Fix issue #5102: [Bug]: lint-fix.yml workflow doesn't work when (frontend) tests are failing

Co-authored-by: Graham Neubig <neubig@gmail.com>

.github/workflows/ghcr-build.yml

@@ -286,7 +286,6 @@ jobs:
           image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
           image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
 
-          SKIP_CONTAINER_LOGS=true \
           TEST_RUNTIME=eventstream \
           SANDBOX_USER_ID=$(id -u) \
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \
@@ -364,7 +363,6 @@ jobs:
           image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
           image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
 
-          SKIP_CONTAINER_LOGS=true \
           TEST_RUNTIME=eventstream \
           SANDBOX_USER_ID=$(id -u) \
           SANDBOX_RUNTIME_CONTAINER_IMAGE=$image_name \

.github/workflows/lint-fix.yml

@@ -0,0 +1,65 @@
+name: Lint Fix
+
+on:
+  pull_request:
+    types: [labeled]
+
+jobs:
+  lint-fix:
+    if: github.event.label.name == 'lint-fix'
+    name: Fix 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 }}
+
+      # Frontend lint fixes
+      - name: Install Node.js 20
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+      - name: Install frontend dependencies
+        run: |
+          cd frontend
+          npm install --frozen-lockfile
+      - name: Generate i18n declaration files
+        run: |
+          cd frontend
+          npm run make-i18n
+      - name: Fix frontend lint issues
+        run: |
+          cd frontend
+          npm run lint:fix
+
+      # Python lint fixes
+      - name: Set up python
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.12
+          cache: 'pip'
+      - name: Install pre-commit
+        run: pip install pre-commit==3.7.0
+      - name: Fix python lint issues
+        run: |
+          pre-commit run --files openhands/**/* evaluation/**/* tests/**/* --config ./dev_config/python/.pre-commit-config.yaml
+
+      # 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 linting issues"
+          git push

.github/workflows/openhands-resolver.yml

@@ -1,15 +1,269 @@
-name: Resolve Issues with OpenHands
+name: Auto-Fix Tagged Issue with OpenHands
 
 on:
+  workflow_call:
+    inputs:
+      max_iterations:
+        required: false
+        type: number
+        default: 50
+      macro:
+        required: false
+        type: string
+        default: "@openhands-agent"
+    secrets:
+      LLM_MODEL:
+        required: true
+      LLM_API_KEY:
+        required: true
+      LLM_BASE_URL:
+        required: false
+      PAT_TOKEN:
+        required: true
+      PAT_USERNAME:
+        required: true
+
   issues:
     types: [labeled]
   pull_request:
     types: [labeled]
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  pull_request_review:
+    types: [submitted]
+
+permissions:
+  contents: write
+  pull-requests: write
+  issues: write
 
 jobs:
-  call-openhands-resolver:
-    uses: All-Hands-AI/openhands-resolver/.github/workflows/openhands-resolver.yml@main
-    if: github.event.label.name == 'fix-me'
-    with:
-      max_iterations: 50
-    secrets: inherit
+
+  auto-fix:
+    if: |
+      github.event_name == 'workflow_call' ||
+      github.event.label.name == 'fix-me' ||
+      github.event.label.name == 'fix-me-experimental' ||
+
+      (
+        ((github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment') &&
+        startsWith(github.event.comment.body, inputs.macro || '@openhands-agent') &&
+        (github.event.comment.author_association == 'OWNER' || github.event.comment.author_association == 'COLLABORATOR' || github.event.comment.author_association == 'MEMBER')
+        ) ||
+
+        (github.event_name == 'pull_request_review' &&
+        startsWith(github.event.review.body, inputs.macro || '@openhands-agent') &&
+        (github.event.review.author_association == 'OWNER' || github.event.review.author_association == 'COLLABORATOR' || github.event.review.author_association == 'MEMBER')
+        )
+      )
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Get latest versions and create requirements.txt
+        run: |
+          python -m pip index versions openhands-ai > openhands_versions.txt
+          OPENHANDS_VERSION=$(head -n 1 openhands_versions.txt | awk '{print $2}' | tr -d '()')
+          echo "openhands-ai==${OPENHANDS_VERSION}" >> requirements.txt
+          cat requirements.txt
+
+      - name: Cache pip dependencies
+        if: github.event.label.name != 'fix-me-experimental'
+        uses: actions/cache@v3
+        with:
+          path: ${{ env.pythonLocation }}/lib/python3.12/site-packages/*
+          key: ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }}
+
+      - name: Check required environment variables
+        env:
+          LLM_MODEL: ${{ secrets.LLM_MODEL }}
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          PAT_TOKEN: ${{ secrets.PAT_TOKEN }}
+          PAT_USERNAME: ${{ secrets.PAT_USERNAME }}
+        run: |
+          required_vars=("LLM_MODEL" "LLM_API_KEY" "PAT_TOKEN" "PAT_USERNAME")
+          for var in "${required_vars[@]}"; do
+            if [ -z "${!var}" ]; then
+              echo "Error: Required environment variable $var is not set."
+              exit 1
+            fi
+          done
+
+      - name: Set environment variables
+        run: |
+          if [ -n "${{ github.event.review.body }}" ]; then
+            echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
+            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
+          elif [ -n "${{ github.event.issue.pull_request }}" ]; then
+            echo "ISSUE_NUMBER=${{ github.event.issue.number }}" >> $GITHUB_ENV
+            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
+          elif [ -n "${{ github.event.pull_request.number }}" ]; then
+            echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
+            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
+          else
+            echo "ISSUE_NUMBER=${{ github.event.issue.number }}" >> $GITHUB_ENV
+            echo "ISSUE_TYPE=issue" >> $GITHUB_ENV
+          fi
+
+          if [ -n "${{ github.event.review.body }}" ]; then
+            echo "COMMENT_ID=${{ github.event.review.id || 'None' }}" >> $GITHUB_ENV
+          else
+            echo "COMMENT_ID=${{ github.event.comment.id || 'None' }}" >> $GITHUB_ENV
+          fi
+
+          echo "MAX_ITERATIONS=${{ inputs.max_iterations || 50 }}" >> $GITHUB_ENV
+          echo "SANDBOX_ENV_GITHUB_TOKEN=${{ secrets.GITHUB_TOKEN }}" >> $GITHUB_ENV
+
+      - name: Comment on issue with start message
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{secrets.GITHUB_TOKEN}}
+          script: |
+            const issueType = process.env.ISSUE_TYPE;
+            github.rest.issues.createComment({
+              issue_number: ${{ env.ISSUE_NUMBER }},
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: `[OpenHands](https://github.com/All-Hands-AI/OpenHands) started fixing the ${issueType}! You can monitor the progress [here](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}).`
+            });
+
+      - name: Install OpenHands
+        run: |
+          if [ "${{ github.event.label.name }}" == "fix-me-experimental" ]; then
+            python -m pip install --upgrade pip
+            pip install git+https://github.com/all-hands-ai/openhands.git
+          else
+            python -m pip install --upgrade -r requirements.txt
+          fi
+
+      - name: Attempt to resolve issue
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_USERNAME: ${{ secrets.PAT_USERNAME }}
+          LLM_MODEL: ${{ secrets.LLM_MODEL }}
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          PYTHONPATH: ""
+        run: |
+          cd /tmp && python -m openhands.resolver.resolve_issue \
+            --repo ${{ github.repository }} \
+            --issue-number ${{ env.ISSUE_NUMBER }} \
+            --issue-type ${{ env.ISSUE_TYPE }} \
+            --max-iterations ${{ env.MAX_ITERATIONS }} \
+            --comment-id ${{ env.COMMENT_ID }}
+
+      - name: Check resolution result
+        id: check_result
+        run: |
+          if cd /tmp && grep -q '"success":true' output/output.jsonl; then
+            echo "RESOLUTION_SUCCESS=true" >> $GITHUB_OUTPUT
+          else
+            echo "RESOLUTION_SUCCESS=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Upload output.jsonl as artifact
+        uses: actions/upload-artifact@v4
+        if: always() # Upload even if the previous steps fail
+        with:
+          name: resolver-output
+          path: /tmp/output/output.jsonl
+          retention-days: 30 # Keep the artifact for 30 days
+
+      - name: Create draft PR or push branch
+        if: always() # Create PR or branch even if the previous steps fail
+        env:
+          GITHUB_TOKEN: ${{ secrets.PAT_TOKEN }}
+          GITHUB_USERNAME: ${{ secrets.PAT_USERNAME }}
+          LLM_MODEL: ${{ secrets.LLM_MODEL }}
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          PYTHONPATH: ""
+        run: |
+          if [ "${{ steps.check_result.outputs.RESOLUTION_SUCCESS }}" == "true" ]; then
+            cd /tmp && python -m openhands.resolver.send_pull_request \
+              --issue-number ${{ env.ISSUE_NUMBER }} \
+              --pr-type draft | tee pr_result.txt && \
+              grep "draft created" pr_result.txt | sed 's/.*\///g' > pr_number.txt
+          else
+            cd /tmp && python -m openhands.resolver.send_pull_request \
+              --issue-number ${{ env.ISSUE_NUMBER }} \
+              --pr-type branch \
+              --send-on-failure | tee branch_result.txt && \
+              grep "branch created" branch_result.txt | sed 's/.*\///g; s/.expand=1//g' > branch_name.txt
+          fi
+
+      - name: Comment on issue
+        uses: actions/github-script@v7
+        if: always() # Comment on issue even if the previous steps fail
+        with:
+          github-token: ${{secrets.GITHUB_TOKEN}}
+          script: |
+            const fs = require('fs');
+            const issueNumber = ${{ env.ISSUE_NUMBER }};
+            const success = ${{ steps.check_result.outputs.RESOLUTION_SUCCESS }};
+
+            let prNumber = '';
+            let branchName = '';
+            let logContent = '';
+            const noChangesMessage = `No changes to commit for issue #${issueNumber}. Skipping commit.`;
+
+            try {
+              if (success){
+                logContent = fs.readFileSync('/tmp/pr_result.txt', 'utf8').trim();
+              } else {
+                logContent = fs.readFileSync('/tmp/branch_result.txt', 'utf8').trim();
+              }
+            } catch (error) {
+              console.error('Error reading results file:', error);
+            }
+
+            try {
+              if (success) {
+                prNumber = fs.readFileSync('/tmp/pr_number.txt', 'utf8').trim();
+              } else {
+                branchName = fs.readFileSync('/tmp/branch_name.txt', 'utf8').trim();
+              }
+            } catch (error) {
+              console.error('Error reading file:', error);
+            }
+
+            if (logContent.includes(noChangesMessage)) {
+              github.rest.issues.createComment({
+                issue_number: issueNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: `The workflow to fix this issue encountered an error. Openhands failed to create any code changes.`
+              });
+            } else if (success && prNumber) {
+              github.rest.issues.createComment({
+                issue_number: issueNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: `A potential fix has been generated and a draft PR #${prNumber} has been created. Please review the changes.`
+              });
+            } else if (!success && branchName) {
+              github.rest.issues.createComment({
+                issue_number: issueNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: `An attempt was made to automatically fix this issue, but it was unsuccessful. A branch named '${branchName}' has been created with the attempted changes. You can view the branch [here](https://github.com/${context.repo.owner}/${context.repo.repo}/tree/${branchName}). Manual intervention may be required.`
+              });
+            } else {
+              github.rest.issues.createComment({
+                issue_number: issueNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: `The workflow to fix this issue encountered an error. Please check the [workflow logs](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}) for more information.`
+              });
+            }

.gitignore

@@ -176,6 +176,9 @@ evaluation/gorilla/data
 evaluation/toolqa/data
 evaluation/scienceagentbench/benchmark
 
+# openhands resolver
+output/
+
 # frontend
 
 # dependencies

COMMUNITY.md

@@ -0,0 +1,43 @@
+# 🙌 The OpenHands Community
+
+The OpenHands community is built around the belief that (1) AI and AI agents are going to fundamentally change the way
+we build software, and (2) if this is true, we should do everything we can to make sure that the benefits provided by
+such powerful technology are accessible to everyone.
+
+If this resonates with you, we'd love to have you join us in our quest!
+
+## 🤝 How to Join
+
+Check out our [How to Join the Community section.](https://github.com/All-Hands-AI/OpenHands?tab=readme-ov-file#-how-to-join-the-community)
+
+## 💪 Becoming a Contributor
+
+We welcome contributions from everyone! Whether you're a developer, a researcher, or simply enthusiastic about advancing
+the field of software engineering with AI, there are many ways to get involved:
+
+- **Code Contributions:** Help us develop new core functionality, improve our agents, improve the frontend and other
+interfaces, or anything else that would help make OpenHands better.
+- **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in
+evaluating the models, or suggest improvements.
+- **Feedback and Testing:** Use the OpenHands toolset, report bugs, suggest features, or provide feedback on usability.
+
+For details, please check [CONTRIBUTING.md](./CONTRIBUTING.md).
+
+## Code of Conduct
+
+We have a [Code of Conduct](./CODE_OF_CONDUCT.md) that we expect all contributors to adhere to.
+Long story short, we are aiming for an open, welcoming, diverse, inclusive, and healthy community.
+All contributors are expected to contribute to building this sort of community.
+
+## 🛠️ Becoming a Maintainer
+
+For contributors who have made significant and sustained contributions to the project, there is a possibility of joining
+the maintainer team. The process for this is as follows:
+
+1. Any contributor who has made sustained and high-quality contributions to the codebase can be nominated by any
+maintainer. If you feel that you may qualify you can reach out to any of the maintainers that have reviewed your PRs and ask if you can be nominated.
+2. Once a maintainer nominates a new maintainer, there will be a discussion period among the maintainers for at least 3 days.
+3. If no concerns are raised the nomination will be accepted by acclamation, and if concerns are raised there will be a discussion and possible vote.
+
+Note that just making many PRs does not immediately imply that you will become a maintainer. We will be looking
+at sustained high-quality contributions over a period of time, as well as good teamwork and adherence to our [Code of Conduct](./CODE_OF_CONDUCT.md).

CONTRIBUTING.md

@@ -92,3 +92,32 @@ You may also check out previous PRs in the [PR list](https://github.com/All-Hand
 
 If your changes are user-facing (e.g. a new feature in the UI, a change in behavior, or a bugfix)
 please include a short message that we can add to our changelog.
+
+## How to Make Effective Contributions
+
+### Opening Issues
+
+If you notice any bugs or have any feature requests please open them via the [issues page](https://github.com/All-Hands-AI/OpenHands/issues). We will triage based on how critical the bug is or how potentially useful the improvement is, discuss, and implement the ones that the community has interest/effort for.
+
+Further, if you see an issue you like, please leave a "thumbs-up" or a comment, which will help us prioritize.
+
+### Making Pull Requests
+
+We're generally happy to consider all PRs, with the evaluation process varying based on the type of change:
+
+#### For Small Improvements
+
+Small improvements with few downsides are typically reviewed and approved quickly.
+One thing to check when making changes is to ensure that all continuous integration tests pass, which you can check before getting a review.
+
+#### For Core Agent Changes
+
+We need to be more careful with changes to the core agent, as it is imperative to maintain high quality. These PRs are evaluated based on three key metrics:
+
+1. **Accuracy**
+2. **Efficiency**
+3. **Code Complexity**
+
+If it improves accuracy, efficiency, or both with only a minimal change to code quality, that's great we're happy to merge it in!
+If there are bigger tradeoffs (e.g. helping efficiency a lot and hurting accuracy a little) we might want to put it behind a feature flag.
+Either way, please feel free to discuss on github issues or slack, and we will give guidance and preliminary feedback.

Development.md

@@ -38,7 +38,9 @@ make build
 ```
 
 ### 3. Configuring the Language Model
-OpenHands supports a diverse array of Language Models (LMs) through the powerful [litellm](https://docs.litellm.ai) library. By default, we've chosen the mighty GPT-4 from OpenAI as our go-to model, but the world is your oyster! You can unleash the potential of Anthropic's suave Claude, the enigmatic Llama, or any other LM that piques your interest.
+OpenHands supports a diverse array of Language Models (LMs) through the powerful [litellm](https://docs.litellm.ai) library.
+By default, we've chosen Claude Sonnet 3.5 as our go-to model, but the world is your oyster! You can unleash the
+potential of any other LM that piques your interest.
 
 To configure the LM of your choice, run:
 
@@ -52,10 +54,7 @@ To configure the LM of your choice, run:
    Environment variables > config.toml variables > default variables
 
 **Note on Alternative Models:**
-Some alternative models may prove more challenging to tame than others. Fear not, brave adventurer! We shall soon unveil LLM-specific documentation to guide you on your quest.
-And if you've already mastered the art of wielding a model other than OpenAI's GPT, we encourage you to share your setup instructions with us by creating instructions and adding it [to our documentation](https://github.com/All-Hands-AI/OpenHands/tree/main/docs/modules/usage/llms).
-
-For a full list of the LM providers and models available, please consult the [litellm documentation](https://docs.litellm.ai/docs/providers).
+See [our documentation](https://docs.all-hands.dev/modules/usage/llms) for recommended models.
 
 ### 4. Running the application
 #### Option A: Run the Full Application
@@ -98,9 +97,10 @@ poetry run pytest ./tests/unit/test_*.py
 2. Update the poetry.lock file via `poetry lock --no-update`
 
 ### 9. Use existing Docker image
-To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker container image. Follow these steps:
-1. Set the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
-2. Example: export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.13-nikolaik
+To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker container image by
+setting the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
+
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.14-nikolaik`
 
 ## Develop inside Docker container
 

ISSUE_TRIAGE.md

@@ -6,9 +6,9 @@ These are the procedures and guidelines on how issues are triaged in this repo b
 * Issues may be tagged with what it relates to (**backend**, **frontend**, **agent quality**, etc.)
 
 ## Severity
-* **Low**: Minor issues, single user report
-* **Medium**: Affecting multiple users
-* **Critical**: Affecting all users or potential security issues
+* **Low**: Minor issues or affecting single user.
+* **Medium**: Affecting multiple users.
+* **Critical**: Affecting all users or potential security issues.
 
 ## Effort
 * Issues may be estimated with effort required (**small effort**, **medium effort**, **large effort**)
@@ -17,9 +17,9 @@ These are the procedures and guidelines on how issues are triaged in this repo b
 * Issues with low implementation difficulty may be tagged with **good first issue**
 
 ## Not Enough Information
-* User is asked to provide more information (logs, how to reproduce, etc.) when the issue is not clear
-* If an issue is unclear and the author does not provide more information or respond to a request, the issue may be closed as **not planned** (Usually after a week)
+* User is asked to provide more information (logs, how to reproduce, etc.) when the issue is not clear.
+* If an issue is unclear and the author does not provide more information or respond to a request, the issue may be closed as **not planned** (Usually after a week).
 
 ## Multiple Requests/Fixes in One Issue
-* These issues will be narrowed down to one request/fix so the issue is more easily tracked and fixed
-* Issues may be broken down into multiple issues if required
+* These issues will be narrowed down to one request/fix so the issue is more easily tracked and fixed.
+* Issues may be broken down into multiple issues if required.

README.md

@@ -38,16 +38,16 @@ See the [Installation](https://docs.all-hands.dev/modules/usage/installation) gu
 system requirements and more information.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.14-nikolaik
 
 docker run -it --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.14-nikolaik \
+    -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
-    -e LOG_ALL_EVENTS=true \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.13
+    docker.all-hands.dev/all-hands-ai/openhands:0.14
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
@@ -61,7 +61,7 @@ works best, but you have [many options](https://docs.all-hands.dev/modules/usage
 You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes),
 run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
 interact with it via a [friendly CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode),
-or run it on tagged issues with [a github action](https://github.com/All-Hands-AI/OpenHands-resolver).
+or run it on tagged issues with [a github action](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/resolver/README.md).
 
 Visit [Installation](https://docs.all-hands.dev/modules/usage/installation) for more information and setup instructions.
 
@@ -77,25 +77,16 @@ To learn more about the project, and for tips on using OpenHands,
 There you'll find resources on how to use different LLM providers,
 troubleshooting resources, and advanced configuration options.
 
-## 🤝 How to Contribute
+## 🤝 How to Join the Community
 
-OpenHands is a community-driven project, and we welcome contributions from everyone.
-Whether you're a developer, a researcher, or simply enthusiastic about advancing the field of
-software engineering with AI, there are many ways to get involved:
+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:
 
-- **Code Contributions:** Help us develop new agents, core functionality, the frontend and other interfaces, or sandboxing solutions.
-- **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in evaluating the models, or suggest improvements.
-- **Feedback and Testing:** Use the OpenHands toolset, report bugs, suggest features, or provide feedback on usability.
+- [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.
 
-For details, please check [CONTRIBUTING.md](./CONTRIBUTING.md).
-
-## 🤖 Join Our Community
-
-Whether you're a developer, a researcher, or simply enthusiastic about OpenHands, we'd love to have you in our community.
-Let's make software engineering better together!
-
-- [Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-2tom0er4l-JeNUGHt_AxpEfIBstbLPiw) - Here we talk about research, architecture, and future development.
-- [Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
+See more about the community in [COMMUNITY.md](./COMMUNITY.md) or find details on contributing in [CONTRIBUTING.md](./CONTRIBUTING.md).
 
 ## 📈 Progress
 

compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.13-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.14-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

containers/dev/compose.yml

@@ -11,7 +11,7 @@ services:
       - BACKEND_HOST=${BACKEND_HOST:-"0.0.0.0"}
       - SANDBOX_API_HOSTNAME=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.13-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.14-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/github-action.md

@@ -14,4 +14,4 @@ Pour utiliser l'Action GitHub OpenHands dans le dépôt OpenHands, un mainteneur
 
 ## Installation de l'Action dans un nouveau dépôt
 
-Pour installer l'Action GitHub OpenHands dans votre propre dépôt, suivez les [instructions dans le dépôt OpenHands Resolver](https://github.com/All-Hands-AI/OpenHands-resolver?tab=readme-ov-file#using-the-github-actions-workflow).
+Pour installer l'Action GitHub OpenHands dans votre propre dépôt, suivez les [instructions dans le dépôt OpenHands Resolver](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/resolver/README.md).

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/github-action.md

@@ -12,4 +12,4 @@
 
 ## 在新仓库中安装 Action
 
-要在你自己的仓库中安装 OpenHands GitHub Action，请按照 [OpenHands Resolver 仓库中的说明](https://github.com/All-Hands-AI/OpenHands-resolver?tab=readme-ov-file#using-the-github-actions-workflow) 进行操作。
+要在你自己的仓库中安装 OpenHands GitHub Action，请按照 [OpenHands Resolver 仓库中的说明](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/resolver/README.md) 进行操作。

docs/modules/usage/about.md

@@ -1,6 +1,6 @@
-# 📚 Misc
+# About OpenHands
 
-## ⭐️ Research Strategy
+## Research Strategy
 
 Achieving full replication of production-grade applications with LLMs is a complex endeavor. Our strategy involves:
 
@@ -9,34 +9,11 @@ Achieving full replication of production-grade applications with LLMs is a compl
 3. **Task Planning:** Developing capabilities for bug detection, codebase management, and optimization
 4. **Evaluation:** Establishing comprehensive evaluation metrics to better understand and improve our models
 
-## 🚧 Default Agent
+## Default Agent
 
 Our default Agent is currently the [CodeActAgent](agents), which is capable of generating code and handling files.
 
-## 🤝 How to Contribute
-
-OpenHands is a community-driven project, and we welcome contributions from everyone. Whether you're a developer, a researcher, or simply enthusiastic about advancing the field of software engineering with AI, there are many ways to get involved:
-
-- **Code Contributions:** Help us develop the core functionalities, frontend interface, or sandboxing solutions
-- **Research and Evaluation:** Contribute to our understanding of LLMs in software engineering, participate in evaluating the models, or suggest improvements
-- **Feedback and Testing:** Use the OpenHands toolset, report bugs, suggest features, or provide feedback on usability
-
-For details, please check [this document](https://github.com/All-Hands-AI/OpenHands/blob/main/CONTRIBUTING.md).
-
-## 🤖 Join Our Community
-
-We have both Slack workspace for the collaboration on building OpenHands and Discord server for discussion about anything related, e.g., this project, LLM, agent, etc.
-
-- [Slack workspace](https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA)
-- [Discord server](https://discord.gg/ESHStjSjD4)
-
-If you would love to contribute, feel free to join our community. Let's simplify software engineering together!
-
-🐚 **Code less, make more with OpenHands.**
-
-[![Star History Chart](https://api.star-history.com/svg?repos=All-Hands-AI/OpenHands&type=Date)](https://star-history.com/#All-Hands-AI/OpenHands&Date)
-
-## 🛠️ Built With
+## Built With
 
 OpenHands is built using a combination of powerful frameworks and libraries, providing a robust foundation for its development. Here are the key technologies used in the project:
 
@@ -44,6 +21,6 @@ OpenHands is built using a combination of powerful frameworks and libraries, pro
 
 Please note that the selection of these technologies is in progress, and additional technologies may be added or existing ones may be removed as the project evolves. We strive to adopt the most suitable and efficient tools to enhance the capabilities of OpenHands.
 
-## 📜 License
+## License
 
-Distributed under the MIT License. See [our license](https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE) for more information.
+Distributed under MIT [License](https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE).

docs/modules/usage/how-to/cli-mode.md

@@ -50,7 +50,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.14-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -59,7 +59,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.13 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.14 \
     python -m openhands.core.cli
 ```
 

docs/modules/usage/how-to/custom-sandbox-guide.md

@@ -62,25 +62,3 @@ Run OpenHands by running ```make run``` in the top level directory.
 ## Technical Explanation
 
 Please refer to [custom docker image section of the runtime documentation](https://docs.all-hands.dev/modules/usage/architecture/runtime#advanced-how-openhands-builds-and-maintains-od-runtime-images) for more details.
-
-## Troubleshooting / Errors
-
-### Error: ```useradd: UID 1000 is not unique```
-
-If you see this error in the console output it is because OpenHands is trying to create the openhands user in the sandbox with a UID of 1000, however this UID is already being used in the image (for some reason). To fix this change the sandbox_user_id field in the config.toml file to a different value:
-
-```toml
-[core]
-workspace_base="./workspace"
-run_as_openhands=true
-sandbox_base_container_image="custom_image"
-sandbox_user_id="1001"
-```
-
-### Port use errors
-
-If you see an error about a port being in use or unavailable, try deleting all running Docker Containers (run `docker ps` and `docker rm` relevant containers) and then re-running ```make run``` .
-
-## Discuss
-
-For other issues or questions join the [Slack](https://join.slack.com/t/opendevin/shared_invite/zt-2oikve2hu-UDxHeo8nsE69y6T7yFX_BA) or [Discord](https://discord.gg/ESHStjSjD4) and ask!

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

@@ -12,4 +12,5 @@ To use the OpenHands GitHub Action in the OpenHands repository, an OpenHands mai
 
 ## Installing the Action in a New Repository
 
-To install the OpenHands GitHub Action in your own repository, follow the [directions in the OpenHands Resolver repo](https://github.com/All-Hands-AI/OpenHands-resolver?tab=readme-ov-file#using-the-github-actions-workflow).
+To install the OpenHands GitHub Action in your own repository, follow
+the [README for the OpenHands Resolver](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/resolver/README.md).

docs/modules/usage/how-to/headless-mode.md

@@ -44,7 +44,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.14-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -54,6 +54,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.13 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.14 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```

docs/modules/usage/installation.mdx

@@ -11,16 +11,16 @@
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.14-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.14-nikolaik \
+    -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
-    -e LOG_ALL_EVENTS=true \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.13
+    docker.all-hands.dev/all-hands-ai/openhands:0.14
 ```
 
 You can also run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), as an [interactive CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), or using the [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action).

docs/modules/usage/llms/litellm-proxy.md

@@ -0,0 +1,20 @@
+# LiteLLM Proxy
+
+OpenHands supports using the [LiteLLM proxy](https://docs.litellm.ai/docs/proxy/quick_start) to access various LLM providers.
+
+## Configuration
+
+To use LiteLLM proxy with OpenHands, you need to:
+
+1. Set up a LiteLLM proxy server (see [LiteLLM documentation](https://docs.litellm.ai/docs/proxy/quick_start))
+2. When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings:
+  * Enable `Advanced Options`
+  * `Custom Model` to the prefix `litellm_proxy/` + the model you will be using (e.g. `litellm_proxy/anthropic.claude-3-5-sonnet-20241022-v2:0`)
+  * `Base URL` to your LiteLLM proxy URL (e.g. `https://your-litellm-proxy.com`)
+  * `API Key` to your LiteLLM proxy API key
+
+## Supported Models
+
+The supported models depend on your LiteLLM proxy configuration. OpenHands supports any model that your LiteLLM proxy is configured to handle.
+
+Refer to your LiteLLM proxy configuration for the list of available models and their names.

docs/modules/usage/llms/llms.md

@@ -63,6 +63,7 @@ We have a few guides for running OpenHands with specific model providers:
 - [Azure](llms/azure-llms)
 - [Google](llms/google-llms)
 - [Groq](llms/groq)
+- [LiteLLM Proxy](llms/litellm-proxy)
 - [OpenAI](llms/openai-llms)
 - [OpenRouter](llms/openrouter)
 

docs/modules/usage/runtimes.md

@@ -49,7 +49,7 @@ but seems to work well on most systems.
 
 ## All Hands Runtime
 The All Hands Runtime is currently in beta. You can request access by joining
-the #remote-runtime-limited-beta channel on Slack (see the README for an invite).
+the #remote-runtime-limited-beta channel on Slack ([see the README](https://github.com/All-Hands-AI/OpenHands?tab=readme-ov-file#-join-our-community) for an invite).
 
 To use the All Hands Runtime, set the following environment variables when
 starting OpenHands:
@@ -59,14 +59,14 @@ docker run # ...
     -e RUNTIME=remote \
     -e SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.app.all-hands.dev" \
     -e SANDBOX_API_KEY="your-all-hands-api-key" \
-    -e SANDBOX_KEEP_REMOTE_RUNTIME_ALIVE="true" \
+    -e SANDBOX_KEEP_RUNTIME_ALIVE="true" \
     # ...
 ```
 
 ## Modal Runtime
 Our partners at [Modal](https://modal.com/) have also provided a runtime for OpenHands.
 
-To use the Modal Runtime, create an account, and then [create an API key](https://modal.com/settings)
+To use the Modal Runtime, create an account, and then [create an API key.](https://modal.com/settings)
 
 You'll then need to set the following environment variables when starting OpenHands:
 ```bash

docs/sidebars.ts

@@ -76,6 +76,11 @@ const sidebars: SidebarsConfig = {
                   label: 'Groq',
                   id: 'usage/llms/groq',
                 },
+                {
+                  type: 'doc',
+                  label: 'LiteLLM Proxy',
+                  id: 'usage/llms/litellm-proxy',
+                },
                 {
                   type: 'doc',
                   label: 'OpenAI',

evaluation/EDA/game.py

@@ -87,9 +87,7 @@ class Q20Game:
         # others
         bingo, anwser_reply = self.judge_winner(response)
         if bingo:
-            return (
-                'You are bingo! quit now, run: <execute_bash> exit </execute_bash>.\n'
-            )
+            return 'You are bingo! Use the "finish" tool to finish the interaction.\n'
         if self.curr_turn == self.num_turns - 2:
             anwser_reply += " You must guess now, what's it?"
         return anwser_reply

evaluation/aider_bench/README.md

@@ -56,6 +56,20 @@ You can update the arguments in the script
 ./evaluation/aider_bench/scripts/run_infer.sh eval_gpt35_turbo HEAD CodeActAgent 100 1 "1,3,10"
 ```
 
+### Run Inference on `RemoteRuntime` (experimental)
+
+This is in limited beta. Contact Xingyao over slack if you want to try this out!
+
+```bash
+./evaluation/aider_bench/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [eval-num-workers] [eval_ids]
+
+# Example - This runs evaluation on CodeActAgent for 133 instances on aider_bench test set, with 2 workers running in parallel
+export ALLHANDS_API_KEY="YOUR-API-KEY"
+export RUNTIME=remote
+export SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev"
+./evaluation/aider_bench/scripts/run_infer.sh llm.eval HEAD CodeActAgent 133 2
+```
+
 ## Summarize Results
 
 ```bash

evaluation/aider_bench/run_infer.py

@@ -58,6 +58,9 @@ def get_config(
             use_host_network=False,
             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=1800,
         ),
         # do not mount workspace
         workspace_base=None,

evaluation/biocoder/run_infer.py

@@ -40,7 +40,7 @@ AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
 }
 
 AGENT_CLS_TO_INST_SUFFIX = {
-    'CodeActAgent': 'When you think you have fixed the issue through code changes, please run the following command: <execute_bash> exit </execute_bash>.\n'
+    'CodeActAgent': 'When you think you have fixed the issue through code changes, please finish the interaction using the "finish" tool.\n'
 }
 
 FILE_EXT_MAP = {

evaluation/bird/run_infer.py

@@ -40,7 +40,7 @@ from openhands.utils.async_utils import call_async_from_sync
 def codeact_user_response(state: State) -> str:
     msg = (
         'Please continue working on the task on whatever approach you think is suitable.\n'
-        'If you think you have completed the SQL, please run the following command: <execute_bash> exit </execute_bash>.\n'
+        'If you think you have completed the SQL, please finish the interaction using the "finish" tool.\n'
         'IMPORTANT: YOU SHOULD NEVER ASK FOR HUMAN HELP OR USE THE INTERNET TO SOLVE THIS TASK.\n'
     )
     if state.history:
@@ -54,7 +54,7 @@ def codeact_user_response(state: State) -> str:
             # let the agent know that it can give up when it has tried 3 times
             return (
                 msg
-                + 'If you want to give up, run: <execute_bash> exit </execute_bash>.\n'
+                + 'If you want to give up, use the "finish" tool to finish the interaction.\n'
             )
     return msg
 
@@ -64,7 +64,7 @@ AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
 }
 
 AGENT_CLS_TO_INST_SUFFIX = {
-    'CodeActAgent': 'When you think you have fixed the issue through code changes, please run the following command: <execute_bash> exit </execute_bash>.\n'
+    'CodeActAgent': 'When you think you have fixed the issue through code changes, please finish the interaction using the "finish" tool.\n'
 }
 
 

evaluation/discoverybench/run_infer.py

@@ -55,7 +55,7 @@ AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
 }
 
 AGENT_CLS_TO_INST_SUFFIX = {
-    'CodeActAgent': 'When you think you have fixed the issue through code changes, please run the following command: <execute_bash> exit </execute_bash>.\n'
+    'CodeActAgent': 'When you think you have fixed the issue through code changes, please finish the interaction using the "finish" tool.\n'
 }
 
 

evaluation/gorilla/run_infer.py

@@ -33,7 +33,7 @@ AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
 }
 
 AGENT_CLS_TO_INST_SUFFIX = {
-    'CodeActAgent': 'When you think you have completed the request, please run the following command: <execute_bash> exit </execute_bash>.\n'
+    'CodeActAgent': 'When you think you have completed the request, please finish the interaction using the "finish" tool.\n'
 }
 
 

evaluation/gpqa/run_infer.py

@@ -87,11 +87,10 @@ def gpqa_codeact_user_response(
     msg = (
         'Please continue working on the task on whatever approach you think is suitable.\n'
         'Feel free to use all tools for calculations and solving the problem, and web-search for finding relevant facts during the process if needed\n'
-        'If you have finished reporting the answer in the expected format, (and only once that is done), please run the following command to submit: <execute_bash> exit </execute_bash>.\n'
+        'If you have finished reporting the answer in the expected format, (and only once that is done), please use the "finish" tool to finish the interaction.\n'
         'Again you are being told a million times to first report the answer in the requested format (see again below for reference) before exiting. DO NOT EXIT WITHOUT REPORTING THE ANSWER FIRST.\n'
         'That is, when you have decided on the answer report in the following format:\n'
         f'{ACTION_FORMAT}\n'
-        '<execute_bash> exit </execute_bash>\n'
         'IMPORTANT: YOU SHOULD NEVER ASK FOR HUMAN HELP TO SOLVE THIS TASK.\n'
     )
     return msg
@@ -100,7 +99,7 @@ def gpqa_codeact_user_response(
 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {'CodeActAgent': gpqa_codeact_user_response}
 
 AGENT_CLS_TO_INST_SUFFIX = {
-    'CodeActAgent': '\n\n SUPER IMPORTANT: When you think you have solved the question, first report it back to the user in the requested format. Only once that is done, in the next turn, please run the following command: <execute_bash> exit </execute_bash>.\n'
+    'CodeActAgent': '\n\n SUPER IMPORTANT: When you think you have solved the question, first report it back to the user in the requested format. Only once that is done, in the next turn, please finish the interaction using the "finish" tool.\n'
 }
 
 
@@ -205,12 +204,11 @@ Additional Instructions:
 - Do not try to solve the question in a single step. Break it down into smaller steps.
 - You should ONLY interact with the environment provided to you AND NEVER ASK FOR HUMAN HELP.
 
-- SUPER IMPORTANT: When you have reported the answer to the user in the requested format, (and only once that is done) in the next turn, please run the following command: <execute_bash> exit </execute_bash>.
+- SUPER IMPORTANT: When you have reported the answer to the user in the requested format, (and only once that is done) in the next turn, please finish the interaction using the "finish" tool.
 - Again you are being told a million times to first report the answer in the requested format (see again below for reference) before exiting. DO NOT EXIT WITHOUT REPORTING THE ANSWER FIRST.
     That is, when you have decided on the answer report in the following format:
 
 {ACTION_FORMAT}
-<execute_bash> exit </execute_bash>
 
 Again do not quit without reporting the answer first.
 Ok now its time to start solving the question. Good luck!

evaluation/humanevalfix/README.md

@@ -23,7 +23,7 @@ For each problem, OpenHands is given a set number of iterations to fix the faili
 ```
 {
     "task_id": "Python/2",
-    "instruction": "Please fix the function in Python__2.py such that all test cases pass.\nEnvironment has been set up for you to start working. You may assume all necessary tools are installed.\n\n# Problem Statement\ndef truncate_number(number: float) -> float:\n    return number % 1.0 + 1.0\n\n\n\n\n\n\ndef check(truncate_number):\n    assert truncate_number(3.5) == 0.5\n    assert abs(truncate_number(1.33) - 0.33) < 1e-6\n    assert abs(truncate_number(123.456) - 0.456) < 1e-6\n\ncheck(truncate_number)\n\nIMPORTANT: You should ONLY interact with the environment provided to you AND NEVER ASK FOR HUMAN HELP.\nYou should NOT modify any existing test case files. If needed, you can add new test cases in a NEW file to reproduce the issue.\nYou SHOULD INCLUDE PROPER INDENTATION in your edit commands.\nWhen you think you have fixed the issue through code changes, please run the following command: <execute_bash> exit </execute_bash>.\n",
+    "instruction": "Please fix the function in Python__2.py such that all test cases pass.\nEnvironment has been set up for you to start working. You may assume all necessary tools are installed.\n\n# Problem Statement\ndef truncate_number(number: float) -> float:\n    return number % 1.0 + 1.0\n\n\n\n\n\n\ndef check(truncate_number):\n    assert truncate_number(3.5) == 0.5\n    assert abs(truncate_number(1.33) - 0.33) < 1e-6\n    assert abs(truncate_number(123.456) - 0.456) < 1e-6\n\ncheck(truncate_number)\n\nIMPORTANT: You should ONLY interact with the environment provided to you AND NEVER ASK FOR HUMAN HELP.\nYou should NOT modify any existing test case files. If needed, you can add new test cases in a NEW file to reproduce the issue.\nYou SHOULD INCLUDE PROPER INDENTATION in your edit commands.\nWhen you think you have fixed the issue through code changes, please finish the interaction using the "finish" tool.\n",
     "metadata": {
         "agent_class": "CodeActAgent",
         "model_name": "gpt-4",
@@ -38,10 +38,10 @@ For each problem, OpenHands is given a set number of iterations to fix the faili
                 "id": 27,
                 "timestamp": "2024-05-22T20:57:24.688651",
                 "source": "user",
-                "message": "Please fix the function in Python__2.py such that all test cases pass.\nEnvironment has been set up for you to start working. You may assume all necessary tools are installed.\n\n# Problem Statement\ndef truncate_number(number: float) -> float:\n    return number % 1.0 + 1.0\n\n\n\n\n\n\ndef check(truncate_number):\n    assert truncate_number(3.5) == 0.5\n    assert abs(truncate_number(1.33) - 0.33) < 1e-6\n    assert abs(truncate_number(123.456) - 0.456) < 1e-6\n\ncheck(truncate_number)\n\nIMPORTANT: You should ONLY interact with the environment provided to you AND NEVER ASK FOR HUMAN HELP.\nYou should NOT modify any existing test case files. If needed, you can add new test cases in a NEW file to reproduce the issue.\nYou SHOULD INCLUDE PROPER INDENTATION in your edit commands.\nWhen you think you have fixed the issue through code changes, please run the following command: <execute_bash> exit </execute_bash>.\n",
+                "message": "Please fix the function in Python__2.py such that all test cases pass.\nEnvironment has been set up for you to start working. You may assume all necessary tools are installed.\n\n# Problem Statement\ndef truncate_number(number: float) -> float:\n    return number % 1.0 + 1.0\n\n\n\n\n\n\ndef check(truncate_number):\n    assert truncate_number(3.5) == 0.5\n    assert abs(truncate_number(1.33) - 0.33) < 1e-6\n    assert abs(truncate_number(123.456) - 0.456) < 1e-6\n\ncheck(truncate_number)\n\nIMPORTANT: You should ONLY interact with the environment provided to you AND NEVER ASK FOR HUMAN HELP.\nYou should NOT modify any existing test case files. If needed, you can add new test cases in a NEW file to reproduce the issue.\nYou SHOULD INCLUDE PROPER INDENTATION in your edit commands.\nWhen you think you have fixed the issue through code changes, please finish the interaction using the "finish" tool.\n",
                 "action": "message",
                 "args": {
-                    "content": "Please fix the function in Python__2.py such that all test cases pass.\nEnvironment has been set up for you to start working. You may assume all necessary tools are installed.\n\n# Problem Statement\ndef truncate_number(number: float) -> float:\n    return number % 1.0 + 1.0\n\n\n\n\n\n\ndef check(truncate_number):\n    assert truncate_number(3.5) == 0.5\n    assert abs(truncate_number(1.33) - 0.33) < 1e-6\n    assert abs(truncate_number(123.456) - 0.456) < 1e-6\n\ncheck(truncate_number)\n\nIMPORTANT: You should ONLY interact with the environment provided to you AND NEVER ASK FOR HUMAN HELP.\nYou should NOT modify any existing test case files. If needed, you can add new test cases in a NEW file to reproduce the issue.\nYou SHOULD INCLUDE PROPER INDENTATION in your edit commands.\nWhen you think you have fixed the issue through code changes, please run the following command: <execute_bash> exit </execute_bash>.\n",
+                    "content": "Please fix the function in Python__2.py such that all test cases pass.\nEnvironment has been set up for you to start working. You may assume all necessary tools are installed.\n\n# Problem Statement\ndef truncate_number(number: float) -> float:\n    return number % 1.0 + 1.0\n\n\n\n\n\n\ndef check(truncate_number):\n    assert truncate_number(3.5) == 0.5\n    assert abs(truncate_number(1.33) - 0.33) < 1e-6\n    assert abs(truncate_number(123.456) - 0.456) < 1e-6\n\ncheck(truncate_number)\n\nIMPORTANT: You should ONLY interact with the environment provided to you AND NEVER ASK FOR HUMAN HELP.\nYou should NOT modify any existing test case files. If needed, you can add new test cases in a NEW file to reproduce the issue.\nYou SHOULD INCLUDE PROPER INDENTATION in your edit commands.\nWhen you think you have fixed the issue through code changes, please finish the interaction using the "finish" tool.\n",
                     "wait_for_response": false
                 }
             },

evaluation/humanevalfix/run_infer.py

@@ -75,7 +75,7 @@ AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
 }
 
 AGENT_CLS_TO_INST_SUFFIX = {
-    'CodeActAgent': 'When you think you have fixed the issue through code changes, please run the following command: <execute_bash> exit </execute_bash>.\n'
+    'CodeActAgent': 'When you think you have fixed the issue through code changes, please finish the interaction using the "finish" tool.\n'
 }
 
 

evaluation/miniwob/README.md

@@ -16,6 +16,20 @@ Access with browser the above MiniWoB URLs and see if they load correctly.
 ./evaluation/miniwob/scripts/run_infer.sh llm.claude-35-sonnet-eval
 ```
 
+### Run Inference on `RemoteRuntime` (experimental)
+
+This is in limited beta. Contact Xingyao over slack if you want to try this out!
+
+```bash
+./evaluation/miniwob/scripts/run_infer.sh [model_config] [git-version] [agent] [note] [eval_limit] [num_workers]
+
+# Example - This runs evaluation on BrowsingAgent for 125 instances on miniwob, with 2 workers running in parallel
+export ALLHANDS_API_KEY="YOUR-API-KEY"
+export RUNTIME=remote
+export SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev"
+./evaluation/miniwob/scripts/run_infer.sh llm.eval HEAD BrowsingAgent "" 125 2
+```
+
 Results will be in `evaluation/evaluation_outputs/outputs/miniwob/`
 
 To calculate the average reward, run:

evaluation/miniwob/get_avg_reward.py

@@ -23,7 +23,7 @@ if __name__ == '__main__':
             data = json.loads(line)
             actual_num += 1
             total_cost += data['metrics']['accumulated_cost']
-            total_reward += data['test_result']
+            total_reward += data['test_result']['reward']
 
     avg_reward = total_reward / total_num
     print('Avg Reward: ', avg_reward)

evaluation/miniwob/run_infer.py

@@ -47,6 +47,7 @@ SUPPORTED_AGENT_CLS = {'BrowsingAgent', 'CodeActAgent'}
 
 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
     'CodeActAgent': codeact_user_response,
+    'BrowsingAgent': 'Continue the task. IMPORTANT: do not talk to the user until you have finished the task',
 }
 
 
@@ -66,7 +67,9 @@ def get_config(
             browsergym_eval_env=env_id,
             api_key=os.environ.get('ALLHANDS_API_KEY', None),
             remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            keep_remote_runtime_alive=False,
+            remote_runtime_init_timeout=1800,
+            keep_runtime_alive=False,
+            timeout=120,
         ),
         # do not mount workspace
         workspace_base=None,

evaluation/miniwob/scripts/run_infer.sh

@@ -33,7 +33,7 @@ echo "MODEL_CONFIG: $MODEL_CONFIG"
 
 EVAL_NOTE="${AGENT_VERSION}_${NOTE}"
 
-COMMAND="poetry run python evaluation/miniwob/run_infer.py \
+COMMAND="export PYTHONPATH=evaluation/miniwob:\$PYTHONPATH && poetry run python evaluation/miniwob/run_infer.py \
   --agent-cls $AGENT \
   --llm-config $MODEL_CONFIG \
   --max-iterations 10 \

evaluation/mint/run_infer.py

@@ -70,7 +70,7 @@ AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
 }
 
 AGENT_CLS_TO_INST_SUFFIX = {
-    'CodeActAgent': '\nIMPORTANT: When your answer is confirmed by the user to be correct, you can exit using the following command: <execute_bash> exit </execute_bash>.\n'
+    'CodeActAgent': 'IMPORTANT: When your answer is confirmed by the user to be correct, you can use the "finish" tool to finish the interaction.\n'
 }
 
 with open(os.path.join(os.path.dirname(__file__), 'requirements.txt'), 'r') as f:

evaluation/ml_bench/README.md

@@ -55,7 +55,7 @@ Here's an example of the evaluation output for a single task instance:
 {
   "instance_id": 3,
   "repo": "https://github.com/dmlc/dgl",
-  "instruction": "Please complete the Machine Learning task in the following repository: dgl\n\nThe task is: DGL Implementation of NGCF model\n\nI have a deep desire to embark on a journey brimming with knowledge and expertise. My objective is to train a cutting-edge NGCF Model, known for its unparalleled capabilities, on the illustrious dataset known as gowalla. To ensure swift execution, I kindly request your assistance in crafting the code, making use of the powerful GPU #3 and an embedding size of 32. Can you lend a helping hand to transform this dream into a reality?\n\nYou should create a script named `run.sh` under the specified path in the repo to run the task.\n\nYou can find the task repo at: /workspace/dgl/examples/pytorch/NGCF/NGCF\n\nYou should terminate the subprocess after running the task (e.g., call subprocess.Popen(args).wait()).When you think you have completed the task, please run the following command: <execute_bash> exit </execute_bash>.\n",
+  "instruction": "Please complete the Machine Learning task in the following repository: dgl\n\nThe task is: DGL Implementation of NGCF model\n\nI have a deep desire to embark on a journey brimming with knowledge and expertise. My objective is to train a cutting-edge NGCF Model, known for its unparalleled capabilities, on the illustrious dataset known as gowalla. To ensure swift execution, I kindly request your assistance in crafting the code, making use of the powerful GPU #3 and an embedding size of 32. Can you lend a helping hand to transform this dream into a reality?\n\nYou should create a script named `run.sh` under the specified path in the repo to run the task.\n\nYou can find the task repo at: /workspace/dgl/examples/pytorch/NGCF/NGCF\n\nYou should terminate the subprocess after running the task (e.g., call subprocess.Popen(args).wait()).When you think you have completed the task, please finish the interaction using the "finish" tool.\n",
   "metadata": {
     "agent_class": "CodeActAgent",
     "model_name": "gpt-4-1106-preview",
@@ -70,10 +70,10 @@ Here's an example of the evaluation output for a single task instance:
         "id": 0,
         "timestamp": "2024-05-26T17:40:41.060009",
         "source": "user",
-        "message": "Please complete the Machine Learning task in the following repository: dgl\n\nThe task is: DGL Implementation of NGCF model\n\nI have a deep desire to embark on a journey brimming with knowledge and expertise. My objective is to train a cutting-edge NGCF Model, known for its unparalleled capabilities, on the illustrious dataset known as gowalla. To ensure swift execution, I kindly request your assistance in crafting the code, making use of the powerful GPU #3 and an embedding size of 32. Can you lend a helping hand to transform this dream into a reality?\n\nYou should create a script named `run.sh` under the specified path in the repo to run the task.\n\nYou can find the task repo at: /workspace/dgl/examples/pytorch/NGCF/NGCF\n\nYou should terminate the subprocess after running the task (e.g., call subprocess.Popen(args).wait()).When you think you have completed the task, please run the following command: <execute_bash> exit </execute_bash>.\n",
+        "message": "Please complete the Machine Learning task in the following repository: dgl\n\nThe task is: DGL Implementation of NGCF model\n\nI have a deep desire to embark on a journey brimming with knowledge and expertise. My objective is to train a cutting-edge NGCF Model, known for its unparalleled capabilities, on the illustrious dataset known as gowalla. To ensure swift execution, I kindly request your assistance in crafting the code, making use of the powerful GPU #3 and an embedding size of 32. Can you lend a helping hand to transform this dream into a reality?\n\nYou should create a script named `run.sh` under the specified path in the repo to run the task.\n\nYou can find the task repo at: /workspace/dgl/examples/pytorch/NGCF/NGCF\n\nYou should terminate the subprocess after running the task (e.g., call subprocess.Popen(args).wait()).When you think you have completed the task, please finish the interaction using the "finish" tool.\n",
         "action": "message",
         "args": {
-          "content": "Please complete the Machine Learning task in the following repository: dgl\n\nThe task is: DGL Implementation of NGCF model\n\nI have a deep desire to embark on a journey brimming with knowledge and expertise. My objective is to train a cutting-edge NGCF Model, known for its unparalleled capabilities, on the illustrious dataset known as gowalla. To ensure swift execution, I kindly request your assistance in crafting the code, making use of the powerful GPU #3 and an embedding size of 32. Can you lend a helping hand to transform this dream into a reality?\n\nYou should create a script named `run.sh` under the specified path in the repo to run the task.\n\nYou can find the task repo at: /workspace/dgl/examples/pytorch/NGCF/NGCF\n\nYou should terminate the subprocess after running the task (e.g., call subprocess.Popen(args).wait()).When you think you have completed the task, please run the following command: <execute_bash> exit </execute_bash>.\n",
+          "content": "Please complete the Machine Learning task in the following repository: dgl\n\nThe task is: DGL Implementation of NGCF model\n\nI have a deep desire to embark on a journey brimming with knowledge and expertise. My objective is to train a cutting-edge NGCF Model, known for its unparalleled capabilities, on the illustrious dataset known as gowalla. To ensure swift execution, I kindly request your assistance in crafting the code, making use of the powerful GPU #3 and an embedding size of 32. Can you lend a helping hand to transform this dream into a reality?\n\nYou should create a script named `run.sh` under the specified path in the repo to run the task.\n\nYou can find the task repo at: /workspace/dgl/examples/pytorch/NGCF/NGCF\n\nYou should terminate the subprocess after running the task (e.g., call subprocess.Popen(args).wait()).When you think you have completed the task, please finish the interaction using the "finish" tool.\n",
           "wait_for_response": false
         }
       },

evaluation/ml_bench/run_infer.py

@@ -52,7 +52,7 @@ AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
 }
 
 AGENT_CLS_TO_INST_SUFFIX = {
-    'CodeActAgent': 'When you think you have completed the task, please run the following command: <execute_bash> exit </execute_bash>.\n'
+    'CodeActAgent': 'When you think you have completed the task, please finish the interaction using the "finish" tool.\n'
 }
 
 ID2CONDA = {

evaluation/scienceagentbench/run_infer.py

@@ -72,7 +72,7 @@ def get_config(
             timeout=300,
             api_key=os.environ.get('ALLHANDS_API_KEY', None),
             remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            keep_remote_runtime_alive=False,
+            keep_runtime_alive=False,
         ),
         # do not mount workspace
         workspace_base=None,

evaluation/swe_bench/eval_infer.py

@@ -1,6 +1,7 @@
 import os
 import tempfile
 import time
+from functools import partial
 
 import pandas as pd
 from swebench.harness.grading import get_eval_report
@@ -83,7 +84,7 @@ def get_config(instance: pd.Series) -> AppConfig:
             timeout=1800,
             api_key=os.environ.get('ALLHANDS_API_KEY', None),
             remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            remote_runtime_init_timeout=1800,
+            remote_runtime_init_timeout=3600,
         ),
         # do not mount workspace
         workspace_base=None,
@@ -94,13 +95,28 @@ def get_config(instance: pd.Series) -> AppConfig:
 
 def process_instance(
     instance: pd.Series,
-    metadata: EvalMetadata | None = None,
+    metadata: EvalMetadata,
     reset_logger: bool = True,
+    log_dir: str | None = None,
 ) -> EvalOutput:
+    """
+    Evaluate agent performance on a SWE-bench problem instance.
+
+    Note that this signature differs from the expected input to `run_evaluation`. Use
+    `functools.partial` to provide optional arguments before passing to the evaluation harness.
+
+    Args:
+        log_dir (str | None, default=None): Path to directory where log files will be written. Must
+        be provided if `reset_logger` is set.
+
+    Raises:
+        AssertionError: if the `reset_logger` flag is set without a provided log directory.
+    """
     # Setup the logger properly, so you can run multi-processing to parallelize the evaluation
     if reset_logger:
-        global output_file
-        log_dir = output_file.replace('.jsonl', '.logs')
+        assert (
+            log_dir is not None
+        ), "Can't reset logger without a provided log directory."
         os.makedirs(log_dir, exist_ok=True)
         reset_logger_for_multiprocessing(logger, instance.instance_id, log_dir)
     else:
@@ -127,6 +143,7 @@ def process_instance(
         return EvalOutput(
             instance_id=instance_id,
             test_result=instance['test_result'],
+            metadata=metadata,
         )
 
     runtime = create_runtime(config)
@@ -176,6 +193,7 @@ def process_instance(
             return EvalOutput(
                 instance_id=instance_id,
                 test_result=instance['test_result'],
+                metadata=metadata,
             )
         elif 'APPLY_PATCH_PASS' in apply_patch_output:
             logger.info(f'[{instance_id}] {APPLY_PATCH_PASS}:\n{apply_patch_output}')
@@ -245,23 +263,29 @@ def process_instance(
                         test_output_path = os.path.join(log_dir, 'test_output.txt')
                         with open(test_output_path, 'w') as f:
                             f.write(test_output)
-
-                        _report = get_eval_report(
-                            test_spec=test_spec,
-                            prediction={
-                                'model_patch': model_patch,
-                                'instance_id': instance_id,
-                            },
-                            log_path=test_output_path,
-                            include_tests_status=True,
-                        )
-                        report = _report[instance_id]
-                        logger.info(
-                            f"[{instance_id}] report: {report}\nResult for {instance_id}: resolved: {report['resolved']}"
-                        )
-                        instance['test_result']['report']['resolved'] = report[
-                            'resolved'
-                        ]
+                        try:
+                            _report = get_eval_report(
+                                test_spec=test_spec,
+                                prediction={
+                                    'model_patch': model_patch,
+                                    'instance_id': instance_id,
+                                },
+                                log_path=test_output_path,
+                                include_tests_status=True,
+                            )
+                            report = _report[instance_id]
+                            logger.info(
+                                f"[{instance_id}] report: {report}\nResult for {instance_id}: resolved: {report['resolved']}"
+                            )
+                            instance['test_result']['report']['resolved'] = report[
+                                'resolved'
+                            ]
+                        except Exception as e:
+                            logger.error(
+                                f'[{instance_id}] Error when getting eval report: {e}'
+                            )
+                            instance['test_result']['report']['resolved'] = False
+                            instance['test_result']['report']['error_eval'] = True
             else:
                 logger.info(f'[{instance_id}] Error when starting eval:\n{obs.content}')
                 instance['test_result']['report']['error_eval'] = True
@@ -269,6 +293,7 @@ def process_instance(
             return EvalOutput(
                 instance_id=instance_id,
                 test_result=instance['test_result'],
+                metadata=metadata,
             )
         else:
             logger.info(
@@ -336,7 +361,7 @@ if __name__ == '__main__':
 
     if 'model_patch' not in predictions.columns:
         predictions['model_patch'] = predictions['test_result'].apply(
-            lambda x: x['git_patch']
+            lambda x: x.get('git_patch', '')
         )
     assert {'instance_id', 'model_patch'}.issubset(
         set(predictions.columns)
@@ -355,12 +380,26 @@ if __name__ == '__main__':
     output_file = args.input_file.replace('.jsonl', '.swebench_eval.jsonl')
     instances = prepare_dataset(predictions, output_file, args.eval_n_limit)
 
+    # If possible, load the relevant metadata to avoid issues with `run_evaluation`.
+    metadata: EvalMetadata | None = None
+    metadata_filepath = os.path.join(os.path.dirname(args.input_file), 'metadata.json')
+    if os.path.exists(metadata_filepath):
+        with open(metadata_filepath, 'r') as metadata_file:
+            data = metadata_file.read()
+            metadata = EvalMetadata.model_validate_json(data)
+
+    # The evaluation harness constrains the signature of `process_instance_func` but we need to
+    # pass extra information. Build a new function object to avoid issues with multiprocessing.
+    process_instance_func = partial(
+        process_instance, log_dir=output_file.replace('.jsonl', '.logs')
+    )
+
     run_evaluation(
         instances,
-        metadata=None,
+        metadata=metadata,
         output_file=output_file,
         num_workers=args.eval_num_workers,
-        process_instance_func=process_instance,
+        process_instance_func=process_instance_func,
     )
 
     # Load evaluated predictions & print number of resolved predictions

evaluation/swe_bench/prompt.py

@@ -1,6 +1,6 @@
 CODEACT_SWE_PROMPT = """Now, you're going to solve this issue on your own. Your terminal session has started and you're in the repository's root directory. You can use any bash commands or the special interface to help you. Edit all the files you need to and run any checks or tests that you want.
 Remember, YOU CAN ONLY ENTER ONE COMMAND AT A TIME. You should always wait for feedback after every command.
-When you're satisfied with all of the changes you've made, you can run the following command: <execute_bash> exit </execute_bash>.
+When you're satisfied with all of the changes you've made, you can use the "finish" tool to finish the interaction.
 Note however that you cannot use any interactive session commands (e.g. vim) in this environment, but you can write scripts and run them. E.g. you can write a python script and then run it with `python <script_name>.py`.
 
 NOTE ABOUT THE EDIT COMMAND: Indentation really matters! When editing a file, make sure to insert appropriate indentation before each line!

evaluation/swe_bench/run_infer.py

@@ -36,8 +36,8 @@ from openhands.events.action import CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation, ErrorObservation
 from openhands.events.serialization.event import event_to_dict
 from openhands.runtime.base import Runtime
-from openhands.runtime.utils.shutdown_listener import sleep_if_should_continue
 from openhands.utils.async_utils import call_async_from_sync
+from openhands.utils.shutdown_listener import sleep_if_should_continue
 
 USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
 USE_INSTANCE_IMAGE = os.environ.get('USE_INSTANCE_IMAGE', 'false').lower() == 'true'
@@ -146,7 +146,7 @@ def get_config(
             api_key=os.environ.get('ALLHANDS_API_KEY', None),
             remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
             keep_remote_runtime_alive=False,
-            remote_runtime_init_timeout=1800,
+            remote_runtime_init_timeout=3600,
         ),
         # do not mount workspace
         workspace_base=None,
@@ -534,5 +534,10 @@ if __name__ == '__main__':
             instances[col] = instances[col].apply(lambda x: str(x))
 
     run_evaluation(
-        instances, metadata, output_file, args.eval_num_workers, process_instance
+        instances,
+        metadata,
+        output_file,
+        args.eval_num_workers,
+        process_instance,
+        timeout_seconds=120 * 60,  # 2 hour PER instance should be more than enough
     )

evaluation/toolqa/run_infer.py

@@ -34,7 +34,7 @@ AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
 }
 
 AGENT_CLS_TO_INST_SUFFIX = {
-    'CodeActAgent': 'When you think you have completed the request, please run the following command: <execute_bash> exit </execute_bash>.\n'
+    'CodeActAgent': 'When you think you have completed the request, please finish the interaction using the "finish" tool.\n'
 }
 
 

evaluation/utils/shared.py

@@ -137,7 +137,7 @@ def codeact_user_response(
             # let the agent know that it can give up when it has tried 3 times
             return (
                 msg
-                + 'If you want to give up, run: <execute_bash> exit </execute_bash>.\n'
+                + 'If you want to give up, use the "finish" tool to finish the interaction.\n'
             )
     return msg
 
@@ -346,6 +346,7 @@ def run_evaluation(
             f'model {metadata.llm_config.model}, max iterations {metadata.max_iterations}.\n'
         )
     else:
+        logger.warning('Running evaluation without metadata.')
         logger.info(f'Evaluation started with {num_workers} workers.')
 
     total_instances = len(dataset)

frontend/__tests__/clear-session.test.ts

@@ -0,0 +1,40 @@
+import { describe, it, expect, beforeEach, vi } from "vitest";
+import { clearSession } from "../src/utils/clear-session";
+import store from "../src/store";
+import { initialState as browserInitialState } from "../src/state/browserSlice";
+
+describe("clearSession", () => {
+  beforeEach(() => {
+    // Mock localStorage
+    const localStorageMock = {
+      getItem: vi.fn(),
+      setItem: vi.fn(),
+      removeItem: vi.fn(),
+      clear: vi.fn(),
+    };
+    vi.stubGlobal("localStorage", localStorageMock);
+
+    // Set initial browser state to non-default values
+    store.dispatch({
+      type: "browser/setUrl",
+      payload: "https://example.com",
+    });
+    store.dispatch({
+      type: "browser/setScreenshotSrc",
+      payload: "base64screenshot",
+    });
+  });
+
+  it("should clear localStorage and reset browser state", () => {
+    clearSession();
+
+    // Verify localStorage items were removed
+    expect(localStorage.removeItem).toHaveBeenCalledWith("token");
+    expect(localStorage.removeItem).toHaveBeenCalledWith("repo");
+
+    // Verify browser state was reset
+    const state = store.getState();
+    expect(state.browser.url).toBe(browserInitialState.url);
+    expect(state.browser.screenshotSrc).toBe(browserInitialState.screenshotSrc);
+  });
+});

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

@@ -21,6 +21,11 @@ describe("Empty state", () => {
   }));
 
   beforeAll(() => {
+    vi.mock("@remix-run/react", async (importActual) => ({
+      ...(await importActual<typeof import("@remix-run/react")>()),
+      useRouteLoaderData: vi.fn(() => ({})),
+    }));
+
     vi.mock("#/context/socket", async (importActual) => ({
       ...(await importActual<typeof import("#/context/ws-client-provider")>()),
       useWsClient: useWsClientMock,

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

@@ -0,0 +1,93 @@
+import { act, renderHook } from "@testing-library/react";
+import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
+import { useRate } from "#/utils/use-rate";
+
+describe("useRate", () => {
+  beforeEach(() => {
+    vi.useFakeTimers();
+  });
+
+  afterEach(() => {
+    vi.useRealTimers();
+  });
+
+  it("should initialize", () => {
+    const { result } = renderHook(() => useRate());
+
+    expect(result.current.items).toHaveLength(0);
+    expect(result.current.rate).toBeNull();
+    expect(result.current.lastUpdated).toBeNull();
+    expect(result.current.isUnderThreshold).toBe(true);
+  });
+
+  it("should handle the case of a single element", () => {
+    const { result } = renderHook(() => useRate());
+
+    act(() => {
+      result.current.record(123);
+    });
+
+    expect(result.current.items).toHaveLength(1);
+    expect(result.current.lastUpdated).not.toBeNull();
+  });
+
+  it("should return the difference between the last two elements", () => {
+    const { result } = renderHook(() => useRate());
+
+    vi.setSystemTime(500);
+    act(() => {
+      result.current.record(4);
+    });
+
+    vi.advanceTimersByTime(500);
+    act(() => {
+      result.current.record(9);
+    });
+
+    expect(result.current.items).toHaveLength(2);
+    expect(result.current.rate).toBe(5);
+    expect(result.current.lastUpdated).toBe(1000);
+  });
+
+  it("should update isUnderThreshold after [threshold]ms of no activity", () => {
+    const { result } = renderHook(() => useRate({ threshold: 500 }));
+
+    expect(result.current.isUnderThreshold).toBe(true);
+
+    act(() => {
+       // not sure if fake timers is buggy with intervals,
+       // but I need to call it twice to register
+      vi.advanceTimersToNextTimer();
+      vi.advanceTimersToNextTimer();
+    });
+
+    expect(result.current.isUnderThreshold).toBe(false);
+  });
+
+  it("should return an isUnderThreshold boolean", () => {
+    const { result } = renderHook(() => useRate({ threshold: 500 }));
+
+    vi.setSystemTime(500);
+    act(() => {
+      result.current.record(400);
+    });
+    act(() => {
+      result.current.record(1000);
+    });
+
+    expect(result.current.isUnderThreshold).toBe(false);
+
+    act(() => {
+      result.current.record(1500);
+    });
+
+    expect(result.current.isUnderThreshold).toBe(true);
+
+    act(() => {
+      vi.advanceTimersToNextTimer();
+      vi.advanceTimersToNextTimer();
+    });
+
+    expect(result.current.isUnderThreshold).toBe(false);
+  });
+});

frontend/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "openhands-frontend",
-  "version": "0.13.0",
+  "version": "0.14.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "openhands-frontend",
-      "version": "0.13.0",
+      "version": "0.14.0",
       "dependencies": {
         "@monaco-editor/react": "^4.6.0",
         "@nextui-org/react": "^2.4.8",
@@ -26,7 +26,7 @@
         "isbot": "^5.1.17",
         "jose": "^5.9.4",
         "monaco-editor": "^0.52.0",
-        "posthog-js": "^1.176.0",
+        "posthog-js": "^1.184.1",
         "react": "^18.3.1",
         "react-dom": "^18.3.1",
         "react-highlight": "^0.15.0",
@@ -19749,9 +19749,9 @@
       "integrity": "sha512-1NNCs6uurfkVbeXG4S8JFT9t19m45ICnif8zWLd5oPSZ50QnwMfK+H3jv408d4jw/7Bttv5axS5IiHoLaVNHeQ=="
     },
     "node_modules/posthog-js": {
-      "version": "1.176.0",
-      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.176.0.tgz",
-      "integrity": "sha512-T5XKNtRzp7q6CGb7Vc7wAI76rWap9fiuDUPxPsyPBPDkreKya91x9RIsSapAVFafwD1AEin1QMczCmt9Le9BWw==",
+      "version": "1.184.1",
+      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.184.1.tgz",
+      "integrity": "sha512-q/1Kdard5SZnL2smrzeKcD+RuUi2PnbidiN4D3ThK20bNrhy5Z2heIy9SnRMvEiARY5lcQ7zxmDCAKPBKGSOtQ==",
       "dependencies": {
         "core-js": "^3.38.1",
         "fflate": "^0.4.8",

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.13.0",
+  "version": "0.14.0",
   "private": true,
   "type": "module",
   "engines": {
@@ -25,7 +25,7 @@
     "isbot": "^5.1.17",
     "jose": "^5.9.4",
     "monaco-editor": "^0.52.0",
-    "posthog-js": "^1.176.0",
+    "posthog-js": "^1.184.1",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
     "react-highlight": "^0.15.0",

frontend/public/config.json

@@ -1,4 +1,5 @@
 {
   "APP_MODE": "oss",
-  "GITHUB_CLIENT_ID": ""
-}
+  "GITHUB_CLIENT_ID": "",
+  "POSTHOG_CLIENT_KEY": "phc_3ESMmY9SgqEAGBB6sMGK5ayYHkeUuknH2vP6FmWH9RA"
+}

frontend/src/api/open-hands.ts

@@ -8,6 +8,7 @@ import {
   GitHubAccessTokenResponse,
   ErrorResponse,
   GetConfigResponse,
+  GetVSCodeUrlResponse,
 } from "./open-hands.types";
 
 class OpenHands {
@@ -174,6 +175,21 @@ class OpenHands {
       true,
     );
   }
+
+  /**
+   * Get the VSCode URL
+   * @returns VSCode URL
+   */
+  static async getVSCodeUrl(): Promise<GetVSCodeUrlResponse> {
+    return request(`/api/vscode-url`, {}, false, false, 1);
+  }
+
+  static async getRuntimeId(): Promise<{ runtime_id: string }> {
+    const response = await request("/api/config");
+    const data = await response.json();
+
+    return data;
+  }
 }
 
 export default OpenHands;

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

@@ -43,5 +43,11 @@ export interface Feedback {
 
 export interface GetConfigResponse {
   APP_MODE: "saas" | "oss";
-  GITHUB_CLIENT_ID: string | null;
+  GITHUB_CLIENT_ID: string;
+  POSTHOG_CLIENT_KEY: string;
+}
+
+export interface GetVSCodeUrlResponse {
+  vscode_url: string | null;
+  error?: string;
 }

frontend/src/assets/vscode-alt.svg

@@ -0,0 +1,57 @@
+<svg width="100" height="100" viewBox="0 0 100 100" fill="none" xmlns="http://www.w3.org/2000/svg">
+<g clip-path="url(#clip0)">
+<g filter="url(#filter0_d)">
+<mask id="mask0" mask-type="alpha" maskUnits="userSpaceOnUse" x="0" y="0" width="100" height="100">
+<path fill-rule="evenodd" clip-rule="evenodd" d="M70.9119 99.5723C72.4869 100.189 74.2828 100.15 75.8725 99.3807L96.4604 89.4231C98.624 88.3771 100 86.1762 100 83.7616V16.2392C100 13.8247 98.624 11.6238 96.4604 10.5774L75.8725 0.619067C73.7862 -0.389991 71.3446 -0.142885 69.5135 1.19527C69.252 1.38636 69.0028 1.59985 68.769 1.83502L29.3551 37.9795L12.1872 24.88C10.5891 23.6607 8.35365 23.7606 6.86938 25.1178L1.36302 30.1525C-0.452603 31.8127 -0.454583 34.6837 1.35854 36.3466L16.2471 50.0001L1.35854 63.6536C-0.454583 65.3164 -0.452603 68.1876 1.36302 69.8477L6.86938 74.8824C8.35365 76.2395 10.5891 76.34 12.1872 75.1201L29.3551 62.0207L68.769 98.1651C69.3925 98.7923 70.1246 99.2645 70.9119 99.5723ZM75.0152 27.1813L45.1092 50.0001L75.0152 72.8189V27.1813Z" fill="white"/>
+</mask>
+<g mask="url(#mask0)">
+<path d="M96.4614 10.593L75.8567 0.62085C73.4717 -0.533437 70.6215 -0.0465506 68.7498 1.83492L1.29834 63.6535C-0.515935 65.3164 -0.513852 68.1875 1.30281 69.8476L6.8125 74.8823C8.29771 76.2395 10.5345 76.339 12.1335 75.1201L93.3604 13.18C96.0854 11.102 100 13.0557 100 16.4939V16.2535C100 13.84 98.6239 11.64 96.4614 10.593Z" fill="#D9D9D9"/>
+<g filter="url(#filter1_d)">
+<path d="M96.4614 89.4074L75.8567 99.3797C73.4717 100.534 70.6215 100.047 68.7498 98.1651L1.29834 36.3464C-0.515935 34.6837 -0.513852 31.8125 1.30281 30.1524L6.8125 25.1177C8.29771 23.7605 10.5345 23.6606 12.1335 24.88L93.3604 86.8201C96.0854 88.8985 100 86.9447 100 83.5061V83.747C100 86.1604 98.6239 88.3603 96.4614 89.4074Z" fill="#E6E6E6"/>
+</g>
+<g filter="url(#filter2_d)">
+<path d="M75.8578 99.3807C73.4721 100.535 70.6219 100.047 68.75 98.1651C71.0564 100.483 75 98.8415 75 95.5631V4.43709C75 1.15852 71.0565 -0.483493 68.75 1.83492C70.6219 -0.0467614 73.4721 -0.534276 75.8578 0.618963L96.4583 10.5773C98.6229 11.6237 100 13.8246 100 16.2391V83.7616C100 86.1762 98.6229 88.3761 96.4583 89.4231L75.8578 99.3807Z" fill="white"/>
+</g>
+<g style="mix-blend-mode:overlay" opacity="0.25">
+<path style="mix-blend-mode:overlay" opacity="0.25" fill-rule="evenodd" clip-rule="evenodd" d="M70.8508 99.5723C72.4258 100.189 74.2218 100.15 75.8115 99.3807L96.4 89.4231C98.5635 88.3771 99.9386 86.1762 99.9386 83.7616V16.2391C99.9386 13.8247 98.5635 11.6239 96.4 10.5774L75.8115 0.618974C73.7252 -0.390085 71.2835 -0.142871 69.4525 1.19518C69.1909 1.38637 68.9418 1.59976 68.7079 1.83493L29.2941 37.9795L12.1261 24.88C10.528 23.6606 8.2926 23.7605 6.80833 25.1177L1.30198 30.1524C-0.51354 31.8126 -0.515625 34.6837 1.2975 36.3465L16.186 50L1.2975 63.6536C-0.515625 65.3164 -0.51354 68.1875 1.30198 69.8476L6.80833 74.8824C8.2926 76.2395 10.528 76.339 12.1261 75.1201L29.2941 62.0207L68.7079 98.1651C69.3315 98.7923 70.0635 99.2645 70.8508 99.5723ZM74.9542 27.1812L45.0481 50L74.9542 72.8188V27.1812Z" fill="url(#paint0_linear)"/>
+</g>
+</g>
+</g>
+</g>
+<defs>
+<filter id="filter0_d" x="-6.25" y="-4.16667" width="112.5" height="112.5" filterUnits="userSpaceOnUse" color-interpolation-filters="sRGB">
+<feFlood flood-opacity="0" result="BackgroundImageFix"/>
+<feColorMatrix in="SourceAlpha" type="matrix" values="0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 127 0"/>
+<feOffset dy="2.08333"/>
+<feGaussianBlur stdDeviation="3.125"/>
+<feColorMatrix type="matrix" values="0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0.15 0"/>
+<feBlend mode="normal" in2="BackgroundImageFix" result="effect1_dropShadow"/>
+<feBlend mode="normal" in="SourceGraphic" in2="effect1_dropShadow" result="shape"/>
+</filter>
+<filter id="filter1_d" x="-8.39436" y="15.6951" width="116.728" height="92.6376" filterUnits="userSpaceOnUse" color-interpolation-filters="sRGB">
+<feFlood flood-opacity="0" result="BackgroundImageFix"/>
+<feColorMatrix in="SourceAlpha" type="matrix" values="0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 127 0"/>
+<feOffset/>
+<feGaussianBlur stdDeviation="4.16667"/>
+<feColorMatrix type="matrix" values="0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0.25 0"/>
+<feBlend mode="overlay" in2="BackgroundImageFix" result="effect1_dropShadow"/>
+<feBlend mode="normal" in="SourceGraphic" in2="effect1_dropShadow" result="shape"/>
+</filter>
+<filter id="filter2_d" x="60.4167" y="-8.33346" width="47.9167" height="116.667" filterUnits="userSpaceOnUse" color-interpolation-filters="sRGB">
+<feFlood flood-opacity="0" result="BackgroundImageFix"/>
+<feColorMatrix in="SourceAlpha" type="matrix" values="0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 127 0"/>
+<feOffset/>
+<feGaussianBlur stdDeviation="4.16667"/>
+<feColorMatrix type="matrix" values="0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0.25 0"/>
+<feBlend mode="overlay" in2="BackgroundImageFix" result="effect1_dropShadow"/>
+<feBlend mode="normal" in="SourceGraphic" in2="effect1_dropShadow" result="shape"/>
+</filter>
+<linearGradient id="paint0_linear" x1="49.939" y1="-5.19792e-05" x2="49.939" y2="100.001" gradientUnits="userSpaceOnUse">
+<stop stop-color="white"/>
+<stop offset="1" stop-color="white" stop-opacity="0"/>
+</linearGradient>
+<clipPath id="clip0">
+<rect width="100" height="100" fill="white"/>
+</clipPath>
+</defs>
+</svg>

frontend/src/components/chat-input.tsx

@@ -18,6 +18,7 @@ interface ChatInputProps {
   onBlur?: () => void;
   onImagePaste?: (files: File[]) => void;
   className?: React.HTMLAttributes<HTMLDivElement>["className"];
+  buttonClassName?: React.HTMLAttributes<HTMLButtonElement>["className"];
 }
 
 export function ChatInput({
@@ -35,6 +36,7 @@ export function ChatInput({
   onBlur,
   onImagePaste,
   className,
+  buttonClassName,
 }: ChatInputProps) {
   const textareaRef = React.useRef<HTMLTextAreaElement>(null);
   const [isDraggingOver, setIsDraggingOver] = React.useState(false);
@@ -100,7 +102,7 @@ export function ChatInput({
   return (
     <div
       data-testid="chat-input"
-      className="flex items-end justify-end grow gap-1 min-h-6"
+      className="flex items-end justify-end grow gap-1 min-h-6 w-full"
     >
       <TextareaAutosize
         ref={textareaRef}
@@ -128,7 +130,7 @@ export function ChatInput({
         )}
       />
       {showButton && (
-        <>
+        <div className={buttonClassName}>
           {button === "submit" && (
             <button
               aria-label="Send"
@@ -152,7 +154,7 @@ export function ChatInput({
               <div className="w-[10px] h-[10px] bg-white" />
             </button>
           )}
-        </>
+        </div>
       )}
     </div>
   );

frontend/src/components/chat-interface.tsx

@@ -1,6 +1,7 @@
 import { useDispatch, useSelector } from "react-redux";
 import React from "react";
 import posthog from "posthog-js";
+import { useRouteLoaderData } from "@remix-run/react";
 import { convertImageToBase64 } from "#/utils/convert-image-to-base-64";
 import { ChatMessage } from "./chat-message";
 import { FeedbackActions } from "./feedback-actions";
@@ -21,18 +22,27 @@ import { ScrollToBottomButton } from "./scroll-to-bottom-button";
 import { Suggestions } from "./suggestions";
 import { SUGGESTIONS } from "#/utils/suggestions";
 import BuildIt from "#/icons/build-it.svg?react";
-import { useWsClient } from "#/context/ws-client-provider";
+import {
+  useWsClient,
+  WsClientProviderStatus,
+} from "#/context/ws-client-provider";
+import OpenHands from "#/api/open-hands";
+import { clientLoader } from "#/routes/_oh";
+import { downloadWorkspace } from "#/utils/download-workspace";
+import { SuggestionItem } from "./suggestion-item";
 
 const isErrorMessage = (
   message: Message | ErrorMessage,
 ): message is ErrorMessage => "error" in message;
 
 export function ChatInterface() {
-  const { send } = useWsClient();
+  const { send, status, isLoadingMessages } = useWsClient();
+
   const dispatch = useDispatch();
   const scrollRef = React.useRef<HTMLDivElement>(null);
   const { scrollDomToBottom, onChatBodyScroll, hitBottom } =
     useScrollToBottom(scrollRef);
+  const rootLoaderData = useRouteLoaderData<typeof clientLoader>("routes/_oh");
 
   const { messages } = useSelector((state: RootState) => state.chat);
   const { curAgentState } = useSelector((state: RootState) => state.agent);
@@ -42,6 +52,24 @@ export function ChatInterface() {
   >("positive");
   const [feedbackModalIsOpen, setFeedbackModalIsOpen] = React.useState(false);
   const [messageToSend, setMessageToSend] = React.useState<string | null>(null);
+  const [isDownloading, setIsDownloading] = React.useState(false);
+
+  React.useEffect(() => {
+    if (status === WsClientProviderStatus.ACTIVE) {
+      try {
+        OpenHands.getRuntimeId().then(({ runtime_id }) => {
+          // eslint-disable-next-line no-console
+          console.log(
+            "Runtime ID: %c%s",
+            "background: #444; color: #ffeb3b; font-weight: bold; padding: 2px 4px; border-radius: 4px;",
+            runtime_id,
+          );
+        });
+      } catch (e) {
+        console.warn("Runtime ID not available in this environment");
+      }
+    }
+  }, [status]);
 
   const handleSendMessage = async (content: string, files: File[]) => {
     posthog.capture("user_message_sent", {
@@ -72,6 +100,17 @@ export function ChatInterface() {
     setFeedbackPolarity(polarity);
   };
 
+  const handleDownloadWorkspace = async () => {
+    setIsDownloading(true);
+    try {
+      await downloadWorkspace();
+    } catch (error) {
+      // TODO: Handle error
+    } finally {
+      setIsDownloading(false);
+    }
+  };
+
   return (
     <div className="h-full flex flex-col justify-between">
       {messages.length === 0 && (
@@ -101,29 +140,64 @@ export function ChatInterface() {
         onScroll={(e) => onChatBodyScroll(e.currentTarget)}
         className="flex flex-col grow overflow-y-auto overflow-x-hidden px-4 pt-4 gap-2"
       >
-        {messages.map((message, index) =>
-          isErrorMessage(message) ? (
-            <ErrorMessage
-              key={index}
-              id={message.id}
-              message={message.message}
-            />
-          ) : (
-            <ChatMessage
-              key={index}
-              type={message.sender}
-              message={message.content}
-            >
-              {message.imageUrls.length > 0 && (
-                <ImageCarousel size="small" images={message.imageUrls} />
-              )}
-              {messages.length - 1 === index &&
-                message.sender === "assistant" &&
-                curAgentState === AgentState.AWAITING_USER_CONFIRMATION && (
-                  <ConfirmationButtons />
+        {isLoadingMessages && (
+          <div className="flex justify-center">
+            <div className="w-6 h-6 border-2 border-t-[4px] border-primary-500 rounded-full animate-spin" />
+          </div>
+        )}
+
+        {!isLoadingMessages &&
+          messages.map((message, index) =>
+            isErrorMessage(message) ? (
+              <ErrorMessage
+                key={index}
+                id={message.id}
+                message={message.message}
+              />
+            ) : (
+              <ChatMessage
+                key={index}
+                type={message.sender}
+                message={message.content}
+              >
+                {message.imageUrls.length > 0 && (
+                  <ImageCarousel size="small" images={message.imageUrls} />
                 )}
-            </ChatMessage>
-          ),
+                {messages.length - 1 === index &&
+                  message.sender === "assistant" &&
+                  curAgentState === AgentState.AWAITING_USER_CONFIRMATION && (
+                    <ConfirmationButtons />
+                  )}
+              </ChatMessage>
+            ),
+          )}
+
+        {(curAgentState === AgentState.AWAITING_USER_INPUT ||
+          curAgentState === AgentState.FINISHED) && (
+          <div className="flex flex-col gap-2 mb-2">
+            {rootLoaderData?.ghToken ? (
+              <SuggestionItem
+                suggestion={{
+                  label: "Push to GitHub",
+                  value:
+                    "Please push the changes to GitHub and open a pull request.",
+                }}
+                onClick={(value) => {
+                  handleSendMessage(value, []);
+                }}
+              />
+            ) : (
+              <SuggestionItem
+                suggestion={{
+                  label: !isDownloading
+                    ? "Download .zip"
+                    : "Downloading, please wait...",
+                  value: "Download .zip",
+                }}
+                onClick={handleDownloadWorkspace}
+              />
+            )}
+          </div>
         )}
       </div>
 

frontend/src/components/event-handler.tsx

@@ -14,13 +14,13 @@ import {
 } from "#/context/ws-client-provider";
 import { ErrorObservation } from "#/types/core/observations";
 import { addErrorMessage, addUserMessage } from "#/state/chatSlice";
-import { handleAssistantMessage } from "#/services/actions";
 import {
   getCloneRepoCommand,
   getGitHubTokenCommand,
 } from "#/services/terminalService";
 import {
   clearFiles,
+  clearInitialQuery,
   clearSelectedRepository,
   setImportedProjectZip,
 } from "#/state/initial-query-slice";
@@ -34,6 +34,7 @@ import { base64ToBlob } from "#/utils/base64-to-blob";
 import { setCurrentAgentState } from "#/state/agentSlice";
 import AgentState from "#/types/AgentState";
 import { getSettings } from "#/services/settings";
+import { generateAgentStateChangeEvent } from "#/services/agentStateService";
 
 interface ServerError {
   error: boolean | string;
@@ -52,13 +53,10 @@ export function EventHandler({ children }: React.PropsWithChildren) {
   const runtimeActive = status === WsClientProviderStatus.ACTIVE;
   const fetcher = useFetcher();
   const dispatch = useDispatch();
-  const { files, importedProjectZip } = useSelector(
+  const { files, importedProjectZip, initialQuery } = useSelector(
     (state: RootState) => state.initalQuery,
   );
   const { ghToken, repo } = useLoaderData<typeof appClientLoader>();
-  const initialQueryRef = React.useRef<string | null>(
-    store.getState().initalQuery.initialQuery,
-  );
 
   const sendInitialQuery = (query: string, base64Files: string[]) => {
     const timestamp = new Date().toISOString();
@@ -96,6 +94,14 @@ export function EventHandler({ children }: React.PropsWithChildren) {
       return;
     }
 
+    if (event.type === "error") {
+      const message: string = `${event.message}`;
+      if (message.startsWith("Agent reached maximum")) {
+        // We set the agent state to paused here - if the user clicks resume, it auto updates the max iterations
+        send(generateAgentStateChangeEvent(AgentState.PAUSED));
+      }
+    }
+
     if (isErrorObservation(event)) {
       dispatch(
         addErrorMessage({
@@ -103,9 +109,7 @@ export function EventHandler({ children }: React.PropsWithChildren) {
           message: event.message,
         }),
       );
-      return;
     }
-    handleAssistantMessage(event);
   }, [events.length]);
 
   React.useEffect(() => {
@@ -113,7 +117,6 @@ export function EventHandler({ children }: React.PropsWithChildren) {
       return; // This is a check because of strict mode - if the status did not change, don't do anything
     }
     statusRef.current = status;
-    const initialQuery = initialQueryRef.current;
 
     if (status === WsClientProviderStatus.ACTIVE) {
       let additionalInfo = "";
@@ -134,7 +137,7 @@ export function EventHandler({ children }: React.PropsWithChildren) {
           sendInitialQuery(initialQuery, files);
         }
         dispatch(clearFiles()); // reset selected files
-        initialQueryRef.current = null;
+        dispatch(clearInitialQuery()); // reset initial query
       }
     }
 

frontend/src/components/file-explorer/FileExplorer.tsx

@@ -12,6 +12,7 @@ import { useTranslation } from "react-i18next";
 import { twMerge } from "tailwind-merge";
 import AgentState from "#/types/AgentState";
 import { setRefreshID } from "#/state/codeSlice";
+import { addAssistantMessage } from "#/state/chatSlice";
 import IconButton from "../IconButton";
 import ExplorerTree from "./ExplorerTree";
 import toast from "#/utils/toast";
@@ -20,6 +21,7 @@ import { I18nKey } from "#/i18n/declaration";
 import OpenHands from "#/api/open-hands";
 import { useFiles } from "#/context/files";
 import { isOpenHandsErrorResponse } from "#/api/open-hands.utils";
+import VSCodeIcon from "#/assets/vscode-alt.svg?react";
 
 interface ExplorerActionsProps {
   onRefresh: () => void;
@@ -168,6 +170,35 @@ function FileExplorer({ error, isOpen, onToggle }: FileExplorerProps) {
     }
   };
 
+  const handleVSCodeClick = async (e: React.MouseEvent) => {
+    e.preventDefault();
+    try {
+      const response = await OpenHands.getVSCodeUrl();
+      if (response.vscode_url) {
+        dispatch(
+          addAssistantMessage(
+            "You opened VS Code. Please inform the agent of any changes you made to the workspace or environment. To avoid conflicts, it's best to pause the agent before making any changes.",
+          ),
+        );
+        window.open(response.vscode_url, "_blank");
+      } else {
+        toast.error(
+          `open-vscode-error-${new Date().getTime()}`,
+          t(I18nKey.EXPLORER$VSCODE_SWITCHING_ERROR_MESSAGE, {
+            error: response.error,
+          }),
+        );
+      }
+    } catch (exp_error) {
+      toast.error(
+        `open-vscode-error-${new Date().getTime()}`,
+        t(I18nKey.EXPLORER$VSCODE_SWITCHING_ERROR_MESSAGE, {
+          error: String(exp_error),
+        }),
+      );
+    }
+  };
+
   React.useEffect(() => {
     refreshWorkspace();
   }, [curAgentState]);
@@ -210,7 +241,7 @@ function FileExplorer({ error, isOpen, onToggle }: FileExplorerProps) {
           !isOpen ? "w-12" : "w-60",
         )}
       >
-        <div className="flex flex-col relative h-full px-3 py-2">
+        <div className="flex flex-col relative h-full px-3 py-2 overflow-hidden">
           <div className="sticky top-0 bg-neutral-800">
             <div
               className={twMerge(
@@ -232,7 +263,7 @@ function FileExplorer({ error, isOpen, onToggle }: FileExplorerProps) {
             </div>
           </div>
           {!error && (
-            <div className="overflow-auto flex-grow">
+            <div className="overflow-auto flex-grow min-h-0">
               <div style={{ display: !isOpen ? "none" : "block" }}>
                 <ExplorerTree files={paths} />
               </div>
@@ -243,6 +274,27 @@ function FileExplorer({ error, isOpen, onToggle }: FileExplorerProps) {
               <p className="text-neutral-300 text-sm">{error}</p>
             </div>
           )}
+          {isOpen && (
+            <button
+              type="button"
+              onClick={handleVSCodeClick}
+              disabled={
+                curAgentState === AgentState.INIT ||
+                curAgentState === AgentState.LOADING
+              }
+              className={twMerge(
+                "mt-auto mb-2 w-full h-10 text-white rounded flex items-center justify-center gap-2 transition-colors",
+                curAgentState === AgentState.INIT ||
+                  curAgentState === AgentState.LOADING
+                  ? "bg-neutral-600 cursor-not-allowed"
+                  : "bg-[#4465DB] hover:bg-[#3451C7]",
+              )}
+              aria-label="Open in VS Code"
+            >
+              <VSCodeIcon width={20} height={20} />
+              Open in VS Code
+            </button>
+          )}
         </div>
         <input
           data-testid="file-input"

frontend/src/components/github-repositories-suggestion-box.tsx

@@ -10,32 +10,8 @@ import { GitHubRepositorySelector } from "#/routes/_oh._index/github-repo-select
 import ModalButton from "./buttons/ModalButton";
 import GitHubLogo from "#/assets/branding/github-logo.svg?react";
 
-interface GitHubAuthProps {
-  onConnectToGitHub: () => void;
-  repositories: GitHubRepository[];
-  isLoggedIn: boolean;
-}
-
-function GitHubAuth({
-  onConnectToGitHub,
-  repositories,
-  isLoggedIn,
-}: GitHubAuthProps) {
-  if (isLoggedIn) {
-    return <GitHubRepositorySelector repositories={repositories} />;
-  }
-
-  return (
-    <ModalButton
-      text="Connect to GitHub"
-      icon={<GitHubLogo width={20} height={20} />}
-      className="bg-[#791B80] w-full"
-      onClick={onConnectToGitHub}
-    />
-  );
-}
-
 interface GitHubRepositoriesSuggestionBoxProps {
+  handleSubmit: () => void;
   repositories: Awaited<
     ReturnType<typeof retrieveAllGitHubUserRepositories>
   > | null;
@@ -44,6 +20,7 @@ interface GitHubRepositoriesSuggestionBoxProps {
 }
 
 export function GitHubRepositoriesSuggestionBox({
+  handleSubmit,
   repositories,
   gitHubAuthUrl,
   user,
@@ -70,16 +47,26 @@ export function GitHubRepositoriesSuggestionBox({
     );
   }
 
+  const isLoggedIn = !!user && !isGitHubErrorReponse(user);
+
   return (
     <>
       <SuggestionBox
         title="Open a Repo"
         content={
-          <GitHubAuth
-            isLoggedIn={!!user && !isGitHubErrorReponse(user)}
-            repositories={repositories || []}
-            onConnectToGitHub={handleConnectToGitHub}
-          />
+          isLoggedIn ? (
+            <GitHubRepositorySelector
+              onSelect={handleSubmit}
+              repositories={repositories || []}
+            />
+          ) : (
+            <ModalButton
+              text="Connect to GitHub"
+              icon={<GitHubLogo width={20} height={20} />}
+              className="bg-[#791B80] w-full"
+              onClick={handleConnectToGitHub}
+            />
+          )
         }
       />
       {connectToGitHubModalOpen && (

frontend/src/components/interactive-chat-box.tsx

@@ -56,14 +56,9 @@ export function InteractiveChatBox({
       <div
         className={cn(
           "flex items-end gap-1",
-          "bg-neutral-700 border border-neutral-600 rounded-lg px-2 py-[10px]",
+          "bg-neutral-700 border border-neutral-600 rounded-lg px-2",
           "transition-colors duration-200",
           "hover:border-neutral-500 focus-within:border-neutral-500",
-          "group relative",
-          "before:pointer-events-none before:absolute before:inset-0 before:rounded-lg before:transition-colors",
-          "before:border-2 before:border-dashed before:border-transparent",
-          "[&:has(*:focus-within)]:before:border-neutral-500/50",
-          "[&:has(*[data-dragging-over='true'])]:before:border-neutral-500/50",
         )}
       >
         <UploadImageInput onUpload={handleUpload} />
@@ -76,6 +71,8 @@ export function InteractiveChatBox({
           onStop={onStop}
           value={value}
           onImagePaste={handleUpload}
+          className="py-[10px]"
+          buttonClassName="py-[10px]"
         />
       </div>
     </div>

frontend/src/components/markdown/list.tsx

@@ -4,8 +4,8 @@ import { ExtraProps } from "react-markdown";
 // Custom component to render <ul> in markdown
 export function ul({
   children,
-}: React.ClassAttributes<HTMLElement> &
-  React.HTMLAttributes<HTMLElement> &
+}: React.ClassAttributes<HTMLUListElement> &
+  React.HTMLAttributes<HTMLUListElement> &
   ExtraProps) {
   return <ul className="list-disc ml-5 pl-2 whitespace-normal">{children}</ul>;
 }
@@ -13,10 +13,13 @@ export function ul({
 // Custom component to render <ol> in markdown
 export function ol({
   children,
-}: React.ClassAttributes<HTMLElement> &
-  React.HTMLAttributes<HTMLElement> &
+  start,
+}: React.ClassAttributes<HTMLOListElement> &
+  React.OlHTMLAttributes<HTMLOListElement> &
   ExtraProps) {
   return (
-    <ol className="list-decimal ml-5 pl-2 whitespace-normal">{children}</ol>
+    <ol className="list-decimal ml-5 pl-2 whitespace-normal" start={start}>
+      {children}
+    </ol>
   );
 }

frontend/src/components/modals/AccountSettingsModal.tsx

@@ -1,7 +1,10 @@
 import { useFetcher, useRouteLoaderData } from "@remix-run/react";
 import React from "react";
 import { useTranslation } from "react-i18next";
-import { BaseModalTitle } from "./confirmation-modals/BaseModal";
+import {
+  BaseModalDescription,
+  BaseModalTitle,
+} from "./confirmation-modals/BaseModal";
 import ModalBody from "./ModalBody";
 import ModalButton from "../buttons/ModalButton";
 import FormFieldset from "../form/FormFieldset";
@@ -87,6 +90,17 @@ function AccountSettingsModal({
             type="password"
             defaultValue={data?.ghToken ?? ""}
           />
+          <BaseModalDescription>
+            {t(I18nKey.CONNECT_TO_GITHUB_MODAL$GET_YOUR_TOKEN)}{" "}
+            <a
+              href="https://github.com/settings/tokens/new?description=openhands-app&scopes=repo,user,workflow"
+              target="_blank"
+              rel="noreferrer noopener"
+              className="text-[#791B80] underline"
+            >
+              {t(I18nKey.CONNECT_TO_GITHUB_MODAL$HERE)}
+            </a>
+          </BaseModalDescription>
           {gitHubError && (
             <p className="text-danger text-xs">
               {t(I18nKey.ACCOUNT_SETTINGS_MODAL$GITHUB_TOKEN_INVALID)}

frontend/src/components/suggestion-item.tsx

@@ -7,12 +7,12 @@ interface SuggestionItemProps {
 
 export function SuggestionItem({ suggestion, onClick }: SuggestionItemProps) {
   return (
-    <li className="border border-neutral-600 rounded-xl hover:bg-neutral-700">
+    <li className="list-none border border-neutral-600 rounded-xl hover:bg-neutral-700">
       <button
         type="button"
         data-testid="suggestion"
         onClick={() => onClick(suggestion.value)}
-        className="text-[16px] leading-6 -tracking-[0.01em] text-center w-full p-4 font-semibold"
+        className="text-[16px] leading-6 -tracking-[0.01em] text-center w-full p-3 font-semibold"
       >
         {suggestion.label}
       </button>

frontend/src/components/upload-image-input.tsx

@@ -11,7 +11,7 @@ export function UploadImageInput({ onUpload, label }: UploadImageInputProps) {
   };
 
   return (
-    <label className="cursor-pointer">
+    <label className="cursor-pointer py-[10px]">
       {label || <Clip data-testid="default-label" width={24} height={24} />}
       <input
         data-testid="upload-image-input"

frontend/src/context/ws-client-provider.tsx

@@ -4,6 +4,13 @@ import { Settings } from "#/services/settings";
 import ActionType from "#/types/ActionType";
 import EventLogger from "#/utils/event-logger";
 import AgentState from "#/types/AgentState";
+import { handleAssistantMessage } from "#/services/actions";
+import { useRate } from "#/utils/use-rate";
+
+const isOpenHandsMessage = (event: Record<string, unknown>) =>
+  event.action === "message";
+
+const RECONNECT_RETRIES = 5;
 
 export enum WsClientProviderStatus {
   STOPPED,
@@ -14,12 +21,14 @@ export enum WsClientProviderStatus {
 
 interface UseWsClient {
   status: WsClientProviderStatus;
+  isLoadingMessages: boolean;
   events: Record<string, unknown>[];
   send: (event: Record<string, unknown>) => void;
 }
 
 const WsClientContext = React.createContext<UseWsClient>({
   status: WsClientProviderStatus.STOPPED,
+  isLoadingMessages: true,
   events: [],
   send: () => {
     throw new Error("not connected");
@@ -46,6 +55,9 @@ export function WsClientProvider({
   const closeRef = React.useRef<ReturnType<typeof setTimeout> | null>(null);
   const [status, setStatus] = React.useState(WsClientProviderStatus.STOPPED);
   const [events, setEvents] = React.useState<Record<string, unknown>[]>([]);
+  const [retryCount, setRetryCount] = React.useState(RECONNECT_RETRIES);
+
+  const messageRateHandler = useRate({ threshold: 500 });
 
   function send(event: Record<string, unknown>) {
     if (!wsRef.current) {
@@ -56,6 +68,7 @@ export function WsClientProvider({
   }
 
   function handleOpen() {
+    setRetryCount(RECONNECT_RETRIES);
     setStatus(WsClientProviderStatus.OPENING);
     const initEvent = {
       action: ActionType.INIT,
@@ -66,6 +79,9 @@ export function WsClientProvider({
 
   function handleMessage(messageEvent: MessageEvent) {
     const event = JSON.parse(messageEvent.data);
+    if (isOpenHandsMessage(event)) {
+      messageRateHandler.record(new Date().getTime());
+    }
     setEvents((prevEvents) => [...prevEvents, event]);
     if (event.extras?.agent_state === AgentState.INIT) {
       setStatus(WsClientProviderStatus.ACTIVE);
@@ -76,11 +92,19 @@ export function WsClientProvider({
     ) {
       setStatus(WsClientProviderStatus.ERROR);
     }
+
+    handleAssistantMessage(event);
   }
 
   function handleClose() {
-    setStatus(WsClientProviderStatus.STOPPED);
-    setEvents([]);
+    if (retryCount) {
+      setTimeout(() => {
+        setRetryCount(retryCount - 1);
+      }, 1000);
+    } else {
+      setStatus(WsClientProviderStatus.STOPPED);
+      setEvents([]);
+    }
     wsRef.current = null;
   }
 
@@ -95,7 +119,7 @@ export function WsClientProvider({
     let ws = wsRef.current;
 
     // If disabled close any existing websockets...
-    if (!enabled) {
+    if (!enabled || !retryCount) {
       if (ws) {
         ws.close();
       }
@@ -116,7 +140,11 @@ export function WsClientProvider({
       const baseUrl =
         import.meta.env.VITE_BACKEND_BASE_URL || window?.location.host;
       const protocol = window.location.protocol === "https:" ? "wss:" : "ws:";
-      ws = new WebSocket(`${protocol}//${baseUrl}/ws`, [
+      let wsUrl = `${protocol}//${baseUrl}/ws`;
+      if (events.length) {
+        wsUrl += `?latest_event_id=${events[events.length - 1].id}`;
+      }
+      ws = new WebSocket(wsUrl, [
         "openhands",
         token || "NO_JWT",
         ghToken || "NO_GITHUB",
@@ -136,7 +164,7 @@ export function WsClientProvider({
       ws.removeEventListener("error", handleError);
       ws.removeEventListener("close", handleClose);
     };
-  }, [enabled, token, ghToken]);
+  }, [enabled, token, ghToken, retryCount]);
 
   // Strict mode mounts and unmounts each component twice, so we have to wait in the destructor
   // before actually closing the socket and cancel the operation if the component gets remounted.
@@ -148,7 +176,11 @@ export function WsClientProvider({
 
     return () => {
       closeRef.current = setTimeout(() => {
-        wsRef.current?.close();
+        const ws = wsRef.current;
+        if (ws) {
+          ws.removeEventListener("close", handleClose);
+          ws.close();
+        }
       }, 100);
     };
   }, []);
@@ -156,10 +188,11 @@ export function WsClientProvider({
   const value = React.useMemo<UseWsClient>(
     () => ({
       status,
+      isLoadingMessages: messageRateHandler.isUnderThreshold,
       events,
       send,
     }),
-    [status, events],
+    [status, messageRateHandler.isUnderThreshold, events],
   );
 
   return (

frontend/src/entry.client.tsx

@@ -12,15 +12,26 @@ import { Provider } from "react-redux";
 import posthog from "posthog-js";
 import "./i18n";
 import store from "./store";
+import OpenHands from "./api/open-hands";
 
 function PosthogInit() {
+  const [key, setKey] = React.useState<string | null>(null);
+
   React.useEffect(() => {
-    posthog.init("phc_3ESMmY9SgqEAGBB6sMGK5ayYHkeUuknH2vP6FmWH9RA", {
-      api_host: "https://us.i.posthog.com",
-      person_profiles: "identified_only",
+    OpenHands.getConfig().then((config) => {
+      setKey(config.POSTHOG_CLIENT_KEY);
     });
   }, []);
 
+  React.useEffect(() => {
+    if (key) {
+      posthog.init(key, {
+        api_host: "https://us.i.posthog.com",
+        person_profiles: "identified_only",
+      });
+    }
+  }, [key]);
+
   return null;
 }
 

frontend/src/i18n/translation.json

@@ -678,6 +678,16 @@
     "tr": "Sunucudan beklenmeyen yanıt yapısı",
     "no": "Uventet responsstruktur fra serveren"
   },
+  "EXPLORER$VSCODE_SWITCHING_MESSAGE": {
+    "en": "Switching to VS Code in 3 seconds...\nImportant: Please inform the agent of any changes you make in VS Code. To avoid conflicts, wait for the assistant to complete its work before making your own changes.",
+    "zh-CN": "3 秒后切换到 VS Code\n重要提示：请告知 OpenHands 您在 VS Code 中进行的任何更改。为了避免冲突，请在 OpenHands 完成工作后再进行自己的更改。",
+    "zh-TW": "3 秒後切換到 VS Code\n重要提示：請告知 OpenHands 您在 VS Code 中進行的任何更改。為避免衝突，請在 OpenHands 完成工作後再進行自己的更改。"
+  },
+  "EXPLORER$VSCODE_SWITCHING_ERROR_MESSAGE": {
+    "en": "Error switching to VS Code: {{error}}",
+    "zh-CN": "切换到 VS Code 时发生错误: {{error}}",
+    "zh-TW": "切換到 VS Code 時發生錯誤: {{error}}"
+  },
   "LOAD_SESSION$MODAL_TITLE": {
     "en": "Return to existing session?",
     "de": "Zurück zu vorhandener Sitzung?",

frontend/src/mocks/handlers.ts

@@ -71,8 +71,6 @@ const openHandsHandlers = [
 export const handlers = [
   ...openHandsHandlers,
   http.get("https://api.github.com/user/repos", async ({ request }) => {
-    if (import.meta.env.MODE !== "test") await delay(3500);
-
     const token = request.headers
       .get("Authorization")
       ?.replace("Bearer", "")

frontend/src/mocks/handlers.ws.ts

@@ -29,7 +29,7 @@ const generateAgentResponse = (message: string): AssistantMessageAction => ({
   action: "message",
   args: {
     content: message,
-    images_urls: [],
+    image_urls: [],
     wait_for_response: false,
   },
 });

frontend/src/routes/_oh._index/github-repo-selector.tsx

@@ -1,16 +1,16 @@
 import { Autocomplete, AutocompleteItem } from "@nextui-org/react";
 import { useDispatch } from "react-redux";
-import { useNavigate } from "react-router-dom";
 import { setSelectedRepository } from "#/state/initial-query-slice";
 
 interface GitHubRepositorySelectorProps {
+  onSelect: () => void;
   repositories: GitHubRepository[];
 }
 
 export function GitHubRepositorySelector({
+  onSelect,
   repositories,
 }: GitHubRepositorySelectorProps) {
-  const navigate = useNavigate();
   const dispatch = useDispatch();
 
   const handleRepoSelection = (id: string | null) => {
@@ -18,7 +18,7 @@ export function GitHubRepositorySelector({
     if (repo) {
       // set query param
       dispatch(setSelectedRepository(repo.full_name));
-      navigate("/app");
+      onSelect();
     }
   };
 

frontend/src/routes/_oh._index/route.tsx

@@ -5,7 +5,6 @@ import {
   defer,
   redirect,
   useLoaderData,
-  useNavigate,
   useRouteLoaderData,
 } from "@remix-run/react";
 import React from "react";
@@ -73,10 +72,10 @@ export const clientAction = async ({ request }: ClientActionFunctionArgs) => {
 };
 
 function Home() {
-  const navigate = useNavigate();
   const dispatch = useDispatch();
   const rootData = useRouteLoaderData<typeof rootClientLoader>("routes/_oh");
   const { repositories, githubAuthUrl } = useLoaderData<typeof clientLoader>();
+  const formRef = React.useRef<HTMLFormElement>(null);
 
   return (
     <div
@@ -86,7 +85,7 @@ function Home() {
       <HeroHeading />
       <div className="flex flex-col gap-16 w-[600px] items-center">
         <div className="flex flex-col gap-2 w-full">
-          <TaskForm />
+          <TaskForm ref={formRef} />
         </div>
         <div className="flex gap-4 w-full">
           <React.Suspense
@@ -100,6 +99,7 @@ function Home() {
             <Await resolve={repositories}>
               {(resolvedRepositories) => (
                 <GitHubRepositoriesSuggestionBox
+                  handleSubmit={() => formRef.current?.requestSubmit()}
                   repositories={resolvedRepositories}
                   gitHubAuthUrl={githubAuthUrl}
                   user={rootData?.user || null}
@@ -129,7 +129,7 @@ function Home() {
                       dispatch(
                         setImportedProjectZip(await convertZipToBase64(zip)),
                       );
-                      navigate("/app");
+                      formRef.current?.requestSubmit();
                     } else {
                       // TODO: handle error
                     }

frontend/src/routes/_oh._index/task-form.tsx

@@ -13,7 +13,7 @@ import { getRandomKey } from "#/utils/get-random-key";
 import { AttachImageLabel } from "#/components/attach-image-label";
 import { cn } from "#/utils/utils";
 
-export function TaskForm() {
+export const TaskForm = React.forwardRef<HTMLFormElement>((_, ref) => {
   const dispatch = useDispatch();
   const navigation = useNavigation();
 
@@ -21,7 +21,6 @@ export function TaskForm() {
     (state: RootState) => state.initalQuery,
   );
 
-  const formRef = React.useRef<HTMLFormElement>(null);
   const [text, setText] = React.useState("");
   const [suggestion, setSuggestion] = React.useState(
     getRandomKey(SUGGESTIONS["non-repo"]),
@@ -55,7 +54,7 @@ export function TaskForm() {
   return (
     <div className="flex flex-col gap-2 w-full">
       <Form
-        ref={formRef}
+        ref={ref}
         method="post"
         className="flex flex-col items-center gap-2"
         replace
@@ -67,20 +66,15 @@ export function TaskForm() {
         />
         <div
           className={cn(
-            "border border-neutral-600 px-4 py-[17px] rounded-lg text-[17px] leading-5 w-full transition-colors duration-200",
+            "border border-neutral-600 px-4 rounded-lg text-[17px] leading-5 w-full transition-colors duration-200",
             inputIsFocused ? "bg-neutral-600" : "bg-neutral-700",
             "hover:border-neutral-500 focus-within:border-neutral-500",
-            "group relative",
-            "before:pointer-events-none before:absolute before:inset-0 before:rounded-lg before:transition-colors",
-            "before:border-2 before:border-dashed before:border-transparent",
-            "[&:has(*:focus-within)]:before:border-neutral-500/50",
-            "[&:has(*[data-dragging-over='true'])]:before:border-neutral-500/50",
           )}
         >
           <ChatInput
             name="q"
             onSubmit={() => {
-              formRef.current?.requestSubmit();
+              if (typeof ref !== "function") ref?.current?.requestSubmit();
             }}
             onChange={(message) => setText(message)}
             onFocus={() => setInputIsFocused(true)}
@@ -96,7 +90,8 @@ export function TaskForm() {
             value={text}
             maxRows={15}
             showButton={!!text}
-            className="text-[17px] leading-5"
+            className="text-[17px] leading-5 py-[17px]"
+            buttonClassName="pb-[17px]"
             disabled={navigation.state === "submitting"}
           />
         </div>
@@ -120,4 +115,6 @@ export function TaskForm() {
       )}
     </div>
   );
-}
+});
+
+TaskForm.displayName = "TaskForm";

frontend/src/routes/_oh.app._index/code-editor-component.tsx

@@ -7,15 +7,15 @@ import { I18nKey } from "#/i18n/declaration";
 import { useFiles } from "#/context/files";
 import OpenHands from "#/api/open-hands";
 
-interface CodeEditorCompoonentProps {
+interface CodeEditorComponentProps {
   onMount: EditorProps["onMount"];
   isReadOnly: boolean;
 }
 
-function CodeEditorCompoonent({
+function CodeEditorComponent({
   onMount,
   isReadOnly,
-}: CodeEditorCompoonentProps) {
+}: CodeEditorComponentProps) {
   const { t } = useTranslation();
   const {
     files,
@@ -107,4 +107,4 @@ function CodeEditorCompoonent({
   );
 }
 
-export default React.memo(CodeEditorCompoonent);
+export default React.memo(CodeEditorComponent);

frontend/src/routes/_oh.app._index/route.tsx

@@ -8,10 +8,22 @@ import { RootState } from "#/store";
 import AgentState from "#/types/AgentState";
 import FileExplorer from "#/components/file-explorer/FileExplorer";
 import OpenHands from "#/api/open-hands";
-import CodeEditorCompoonent from "./code-editor-component";
+import CodeEditorComponent from "./code-editor-component";
 import { useFiles } from "#/context/files";
 import { EditorActions } from "#/components/editor-actions";
 
+const ASSET_FILE_TYPES = [
+  ".png",
+  ".jpg",
+  ".jpeg",
+  ".bmp",
+  ".gif",
+  ".pdf",
+  ".mp4",
+  ".webm",
+  ".ogg",
+];
+
 export const clientLoader = async () => {
   const token = localStorage.getItem("token");
   return json({ token });
@@ -104,6 +116,10 @@ function CodeEditor() {
     if (selectedPath) discardChanges(selectedPath);
   };
 
+  const isAssetFileType = selectedPath
+    ? ASSET_FILE_TYPES.some((ext) => selectedPath.endsWith(ext))
+    : false;
+
   return (
     <div className="flex h-full bg-neutral-900 relative">
       <FileExplorer
@@ -112,7 +128,7 @@ function CodeEditor() {
         error={errors.getFiles}
       />
       <div className="w-full">
-        {selectedPath && (
+        {selectedPath && !isAssetFileType && (
           <div className="flex w-full items-center justify-between self-end p-2">
             <span className="text-sm text-neutral-500">{selectedPath}</span>
             <EditorActions
@@ -122,7 +138,7 @@ function CodeEditor() {
             />
           </div>
         )}
-        <CodeEditorCompoonent
+        <CodeEditorComponent
           onMount={handleEditorDidMount}
           isReadOnly={!isEditingAllowed}
         />

frontend/src/routes/_oh.app.tsx

@@ -18,7 +18,6 @@ import { useEffectOnce } from "#/utils/use-effect-once";
 import CodeIcon from "#/icons/code.svg?react";
 import GlobeIcon from "#/icons/globe.svg?react";
 import ListIcon from "#/icons/list-type-number.svg?react";
-import { clearInitialQuery } from "#/state/initial-query-slice";
 import { isGitHubErrorReponse, retrieveLatestGitHubCommit } from "#/api/github";
 import { clearJupyter } from "#/state/jupyterSlice";
 import { FilesProvider } from "#/context/files";
@@ -28,8 +27,6 @@ import { EventHandler } from "#/components/event-handler";
 
 export const clientLoader = async () => {
   const ghToken = localStorage.getItem("ghToken");
-
-  const q = store.getState().initalQuery.initialQuery;
   const repo =
     store.getState().initalQuery.selectedRepository ||
     localStorage.getItem("repo");
@@ -55,7 +52,6 @@ export const clientLoader = async () => {
     token,
     ghToken,
     repo,
-    q,
     lastCommit,
   });
 };
@@ -91,7 +87,6 @@ function App() {
     dispatch(clearMessages());
     dispatch(clearTerminal());
     dispatch(clearJupyter());
-    dispatch(clearInitialQuery()); // Clear initial query when navigating to /app
   });
 
   const {

frontend/src/routes/_oh.tsx

@@ -171,6 +171,8 @@ export default function MainApp() {
         company: user.company,
         name: user.name,
         email: user.email,
+        user: user.login,
+        mode: window.__APP_MODE__ || "oss",
       });
     }
   }, [user]);
@@ -241,7 +243,7 @@ export default function MainApp() {
               type="button"
               aria-label="All Hands Logo"
               onClick={() => {
-                if (location.pathname === "/app")
+                if (location.pathname.startsWith("/app"))
                   setStartNewProjectModalIsOpen(true);
               }}
             >

frontend/src/services/chatService.ts

@@ -2,12 +2,12 @@ import ActionType from "#/types/ActionType";
 
 export function createChatMessage(
   message: string,
-  images_urls: string[],
+  image_urls: string[],
   timestamp: string,
 ) {
   const event = {
     action: ActionType.MESSAGE,
-    args: { content: message, images_urls, timestamp },
+    args: { content: message, image_urls, timestamp },
   };
   return event;
 }

frontend/src/types/core/actions.ts

@@ -4,7 +4,7 @@ export interface UserMessageAction extends OpenHandsActionEvent<"message"> {
   source: "user";
   args: {
     content: string;
-    images_urls: string[];
+    image_urls: string[];
   };
 }
 
@@ -23,7 +23,7 @@ export interface AssistantMessageAction
   source: "agent";
   args: {
     content: string;
-    images_urls: string[] | null;
+    image_urls: string[] | null;
     wait_for_response: boolean;
   };
 }

frontend/src/types/core/variances.ts

@@ -27,7 +27,7 @@ interface LocalUserMessageAction {
   action: "message";
   args: {
     content: string;
-    images_urls: string[];
+    image_urls: string[];
   };
 }
 

frontend/src/utils/clear-session.ts

@@ -1,7 +1,21 @@
+import store from "#/store";
+import { initialState as browserInitialState } from "#/state/browserSlice";
+
 /**
- * Clear the session data from the local storage. This will remove the token and repo
+ * Clear the session data from the local storage and reset relevant Redux state
  */
 export const clearSession = () => {
+  // Clear local storage
   localStorage.removeItem("token");
   localStorage.removeItem("repo");
+
+  // Reset browser state to initial values
+  store.dispatch({
+    type: "browser/setUrl",
+    payload: browserInitialState.url,
+  });
+  store.dispatch({
+    type: "browser/setScreenshotSrc",
+    payload: browserInitialState.screenshotSrc,
+  });
 };

frontend/src/utils/suggestions/repo-suggestions.ts

@@ -13,14 +13,14 @@ const KEY_2 = "Auto-merge Dependabot PRs";
 const VALUE_2 = `Please add a GitHub action to this repository which automatically merges pull requests from Dependabot so long as the tests are passing.`;
 
 const KEY_3 = "Fix up my README";
-const VALUE_3 = `"Please look at the README and make the following improvements, if they make sense:
+const VALUE_3 = `Please look at the README and make the following improvements, if they make sense:
 * correct any typos that you find
 * add missing language annotations on codeblocks
 * if there are references to other files or other sections of the README, turn them into links
 * make sure the readme has an h1 title towards the top
 * make sure any existing sections in the readme are appropriately separated with headings
 
-If there are no obvious ways to improve the README, make at least one small change to make the wording clearer or friendlier"`;
+If there are no obvious ways to improve the README, make at least one small change to make the wording clearer or friendlier`;
 
 const KEY_4 = "Clean up my dependencies";
 const VALUE_4 = `Examine the dependencies of the current codebase. Make sure you can run the code and any tests.

frontend/src/utils/toast.tsx

@@ -10,7 +10,6 @@ export default {
       style: {
         background: "#ef4444",
         color: "#fff",
-        lineBreak: "anywhere",
       },
       iconTheme: {
         primary: "#ef4444",
@@ -19,25 +18,20 @@ export default {
     });
     idMap.set(id, toastId);
   },
-  success: (id: string, msg: string) => {
-    const toastId = idMap.get(id);
-    if (toastId === undefined) return;
-    if (toastId) {
-      toast.success(msg, {
-        id: toastId,
-        duration: 4000,
-        style: {
-          background: "#333",
-          color: "#fff",
-          lineBreak: "anywhere",
-        },
-        iconTheme: {
-          primary: "#333",
-          secondary: "#fff",
-        },
-      });
-    }
-    idMap.delete(id);
+  success: (id: string, msg: string, duration: number = 4000) => {
+    if (idMap.has(id)) return; // prevent duplicate toast
+    const toastId = toast.success(msg, {
+      duration,
+      style: {
+        background: "#333",
+        color: "#fff",
+      },
+      iconTheme: {
+        primary: "#333",
+        secondary: "#fff",
+      },
+    });
+    idMap.set(id, toastId);
   },
   settingsChanged: (msg: string) => {
     toast(msg, {
@@ -48,7 +42,6 @@ export default {
       style: {
         background: "#333",
         color: "#fff",
-        lineBreak: "anywhere",
       },
     });
   },

frontend/src/utils/use-rate.ts

@@ -0,0 +1,67 @@
+import React from "react";
+
+interface UseRateProps {
+  threshold: number;
+}
+
+const DEFAULT_CONFIG: UseRateProps = { threshold: 1000 };
+
+export const useRate = (config = DEFAULT_CONFIG) => {
+  const [items, setItems] = React.useState<number[]>([]);
+  const [rate, setRate] = React.useState<number | null>(null);
+  const [lastUpdated, setLastUpdated] = React.useState<number | null>(null);
+  const [isUnderThreshold, setIsUnderThreshold] = React.useState(true);
+
+  /**
+   * Record an entry in order to calculate the rate
+   * @param entry Entry to record
+   *
+   * @example
+   * record(new Date().getTime());
+   */
+  const record = (entry: number) => {
+    setItems((prev) => [...prev, entry]);
+    setLastUpdated(new Date().getTime());
+  };
+
+  /**
+   * Update the rate based on the last two entries (if available)
+   */
+  const updateRate = () => {
+    if (items.length > 1) {
+      const newRate = items[items.length - 1] - items[items.length - 2];
+      setRate(newRate);
+
+      if (newRate <= config.threshold) setIsUnderThreshold(true);
+      else setIsUnderThreshold(false);
+    }
+  };
+
+  React.useEffect(() => {
+    updateRate();
+  }, [items]);
+
+  React.useEffect(() => {
+    // Set up an interval to check if the time since the last update exceeds the threshold
+    // If it does, set isUnderThreshold to false, otherwise set it to true
+    // This ensures that the component can react to periods of inactivity
+    const intervalId = setInterval(() => {
+      if (lastUpdated !== null) {
+        const timeSinceLastUpdate = new Date().getTime() - lastUpdated;
+        setIsUnderThreshold(timeSinceLastUpdate <= config.threshold);
+      } else {
+        setIsUnderThreshold(false);
+      }
+    }, config.threshold);
+
+    return () => clearInterval(intervalId);
+  }, [lastUpdated, config.threshold]);
+
+  return {
+    items,
+    rate,
+    lastUpdated,
+    isUnderThreshold,
+    record,
+  };
+};

frontend/tests/redirect.spec.ts

@@ -59,3 +59,29 @@ test("should redirect to /app after selecting a repo", async ({ page }) => {
   await page.waitForURL("/app");
   expect(page.url()).toBe("http://127.0.0.1:3000/app");
 });
+
+// FIXME: This fails because the MSW WS mocks change state too quickly,
+// missing the OPENING status where the initial query is rendered.
+test.fail(
+  "should redirect the user to /app with their initial query after selecting a project",
+  async ({ page }) => {
+    await page.goto("/");
+    await confirmSettings(page);
+
+    // enter query
+    const testQuery = "this is my test query";
+    const textbox = page.getByPlaceholder(/what do you want to build/i);
+    expect(textbox).not.toBeNull();
+    await textbox.fill(testQuery);
+
+    const fileInput = page.getByLabel("Upload a .zip");
+    const filePath = path.join(dirname, "fixtures/project.zip");
+    await fileInput.setInputFiles(filePath);
+
+    await page.waitForURL("/app");
+
+    // get user message
+    const userMessage = page.getByTestId("user-message");
+    expect(await userMessage.textContent()).toBe(testQuery);
+  },
+);

frontend/vite.config.ts

@@ -91,6 +91,7 @@ export default defineConfig(({ mode }) => {
     test: {
       environment: "jsdom",
       setupFiles: ["vitest.setup.ts"],
+      reporters: "basic",
       exclude: [...configDefaults.exclude, "tests"],
       coverage: {
         reporter: ["text", "json", "html", "lcov", "text-summary"],

frontend/vitest.setup.ts

@@ -13,7 +13,7 @@ vi.mock("react-i18next", async (importOriginal) => ({
 }));
 
 // Mock requests during tests
-beforeAll(() => server.listen());
+beforeAll(() => server.listen({ onUnhandledRequest: "bypass" }));
 afterEach(() => {
   server.resetHandlers();
   // Cleanup the document body after each test

openhands/agenthub/codeact_agent/action_parser.py

@@ -1,304 +0,0 @@
-import re
-
-from openhands.controller.action_parser import (
-    ActionParser,
-    ResponseParser,
-)
-from openhands.core.exceptions import LLMMalformedActionError
-from openhands.core.logger import openhands_logger as logger
-from openhands.events.action import (
-    Action,
-    AgentDelegateAction,
-    AgentFinishAction,
-    CmdRunAction,
-    FileEditAction,
-    IPythonRunCellAction,
-    MessageAction,
-)
-
-
-class CodeActResponseParser(ResponseParser):
-    """Parser action:
-    - CmdRunAction(command) - bash command to run
-    - FileEditAction(path, content) - edit a file
-    - IPythonRunCellAction(code) - IPython code to run
-    - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
-    - MessageAction(content) - Message action to run (e.g. ask for clarification)
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(self):
-        # Need pay attention to the item order in self.action_parsers
-        super().__init__()
-        self.action_parsers = [
-            CodeActActionParserFinish(),
-            CodeActActionParserFileEdit(),
-            CodeActActionParserCmdRun(),
-            CodeActActionParserIPythonRunCell(),
-            CodeActActionParserAgentDelegate(),
-        ]
-        self.default_parser = CodeActActionParserMessage()
-
-    def parse(self, response) -> Action:
-        action_str = self.parse_response(response)
-        return self.parse_action(action_str)
-
-    def parse_response(self, response) -> str:
-        action = response.choices[0].message.content
-        if action is None:
-            return ''
-        for lang in ['bash', 'ipython', 'browse']:
-            # special handling for DeepSeek: it has stop-word bug and returns </execute_ipython instead of </execute_ipython>
-            if f'</execute_{lang}' in action and f'</execute_{lang}>' not in action:
-                action = action.replace(f'</execute_{lang}', f'</execute_{lang}>')
-
-            if f'<execute_{lang}>' in action and f'</execute_{lang}>' not in action:
-                action += f'</execute_{lang}>'
-
-        # special handling for DeepSeek: it has stop-word bug and returns </execute_ipython instead of </execute_ipython>
-        if '</file_edit' in action and '</file_edit>' not in action:
-            action = action.replace('</file_edit', '</file_edit>')
-
-        if '<file_edit' in action and '</file_edit>' not in action:
-            action += '</file_edit>'
-        return action
-
-    def parse_action(self, action_str: str) -> Action:
-        for action_parser in self.action_parsers:
-            if action_parser.check_condition(action_str):
-                return action_parser.parse(action_str)
-        return self.default_parser.parse(action_str)
-
-    def action_to_str(self, action: Action) -> str:
-        if isinstance(action, CmdRunAction):
-            return (
-                f'{action.thought}\n<execute_bash>\n{action.command}\n</execute_bash>'
-            )
-        elif isinstance(action, IPythonRunCellAction):
-            return f'{action.thought}\n<execute_ipython>\n{action.code}\n</execute_ipython>'
-        elif isinstance(action, AgentDelegateAction):
-            return f'{action.thought}\n<execute_browse>\n{action.inputs["task"]}\n</execute_browse>'
-        elif isinstance(action, FileEditAction):
-            return f'{action.thought}\n<file_edit path={action.path}>\n{action.content}\n</file_edit>'
-        elif isinstance(action, MessageAction):
-            return action.content
-        elif isinstance(action, AgentFinishAction) and action.source == 'agent':
-            return action.thought
-        return ''
-
-
-class CodeActActionParserFinish(ActionParser):
-    """Parser action:
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(
-        self,
-    ):
-        self.finish_command = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.finish_command = re.search(r'<finish>.*</finish>', action_str, re.DOTALL)
-        return self.finish_command is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.finish_command is not None
-        ), 'self.finish_command should not be None when parse is called'
-        thought = action_str.replace(self.finish_command.group(0), '').strip()
-        return AgentFinishAction(thought=thought)
-
-
-class CodeActActionParserCmdRun(ActionParser):
-    """Parser action:
-    - CmdRunAction(command) - bash command to run
-    - AgentFinishAction() - end the interaction
-    """
-
-    def __init__(
-        self,
-    ):
-        self.bash_command = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.bash_command = re.search(
-            r'<execute_bash>(.*?)</execute_bash>', action_str, re.DOTALL
-        )
-        return self.bash_command is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.bash_command is not None
-        ), 'self.bash_command should not be None when parse is called'
-        thought = action_str.replace(self.bash_command.group(0), '').strip()
-        # a command was found
-        command_group = self.bash_command.group(1).strip()
-        if command_group.strip() == 'exit':
-            return AgentFinishAction(thought=thought)
-        return CmdRunAction(command=command_group, thought=thought)
-
-
-class CodeActActionParserIPythonRunCell(ActionParser):
-    """Parser action:
-    - IPythonRunCellAction(code) - IPython code to run
-    """
-
-    def __init__(
-        self,
-    ):
-        self.python_code = None
-        self.jupyter_kernel_init_code: str = 'from agentskills import *'
-
-    def check_condition(self, action_str: str) -> bool:
-        self.python_code = re.search(
-            r'<execute_ipython>(.*?)</execute_ipython>', action_str, re.DOTALL
-        )
-        return self.python_code is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.python_code is not None
-        ), 'self.python_code should not be None when parse is called'
-        code_group = self.python_code.group(1).strip()
-        thought = action_str.replace(self.python_code.group(0), '').strip()
-        return IPythonRunCellAction(
-            code=code_group,
-            thought=thought,
-            kernel_init_code=self.jupyter_kernel_init_code,
-        )
-
-
-class CodeActActionParserAgentDelegate(ActionParser):
-    """Parser action:
-    - AgentDelegateAction(agent, inputs) - delegate action for (sub)task
-    """
-
-    def __init__(
-        self,
-    ):
-        self.agent_delegate = None
-
-    def check_condition(self, action_str: str) -> bool:
-        self.agent_delegate = re.search(
-            r'<execute_browse>(.*)</execute_browse>', action_str, re.DOTALL
-        )
-        return self.agent_delegate is not None
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.agent_delegate is not None
-        ), 'self.agent_delegate should not be None when parse is called'
-        thought = action_str.replace(self.agent_delegate.group(0), '').strip()
-        browse_actions = self.agent_delegate.group(1).strip()
-        thought = (
-            f'{thought}\nI should start with: {browse_actions}'
-            if thought
-            else f'I should start with: {browse_actions}'
-        )
-
-        return AgentDelegateAction(
-            agent='BrowsingAgent', thought=thought, inputs={'task': browse_actions}
-        )
-
-
-class CodeActActionParserMessage(ActionParser):
-    """Parser action:
-    - MessageAction(content) - Message action to run (e.g. ask for clarification)
-    """
-
-    def __init__(
-        self,
-    ):
-        pass
-
-    def check_condition(self, action_str: str) -> bool:
-        # We assume the LLM is GOOD enough that when it returns pure natural language
-        # it wants to talk to the user
-        return True
-
-    def parse(self, action_str: str) -> Action:
-        return MessageAction(content=action_str, wait_for_response=True)
-
-
-class CodeActActionParserFileEdit(ActionParser):
-    """Parser action:
-    - FileEditAction(path, content) - edit a file
-    """
-
-    def __init__(self):
-        self.file_edit_match: re.Match | None = None
-
-    def check_condition(self, action_str: str) -> bool:
-        if '<file_edit' not in action_str:
-            return False
-
-        # Updated regex to make start and end optional
-        self.file_edit_match = re.search(
-            r'<file_edit\s+path=(["\']?)(.*?)\1(?:\s+start=(["\']?)(.*?)\3)?(?:\s+end=(["\']?)(.*?)\5)?\s*>(.*?)</file_edit>',
-            action_str,
-            re.DOTALL,
-        )
-
-        if self.file_edit_match is None:
-            logger.error(
-                f'FileEditAction detected but the format is incorrect. Unable to match for <file_edit> in:\n{"-" * 80}\n{action_str}\n{"-" * 80}'
-            )
-            raise LLMMalformedActionError(
-                'FileEditAction detected but the format is incorrect. Usage:\n'
-                '<file_edit path="[path]" start=[start_line] end=[end_line]>\n'
-                '[content_to_edit]\n'
-                '</file_edit>\n'
-            )
-
-        path = self.file_edit_match.group(2)
-        start = self.file_edit_match.group(4)
-        end = self.file_edit_match.group(6)
-
-        if not path:
-            raise LLMMalformedActionError(
-                'FileEditAction detected but no `path` specified. You should specify the path of the file to edit.'
-            )
-
-        if start:
-            try:
-                int(start)
-            except ValueError:
-                raise LLMMalformedActionError(
-                    f'FileEditAction detected but `start` is not a valid integer: {start}'
-                )
-
-        if end:
-            try:
-                int(end)
-            except ValueError:
-                raise LLMMalformedActionError(
-                    f'FileEditAction detected but `end` is not a valid integer: {end}'
-                )
-
-        return True
-
-    def parse(self, action_str: str) -> Action:
-        assert (
-            self.file_edit_match is not None
-        ), 'self.file_edit_match should not be None when parse is called'
-
-        file_path = self.file_edit_match.group(2).strip()
-        start_line = (
-            int(self.file_edit_match.group(4))
-            if self.file_edit_match.group(4)
-            else None
-        )
-        end_line = (
-            int(self.file_edit_match.group(6))
-            if self.file_edit_match.group(6)
-            else None
-        )
-        content = self.file_edit_match.group(7)
-        thought = action_str.replace(self.file_edit_match.group(0), '').strip()
-
-        action = FileEditAction(path=file_path, content=content, thought=thought)
-        if start_line is not None:
-            action.start = start_line
-        if end_line is not None:
-            action.end = end_line
-        return action

openhands/agenthub/codeact_agent/codeact_agent.py

@@ -1,12 +1,10 @@
 import json
 import os
 from collections import deque
-from itertools import islice
 
 from litellm import ModelResponse
 
 import openhands.agenthub.codeact_agent.function_calling as codeact_function_calling
-from openhands.agenthub.codeact_agent.action_parser import CodeActResponseParser
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig
@@ -70,7 +68,6 @@ class CodeActAgent(Agent):
         AgentSkillsRequirement(),
         JupyterRequirement(),
     ]
-    obs_prefix = 'OBSERVATION:\n'
 
     def __init__(
         self,
@@ -85,34 +82,30 @@ class CodeActAgent(Agent):
         super().__init__(llm, config)
         self.reset()
 
-        self.function_calling_active = self.config.function_calling
-        if self.function_calling_active and not self.llm.is_function_calling_active():
-            logger.warning(
-                f'Function calling not supported for model {self.llm.config.model}. '
-                'Disabling function calling.'
+        self.mock_function_calling = False
+        if not self.llm.is_function_calling_active():
+            logger.info(
+                f'Function calling not enabled for model {self.llm.config.model}. '
+                'Mocking function calling via prompting.'
             )
-            self.function_calling_active = False
+            self.mock_function_calling = True
 
-        if self.function_calling_active:
-            self.tools = codeact_function_calling.get_tools(
-                codeact_enable_browsing=self.config.codeact_enable_browsing,
-                codeact_enable_jupyter=self.config.codeact_enable_jupyter,
-                codeact_enable_llm_editor=self.config.codeact_enable_llm_editor,
-            )
-            logger.debug(
-                f'TOOLS loaded for CodeActAgent: {json.dumps(self.tools, indent=2)}'
-            )
-            self.prompt_manager = PromptManager(
-                microagent_dir=os.path.join(os.path.dirname(__file__), 'micro'),
-                prompt_dir=os.path.join(os.path.dirname(__file__), 'prompts', 'tools'),
-            )
-        else:
-            self.action_parser = CodeActResponseParser()
-            self.prompt_manager = PromptManager(
-                microagent_dir=os.path.join(os.path.dirname(__file__), 'micro'),
-                prompt_dir=os.path.join(os.path.dirname(__file__), 'prompts', 'default'),
-                agent_skills_docs=AgentSkillsRequirement.documentation,
-            )
+        # Function calling mode
+        self.tools = codeact_function_calling.get_tools(
+            codeact_enable_browsing=self.config.codeact_enable_browsing,
+            codeact_enable_jupyter=self.config.codeact_enable_jupyter,
+            codeact_enable_llm_editor=self.config.codeact_enable_llm_editor,
+        )
+        logger.debug(
+            f'TOOLS loaded for CodeActAgent: {json.dumps(self.tools, indent=2)}'
+        )
+        self.prompt_manager = PromptManager(
+            microagent_dir=os.path.join(os.path.dirname(__file__), 'micro')
+            if self.config.use_microagents
+            else None,
+            prompt_dir=os.path.join(os.path.dirname(__file__), 'prompts'),
+            disabled_microagents=self.config.disabled_microagents,
+        )
 
         self.pending_actions: deque[Action] = deque()
 
@@ -155,55 +148,52 @@ class CodeActAgent(Agent):
             action,
             (
                 AgentDelegateAction,
-                CmdRunAction,
                 IPythonRunCellAction,
                 FileEditAction,
                 BrowseInteractiveAction,
             ),
-        ) or (isinstance(action, AgentFinishAction) and action.source == 'agent'):
-            if self.function_calling_active:
-                tool_metadata = action.tool_call_metadata
-                assert tool_metadata is not None, (
-                    'Tool call metadata should NOT be None when function calling is enabled. Action: '
-                    + str(action)
-                )
+        ) or (
+            isinstance(action, (AgentFinishAction, CmdRunAction))
+            and action.source == 'agent'
+        ):
+            tool_metadata = action.tool_call_metadata
+            assert tool_metadata is not None, (
+                'Tool call metadata should NOT be None when function calling is enabled. Action: '
+                + str(action)
+            )
 
-                llm_response: ModelResponse = tool_metadata.model_response
-                assistant_msg = llm_response.choices[0].message
-                # Add the LLM message (assistant) that initiated the tool calls
-                # (overwrites any previous message with the same response_id)
-                pending_tool_call_action_messages[llm_response.id] = Message(
-                    role=assistant_msg.role,
-                    # tool call content SHOULD BE a string
-                    content=[TextContent(text=assistant_msg.content or '')]
-                    if assistant_msg.content is not None
-                    else [],
-                    tool_calls=assistant_msg.tool_calls,
-                )
-                return []
-            else:
-                assert not isinstance(action, BrowseInteractiveAction), (
-                    'BrowseInteractiveAction is not supported in non-function calling mode. Action: '
-                    + str(action)
-                )
-                content = [TextContent(text=self.action_parser.action_to_str(action))]
-                return [
-                    Message(
-                        role='user' if action.source == 'user' else 'assistant',
-                        content=content,
-                    )
-                ]
+            llm_response: ModelResponse = tool_metadata.model_response
+            assistant_msg = llm_response.choices[0].message
+            # Add the LLM message (assistant) that initiated the tool calls
+            # (overwrites any previous message with the same response_id)
+            pending_tool_call_action_messages[llm_response.id] = Message(
+                role=assistant_msg.role,
+                # tool call content SHOULD BE a string
+                content=[TextContent(text=assistant_msg.content or '')]
+                if assistant_msg.content is not None
+                else [],
+                tool_calls=assistant_msg.tool_calls,
+            )
+            return []
         elif isinstance(action, MessageAction):
             role = 'user' if action.source == 'user' else 'assistant'
             content = [TextContent(text=action.content or '')]
-            if self.llm.vision_is_active() and action.images_urls:
-                content.append(ImageContent(image_urls=action.images_urls))
+            if self.llm.vision_is_active() and action.image_urls:
+                content.append(ImageContent(image_urls=action.image_urls))
             return [
                 Message(
                     role=role,
                     content=content,
                 )
             ]
+        elif isinstance(action, CmdRunAction) and action.source == 'user':
+            content = [TextContent(text=f'User executed the command:\n{action.command}')]
+            return [
+                Message(
+                    role='user',
+                    content=content,
+                )
+            ]
         return []
 
     def get_observation_message(
@@ -238,15 +228,21 @@ class CodeActAgent(Agent):
         """
         message: Message
         max_message_chars = self.llm.config.max_message_chars
-        obs_prefix = 'OBSERVATION:\n'
         if isinstance(obs, CmdOutputObservation):
-            text = obs_prefix + truncate_content(
-                obs.content + obs.interpreter_details, max_message_chars
-            )
+            # if it doesn't have tool call metadata, it was triggered by a user action
+            if obs.tool_call_metadata is None:
+                text = truncate_content(
+                    f'\nObserved result of command executed by user:\n{obs.content}',
+                    max_message_chars,
+                )
+            else:
+                text = truncate_content(
+                    obs.content + obs.interpreter_details, max_message_chars
+                )
             text += f'\n[Command finished with exit code {obs.exit_code}]'
             message = Message(role='user', content=[TextContent(text=text)])
         elif isinstance(obs, IPythonRunCellObservation):
-            text = obs_prefix + obs.content
+            text = obs.content
             # replace base64 images with a placeholder
             splitted = text.split('\n')
             for i, line in enumerate(splitted):
@@ -258,22 +254,22 @@ class CodeActAgent(Agent):
             text = truncate_content(text, max_message_chars)
             message = Message(role='user', content=[TextContent(text=text)])
         elif isinstance(obs, FileEditObservation):
-            text = obs_prefix + truncate_content(str(obs), max_message_chars)
+            text = truncate_content(str(obs), max_message_chars)
             message = Message(role='user', content=[TextContent(text=text)])
         elif isinstance(obs, BrowserOutputObservation):
             text = obs.get_agent_obs_text()
             message = Message(
                 role='user',
-                content=[TextContent(text=obs_prefix + text)],
+                content=[TextContent(text=text)],
             )
         elif isinstance(obs, AgentDelegateObservation):
-            text = obs_prefix + truncate_content(
+            text = truncate_content(
                 obs.outputs['content'] if 'content' in obs.outputs else '',
                 max_message_chars,
             )
             message = Message(role='user', content=[TextContent(text=text)])
         elif isinstance(obs, ErrorObservation):
-            text = obs_prefix + truncate_content(obs.content, max_message_chars)
+            text = truncate_content(obs.content, max_message_chars)
             text += '\n[Error occurred in processing last action]'
             message = Message(role='user', content=[TextContent(text=text)])
         elif isinstance(obs, UserRejectObservation):
@@ -285,19 +281,18 @@ class CodeActAgent(Agent):
             # when the LLM tries to return the next message
             raise ValueError(f'Unknown observation type: {type(obs)}')
 
-        if self.function_calling_active:
-            # Update the message as tool response properly
-            if (tool_call_metadata := obs.tool_call_metadata) is not None:
-                tool_call_id_to_message[tool_call_metadata.tool_call_id] = Message(
-                    role='tool',
-                    content=message.content,
-                    tool_call_id=tool_call_metadata.tool_call_id,
-                    name=tool_call_metadata.function_name,
-                )
-                # No need to return the observation message
-                # because it will be added by get_action_message when all the corresponding
-                # tool calls in the SAME request are processed
-                return []
+        # Update the message as tool response properly
+        if (tool_call_metadata := obs.tool_call_metadata) is not None:
+            tool_call_id_to_message[tool_call_metadata.tool_call_id] = Message(
+                role='tool',
+                content=message.content,
+                tool_call_id=tool_call_metadata.tool_call_id,
+                name=tool_call_metadata.function_name,
+            )
+            # No need to return the observation message
+            # because it will be added by get_action_message when all the corresponding
+            # tool calls in the SAME request are processed
+            return []
 
         return [message]
 
@@ -333,25 +328,14 @@ class CodeActAgent(Agent):
         params: dict = {
             'messages': self.llm.format_messages_for_llm(messages),
         }
-        if self.function_calling_active:
-            params['tools'] = self.tools
-            params['parallel_tool_calls'] = False
-        else:
-            params['stop'] = [
-                '</execute_ipython>',
-                '</execute_bash>',
-                '</execute_browse>',
-                '</file_edit>',
-            ]
+        params['tools'] = self.tools
+        if self.mock_function_calling:
+            params['mock_function_calling'] = True
         response = self.llm.completion(**params)
-
-        if self.function_calling_active:
-            actions = codeact_function_calling.response_to_actions(response)
-            for action in actions:
-                self.pending_actions.append(action)
-            return self.pending_actions.popleft()
-        else:
-            return self.action_parser.parse(response)
+        actions = codeact_function_calling.response_to_actions(response)
+        for action in actions:
+            self.pending_actions.append(action)
+        return self.pending_actions.popleft()
 
     def _get_messages(self, state: State) -> list[Message]:
         """Constructs the message history for the LLM conversation.
@@ -482,7 +466,4 @@ class CodeActAgent(Agent):
                     else:
                         break
 
-        if not self.function_calling_active:
-            self.prompt_manager.add_turns_left_reminder(messages, state)
-
         return messages

openhands/agenthub/codeact_agent/function_calling.py

@@ -53,9 +53,6 @@ _IPYTHON_DESCRIPTION = """Run a cell of Python code in an IPython environment.
 * The assistant should define variables and import packages before using them.
 * The variable defined in the IPython environment will not be available outside the IPython environment (e.g., in terminal).
 """
-# We are not using agentskills's file_ops for viewing files now because StrReplaceEditorTool already supports viewing files
-# """* Apart from the standard Python library, the assistant can also use the following functions (already imported):
-# {AgentSkillsRequirement.documentation}"""
 
 IPythonTool = ChatCompletionToolParam(
     type='function',

openhands/agenthub/codeact_agent/prompts/default/system_prompt.j2

@@ -1,174 +0,0 @@
-{% set MINIMAL_SYSTEM_PREFIX %}
-A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed answers to the user's questions.
-
-[1] The assistant can use a Python environment with <execute_ipython>, e.g.:
-<execute_ipython>
-print("Hello World!")
-</execute_ipython>
-
-[2] The assistant can execute bash commands wrapped with <execute_bash>, e.g. <execute_bash> ls </execute_bash>.
-If a bash command returns exit code `-1`, this means the process is not yet finished.
-The assistant must then send a second <execute_bash>. The second <execute_bash> can be empty
-(which will retrieve any additional logs), or it can contain text to be sent to STDIN of the running process,
-or it can contain the text `ctrl+c` to interrupt the process.
-
-For commands that may run indefinitely, the output should be redirected to a file and the command run
-in the background, e.g. <execute_bash> python3 app.py > server.log 2>&1 & </execute_bash>
-If a command execution result says "Command timed out. Sending SIGINT to the process",
-the assistant should retry running the command in the background.
-
-[3] The assistant can edit files using <file_edit> by setting the file path and providing a draft of the new file content. The draft file content does not need to be exactly the same as the existing file content; the assistant may skip some lines and only include the parts that need to be changed.
-
-IMPORTANT: When editing large file (e.g., > 300 lines), the assistant MUST SPECIFY the range of lines to be edited by setting `start` and `end` (1-indexed, both inclusive). For example, `<file_edit path="/path/to/file.txt" start=1 end=-1>` means the assistant will edit the whole file (from line 1 to the end of the file). `start=1` and `end=-1` are the default values, so the assistant can omit them if they are the same as the default values.
-BEFORE you start editing, you MUST view the ENTIRE body of the part you want to edit and get the correct begin and end line numbers.
-
-When editing files, the assistant should include comments indicating where the code will not change. For example, use comments like `# no changes before` or `# no changes here` to clearly mark sections of the code that remain unchanged. This helps to provide context and ensure clarity in the edits being made.
-
-Possible cases:
-- File too long: When the file to be edited is too long, the assistant should set `start` and `end` (1-indexed, both inclusive) to specify the range of lines to be edited. For example, `<file_edit path="/path/to/file.txt" start=100 end=200>` means the assistant will only edit lines 100 to 200 of `/path/to/file.txt`.
-- Append to file: If the assistant wants to append to a file, it should set both `start` and `end` to `-1`.
-- File does not exist: If `<file_edit>` is pointing to a file that does not exist, a new file with the exact content will be created.
-
-Important: because line numbers are useful, the assistant should always use the provided functions to search (e.g., `search_dir`) or view the file content (e.g., `open_file`) along with the line numbers. DO NOT use other methods (e.g., `cat`) to view the file content.
-
-**Example 1 (general edit for short files)**
-For example, given an existing file `/path/to/file.py` that looks like this:
-
-(this is the end of the file)
-1|class MyClass:
-2|    def __init__(self):
-3|        self.x = 1
-4|        self.y = 2
-5|        self.z = 3
-6|
-7|print(MyClass().z)
-8|print(MyClass().x)
-(this is the end of the file)
-
-
-The assistant wants to edit the file to look like this:
-
-(this is the end of the file)
-1|class MyClass:
-2|    def __init__(self):
-3|        self.x = 1
-4|        self.y = 2
-5|
-6|print(MyClass().y)
-(this is the end of the file)
-
-
-The assistant may produce an edit action like this:
-<file_edit path="/path/to/file.txt" start=1 end=-1>
-class MyClass:
-    def __init__(self):
-        # no changes before
-        self.y = 2
-        # self.z is removed
-
-# MyClass().z is removed
-print(MyClass().y)
-</file_edit>
-
-**Example 2 (append to file for short files)**
-
-For example, given an existing file `/path/to/file.py` that looks like this:
-
-(this is the end of the file)
-1|class MyClass:
-2|    def __init__(self):
-3|        self.x = 1
-4|        self.y = 2
-5|        self.z = 3
-6|
-7|print(MyClass().z)
-8|print(MyClass().x)
-(this is the end of the file)
-
-To append the following lines to the file:
-```python
-print(MyClass().y)
-```
-
-The assistant may produce an edit action like this:
-<file_edit path="/path/to/file.txt" start=-1 end=-1>
-print(MyClass().y)
-</file_edit>
-
-**Example 3 (edit for long files)**
-
-Given an existing file `/path/to/file.py` that looks like this:
-
-(1000 more lines above)
-1001|class MyClass:
-1002|    def __init__(self):
-1003|        self.x = 1
-1004|        self.y = 2
-1005|        self.z = 3
-1006|
-1007|print(MyClass().z)
-1008|print(MyClass().x)
-(2000 more lines below)
-
-
-The assistant wants to edit the file to look like this:
-
-(1000 more lines above)
-1001|class MyClass:
-1002|    def __init__(self):
-1003|        self.x = 1
-1004|        self.y = 2
-1005|
-1006|print(MyClass().y)
-(2000 more lines below)
-
-The assistant may produce an edit action like this:
-
-<file_edit path="/path/to/file.txt" start=1001 end=1008>
-class MyClass:
-    def __init__(self):
-        # no changes before
-        self.y = 2
-        # self.z is removed
-
-# MyClass().z is removed
-print(MyClass().y)
-</file_edit>
-
-
-{% endset %}
-{% set BROWSING_PREFIX %}
-The assistant can browse the Internet with <execute_browse> and </execute_browse>.
-For example, <execute_browse> Tell me the usa's president using google search </execute_browse>.
-Or <execute_browse> Tell me what is in http://example.com </execute_browse>.
-{% endset %}
-{% set PIP_INSTALL_PREFIX %}
-The assistant can install Python packages using the %pip magic command in an IPython environment by using the following syntax: <execute_ipython> %pip install [package needed] </execute_ipython> and should always import packages and define variables before starting to use them.
-{% endset %}
-{% set SYSTEM_PREFIX = MINIMAL_SYSTEM_PREFIX + BROWSING_PREFIX + PIP_INSTALL_PREFIX %}
-{% set COMMAND_DOCS %}
-Apart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:
-{{ agent_skills_docs }}
-IMPORTANT:
-- `open_file` only returns the first 100 lines of the file by default! The assistant MUST use `scroll_down` repeatedly to read the full file BEFORE making edits!
-- Indentation is important and code that is not indented correctly will fail and require fixing before it can be run.
-- Any code issued should be less than 50 lines to avoid context being cut off!
-{% endset %}
-{% set SYSTEM_SUFFIX %}
-Responses should be concise.
-The assistant should attempt fewer things at a time instead of putting too many commands OR too much code in one "execute" block.
-Include ONLY ONE <execute_ipython>, <execute_bash>, or <execute_browse> per response, unless the assistant is finished with the task or needs more input or action from the user in order to proceed.
-If the assistant is finished with the task you MUST include <finish></finish> in your response.
-IMPORTANT: Execute code using <execute_ipython>, <execute_bash>, or <execute_browse> whenever possible.
-The assistant should utilize full file paths and the `pwd` command to prevent path-related errors.
-The assistant MUST NOT apologize to the user or thank the user after running commands or editing files. It should only address the user in response to an explicit message from the user, or to ask for more information.
-The assistant MUST NOT push any changes to GitHub unless explicitly requested to do so.
-The assistant MUST NOT include comments in the code unless they are necessary to describe non-obvious behavior, or
-to describe precisely how to apply proposed edits. Comments about applying edits should always have blank lines above
-and below.
-
-{% endset %}
-{# Combine all parts without newlines between them #}
-{{ SYSTEM_PREFIX -}}
-{{- COMMAND_DOCS -}}
-{{- SYSTEM_SUFFIX }}

openhands/agenthub/codeact_agent/prompts/default/user_prompt.j2

@@ -1,219 +0,0 @@
-{% set DEFAULT_EXAMPLE %}
---- START OF EXAMPLE ---
-
-USER: Create a list of numbers from 1 to 10, and display them in a web page at port 5000.
-
-ASSISTANT:
-Sure! Let me first check the current directory:
-<execute_bash>
-ls
-</execute_bash>
-
-USER:
-OBSERVATION:
-openhands@runtime:~/workspace$
-
-ASSISTANT:
-There is no `app.py` file in the current directory. Let me create a Python file `app.py`:
-<file_edit path="/workspace/app.py" start=-1 end=-1>
-from flask import Flask
-app = Flask(__name__)
-
-@app.route('/')
-def index():
-    numbers = list(range(1, 11))
-    return str(numbers)
-
-if __name__ == '__main__':
-    app.run(port=5000)
-</file_edit>
-
-USER:
-OBSERVATION:
-[New file /workspace/app.py is created.]
-(begin of changes)
---- /workspace/app.py
-+++ /workspace/app.py
-@@ -1 +1,10 @@
-+from flask import Flask
-+app = Flask(__name__)
-
-+@app.route('/')
-+def index():
-+    numbers = list(range(1, 11))
-+    return str(numbers)
-+
-+if __name__ == '__main__':
-+    app.run(port=5000)
-(end of changes)
-
-ASSISTANT:
-I have created a Python file `app.py` that will display a list of numbers from 1 to 10 when you run it. Let me run the Python file for you:
-<execute_bash>
-python3 app.py > server.log 2>&1 &
-</execute_bash>
-
-USER:
-OBSERVATION:
-[1] 121[1]+  Exit 1                  python3 app.py > server.log 2>&1
-
-ASSISTANT: Looks like the server is running with PID 121 then crashed. Let me check the server log:
-<execute_bash>
-cat server.log
-</execute_bash>
-
-USER:
-OBSERVATION:
-Traceback (most recent call last):
-  File "/workspace/app.py", line 2, in <module>
-    from flask import Flask
-ModuleNotFoundError: No module named 'flask'
-
-ASSISTANT:
-It seems that Flask is not installed. Let me install Flask for you:
-<execute_bash>
-pip install flask
-</execute_bash>
-
-USER:
-OBSERVATION:
-Defaulting to user installation because normal site-packages is not writeable
-Collecting flask
-  Using cached flask-3.0.3-py3-none-any.whl (101 kB)
-Collecting blinker>=1.6.2
-  Using cached blinker-1.7.0-py3-none-any.whl (13 kB)
-Collecting Werkzeug>=3.0.0
-  Using cached werkzeug-3.0.2-py3-none-any.whl (226 kB)
-Collecting click>=8.1.3
-  Using cached click-8.1.7-py3-none-any.whl (97 kB)
-Collecting itsdangerous>=2.1.2
-  Using cached itsdangerous-2.2.0-py3-none-any.whl (16 kB)
-Requirement already satisfied: Jinja2>=3.1.2 in /home/openhands/.local/lib/python3.10/site-packages (from flask) (3.1.3)
-Requirement already satisfied: MarkupSafe>=2.0 in /home/openhands/.local/lib/python3.10/site-packages (from Jinja2>=3.1.2->flask) (2.1.5)
-Installing collected packages: Werkzeug, itsdangerous, click, blinker, flask
-Successfully installed Werkzeug-3.0.2 blinker-1.7.0 click-8.1.7 flask-3.0.3 itsdangerous-2.2.0
-
-ASSISTANT:
-Now that Flask is installed, let me run the Python file again:
-<execute_bash>
-python3 app.py > server.log 2>&1 &
-</execute_bash>
-
-USER:
-OBSERVATION:
-[1] 124
-
-ASSISTANT:
-Let me check the server log again:
-<execute_bash>
-cat server.log
-</execute_bash>
-
-USER:
-OBSERVATION:
-* Serving Flask app 'app'
- * Debug mode: off
-WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
- * Running on http://127.0.0.1:5000
-Press CTRL+C to quit
-
-ASSISTANT:
-The server is running on port 5000 with PID 124. You can access the list of numbers by visiting http://127.0.0.1:5000. If you have any further questions, feel free to ask!
-
-USER: Now browse the newly started server's homepage and show me the content.
-
-ASSISTANT:
-Sure! Let me browse the server's homepage at http://127.0.0.1:5000:
-<execute_browse>
-Get the content on "http://127.0.0.1:5000"
-</execute_browse>
-
-USER:
-OBSERVATION:
-[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
-
-ASSISTANT:
-The content of the server's homepage is "[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]". If you have any further questions, feel free to ask!
-
-USER: Now kill the server, make it display the numbers in a table format.
-
-ASSISTANT:
-Sure! Let me stop the server first:
-<execute_bash>
-kill 124
-</execute_bash>
-
-USER:
-OBSERVATION:
-[1]+  Terminated              python3 app.py > server.log 2>&1
-
-ASSISTANT:
-The server has been stopped. Let me open the Python file and modify it.
-<execute_ipython>
-open_file('app.py')
-</execute_ipython>
-
-USER:
-[File: /workspace/app.py (10 lines total)]
-(this is the beginning of the file)
-1|from flask import Flask
-2|app = Flask(__name__)
-3|
-4|@app.route('/')
-5|def index():
-6|    numbers = list(range(1, 11))
-7|    return str(numbers)
-8|
-9|if __name__ == '__main__':
-10|    app.run(port=5000)
-(this is the end of the file)
-
-ASSISTANT:
-I should edit the file to display the numbers in a table format. I should include correct indentation. Let me update the file:
-<file_edit path="/workspace/app.py" start=4 end=7>
-@app.route('/')
-def index():
-    numbers = list(range(1, 11))
-    ret = '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
-    return ret
-</file_edit>
-
-USER:
-Observation:
-[Edited existing file /workspace/app.py]
-[File: /workspace/app.py (10 lines total after edit)]
-(this is the beginning of the file)
-1|from flask import Flask
-2|app = Flask(__name__)
-3|
-4|@app.route('/')
-5|def index():
-6|    numbers = list(range(1, 11))
-7|    ret = '<table>' + ''.join([f'<tr><td>{i}</td></tr>' for i in numbers]) + '</table>'
-8|    return ret
-9|
-10|if __name__ == '__main__':
-11|    app.run(port=5000)
-(this is the end of the file)
-[File updated (edited at line 7). Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
-
-ASSISTANT:
-Running the updated file:
-<execute_bash>
-python3 app.py > server.log 2>&1 &
-</execute_bash>
-
-USER:
-Observation:
-[1] 126
-
-ASSISTANT:
-The server is running on port 5000 with PID 126. You can access the list of numbers in a table format by visiting http://127.0.0.1:5000. Let me know if you have any further requests!
-<finish></finish>
-
---- END OF EXAMPLE ---
-{% endset %}
-Here is an example of how you can interact with the environment for task solving:
-{{ DEFAULT_EXAMPLE }}
-
-NOW, LET'S START!

openhands/agenthub/codeact_agent/prompts/system_prompt.j2

@@ -4,4 +4,3 @@ You are OpenHands agent, a helpful AI assistant that can interact with a compute
 * When configuring git credentials, use "openhands" as the user.name and "openhands@all-hands.dev" as the user.email by default, unless explicitly instructed otherwise.
 * The assistant MUST NOT include comments in the code unless they are necessary to describe non-obvious behavior.
 </IMPORTANT>
-

openhands/agenthub/codeact_swe_agent/codeact_swe_agent.py

@@ -95,9 +95,9 @@ class CodeActSWEAgent(Agent):
             if (
                 self.llm.vision_is_active()
                 and isinstance(action, MessageAction)
-                and action.images_urls
+                and action.image_urls
             ):
-                content.append(ImageContent(image_urls=action.images_urls))
+                content.append(ImageContent(image_urls=action.image_urls))
 
             return Message(
                 role='user' if action.source == 'user' else 'assistant', content=content

openhands/controller/agent_controller.py

@@ -5,12 +5,14 @@ import traceback
 from typing import Callable, ClassVar, Type
 
 import litellm
+from litellm.exceptions import ContextWindowExceededError
 
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State, TrafficControlState
 from openhands.controller.stuck import StuckDetector
 from openhands.core.config import AgentConfig, LLMConfig
 from openhands.core.exceptions import (
+    FunctionCallValidationError,
     LLMMalformedActionError,
     LLMNoActionError,
     LLMResponseError,
@@ -42,7 +44,7 @@ from openhands.events.observation import (
 )
 from openhands.events.serialization.event import truncate_content
 from openhands.llm.llm import LLM
-from openhands.runtime.utils.shutdown_listener import should_continue
+from openhands.utils.shutdown_listener import should_continue
 
 # note: RESUME is only available on web GUI
 TRAFFIC_CONTROL_REMINDER = (
@@ -63,6 +65,7 @@ class AgentController:
     parent: 'AgentController | None' = None
     delegate: 'AgentController | None' = None
     _pending_action: Action | None = None
+    _closed: bool = False
     filter_out: ClassVar[tuple[type[Event], ...]] = (
         NullAction,
         NullObservation,
@@ -158,6 +161,7 @@ class AgentController:
 
         # unsubscribe from the event stream
         self.event_stream.unsubscribe(EventStreamSubscriber.AGENT_CONTROLLER, self.id)
+        self._closed = True
 
     def log(self, level: str, message: str, extra: dict | None = None):
         """Logs a message to the agent controller's logger.
@@ -192,6 +196,8 @@ class AgentController:
 
         self.log('info', 'Starting step loop...')
         while should_continue():
+            if self._closed:
+                break
             try:
                 await self._step()
             except asyncio.CancelledError:
@@ -477,7 +483,12 @@ class AgentController:
             action = self.agent.step(self.state)
             if action is None:
                 raise LLMNoActionError('No action was returned')
-        except (LLMMalformedActionError, LLMNoActionError, LLMResponseError) as e:
+        except (
+            LLMMalformedActionError,
+            LLMNoActionError,
+            LLMResponseError,
+            FunctionCallValidationError,
+        ) as e:
             self.event_stream.add_event(
                 ErrorObservation(
                     content=str(e),
@@ -485,6 +496,15 @@ class AgentController:
                 EventSource.AGENT,
             )
             return
+        except ContextWindowExceededError:
+            # When context window is exceeded, keep roughly half of agent interactions
+            self.state.history = self._apply_conversation_window(self.state.history)
+
+            # Save the ID of the first event in our truncated history for future reloading
+            if self.state.history:
+                self.state.start_id = self.state.history[0].id
+            # Don't add error event - let the agent retry with reduced context
+            return
 
         if action.runnable:
             if self.state.confirmation_mode and (
@@ -659,6 +679,12 @@ class AgentController:
         - For delegate events (between AgentDelegateAction and AgentDelegateObservation):
             - Excludes all events between the action and observation
             - Includes the delegate action and observation themselves
+
+        The history is loaded in two parts if truncation_id is set:
+        1. First user message from start_id onwards
+        2. Rest of history from truncation_id to the end
+
+        Otherwise loads normally from start_id.
         """
 
         # define range of events to fetch
@@ -680,8 +706,33 @@ class AgentController:
             self.state.history = []
             return
 
-        # Get all events, filtering out backend events and hidden events
-        events = list(
+        events: list[Event] = []
+
+        # If we have a truncation point, get first user message and then rest of history
+        if hasattr(self.state, 'truncation_id') and self.state.truncation_id > 0:
+            # Find first user message from stream
+            first_user_msg = next(
+                (
+                    e
+                    for e in self.event_stream.get_events(
+                        start_id=start_id,
+                        end_id=end_id,
+                        reverse=False,
+                        filter_out_type=self.filter_out,
+                        filter_hidden=True,
+                    )
+                    if isinstance(e, MessageAction) and e.source == EventSource.USER
+                ),
+                None,
+            )
+            if first_user_msg:
+                events.append(first_user_msg)
+
+            # the rest of the events are from the truncation point
+            start_id = self.state.truncation_id
+
+        # Get rest of history
+        events_to_add = list(
             self.event_stream.get_events(
                 start_id=start_id,
                 end_id=end_id,
@@ -690,6 +741,7 @@ class AgentController:
                 filter_hidden=True,
             )
         )
+        events.extend(events_to_add)
 
         # Find all delegate action/observation pairs
         delegate_ranges: list[tuple[int, int]] = []
@@ -744,6 +796,92 @@ class AgentController:
         # make sure history is in sync
         self.state.start_id = start_id
 
+    def _apply_conversation_window(self, events: list[Event]) -> list[Event]:
+        """Cuts history roughly in half when context window is exceeded, preserving action-observation pairs
+        and ensuring the first user message is always included.
+
+        The algorithm:
+        1. Cut history in half
+        2. Check first event in new history:
+           - If Observation: find and include its Action
+           - If MessageAction: ensure its related Action-Observation pair isn't split
+        3. Always include the first user message
+
+        Args:
+            events: List of events to filter
+
+        Returns:
+            Filtered list of events keeping newest half while preserving pairs
+        """
+        if not events:
+            return events
+
+        # Find first user message - we'll need to ensure it's included
+        first_user_msg = next(
+            (
+                e
+                for e in events
+                if isinstance(e, MessageAction) and e.source == EventSource.USER
+            ),
+            None,
+        )
+
+        # cut in half
+        mid_point = max(1, len(events) // 2)
+        kept_events = events[mid_point:]
+
+        # Handle first event in truncated history
+        if kept_events:
+            i = 0
+            while i < len(kept_events):
+                first_event = kept_events[i]
+                if isinstance(first_event, Observation) and first_event.cause:
+                    # Find its action and include it
+                    matching_action = next(
+                        (
+                            e
+                            for e in reversed(events[:mid_point])
+                            if isinstance(e, Action) and e.id == first_event.cause
+                        ),
+                        None,
+                    )
+                    if matching_action:
+                        kept_events = [matching_action] + kept_events
+                    else:
+                        self.log(
+                            'warning',
+                            f'Found Observation without matching Action at id={first_event.id}',
+                        )
+                        # drop this observation
+                        kept_events = kept_events[1:]
+                    break
+
+                elif isinstance(first_event, MessageAction) or (
+                    isinstance(first_event, Action)
+                    and first_event.source == EventSource.USER
+                ):
+                    # if it's a message action or a user action, keep it and continue to find the next event
+                    i += 1
+                    continue
+
+                else:
+                    # if it's an action with source == EventSource.AGENT, we're good
+                    break
+
+        # Save where to continue from in next reload
+        if kept_events:
+            self.state.truncation_id = kept_events[0].id
+
+        # Ensure first user message is included
+        if first_user_msg and first_user_msg not in kept_events:
+            kept_events = [first_user_msg] + kept_events
+
+        # start_id points to first user message
+        if first_user_msg:
+            self.state.start_id = first_user_msg.id
+
+        return kept_events
+
     def _is_stuck(self):
         """Checks if the agent or its delegate is stuck in a loop.
 

openhands/controller/state/state.py

@@ -92,6 +92,8 @@ class State:
     # start_id and end_id track the range of events in history
     start_id: int = -1
     end_id: int = -1
+    # truncation_id tracks where to load history after context window truncation
+    truncation_id: int = -1
     almost_stuck: int = 0
     delegates: dict[tuple[int, int], tuple[str, str]] = field(default_factory=dict)
     # NOTE: This will never be used by the controller, but it can be used by different
@@ -149,7 +151,7 @@ class State:
         for event in reversed(self.history):
             if isinstance(event, MessageAction) and event.source == 'user':
                 last_user_message = event.content
-                last_user_message_image_urls = event.images_urls
+                last_user_message_image_urls = event.image_urls
             elif isinstance(event, AgentFinishAction):
                 if last_user_message is not None:
                     return last_user_message, None

openhands/core/cli.py

@@ -116,6 +116,7 @@ async def main():
         event_stream=event_stream,
         sid=sid,
         plugins=agent_cls.sandbox_plugins,
+        headless_mode=True,
     )
 
     controller = AgentController(