Merge branch 'main' into rb/fix-client-loader

.github/workflows/ghcr-build.yml

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

.github/workflows/openhands-resolver.yml

@@ -1,267 +1,15 @@
-name: Auto-Fix Tagged Issue with OpenHands
+name: Resolve Issues with OpenHands
 
 on:
-  workflow_call:
-    inputs:
-      max_iterations:
-        required: false
-        type: number
-        default: 50
-      macro:
-        required: false
-        type: string
-        default: "@openhands-agent"
-    secrets:
-      LLM_MODEL:
-        required: true
-      LLM_API_KEY:
-        required: true
-      LLM_BASE_URL:
-        required: false
-      PAT_TOKEN:
-        required: true
-      PAT_USERNAME:
-        required: true
-
   issues:
     types: [labeled]
   pull_request:
     types: [labeled]
-  issue_comment:
-    types: [created]
-  pull_request_review_comment:
-    types: [created]
-  pull_request_review:
-    types: [submitted]
-
-permissions:
-  contents: write
-  pull-requests: write
-  issues: write
 
 jobs:
-
-  auto-fix:
-    if: |
-      github.event_name == 'workflow_call' ||
-      github.event.label.name == 'fix-me' ||
-      github.event.label.name == 'fix-me-experimental' ||
-
-      (
-        ((github.event_name == 'issue_comment' || github.event_name == 'pull_request_review_comment') &&
-        startsWith(github.event.comment.body, inputs.macro || '@openhands-agent') &&
-        (github.event.comment.author_association == 'OWNER' || github.event.comment.author_association == 'COLLABORATOR' || github.event.comment.author_association == 'MEMBER')
-        ) ||
-
-        (github.event_name == 'pull_request_review' &&
-        startsWith(github.event.review.body, inputs.macro || '@openhands-agent') &&
-        (github.event.review.author_association == 'OWNER' || github.event.review.author_association == 'COLLABORATOR' || github.event.review.author_association == 'MEMBER')
-        )
-      )
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-
-      - name: Get latest versions and create requirements.txt
-        run: |
-          python -m pip index versions openhands-ai > openhands_versions.txt
-          OPENHANDS_VERSION=$(head -n 1 openhands_versions.txt | awk '{print $2}' | tr -d '()')
-          echo "openhands-ai==${OPENHANDS_VERSION}" >> requirements.txt
-          cat requirements.txt
-
-      - name: Cache pip dependencies
-        if: github.event.label.name != 'fix-me-experimental'
-        uses: actions/cache@v3
-        with:
-          path: ${{ env.pythonLocation }}/lib/python3.12/site-packages/*
-          key: ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }}
-          restore-keys: |
-            ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }}
-
-      - name: Check required environment variables
-        env:
-          LLM_MODEL: ${{ secrets.LLM_MODEL }}
-          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
-          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-          PAT_TOKEN: ${{ secrets.PAT_TOKEN }}
-          PAT_USERNAME: ${{ secrets.PAT_USERNAME }}
-        run: |
-          required_vars=("LLM_MODEL" "LLM_API_KEY" "PAT_TOKEN" "PAT_USERNAME")
-          for var in "${required_vars[@]}"; do
-            if [ -z "${!var}" ]; then
-              echo "Error: Required environment variable $var is not set."
-              exit 1
-            fi
-          done
-
-      - name: Set environment variables
-        run: |
-          if [ -n "${{ github.event.review.body }}" ]; then
-            echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
-            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
-          elif [ -n "${{ github.event.issue.pull_request }}" ]; then
-            echo "ISSUE_NUMBER=${{ github.event.issue.number }}" >> $GITHUB_ENV
-            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
-          elif [ -n "${{ github.event.pull_request.number }}" ]; then
-            echo "ISSUE_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
-            echo "ISSUE_TYPE=pr" >> $GITHUB_ENV
-          else
-            echo "ISSUE_NUMBER=${{ github.event.issue.number }}" >> $GITHUB_ENV
-            echo "ISSUE_TYPE=issue" >> $GITHUB_ENV
-          fi
-
-          if [ -n "${{ github.event.review.body }}" ]; then
-            echo "COMMENT_ID=${{ github.event.review.id || 'None' }}" >> $GITHUB_ENV
-          else
-            echo "COMMENT_ID=${{ github.event.comment.id || 'None' }}" >> $GITHUB_ENV
-          fi
-
-          echo "MAX_ITERATIONS=${{ inputs.max_iterations || 50 }}" >> $GITHUB_ENV
-          echo "SANDBOX_ENV_GITHUB_TOKEN=${{ secrets.GITHUB_TOKEN }}" >> $GITHUB_ENV
-
-      - name: Comment on issue with start message
-        uses: actions/github-script@v7
-        with:
-          github-token: ${{secrets.GITHUB_TOKEN}}
-          script: |
-            const issueType = process.env.ISSUE_TYPE;
-            github.rest.issues.createComment({
-              issue_number: ${{ env.ISSUE_NUMBER }},
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              body: `[OpenHands](https://github.com/All-Hands-AI/OpenHands) started fixing the ${issueType}! You can monitor the progress [here](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}).`
-            });
-
-      - name: Install OpenHands
-        run: |
-          if [ "${{ github.event.label.name }}" == "fix-me-experimental" ]; then
-            python -m pip install --upgrade pip
-            pip install git+https://github.com/all-hands-ai/openhands.git
-          else
-            python -m pip install --upgrade -r requirements.txt
-          fi
-
-      - name: Attempt to resolve issue
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          GITHUB_USERNAME: ${{ secrets.PAT_USERNAME }}
-          LLM_MODEL: ${{ secrets.LLM_MODEL }}
-          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
-          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-          PYTHONPATH: ""
-        run: |
-          cd /tmp && python -m openhands.resolver.resolve_issue \
-            --repo ${{ github.repository }} \
-            --issue-number ${{ env.ISSUE_NUMBER }} \
-            --issue-type ${{ env.ISSUE_TYPE }} \
-            --max-iterations ${{ env.MAX_ITERATIONS }} \
-            --comment-id ${{ env.COMMENT_ID }}
-
-      - name: Check resolution result
-        id: check_result
-        run: |
-          if cd /tmp && grep -q '"success":true' output/output.jsonl; then
-            echo "RESOLUTION_SUCCESS=true" >> $GITHUB_OUTPUT
-          else
-            echo "RESOLUTION_SUCCESS=false" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Upload output.jsonl as artifact
-        uses: actions/upload-artifact@v4
-        if: always() # Upload even if the previous steps fail
-        with:
-          name: resolver-output
-          path: /tmp/output/output.jsonl
-          retention-days: 30 # Keep the artifact for 30 days
-
-      - name: Create draft PR or push branch
-        env:
-          GITHUB_TOKEN: ${{ secrets.PAT_TOKEN }}
-          GITHUB_USERNAME: ${{ secrets.PAT_USERNAME }}
-          LLM_MODEL: ${{ secrets.LLM_MODEL }}
-          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
-          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
-          PYTHONPATH: ""
-        run: |
-          if [ "${{ steps.check_result.outputs.RESOLUTION_SUCCESS }}" == "true" ]; then
-            cd /tmp && python -m openhands.resolver.send_pull_request \
-              --issue-number ${{ env.ISSUE_NUMBER }} \
-              --pr-type draft | tee pr_result.txt && \
-              grep "draft created" pr_result.txt | sed 's/.*\///g' > pr_number.txt
-          else
-            cd /tmp && python -m openhands.resolver.send_pull_request \
-              --issue-number ${{ env.ISSUE_NUMBER }} \
-              --pr-type branch \
-              --send-on-failure | tee branch_result.txt && \
-              grep "branch created" branch_result.txt | sed 's/.*\///g; s/.expand=1//g' > branch_name.txt
-          fi
-
-      - name: Comment on issue
-        uses: actions/github-script@v7
-        with:
-          github-token: ${{secrets.GITHUB_TOKEN}}
-          script: |
-            const fs = require('fs');
-            const issueNumber = ${{ env.ISSUE_NUMBER }};
-            const success = ${{ steps.check_result.outputs.RESOLUTION_SUCCESS }};
-
-            let prNumber = '';
-            let branchName = '';
-            let logContent = '';
-            const noChangesMessage = `No changes to commit for issue #${issueNumber}. Skipping commit.`;
-
-            try {
-              if (success){
-                logContent = fs.readFileSync('/tmp/pr_result.txt', 'utf8').trim();
-              } else {
-                logContent = fs.readFileSync('/tmp/branch_result.txt', 'utf8').trim();
-              }
-            } catch (error) {
-              console.error('Error reading results file:', error);
-            }
-
-            try {
-              if (success) {
-                prNumber = fs.readFileSync('/tmp/pr_number.txt', 'utf8').trim();
-              } else {
-                branchName = fs.readFileSync('/tmp/branch_name.txt', 'utf8').trim();
-              }
-            } catch (error) {
-              console.error('Error reading file:', error);
-            }
-
-            if (logContent.includes(noChangesMessage)) {
-              github.rest.issues.createComment({
-                issue_number: issueNumber,
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                body: `The workflow to fix this issue encountered an error. Openhands failed to create any code changes.`
-              });
-            } else if (success && prNumber) {
-              github.rest.issues.createComment({
-                issue_number: issueNumber,
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                body: `A potential fix has been generated and a draft PR #${prNumber} has been created. Please review the changes.`
-              });
-            } else if (!success && branchName) {
-              github.rest.issues.createComment({
-                issue_number: issueNumber,
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                body: `An attempt was made to automatically fix this issue, but it was unsuccessful. A branch named '${branchName}' has been created with the attempted changes. You can view the branch [here](https://github.com/${context.repo.owner}/${context.repo.repo}/tree/${branchName}). Manual intervention may be required.`
-              });
-            } else {
-              github.rest.issues.createComment({
-                issue_number: issueNumber,
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                body: `The workflow to fix this issue encountered an error. Please check the [workflow logs](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}) for more information.`
-              });
-            }
+  call-openhands-resolver:
+    uses: All-Hands-AI/openhands-resolver/.github/workflows/openhands-resolver.yml@main
+    if: github.event.label.name == 'fix-me'
+    with:
+      issue_number: ${{ github.event.issue.number || github.event.pull_request.number }}
+    secrets: inherit

.gitignore

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

Development.md

@@ -100,7 +100,7 @@ poetry run pytest ./tests/unit/test_*.py
 ### 9. Use existing Docker image
 To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker container image. Follow these steps:
 1. Set the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
-2. Example: export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.13-nikolaik
+2. Example: export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.12-nikolaik
 
 ## Develop inside Docker container
 

README.md

@@ -38,16 +38,15 @@ See the [Installation](https://docs.all-hands.dev/modules/usage/installation) gu
 system requirements and more information.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik
 
 docker run -it --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
-    -e LOG_ALL_EVENTS=true \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.13
+    docker.all-hands.dev/all-hands-ai/openhands:0.12
 ```
 
 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:0.13-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.12-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

config.template.toml

@@ -32,8 +32,7 @@ workspace_base = "./workspace"
 # Enable saving and restoring the session when run from CLI
 #enable_cli_session = false
 
-# Path to store trajectories, can be a folder or a file
-# If it's a folder, the session id will be used as the file name
+# Path to store trajectories
 #trajectories_path="./trajectories"
 
 # File store path

containers/dev/compose.yml

@@ -11,7 +11,7 @@ services:
       - BACKEND_HOST=${BACKEND_HOST:-"0.0.0.0"}
       - SANDBOX_API_HOSTNAME=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.13-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.12-nikolaik}
       - SANDBOX_USER_ID=${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:0.13-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -59,7 +59,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.13 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.12 \
     python -m openhands.core.cli
 ```
 

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

@@ -44,16 +44,15 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
     -e LLM_MODEL=$LLM_MODEL \
-    -e LOG_ALL_EVENTS=true \
     -v $WORKSPACE_BASE:/opt/workspace_base \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.13 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.12 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```

docs/modules/usage/installation.mdx

@@ -11,16 +11,15 @@
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
-    -e LOG_ALL_EVENTS=true \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.13
+    docker.all-hands.dev/all-hands-ai/openhands:0.12
 ```
 
 You can also run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), as an [interactive CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), or using the [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action).

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

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

docs/modules/usage/llms/llms.md

@@ -4,11 +4,11 @@ OpenHands can connect to any LLM supported by LiteLLM. However, it requires a po
 
 ## Model Recommendations
 
-Based on our evaluations of language models for coding tasks (using the SWE-bench dataset), we can provide some recommendations for model selection. Some analyses can be found in [this blog article comparing LLMs](https://www.all-hands.dev/blog/evaluation-of-llms-as-coding-agents-on-swe-bench-at-30x-speed) and [this blog article with some more recent results](https://www.all-hands.dev/blog/openhands-codeact-21-an-open-state-of-the-art-software-development-agent).
+Based on a recent evaluation of language models for coding tasks (using the SWE-bench dataset), we can provide some recommendations for model selection. The full analysis can be found in [this blog article](https://www.all-hands.dev/blog/evaluation-of-llms-as-coding-agents-on-swe-bench-at-30x-speed).
 
 When choosing a model, consider both the quality of outputs and the associated costs. Here's a summary of the findings:
 
-- Claude 3.5 Sonnet is the best by a fair amount, achieving a 53% resolve rate on SWE-Bench Verified with the default agent in OpenHands.
+- Claude 3.5 Sonnet is the best by a fair amount, achieving a 27% resolve rate with the default agent in OpenHands.
 - GPT-4o lags behind, and o1-mini actually performed somewhat worse than GPT-4o. We went in and analyzed the results a little, and briefly it seemed like o1 was sometimes "overthinking" things, performing extra environment configuration tasks when it could just go ahead and finish the task.
 - Finally, the strongest open models were Llama 3.1 405 B and deepseek-v2.5, and they performed reasonably, even besting some of the closed models.
 
@@ -63,7 +63,6 @@ We have a few guides for running OpenHands with specific model providers:
 - [Azure](llms/azure-llms)
 - [Google](llms/google-llms)
 - [Groq](llms/groq)
-- [LiteLLM Proxy](llms/litellm-proxy)
 - [OpenAI](llms/openai-llms)
 - [OpenRouter](llms/openrouter)
 

docs/modules/usage/runtimes.md

@@ -59,7 +59,7 @@ docker run # ...
     -e RUNTIME=remote \
     -e SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.app.all-hands.dev" \
     -e SANDBOX_API_KEY="your-all-hands-api-key" \
-    -e SANDBOX_KEEP_RUNTIME_ALIVE="true" \
+    -e SANDBOX_KEEP_REMOTE_RUNTIME_ALIVE="true" \
     # ...
 ```
 

docs/sidebars.ts

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

evaluation/EDA/game.py

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

evaluation/EDA/run_infer.py

@@ -35,8 +35,7 @@ def codeact_user_response_eda(state: State) -> str:
 
     # retrieve the latest model message from history
     if state.history:
-        last_agent_message = state.get_last_agent_message()
-        model_guess = last_agent_message.content if last_agent_message else ''
+        model_guess = state.get_last_agent_message()
 
     assert game is not None, 'Game is not initialized.'
     msg = game.generate_user_response(model_guess)
@@ -141,8 +140,7 @@ def process_instance(
     if state is None:
         raise ValueError('State should not be None.')
 
-    last_agent_message = state.get_last_agent_message()
-    final_message = last_agent_message.content if last_agent_message else ''
+    final_message = state.get_last_agent_message()
 
     logger.info(f'Final message: {final_message} | Ground truth: {instance["text"]}')
     test_result = game.reward()

evaluation/aider_bench/README.md

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

evaluation/aider_bench/run_infer.py

@@ -58,9 +58,6 @@ def get_config(
             use_host_network=False,
             timeout=100,
             api_key=os.environ.get('ALLHANDS_API_KEY', None),
-            remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            keep_runtime_alive=False,
-            remote_runtime_init_timeout=1800,
         ),
         # do not mount workspace
         workspace_base=None,

evaluation/biocoder/run_infer.py

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

evaluation/bird/run_infer.py

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

evaluation/discoverybench/run_infer.py

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

evaluation/gorilla/run_infer.py

@@ -33,7 +33,7 @@ AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
 }
 
 AGENT_CLS_TO_INST_SUFFIX = {
-    'CodeActAgent': 'When you think you have completed the request, please finish the interaction using the "finish" tool.\n'
+    'CodeActAgent': 'When you think you have completed the request, please run the following command: <execute_bash> exit </execute_bash>.\n'
 }
 
 
@@ -102,8 +102,7 @@ def process_instance(
         raise ValueError('State should not be None.')
 
     # retrieve the last message from the agent
-    last_agent_message = state.get_last_agent_message()
-    model_answer_raw = last_agent_message.content if last_agent_message else ''
+    model_answer_raw = state.get_last_agent_message()
 
     # attempt to parse model_answer
     ast_eval_fn = instance['ast_eval']

evaluation/gpqa/run_infer.py

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

evaluation/humanevalfix/README.md

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

evaluation/humanevalfix/run_infer.py

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

evaluation/miniwob/README.md

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

evaluation/miniwob/get_avg_reward.py

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

evaluation/miniwob/run_infer.py

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

evaluation/miniwob/scripts/run_infer.sh

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

evaluation/mint/run_infer.py

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

evaluation/ml_bench/README.md

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

evaluation/ml_bench/run_infer.py

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

evaluation/scienceagentbench/run_infer.py

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

evaluation/swe_bench/eval_infer.py

@@ -1,7 +1,6 @@
 import os
 import tempfile
 import time
-from functools import partial
 
 import pandas as pd
 from swebench.harness.grading import get_eval_report
@@ -84,7 +83,6 @@ def get_config(instance: pd.Series) -> AppConfig:
             timeout=1800,
             api_key=os.environ.get('ALLHANDS_API_KEY', None),
             remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            remote_runtime_init_timeout=3600,
         ),
         # do not mount workspace
         workspace_base=None,
@@ -95,28 +93,13 @@ def get_config(instance: pd.Series) -> AppConfig:
 
 def process_instance(
     instance: pd.Series,
-    metadata: EvalMetadata,
+    metadata: EvalMetadata | None = None,
     reset_logger: bool = True,
-    log_dir: str | None = None,
 ) -> EvalOutput:
-    """
-    Evaluate agent performance on a SWE-bench problem instance.
-
-    Note that this signature differs from the expected input to `run_evaluation`. Use
-    `functools.partial` to provide optional arguments before passing to the evaluation harness.
-
-    Args:
-        log_dir (str | None, default=None): Path to directory where log files will be written. Must
-        be provided if `reset_logger` is set.
-
-    Raises:
-        AssertionError: if the `reset_logger` flag is set without a provided log directory.
-    """
     # Setup the logger properly, so you can run multi-processing to parallelize the evaluation
     if reset_logger:
-        assert (
-            log_dir is not None
-        ), "Can't reset logger without a provided log directory."
+        global output_file
+        log_dir = output_file.replace('.jsonl', '.logs')
         os.makedirs(log_dir, exist_ok=True)
         reset_logger_for_multiprocessing(logger, instance.instance_id, log_dir)
     else:
@@ -143,7 +126,6 @@ def process_instance(
         return EvalOutput(
             instance_id=instance_id,
             test_result=instance['test_result'],
-            metadata=metadata,
         )
 
     runtime = create_runtime(config)
@@ -193,7 +175,6 @@ def process_instance(
             return EvalOutput(
                 instance_id=instance_id,
                 test_result=instance['test_result'],
-                metadata=metadata,
             )
         elif 'APPLY_PATCH_PASS' in apply_patch_output:
             logger.info(f'[{instance_id}] {APPLY_PATCH_PASS}:\n{apply_patch_output}')
@@ -287,7 +268,6 @@ def process_instance(
             return EvalOutput(
                 instance_id=instance_id,
                 test_result=instance['test_result'],
-                metadata=metadata,
             )
         else:
             logger.info(
@@ -374,26 +354,12 @@ if __name__ == '__main__':
     output_file = args.input_file.replace('.jsonl', '.swebench_eval.jsonl')
     instances = prepare_dataset(predictions, output_file, args.eval_n_limit)
 
-    # If possible, load the relevant metadata to avoid issues with `run_evaluation`.
-    metadata: EvalMetadata | None = None
-    metadata_filepath = os.path.join(os.path.dirname(args.input_file), 'metadata.json')
-    if os.path.exists(metadata_filepath):
-        with open(metadata_filepath, 'r') as metadata_file:
-            data = metadata_file.read()
-            metadata = EvalMetadata.model_validate_json(data)
-
-    # The evaluation harness constrains the signature of `process_instance_func` but we need to
-    # pass extra information. Build a new function object to avoid issues with multiprocessing.
-    process_instance_func = partial(
-        process_instance, log_dir=output_file.replace('.jsonl', '.logs')
-    )
-
     run_evaluation(
         instances,
-        metadata=metadata,
+        metadata=None,
         output_file=output_file,
         num_workers=args.eval_num_workers,
-        process_instance_func=process_instance_func,
+        process_instance_func=process_instance,
     )
 
     # Load evaluated predictions & print number of resolved predictions

evaluation/swe_bench/prompt.py

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

evaluation/swe_bench/run_infer.py

@@ -36,8 +36,8 @@ from openhands.events.action import CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation, ErrorObservation
 from openhands.events.serialization.event import event_to_dict
 from openhands.runtime.base import Runtime
+from openhands.runtime.utils.shutdown_listener import sleep_if_should_continue
 from openhands.utils.async_utils import call_async_from_sync
-from openhands.utils.shutdown_listener import sleep_if_should_continue
 
 USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
 USE_INSTANCE_IMAGE = os.environ.get('USE_INSTANCE_IMAGE', 'false').lower() == 'true'
@@ -146,7 +146,6 @@ def get_config(
             api_key=os.environ.get('ALLHANDS_API_KEY', None),
             remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
             keep_remote_runtime_alive=False,
-            remote_runtime_init_timeout=3600,
         ),
         # do not mount workspace
         workspace_base=None,

evaluation/toolqa/run_infer.py

@@ -34,7 +34,7 @@ AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
 }
 
 AGENT_CLS_TO_INST_SUFFIX = {
-    'CodeActAgent': 'When you think you have completed the request, please finish the interaction using the "finish" tool.\n'
+    'CodeActAgent': 'When you think you have completed the request, please run the following command: <execute_bash> exit </execute_bash>.\n'
 }
 
 
@@ -127,8 +127,7 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
         raise ValueError('State should not be None.')
 
     # retrieve the last message from the agent
-    last_agent_message = state.get_last_agent_message()
-    model_answer_raw = last_agent_message.content if last_agent_message else ''
+    model_answer_raw = state.get_last_agent_message()
 
     # attempt to parse model_answer
     correct = eval_answer(str(model_answer_raw), str(answer))

evaluation/utils/shared.py

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

frontend/__tests__/clear-session.test.ts

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

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

@@ -1,5 +1,5 @@
 import userEvent from "@testing-library/user-event";
-import { fireEvent, render, screen } from "@testing-library/react";
+import { render, screen } from "@testing-library/react";
 import { describe, afterEach, vi, it, expect } from "vitest";
 import { ChatInput } from "#/components/chat-input";
 
@@ -158,46 +158,4 @@ describe("ChatInput", () => {
     await user.tab();
     expect(onBlurMock).toHaveBeenCalledOnce();
   });
-
-  it("should handle text paste correctly", () => {
-    const onSubmit = vi.fn();
-    const onChange = vi.fn();
-
-    render(<ChatInput onSubmit={onSubmit} onChange={onChange} />);
-
-    const input = screen.getByTestId("chat-input").querySelector("textarea");
-    expect(input).toBeTruthy();
-
-    // Fire paste event with text data
-    fireEvent.paste(input!, {
-      clipboardData: {
-        getData: (type: string) => type === 'text/plain' ? 'test paste' : '',
-        files: []
-      }
-    });
-  });
-
-  it("should handle image paste correctly", () => {
-    const onSubmit = vi.fn();
-    const onImagePaste = vi.fn();
-
-    render(<ChatInput onSubmit={onSubmit} onImagePaste={onImagePaste} />);
-
-    const input = screen.getByTestId("chat-input").querySelector("textarea");
-    expect(input).toBeTruthy();
-
-    // Create a paste event with an image file
-    const file = new File(["dummy content"], "image.png", { type: "image/png" });
-
-    // Fire paste event with image data
-    fireEvent.paste(input!, {
-      clipboardData: {
-        getData: () => '',
-        files: [file]
-      }
-    });
-
-    // Verify image paste was handled
-    expect(onImagePaste).toHaveBeenCalledWith([file]);
-  });
 });

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

@@ -16,14 +16,14 @@ describe("Empty state", () => {
     send: vi.fn(),
   }));
 
-  const { useWsClient: useWsClientMock } = vi.hoisted(() => ({
-    useWsClient: vi.fn(() => ({ send: sendMock, runtimeActive: true })),
+  const { useSocket: useSocketMock } = vi.hoisted(() => ({
+    useSocket: vi.fn(() => ({ send: sendMock, runtimeActive: true })),
   }));
 
   beforeAll(() => {
     vi.mock("#/context/socket", async (importActual) => ({
-      ...(await importActual<typeof import("#/context/ws-client-provider")>()),
-      useWsClient: useWsClientMock,
+      ...(await importActual<typeof import("#/context/socket")>()),
+      useSocket: useSocketMock,
     }));
   });
 
@@ -77,7 +77,7 @@ describe("Empty state", () => {
     "should load the a user message to the input when selecting",
     async () => {
       // this is to test that the message is in the UI before the socket is called
-      useWsClientMock.mockImplementation(() => ({
+      useSocketMock.mockImplementation(() => ({
         send: sendMock,
         runtimeActive: false, // mock an inactive runtime setup
       }));
@@ -106,7 +106,7 @@ describe("Empty state", () => {
   it.fails(
     "should send the message to the socket only if the runtime is active",
     async () => {
-      useWsClientMock.mockImplementation(() => ({
+      useSocketMock.mockImplementation(() => ({
         send: sendMock,
         runtimeActive: false, // mock an inactive runtime setup
       }));
@@ -123,7 +123,7 @@ describe("Empty state", () => {
       await user.click(displayedSuggestions[0]);
       expect(sendMock).not.toHaveBeenCalled();
 
-      useWsClientMock.mockImplementation(() => ({
+      useSocketMock.mockImplementation(() => ({
         send: sendMock,
         runtimeActive: true, // mock an active runtime setup
       }));

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

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

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

@@ -2,9 +2,8 @@ import { beforeAll, describe, expect, it, vi } from "vitest";
 import { render } from "@testing-library/react";
 import { afterEach } from "node:test";
 import { useTerminal } from "#/hooks/useTerminal";
+import { SocketProvider } from "#/context/socket";
 import { Command } from "#/state/commandSlice";
-import { WsClientProvider } from "#/context/ws-client-provider";
-import { ReactNode } from "react";
 
 interface TestTerminalComponentProps {
   commands: Command[];
@@ -19,17 +18,6 @@ function TestTerminalComponent({
   return <div ref={ref} />;
 }
 
-interface WrapperProps {
-  children: ReactNode;
-}
-
-
-function Wrapper({children}: WrapperProps) {
-  return (
-    <WsClientProvider enabled={true} token="NO_JWT" ghToken="NO_GITHUB" settings={null}>{children}</WsClientProvider>
-  )
-}
-
 describe("useTerminal", () => {
   const mockTerminal = vi.hoisted(() => ({
     loadAddon: vi.fn(),
@@ -62,7 +50,7 @@ describe("useTerminal", () => {
 
   it("should render", () => {
     render(<TestTerminalComponent commands={[]} secrets={[]} />, {
-      wrapper: Wrapper,
+      wrapper: SocketProvider,
     });
   });
 
@@ -73,7 +61,7 @@ describe("useTerminal", () => {
     ];
 
     render(<TestTerminalComponent commands={commands} secrets={[]} />, {
-      wrapper: Wrapper,
+      wrapper: SocketProvider,
     });
 
     expect(mockTerminal.writeln).toHaveBeenNthCalledWith(1, "echo hello");
@@ -97,7 +85,7 @@ describe("useTerminal", () => {
         secrets={[secret, anotherSecret]}
       />,
       {
-        wrapper: Wrapper,
+        wrapper: SocketProvider,
       },
     );
 

frontend/__tests__/utils/cache.test.ts

@@ -8,6 +8,7 @@ describe("Cache", () => {
   const testTTL = 1000; // 1 second
 
   beforeEach(() => {
+    localStorage.clear();
     vi.useFakeTimers();
   });
 
@@ -15,7 +16,17 @@ describe("Cache", () => {
     vi.useRealTimers();
   });
 
-  it("gets data from memory if not expired", () => {
+  it("sets data in localStorage with expiration", () => {
+    cache.set(testKey, testData, testTTL);
+    const cachedEntry = JSON.parse(
+      localStorage.getItem(`app_cache_${testKey}`) || "",
+    );
+
+    expect(cachedEntry.data).toEqual(testData);
+    expect(cachedEntry.expiration).toBeGreaterThan(Date.now());
+  });
+
+  it("gets data from localStorage if not expired", () => {
     cache.set(testKey, testData, testTTL);
 
     expect(cache.get(testKey)).toEqual(testData);
@@ -28,6 +39,7 @@ describe("Cache", () => {
     vi.advanceTimersByTime(5 * 60 * 1000 + 1);
 
     expect(cache.get(testKey)).toBeNull();
+    expect(localStorage.getItem(`app_cache_${testKey}`)).toBeNull();
   });
 
   it("returns null if cached data is expired", () => {
@@ -35,19 +47,28 @@ describe("Cache", () => {
 
     vi.advanceTimersByTime(testTTL + 1);
     expect(cache.get(testKey)).toBeNull();
+    expect(localStorage.getItem(`app_cache_${testKey}`)).toBeNull();
   });
 
-  it("deletes data from memory", () => {
+  it("deletes data from localStorage", () => {
     cache.set(testKey, testData, testTTL);
     cache.delete(testKey);
-    expect(cache.get(testKey)).toBeNull();
+
+    expect(localStorage.getItem(`app_cache_${testKey}`)).toBeNull();
   });
 
-  it("clears all data with the app prefix from memory", () => {
+  it("clears all data with the app prefix from localStorage", () => {
     cache.set(testKey, testData, testTTL);
     cache.set("anotherKey", { data: "More data" }, testTTL);
     cache.clearAll();
-    expect(cache.get(testKey)).toBeNull();
-    expect(cache.get("anotherKey")).toBeNull();
+
+    expect(localStorage.length).toBe(0);
+  });
+
+  it("does not retrieve non-prefixed data from localStorage when clearing", () => {
+    localStorage.setItem("nonPrefixedKey", "should remain");
+    cache.set(testKey, testData, testTTL);
+    cache.clearAll();
+    expect(localStorage.getItem("nonPrefixedKey")).toBe("should remain");
   });
 });

frontend/__tests__/utils/extractModelAndProvider.test.ts

@@ -59,9 +59,9 @@ describe("extractModelAndProvider", () => {
       separator: "/",
     });
 
-    expect(extractModelAndProvider("claude-3-5-sonnet-20240620")).toEqual({
+    expect(extractModelAndProvider("claude-3-5-sonnet-20241022")).toEqual({
       provider: "anthropic",
-      model: "claude-3-5-sonnet-20240620",
+      model: "claude-3-5-sonnet-20241022",
       separator: "/",
     });
 

frontend/__tests__/utils/organizeModelsAndProviders.test.ts

@@ -15,7 +15,7 @@ test("organizeModelsAndProviders", () => {
     "gpt-4o",
     "together-ai-21.1b-41b",
     "gpt-4o-mini",
-    "anthropic/claude-3-5-sonnet-20241022",
+    "claude-3-5-sonnet-20241022",
     "claude-3-haiku-20240307",
     "claude-2",
     "claude-2.1",

frontend/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "openhands-frontend",
-  "version": "0.13.1",
+  "version": "0.12.3",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "openhands-frontend",
-      "version": "0.13.1",
+      "version": "0.12.3",
       "dependencies": {
         "@monaco-editor/react": "^4.6.0",
         "@nextui-org/react": "^2.4.8",
@@ -26,7 +26,7 @@
         "isbot": "^5.1.17",
         "jose": "^5.9.4",
         "monaco-editor": "^0.52.0",
-        "posthog-js": "^1.184.1",
+        "posthog-js": "^1.176.0",
         "react": "^18.3.1",
         "react-dom": "^18.3.1",
         "react-highlight": "^0.15.0",
@@ -19749,9 +19749,9 @@
       "integrity": "sha512-1NNCs6uurfkVbeXG4S8JFT9t19m45ICnif8zWLd5oPSZ50QnwMfK+H3jv408d4jw/7Bttv5axS5IiHoLaVNHeQ=="
     },
     "node_modules/posthog-js": {
-      "version": "1.184.1",
-      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.184.1.tgz",
-      "integrity": "sha512-q/1Kdard5SZnL2smrzeKcD+RuUi2PnbidiN4D3ThK20bNrhy5Z2heIy9SnRMvEiARY5lcQ7zxmDCAKPBKGSOtQ==",
+      "version": "1.176.0",
+      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.176.0.tgz",
+      "integrity": "sha512-T5XKNtRzp7q6CGb7Vc7wAI76rWap9fiuDUPxPsyPBPDkreKya91x9RIsSapAVFafwD1AEin1QMczCmt9Le9BWw==",
       "dependencies": {
         "core-js": "^3.38.1",
         "fflate": "^0.4.8",

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.13.1",
+  "version": "0.12.3",
   "private": true,
   "type": "module",
   "engines": {
@@ -25,7 +25,7 @@
     "isbot": "^5.1.17",
     "jose": "^5.9.4",
     "monaco-editor": "^0.52.0",
-    "posthog-js": "^1.184.1",
+    "posthog-js": "^1.176.0",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
     "react-highlight": "^0.15.0",

frontend/public/config.json

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

frontend/src/api/open-hands.ts

@@ -8,7 +8,6 @@ import {
   GitHubAccessTokenResponse,
   ErrorResponse,
   GetConfigResponse,
-  GetVSCodeUrlResponse,
 } from "./open-hands.types";
 
 class OpenHands {
@@ -175,14 +174,6 @@ class OpenHands {
       true,
     );
   }
-
-  /**
-   * Get the VSCode URL
-   * @returns VSCode URL
-   */
-  static async getVSCodeUrl(): Promise<GetVSCodeUrlResponse> {
-    return request(`/api/vscode-url`, {}, false, false, 1);
-  }
 }
 
 export default OpenHands;

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

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

frontend/src/assets/vscode-alt.svg

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

frontend/src/components/AgentControlBar.tsx

@@ -6,7 +6,7 @@ import PlayIcon from "#/assets/play";
 import { generateAgentStateChangeEvent } from "#/services/agentStateService";
 import { RootState } from "#/store";
 import AgentState from "#/types/AgentState";
-import { useWsClient } from "#/context/ws-client-provider";
+import { useSocket } from "#/context/socket";
 
 const IgnoreTaskStateMap: Record<string, AgentState[]> = {
   [AgentState.PAUSED]: [
@@ -72,7 +72,7 @@ function ActionButton({
 }
 
 function AgentControlBar() {
-  const { send } = useWsClient();
+  const { send } = useSocket();
   const { curAgentState } = useSelector((state: RootState) => state.agent);
 
   const handleAction = (action: AgentState) => {

frontend/src/components/attach-image-label.tsx

@@ -1,4 +1,4 @@
-import Clip from "#/icons/clip.svg?react";
+import Clip from "#/assets/clip.svg?react";
 
 export function AttachImageLabel() {
   return (

frontend/src/components/chat-input.tsx

@@ -1,6 +1,6 @@
 import React from "react";
 import TextareaAutosize from "react-textarea-autosize";
-import ArrowSendIcon from "#/icons/arrow-send.svg?react";
+import ArrowSendIcon from "#/assets/arrow-send.svg?react";
 import { cn } from "#/utils/utils";
 
 interface ChatInputProps {
@@ -18,7 +18,6 @@ interface ChatInputProps {
   onBlur?: () => void;
   onImagePaste?: (files: File[]) => void;
   className?: React.HTMLAttributes<HTMLDivElement>["className"];
-  buttonClassName?: React.HTMLAttributes<HTMLButtonElement>["className"];
 }
 
 export function ChatInput({
@@ -36,24 +35,18 @@ export function ChatInput({
   onBlur,
   onImagePaste,
   className,
-  buttonClassName,
 }: ChatInputProps) {
   const textareaRef = React.useRef<HTMLTextAreaElement>(null);
   const [isDraggingOver, setIsDraggingOver] = React.useState(false);
 
   const handlePaste = (event: React.ClipboardEvent<HTMLTextAreaElement>) => {
-    // Only handle paste if we have an image paste handler and there are files
+    event.preventDefault();
     if (onImagePaste && event.clipboardData.files.length > 0) {
       const files = Array.from(event.clipboardData.files).filter((file) =>
         file.type.startsWith("image/"),
       );
-      // Only prevent default if we found image files to handle
-      if (files.length > 0) {
-        event.preventDefault();
-        onImagePaste(files);
-      }
+      if (files.length > 0) onImagePaste(files);
     }
-    // For text paste, let the default behavior handle it
   };
 
   const handleDragOver = (event: React.DragEvent<HTMLTextAreaElement>) => {
@@ -102,7 +95,7 @@ export function ChatInput({
   return (
     <div
       data-testid="chat-input"
-      className="flex items-end justify-end grow gap-1 min-h-6 w-full"
+      className="flex items-end justify-end grow gap-1 min-h-6"
     >
       <TextareaAutosize
         ref={textareaRef}
@@ -130,7 +123,7 @@ export function ChatInput({
         )}
       />
       {showButton && (
-        <div className={buttonClassName}>
+        <>
           {button === "submit" && (
             <button
               aria-label="Send"
@@ -154,7 +147,7 @@ export function ChatInput({
               <div className="w-[10px] h-[10px] bg-white" />
             </button>
           )}
-        </div>
+        </>
       )}
     </div>
   );

frontend/src/components/chat-interface.tsx

@@ -1,6 +1,7 @@
 import { useDispatch, useSelector } from "react-redux";
 import React from "react";
 import posthog from "posthog-js";
+import { useSocket } from "#/context/socket";
 import { convertImageToBase64 } from "#/utils/convert-image-to-base-64";
 import { ChatMessage } from "./chat-message";
 import { FeedbackActions } from "./feedback-actions";
@@ -20,16 +21,14 @@ import { ContinueButton } from "./continue-button";
 import { ScrollToBottomButton } from "./scroll-to-bottom-button";
 import { Suggestions } from "./suggestions";
 import { SUGGESTIONS } from "#/utils/suggestions";
-import BuildIt from "#/icons/build-it.svg?react";
-import { useWsClient } from "#/context/ws-client-provider";
+import BuildIt from "#/assets/build-it.svg?react";
 
 const isErrorMessage = (
   message: Message | ErrorMessage,
 ): message is ErrorMessage => "error" in message;
 
 export function ChatInterface() {
-  const { send, isLoadingMessages } = useWsClient();
-
+  const { send } = useSocket();
   const dispatch = useDispatch();
   const scrollRef = React.useRef<HTMLDivElement>(null);
   const { scrollDomToBottom, onChatBodyScroll, hitBottom } =
@@ -102,36 +101,30 @@ export function ChatInterface() {
         onScroll={(e) => onChatBodyScroll(e.currentTarget)}
         className="flex flex-col grow overflow-y-auto overflow-x-hidden px-4 pt-4 gap-2"
       >
-        {isLoadingMessages && (
-          <div className="flex justify-center">
-            <div className="w-6 h-6 border-2 border-t-[4px] border-primary-500 rounded-full animate-spin" />
-          </div>
-        )}
-        {!isLoadingMessages &&
-          messages.map((message, index) =>
-            isErrorMessage(message) ? (
-              <ErrorMessage
-                key={index}
-                id={message.id}
-                message={message.message}
-              />
-            ) : (
-              <ChatMessage
-                key={index}
-                type={message.sender}
-                message={message.content}
-              >
-                {message.imageUrls.length > 0 && (
-                  <ImageCarousel size="small" images={message.imageUrls} />
+        {messages.map((message, index) =>
+          isErrorMessage(message) ? (
+            <ErrorMessage
+              key={index}
+              id={message.id}
+              message={message.message}
+            />
+          ) : (
+            <ChatMessage
+              key={index}
+              type={message.sender}
+              message={message.content}
+            >
+              {message.imageUrls.length > 0 && (
+                <ImageCarousel size="small" images={message.imageUrls} />
+              )}
+              {messages.length - 1 === index &&
+                message.sender === "assistant" &&
+                curAgentState === AgentState.AWAITING_USER_CONFIRMATION && (
+                  <ConfirmationButtons />
                 )}
-                {messages.length - 1 === index &&
-                  message.sender === "assistant" &&
-                  curAgentState === AgentState.AWAITING_USER_CONFIRMATION && (
-                    <ConfirmationButtons />
-                  )}
-              </ChatMessage>
-            ),
-          )}
+            </ChatMessage>
+          ),
+        )}
       </div>
 
       <div className="flex flex-col gap-[6px] px-4 pb-4">

frontend/src/components/chat/ConfirmationButtons.tsx

@@ -5,7 +5,7 @@ import RejectIcon from "#/assets/reject";
 import { I18nKey } from "#/i18n/declaration";
 import AgentState from "#/types/AgentState";
 import { generateAgentStateChangeEvent } from "#/services/agentStateService";
-import { useWsClient } from "#/context/ws-client-provider";
+import { useSocket } from "#/context/socket";
 
 interface ActionTooltipProps {
   type: "confirm" | "reject";
@@ -37,7 +37,7 @@ function ActionTooltip({ type, onClick }: ActionTooltipProps) {
 
 function ConfirmationButtons() {
   const { t } = useTranslation();
-  const { send } = useWsClient();
+  const { send } = useSocket();
 
   const handleStateChange = (state: AgentState) => {
     const event = generateAgentStateChangeEvent(state);

frontend/src/components/event-handler.tsx

@@ -1,194 +0,0 @@
-import React from "react";
-import {
-  useFetcher,
-  useLoaderData,
-  useRouteLoaderData,
-} from "@remix-run/react";
-import { useDispatch, useSelector } from "react-redux";
-import toast from "react-hot-toast";
-
-import posthog from "posthog-js";
-import {
-  useWsClient,
-  WsClientProviderStatus,
-} from "#/context/ws-client-provider";
-import { ErrorObservation } from "#/types/core/observations";
-import { addErrorMessage, addUserMessage } from "#/state/chatSlice";
-import {
-  getCloneRepoCommand,
-  getGitHubTokenCommand,
-} from "#/services/terminalService";
-import {
-  clearFiles,
-  clearSelectedRepository,
-  setImportedProjectZip,
-} from "#/state/initial-query-slice";
-import { clientLoader as appClientLoader } from "#/routes/_oh.app";
-import store, { RootState } from "#/store";
-import { createChatMessage } from "#/services/chatService";
-import { clientLoader as rootClientLoader } from "#/routes/_oh";
-import { isGitHubErrorReponse } from "#/api/github";
-import OpenHands from "#/api/open-hands";
-import { base64ToBlob } from "#/utils/base64-to-blob";
-import { setCurrentAgentState } from "#/state/agentSlice";
-import AgentState from "#/types/AgentState";
-import { getSettings } from "#/services/settings";
-import { generateAgentStateChangeEvent } from "#/services/agentStateService";
-
-interface ServerError {
-  error: boolean | string;
-  message: string;
-  [key: string]: unknown;
-}
-
-const isServerError = (data: object): data is ServerError => "error" in data;
-
-const isErrorObservation = (data: object): data is ErrorObservation =>
-  "observation" in data && data.observation === "error";
-
-export function EventHandler({ children }: React.PropsWithChildren) {
-  const { events, status, send } = useWsClient();
-  const statusRef = React.useRef<WsClientProviderStatus | null>(null);
-  const runtimeActive = status === WsClientProviderStatus.ACTIVE;
-  const fetcher = useFetcher();
-  const dispatch = useDispatch();
-  const { files, importedProjectZip } = useSelector(
-    (state: RootState) => state.initalQuery,
-  );
-  const { ghToken, repo } = useLoaderData<typeof appClientLoader>();
-  const initialQueryRef = React.useRef<string | null>(
-    store.getState().initalQuery.initialQuery,
-  );
-
-  const sendInitialQuery = (query: string, base64Files: string[]) => {
-    const timestamp = new Date().toISOString();
-    send(createChatMessage(query, base64Files, timestamp));
-  };
-  const data = useRouteLoaderData<typeof rootClientLoader>("routes/_oh");
-  const userId = React.useMemo(() => {
-    if (data?.user && !isGitHubErrorReponse(data.user)) return data.user.id;
-    return null;
-  }, [data?.user]);
-  const userSettings = getSettings();
-
-  React.useEffect(() => {
-    if (!events.length) {
-      return;
-    }
-    const event = events[events.length - 1];
-    if (event.token) {
-      fetcher.submit({ token: event.token as string }, { method: "post" });
-      return;
-    }
-
-    if (isServerError(event)) {
-      if (event.error_code === 401) {
-        toast.error("Session expired.");
-        fetcher.submit({}, { method: "POST", action: "/end-session" });
-        return;
-      }
-
-      if (typeof event.error === "string") {
-        toast.error(event.error);
-      } else {
-        toast.error(event.message);
-      }
-      return;
-    }
-
-    if (event.type === "error") {
-      const message: string = `${event.message}`;
-      if (message.startsWith("Agent reached maximum")) {
-        // We set the agent state to paused here - if the user clicks resume, it auto updates the max iterations
-        send(generateAgentStateChangeEvent(AgentState.PAUSED));
-      }
-    }
-
-    if (isErrorObservation(event)) {
-      dispatch(
-        addErrorMessage({
-          id: event.extras?.error_id,
-          message: event.message,
-        }),
-      );
-    }
-  }, [events.length]);
-
-  React.useEffect(() => {
-    if (statusRef.current === status) {
-      return; // This is a check because of strict mode - if the status did not change, don't do anything
-    }
-    statusRef.current = status;
-    const initialQuery = initialQueryRef.current;
-
-    if (status === WsClientProviderStatus.ACTIVE) {
-      let additionalInfo = "";
-      if (ghToken && repo) {
-        send(getCloneRepoCommand(ghToken, repo));
-        additionalInfo = `Repository ${repo} has been cloned to /workspace. Please check the /workspace for files.`;
-        dispatch(clearSelectedRepository()); // reset selected repository; maybe better to move this to '/'?
-      }
-      // if there's an uploaded project zip, add it to the chat
-      else if (importedProjectZip) {
-        additionalInfo = `Files have been uploaded. Please check the /workspace for files.`;
-      }
-
-      if (initialQuery) {
-        if (additionalInfo) {
-          sendInitialQuery(`${initialQuery}\n\n[${additionalInfo}]`, files);
-        } else {
-          sendInitialQuery(initialQuery, files);
-        }
-        dispatch(clearFiles()); // reset selected files
-        initialQueryRef.current = null;
-      }
-    }
-
-    if (status === WsClientProviderStatus.OPENING && initialQuery) {
-      dispatch(
-        addUserMessage({
-          content: initialQuery,
-          imageUrls: files,
-          timestamp: new Date().toISOString(),
-        }),
-      );
-    }
-
-    if (status === WsClientProviderStatus.STOPPED) {
-      store.dispatch(setCurrentAgentState(AgentState.STOPPED));
-    }
-  }, [status]);
-
-  React.useEffect(() => {
-    if (runtimeActive && userId && ghToken) {
-      // Export if the user valid, this could happen mid-session so it is handled here
-      send(getGitHubTokenCommand(ghToken));
-    }
-  }, [userId, ghToken, runtimeActive]);
-
-  React.useEffect(() => {
-    (async () => {
-      if (runtimeActive && importedProjectZip) {
-        // upload files action
-        try {
-          const blob = base64ToBlob(importedProjectZip);
-          const file = new File([blob], "imported-project.zip", {
-            type: blob.type,
-          });
-          await OpenHands.uploadFiles([file]);
-          dispatch(setImportedProjectZip(null));
-        } catch (error) {
-          toast.error("Failed to upload project files.");
-        }
-      }
-    })();
-  }, [runtimeActive, importedProjectZip]);
-
-  React.useEffect(() => {
-    if (userSettings.LLM_API_KEY) {
-      posthog.capture("user_activated");
-    }
-  }, [userSettings.LLM_API_KEY]);
-
-  return children;
-}

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

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

frontend/src/components/image-preview.tsx

@@ -1,4 +1,4 @@
-import CloseIcon from "#/icons/close.svg?react";
+import CloseIcon from "#/assets/close.svg?react";
 import { cn } from "#/utils/utils";
 
 interface ImagePreviewProps {

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

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

frontend/src/components/markdown/list.tsx

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

frontend/src/components/modals/AccountSettingsModal.tsx

@@ -1,15 +1,11 @@
-import { useFetcher, useRouteLoaderData } from "@remix-run/react";
+import { useFetcher } from "@remix-run/react";
 import React from "react";
 import { useTranslation } from "react-i18next";
-import {
-  BaseModalDescription,
-  BaseModalTitle,
-} from "./confirmation-modals/BaseModal";
+import { BaseModalTitle } from "./confirmation-modals/BaseModal";
 import ModalBody from "./ModalBody";
 import ModalButton from "../buttons/ModalButton";
 import FormFieldset from "../form/FormFieldset";
 import { CustomInput } from "../form/custom-input";
-import { clientLoader } from "#/routes/_oh";
 import { clientAction as settingsClientAction } from "#/routes/settings";
 import { clientAction as loginClientAction } from "#/routes/login";
 import { AvailableLanguages } from "#/i18n";
@@ -28,8 +24,8 @@ function AccountSettingsModal({
   gitHubError,
   analyticsConsent,
 }: AccountSettingsModalProps) {
+  const ghToken = localStorage.getItem("ghToken");
   const { t } = useTranslation();
-  const data = useRouteLoaderData<typeof clientLoader>("routes/_oh");
   const settingsFetcher = useFetcher<typeof settingsClientAction>({
     key: "settings",
   });
@@ -39,7 +35,7 @@ function AccountSettingsModal({
     event.preventDefault();
     const formData = new FormData(event.currentTarget);
     const language = formData.get("language")?.toString();
-    const ghToken = formData.get("ghToken")?.toString();
+    const newGHToken = formData.get("ghToken")?.toString();
     const analytics = formData.get("analytics")?.toString() === "on";
 
     const accountForm = new FormData();
@@ -52,7 +48,7 @@ function AccountSettingsModal({
       )?.value;
       accountForm.append("language", languageKey ?? "en");
     }
-    if (ghToken) loginForm.append("ghToken", ghToken);
+    if (newGHToken) loginForm.append("ghToken", newGHToken);
     accountForm.append("analytics", analytics.toString());
 
     settingsFetcher.submit(accountForm, {
@@ -88,25 +84,14 @@ function AccountSettingsModal({
             name="ghToken"
             label="GitHub Token"
             type="password"
-            defaultValue={data?.ghToken ?? ""}
+            defaultValue={ghToken ?? ""}
           />
-          <BaseModalDescription>
-            {t(I18nKey.CONNECT_TO_GITHUB_MODAL$GET_YOUR_TOKEN)}{" "}
-            <a
-              href="https://github.com/settings/tokens/new?description=openhands-app&scopes=repo,user,workflow"
-              target="_blank"
-              rel="noreferrer noopener"
-              className="text-[#791B80] underline"
-            >
-              {t(I18nKey.CONNECT_TO_GITHUB_MODAL$HERE)}
-            </a>
-          </BaseModalDescription>
           {gitHubError && (
             <p className="text-danger text-xs">
               {t(I18nKey.ACCOUNT_SETTINGS_MODAL$GITHUB_TOKEN_INVALID)}
             </p>
           )}
-          {data?.ghToken && !gitHubError && (
+          {ghToken && !gitHubError && (
             <ModalButton
               variant="text-like"
               text={t(I18nKey.ACCOUNT_SETTINGS_MODAL$DISCONNECT)}

frontend/src/components/modals/LoadingProject.tsx

@@ -1,5 +1,5 @@
 import { useTranslation } from "react-i18next";
-import LoadingSpinnerOuter from "#/icons/loading-outer.svg?react";
+import LoadingSpinnerOuter from "#/assets/loading-outer.svg?react";
 import { cn } from "#/utils/utils";
 import ModalBody from "./ModalBody";
 import { I18nKey } from "#/i18n/declaration";

frontend/src/components/modals/connect-to-github-modal.tsx

@@ -1,4 +1,4 @@
-import { useFetcher, useRouteLoaderData } from "@remix-run/react";
+import { useFetcher } from "@remix-run/react";
 import { useTranslation } from "react-i18next";
 import ModalBody from "./ModalBody";
 import { CustomInput } from "../form/custom-input";
@@ -7,7 +7,6 @@ import {
   BaseModalDescription,
   BaseModalTitle,
 } from "./confirmation-modals/BaseModal";
-import { clientLoader } from "#/routes/_oh";
 import { clientAction } from "#/routes/login";
 import { I18nKey } from "#/i18n/declaration";
 
@@ -16,7 +15,7 @@ interface ConnectToGitHubModalProps {
 }
 
 export function ConnectToGitHubModal({ onClose }: ConnectToGitHubModalProps) {
-  const data = useRouteLoaderData<typeof clientLoader>("routes/_oh");
+  const ghToken = localStorage.getItem("ghToken");
   const fetcher = useFetcher<typeof clientAction>({ key: "login" });
   const { t } = useTranslation();
 
@@ -51,7 +50,7 @@ export function ConnectToGitHubModal({ onClose }: ConnectToGitHubModalProps) {
           name="ghToken"
           required
           type="password"
-          defaultValue={data?.ghToken ?? ""}
+          defaultValue={ghToken ?? ""}
         />
 
         <div className="flex flex-col gap-2 w-full">

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

@@ -2,17 +2,16 @@ import React from "react";
 import { useDispatch } from "react-redux";
 import toast from "react-hot-toast";
 import posthog from "posthog-js";
-import EllipsisH from "#/icons/ellipsis-h.svg?react";
+import EllipsisH from "#/assets/ellipsis-h.svg?react";
 import { ModalBackdrop } from "../modals/modal-backdrop";
 import { ConnectToGitHubModal } from "../modals/connect-to-github-modal";
 import { addUserMessage } from "#/state/chatSlice";
+import { useSocket } from "#/context/socket";
 import { createChatMessage } from "#/services/chatService";
 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 { LoadingSpinner } from "../modals/LoadingProject";
-import { useWsClient } from "#/context/ws-client-provider";
 
 interface ProjectMenuCardProps {
   isConnectedToGitHub: boolean;
@@ -27,13 +26,12 @@ export function ProjectMenuCard({
   isConnectedToGitHub,
   githubData,
 }: ProjectMenuCardProps) {
-  const { send } = useWsClient();
+  const { send } = useSocket();
   const dispatch = useDispatch();
 
   const [contextMenuIsOpen, setContextMenuIsOpen] = React.useState(false);
   const [connectToGitHubModalOpen, setConnectToGitHubModalOpen] =
     React.useState(false);
-  const [working, setWorking] = React.useState(false);
 
   const toggleMenuVisibility = () => {
     setContextMenuIsOpen((prev) => !prev);
@@ -43,7 +41,10 @@ export function ProjectMenuCard({
     posthog.capture("push_to_github_button_clicked");
     const rawEvent = {
       content: `
-Please push the changes to GitHub and open a pull request.
+Let's push the code to GitHub.
+If we're currently on the openhands-workspace branch, please create a new branch with a descriptive name.
+Commit any changes and push them to the remote repository.
+Finally, open up a pull request using the GitHub API and the token in the GITHUB_TOKEN environment variable, then show me the URL of the pull request.
 `,
       imageUrls: [],
       timestamp: new Date().toISOString(),
@@ -62,11 +63,7 @@ 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),
-      );
+      downloadWorkspace();
     } catch (error) {
       toast.error("Failed to download workspace");
     }
@@ -74,7 +71,7 @@ Please push the changes to GitHub and open a pull request.
 
   return (
     <div className="px-4 py-[10px] w-[337px] rounded-xl border border-[#525252] flex justify-between items-center relative">
-      {!working && contextMenuIsOpen && (
+      {contextMenuIsOpen && (
         <ProjectMenuCardContextMenu
           isConnectedToGitHub={isConnectedToGitHub}
           onConnectToGitHub={() => setConnectToGitHubModalOpen(true)}
@@ -101,11 +98,7 @@ Please push the changes to GitHub and open a pull request.
         onClick={toggleMenuVisibility}
         aria-label="Open project menu"
       >
-        {working ? (
-          <LoadingSpinner size="small" />
-        ) : (
-          <EllipsisH width={36} height={36} />
-        )}
+        <EllipsisH width={36} height={36} />
       </button>
       {connectToGitHubModalOpen && (
         <ModalBackdrop onClose={() => setConnectToGitHubModalOpen(false)}>

frontend/src/components/project-menu/project-menu-details-placeholder.tsx

@@ -1,6 +1,6 @@
 import { useTranslation } from "react-i18next";
 import { cn } from "#/utils/utils";
-import CloudConnection from "#/icons/cloud-connection.svg?react";
+import CloudConnection from "#/assets/cloud-connection.svg?react";
 import { I18nKey } from "#/i18n/declaration";
 
 interface ProjectMenuDetailsPlaceholderProps {

frontend/src/components/project-menu/project-menu-details.tsx

@@ -1,5 +1,5 @@
 import { useTranslation } from "react-i18next";
-import ExternalLinkIcon from "#/icons/external-link.svg?react";
+import ExternalLinkIcon from "#/assets/external-link.svg?react";
 import { formatTimeDelta } from "#/utils/format-time-delta";
 import { I18nKey } from "#/i18n/declaration";
 

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

@@ -1,8 +1,6 @@
-import { useTranslation } from "react-i18next";
 import { useClickOutsideElement } from "#/hooks/useClickOutsideElement";
 import { ContextMenu } from "../context-menu/context-menu";
 import { ContextMenuListItem } from "../context-menu/context-menu-list-item";
-import { I18nKey } from "#/i18n/declaration";
 
 interface ProjectMenuCardContextMenuProps {
   isConnectedToGitHub: boolean;
@@ -20,7 +18,7 @@ export function ProjectMenuCardContextMenu({
   onClose,
 }: ProjectMenuCardContextMenuProps) {
   const menuRef = useClickOutsideElement<HTMLUListElement>(onClose);
-  const { t } = useTranslation();
+
   return (
     <ContextMenu
       ref={menuRef}
@@ -28,16 +26,16 @@ export function ProjectMenuCardContextMenu({
     >
       {!isConnectedToGitHub && (
         <ContextMenuListItem onClick={onConnectToGitHub}>
-          {t(I18nKey.PROJECT_MENU_CARD_CONTEXT_MENU$CONNECT_TO_GITHUB_LABEL)}
+          Connect to GitHub
         </ContextMenuListItem>
       )}
       {isConnectedToGitHub && (
         <ContextMenuListItem onClick={onPushToGitHub}>
-          {t(I18nKey.PROJECT_MENU_CARD_CONTEXT_MENU$PUSH_TO_GITHUB_LABEL)}
+          Push to GitHub
         </ContextMenuListItem>
       )}
       <ContextMenuListItem onClick={onDownloadWorkspace}>
-        {t(I18nKey.PROJECT_MENU_CARD_CONTEXT_MENU$DOWNLOAD_AS_ZIP_LABEL)}
+        Download as .zip
       </ContextMenuListItem>
     </ContextMenu>
   );

frontend/src/components/scroll-to-bottom-button.tsx

@@ -1,4 +1,4 @@
-import ArrowSendIcon from "#/icons/arrow-send.svg?react";
+import ArrowSendIcon from "#/assets/arrow-send.svg?react";
 
 interface ScrollToBottomButtonProps {
   onClick: () => void;

frontend/src/components/suggestion-bubble.tsx

@@ -1,5 +1,5 @@
-import Lightbulb from "#/icons/lightbulb.svg?react";
-import Refresh from "#/icons/refresh.svg?react";
+import Lightbulb from "#/assets/lightbulb.svg?react";
+import Refresh from "#/assets/refresh.svg?react";
 
 interface SuggestionBubbleProps {
   suggestion: string;

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

@@ -1,4 +1,4 @@
-import Clip from "#/icons/clip.svg?react";
+import Clip from "#/assets/clip.svg?react";
 
 interface UploadImageInputProps {
   onUpload: (files: File[]) => void;
@@ -11,7 +11,7 @@ export function UploadImageInput({ onUpload, label }: UploadImageInputProps) {
   };
 
   return (
-    <label className="cursor-pointer py-[10px]">
+    <label className="cursor-pointer">
       {label || <Clip data-testid="default-label" width={24} height={24} />}
       <input
         data-testid="upload-image-input"

frontend/src/components/user-avatar.tsx

@@ -1,5 +1,5 @@
 import { LoadingSpinner } from "./modals/LoadingProject";
-import DefaultUserAvatar from "#/icons/default-user.svg?react";
+import DefaultUserAvatar from "#/assets/default-user.svg?react";
 import { cn } from "#/utils/utils";
 
 interface UserAvatarProps {

frontend/src/context/socket.tsx

@@ -0,0 +1,146 @@
+import React from "react";
+import { Data } from "ws";
+import posthog from "posthog-js";
+import EventLogger from "#/utils/event-logger";
+
+interface WebSocketClientOptions {
+  token: string | null;
+  onOpen?: (event: Event) => void;
+  onMessage?: (event: MessageEvent<Data>) => void;
+  onError?: (event: Event) => void;
+  onClose?: (event: Event) => void;
+}
+
+interface WebSocketContextType {
+  send: (data: string | ArrayBufferLike | Blob | ArrayBufferView) => void;
+  start: (options?: WebSocketClientOptions) => void;
+  stop: () => void;
+  setRuntimeIsInitialized: () => void;
+  runtimeActive: boolean;
+  isConnected: boolean;
+  events: Record<string, unknown>[];
+}
+
+const SocketContext = React.createContext<WebSocketContextType | undefined>(
+  undefined,
+);
+
+interface SocketProviderProps {
+  children: React.ReactNode;
+}
+
+function SocketProvider({ children }: SocketProviderProps) {
+  const wsRef = React.useRef<WebSocket | null>(null);
+  const [isConnected, setIsConnected] = React.useState(false);
+  const [runtimeActive, setRuntimeActive] = React.useState(false);
+  const [events, setEvents] = React.useState<Record<string, unknown>[]>([]);
+
+  const setRuntimeIsInitialized = () => {
+    setRuntimeActive(true);
+  };
+
+  const start = React.useCallback((options?: WebSocketClientOptions): void => {
+    if (wsRef.current) {
+      EventLogger.warning(
+        "WebSocket connection is already established, but a new one is starting anyways.",
+      );
+    }
+
+    const baseUrl =
+      import.meta.env.VITE_BACKEND_BASE_URL || window?.location.host;
+    const protocol = window.location.protocol === "https:" ? "wss:" : "ws:";
+    const sessionToken = options?.token || "NO_JWT"; // not allowed to be empty or duplicated
+    const ghToken = localStorage.getItem("ghToken") || "NO_GITHUB";
+
+    const ws = new WebSocket(`${protocol}//${baseUrl}/ws`, [
+      "openhands",
+      sessionToken,
+      ghToken,
+    ]);
+
+    ws.addEventListener("open", (event) => {
+      posthog.capture("socket_opened");
+      setIsConnected(true);
+      options?.onOpen?.(event);
+    });
+
+    ws.addEventListener("message", (event) => {
+      EventLogger.message(event);
+
+      setEvents((prevEvents) => [...prevEvents, JSON.parse(event.data)]);
+      options?.onMessage?.(event);
+    });
+
+    ws.addEventListener("error", (event) => {
+      posthog.capture("socket_error");
+      EventLogger.event(event, "SOCKET ERROR");
+      options?.onError?.(event);
+    });
+
+    ws.addEventListener("close", (event) => {
+      posthog.capture("socket_closed");
+      EventLogger.event(event, "SOCKET CLOSE");
+
+      setIsConnected(false);
+      setRuntimeActive(false);
+      wsRef.current = null;
+      options?.onClose?.(event);
+    });
+
+    wsRef.current = ws;
+  }, []);
+
+  const stop = React.useCallback((): void => {
+    if (wsRef.current) {
+      wsRef.current.close();
+      wsRef.current = null;
+    }
+  }, []);
+
+  const send = React.useCallback(
+    (data: string | ArrayBufferLike | Blob | ArrayBufferView) => {
+      if (!wsRef.current) {
+        EventLogger.error("WebSocket is not connected.");
+        return;
+      }
+      setEvents((prevEvents) => [...prevEvents, JSON.parse(data.toString())]);
+      wsRef.current.send(data);
+    },
+    [],
+  );
+
+  const value = React.useMemo(
+    () => ({
+      send,
+      start,
+      stop,
+      setRuntimeIsInitialized,
+      runtimeActive,
+      isConnected,
+      events,
+    }),
+    [
+      send,
+      start,
+      stop,
+      setRuntimeIsInitialized,
+      runtimeActive,
+      isConnected,
+      events,
+    ],
+  );
+
+  return (
+    <SocketContext.Provider value={value}>{children}</SocketContext.Provider>
+  );
+}
+
+function useSocket() {
+  const context = React.useContext(SocketContext);
+  if (context === undefined) {
+    throw new Error("useSocket must be used within a SocketProvider");
+  }
+  return context;
+}
+
+export { SocketProvider, useSocket };

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

@@ -1,208 +0,0 @@
-import posthog from "posthog-js";
-import React from "react";
-import { Settings } from "#/services/settings";
-import ActionType from "#/types/ActionType";
-import EventLogger from "#/utils/event-logger";
-import AgentState from "#/types/AgentState";
-import { handleAssistantMessage } from "#/services/actions";
-import { useRate } from "#/utils/use-rate";
-
-const isOpenHandsMessage = (event: Record<string, unknown>) =>
-  event.action === "message";
-
-const RECONNECT_RETRIES = 5;
-
-export enum WsClientProviderStatus {
-  STOPPED,
-  OPENING,
-  ACTIVE,
-  ERROR,
-}
-
-interface UseWsClient {
-  status: WsClientProviderStatus;
-  isLoadingMessages: boolean;
-  events: Record<string, unknown>[];
-  send: (event: Record<string, unknown>) => void;
-}
-
-const WsClientContext = React.createContext<UseWsClient>({
-  status: WsClientProviderStatus.STOPPED,
-  isLoadingMessages: true,
-  events: [],
-  send: () => {
-    throw new Error("not connected");
-  },
-});
-
-interface WsClientProviderProps {
-  enabled: boolean;
-  token: string | null;
-  ghToken: string | null;
-  settings: Settings | null;
-}
-
-export function WsClientProvider({
-  enabled,
-  token,
-  ghToken,
-  settings,
-  children,
-}: React.PropsWithChildren<WsClientProviderProps>) {
-  const wsRef = React.useRef<WebSocket | null>(null);
-  const tokenRef = React.useRef<string | null>(token);
-  const ghTokenRef = React.useRef<string | null>(ghToken);
-  const closeRef = React.useRef<ReturnType<typeof setTimeout> | null>(null);
-  const [status, setStatus] = React.useState(WsClientProviderStatus.STOPPED);
-  const [events, setEvents] = React.useState<Record<string, unknown>[]>([]);
-  const [retryCount, setRetryCount] = React.useState(RECONNECT_RETRIES);
-
-  const messageRateHandler = useRate({ threshold: 500 });
-
-  function send(event: Record<string, unknown>) {
-    if (!wsRef.current) {
-      EventLogger.error("WebSocket is not connected.");
-      return;
-    }
-    wsRef.current.send(JSON.stringify(event));
-  }
-
-  function handleOpen() {
-    setRetryCount(RECONNECT_RETRIES);
-    setStatus(WsClientProviderStatus.OPENING);
-    const initEvent = {
-      action: ActionType.INIT,
-      args: settings,
-    };
-    send(initEvent);
-  }
-
-  function handleMessage(messageEvent: MessageEvent) {
-    const event = JSON.parse(messageEvent.data);
-    if (isOpenHandsMessage(event)) {
-      messageRateHandler.record(new Date().getTime());
-    }
-    setEvents((prevEvents) => [...prevEvents, event]);
-    if (event.extras?.agent_state === AgentState.INIT) {
-      setStatus(WsClientProviderStatus.ACTIVE);
-    }
-    if (
-      status !== WsClientProviderStatus.ACTIVE &&
-      event?.observation === "error"
-    ) {
-      setStatus(WsClientProviderStatus.ERROR);
-    }
-
-    handleAssistantMessage(event);
-  }
-
-  function handleClose() {
-    if (retryCount) {
-      setTimeout(() => {
-        setRetryCount(retryCount - 1);
-      }, 1000);
-    } else {
-      setStatus(WsClientProviderStatus.STOPPED);
-      setEvents([]);
-    }
-    wsRef.current = null;
-  }
-
-  function handleError(event: Event) {
-    posthog.capture("socket_error");
-    EventLogger.event(event, "SOCKET ERROR");
-    setStatus(WsClientProviderStatus.ERROR);
-  }
-
-  // Connect websocket
-  React.useEffect(() => {
-    let ws = wsRef.current;
-
-    // If disabled close any existing websockets...
-    if (!enabled || !retryCount) {
-      if (ws) {
-        ws.close();
-      }
-      wsRef.current = null;
-      return () => {};
-    }
-
-    // If there is no websocket or the tokens have changed or the current websocket is closed,
-    // create a new one
-    if (
-      !ws ||
-      (tokenRef.current && token !== tokenRef.current) ||
-      ghToken !== ghTokenRef.current ||
-      ws.readyState === WebSocket.CLOSED ||
-      ws.readyState === WebSocket.CLOSING
-    ) {
-      ws?.close();
-      const baseUrl =
-        import.meta.env.VITE_BACKEND_BASE_URL || window?.location.host;
-      const protocol = window.location.protocol === "https:" ? "wss:" : "ws:";
-      let wsUrl = `${protocol}//${baseUrl}/ws`;
-      if (events.length) {
-        wsUrl += `?latest_event_id=${events[events.length - 1].id}`;
-      }
-      ws = new WebSocket(wsUrl, [
-        "openhands",
-        token || "NO_JWT",
-        ghToken || "NO_GITHUB",
-      ]);
-    }
-    ws.addEventListener("open", handleOpen);
-    ws.addEventListener("message", handleMessage);
-    ws.addEventListener("error", handleError);
-    ws.addEventListener("close", handleClose);
-    wsRef.current = ws;
-    tokenRef.current = token;
-    ghTokenRef.current = ghToken;
-
-    return () => {
-      ws.removeEventListener("open", handleOpen);
-      ws.removeEventListener("message", handleMessage);
-      ws.removeEventListener("error", handleError);
-      ws.removeEventListener("close", handleClose);
-    };
-  }, [enabled, token, ghToken, retryCount]);
-
-  // Strict mode mounts and unmounts each component twice, so we have to wait in the destructor
-  // before actually closing the socket and cancel the operation if the component gets remounted.
-  React.useEffect(() => {
-    const timeout = closeRef.current;
-    if (timeout != null) {
-      clearTimeout(timeout);
-    }
-
-    return () => {
-      closeRef.current = setTimeout(() => {
-        const ws = wsRef.current;
-        if (ws) {
-          ws.removeEventListener("close", handleClose);
-          ws.close();
-        }
-      }, 100);
-    };
-  }, []);
-
-  const value = React.useMemo<UseWsClient>(
-    () => ({
-      status,
-      isLoadingMessages: messageRateHandler.isUnderThreshold,
-      events,
-      send,
-    }),
-    [status, messageRateHandler.isUnderThreshold, events],
-  );
-
-  return (
-    <WsClientContext.Provider value={value}>
-      {children}
-    </WsClientContext.Provider>
-  );
-}
-
-export function useWsClient() {
-  const context = React.useContext(WsClientContext);
-  return context;
-}

frontend/src/entry.client.tsx

@@ -10,28 +10,18 @@ import React, { startTransition, StrictMode } from "react";
 import { hydrateRoot } from "react-dom/client";
 import { Provider } from "react-redux";
 import posthog from "posthog-js";
+import { SocketProvider } from "./context/socket";
 import "./i18n";
 import store from "./store";
-import OpenHands from "./api/open-hands";
 
 function PosthogInit() {
-  const [key, setKey] = React.useState<string | null>(null);
-
   React.useEffect(() => {
-    OpenHands.getConfig().then((config) => {
-      setKey(config.POSTHOG_CLIENT_KEY);
+    posthog.init("phc_3ESMmY9SgqEAGBB6sMGK5ayYHkeUuknH2vP6FmWH9RA", {
+      api_host: "https://us.i.posthog.com",
+      person_profiles: "identified_only",
     });
   }, []);
 
-  React.useEffect(() => {
-    if (key) {
-      posthog.init(key, {
-        api_host: "https://us.i.posthog.com",
-        person_profiles: "identified_only",
-      });
-    }
-  }, [key]);
-
   return null;
 }
 
@@ -53,10 +43,12 @@ prepareApp().then(() =>
     hydrateRoot(
       document,
       <StrictMode>
-        <Provider store={store}>
-          <RemixBrowser />
-          <PosthogInit />
-        </Provider>
+        <SocketProvider>
+          <Provider store={store}>
+            <RemixBrowser />
+            <PosthogInit />
+          </Provider>
+        </SocketProvider>
       </StrictMode>,
     );
   }),