[Bug]: Prevent selection of "add more repo" option in dropdown (#5688)

Co-authored-by: openhands <openhands@all-hands.dev>

.github/workflows/ghcr-build.yml

@@ -68,9 +68,6 @@ jobs:
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
-      - name: "Set up docker layer caching"
-        uses: satackey/action-docker-layer-caching@v0.0.11
-        continue-on-error: true
       - name: Build and push app image
         if: "!github.event.pull_request.head.repo.fork"
         run: |

.github/workflows/openhands-resolver.yml

@@ -59,7 +59,6 @@ jobs:
       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') &&
         contains(github.event.comment.body, inputs.macro || '@openhands-agent') &&
@@ -140,15 +139,19 @@ jobs:
 
       - name: Set environment variables
         run: |
-          if [ -n "${{ github.event.review.body }}" ]; then
+          # Handle pull request events first
+          if [ -n "${{ github.event.pull_request.number }}" ]; then
             echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
             echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
+          # Handle pull request review events
+          elif [ -n "${{ github.event.review.body }}" ]; then
+            echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
+            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
+          # Handle issue comment events that reference a PR
           elif [ -n "${{ 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" >> $GITHUB_ENV
+          # Handle regular issue events
           else
             echo "ISSUE_NUMBER=${{ github.event.issue.number }}" >> $GITHUB_ENV
             echo "ISSUE_TYPE=issue" >> $GITHUB_ENV
@@ -181,17 +184,32 @@ jobs:
             });
 
       - name: Install OpenHands
-        run: |
-          if [[ "${{ github.event.label.name }}" == "fix-me-experimental" ]] ||
-             ([[ "${{ github.event_name }}" == "issue_comment" || "${{ github.event_name }}" == "pull_request_review_comment" ]] &&
-              [[ "${{ github.event.comment.body }}" == "@openhands-agent-exp"* ]]) ||
-             ([[ "${{ github.event_name }}" == "pull_request_review" ]] &&
-              [[ "${{ github.event.review.body }}" == "@openhands-agent-exp"* ]]); 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
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const commentBody = `${{ github.event.comment.body || '' }}`.trim();
+            const reviewBody = `${{ github.event.review.body || '' }}`.trim();
+            const labelName = `${{ github.event.label.name || '' }}`.trim();
+            const eventName = `${{ github.event_name }}`.trim();
+
+            // Check conditions
+            const isExperimentalLabel = labelName === "fix-me-experimental";
+            const isIssueCommentExperimental =
+              (eventName === "issue_comment" || eventName === "pull_request_review_comment") &&
+              commentBody.includes("@openhands-agent-exp");
+            const isReviewCommentExperimental =
+              eventName === "pull_request_review" && reviewBody.includes("@openhands-agent-exp");
+
+            // Perform package installation
+            if (isExperimentalLabel || isIssueCommentExperimental || isReviewCommentExperimental) {
+              console.log("Installing experimental OpenHands...");
+              await exec.exec("python -m pip install --upgrade pip");
+              await exec.exec("pip install git+https://github.com/all-hands-ai/openhands.git");
+            } else {
+              console.log("Installing from requirements.txt...");
+              await exec.exec("python -m pip install --upgrade pip");
+              await exec.exec("pip install -r requirements.txt");
+            }
 
       - name: Attempt to resolve issue
         env:
@@ -250,9 +268,47 @@ jobs:
               grep "branch created" branch_result.txt | sed 's/.*\///g; s/.expand=1//g' > branch_name.txt
           fi
 
-      - name: Comment on issue
+      # Step leaves comment for when agent is invoked on PR
+      - name: Analyze Push Logs (Updated PR or No Changes) # Skip comment if PR update was successful OR leave comment if the agent made no code changes
+        uses: actions/github-script@v7
+        if: always()
+        env:
+          AGENT_RESPONDED: ${{ env.AGENT_RESPONDED || 'false' }}
+        with:
+          github-token: ${{ secrets.PAT_TOKEN || github.token }}
+          script: |
+            const fs = require('fs');
+            const issueNumber = ${{ env.ISSUE_NUMBER }};
+            let logContent = '';
+
+            try {
+              logContent = fs.readFileSync('/tmp/pr_result.txt', 'utf8').trim();
+            } catch (error) {
+              console.error('Error reading pr_result.txt file:', error);
+            }
+
+            const noChangesMessage = `No changes to commit for issue #${issueNumber}. Skipping commit.`;
+
+            // Check logs from send_pull_request.py (pushes code to GitHub)
+            if (logContent.includes("Updated pull request")) {
+              console.log("Updated pull request found. Skipping comment.");
+              process.env.AGENT_RESPONDED = 'true';
+            } else 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.`
+              });
+              process.env.AGENT_RESPONDED = 'true';
+            }
+
+      # Step leaves comment for when agent is invoked on issue
+      - name: Comment on issue # Comment link to either PR or branch created by agent
         uses: actions/github-script@v7
         if: always() # Comment on issue even if the previous steps fail
+        env:
+          AGENT_RESPONDED: ${{ env.AGENT_RESPONDED || 'false' }}
         with:
           github-token: ${{ secrets.PAT_TOKEN || github.token }}
           script: |
@@ -262,18 +318,6 @@ jobs:
 
             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) {
@@ -285,20 +329,16 @@ jobs:
               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) {
+
+            // Check "success" log from resolver output
+            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 #${prNumber} has been created. Please review the changes.`
               });
+              process.env.AGENT_RESPONDED = 'true';
             } else if (!success && branchName) {
               github.rest.issues.createComment({
                 issue_number: issueNumber,
@@ -306,11 +346,21 @@ jobs:
                 repo: context.repo.repo,
                 body: `An attempt was made to automatically fix this issue, but it was unsuccessful. A branch named '${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.`
-              });
+              process.env.AGENT_RESPONDED = 'true';
             }
+
+      # Leave error comment when both PR/Issue comment handling fail
+      - name: Fallback Error Comment
+        uses: actions/github-script@v7
+        if: ${{ env.AGENT_RESPONDED == 'false' }} # Only run if no conditions were met in previous steps
+        with:
+          github-token: ${{ secrets.PAT_TOKEN || github.token }}
+          script: |
+            const issueNumber = ${{ env.ISSUE_NUMBER }};
+
+            github.rest.issues.createComment({
+              issue_number: issueNumber,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: `The workflow to fix this issue encountered an error. Please check the [workflow logs](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}) for more information.`
+            });

.nvmrc

@@ -0,0 +1 @@
+22

Development.md

@@ -100,7 +100,7 @@ poetry run pytest ./tests/unit/test_*.py
 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:0.15-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.16-nikolaik`
 
 ## Develop inside Docker container
 

README.md

@@ -43,16 +43,17 @@ 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:0.15-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik
 
-docker run -it --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.15-nikolaik \
+docker run -it --rm --pull=always \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
+    -v ~/.openhands:/home/openhands/.openhands \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.15
+    docker.all-hands.dev/all-hands-ai/openhands:0.16
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!

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:0.15-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.16-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

config.template.toml

@@ -154,6 +154,10 @@ model = "gpt-4o"
 # Drop any unmapped (unsupported) params without causing an exception
 #drop_params = false
 
+# Modify params for litellm to do transformations like adding a default message, when a message is empty.
+# Note: this setting is global, unlike drop_params, it cannot be overridden in each call to litellm.
+#modify_params = true
+
 # Using the prompt caching feature if provided by the LLM and supported
 #caching_prompt = true
 
@@ -172,6 +176,10 @@ model = "gpt-4o"
 # If model is vision capable, this option allows to disable image processing (useful for cost reduction).
 #disable_vision = true
 
+# Custom tokenizer to use for token counting
+# https://docs.litellm.ai/docs/completion/token_usage
+#custom_tokenizer = ""
+
 [llm.gpt4o-mini]
 api_key = "your-api-key"
 model = "gpt-4o"

containers/app/Dockerfile

@@ -42,6 +42,8 @@ ENV USE_HOST_NETWORK=false
 ENV WORKSPACE_BASE=/opt/workspace_base
 ENV OPENHANDS_BUILD_VERSION=$OPENHANDS_BUILD_VERSION
 ENV SANDBOX_USER_ID=0
+ENV FILE_STORE=local
+ENV FILE_STORE_PATH=~/.openhands
 RUN mkdir -p $WORKSPACE_BASE
 
 RUN apt-get update -y \

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:0.15-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.16-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

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:0.15-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-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:0.15 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.16 \
     python -m openhands.core.cli
 ```
 

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:0.15-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-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:0.15 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.16 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

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:0.15-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.15-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.15
+    docker.all-hands.dev/all-hands-ai/openhands:0.16
 ```
 
 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/micro-agents.md

@@ -14,7 +14,7 @@ Micro-agents are defined in markdown files under the `openhands/agenthub/codeact
 ## Available Micro-Agents
 
 ### GitHub Agent
-**File**: `github.md`  
+**File**: `github.md`
 **Triggers**: `github`, `git`
 
 The GitHub agent specializes in GitHub API interactions and repository management. It:
@@ -30,7 +30,7 @@ Key features:
 - API-first approach for GitHub operations
 
 ### NPM Agent
-**File**: `npm.md`  
+**File**: `npm.md`
 **Triggers**: `npm`
 
 Specializes in handling npm package management with specific focus on:

docs/modules/usage/prompting-best-practices.md

@@ -90,7 +90,7 @@ When working with a customized repository:
 
 Example customized prompt:
 ```
-Add a new task completion feature to src/components/TaskList.tsx following our existing component patterns. 
+Add a new task completion feature to src/components/TaskList.tsx following our existing component patterns.
 Include unit tests in tests/components/ and update the documentation in docs/features/.
 The component should use our shared styling from src/styles/components.
 ```

docs/modules/usage/runtimes.md

@@ -16,7 +16,7 @@ some flags being passed to `docker run` that make this possible:
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.15-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.16-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

evaluation/benchmarks/EDA/run_infer.py

@@ -202,6 +202,9 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
+
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 

evaluation/benchmarks/agent_bench/run_infer.py

@@ -307,6 +307,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
 
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')

evaluation/benchmarks/aider_bench/run_infer.py

@@ -279,6 +279,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
 
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')

evaluation/benchmarks/biocoder/run_infer.py

@@ -328,6 +328,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
 
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')

evaluation/benchmarks/bird/run_infer.py

@@ -456,6 +456,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 

evaluation/benchmarks/browsing_delegation/run_infer.py

@@ -142,6 +142,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
 
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')

evaluation/benchmarks/commit0_bench/run_infer.py

@@ -571,6 +571,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
         llm_config.log_completions = True
 
     if llm_config is None:

evaluation/benchmarks/discoverybench/run_infer.py

@@ -466,6 +466,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 

evaluation/benchmarks/gaia/run_infer.py

@@ -238,6 +238,9 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
+
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 

evaluation/benchmarks/gorilla/run_infer.py

@@ -146,6 +146,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 

evaluation/benchmarks/gpqa/run_infer.py

@@ -326,6 +326,9 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
+
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 

evaluation/benchmarks/humanevalfix/run_infer.py

@@ -285,6 +285,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 

evaluation/benchmarks/logic_reasoning/run_infer.py

@@ -288,6 +288,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 

evaluation/benchmarks/miniwob/run_infer.py

@@ -231,6 +231,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 

evaluation/benchmarks/mint/run_infer.py

@@ -279,6 +279,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 

evaluation/benchmarks/ml_bench/run_analysis.py

@@ -124,6 +124,9 @@ if __name__ == '__main__':
     # for details of how to set `llm_config`
     if args.llm_config:
         specified_llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        specified_llm_config.modify_params = False
+
         if specified_llm_config:
             config.llm = specified_llm_config
     logger.info(f'Config for evaluation: {config}')

evaluation/benchmarks/ml_bench/run_infer.py

@@ -292,6 +292,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 

evaluation/benchmarks/scienceagentbench/run_infer.py

@@ -272,6 +272,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 

evaluation/benchmarks/swe_bench/prompt.py

@@ -1,28 +0,0 @@
-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 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!
-
-IMPORTANT TIPS:
-1. Always start by trying to replicate the bug that the issues discusses.
-    If the issue includes code for reproducing the bug, we recommend that you re-implement that in your environment, and run it to make sure you can reproduce the bug.
-    Then start trying to fix it.
-    When you think you've fixed the bug, re-run the bug reproduction script to make sure that the bug has indeed been fixed.
-
-    If the bug reproduction script does not print anything when it successfully runs, we recommend adding a print("Script completed successfully, no errors.") command at the end of the file,
-    so that you can be sure that the script indeed ran fine all the way through.
-
-2. If you run a command and it doesn't work, try running a different command. A command that did not work once will not work the second time unless you modify it!
-
-3. If you open a file and need to get to an area around a specific line that is not in the first 100 lines, say line 583, don't just use the scroll_down command multiple times. Instead, use the goto 583 command. It's much quicker.
-
-4. If the bug reproduction script requires inputting/reading a specific file, such as buggy-input.png, and you'd like to understand how to input that file, conduct a search in the existing repo code, to see whether someone else has already done that. Do this by running the command: find_file("buggy-input.png") If that doesn't work, use the linux 'find' command.
-
-5. Always make sure to look at the currently open file and the current working directory (which appears right after the currently open file). The currently open file might be in a different directory than the working directory! Note that some commands, such as 'create', open files, so they might change the current  open file.
-
-6. When editing files, it is easy to accidentally specify a wrong line number or to write code with incorrect indentation. Always check the code after you issue an edit to make sure that it reflects what you wanted to accomplish. If it didn't, issue another command to fix it.
-
-[Current directory: /workspace/{workspace_dir_name}]
-"""

evaluation/benchmarks/swe_bench/run_infer.py

@@ -9,7 +9,6 @@ import toml
 from datasets import load_dataset
 
 import openhands.agenthub
-from evaluation.benchmarks.swe_bench.prompt import CODEACT_SWE_PROMPT
 from evaluation.utils.shared import (
     EvalException,
     EvalMetadata,
@@ -45,7 +44,6 @@ RUN_WITH_BROWSING = os.environ.get('RUN_WITH_BROWSING', 'false').lower() == 'tru
 
 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
     'CodeActAgent': codeact_user_response,
-    'CodeActSWEAgent': codeact_user_response,
 }
 
 
@@ -56,40 +54,28 @@ def _get_swebench_workspace_dir_name(instance: pd.Series) -> str:
 def get_instruction(instance: pd.Series, metadata: EvalMetadata):
     workspace_dir_name = _get_swebench_workspace_dir_name(instance)
     # Prepare instruction
-    if metadata.agent_class == 'CodeActSWEAgent':
-        instruction = (
-            'We are currently solving the following issue within our repository. Here is the issue text:\n'
-            '--- BEGIN ISSUE ---\n'
-            f'{instance.problem_statement}\n'
-            '--- END ISSUE ---\n\n'
-        )
-        if USE_HINT_TEXT and instance.hints_text:
-            instruction += (
-                f'--- BEGIN HINTS ---\n{instance.hints_text}\n--- END HINTS ---\n'
-            )
-        instruction += CODEACT_SWE_PROMPT.format(workspace_dir_name=workspace_dir_name)
-    else:
-        # Instruction based on Anthropic's official trajectory
-        # https://github.com/eschluntz/swe-bench-experiments/tree/main/evaluation/verified/20241022_tools_claude-3-5-sonnet-updated/trajs
-        instruction = (
-            '<uploaded_files>\n'
-            f'/workspace/{workspace_dir_name}\n'
-            '</uploaded_files>\n'
-            f"I've uploaded a python code repository in the directory {workspace_dir_name}. Consider the following PR description:\n\n"
-            f'<pr_description>\n'
-            f'{instance.problem_statement}\n'
-            '</pr_description>\n\n'
-            'Can you help me implement the necessary changes to the repository so that the requirements specified in the <pr_description> are met?\n'
-            "I've already taken care of all changes to any of the test files described in the <pr_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!\n"
-            'Your task is to make the minimal changes to non-tests files in the /workspace directory to ensure the <pr_description> is satisfied.\n'
-            'Follow these steps to resolve the issue:\n'
-            '1. As a first step, it might be a good idea to explore the repo to familiarize yourself with its structure.\n'
-            '2. Create a script to reproduce the error and execute it with `python <filename.py>` using the BashTool, to confirm the error\n'
-            '3. Edit the sourcecode of the repo to resolve the issue\n'
-            '4. Rerun your reproduce script and confirm that the error is fixed!\n'
-            '5. Think about edgecases and make sure your fix handles them as well\n'
-            "Your thinking should be thorough and so it's fine if it's very long.\n"
-        )
+
+    # Instruction based on Anthropic's official trajectory
+    # https://github.com/eschluntz/swe-bench-experiments/tree/main/evaluation/verified/20241022_tools_claude-3-5-sonnet-updated/trajs
+    instruction = (
+        '<uploaded_files>\n'
+        f'/workspace/{workspace_dir_name}\n'
+        '</uploaded_files>\n'
+        f"I've uploaded a python code repository in the directory {workspace_dir_name}. Consider the following PR description:\n\n"
+        f'<pr_description>\n'
+        f'{instance.problem_statement}\n'
+        '</pr_description>\n\n'
+        'Can you help me implement the necessary changes to the repository so that the requirements specified in the <pr_description> are met?\n'
+        "I've already taken care of all changes to any of the test files described in the <pr_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!\n"
+        'Your task is to make the minimal changes to non-tests files in the /workspace directory to ensure the <pr_description> is satisfied.\n'
+        'Follow these steps to resolve the issue:\n'
+        '1. As a first step, it might be a good idea to explore the repo to familiarize yourself with its structure.\n'
+        '2. Create a script to reproduce the error and execute it with `python <filename.py>` using the BashTool, to confirm the error\n'
+        '3. Edit the sourcecode of the repo to resolve the issue\n'
+        '4. Rerun your reproduce script and confirm that the error is fixed!\n'
+        '5. Think about edgecases and make sure your fix handles them as well\n'
+        "Your thinking should be thorough and so it's fine if it's very long.\n"
+    )
 
     if RUN_WITH_BROWSING:
         instruction += (
@@ -504,6 +490,8 @@ if __name__ == '__main__':
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
         llm_config.log_completions = True
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
 
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')

evaluation/benchmarks/swe_bench/scripts/setup/instance_swe_entry.sh

@@ -33,7 +33,7 @@ if [ -d /workspace/$WORKSPACE_NAME ]; then
     rm -rf /workspace/$WORKSPACE_NAME
 fi
 mkdir -p /workspace
-mv /testbed /workspace/$WORKSPACE_NAME
+cp -r /testbed /workspace/$WORKSPACE_NAME
 
 # Activate instance-specific environment
 . /opt/miniconda3/etc/profile.d/conda.sh

evaluation/benchmarks/toolqa/run_infer.py

@@ -181,6 +181,9 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
+
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 

evaluation/benchmarks/webarena/run_infer.py

@@ -212,6 +212,8 @@ if __name__ == '__main__':
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
+        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        llm_config.modify_params = False
     if llm_config is None:
         raise ValueError(f'Could not find LLM config: --llm_config {args.llm_config}')
 

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

@@ -51,6 +51,22 @@ describe("ChatInput", () => {
     expect(onSubmitMock).not.toHaveBeenCalled();
   });
 
+  it("should not call onSubmit when the message is only whitespace", async () => {
+    const user = userEvent.setup();
+    render(<ChatInput onSubmit={onSubmitMock} />);
+    const textarea = screen.getByRole("textbox");
+
+    await user.type(textarea, "   ");
+    await user.keyboard("{Enter}");
+
+    expect(onSubmitMock).not.toHaveBeenCalled();
+
+    await user.type(textarea, " \t\n");
+    await user.keyboard("{Enter}");
+
+    expect(onSubmitMock).not.toHaveBeenCalled();
+  });
+
   it("should disable submit", async () => {
     const user = userEvent.setup();
     render(<ChatInput disabled onSubmit={onSubmitMock} />);

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

@@ -2,12 +2,28 @@ import { describe, expect, it } from "vitest";
 import { screen } from "@testing-library/react";
 import { renderWithProviders } from "test-utils";
 import { ExpandableMessage } from "#/components/features/chat/expandable-message";
+import { vi } from 'vitest';
+
+vi.mock('react-i18next', async () => {
+  const actual = await vi.importActual('react-i18next');
+  return {
+    ...actual,
+    useTranslation: () => ({
+      t: (key:string) => key,
+      i18n: {
+        changeLanguage: () => new Promise(() => {}),
+        language: 'en',
+        exists: () => true,
+      },
+    }),
+  }
+});
 
 describe("ExpandableMessage", () => {
   it("should render with neutral border for non-action messages", () => {
     renderWithProviders(<ExpandableMessage message="Hello" type="thought" />);
     const element = screen.getByText("Hello");
-    const container = element.closest("div.flex.gap-2.items-center.justify-between");
+    const container = element.closest("div.flex.gap-2.items-center.justify-start");
     expect(container).toHaveClass("border-neutral-300");
     expect(screen.queryByTestId("status-icon")).not.toBeInTheDocument();
   });
@@ -15,21 +31,22 @@ describe("ExpandableMessage", () => {
   it("should render with neutral border for error messages", () => {
     renderWithProviders(<ExpandableMessage message="Error occurred" type="error" />);
     const element = screen.getByText("Error occurred");
-    const container = element.closest("div.flex.gap-2.items-center.justify-between");
-    expect(container).toHaveClass("border-neutral-300");
+    const container = element.closest("div.flex.gap-2.items-center.justify-start");
+    expect(container).toHaveClass("border-danger");
     expect(screen.queryByTestId("status-icon")).not.toBeInTheDocument();
   });
 
   it("should render with success icon for successful action messages", () => {
     renderWithProviders(
       <ExpandableMessage
+        id="OBSERVATION_MESSAGE$RUN"
         message="Command executed successfully"
         type="action"
         success={true}
       />
     );
-    const element = screen.getByText("Command executed successfully");
-    const container = element.closest("div.flex.gap-2.items-center.justify-between");
+    const element = screen.getByText("OBSERVATION_MESSAGE$RUN");
+    const container = element.closest("div.flex.gap-2.items-center.justify-start");
     expect(container).toHaveClass("border-neutral-300");
     const icon = screen.getByTestId("status-icon");
     expect(icon).toHaveClass("fill-success");
@@ -38,22 +55,29 @@ describe("ExpandableMessage", () => {
   it("should render with error icon for failed action messages", () => {
     renderWithProviders(
       <ExpandableMessage
+        id="OBSERVATION_MESSAGE$RUN"
         message="Command failed"
         type="action"
         success={false}
       />
     );
-    const element = screen.getByText("Command failed");
-    const container = element.closest("div.flex.gap-2.items-center.justify-between");
+    const element = screen.getByText("OBSERVATION_MESSAGE$RUN");
+    const container = element.closest("div.flex.gap-2.items-center.justify-start");
     expect(container).toHaveClass("border-neutral-300");
     const icon = screen.getByTestId("status-icon");
     expect(icon).toHaveClass("fill-danger");
   });
 
   it("should render with neutral border and no icon for action messages without success prop", () => {
-    renderWithProviders(<ExpandableMessage message="Running command" type="action" />);
-    const element = screen.getByText("Running command");
-    const container = element.closest("div.flex.gap-2.items-center.justify-between");
+    renderWithProviders(
+      <ExpandableMessage
+        id="OBSERVATION_MESSAGE$RUN"
+        message="Running command"
+        type="action"
+      />
+    );
+    const element = screen.getByText("OBSERVATION_MESSAGE$RUN");
+    const container = element.closest("div.flex.gap-2.items-center.justify-start");
     expect(container).toHaveClass("border-neutral-300");
     expect(screen.queryByTestId("status-icon")).not.toBeInTheDocument();
   });

frontend/__tests__/components/jupyter/jupyter.test.tsx

@@ -0,0 +1,45 @@
+import { render, screen } from "@testing-library/react";
+import { Provider } from "react-redux";
+import { configureStore } from "@reduxjs/toolkit";
+import { JupyterEditor } from "#/components/features/jupyter/jupyter";
+import { jupyterReducer } from "#/state/jupyter-slice";
+import { vi, describe, it, expect } from "vitest";
+
+describe("JupyterEditor", () => {
+  const mockStore = configureStore({
+    reducer: {
+      fileState: () => ({}),
+      initalQuery: () => ({}),
+      browser: () => ({}),
+      chat: () => ({}),
+      code: () => ({}),
+      cmd: () => ({}),
+      agent: () => ({}),
+      jupyter: jupyterReducer,
+      securityAnalyzer: () => ({}),
+      status: () => ({}),
+    },
+    preloadedState: {
+      jupyter: {
+        cells: Array(20).fill({
+          content: "Test cell content",
+          type: "input",
+          output: "Test output",
+        }),
+      },
+    },
+  });
+
+  it("should have a scrollable container", () => {
+    render(
+      <Provider store={mockStore}>
+        <div style={{ height: "100vh" }}>
+          <JupyterEditor maxWidth={800} />
+        </div>
+      </Provider>
+    );
+
+    const container = screen.getByTestId("jupyter-container");
+    expect(container).toHaveClass("flex-1 overflow-y-auto");
+  });
+});

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

@@ -4,26 +4,6 @@ import { vi, describe, afterEach, it, expect } from "vitest";
 import { Command, appendInput, appendOutput } from "#/state/command-slice";
 import Terminal from "#/components/features/terminal/terminal";
 
-global.ResizeObserver = vi.fn().mockImplementation(() => ({
-  observe: vi.fn(),
-  disconnect: vi.fn(),
-}));
-
-const mockTerminal = {
-  open: vi.fn(),
-  write: vi.fn(),
-  writeln: vi.fn(),
-  dispose: vi.fn(),
-  onKey: vi.fn(),
-  attachCustomKeyEventHandler: vi.fn(),
-  loadAddon: vi.fn(),
-};
-
-vi.mock("@xterm/xterm", async (importOriginal) => ({
-  ...(await importOriginal<typeof import("@xterm/xterm")>()),
-  Terminal: vi.fn().mockImplementation(() => mockTerminal),
-}));
-
 const renderTerminal = (commands: Command[] = []) =>
   renderWithProviders(<Terminal secrets={[]} />, {
     preloadedState: {
@@ -34,6 +14,26 @@ const renderTerminal = (commands: Command[] = []) =>
   });
 
 describe.skip("Terminal", () => {
+  global.ResizeObserver = vi.fn().mockImplementation(() => ({
+    observe: vi.fn(),
+    disconnect: vi.fn(),
+  }));
+
+  const mockTerminal = {
+    open: vi.fn(),
+    write: vi.fn(),
+    writeln: vi.fn(),
+    dispose: vi.fn(),
+    onKey: vi.fn(),
+    attachCustomKeyEventHandler: vi.fn(),
+    loadAddon: vi.fn(),
+  };
+
+  vi.mock("@xterm/xterm", async (importOriginal) => ({
+    ...(await importOriginal<typeof import("@xterm/xterm")>()),
+    Terminal: vi.fn().mockImplementation(() => mockTerminal),
+  }));
+
   afterEach(() => {
     vi.clearAllMocks();
   });

frontend/__tests__/hooks/use-terminal.test.tsx

@@ -5,7 +5,6 @@ import { ReactNode } from "react";
 import { useTerminal } from "#/hooks/use-terminal";
 import { Command } from "#/state/command-slice";
 
-
 interface TestTerminalComponentProps {
   commands: Command[];
   secrets: string[];
@@ -15,7 +14,7 @@ function TestTerminalComponent({
   commands,
   secrets,
 }: TestTerminalComponentProps) {
-  const ref = useTerminal(commands, secrets);
+  const ref = useTerminal({ commands, secrets, disabled: false });
   return <div ref={ref} />;
 }
 
@@ -24,9 +23,7 @@ interface WrapperProps {
 }
 
 function Wrapper({ children }: WrapperProps) {
-  return (
-    <div>{children}</div>
-  )
+  return <div>{children}</div>;
 }
 
 describe("useTerminal", () => {

frontend/__tests__/routes/_oh.test.tsx

@@ -39,12 +39,6 @@ describe("frontend/routes/_oh", () => {
     await screen.findByTestId("root-layout");
   });
 
-  it("should render the AI config modal if the user is authed", async () => {
-    // Our mock return value is true by default
-    renderWithProviders(<RouteStub />);
-    await screen.findByTestId("ai-config-modal");
-  });
-
   it("should render the AI config modal if settings are not up-to-date", async () => {
     settingsAreUpToDateMock.mockReturnValue(false);
     renderWithProviders(<RouteStub />);

frontend/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "openhands-frontend",
-  "version": "0.15.2",
+  "version": "0.16.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "openhands-frontend",
-      "version": "0.15.2",
+      "version": "0.16.0",
       "dependencies": {
         "@monaco-editor/react": "^4.6.0",
         "@nextui-org/react": "^2.4.8",

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.15.2",
+  "version": "0.16.0",
   "private": true,
   "type": "module",
   "engines": {

frontend/public/config.json

@@ -1,5 +0,0 @@
-{
-  "APP_MODE": "oss",
-  "GITHUB_CLIENT_ID": "",
-  "POSTHOG_CLIENT_KEY": "phc_3ESMmY9SgqEAGBB6sMGK5ayYHkeUuknH2vP6FmWH9RA"
-}

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

@@ -1,4 +1,4 @@
-import axios from "axios";
+import axios, { AxiosError } from "axios";
 
 const github = axios.create({
   baseURL: "https://api.github.com",
@@ -18,4 +18,86 @@ const removeAuthTokenHeader = () => {
   }
 };
 
-export { github, setAuthTokenHeader, removeAuthTokenHeader };
+/**
+ * Checks if response has attributes to perform refresh
+ */
+const canRefresh = (error: unknown): boolean =>
+  !!(
+    error instanceof AxiosError &&
+    error.config &&
+    error.response &&
+    error.response.status
+  );
+
+/**
+ * Checks if the data is a GitHub error response
+ * @param data The data to check
+ * @returns Boolean indicating if the data is a GitHub error response
+ */
+export const isGitHubErrorReponse = <T extends object | Array<unknown>>(
+  data: T | GitHubErrorReponse | null,
+): data is GitHubErrorReponse =>
+  !!data && "message" in data && data.message !== undefined;
+
+// Axios interceptor to handle token refresh
+const setupAxiosInterceptors = (
+  refreshToken: () => Promise<boolean>,
+  logout: () => void,
+) => {
+  github.interceptors.response.use(
+    // Pass successful responses through
+    (response) => {
+      const parsedData = response.data;
+      if (isGitHubErrorReponse(parsedData)) {
+        const error = new AxiosError(
+          "Failed",
+          "",
+          response.config,
+          response.request,
+          response,
+        );
+        throw error;
+      }
+      return response;
+    },
+    // Retry request exactly once if token is expired
+    async (error) => {
+      if (!canRefresh(error)) {
+        return Promise.reject(new Error("Failed to refresh token"));
+      }
+
+      const originalRequest = error.config;
+
+      // Check if the error is due to an expired token
+      if (
+        error.response.status === 401 &&
+        !originalRequest._retry // Prevent infinite retry loops
+      ) {
+        originalRequest._retry = true;
+        try {
+          const refreshed = await refreshToken();
+          if (refreshed) {
+            return await github(originalRequest);
+          }
+
+          logout();
+          return await Promise.reject(new Error("Failed to refresh token"));
+        } catch (refreshError) {
+          // If token refresh fails, evict the user
+          logout();
+          return Promise.reject(refreshError);
+        }
+      }
+
+      // If the error is not due to an expired token, propagate the error
+      return Promise.reject(error);
+    },
+  );
+};
+
+export {
+  github,
+  setAuthTokenHeader,
+  removeAuthTokenHeader,
+  setupAxiosInterceptors,
+};

frontend/src/api/github.ts

@@ -1,42 +1,81 @@
 import { extractNextPageFromLink } from "#/utils/extract-next-page-from-link";
 import { github } from "./github-axios-instance";
+import { openHands } from "./open-hands-axios";
 
 /**
- * Checks if the data is a GitHub error response
- * @param data The data to check
- * @returns Boolean indicating if the data is a GitHub error response
+ * Given the user, retrieves app installations IDs for OpenHands Github App
+ * Uses user access token for Github App
  */
-export const isGitHubErrorReponse = <T extends object | Array<unknown>>(
-  data: T | GitHubErrorReponse | null,
-): data is GitHubErrorReponse =>
-  !!data && "message" in data && data.message !== undefined;
+export const retrieveGitHubAppInstallations = async (): Promise<number[]> => {
+  const response = await github.get<GithubAppInstallation>(
+    "/user/installations",
+  );
+
+  return response.data.installations.map((installation) => installation.id);
+};
 
 /**
- * Given a GitHub token, retrieves the repositories of the authenticated user
- * @param token The GitHub token
- * @returns A list of repositories or an error response
+ * Retrieves repositories where OpenHands Github App has been installed
+ * @param installationIndex Pagination cursor position for app installation IDs
+ * @param installations Collection of all App installation IDs for OpenHands Github App
+ * @returns A list of repositories
+ */
+export const retrieveGitHubAppRepositories = async (
+  installationIndex: number,
+  installations: number[],
+  page = 1,
+  per_page = 30,
+) => {
+  const installationId = installations[installationIndex];
+  const response = await openHands.get<GitHubAppRepository>(
+    "/api/github/repositories",
+    {
+      params: {
+        sort: "pushed",
+        page,
+        per_page,
+        installation_id: installationId,
+      },
+    },
+  );
+
+  const link = response.headers.link ?? "";
+  const nextPage = extractNextPageFromLink(link);
+  let nextInstallation: number | null;
+
+  if (nextPage) {
+    nextInstallation = installationIndex;
+  } else if (installationIndex + 1 < installations.length) {
+    nextInstallation = installationIndex + 1;
+  } else {
+    nextInstallation = null;
+  }
+
+  return {
+    data: response.data.repositories,
+    nextPage,
+    installationIndex: nextInstallation,
+  };
+};
+
+/**
+ * Given a PAT, retrieves the repositories of the user
+ * @returns A list of repositories
  */
 export const retrieveGitHubUserRepositories = async (
   page = 1,
   per_page = 30,
 ) => {
-  const response = await github.get<GitHubRepository[]>("/user/repos", {
-    params: {
-      sort: "pushed",
-      page,
-      per_page,
+  const response = await openHands.get<GitHubRepository[]>(
+    "/api/github/repositories",
+    {
+      params: {
+        sort: "pushed",
+        page,
+        per_page,
+      },
     },
-    transformResponse: (data) => {
-      const parsedData: GitHubRepository[] | GitHubErrorReponse =
-        JSON.parse(data);
-
-      if (isGitHubErrorReponse(parsedData)) {
-        throw new Error(parsedData.message);
-      }
-
-      return parsedData;
-    },
-  });
+  );
 
   const link = response.headers.link ?? "";
   const nextPage = extractNextPageFromLink(link);
@@ -46,21 +85,10 @@ export const retrieveGitHubUserRepositories = async (
 
 /**
  * Given a GitHub token, retrieves the authenticated user
- * @param token The GitHub token
  * @returns The authenticated user or an error response
  */
 export const retrieveGitHubUser = async () => {
-  const response = await github.get<GitHubUser>("/user", {
-    transformResponse: (data) => {
-      const parsedData: GitHubUser | GitHubErrorReponse = JSON.parse(data);
-
-      if (isGitHubErrorReponse(parsedData)) {
-        throw new Error(parsedData.message);
-      }
-
-      return parsedData;
-    },
-  });
+  const response = await github.get<GitHubUser>("/user");
 
   const { data } = response;
 
@@ -79,24 +107,14 @@ export const retrieveGitHubUser = async () => {
 export const retrieveLatestGitHubCommit = async (
   repository: string,
 ): Promise<GitHubCommit> => {
-  const response = await github.get<GitHubCommit>(
+  const response = await github.get<GitHubCommit[]>(
     `/repos/${repository}/commits`,
     {
       params: {
         per_page: 1,
       },
-      transformResponse: (data) => {
-        const parsedData: GitHubCommit[] | GitHubErrorReponse =
-          JSON.parse(data);
-
-        if (isGitHubErrorReponse(parsedData)) {
-          throw new Error(parsedData.message);
-        }
-
-        return parsedData[0];
-      },
     },
   );
 
-  return response.data;
+  return response.data[0];
 };

frontend/src/api/open-hands.ts

@@ -42,7 +42,9 @@ class OpenHands {
   }
 
   static async getConfig(): Promise<GetConfigResponse> {
-    const { data } = await openHands.get<GetConfigResponse>("/config.json");
+    const { data } = await openHands.get<GetConfigResponse>(
+      "/api/options/config",
+    );
     return data;
   }
 
@@ -136,6 +138,20 @@ class OpenHands {
     return response.status === 200;
   }
 
+  /**
+   * Refresh Github Token
+   * @returns Refreshed Github access token
+   */
+  static async refreshToken(
+    appMode: GetConfigResponse["APP_MODE"],
+  ): Promise<string> {
+    if (appMode === "oss") return "";
+
+    const response =
+      await openHands.post<GitHubAccessTokenResponse>("/api/refresh-token");
+    return response.data.access_token;
+  }
+
   /**
    * Get the blob of the workspace zip
    * @returns Blob of the workspace zip

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

@@ -43,6 +43,7 @@ export interface Feedback {
 
 export interface GetConfigResponse {
   APP_MODE: "saas" | "oss";
+  APP_SLUG?: string;
   GITHUB_CLIENT_ID: string;
   POSTHOG_CLIENT_KEY: string;
 }

frontend/src/components/features/chat/action-suggestions.tsx

@@ -2,7 +2,7 @@ import posthog from "posthog-js";
 import React from "react";
 import { SuggestionItem } from "#/components/features/suggestions/suggestion-item";
 import { useAuth } from "#/context/auth-context";
-import { downloadWorkspace } from "#/utils/download-workspace";
+import { DownloadModal } from "#/components/shared/download-modal";
 
 interface ActionSuggestionsProps {
   onSuggestionsClick: (value: string) => void;
@@ -16,19 +16,17 @@ export function ActionSuggestions({
   const [isDownloading, setIsDownloading] = React.useState(false);
   const [hasPullRequest, setHasPullRequest] = React.useState(false);
 
-  const handleDownloadWorkspace = async () => {
-    setIsDownloading(true);
-    try {
-      await downloadWorkspace();
-    } catch (error) {
-      // TODO: Handle error
-    } finally {
-      setIsDownloading(false);
-    }
+  const handleDownloadClose = () => {
+    setIsDownloading(false);
   };
 
   return (
     <div className="flex flex-col gap-2 mb-2">
+      <DownloadModal
+        initialPath=""
+        onClose={handleDownloadClose}
+        isOpen={isDownloading}
+      />
       {gitHubToken ? (
         <div className="flex flex-row gap-2 justify-center w-full">
           {!hasPullRequest ? (
@@ -75,13 +73,15 @@ export function ActionSuggestions({
         <SuggestionItem
           suggestion={{
             label: !isDownloading
-              ? "Download .zip"
+              ? "Download files"
               : "Downloading, please wait...",
-            value: "Download .zip",
+            value: "Download files",
           }}
           onClick={() => {
             posthog.capture("download_workspace_button_clicked");
-            handleDownloadWorkspace();
+            if (!isDownloading) {
+              setIsDownloading(true);
+            }
           }}
         />
       )}

frontend/src/components/features/chat/chat-input.tsx

@@ -84,7 +84,7 @@ export function ChatInput({
 
   const handleSubmitMessage = () => {
     const message = value || textareaRef.current?.value || "";
-    if (message) {
+    if (message.trim()) {
       onSubmit(message);
       onChange?.("");
       if (textareaRef.current) {

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

@@ -8,6 +8,7 @@ import ArrowUp from "#/icons/angle-up-solid.svg?react";
 import ArrowDown from "#/icons/angle-down-solid.svg?react";
 import CheckCircle from "#/icons/check-circle-solid.svg?react";
 import XCircle from "#/icons/x-circle-solid.svg?react";
+import { cn } from "#/utils/utils";
 
 interface ExpandableMessageProps {
   id?: string;
@@ -35,27 +36,63 @@ export function ExpandableMessage({
     }
   }, [id, message, i18n.language]);
 
-  const arrowClasses = "h-4 w-4 ml-2 inline fill-neutral-300";
   const statusIconClasses = "h-4 w-4 ml-2 inline";
 
   return (
-    <div className="flex gap-2 items-center justify-between border-l-2 border-neutral-300 pl-2 my-2 py-2">
-      <div className="text-sm leading-4 flex flex-col gap-2 max-w-full">
+    <div
+      className={cn(
+        "flex gap-2 items-center justify-start border-l-2 pl-2 my-2 py-2",
+        type === "error" ? "border-danger" : "border-neutral-300",
+      )}
+    >
+      <div className="text-sm w-full">
         {headline && (
-          <p className="text-neutral-300 font-bold">
-            {headline}
-            <button
-              type="button"
-              onClick={() => setShowDetails(!showDetails)}
-              className="cursor-pointer text-left"
-            >
-              {showDetails ? (
-                <ArrowUp className={arrowClasses} />
-              ) : (
-                <ArrowDown className={arrowClasses} />
+          <div className="flex flex-row justify-between items-center w-full">
+            <span
+              className={cn(
+                "font-bold",
+                type === "error" ? "text-danger" : "text-neutral-300",
               )}
-            </button>
-          </p>
+            >
+              {headline}
+              <button
+                type="button"
+                onClick={() => setShowDetails(!showDetails)}
+                className="cursor-pointer text-left"
+              >
+                {showDetails ? (
+                  <ArrowUp
+                    className={cn(
+                      "h-4 w-4 ml-2 inline",
+                      type === "error" ? "fill-danger" : "fill-neutral-300",
+                    )}
+                  />
+                ) : (
+                  <ArrowDown
+                    className={cn(
+                      "h-4 w-4 ml-2 inline",
+                      type === "error" ? "fill-danger" : "fill-neutral-300",
+                    )}
+                  />
+                )}
+              </button>
+            </span>
+            {type === "action" && success !== undefined && (
+              <span className="flex-shrink-0">
+                {success ? (
+                  <CheckCircle
+                    data-testid="status-icon"
+                    className={cn(statusIconClasses, "fill-success")}
+                  />
+                ) : (
+                  <XCircle
+                    data-testid="status-icon"
+                    className={cn(statusIconClasses, "fill-danger")}
+                  />
+                )}
+              </span>
+            )}
+          </div>
         )}
         {showDetails && (
           <Markdown
@@ -71,21 +108,6 @@ export function ExpandableMessage({
           </Markdown>
         )}
       </div>
-      {type === "action" && success !== undefined && (
-        <div className="flex-shrink-0">
-          {success ? (
-            <CheckCircle
-              data-testid="status-icon"
-              className={`${statusIconClasses} fill-success`}
-            />
-          ) : (
-            <XCircle
-              data-testid="status-icon"
-              className={`${statusIconClasses} fill-danger`}
-            />
-          )}
-        </div>
-      )}
     </div>
   );
 }

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

@@ -15,6 +15,10 @@ import { FileExplorerHeader } from "./file-explorer-header";
 import { useVSCodeUrl } from "#/hooks/query/use-vscode-url";
 import { OpenVSCodeButton } from "#/components/shared/buttons/open-vscode-button";
 import { addAssistantMessage } from "#/state/chat-slice";
+import {
+  useWsClient,
+  WsClientProviderStatus,
+} from "#/context/ws-client-provider";
 
 interface FileExplorerProps {
   isOpen: boolean;
@@ -22,6 +26,7 @@ interface FileExplorerProps {
 }
 
 export function FileExplorer({ isOpen, onToggle }: FileExplorerProps) {
+  const { status } = useWsClient();
   const { t } = useTranslation();
   const dispatch = useDispatch();
 
@@ -30,12 +35,11 @@ export function FileExplorer({ isOpen, onToggle }: FileExplorerProps) {
 
   const { curAgentState } = useSelector((state: RootState) => state.agent);
 
-  const agentIsReady =
-    curAgentState !== AgentState.INIT && curAgentState !== AgentState.LOADING;
-
   const { data: paths, refetch, error } = useListFiles();
   const { mutate: uploadFiles } = useUploadFiles();
-  const { data: vscodeUrl } = useVSCodeUrl({ enabled: agentIsReady });
+  const { data: vscodeUrl } = useVSCodeUrl({
+    enabled: status === WsClientProviderStatus.ACTIVE,
+  });
 
   const handleOpenVSCode = () => {
     if (vscodeUrl?.vscode_url) {
@@ -166,7 +170,7 @@ export function FileExplorer({ isOpen, onToggle }: FileExplorerProps) {
           {isOpen && (
             <OpenVSCodeButton
               onClick={handleOpenVSCode}
-              isDisabled={!agentIsReady}
+              isDisabled={status === WsClientProviderStatus.OPENING}
             />
           )}
         </div>

frontend/src/components/features/github/github-repo-selector.tsx

@@ -1,7 +1,9 @@
+import React from "react";
 import { Autocomplete, AutocompleteItem } from "@nextui-org/react";
 import { useDispatch } from "react-redux";
 import posthog from "posthog-js";
 import { setSelectedRepository } from "#/state/initial-query-slice";
+import { useConfig } from "#/hooks/query/use-config";
 
 interface GitHubRepositorySelectorProps {
   onSelect: () => void;
@@ -12,15 +14,31 @@ export function GitHubRepositorySelector({
   onSelect,
   repositories,
 }: GitHubRepositorySelectorProps) {
+  const { data: config } = useConfig();
+  const [selectedKey, setSelectedKey] = React.useState<string | null>(null);
+
+  // Add option to install app onto more repos
+  const finalRepositories =
+    config?.APP_MODE === "saas"
+      ? [{ id: -1000, full_name: "Add more repositories..." }, ...repositories]
+      : repositories;
+
   const dispatch = useDispatch();
 
   const handleRepoSelection = (id: string | null) => {
-    const repo = repositories.find((r) => r.id.toString() === id);
-    if (repo) {
+    const repo = finalRepositories.find((r) => r.id.toString() === id);
+    if (id === "-1000") {
+      if (config?.APP_SLUG)
+        window.open(
+          `https://github.com/apps/${config.APP_SLUG}/installations/new`,
+          "_blank",
+        );
+    } else if (repo) {
       // set query param
       dispatch(setSelectedRepository(repo.full_name));
       posthog.capture("repository_selected");
       onSelect();
+      setSelectedKey(id);
     }
   };
 
@@ -29,12 +47,26 @@ export function GitHubRepositorySelector({
     dispatch(setSelectedRepository(null));
   };
 
+  const emptyContent = config?.APP_SLUG ? (
+    <a
+      href={`https://github.com/apps/${config.APP_SLUG}/installations/new`}
+      target="_blank"
+      rel="noreferrer noopener"
+      className="underline"
+    >
+      Add more repositories...
+    </a>
+  ) : (
+    "No results found."
+  );
+
   return (
     <Autocomplete
       data-testid="github-repo-selector"
       name="repo"
       aria-label="GitHub Repository"
       placeholder="Select a GitHub project"
+      selectedKey={selectedKey}
       inputProps={{
         classNames: {
           inputWrapper:
@@ -43,8 +75,11 @@ export function GitHubRepositorySelector({
       }}
       onSelectionChange={(id) => handleRepoSelection(id?.toString() ?? null)}
       clearButtonProps={{ onClick: handleClearSelection }}
+      listboxProps={{
+        emptyContent,
+      }}
     >
-      {repositories.map((repo) => (
+      {finalRepositories.map((repo) => (
         <AutocompleteItem
           data-testid="github-repo-item"
           key={repo.id}

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

@@ -1,11 +1,11 @@
 import React from "react";
-import { isGitHubErrorReponse } from "#/api/github";
 import { SuggestionBox } from "#/components/features/suggestions/suggestion-box";
 import GitHubLogo from "#/assets/branding/github-logo.svg?react";
 import { GitHubRepositorySelector } from "./github-repo-selector";
 import { ModalButton } from "#/components/shared/buttons/modal-button";
 import { ConnectToGitHubModal } from "#/components/shared/modals/connect-to-github-modal";
 import { ModalBackdrop } from "#/components/shared/modals/modal-backdrop";
+import { isGitHubErrorReponse } from "#/api/github-axios-instance";
 
 interface GitHubRepositoriesSuggestionBoxProps {
   handleSubmit: () => void;

frontend/src/components/features/jupyter/jupyter.tsx

@@ -10,16 +10,17 @@ interface JupyterEditorProps {
 }
 
 export function JupyterEditor({ maxWidth }: JupyterEditorProps) {
-  const { cells } = useSelector((state: RootState) => state.jupyter);
+  const cells = useSelector((state: RootState) => state.jupyter?.cells ?? []);
   const jupyterRef = React.useRef<HTMLDivElement>(null);
 
   const { hitBottom, scrollDomToBottom, onChatBodyScroll } =
     useScrollToBottom(jupyterRef);
 
   return (
-    <div className="flex-1" style={{ maxWidth }}>
+    <div className="flex-1 h-full flex flex-col" style={{ maxWidth }}>
       <div
-        className="overflow-y-auto h-full"
+        data-testid="jupyter-container"
+        className="flex-1 overflow-y-auto"
         ref={jupyterRef}
         onScroll={(e) => onChatBodyScroll(e.currentTarget)}
       >

frontend/src/components/features/markdown/code.tsx

@@ -17,19 +17,38 @@ export function code({
   const match = /language-(\w+)/.exec(className || ""); // get the language
 
   if (!match) {
+    const isMultiline = String(children).includes("\n");
+
+    if (!isMultiline) {
+      return (
+        <code
+          className={className}
+          style={{
+            backgroundColor: "#2a3038",
+            padding: "0.2em 0.4em",
+            borderRadius: "4px",
+            color: "#e6edf3",
+            border: "1px solid #30363d",
+          }}
+        >
+          {children}
+        </code>
+      );
+    }
+
     return (
-      <code
-        className={className}
+      <pre
         style={{
           backgroundColor: "#2a3038",
-          padding: "0.2em 0.4em",
+          padding: "1em",
           borderRadius: "4px",
           color: "#e6edf3",
           border: "1px solid #30363d",
+          overflow: "auto",
         }}
       >
-        {children}
-      </code>
+        <code className={className}>{String(children).replace(/\n$/, "")}</code>
+      </pre>
     );
   }
 

frontend/src/components/features/project-menu/ProjectMenuCard.tsx

@@ -1,16 +1,14 @@
 import React from "react";
-import toast from "react-hot-toast";
 import posthog from "posthog-js";
 import EllipsisH from "#/icons/ellipsis-h.svg?react";
 import { createChatMessage } from "#/services/chat-service";
 import { ProjectMenuCardContextMenu } from "./project.menu-card-context-menu";
 import { ProjectMenuDetailsPlaceholder } from "./project-menu-details-placeholder";
 import { ProjectMenuDetails } from "./project-menu-details";
-import { downloadWorkspace } from "#/utils/download-workspace";
 import { useWsClient } from "#/context/ws-client-provider";
-import { LoadingSpinner } from "#/components/shared/loading-spinner";
 import { ConnectToGitHubModal } from "#/components/shared/modals/connect-to-github-modal";
 import { ModalBackdrop } from "#/components/shared/modals/modal-backdrop";
+import { DownloadModal } from "#/components/shared/download-modal";
 
 interface ProjectMenuCardProps {
   isConnectedToGitHub: boolean;
@@ -30,7 +28,7 @@ export function ProjectMenuCard({
   const [contextMenuIsOpen, setContextMenuIsOpen] = React.useState(false);
   const [connectToGitHubModalOpen, setConnectToGitHubModalOpen] =
     React.useState(false);
-  const [working, setWorking] = React.useState(false);
+  const [downloading, setDownloading] = React.useState(false);
 
   const toggleMenuVisibility = () => {
     setContextMenuIsOpen((prev) => !prev);
@@ -58,20 +56,16 @@ Please push the changes to GitHub and open a pull request.
 
   const handleDownloadWorkspace = () => {
     posthog.capture("download_workspace_button_clicked");
-    try {
-      setWorking(true);
-      downloadWorkspace().then(
-        () => setWorking(false),
-        () => setWorking(false),
-      );
-    } catch (error) {
-      toast.error("Failed to download workspace");
-    }
+    setDownloading(true);
+  };
+
+  const handleDownloadClose = () => {
+    setDownloading(false);
   };
 
   return (
     <div className="px-4 py-[10px] w-[337px] rounded-xl border border-[#525252] flex justify-between items-center relative">
-      {!working && contextMenuIsOpen && (
+      {!downloading && contextMenuIsOpen && (
         <ProjectMenuCardContextMenu
           isConnectedToGitHub={isConnectedToGitHub}
           onConnectToGitHub={() => setConnectToGitHubModalOpen(true)}
@@ -93,17 +87,20 @@ Please push the changes to GitHub and open a pull request.
           onConnectToGitHub={() => setConnectToGitHubModalOpen(true)}
         />
       )}
-      <button
-        type="button"
-        onClick={toggleMenuVisibility}
-        aria-label="Open project menu"
-      >
-        {working ? (
-          <LoadingSpinner size="small" />
-        ) : (
+      <DownloadModal
+        initialPath=""
+        onClose={handleDownloadClose}
+        isOpen={downloading}
+      />
+      {!downloading && (
+        <button
+          type="button"
+          onClick={toggleMenuVisibility}
+          aria-label="Open project menu"
+        >
           <EllipsisH width={36} height={36} />
-        )}
-      </button>
+        </button>
+      )}
       {connectToGitHubModalOpen && (
         <ModalBackdrop onClose={() => setConnectToGitHubModalOpen(false)}>
           <ConnectToGitHubModal

frontend/src/components/features/project-menu/project.menu-card-context-menu.tsx

@@ -37,7 +37,7 @@ export function ProjectMenuCardContextMenu({
         </ContextMenuListItem>
       )}
       <ContextMenuListItem onClick={onDownloadWorkspace}>
-        {t(I18nKey.PROJECT_MENU_CARD_CONTEXT_MENU$DOWNLOAD_AS_ZIP_LABEL)}
+        {t(I18nKey.PROJECT_MENU_CARD_CONTEXT_MENU$DOWNLOAD_FILES_LABEL)}
       </ContextMenuListItem>
     </ContextMenu>
   );

frontend/src/components/features/terminal/terminal-status-label.tsx

@@ -0,0 +1,23 @@
+import {
+  useWsClient,
+  WsClientProviderStatus,
+} from "#/context/ws-client-provider";
+import { cn } from "#/utils/utils";
+
+export function TerminalStatusLabel() {
+  const { status } = useWsClient();
+
+  return (
+    <div className="flex items-center gap-2">
+      <div
+        className={cn(
+          "w-2 h-2 rounded-full",
+          status === WsClientProviderStatus.ACTIVE && "bg-green-500",
+          status !== WsClientProviderStatus.ACTIVE &&
+            "bg-red-500 animate-pulse",
+        )}
+      />
+      Terminal
+    </div>
+  );
+}

frontend/src/components/features/terminal/terminal.tsx

@@ -1,16 +1,25 @@
 import { useSelector } from "react-redux";
 import { RootState } from "#/store";
 import { useTerminal } from "#/hooks/use-terminal";
-
 import "@xterm/xterm/css/xterm.css";
+import {
+  useWsClient,
+  WsClientProviderStatus,
+} from "#/context/ws-client-provider";
 
 interface TerminalProps {
   secrets: string[];
 }
 
 function Terminal({ secrets }: TerminalProps) {
+  const { status } = useWsClient();
   const { commands } = useSelector((state: RootState) => state.cmd);
-  const ref = useTerminal(commands, secrets);
+
+  const ref = useTerminal({
+    commands,
+    secrets,
+    disabled: status === WsClientProviderStatus.OPENING,
+  });
 
   return (
     <div className="h-full p-2 min-h-0">

frontend/src/components/layout/container.tsx

@@ -3,7 +3,7 @@ import React from "react";
 import { NavTab } from "./nav-tab";
 
 interface ContainerProps {
-  label?: string;
+  label?: React.ReactNode;
   labels?: {
     label: string | React.ReactNode;
     to: string;

frontend/src/components/shared/download-modal.tsx

@@ -0,0 +1,33 @@
+import { useDownloadProgress } from "#/hooks/use-download-progress";
+import { DownloadProgress } from "./download-progress";
+
+interface DownloadModalProps {
+  initialPath: string;
+  onClose: () => void;
+  isOpen: boolean;
+}
+
+function ActiveDownload({
+  initialPath,
+  onClose,
+}: {
+  initialPath: string;
+  onClose: () => void;
+}) {
+  const { progress, cancelDownload } = useDownloadProgress(
+    initialPath,
+    onClose,
+  );
+
+  return <DownloadProgress progress={progress} onCancel={cancelDownload} />;
+}
+
+export function DownloadModal({
+  initialPath,
+  onClose,
+  isOpen,
+}: DownloadModalProps) {
+  if (!isOpen) return null;
+
+  return <ActiveDownload initialPath={initialPath} onClose={onClose} />;
+}

frontend/src/components/shared/download-progress.tsx

@@ -0,0 +1,87 @@
+export interface DownloadProgressState {
+  filesTotal: number;
+  filesDownloaded: number;
+  currentFile: string;
+  totalBytesDownloaded: number;
+  bytesDownloadedPerSecond: number;
+  isDiscoveringFiles: boolean;
+}
+
+interface DownloadProgressProps {
+  progress: DownloadProgressState;
+  onCancel: () => void;
+}
+
+export function DownloadProgress({
+  progress,
+  onCancel,
+}: DownloadProgressProps) {
+  const formatBytes = (bytes: number) => {
+    const units = ["B", "KB", "MB", "GB"];
+    let size = bytes;
+    let unitIndex = 0;
+    while (size >= 1024 && unitIndex < units.length - 1) {
+      size /= 1024;
+      unitIndex += 1;
+    }
+    return `${size.toFixed(1)} ${units[unitIndex]}`;
+  };
+
+  return (
+    <div className="fixed inset-0 bg-black/50 flex items-center justify-center z-20">
+      <div className="bg-[#1C1C1C] rounded-lg p-6 max-w-md w-full mx-4 border border-[#525252]">
+        <div className="mb-4">
+          <h3 className="text-lg font-semibold mb-2 text-white">
+            {progress.isDiscoveringFiles
+              ? "Preparing Download..."
+              : "Downloading Files"}
+          </h3>
+          <p className="text-sm text-gray-400 truncate">
+            {progress.isDiscoveringFiles
+              ? `Found ${progress.filesTotal} files...`
+              : progress.currentFile}
+          </p>
+        </div>
+
+        <div className="mb-4">
+          <div className="h-2 bg-[#2C2C2C] rounded-full overflow-hidden">
+            {progress.isDiscoveringFiles ? (
+              <div
+                className="h-full bg-blue-500 animate-pulse"
+                style={{ width: "100%" }}
+              />
+            ) : (
+              <div
+                className="h-full bg-blue-500 transition-all duration-300"
+                style={{
+                  width: `${(progress.filesDownloaded / progress.filesTotal) * 100}%`,
+                }}
+              />
+            )}
+          </div>
+        </div>
+
+        <div className="flex justify-between text-sm text-gray-400">
+          <span>
+            {progress.isDiscoveringFiles
+              ? `Scanning workspace...`
+              : `${progress.filesDownloaded} of ${progress.filesTotal} files`}
+          </span>
+          {!progress.isDiscoveringFiles && (
+            <span>{formatBytes(progress.bytesDownloadedPerSecond)}/s</span>
+          )}
+        </div>
+
+        <div className="mt-4 flex justify-end">
+          <button
+            type="button"
+            onClick={onCancel}
+            className="px-4 py-2 text-sm text-gray-400 hover:text-white transition-colors"
+          >
+            Cancel
+          </button>
+        </div>
+      </div>
+    </div>
+  );
+}

frontend/src/components/shared/modals/account-settings/account-settings-form.tsx

@@ -13,6 +13,7 @@ import { handleCaptureConsent } from "#/utils/handle-capture-consent";
 import { ModalButton } from "../../buttons/modal-button";
 import { CustomInput } from "../../custom-input";
 import { FormFieldset } from "../../form-fieldset";
+import { useConfig } from "#/hooks/query/use-config";
 
 interface AccountSettingsFormProps {
   onClose: () => void;
@@ -28,6 +29,7 @@ export function AccountSettingsForm({
   analyticsConsent,
 }: AccountSettingsFormProps) {
   const { gitHubToken, setGitHubToken, logout } = useAuth();
+  const { data: config } = useConfig();
   const { saveSettings } = useUserPrefs();
   const { t } = useTranslation();
 
@@ -64,6 +66,16 @@ export function AccountSettingsForm({
         <div className="w-full flex flex-col gap-2">
           <BaseModalTitle title="Account Settings" />
 
+          {config?.APP_MODE === "saas" && config?.APP_SLUG && (
+            <a
+              href={`https://github.com/apps/${config.APP_SLUG}/installations/new`}
+              target="_blank"
+              rel="noreferrer noopener"
+              className="underline"
+            >
+              Configure Github Repositories
+            </a>
+          )}
           <FormFieldset
             id="language"
             label="Language"
@@ -75,23 +87,27 @@ export function AccountSettingsForm({
             }))}
           />
 
-          <CustomInput
-            name="ghToken"
-            label="GitHub Token"
-            type="password"
-            defaultValue={gitHubToken ?? ""}
-          />
-          <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>
+          {config?.APP_MODE !== "saas" && (
+            <>
+              <CustomInput
+                name="ghToken"
+                label="GitHub Token"
+                type="password"
+                defaultValue={gitHubToken ?? ""}
+              />
+              <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/shared/modals/modal-backdrop.tsx

@@ -20,7 +20,7 @@ export function ModalBackdrop({ children, onClose }: ModalBackdropProps) {
   };
 
   return (
-    <div className="fixed inset-0 flex items-center justify-center z-10">
+    <div className="fixed inset-0 flex items-center justify-center z-20">
       <div
         onClick={handleClick}
         className="fixed inset-0 bg-black bg-opacity-80"

frontend/src/components/shared/modals/settings/settings-form.tsx

@@ -24,6 +24,7 @@ import { CustomModelInput } from "../../inputs/custom-model-input";
 import { SecurityAnalyzerInput } from "../../inputs/security-analyzers-input";
 import { ModalBackdrop } from "../modal-backdrop";
 import { ModelSelector } from "./model-selector";
+import { useAuth } from "#/context/auth-context";
 
 interface SettingsFormProps {
   disabled?: boolean;
@@ -44,6 +45,7 @@ export function SettingsForm({
 }: SettingsFormProps) {
   const { saveSettings } = useUserPrefs();
   const endSession = useEndSession();
+  const { logout } = useAuth();
 
   const location = useLocation();
   const { t } = useTranslation();
@@ -96,9 +98,9 @@ export function SettingsForm({
     const isUsingAdvancedOptions = keys.includes("use-advanced-options");
     const newSettings = extractSettings(formData);
 
-    saveSettings(newSettings);
     saveSettingsView(isUsingAdvancedOptions ? "advanced" : "basic");
-    updateSettingsVersion();
+    updateSettingsVersion(logout);
+    saveSettings(newSettings);
     resetOngoingSession();
 
     posthog.capture("settings_saved", {

frontend/src/context/auth-context.tsx

@@ -1,5 +1,6 @@
 import posthog from "posthog-js";
 import React from "react";
+import OpenHands from "#/api/open-hands";
 import {
   removeAuthTokenHeader as removeOpenHandsAuthTokenHeader,
   removeGitHubTokenHeader as removeOpenHandsGitHubTokenHeader,
@@ -9,6 +10,7 @@ import {
 import {
   setAuthTokenHeader as setGitHubAuthTokenHeader,
   removeAuthTokenHeader as removeGitHubAuthTokenHeader,
+  setupAxiosInterceptors as setupGithubAxiosInterceptors,
 } from "#/api/github-axios-instance";
 
 interface AuthContextType {
@@ -18,6 +20,7 @@ interface AuthContextType {
   setGitHubToken: (token: string | null) => void;
   clearToken: () => void;
   clearGitHubToken: () => void;
+  refreshToken: () => Promise<boolean>;
   logout: () => void;
 }
 
@@ -69,19 +72,37 @@ function AuthProvider({ children }: React.PropsWithChildren) {
     }
   };
 
+  const logout = () => {
+    clearGitHubToken();
+    posthog.reset();
+  };
+
+  const refreshToken = async (): Promise<boolean> => {
+    const config = await OpenHands.getConfig();
+
+    if (config.APP_MODE !== "saas" || !gitHubTokenState) {
+      return false;
+    }
+
+    const newToken = await OpenHands.refreshToken(config.APP_MODE);
+    if (newToken) {
+      setGitHubToken(newToken);
+      return true;
+    }
+
+    clearGitHubToken();
+    return false;
+  };
+
   React.useEffect(() => {
     const storedToken = localStorage.getItem("token");
     const storedGitHubToken = localStorage.getItem("ghToken");
 
     setToken(storedToken);
     setGitHubToken(storedGitHubToken);
+    setupGithubAxiosInterceptors(refreshToken, logout);
   }, []);
 
-  const logout = () => {
-    clearGitHubToken();
-    posthog.reset();
-  };
-
   const value = React.useMemo(
     () => ({
       token: tokenState,
@@ -90,6 +111,7 @@ function AuthProvider({ children }: React.PropsWithChildren) {
       setGitHubToken,
       clearToken,
       clearGitHubToken,
+      refreshToken,
       logout,
     }),
     [tokenState, gitHubTokenState],

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

@@ -4,9 +4,9 @@ import { io, Socket } from "socket.io-client";
 import { Settings } from "#/services/settings";
 import ActionType from "#/types/action-type";
 import EventLogger from "#/utils/event-logger";
-import AgentState from "#/types/agent-state";
 import { handleAssistantMessage } from "#/services/actions";
 import { useRate } from "#/hooks/use-rate";
+import AgentState from "#/types/agent-state";
 
 const isOpenHandsMessage = (event: Record<string, unknown>) =>
   event.action === "message";
@@ -102,10 +102,12 @@ export function WsClientProvider({
     if (!Number.isNaN(parseInt(event.id as string, 10))) {
       lastEventRef.current = event;
     }
+
     const extras = event.extras as Record<string, unknown>;
     if (extras?.agent_state === AgentState.INIT) {
       setStatus(WsClientProviderStatus.ACTIVE);
     }
+
     if (
       status !== WsClientProviderStatus.ACTIVE &&
       event?.observation === "error"

frontend/src/hooks/query/use-app-installations.ts

@@ -0,0 +1,21 @@
+import { useQuery } from "@tanstack/react-query";
+import { useAuth } from "#/context/auth-context";
+import { useConfig } from "./use-config";
+import { retrieveGitHubAppInstallations } from "#/api/github";
+
+export const useAppInstallations = () => {
+  const { data: config } = useConfig();
+  const { gitHubToken } = useAuth();
+
+  return useQuery({
+    queryKey: ["installations", gitHubToken, config?.GITHUB_CLIENT_ID],
+    queryFn: async () => {
+      const data = await retrieveGitHubAppInstallations();
+      return data;
+    },
+    enabled:
+      !!gitHubToken &&
+      !!config?.GITHUB_CLIENT_ID &&
+      config?.APP_MODE === "saas",
+  });
+};

frontend/src/hooks/query/use-app-repositories.ts

@@ -0,0 +1,65 @@
+import { useInfiniteQuery } from "@tanstack/react-query";
+import React from "react";
+import { retrieveGitHubAppRepositories } from "#/api/github";
+import { useAuth } from "#/context/auth-context";
+import { useAppInstallations } from "./use-app-installations";
+import { useConfig } from "./use-config";
+
+export const useAppRepositories = () => {
+  const { gitHubToken } = useAuth();
+  const { data: config } = useConfig();
+  const { data: installations } = useAppInstallations();
+
+  const repos = useInfiniteQuery({
+    queryKey: ["repositories", gitHubToken, installations],
+    queryFn: async ({
+      pageParam,
+    }: {
+      pageParam: { installationIndex: number | null; repoPage: number | null };
+    }) => {
+      const { repoPage, installationIndex } = pageParam;
+
+      if (!installations) {
+        throw new Error("Missing installation list");
+      }
+
+      return retrieveGitHubAppRepositories(
+        installationIndex || 0,
+        installations,
+        repoPage || 1,
+        30,
+      );
+    },
+    initialPageParam: { installationIndex: 0, repoPage: 1 },
+    getNextPageParam: (lastPage) => {
+      if (lastPage.nextPage) {
+        return {
+          installationIndex: lastPage.installationIndex,
+          repoPage: lastPage.nextPage,
+        };
+      }
+
+      if (lastPage.installationIndex !== null) {
+        return { installationIndex: lastPage.installationIndex, repoPage: 1 };
+      }
+
+      return null;
+    },
+    enabled:
+      !!gitHubToken &&
+      Array.isArray(installations) &&
+      installations.length > 0 &&
+      config?.APP_MODE === "saas",
+  });
+
+  // TODO: Once we create our custom dropdown component, we should fetch data onEndReached
+  // (nextui autocomplete doesn't support onEndReached nor is it compatible for extending)
+  const { isSuccess, isFetchingNextPage, hasNextPage, fetchNextPage } = repos;
+  React.useEffect(() => {
+    if (!isFetchingNextPage && isSuccess && hasNextPage) {
+      fetchNextPage();
+    }
+  }, [isFetchingNextPage, isSuccess, hasNextPage, fetchNextPage]);
+
+  return repos;
+};

frontend/src/hooks/query/use-user-repositories.ts

@@ -2,9 +2,11 @@ import { useInfiniteQuery } from "@tanstack/react-query";
 import React from "react";
 import { retrieveGitHubUserRepositories } from "#/api/github";
 import { useAuth } from "#/context/auth-context";
+import { useConfig } from "./use-config";
 
 export const useUserRepositories = () => {
   const { gitHubToken } = useAuth();
+  const { data: config } = useConfig();
 
   const repos = useInfiniteQuery({
     queryKey: ["repositories", gitHubToken],
@@ -12,7 +14,7 @@ export const useUserRepositories = () => {
       retrieveGitHubUserRepositories(pageParam, 100),
     initialPageParam: 1,
     getNextPageParam: (lastPage) => lastPage.nextPage,
-    enabled: !!gitHubToken,
+    enabled: !!gitHubToken && config?.APP_MODE === "oss",
   });
 
   // TODO: Once we create our custom dropdown component, we should fetch data onEndReached

frontend/src/hooks/use-download-progress.ts

@@ -0,0 +1,78 @@
+import { useCallback, useEffect, useRef, useState } from "react";
+import { downloadFiles } from "#/utils/download-files";
+import { DownloadProgressState } from "#/components/shared/download-progress";
+
+export const INITIAL_PROGRESS: DownloadProgressState = {
+  filesTotal: 0,
+  filesDownloaded: 0,
+  currentFile: "",
+  totalBytesDownloaded: 0,
+  bytesDownloadedPerSecond: 0,
+  isDiscoveringFiles: true,
+};
+
+export function useDownloadProgress(
+  initialPath: string | undefined,
+  onClose: () => void,
+) {
+  const [isStarted, setIsStarted] = useState(false);
+  const [progress, setProgress] =
+    useState<DownloadProgressState>(INITIAL_PROGRESS);
+  const progressRef = useRef<DownloadProgressState>(INITIAL_PROGRESS);
+  const abortController = useRef<AbortController>();
+
+  // Create AbortController on mount
+  useEffect(() => {
+    const controller = new AbortController();
+    abortController.current = controller;
+    // Initialize progress ref with initial state
+    progressRef.current = INITIAL_PROGRESS;
+    return () => {
+      controller.abort();
+      abortController.current = undefined;
+    };
+  }, []); // Empty deps array - only run on mount/unmount
+
+  // Start download when isStarted becomes true
+  useEffect(() => {
+    if (!isStarted) {
+      setIsStarted(true);
+      return;
+    }
+
+    if (!abortController.current) return;
+
+    // Start download
+    const download = async () => {
+      try {
+        await downloadFiles(initialPath, {
+          onProgress: (p) => {
+            // Update both the ref and state
+            progressRef.current = { ...p };
+            setProgress((prev: DownloadProgressState) => ({ ...prev, ...p }));
+          },
+          signal: abortController.current!.signal,
+        });
+        onClose();
+      } catch (error) {
+        if (error instanceof Error && error.message === "Download cancelled") {
+          onClose();
+        } else {
+          throw error;
+        }
+      }
+    };
+    download();
+  }, [initialPath, onClose, isStarted]);
+
+  // No longer need startDownload as it's handled in useEffect
+
+  const cancelDownload = useCallback(() => {
+    abortController.current?.abort();
+  }, []);
+
+  return {
+    progress,
+    cancelDownload,
+  };
+}

frontend/src/hooks/use-terminal.ts

@@ -11,15 +11,29 @@ import { useWsClient } from "#/context/ws-client-provider";
   The reason for this is that the hook exposes a ref that requires a DOM element to be rendered.
 */
 
-export const useTerminal = (
-  commands: Command[] = [],
-  secrets: string[] = [],
-) => {
+interface UseTerminalConfig {
+  commands: Command[];
+  secrets: string[];
+  disabled: boolean;
+}
+
+const DEFAULT_TERMINAL_CONFIG: UseTerminalConfig = {
+  commands: [],
+  secrets: [],
+  disabled: false,
+};
+
+export const useTerminal = ({
+  commands,
+  secrets,
+  disabled,
+}: UseTerminalConfig = DEFAULT_TERMINAL_CONFIG) => {
   const { send } = useWsClient();
   const terminal = React.useRef<Terminal | null>(null);
   const fitAddon = React.useRef<FitAddon | null>(null);
   const ref = React.useRef<HTMLDivElement>(null);
   const lastCommandIndex = React.useRef(0);
+  const keyEventDisposable = React.useRef<{ dispose: () => void } | null>(null);
 
   const createTerminal = () =>
     new Terminal({
@@ -85,36 +99,12 @@ export const useTerminal = (
     terminal.current = createTerminal();
     fitAddon.current = new FitAddon();
 
-    let resizeObserver: ResizeObserver;
-    let commandBuffer = "";
+    let resizeObserver: ResizeObserver | null = null;
 
     if (ref.current) {
       /* Initialize the terminal in the DOM */
       initializeTerminal();
-
       terminal.current.write("$ ");
-      terminal.current.onKey(({ key, domEvent }) => {
-        if (domEvent.key === "Enter") {
-          handleEnter(commandBuffer);
-          commandBuffer = "";
-        } else if (domEvent.key === "Backspace") {
-          if (commandBuffer.length > 0) {
-            commandBuffer = handleBackspace(commandBuffer);
-          }
-        } else {
-          // Ignore paste event
-          if (key.charCodeAt(0) === 22) {
-            return;
-          }
-          commandBuffer += key;
-          terminal.current?.write(key);
-        }
-      });
-      terminal.current.attachCustomKeyEventHandler((event) =>
-        pasteHandler(event, (text) => {
-          commandBuffer += text;
-        }),
-      );
 
       /* Listen for resize events */
       resizeObserver = new ResizeObserver(() => {
@@ -125,7 +115,7 @@ export const useTerminal = (
 
     return () => {
       terminal.current?.dispose();
-      resizeObserver.disconnect();
+      resizeObserver?.disconnect();
     };
   }, []);
 
@@ -152,5 +142,60 @@ export const useTerminal = (
     }
   }, [commands]);
 
+  React.useEffect(() => {
+    if (terminal.current) {
+      // Dispose of existing listeners if they exist
+      if (keyEventDisposable.current) {
+        keyEventDisposable.current.dispose();
+        keyEventDisposable.current = null;
+      }
+
+      let commandBuffer = "";
+
+      if (!disabled) {
+        // Add new key event listener and store the disposable
+        keyEventDisposable.current = terminal.current.onKey(
+          ({ key, domEvent }) => {
+            if (domEvent.key === "Enter") {
+              handleEnter(commandBuffer);
+              commandBuffer = "";
+            } else if (domEvent.key === "Backspace") {
+              if (commandBuffer.length > 0) {
+                commandBuffer = handleBackspace(commandBuffer);
+              }
+            } else {
+              // Ignore paste event
+              if (key.charCodeAt(0) === 22) {
+                return;
+              }
+              commandBuffer += key;
+              terminal.current?.write(key);
+            }
+          },
+        );
+
+        // Add custom key handler and store the disposable
+        terminal.current.attachCustomKeyEventHandler((event) =>
+          pasteHandler(event, (text) => {
+            commandBuffer += text;
+          }),
+        );
+      } else {
+        // Add a noop handler when disabled
+        keyEventDisposable.current = terminal.current.onKey((e) => {
+          e.domEvent.preventDefault();
+          e.domEvent.stopPropagation();
+        });
+      }
+    }
+
+    return () => {
+      if (keyEventDisposable.current) {
+        keyEventDisposable.current.dispose();
+        keyEventDisposable.current = null;
+      }
+    };
+  }, [disabled]);
+
   return ref;
 };

frontend/src/i18n/translation.json

@@ -2001,9 +2001,9 @@
     "en": "Push to GitHub",
     "es": "Subir a GitHub"
   },
-  "PROJECT_MENU_CARD_CONTEXT_MENU$DOWNLOAD_AS_ZIP_LABEL": {
-    "en": "Download as .zip",
-    "es": "Descargar como .zip"
+  "PROJECT_MENU_CARD_CONTEXT_MENU$DOWNLOAD_FILES_LABEL": {
+    "en": "Download files",
+    "es": "Descargar archivos"
   },
   "ACTION_MESSAGE$RUN": {
     "en": "Running a bash command"

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

@@ -5,6 +5,8 @@ import posthog from "posthog-js";
 import { setImportedProjectZip } from "#/state/initial-query-slice";
 import { convertZipToBase64 } from "#/utils/convert-zip-to-base64";
 import { useUserRepositories } from "#/hooks/query/use-user-repositories";
+import { useAppRepositories } from "#/hooks/query/use-app-repositories";
+
 import { useGitHubUser } from "#/hooks/query/use-github-user";
 import { useGitHubAuthUrl } from "#/hooks/use-github-auth-url";
 import { useConfig } from "#/hooks/query/use-config";
@@ -25,7 +27,8 @@ function Home() {
 
   const { data: config } = useConfig();
   const { data: user } = useGitHubUser();
-  const { data: repositories } = useUserRepositories();
+  const { data: appRepositories } = useAppRepositories();
+  const { data: userRepositories } = useUserRepositories();
 
   const gitHubAuthUrl = useGitHubAuthUrl({
     gitHubToken,
@@ -52,7 +55,9 @@ function Home() {
           <GitHubRepositoriesSuggestionBox
             handleSubmit={() => formRef.current?.requestSubmit()}
             repositories={
-              repositories?.pages.flatMap((page) => page.data) || []
+              userRepositories?.pages.flatMap((page) => page.data) ||
+              appRepositories?.pages.flatMap((page) => page.data) ||
+              []
             }
             gitHubAuthUrl={gitHubAuthUrl}
             user={user || null}

frontend/src/routes/_oh.app.jupyter.tsx

@@ -14,7 +14,7 @@ function Jupyter() {
   }, []);
 
   return (
-    <div ref={parentRef}>
+    <div ref={parentRef} className="h-full">
       <JupyterEditor maxWidth={parentWidth} />
     </div>
   );

frontend/src/routes/_oh.app.terminal.tsx

@@ -1,23 +0,0 @@
-import React from "react";
-import { useAuth } from "#/context/auth-context";
-
-function TerminalRoute() {
-  const { token, gitHubToken } = useAuth();
-  const Terminal = React.useMemo(
-    () => React.lazy(() => import("#/components/features/terminal/terminal")),
-    [],
-  );
-
-  const secrets = React.useMemo(
-    () => [gitHubToken, token].filter((secret) => secret !== null),
-    [gitHubToken, token],
-  );
-
-  return (
-    <React.Suspense fallback={<div className="h-full" />}>
-      <Terminal secrets={secrets} />
-    </React.Suspense>
-  );
-}
-
-export default TerminalRoute;

frontend/src/routes/_oh.app/hooks/use-handle-runtime-active.ts

@@ -1,7 +1,6 @@
 import React from "react";
 import toast from "react-hot-toast";
 import { useDispatch, useSelector } from "react-redux";
-import { isGitHubErrorReponse } from "#/api/github";
 import { useAuth } from "#/context/auth-context";
 import {
   useWsClient,
@@ -13,6 +12,7 @@ import { RootState } from "#/store";
 import { base64ToBlob } from "#/utils/base64-to-blob";
 import { useUploadFiles } from "../../../hooks/mutation/use-upload-files";
 import { useGitHubUser } from "../../../hooks/query/use-github-user";
+import { isGitHubErrorReponse } from "#/api/github-axios-instance";
 
 export const useHandleRuntimeActive = () => {
   const { gitHubToken } = useAuth();

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

@@ -22,38 +22,11 @@ import { useConversationConfig } from "#/hooks/query/use-conversation-config";
 import { Container } from "#/components/layout/container";
 import Security from "#/components/shared/modals/security/security";
 import { CountBadge } from "#/components/layout/count-badge";
+import { TerminalStatusLabel } from "#/components/features/terminal/terminal-status-label";
 
 function App() {
   const { token, gitHubToken } = useAuth();
   const { settings } = useUserPrefs();
-  const [leftPanelWidth, setLeftPanelWidth] = React.useState(50); // 50% default width
-  const isDragging = React.useRef(false);
-
-  const handleMouseDown = React.useCallback(() => {
-    isDragging.current = true;
-    document.body.style.userSelect = "none";
-  }, []);
-
-  const handleMouseUp = React.useCallback(() => {
-    isDragging.current = false;
-    document.body.style.userSelect = "";
-  }, []);
-
-  const handleMouseMove = React.useCallback((e: MouseEvent) => {
-    if (!isDragging.current) return;
-    const containerWidth = window.innerWidth;
-    const newWidth = (e.clientX / containerWidth) * 100;
-    setLeftPanelWidth(Math.min(Math.max(20, newWidth), 80)); // Limit between 20% and 80%
-  }, []);
-
-  React.useEffect(() => {
-    window.addEventListener("mousemove", handleMouseMove);
-    window.addEventListener("mouseup", handleMouseUp);
-    return () => {
-      window.removeEventListener("mousemove", handleMouseMove);
-      window.removeEventListener("mouseup", handleMouseUp);
-    };
-  }, [handleMouseMove, handleMouseUp]);
 
   const dispatch = useDispatch();
   useConversationConfig();
@@ -68,6 +41,16 @@ function App() {
     repository: selectedRepository,
   });
 
+  const secrets = React.useMemo(
+    () => [gitHubToken, token].filter((secret) => secret !== null),
+    [gitHubToken, token],
+  );
+
+  const Terminal = React.useMemo(
+    () => React.lazy(() => import("#/components/features/terminal/terminal")),
+    [],
+  );
+
   useEffectOnce(() => {
     dispatch(clearMessages());
     dispatch(clearTerminal());
@@ -90,24 +73,14 @@ function App() {
     >
       <EventHandler>
         <div className="flex flex-col h-full gap-3">
-          <div className="flex h-full overflow-auto">
-            <div
-              className="w-full md:w-auto max-h-full relative"
-              style={{ width: `${leftPanelWidth}%` }}
-            >
-              <Container className="h-full">
-                <ChatInterface />
-              </Container>
-            </div>
-
-            <div
-              className="hidden md:block w-1 bg-default-100 hover:bg-default-200 cursor-col-resize"
-              onMouseDown={handleMouseDown}
-            />
+          <div className="flex h-full overflow-auto gap-3">
+            <Container className="w-full md:w-[390px] max-h-full relative">
+              <ChatInterface />
+            </Container>
 
             <div className="hidden md:flex flex-col grow gap-3">
               <Container
-                className="h-full"
+                className="h-2/3"
                 labels={[
                   { label: "Workspace", to: "", icon: <CodeIcon /> },
                   { label: "Jupyter", to: "jupyter", icon: <ListIcon /> },
@@ -121,17 +94,22 @@ function App() {
                     to: "browser",
                     icon: <GlobeIcon />,
                   },
-                  {
-                    label: "Terminal",
-                    to: "terminal",
-                    icon: <CodeIcon />,
-                  },
                 ]}
               >
                 <FilesProvider>
                   <Outlet />
                 </FilesProvider>
               </Container>
+              {/* Terminal uses some API that is not compatible in a server-environment. For this reason, we lazy load it to ensure
+               * that it loads only in the client-side. */}
+              <Container
+                className="h-1/3 overflow-scroll"
+                label={<TerminalStatusLabel />}
+              >
+                <React.Suspense fallback={<div className="h-full" />}>
+                  <Terminal secrets={secrets} />
+                </React.Suspense>
+              </Container>
             </div>
           </div>
 

frontend/src/routes/_oh/route.tsx

@@ -9,6 +9,7 @@ import { useConfig } from "#/hooks/query/use-config";
 import { Sidebar } from "#/components/features/sidebar/sidebar";
 import { WaitlistModal } from "#/components/features/waitlist/waitlist-modal";
 import { AnalyticsConsentFormModal } from "#/components/features/analytics/analytics-consent-form-modal";
+import { SettingsModal } from "#/components/shared/modals/settings/settings-modal";
 
 export function ErrorBoundary() {
   const error = useRouteError();
@@ -44,12 +45,15 @@ export function ErrorBoundary() {
 
 export default function MainApp() {
   const { gitHubToken, clearToken } = useAuth();
-  const { settings } = useUserPrefs();
+  const { settings, settingsAreUpToDate } = useUserPrefs();
 
   const [consentFormIsOpen, setConsentFormIsOpen] = React.useState(
     !localStorage.getItem("analytics-consent"),
   );
 
+  const [aiConfigModalIsOpen, setAiConfigModalIsOpen] =
+    React.useState(!settingsAreUpToDate);
+
   const config = useConfig();
   const {
     data: isAuthed,
@@ -96,6 +100,13 @@ export default function MainApp() {
           onClose={() => setConsentFormIsOpen(false)}
         />
       )}
+
+      {aiConfigModalIsOpen && (
+        <SettingsModal
+          onClose={() => setAiConfigModalIsOpen(false)}
+          data-testid="ai-config-modal"
+        />
+      )}
     </div>
   );
 }

frontend/src/services/settings.ts

@@ -1,4 +1,4 @@
-export const LATEST_SETTINGS_VERSION = 3;
+export const LATEST_SETTINGS_VERSION = 4;
 
 export type Settings = {
   LLM_MODEL: string;
@@ -35,10 +35,11 @@ export const getCurrentSettingsVersion = () => {
 export const settingsAreUpToDate = () =>
   getCurrentSettingsVersion() === LATEST_SETTINGS_VERSION;
 
-export const maybeMigrateSettings = () => {
+export const maybeMigrateSettings = (logout: () => void) => {
   // Sometimes we ship major changes, like a new default agent.
   // In this case, we may want to override a previous choice made by the user.
   const currentVersion = getCurrentSettingsVersion();
+
   if (currentVersion < 1) {
     localStorage.setItem("AGENT", DEFAULT_SETTINGS.AGENT);
   }
@@ -53,6 +54,10 @@ export const maybeMigrateSettings = () => {
   if (currentVersion < 3) {
     localStorage.removeItem("token");
   }
+
+  if (currentVersion < 4) {
+    logout();
+  }
 };
 
 /**

frontend/src/state/jupyter-slice.ts

@@ -7,8 +7,8 @@ export type Cell = {
 
 const initialCells: Cell[] = [];
 
-export const cellSlice = createSlice({
-  name: "cell",
+export const jupyterSlice = createSlice({
+  name: "jupyter",
   initialState: {
     cells: initialCells,
   },
@@ -26,6 +26,7 @@ export const cellSlice = createSlice({
 });
 
 export const { appendJupyterInput, appendJupyterOutput, clearJupyter } =
-  cellSlice.actions;
+  jupyterSlice.actions;
 
-export default cellSlice.reducer;
+export const jupyterReducer = jupyterSlice.reducer;
+export default jupyterReducer;

frontend/src/store.ts

@@ -6,7 +6,7 @@ import codeReducer from "./state/code-slice";
 import fileStateReducer from "./state/file-state-slice";
 import initialQueryReducer from "./state/initial-query-slice";
 import commandReducer from "./state/command-slice";
-import jupyterReducer from "./state/jupyter-slice";
+import { jupyterReducer } from "./state/jupyter-slice";
 import securityAnalyzerReducer from "./state/security-analyzer-slice";
 import statusReducer from "./state/status-slice";
 

frontend/src/types/file-system.d.ts

@@ -0,0 +1,31 @@
+interface FileSystemWritableFileStream extends WritableStream {
+  write(data: BufferSource | Blob | string): Promise<void>;
+  seek(position: number): Promise<void>;
+  truncate(size: number): Promise<void>;
+}
+
+interface FileSystemFileHandle {
+  kind: "file";
+  name: string;
+  getFile(): Promise<File>;
+  createWritable(options?: {
+    keepExistingData?: boolean;
+  }): Promise<FileSystemWritableFileStream>;
+}
+
+interface FileSystemDirectoryHandle {
+  kind: "directory";
+  name: string;
+  getDirectoryHandle(
+    name: string,
+    options?: { create?: boolean },
+  ): Promise<FileSystemDirectoryHandle>;
+  getFileHandle(
+    name: string,
+    options?: { create?: boolean },
+  ): Promise<FileSystemFileHandle>;
+}
+
+interface Window {
+  showDirectoryPicker(): Promise<FileSystemDirectoryHandle>;
+}

frontend/src/types/github.d.ts

@@ -18,6 +18,10 @@ interface GitHubRepository {
   full_name: string;
 }
 
+interface GitHubAppRepository {
+  repositories: GitHubRepository[];
+}
+
 interface GitHubCommit {
   html_url: string;
   sha: string;
@@ -27,3 +31,7 @@ interface GitHubCommit {
     };
   };
 }
+
+interface GithubAppInstallation {
+  installations: { id: number }[];
+}

frontend/src/utils/download-files.ts

@@ -0,0 +1,305 @@
+import OpenHands from "#/api/open-hands";
+
+interface DownloadProgress {
+  filesTotal: number;
+  filesDownloaded: number;
+  currentFile: string;
+  totalBytesDownloaded: number;
+  bytesDownloadedPerSecond: number;
+  isDiscoveringFiles: boolean;
+}
+
+interface DownloadOptions {
+  onProgress?: (progress: DownloadProgress) => void;
+  signal?: AbortSignal;
+}
+
+/**
+ * Checks if the File System Access API is supported
+ */
+function isFileSystemAccessSupported(): boolean {
+  return "showDirectoryPicker" in window;
+}
+
+/**
+ * Creates subdirectories and returns the final directory handle
+ */
+async function createSubdirectories(
+  baseHandle: FileSystemDirectoryHandle,
+  pathParts: string[],
+): Promise<FileSystemDirectoryHandle> {
+  return pathParts.reduce(async (promise, part) => {
+    const handle = await promise;
+    return handle.getDirectoryHandle(part, { create: true });
+  }, Promise.resolve(baseHandle));
+}
+
+/**
+ * Recursively gets all files in a directory
+ */
+async function getAllFiles(
+  path: string,
+  progress: DownloadProgress,
+  options?: DownloadOptions,
+): Promise<string[]> {
+  const entries = await OpenHands.getFiles(path);
+
+  const processEntry = async (entry: string): Promise<string[]> => {
+    if (options?.signal?.aborted) {
+      throw new Error("Download cancelled");
+    }
+
+    const fullPath = path + entry;
+    if (entry.endsWith("/")) {
+      const subEntries = await OpenHands.getFiles(fullPath);
+      const subFilesPromises = subEntries.map((subEntry) =>
+        processEntry(subEntry),
+      );
+      const subFilesArrays = await Promise.all(subFilesPromises);
+      return subFilesArrays.flat();
+    }
+    const updatedProgress = {
+      ...progress,
+      filesTotal: progress.filesTotal + 1,
+      currentFile: fullPath,
+    };
+    options?.onProgress?.(updatedProgress);
+    return [fullPath];
+  };
+
+  const filePromises = entries.map((entry) => processEntry(entry));
+  const fileArrays = await Promise.all(filePromises);
+
+  const updatedProgress = {
+    ...progress,
+    isDiscoveringFiles: false,
+  };
+  options?.onProgress?.(updatedProgress);
+
+  return fileArrays.flat();
+}
+
+/**
+ * Process a batch of files
+ */
+async function processBatch(
+  batch: string[],
+  directoryHandle: FileSystemDirectoryHandle,
+  progress: DownloadProgress,
+  startTime: number,
+  completedFiles: number,
+  totalBytes: number,
+  options?: DownloadOptions,
+): Promise<{ newCompleted: number; newBytes: number }> {
+  if (options?.signal?.aborted) {
+    throw new Error("Download cancelled");
+  }
+
+  // Process files in the batch in parallel
+  const results = await Promise.all(
+    batch.map(async (path) => {
+      try {
+        const newProgress = {
+          ...progress,
+          currentFile: path,
+          isDiscoveringFiles: false,
+          filesDownloaded: completedFiles,
+          totalBytesDownloaded: totalBytes,
+          bytesDownloadedPerSecond:
+            totalBytes / ((Date.now() - startTime) / 1000),
+        };
+        options?.onProgress?.(newProgress);
+
+        const content = await OpenHands.getFile(path);
+
+        // Save to the selected directory preserving structure
+        const pathParts = path.split("/").filter(Boolean);
+        const fileName = pathParts.pop() || "file";
+        const dirHandle =
+          pathParts.length > 0
+            ? await createSubdirectories(directoryHandle, pathParts)
+            : directoryHandle;
+
+        // Create and write the file
+        const fileHandle = await dirHandle.getFileHandle(fileName, {
+          create: true,
+        });
+        const writable = await fileHandle.createWritable();
+        await writable.write(content);
+        await writable.close();
+
+        // Return the size of this file
+        return new Blob([content]).size;
+      } catch (error) {
+        // Silently handle file processing errors and return 0 bytes
+        return 0;
+      }
+    }),
+  );
+
+  // Calculate batch totals
+  const batchBytes = results.reduce((sum, size) => sum + size, 0);
+  const newTotalBytes = totalBytes + batchBytes;
+  const newCompleted =
+    completedFiles + results.filter((size) => size > 0).length;
+
+  // Update progress with batch results
+  const updatedProgress = {
+    ...progress,
+    filesDownloaded: newCompleted,
+    totalBytesDownloaded: newTotalBytes,
+    bytesDownloadedPerSecond: newTotalBytes / ((Date.now() - startTime) / 1000),
+    isDiscoveringFiles: false,
+  };
+  options?.onProgress?.(updatedProgress);
+
+  return {
+    newCompleted,
+    newBytes: newTotalBytes,
+  };
+}
+
+/**
+ * Downloads files from the workspace one by one
+ * @param initialPath Initial path to start downloading from. If not provided, downloads from root
+ * @param options Download options including progress callback and abort signal
+ */
+export async function downloadFiles(
+  initialPath?: string,
+  options?: DownloadOptions,
+): Promise<void> {
+  const startTime = Date.now();
+  const progress: DownloadProgress = {
+    filesTotal: 0, // Will be updated during file discovery
+    filesDownloaded: 0,
+    currentFile: "",
+    totalBytesDownloaded: 0,
+    bytesDownloadedPerSecond: 0,
+    isDiscoveringFiles: true,
+  };
+
+  try {
+    // Check if File System Access API is supported
+    if (!isFileSystemAccessSupported()) {
+      throw new Error(
+        "Your browser doesn't support downloading folders. Please use Chrome, Edge, or another browser that supports the File System Access API.",
+      );
+    }
+
+    // Show directory picker first
+    let directoryHandle: FileSystemDirectoryHandle;
+    try {
+      directoryHandle = await window.showDirectoryPicker();
+    } catch (error) {
+      if (error instanceof Error && error.name === "AbortError") {
+        throw new Error("Download cancelled");
+      }
+      if (error instanceof Error && error.name === "SecurityError") {
+        throw new Error(
+          "Permission denied. Please allow access to the download location when prompted.",
+        );
+      }
+      throw new Error("Failed to select download location. Please try again.");
+    }
+
+    // Then recursively get all files
+    const files = await getAllFiles(initialPath || "", progress, options);
+
+    // Set isDiscoveringFiles to false now that we have the full list and preserve filesTotal
+    const finalTotal = progress.filesTotal;
+    options?.onProgress?.({
+      ...progress,
+      filesTotal: finalTotal,
+      isDiscoveringFiles: false,
+    });
+
+    // Verify we still have permission after the potentially long file scan
+    try {
+      // Try to create and write to a test file to verify permissions
+      const testHandle = await directoryHandle.getFileHandle(
+        ".openhands-test",
+        { create: true },
+      );
+      const writable = await testHandle.createWritable();
+      await writable.close();
+    } catch (error) {
+      if (
+        error instanceof Error &&
+        error.message.includes("User activation is required")
+      ) {
+        // Ask for permission again
+        try {
+          directoryHandle = await window.showDirectoryPicker();
+        } catch (permissionError) {
+          if (
+            permissionError instanceof Error &&
+            permissionError.name === "AbortError"
+          ) {
+            throw new Error("Download cancelled");
+          }
+          if (
+            permissionError instanceof Error &&
+            permissionError.name === "SecurityError"
+          ) {
+            throw new Error(
+              "Permission denied. Please allow access to the download location when prompted.",
+            );
+          }
+          throw new Error(
+            "Failed to select download location. Please try again.",
+          );
+        }
+      } else {
+        throw error;
+      }
+    }
+
+    // Process files in parallel batches to avoid overwhelming the browser
+    const BATCH_SIZE = 5;
+    const batches = Array.from(
+      { length: Math.ceil(files.length / BATCH_SIZE) },
+      (_, i) => files.slice(i * BATCH_SIZE, (i + 1) * BATCH_SIZE),
+    );
+
+    // Keep track of completed files across all batches
+    let completedFiles = 0;
+    let totalBytesDownloaded = 0;
+
+    // Process batches sequentially to maintain order and avoid overwhelming the browser
+    await batches.reduce(
+      (promise, batch) =>
+        promise.then(async () => {
+          const { newCompleted, newBytes } = await processBatch(
+            batch,
+            directoryHandle,
+            progress,
+            startTime,
+            completedFiles,
+            totalBytesDownloaded,
+            options,
+          );
+          completedFiles = newCompleted;
+          totalBytesDownloaded = newBytes;
+        }),
+      Promise.resolve(),
+    );
+  } catch (error) {
+    if (error instanceof Error && error.message === "Download cancelled") {
+      throw error;
+    }
+    // Re-throw the error as is if it's already a user-friendly message
+    if (
+      error instanceof Error &&
+      (error.message.includes("browser doesn't support") ||
+        error.message.includes("Failed to select") ||
+        error.message === "Download cancelled")
+    ) {
+      throw error;
+    }
+
+    // Otherwise, wrap it with a generic message
+    throw new Error(
+      `Failed to download files: ${error instanceof Error ? error.message : String(error)}`,
+    );
+  }
+}

frontend/src/utils/generate-github-auth-url.ts

@@ -6,5 +6,6 @@
  */
 export const generateGitHubAuthUrl = (clientId: string, requestUrl: URL) => {
   const redirectUri = `${requestUrl.origin}/oauth/github/callback`;
-  return `https://github.com/login/oauth/authorize?client_id=${clientId}&redirect_uri=${encodeURIComponent(redirectUri)}&scope=repo,user,workflow`;
+  const scope = "repo,user,workflow,offline_access";
+  return `https://github.com/login/oauth/authorize?client_id=${clientId}&redirect_uri=${encodeURIComponent(redirectUri)}&scope=${encodeURIComponent(scope)}`;
 };

frontend/src/utils/settings-utils.ts

@@ -82,9 +82,9 @@ const saveSettingsView = (view: "basic" | "advanced") => {
  * Updates the settings version in local storage if the current settings are not up to date.
  * If the settings are outdated, it attempts to migrate them before updating the version.
  */
-const updateSettingsVersion = () => {
+const updateSettingsVersion = (logout: () => void) => {
   if (!settingsAreUpToDate()) {
-    maybeMigrateSettings();
+    maybeMigrateSettings(logout);
     localStorage.setItem(
       "SETTINGS_VERSION",
       LATEST_SETTINGS_VERSION.toString(),

frontend/tailwind.config.js

@@ -1,7 +1,6 @@
 /** @type {import('tailwindcss').Config} */
 import { nextui } from "@nextui-org/react";
 import typography from '@tailwindcss/typography';
-
 export default {
   content: [
     "./src/**/*.{js,ts,jsx,tsx}",

openhands/agenthub/__init__.py

@@ -10,7 +10,6 @@ load_dotenv()
 from openhands.agenthub import (  # noqa: E402
     browsing_agent,
     codeact_agent,
-    codeact_swe_agent,
     delegator_agent,
     dummy_agent,
     planner_agent,
@@ -18,7 +17,6 @@ from openhands.agenthub import (  # noqa: E402
 
 __all__ = [
     'codeact_agent',
-    'codeact_swe_agent',
     'planner_agent',
     'delegator_agent',
     'dummy_agent',

openhands/agenthub/browsing_agent/prompt.py

@@ -1,786 +0,0 @@
-import abc
-import difflib
-import logging
-import platform
-from copy import deepcopy
-from dataclasses import asdict, dataclass
-from textwrap import dedent
-from typing import Literal, Union
-from warnings import warn
-
-from browsergym.core.action.base import AbstractActionSet
-from browsergym.core.action.highlevel import HighLevelActionSet
-from browsergym.core.action.python import PythonActionSet
-
-from openhands.agenthub.browsing_agent.utils import (
-    ParseError,
-    parse_html_tags_raise,
-)
-from openhands.runtime.browser.browser_env import BrowserEnv
-
-
-@dataclass
-class Flags:
-    use_html: bool = True
-    use_ax_tree: bool = False
-    drop_ax_tree_first: bool = True  # This flag is no longer active TODO delete
-    use_thinking: bool = False
-    use_error_logs: bool = False
-    use_past_error_logs: bool = False
-    use_history: bool = False
-    use_action_history: bool = False
-    use_memory: bool = False
-    use_diff: bool = False
-    html_type: str = 'pruned_html'
-    use_concrete_example: bool = True
-    use_abstract_example: bool = False
-    multi_actions: bool = False
-    action_space: Literal[
-        'python', 'bid', 'coord', 'bid+coord', 'bid+nav', 'coord+nav', 'bid+coord+nav'
-    ] = 'bid'
-    is_strict: bool = False
-    # This flag will be automatically disabled `if not chat_model_args.has_vision()`
-    use_screenshot: bool = True
-    enable_chat: bool = False
-    max_prompt_tokens: int = 100_000
-    extract_visible_tag: bool = False
-    extract_coords: Literal['False', 'center', 'box'] = 'False'
-    extract_visible_elements_only: bool = False
-    demo_mode: Literal['off', 'default', 'only_visible_elements'] = 'off'
-
-    def copy(self):
-        return deepcopy(self)
-
-    def asdict(self):
-        """Helper for JSON serializble requirement."""
-        return asdict(self)
-
-    @classmethod
-    def from_dict(self, flags_dict):
-        """Helper for JSON serializable requirement."""
-        if isinstance(flags_dict, Flags):
-            return flags_dict
-
-        if not isinstance(flags_dict, dict):
-            raise ValueError(
-                f'Unregcognized type for flags_dict of type {type(flags_dict)}.'
-            )
-        return Flags(**flags_dict)
-
-
-class PromptElement:
-    """Base class for all prompt elements. Prompt elements can be hidden.
-
-    Prompt elements are used to build the prompt. Use flags to control which
-    prompt elements are visible. We use class attributes as a convenient way
-    to implement static prompts, but feel free to override them with instance
-    attributes or @property decorator.
-    """
-
-    _prompt = ''
-    _abstract_ex = ''
-    _concrete_ex = ''
-
-    def __init__(self, visible: bool = True) -> None:
-        """Prompt element that can be hidden.
-
-        Parameters
-        ----------
-        visible : bool, optional
-            Whether the prompt element should be visible, by default True. Can
-            be a callable that returns a bool. This is useful when a specific
-            flag changes during a shrink iteration.
-        """
-        self._visible = visible
-
-    @property
-    def prompt(self):
-        """Avoid overriding this method. Override _prompt instead."""
-        return self._hide(self._prompt)
-
-    @property
-    def abstract_ex(self):
-        """Useful when this prompt element is requesting an answer from the llm.
-        Provide an abstract example of the answer here. See Memory for an
-        example.
-
-        Avoid overriding this method. Override _abstract_ex instead
-        """
-        return self._hide(self._abstract_ex)
-
-    @property
-    def concrete_ex(self):
-        """Useful when this prompt element is requesting an answer from the llm.
-        Provide a concrete example of the answer here. See Memory for an
-        example.
-
-        Avoid overriding this method. Override _concrete_ex instead
-        """
-        return self._hide(self._concrete_ex)
-
-    @property
-    def is_visible(self):
-        """Handle the case where visible is a callable."""
-        visible = self._visible
-        if callable(visible):
-            visible = visible()
-        return visible
-
-    def _hide(self, value):
-        """Return value if visible is True, else return empty string."""
-        if self.is_visible:
-            return value
-        else:
-            return ''
-
-    def _parse_answer(self, text_answer) -> dict:
-        if self.is_visible:
-            return self._parse_answer(text_answer)
-        else:
-            return {}
-
-
-class Shrinkable(PromptElement, abc.ABC):
-    @abc.abstractmethod
-    def shrink(self) -> None:
-        """Implement shrinking of this prompt element.
-
-        You need to recursively call all shrinkable elements that are part of
-        this prompt. You can also implement a shrinking strategy for this prompt.
-        Shrinking is can be called multiple times to progressively shrink the
-        prompt until it fits max_tokens. Default max shrink iterations is 20.
-        """
-        pass
-
-
-class Truncater(Shrinkable):
-    """A prompt element that can be truncated to fit the context length of the LLM.
-    Of course, it will be great that we never have to use the functionality here to `shrink()` the prompt.
-    Extend this class for prompt elements that can be truncated. Usually long observations such as AxTree or HTML.
-    """
-
-    def __init__(self, visible, shrink_speed=0.3, start_truncate_iteration=10):
-        super().__init__(visible=visible)
-        self.shrink_speed = shrink_speed  # the percentage shrunk in each iteration
-        self.start_truncate_iteration = (
-            start_truncate_iteration  # the iteration to start truncating
-        )
-        self.shrink_calls = 0
-        self.deleted_lines = 0
-
-    def shrink(self) -> None:
-        if self.is_visible and self.shrink_calls >= self.start_truncate_iteration:
-            # remove the fraction of _prompt
-            lines = self._prompt.splitlines()
-            new_line_count = int(len(lines) * (1 - self.shrink_speed))
-            self.deleted_lines += len(lines) - new_line_count
-            self._prompt = '\n'.join(lines[:new_line_count])
-            self._prompt += (
-                f'\n... Deleted {self.deleted_lines} lines to reduce prompt size.'
-            )
-
-        self.shrink_calls += 1
-
-
-def fit_tokens(
-    shrinkable: Shrinkable,
-    max_prompt_chars=None,
-    max_iterations=20,
-):
-    """Shrink a prompt element until it fits max_tokens.
-
-    Parameters
-    ----------
-    shrinkable : Shrinkable
-        The prompt element to shrink.
-    max_prompt_chars : int
-        The maximum number of chars allowed.
-    max_iterations : int, optional
-        The maximum number of shrink iterations, by default 20.
-    model_name : str, optional
-        The name of the model used when tokenizing.
-
-    Returns:
-    -------
-    str : the prompt after shrinking.
-    """
-    if max_prompt_chars is None:
-        return shrinkable.prompt
-
-    for _ in range(max_iterations):
-        prompt = shrinkable.prompt
-        if isinstance(prompt, str):
-            prompt_str = prompt
-        elif isinstance(prompt, list):
-            prompt_str = '\n'.join([p['text'] for p in prompt if p['type'] == 'text'])
-        else:
-            raise ValueError(f'Unrecognized type for prompt: {type(prompt)}')
-        n_chars = len(prompt_str)
-        if n_chars <= max_prompt_chars:
-            return prompt
-        shrinkable.shrink()
-
-    logging.info(
-        dedent(
-            f"""\
-            After {max_iterations} shrink iterations, the prompt is still
-            {len(prompt_str)} chars (greater than {max_prompt_chars}). Returning the prompt as is."""
-        )
-    )
-    return prompt
-
-
-class HTML(Truncater):
-    def __init__(self, html, visible: bool = True, prefix='') -> None:
-        super().__init__(visible=visible, start_truncate_iteration=5)
-        self._prompt = f'\n{prefix}HTML:\n{html}\n'
-
-
-class AXTree(Truncater):
-    def __init__(
-        self, ax_tree, visible: bool = True, coord_type=None, prefix=''
-    ) -> None:
-        super().__init__(visible=visible, start_truncate_iteration=10)
-        if coord_type == 'center':
-            coord_note = """\
-Note: center coordinates are provided in parenthesis and are
-  relative to the top left corner of the page.\n\n"""
-        elif coord_type == 'box':
-            coord_note = """\
-Note: bounding box of each object are provided in parenthesis and are
-  relative to the top left corner of the page.\n\n"""
-        else:
-            coord_note = ''
-        self._prompt = f'\n{prefix}AXTree:\n{coord_note}{ax_tree}\n'
-
-
-class Error(PromptElement):
-    def __init__(self, error, visible: bool = True, prefix='') -> None:
-        super().__init__(visible=visible)
-        self._prompt = f'\n{prefix}Error from previous action:\n{error}\n'
-
-
-class Observation(Shrinkable):
-    """Observation of the current step.
-
-    Contains the html, the accessibility tree and the error logs.
-    """
-
-    def __init__(self, obs, flags: Flags) -> None:
-        super().__init__()
-        self.flags = flags
-        self.obs = obs
-        self.html = HTML(obs[flags.html_type], visible=flags.use_html, prefix='## ')
-        self.ax_tree = AXTree(
-            obs['axtree_txt'],
-            visible=flags.use_ax_tree,
-            coord_type=flags.extract_coords,
-            prefix='## ',
-        )
-        self.error = Error(
-            obs['last_action_error'],
-            visible=flags.use_error_logs and obs['last_action_error'],
-            prefix='## ',
-        )
-
-    def shrink(self):
-        self.ax_tree.shrink()
-        self.html.shrink()
-
-    @property
-    def _prompt(self) -> str:  # type: ignore
-        return f'\n# Observation of current step:\n{self.html.prompt}{self.ax_tree.prompt}{self.error.prompt}\n\n'
-
-    def add_screenshot(self, prompt):
-        if self.flags.use_screenshot:
-            if isinstance(prompt, str):
-                prompt = [{'type': 'text', 'text': prompt}]
-            img_url = BrowserEnv.image_to_jpg_base64_url(
-                self.obs['screenshot'], add_data_prefix=True
-            )
-            prompt.append({'type': 'image_url', 'image_url': img_url})
-
-        return prompt
-
-
-class MacNote(PromptElement):
-    def __init__(self) -> None:
-        super().__init__(visible=platform.system() == 'Darwin')
-        self._prompt = '\nNote: you are on mac so you should use Meta instead of Control for Control+C etc.\n'
-
-
-class BeCautious(PromptElement):
-    def __init__(self, visible: bool = True) -> None:
-        super().__init__(visible=visible)
-        self._prompt = """\
-\nBe very cautious. Avoid submitting anything before verifying the effect of your
-actions. Take the time to explore the effect of safe actions first. For example
-you can fill a few elements of a form, but don't click submit before verifying
-that everything was filled correctly.\n"""
-
-
-class GoalInstructions(PromptElement):
-    def __init__(self, goal, visible: bool = True) -> None:
-        super().__init__(visible)
-        self._prompt = f"""\
-# Instructions
-Review the current state of the page and all other information to find the best
-possible next action to accomplish your goal. Your answer will be interpreted
-and executed by a program, make sure to follow the formatting instructions.
-
-## Goal:
-{goal}
-"""
-
-
-class ChatInstructions(PromptElement):
-    def __init__(self, chat_messages, visible: bool = True) -> None:
-        super().__init__(visible)
-        self._prompt = """\
-# Instructions
-
-You are a UI Assistant, your goal is to help the user perform tasks using a web browser. You can
-communicate with the user via a chat, in which the user gives you instructions and in which you
-can send back messages. You have access to a web browser that both you and the user can see,
-and with which only you can interact via specific commands.
-
-Review the instructions from the user, the current state of the page and all other information
-to find the best possible next action to accomplish your goal. Your answer will be interpreted
-and executed by a program, make sure to follow the formatting instructions.
-
-## Chat messages:
-
-"""
-        self._prompt += '\n'.join(
-            [
-                f"""\
- - [{msg['role']}], {msg['message']}"""
-                for msg in chat_messages
-            ]
-        )
-
-
-class SystemPrompt(PromptElement):
-    _prompt = """\
-You are an agent trying to solve a web task based on the content of the page and
-a user instructions. You can interact with the page and explore. Each time you
-submit an action it will be sent to the browser and you will receive a new page."""
-
-
-class MainPrompt(Shrinkable):
-    def __init__(
-        self,
-        obs_history,
-        actions,
-        memories,
-        thoughts,
-        flags: Flags,
-    ) -> None:
-        super().__init__()
-        self.flags = flags
-        self.history = History(obs_history, actions, memories, thoughts, flags)
-        if self.flags.enable_chat:
-            self.instructions: Union[ChatInstructions, GoalInstructions] = (
-                ChatInstructions(obs_history[-1]['chat_messages'])
-            )
-        else:
-            if (
-                'chat_messages' in obs_history[-1]
-                and sum(
-                    [msg['role'] == 'user' for msg in obs_history[-1]['chat_messages']]
-                )
-                > 1
-            ):
-                logging.warning(
-                    'Agent is in goal mode, but multiple user messages are present in the chat. Consider switching to `enable_chat=True`.'
-                )
-            self.instructions = GoalInstructions(obs_history[-1]['goal'])
-
-        self.obs = Observation(obs_history[-1], self.flags)
-        self.action_space = ActionSpace(self.flags)
-
-        self.think = Think(visible=flags.use_thinking)
-        self.memory = Memory(visible=flags.use_memory)
-
-    @property
-    def _prompt(self) -> str:  # type: ignore
-        prompt = f"""\
-{self.instructions.prompt}\
-{self.obs.prompt}\
-{self.history.prompt}\
-{self.action_space.prompt}\
-{self.think.prompt}\
-{self.memory.prompt}\
-"""
-
-        if self.flags.use_abstract_example:
-            prompt += f"""
-# Abstract Example
-
-Here is an abstract version of the answer with description of the content of
-each tag. Make sure you follow this structure, but replace the content with your
-answer:
-{self.think.abstract_ex}\
-{self.memory.abstract_ex}\
-{self.action_space.abstract_ex}\
-"""
-
-        if self.flags.use_concrete_example:
-            prompt += f"""
-# Concrete Example
-
-Here is a concrete example of how to format your answer.
-Make sure to follow the template with proper tags:
-{self.think.concrete_ex}\
-{self.memory.concrete_ex}\
-{self.action_space.concrete_ex}\
-"""
-        return self.obs.add_screenshot(prompt)
-
-    def shrink(self):
-        self.history.shrink()
-        self.obs.shrink()
-
-    def _parse_answer(self, text_answer):
-        ans_dict = {}
-        ans_dict.update(self.think._parse_answer(text_answer))
-        ans_dict.update(self.memory._parse_answer(text_answer))
-        ans_dict.update(self.action_space._parse_answer(text_answer))
-        return ans_dict
-
-
-class ActionSpace(PromptElement):
-    def __init__(self, flags: Flags) -> None:
-        super().__init__()
-        self.flags = flags
-        self.action_space = _get_action_space(flags)
-
-        self._prompt = (
-            f'# Action space:\n{self.action_space.describe()}{MacNote().prompt}\n'
-        )
-        self._abstract_ex = f"""
-<action>
-{self.action_space.example_action(abstract=True)}
-</action>
-"""
-        self._concrete_ex = f"""
-<action>
-{self.action_space.example_action(abstract=False)}
-</action>
-"""
-
-    def _parse_answer(self, text_answer):
-        ans_dict = parse_html_tags_raise(
-            text_answer, keys=['action'], merge_multiple=True
-        )
-
-        try:
-            # just check if action can be mapped to python code but keep action as is
-            # the environment will be responsible for mapping it to python
-            self.action_space.to_python_code(ans_dict['action'])
-        except Exception as e:
-            raise ParseError(
-                f'Error while parsing action\n: {e}\n'
-                'Make sure your answer is restricted to the allowed actions.'
-            )
-
-        return ans_dict
-
-
-def _get_action_space(flags: Flags) -> AbstractActionSet:
-    match flags.action_space:
-        case 'python':
-            action_space = PythonActionSet(strict=flags.is_strict)
-            if flags.multi_actions:
-                warn(
-                    f'Flag action_space={repr(flags.action_space)} incompatible with multi_actions={repr(flags.multi_actions)}.',
-                    stacklevel=2,
-                )
-            if flags.demo_mode != 'off':
-                warn(
-                    f'Flag action_space={repr(flags.action_space)} incompatible with demo_mode={repr(flags.demo_mode)}.',
-                    stacklevel=2,
-                )
-            return action_space
-        case 'bid':
-            action_subsets = ['chat', 'bid']
-        case 'coord':
-            action_subsets = ['chat', 'coord']
-        case 'bid+coord':
-            action_subsets = ['chat', 'bid', 'coord']
-        case 'bid+nav':
-            action_subsets = ['chat', 'bid', 'nav']
-        case 'coord+nav':
-            action_subsets = ['chat', 'coord', 'nav']
-        case 'bid+coord+nav':
-            action_subsets = ['chat', 'bid', 'coord', 'nav']
-        case _:
-            raise NotImplementedError(
-                f'Unknown action_space {repr(flags.action_space)}'
-            )
-
-    action_space = HighLevelActionSet(
-        subsets=action_subsets,
-        multiaction=flags.multi_actions,
-        strict=flags.is_strict,
-        demo_mode=flags.demo_mode,
-    )
-
-    return action_space
-
-
-class Memory(PromptElement):
-    _prompt = ''  # provided in the abstract and concrete examples
-
-    _abstract_ex = """
-<memory>
-Write down anything you need to remember for next steps. You will be presented
-with the list of previous memories and past actions.
-</memory>
-"""
-
-    _concrete_ex = """
-<memory>
-I clicked on bid 32 to activate tab 2. The accessibility tree should mention
-focusable for elements of the form at next step.
-</memory>
-"""
-
-    def _parse_answer(self, text_answer):
-        return parse_html_tags_raise(
-            text_answer, optional_keys=['memory'], merge_multiple=True
-        )
-
-
-class Think(PromptElement):
-    _prompt = ''
-
-    _abstract_ex = """
-<think>
-Think step by step. If you need to make calculations such as coordinates, write them here. Describe the effect
-that your previous action had on the current content of the page.
-</think>
-"""
-    _concrete_ex = """
-<think>
-My memory says that I filled the first name and last name, but I can't see any
-content in the form. I need to explore different ways to fill the form. Perhaps
-the form is not visible yet or some fields are disabled. I need to replan.
-</think>
-"""
-
-    def _parse_answer(self, text_answer):
-        return parse_html_tags_raise(
-            text_answer, optional_keys=['think'], merge_multiple=True
-        )
-
-
-def diff(previous, new):
-    """Return a string showing the difference between original and new.
-
-    If the difference is above diff_threshold, return the diff string.
-    """
-    if previous == new:
-        return 'Identical', []
-
-    if len(previous) == 0 or previous is None:
-        return 'previous is empty', []
-
-    diff_gen = difflib.ndiff(previous.splitlines(), new.splitlines())
-
-    diff_lines = []
-    plus_count = 0
-    minus_count = 0
-    for line in diff_gen:
-        if line.strip().startswith('+'):
-            diff_lines.append(line)
-            plus_count += 1
-        elif line.strip().startswith('-'):
-            diff_lines.append(line)
-            minus_count += 1
-        else:
-            continue
-
-    header = f'{plus_count} lines added and {minus_count} lines removed:'
-
-    return header, diff_lines
-
-
-class Diff(Shrinkable):
-    def __init__(
-        self, previous, new, prefix='', max_line_diff=20, shrink_speed=2, visible=True
-    ) -> None:
-        super().__init__(visible=visible)
-        self.max_line_diff = max_line_diff
-        self.header, self.diff_lines = diff(previous, new)
-        self.shrink_speed = shrink_speed
-        self.prefix = prefix
-
-    def shrink(self):
-        self.max_line_diff -= self.shrink_speed
-        self.max_line_diff = max(1, self.max_line_diff)
-
-    @property
-    def _prompt(self) -> str:  # type: ignore
-        diff_str = '\n'.join(self.diff_lines[: self.max_line_diff])
-        if len(self.diff_lines) > self.max_line_diff:
-            original_count = len(self.diff_lines)
-            diff_str = f'{diff_str}\nDiff truncated, {original_count - self.max_line_diff} changes now shown.'
-        return f'{self.prefix}{self.header}\n{diff_str}\n'
-
-
-class HistoryStep(Shrinkable):
-    def __init__(
-        self, previous_obs, current_obs, action, memory, flags: Flags, shrink_speed=1
-    ) -> None:
-        super().__init__()
-        self.html_diff = Diff(
-            previous_obs[flags.html_type],
-            current_obs[flags.html_type],
-            prefix='\n### HTML diff:\n',
-            shrink_speed=shrink_speed,
-            visible=lambda: flags.use_html and flags.use_diff,
-        )
-        self.ax_tree_diff = Diff(
-            previous_obs['axtree_txt'],
-            current_obs['axtree_txt'],
-            prefix='\n### Accessibility tree diff:\n',
-            shrink_speed=shrink_speed,
-            visible=lambda: flags.use_ax_tree and flags.use_diff,
-        )
-        self.error = Error(
-            current_obs['last_action_error'],
-            visible=(
-                flags.use_error_logs
-                and current_obs['last_action_error']
-                and flags.use_past_error_logs
-            ),
-            prefix='### ',
-        )
-        self.shrink_speed = shrink_speed
-        self.action = action
-        self.memory = memory
-        self.flags = flags
-
-    def shrink(self):
-        super().shrink()
-        self.html_diff.shrink()
-        self.ax_tree_diff.shrink()
-
-    @property
-    def _prompt(self) -> str:  # type: ignore
-        prompt = ''
-
-        if self.flags.use_action_history:
-            prompt += f'\n### Action:\n{self.action}\n'
-
-        prompt += (
-            f'{self.error.prompt}{self.html_diff.prompt}{self.ax_tree_diff.prompt}'
-        )
-
-        if self.flags.use_memory and self.memory is not None:
-            prompt += f'\n### Memory:\n{self.memory}\n'
-
-        return prompt
-
-
-class History(Shrinkable):
-    def __init__(
-        self, history_obs, actions, memories, thoughts, flags: Flags, shrink_speed=1
-    ) -> None:
-        super().__init__(visible=flags.use_history)
-        assert len(history_obs) == len(actions) + 1
-        assert len(history_obs) == len(memories) + 1
-
-        self.shrink_speed = shrink_speed
-        self.history_steps: list[HistoryStep] = []
-
-        for i in range(1, len(history_obs)):
-            self.history_steps.append(
-                HistoryStep(
-                    history_obs[i - 1],
-                    history_obs[i],
-                    actions[i - 1],
-                    memories[i - 1],
-                    flags,
-                )
-            )
-
-    def shrink(self):
-        """Shrink individual steps"""
-        # TODO set the shrink speed of older steps to be higher
-        super().shrink()
-        for step in self.history_steps:
-            step.shrink()
-
-    @property
-    def _prompt(self):
-        prompts = ['# History of interaction with the task:\n']
-        for i, step in enumerate(self.history_steps):
-            prompts.append(f'## step {i}')
-            prompts.append(step.prompt)
-        return '\n'.join(prompts) + '\n'
-
-
-if __name__ == '__main__':
-    html_template = """
-    <html>
-    <body>
-    <div>
-    Hello World.
-    Step {}.
-    </div>
-    </body>
-    </html>
-    """
-
-    OBS_HISTORY = [
-        {
-            'goal': 'do this and that',
-            'pruned_html': html_template.format(1),
-            'axtree_txt': '[1] Click me',
-            'last_action_error': '',
-        },
-        {
-            'goal': 'do this and that',
-            'pruned_html': html_template.format(2),
-            'axtree_txt': '[1] Click me',
-            'last_action_error': '',
-        },
-        {
-            'goal': 'do this and that',
-            'pruned_html': html_template.format(3),
-            'axtree_txt': '[1] Click me',
-            'last_action_error': 'Hey, there is an error now',
-        },
-    ]
-    ACTIONS = ["click('41')", "click('42')"]
-    MEMORIES = ['memory A', 'memory B']
-    THOUGHTS = ['thought A', 'thought B']
-
-    flags = Flags(
-        use_html=True,
-        use_ax_tree=True,
-        use_thinking=True,
-        use_error_logs=True,
-        use_past_error_logs=True,
-        use_history=True,
-        use_action_history=True,
-        use_memory=True,
-        use_diff=True,
-        html_type='pruned_html',
-        use_concrete_example=True,
-        use_abstract_example=True,
-        use_screenshot=False,
-        multi_actions=True,
-    )
-
-    print(
-        MainPrompt(
-            obs_history=OBS_HISTORY,
-            actions=ACTIONS,
-            memories=MEMORIES,
-            thoughts=THOUGHTS,
-            flags=flags,
-        ).prompt
-    )

openhands/agenthub/codeact_agent/codeact_agent.py

@@ -166,6 +166,9 @@ class CodeActAgent(Agent):
 
             # Add the LLM message (assistant) that initiated the tool calls
             # (overwrites any previous message with the same response_id)
+            logger.debug(
+                f'Tool calls type: {type(assistant_msg.tool_calls)}, value: {assistant_msg.tool_calls}'
+            )
             pending_tool_call_action_messages[llm_response.id] = Message(
                 role=assistant_msg.role,
                 # tool call content SHOULD BE a string

openhands/agenthub/codeact_swe_agent/README.md

@@ -1,7 +0,0 @@
-# CodeAct (SWE Edit Specialized)
-
-This agent is an adaptation of the original [SWE Agent](https://swe-agent.com/) based on CodeAct using the `agentskills` library of OpenHands.
-
-Its intended use is **solving GitHub issues**.
-
-It removes web-browsing and GitHub capability from the original CodeAct agent to avoid confusion to the agent.

openhands/agenthub/codeact_swe_agent/__init__.py

@@ -1,4 +0,0 @@
-from openhands.agenthub.codeact_swe_agent.codeact_swe_agent import CodeActSWEAgent
-from openhands.controller.agent import Agent
-
-Agent.register('CodeActSWEAgent', CodeActSWEAgent)

openhands/agenthub/codeact_swe_agent/action_parser.py

@@ -1,110 +0,0 @@
-import re
-
-from openhands.controller.action_parser import ActionParser
-from openhands.events.action import (
-    Action,
-    AgentFinishAction,
-    CmdRunAction,
-    IPythonRunCellAction,
-    MessageAction,
-)
-
-
-class CodeActSWEActionParserFinish(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 CodeActSWEActionParserCmdRun(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()
-        return CmdRunAction(command=command_group, thought=thought)
-
-
-class CodeActSWEActionParserIPythonRunCell(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 CodeActSWEActionParserMessage(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)

openhands/agenthub/codeact_swe_agent/codeact_swe_agent.py

@@ -1,224 +0,0 @@
-from openhands.agenthub.codeact_swe_agent.prompt import (
-    COMMAND_DOCS,
-    SWE_EXAMPLE,
-    SYSTEM_PREFIX,
-    SYSTEM_SUFFIX,
-)
-from openhands.agenthub.codeact_swe_agent.response_parser import (
-    CodeActSWEResponseParser,
-)
-from openhands.controller.agent import Agent
-from openhands.controller.state.state import State
-from openhands.core.config import AgentConfig
-from openhands.core.message import ImageContent, Message, TextContent
-from openhands.events.action import (
-    Action,
-    AgentFinishAction,
-    CmdRunAction,
-    IPythonRunCellAction,
-    MessageAction,
-)
-from openhands.events.observation import (
-    CmdOutputObservation,
-    IPythonRunCellObservation,
-)
-from openhands.events.observation.error import ErrorObservation
-from openhands.events.observation.observation import Observation
-from openhands.events.serialization.event import truncate_content
-from openhands.llm.llm import LLM
-from openhands.runtime.plugins import (
-    AgentSkillsRequirement,
-    JupyterRequirement,
-    PluginRequirement,
-)
-
-
-def get_system_message() -> str:
-    return f'{SYSTEM_PREFIX}\n\n{COMMAND_DOCS}\n\n{SYSTEM_SUFFIX}'
-
-
-def get_in_context_example() -> str:
-    return SWE_EXAMPLE
-
-
-class CodeActSWEAgent(Agent):
-    VERSION = '1.6'
-    """
-    This agent is an adaptation of the original [SWE Agent](https://swe-agent.com/) based on CodeAct 1.5 using the `agentskills` library of OpenHands.
-
-    It is intended use is **solving Github issues**.
-
-    It removes web-browsing and Github capability from the original CodeAct agent to avoid confusion to the agent.
-    """
-
-    sandbox_plugins: list[PluginRequirement] = [
-        # NOTE: AgentSkillsRequirement need to go before JupyterRequirement, since
-        # AgentSkillsRequirement provides a lot of Python functions,
-        # and it needs to be initialized before Jupyter for Jupyter to use those functions.
-        AgentSkillsRequirement(),
-        JupyterRequirement(),
-    ]
-
-    system_message: str = get_system_message()
-    in_context_example: str = f"Here is an example of how you can interact with the environment for task solving:\n{get_in_context_example()}\n\nNOW, LET'S START!"
-
-    response_parser = CodeActSWEResponseParser()
-
-    def __init__(
-        self,
-        llm: LLM,
-        config: AgentConfig,
-    ) -> None:
-        """Initializes a new instance of the CodeActSWEAgent class.
-
-        Parameters:
-        - llm (LLM): The llm to be used by this agent
-        """
-        super().__init__(llm, config)
-        self.reset()
-
-    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, MessageAction):
-            return action.content
-        return ''
-
-    def get_action_message(self, action: Action) -> Message | None:
-        if isinstance(action, (CmdRunAction, IPythonRunCellAction, MessageAction)):
-            content = [TextContent(text=self.action_to_str(action))]
-
-            if (
-                self.llm.vision_is_active()
-                and isinstance(action, MessageAction)
-                and action.image_urls
-            ):
-                content.append(ImageContent(image_urls=action.image_urls))
-
-            return Message(
-                role='user' if action.source == 'user' else 'assistant', content=content
-            )
-
-        return None
-
-    def get_observation_message(self, obs: Observation) -> Message | None:
-        max_message_chars = self.llm.config.max_message_chars
-        if isinstance(obs, CmdOutputObservation):
-            text = 'OBSERVATION:\n' + truncate_content(
-                obs.content + obs.interpreter_details, max_message_chars
-            )
-            text += (
-                f'\n[Command {obs.command_id} finished with exit code {obs.exit_code}]'
-            )
-            return Message(role='user', content=[TextContent(text=text)])
-        elif isinstance(obs, IPythonRunCellObservation):
-            text = 'OBSERVATION:\n' + obs.content
-            # replace base64 images with a placeholder
-            splitted = text.split('\n')
-            for i, line in enumerate(splitted):
-                if '![image](data:image/png;base64,' in line:
-                    splitted[i] = (
-                        '![image](data:image/png;base64, ...) already displayed to user'
-                    )
-            text = '\n'.join(splitted)
-            text = truncate_content(text, max_message_chars)
-            return Message(role='user', content=[TextContent(text=text)])
-        elif isinstance(obs, ErrorObservation):
-            text = 'OBSERVATION:\n' + truncate_content(obs.content, max_message_chars)
-            text += '\n[Error occurred in processing last action]'
-            return Message(role='user', content=[TextContent(text=text)])
-        else:
-            # If an observation message is not returned, it will cause an error
-            # when the LLM tries to return the next message
-            raise ValueError(f'Unknown observation type: {type(obs)}')
-
-    def reset(self) -> None:
-        """Resets the CodeAct Agent."""
-        super().reset()
-
-    def step(self, state: State) -> Action:
-        """Performs one step using the CodeAct Agent.
-        This includes gathering info on previous steps and prompting the model to make a command to execute.
-
-        Parameters:
-        - state (State): used to get updated info and background commands
-
-        Returns:
-        - CmdRunAction(command) - bash command to run
-        - IPythonRunCellAction(code) - IPython code to run
-        - MessageAction(content) - Message action to run (e.g. ask for clarification)
-        - AgentFinishAction() - end the interaction
-        """
-        # if we're done, go back
-        last_user_message = state.get_last_user_message()
-        if last_user_message and last_user_message.content.strip() == '/exit':
-            return AgentFinishAction()
-
-        # prepare what we want to send to the LLM
-        messages: list[Message] = self._get_messages(state)
-        response = self.llm.completion(
-            messages=self.llm.format_messages_for_llm(messages),
-            stop=[
-                '</execute_ipython>',
-                '</execute_bash>',
-            ],
-        )
-
-        return self.response_parser.parse(response)
-
-    def _get_messages(self, state: State) -> list[Message]:
-        messages: list[Message] = [
-            Message(role='system', content=[TextContent(text=self.system_message)]),
-            Message(role='user', content=[TextContent(text=self.in_context_example)]),
-        ]
-
-        for event in state.history:
-            # create a regular message from an event
-            if isinstance(event, Action):
-                message = self.get_action_message(event)
-            elif isinstance(event, Observation):
-                message = self.get_observation_message(event)
-            else:
-                raise ValueError(f'Unknown event type: {type(event)}')
-
-            # add regular message
-            if message:
-                # handle error if the message is the SAME role as the previous message
-                # litellm.exceptions.BadRequestError: litellm.BadRequestError: OpenAIException - Error code: 400 - {'detail': 'Only supports u/a/u/a/u...'}
-                # there should not have two consecutive messages from the same role
-                if messages and messages[-1].role == message.role:
-                    messages[-1].content.extend(message.content)
-                else:
-                    messages.append(message)
-
-        # the latest user message is important:
-        # we want to remind the agent of the environment constraints
-        latest_user_message = next(
-            (m for m in reversed(messages) if m.role == 'user'), None
-        )
-
-        # Get the last user text inside content
-        if latest_user_message:
-            latest_user_message_text = next(
-                (
-                    t
-                    for t in reversed(latest_user_message.content)
-                    if isinstance(t, TextContent)
-                )
-            )
-            # add a reminder to the prompt
-            reminder_text = f'\n\nENVIRONMENT REMINDER: You have {state.max_iterations - state.iteration} turns left to complete the task. When finished reply with <finish></finish>.'
-
-            if latest_user_message_text:
-                latest_user_message_text.text = (
-                    latest_user_message_text.text + reminder_text
-                )
-            else:
-                latest_user_message_text = TextContent(text=reminder_text)
-                latest_user_message.content.append(latest_user_message_text)
-
-        return messages

openhands/agenthub/codeact_swe_agent/prompt.py

@@ -1,455 +0,0 @@
-from openhands.runtime.plugins import AgentSkillsRequirement
-
-_AGENT_SKILLS_DOCS = AgentSkillsRequirement.documentation
-
-COMMAND_DOCS = (
-    '\nApart from the standard Python library, the assistant can also use the following functions (already imported) in <execute_ipython> environment:\n'
-    f'{_AGENT_SKILLS_DOCS}'
-    "Please note that THE `edit_file` FUNCTION REQUIRES PROPER INDENTATION. If the assistant would like to add the line '        print(x)', it must fully write that out, with all those spaces before the code! Indentation is important and code that is not indented correctly will fail and require fixing before it can be run."
-)
-
-# ======= SYSTEM MESSAGE =======
-MINIMAL_SYSTEM_PREFIX = """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
-The assistant can interact with an interactive Python (Jupyter Notebook) environment and receive the corresponding output when needed. The code should be enclosed using "<execute_ipython>" tag, for example:
-<execute_ipython>
-print("Hello World!")
-</execute_ipython>
-The assistant can execute bash commands on behalf of the user by wrapping them with <execute_bash> and </execute_bash>.
-For example, you can list the files in the current directory by <execute_bash> ls </execute_bash>.
-"""
-
-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."""
-
-SYSTEM_PREFIX = MINIMAL_SYSTEM_PREFIX + PIP_INSTALL_PREFIX
-
-SYSTEM_SUFFIX = """The assistant's response should be concise.
-The assistant should include ONLY ONE <execute_ipython> or <execute_bash> in every one of the responses, unless the assistant is finished with the task or need more input or action from the user in order to proceed.
-IMPORTANT: Whenever possible, execute the code for the user using <execute_ipython> or <execute_bash> instead of providing it.
-"""
-
-SWE_EXAMPLE = """
---- START OF EXAMPLE ---
-
-USER: We are currently solving the following issue within our repository. Here is the issue text:
---- BEGIN ISSUE ---
-TimeDelta serialization precision
-Hi there!
-
-I just found quite strange behaviour of `TimeDelta` field serialization
-
-```python3
-from marshmallow.fields import TimeDelta
-from datetime import timedelta
-
-td_field = TimeDelta(precision="milliseconds")
-
-obj = dict()
-obj["td_field"] = timedelta(milliseconds=345)
-
-print(td_field.serialize("td_field", obj))
-```
-
-Output of this snippet is `344`, but it seems that `345` is correct.
-
-Looks like a rounding issue here: https://github.com/marshmallow-code/marshmallow/blob/dev/src/marshmallow/fields.py#L1474
---- END ISSUE ---
-
-[Current directory: /workspace/marshmallow-code__marshmallow]
-
-ASSISTANT:
-Let's first start by reproducing the results of the issue. The issue includes some example code for reproduction, which we can use. We'll create a new file called `reproduce.py` and paste the example code into it.
-<execute_ipython>
-create_file('/workspace/marshmallow-code__marshmallow/reproduce.py')
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[File: /workspace/marshmallow-code__marshmallow/reproduce.py (1 lines total)]
-1|
-[File /workspace/marshmallow-code__marshmallow/reproduce.py created.]
-
-ASSISTANT:
-Now let's paste in the example code from the issue.
-<execute_ipython>
-EDITED_CODE = \"\"\"from marshmallow.fields import TimeDelta
-from datetime import timedelta
-
-td_field = TimeDelta(precision="milliseconds")
-
-obj = dict()
-obj["td_field"] = timedelta(milliseconds=345)
-
-print(td_field.serialize("td_field", obj))
-\"\"\"
-edit_file(start=1, end=1, content=EDITED_CODE)
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[File: /workspace/marshmallow-code__marshmallow/reproduce.py (9 lines total)]
-1|from marshmallow.fields import TimeDelta
-2|from datetime import timedelta
-3|
-4|td_field = TimeDelta(precision="milliseconds")
-5|
-6|obj = dict()
-7|obj["td_field"] = timedelta(milliseconds=345)
-8|
-9|print(td_field.serialize("td_field", obj))
-[File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
-
-ASSISTANT:
-Now let's run the code to see if we see the same output as the issue.
-<execute_bash>
-python reproduce.py
-</execute_bash>
-
-USER:
-OBSERVATION:
-344
-
-ASSISTANT:
-We are indeed seeing the same output as the issue. The issue suggests that we should look at line 1474 of the `fields.py` file to see if there is a rounding issue. Let's open the `fields.py` file and navigate to line 1474 to see the relevant code. First we should find the `fields.py` file in the repository. It is likely to be in the `src/marshmallow` directory, but we should check to be sure.
-<execute_bash>
-ls -F
-</execute_bash>
-
-USER:
-OBSERVATION:
-AUTHORS.rst
-CHANGELOG.rst
-CODE_OF_CONDUCT.md
-CONTRIBUTING.rst
-LICENSE
-MANIFEST.in
-NOTICE
-README.rst
-RELEASING.md
-azure-pipelines.yml
-docs/
-examples/
-performance/
-pyproject.toml
-reproduce.py
-setup.cfg
-setup.py
-src/
-tests/
-tox.ini
-
-ASSISTANT:
-It looks like the `src` directory is present, which suggests that the `fields.py` file is likely to be in the `src` directory. Let's use find_file to see where it is.
-<execute_ipython>
-find_file("fields.py", "/workspace/marshmallow-code__marshmallow/src")
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[Found 1 matches for "fields.py" in /workspace/marshmallow-code__marshmallow/src]
-/workspace/marshmallow-code__marshmallow/src/marshmallow/fields.py
-
-ASSISTANT:
-It looks like the `fields.py` file is present in the `./src/marshmallow/` directory. The issue also points to a specific URL with line number 1474. We should navigate to that line in fields.py to see the relevant code for the `TimeDelta` serialization.
-<execute_ipython>
-open_file("/workspace/marshmallow-code__marshmallow/src/marshmallow/fields.py", 1474)
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[File: /workspace/marshmallow-code__marshmallow/src/marshmallow/fields.py (1997 lines total)]
-(1458 more lines above)
-1459|            self.WEEKS,
-1460|        )
-1461|
-1462|        if precision not in units:
-1463|            msg = 'The precision must be {} or "{}".'.format(
-1464|                ", ".join([f'"{each}"' for each in units[:-1]]), units[-1]
-1465|            )
-1466|            raise ValueError(msg)
-1467|
-1468|        self.precision = precision
-1469|        super().__init__(**kwargs)
-1470|
-1471|    def _serialize(self, value, attr, obj, **kwargs):
-1472|        if value is None:
-1473|            return None
-1474|        base_unit = dt.timedelta(**{self.precision: 1})
-1475|        return int(value.total_seconds() / base_unit.total_seconds())
-1476|
-1477|    def _deserialize(self, value, attr, data, **kwargs):
-1478|        try:
-1479|            value = int(value)
-1480|        except (TypeError, ValueError) as error:
-1481|            raise self.make_error("invalid") from error
-1482|
-1483|        kwargs = {self.precision: value}
-1484|
-1485|        try:
-1486|            return dt.timedelta(**kwargs)
-1487|        except OverflowError as error:
-1488|            raise self.make_error("invalid") from error
-1489|
-1490|
-1491|class Mapping(Field):
-1492|    \"\"\"An abstract class for objects with key-value pairs.
-1493|
-1494|    :param keys: A field class or instance for dict keys.
-1495|    :param values: A field class or instance for dict values.
-1496|    :param kwargs: The same keyword arguments that :class:`Field` receives.
-1497|
-1498|    .. note::
-1499|        When the structure of nested data is not known, you may omit the
-1500|        `keys` and `values` arguments to prevent content validation.
-1501|
-1502|    .. versionadded:: 3.0.0rc4
-1503|    \"\"\"
-1504|
-1505|    mapping_type = dict
-1506|
-1507|    #: Default error messages.
-1508|    default_error_messages = {"invalid": "Not a valid mapping type."}
-1509|
-1510|    def __init__(
-1511|        self,
-1512|        keys: typing.Optional[typing.Union[Field, type]] = None,
-1513|        values: typing.Optional[typing.Union[Field, type]] = None,
-1514|        **kwargs,
-1515|    ):
-1516|        super().__init__(**kwargs)
-1517|        if keys is None:
-1518|            self.key_field = None
-1519|        else:
-1520|            try:
-1521|                self.key_field = resolve_field_instance(keys)
-1522|            except FieldInstanceResolutionError as error:
-1523|                raise ValueError(
-1524|                    '"keys" must be a subclass or instance of '
-1525|                    "marshmallow.base.FieldABC."
-1526|                ) from error
-1527|
-1528|        if values is None:
-1529|            self.value_field = None
-1530|        else:
-1531|            try:
-1532|                self.value_field = resolve_field_instance(values)
-1533|            except FieldInstanceResolutionError as error:
-1534|                raise ValueError(
-1535|                    '"values" must be a subclass or instance of '
-1536|                    "marshmallow.base.FieldABC."
-1537|                ) from error
-1538|            if isinstance(self.value_field, Nested):
-1539|                self.only = self.value_field.only
-1540|                self.exclude = self.value_field.exclude
-1541|
-1542|    def _bind_to_schema(self, field_name, schema):
-1543|        super()._bind_to_schema(field_name, schema)
-1544|        if self.value_field:
-1545|            self.value_field = copy.deepcopy(self.value_field)
-1546|            self.value_field._bind_to_schema(field_name, self)
-1547|        if isinstance(self.value_field, Nested):
-1548|            self.value_field.only = self.only
-1549|            self.value_field.exclude = self.exclude
-1550|        if self.key_field:
-1551|            self.key_field = copy.deepcopy(self.key_field)
-1552|            self.key_field._bind_to_schema(field_name, self)
-1553|
-1554|    def _serialize(self, value, attr, obj, **kwargs):
-1555|        if value is None:
-1556|            return None
-1557|        if not self.value_field and not self.key_field:
-1558|            return self.mapping_type(value)
-(439 more lines below)
-
-ASSISTANT:
-We are now looking at the relevant section of the `fields.py` file where the `TimeDelta` serialization occurs. The issue suggests that there is a rounding problem near line 1474. The current implementation uses integer division, which truncates the decimal part and can lead to incorrect rounding on line 1475. To fix this issue, we should ensure that the division results in a float, and then round the result to the nearest integer before converting it to an int. This should preserve the milliseconds precision as expected. Let's make the necessary edit to the code.
-<execute_ipython>
-edit_file(start=1475, end=1475, content="return int(round(value.total_seconds() / base_unit.total_seconds()))  # round to nearest int")
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[Your proposed edit has introduced new syntax error(s). Please understand the errors and retry your edit command.]
-
-ERRORS:
-- E999 IndentationError: unexpected indent
-
-[This is how your edit would have looked if applied]
--------------------------------------------------
-[File: /marshmallow-code__marshmallow/src/marshmallow/fields.py (1997 lines total)]
-(1468 more lines above)
-1469|        super().__init__(**kwargs)
-1470|
-1471|    def _serialize(self, value, attr, obj, **kwargs):
-1472|        if value is None:
-1473|            return None
-1474|        base_unit = dt.timedelta(**{self.precision: 1})
-1475|return int(round(value.total_seconds() / base_unit.total_seconds()))  # round to nearest int
-1476|
-1477|    def _deserialize(self, value, attr, data, **kwargs):
-1478|        try:
-1479|            value = int(value)
-(518 more lines below)
--------------------------------------------------
-
-[This is the original code before your edit]
--------------------------------------------------
-[File: /marshmallow-code__marshmallow/src/marshmallow/fields.py (1997 lines total)]
-(1469 more lines above)
-1470|
-1471|    def _serialize(self, value, attr, obj, **kwargs):
-1472|        if value is None:
-1473|            return None
-1474|        base_unit = dt.timedelta(**{self.precision: 1})
-1475|        return int(value.total_seconds() / base_unit.total_seconds())
-1476|
-1477|    def _deserialize(self, value, attr, data, **kwargs):
-1478|        try:
-1479|            value = int(value)
-1480|        except (TypeError, ValueError) as error:
-(517 more lines below)
--------------------------------------------------
-Your changes have NOT been applied. Please fix your edit command and try again.
-You either need to 1) Specify the correct start/end line arguments or 2) Correct your edit code.
-DO NOT re-run the same failed edit command. Running it again will lead to the same error.
-
-ASSISTANT:
-My edit command did not use the proper indentation, I will fix my syntax in this follow up edit command.
-<execute_ipython>
-EDITED_CODE="        return int(round(value.total_seconds() / base_unit.total_seconds()))  # round to nearest int"
-edit_file(start=1475, end=1475, content=EDITED_CODE)
-</execute_ipython>
-
-USER:
-OBSERVATION:
-[File: /marshmallow-code__marshmallow/src/marshmallow/fields.py (1997 lines total)]
-(1424 more lines above)
-1425|
-1426|    :param precision: Influences how the integer is interpreted during
-1427|        (de)serialization. Must be 'days', 'seconds', 'microseconds',
-1428|        'milliseconds', 'minutes', 'hours' or 'weeks'.
-1429|    :param kwargs: The same keyword arguments that :class:`Field` receives.
-1430|
-1431|    .. versionchanged:: 2.0.0
-1432|        Always serializes to an integer value to avoid rounding errors.
-1433|        Add `precision` parameter.
-1434|    \"\"\"
-1435|
-1436|    DAYS = "days"
-1437|    SECONDS = "seconds"
-1438|    MICROSECONDS = "microseconds"
-1439|    MILLISECONDS = "milliseconds"
-1440|    MINUTES = "minutes"
-1441|    HOURS = "hours"
-1442|    WEEKS = "weeks"
-1443|
-1444|    #: Default error messages.
-1445|    default_error_messages = {
-1446|        "invalid": "Not a valid period of time.",
-1447|        "format": "{input!r} cannot be formatted as a timedelta.",
-1448|    }
-1449|
-1450|    def __init__(self, precision: str = SECONDS, **kwargs):
-1451|        precision = precision.lower()
-1452|        units = (
-1453|            self.DAYS,
-1454|            self.SECONDS,
-1455|            self.MICROSECONDS,
-1456|            self.MILLISECONDS,
-1457|            self.MINUTES,
-1458|            self.HOURS,
-1459|            self.WEEKS,
-1460|        )
-1461|
-1462|        if precision not in units:
-1463|            msg = 'The precision must be {} or "{}".'.format(
-1464|                ", ".join([f'"{each}"' for each in units[:-1]]), units[-1]
-1465|            )
-1466|            raise ValueError(msg)
-1467|
-1468|        self.precision = precision
-1469|        super().__init__(**kwargs)
-1470|
-1471|    def _serialize(self, value, attr, obj, **kwargs):
-1472|        if value is None:
-1473|            return None
-1474|        base_unit = dt.timedelta(**{self.precision: 1})
-1475|        return int(round(value.total_seconds() / base_unit.total_seconds()))  # round to nearest int
-1476|
-1477|    def _deserialize(self, value, attr, data, **kwargs):
-1478|        try:
-1479|            value = int(value)
-1480|        except (TypeError, ValueError) as error:
-1481|            raise self.make_error("invalid") from error
-1482|
-1483|        kwargs = {self.precision: value}
-1484|
-1485|        try:
-1486|            return dt.timedelta(**kwargs)
-1487|        except OverflowError as error:
-1488|            raise self.make_error("invalid") from error
-1489|
-1490|
-1491|class Mapping(Field):
-1492|    \"\"\"An abstract class for objects with key-value pairs.
-1493|
-1494|    :param keys: A field class or instance for dict keys.
-1495|    :param values: A field class or instance for dict values.
-1496|    :param kwargs: The same keyword arguments that :class:`Field` receives.
-1497|
-1498|    .. note::
-1499|        When the structure of nested data is not known, you may omit the
-1500|        `keys` and `values` arguments to prevent content validation.
-1501|
-1502|    .. versionadded:: 3.0.0rc4
-1503|    \"\"\"
-1504|
-1505|    mapping_type = dict
-1506|
-1507|    #: Default error messages.
-1508|    default_error_messages = {"invalid": "Not a valid mapping type."}
-1509|
-1510|    def __init__(
-1511|        self,
-1512|        keys: typing.Optional[typing.Union[Field, type]] = None,
-1513|        values: typing.Optional[typing.Union[Field, type]] = None,
-1514|        **kwargs,
-1515|    ):
-1516|        super().__init__(**kwargs)
-1517|        if keys is None:
-1518|            self.key_field = None
-1519|        else:
-1520|            try:
-1521|                self.key_field = resolve_field_instance(keys)
-1522|            except FieldInstanceResolutionError as error:
-1523|                raise ValueError(
-1524|                    '"keys" must be a subclass or instance of '
-(473 more lines below)
-[File updated. Please review the changes and make sure they are correct (correct indentation, no duplicate lines, etc). Edit the file again if necessary.]
-
-ASSISTANT:
-The code has been updated to use the `round` function, which should fix the rounding issue. Before submitting the changes, it would be prudent to run the reproduce.py code again to ensure that this change has the desired effect. I see that "Current directory" is still `/marshmallow-code__marshmallow`, so we can just run `reproduce.py` directly.
-<execute_bash>
-python reproduce.py
-</execute_bash>
-
-USER:
-OBSERVATION:
-345
-
-ASSISTANT:
-The output has changed from 344 to 345, which suggests that the rounding issue has been fixed. Let's remove the reproduce.py file since it is no longer needed.
-<execute_bash>
-rm reproduce.py
-</execute_bash>
-
-USER:
-OBSERVATION:
-
-ASSISTANT:
-rm doesn't have any output when it deletes successfully, so that must have worked. Now that we have fixed the issue, we can exit the current task.
-<execute_bash>
-exit
-</execute_bash>
-
---- END OF EXAMPLE ---
-"""