Update run_infer to add github prior knowledge

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

.github/workflows/ghcr-build.yml

@@ -56,7 +56,7 @@ jobs:
           docker-images: false
           swap-storage: true
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3.2.0
+        uses: docker/setup-qemu-action@v3.3.0
         with:
           image: tonistiigi/binfmt:latest
       - name: Login to GHCR
@@ -119,7 +119,7 @@ jobs:
           docker-images: false
           swap-storage: true
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3.2.0
+        uses: docker/setup-qemu-action@v3.3.0
         with:
           image: tonistiigi/binfmt:latest
       - name: Login to GHCR

.github/workflows/integration-runner.yml

@@ -56,6 +56,7 @@ jobs:
           LLM_MODEL: "litellm_proxy/claude-3-5-haiku-20241022"
           LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
           LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 10
         run: |
           echo "[llm.eval]" > config.toml
           echo "model = \"$LLM_MODEL\"" >> config.toml
@@ -70,7 +71,7 @@ jobs:
         env:
           SANDBOX_FORCE_REBUILD_RUNTIME: True
         run: |
-          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' $N_PROCESSES '' 'haiku_run'
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' 10 $N_PROCESSES '' 'haiku_run'
 
           # get integration tests report
           REPORT_FILE_HAIKU=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/*haiku*_maxiter_10_N* -name "report.md" -type f | head -n 1)
@@ -88,6 +89,7 @@ jobs:
           LLM_MODEL: "litellm_proxy/deepseek-chat"
           LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
           LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 10
         run: |
           echo "[llm.eval]" > config.toml
           echo "model = \"$LLM_MODEL\"" >> config.toml
@@ -99,7 +101,7 @@ jobs:
         env:
           SANDBOX_FORCE_REBUILD_RUNTIME: True
         run: |
-          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' $N_PROCESSES '' 'deepseek_run'
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD CodeActAgent '' 10 $N_PROCESSES '' 'deepseek_run'
 
           # get integration tests report
           REPORT_FILE_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/CodeActAgent/deepseek*_maxiter_10_N* -name "report.md" -type f | head -n 1)
@@ -109,11 +111,75 @@ jobs:
           echo >> $GITHUB_ENV
           echo "EOF" >> $GITHUB_ENV
 
+      # -------------------------------------------------------------
+      # Run DelegatorAgent tests for Haiku, limited to t01 and t02
+      - name: Wait a little bit (again)
+        run: sleep 5
+
+      - name: Configure config.toml for testing DelegatorAgent (Haiku)
+        env:
+          LLM_MODEL: "litellm_proxy/claude-3-5-haiku-20241022"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 30
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+
+      - name: Run integration test evaluation for DelegatorAgent (Haiku)
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD DelegatorAgent '' 30 $N_PROCESSES "t01_fix_simple_typo,t02_add_bash_hello" 'delegator_haiku_run'
+
+          # Find and export the delegator test results
+          REPORT_FILE_DELEGATOR_HAIKU=$(find evaluation/evaluation_outputs/outputs/integration_tests/DelegatorAgent/*haiku*_maxiter_30_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE_DELEGATOR_HAIKU: $REPORT_FILE_DELEGATOR_HAIKU"
+          echo "INTEGRATION_TEST_REPORT_DELEGATOR_HAIKU<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_DELEGATOR_HAIKU >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      # -------------------------------------------------------------
+      # Run DelegatorAgent tests for DeepSeek, limited to t01 and t02
+      - name: Wait a little bit (again)
+        run: sleep 5
+
+      - name: Configure config.toml for testing DelegatorAgent (DeepSeek)
+        env:
+          LLM_MODEL: "litellm_proxy/deepseek-chat"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 30
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+
+      - name: Run integration test evaluation for DelegatorAgent (DeepSeek)
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD DelegatorAgent '' 30 $N_PROCESSES "t01_fix_simple_typo,t02_add_bash_hello" 'delegator_deepseek_run'
+
+          # Find and export the delegator test results
+          REPORT_FILE_DELEGATOR_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/DelegatorAgent/deepseek*_maxiter_30_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE_DELEGATOR_DEEPSEEK: $REPORT_FILE_DELEGATOR_DEEPSEEK"
+          echo "INTEGRATION_TEST_REPORT_DELEGATOR_DEEPSEEK<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_DELEGATOR_DEEPSEEK >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
       - name: Create archive of evaluation outputs
         run: |
           TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
           cd evaluation/evaluation_outputs/outputs  # Change to the outputs directory
-          tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/*  # Only include the actual result directories
+          tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/* integration_tests/DelegatorAgent/*  # Only include the actual result directories
 
       - name: Upload evaluation results as artifact
         uses: actions/upload-artifact@v4
@@ -154,5 +220,11 @@ jobs:
               **Integration Tests Report (DeepSeek)**
               DeepSeek LLM Test Results:
               ${{ env.INTEGRATION_TEST_REPORT_DEEPSEEK }}
+              ---
+                **Integration Tests Report Delegator (Haiku)**
+              ${{ env.INTEGRATION_TEST_REPORT_DELEGATOR_HAIKU }}
+              ---
+              **Integration Tests Report Delegator (DeepSeek)**
+              ${{ env.INTEGRATION_TEST_REPORT_DELEGATOR_DEEPSEEK }}
               ---
               Download testing outputs (includes both Haiku and DeepSeek results): [Download](${{ steps.upload_results_artifact.outputs.artifact-url }})

.github/workflows/openhands-resolver.yml

@@ -184,6 +184,7 @@ jobs:
             });
 
       - name: Install OpenHands
+        id: install_openhands
         uses: actions/github-script@v7
         env:
           COMMENT_BODY: ${{ github.event.comment.body || '' }}
@@ -196,7 +197,6 @@ jobs:
             const reviewBody = process.env.REVIEW_BODY.trim();
             const labelName = process.env.LABEL_NAME.trim();
             const eventName = process.env.EVENT_NAME.trim();
-
             // Check conditions
             const isExperimentalLabel = labelName === "fix-me-experimental";
             const isIssueCommentExperimental =
@@ -205,6 +205,9 @@ jobs:
             const isReviewCommentExperimental =
               eventName === "pull_request_review" && reviewBody.includes("@openhands-agent-exp");
 
+            // Set output variable
+            core.setOutput('isExperimental', isExperimentalLabel || isIssueCommentExperimental || isReviewCommentExperimental);
+
             // Perform package installation
             if (isExperimentalLabel || isIssueCommentExperimental || isReviewCommentExperimental) {
               console.log("Installing experimental OpenHands...");
@@ -230,7 +233,8 @@ jobs:
             --issue-number ${{ env.ISSUE_NUMBER }} \
             --issue-type ${{ env.ISSUE_TYPE }} \
             --max-iterations ${{ env.MAX_ITERATIONS }} \
-            --comment-id ${{ env.COMMENT_ID }}
+            --comment-id ${{ env.COMMENT_ID }} \
+            --is-experimental ${{ steps.install_openhands.outputs.isExperimental }}
 
       - name: Check resolution result
         id: check_result

CODE_OF_CONDUCT.md

@@ -18,24 +18,24 @@ diverse, inclusive, and healthy community.
 Examples of behavior that contributes to a positive environment for our
 community include:
 
-* Demonstrating empathy and kindness toward other people
-* Being respectful of differing opinions, viewpoints, and experiences
-* Giving and gracefully accepting constructive feedback
+* Demonstrating empathy and kindness toward other people.
+* Being respectful of differing opinions, viewpoints, and experiences.
+* Giving and gracefully accepting constructive feedback.
 * Accepting responsibility and apologizing to those affected by our mistakes,
-  and learning from the experience
+  and learning from the experience.
 * Focusing on what is best not just for us as individuals, but for the overall
-  community
+  community.
 
 Examples of unacceptable behavior include:
 
 * The use of sexualized language or imagery, and sexual attention or advances of
-  any kind
-* Trolling, insulting or derogatory comments, and personal or political attacks
-* Public or private harassment
+  any kind.
+* Trolling, insulting or derogatory comments, and personal or political attacks.
+* Public or private harassment.
 * Publishing others' private information, such as a physical or email address,
-  without their explicit permission
+  without their explicit permission.
 * Other conduct which could reasonably be considered inappropriate in a
-  professional setting
+  professional setting.
 
 ## Enforcement Responsibilities
 
@@ -61,7 +61,7 @@ representative at an online or offline event.
 
 Instances of abusive, harassing, or otherwise unacceptable behavior may be
 reported to the community leaders responsible for enforcement at
-contact@all-hands.dev
+contact@all-hands.dev.
 All complaints will be reviewed and investigated promptly and fairly.
 
 All community leaders are obligated to respect the privacy and security of the
@@ -113,6 +113,20 @@ individual, or aggression toward or disparagement of classes of individuals.
 **Consequence**: A permanent ban from any sort of public interaction within the
 community.
 
+### Slack and Discord Etiquettes
+
+These Slack and Discord etiquette guidelines are designed to foster an inclusive, respectful, and productive environment for all community members. By following these best practices, we ensure effective communication and collaboration while minimizing disruptions. Let’s work together to build a supportive and welcoming community!
+
+- Communicate respectfully and professionally, avoiding sarcasm or harsh language, and remember that tone can be difficult to interpret in text.
+- Use threads for specific discussions to keep channels organized and easier to follow.
+- Tag others only when their input is critical or urgent, and use @here, @channel or @everyone sparingly to minimize disruptions.
+- Be patient, as open-source contributors and maintainers often have other commitments and may need time to respond.
+- Post questions or discussions in the most relevant channel (e.g., for [slack - #general](https://app.slack.com/client/T06P212QSEA/C06P5NCGSFP) for general topics, [slack - #questions](https://openhands-ai.slack.com/archives/C06U8UTKSAD) for queries/questions, [discord - #general](https://discord.com/channels/1222935860639563850/1222935861386018885)).
+- When asking for help or raising issues, include necessary details like links, screenshots, or clear explanations to provide context.
+- Keep discussions in public channels whenever possible to allow others to benefit from the conversation, unless the matter is sensitive or private.
+- Always adhere to [our standards](https://github.com/All-Hands-AI/OpenHands/blob/main/CODE_OF_CONDUCT.md#our-standards) to ensure a welcoming and collaborative environment.
+- If you choose to mute a channel, consider setting up alerts for topics that still interest you to stay engaged. For Slack, Go to Settings → Notifications → My Keywords to add specific keywords that will notify you when mentioned. For example, if you're here for discussions about LLMs, mute the channel if it’s too busy, but set notifications to alert you only when “LLMs” appears in messages. Also for Discord, go to the channel notifications and choose the option that best describes your need.
+
 ## Attribution
 
 This Code of Conduct is adapted from the [Contributor Covenant][homepage],

CONTRIBUTING.md

@@ -11,11 +11,11 @@ To understand the codebase, please refer to the README in each module:
    - [agenthub](./openhands/agenthub/README.md)
    - [server](./openhands/server/README.md)
 
-## Setting up your development environment
+## Setting up Your Development Environment
 
 We have a separate doc [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md) that tells you how to set up a development workflow.
 
-## How can I contribute?
+## How Can I Contribute?
 
 There are many ways that you can contribute:
 
@@ -23,7 +23,7 @@ There are many ways that you can contribute:
 2. **Send feedback** after each session by [clicking the thumbs-up thumbs-down buttons](https://docs.all-hands.dev/modules/usage/feedback), so we can see where things are working and failing, and also build an open dataset for training code agents.
 3. **Improve the Codebase** by sending [PRs](#sending-pull-requests-to-openhands) (see details below). In particular, we have some [good first issues](https://github.com/All-Hands-AI/OpenHands/labels/good%20first%20issue) that may be ones to start on.
 
-## What can I build?
+## What Can I Build?
 Here are a few ways you can help improve the codebase.
 
 #### UI/UX
@@ -35,7 +35,7 @@ of the application, please open an issue first, or better, join the #frontend ch
 to gather consensus from our design team first.
 
 #### Improving the agent
-Our main agent is the CodeAct agent. You can [see its prompts here](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/agenthub/codeact_agent)
+Our main agent is the CodeAct agent. You can [see its prompts here](https://github.com/All-Hands-AI/OpenHands/tree/main/openhands/agenthub/codeact_agent).
 
 Changes to these prompts, and to the underlying behavior in Python, can have a huge impact on user experience.
 You can try modifying the prompts to see how they change the behavior of the agent as you use the app
@@ -63,7 +63,7 @@ At the moment, we have two kinds of tests: [`unit`](./tests/unit) and [`integrat
 ## Sending Pull Requests to OpenHands
 
 You'll need to fork our repository to send us a Pull Request. You can learn more
-about how to fork a GitHub repo and open a PR with your changes in [this article](https://medium.com/swlh/forks-and-pull-requests-how-to-contribute-to-github-repos-8843fac34ce8)
+about how to fork a GitHub repo and open a PR with your changes in [this article](https://medium.com/swlh/forks-and-pull-requests-how-to-contribute-to-github-repos-8843fac34ce8).
 
 ### Pull Request title
 As described [here](https://github.com/commitizen/conventional-commit-types/blob/master/index.json), a valid PR title should begin with one of the following prefixes:
@@ -103,7 +103,7 @@ Further, if you see an issue you like, please leave a "thumbs-up" or a comment,
 
 ### Making Pull Requests
 
-We're generally happy to consider all [PRs](https://github.com/All-Hands-AI/OpenHands/pulls), with the evaluation process varying based on the type of change:
+We're generally happy to consider all pull requests with the evaluation process varying based on the type of change:
 
 #### For Small Improvements
 

Development.md

@@ -3,9 +3,9 @@ This guide is for people working on OpenHands and editing the source code.
 If you wish to contribute your changes, check out the [CONTRIBUTING.md](https://github.com/All-Hands-AI/OpenHands/blob/main/CONTRIBUTING.md) on how to clone and setup the project initially before moving on.
 Otherwise, you can clone the OpenHands project directly.
 
-## Start the server for development
+## Start the Server for Development
 ### 1. Requirements
-* Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)  [Ubuntu <= 22.04]
+* Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)  [Ubuntu >= 22.04]
 * [Docker](https://docs.docker.com/engine/install/) (For those on MacOS, make sure to allow the default Docker socket to be used from advanced settings!)
 * [Python](https://www.python.org/downloads/) = 3.12
 * [NodeJS](https://nodejs.org/en/download/package-manager) >= 20.x
@@ -58,7 +58,7 @@ See [our documentation](https://docs.all-hands.dev/modules/usage/llms) for recom
 
 ### 4. Running the application
 #### Option A: Run the Full Application
-Once the setup is complete, launching OpenHands is as simple as running a single command. This command starts both the backend and frontend servers seamlessly, allowing you to interact with OpenHands:
+Once the setup is complete, this command starts both the backend and frontend servers, allowing you to interact with OpenHands:
 ```bash
 make run
 ```
@@ -75,11 +75,11 @@ make run
     ```
 
 ### 6. LLM Debugging
-If you encounter any issues with the Language Model (LM) or you're simply curious, you can inspect the actual LLM prompts and responses. To do so, export DEBUG=1 in the environment and restart the backend.
-OpenHands will then log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
+If you encounter any issues with the Language Model (LM) or you're simply curious, export DEBUG=1 in the environment and restart the backend.
+OpenHands will log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
 
 ### 7. Help
-Need assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenHands.
+Need help or info on available targets and commands? Use the help command for all the guidance you need with OpenHands.
 ```bash
 make help
  ```
@@ -93,14 +93,14 @@ poetry run pytest ./tests/unit/test_*.py
 ```
 
 ### 9. Add or update dependency
-1. Add your dependency in `pyproject.toml` or use `poetry add xxx`
-2. Update the poetry.lock file via `poetry lock --no-update`
+1. Add your dependency in `pyproject.toml` or use `poetry add xxx`.
+2. Update the poetry.lock file via `poetry lock --no-update`.
 
 ### 9. Use existing Docker image
 To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker container image by
 setting the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
 
-Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.18-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.20-nikolaik`
 
 ## Develop inside Docker container
 
@@ -110,7 +110,7 @@ TL;DR
 make docker-dev
 ```
 
-See more details [here](./containers/dev/README.md)
+See more details [here](./containers/dev/README.md).
 
 If you are just interested in running `OpenHands` without installing all the required tools on your host.
 

ISSUE_TRIAGE.md

@@ -2,8 +2,8 @@
 These are the procedures and guidelines on how issues are triaged in this repo by the maintainers.
 
 ## General
-* Most issues must be tagged with **enhancement** or **bug**
-* Issues may be tagged with what it relates to (**backend**, **frontend**, **agent quality**, etc.)
+* Most issues must be tagged with **enhancement** or **bug**.
+* Issues may be tagged with what it relates to (**backend**, **frontend**, **agent quality**, etc.).
 
 ## Severity
 * **Low**: Minor issues or affecting single user.
@@ -11,10 +11,10 @@ These are the procedures and guidelines on how issues are triaged in this repo b
 * **Critical**: Affecting all users or potential security issues.
 
 ## Effort
-* Issues may be estimated with effort required (**small effort**, **medium effort**, **large effort**)
+* Issues may be estimated with effort required (**small effort**, **medium effort**, **large effort**).
 
 ## Difficulty
-* Issues with low implementation difficulty may be tagged with **good first issue**
+* Issues with low implementation difficulty may be tagged with **good first issue**.
 
 ## Not Enough Information
 * User is asked to provide more information (logs, how to reproduce, etc.) when the issue is not clear.

README.md

@@ -39,21 +39,21 @@ Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or jump to the [
 ## ⚡ Quick Start
 
 The easiest way to run OpenHands is in Docker.
-See the [Installation](https://docs.all-hands.dev/modules/usage/installation) guide for
+See the [Running OpenHands](https://docs.all-hands.dev/modules/usage/installation) guide for
 system requirements and more information.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18
+    docker.all-hands.dev/all-hands-ai/openhands:0.20
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
@@ -69,7 +69,7 @@ run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules
 interact with it via a [friendly CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode),
 or run it on tagged issues with [a github action](https://docs.all-hands.dev/modules/usage/how-to/github-action).
 
-Visit [Installation](https://docs.all-hands.dev/modules/usage/installation) for more information and setup instructions.
+Visit [Running OpenHands](https://docs.all-hands.dev/modules/usage/installation) for more information and setup instructions.
 
 > [!CAUTION]
 > OpenHands is meant to be run by a single user on their local workstation.

config.template.toml

@@ -23,6 +23,9 @@ workspace_base = "./workspace"
 # Cache directory path
 #cache_dir = "/tmp/cache"
 
+# Reasoning effort for o1 models (low, medium, high, or not set)
+#reasoning_effort = "medium"
+
 # Debugging enabled
 #debug = false
 
@@ -34,7 +37,12 @@ workspace_base = "./workspace"
 
 # 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
-#trajectories_path="./trajectories"
+#save_trajectory_path="./trajectories"
+
+# Path to replay a trajectory, must be a file path
+# If provided, trajectory will be loaded and replayed before the
+# agent responds to any user instruction
+#replay_trajectory_path = ""
 
 # File store path
 #file_store_path = "/tmp/file_store"
@@ -220,8 +228,8 @@ codeact_enable_jupyter = true
 # LLM config group to use
 #llm_config = 'your-llm-config-group'
 
-# Whether to use microagents at all
-#use_microagents = true
+# Whether to use prompt extension (e.g., microagent, repo/runtime info) at all
+#enable_prompt_extensions = true
 
 # List of microagents to disable
 #disabled_microagents = []

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:0.18-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.20-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docker-compose.yml

@@ -1,4 +1,4 @@
-#
+
 services:
   openhands:
     build:
@@ -7,8 +7,8 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.18-nikolaik}
-      - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik}
+      #- SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234} # enable this only if you want a specific non-root sandbox user but you will have to manually adjust permissions of openhands-state for this user
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:
       - "3000:3000"
@@ -16,6 +16,7 @@ services:
       - "host.docker.internal:host-gateway"
     volumes:
       - /var/run/docker.sock:/var/run/docker.sock
+      - ~/.openhands-state:/.openhands-state
       - ${WORKSPACE_BASE:-$PWD/workspace}:/opt/workspace_base
     pull_policy: build
     stdin_open: true

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

@@ -1,5 +1,3 @@
-
-
 # Options de configuration
 
 Ce guide détaille toutes les options de configuration disponibles pour OpenHands, vous aidant à personnaliser son comportement et à l'intégrer avec d'autres services.
@@ -94,7 +92,7 @@ Les options de configuration de base sont définies dans la section `[core]` du
   - Description : Désactiver la couleur dans la sortie du terminal
 
 **Trajectoires**
-- `trajectories_path`
+- `save_trajectory_path`
   - Type : `str`
   - Valeur par défaut : `"./trajectories"`
   - Description : Chemin pour stocker les trajectoires (peut être un dossier ou un fichier). Si c'est un dossier, les trajectoires seront enregistrées dans un fichier nommé avec l'ID de session et l'extension .json, dans ce dossier.
@@ -184,6 +182,10 @@ Les options de configuration LLM (Large Language Model) sont définies dans la s
 
 Pour les utiliser avec la commande docker, passez `-e LLM_<option>`. Exemple : `-e LLM_NUM_RETRIES`.
 
+:::note
+Pour les configurations de développement, vous pouvez également définir des configurations LLM personnalisées. Voir [Configurations LLM personnalisées](./llms/custom-llm-configs) pour plus de détails.
+:::
+
 **Informations d'identification AWS**
 - `aws_access_key_id`
   - Type : `str`
@@ -368,4 +370,26 @@ Les options de configuration de l'agent sont définies dans les sections `[agent
 - `codeact_enable_llm_editor`
   - Type : `bool`
   - Valeur par défaut : `false`
-  - Description : Si l'éditeur LLM est activé dans l'espace d'action (foncti
+  - Description : Si l'éditeur LLM est activé dans l'espace d'action (fonctionne uniquement avec l'appel de fonction)
+
+**Utilisation du micro-agent**
+- `enable_prompt_extensions`
+  - Type : `bool`
+  - Valeur par défaut : `true`
+  - Description : Indique si l'utilisation des micro-agents est activée ou non
+
+- `disabled_microagents`
+  - Type : `list of str`
+  - Valeur par défaut : `None`
+  - Description : Liste des micro-agents à désactiver
+
+### Exécution
+- `timeout`
+  - Type : `int`
+  - Valeur par défaut : `120`
+  - Description : Délai d'expiration du bac à sable, en secondes
+
+- `user_id`
+  - Type : `int`
+  - Valeur par défaut : `1000`
+  - Description : ID de l'utilisateur du bac à sable

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -52,7 +52,7 @@ 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:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -61,7 +61,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.20 \
     python -m openhands.core.cli
 ```
 

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -46,7 +46,7 @@ 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:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -56,6 +56,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.20 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/installation.mdx

@@ -13,16 +13,16 @@
 La façon la plus simple d'exécuter OpenHands est avec Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18
+    docker.all-hands.dev/all-hands-ai/openhands:0.20
 ```
 
 Vous pouvez également exécuter OpenHands en mode [headless scriptable](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), en tant que [CLI interactive](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), ou en utilisant l'[Action GitHub OpenHands](https://docs.all-hands.dev/modules/usage/how-to/github-action).

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/llms/custom-llm-configs.md

@@ -0,0 +1,106 @@
+# Configurations LLM personnalisées
+
+OpenHands permet de définir plusieurs configurations LLM nommées dans votre fichier `config.toml`. Cette fonctionnalité vous permet d'utiliser différentes configurations LLM pour différents usages, comme utiliser un modèle moins coûteux pour les tâches qui ne nécessitent pas de réponses de haute qualité, ou utiliser différents modèles avec différents paramètres pour des agents spécifiques.
+
+## Comment ça fonctionne
+
+Les configurations LLM nommées sont définies dans le fichier `config.toml` en utilisant des sections qui commencent par `llm.`. Par exemple :
+
+```toml
+# Configuration LLM par défaut
+[llm]
+model = "gpt-4"
+api_key = "votre-clé-api"
+temperature = 0.0
+
+# Configuration LLM personnalisée pour un modèle moins coûteux
+[llm.gpt3]
+model = "gpt-3.5-turbo"
+api_key = "votre-clé-api"
+temperature = 0.2
+
+# Une autre configuration personnalisée avec des paramètres différents
+[llm.haute-creativite]
+model = "gpt-4"
+api_key = "votre-clé-api"
+temperature = 0.8
+top_p = 0.9
+```
+
+Chaque configuration nommée hérite de tous les paramètres de la section `[llm]` par défaut et peut remplacer n'importe lequel de ces paramètres. Vous pouvez définir autant de configurations personnalisées que nécessaire.
+
+## Utilisation des configurations personnalisées
+
+### Avec les agents
+
+Vous pouvez spécifier quelle configuration LLM un agent doit utiliser en définissant le paramètre `llm_config` dans la section de configuration de l'agent :
+
+```toml
+[agent.RepoExplorerAgent]
+# Utiliser la configuration GPT-3 moins coûteuse pour cet agent
+llm_config = 'gpt3'
+
+[agent.CodeWriterAgent]
+# Utiliser la configuration haute créativité pour cet agent
+llm_config = 'haute-creativite'
+```
+
+### Options de configuration
+
+Chaque configuration LLM nommée prend en charge toutes les mêmes options que la configuration LLM par défaut. Celles-ci incluent :
+
+- Sélection du modèle (`model`)
+- Configuration de l'API (`api_key`, `base_url`, etc.)
+- Paramètres du modèle (`temperature`, `top_p`, etc.)
+- Paramètres de nouvelle tentative (`num_retries`, `retry_multiplier`, etc.)
+- Limites de jetons (`max_input_tokens`, `max_output_tokens`)
+- Et toutes les autres options de configuration LLM
+
+Pour une liste complète des options disponibles, consultez la section Configuration LLM dans la documentation des [Options de configuration](../configuration-options).
+
+## Cas d'utilisation
+
+Les configurations LLM personnalisées sont particulièrement utiles dans plusieurs scénarios :
+
+- **Optimisation des coûts** : Utiliser des modèles moins coûteux pour les tâches qui ne nécessitent pas de réponses de haute qualité, comme l'exploration de dépôt ou les opérations simples sur les fichiers.
+- **Réglage spécifique aux tâches** : Configurer différentes valeurs de température et de top_p pour les tâches qui nécessitent différents niveaux de créativité ou de déterminisme.
+- **Différents fournisseurs** : Utiliser différents fournisseurs LLM ou points d'accès API pour différentes tâches.
+- **Tests et développement** : Basculer facilement entre différentes configurations de modèles pendant le développement et les tests.
+
+## Exemple : Optimisation des coûts
+
+Un exemple pratique d'utilisation des configurations LLM personnalisées pour optimiser les coûts :
+
+```toml
+# Configuration par défaut utilisant GPT-4 pour des réponses de haute qualité
+[llm]
+model = "gpt-4"
+api_key = "votre-clé-api"
+temperature = 0.0
+
+# Configuration moins coûteuse pour l'exploration de dépôt
+[llm.repo-explorer]
+model = "gpt-3.5-turbo"
+temperature = 0.2
+
+# Configuration pour la génération de code
+[llm.code-gen]
+model = "gpt-4"
+temperature = 0.0
+max_output_tokens = 2000
+
+[agent.RepoExplorerAgent]
+llm_config = 'repo-explorer'
+
+[agent.CodeWriterAgent]
+llm_config = 'code-gen'
+```
+
+Dans cet exemple :
+- L'exploration de dépôt utilise un modèle moins coûteux car il s'agit principalement de comprendre et de naviguer dans le code
+- La génération de code utilise GPT-4 avec une limite de jetons plus élevée pour générer des blocs de code plus importants
+- La configuration par défaut reste disponible pour les autres tâches
+
+:::note
+Les configurations LLM personnalisées ne sont disponibles que lors de l'utilisation d'OpenHands en mode développement, via `main.py` ou `cli.py`. Lors de l'exécution via `docker run`, veuillez utiliser les options de configuration standard.
+:::

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

@@ -13,7 +13,7 @@ C'est le Runtime par défaut qui est utilisé lorsque vous démarrez OpenHands.
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

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

@@ -91,7 +91,7 @@
   - 描述: 禁用终端输出中的颜色
 
 **轨迹**
-- `trajectories_path`
+- `save_trajectory_path`
   - 类型: `str`
   - 默认值: `"./trajectories"`
   - 描述: 存储轨迹的路径(可以是文件夹或文件)。如果是文件夹,轨迹将保存在该文件夹中以会话 ID 命名的 .json 文件中。
@@ -373,7 +373,7 @@ Agent 配置选项在 `config.toml` 文件的 `[agent]` 和 `[agent.<agent_name>
   - 描述: 是否在 action space 中启用 Jupyter
 
 **Microagent 使用**
-- `use_microagents`
+- `enable_prompt_extensions`
   - 类型: `bool`
   - 默认值: `true`
   - 描述: 是否使用 microagents

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/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:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.20-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:0.18 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.20 \
     python -m openhands.core.cli
 ```
 

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -47,7 +47,7 @@ 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:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -57,6 +57,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.20 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/installation.mdx

@@ -11,16 +11,16 @@
 在 Docker 中运行 OpenHands 是最简单的方式。
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18
+    docker.all-hands.dev/all-hands-ai/openhands:0.20
 ```
 
 你也可以在可脚本化的[无头模式](https://docs.all-hands.dev/modules/usage/how-to/headless-mode)下运行 OpenHands，作为[交互式 CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode)，或使用 [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action)。

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

@@ -11,7 +11,7 @@
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/modules/usage/configuration-options.md

@@ -7,53 +7,11 @@ If you are running in [GUI Mode](https://docs.all-hands.dev/modules/usage/how-to
 take precedence.
 :::
 
----
-
-# Table of Contents
-
-- [Core Configuration](#core-configuration)
-   - [API Keys](#api-keys)
-   - [Workspace](#workspace)
-   - [Debugging and Logging](#debugging-and-logging)
-   - [Session Management](#session-management)
-   - [Trajectories](#trajectories)
-   - [File Store](#file-store)
-   - [Task Management](#task-management)
-   - [Sandbox Configuration](#sandbox-configuration)
-   - [Miscellaneous](#miscellaneous)
-- [LLM Configuration](#llm-configuration)
-   - [AWS Credentials](#aws-credentials)
-   - [API Configuration](#api-configuration)
-   - [Custom LLM Provider](#custom-llm-provider)
-   - [Embeddings](#embeddings)
-   - [Message Handling](#message-handling)
-   - [Model Selection](#model-selection)
-   - [Retrying](#retrying)
-   - [Advanced Options](#advanced-options)
-- [Agent Configuration](#agent-configuration)
-   - [Microagent Configuration](#microagent-configuration)
-   - [Memory Configuration](#memory-configuration)
-   - [LLM Configuration](#llm-configuration-2)
-   - [ActionSpace Configuration](#actionspace-configuration)
-   - [Microagent Usage](#microagent-usage)
-- [Sandbox Configuration](#sandbox-configuration)
-   - [Execution](#execution)
-   - [Container Image](#container-image)
-   - [Networking](#networking)
-   - [Linting and Plugins](#linting-and-plugins)
-   - [Dependencies and Environment](#dependencies-and-environment)
-   - [Evaluation](#evaluation)
-- [Security Configuration](#security-configuration)
-   - [Confirmation Mode](#confirmation-mode)
-   - [Security Analyzer](#security-analyzer)
-
----
-
 ## Core Configuration
 
 The core configuration options are defined in the `[core]` section of the `config.toml` file.
 
-**API Keys**
+### API Keys
 - `e2b_api_key`
   - Type: `str`
   - Default: `""`
@@ -69,7 +27,7 @@ The core configuration options are defined in the `[core]` section of the `confi
   - Default: `""`
   - Description: API token secret for Modal
 
-**Workspace**
+### Workspace
 - `workspace_base`
   - Type: `str`
   - Default: `"./workspace"`
@@ -80,7 +38,7 @@ The core configuration options are defined in the `[core]` section of the `confi
   - Default: `"/tmp/cache"`
   - Description: Cache directory path
 
-**Debugging and Logging**
+### Debugging and Logging
 - `debug`
   - Type: `bool`
   - Default: `false`
@@ -91,13 +49,18 @@ The core configuration options are defined in the `[core]` section of the `confi
   - Default: `false`
   - Description: Disable color in terminal output
 
-**Trajectories**
-- `trajectories_path`
+### Trajectories
+- `save_trajectory_path`
   - Type: `str`
   - Default: `"./trajectories"`
   - Description: Path to store trajectories (can be a folder or a file). If it's a folder, the trajectories will be saved in a file named with the session id name and .json extension, in that folder.
 
-**File Store**
+- `replay_trajectory_path`
+  - Type: `str`
+  - Default: `""`
+  - Description: Path to load a trajectory and replay. If given, must be a path to the trajectory file in JSON format. The actions in the trajectory file would be replayed first before any user instruction is executed.
+
+### File Store
 - `file_store_path`
   - Type: `str`
   - Default: `"/tmp/file_store"`
@@ -128,7 +91,7 @@ The core configuration options are defined in the `[core]` section of the `confi
   - Default: `[".*"]`
   - Description: List of allowed file extensions for uploads
 
-**Task Management**
+### Task Management
 - `max_budget_per_task`
   - Type: `float`
   - Default: `0.0`
@@ -139,7 +102,7 @@ The core configuration options are defined in the `[core]` section of the `confi
   - Default: `100`
   - Description: Maximum number of iterations
 
-**Sandbox Configuration**
+### Sandbox Configuration
 - `workspace_mount_path_in_sandbox`
   - Type: `str`
   - Default: `"/workspace"`
@@ -155,7 +118,7 @@ The core configuration options are defined in the `[core]` section of the `confi
   - Default: `""`
   - Description: Path to rewrite the workspace mount path to. You can usually ignore this, it refers to special cases of running inside another container.
 
-**Miscellaneous**
+### Miscellaneous
 - `run_as_openhands`
   - Type: `bool`
   - Default: `true`
@@ -182,6 +145,10 @@ The LLM (Large Language Model) configuration options are defined in the `[llm]`
 
 To use these with the docker command, pass in `-e LLM_<option>`. Example: `-e LLM_NUM_RETRIES`.
 
+:::note
+For development setups, you can also define custom named LLM configurations. See [Custom LLM Configurations](./llms/custom-llm-configs) for details.
+:::
+
 **AWS Credentials**
 - `aws_access_key_id`
   - Type: `str`
@@ -198,7 +165,7 @@ To use these with the docker command, pass in `-e LLM_<option>`. Example: `-e LL
   - Default: `""`
   - Description: AWS secret access key
 
-**API Configuration**
+### API Configuration
 - `api_key`
   - Type: `str`
   - Default: `None`
@@ -224,13 +191,13 @@ To use these with the docker command, pass in `-e LLM_<option>`. Example: `-e LL
   - Default: `0.0`
   - Description: Cost per output token
 
-**Custom LLM Provider**
+### Custom LLM Provider
 - `custom_llm_provider`
   - Type: `str`
   - Default: `""`
   - Description: Custom LLM provider
 
-**Embeddings**
+### Embeddings
 - `embedding_base_url`
   - Type: `str`
   - Default: `""`
@@ -246,7 +213,7 @@ To use these with the docker command, pass in `-e LLM_<option>`. Example: `-e LL
   - Default: `"local"`
   - Description: Embedding model to use
 
-**Message Handling**
+### Message Handling
 - `max_message_chars`
   - Type: `int`
   - Default: `30000`
@@ -262,13 +229,13 @@ To use these with the docker command, pass in `-e LLM_<option>`. Example: `-e LL
   - Default: `0`
   - Description: Maximum number of output tokens
 
-**Model Selection**
+### Model Selection
 - `model`
   - Type: `str`
   - Default: `"claude-3-5-sonnet-20241022"`
   - Description: Model to use
 
-**Retrying**
+### Retrying
 - `num_retries`
   - Type: `int`
   - Default: `8`
@@ -289,7 +256,7 @@ To use these with the docker command, pass in `-e LLM_<option>`. Example: `-e LL
   - Default: `2.0`
   - Description: Multiplier for exponential backoff calculation
 
-**Advanced Options**
+### Advanced Options
 - `drop_params`
   - Type: `bool`
   - Default: `false`
@@ -329,13 +296,13 @@ To use these with the docker command, pass in `-e LLM_<option>`. Example: `-e LL
 
 The agent configuration options are defined in the `[agent]` and `[agent.<agent_name>]` sections of the `config.toml` file.
 
-**Microagent Configuration**
+### Microagent Configuration
 - `micro_agent_name`
   - Type: `str`
   - Default: `""`
   - Description: Name of the micro agent to use for this agent
 
-**Memory Configuration**
+### Memory Configuration
 - `memory_enabled`
   - Type: `bool`
   - Default: `false`
@@ -346,13 +313,13 @@ The agent configuration options are defined in the `[agent]` and `[agent.<agent_
   - Default: `3`
   - Description: The maximum number of threads indexing at the same time for embeddings
 
-**LLM Configuration**
+### LLM Configuration
 - `llm_config`
   - Type: `str`
   - Default: `'your-llm-config-group'`
   - Description: The name of the LLM config to use
 
-**ActionSpace Configuration**
+### ActionSpace Configuration
 - `function_calling`
   - Type: `bool`
   - Default: `true`
@@ -373,8 +340,8 @@ The agent configuration options are defined in the `[agent]` and `[agent.<agent_
   - Default: `false`
   - Description: Whether Jupyter is enabled in the action space
 
-**Microagent Usage**
-- `use_microagents`
+### Microagent Usage
+- `enable_prompt_extensions`
   - Type: `bool`
   - Default: `true`
   - Description: Whether to use microagents at all
@@ -390,7 +357,7 @@ The sandbox configuration options are defined in the `[sandbox]` section of the
 
 To use these with the docker command, pass in `-e SANDBOX_<option>`. Example: `-e SANDBOX_TIMEOUT`.
 
-**Execution**
+### Execution
 - `timeout`
   - Type: `int`
   - Default: `120`
@@ -401,19 +368,19 @@ To use these with the docker command, pass in `-e SANDBOX_<option>`. Example: `-
   - Default: `1000`
   - Description: Sandbox user ID
 
-**Container Image**
+### Container Image
 - `base_container_image`
   - Type: `str`
   - Default: `"nikolaik/python-nodejs:python3.12-nodejs22"`
   - Description: Container image to use for the sandbox
 
-**Networking**
+### Networking
 - `use_host_network`
   - Type: `bool`
   - Default: `false`
   - Description: Use host network
 
-**Linting and Plugins**
+### Linting and Plugins
 - `enable_auto_lint`
   - Type: `bool`
   - Default: `false`
@@ -424,7 +391,7 @@ To use these with the docker command, pass in `-e SANDBOX_<option>`. Example: `-
   - Default: `true`
   - Description: Whether to initialize plugins
 
-**Dependencies and Environment**
+### Dependencies and Environment
 - `runtime_extra_deps`
   - Type: `str`
   - Default: `""`
@@ -435,7 +402,7 @@ To use these with the docker command, pass in `-e SANDBOX_<option>`. Example: `-
   - Default: `{}`
   - Description: Environment variables to set at the launch of the runtime
 
-**Evaluation**
+### Evaluation
 - `browsergym_eval_env`
   - Type: `str`
   - Default: `""`
@@ -447,13 +414,13 @@ The security configuration options are defined in the `[security]` section of th
 
 To use these with the docker command, pass in `-e SECURITY_<option>`. Example: `-e SECURITY_CONFIRMATION_MODE`.
 
-**Confirmation Mode**
+### Confirmation Mode
 - `confirmation_mode`
   - Type: `bool`
   - Default: `false`
   - Description: Enable confirmation mode
 
-**Security Analyzer**
+### Security Analyzer
 - `security_analyzer`
   - Type: `str`
   - Default: `""`

docs/modules/usage/getting-started.mdx

@@ -1,6 +1,6 @@
 # Getting Started with OpenHands
 
-So you've [installed OpenHands](./installation) and have
+So you've [run OpenHands](./installation) and have
 [set up your LLM](./installation#setup). Now what?
 
 OpenHands can help you tackle a wide variety of engineering tasks. But the technology

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

@@ -35,7 +35,7 @@ To run OpenHands in CLI mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -45,7 +45,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.20 \
     python -m openhands.core.cli
 ```
 
@@ -58,7 +58,7 @@ Here are some examples of CLI commands and their expected outputs:
 ### Example 1: Simple Task
 
 ```bash
-How can I help? >> Write a Python script that prints "Hello, World!"
+>> Write a Python script that prints "Hello, World!"
 ```
 
 Expected Output:
@@ -72,7 +72,7 @@ Expected Output:
 ### Example 2: Bash Command
 
 ```bash
-How can I help? >> Create a directory named "test_dir"
+>> Create a directory named "test_dir"
 ```
 
 Expected Output:
@@ -86,7 +86,7 @@ Expected Output:
 ### Example 3: Error Handling
 
 ```bash
-How can I help? >> Delete a non-existent file
+>> Delete a non-existent file
 ```
 
 Expected Output:

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

@@ -18,15 +18,21 @@ If you choose the first option, you can skip the `Create Your Docker Image` sect
 
 To create a custom Docker image, it must be Debian based.
 
-For example, if you want OpenHands to have `ruby` installed, create a `Dockerfile` with the following content:
+For example, if you want OpenHands to have `ruby` installed, you could create a `Dockerfile` with the following content:
 
 ```dockerfile
-FROM debian:latest
+FROM nikolaik/python-nodejs:python3.12-nodejs22
 
 # Install required packages
 RUN apt-get update && apt-get install -y ruby
 ```
 
+Or you could use a Ruby-specific base image:
+
+```dockerfile
+FROM ruby:latest
+```
+
 Save this file in a folder. Then, build your Docker image (e.g., named custom-image) by navigating to the folder in
 the terminal and running::
 ```bash
@@ -55,6 +61,28 @@ This can be an image you’ve already pulled or one you’ve built:
 sandbox_base_container_image="custom-image"
 ```
 
+### Additional Configuration Options
+
+The `config.toml` file supports several other options for customizing your sandbox:
+
+```toml
+[core]
+# Install additional dependencies when the runtime is built
+# Can contain any valid shell commands
+# If you need the path to the Python interpreter in any of these commands, you can use the $OH_INTERPRETER_PATH variable
+runtime_extra_deps = """
+pip install numpy pandas
+apt-get update && apt-get install -y ffmpeg
+"""
+
+# Set environment variables for the runtime
+# Useful for configuration that needs to be available at runtime
+runtime_startup_env_vars = { DATABASE_URL = "postgresql://user:pass@localhost/db" }
+
+# Specify platform for multi-architecture builds (e.g., "linux/amd64" or "linux/arm64")
+platform = "linux/amd64"
+```
+
 ### Run
 
 Run OpenHands by running ```make run``` in the top level directory.

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

@@ -76,18 +76,18 @@ When using OpenHands in online mode, the GitHub OAuth flow:
 
 Common issues and solutions:
 
-1. **Token Not Recognized**:
+- **Token Not Recognized**:
    - Ensure the token is properly saved in settings.
    - Check that the token hasn't expired.
    - Verify the token has the required scopes.
    - Try regenerating the token.
 
-2. **Organization Access Denied**:
+- **Organization Access Denied**:
    - Check if SSO is required but not enabled.
    - Verify organization membership.
    - Contact organization admin if token policies are blocking access.
 
-3. **Verifying Token Works**:
+- **Verifying Token Works**:
    - The app will show a green checkmark if the token is valid.
    - Try accessing a repository to confirm permissions.
    - Check the browser console for any error messages.

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

@@ -32,7 +32,7 @@ To run OpenHands in Headless mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -43,7 +43,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.20 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/modules/usage/how-to/persist-session-data.md

@@ -1,16 +0,0 @@
-# Persisting Session Data
-
-Using the standard Development Workflow, the session data is stored in memory. Currently, if OpenHands' service is restarted,
-previous sessions become invalid (a new secret is generated) and thus not recoverable.
-
-## How to Persist Session Data
-
-### Development Workflow
-In the `config.toml` file, specify the following:
-```
-[core]
-...
-file_store="local"
-file_store_path="/absolute/path/to/openhands/cache/directory"
-jwt_secret="secretpass"
-```

docs/modules/usage/installation.mdx

@@ -1,27 +1,66 @@
-# Installation
+# Running OpenHands
 
 ## System Requirements
 
-- Docker version 26.0.0+ or Docker Desktop 4.31.0+.
-- You must be using Linux or Mac OS.
-  - If you are on Windows, you must use [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
+- MacOS with [Docker Desktop support](https://docs.docker.com/desktop/setup/install/mac-install/#system-requirements)
+- Linux
+- Windows with [WSL](https://learn.microsoft.com/en-us/windows/wsl/install) and [Docker Desktop support](https://docs.docker.com/desktop/setup/install/windows-install/#system-requirements)
 
-## Start the app
+## Prerequisites
+
+<details>
+  <summary>MacOS</summary>
+  ### Docker Desktop
+
+  1. [Install Docker Desktop on Mac](https://docs.docker.com/desktop/setup/install/mac-install).
+  2. Open Docker Desktop, go to `Settings > Advanced` and ensure `Allow the default Docker socket to be used` is enabled.
+</details>
+
+<details>
+  <summary>Linux</summary>
+
+  :::note
+  Tested with Ubuntu 22.04.
+  :::
+
+  ### Docker Desktop
+
+  1. [Install Docker Desktop on Linux](https://docs.docker.com/desktop/setup/install/linux/).
+
+</details>
+
+<details>
+  <summary>Windows</summary>
+  ### WSL
+
+  1. [Install WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
+  2. Run `wsl --version` in powershell and confirm `Default Version: 2`.
+
+  ### Docker Desktop
+
+  1. [Install Docker Desktop on Windows](https://docs.docker.com/desktop/setup/install/windows-install).
+  2. Open Docker Desktop, go to `Settings` and confirm the following:
+  - General: `Use the WSL 2 based engine` is enabled.
+  - Resources > WSL Integration: `Enable integration with my default WSL distro` is enabled.
+
+</details>
+
+## Start the App
 
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.18
+    docker.all-hands.dev/all-hands-ai/openhands:0.20
 ```
 
 You'll find OpenHands running at http://localhost:3000!

docs/modules/usage/llms/custom-llm-configs.md

@@ -0,0 +1,136 @@
+# Custom LLM Configurations
+
+OpenHands supports defining multiple named LLM configurations in your `config.toml` file. This feature allows you to use different LLM configurations for different purposes, such as using a cheaper model for tasks that don't require high-quality responses, or using different models with different parameters for specific agents.
+
+## How It Works
+
+Named LLM configurations are defined in the `config.toml` file using sections that start with `llm.`. For example:
+
+```toml
+# Default LLM configuration
+[llm]
+model = "gpt-4"
+api_key = "your-api-key"
+temperature = 0.0
+
+# Custom LLM configuration for a cheaper model
+[llm.gpt3]
+model = "gpt-3.5-turbo"
+api_key = "your-api-key"
+temperature = 0.2
+
+# Another custom configuration with different parameters
+[llm.high-creativity]
+model = "gpt-4"
+api_key = "your-api-key"
+temperature = 0.8
+top_p = 0.9
+```
+
+Each named configuration inherits all settings from the default `[llm]` section and can override any of those settings. You can define as many custom configurations as needed.
+
+## Using Custom Configurations
+
+### With Agents
+
+You can specify which LLM configuration an agent should use by setting the `llm_config` parameter in the agent's configuration section:
+
+```toml
+[agent.RepoExplorerAgent]
+# Use the cheaper GPT-3 configuration for this agent
+llm_config = 'gpt3'
+
+[agent.CodeWriterAgent]
+# Use the high creativity configuration for this agent
+llm_config = 'high-creativity'
+```
+
+### Configuration Options
+
+Each named LLM configuration supports all the same options as the default LLM configuration. These include:
+
+- Model selection (`model`)
+- API configuration (`api_key`, `base_url`, etc.)
+- Model parameters (`temperature`, `top_p`, etc.)
+- Retry settings (`num_retries`, `retry_multiplier`, etc.)
+- Token limits (`max_input_tokens`, `max_output_tokens`)
+- And all other LLM configuration options
+
+For a complete list of available options, see the LLM Configuration section in the [Configuration Options](../configuration-options) documentation.
+
+## Use Cases
+
+Custom LLM configurations are particularly useful in several scenarios:
+
+- **Cost Optimization**: Use cheaper models for tasks that don't require high-quality responses, like repository exploration or simple file operations.
+- **Task-Specific Tuning**: Configure different temperature and top_p values for tasks that require different levels of creativity or determinism.
+- **Different Providers**: Use different LLM providers or API endpoints for different tasks.
+- **Testing and Development**: Easily switch between different model configurations during development and testing.
+
+## Example: Cost Optimization
+
+A practical example of using custom LLM configurations to optimize costs:
+
+```toml
+# Default configuration using GPT-4 for high-quality responses
+[llm]
+model = "gpt-4"
+api_key = "your-api-key"
+temperature = 0.0
+
+# Cheaper configuration for repository exploration
+[llm.repo-explorer]
+model = "gpt-3.5-turbo"
+temperature = 0.2
+
+# Configuration for code generation
+[llm.code-gen]
+model = "gpt-4"
+temperature = 0.0
+max_output_tokens = 2000
+
+[agent.RepoExplorerAgent]
+llm_config = 'repo-explorer'
+
+[agent.CodeWriterAgent]
+llm_config = 'code-gen'
+```
+
+In this example:
+- Repository exploration uses a cheaper model since it mainly involves understanding and navigating code
+- Code generation uses GPT-4 with a higher token limit for generating larger code blocks
+- The default configuration remains available for other tasks
+
+# Custom Configurations with Reserved Names
+
+OpenHands can use custom LLM configurations named with reserved names, for specific use cases. If you specify the model and other settings under the reserved names, then OpenHands will load and them for a specific purpose. As of now, one such configuration is implemented: draft editor.
+
+## Draft Editor Configuration
+
+The `draft_editor` configuration is a group of settings you can provide, to specify the model to use for preliminary drafting of code edits, for any tasks that involve editing and refining code. You need to provide it under the section `[llm.draft_editor]`.
+
+For example, you can define in `config.toml` a draft editor like this:
+
+```toml
+[llm.draft_editor]
+model = "gpt-4"
+temperature = 0.2
+top_p = 0.95
+presence_penalty = 0.0
+frequency_penalty = 0.0
+```
+
+This configuration:
+- Uses GPT-4 for high-quality edits and suggestions
+- Sets a low temperature (0.2) to maintain consistency while allowing some flexibility
+- Uses a high top_p value (0.95) to consider a wide range of token options
+- Disables presence and frequency penalties to maintain focus on the specific edits needed
+
+Use this configuration when you want to let an LLM draft edits before making them. In general, it may be useful to:
+- Review and suggest code improvements
+- Refine existing content while maintaining its core meaning
+- Make precise, focused changes to code or text
+
+:::note
+Custom LLM configurations are only available when using OpenHands in development mode, via `main.py` or `cli.py`. When running via `docker run`, please use the standard configuration options.
+:::

docs/modules/usage/llms/llms.md

@@ -5,23 +5,14 @@ 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).
-
-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.
-- 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.
-
-Please refer to the [full article](https://www.all-hands.dev/blog/evaluation-of-llms-as-coding-agents-on-swe-bench-at-30x-speed) for more details.
+recommendations for model selection. Our latest benchmarking results can be found in [this spreadsheet](https://docs.google.com/spreadsheets/d/1wOUdFCMyY6Nt0AIqF705KN4JKOWgeI4wUGUP60krXXs/edit?gid=0).
 
 Based on these findings and community feedback, the following models have been verified to work reasonably well with OpenHands:
 
-- claude-3-5-sonnet (recommended)
-- gpt-4 / gpt-4o
-- llama-3.1-405b
-- deepseek-v2.5
+- anthropic/claude-3-5-sonnet-20241022 (recommended)
+- anthropic/claude-3-5-haiku-20241022
+- deepseek/deepseek-chat
+- gpt-4o
 
 :::warning
 OpenHands will issue many prompts to the LLM you configure. Most of these LLMs cost money, so be sure to set spending

docs/modules/usage/prompting/customization.md

@@ -1,67 +0,0 @@
-# Customizing Agent Behavior
-
-OpenHands can be customized to work more effectively with specific repositories by providing repository-specific context and guidelines. This section explains how to optimize OpenHands for your project.
-
-## Repository Configuration
-
-You can customize OpenHands' behavior for your repository by creating a `.openhands` directory in your repository's root. At minimum, it should contain the file
-`.openhands/microagents/repo.md`, which includes instructions that will
-be given to the agent every time it works with this repository.
-
-We suggest including the following information:
-- **Repository Overview**: A brief description of your project's purpose and architecture.
-- **Directory Structure**: Key directories and their purposes.
-- **Development Guidelines**: Project-specific coding standards and practices.
-- **Testing Requirements**: How to run tests and what types of tests are required.
-- **Setup Instructions**: Steps needed to build and run the project.
-
-### Example Repository Configuration
-Example `.openhands/microagents/repo.md` file:
-```
-Repository: MyProject
-Description: A web application for task management
-
-Directory Structure:
-- src/: Main application code
-- tests/: Test files
-- docs/: Documentation
-
-Setup:
-- Run `npm install` to install dependencies
-- Use `npm run dev` for development
-- Run `npm test` for testing
-
-Guidelines:
-- Follow ESLint configuration
-- Write tests for all new features
-- Use TypeScript for new code
-```
-
-### Customizing Prompts
-
-When working with a repository:
-
-- **Reference Project Standards**: Mention specific coding standards or patterns used in your project.
-- **Include Context**: Reference relevant documentation or existing implementations.
-- **Specify Testing Requirements**: Include project-specific testing requirements in your prompts.
-
-Example customized prompt:
-```
-Add a new task completion feature to src/components/TaskList.tsx following our existing component patterns.
-Include unit tests in tests/components/ and update the documentation in docs/features/.
-The component should use our shared styling from src/styles/components.
-```
-
-### Best Practices for Repository Customization
-
-- **Keep Instructions Updated**: Regularly update your `.openhands` directory as your project evolves.
-- **Be Specific**: Include specific paths, patterns, and requirements unique to your project.
-- **Document Dependencies**: List all tools and dependencies required for development.
-- **Include Examples**: Provide examples of good code patterns from your project.
-- **Specify Conventions**: Document naming conventions, file organization, and code style preferences.
-
-By customizing OpenHands for your repository, you'll get more accurate and consistent results that align with your project's standards and requirements.
-
-## Other Microagents
-You can create other instructions in the `.openhands/microagents/` directory
-that will be sent to the agent if a particular keyword is found, like `test`, `frontend`, or `migration`. See [Micro-Agents](microagents.md) for more information.

docs/modules/usage/prompting/microagents-overview.md

@@ -0,0 +1,36 @@
+# Microagents Overview
+
+Microagents are specialized prompts that enhance OpenHands with domain-specific knowledge, repository-specific context
+and task-specific workflows. They help by providing expert guidance, automating common tasks, and ensuring
+consistent practices across projects.
+
+## Microagent Types
+
+Currently OpenHands supports the following types of microagents:
+
+* [Repository Microagents](./microagents-repo): Repository-specific context and guidelines for OpenHands.
+* [Public Microagents](./microagents-public): General guidelines triggered by keywords for all OpenHands users.
+
+When OpenHands works with a repository, it:
+
+1. Loads repository-specific instructions from `.openhands/microagents/` if present in the repository.
+2. Loads general guidelines triggered by keywords in conversations.
+See current [Public Microagents](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge).
+
+## Microagent Format
+
+All microagents use markdown files with YAML frontmatter that have special instructions to help OpenHands accomplish
+tasks:
+```
+---
+name: <Name of the microagent>
+type: <MicroAgent type>
+version: <MicroAgent version>
+agent: <The agent type (Typically CodeActAgent)>
+triggers:
+- <Optional keywords triggering the microagent. If triggers are removed, it will always be included>
+---
+
+<Markdown with any special guidelines, instructions, and prompts that OpenHands should follow.
+Check out the specific documentation for each microagent on best practices for more information.>
+```

docs/modules/usage/prompting/microagents-public.md

@@ -0,0 +1,153 @@
+# Public Microagents
+
+## Overview
+
+Public microagents are specialized guidelines triggered by keywords for all OpenHands users.
+They are defined in markdown files under the
+[`microagents/knowledge/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge) directory.
+
+Public microagents:
+- Monitor incoming commands for their trigger words.
+- Activate when relevant triggers are detected.
+- Apply their specialized knowledge and capabilities.
+- Follow their specific guidelines and restrictions.
+
+## Current Public Microagents
+
+For more information about specific microagents, refer to their individual documentation files in
+the [`microagents/knowledge/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge/) directory.
+
+### GitHub Agent
+**File**: `github.md`
+**Triggers**: `github`, `git`
+
+The GitHub agent specializes in GitHub API interactions and repository management. It:
+- Has access to a `GITHUB_TOKEN` for API authentication.
+- Follows strict guidelines for repository interactions.
+- Handles branch management and pull requests.
+- Uses the GitHub API instead of web browser interactions.
+
+Key features:
+- Branch protection (prevents direct pushes to main/master)
+- Automated PR creation
+- Git configuration management
+- API-first approach for GitHub operations
+
+Usage Example:
+
+```bash
+git checkout -b feature-branch
+git commit -m "Add new feature"
+git push origin feature-branch
+```
+
+### NPM Agent
+**File**: `npm.md`
+**Triggers**: `npm`
+
+Specializes in handling npm package management with specific focus on:
+- Non-interactive shell operations.
+- Automated confirmation handling using Unix 'yes' command.
+- Package installation automation.
+
+Usage Example:
+
+```bash
+yes | npm install package-name
+```
+
+## Contributing a Public Microagent
+
+You can create your own public microagents by adding new markdown files to the
+[`microagents/knowledge/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge/) directory.
+
+### Public Microagents Best Practices
+
+- **Clear Scope**: Keep the microagent focused on a specific domain or task.
+- **Explicit Instructions**: Provide clear, unambiguous guidelines.
+- **Useful Examples**: Include practical examples of common use cases.
+- **Safety First**: Include necessary warnings and constraints.
+- **Integration Awareness**: Consider how the microagent interacts with other components.
+
+### Steps to Contribute a Public Microagent
+
+#### 1. Plan the Public Microagent
+
+Before creating a public microagent, consider:
+- What specific problem or use case will it address?
+- What unique capabilities or knowledge should it have?
+- What trigger words make sense for activating it?
+- What constraints or guidelines should it follow?
+
+#### 2. Create File
+
+Create a new markdown file in [`microagents/knowledge/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge/)
+with a descriptive name (e.g., `docker.md` for a Docker-focused agent).
+
+Update the file with the required frontmatter [according to the required format](./microagents-overview#microagent-format)
+and the required specialized guidelines while following the [best practices above](#public-microagents-best-practices).
+
+#### 3. Testing the Public Microagent
+
+- Test the agent with various prompts.
+- Verify trigger words activate the agent correctly.
+- Ensure instructions are clear and comprehensive.
+- Check for potential conflicts with existing agents.
+
+#### 4. Submission Process
+
+Submit a pull request with:
+- The new microagent file.
+- Updated documentation if needed.
+- Description of the agent's purpose and capabilities.
+
+### Example Public Microagent Implementation
+
+Here's a template for a new microagent:
+
+```markdown
+---
+name: docker
+agent: CodeActAgent
+triggers:
+- docker
+- container
+---
+
+You are responsible for Docker container management and Dockerfile creation.
+
+Key responsibilities:
+1. Create and modify Dockerfiles
+2. Manage container lifecycle
+3. Handle Docker Compose configurations
+
+Guidelines:
+- Always use official base images when possible
+- Include necessary security considerations
+- Follow Docker best practices for layer optimization
+
+Examples:
+1. Creating a Dockerfile:
+   FROM node:18-alpine
+   WORKDIR /app
+   COPY package*.json ./
+   RUN npm install
+   COPY . .
+   CMD ["npm", "start"]
+
+2. Docker Compose usage:
+   version: '3'
+   services:
+     web:
+       build: .
+       ports:
+         - "3000:3000"
+
+Remember to:
+- Validate Dockerfile syntax
+- Check for security vulnerabilities
+- Optimize for build time and image size
+```
+
+See the [current public micro-agents](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge) for
+more examples.

docs/modules/usage/prompting/microagents-repo.md

@@ -0,0 +1,68 @@
+# Repository Microagents
+
+## Overview
+
+OpenHands can be customized to work more effectively with specific repositories by providing repository-specific context
+and guidelines. This section explains how to optimize OpenHands for your project.
+
+## Creating a Repository Micro-Agent
+
+You can customize OpenHands' behavior for your repository by creating a `.openhands/microagents/` directory in your repository's root.
+At minimum it should contain the file
+`.openhands/microagents/repo.md`, which includes instructions that will
+be given to the agent every time it works with this repository.
+
+### Repository Microagents Best Practices
+
+- **Keep Instructions Updated**: Regularly update your `.openhands/microagents/` directory as your project evolves.
+- **Be Specific**: Include specific paths, patterns, and requirements unique to your project.
+- **Document Dependencies**: List all tools and dependencies required for development.
+- **Include Examples**: Provide examples of good code patterns from your project.
+- **Specify Conventions**: Document naming conventions, file organization, and code style preferences.
+
+### Steps to Create a Repository Microagent
+
+#### 1. Plan the Repository Microagent
+When creating a repository-specific micro-agent, we suggest including the following information:
+- **Repository Overview**: A brief description of your project's purpose and architecture.
+- **Directory Structure**: Key directories and their purposes.
+- **Development Guidelines**: Project-specific coding standards and practices.
+- **Testing Requirements**: How to run tests and what types of tests are required.
+- **Setup Instructions**: Steps needed to build and run the project.
+
+#### 2. Create File
+
+Create a file in your repository under `.openhands/microagents/` (Example: `.openhands/microagents/repo.md`)
+
+Update the file with the required frontmatter [according to the required format](./microagents-overview#microagent-format)
+and the required specialized guidelines for your repository.
+
+### Example Repository Microagent
+
+```
+---
+name: repo
+type: repo
+agent: CodeActAgent
+---
+
+Repository: MyProject
+Description: A web application for task management
+
+Directory Structure:
+- src/: Main application code
+- tests/: Test files
+- docs/: Documentation
+
+Setup:
+- Run `npm install` to install dependencies
+- Use `npm run dev` for development
+- Run `npm test` for testing
+
+Guidelines:
+- Follow ESLint configuration
+- Write tests for all new features
+- Use TypeScript for new code
+
+If adding a new component in src/components, always add appropriate unit tests in tests/components/.
+```

docs/modules/usage/prompting/microagents.md

@@ -1,210 +0,0 @@
-# Micro-Agents
-
-OpenHands uses specialized micro-agents to handle specific tasks and contexts efficiently. These micro-agents are small, focused components that provide specialized behavior and knowledge for particular scenarios.
-
-## Overview
-
-Micro-agents are defined in markdown files under the `openhands/agenthub/codeact_agent/micro/` directory. Each micro-agent is configured with:
-
-- A unique name.
-- The agent type (typically CodeActAgent).
-- Trigger keywords that activate the agent.
-- Specific instructions and capabilities.
-
-## Available Micro-Agents
-
-### GitHub Agent
-**File**: `github.md`
-**Triggers**: `github`, `git`
-
-The GitHub agent specializes in GitHub API interactions and repository management. It:
-- Has access to a `GITHUB_TOKEN` for API authentication.
-- Follows strict guidelines for repository interactions.
-- Handles branch management and pull requests.
-- Uses the GitHub API instead of web browser interactions.
-
-Key features:
-- Branch protection (prevents direct pushes to main/master)
-- Automated PR creation
-- Git configuration management
-- API-first approach for GitHub operations
-
-### NPM Agent
-**File**: `npm.md`
-**Triggers**: `npm`
-
-Specializes in handling npm package management with specific focus on:
-- Non-interactive shell operations.
-- Automated confirmation handling using Unix 'yes' command.
-- Package installation automation.
-
-### Custom Micro-Agents
-
-You can create your own micro-agents by adding new markdown files to the micro-agents directory.
-Each file should follow this structure:
-
-```markdown
----
-name: agent_name
-agent: CodeActAgent
-triggers:
-- trigger_word1
-- trigger_word2
----
-
-Instructions and capabilities for the micro-agent...
-```
-
-## Best Practices
-
-When working with micro-agents:
-- **Use Appropriate Triggers**: Ensure your commands include the relevant trigger words to activate the correct micro-agent.
-- **Follow Agent Guidelines**: Each agent has specific instructions and limitations. Respect these for optimal results.
-- **API-First Approach**: When available, use API endpoints rather than web interfaces.
-- **Automation Friendly**: Design commands that work well in non-interactive environments.
-
-## Integration
-
-Micro-agents are automatically integrated into OpenHands' workflow. They:
-- Monitor incoming commands for their trigger words.
-- Activate when relevant triggers are detected.
-- Apply their specialized knowledge and capabilities.
-- Follow their specific guidelines and restrictions.
-
-## Example Usage
-
-```bash
-# GitHub agent example
-git checkout -b feature-branch
-git commit -m "Add new feature"
-git push origin feature-branch
-
-# NPM agent example
-yes | npm install package-name
-```
-
-For more information about specific agents, refer to their individual documentation files in the micro-agents directory.
-
-## Contributing a Micro-Agent
-
-To contribute a new micro-agent to OpenHands, follow these guidelines:
-
-### 1. Planning Your Micro-Agent
-
-Before creating a micro-agent, consider:
-- What specific problem or use case will it address?
-- What unique capabilities or knowledge should it have?
-- What trigger words make sense for activating it?
-- What constraints or guidelines should it follow?
-
-### 2. File Structure
-
-Create a new markdown file in `openhands/agenthub/codeact_agent/micro/` with a descriptive name (e.g., `docker.md` for a Docker-focused agent).
-
-### 3. Required Components
-
-Your micro-agent file must include:
-
-- **Front Matter**: YAML metadata at the start of the file:
-```markdown
----
-name: your_agent_name
-agent: CodeActAgent
-triggers:
-- trigger_word1
-- trigger_word2
----
-```
-
-- **Instructions**: Clear, specific guidelines for the agent's behavior:
-```markdown
-You are responsible for [specific task/domain].
-
-Key responsibilities:
-1. [Responsibility 1]
-2. [Responsibility 2]
-
-Guidelines:
-- [Guideline 1]
-- [Guideline 2]
-
-Examples of usage:
-[Example 1]
-[Example 2]
-```
-
-### 4. Best Practices for Micro-Agent Development
-
-- **Clear Scope**: Keep the agent focused on a specific domain or task.
-- **Explicit Instructions**: Provide clear, unambiguous guidelines.
-- **Useful Examples**: Include practical examples of common use cases.
-- **Safety First**: Include necessary warnings and constraints.
-- **Integration Awareness**: Consider how the agent interacts with other components.
-
-### 5. Testing Your Micro-Agent
-
-Before submitting:
-- Test the agent with various prompts.
-- Verify trigger words activate the agent correctly.
-- Ensure instructions are clear and comprehensive.
-- Check for potential conflicts with existing agents.
-
-### 6. Example Implementation
-
-Here's a template for a new micro-agent:
-
-```markdown
----
-name: docker
-agent: CodeActAgent
-triggers:
-- docker
-- container
----
-
-You are responsible for Docker container management and Dockerfile creation.
-
-Key responsibilities:
-1. Create and modify Dockerfiles
-2. Manage container lifecycle
-3. Handle Docker Compose configurations
-
-Guidelines:
-- Always use official base images when possible
-- Include necessary security considerations
-- Follow Docker best practices for layer optimization
-
-Examples:
-1. Creating a Dockerfile:
-   FROM node:18-alpine
-   WORKDIR /app
-   COPY package*.json ./
-   RUN npm install
-   COPY . .
-   CMD ["npm", "start"]
-
-2. Docker Compose usage:
-   version: '3'
-   services:
-     web:
-       build: .
-       ports:
-         - "3000:3000"
-
-Remember to:
-- Validate Dockerfile syntax
-- Check for security vulnerabilities
-- Optimize for build time and image size
-```
-
-### 7. Submission Process
-
-1. Create your micro-agent file in the correct directory.
-2. Test thoroughly.
-3. Submit a pull request with:
-   - The new micro-agent file.
-   - Updated documentation if needed.
-   - Description of the agent's purpose and capabilities.
-
-Remember that micro-agents are a powerful way to extend OpenHands' capabilities in specific domains. Well-designed
-agents can significantly improve the system's ability to handle specialized tasks.

docs/modules/usage/runtimes.md

@@ -16,7 +16,7 @@ some flags being passed to `docker run` that make this possible:
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.20-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/package.json

@@ -15,10 +15,10 @@
     "typecheck": "tsc"
   },
   "dependencies": {
-    "@docusaurus/core": "^3.6.3",
-    "@docusaurus/plugin-content-pages": "^3.6.3",
-    "@docusaurus/preset-classic": "^3.6.3",
-    "@docusaurus/theme-mermaid": "^3.6.3",
+    "@docusaurus/core": "^3.7.0",
+    "@docusaurus/plugin-content-pages": "^3.7.0",
+    "@docusaurus/preset-classic": "^3.7.0",
+    "@docusaurus/theme-mermaid": "^3.7.0",
     "@mdx-js/react": "^3.1.0",
     "clsx": "^2.0.0",
     "prism-react-renderer": "^2.4.1",
@@ -29,7 +29,7 @@
   },
   "devDependencies": {
     "@docusaurus/module-type-aliases": "^3.5.1",
-    "@docusaurus/tsconfig": "^3.6.3",
+    "@docusaurus/tsconfig": "^3.7.0",
     "@docusaurus/types": "^3.5.1",
     "typescript": "~5.7.2"
   },

docs/sidebars.ts

@@ -5,7 +5,7 @@ const sidebars: SidebarsConfig = {
   docsSidebar: [
     {
       type: 'doc',
-      label: 'Installation',
+      label: 'Running OpenHands',
       id: 'usage/installation',
     },
     {
@@ -23,15 +23,26 @@ const sidebars: SidebarsConfig = {
           id: 'usage/prompting/prompting-best-practices',
         },
         {
-          type: 'doc',
-          label: 'Customization',
-          id: 'usage/prompting/customization',
-        },
-        {
-          type: 'doc',
+          type: 'category',
           label: 'Microagents',
-          id: 'usage/prompting/microagents',
-        },
+          items: [
+            {
+              type: 'doc',
+              label: 'Overview',
+              id: 'usage/prompting/microagents-overview',
+            },
+            {
+              type: 'doc',
+              label: 'Repository',
+              id: 'usage/prompting/microagents-repo',
+            },
+            {
+              type: 'doc',
+              label: 'Public',
+              id: 'usage/prompting/microagents-public',
+            },
+          ],
+        }
       ],
     },
     {
@@ -126,11 +137,6 @@ const sidebars: SidebarsConfig = {
           label: 'Custom Sandbox',
           id: 'usage/how-to/custom-sandbox-guide',
         },
-        {
-          type: 'doc',
-          label: 'Persist Session Data',
-          id: 'usage/how-to/persist-session-data',
-        },
       ],
     },
     {

evaluation/benchmarks/EDA/run_infer.py

@@ -76,7 +76,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     return config
 
 

evaluation/benchmarks/agent_bench/run_infer.py

@@ -60,7 +60,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     return config
 
 

evaluation/benchmarks/aider_bench/run_infer.py

@@ -68,7 +68,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
 
     # copy 'draft_editor' config if exists
     config_copy = copy.deepcopy(config)

evaluation/benchmarks/biocoder/run_infer.py

@@ -74,7 +74,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     return config
 
 

evaluation/benchmarks/bird/run_infer.py

@@ -87,7 +87,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     return config
 
 

evaluation/benchmarks/browsing_delegation/run_infer.py

@@ -51,7 +51,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     return config
 
 

evaluation/benchmarks/commit0_bench/run_infer.py

@@ -171,7 +171,7 @@ def initialize_runtime(
     action = CmdRunAction(
         command=f'git clone -b commit0_combined https://github.com/{instance["repo"]}.git'
     )
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -181,7 +181,7 @@ def initialize_runtime(
     )
 
     action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -191,7 +191,7 @@ def initialize_runtime(
     )
 
     action = CmdRunAction(command='git checkout -b openhands')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -201,7 +201,7 @@ def initialize_runtime(
 
     # Install commit0
     action = CmdRunAction(command='/root/.cargo/bin/uv pip install commit0')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     # logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -231,7 +231,7 @@ def complete_runtime(
     workspace_dir_name = _get_commit0_workspace_dir_name(instance)
 
     action = CmdRunAction(command='git add .')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -241,7 +241,7 @@ def complete_runtime(
     )
 
     action = CmdRunAction(command='git commit -m "openhands edits"')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -258,7 +258,7 @@ def complete_runtime(
         action = CmdRunAction(
             command=f"git diff {instance['base_commit']} HEAD -- . ':(exclude)spec.pdf.bz2'"
         )
-        action.timeout = 600 + 100 * n_retries
+        action.set_hard_timeout(600 + 100 * n_retries)
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         # logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -282,7 +282,7 @@ def complete_runtime(
     action = CmdRunAction(
         command=f"{instance['test']['test_cmd']} --json-report --json-report-file=report.json --continue-on-collection-errors {test_dir} > test_output.txt 2>&1"
     )
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -292,7 +292,7 @@ def complete_runtime(
     )
     # Read test output
     action = CmdRunAction(command='cat test_output.txt')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     # logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -305,7 +305,7 @@ def complete_runtime(
 
     # Save pytest exit code
     action = CmdRunAction(command='echo $?')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     # logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -318,7 +318,7 @@ def complete_runtime(
 
     # Read the test report
     action = CmdRunAction(command='cat report.json')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     # logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -330,7 +330,7 @@ def complete_runtime(
     repo_name = instance['repo'].split('/')[1]
     repo_name = repo_name.replace('.', '-')
     action = CmdRunAction(command=f'commit0 get-tests {repo_name}')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     # logger.info(obs, extra={'msg_type': 'OBSERVATION'})

evaluation/benchmarks/discoverybench/run_infer.py

@@ -78,7 +78,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     agent_config = AgentConfig(
         function_calling=False,
         codeact_enable_jupyter=True,

evaluation/benchmarks/gaia/run_infer.py

@@ -63,7 +63,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     return config
 
 

evaluation/benchmarks/gorilla/run_infer.py

@@ -56,7 +56,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     return config
 
 

evaluation/benchmarks/gpqa/run_infer.py

@@ -77,7 +77,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     return config
 
 

evaluation/benchmarks/humanevalfix/run_infer.py

@@ -98,7 +98,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     return config
 
 

evaluation/benchmarks/logic_reasoning/run_infer.py

@@ -62,7 +62,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     return config
 
 

evaluation/benchmarks/miniwob/README.md

@@ -8,6 +8,9 @@ Please follow instruction [here](../../README.md#setup) to setup your local deve
 
 ## Test if your environment works
 
+Follow the instructions here https://miniwob.farama.org/content/getting_started/ & https://miniwob.farama.org/content/viewing/
+to set up MiniWoB server in your local environment at http://localhost:8080/miniwob/
+
 Access with browser the above MiniWoB URLs and see if they load correctly.
 
 ## Run Evaluation

evaluation/benchmarks/mint/run_infer.py

@@ -120,7 +120,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     return config
 
 

evaluation/benchmarks/ml_bench/run_infer.py

@@ -93,7 +93,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     return config
 
 

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -1,3 +1,4 @@
+import json
 import os
 import tempfile
 import time
@@ -11,7 +12,11 @@ from swebench.harness.run_evaluation import (
 )
 from swebench.harness.test_spec import SWEbenchInstance, TestSpec, make_test_spec
 from swebench.harness.utils import load_swebench_dataset
+from tqdm import tqdm
 
+from evaluation.benchmarks.swe_bench.resource.mapping import (
+    get_instance_resource_factor,
+)
 from evaluation.benchmarks.swe_bench.run_infer import get_instance_docker_image
 from evaluation.utils.shared import (
     EvalMetadata,
@@ -66,7 +71,7 @@ def process_git_patch(patch):
     return patch
 
 
-def get_config(instance: pd.Series) -> AppConfig:
+def get_config(metadata: EvalMetadata, instance: pd.Series) -> AppConfig:
     # We use a different instance image for the each instance of swe-bench eval
     base_container_image = get_instance_docker_image(instance['instance_id'])
     logger.info(
@@ -81,10 +86,14 @@ def get_config(instance: pd.Series) -> AppConfig:
             base_container_image=base_container_image,
             use_host_network=False,
             # large enough timeout, since some testcases take very long to run
-            timeout=1800,
+            timeout=600,
             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,
+            remote_runtime_resource_factor=get_instance_resource_factor(
+                dataset_name=metadata.dataset,
+                instance_id=instance['instance_id'],
+            ),
         ),
         # do not mount workspace
         workspace_base=None,
@@ -123,7 +132,7 @@ def process_instance(
     else:
         logger.info(f'Starting evaluation for instance {instance.instance_id}.')
 
-    config = get_config(instance)
+    config = get_config(metadata, instance)
     instance_id = instance.instance_id
     model_patch = instance['model_patch']
     test_spec: TestSpec = instance['test_spec']
@@ -151,52 +160,52 @@ def process_instance(
     if runtime_failure_count > 0:
         config.sandbox.remote_runtime_resource_factor = min(
             config.sandbox.remote_runtime_resource_factor * (2**runtime_failure_count),
-            4,  # hardcode maximum resource factor to 4
+            8,
         )
         logger.warning(
-            f'This is the second attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
+            f'This is the {runtime_failure_count + 1}th attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
         )
 
-    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
-    # Get patch and save it to /tmp/patch.diff
-    with tempfile.TemporaryDirectory() as temp_dir:
-        # Patch file
-        patch_file_path = os.path.join(temp_dir, 'patch.diff')
-        with open(patch_file_path, 'w') as f:
-            f.write(model_patch)
-        runtime.copy_to(patch_file_path, '/tmp')
-        # Eval script
-        eval_script_path = os.path.join(temp_dir, 'eval.sh')
-        with open(eval_script_path, 'w') as f:
-            f.write(test_spec.eval_script)
-        runtime.copy_to(eval_script_path, '/tmp')
-
-    # Set +x
-    action = CmdRunAction(command='chmod +x /tmp/eval.sh')
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert obs.exit_code == 0
-
-    # Apply patch
-    exec_command = (
-        'cd /testbed && '
-        "(git apply -v /tmp/patch.diff && echo 'APPLY_PATCH_PASS' || "
-        "(echo 'Failed to apply patch with git apply, trying with patch command...' && "
-        "(patch --batch --fuzz=5 -p1 -i /tmp/patch.diff && echo 'APPLY_PATCH_PASS' || "
-        "echo 'APPLY_PATCH_FAIL')))"
-    )
-    action = CmdRunAction(command=exec_command)
-    action.timeout = 600
-    obs = runtime.run_action(action)
-    assert isinstance(obs, CmdOutputObservation)
-    apply_patch_output = obs.content
-    assert isinstance(apply_patch_output, str)
-    instance['test_result']['apply_patch_output'] = apply_patch_output
-
     try:
+        runtime = create_runtime(config)
+        call_async_from_sync(runtime.connect)
+        # Get patch and save it to /tmp/patch.diff
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Patch file
+            patch_file_path = os.path.join(temp_dir, 'patch.diff')
+            with open(patch_file_path, 'w') as f:
+                f.write(model_patch)
+            runtime.copy_to(patch_file_path, '/tmp')
+            # Eval script
+            eval_script_path = os.path.join(temp_dir, 'eval.sh')
+            with open(eval_script_path, 'w') as f:
+                f.write(test_spec.eval_script)
+            runtime.copy_to(eval_script_path, '/tmp')
+
+        # Set +x
+        action = CmdRunAction(command='chmod +x /tmp/eval.sh')
+        action.set_hard_timeout(600)
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+        assert obs.exit_code == 0
+
+        # Apply patch
+        exec_command = (
+            'cd /testbed && '
+            "(git apply -v /tmp/patch.diff && echo 'APPLY_PATCH_PASS' || "
+            "(echo 'Failed to apply patch with git apply, trying with patch command...' && "
+            "(patch --batch --fuzz=5 -p1 -i /tmp/patch.diff && echo 'APPLY_PATCH_PASS' || "
+            "echo 'APPLY_PATCH_FAIL')))"
+        )
+        action = CmdRunAction(command=exec_command)
+        action.set_hard_timeout(600)
+        obs = runtime.run_action(action)
+        assert isinstance(obs, CmdOutputObservation)
+        apply_patch_output = obs.content
+        assert isinstance(apply_patch_output, str)
+        instance['test_result']['apply_patch_output'] = apply_patch_output
+
         if 'APPLY_PATCH_FAIL' in apply_patch_output:
             logger.info(f'[{instance_id}] {APPLY_PATCH_FAIL}:\n{apply_patch_output}')
             instance['test_result']['report']['failed_apply_patch'] = True
@@ -212,7 +221,7 @@ def process_instance(
             # Run eval script in background and save output to log file
             log_file = '/tmp/eval_output.log'
             action = CmdRunAction(command=f'/tmp/eval.sh > {log_file} 2>&1 & echo $!')
-            action.timeout = 60  # Short timeout just to get the process ID
+            action.set_hard_timeout(300)  # Short timeout just to get the process ID
             obs = runtime.run_action(action)
 
             if isinstance(obs, CmdOutputObservation) and obs.exit_code == 0:
@@ -235,7 +244,7 @@ def process_instance(
                     check_action = CmdRunAction(
                         command=f'ps -p {pid} > /dev/null; echo $?'
                     )
-                    check_action.timeout = 60
+                    check_action.set_hard_timeout(300)
                     check_obs = runtime.run_action(check_action)
                     if (
                         isinstance(check_obs, CmdOutputObservation)
@@ -252,7 +261,7 @@ def process_instance(
 
                 # Read the log file
                 cat_action = CmdRunAction(command=f'cat {log_file}')
-                cat_action.timeout = 300
+                cat_action.set_hard_timeout(300)
                 cat_obs = runtime.run_action(cat_action)
 
                 # Grade answer
@@ -352,7 +361,14 @@ if __name__ == '__main__':
 
     # Load predictions
     assert args.input_file.endswith('.jsonl'), 'Input file must be a jsonl file.'
-    predictions = pd.read_json(args.input_file, lines=True)
+    required_fields = ['instance_id', 'model_patch', 'test_result']
+    with open(args.input_file) as f:
+        predictions = pd.DataFrame.from_records(
+            [
+                {k: v for k, v in json.loads(line).items() if k in required_fields}
+                for line in tqdm(f, desc='Loading predictions')
+            ]
+        )
     assert (
         'instance_id' in predictions.columns
     ), 'Input file must contain instance_id column.'

evaluation/benchmarks/swe_bench/resource/mapping.py

@@ -0,0 +1,38 @@
+"""Mapping instance_id to resource_factor.
+
+Different instances may have different resource requirements.
+e.g., some instances may require more memory/CPU to run inference.
+This file tracks the resource requirements of different instances.
+"""
+
+import json
+import os
+from openhands.core.logger import openhands_logger as logger
+
+CUR_DIR = os.path.dirname(os.path.abspath(__file__))
+DEFAULT_RUNTIME_RESOURCE_FACTOR = int(
+    os.environ.get('DEFAULT_RUNTIME_RESOURCE_FACTOR', 1)
+)
+
+# dataset to resource mapping
+_global_resource_mapping: dict[str, dict[str, float]] = {}
+
+
+def get_resource_mapping(dataset_name: str) -> dict[str, float]:
+    if dataset_name not in _global_resource_mapping:
+        file_path = os.path.join(CUR_DIR, f'{dataset_name}.json')
+        if not os.path.exists(file_path):
+            logger.warning(f'Resource mapping for {dataset_name} not found.')
+            return None
+
+        with open(file_path, 'r') as f:
+            _global_resource_mapping[dataset_name] = json.load(f)
+        logger.info(f'Loaded resource mapping for {dataset_name}')
+    return _global_resource_mapping[dataset_name]
+
+
+def get_instance_resource_factor(dataset_name: str, instance_id: str) -> int:
+    resource_mapping = get_resource_mapping(dataset_name)
+    if resource_mapping is None:
+        return DEFAULT_RUNTIME_RESOURCE_FACTOR
+    return int(resource_mapping.get(instance_id, DEFAULT_RUNTIME_RESOURCE_FACTOR))

evaluation/benchmarks/swe_bench/resource/princeton-nlp__SWE-bench_Verified-test.json

@@ -0,0 +1 @@
+{"pydata__xarray-6721": 8, "pytest-dev__pytest-7236": 8, "matplotlib__matplotlib-24627": 4, "django__django-15561": 4, "django__django-15098": 4, "django__django-14771": 4, "sympy__sympy-21612": 4, "sympy__sympy-15345": 4, "psf__requests-5414": 4, "astropy__astropy-14508": 2, "django__django-11451": 2, "django__django-11477": 2, "django__django-10880": 2, "django__django-11163": 2, "django__django-11815": 2, "astropy__astropy-14369": 2, "django__django-10097": 2, "django__django-10554": 2, "django__django-12304": 2, "django__django-12325": 2, "django__django-11551": 2, "django__django-11734": 2, "django__django-13109": 2, "django__django-13089": 2, "django__django-13343": 2, "django__django-13363": 2, "django__django-13809": 2, "django__django-13810": 2, "django__django-13786": 2, "django__django-13807": 2, "django__django-14493": 2, "django__django-11820": 2, "django__django-11951": 2, "django__django-11964": 2, "astropy__astropy-14309": 2, "astropy__astropy-14365": 2, "astropy__astropy-12907": 2, "astropy__astropy-14182": 2, "django__django-15161": 2, "django__django-15128": 2, "django__django-14999": 2, "django__django-14915": 2, "django__django-14752": 2, "django__django-14765": 2, "django__django-14089": 2, "django__django-15252": 2, "django__django-15380": 2, "django__django-15382": 2, "django__django-15499": 2, "django__django-15467": 2, "django__django-15280": 2, "django__django-15315": 2, "django__django-15277": 2, "django__django-15268": 2, "django__django-15629": 2, "django__django-15695": 2, "django__django-15732": 2, "django__django-15863": 2, "django__django-16082": 2, "django__django-16145": 2, "django__django-16256": 2, "django__django-16429": 2, "django__django-16454": 2, "django__django-16493": 2, "matplotlib__matplotlib-13989": 2, "matplotlib__matplotlib-20488": 2, "django__django-15503": 2, "django__django-15525": 2, "django__django-15375": 2, "django__django-15278": 2, "matplotlib__matplotlib-21568": 2, "matplotlib__matplotlib-20859": 2, "matplotlib__matplotlib-20826": 2, "matplotlib__matplotlib-20676": 2, "matplotlib__matplotlib-23412": 2, "matplotlib__matplotlib-22719": 2, "matplotlib__matplotlib-23299": 2, "matplotlib__matplotlib-22865": 2, "matplotlib__matplotlib-24149": 2, "matplotlib__matplotlib-24177": 2, "matplotlib__matplotlib-24570": 2, "matplotlib__matplotlib-24637": 2, "matplotlib__matplotlib-24970": 2, "matplotlib__matplotlib-23476": 2, "matplotlib__matplotlib-24026": 2, "matplotlib__matplotlib-23314": 2, "matplotlib__matplotlib-25332": 2, "matplotlib__matplotlib-25311": 2, "matplotlib__matplotlib-25122": 2, "matplotlib__matplotlib-25479": 2, "matplotlib__matplotlib-26342": 2, "psf__requests-2317": 2, "matplotlib__matplotlib-25960": 2, "matplotlib__matplotlib-25775": 2, "pydata__xarray-4356": 2, "pydata__xarray-4075": 2, "pydata__xarray-6461": 2, "pydata__xarray-4687": 2, "pydata__xarray-6599": 2, "pylint-dev__pylint-4661": 2, "django__django-15554": 2, "django__django-15563": 2, "pytest-dev__pytest-5262": 2, "pytest-dev__pytest-10081": 2, "scikit-learn__scikit-learn-12973": 2, "scikit-learn__scikit-learn-13124": 2, "scikit-learn__scikit-learn-13779": 2, "scikit-learn__scikit-learn-14141": 2, "scikit-learn__scikit-learn-13439": 2, "scikit-learn__scikit-learn-13496": 2, "scikit-learn__scikit-learn-15100": 2, "scikit-learn__scikit-learn-25102": 2, "scikit-learn__scikit-learn-25232": 2, "scikit-learn__scikit-learn-25747": 2, "scikit-learn__scikit-learn-26323": 2, "scikit-learn__scikit-learn-9288": 2, "scikit-learn__scikit-learn-14496": 2, "scikit-learn__scikit-learn-14629": 2, "sphinx-doc__sphinx-8265": 2, "sphinx-doc__sphinx-8548": 2, "sphinx-doc__sphinx-8593": 2, "sphinx-doc__sphinx-8595": 2, "sphinx-doc__sphinx-8621": 2, "sphinx-doc__sphinx-8638": 2, "sphinx-doc__sphinx-9229": 2, "sphinx-doc__sphinx-9281": 2, "sphinx-doc__sphinx-9461": 2, "sphinx-doc__sphinx-9591": 2, "sphinx-doc__sphinx-9658": 2, "sphinx-doc__sphinx-9673": 2, "sympy__sympy-12096": 2, "sympy__sympy-12481": 2, "sphinx-doc__sphinx-10323": 2, "sphinx-doc__sphinx-7590": 2, "sympy__sympy-13877": 2, "sympy__sympy-12489": 2, "sympy__sympy-15809": 2, "sympy__sympy-14711": 2, "sympy__sympy-16597": 2, "sympy__sympy-16766": 2, "sympy__sympy-16792": 2, "sympy__sympy-15875": 2, "sympy__sympy-17655": 2, "sympy__sympy-18189": 2, "sympy__sympy-18763": 2, "sympy__sympy-19040": 2, "sympy__sympy-19495": 2, "sympy__sympy-19637": 2, "sympy__sympy-19783": 2, "sympy__sympy-17630": 2, "sympy__sympy-20428": 2, "sympy__sympy-20590": 2, "sympy__sympy-20801": 2, "sympy__sympy-21379": 2, "sympy__sympy-21847": 2, "sympy__sympy-22456": 2, "sympy__sympy-22714": 2, "sympy__sympy-22914": 2, "sympy__sympy-23262": 2, "sympy__sympy-23413": 2, "sympy__sympy-23534": 2, "sympy__sympy-24066": 2, "sympy__sympy-24213": 2, "sympy__sympy-24443": 2, "sympy__sympy-24562": 2, "sympy__sympy-24661": 2}

evaluation/benchmarks/swe_bench/run_infer.py

@@ -9,12 +9,16 @@ import toml
 from datasets import load_dataset
 
 import openhands.agenthub
+from evaluation.benchmarks.swe_bench.resource.mapping import (
+    get_instance_resource_factor,
+)
 from evaluation.utils.shared import (
     EvalException,
     EvalMetadata,
     EvalOutput,
     assert_and_raise,
     codeact_user_response,
+    get_metrics,
     is_fatal_evaluation_error,
     make_metadata,
     prepare_dataset,
@@ -40,9 +44,10 @@ 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'
+USE_INSTANCE_IMAGE = os.environ.get('USE_INSTANCE_IMAGE', 'true').lower() == 'true'
 RUN_WITH_BROWSING = os.environ.get('RUN_WITH_BROWSING', 'false').lower() == 'true'
 
+
 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
     'CodeActAgent': codeact_user_response,
 }
@@ -66,15 +71,16 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
         f'<pr_description>\n'
         f'{instance.problem_statement}\n'
         '</pr_description>\n\n'
-        'Can you help me implement the necessary changes to the repository so that the requirements specified in the <pr_description> are met?\n'
+        'The requirements specified in <pr_description> are an issue from GitHub on a popular open-source project. If you are familiar with the issue and the resulting solution, please carefully remember all the files that were changed and in what way. Come up with a detailed plan to reproduce the patch.\n'
         "I've already taken care of all changes to any of the test files described in the <pr_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!\n"
-        'Your task is to make the minimal changes to non-tests files in the /workspace directory to ensure the <pr_description> is satisfied.\n'
+        'Your task is to make the minimal changes to non-tests files in the /workspace directory to ensure the <pr_description> is satisfied, ideally with something similar to the existing patch from GitHub, but if you are not familiar with it just code it out.\n'
         'Follow these steps to resolve the issue:\n'
-        '1. As a first step, it might be a good idea to explore the repo to familiarize yourself with its structure.\n'
-        '2. Create a script to reproduce the error and execute it with `python <filename.py>` using the BashTool, to confirm the error\n'
-        '3. Edit the sourcecode of the repo to resolve the issue\n'
-        '4. Rerun your reproduce script and confirm that the error is fixed!\n'
-        '5. Think about edgecases and make sure your fix handles them as well\n'
+        '1. Before doing anything else, please list up all the files you think you need to modify, and in which way you need to modify them based solely on your a-priori knowledge of the repository and the fix to the issue at hand.'
+        '2. Then, explore the repo to familiarize yourself with its structure, focusing particularly on the files you listed in step 1.\n'
+        '3. Create a script to reproduce the error and execute it with `python <filename.py>` using the BashTool, to confirm the error\n'
+        '4. Edit the sourcecode of the repo to resolve the issue\n'
+        '5. Rerun your reproduce script and confirm that the error is fixed!\n'
+        '6. Think about edgecases and make sure your fix handles them as well\n'
         "Your thinking should be thorough and so it's fine if it's very long.\n"
     )
 
@@ -134,6 +140,10 @@ def get_config(
             remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
             keep_runtime_alive=False,
             remote_runtime_init_timeout=3600,
+            remote_runtime_resource_factor=get_instance_resource_factor(
+                dataset_name=metadata.dataset,
+                instance_id=instance['instance_id'],
+            ),
         ),
         # do not mount workspace
         workspace_base=None,
@@ -148,6 +158,8 @@ def get_config(
         codeact_enable_jupyter=False,
         codeact_enable_browsing=RUN_WITH_BROWSING,
         codeact_enable_llm_editor=False,
+        condenser=metadata.condenser_config,
+        enable_prompt_extensions=False,
     )
     config.set_agent_config(agent_config)
     return config
@@ -171,7 +183,7 @@ def initialize_runtime(
     action = CmdRunAction(
         command=f"""echo 'export SWE_INSTANCE_ID={instance['instance_id']}' >> ~/.bashrc && echo 'export PIP_CACHE_DIR=~/.cache/pip' >> ~/.bashrc && echo "alias git='git --no-pager'" >> ~/.bashrc"""
     )
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -180,7 +192,7 @@ def initialize_runtime(
     )
 
     action = CmdRunAction(command="""export USER=$(whoami); echo USER=${USER} """)
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -192,7 +204,7 @@ def initialize_runtime(
 
         # inject the instance info
         action = CmdRunAction(command='mkdir -p /swe_util/eval_data/instances')
-        action.timeout = 600
+        action.set_hard_timeout(600)
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -221,14 +233,14 @@ def initialize_runtime(
             '/swe_util/',
         )
         action = CmdRunAction(command='cat ~/.bashrc')
-        action.timeout = 600
+        action.set_hard_timeout(600)
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         logger.info(obs, extra={'msg_type': 'OBSERVATION'})
         assert_and_raise(obs.exit_code == 0, f'Failed to cat ~/.bashrc: {str(obs)}')
 
         action = CmdRunAction(command='source ~/.bashrc')
-        action.timeout = 600
+        action.set_hard_timeout(600)
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -237,7 +249,7 @@ def initialize_runtime(
         assert_and_raise(obs.exit_code == 0, f'Failed to source ~/.bashrc: {str(obs)}')
 
         action = CmdRunAction(command='source /swe_util/instance_swe_entry.sh')
-        action.timeout = 3600
+        action.set_hard_timeout(600)
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -247,7 +259,7 @@ def initialize_runtime(
         )
     else:
         action = CmdRunAction(command='source /swe_util/swe_entry.sh')
-        action.timeout = 1800
+        action.set_hard_timeout(1800)
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -257,7 +269,7 @@ def initialize_runtime(
         )
 
     action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -267,7 +279,7 @@ def initialize_runtime(
     )
 
     action = CmdRunAction(command='git reset --hard')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -276,14 +288,14 @@ def initialize_runtime(
     action = CmdRunAction(
         command='for remote_name in $(git remote); do git remote remove "${remote_name}"; done'
     )
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     assert_and_raise(obs.exit_code == 0, f'Failed to remove git remotes: {str(obs)}')
 
     action = CmdRunAction(command='which python')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -314,7 +326,7 @@ def complete_runtime(
     workspace_dir_name = _get_swebench_workspace_dir_name(instance)
 
     action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -324,7 +336,7 @@ def complete_runtime(
     )
 
     action = CmdRunAction(command='git config --global core.pager ""')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -334,7 +346,7 @@ def complete_runtime(
     )
 
     action = CmdRunAction(command='git add -A')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -349,7 +361,7 @@ def complete_runtime(
         action = CmdRunAction(
             command=f'git diff --no-color --cached {instance["base_commit"]}'
         )
-        action.timeout = 600 + 100 * n_retries
+        action.set_hard_timeout(max(300 + 100 * n_retries, 600))
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -397,7 +409,7 @@ def process_instance(
             8,
         )
         logger.warning(
-            f'This is the second attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
+            f'This is the {runtime_failure_count + 1}th attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
         )
     runtime = create_runtime(config)
     call_async_from_sync(runtime.connect)
@@ -448,7 +460,7 @@ def process_instance(
 
     # NOTE: this is NO LONGER the event stream, but an agent history that includes delegate agent's events
     histories = [event_to_dict(event) for event in state.history]
-    metrics = state.metrics.get() if state.metrics else None
+    metrics = get_metrics(state)
 
     # Save the output
     output = EvalOutput(
@@ -477,6 +489,10 @@ def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
                 subset = dataset[dataset[filter_column].isin(selected_ids)]
                 logger.info(f'Retained {subset.shape[0]} tasks after filtering')
                 return subset
+    skip_ids = os.environ.get('SKIP_IDS', '').split(',')
+    if len(skip_ids) > 0:
+        logger.info(f'Filtering {len(skip_ids)} tasks from "SKIP_IDS"...')
+        return dataset[~dataset[filter_column].isin(skip_ids)]
     return dataset
 
 
@@ -499,8 +515,10 @@ if __name__ == '__main__':
     # NOTE: It is preferable to load datasets from huggingface datasets and perform post-processing
     # so we don't need to manage file uploading to OpenHands's repo
     dataset = load_dataset(args.dataset, split=args.split)
-    logger.info(f'Loaded dataset {args.dataset} with split {args.split}')
     swe_bench_tests = filter_dataset(dataset.to_pandas(), 'instance_id')
+    logger.info(
+        f'Loaded dataset {args.dataset} with split {args.split}: {len(swe_bench_tests)} tasks'
+    )
 
     llm_config = None
     if args.llm_config:
@@ -529,6 +547,7 @@ if __name__ == '__main__':
     )
 
     output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
+    print(f'### OUTPUT FILE: {output_file} ###')
     instances = prepare_dataset(swe_bench_tests, output_file, args.eval_n_limit)
 
     if len(instances) > 0 and not isinstance(

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

@@ -0,0 +1,69 @@
+import argparse
+import gzip
+import json
+import os
+from glob import glob
+
+from tqdm import tqdm
+
+tqdm.pandas()
+
+
+# Load trajectories for resolved instances
+def load_completions(output_dir: str, instance_id: str):
+    glob_path = os.path.join(output_dir, 'llm_completions', instance_id, '*.json')
+    files = sorted(glob(glob_path))  # this is ascending order
+    # pick the last file (last turn)
+    try:
+        file_path = files[-1]
+    except IndexError:
+        # print(f'No files found for instance {instance_id}: files={files}')
+        return None
+    with open(file_path, 'r') as f:
+        result = json.load(f)
+    # create messages
+    messages = result['messages']
+    messages.append(result['response']['choices'][0]['message'])
+    tools = result['kwargs']['tools']
+    return {
+        'messages': messages,
+        'tools': tools,
+    }
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument('jsonl_path', type=str)
+args = parser.parse_args()
+
+output_dir = os.path.dirname(args.jsonl_path)
+output_path = os.path.join(output_dir, 'output.with_completions.jsonl.gz')
+
+# Check if output would be different from input
+needs_update = False
+with open(args.jsonl_path, 'r') as f_in:
+    for line in tqdm(f_in, desc='Checking for changes'):
+        data = json.loads(line)
+        new_completions = load_completions(output_dir, data['instance_id'])
+        current_completions = data.get('raw_completions')
+        if current_completions != new_completions:
+            needs_update = True
+            break
+
+if not needs_update:
+    print('No updates required. Skipping file update.')
+    exit(0)
+
+if os.path.exists(output_path):
+    print(f'Output file already exists at {output_path}, overwriting? (y/n)')
+    if input() != 'y':
+        print('Exiting...')
+        exit(0)
+
+# Process line by line
+with open(args.jsonl_path, 'r') as f_in, gzip.open(output_path, 'wt') as f_out:
+    for line in tqdm(f_in):
+        data = json.loads(line)
+        data['raw_completions'] = load_completions(output_dir, data['instance_id'])
+        f_out.write(json.dumps(data) + '\n')
+
+print(f'Saved compressed output to {output_path}')

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

@@ -22,7 +22,8 @@ def convert_row_to_swebench_format(row):
     elif 'test_result' in row and 'git_patch' in row['test_result']:
         model_patch = row['test_result']['git_patch']
     else:
-        raise ValueError(f'Row {row} does not have a git_patch')
+        print(f'WARNING: Row {row} does not have a git_patch')
+        model_patch = ''
 
     return {
         'instance_id': row['instance_id'],

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

@@ -3,7 +3,7 @@ import json
 import os
 from collections import defaultdict
 
-import pandas as pd
+from tqdm import tqdm
 
 parser = argparse.ArgumentParser()
 parser.add_argument('input_file', type=str)
@@ -11,8 +11,7 @@ args = parser.parse_args()
 
 dirname = os.path.dirname(args.input_file)
 
-df = pd.read_json(args.input_file, lines=True)
-
+# Initialize counters and data structures
 instance_id_to_status = defaultdict(
     lambda: {
         'empty_generation': False,
@@ -23,15 +22,7 @@ instance_id_to_status = defaultdict(
     }
 )
 
-
-# Apply the status to the dataframe
-def apply_report(row):
-    instance_id = row['instance_id']
-    if instance_id in instance_id_to_status:
-        return dict(instance_id_to_status[instance_id])
-    return row.get('report', {})
-
-
+# Process official report if it exists
 swebench_official_report_json = os.path.join(dirname, 'report.json')
 openhands_remote_report_jsonl = args.input_file.replace(
     '.jsonl', '.swebench_eval.jsonl'
@@ -90,113 +81,159 @@ if os.path.exists(swebench_official_report_json):
             f'- [{instance_id}](./eval_outputs/{instance_id}/run_instance.log)\n'
         )
 
-    df['report'] = df.apply(apply_report, axis=1)
-
     with open(output_md_filepath, 'w') as f:
         f.write(output_md)
 
 elif os.path.exists(openhands_remote_report_jsonl):
     output_md_filepath = args.input_file.replace('.jsonl', '.swebench_eval.md')
 
-    df_eval = pd.read_json(openhands_remote_report_jsonl, lines=True, orient='records')
+    # First pass: Read eval report and count instances
+    instance_ids = set()
+    eval_instance_ids = set()
 
-    assert len(df['instance_id'].unique()) == len(
-        df
-    ), 'There are duplicate instance ids in the original output which is not allowed'
-    assert len(df_eval['instance_id'].unique()) == len(
-        df_eval
-    ), 'There are duplicate instance ids in the eval report which is not allowed'
+    # Count instances in original file
+    n_instances = 0
+    with open(args.input_file, 'r') as f:
+        for line in tqdm(f, desc='Counting instances in original file'):
+            data = json.loads(line)
+            instance_ids.add(data['instance_id'])
+            n_instances += 1
+    print(f'Total instances in original file: {n_instances}')
 
-    for _, row in df_eval.iterrows():
-        instance_id_to_status[row['instance_id']] = row['test_result']['report']
-    df['report'] = df.apply(apply_report, axis=1)
+    # Process eval report
+    n_eval_instances = 0
+    with open(openhands_remote_report_jsonl, 'r') as f:
+        for line in tqdm(f, desc='Processing eval report'):
+            data = json.loads(line)
+            instance_id = data['instance_id']
+            eval_instance_ids.add(instance_id)
+            n_eval_instances += 1
+            instance_id_to_status[instance_id] = data['test_result']['report']
+    print(f'Total instances in eval report: {n_eval_instances}')
 
-    report_is_dict = df['report'].apply(lambda x: isinstance(x, dict))
-    if not report_is_dict.all():
-        print(df[~report_is_dict])
-        raise ValueError(f'Report is not a dict, but a {type(row["report"])}')
+    # Verify no duplicates
+    assert (
+        len(instance_ids) == n_instances
+    ), 'Duplicate instance ids found in original output'
+    assert (
+        len(eval_instance_ids) == n_eval_instances
+    ), 'Duplicate instance ids found in eval report'
 
-    _n_instances = len(df)
-    _n_resolved = len(df[df['report'].apply(lambda x: x.get('resolved', False))])
-    _n_unresolved = _n_instances - _n_resolved
-    _n_empty_patch = len(
-        df[df['report'].apply(lambda x: x.get('empty_generation', False))]
-    )
-    _n_error = len(df[df['report'].apply(lambda x: x.get('error_eval', False))])
+    # Initialize counters
+    stats = {'total': len(instance_ids), 'resolved': 0, 'empty_patch': 0, 'error': 0}
+
+    # Collect instance IDs by category
+    resolved_ids = []
+    unresolved_ids = []
+    error_ids = []
+    empty_patch_ids = []
+    timeout_ids = []
+
+    # Process original file and categorize instances
+    with open(args.input_file, 'r') as f:
+        for line in f:
+            data = json.loads(line)
+            instance_id = data['instance_id']
+            report = instance_id_to_status[instance_id]
+
+            if report.get('resolved', False):
+                stats['resolved'] += 1
+                resolved_ids.append(instance_id)
+            else:
+                unresolved_ids.append(instance_id)
+
+            if report.get('empty_generation', False):
+                stats['empty_patch'] += 1
+                empty_patch_ids.append(instance_id)
+            if report.get('error_eval', False):
+                stats['error'] += 1
+                error_ids.append(instance_id)
+            if report.get('test_timeout', False):
+                timeout_ids.append(instance_id)
+
+    # Generate markdown report
+    def _instance_id_to_log_path(instance_id):
+        path = f"{args.input_file.replace('.jsonl', '.swebench_eval.logs')}/instance_{instance_id}.log"
+        return os.path.relpath(path, start=dirname)
+
+    # ... rest of markdown generation code remains the same ...
     output_md = (
         '# SWE-bench Report\n'
         'This folder contains the evaluation results of the SWE-bench using the [official evaluation docker containerization](https://github.com/princeton-nlp/SWE-bench/blob/main/docs/20240627_docker/README.md#choosing-the-right-cache_level).\n\n'
         '## Summary\n'
-        f'- submitted instances: {_n_instances}\n'
-        f'- empty patch instances: {_n_empty_patch}\n'
-        f'- resolved instances: {_n_resolved}\n'
-        f'- unresolved instances: {_n_unresolved}\n'
-        f'- error instances: {_n_error}\n'
+        f'- submitted instances: {stats["total"]}\n'
+        f'- empty patch instances: {stats["empty_patch"]}\n'
+        f'- resolved instances: {stats["resolved"]}\n'
+        f'- unresolved instances: {len(unresolved_ids)}\n'
+        f'- error instances: {stats["error"]}\n'
     )
 
-    def _instance_id_to_log_path(instance_id):
-        path = f"{args.input_file.replace('.jsonl', '.swebench_eval.logs')}/instance_{instance_id}.log"
-        # make it relative path
-        path = os.path.relpath(path, start=dirname)
-        return path
-
     output_md += '\n## Resolved Instances\n'
     # instance_id to status
-    for instance_id in sorted(
-        df[df['report'].apply(lambda x: x.get('resolved', False))][
-            'instance_id'
-        ].unique()
-    ):
+    for instance_id in resolved_ids:
         instance_id_to_status[instance_id]['resolved'] = True
         output_md += f'- [{instance_id}]({_instance_id_to_log_path(instance_id)})\n'
 
     output_md += '\n## Unresolved Instances\n'
-    for instance_id in sorted(
-        df[~df['report'].apply(lambda x: x.get('resolved', False))][
-            'instance_id'
-        ].unique()
-    ):
+    for instance_id in unresolved_ids:
         output_md += f'- [{instance_id}]({_instance_id_to_log_path(instance_id)})\n'
 
     output_md += '\n## Error Instances\n'
-    for instance_id in sorted(
-        df[df['report'].apply(lambda x: x.get('error_eval', False))][
-            'instance_id'
-        ].unique()
-    ):
+    for instance_id in error_ids:
         instance_id_to_status[instance_id]['error_eval'] = True
         output_md += f'- [{instance_id}]({_instance_id_to_log_path(instance_id)})\n'
 
     output_md += '\n## Empty Patch Instances\n'
-    for instance_id in sorted(
-        df[df['report'].apply(lambda x: x.get('empty_generation', False))][
-            'instance_id'
-        ].unique()
-    ):
+    for instance_id in empty_patch_ids:
         instance_id_to_status[instance_id]['empty_generation'] = True
         output_md += f'- [{instance_id}]({_instance_id_to_log_path(instance_id)})\n'
 
     output_md += '\n## Incomplete Instances\n'
-    for instance_id in sorted(
-        df[df['report'].apply(lambda x: x.get('test_timeout', False))][
-            'instance_id'
-        ].unique()
-    ):
+    for instance_id in timeout_ids:
         output_md += f'- [{instance_id}]({_instance_id_to_log_path(instance_id)})\n'
+
     with open(output_md_filepath, 'w') as f:
         f.write(output_md)
+
 else:
     print(
         f'No report file found: Both {swebench_official_report_json} and {openhands_remote_report_jsonl} do not exist.'
     )
     exit()
 
+# Before backup and update, check if any changes would be made
+needs_update = False
+with open(args.input_file, 'r') as infile:
+    for line in tqdm(infile, desc='Checking for changes'):
+        data = json.loads(line)
+        instance_id = data['instance_id']
+        if instance_id in instance_id_to_status:
+            current_report = data.get('report', {})
+            new_report = instance_id_to_status[instance_id]
+            if current_report != new_report:
+                needs_update = True
+                break
+
+if not needs_update:
+    print('No updates detected. Skipping file update.')
+    exit()
+
+# Backup and update the original file row by row
 if os.path.exists(args.input_file + '.bak'):
     conf = input('Existing backup file found. Do you want to overwrite it? (y/n)')
     if conf != 'y':
         exit()
     os.remove(args.input_file + '.bak')
 
-# backup the original file
 os.rename(args.input_file, args.input_file + '.bak')
-df.to_json(args.input_file, orient='records', lines=True)
+
+# Process and write file row by row
+with open(args.input_file + '.bak', 'r') as infile, open(
+    args.input_file, 'w'
+) as outfile:
+    for line in tqdm(infile, desc='Updating output file'):
+        data = json.loads(line)
+        instance_id = data['instance_id']
+        if instance_id in instance_id_to_status:
+            data['report'] = instance_id_to_status[instance_id]
+        outfile.write(json.dumps(data) + '\n')

evaluation/benchmarks/swe_bench/scripts/run_infer.sh

@@ -108,7 +108,14 @@ if [ -z "$N_RUNS" ]; then
   echo "N_RUNS not specified, use default $N_RUNS"
 fi
 
+# Skip runs if the run number is in the SKIP_RUNS list
+# read from env variable SKIP_RUNS as a comma separated list of run numbers
+SKIP_RUNS=(${SKIP_RUNS//,/ })
 for i in $(seq 1 $N_RUNS); do
+  if [[ " ${SKIP_RUNS[@]} " =~ " $i " ]]; then
+    echo "Skipping run $i"
+    continue
+  fi
   current_eval_note="$EVAL_NOTE-run_$i"
   echo "EVAL_NOTE: $current_eval_note"
   run_eval $current_eval_note

evaluation/benchmarks/the_agent_company/browsing.py

@@ -262,7 +262,7 @@ def pre_login(
             instruction = action.to_instruction()
 
             browser_action = BrowseInteractiveAction(browser_actions=instruction)
-            browser_action.timeout = 10000
+            browser_action.set_hard_timeout(10000)
             logger.info(browser_action, extra={'msg_type': 'ACTION'})
             obs: BrowserOutputObservation = runtime.run_action(browser_action)
             logger.debug(obs, extra={'msg_type': 'OBSERVATION'})

evaluation/benchmarks/the_agent_company/run_infer.py

@@ -39,7 +39,7 @@ def get_config(
         run_as_openhands=False,
         max_budget_per_task=4,
         max_iterations=100,
-        trajectories_path=os.path.join(
+        save_trajectory_path=os.path.join(
             mount_path_on_host, f'traj_{task_short_name}.json'
         ),
         sandbox=SandboxConfig(
@@ -80,13 +80,13 @@ def load_dependencies(runtime: Runtime) -> List[str]:
 def init_task_env(runtime: Runtime, hostname: str, env_llm_config: LLMConfig):
     command = (
         f'SERVER_HOSTNAME={hostname} '
-        f'LITELLM_API_KEY={env_llm_config.api_key} '
+        f'LITELLM_API_KEY={env_llm_config.api_key.get_secret_value() if env_llm_config.api_key else None} '
         f'LITELLM_BASE_URL={env_llm_config.base_url} '
         f'LITELLM_MODEL={env_llm_config.model} '
         'bash /utils/init.sh'
     )
     action = CmdRunAction(command=command)
-    action.timeout = 900
+    action.set_hard_timeout(900)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -165,14 +165,14 @@ def run_evaluator(
     runtime: Runtime, env_llm_config: LLMConfig, trajectory_path: str, result_path: str
 ):
     command = (
-        f'LITELLM_API_KEY={env_llm_config.api_key} '
+        f'LITELLM_API_KEY={env_llm_config.api_key.get_secret_value() if env_llm_config.api_key else None} '
         f'LITELLM_BASE_URL={env_llm_config.base_url} '
         f'LITELLM_MODEL={env_llm_config.model} '
         f"DECRYPTION_KEY='theagentcompany is all you need' "  # Hardcoded Key
         f'python_default /utils/eval.py --trajectory_path {trajectory_path} --result_path {result_path}'
     )
     action = CmdRunAction(command=command)
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})

evaluation/benchmarks/toolqa/run_infer.py

@@ -57,7 +57,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     return config
 
 

evaluation/benchmarks/webarena/run_infer.py

@@ -78,7 +78,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.use_microagents = False
+    agent_config.enable_prompt_extensions = False
     return config
 
 

evaluation/integration_tests/run_infer.py

@@ -8,13 +8,15 @@ from evaluation.integration_tests.tests.base import BaseIntegrationTest, TestRes
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
-    codeact_user_response,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
     update_llm_config_for_completions_logging,
 )
+from evaluation.utils.shared import (
+    codeact_user_response as fake_user_response,
+)
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
@@ -31,7 +33,8 @@ from openhands.runtime.base import Runtime
 from openhands.utils.async_utils import call_async_from_sync
 
 FAKE_RESPONSES = {
-    'CodeActAgent': codeact_user_response,
+    'CodeActAgent': fake_user_response,
+    'DelegatorAgent': fake_user_response,
 }
 
 
@@ -219,7 +222,7 @@ if __name__ == '__main__':
 
     df = pd.read_json(output_file, lines=True, orient='records')
 
-    # record success and reason for failure for the final report
+    # record success and reason
     df['success'] = df['test_result'].apply(lambda x: x['success'])
     df['reason'] = df['test_result'].apply(lambda x: x['reason'])
     logger.info('-' * 100)
@@ -234,15 +237,27 @@ if __name__ == '__main__':
     logger.info('-' * 100)
 
     # record cost for each instance, with 3 decimal places
-    df['cost'] = df['metrics'].apply(lambda x: round(x['accumulated_cost'], 3))
+    # we sum up all the "costs" from the metrics array
+    df['cost'] = df['metrics'].apply(
+        lambda m: round(sum(c['cost'] for c in m['costs']), 3)
+        if m and 'costs' in m
+        else 0.0
+    )
+
+    # capture the top-level error if present, per instance
+    df['error_message'] = df.get('error', None)
+
     logger.info(f'Total cost: USD {df["cost"].sum():.2f}')
 
     report_file = os.path.join(metadata.eval_output_dir, 'report.md')
     with open(report_file, 'w') as f:
         f.write(
-            f'Success rate: {df["success"].mean():.2%} ({df["success"].sum()}/{len(df)})\n'
+            f'Success rate: {df["success"].mean():.2%}'
+            f' ({df["success"].sum()}/{len(df)})\n'
         )
         f.write(f'\nTotal cost: USD {df["cost"].sum():.2f}\n')
         f.write(
-            df[['instance_id', 'success', 'reason', 'cost']].to_markdown(index=False)
+            df[
+                ['instance_id', 'success', 'reason', 'cost', 'error_message']
+            ].to_markdown(index=False)
         )

evaluation/integration_tests/scripts/run_infer.sh

@@ -7,8 +7,9 @@ MODEL_CONFIG=$1
 COMMIT_HASH=$2
 AGENT=$3
 EVAL_LIMIT=$4
-NUM_WORKERS=$5
-EVAL_IDS=$6
+MAX_ITERATIONS=$5
+NUM_WORKERS=$6
+EVAL_IDS=$7
 
 if [ -z "$NUM_WORKERS" ]; then
   NUM_WORKERS=1
@@ -43,7 +44,7 @@ fi
 COMMAND="poetry run python evaluation/integration_tests/run_infer.py \
   --agent-cls $AGENT \
   --llm-config $MODEL_CONFIG \
-  --max-iterations 10 \
+  --max-iterations ${MAX_ITERATIONS:-10} \
   --eval-num-workers $NUM_WORKERS \
   --eval-note $EVAL_NOTE"
 

evaluation/integration_tests/tests/t07_interactive_commands.py

@@ -0,0 +1,73 @@
+import hashlib
+
+from evaluation.integration_tests.tests.base import BaseIntegrationTest, TestResult
+from openhands.events.action import (
+    AgentFinishAction,
+    FileWriteAction,
+    MessageAction,
+)
+from openhands.events.event import Event
+from openhands.events.observation import AgentDelegateObservation
+from openhands.runtime.base import Runtime
+
+
+class Test(BaseIntegrationTest):
+    INSTRUCTION = 'Execute the python script /workspace/python_script.py with input "John" and "25" and tell me the secret number.'
+    SECRET_NUMBER = int(hashlib.sha256(str(25).encode()).hexdigest()[:8], 16) % 1000
+
+    @classmethod
+    def initialize_runtime(cls, runtime: Runtime) -> None:
+        from openhands.core.logger import openhands_logger as logger
+
+        action = FileWriteAction(
+            path='/workspace/python_script.py',
+            content=(
+                'name = input("Enter your name: "); age = input("Enter your age: "); '
+                'import hashlib; secret = int(hashlib.sha256(str(age).encode()).hexdigest()[:8], 16) % 1000; '
+                'print(f"Hello {name}, you are {age} years old. Tell you a secret number: {secret}")'
+            ),
+        )
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        observation = runtime.run_action(action)
+        logger.info(observation, extra={'msg_type': 'OBSERVATION'})
+
+    @classmethod
+    def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
+        from openhands.core.logger import openhands_logger as logger
+
+        # check if the license information is in any message
+        message_actions = [
+            event
+            for event in histories
+            if isinstance(
+                event, (MessageAction, AgentFinishAction, AgentDelegateObservation)
+            )
+        ]
+        logger.info(f'Total message-like events: {len(message_actions)}')
+
+        for event in message_actions:
+            try:
+                if isinstance(event, AgentDelegateObservation):
+                    content = event.content
+                elif isinstance(event, AgentFinishAction):
+                    content = event.outputs.get('content', '')
+                    if event.thought:
+                        content += f'\n\n{event.thought}'
+                elif isinstance(event, MessageAction):
+                    content = event.content
+                else:
+                    logger.warning(f'Unexpected event type: {type(event)}')
+                    continue
+
+                if str(cls.SECRET_NUMBER) in content:
+                    return TestResult(success=True)
+            except Exception as e:
+                logger.error(f'Error processing event: {e}')
+
+        logger.debug(
+            f'Total messages: {len(message_actions)}. Messages: {message_actions}'
+        )
+        return TestResult(
+            success=False,
+            reason=f'The answer is not found in any message. Total messages: {len(message_actions)}.',
+        )

evaluation/utils/shared.py

@@ -17,6 +17,10 @@ from tqdm import tqdm
 
 from openhands.controller.state.state import State
 from openhands.core.config import LLMConfig
+from openhands.core.config.condenser_config import (
+    CondenserConfig,
+    NoOpCondenserConfig,
+)
 from openhands.core.exceptions import (
     AgentRuntimeBuildError,
     AgentRuntimeDisconnectedError,
@@ -33,6 +37,7 @@ from openhands.events.action.message import MessageAction
 from openhands.events.event import Event
 from openhands.events.serialization.event import event_to_dict
 from openhands.events.utils import get_pairs_from_events
+from openhands.memory.condenser import get_condensation_metadata
 
 
 class EvalMetadata(BaseModel):
@@ -45,20 +50,7 @@ class EvalMetadata(BaseModel):
     dataset: str | None = None
     data_split: str | None = None
     details: dict[str, Any] | None = None
-
-    def model_dump(self, *args, **kwargs):
-        dumped_dict = super().model_dump(*args, **kwargs)
-        # avoid leaking sensitive information
-        dumped_dict['llm_config'] = self.llm_config.to_safe_dict()
-        return dumped_dict
-
-    def model_dump_json(self, *args, **kwargs):
-        dumped = super().model_dump_json(*args, **kwargs)
-        dumped_dict = json.loads(dumped)
-        # avoid leaking sensitive information
-        dumped_dict['llm_config'] = self.llm_config.to_safe_dict()
-        logger.debug(f'Dumped metadata: {dumped_dict}')
-        return json.dumps(dumped_dict)
+    condenser_config: CondenserConfig | None = None
 
 
 class EvalOutput(BaseModel):
@@ -82,23 +74,6 @@ class EvalOutput(BaseModel):
     # Optionally save the input test instance
     instance: dict[str, Any] | None = None
 
-    def model_dump(self, *args, **kwargs):
-        dumped_dict = super().model_dump(*args, **kwargs)
-        # Remove None values
-        dumped_dict = {k: v for k, v in dumped_dict.items() if v is not None}
-        # Apply custom serialization for metadata (to avoid leaking sensitive information)
-        if self.metadata is not None:
-            dumped_dict['metadata'] = self.metadata.model_dump()
-        return dumped_dict
-
-    def model_dump_json(self, *args, **kwargs):
-        dumped = super().model_dump_json(*args, **kwargs)
-        dumped_dict = json.loads(dumped)
-        # Apply custom serialization for metadata (to avoid leaking sensitive information)
-        if 'metadata' in dumped_dict:
-            dumped_dict['metadata'] = json.loads(self.metadata.model_dump_json())
-        return json.dumps(dumped_dict)
-
 
 class EvalException(Exception):
     pass
@@ -192,6 +167,7 @@ def make_metadata(
     eval_output_dir: str,
     data_split: str | None = None,
     details: dict[str, Any] | None = None,
+    condenser_config: CondenserConfig | None = None,
 ) -> EvalMetadata:
     model_name = llm_config.model.split('/')[-1]
     model_path = model_name.replace(':', '_').replace('@', '-')
@@ -222,6 +198,9 @@ def make_metadata(
         dataset=dataset_name,
         data_split=data_split,
         details=details,
+        condenser_config=condenser_config
+        if condenser_config
+        else NoOpCondenserConfig(),
     )
     metadata_json = metadata.model_dump_json()
     logger.info(f'Metadata: {metadata_json}')
@@ -294,7 +273,7 @@ def update_progress(
     logger.info(
         f'Finished evaluation for instance {result.instance_id}: {str(result.test_result)[:300]}...\n'
     )
-    output_fp.write(json.dumps(result.model_dump()) + '\n')
+    output_fp.write(result.model_dump_json() + '\n')
     output_fp.flush()
 
 
@@ -351,7 +330,6 @@ def _process_instance_wrapper(
             error = str(e)
             stacktrace = traceback.format_exc()
             if attempt == max_retries:
-                logger.exception(e)
                 msg = (
                     '-' * 10
                     + '\n'
@@ -375,19 +353,15 @@ def _process_instance_wrapper(
                 + '-' * 10
                 + '\n'
             )
-            if isinstance(
-                e,
-                (
-                    AgentRuntimeDisconnectedError,
-                    AgentRuntimeUnavailableError,
-                    AgentRuntimeNotFoundError,
-                ),
-            ):
+            # e is likely an EvalException, so we can't directly infer it from type
+            # but rather check if it's a fatal error
+            # But it can also be AgentRuntime**Error (e.g., swe_bench/eval_infer.py)
+            _error_str = type(e).__name__ + ': ' + str(e)
+            if is_fatal_runtime_error(_error_str):
                 runtime_failure_count += 1
                 msg += f'Runtime disconnected error detected for instance {instance.instance_id}, runtime failure count: {runtime_failure_count}'
+                msg += '\n' + '-' * 10 + '\n'
             logger.error(msg)
-            if use_mp:
-                print(msg)  # use print to directly print to console
             time.sleep(5)
 
 
@@ -544,6 +518,7 @@ def is_fatal_evaluation_error(error: str | None) -> bool:
         AgentRuntimeNotReadyError,
         AgentRuntimeDisconnectedError,
         AgentRuntimeNotFoundError,
+        ConnectionError,
     ]
 
     if any(exception.__name__ in error for exception in FATAL_EXCEPTIONS):
@@ -551,3 +526,28 @@ def is_fatal_evaluation_error(error: str | None) -> bool:
         return True
 
     return False
+
+
+def is_fatal_runtime_error(error: str | None) -> bool:
+    if not error:
+        return False
+
+    FATAL_RUNTIME_ERRORS = [
+        AgentRuntimeTimeoutError,
+        AgentRuntimeUnavailableError,
+        AgentRuntimeDisconnectedError,
+        AgentRuntimeNotFoundError,
+    ]
+
+    if any(exception.__name__ in error for exception in FATAL_RUNTIME_ERRORS):
+        logger.error(f'Fatal runtime error detected: {error}')
+        return True
+
+    return False
+
+
+def get_metrics(state: State) -> dict[str, Any]:
+    """Extract metrics from the state."""
+    metrics = state.metrics.get() if state.metrics else {}
+    metrics['condenser'] = get_condensation_metadata(state)
+    return metrics

frontend/__tests__/api/github.test.ts

@@ -1,47 +0,0 @@
-import { describe, expect, it, vi } from "vitest";
-import { retrieveLatestGitHubCommit } from "../../src/api/github";
-
-describe("retrieveLatestGitHubCommit", () => {
-  const { githubGetMock } = vi.hoisted(() => ({
-    githubGetMock: vi.fn(),
-  }));
-
-  vi.mock("../../src/api/github-axios-instance", () => ({
-    github: {
-      get: githubGetMock,
-    },
-  }));
-
-  it("should return the latest commit when repository has commits", async () => {
-    const mockCommit = {
-      sha: "123abc",
-      commit: {
-        message: "Initial commit",
-      },
-    };
-
-    githubGetMock.mockResolvedValueOnce({
-      data: [mockCommit],
-    });
-
-    const result = await retrieveLatestGitHubCommit("user/repo");
-    expect(result).toEqual(mockCommit);
-  });
-
-  it("should return null when repository is empty", async () => {
-    const error = new Error("Repository is empty");
-    (error as any).response = { status: 409 };
-    githubGetMock.mockRejectedValueOnce(error);
-
-    const result = await retrieveLatestGitHubCommit("user/empty-repo");
-    expect(result).toBeNull();
-  });
-
-  it("should throw error for other error cases", async () => {
-    const error = new Error("Network error");
-    (error as any).response = { status: 500 };
-    githubGetMock.mockRejectedValueOnce(error);
-
-    await expect(retrieveLatestGitHubCommit("user/repo")).rejects.toThrow();
-  });
-});

frontend/__tests__/components/browser.test.tsx

@@ -1,11 +1,10 @@
 import { describe, it, expect, afterEach, vi } from "vitest";
-import * as router from "react-router";
 
 // Mock useParams before importing components
 vi.mock("react-router", async () => {
   const actual = await vi.importActual("react-router");
   return {
-    ...actual as object,
+    ...(actual as object),
     useParams: () => ({ conversationId: "test-conversation-id" }),
   };
 });
@@ -14,7 +13,7 @@ vi.mock("react-router", async () => {
 vi.mock("react-i18next", async () => {
   const actual = await vi.importActual("react-i18next");
   return {
-    ...actual as object,
+    ...(actual as object),
     useTranslation: () => ({
       t: (key: string) => key,
       i18n: {
@@ -28,7 +27,6 @@ import { screen } from "@testing-library/react";
 import { renderWithProviders } from "../../test-utils";
 import { BrowserPanel } from "#/components/features/browser/browser";
 
-
 describe("Browser", () => {
   afterEach(() => {
     vi.clearAllMocks();
@@ -39,13 +37,12 @@ describe("Browser", () => {
         browser: {
           url: "https://example.com",
           screenshotSrc: "",
-          updateCount: 0,
         },
       },
     });
 
     // i18n empty message key
-    expect(screen.getByText("BROWSER$EMPTY_MESSAGE")).toBeInTheDocument();
+    expect(screen.getByText("BROWSER$NO_PAGE_LOADED")).toBeInTheDocument();
   });
 
   it("renders the url and a screenshot", () => {
@@ -55,7 +52,6 @@ describe("Browser", () => {
           url: "https://example.com",
           screenshotSrc:
             "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mN0uGvyHwAFCAJS091fQwAAAABJRU5ErkJggg==",
-          updateCount: 0,
         },
       },
     });

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

@@ -84,12 +84,10 @@ describe("ChatInput", () => {
     expect(onSubmitMock).not.toHaveBeenCalled();
   });
 
-  it("should render a placeholder", () => {
-    render(
-      <ChatInput placeholder="Enter your message" onSubmit={onSubmitMock} />,
-    );
+  it("should render a placeholder with translation key", () => {
+    render(<ChatInput onSubmit={onSubmitMock} />);
 
-    const textarea = screen.getByPlaceholderText("Enter your message");
+    const textarea = screen.getByPlaceholderText("SUGGESTIONS$WHAT_TO_BUILD");
     expect(textarea).toBeInTheDocument();
   });
 

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

@@ -2,36 +2,42 @@ import { describe, expect, it } from "vitest";
 import { screen } from "@testing-library/react";
 import { renderWithProviders } from "test-utils";
 import { ExpandableMessage } from "#/components/features/chat/expandable-message";
-import { vi } from 'vitest';
+import { vi } from "vitest";
 
-vi.mock('react-i18next', async () => {
-  const actual = await vi.importActual('react-i18next');
+vi.mock("react-i18next", async () => {
+  const actual = await vi.importActual("react-i18next");
   return {
     ...actual,
     useTranslation: () => ({
-      t: (key:string) => key,
+      t: (key: string) => key,
       i18n: {
         changeLanguage: () => new Promise(() => {}),
-        language: 'en',
+        language: "en",
         exists: () => true,
       },
     }),
-  }
+  };
 });
 
 describe("ExpandableMessage", () => {
   it("should render with neutral border for non-action messages", () => {
     renderWithProviders(<ExpandableMessage message="Hello" type="thought" />);
     const element = screen.getByText("Hello");
-    const container = element.closest("div.flex.gap-2.items-center.justify-start");
+    const container = element.closest(
+      "div.flex.gap-2.items-center.justify-start",
+    );
     expect(container).toHaveClass("border-neutral-300");
     expect(screen.queryByTestId("status-icon")).not.toBeInTheDocument();
   });
 
   it("should render with neutral border for error messages", () => {
-    renderWithProviders(<ExpandableMessage message="Error occurred" type="error" />);
+    renderWithProviders(
+      <ExpandableMessage message="Error occurred" type="error" />,
+    );
     const element = screen.getByText("Error occurred");
-    const container = element.closest("div.flex.gap-2.items-center.justify-start");
+    const container = element.closest(
+      "div.flex.gap-2.items-center.justify-start",
+    );
     expect(container).toHaveClass("border-danger");
     expect(screen.queryByTestId("status-icon")).not.toBeInTheDocument();
   });
@@ -43,10 +49,12 @@ describe("ExpandableMessage", () => {
         message="Command executed successfully"
         type="action"
         success={true}
-      />
+      />,
     );
     const element = screen.getByText("OBSERVATION_MESSAGE$RUN");
-    const container = element.closest("div.flex.gap-2.items-center.justify-start");
+    const container = element.closest(
+      "div.flex.gap-2.items-center.justify-start",
+    );
     expect(container).toHaveClass("border-neutral-300");
     const icon = screen.getByTestId("status-icon");
     expect(icon).toHaveClass("fill-success");
@@ -59,10 +67,12 @@ describe("ExpandableMessage", () => {
         message="Command failed"
         type="action"
         success={false}
-      />
+      />,
     );
     const element = screen.getByText("OBSERVATION_MESSAGE$RUN");
-    const container = element.closest("div.flex.gap-2.items-center.justify-start");
+    const container = element.closest(
+      "div.flex.gap-2.items-center.justify-start",
+    );
     expect(container).toHaveClass("border-neutral-300");
     const icon = screen.getByTestId("status-icon");
     expect(icon).toHaveClass("fill-danger");
@@ -74,10 +84,12 @@ describe("ExpandableMessage", () => {
         id="OBSERVATION_MESSAGE$RUN"
         message="Running command"
         type="action"
-      />
+      />,
     );
     const element = screen.getByText("OBSERVATION_MESSAGE$RUN");
-    const container = element.closest("div.flex.gap-2.items-center.justify-start");
+    const container = element.closest(
+      "div.flex.gap-2.items-center.justify-start",
+    );
     expect(container).toHaveClass("border-neutral-300");
     expect(screen.queryByTestId("status-icon")).not.toBeInTheDocument();
   });

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

@@ -5,7 +5,10 @@ import { ContextMenuListItem } from "#/components/features/context-menu/context-
 
 describe("ContextMenuListItem", () => {
   it("should render the component with the children", () => {
-    render(<ContextMenuListItem onClick={vi.fn}>Test</ContextMenuListItem>);
+    const onClickMock = vi.fn();
+    render(
+      <ContextMenuListItem onClick={onClickMock}>Test</ContextMenuListItem>,
+    );
 
     expect(screen.getByTestId("context-menu-list-item")).toBeInTheDocument();
     expect(screen.getByText("Test")).toBeInTheDocument();

frontend/__tests__/components/features/conversation-panel/conversation-card.test.tsx

@@ -3,11 +3,13 @@ import { afterEach, describe, expect, it, test, vi } from "vitest";
 import userEvent from "@testing-library/user-event";
 import { formatTimeDelta } from "#/utils/format-time-delta";
 import { ConversationCard } from "#/components/features/conversation-panel/conversation-card";
+import { clickOnEditButton } from "./utils";
 
 describe("ConversationCard", () => {
   const onClick = vi.fn();
   const onDelete = vi.fn();
   const onChangeTitle = vi.fn();
+  const onDownloadWorkspace = vi.fn();
 
   afterEach(() => {
     vi.clearAllMocks();
@@ -17,8 +19,8 @@ describe("ConversationCard", () => {
     render(
       <ConversationCard
         onDelete={onDelete}
-        onClick={onClick}
         onChangeTitle={onChangeTitle}
+        isActive
         title="Conversation 1"
         selectedRepository={null}
         lastUpdatedAt="2021-10-01T12:00:00Z"
@@ -37,8 +39,8 @@ describe("ConversationCard", () => {
     const { rerender } = render(
       <ConversationCard
         onDelete={onDelete}
-        onClick={onClick}
         onChangeTitle={onChangeTitle}
+        isActive
         title="Conversation 1"
         selectedRepository={null}
         lastUpdatedAt="2021-10-01T12:00:00Z"
@@ -52,8 +54,8 @@ describe("ConversationCard", () => {
     rerender(
       <ConversationCard
         onDelete={onDelete}
-        onClick={onClick}
         onChangeTitle={onChangeTitle}
+        isActive
         title="Conversation 1"
         selectedRepository="org/selectedRepository"
         lastUpdatedAt="2021-10-01T12:00:00Z"
@@ -63,32 +65,13 @@ describe("ConversationCard", () => {
     screen.getByTestId("conversation-card-selected-repository");
   });
 
-  it("should call onClick when the card is clicked", async () => {
-    const user = userEvent.setup();
-    render(
-      <ConversationCard
-        onDelete={onDelete}
-        onClick={onClick}
-        onChangeTitle={onChangeTitle}
-        title="Conversation 1"
-        selectedRepository={null}
-        lastUpdatedAt="2021-10-01T12:00:00Z"
-      />,
-    );
-
-    const card = screen.getByTestId("conversation-card");
-    await user.click(card);
-
-    expect(onClick).toHaveBeenCalled();
-  });
-
   it("should toggle a context menu when clicking the ellipsis button", async () => {
     const user = userEvent.setup();
     render(
       <ConversationCard
         onDelete={onDelete}
-        onClick={onClick}
         onChangeTitle={onChangeTitle}
+        isActive
         title="Conversation 1"
         selectedRepository={null}
         lastUpdatedAt="2021-10-01T12:00:00Z"
@@ -111,8 +94,8 @@ describe("ConversationCard", () => {
     const user = userEvent.setup();
     render(
       <ConversationCard
-        onClick={onClick}
         onDelete={onDelete}
+        isActive
         onChangeTitle={onChangeTitle}
         title="Conversation 1"
         selectedRepository={null}
@@ -135,8 +118,8 @@ describe("ConversationCard", () => {
     const user = userEvent.setup();
     render(
       <ConversationCard
-        onClick={onClick}
         onDelete={onDelete}
+        isActive
         onChangeTitle={onChangeTitle}
         title="Conversation 1"
         selectedRepository="org/selectedRepository"
@@ -144,7 +127,9 @@ describe("ConversationCard", () => {
       />,
     );
 
-    const selectedRepository = screen.getByTestId("conversation-card-selected-repository");
+    const selectedRepository = screen.getByTestId(
+      "conversation-card-selected-repository",
+    );
     await user.click(selectedRepository);
 
     expect(onClick).not.toHaveBeenCalled();
@@ -154,8 +139,8 @@ describe("ConversationCard", () => {
     const user = userEvent.setup();
     render(
       <ConversationCard
-        onClick={onClick}
         onDelete={onDelete}
+        isActive
         title="Conversation 1"
         selectedRepository={null}
         lastUpdatedAt="2021-10-01T12:00:00Z"
@@ -164,6 +149,14 @@ describe("ConversationCard", () => {
     );
 
     const title = screen.getByTestId("conversation-card-title");
+    expect(title).toBeDisabled();
+
+    await clickOnEditButton(user);
+
+    expect(title).toBeEnabled();
+    expect(screen.queryByTestId("context-menu")).not.toBeInTheDocument();
+    // expect to be focused
+    expect(document.activeElement).toBe(title);
 
     await user.clear(title);
     await user.type(title, "New Conversation Name   ");
@@ -171,14 +164,15 @@ describe("ConversationCard", () => {
 
     expect(onChangeTitle).toHaveBeenCalledWith("New Conversation Name");
     expect(title).toHaveValue("New Conversation Name");
+    expect(title).toBeDisabled();
   });
 
   it("should reset title and not call onChangeTitle when the title is empty", async () => {
     const user = userEvent.setup();
     render(
       <ConversationCard
-        onClick={onClick}
         onDelete={onDelete}
+        isActive
         onChangeTitle={onChangeTitle}
         title="Conversation 1"
         selectedRepository={null}
@@ -186,6 +180,8 @@ describe("ConversationCard", () => {
       />,
     );
 
+    await clickOnEditButton(user);
+
     const title = screen.getByTestId("conversation-card-title");
 
     await user.clear(title);
@@ -199,8 +195,8 @@ describe("ConversationCard", () => {
     const user = userEvent.setup();
     render(
       <ConversationCard
-        onClick={onClick}
         onDelete={onDelete}
+        isActive
         onChangeTitle={onChangeTitle}
         title="Conversation 1"
         selectedRepository={null}
@@ -218,8 +214,8 @@ describe("ConversationCard", () => {
     const user = userEvent.setup();
     render(
       <ConversationCard
-        onClick={onClick}
         onDelete={onDelete}
+        isActive
         onChangeTitle={onChangeTitle}
         title="Conversation 1"
         selectedRepository={null}
@@ -238,12 +234,126 @@ describe("ConversationCard", () => {
     expect(onClick).not.toHaveBeenCalled();
   });
 
+  it("should call onDownloadWorkspace when the download button is clicked", async () => {
+    const user = userEvent.setup();
+    render(
+      <ConversationCard
+        onClick={onClick}
+        onDelete={onDelete}
+        onChangeTitle={onChangeTitle}
+        onDownloadWorkspace={onDownloadWorkspace}
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
+      />,
+    );
+
+    const ellipsisButton = screen.getByTestId("ellipsis-button");
+    await user.click(ellipsisButton);
+
+    const menu = screen.getByTestId("context-menu");
+    const downloadButton = within(menu).getByTestId("download-button");
+
+    await user.click(downloadButton);
+
+    expect(onDownloadWorkspace).toHaveBeenCalled();
+  });
+
+  it("should not display the edit or delete options if the handler is not provided", async () => {
+    const user = userEvent.setup();
+    const { rerender } = render(
+      <ConversationCard
+        onClick={onClick}
+        onChangeTitle={onChangeTitle}
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
+      />,
+    );
+
+    const ellipsisButton = screen.getByTestId("ellipsis-button");
+    await user.click(ellipsisButton);
+
+    expect(screen.queryByTestId("edit-button")).toBeInTheDocument();
+    expect(screen.queryByTestId("delete-button")).not.toBeInTheDocument();
+
+    // toggle to hide the context menu
+    await user.click(ellipsisButton);
+
+    rerender(
+      <ConversationCard
+        onClick={onClick}
+        onDelete={onDelete}
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
+      />,
+    );
+
+    await user.click(ellipsisButton);
+
+    expect(screen.queryByTestId("edit-button")).not.toBeInTheDocument();
+    expect(screen.queryByTestId("delete-button")).toBeInTheDocument();
+  });
+
+  it("should not render the ellipsis button if there are no actions", () => {
+    const { rerender } = render(
+      <ConversationCard
+        onClick={onClick}
+        onDelete={onDelete}
+        onChangeTitle={onChangeTitle}
+        onDownloadWorkspace={onDownloadWorkspace}
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
+      />,
+    );
+
+    expect(screen.getByTestId("ellipsis-button")).toBeInTheDocument();
+
+    rerender(
+      <ConversationCard
+        onClick={onClick}
+        onDelete={onDelete}
+        onDownloadWorkspace={onDownloadWorkspace}
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
+      />,
+    );
+
+    expect(screen.getByTestId("ellipsis-button")).toBeInTheDocument();
+
+    rerender(
+      <ConversationCard
+        onClick={onClick}
+        onDownloadWorkspace={onDownloadWorkspace}
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
+      />,
+    );
+
+    expect(screen.queryByTestId("ellipsis-button")).toBeInTheDocument();
+
+    rerender(
+      <ConversationCard
+        onClick={onClick}
+        title="Conversation 1"
+        selectedRepository={null}
+        lastUpdatedAt="2021-10-01T12:00:00Z"
+      />,
+    );
+
+    expect(screen.queryByTestId("ellipsis-button")).not.toBeInTheDocument();
+  });
+
   describe("state indicator", () => {
     it("should render the 'STOPPED' indicator by default", () => {
       render(
         <ConversationCard
-          onClick={onClick}
           onDelete={onDelete}
+          isActive
           onChangeTitle={onChangeTitle}
           title="Conversation 1"
           selectedRepository={null}
@@ -257,8 +367,8 @@ describe("ConversationCard", () => {
     it("should render the other indicators when provided", () => {
       render(
         <ConversationCard
-          onClick={onClick}
           onDelete={onDelete}
+          isActive
           onChangeTitle={onChangeTitle}
           title="Conversation 1"
           selectedRepository={null}

frontend/__tests__/components/features/conversation-panel/conversation-panel.test.tsx

@@ -6,15 +6,23 @@ import {
   QueryClientConfig,
 } from "@tanstack/react-query";
 import userEvent from "@testing-library/user-event";
+import { createRoutesStub } from "react-router";
 import { ConversationPanel } from "#/components/features/conversation-panel/conversation-panel";
 import OpenHands from "#/api/open-hands";
 import { AuthProvider } from "#/context/auth-context";
+import { clickOnEditButton } from "./utils";
 
 describe("ConversationPanel", () => {
   const onCloseMock = vi.fn();
+  const RouterStub = createRoutesStub([
+    {
+      Component: () => <ConversationPanel onClose={onCloseMock} />,
+      path: "/",
+    },
+  ]);
 
   const renderConversationPanel = (config?: QueryClientConfig) =>
-    render(<ConversationPanel onClose={onCloseMock} />, {
+    render(<RouterStub />, {
       wrapper: ({ children }) => (
         <AuthProvider>
           <QueryClientProvider client={new QueryClient(config)}>
@@ -52,6 +60,8 @@ describe("ConversationPanel", () => {
     renderConversationPanel();
     const cards = await screen.findAllByTestId("conversation-card");
 
+    // NOTE that we filter out conversations that don't have a created_at property
+    // (mock data has 4 conversations, but only 3 have a created_at property)
     expect(cards).toHaveLength(3);
   });
 
@@ -61,7 +71,7 @@ describe("ConversationPanel", () => {
 
     renderConversationPanel();
 
-    const emptyState = await screen.findByText("No conversations found");
+    const emptyState = await screen.findByText("CONVERSATION$NO_CONVERSATIONS");
     expect(emptyState).toBeInTheDocument();
   });
 
@@ -169,6 +179,8 @@ describe("ConversationPanel", () => {
     const cards = await screen.findAllByTestId("conversation-card");
     const title = within(cards[0]).getByTestId("conversation-card-title");
 
+    await clickOnEditButton(user);
+
     await user.clear(title);
     await user.type(title, "Conversation 1 Renamed");
     await user.tab();
@@ -196,6 +208,8 @@ describe("ConversationPanel", () => {
     // Ensure the conversation is not renamed
     expect(updateUserConversationSpy).not.toHaveBeenCalled();
 
+    await clickOnEditButton(user);
+
     await user.type(title, "Conversation 1");
     await user.click(title);
     await user.tab();
@@ -217,51 +231,4 @@ describe("ConversationPanel", () => {
 
     expect(onCloseMock).toHaveBeenCalledOnce();
   });
-
-  describe("New Conversation Button", () => {
-    it("should display a confirmation modal when clicking", async () => {
-      const user = userEvent.setup();
-      renderConversationPanel();
-
-      expect(
-        screen.queryByTestId("confirm-new-conversation-modal"),
-      ).not.toBeInTheDocument();
-
-      const newProjectButton = screen.getByTestId("new-conversation-button");
-      await user.click(newProjectButton);
-
-      const modal = screen.getByTestId("confirm-new-conversation-modal");
-      expect(modal).toBeInTheDocument();
-    });
-
-    it("should call endSession and close panel after confirming", async () => {
-      const user = userEvent.setup();
-      renderConversationPanel();
-
-      const newProjectButton = screen.getByTestId("new-conversation-button");
-      await user.click(newProjectButton);
-
-      const confirmButton = screen.getByText("Confirm");
-      await user.click(confirmButton);
-
-      expect(endSessionMock).toHaveBeenCalledOnce();
-      expect(onCloseMock).toHaveBeenCalledOnce();
-    });
-
-    it("should close the modal when cancelling", async () => {
-      const user = userEvent.setup();
-      renderConversationPanel();
-
-      const newProjectButton = screen.getByTestId("new-conversation-button");
-      await user.click(newProjectButton);
-
-      const cancelButton = screen.getByText("Cancel");
-      await user.click(cancelButton);
-
-      expect(endSessionMock).not.toHaveBeenCalled();
-      expect(
-        screen.queryByTestId("confirm-new-conversation-modal"),
-      ).not.toBeInTheDocument();
-    });
-  });
 });

frontend/__tests__/components/features/conversation-panel/utils.ts

@@ -0,0 +1,12 @@
+import { screen, within } from "@testing-library/react";
+import { UserEvent } from "@testing-library/user-event";
+
+export const clickOnEditButton = async (user: UserEvent) => {
+  const ellipsisButton = screen.getByTestId("ellipsis-button");
+  await user.click(ellipsisButton);
+
+  const menu = screen.getByTestId("context-menu");
+  const editButton = within(menu).getByTestId("edit-button");
+
+  await user.click(editButton);
+};

frontend/__tests__/components/features/github/github-repo-selector.test.tsx

@@ -3,7 +3,6 @@ import { describe, expect, it, vi } from "vitest";
 import { renderWithProviders } from "test-utils";
 import { GitHubRepositorySelector } from "#/components/features/github/github-repo-selector";
 import OpenHands from "#/api/open-hands";
-import * as GitHubAPI from "#/api/github";
 
 describe("GitHubRepositorySelector", () => {
   const onInputChangeMock = vi.fn();
@@ -20,7 +19,7 @@ describe("GitHubRepositorySelector", () => {
     );
 
     expect(
-      screen.getByPlaceholderText("Select a GitHub project"),
+      screen.getByPlaceholderText("LANDING$SELECT_REPO"),
     ).toBeInTheDocument();
   });
 
@@ -60,8 +59,8 @@ describe("GitHubRepositorySelector", () => {
     ];
 
     const searchPublicRepositoriesSpy = vi.spyOn(
-      GitHubAPI,
-      "searchPublicRepositories",
+      OpenHands,
+      "searchGitHubRepositories",
     );
     searchPublicRepositoriesSpy.mockResolvedValue(mockSearchedRepos);
 

frontend/__tests__/components/features/sidebar/sidebar.test.tsx

@@ -1,10 +1,12 @@
-import { screen } from "@testing-library/react";
+import { screen, within } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
-import { describe, expect, it } from "vitest";
+import { afterEach, describe, expect, it, vi } from "vitest";
 import { renderWithProviders } from "test-utils";
 import { createRoutesStub } from "react-router";
 import { Sidebar } from "#/components/features/sidebar/sidebar";
 import { MULTI_CONVERSATION_UI } from "#/utils/feature-flags";
+import OpenHands from "#/api/open-hands";
+import { MOCK_USER_PREFERENCES } from "#/mocks/handlers";
 
 const renderSidebar = () => {
   const RouterStub = createRoutesStub([
@@ -43,4 +45,130 @@ describe("Sidebar", () => {
       ).not.toBeInTheDocument();
     },
   );
+
+  describe("Settings", () => {
+    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+
+    afterEach(() => {
+      vi.clearAllMocks();
+    });
+
+    it("should fetch settings data on mount", () => {
+      renderSidebar();
+      expect(getSettingsSpy).toHaveBeenCalledOnce();
+    });
+
+    it("should send all settings data when saving AI configuration", async () => {
+      const user = userEvent.setup();
+      renderSidebar();
+
+      const settingsButton = screen.getByTestId("settings-button");
+      await user.click(settingsButton);
+
+      const settingsModal = screen.getByTestId("ai-config-modal");
+      const saveButton = within(settingsModal).getByTestId(
+        "save-settings-button",
+      );
+      await user.click(saveButton);
+
+      expect(saveSettingsSpy).toHaveBeenCalledWith({
+        ...MOCK_USER_PREFERENCES.settings,
+        // the actual values are falsey (null or "") but we're checking for undefined
+        llm_api_key: undefined,
+        llm_base_url: undefined,
+        security_analyzer: undefined,
+      });
+    });
+
+    it("should send all settings data when saving account settings", async () => {
+      const user = userEvent.setup();
+      renderSidebar();
+
+      const userAvatar = screen.getByTestId("user-avatar");
+      await user.click(userAvatar);
+
+      const menu = screen.getByTestId("account-settings-context-menu");
+      const accountSettingsButton = within(menu).getByTestId(
+        "account-settings-button",
+      );
+      await user.click(accountSettingsButton);
+
+      const accountSettingsModal = screen.getByTestId("account-settings-form");
+      const saveButton =
+        within(accountSettingsModal).getByTestId("save-settings");
+      await user.click(saveButton);
+
+      expect(saveSettingsSpy).toHaveBeenCalledWith({
+        ...MOCK_USER_PREFERENCES.settings,
+        llm_api_key: undefined, // null or undefined
+      });
+    });
+
+    it("should not reset AI configuration when saving account settings", async () => {
+      const user = userEvent.setup();
+      renderSidebar();
+
+      const userAvatar = screen.getByTestId("user-avatar");
+      await user.click(userAvatar);
+
+      const menu = screen.getByTestId("account-settings-context-menu");
+      const accountSettingsButton = within(menu).getByTestId(
+        "account-settings-button",
+      );
+      await user.click(accountSettingsButton);
+
+      const accountSettingsModal = screen.getByTestId("account-settings-form");
+
+      const languageInput =
+        within(accountSettingsModal).getByLabelText(/language/i);
+      await user.click(languageInput);
+
+      const norskOption = screen.getByText(/norsk/i);
+      await user.click(norskOption);
+
+      const tokenInput =
+        within(accountSettingsModal).getByLabelText(/GITHUB\$TOKEN_LABEL/i);
+      await user.type(tokenInput, "new-token");
+
+      const saveButton =
+        within(accountSettingsModal).getByTestId("save-settings");
+      await user.click(saveButton);
+
+      expect(saveSettingsSpy).toHaveBeenCalledWith({
+        ...MOCK_USER_PREFERENCES.settings,
+        language: "no",
+        llm_api_key: undefined, // null or undefined
+      });
+    });
+
+    it("should not send the api key if its SET", async () => {
+      const user = userEvent.setup();
+      renderSidebar();
+
+      const settingsButton = screen.getByTestId("settings-button");
+      await user.click(settingsButton);
+
+      const settingsModal = screen.getByTestId("ai-config-modal");
+
+      // Click the advanced options switch to show the API key input
+      const advancedOptionsSwitch = within(settingsModal).getByTestId("advanced-option-switch");
+      await user.click(advancedOptionsSwitch);
+
+      const apiKeyInput = within(settingsModal).getByLabelText(/API\$KEY/i);
+      await user.type(apiKeyInput, "**********");
+
+      const saveButton = within(settingsModal).getByTestId(
+        "save-settings-button",
+      );
+      await user.click(saveButton);
+
+      expect(saveSettingsSpy).toHaveBeenCalledWith({
+        ...MOCK_USER_PREFERENCES.settings,
+        llm_api_key: undefined,
+        llm_base_url: "",
+        security_analyzer: undefined,
+      });
+    });
+  });
 });

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

@@ -1,11 +1,10 @@
-import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
-import * as router from "react-router";
+import { afterEach, describe, expect, it, vi } from "vitest";
 
 // Mock useParams before importing components
 vi.mock("react-router", async () => {
   const actual = await vi.importActual("react-router");
   return {
-    ...actual as object,
+    ...(actual as object),
     useParams: () => ({ conversationId: "test-conversation-id" }),
   };
 });
@@ -14,6 +13,7 @@ import { screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { renderWithProviders } from "test-utils";
 import { FeedbackForm } from "#/components/features/feedback/feedback-form";
+import { I18nKey } from "#/i18n/declaration";
 
 describe("FeedbackForm", () => {
   const user = userEvent.setup();
@@ -28,20 +28,20 @@ describe("FeedbackForm", () => {
       <FeedbackForm polarity="positive" onClose={onCloseMock} />,
     );
 
-    screen.getByLabelText("Email");
-    screen.getByLabelText("Private");
-    screen.getByLabelText("Public");
+    screen.getByLabelText(I18nKey.FEEDBACK$EMAIL_LABEL);
+    screen.getByLabelText(I18nKey.FEEDBACK$PRIVATE_LABEL);
+    screen.getByLabelText(I18nKey.FEEDBACK$PUBLIC_LABEL);
 
-    screen.getByRole("button", { name: "Submit" });
-    screen.getByRole("button", { name: "Cancel" });
+    screen.getByRole("button", { name: I18nKey.FEEDBACK$CONTRIBUTE_LABEL });
+    screen.getByRole("button", { name: I18nKey.FEEDBACK$CANCEL_LABEL });
   });
 
   it("should switch between private and public permissions", async () => {
     renderWithProviders(
       <FeedbackForm polarity="positive" onClose={onCloseMock} />,
     );
-    const privateRadio = screen.getByLabelText("Private");
-    const publicRadio = screen.getByLabelText("Public");
+    const privateRadio = screen.getByLabelText(I18nKey.FEEDBACK$PRIVATE_LABEL);
+    const publicRadio = screen.getByLabelText(I18nKey.FEEDBACK$PUBLIC_LABEL);
 
     expect(privateRadio).toBeChecked(); // private is the default value
     expect(publicRadio).not.toBeChecked();
@@ -59,7 +59,9 @@ describe("FeedbackForm", () => {
     renderWithProviders(
       <FeedbackForm polarity="positive" onClose={onCloseMock} />,
     );
-    await user.click(screen.getByRole("button", { name: "Cancel" }));
+    await user.click(
+      screen.getByRole("button", { name: I18nKey.FEEDBACK$CANCEL_LABEL }),
+    );
 
     expect(onCloseMock).toHaveBeenCalled();
   });

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

@@ -157,7 +157,7 @@ describe("InteractiveChatBox", () => {
     expect(onChange).not.toHaveBeenCalledWith("");
 
     // Submit the message with image
-    const submitButton = screen.getByRole("button", { name: "Send" });
+    const submitButton = screen.getByRole("button", { name: "BUTTON$SEND" });
     await user.click(submitButton);
 
     // Verify onSubmit was called with the message and image

frontend/__tests__/components/landing-translations.test.tsx

@@ -0,0 +1,190 @@
+import { render, screen } from "@testing-library/react";
+import { test, expect, describe, vi } from "vitest";
+import { useTranslation } from "react-i18next";
+import translations from "../../src/i18n/translation.json";
+import { UserAvatar } from "../../src/components/features/sidebar/user-avatar";
+
+vi.mock("@nextui-org/react", () => ({
+  Tooltip: ({ content, children }: { content: string; children: React.ReactNode }) => (
+    <div>
+      {children}
+      <div>{content}</div>
+    </div>
+  ),
+}));
+
+const supportedLanguages = ['en', 'ja', 'zh-CN', 'zh-TW', 'ko-KR', 'de', 'no', 'it', 'pt', 'es', 'ar', 'fr', 'tr'];
+
+// Helper function to check if a translation exists for all supported languages
+function checkTranslationExists(key: string) {
+  const missingTranslations: string[] = [];
+
+  const translationEntry = (translations as Record<string, Record<string, string>>)[key];
+  if (!translationEntry) {
+    throw new Error(`Translation key "${key}" does not exist in translation.json`);
+  }
+
+  for (const lang of supportedLanguages) {
+    if (!translationEntry[lang]) {
+      missingTranslations.push(lang);
+    }
+  }
+
+  return missingTranslations;
+}
+
+// Helper function to find duplicate translation keys
+function findDuplicateKeys(obj: Record<string, any>) {
+  const seen = new Set<string>();
+  const duplicates = new Set<string>();
+
+  // Only check top-level keys as these are our translation keys
+  for (const key in obj) {
+    if (seen.has(key)) {
+      duplicates.add(key);
+    } else {
+      seen.add(key);
+    }
+  }
+
+  return Array.from(duplicates);
+}
+
+vi.mock("react-i18next", () => ({
+  useTranslation: () => ({
+    t: (key: string) => {
+      const translationEntry = (translations as Record<string, Record<string, string>>)[key];
+      return translationEntry?.ja || key;
+    },
+  }),
+}));
+
+describe("Landing page translations", () => {
+  test("should render Japanese translations correctly", () => {
+    // Mock a simple component that uses the translations
+    const TestComponent = () => {
+      const { t } = useTranslation();
+      return (
+        <div>
+          <UserAvatar onClick={() => {}} />
+          <div data-testid="main-content">
+            <h1>{t("LANDING$TITLE")}</h1>
+            <button>{t("VSCODE$OPEN")}</button>
+            <button>{t("SUGGESTIONS$INCREASE_TEST_COVERAGE")}</button>
+            <button>{t("SUGGESTIONS$AUTO_MERGE_PRS")}</button>
+            <button>{t("SUGGESTIONS$FIX_README")}</button>
+            <button>{t("SUGGESTIONS$CLEAN_DEPENDENCIES")}</button>
+          </div>
+          <div data-testid="tabs">
+            <span>{t("WORKSPACE$TERMINAL_TAB_LABEL")}</span>
+            <span>{t("WORKSPACE$BROWSER_TAB_LABEL")}</span>
+            <span>{t("WORKSPACE$JUPYTER_TAB_LABEL")}</span>
+            <span>{t("WORKSPACE$CODE_EDITOR_TAB_LABEL")}</span>
+          </div>
+          <div data-testid="workspace-label">{t("WORKSPACE$TITLE")}</div>
+          <button data-testid="new-project">{t("PROJECT$NEW_PROJECT")}</button>
+          <div data-testid="status">
+            <span>{t("TERMINAL$WAITING_FOR_CLIENT")}</span>
+            <span>{t("STATUS$CONNECTED")}</span>
+            <span>{t("STATUS$CONNECTED_TO_SERVER")}</span>
+          </div>
+          <div data-testid="time">
+            <span>{`5 ${t("TIME$MINUTES_AGO")}`}</span>
+            <span>{`2 ${t("TIME$HOURS_AGO")}`}</span>
+            <span>{`3 ${t("TIME$DAYS_AGO")}`}</span>
+          </div>
+        </div>
+      );
+    };
+
+    render(<TestComponent />);
+
+    // Check main content translations
+    expect(screen.getByText("開発を始めましょう！")).toBeInTheDocument();
+    expect(screen.getByText("VS Codeで開く")).toBeInTheDocument();
+    expect(screen.getByText("テストカバレッジを向上させる")).toBeInTheDocument();
+    expect(screen.getByText("Dependabot PRを自動マージ")).toBeInTheDocument();
+    expect(screen.getByText("READMEを改善")).toBeInTheDocument();
+    expect(screen.getByText("依存関係を整理")).toBeInTheDocument();
+
+    // Check user avatar tooltip
+    const userAvatar = screen.getByTestId("user-avatar");
+    userAvatar.focus();
+    expect(screen.getByText("アカウント設定")).toBeInTheDocument();
+
+    // Check tab labels
+    const tabs = screen.getByTestId("tabs");
+    expect(tabs).toHaveTextContent("ターミナル");
+    expect(tabs).toHaveTextContent("ブラウザ");
+    expect(tabs).toHaveTextContent("Jupyter");
+    expect(tabs).toHaveTextContent("コードエディタ");
+
+    // Check workspace label and new project button
+    expect(screen.getByTestId("workspace-label")).toHaveTextContent("ワークスペース");
+    expect(screen.getByTestId("new-project")).toHaveTextContent("新規プロジェクト");
+
+    // Check status messages
+    const status = screen.getByTestId("status");
+    expect(status).toHaveTextContent("クライアントの準備を待機中");
+    expect(status).toHaveTextContent("接続済み");
+    expect(status).toHaveTextContent("サーバーに接続済み");
+
+    // Check account settings menu
+    expect(screen.getByText("アカウント設定")).toBeInTheDocument();
+
+    // Check time-related translations
+    const time = screen.getByTestId("time");
+    expect(time).toHaveTextContent("5 分前");
+    expect(time).toHaveTextContent("2 時間前");
+    expect(time).toHaveTextContent("3 日前");
+  });
+
+  test("all translation keys should have translations for all supported languages", () => {
+    // Test all translation keys used in the component
+    const translationKeys = [
+      "LANDING$TITLE",
+      "VSCODE$OPEN",
+      "SUGGESTIONS$INCREASE_TEST_COVERAGE",
+      "SUGGESTIONS$AUTO_MERGE_PRS",
+      "SUGGESTIONS$FIX_README",
+      "SUGGESTIONS$CLEAN_DEPENDENCIES",
+      "WORKSPACE$TERMINAL_TAB_LABEL",
+      "WORKSPACE$BROWSER_TAB_LABEL",
+      "WORKSPACE$JUPYTER_TAB_LABEL",
+      "WORKSPACE$CODE_EDITOR_TAB_LABEL",
+      "WORKSPACE$TITLE",
+      "PROJECT$NEW_PROJECT",
+      "TERMINAL$WAITING_FOR_CLIENT",
+      "STATUS$CONNECTED",
+      "STATUS$CONNECTED_TO_SERVER",
+      "TIME$MINUTES_AGO",
+      "TIME$HOURS_AGO",
+      "TIME$DAYS_AGO"
+    ];
+
+    // Check all keys and collect missing translations
+    const missingTranslationsMap = new Map<string, string[]>();
+    translationKeys.forEach(key => {
+      const missing = checkTranslationExists(key);
+      if (missing.length > 0) {
+        missingTranslationsMap.set(key, missing);
+      }
+    });
+
+    // If any translations are missing, throw an error with all missing translations
+    if (missingTranslationsMap.size > 0) {
+      const errorMessage = Array.from(missingTranslationsMap.entries())
+        .map(([key, langs]) => `\n- "${key}" is missing translations for: ${langs.join(', ')}`)
+        .join('');
+      throw new Error(`Missing translations:${errorMessage}`);
+    }
+  });
+
+  test("translation file should not have duplicate keys", () => {
+    const duplicates = findDuplicateKeys(translations);
+
+    if (duplicates.length > 0) {
+      throw new Error(`Found duplicate translation keys: ${duplicates.join(', ')}`);
+    }
+  });
+});

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

@@ -4,13 +4,21 @@ import { describe, it, vi, expect } from "vitest";
 import { BaseModal } from "#/components/shared/modals/base-modal/base-modal";
 
 describe("BaseModal", () => {
+  const onOpenChangeMock = vi.fn();
+
   it("should render if the modal is open", () => {
     const { rerender } = render(
-      <BaseModal isOpen={false} onOpenChange={vi.fn} title="Settings" />,
+      <BaseModal
+        isOpen={false}
+        onOpenChange={onOpenChangeMock}
+        title="Settings"
+      />,
     );
     expect(screen.queryByText("Settings")).not.toBeInTheDocument();
 
-    rerender(<BaseModal title="Settings" onOpenChange={vi.fn} isOpen />);
+    rerender(
+      <BaseModal title="Settings" onOpenChange={onOpenChangeMock} isOpen />,
+    );
     expect(screen.getByText("Settings")).toBeInTheDocument();
   });
 
@@ -18,7 +26,7 @@ describe("BaseModal", () => {
     render(
       <BaseModal
         isOpen
-        onOpenChange={vi.fn}
+        onOpenChange={onOpenChangeMock}
         title="Settings"
         subtitle="Subtitle"
       />,
@@ -43,7 +51,7 @@ describe("BaseModal", () => {
     render(
       <BaseModal
         isOpen
-        onOpenChange={vi.fn}
+        onOpenChange={onOpenChangeMock}
         title="Settings"
         actions={[primaryAction, secondaryAction]}
       />,
@@ -60,7 +68,6 @@ describe("BaseModal", () => {
   });
 
   it("should close the modal after an action is performed", async () => {
-    const onOpenChangeMock = vi.fn();
     render(
       <BaseModal
         isOpen
@@ -82,7 +89,7 @@ describe("BaseModal", () => {
 
   it("should render children", () => {
     render(
-      <BaseModal isOpen onOpenChange={vi.fn} title="Settings">
+      <BaseModal isOpen onOpenChange={onOpenChangeMock} title="Settings">
         <div>Children</div>
       </BaseModal>,
     );
@@ -93,7 +100,7 @@ describe("BaseModal", () => {
     const { rerender } = render(
       <BaseModal
         isOpen
-        onOpenChange={vi.fn}
+        onOpenChange={onOpenChangeMock}
         title="Settings"
         actions={[
           {
@@ -110,7 +117,7 @@ describe("BaseModal", () => {
     rerender(
       <BaseModal
         isOpen
-        onOpenChange={vi.fn}
+        onOpenChange={onOpenChangeMock}
         title="Settings"
         actions={[
           {
@@ -126,7 +133,6 @@ describe("BaseModal", () => {
   });
 
   it.skip("should not close if the backdrop or escape key is pressed", () => {
-    const onOpenChangeMock = vi.fn();
     render(
       <BaseModal
         isOpen

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

@@ -1,7 +1,23 @@
-import { describe, it, expect } from "vitest";
+import { describe, it, expect, vi } from "vitest";
 import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { ModelSelector } from "#/components/shared/modals/settings/model-selector";
+import { I18nKey } from "#/i18n/declaration";
+
+// Mock react-i18next
+vi.mock("react-i18next", () => ({
+  useTranslation: () => ({
+    t: (key: string) => {
+      const translations: { [key: string]: string } = {
+        LLM$PROVIDER: "LLM Provider",
+        LLM$MODEL: "LLM Model",
+        LLM$SELECT_PROVIDER_PLACEHOLDER: "Select a provider",
+        LLM$SELECT_MODEL_PLACEHOLDER: "Select a model",
+      };
+      return translations[key] || key;
+    },
+  }),
+}));
 
 describe("ModelSelector", () => {
   const models = {

frontend/__tests__/components/shared/modals/settings/settings-form.test.tsx

@@ -1,13 +1,22 @@
 import { screen, fireEvent } from "@testing-library/react";
-import { describe, it, expect, vi } from "vitest";
+import { describe, it, expect, vi, afterEach } from "vitest";
 import { renderWithProviders } from "test-utils";
 import { createRoutesStub } from "react-router";
+import userEvent from "@testing-library/user-event";
 import { DEFAULT_SETTINGS } from "#/services/settings";
 import { SettingsForm } from "#/components/shared/modals/settings/settings-form";
 import OpenHands from "#/api/open-hands";
 
 describe("SettingsForm", () => {
   const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+  const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
+
+  const onCloseMock = vi.fn();
+
+  afterEach(() => {
+    vi.clearAllMocks();
+  });
+
   getConfigSpy.mockResolvedValue({
     APP_MODE: "saas",
     GITHUB_CLIENT_ID: "123",
@@ -19,10 +28,10 @@ describe("SettingsForm", () => {
       Component: () => (
         <SettingsForm
           settings={DEFAULT_SETTINGS}
-          models={[]}
-          agents={[]}
-          securityAnalyzers={[]}
-          onClose={() => {}}
+          models={["anthropic/claude-3-5-sonnet-20241022", "model2"]}
+          agents={["CodeActAgent", "agent2"]}
+          securityAnalyzers={["analyzer1", "analyzer2"]}
+          onClose={onCloseMock}
         />
       ),
       path: "/",
@@ -35,11 +44,33 @@ describe("SettingsForm", () => {
   });
 
   it("should show runtime size selector when advanced options are enabled", async () => {
+    const user = userEvent.setup();
     renderWithProviders(<RouterStub />);
-    const advancedSwitch = screen.getByRole("switch", {
-      name: "SETTINGS_FORM$ADVANCED_OPTIONS_LABEL",
-    });
-    fireEvent.click(advancedSwitch);
-    await screen.findByText("SETTINGS_FORM$RUNTIME_SIZE_LABEL");
+
+    const toggleAdvancedMode = screen.getByTestId("advanced-option-switch");
+    await user.click(toggleAdvancedMode);
+
+    await screen.findByTestId("runtime-size");
+  });
+
+  it("should not submit the form if required fields are empty", async () => {
+    const user = userEvent.setup();
+    renderWithProviders(<RouterStub />);
+
+    expect(screen.queryByTestId("custom-model-input")).not.toBeInTheDocument();
+
+    const toggleAdvancedMode = screen.getByTestId("advanced-option-switch");
+    await user.click(toggleAdvancedMode);
+
+    const customModelInput = screen.getByTestId("custom-model-input");
+    expect(customModelInput).toBeInTheDocument();
+
+    await user.clear(customModelInput);
+
+    const saveButton = screen.getByTestId("save-settings-button");
+    await user.click(saveButton);
+
+    expect(saveSettingsSpy).not.toHaveBeenCalled();
+    expect(onCloseMock).not.toHaveBeenCalled();
   });
 });

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

@@ -2,6 +2,20 @@ import { render, screen } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
 import { SuggestionItem } from "#/components/features/suggestions/suggestion-item";
+import { I18nKey } from "#/i18n/declaration";
+
+vi.mock("react-i18next", () => ({
+  useTranslation: () => ({
+    t: (key: string) => {
+      const translations: Record<string, string> = {
+        "SUGGESTIONS$TODO_APP": "ToDoリストアプリを開発する",
+        "LANDING$BUILD_APP_BUTTON": "プルリクエストを表示するアプリを開発する",
+        "SUGGESTIONS$HACKER_NEWS": "Hacker Newsのトップ記事を表示するbashスクリプトを作成する",
+      };
+      return translations[key] || key;
+    },
+  }),
+}));
 
 describe("SuggestionItem", () => {
   const suggestionItem = { label: "suggestion1", value: "a long text value" };
@@ -18,6 +32,19 @@ describe("SuggestionItem", () => {
     expect(screen.getByText(/suggestion1/i)).toBeInTheDocument();
   });
 
+  it("should render a translated suggestion when using I18nKey", async () => {
+    const translatedSuggestion = {
+      label: I18nKey.SUGGESTIONS$TODO_APP,
+      value: "todo app value",
+    };
+
+    const { container } = render(<SuggestionItem suggestion={translatedSuggestion} onClick={onClick} />);
+    console.log('Rendered HTML:', container.innerHTML);
+
+
+    expect(screen.getByText("ToDoリストアプリを開発する")).toBeInTheDocument();
+  });
+
   it("should call onClick when clicking a suggestion", async () => {
     const user = userEvent.setup();
     render(<SuggestionItem suggestion={suggestionItem} onClick={onClick} />);

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

@@ -14,7 +14,7 @@ describe("UserAvatar", () => {
     render(<UserAvatar onClick={onClickMock} />);
     expect(screen.getByTestId("user-avatar")).toBeInTheDocument();
     expect(
-      screen.getByLabelText("user avatar placeholder"),
+      screen.getByLabelText("USER$AVATAR_PLACEHOLDER"),
     ).toBeInTheDocument();
   });
 
@@ -38,7 +38,7 @@ describe("UserAvatar", () => {
 
     expect(screen.getByAltText("user avatar")).toBeInTheDocument();
     expect(
-      screen.queryByLabelText("user avatar placeholder"),
+      screen.queryByLabelText("USER$AVATAR_PLACEHOLDER"),
     ).not.toBeInTheDocument();
   });
 
@@ -46,13 +46,13 @@ describe("UserAvatar", () => {
     const { rerender } = render(<UserAvatar onClick={onClickMock} />);
     expect(screen.queryByTestId("loading-spinner")).not.toBeInTheDocument();
     expect(
-      screen.getByLabelText("user avatar placeholder"),
+      screen.getByLabelText("USER$AVATAR_PLACEHOLDER"),
     ).toBeInTheDocument();
 
     rerender(<UserAvatar onClick={onClickMock} isLoading />);
     expect(screen.getByTestId("loading-spinner")).toBeInTheDocument();
     expect(
-      screen.queryByLabelText("user avatar placeholder"),
+      screen.queryByLabelText("USER$AVATAR_PLACEHOLDER"),
     ).not.toBeInTheDocument();
 
     rerender(

frontend/__tests__/context/ws-client-provider.test.tsx

@@ -0,0 +1,43 @@
+import { describe, it, expect, vi } from "vitest";
+import { render, screen } from "@testing-library/react";
+import * as ChatSlice from "#/state/chat-slice";
+import {
+  updateStatusWhenErrorMessagePresent,
+} from "#/context/ws-client-provider";
+
+describe("Propagate error message", () => {
+  it("should do nothing when no message was passed from server", () => {
+    const addErrorMessageSpy = vi.spyOn(ChatSlice, "addErrorMessage");
+    updateStatusWhenErrorMessagePresent(null)
+    updateStatusWhenErrorMessagePresent(undefined)
+    updateStatusWhenErrorMessagePresent({})
+    updateStatusWhenErrorMessagePresent({message: null})
+
+    expect(addErrorMessageSpy).not.toHaveBeenCalled();
+  });
+
+  it("should display error to user when present", () => {
+    const message = "We have a problem!"
+    const addErrorMessageSpy = vi.spyOn(ChatSlice, "addErrorMessage")
+    updateStatusWhenErrorMessagePresent({message})
+
+    expect(addErrorMessageSpy).toHaveBeenCalledWith({
+      message,
+      status_update: true,
+      type: 'error'
+     });
+  });
+
+  it("should display error including translation id when present", () => {
+    const message = "We have a problem!"
+    const addErrorMessageSpy = vi.spyOn(ChatSlice, "addErrorMessage")
+    updateStatusWhenErrorMessagePresent({message, data: {msg_id: '..id..'}})
+
+    expect(addErrorMessageSpy).toHaveBeenCalledWith({
+      message,
+      id: '..id..',
+      status_update: true,
+      type: 'error'
+     });
+  });
+});

frontend/__tests__/i18n/duplicate-keys.test.ts

@@ -0,0 +1,76 @@
+import { describe, expect, it } from 'vitest';
+import fs from 'fs';
+import path from 'path';
+
+describe('translation.json', () => {
+  it('should not have duplicate translation keys', () => {
+    // Read the translation.json file
+    const translationPath = path.join(__dirname, '../../src/i18n/translation.json');
+    const translationContent = fs.readFileSync(translationPath, 'utf-8');
+
+    // First, let's check for exact string matches of key definitions
+    const keyRegex = /"([^"]+)": {/g;
+    const matches = translationContent.matchAll(keyRegex);
+    const keyOccurrences = new Map<string, number>();
+    const duplicateKeys: string[] = [];
+
+    for (const match of matches) {
+      const key = match[1];
+      const count = (keyOccurrences.get(key) || 0) + 1;
+      keyOccurrences.set(key, count);
+      if (count > 1) {
+        duplicateKeys.push(key);
+      }
+    }
+
+    // Remove duplicates from duplicateKeys array
+    const uniqueDuplicates = [...new Set(duplicateKeys)];
+
+    // If there are duplicates, create a helpful error message
+    if (uniqueDuplicates.length > 0) {
+      const errorMessage = `Found duplicate translation keys:\n${uniqueDuplicates
+        .map((key) => `  - "${key}" appears ${keyOccurrences.get(key)} times`)
+        .join('\n')}`;
+      throw new Error(errorMessage);
+    }
+
+    // Expect no duplicates (this will pass if we reach here)
+    expect(uniqueDuplicates).toHaveLength(0);
+  });
+
+  it('should have consistent translations for each key', () => {
+    // Read the translation.json file
+    const translationPath = path.join(__dirname, '../../src/i18n/translation.json');
+    const translationContent = fs.readFileSync(translationPath, 'utf-8');
+    const translations = JSON.parse(translationContent);
+
+    // Create a map to store English translations for each key
+    const englishTranslations = new Map<string, string>();
+    const inconsistentKeys: string[] = [];
+
+    // Check each key's English translation
+    Object.entries(translations).forEach(([key, value]: [string, any]) => {
+      if (typeof value === 'object' && value.en !== undefined) {
+        const currentEn = value.en.toLowerCase();
+        const existingEn = englishTranslations.get(key)?.toLowerCase();
+
+        if (existingEn !== undefined && existingEn !== currentEn) {
+          inconsistentKeys.push(key);
+        } else {
+          englishTranslations.set(key, value.en);
+        }
+      }
+    });
+
+    // If there are inconsistencies, create a helpful error message
+    if (inconsistentKeys.length > 0) {
+      const errorMessage = `Found inconsistent translations for keys:\n${inconsistentKeys
+        .map((key) => `  - "${key}" has multiple different English translations`)
+        .join('\n')}`;
+      throw new Error(errorMessage);
+    }
+
+    // Expect no inconsistencies
+    expect(inconsistentKeys).toHaveLength(0);
+  });
+});

frontend/__tests__/i18n/translations.test.tsx

@@ -0,0 +1,20 @@
+import { screen } from '@testing-library/react';
+import { describe, expect, it } from 'vitest';
+import i18n from '../../src/i18n';
+import { AccountSettingsContextMenu } from '../../src/components/features/context-menu/account-settings-context-menu';
+import { renderWithProviders } from '../../test-utils';
+
+describe('Translations', () => {
+  it('should render translated text', () => {
+    i18n.changeLanguage('en');
+    renderWithProviders(
+      <AccountSettingsContextMenu
+        onClickAccountSettings={() => {}}
+        onLogout={() => {}}
+        onClose={() => {}}
+        isLoggedIn={true}
+      />
+    );
+    expect(screen.getByTestId('account-settings-context-menu')).toBeInTheDocument();
+  });
+});

frontend/__tests__/routes/_oh.app.test.tsx

@@ -60,6 +60,7 @@ describe("App", () => {
     getConversationSpy.mockResolvedValue({
       conversation_id: "9999",
       last_updated_at: "",
+      created_at: "",
       title: "",
       selected_repository: "",
       status: "STOPPED",

frontend/__tests__/routes/_oh.test.tsx

@@ -1,5 +1,4 @@
 import { afterEach, beforeAll, describe, expect, it, vi } from "vitest";
-import * as router from "react-router";
 import { createRoutesStub } from "react-router";
 import { screen, waitFor, within } from "@testing-library/react";
 import { renderWithProviders } from "test-utils";

frontend/__tests__/utils/check-hardcoded-strings.test.tsx

@@ -0,0 +1,40 @@
+import { render, screen } from "@testing-library/react";
+import { test, expect, describe, vi } from "vitest";
+import { InteractiveChatBox } from "#/components/features/chat/interactive-chat-box";
+import { ChatInput } from "#/components/features/chat/chat-input";
+
+// Mock react-i18next
+vi.mock("react-i18next", () => ({
+  useTranslation: () => ({
+    t: (key: string) => key,
+  }),
+}));
+
+describe("Check for hardcoded English strings", () => {
+  test("InteractiveChatBox should not have hardcoded English strings", () => {
+    const { container } = render(
+      <InteractiveChatBox
+        onSubmit={() => {}}
+        onStop={() => {}}
+      />
+    );
+
+    // Get all text content
+    const text = container.textContent;
+
+    // List of English strings that should be translated
+    const hardcodedStrings = [
+      "What do you want to build?",
+    ];
+
+    // Check each string
+    hardcodedStrings.forEach(str => {
+      expect(text).not.toContain(str);
+    });
+  });
+
+  test("ChatInput should use translation key for placeholder", () => {
+    render(<ChatInput onSubmit={() => {}} />);
+    screen.getByPlaceholderText("SUGGESTIONS$WHAT_TO_BUILD");
+  });
+});

frontend/__tests__/utils/i18n-test-utils.tsx

@@ -0,0 +1,29 @@
+import { ReactNode } from "react";
+import { I18nextProvider } from "react-i18next";
+
+const mockI18n = {
+  language: "ja",
+  t: (key: string) => {
+    const translations: Record<string, string> = {
+      "SUGGESTIONS$TODO_APP": "ToDoリストアプリを開発する",
+      "LANDING$BUILD_APP_BUTTON": "プルリクエストを表示するアプリを開発する",
+      "SUGGESTIONS$HACKER_NEWS": "Hacker Newsのトップ記事を表示するbashスクリプトを作成する",
+      "LANDING$TITLE": "一緒に開発を始めましょう！",
+      "OPEN_IN_VSCODE": "VS Codeで開く",
+      "INCREASE_TEST_COVERAGE": "テストカバレッジを向上",
+      "AUTO_MERGE_PRS": "PRを自動マージ",
+      "FIX_README": "READMEを修正",
+      "CLEAN_DEPENDENCIES": "依存関係を整理"
+    };
+    return translations[key] || key;
+  },
+  exists: () => true,
+  changeLanguage: () => new Promise(() => {}),
+  use: () => mockI18n,
+};
+
+export function I18nTestProvider({ children }: { children: ReactNode }) {
+  return (
+    <I18nextProvider i18n={mockI18n as any}>{children}</I18nextProvider>
+  );
+}

frontend/__tests__/utils/test-config.tsx

@@ -0,0 +1,20 @@
+import { vi } from "vitest";
+import OpenHands from "#/api/open-hands";
+
+export const setupTestConfig = () => {
+  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+  getConfigSpy.mockResolvedValue({
+    APP_MODE: "oss",
+    GITHUB_CLIENT_ID: "test-id",
+    POSTHOG_CLIENT_KEY: "test-key",
+  });
+};
+
+export const setupSaasTestConfig = () => {
+  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+  getConfigSpy.mockResolvedValue({
+    APP_MODE: "saas",
+    GITHUB_CLIENT_ID: "test-id",
+    POSTHOG_CLIENT_KEY: "test-key",
+  });
+};