$(poetry run python -c "import openhands.agenthub; from openhands.controller.agent import Agent; print(Agent.get_cls('$AGENT').VERSION)")
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 echo "DATASET: $DATASET"
 
@@ -48,7 +51,7 @@ COMMAND="poetry run python evaluation/benchmarks/EDA/run_infer.py \
   --max-iterations 20 \
   --OPENAI_API_KEY $OPENAI_API_KEY \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note ${OPENHANDS_VERSION}_${DATASET}"
+  --eval-note ${AGENT_VERSION}_${DATASET}"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/agent_bench/scripts/run_infer.sh

@@ -20,10 +20,10 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
 COMMAND="export PYTHONPATH=evaluation/benchmarks/agent_bench:\$PYTHONPATH && poetry run python evaluation/benchmarks/agent_bench/run_infer.py \
@@ -31,7 +31,7 @@ COMMAND="export PYTHONPATH=evaluation/benchmarks/agent_bench:\$PYTHONPATH && poe
   --llm-config $MODEL_CONFIG \
   --max-iterations 30 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note $OPENHANDS_VERSION"
+  --eval-note $AGENT_VERSION"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/aider_bench/scripts/run_infer.sh

@@ -21,13 +21,13 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
-EVAL_NOTE=$OPENHANDS_VERSION
+EVAL_NOTE=$AGENT_VERSION
 
 # Default to NOT use unit tests.
 if [ -z "$USE_UNIT_TESTS" ]; then

evaluation/benchmarks/biocoder/scripts/run_infer.sh

@@ -21,10 +21,10 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 echo "DATASET: $DATASET"
 
@@ -33,7 +33,7 @@ COMMAND="poetry run python evaluation/benchmarks/biocoder/run_infer.py \
   --llm-config $MODEL_CONFIG \
   --max-iterations 10 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note ${OPENHANDS_VERSION}_${DATASET}"
+  --eval-note ${AGENT_VERSION}_${DATASET}"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/bird/scripts/run_infer.sh

@@ -20,10 +20,10 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
 COMMAND="poetry run python evaluation/benchmarks/bird/run_infer.py \
@@ -31,7 +31,7 @@ COMMAND="poetry run python evaluation/benchmarks/bird/run_infer.py \
   --llm-config $MODEL_CONFIG \
   --max-iterations 5 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note $OPENHANDS_VERSION" \
+  --eval-note $AGENT_VERSION" \
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/browsing_delegation/scripts/run_infer.sh

@@ -20,13 +20,13 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
-EVAL_NOTE="$OPENHANDS_VERSION"
+EVAL_NOTE="$AGENT_VERSION"
 
 COMMAND="poetry run python evaluation/benchmarks/browsing_delegation/run_infer.py \
   --agent-cls $AGENT \

evaluation/benchmarks/commit0_bench/scripts/run_infer.sh

@@ -61,10 +61,10 @@ echo "USE_INSTANCE_IMAGE: $USE_INSTANCE_IMAGE"
 export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
 echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 echo "DATASET: $DATASET"
 echo "HF SPLIT: $SPLIT"
@@ -75,7 +75,7 @@ if [ -z "$USE_HINT_TEXT" ]; then
   export USE_HINT_TEXT=false
 fi
 echo "USE_HINT_TEXT: $USE_HINT_TEXT"
-EVAL_NOTE="$OPENHANDS_VERSION"
+EVAL_NOTE="$AGENT_VERSION"
 # if not using Hint, add -no-hint to the eval note
 if [ "$USE_HINT_TEXT" = false ]; then
   EVAL_NOTE="$EVAL_NOTE-no-hint"

evaluation/benchmarks/discoverybench/scripts/run_infer.sh

@@ -23,10 +23,10 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
 COMMAND="poetry run python evaluation/benchmarks/discoverybench/run_infer.py \
@@ -35,7 +35,7 @@ COMMAND="poetry run python evaluation/benchmarks/discoverybench/run_infer.py \
   --max-iterations 10 \
   --max-chars 10000000 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note $OPENHANDS_VERSION"
+  --eval-note $AGENT_VERSION"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/gaia/scripts/run_infer.sh

@@ -21,17 +21,17 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 if [ -z "$LEVELS" ]; then
   LEVELS="2023_level1"
   echo "Levels not specified, use default $LEVELS"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 echo "LEVELS: $LEVELS"
 
@@ -42,7 +42,7 @@ COMMAND="poetry run python ./evaluation/benchmarks/gaia/run_infer.py \
   --level $LEVELS \
   --data-split validation \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note ${OPENHANDS_VERSION}_${LEVELS}"
+  --eval-note ${AGENT_VERSION}_${LEVELS}"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/gorilla/scripts/run_infer.sh

@@ -21,7 +21,7 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 if [ -z "$HUBS" ]; then
   HUBS="hf,torch,tf"
@@ -29,7 +29,7 @@ if [ -z "$HUBS" ]; then
 fi
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 echo "HUBS: $HUBS"
 
@@ -40,7 +40,7 @@ COMMAND="poetry run python evaluation/benchmarks/gorilla/run_infer.py \
   --hubs $HUBS \
   --data-split validation \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note ${OPENHANDS_VERSION}_${LEVELS}"
+  --eval-note ${AGENT_VERSION}_${LEVELS}"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/gpqa/scripts/run_infer.sh

@@ -27,10 +27,10 @@ if [ -z "$DATA_SPLIT" ]; then
   DATA_SPLIT="gpqa_diamond"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
 COMMAND="poetry run python evaluation/benchmarks/gpqa/run_infer.py \
@@ -39,7 +39,7 @@ COMMAND="poetry run python evaluation/benchmarks/gpqa/run_infer.py \
   --max-iterations 10 \
   --eval-num-workers $NUM_WORKERS \
   --data-split $DATA_SPLIT \
-  --eval-note $OPENHANDS_VERSION"
+  --eval-note $AGENT_VERSION"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/humanevalfix/scripts/run_infer.sh

@@ -58,10 +58,10 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
 COMMAND="poetry run python evaluation/benchmarks/humanevalfix/run_infer.py \
@@ -69,7 +69,7 @@ COMMAND="poetry run python evaluation/benchmarks/humanevalfix/run_infer.py \
   --llm-config $MODEL_CONFIG \
   --max-iterations 10 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note $OPENHANDS_VERSION"
+  --eval-note $AGENT_VERSION"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/logic_reasoning/scripts/run_infer.sh

@@ -28,10 +28,10 @@ if [ -z "$DATASET" ]; then
   DATASET="ProofWriter"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
 COMMAND="poetry run python evaluation/benchmarks/logic_reasoning/run_infer.py \
@@ -40,7 +40,7 @@ COMMAND="poetry run python evaluation/benchmarks/logic_reasoning/run_infer.py \
   --dataset $DATASET \
   --max-iterations 10 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note $OPENHANDS_VERSION"
+  --eval-note $AGENT_VERSION"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/miniwob/scripts/run_infer.sh

@@ -25,13 +25,13 @@ if [ -z "$AGENT" ]; then
   AGENT="BrowsingAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
-EVAL_NOTE="${OPENHANDS_VERSION}_${NOTE}"
+EVAL_NOTE="${AGENT_VERSION}_${NOTE}"
 
 COMMAND="export PYTHONPATH=evaluation/benchmarks/miniwob:\$PYTHONPATH && poetry run python evaluation/benchmarks/miniwob/run_infer.py \
   --agent-cls $AGENT \

evaluation/benchmarks/mint/scripts/run_infer.sh

@@ -18,10 +18,10 @@ checkout_eval_branch
 # Only 'CodeActAgent' is supported for MINT now
 AGENT="CodeActAgent"
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 
 export PYTHONPATH=$(pwd)
 

evaluation/benchmarks/ml_bench/scripts/run_infer.sh

@@ -26,10 +26,10 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
 COMMAND="poetry run python evaluation/benchmarks/ml_bench/run_infer.py \
@@ -37,7 +37,7 @@ COMMAND="poetry run python evaluation/benchmarks/ml_bench/run_infer.py \
   --llm-config $MODEL_CONFIG \
   --max-iterations 10 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note $OPENHANDS_VERSION"
+  --eval-note $AGENT_VERSION"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/scienceagentbench/scripts/run_infer.sh

@@ -26,10 +26,10 @@ if [ -z "$USE_KNOWLEDGE" ]; then
   USE_KNOWLEDGE=false
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
 COMMAND="poetry run python evaluation/benchmarks/scienceagentbench/run_infer.py \
@@ -38,7 +38,7 @@ COMMAND="poetry run python evaluation/benchmarks/scienceagentbench/run_infer.py
   --use_knowledge $USE_KNOWLEDGE \
   --max-iterations 30 \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note $OPENHANDS_VERSION" \
+  --eval-note $AGENT_VERSION" \
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/swe_bench/scripts/eval/summarize_outputs.py

@@ -1,12 +1,8 @@
 #!/usr/bin/env python3
 import argparse
-import glob
 import json
-import os
 from collections import Counter
 
-import pandas as pd
-
 from openhands.events.serialization import event_from_dict
 from openhands.events.utils import get_pairs_from_events
 
@@ -14,21 +10,25 @@ ERROR_KEYWORDS = [
     'Agent encountered an error while processing the last action',
     'APIError',
     'Action execution failed',
-    'litellm.Timeout: APITimeoutError',
 ]
 
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('output_file', type=str, help='The file to summarize')
+    args = parser.parse_args()
 
-def process_file(file_path):
-    with open(file_path, 'r') as file:
+    with open(args.output_file, 'r') as file:
         lines = file.readlines()
 
     num_lines = len(lines)
     num_error_lines = 0
     num_agent_stuck_in_loop = 0
+
     num_resolved = 0
     num_empty_patch = 0
-    num_unfinished_runs = 0
+
     error_counter = Counter()
+
     main_agent_cost = []
     editor_cost = []
     num_turns = []
@@ -36,11 +36,6 @@ def process_file(file_path):
     for line in lines:
         _d = json.loads(line)
 
-        if 'metrics' not in _d or _d['metrics'] is None:
-            # this is a failed run
-            num_unfinished_runs += 1
-            continue
-
         # Cost
         costs = _d['metrics'].get('costs', [])
         _cur_main_agent_cost = 0
@@ -94,180 +89,30 @@ def process_file(file_path):
                 num_error_lines += 1
                 break
 
-    return {
-        'file_path': file_path,
-        'total_instances': num_lines,
-        'resolved': {
-            'count': num_resolved,
-            'percentage': (num_resolved / num_lines * 100) if num_lines > 0 else 0,
-        },
-        'empty_patches': {
-            'count': num_empty_patch,
-            'percentage': (num_empty_patch / num_lines * 100) if num_lines > 0 else 0,
-        },
-        'unfinished_runs': {
-            'count': num_unfinished_runs,
-            'percentage': (num_unfinished_runs / num_lines * 100)
-            if num_lines > 0
-            else 0,
-        },
-        'errors': {
-            'total': num_error_lines,
-            'percentage': (num_error_lines / num_lines * 100) if num_lines > 0 else 0,
-            'stuck_in_loop': {
-                'count': num_agent_stuck_in_loop,
-                'percentage': (num_agent_stuck_in_loop / num_lines * 100)
-                if num_lines > 0
-                else 0,
-            },
-            'breakdown': {
-                str(error): {
-                    'count': count,
-                    'percentage': (count / num_lines * 100) if num_lines > 0 else 0,
-                }
-                for error, count in error_counter.items()
-            },
-        },
-        'statistics': {
-            'avg_turns': sum(num_turns) / num_lines if num_lines > 0 else 0,
-            'costs': {
-                'main_agent': sum(main_agent_cost) / num_lines if num_lines > 0 else 0,
-                'editor': sum(editor_cost) / num_lines if num_lines > 0 else 0,
-                'total': (sum(main_agent_cost) + sum(editor_cost)) / num_lines
-                if num_lines > 0
-                else 0,
-            },
-        },
-    }
-
-
-def aggregate_directory(input_path) -> pd.DataFrame:
-    # Process all output.jsonl files in subdirectories
-    pattern = os.path.join(input_path, '**/output.jsonl')
-    files = glob.glob(pattern, recursive=True)
-    print(f'Processing {len(files)} files from directory {input_path}')
-
-    # Process each file silently and collect results
-    results = []
-    for file_path in files:
-        try:
-            result = process_file(file_path)
-            results.append(result)
-        except Exception as e:
-            print(f'Error processing {file_path}: {str(e)}')
-            import traceback
-
-            traceback.print_exc()
-            continue
-
-    # Convert results to pandas DataFrame and sort by resolve rate
-    df = pd.DataFrame(results)
-
-    # Extract directory name from file path
-    df['directory'] = df['file_path'].apply(
-        lambda x: os.path.basename(os.path.dirname(x))
+    # print the error counter (with percentage)
+    print(
+        f'Number of resolved: {num_resolved} / {num_lines} ({num_resolved / num_lines * 100:.2f}%)'
+    )
+    print(
+        f'Number of empty patch: {num_empty_patch} / {num_lines} ({num_empty_patch / num_lines * 100:.2f}%)'
+    )
+    print(
+        f'Number of error lines: {num_error_lines} / {num_lines} ({num_error_lines / num_lines * 100:.2f}%)'
+    )
+    print(
+        f'Number of agent stuck in loop: {num_agent_stuck_in_loop} / {num_lines} ({num_agent_stuck_in_loop / num_lines * 100:.2f}%)'
+    )
+    assert len(num_turns) == num_lines
+    assert len(main_agent_cost) == num_lines
+    assert len(editor_cost) == num_lines
+    print('## Statistics')
+    print(f'Avg. num of turns per instance: {sum(num_turns) / num_lines:.2f}')
+    print(f'Avg. agent cost per instance: {sum(main_agent_cost) / num_lines:.2f} USD')
+    print(f'Avg. editor cost per instance: {sum(editor_cost) / num_lines:.2f} USD')
+    print(
+        f'Avg. total cost per instance: {(sum(main_agent_cost) + sum(editor_cost)) / num_lines:.2f} USD'
     )
 
-    df['resolve_rate'] = df['resolved'].apply(lambda x: x['percentage'])
-    df['empty_patch_rate'] = df['empty_patches'].apply(lambda x: x['percentage'])
-    df['unfinished_rate'] = df['unfinished_runs'].apply(lambda x: x['percentage'])
-    df['avg_turns'] = df['statistics'].apply(lambda x: x['avg_turns'])
-    df['error_rate'] = df['errors'].apply(lambda x: x['percentage'])
-    df['avg_cost'] = df['statistics'].apply(lambda x: x['costs']['total'])
-
-    df = df.sort_values('resolve_rate', ascending=False)
-
-    return df
-
-
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        'input_path', type=str, help='The file or directory to summarize'
-    )
-    parser.add_argument(
-        '--output',
-        type=str,
-        help='Output JSONL file for results',
-        default='summary_results.jsonl',
-    )
-    args = parser.parse_args()
-
-    if os.path.isdir(args.input_path):
-        df = aggregate_directory(args.input_path)
-        # Create the summary string
-        columns = [
-            'directory',
-            'resolve_rate',
-            'empty_patch_rate',
-            'unfinished_rate',
-            'error_rate',
-            'avg_turns',
-            'avg_cost',
-            'total_instances',
-        ]
-        summary_str = df[columns].to_string(
-            float_format=lambda x: '{:.2f}'.format(x),
-            formatters={
-                'directory': lambda x: x[:90]
-            },  # Truncate directory names to 20 chars
-            index=False,
-        )
-
-        # Print to console
-        print('\nResults summary (sorted by resolve rate):')
-        print(summary_str)
-
-        # Save to text file
-        txt_output = args.output.rsplit('.', 1)[0] + '.txt'
-        with open(txt_output, 'w') as f:
-            f.write('Results summary (sorted by resolve rate):\n')
-            f.write(summary_str)
-
-        # Save
-        df.to_json(args.output, lines=True, orient='records')
-        df[columns].to_csv(args.output.rsplit('.', 1)[0] + '.csv', index=False)
-    else:
-        # Process single file with detailed output
-        results = []
-        try:
-            result = process_file(args.input_path)
-            results.append(result)
-
-            # Print detailed results for single file
-            print(f'\nResults for {args.input_path}:')
-            print(
-                f"Number of resolved: {result['resolved']['count']} / {result['total_instances']} ({result['resolved']['percentage']:.2f}%)"
-            )
-            print(
-                f"Number of empty patch: {result['empty_patches']['count']} / {result['total_instances']} ({result['empty_patches']['percentage']:.2f}%)"
-            )
-            print(
-                f"Number of error lines: {result['errors']['total']} / {result['total_instances']} ({result['errors']['percentage']:.2f}%)"
-            )
-            print(
-                f"Number of agent stuck in loop: {result['errors']['stuck_in_loop']['count']} / {result['total_instances']} ({result['errors']['stuck_in_loop']['percentage']:.2f}%)"
-            )
-            print(
-                f"Number of unfinished runs: {result['unfinished_runs']['count']} / {result['total_instances']} ({result['unfinished_runs']['percentage']:.2f}%)"
-            )
-            print('## Statistics')
-            print(
-                f"Avg. num of turns per instance: {result['statistics']['avg_turns']:.2f}"
-            )
-            print(
-                f"Avg. agent cost per instance: {result['statistics']['costs']['main_agent']:.2f} USD"
-            )
-            print(
-                f"Avg. editor cost per instance: {result['statistics']['costs']['editor']:.2f} USD"
-            )
-            print(
-                f"Avg. total cost per instance: {result['statistics']['costs']['total']:.2f} USD"
-            )
-
-            print('## Detailed error breakdown:')
-            for error, data in result['errors']['breakdown'].items():
-                print(f"{error}: {data['count']} ({data['percentage']:.2f}%)")
-
-        except Exception as e:
-            print(f'Error processing {args.input_path}: {str(e)}')
+    print('## Detailed error breakdown:')
+    for error, count in error_counter.items():
+        print(f'{error}: {count} ({count / num_lines * 100:.2f}%)')

evaluation/benchmarks/swe_bench/scripts/run_infer.sh

@@ -55,10 +55,10 @@ echo "USE_INSTANCE_IMAGE: $USE_INSTANCE_IMAGE"
 export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
 echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 echo "DATASET: $DATASET"
 echo "SPLIT: $SPLIT"
@@ -68,7 +68,7 @@ if [ -z "$USE_HINT_TEXT" ]; then
   export USE_HINT_TEXT=false
 fi
 echo "USE_HINT_TEXT: $USE_HINT_TEXT"
-EVAL_NOTE="$OPENHANDS_VERSION"
+EVAL_NOTE="$AGENT_VERSION"
 # if not using Hint, add -no-hint to the eval note
 if [ "$USE_HINT_TEXT" = false ]; then
   EVAL_NOTE="$EVAL_NOTE-no-hint"

evaluation/benchmarks/toolqa/scripts/run_infer.sh

@@ -38,10 +38,10 @@ if [ -z "$WOLFRAM_APPID" ]; then
   echo "WOLFRAM_APPID not specified"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 echo "DATASET: $DATASET"
 echo "HARDNESS: $HARDNESS"
@@ -56,7 +56,7 @@ COMMAND="poetry run python evaluation/benchmarks/toolqa/run_infer.py \
   --wolfram_alpha_appid $WOLFRAM_APPID\
   --data-split validation \
   --eval-num-workers $NUM_WORKERS \
-  --eval-note ${OPENHANDS_VERSION}_${LEVELS}"
+  --eval-note ${AGENT_VERSION}_${LEVELS}"
 
 if [ -n "$EVAL_LIMIT" ]; then
   echo "EVAL_LIMIT: $EVAL_LIMIT"

evaluation/benchmarks/webarena/scripts/run_infer.sh

@@ -27,13 +27,13 @@ if [ -z "$AGENT" ]; then
   AGENT="BrowsingAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
-EVAL_NOTE="$OPENHANDS_VERSION"
+EVAL_NOTE="$AGENT_VERSION"
 
 COMMAND="poetry run python evaluation/benchmarks/webarena/run_infer.py \
   --agent-cls $AGENT \

evaluation/integration_tests/run_infer.py

@@ -48,19 +48,13 @@ def get_config(
             # use default base_container_image
             enable_auto_lint=True,
             use_host_network=False,
-            timeout=300,
-            # Add platform to the sandbox config to solve issue 4401
-            platform='linux/amd64',
+            timeout=100,
             api_key=os.environ.get('ALLHANDS_API_KEY', None),
             remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            keep_runtime_alive=False,
-            remote_runtime_init_timeout=3600,
         ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
-        # debug
-        debug=True,
     )
     config.set_llm_config(
         update_llm_config_for_completions_logging(
@@ -113,37 +107,31 @@ def process_instance(
     # =============================================
     # create sandbox and run the agent
     # =============================================
+
     runtime: Runtime = create_runtime(config)
     call_async_from_sync(runtime.connect)
-    try:
-        test_class.initialize_runtime(runtime)
 
-        # 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=MessageAction(content=instruction),
-                runtime=runtime,
-                fake_user_response_fn=FAKE_RESPONSES[metadata.agent_class],
-            )
+    test_class.initialize_runtime(runtime)
+
+    # 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=MessageAction(content=instruction),
+            runtime=runtime,
+            fake_user_response_fn=FAKE_RESPONSES[metadata.agent_class],
         )
-        if state is None:
-            raise ValueError('State should not be None.')
+    )
+    if state is None:
+        raise ValueError('State should not be None.')
 
-        # # =============================================
-        # # result evaluation
-        # # =============================================
+    # # =============================================
+    # # result evaluation
+    # # =============================================
 
-        histories = state.history
-
-        # some basic check
-        logger.info(f'Total events in history: {len(histories)}')
-        assert len(histories) > 0, 'History should not be empty'
-
-        test_result: TestResult = test_class.verify_result(runtime, histories)
-        metrics = state.metrics.get() if state.metrics else None
-    finally:
-        runtime.close()
+    histories = [event_to_dict(event) for event in state.history]
+    test_result: TestResult = test_class.verify_result(runtime, histories)
+    metrics = state.metrics.get() if state.metrics else None
 
     # Save the output
     output = EvalOutput(
@@ -151,7 +139,7 @@ def process_instance(
         instance=instance.to_dict(),
         instruction=instruction,
         metadata=metadata,
-        history=[event_to_dict(event) for event in histories],
+        history=histories,
         metrics=metrics,
         error=state.last_error if state and state.last_error else None,
         test_result=test_result.model_dump(),
@@ -218,8 +206,6 @@ if __name__ == '__main__':
     )
 
     df = pd.read_json(output_file, lines=True, orient='records')
-
-    # record success and reason for failure for the final report
     df['success'] = df['test_result'].apply(lambda x: x['success'])
     df['reason'] = df['test_result'].apply(lambda x: x['reason'])
     logger.info('-' * 100)
@@ -233,16 +219,9 @@ if __name__ == '__main__':
     )
     logger.info('-' * 100)
 
-    # record cost for each instance, with 3 decimal places
-    df['cost'] = df['metrics'].apply(lambda x: round(x['accumulated_cost'], 3))
-    logger.info(f'Total cost: USD {df["cost"].sum():.2f}')
-
     report_file = os.path.join(metadata.eval_output_dir, 'report.md')
     with open(report_file, 'w') as f:
         f.write(
             f'Success rate: {df["success"].mean():.2%} ({df["success"].sum()}/{len(df)})\n'
         )
-        f.write(f'\nTotal cost: USD {df["cost"].sum():.2f}\n')
-        f.write(
-            df[['instance_id', 'success', 'reason', 'cost']].to_markdown(index=False)
-        )
+        f.write(df[['instance_id', 'success', 'reason']].to_markdown(index=False))

evaluation/integration_tests/scripts/run_infer.sh

@@ -21,13 +21,13 @@ if [ -z "$AGENT" ]; then
   AGENT="CodeActAgent"
 fi
 
-get_openhands_version
+get_agent_version
 
 echo "AGENT: $AGENT"
-echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "AGENT_VERSION: $AGENT_VERSION"
 echo "MODEL_CONFIG: $MODEL_CONFIG"
 
-EVAL_NOTE=$OPENHANDS_VERSION
+EVAL_NOTE=$AGENT_VERSION
 
 # Default to NOT use unit tests.
 if [ -z "$USE_UNIT_TESTS" ]; then

evaluation/integration_tests/tests/t05_simple_browsing.py

@@ -108,8 +108,6 @@ class Test(BaseIntegrationTest):
 
     @classmethod
     def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
-        from openhands.core.logger import openhands_logger as logger
-
         # check if the "The answer is OpenHands is all you need!" is in any message
         message_actions = [
             event
@@ -118,29 +116,19 @@ class Test(BaseIntegrationTest):
                 event, (MessageAction, AgentFinishAction, AgentDelegateObservation)
             )
         ]
-        logger.debug(f'Total message-like events: {len(message_actions)}')
-
         for event in message_actions:
-            try:
-                if isinstance(event, AgentDelegateObservation):
-                    content = event.content
-                elif isinstance(event, AgentFinishAction):
-                    content = event.outputs.get('content', '')
-                elif isinstance(event, MessageAction):
-                    content = event.content
-                else:
-                    logger.warning(f'Unexpected event type: {type(event)}')
-                    continue
+            if isinstance(event, AgentDelegateObservation):
+                content = event.content
+            elif isinstance(event, AgentFinishAction):
+                content = event.outputs.get('content', '')
+            elif isinstance(event, MessageAction):
+                content = event.content
+            else:
+                raise ValueError(f'Unknown event type: {type(event)}')
 
-                if 'OpenHands is all you need!' in content:
-                    return TestResult(success=True)
-            except Exception as e:
-                logger.error(f'Error processing event: {e}')
-
-        logger.debug(
-            f'Total messages: {len(message_actions)}. Messages: {message_actions}'
-        )
+            if 'OpenHands is all you need!' in content:
+                return TestResult(success=True)
         return TestResult(
             success=False,
-            reason=f'The answer is not found in any message. Total messages: {len(message_actions)}.',
+            reason=f'The answer is not found in any message. Total messages: {len(message_actions)}. Messages: {message_actions}',
         )

evaluation/integration_tests/tests/t06_github_pr_browsing.py

@@ -14,9 +14,7 @@ class Test(BaseIntegrationTest):
 
     @classmethod
     def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
-        from openhands.core.logger import openhands_logger as logger
-
-        # check if the license information is in any message
+        # check if the "The answer is OpenHands is all you need!" is in any message
         message_actions = [
             event
             for event in histories
@@ -24,35 +22,23 @@ class Test(BaseIntegrationTest):
                 event, (MessageAction, AgentFinishAction, AgentDelegateObservation)
             )
         ]
-        logger.info(f'Total message-like events: {len(message_actions)}')
-
         for event in message_actions:
-            try:
-                if isinstance(event, AgentDelegateObservation):
-                    content = event.content
-                elif isinstance(event, AgentFinishAction):
-                    content = event.outputs.get('content', '')
-                    if event.thought:
-                        content += f'\n\n{event.thought}'
-                elif isinstance(event, MessageAction):
-                    content = event.content
-                else:
-                    logger.warning(f'Unexpected event type: {type(event)}')
-                    continue
+            if isinstance(event, AgentDelegateObservation):
+                content = event.content
+            elif isinstance(event, AgentFinishAction):
+                content = event.outputs.get('content', '')
+            elif isinstance(event, MessageAction):
+                content = event.content
+            else:
+                raise ValueError(f'Unknown event type: {type(event)}')
 
-                if (
-                    'non-commercial' in content
-                    or 'MIT' in content
-                    or 'Apache 2.0' in content
-                ):
-                    return TestResult(success=True)
-            except Exception as e:
-                logger.error(f'Error processing event: {e}')
-
-        logger.debug(
-            f'Total messages: {len(message_actions)}. Messages: {message_actions}'
-        )
+            if (
+                'non-commercial' in content
+                or 'MIT' in content
+                or 'Apache 2.0' in content
+            ):
+                return TestResult(success=True)
         return TestResult(
             success=False,
-            reason=f'The answer is not found in any message. Total messages: {len(message_actions)}.',
+            reason=f'The answer is not found in any message. Total messages: {len(message_actions)}. Messages: {message_actions}',
         )

evaluation/utils/version_control.sh

@@ -39,8 +39,8 @@ checkout_original_branch() {
     git checkout $current_branch
 }
 
-get_openhands_version() {
+get_agent_version() {
     # IMPORTANT: Because Agent's prompt changes fairly often in the rapidly evolving codebase of OpenHands
     # We need to track the version of Agent in the evaluation to make sure results are comparable
-    OPENHANDS_VERSION=v$(poetry run python -c "from openhands import get_version; print(get_version())")
+    AGENT_VERSION=v$(poetry run python -c "import openhands.agenthub; from openhands.controller.agent import Agent; print(Agent.get_cls('$AGENT').VERSION)")
 }

frontend/.gitignore

@@ -7,4 +7,3 @@ node_modules/
 /playwright-report/
 /blob-report/
 /playwright/.cache/
-.react-router/

frontend/README.md

@@ -9,7 +9,6 @@ This is the frontend of the OpenHands project. It is a React application that pr
 - Remix SPA Mode (React + Vite + React Router)
 - TypeScript
 - Redux
-- TanStack Query
 - Tailwind CSS
 - i18next
 - React Testing Library
@@ -86,7 +85,7 @@ frontend
 ├── src
 │   ├── api # API calls
 │   ├── assets
-│   ├── components
+│   ├── components # Reusable components
 │   ├── context # Local state management
 │   ├── hooks # Custom hooks
 │   ├── i18n # Internationalization
@@ -100,18 +99,6 @@ frontend
 └── .env.sample # Sample environment variables
 ```
 
-#### Components
-
-Components are organized into folders based on their **domain**, **feature**, or **shared functionality**.
-
-```sh
-components
-├── features # Domain-specific components
-├── layout
-├── modals
-└── ui # Shared UI components
-```
-
 ### Features
 
 - Real-time updates with WebSockets

frontend/__tests__/components/browser.test.tsx

@@ -1,8 +1,7 @@
 import { screen } from "@testing-library/react";
 import { describe, it, expect } from "vitest";
 import { renderWithProviders } from "../../test-utils";
-import { BrowserPanel } from "#/components/features/browser/browser";
-
+import BrowserPanel from "#/components/browser";
 
 describe("Browser", () => {
   it("renders a message if no screenshotSrc is provided", () => {

frontend/__tests__/components/chat-message.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { describe, it, expect, test } from "vitest";
-import { ChatMessage } from "#/components/features/chat/chat-message";
+import { ChatMessage } from "#/components/chat-message";
 
 describe("ChatMessage", () => {
   it("should render a user message", () => {

frontend/__tests__/components/chat/chat-input.test.tsx

@@ -1,7 +1,7 @@
 import userEvent from "@testing-library/user-event";
 import { fireEvent, render, screen } from "@testing-library/react";
 import { describe, afterEach, vi, it, expect } from "vitest";
-import { ChatInput } from "#/components/features/chat/chat-input";
+import { ChatInput } from "#/components/chat-input";
 
 describe("ChatInput", () => {
   const onSubmitMock = vi.fn();

frontend/__tests__/components/chat/chat-interface.test.tsx

@@ -6,10 +6,10 @@ import { addUserMessage } from "#/state/chat-slice";
 import { SUGGESTIONS } from "#/utils/suggestions";
 import * as ChatSlice from "#/state/chat-slice";
 import { WsClientProviderStatus } from "#/context/ws-client-provider";
-import { ChatInterface } from "#/components/features/chat/chat-interface";
+import { ChatInterface } from "#/routes/_oh.app/chat-interface";
 
 // eslint-disable-next-line @typescript-eslint/no-unused-vars
-const renderChatInterface = (messages: (Message)[]) =>
+const renderChatInterface = (messages: (Message | ErrorMessage)[]) =>
   renderWithProviders(<ChatInterface />);
 
 describe("Empty state", () => {
@@ -26,8 +26,8 @@ describe("Empty state", () => {
   }));
 
   beforeAll(() => {
-    vi.mock("react-router", async (importActual) => ({
-      ...(await importActual<typeof import("react-router")>()),
+    vi.mock("@remix-run/react", async (importActual) => ({
+      ...(await importActual<typeof import("@remix-run/react")>()),
       useRouteLoaderData: vi.fn(() => ({})),
     }));
 
@@ -56,7 +56,6 @@ describe("Empty state", () => {
           content: "Hello",
           imageUrls: [],
           timestamp: new Date().toISOString(),
-          pending: true,
         }),
       );
     });
@@ -173,14 +172,12 @@ describe.skip("ChatInterface", () => {
         content: "Hello",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
       {
         sender: "assistant",
         content: "Hi",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
     ];
     renderChatInterface(messages);
@@ -214,7 +211,6 @@ describe.skip("ChatInterface", () => {
         content: "Here are some images",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
     ];
     const { rerender } = renderChatInterface(messages);
@@ -227,7 +223,6 @@ describe.skip("ChatInterface", () => {
         content: "Here are some images",
         imageUrls: ["image1", "image2"],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
     ];
 
@@ -249,14 +244,12 @@ describe.skip("ChatInterface", () => {
         content: "Hello",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
       {
         sender: "user",
         content: "Hi",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
     ];
     const { rerender } = renderChatInterface(messages);
@@ -269,7 +262,6 @@ describe.skip("ChatInterface", () => {
       content: "How can I help you?",
       imageUrls: [],
       timestamp: new Date().toISOString(),
-      pending: true,
     });
 
     rerender(<ChatInterface />);
@@ -278,19 +270,17 @@ describe.skip("ChatInterface", () => {
   });
 
   it("should render inline errors", () => {
-    const messages: (Message)[] = [
+    const messages: (Message | ErrorMessage)[] = [
       {
         sender: "assistant",
         content: "Hello",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
       {
-        type: "error",
-        content: "Something went wrong",
-        sender: "assistant",
-        timestamp: new Date().toISOString(),
+        error: true,
+        id: "",
+        message: "Something went wrong",
       },
     ];
     renderChatInterface(messages);
@@ -300,8 +290,8 @@ describe.skip("ChatInterface", () => {
   });
 
   it("should render both GitHub buttons initially when ghToken is available", () => {
-    vi.mock("react-router", async (importActual) => ({
-      ...(await importActual<typeof import("react-router")>()),
+    vi.mock("@remix-run/react", async (importActual) => ({
+      ...(await importActual<typeof import("@remix-run/react")>()),
       useRouteLoaderData: vi.fn(() => ({ ghToken: "test-token" })),
     }));
 
@@ -311,7 +301,6 @@ describe.skip("ChatInterface", () => {
         content: "Hello",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
     ];
     renderChatInterface(messages);
@@ -326,8 +315,8 @@ describe.skip("ChatInterface", () => {
   });
 
   it("should render only 'Push changes to PR' button after PR is created", async () => {
-    vi.mock("react-router", async (importActual) => ({
-      ...(await importActual<typeof import("react-router")>()),
+    vi.mock("@remix-run/react", async (importActual) => ({
+      ...(await importActual<typeof import("@remix-run/react")>()),
       useRouteLoaderData: vi.fn(() => ({ ghToken: "test-token" })),
     }));
 
@@ -337,7 +326,6 @@ describe.skip("ChatInterface", () => {
         content: "Hello",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
     ];
     const { rerender } = renderChatInterface(messages);
@@ -370,21 +358,18 @@ describe.skip("ChatInterface", () => {
         content: "Hello",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
       {
         sender: "user",
         content: "Hi",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
       {
         sender: "assistant",
         content: "How can I help you?",
         imageUrls: [],
         timestamp: new Date().toISOString(),
-        pending: true,
       },
     ];
     const { rerender } = renderChatInterface(messages);
@@ -395,7 +380,6 @@ describe.skip("ChatInterface", () => {
       content: "I need help",
       imageUrls: [],
       timestamp: new Date().toISOString(),
-      pending: true,
     });
 
     rerender(<ChatInterface />);

frontend/__tests__/components/context-menu/account-settings-context-menu.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, test, vi } from "vitest";
-import { AccountSettingsContextMenu } from "#/components/features/context-menu/account-settings-context-menu";
+import { AccountSettingsContextMenu } from "#/components/context-menu/account-settings-context-menu";
 
 describe("AccountSettingsContextMenu", () => {
   const user = userEvent.setup();

frontend/__tests__/components/context-menu/context-menu-list-item.test.tsx

@@ -1,7 +1,7 @@
 import { describe, it, expect, vi } from "vitest";
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
-import { ContextMenuListItem } from "#/components/features/context-menu/context-menu-list-item";
+import { ContextMenuListItem } from "#/components/context-menu/context-menu-list-item";
 
 describe("ContextMenuListItem", () => {
   it("should render the component with the children", () => {

frontend/__tests__/components/feedback-actions.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen, within } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
-import { FeedbackActions } from "#/components/features/feedback/feedback-actions";
+import { FeedbackActions } from "#/components/feedback-actions";
 
 describe("FeedbackActions", () => {
   const user = userEvent.setup();

frontend/__tests__/components/feedback-form.test.tsx

@@ -1,8 +1,8 @@
-import { screen } from "@testing-library/react";
+import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
 import { renderWithProviders } from "test-utils";
-import { FeedbackForm } from "#/components/features/feedback/feedback-form";
+import { FeedbackForm } from "#/components/feedback-form";
 
 describe("FeedbackForm", () => {
   const user = userEvent.setup();

frontend/__tests__/components/file-explorer/explorer-tree.test.tsx

@@ -1,7 +1,7 @@
 import { screen } from "@testing-library/react";
 import { renderWithProviders } from "test-utils";
 import { describe, afterEach, vi, it, expect } from "vitest";
-import { ExplorerTree } from "#/components/features/file-explorer/explorer-tree";
+import ExplorerTree from "#/components/file-explorer/explorer-tree";
 
 const FILES = ["file-1-1.ts", "folder-1-2"];
 

frontend/__tests__/components/file-explorer/file-explorer.test.tsx

@@ -4,8 +4,8 @@ import { renderWithProviders } from "test-utils";
 import { describe, it, expect, vi, Mock, afterEach } from "vitest";
 import toast from "#/utils/toast";
 import AgentState from "#/types/agent-state";
+import FileExplorer from "#/components/file-explorer/file-explorer";
 import OpenHands from "#/api/open-hands";
-import { FileExplorer } from "#/components/features/file-explorer/file-explorer";
 
 const toastSpy = vi.spyOn(toast, "error");
 const uploadFilesSpy = vi.spyOn(OpenHands, "uploadFiles");

frontend/__tests__/components/file-explorer/tree-node.test.tsx

@@ -2,7 +2,7 @@ import { screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { renderWithProviders } from "test-utils";
 import { vi, describe, afterEach, it, expect } from "vitest";
-import TreeNode from "#/components/features/file-explorer/tree-node";
+import TreeNode from "#/components/file-explorer/tree-node";
 import OpenHands from "#/api/open-hands";
 
 const getFileSpy = vi.spyOn(OpenHands, "getFile");

frontend/__tests__/components/image-preview.test.tsx

@@ -1,7 +1,7 @@
-import { ImagePreview } from "#/components/features/images/image-preview";
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { describe, expect, it, vi } from "vitest";
+import { ImagePreview } from "#/components/image-preview";
 
 describe("ImagePreview", () => {
   it("should render an image", () => {

frontend/__tests__/components/interactive-chat-box.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen, within } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, beforeAll, describe, expect, it, vi } from "vitest";
-import { InteractiveChatBox } from "#/components/features/chat/interactive-chat-box";
+import { InteractiveChatBox } from "#/components/interactive-chat-box";
 
 describe("InteractiveChatBox", () => {
   const onSubmitMock = vi.fn();

frontend/__tests__/components/modals/base-modal/base-modal.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen, act } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { describe, it, vi, expect } from "vitest";
-import { BaseModal } from "#/components/shared/modals/base-modal/base-modal";
+import BaseModal from "#/components/modals/base-modal/base-modal";
 
 describe("BaseModal", () => {
   it("should render if the modal is open", () => {

frontend/__tests__/components/modals/settings/model-selector.test.tsx

@@ -1,7 +1,7 @@
 import { describe, it, expect } from "vitest";
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
-import { ModelSelector } from "#/components/shared/modals/settings/model-selector";
+import { ModelSelector } from "#/components/modals/settings/model-selector";
 
 describe("ModelSelector", () => {
   const models = {

frontend/__tests__/components/suggestion-item.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
-import { SuggestionItem } from "#/components/features/suggestions/suggestion-item";
+import { SuggestionItem } from "#/components/suggestion-item";
 
 describe("SuggestionItem", () => {
   const suggestionItem = { label: "suggestion1", value: "a long text value" };

frontend/__tests__/components/suggestions.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
-import { Suggestions } from "#/components/features/suggestions/suggestions";
+import { Suggestions } from "#/components/suggestions";
 
 describe("Suggestions", () => {
   const firstSuggestion = {

frontend/__tests__/components/terminal/terminal.test.tsx

@@ -2,7 +2,7 @@ import { act, screen } from "@testing-library/react";
 import { renderWithProviders } from "test-utils";
 import { vi, describe, afterEach, it, expect } from "vitest";
 import { Command, appendInput, appendOutput } from "#/state/command-slice";
-import Terminal from "#/components/features/terminal/terminal";
+import Terminal from "#/components/terminal/terminal";
 
 global.ResizeObserver = vi.fn().mockImplementation(() => ({
   observe: vi.fn(),

frontend/__tests__/components/upload-image-input.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
-import { UploadImageInput } from "#/components/features/images/upload-image-input";
+import { UploadImageInput } from "#/components/upload-image-input";
 
 describe("UploadImageInput", () => {
   const user = userEvent.setup();

frontend/__tests__/components/user-actions.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen } from "@testing-library/react";
 import { describe, expect, it, test, vi, afterEach } from "vitest";
 import userEvent from "@testing-library/user-event";
-import { UserActions } from "#/components/features/sidebar/user-actions";
+import { UserActions } from "#/components/user-actions";
 
 describe("UserActions", () => {
   const user = userEvent.setup();

frontend/__tests__/components/user-avatar.test.tsx

@@ -1,7 +1,7 @@
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
-import { UserAvatar } from "#/components/features/sidebar/user-avatar";
+import { UserAvatar } from "#/components/user-avatar";
 
 describe("UserAvatar", () => {
   const onClickMock = vi.fn();

frontend/__tests__/hooks/use-rate.test.ts

@@ -1,6 +1,6 @@
 import { act, renderHook } from "@testing-library/react";
 import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
-import { useRate } from "#/hooks/use-rate";
+import { useRate } from "#/utils/use-rate";
 
 describe("useRate", () => {
   beforeEach(() => {

frontend/__tests__/routes/_oh.test.tsx

@@ -1,5 +1,5 @@
 import { afterEach, beforeAll, describe, expect, it, vi } from "vitest";
-import { createRoutesStub } from "react-router";
+import { createRemixStub } from "@remix-run/testing";
 import { screen, waitFor, within } from "@testing-library/react";
 import { renderWithProviders } from "test-utils";
 import userEvent from "@testing-library/user-event";
@@ -8,7 +8,7 @@ import * as CaptureConsent from "#/utils/handle-capture-consent";
 import i18n from "#/i18n";
 
 describe("frontend/routes/_oh", () => {
-  const RouteStub = createRoutesStub([{ Component: MainApp, path: "/" }]);
+  const RemixStub = createRemixStub([{ Component: MainApp, path: "/" }]);
 
   const { userIsAuthenticatedMock, settingsAreUpToDateMock } = vi.hoisted(
     () => ({
@@ -34,26 +34,26 @@ describe("frontend/routes/_oh", () => {
   });
 
   it("should render", async () => {
-    renderWithProviders(<RouteStub />);
+    renderWithProviders(<RemixStub />);
     await screen.findByTestId("root-layout");
   });
 
   it("should render the AI config modal if the user is authed", async () => {
     // Our mock return value is true by default
-    renderWithProviders(<RouteStub />);
+    renderWithProviders(<RemixStub />);
     await screen.findByTestId("ai-config-modal");
   });
 
   it("should render the AI config modal if settings are not up-to-date", async () => {
     settingsAreUpToDateMock.mockReturnValue(false);
-    renderWithProviders(<RouteStub />);
+    renderWithProviders(<RemixStub />);
 
     await screen.findByTestId("ai-config-modal");
   });
 
   it("should not render the AI config modal if the settings are up-to-date", async () => {
     settingsAreUpToDateMock.mockReturnValue(true);
-    renderWithProviders(<RouteStub />);
+    renderWithProviders(<RemixStub />);
 
     await waitFor(() => {
       expect(screen.queryByTestId("ai-config-modal")).not.toBeInTheDocument();
@@ -67,7 +67,7 @@ describe("frontend/routes/_oh", () => {
       "handleCaptureConsent",
     );
 
-    renderWithProviders(<RouteStub />);
+    renderWithProviders(<RemixStub />);
 
     // The user has not consented to tracking
     const consentForm = await screen.findByTestId("user-capture-consent-form");
@@ -89,7 +89,7 @@ describe("frontend/routes/_oh", () => {
 
   it("should not render the user consent form if the user has already made a decision", async () => {
     localStorage.setItem("analytics-consent", "true");
-    renderWithProviders(<RouteStub />);
+    renderWithProviders(<RemixStub />);
 
     await waitFor(() => {
       expect(
@@ -98,15 +98,14 @@ describe("frontend/routes/_oh", () => {
     });
   });
 
-  // TODO: Likely failing due to how tokens are now handled in context. Move to e2e tests
-  it.skip("should render a new project button if a token is set", async () => {
+  it("should render a new project button if a token is set", async () => {
     localStorage.setItem("token", "test-token");
-    const { rerender } = renderWithProviders(<RouteStub />);
+    const { rerender } = renderWithProviders(<RemixStub />);
 
     await screen.findByTestId("new-project-button");
 
     localStorage.removeItem("token");
-    rerender(<RouteStub />);
+    rerender(<RemixStub />);
 
     await waitFor(() => {
       expect(
@@ -118,17 +117,17 @@ describe("frontend/routes/_oh", () => {
   // TODO: Move to e2e tests
   it.skip("should update the i18n language when the language settings change", async () => {
     const changeLanguageSpy = vi.spyOn(i18n, "changeLanguage");
-    const { rerender } = renderWithProviders(<RouteStub />);
+    const { rerender } = renderWithProviders(<RemixStub />);
 
     // The default language is English
     expect(changeLanguageSpy).toHaveBeenCalledWith("en");
 
     localStorage.setItem("LANGUAGE", "es");
 
-    rerender(<RouteStub />);
+    rerender(<RemixStub />);
     expect(changeLanguageSpy).toHaveBeenCalledWith("es");
 
-    rerender(<RouteStub />);
+    rerender(<RemixStub />);
     // The language has not changed, so the spy should not have been called again
     expect(changeLanguageSpy).toHaveBeenCalledTimes(2);
   });
@@ -139,7 +138,7 @@ describe("frontend/routes/_oh", () => {
     localStorage.setItem("ghToken", "test-token");
 
     // const logoutCleanupSpy = vi.spyOn(LogoutCleanup, "logoutCleanup");
-    renderWithProviders(<RouteStub />);
+    renderWithProviders(<RemixStub />);
 
     const userActions = await screen.findByTestId("user-actions");
     const userAvatar = within(userActions).getByTestId("user-avatar");

frontend/package.json

@@ -9,15 +9,15 @@
   "dependencies": {
     "@monaco-editor/react": "^4.6.0",
     "@nextui-org/react": "^2.4.8",
-    "@react-router/node": "^7.0.1",
-    "@react-router/serve": "^7.0.1",
     "@react-types/shared": "^3.25.0",
     "@reduxjs/toolkit": "^2.3.0",
+    "@remix-run/node": "^2.11.2",
+    "@remix-run/react": "^2.11.2",
+    "@remix-run/serve": "^2.11.2",
     "@tanstack/react-query": "^5.60.5",
     "@vitejs/plugin-react": "^4.3.2",
     "@xterm/addon-fit": "^0.10.0",
     "@xterm/xterm": "^5.4.0",
-    "axios": "^1.7.7",
     "clsx": "^2.1.1",
     "eslint-config-airbnb-typescript": "^18.0.0",
     "i18next": "^23.15.2",
@@ -35,7 +35,7 @@
     "react-icons": "^5.3.0",
     "react-markdown": "^9.0.1",
     "react-redux": "^9.1.2",
-    "react-router": "^7.0.1",
+    "react-router-dom": "^6.26.1",
     "react-syntax-highlighter": "^15.6.1",
     "react-textarea-autosize": "^8.5.4",
     "remark-gfm": "^4.0.0",
@@ -47,9 +47,9 @@
     "ws": "^8.18.0"
   },
   "scripts": {
-    "dev": "npm run make-i18n && cross-env VITE_MOCK_API=false react-router dev",
-    "dev:mock": "npm run make-i18n && cross-env VITE_MOCK_API=true react-router dev",
-    "build": "npm run make-i18n && tsc && react-router build",
+    "dev": "npm run make-i18n && cross-env VITE_MOCK_API=false remix vite:dev",
+    "dev:mock": "npm run make-i18n && cross-env VITE_MOCK_API=true remix vite:dev",
+    "build": "npm run make-i18n && tsc && remix vite:build",
     "start": "npx sirv-cli build/ --single",
     "test": "vitest run",
     "test:e2e": "playwright test",
@@ -60,8 +60,7 @@
     "prelint": "npm run make-i18n",
     "lint": "eslint src --ext .ts,.tsx,.js && prettier --check src/**/*.{ts,tsx}",
     "lint:fix": "eslint src --ext .ts,.tsx,.js --fix && prettier --write src/**/*.{ts,tsx}",
-    "prepare": "cd .. && husky frontend/.husky",
-    "typecheck": "react-router typegen && tsc"
+    "prepare": "cd .. && husky frontend/.husky"
   },
   "husky": {
     "hooks": {
@@ -76,7 +75,8 @@
   },
   "devDependencies": {
     "@playwright/test": "^1.48.2",
-    "@react-router/dev": "^7.0.1",
+    "@remix-run/dev": "^2.11.2",
+    "@remix-run/testing": "^2.11.2",
     "@tailwindcss/typography": "^0.5.15",
     "@tanstack/eslint-plugin-query": "^5.60.1",
     "@testing-library/jest-dom": "^6.6.1",

frontend/react-router.config.ts

@@ -1,35 +0,0 @@
-import type { Config } from "@react-router/dev/config";
-
-/**
- * This script is used to unpack the client directory from the frontend build directory.
- * Remix SPA mode builds the client directory into the build directory. This function
- * moves the contents of the client directory to the build directory and then removes the
- * client directory.
- *
- * This script is used in the buildEnd function of the Vite config.
- */
-const unpackClientDirectory = async () => {
-  const fs = await import("fs");
-  const path = await import("path");
-
-  const buildDir = path.resolve(__dirname, "build");
-  const clientDir = path.resolve(buildDir, "client");
-
-  const files = await fs.promises.readdir(clientDir);
-  await Promise.all(
-    files.map((file) =>
-      fs.promises.rename(
-        path.resolve(clientDir, file),
-        path.resolve(buildDir, file),
-      ),
-    ),
-  );
-
-  await fs.promises.rmdir(clientDir);
-};
-
-export default {
-  appDirectory: "src",
-  buildEnd: unpackClientDirectory,
-  ssr: false,
-} satisfies Config;

frontend/src/api/github-axios-instance.ts

@@ -1,21 +0,0 @@
-import axios from "axios";
-
-const github = axios.create({
-  baseURL: "https://api.github.com",
-  headers: {
-    Accept: "application/vnd.github+json",
-    "X-GitHub-Api-Version": "2022-11-28",
-  },
-});
-
-const setAuthTokenHeader = (token: string) => {
-  github.defaults.headers.common.Authorization = `Bearer ${token}`;
-};
-
-const removeAuthTokenHeader = () => {
-  if (github.defaults.headers.common.Authorization) {
-    delete github.defaults.headers.common.Authorization;
-  }
-};
-
-export { github, setAuthTokenHeader, removeAuthTokenHeader };

frontend/src/api/github.ts

@@ -1,5 +1,14 @@
-import { extractNextPageFromLink } from "#/utils/extract-next-page-from-link";
-import { github } from "./github-axios-instance";
+/**
+ * Generates the headers for the GitHub API
+ * @param token The GitHub token
+ * @returns The headers for the GitHub API
+ */
+const generateGitHubAPIHeaders = (token: string) =>
+  ({
+    Accept: "application/vnd.github+json",
+    Authorization: `Bearer ${token}`,
+    "X-GitHub-Api-Version": "2022-11-28",
+  }) as const;
 
 /**
  * Checks if the data is a GitHub error response
@@ -17,31 +26,18 @@ export const isGitHubErrorReponse = <T extends object | Array<unknown>>(
  * @returns A list of repositories or an error response
  */
 export const retrieveGitHubUserRepositories = async (
+  token: string,
   page = 1,
   per_page = 30,
-) => {
-  const response = await github.get<GitHubRepository[]>("/user/repos", {
-    params: {
-      sort: "pushed",
-      page,
-      per_page,
-    },
-    transformResponse: (data) => {
-      const parsedData: GitHubRepository[] | GitHubErrorReponse =
-        JSON.parse(data);
+): Promise<Response> => {
+  const url = new URL("https://api.github.com/user/repos");
+  url.searchParams.append("sort", "pushed"); // sort by most recently pushed
+  url.searchParams.append("page", page.toString());
+  url.searchParams.append("per_page", per_page.toString());
 
-      if (isGitHubErrorReponse(parsedData)) {
-        throw new Error(parsedData.message);
-      }
-
-      return parsedData;
-    },
+  return fetch(url.toString(), {
+    headers: generateGitHubAPIHeaders(token),
   });
-
-  const link = response.headers.link ?? "";
-  const nextPage = extractNextPageFromLink(link);
-
-  return { data: response.data, nextPage };
 };
 
 /**
@@ -49,54 +45,55 @@ export const retrieveGitHubUserRepositories = async (
  * @param token The GitHub token
  * @returns The authenticated user or an error response
  */
-export const retrieveGitHubUser = async () => {
-  const response = await github.get<GitHubUser>("/user", {
-    transformResponse: (data) => {
-      const parsedData: GitHubUser | GitHubErrorReponse = JSON.parse(data);
-
-      if (isGitHubErrorReponse(parsedData)) {
-        throw new Error(parsedData.message);
-      }
-
-      return parsedData;
-    },
+export const retrieveGitHubUser = async (
+  token: string,
+): Promise<GitHubUser | GitHubErrorReponse> => {
+  const response = await fetch("https://api.github.com/user", {
+    headers: generateGitHubAPIHeaders(token),
   });
 
-  const { data } = response;
+  if (!response.ok) {
+    throw new Error("Failed to retrieve user data");
+  }
 
-  const user: GitHubUser = {
-    id: data.id,
-    login: data.login,
-    avatar_url: data.avatar_url,
-    company: data.company,
-    name: data.name,
-    email: data.email,
+  const data = await response.json();
+
+  if (!isGitHubErrorReponse(data)) {
+    // Only return the necessary user data
+    const user: GitHubUser = {
+      id: data.id,
+      login: data.login,
+      avatar_url: data.avatar_url,
+      company: data.company,
+      name: data.name,
+      email: data.email,
+    };
+
+    return user;
+  }
+
+  const error: GitHubErrorReponse = {
+    message: data.message,
+    documentation_url: data.documentation_url,
+    status: response.status,
   };
 
-  return user;
+  return error;
 };
 
 export const retrieveLatestGitHubCommit = async (
+  token: string,
   repository: string,
-): Promise<GitHubCommit> => {
-  const response = await github.get<GitHubCommit>(
-    `/repos/${repository}/commits`,
-    {
-      params: {
-        per_page: 1,
-      },
-      transformResponse: (data) => {
-        const parsedData: GitHubCommit[] | GitHubErrorReponse =
-          JSON.parse(data);
+): Promise<GitHubCommit[] | GitHubErrorReponse> => {
+  const url = new URL(`https://api.github.com/repos/${repository}/commits`);
+  url.searchParams.append("per_page", "1");
+  const response = await fetch(url.toString(), {
+    headers: generateGitHubAPIHeaders(token),
+  });
 
-        if (isGitHubErrorReponse(parsedData)) {
-          throw new Error(parsedData.message);
-        }
+  if (!response.ok) {
+    throw new Error("Failed to retrieve latest commit");
+  }
 
-        return parsedData[0];
-      },
-    },
-  );
-
-  return response.data;
+  return response.json();
 };

frontend/src/api/invariant-service.ts

@@ -1,30 +0,0 @@
-import { openHands } from "./open-hands-axios";
-
-class InvariantService {
-  static async getPolicy() {
-    const { data } = await openHands.get("/api/security/policy");
-    return data.policy;
-  }
-
-  static async getRiskSeverity() {
-    const { data } = await openHands.get("/api/security/settings");
-    return data.RISK_SEVERITY;
-  }
-
-  static async getTraces() {
-    const { data } = await openHands.get("/api/security/export-trace");
-    return data;
-  }
-
-  static async updatePolicy(policy: string) {
-    await openHands.post("/api/security/policy", { policy });
-  }
-
-  static async updateRiskSeverity(riskSeverity: number) {
-    await openHands.post("/api/security/settings", {
-      RISK_SEVERITY: riskSeverity,
-    });
-  }
-}
-
-export default InvariantService;

frontend/src/api/open-hands-axios.ts

@@ -1,23 +0,0 @@
-import axios from "axios";
-
-export const openHands = axios.create();
-
-export const setAuthTokenHeader = (token: string) => {
-  openHands.defaults.headers.common.Authorization = `Bearer ${token}`;
-};
-
-export const setGitHubTokenHeader = (token: string) => {
-  openHands.defaults.headers.common["X-GitHub-Token"] = token;
-};
-
-export const removeAuthTokenHeader = () => {
-  if (openHands.defaults.headers.common.Authorization) {
-    delete openHands.defaults.headers.common.Authorization;
-  }
-};
-
-export const removeGitHubTokenHeader = () => {
-  if (openHands.defaults.headers.common["X-GitHub-Token"]) {
-    delete openHands.defaults.headers.common["X-GitHub-Token"];
-  }
-};

frontend/src/api/open-hands.ts

@@ -1,3 +1,4 @@
+import { request } from "#/services/api";
 import {
   SaveFileSuccessResponse,
   FileUploadSuccessResponse,
@@ -7,9 +8,7 @@ import {
   ErrorResponse,
   GetConfigResponse,
   GetVSCodeUrlResponse,
-  AuthenticateResponse,
 } from "./open-hands.types";
-import { openHands } from "./open-hands-axios";
 
 class OpenHands {
   /**
@@ -17,8 +16,13 @@ class OpenHands {
    * @returns List of models available
    */
   static async getModels(): Promise<string[]> {
-    const { data } = await openHands.get<string[]>("/api/options/models");
-    return data;
+    const response = await fetch("/api/options/models");
+
+    if (!response.ok) {
+      throw new Error("Failed to fetch models");
+    }
+
+    return response.json();
   }
 
   /**
@@ -26,8 +30,13 @@ class OpenHands {
    * @returns List of agents available
    */
   static async getAgents(): Promise<string[]> {
-    const { data } = await openHands.get<string[]>("/api/options/agents");
-    return data;
+    const response = await fetch("/api/options/agents");
+
+    if (!response.ok) {
+      throw new Error("Failed to fetch agents");
+    }
+
+    return response.json();
   }
 
   /**
@@ -35,15 +44,23 @@ class OpenHands {
    * @returns List of security analyzers available
    */
   static async getSecurityAnalyzers(): Promise<string[]> {
-    const { data } = await openHands.get<string[]>(
-      "/api/options/security-analyzers",
-    );
-    return data;
+    const response = await fetch("/api/options/security-analyzers");
+
+    if (!response.ok) {
+      throw new Error("Failed to fetch security analyzers");
+    }
+
+    return response.json();
   }
 
   static async getConfig(): Promise<GetConfigResponse> {
-    const { data } = await openHands.get<GetConfigResponse>("/config.json");
-    return data;
+    const response = await fetch("/config.json");
+
+    if (!response.ok) {
+      throw new Error("Failed to fetch config");
+    }
+
+    return response.json();
   }
 
   /**
@@ -51,11 +68,21 @@ class OpenHands {
    * @param path Path to list files from
    * @returns List of files available in the given path. If path is not provided, it lists all the files in the workspace
    */
-  static async getFiles(path?: string): Promise<string[]> {
-    const { data } = await openHands.get<string[]>("/api/list-files", {
-      params: { path },
+  static async getFiles(token: string, path?: string): Promise<string[]> {
+    const url = new URL("/api/list-files", window.location.origin);
+    if (path) url.searchParams.append("path", path);
+
+    const response = await fetch(url.toString(), {
+      headers: {
+        Authorization: `Bearer ${token}`,
+      },
     });
-    return data;
+
+    if (!response.ok) {
+      throw new Error("Failed to fetch files");
+    }
+
+    return response.json();
   }
 
   /**
@@ -63,11 +90,21 @@ class OpenHands {
    * @param path Full path of the file to retrieve
    * @returns Content of the file
    */
-  static async getFile(path: string): Promise<string> {
-    const { data } = await openHands.get<{ code: string }>("/api/select-file", {
-      params: { file: path },
+  static async getFile(token: string, path: string): Promise<string> {
+    const url = new URL("/api/select-file", window.location.origin);
+    url.searchParams.append("file", path);
+
+    const response = await fetch(url.toString(), {
+      headers: {
+        Authorization: `Bearer ${token}`,
+      },
     });
 
+    if (!response.ok) {
+      throw new Error("Failed to fetch file");
+    }
+
+    const data = await response.json();
     return data.code;
   }
 
@@ -78,17 +115,31 @@ class OpenHands {
    * @returns Success message or error message
    */
   static async saveFile(
+    token: string,
     path: string,
     content: string,
   ): Promise<SaveFileSuccessResponse> {
-    const { data } = await openHands.post<
-      SaveFileSuccessResponse | ErrorResponse
-    >("/api/save-file", {
-      filePath: path,
-      content,
+    const response = await fetch("/api/save-file", {
+      method: "POST",
+      body: JSON.stringify({ filePath: path, content }),
+      headers: {
+        "Content-Type": "application/json",
+        Authorization: `Bearer ${token}`,
+      },
     });
 
-    if ("error" in data) throw new Error(data.error);
+    if (!response.ok) {
+      throw new Error("Failed to save file");
+    }
+
+    const data = (await response.json()) as
+      | SaveFileSuccessResponse
+      | ErrorResponse;
+
+    if ("error" in data) {
+      throw new Error(data.error);
+    }
+
     return data;
   }
 
@@ -97,15 +148,33 @@ class OpenHands {
    * @param file File to upload
    * @returns Success message or error message
    */
-  static async uploadFiles(files: File[]): Promise<FileUploadSuccessResponse> {
+  static async uploadFiles(
+    token: string,
+    files: File[],
+  ): Promise<FileUploadSuccessResponse> {
     const formData = new FormData();
     files.forEach((file) => formData.append("files", file));
 
-    const { data } = await openHands.post<
-      FileUploadSuccessResponse | ErrorResponse
-    >("/api/upload-files", formData);
+    const response = await fetch("/api/upload-files", {
+      method: "POST",
+      body: formData,
+      headers: {
+        Authorization: `Bearer ${token}`,
+      },
+    });
+
+    if (!response.ok) {
+      throw new Error("Failed to upload files");
+    }
+
+    const data = (await response.json()) as
+      | FileUploadSuccessResponse
+      | ErrorResponse;
+
+    if ("error" in data) {
+      throw new Error(data.error);
+    }
 
-    if ("error" in data) throw new Error(data.error);
     return data;
   }
 
@@ -114,12 +183,24 @@ class OpenHands {
    * @param data Feedback data
    * @returns The stored feedback data
    */
-  static async submitFeedback(feedback: Feedback): Promise<FeedbackResponse> {
-    const { data } = await openHands.post<FeedbackResponse>(
-      "/api/submit-feedback",
-      feedback,
-    );
-    return data;
+  static async submitFeedback(
+    token: string,
+    feedback: Feedback,
+  ): Promise<FeedbackResponse> {
+    const response = await fetch("/api/submit-feedback", {
+      method: "POST",
+      body: JSON.stringify(feedback),
+      headers: {
+        "Content-Type": "application/json",
+        Authorization: `Bearer ${token}`,
+      },
+    });
+
+    if (!response.ok) {
+      throw new Error("Failed to submit feedback");
+    }
+
+    return response.json();
   }
 
   /**
@@ -127,13 +208,19 @@ class OpenHands {
    * @returns Response with authentication status and user info if successful
    */
   static async authenticate(
+    gitHubToken: string,
     appMode: GetConfigResponse["APP_MODE"],
   ): Promise<boolean> {
     if (appMode === "oss") return true;
 
-    const response =
-      await openHands.post<AuthenticateResponse>("/api/authenticate");
-    return response.status === 200;
+    const response = await fetch("/api/authenticate", {
+      method: "POST",
+      headers: {
+        "X-GitHub-Token": gitHubToken,
+      },
+    });
+
+    return response.ok;
   }
 
   /**
@@ -141,10 +228,8 @@ class OpenHands {
    * @returns Blob of the workspace zip
    */
   static async getWorkspaceZip(): Promise<Blob> {
-    const response = await openHands.get("/api/zip-directory", {
-      responseType: "blob",
-    });
-    return response.data;
+    const response = await request(`/api/zip-directory`, {}, false, true);
+    return response.blob();
   }
 
   /**
@@ -154,13 +239,19 @@ class OpenHands {
   static async getGitHubAccessToken(
     code: string,
   ): Promise<GitHubAccessTokenResponse> {
-    const { data } = await openHands.post<GitHubAccessTokenResponse>(
-      "/api/github/callback",
-      {
-        code,
+    const response = await fetch("/api/github/callback", {
+      method: "POST",
+      body: JSON.stringify({ code }),
+      headers: {
+        "Content-Type": "application/json",
       },
-    );
-    return data;
+    });
+
+    if (!response.ok) {
+      throw new Error("Failed to get GitHub access token");
+    }
+
+    return response.json();
   }
 
   /**
@@ -168,15 +259,12 @@ class OpenHands {
    * @returns VSCode URL
    */
   static async getVSCodeUrl(): Promise<GetVSCodeUrlResponse> {
-    const { data } =
-      await openHands.get<GetVSCodeUrlResponse>("/api/vscode-url");
-    return data;
+    return request(`/api/vscode-url`, {}, false, false, 1);
   }
 
   static async getRuntimeId(): Promise<{ runtime_id: string }> {
-    const { data } = await openHands.get<{ runtime_id: string }>(
-      "/api/conversation",
-    );
+    const data = await request("/api/conversation");
+
     return data;
   }
 }

frontend/src/api/open-hands.types.ts

@@ -51,8 +51,3 @@ export interface GetVSCodeUrlResponse {
   vscode_url: string | null;
   error?: string;
 }
-
-export interface AuthenticateResponse {
-  message?: string;
-  error?: string;
-}

frontend/src/components/agent-control-bar.tsx

@@ -0,0 +1,110 @@
+import { Tooltip } from "@nextui-org/react";
+import React from "react";
+import { useSelector } from "react-redux";
+import PauseIcon from "#/assets/pause";
+import PlayIcon from "#/assets/play";
+import { generateAgentStateChangeEvent } from "#/services/agent-state-service";
+import { RootState } from "#/store";
+import AgentState from "#/types/agent-state";
+import { useWsClient } from "#/context/ws-client-provider";
+
+const IgnoreTaskStateMap: Record<string, AgentState[]> = {
+  [AgentState.PAUSED]: [
+    AgentState.INIT,
+    AgentState.PAUSED,
+    AgentState.STOPPED,
+    AgentState.FINISHED,
+    AgentState.REJECTED,
+    AgentState.AWAITING_USER_INPUT,
+    AgentState.AWAITING_USER_CONFIRMATION,
+  ],
+  [AgentState.RUNNING]: [
+    AgentState.INIT,
+    AgentState.RUNNING,
+    AgentState.STOPPED,
+    AgentState.FINISHED,
+    AgentState.REJECTED,
+    AgentState.AWAITING_USER_INPUT,
+    AgentState.AWAITING_USER_CONFIRMATION,
+  ],
+  [AgentState.STOPPED]: [AgentState.INIT, AgentState.STOPPED],
+  [AgentState.USER_CONFIRMED]: [AgentState.RUNNING],
+  [AgentState.USER_REJECTED]: [AgentState.RUNNING],
+  [AgentState.AWAITING_USER_CONFIRMATION]: [],
+};
+
+interface ActionButtonProps {
+  isDisabled?: boolean;
+  content: string;
+  action: AgentState;
+  handleAction: (action: AgentState) => void;
+  large?: boolean;
+}
+
+function ActionButton({
+  isDisabled = false,
+  content,
+  action,
+  handleAction,
+  children,
+  large = false,
+}: React.PropsWithChildren<ActionButtonProps>) {
+  return (
+    <Tooltip content={content} closeDelay={100}>
+      <button
+        onClick={() => handleAction(action)}
+        disabled={isDisabled}
+        className={`
+          relative overflow-visible cursor-default hover:cursor-pointer group
+          disabled:cursor-not-allowed
+          ${large ? "rounded-full bg-neutral-800 p-3" : ""}
+          transition-all duration-300 ease-in-out
+        `}
+        type="button"
+      >
+        <span className="relative z-10 group-hover:filter group-hover:drop-shadow-[0_0_5px_rgba(255,64,0,0.4)]">
+          {children}
+        </span>
+        <span className="absolute -inset-[5px] border-2 border-red-400/40 rounded-full opacity-0 group-hover:opacity-100 transition-opacity duration-300 ease-in-out" />
+      </button>
+    </Tooltip>
+  );
+}
+
+function AgentControlBar() {
+  const { send } = useWsClient();
+  const { curAgentState } = useSelector((state: RootState) => state.agent);
+
+  const handleAction = (action: AgentState) => {
+    if (!IgnoreTaskStateMap[action].includes(curAgentState)) {
+      send(generateAgentStateChangeEvent(action));
+    }
+  };
+
+  return (
+    <div className="flex justify-between items-center gap-20">
+      <ActionButton
+        isDisabled={
+          curAgentState !== AgentState.RUNNING &&
+          curAgentState !== AgentState.PAUSED
+        }
+        content={
+          curAgentState === AgentState.PAUSED
+            ? "Resume the agent task"
+            : "Pause the current task"
+        }
+        action={
+          curAgentState === AgentState.PAUSED
+            ? AgentState.RUNNING
+            : AgentState.PAUSED
+        }
+        handleAction={handleAction}
+        large
+      >
+        {curAgentState === AgentState.PAUSED ? <PlayIcon /> : <PauseIcon />}
+      </ActionButton>
+    </div>
+  );
+}
+
+export default AgentControlBar;

frontend/src/components/agent-status-bar.tsx

@@ -0,0 +1,132 @@
+import React, { useEffect } from "react";
+import { useTranslation } from "react-i18next";
+import { useSelector } from "react-redux";
+import toast from "react-hot-toast";
+import { I18nKey } from "#/i18n/declaration";
+import { RootState } from "#/store";
+import AgentState from "#/types/agent-state";
+import beep from "#/utils/beep";
+
+enum IndicatorColor {
+  BLUE = "bg-blue-500",
+  GREEN = "bg-green-500",
+  ORANGE = "bg-orange-500",
+  YELLOW = "bg-yellow-500",
+  RED = "bg-red-500",
+  DARK_ORANGE = "bg-orange-800",
+}
+
+function AgentStatusBar() {
+  const { t, i18n } = useTranslation();
+  const { curAgentState } = useSelector((state: RootState) => state.agent);
+  const { curStatusMessage } = useSelector((state: RootState) => state.status);
+
+  const AgentStatusMap: {
+    [k: string]: { message: string; indicator: IndicatorColor };
+  } = {
+    [AgentState.INIT]: {
+      message: t(I18nKey.CHAT_INTERFACE$AGENT_INIT_MESSAGE),
+      indicator: IndicatorColor.BLUE,
+    },
+    [AgentState.RUNNING]: {
+      message: t(I18nKey.CHAT_INTERFACE$AGENT_RUNNING_MESSAGE),
+      indicator: IndicatorColor.GREEN,
+    },
+    [AgentState.AWAITING_USER_INPUT]: {
+      message: t(I18nKey.CHAT_INTERFACE$AGENT_AWAITING_USER_INPUT_MESSAGE),
+      indicator: IndicatorColor.ORANGE,
+    },
+    [AgentState.PAUSED]: {
+      message: t(I18nKey.CHAT_INTERFACE$AGENT_PAUSED_MESSAGE),
+      indicator: IndicatorColor.YELLOW,
+    },
+    [AgentState.LOADING]: {
+      message: t(I18nKey.CHAT_INTERFACE$INITIALIZING_AGENT_LOADING_MESSAGE),
+      indicator: IndicatorColor.DARK_ORANGE,
+    },
+    [AgentState.STOPPED]: {
+      message: t(I18nKey.CHAT_INTERFACE$AGENT_STOPPED_MESSAGE),
+      indicator: IndicatorColor.RED,
+    },
+    [AgentState.FINISHED]: {
+      message: t(I18nKey.CHAT_INTERFACE$AGENT_FINISHED_MESSAGE),
+      indicator: IndicatorColor.GREEN,
+    },
+    [AgentState.REJECTED]: {
+      message: t(I18nKey.CHAT_INTERFACE$AGENT_REJECTED_MESSAGE),
+      indicator: IndicatorColor.YELLOW,
+    },
+    [AgentState.ERROR]: {
+      message: t(I18nKey.CHAT_INTERFACE$AGENT_ERROR_MESSAGE),
+      indicator: IndicatorColor.RED,
+    },
+    [AgentState.AWAITING_USER_CONFIRMATION]: {
+      message: t(
+        I18nKey.CHAT_INTERFACE$AGENT_AWAITING_USER_CONFIRMATION_MESSAGE,
+      ),
+      indicator: IndicatorColor.ORANGE,
+    },
+    [AgentState.USER_CONFIRMED]: {
+      message: t(I18nKey.CHAT_INTERFACE$AGENT_ACTION_USER_CONFIRMED_MESSAGE),
+      indicator: IndicatorColor.GREEN,
+    },
+    [AgentState.USER_REJECTED]: {
+      message: t(I18nKey.CHAT_INTERFACE$AGENT_ACTION_USER_REJECTED_MESSAGE),
+      indicator: IndicatorColor.RED,
+    },
+  };
+
+  // TODO: Extend the agent status, e.g.:
+  // - Agent is typing
+  // - Agent is initializing
+  // - Agent is thinking
+  // - Agent is ready
+  // - Agent is not available
+  useEffect(() => {
+    if (
+      curAgentState === AgentState.AWAITING_USER_INPUT ||
+      curAgentState === AgentState.ERROR ||
+      curAgentState === AgentState.INIT
+    ) {
+      if (document.cookie.indexOf("audio") !== -1) beep();
+    }
+  }, [curAgentState]);
+
+  const [statusMessage, setStatusMessage] = React.useState<string>("");
+
+  React.useEffect(() => {
+    let message = curStatusMessage.message || "";
+    if (curStatusMessage?.id) {
+      const id = curStatusMessage.id.trim();
+      if (i18n.exists(id)) {
+        message = t(curStatusMessage.id.trim()) || message;
+      }
+    }
+    if (curStatusMessage?.type === "error") {
+      toast.error(message);
+      return;
+    }
+    if (curAgentState === AgentState.LOADING && message.trim()) {
+      setStatusMessage(message);
+    } else {
+      setStatusMessage(AgentStatusMap[curAgentState].message);
+    }
+  }, [curStatusMessage.id]);
+
+  React.useEffect(() => {
+    setStatusMessage(AgentStatusMap[curAgentState].message);
+  }, [curAgentState]);
+
+  return (
+    <div className="flex flex-col items-center">
+      <div className="flex items-center bg-neutral-800 px-2 py-1 text-gray-400 rounded-[100px] text-sm gap-[6px]">
+        <div
+          className={`w-2 h-2 rounded-full animate-pulse ${AgentStatusMap[curAgentState].indicator}`}
+        />
+        <span className="text-sm text-stone-400">{statusMessage}</span>
+      </div>
+    </div>
+  );
+}
+
+export default AgentStatusBar;

frontend/src/components/agent-status-map.constant.ts

@@ -1,64 +0,0 @@
-import { I18nKey } from "#/i18n/declaration";
-import AgentState from "#/types/agent-state";
-
-enum IndicatorColor {
-  BLUE = "bg-blue-500",
-  GREEN = "bg-green-500",
-  ORANGE = "bg-orange-500",
-  YELLOW = "bg-yellow-500",
-  RED = "bg-red-500",
-  DARK_ORANGE = "bg-orange-800",
-}
-
-export const AGENT_STATUS_MAP: {
-  [k: string]: { message: string; indicator: IndicatorColor };
-} = {
-  [AgentState.INIT]: {
-    message: I18nKey.CHAT_INTERFACE$AGENT_INIT_MESSAGE,
-    indicator: IndicatorColor.BLUE,
-  },
-  [AgentState.RUNNING]: {
-    message: I18nKey.CHAT_INTERFACE$AGENT_RUNNING_MESSAGE,
-    indicator: IndicatorColor.GREEN,
-  },
-  [AgentState.AWAITING_USER_INPUT]: {
-    message: I18nKey.CHAT_INTERFACE$AGENT_AWAITING_USER_INPUT_MESSAGE,
-    indicator: IndicatorColor.ORANGE,
-  },
-  [AgentState.PAUSED]: {
-    message: I18nKey.CHAT_INTERFACE$AGENT_PAUSED_MESSAGE,
-    indicator: IndicatorColor.YELLOW,
-  },
-  [AgentState.LOADING]: {
-    message: I18nKey.CHAT_INTERFACE$INITIALIZING_AGENT_LOADING_MESSAGE,
-    indicator: IndicatorColor.DARK_ORANGE,
-  },
-  [AgentState.STOPPED]: {
-    message: I18nKey.CHAT_INTERFACE$AGENT_STOPPED_MESSAGE,
-    indicator: IndicatorColor.RED,
-  },
-  [AgentState.FINISHED]: {
-    message: I18nKey.CHAT_INTERFACE$AGENT_FINISHED_MESSAGE,
-    indicator: IndicatorColor.GREEN,
-  },
-  [AgentState.REJECTED]: {
-    message: I18nKey.CHAT_INTERFACE$AGENT_REJECTED_MESSAGE,
-    indicator: IndicatorColor.YELLOW,
-  },
-  [AgentState.ERROR]: {
-    message: I18nKey.CHAT_INTERFACE$AGENT_ERROR_MESSAGE,
-    indicator: IndicatorColor.RED,
-  },
-  [AgentState.AWAITING_USER_CONFIRMATION]: {
-    message: I18nKey.CHAT_INTERFACE$AGENT_AWAITING_USER_CONFIRMATION_MESSAGE,
-    indicator: IndicatorColor.ORANGE,
-  },
-  [AgentState.USER_CONFIRMED]: {
-    message: I18nKey.CHAT_INTERFACE$AGENT_ACTION_USER_CONFIRMED_MESSAGE,
-    indicator: IndicatorColor.GREEN,
-  },
-  [AgentState.USER_REJECTED]: {
-    message: I18nKey.CHAT_INTERFACE$AGENT_ACTION_USER_REJECTED_MESSAGE,
-    indicator: IndicatorColor.RED,
-  },
-};

frontend/src/components/analytics-consent-form-modal.tsx

@@ -1,10 +1,10 @@
-import { ModalButton } from "#/components/shared/buttons/modal-button";
+import { ModalBackdrop } from "./modals/modal-backdrop";
+import ModalBody from "./modals/modal-body";
+import ModalButton from "./buttons/modal-button";
 import {
   BaseModalTitle,
   BaseModalDescription,
-} from "#/components/shared/modals/confirmation-modals/base-modal";
-import { ModalBackdrop } from "#/components/shared/modals/modal-backdrop";
-import { ModalBody } from "#/components/shared/modals/modal-body";
+} from "./modals/confirmation-modals/base-modal";
 import { handleCaptureConsent } from "#/utils/handle-capture-consent";
 
 interface AnalyticsConsentFormModalProps {

frontend/src/components/browser.tsx

@@ -1,9 +1,12 @@
+import { useTranslation } from "react-i18next";
+import { IoIosGlobe } from "react-icons/io";
 import { useSelector } from "react-redux";
+import { I18nKey } from "#/i18n/declaration";
 import { RootState } from "#/store";
-import { BrowserSnapshot } from "./browser-snapshot";
-import { EmptyBrowserMessage } from "./empty-browser-message";
 
-export function BrowserPanel() {
+function BrowserPanel() {
+  const { t } = useTranslation();
+
   const { url, screenshotSrc } = useSelector(
     (state: RootState) => state.browser,
   );
@@ -20,11 +23,21 @@ export function BrowserPanel() {
       </div>
       <div className="overflow-y-auto grow scrollbar-hide rounded-xl">
         {screenshotSrc ? (
-          <BrowserSnapshot src={imgSrc} />
+          <img
+            src={imgSrc}
+            style={{ objectFit: "contain", width: "100%", height: "auto" }}
+            className="rounded-xl"
+            alt="Browser Screenshot"
+          />
         ) : (
-          <EmptyBrowserMessage />
+          <div className="flex flex-col items-center h-full justify-center">
+            <IoIosGlobe size={100} />
+            {t(I18nKey.BROWSER$EMPTY_MESSAGE)}
+          </div>
         )}
       </div>
     </div>
   );
 }
+
+export default BrowserPanel;

frontend/src/components/buttons/modal-button.tsx

@@ -13,7 +13,7 @@ interface ModalButtonProps {
   intent?: string;
 }
 
-export function ModalButton({
+function ModalButton({
   testId,
   variant = "default",
   onClick,
@@ -45,3 +45,5 @@ export function ModalButton({
     </button>
   );
 }
+
+export default ModalButton;

frontend/src/components/chat-input.tsx

@@ -1,8 +1,7 @@
 import React from "react";
 import TextareaAutosize from "react-textarea-autosize";
+import ArrowSendIcon from "#/icons/arrow-send.svg?react";
 import { cn } from "#/utils/utils";
-import { SubmitButton } from "#/components/shared/buttons/submit-button";
-import { StopButton } from "#/components/shared/buttons/stop-button";
 
 interface ChatInputProps {
   name?: string;
@@ -133,10 +132,27 @@ export function ChatInput({
       {showButton && (
         <div className={buttonClassName}>
           {button === "submit" && (
-            <SubmitButton isDisabled={disabled} onClick={handleSubmitMessage} />
+            <button
+              aria-label="Send"
+              disabled={disabled}
+              onClick={handleSubmitMessage}
+              type="submit"
+              className="border border-white rounded-lg w-6 h-6 hover:bg-neutral-500 focus:bg-neutral-500 flex items-center justify-center"
+            >
+              <ArrowSendIcon />
+            </button>
           )}
           {button === "stop" && (
-            <StopButton isDisabled={disabled} onClick={onStop} />
+            <button
+              data-testid="stop-button"
+              aria-label="Stop"
+              disabled={disabled}
+              onClick={onStop}
+              type="button"
+              className="border border-white rounded-lg w-6 h-6 hover:bg-neutral-500 focus:bg-neutral-500 flex items-center justify-center"
+            >
+              <div className="w-[10px] h-[10px] bg-white" />
+            </button>
           )}
         </div>
       )}

frontend/src/components/chat-message.tsx

@@ -1,10 +1,11 @@
 import React from "react";
 import Markdown from "react-markdown";
 import remarkGfm from "remark-gfm";
-import { code } from "../markdown/code";
+import CheckmarkIcon from "#/icons/checkmark.svg?react";
+import CopyIcon from "#/icons/copy.svg?react";
+import { code } from "./markdown/code";
 import { cn } from "#/utils/utils";
-import { ul, ol } from "../markdown/list";
-import { CopyToClipboardButton } from "#/components/shared/buttons/copy-to-clipboard-button";
+import { ul, ol } from "./markdown/list";
 
 interface ChatMessageProps {
   type: "user" | "assistant";
@@ -47,15 +48,26 @@ export function ChatMessage({
         "rounded-xl relative",
         "flex flex-col gap-2",
         type === "user" && " max-w-[305px] p-4 bg-neutral-700 self-end",
-        type === "assistant" && "mt-6 max-w-full bg-tranparent",
+        type === "assistant" && "pb-4 max-w-full bg-tranparent",
       )}
     >
-      <CopyToClipboardButton
-        isHidden={!isHovering}
-        isDisabled={isCopy}
+      <button
+        hidden={!isHovering}
+        disabled={isCopy}
+        data-testid="copy-to-clipboard"
+        type="button"
         onClick={handleCopyToClipboard}
-        mode={isCopy ? "copied" : "copy"}
-      />
+        className={cn(
+          "bg-neutral-700 border border-neutral-600 rounded p-1",
+          "absolute top-1 right-1",
+        )}
+      >
+        {!isCopy ? (
+          <CopyIcon width={15} height={15} />
+        ) : (
+          <CheckmarkIcon width={15} height={15} />
+        )}
+      </button>
       <Markdown
         className="text-sm overflow-auto"
         components={{

frontend/src/components/chat/confirmation-buttons.tsx

@@ -0,0 +1,64 @@
+import { Tooltip } from "@nextui-org/react";
+import { useTranslation } from "react-i18next";
+import ConfirmIcon from "#/assets/confirm";
+import RejectIcon from "#/assets/reject";
+import { I18nKey } from "#/i18n/declaration";
+import AgentState from "#/types/agent-state";
+import { generateAgentStateChangeEvent } from "#/services/agent-state-service";
+import { useWsClient } from "#/context/ws-client-provider";
+
+interface ActionTooltipProps {
+  type: "confirm" | "reject";
+  onClick: () => void;
+}
+
+function ActionTooltip({ type, onClick }: ActionTooltipProps) {
+  const { t } = useTranslation();
+
+  const content =
+    type === "confirm"
+      ? t(I18nKey.CHAT_INTERFACE$USER_CONFIRMED)
+      : t(I18nKey.CHAT_INTERFACE$USER_REJECTED);
+
+  return (
+    <Tooltip content={content} closeDelay={100}>
+      <button
+        data-testid={`action-${type}-button`}
+        type="button"
+        aria-label={type === "confirm" ? "Confirm action" : "Reject action"}
+        className="bg-neutral-700 rounded-full p-1 hover:bg-neutral-800"
+        onClick={onClick}
+      >
+        {type === "confirm" ? <ConfirmIcon /> : <RejectIcon />}
+      </button>
+    </Tooltip>
+  );
+}
+
+function ConfirmationButtons() {
+  const { t } = useTranslation();
+  const { send } = useWsClient();
+
+  const handleStateChange = (state: AgentState) => {
+    const event = generateAgentStateChangeEvent(state);
+    send(event);
+  };
+
+  return (
+    <div className="flex justify-between items-center pt-4">
+      <p>{t(I18nKey.CHAT_INTERFACE$USER_ASK_CONFIRMATION)}</p>
+      <div className="flex items-center gap-3">
+        <ActionTooltip
+          type="confirm"
+          onClick={() => handleStateChange(AgentState.USER_CONFIRMED)}
+        />
+        <ActionTooltip
+          type="reject"
+          onClick={() => handleStateChange(AgentState.USER_REJECTED)}
+        />
+      </div>
+    </div>
+  );
+}
+
+export default ConfirmationButtons;

frontend/src/components/chat/message.d.ts

@@ -0,0 +1,12 @@
+type Message = {
+  sender: "user" | "assistant";
+  content: string;
+  imageUrls: string[];
+  timestamp: string;
+};
+
+type ErrorMessage = {
+  error: boolean;
+  id?: string;
+  message: string;
+};

frontend/src/components/chat/typing-indicator.tsx

@@ -1,4 +1,6 @@
-export function TypingIndicator() {
+import React from "react";
+
+function TypingIndicator(): React.ReactElement {
   return (
     <div className="flex items-center space-x-1.5 bg-neutral-700 px-3 py-1.5 rounded-full">
       <span
@@ -16,3 +18,5 @@ export function TypingIndicator() {
     </div>
   );
 }
+
+export default TypingIndicator;

frontend/src/components/container.tsx

@@ -1,6 +1,14 @@
+import { NavLink } from "@remix-run/react";
 import clsx from "clsx";
 import React from "react";
-import { NavTab } from "./nav-tab";
+
+function BetaBadge() {
+  return (
+    <span className="text-[11px] leading-5 text-root-primary bg-neutral-400 px-1 rounded-xl">
+      Beta
+    </span>
+  );
+}
 
 interface ContainerProps {
   label?: string;
@@ -30,7 +38,23 @@ export function Container({
       {labels && (
         <div className="flex text-xs h-[36px]">
           {labels.map(({ label: l, to, icon, isBeta }) => (
-            <NavTab key={to} to={to} label={l} icon={icon} isBeta={isBeta} />
+            <NavLink
+              end
+              key={to}
+              to={to}
+              className={({ isActive }) =>
+                clsx(
+                  "px-2 border-b border-r border-neutral-600 bg-root-primary flex-1",
+                  "first-of-type:rounded-tl-xl last-of-type:rounded-tr-xl last-of-type:border-r-0",
+                  "flex items-center gap-2",
+                  isActive && "bg-root-secondary",
+                )
+              }
+            >
+              {icon}
+              {l}
+              {isBeta && <BetaBadge />}
+            </NavLink>
           ))}
         </div>
       )}

frontend/src/components/continue-button.tsx

@@ -11,7 +11,7 @@ export function ContinueButton({ onClick }: ContinueButtonProps) {
       type="button"
       onClick={onClick}
       className={cn(
-        "button-base px-2 py-1",
+        "px-2 py-1 bg-neutral-700 border border-neutral-600 rounded",
         "text-[11px] leading-4 tracking-[0.01em] font-[500]",
         "flex items-center gap-2",
       )}