Add evaluation changes without disabling repository memory

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

.github/ISSUE_TEMPLATE/feature_request.md

@@ -12,3 +12,6 @@ assignees: ''
 **Describe the UX or technical implementation you have in mind**
 
 **Additional context**
+
+
+### If you find this feature request or enhancement useful, make sure to add a 👍 to the issue

.github/workflows/ghcr-build.yml

@@ -174,20 +174,19 @@ jobs:
           build-args: ${{ env.DOCKER_BUILD_ARGS }}
           context: containers/runtime
           provenance: false
-      # Forked repos can't push to GHCR, so we need to upload the image as an artifact
+      # Forked repos can't push to GHCR, so we just build in order to populate the cache for rebuilding
       - name: Build runtime image ${{ matrix.base_image.image }} for fork
         if: github.event.pull_request.head.repo.fork
         uses: useblacksmith/build-push-action@v1
         with:
           tags: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
-          outputs: type=docker,dest=/tmp/runtime-${{ matrix.base_image.tag }}.tar
           context: containers/runtime
-      - name: Upload runtime image for fork
+      - name: Upload runtime source for fork
         if: github.event.pull_request.head.repo.fork
         uses: actions/upload-artifact@v4
         with:
-          name: runtime-${{ matrix.base_image.tag }}
-          path: /tmp/runtime-${{ matrix.base_image.tag }}.tar
+          name: runtime-src-${{ matrix.base_image.tag }}
+          path: containers/runtime
 
   verify_hash_equivalence_in_runtime_and_app:
     name: Verify Hash Equivalence in Runtime and Docker images
@@ -258,17 +257,23 @@ jobs:
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
-      # Forked repos can't push to GHCR, so we need to download the image as an artifact
-      - name: Download runtime image for fork
+      - name: Download runtime source for fork
         if: github.event.pull_request.head.repo.fork
         uses: actions/download-artifact@v4
         with:
-          name: runtime-${{ matrix.base_image.tag }}
-          path: /tmp
-      - name: Load runtime image for fork
-        if: github.event.pull_request.head.repo.fork
+          name: runtime-src-${{ matrix.base_image.tag }}
+          path: containers/runtime
+      - name: Lowercase Repository Owner
         run: |
-          docker load --input /tmp/runtime-${{ matrix.base_image.tag }}.tar
+          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
+      # Forked repos can't push to GHCR, so we need to rebuild using cache
+      - name: Build runtime image ${{ matrix.base_image.image }} for fork
+        if: github.event.pull_request.head.repo.fork
+        uses: useblacksmith/build-push-action@v1
+        with:
+          load: true
+          tags: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+          context: containers/runtime
       - name: Cache Poetry dependencies
         uses: useblacksmith/cache@v5
         with:
@@ -287,9 +292,6 @@ jobs:
         run: pipx install poetry
       - name: Install Python dependencies using Poetry
         run: make install-python-dependencies POETRY_GROUP=main,test,runtime INSTALL_PLAYWRIGHT=0
-      - name: Lowercase Repository Owner
-        run: |
-          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
       - name: Run docker runtime tests
         run: |
           # We install pytest-xdist in order to run tests across CPUs
@@ -327,17 +329,23 @@ jobs:
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
-      # Forked repos can't push to GHCR, so we need to download the image as an artifact
-      - name: Download runtime image for fork
+      - name: Download runtime source for fork
         if: github.event.pull_request.head.repo.fork
         uses: actions/download-artifact@v4
         with:
-          name: runtime-${{ matrix.base_image.tag }}
-          path: /tmp
-      - name: Load runtime image for fork
-        if: github.event.pull_request.head.repo.fork
+          name: runtime-src-${{ matrix.base_image.tag }}
+          path: containers/runtime
+      - name: Lowercase Repository Owner
         run: |
-          docker load --input /tmp/runtime-${{ matrix.base_image.tag }}.tar
+          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
+      # Forked repos can't push to GHCR, so we need to rebuild using cache
+      - name: Build runtime image ${{ matrix.base_image.image }} for fork
+        if: github.event.pull_request.head.repo.fork
+        uses: useblacksmith/build-push-action@v1
+        with:
+          load: true
+          tags: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+          context: containers/runtime
       - name: Cache Poetry dependencies
         uses: useblacksmith/cache@v5
         with:
@@ -356,9 +364,6 @@ jobs:
         run: pipx install poetry
       - name: Install Python dependencies using Poetry
         run: make install-python-dependencies POETRY_GROUP=main,test,runtime INSTALL_PLAYWRIGHT=0
-      - name: Lowercase Repository Owner
-        run: |
-          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
       - name: Run runtime tests
         run: |
           # We install pytest-xdist in order to run tests across CPUs

.github/workflows/lint.yml

@@ -7,7 +7,7 @@ name: Lint
 on:
   push:
     branches:
-      - main
+    - main
   pull_request:
 
 # If triggered by a PR, it will be in the same group. However, each commit on main will be in its own unique group
@@ -33,23 +33,9 @@ jobs:
       - name: Lint and TypeScript compilation
         run: |
           cd frontend
-          npm run lint:fix
+          npm run lint
           npm run make-i18n && tsc
 
-      # Commit and push changes if any as a result of lint:fix
-      - name: Check for changes
-        id: git-check
-        run: |
-          git diff --quiet || echo "changes=true" >> $GITHUB_OUTPUT
-      - name: Commit and push if there are changes
-        if: steps.git-check.outputs.changes == 'true'
-        run: |
-          git config --local user.email "openhands@all-hands.dev"
-          git config --local user.name "OpenHands Bot"
-          git add -A
-          git commit -m "🤖 Auto-fix frontend linting issues"
-          git push
-
   # Run lint on the python code
   lint-python:
     name: Lint python

.github/workflows/openhands-resolver.yml

@@ -16,6 +16,11 @@ on:
         type: string
         default: "main"
         description: "Target branch to pull and create PR against"
+      pr_type:
+        required: false
+        type: string
+        default: "draft"
+        description: "The PR type that is going to be created (draft, ready)"
       LLM_MODEL:
         required: false
         type: string
@@ -280,9 +285,9 @@ jobs:
             cd /tmp && python -m openhands.resolver.send_pull_request \
               --issue-number ${{ env.ISSUE_NUMBER }} \
               --target-branch ${{ env.TARGET_BRANCH }} \
-              --pr-type draft \
+              --pr-type ${{ inputs.pr_type || 'draft' }} \
               --reviewer ${{ github.actor }} | tee pr_result.txt && \
-              grep "draft created" pr_result.txt | sed 's/.*\///g' > pr_number.txt
+              grep "PR created" pr_result.txt | sed 's/.*\///g' > pr_number.txt
           else
             cd /tmp && python -m openhands.resolver.send_pull_request \
               --issue-number ${{ env.ISSUE_NUMBER }} \

README.md

@@ -27,7 +27,7 @@ Welcome to OpenHands (formerly OpenDevin), a platform for software development a
 OpenHands agents can do anything a human developer can: modify code, run commands, browse the web,
 call APIs, and yes—even copy code snippets from StackOverflow.
 
-Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or jump to the [Quick Start](#-quick-start).
+Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or [sign up for OpenHands Cloud](https://app.all-hands.dev) to get started.
 
 > [!IMPORTANT]
 > Using OpenHands for work? We'd love to chat! Fill out
@@ -36,12 +36,21 @@ Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or jump to the [
 
 ![App screenshot](./docs/static/img/screenshot.png)
 
-## ⚡ Quick Start
+## ☁️ OpenHands Cloud
+The easiest way to get started with OpenHands is on [OpenHands Cloud](https://app.all-hands.dev),
+which comes with $50 in free credits for new users.
 
-The easiest way to run OpenHands is in Docker.
+## 💻 Running OpenHands Locally
+
+OpenHands can also run on your local system using Docker.
 See the [Running OpenHands](https://docs.all-hands.dev/modules/usage/installation) guide for
 system requirements and more information.
 
+> [!WARNING]
+> On a public network? See our [Hardened Docker Installation Guide](https://docs.all-hands.dev/modules/usage/runtimes/docker#hardened-docker-installation)
+> to secure your deployment by restricting network binding and implementing additional security measures.
+
+
 ```bash
 docker pull docker.all-hands.dev/all-hands-ai/runtime:0.32-nikolaik
 
@@ -56,17 +65,21 @@ docker run -it --rm --pull=always \
     docker.all-hands.dev/all-hands-ai/openhands:0.32
 ```
 
-> [!WARNING]
-> On a public network? See our [Hardened Docker Installation](https://docs.all-hands.dev/modules/usage/runtimes/docker#hardened-docker-installation) guide
-> to secure your deployment by restricting network binding and implementing additional security measures.
-
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
 
-Finally, you'll need a model provider and API key.
+When you open the application, you'll be asked to choose an LLM provider and add an API key.
 [Anthropic's Claude 3.5 Sonnet](https://www.anthropic.com/api) (`anthropic/claude-3-5-sonnet-20241022`)
 works best, but you have [many options](https://docs.all-hands.dev/modules/usage/llms).
 
----
+## 💡 Other ways to run OpenHands
+
+> [!CAUTION]
+> OpenHands is meant to be run by a single user on their local workstation.
+> It is not appropriate for multi-tenant deployments where multiple users share the same instance. There is no built-in authentication, isolation, or scalability.
+>
+> If you're interested in running OpenHands in a multi-tenant environment, please
+> [get in touch with us](https://docs.google.com/forms/d/e/1FAIpQLSet3VbGaz8z32gW9Wm-Grl4jpt5WgMXPgJ4EDPVmCETCBpJtQ/viewform)
+> for advanced deployment options.
 
 You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes/docker#connecting-to-your-filesystem),
 run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
@@ -75,14 +88,6 @@ or run it on tagged issues with [a github action](https://docs.all-hands.dev/mod
 
 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.
-> It is not appropriate for multi-tenant deployments where multiple users share the same instance. There is no built-in isolation or scalability.
->
-> If you're interested in running OpenHands in a multi-tenant environment, please
-> [get in touch with us](https://docs.google.com/forms/d/e/1FAIpQLSet3VbGaz8z32gW9Wm-Grl4jpt5WgMXPgJ4EDPVmCETCBpJtQ/viewform)
-> for advanced deployment options.
-
 If you want to modify the OpenHands source code, check out [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
 
 Having issues? The [Troubleshooting Guide](https://docs.all-hands.dev/modules/usage/troubleshooting) can help.

config.template.toml

@@ -216,13 +216,13 @@ model = "gpt-4o"
 [agent]
 
 # Whether the browsing tool is enabled
-codeact_enable_browsing = true
+enable_browsing = true
 
 # Whether the LLM draft editor is enabled
-codeact_enable_llm_editor = false
+enable_llm_editor = false
 
 # Whether the IPython tool is enabled
-codeact_enable_jupyter = true
+enable_jupyter = true
 
 # LLM config group to use
 #llm_config = 'your-llm-config-group'

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

@@ -354,12 +354,12 @@ Les options de configuration de l'agent sont définies dans les sections `[agent
   - Valeur par défaut : `true`
   - Description : Si l'appel de fonction est activé
 
-- `codeact_enable_browsing`
+- `enable_browsing`
   - Type : `bool`
   - Valeur par défaut : `false`
   - Description : Si le délégué de navigation est activé dans l'espace d'action (fonctionne uniquement avec l'appel de fonction)
 
-- `codeact_enable_llm_editor`
+- `enable_llm_editor`
   - Type : `bool`
   - Valeur par défaut : `false`
   - Description : Si l'éditeur LLM est activé dans l'espace d'action (fonctionne uniquement avec l'appel de fonction)

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

@@ -348,12 +348,12 @@ dockerコマンドで使用する場合は、`-e LLM_<option>`として渡しま
   - デフォルト値: `true`
   - 説明: 関数呼び出しが有効かどうか
 
-- `codeact_enable_browsing`
+- `enable_browsing`
   - 型: `bool`
   - デフォルト値: `false`
   - 説明: アクションスペースでブラウジングデリゲートが有効かどうか（関数呼び出しでのみ機能）
 
-- `codeact_enable_llm_editor`
+- `enable_llm_editor`
   - 型: `bool`
   - デフォルト値: `false`
   - 説明: アクションスペースでLLMエディタが有効かどうか（関数呼び出しでのみ機能）

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

@@ -292,17 +292,17 @@ As opções de configuração do agente são definidas nas seções `[agent]` e
   - Padrão: `true`
   - Descrição: Se a chamada de função está habilitada
 
-- `codeact_enable_browsing`
+- `enable_browsing`
   - Tipo: `bool`
   - Padrão: `false`
   - Descrição: Se o delegado de navegação está habilitado no espaço de ação (funciona apenas com chamada de função)
 
-- `codeact_enable_llm_editor`
+- `enable_llm_editor`
   - Tipo: `bool`
   - Padrão: `false`
   - Descrição: Se o editor LLM está habilitado no espaço de ação (funciona apenas com chamada de função)
 
-- `codeact_enable_jupyter`
+- `enable_jupyter`
   - Tipo: `bool`
   - Padrão: `false`
   - Descrição: Se o Jupyter está habilitado no espaço de ação

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

@@ -349,17 +349,17 @@ Agent 配置选项在 `config.toml` 文件的 `[agent]` 和 `[agent.<agent_name>
   - 默认值: `true`
   - 描述: 是否启用函数调用
 
-- `codeact_enable_browsing`
+- `enable_browsing`
   - 类型: `bool`
   - 默认值: `false`
   - 描述: 是否在 action space 中启用浏览代理(仅适用于函数调用)
 
-- `codeact_enable_llm_editor`
+- `enable_llm_editor`
   - 类型: `bool`
   - 默认值: `false`
   - 描述: 是否在 action space 中启用 LLM 编辑器(仅适用于函数调用)
 
-- `codeact_enable_jupyter`
+- `enable_jupyter`
   - 类型: `bool`
   - 默认值: `false`
   - 描述: 是否在 action space 中启用 Jupyter

docs/modules/usage/configuration-options.md

@@ -291,17 +291,17 @@ The agent configuration options are defined in the `[agent]` and `[agent.<agent_
   - Default: `true`
   - Description: Whether function calling is enabled
 
-- `codeact_enable_browsing`
+- `enable_browsing`
   - Type: `bool`
   - Default: `false`
   - Description: Whether browsing delegate is enabled in the action space (only works with function calling)
 
-- `codeact_enable_llm_editor`
+- `enable_llm_editor`
   - Type: `bool`
   - Default: `false`
   - Description: Whether LLM editor is enabled in the action space (only works with function calling)
 
-- `codeact_enable_jupyter`
+- `enable_jupyter`
   - Type: `bool`
   - Default: `false`
   - Description: Whether Jupyter is enabled in the action space

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

@@ -50,3 +50,6 @@ docker run -it \
 ```
 
 This command will start an interactive session in Docker where you can input tasks and receive responses from OpenHands.
+
+The `-e SANDBOX_USER_ID=$(id -u)` is passed to the Docker command to ensure the sandbox user matches the host user’s
+permissions. This prevents the agent from creating root-owned files in the mounted workspace.

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

@@ -47,6 +47,9 @@ docker run -it \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 
+The `-e SANDBOX_USER_ID=$(id -u)` is passed to the Docker command to ensure the sandbox user matches the host user’s
+permissions. This prevents the agent from creating root-owned files in the mounted workspace.
+
 ## Advanced Headless Configurations
 
 To view all available configuration options for headless mode, run the Python command with the `--help` flag.

docs/modules/usage/runtimes/docker.md

@@ -35,8 +35,8 @@ A useful feature is the ability to connect to your local filesystem. To mount yo
 Be careful! There's nothing stopping the OpenHands agent from deleting or modifying
 any files that are mounted into its workspace.
 
-This setup can cause some issues with file permissions (hence the `SANDBOX_USER_ID` variable)
-but seems to work well on most systems.
+The `-e SANDBOX_USER_ID=$(id -u)` is passed to the Docker command to ensure the sandbox user matches the host user’s
+permissions. This prevents the agent from creating root-owned files in the mounted workspace.
 
 ## Hardened Docker Installation
 

docs/modules/usage/troubleshooting/troubleshooting.md

@@ -20,3 +20,18 @@ Try these in order:
 * If using Docker Desktop, ensure `Settings > Advanced > Allow the default Docker socket to be used` is enabled.
 * Depending on your configuration you may need `Settings > Resources > Network > Enable host networking` enabled in Docker Desktop.
 * Reinstall Docker Desktop.
+
+### Permission Error
+
+**Description**
+
+On initial prompt, an error is seen with `Permission Denied` or `PermissionError`.
+
+**Resolution**
+
+* Check if the `~/.openhands-state` is owned by `root`. If so, you can:
+  * Change the directory's ownership: `sudo chown <user>:<user> ~/.openhands-state`.
+  * or update permissions on the directory: `sudo chmod 777 ~/.openhands-state`
+  * or delete it if you don’t need previous data. OpenHands will recreate it. You'll need to re-enter LLM settings.
+* If mounting a local directory, ensure your `WORKSPACE_BASE` has the necessary permissions for the user running
+  OpenHands.

evaluation/benchmarks/EDA/run_infer.py

@@ -14,6 +14,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -74,6 +75,7 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
     return config
 

evaluation/benchmarks/agent_bench/run_infer.py

@@ -22,6 +22,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -55,6 +56,8 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
     return config
 

evaluation/benchmarks/aider_bench/run_infer.py

@@ -21,6 +21,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -61,6 +62,8 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
 
     # copy 'draft_editor' config if exists

evaluation/benchmarks/biocoder/run_infer.py

@@ -19,6 +19,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -72,6 +73,8 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
     return config
 

evaluation/benchmarks/bird/run_infer.py

@@ -22,6 +22,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -86,6 +87,8 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
     return config
 

evaluation/benchmarks/browsing_delegation/run_infer.py

@@ -15,6 +15,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -50,6 +51,8 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
     return config
 

evaluation/benchmarks/commit0/run_infer.py

@@ -20,6 +20,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
     update_llm_config_for_completions_logging,
 )
 from openhands.controller.state.state import State
@@ -131,10 +132,11 @@ def get_config(
         )
     )
     agent_config = AgentConfig(
-        codeact_enable_jupyter=False,
-        codeact_enable_browsing=RUN_WITH_BROWSING,
-        codeact_enable_llm_editor=False,
+        enable_jupyter=False,
+        enable_browsing=RUN_WITH_BROWSING,
+        enable_llm_editor=False,
     )
+    agent_config = update_agent_config_for_eval(agent_config)
     config.set_agent_config(agent_config)
     return config
 

evaluation/benchmarks/discoverybench/run_infer.py

@@ -21,6 +21,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -76,11 +77,13 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
     agent_config = AgentConfig(
         function_calling=False,
-        codeact_enable_jupyter=True,
-        codeact_enable_browsing_delegate=True,
+        enable_jupyter=True,
+        enable_browsing=True,
     )
     config.set_agent_config(agent_config)
     return config

evaluation/benchmarks/gaia/run_infer.py

@@ -18,6 +18,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -66,6 +67,8 @@ def get_config(
     else:
         logger.info('Agent config not provided, using default settings')
         agent_config = config.get_agent_config(metadata.agent_class)
+
+        agent_config = update_agent_config_for_eval(agent_config)
         agent_config.enable_prompt_extensions = False
     return config
 

evaluation/benchmarks/gorilla/run_infer.py

@@ -16,6 +16,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -54,6 +55,8 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
     return config
 

evaluation/benchmarks/gpqa/run_infer.py

@@ -34,6 +34,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -75,6 +76,8 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
     return config
 

evaluation/benchmarks/humanevalfix/run_infer.py

@@ -27,6 +27,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -96,6 +97,8 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
     return config
 

evaluation/benchmarks/logic_reasoning/run_infer.py

@@ -14,6 +14,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -63,6 +64,8 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
     return config
 

evaluation/benchmarks/mint/run_infer.py

@@ -19,6 +19,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -121,6 +122,8 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
     return config
 

evaluation/benchmarks/ml_bench/run_infer.py

@@ -30,6 +30,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -91,6 +92,8 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
     return config
 

evaluation/benchmarks/swe_bench/run_infer.py

@@ -30,6 +30,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
     update_llm_config_for_completions_logging,
 )
 from openhands.controller.state.state import State
@@ -96,7 +97,7 @@ Phase 1. READING: read the problem and reword it in clearer terms
 Phase 2. RUNNING: install and run the tests on the repository
    2.1 Follow the readme
    2.2 Install the environment and anything needed
-   2.2 Iterate and figure out how to run the tests 
+   2.2 Iterate and figure out how to run the tests
 
 Phase 3. EXPLORATION: find the files that are related to the problem and possible solutions
    3.1 Use `grep` to search for relevant methods, classes, keywords and error messages.
@@ -225,12 +226,13 @@ def get_config(
         )
     )
     agent_config = AgentConfig(
-        codeact_enable_jupyter=False,
-        codeact_enable_browsing=RUN_WITH_BROWSING,
-        codeact_enable_llm_editor=False,
+        enable_jupyter=False,
+        enable_browsing=RUN_WITH_BROWSING,
+        enable_llm_editor=False,
         condenser=metadata.condenser_config,
         enable_prompt_extensions=False,
     )
+    agent_config = update_agent_config_for_eval(agent_config)
     config.set_agent_config(agent_config)
     return config
 
@@ -238,6 +240,7 @@ def get_config(
 def initialize_runtime(
     runtime: Runtime,
     instance: pd.Series,  # this argument is not required
+    metadata: EvalMetadata,
 ):
     """Initialize the runtime for the agent.
 
@@ -577,7 +580,7 @@ def process_instance(
     call_async_from_sync(runtime.connect)
 
     try:
-        initialize_runtime(runtime, instance)
+        initialize_runtime(runtime, instance, metadata)
 
         message_action = get_instruction(instance, metadata)
 

evaluation/benchmarks/testgeneval/run_infer.py

@@ -30,6 +30,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
     update_llm_config_for_completions_logging,
 )
 from openhands.controller.state.state import State
@@ -158,12 +159,13 @@ def get_config(
         )
     )
     agent_config = AgentConfig(
-        codeact_enable_jupyter=False,
-        codeact_enable_browsing=RUN_WITH_BROWSING,
-        codeact_enable_llm_editor=False,
+        enable_jupyter=False,
+        enable_browsing=RUN_WITH_BROWSING,
+        enable_llm_editor=False,
         condenser=metadata.condenser_config,
         enable_prompt_extensions=False,
     )
+    agent_config = update_agent_config_for_eval(agent_config)
     config.set_agent_config(agent_config)
     return config
 

evaluation/benchmarks/the_agent_company/run_infer.py

@@ -13,7 +13,10 @@ from typing import List
 import yaml
 from browsing import pre_login
 
-from evaluation.utils.shared import get_default_sandbox_config_for_eval
+from evaluation.utils.shared import (
+    get_default_sandbox_config_for_eval,
+    update_agent_config_for_eval,
+)
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
@@ -58,12 +61,14 @@ def get_config(
     )
     config.set_llm_config(llm_config)
     if agent_config:
+        agent_config = update_agent_config_for_eval(agent_config)
         config.set_agent_config(agent_config)
     else:
         logger.info('Agent config not provided, using default settings')
         agent_config = AgentConfig(
             enable_prompt_extensions=False,
         )
+        agent_config = update_agent_config_for_eval(agent_config)
         config.set_agent_config(agent_config)
     return config
 

evaluation/benchmarks/toolqa/run_infer.py

@@ -15,6 +15,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -55,6 +56,8 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
     return config
 

evaluation/benchmarks/webarena/run_infer.py

@@ -16,6 +16,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_agent_config_for_eval,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -76,6 +77,8 @@ def get_config(
     )
     config.set_llm_config(metadata.llm_config)
     agent_config = config.get_agent_config(metadata.agent_class)
+
+    agent_config = update_agent_config_for_eval(agent_config)
     agent_config.enable_prompt_extensions = False
     return config
 

evaluation/integration_tests/run_infer.py

@@ -62,9 +62,9 @@ def get_config(
         )
     )
     agent_config = AgentConfig(
-        codeact_enable_jupyter=True,
-        codeact_enable_browsing=True,
-        codeact_enable_llm_editor=False,
+        enable_jupyter=True,
+        enable_browsing=True,
+        enable_llm_editor=False,
     )
     config.set_agent_config(agent_config)
     return config

evaluation/utils/shared.py

@@ -160,6 +160,26 @@ def cleanup():
         process.join()
 
 
+def update_agent_config_for_eval(
+    agent_config: AgentConfig | None = None,
+) -> AgentConfig:
+    """Update agent config with evaluation-specific settings.
+
+    Args:
+        agent_config: The agent config to update. If None, a new AgentConfig will be created.
+
+    Returns:
+        The updated agent config.
+    """
+    if agent_config is None:
+        agent_config = AgentConfig()
+
+    # Note: We're not disabling repository memory here as requested
+    # This function can be used for other evaluation-specific settings
+
+    return agent_config
+
+
 def make_metadata(
     llm_config: LLMConfig,
     dataset_name: str,
@@ -172,6 +192,8 @@ def make_metadata(
     agent_config: AgentConfig | None = None,
     condenser_config: CondenserConfig | None = None,
 ) -> EvalMetadata:
+    # Update agent config with evaluation-specific settings
+    agent_config = update_agent_config_for_eval(agent_config)
     model_name = llm_config.model.split('/')[-1]
     model_path = model_name.replace(':', '_').replace('@', '-')
     eval_note = f'_N_{eval_note}' if eval_note else ''

frontend/__tests__/components/browser.test.tsx

@@ -1,9 +1,5 @@
 import { describe, it, expect, afterEach, vi } from "vitest";
 
-import { screen } from "@testing-library/react";
-import { renderWithProviders } from "../../test-utils";
-import { BrowserPanel } from "#/components/features/browser/browser";
-
 // Mock useParams before importing components
 vi.mock("react-router", async () => {
   const actual = await vi.importActual("react-router");
@@ -27,6 +23,10 @@ vi.mock("react-i18next", async () => {
   };
 });
 
+import { screen } from "@testing-library/react";
+import { renderWithProviders } from "../../test-utils";
+import { BrowserPanel } from "#/components/features/browser/browser";
+
 describe("Browser", () => {
   afterEach(() => {
     vi.clearAllMocks();

frontend/__tests__/components/buttons/copy-to-clipboard.test.tsx

@@ -17,7 +17,7 @@ describe("CopyToClipboardButton", () => {
         isDisabled={false}
         onClick={() => {}}
         mode="copy"
-      />,
+      />
     );
 
     const button = screen.getByTestId("copy-to-clipboard");
@@ -31,7 +31,7 @@ describe("CopyToClipboardButton", () => {
         isDisabled={false}
         onClick={() => {}}
         mode="copied"
-      />,
+      />
     );
 
     const button = screen.getByTestId("copy-to-clipboard");

frontend/__tests__/components/chat/action-suggestions.test.tsx

@@ -1,8 +1,8 @@
 import { describe, expect, it, vi, beforeEach } from "vitest";
 import { render, screen } from "@testing-library/react";
-import { useSelector } from "react-redux";
 import { ActionSuggestions } from "#/components/features/chat/action-suggestions";
 import { useAuth } from "#/context/auth-context";
+import { useSelector } from "react-redux";
 
 // Mock dependencies
 vi.mock("posthog-js", () => ({
@@ -24,9 +24,9 @@ vi.mock("react-i18next", () => ({
   useTranslation: () => ({
     t: (key: string) => {
       const translations: Record<string, string> = {
-        ACTION$PUSH_TO_BRANCH: "Push to Branch",
-        ACTION$PUSH_CREATE_PR: "Push & Create PR",
-        ACTION$PUSH_CHANGES_TO_PR: "Push Changes to PR",
+        "ACTION$PUSH_TO_BRANCH": "Push to Branch",
+        "ACTION$PUSH_CREATE_PR": "Push & Create PR",
+        "ACTION$PUSH_CHANGES_TO_PR": "Push Changes to PR"
       };
       return translations[key] || key;
     },

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

@@ -217,6 +217,17 @@ describe("ChatInput", () => {
     expect(onImagePaste).toHaveBeenCalledWith([file]);
   });
 
+  it("should use the default maxRows value", () => {
+    // We can't directly test the maxRows prop as it's not exposed in the DOM
+    // Instead, we'll verify the component renders with the default props
+    render(<ChatInput onSubmit={onSubmitMock} />);
+    const textarea = screen.getByRole("textbox");
+    expect(textarea).toBeInTheDocument();
+    
+    // The actual verification of maxRows=16 is handled internally by the TextareaAutosize component
+    // and affects how many rows the textarea can expand to
+  });
+
   it("should not submit when Enter is pressed during IME composition", async () => {
     const user = userEvent.setup();
     render(<ChatInput onSubmit={onSubmitMock} />);

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

@@ -1,8 +1,8 @@
 import { afterEach, beforeAll, describe, expect, it, vi } from "vitest";
+import type { Message } from "#/message";
 import { act, screen, waitFor, within } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { renderWithProviders } from "test-utils";
-import type { Message } from "#/message";
 import { addUserMessage } from "#/state/chat-slice";
 import { SUGGESTIONS } from "#/utils/suggestions";
 import * as ChatSlice from "#/state/chat-slice";

frontend/__tests__/components/features/auth-modal.test.tsx

@@ -24,9 +24,7 @@ describe("AuthModal", () => {
     const user = userEvent.setup();
     render(<AuthModal githubAuthUrl={null} />);
     const checkbox = screen.getByRole("checkbox");
-    const button = screen.getByRole("button", {
-      name: "GITHUB$CONNECT_TO_GITHUB",
-    });
+    const button = screen.getByRole("button", { name: "GITHUB$CONNECT_TO_GITHUB" });
 
     expect(button).toBeDisabled();
 
@@ -47,9 +45,7 @@ describe("AuthModal", () => {
     const checkbox = screen.getByRole("checkbox");
     await user.click(checkbox);
 
-    const button = screen.getByRole("button", {
-      name: "GITHUB$CONNECT_TO_GITHUB",
-    });
+    const button = screen.getByRole("button", { name: "GITHUB$CONNECT_TO_GITHUB" });
     await user.click(button);
 
     expect(handleCaptureConsentSpy).toHaveBeenCalledWith(true);

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

@@ -16,6 +16,8 @@ import { ConversationCard } from "#/components/features/conversation-panel/conve
 import { clickOnEditButton } from "./utils";
 
 // We'll use the actual i18next implementation but override the translation function
+import { I18nextProvider } from "react-i18next";
+import i18n from "i18next";
 
 // Mock the t function to return our custom translations
 vi.mock("react-i18next", async () => {
@@ -25,9 +27,9 @@ vi.mock("react-i18next", async () => {
     useTranslation: () => ({
       t: (key: string) => {
         const translations: Record<string, string> = {
-          CONVERSATION$CREATED: "Created",
-          CONVERSATION$AGO: "ago",
-          CONVERSATION$UPDATED: "Updated",
+          "CONVERSATION$CREATED": "Created",
+          "CONVERSATION$AGO": "ago",
+          "CONVERSATION$UPDATED": "Updated"
         };
         return translations[key] || key;
       },
@@ -80,9 +82,7 @@ describe("ConversationCard", () => {
     expect(card).toHaveTextContent("ago");
 
     // Use a regex to match the time part since it might have whitespace
-    const timeRegex = new RegExp(
-      formatTimeDelta(new Date("2021-10-01T12:00:00Z")),
-    );
+    const timeRegex = new RegExp(formatTimeDelta(new Date("2021-10-01T12:00:00Z")));
     expect(card).toHaveTextContent(timeRegex);
   });
 

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

@@ -1,13 +1,19 @@
 import { screen, waitFor, within } from "@testing-library/react";
 import { beforeAll, beforeEach, describe, expect, it, vi } from "vitest";
-import { QueryClientConfig } from "@tanstack/react-query";
+import {
+  QueryClientProvider,
+  QueryClient,
+  QueryClientConfig,
+} from "@tanstack/react-query";
 import userEvent from "@testing-library/user-event";
 import { createRoutesStub } from "react-router";
 import React from "react";
-import { renderWithProviders } from "test-utils";
 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";
+import { queryClientConfig } from "#/query-client-config";
+import { renderWithProviders } from "test-utils";
 
 describe("ConversationPanel", () => {
   const onCloseMock = vi.fn();
@@ -23,9 +29,9 @@ describe("ConversationPanel", () => {
       preloadedState: {
         metrics: {
           cost: null,
-          usage: null,
-        },
-      },
+          usage: null
+        }
+      }
     });
 
   const { endSessionMock } = vi.hoisted(() => ({
@@ -78,9 +84,7 @@ describe("ConversationPanel", () => {
     vi.clearAllMocks();
     vi.restoreAllMocks();
     // Setup default mock for getUserConversations
-    vi.spyOn(OpenHands, "getUserConversations").mockResolvedValue([
-      ...mockConversations,
-    ]);
+    vi.spyOn(OpenHands, "getUserConversations").mockResolvedValue([...mockConversations]);
   });
 
   it("should render the conversations", async () => {
@@ -134,9 +138,7 @@ describe("ConversationPanel", () => {
     const cancelButton = screen.getByRole("button", { name: /cancel/i });
     await user.click(cancelButton);
 
-    expect(
-      screen.queryByRole("button", { name: /cancel/i }),
-    ).not.toBeInTheDocument();
+    expect(screen.queryByRole("button", { name: /cancel/i })).not.toBeInTheDocument();
 
     // Ensure the conversation is not deleted
     cards = await screen.findAllByTestId("conversation-card");
@@ -149,22 +151,19 @@ describe("ConversationPanel", () => {
     const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
     getUserConversationsSpy.mockImplementation(async () => mockData);
 
-    const deleteUserConversationSpy = vi.spyOn(
-      OpenHands,
-      "deleteUserConversation",
-    );
+    const deleteUserConversationSpy = vi.spyOn(OpenHands, "deleteUserConversation");
     deleteUserConversationSpy.mockImplementation(async (id: string) => {
-      const index = mockData.findIndex((conv) => conv.conversation_id === id);
+      const index = mockData.findIndex(conv => conv.conversation_id === id);
       if (index !== -1) {
         mockData.splice(index, 1);
       }
       // Wait for React Query to update its cache
-      await new Promise((resolve) => setTimeout(resolve, 0));
+      await new Promise(resolve => setTimeout(resolve, 0));
     });
 
     renderConversationPanel();
 
-    const cards = await screen.findAllByTestId("conversation-card");
+    let cards = await screen.findAllByTestId("conversation-card");
     const ellipsisButton = within(cards[1]).getByTestId("ellipsis-button");
     await user.click(ellipsisButton);
     const deleteButton = screen.getByTestId("delete-button");
@@ -176,18 +175,13 @@ describe("ConversationPanel", () => {
     const confirmButton = screen.getByRole("button", { name: /confirm/i });
     await user.click(confirmButton);
 
-    expect(
-      screen.queryByRole("button", { name: /confirm/i }),
-    ).not.toBeInTheDocument();
+    expect(screen.queryByRole("button", { name: /confirm/i })).not.toBeInTheDocument();
 
     // Wait for the cards to update with a longer timeout
-    await waitFor(
-      () => {
-        const updatedCards = screen.getAllByTestId("conversation-card");
-        expect(updatedCards).toHaveLength(2);
-      },
-      { timeout: 2000 },
-    );
+    await waitFor(() => {
+      const updatedCards = screen.getAllByTestId("conversation-card");
+      expect(updatedCards).toHaveLength(2);
+    }, { timeout: 2000 });
 
     expect(endSessionMock).toHaveBeenCalledOnce();
   });
@@ -224,12 +218,9 @@ describe("ConversationPanel", () => {
     const getUserConversationsSpy = vi.spyOn(OpenHands, "getUserConversations");
     getUserConversationsSpy.mockImplementation(async () => mockData);
 
-    const deleteUserConversationSpy = vi.spyOn(
-      OpenHands,
-      "deleteUserConversation",
-    );
+    const deleteUserConversationSpy = vi.spyOn(OpenHands, "deleteUserConversation");
     deleteUserConversationSpy.mockImplementation(async (id: string) => {
-      const index = mockData.findIndex((conv) => conv.conversation_id === id);
+      const index = mockData.findIndex(conv => conv.conversation_id === id);
       if (index !== -1) {
         mockData.splice(index, 1);
       }
@@ -237,7 +228,7 @@ describe("ConversationPanel", () => {
 
     renderConversationPanel();
 
-    const cards = await screen.findAllByTestId("conversation-card");
+    let cards = await screen.findAllByTestId("conversation-card");
     expect(cards).toHaveLength(3);
 
     const ellipsisButton = within(cards[0]).getByTestId("ellipsis-button");
@@ -251,9 +242,7 @@ describe("ConversationPanel", () => {
     const confirmButton = screen.getByRole("button", { name: /confirm/i });
     await user.click(confirmButton);
 
-    expect(
-      screen.queryByRole("button", { name: /confirm/i }),
-    ).not.toBeInTheDocument();
+    expect(screen.queryByRole("button", { name: /confirm/i })).not.toBeInTheDocument();
 
     // Wait for the cards to update
     await waitFor(() => {
@@ -359,9 +348,9 @@ describe("ConversationPanel", () => {
       preloadedState: {
         metrics: {
           cost: null,
-          usage: null,
-        },
-      },
+          usage: null
+        }
+      }
     });
 
     const toggleButton = screen.getByText("Toggle");

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

@@ -1,11 +1,5 @@
 import { afterEach, describe, expect, it, vi } from "vitest";
 
-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";
-
 // Mock useParams before importing components
 vi.mock("react-router", async () => {
   const actual = await vi.importActual("react-router");
@@ -15,6 +9,12 @@ vi.mock("react-router", async () => {
   };
 });
 
+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();
   const onCloseMock = vi.fn();

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

@@ -1,8 +1,8 @@
-import { screen } from "@testing-library/react";
+import { render, screen } from "@testing-library/react";
 import { describe, it, expect } from "vitest";
-import { renderWithProviders } from "test-utils";
 import { Messages } from "#/components/features/chat/messages";
 import type { Message } from "#/message";
+import { renderWithProviders } from "test-utils";
 
 describe("File Operations Messages", () => {
   it("should show success indicator for successful file read operation", () => {
@@ -17,9 +17,7 @@ describe("File Operations Messages", () => {
       },
     ];
 
-    renderWithProviders(
-      <Messages messages={messages} isAwaitingUserConfirmation={false} />,
-    );
+    renderWithProviders(<Messages messages={messages} isAwaitingUserConfirmation={false} />);
 
     const statusIcon = screen.getByTestId("status-icon");
     expect(statusIcon).toBeInTheDocument();
@@ -38,9 +36,7 @@ describe("File Operations Messages", () => {
       },
     ];
 
-    renderWithProviders(
-      <Messages messages={messages} isAwaitingUserConfirmation={false} />,
-    );
+    renderWithProviders(<Messages messages={messages} isAwaitingUserConfirmation={false} />);
 
     const statusIcon = screen.getByTestId("status-icon");
     expect(statusIcon).toBeInTheDocument();
@@ -59,9 +55,7 @@ describe("File Operations Messages", () => {
       },
     ];
 
-    renderWithProviders(
-      <Messages messages={messages} isAwaitingUserConfirmation={false} />,
-    );
+    renderWithProviders(<Messages messages={messages} isAwaitingUserConfirmation={false} />);
 
     const statusIcon = screen.getByTestId("status-icon");
     expect(statusIcon).toBeInTheDocument();
@@ -80,9 +74,7 @@ describe("File Operations Messages", () => {
       },
     ];
 
-    renderWithProviders(
-      <Messages messages={messages} isAwaitingUserConfirmation={false} />,
-    );
+    renderWithProviders(<Messages messages={messages} isAwaitingUserConfirmation={false} />);
 
     const statusIcon = screen.getByTestId("status-icon");
     expect(statusIcon).toBeInTheDocument();

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

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

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

@@ -1,4 +1,4 @@
-import { render, screen, within } from "@testing-library/react";
+import { render, screen, within, fireEvent } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, beforeAll, describe, expect, it, vi } from "vitest";
 import { InteractiveChatBox } from "#/components/features/chat/interactive-chat-box";
@@ -144,7 +144,7 @@ describe("InteractiveChatBox", () => {
         onStop={onStop}
         onChange={onChange}
         value="test message"
-      />,
+      />
     );
 
     // Upload an image via the upload button - this should NOT clear the text input
@@ -173,7 +173,7 @@ describe("InteractiveChatBox", () => {
         onStop={onStop}
         onChange={onChange}
         value=""
-      />,
+      />
     );
 
     // Verify the text input was cleared

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

@@ -1,9 +1,9 @@
 import { render, screen } from "@testing-library/react";
 import { Provider } from "react-redux";
 import { configureStore } from "@reduxjs/toolkit";
-import { describe, it, expect } from "vitest";
 import { JupyterEditor } from "#/components/features/jupyter/jupyter";
 import { jupyterReducer } from "#/state/jupyter-slice";
+import { vi, describe, it, expect } from "vitest";
 
 describe("JupyterEditor", () => {
   const mockStore = configureStore({
@@ -36,7 +36,7 @@ describe("JupyterEditor", () => {
         <div style={{ height: "100vh" }}>
           <JupyterEditor maxWidth={800} />
         </div>
-      </Provider>,
+      </Provider>
     );
 
     const container = screen.getByTestId("jupyter-container");

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

@@ -5,13 +5,7 @@ import translations from "../../src/i18n/translation.json";
 import { UserAvatar } from "../../src/components/features/sidebar/user-avatar";
 
 vi.mock("@heroui/react", () => ({
-  Tooltip: ({
-    content,
-    children,
-  }: {
-    content: string;
-    children: React.ReactNode;
-  }) => (
+  Tooltip: ({ content, children }: { content: string; children: React.ReactNode }) => (
     <div>
       {children}
       <div>{content}</div>
@@ -19,33 +13,15 @@ vi.mock("@heroui/react", () => ({
   ),
 }));
 
-const supportedLanguages = [
-  "en",
-  "ja",
-  "zh-CN",
-  "zh-TW",
-  "ko-KR",
-  "de",
-  "no",
-  "it",
-  "pt",
-  "es",
-  "ar",
-  "fr",
-  "tr",
-];
+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];
+  const translationEntry = (translations as Record<string, Record<string, string>>)[key];
   if (!translationEntry) {
-    throw new Error(
-      `Translation key "${key}" does not exist in translation.json`,
-    );
+    throw new Error(`Translation key "${key}" does not exist in translation.json`);
   }
 
   for (const lang of supportedLanguages) {
@@ -77,9 +53,7 @@ function findDuplicateKeys(obj: Record<string, any>) {
 vi.mock("react-i18next", () => ({
   useTranslation: () => ({
     t: (key: string) => {
-      const translationEntry = (
-        translations as Record<string, Record<string, string>>
-      )[key];
+      const translationEntry = (translations as Record<string, Record<string, string>>)[key];
       return translationEntry?.ja || key;
     },
   }),
@@ -88,7 +62,7 @@ vi.mock("react-i18next", () => ({
 describe("Landing page translations", () => {
   test("should render Japanese translations correctly", () => {
     // Mock a simple component that uses the translations
-    function TestComponent() {
+    const TestComponent = () => {
       const { t } = useTranslation();
       return (
         <div>
@@ -121,16 +95,14 @@ describe("Landing page translations", () => {
           </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("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();
@@ -148,12 +120,8 @@ describe("Landing page translations", () => {
     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",
-    );
+    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");
@@ -191,12 +159,12 @@ describe("Landing page translations", () => {
       "STATUS$CONNECTED_TO_SERVER",
       "TIME$MINUTES_AGO",
       "TIME$HOURS_AGO",
-      "TIME$DAYS_AGO",
+      "TIME$DAYS_AGO"
     ];
 
     // Check all keys and collect missing translations
     const missingTranslationsMap = new Map<string, string[]>();
-    translationKeys.forEach((key) => {
+    translationKeys.forEach(key => {
       const missing = checkTranslationExists(key);
       if (missing.length > 0) {
         missingTranslationsMap.set(key, missing);
@@ -206,11 +174,8 @@ describe("Landing page translations", () => {
     // 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: ${langs.join(", ")}`,
-        )
-        .join("");
+        .map(([key, langs]) => `\n- "${key}" is missing translations for: ${langs.join(', ')}`)
+        .join('');
       throw new Error(`Missing translations:${errorMessage}`);
     }
   });
@@ -219,9 +184,7 @@ describe("Landing page translations", () => {
     const duplicates = findDuplicateKeys(translations);
 
     if (duplicates.length > 0) {
-      throw new Error(
-        `Found duplicate translation keys: ${duplicates.join(", ")}`,
-      );
+      throw new Error(`Found duplicate translation keys: ${duplicates.join(', ')}`);
     }
   });
 });

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

@@ -1,15 +1,12 @@
-import { describe, expect, it } from "vitest";
-import fs from "fs";
-import path from "path";
+import { describe, expect, it } from 'vitest';
+import fs from 'fs';
+import path from 'path';
 
-describe("translation.json", () => {
-  it("should not have duplicate translation keys", () => {
+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");
+    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;
@@ -33,7 +30,7 @@ describe("translation.json", () => {
     if (uniqueDuplicates.length > 0) {
       const errorMessage = `Found duplicate translation keys:\n${uniqueDuplicates
         .map((key) => `  - "${key}" appears ${keyOccurrences.get(key)} times`)
-        .join("\n")}`;
+        .join('\n')}`;
       throw new Error(errorMessage);
     }
 
@@ -41,13 +38,10 @@ describe("translation.json", () => {
     expect(uniqueDuplicates).toHaveLength(0);
   });
 
-  it("should have consistent translations for each key", () => {
+  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 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
@@ -56,7 +50,7 @@ describe("translation.json", () => {
 
     // Check each key's English translation
     Object.entries(translations).forEach(([key, value]: [string, any]) => {
-      if (typeof value === "object" && value.en !== undefined) {
+      if (typeof value === 'object' && value.en !== undefined) {
         const currentEn = value.en.toLowerCase();
         const existingEn = englishTranslations.get(key)?.toLowerCase();
 
@@ -71,10 +65,8 @@ describe("translation.json", () => {
     // 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")}`;
+        .map((key) => `  - "${key}" has multiple different English translations`)
+        .join('\n')}`;
       throw new Error(errorMessage);
     }
 

frontend/__tests__/routes/settings.test.tsx

@@ -65,9 +65,7 @@ describe("Settings Screen", () => {
 
     await waitFor(() => {
       // Use queryAllByText to handle multiple elements with the same text
-      expect(screen.queryAllByText("SETTINGS$LLM_SETTINGS")).not.toHaveLength(
-        0,
-      );
+      expect(screen.queryAllByText("SETTINGS$LLM_SETTINGS")).not.toHaveLength(0);
       screen.getByText("ACCOUNT_SETTINGS$ADDITIONAL_SETTINGS");
       screen.getByText("BUTTON$RESET_TO_DEFAULTS");
       screen.getByText("BUTTON$SAVE");

frontend/__tests__/services/actions.test.ts

@@ -32,11 +32,9 @@ describe("Actions Service", () => {
 
       handleStatusMessage(message);
 
-      expect(store.dispatch).toHaveBeenCalledWith(
-        expect.objectContaining({
-          payload: message,
-        }),
-      );
+      expect(store.dispatch).toHaveBeenCalledWith(expect.objectContaining({
+        payload: message,
+      }));
     });
 
     it("should log error messages and display them in chat", () => {
@@ -55,11 +53,9 @@ describe("Actions Service", () => {
         metadata: { msgId: "runtime.connection.failed" },
       });
 
-      expect(store.dispatch).toHaveBeenCalledWith(
-        expect.objectContaining({
-          payload: message,
-        }),
-      );
+      expect(store.dispatch).toHaveBeenCalledWith(expect.objectContaining({
+        payload: message,
+      }));
     });
   });
 
@@ -76,27 +72,21 @@ describe("Actions Service", () => {
           final_thought: "",
           task_completed: "partial",
           outputs: "",
-          thought: "",
-        },
+          thought: ""
+        }
       };
 
       // Mock implementation to capture the message
       let capturedPartialMessage = "";
       (store.dispatch as any).mockImplementation((action: any) => {
-        if (
-          action.type === "chat/addAssistantMessage" &&
-          action.payload.includes(
-            "believe that the task was **completed partially**",
-          )
-        ) {
+        if (action.type === "chat/addAssistantMessage" &&
+            action.payload.includes("believe that the task was **completed partially**")) {
           capturedPartialMessage = action.payload;
         }
       });
 
       handleActionMessage(messagePartial);
-      expect(capturedPartialMessage).toContain(
-        "I believe that the task was **completed partially**",
-      );
+      expect(capturedPartialMessage).toContain("I believe that the task was **completed partially**");
 
       // Test not completed
       const messageNotCompleted: ActionMessage = {
@@ -109,25 +99,21 @@ describe("Actions Service", () => {
           final_thought: "",
           task_completed: "false",
           outputs: "",
-          thought: "",
-        },
+          thought: ""
+        }
       };
 
       // Mock implementation to capture the message
       let capturedNotCompletedMessage = "";
       (store.dispatch as any).mockImplementation((action: any) => {
-        if (
-          action.type === "chat/addAssistantMessage" &&
-          action.payload.includes("believe that the task was **not completed**")
-        ) {
+        if (action.type === "chat/addAssistantMessage" &&
+            action.payload.includes("believe that the task was **not completed**")) {
           capturedNotCompletedMessage = action.payload;
         }
       });
 
       handleActionMessage(messageNotCompleted);
-      expect(capturedNotCompletedMessage).toContain(
-        "I believe that the task was **not completed**",
-      );
+      expect(capturedNotCompletedMessage).toContain("I believe that the task was **not completed**");
 
       // Test completed successfully
       const messageCompleted: ActionMessage = {
@@ -140,27 +126,21 @@ describe("Actions Service", () => {
           final_thought: "",
           task_completed: "true",
           outputs: "",
-          thought: "",
-        },
+          thought: ""
+        }
       };
 
       // Mock implementation to capture the message
       let capturedCompletedMessage = "";
       (store.dispatch as any).mockImplementation((action: any) => {
-        if (
-          action.type === "chat/addAssistantMessage" &&
-          action.payload.includes(
-            "believe that the task was **completed successfully**",
-          )
-        ) {
+        if (action.type === "chat/addAssistantMessage" &&
+            action.payload.includes("believe that the task was **completed successfully**")) {
           capturedCompletedMessage = action.payload;
         }
       });
 
       handleActionMessage(messageCompleted);
-      expect(capturedCompletedMessage).toContain(
-        "I believe that the task was **completed successfully**",
-      );
+      expect(capturedCompletedMessage).toContain("I believe that the task was **completed successfully**");
     });
   });
 });

frontend/__tests__/services/observations.test.ts

@@ -0,0 +1,51 @@
+import { beforeEach, describe, expect, it, vi } from "vitest";
+import { handleObservationMessage } from "#/services/observations";
+import store from "#/store";
+import { ObservationMessage } from "#/types/message";
+
+// Mock dependencies
+vi.mock("#/store", () => ({
+  default: {
+    dispatch: vi.fn(),
+  },
+}));
+
+describe("Observations Service", () => {
+  beforeEach(() => {
+    vi.clearAllMocks();
+  });
+
+  describe("handleObservationMessage", () => {
+    const createErrorMessage = (): ObservationMessage => ({
+      id: 14,
+      timestamp: "2025-04-14T13:37:54.451843",
+      message: "The action has not been executed.",
+      cause: 12,
+      observation: "error",
+      content: "The action has not been executed.",
+      extras: {
+        error_id: "",
+        metadata: {},
+      },
+    });
+
+    it("should dispatch error messages exactly once", () => {
+      const errorMessage = createErrorMessage();
+
+      handleObservationMessage(errorMessage);
+
+      expect(store.dispatch).toHaveBeenCalledTimes(1);
+      expect(store.dispatch).toHaveBeenCalledWith({
+        type: "chat/addAssistantObservation",
+        payload: expect.objectContaining({
+          observation: "error",
+          content: "The action has not been executed.",
+          source: "user",
+          extras: {
+            error_id: "",
+          },
+        }),
+      });
+    });
+  });
+});

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

@@ -5,16 +5,15 @@ 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",
+      "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;
   },
@@ -24,5 +23,7 @@ const mockI18n = {
 };
 
 export function I18nTestProvider({ children }: { children: ReactNode }) {
-  return <I18nextProvider i18n={mockI18n as any}>{children}</I18nextProvider>;
+  return (
+    <I18nextProvider i18n={mockI18n as any}>{children}</I18nextProvider>
+  );
 }

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

@@ -29,7 +29,7 @@ export function ChatInput({
   disabled,
   showButton = true,
   value,
-  maxRows = 4,
+  maxRows = 16,
   onSubmit,
   onStop,
   onChange,

frontend/src/components/layout/nav-tab.tsx

@@ -1,7 +1,6 @@
 import { NavLink } from "react-router";
 import { cn } from "#/utils/utils";
 import { BetaBadge } from "./beta-badge";
-import { CopyToClipboardButton } from "#/components/shared/buttons/copy-to-clipboard-button";
 
 interface NavTabProps {
   to: string;

frontend/src/services/actions.ts

@@ -104,7 +104,12 @@ export function handleActionMessage(message: ActionMessage) {
   }
 
   if (message.source === "agent") {
-    if (message.args && message.args.thought) {
+    // Only add thought as a message if it's not a "think" action
+    if (
+      message.args &&
+      message.args.thought &&
+      message.action !== ActionType.THINK
+    ) {
       store.dispatch(addAssistantMessage(message.args.thought));
     }
     // Need to convert ActionMessage to RejectAction

frontend/src/services/observations.ts

@@ -52,6 +52,7 @@ export function handleObservationMessage(message: ObservationMessage) {
     case ObservationType.THINK:
     case ObservationType.NULL:
     case ObservationType.RECALL:
+    case ObservationType.ERROR:
       break; // We don't display the default message for these observations
     default:
       store.dispatch(addAssistantMessage(message.message));

frontend/src/state/chat-slice.ts

@@ -24,6 +24,7 @@ const HANDLED_ACTIONS: OpenHandsEventType[] = [
   "browse_interactive",
   "edit",
   "recall",
+  "think",
 ];
 
 function getRiskText(risk: ActionSecurityRisk) {

frontend/src/types/observation-type.tsx

@@ -32,6 +32,9 @@ enum ObservationType {
   // An observation that shows agent's context extension
   RECALL = "recall",
 
+  // An error observation
+  ERROR = "error",
+
   // A no-op observation
   NULL = "null",
 }

frontend/src/utils/download-trajectory.ts

@@ -1,3 +1,5 @@
+import { downloadJSON } from "./download-json";
+
 function isSaveFilePickerSupported(): boolean {
   return typeof window !== "undefined" && "showSaveFilePicker" in window;
 }
@@ -6,25 +8,37 @@ export async function downloadTrajectory(
   conversationId: string,
   data: unknown[] | null,
 ): Promise<void> {
-  if (!isSaveFilePickerSupported()) {
-    throw new Error(
-      "Your browser doesn't support downloading files. Please use Chrome, Edge, or another browser that supports the File System Access API.",
-    );
-  }
-  const options: SaveFilePickerOptions = {
-    suggestedName: `trajectory-${conversationId}.json`,
-    types: [
-      {
-        description: "JSON File", // This is a file type description, not user-facing text
-        accept: {
-          "application/json": [".json"],
-        },
-      },
-    ],
-  };
+  // Ensure data is an object for downloadJSON
+  const jsonData = data || {};
 
-  const fileHandle = await window.showSaveFilePicker(options);
-  const writable = await fileHandle.createWritable();
-  await writable.write(JSON.stringify(data, null, 2));
-  await writable.close();
+  if (!isSaveFilePickerSupported()) {
+    // Fallback for browsers that don't support File System Access API (Safari, Firefox)
+    // This method dumps the JSON data right into the download folder
+    downloadJSON(jsonData as object, `trajectory-${conversationId}.json`);
+    return;
+  }
+
+  try {
+    const options: SaveFilePickerOptions = {
+      suggestedName: `trajectory-${conversationId}.json`,
+      types: [
+        {
+          description: "JSON File", // This is a file type description, not user-facing text
+          accept: {
+            "application/json": [".json"],
+          },
+        },
+      ],
+    };
+
+    const fileHandle = await window.showSaveFilePicker(options);
+    const writable = await fileHandle.createWritable();
+    await writable.write(JSON.stringify(data, null, 2));
+    await writable.close();
+  } catch (error) {
+    // If an error occurs, fall back to the downloadJSON method
+    if (error instanceof Error && error.name !== "AbortError") {
+      downloadJSON(jsonData as object, `trajectory-${conversationId}.json`);
+    }
+  }
 }

frontend/vite.config.ts

@@ -52,7 +52,7 @@ export default defineConfig(({ mode }) => {
         },
       },
       watch: {
-        ignored: ["**/node_modules/**", "**/.git/**"],
+        ignored: ['**/node_modules/**', '**/.git/**'],
       },
     },
     ssr: {

microagents/knowledge/gitlab.md

@@ -30,6 +30,6 @@ Here are some instructions for pushing, but ONLY do this if the user asks you to
 git remote -v && git branch # to find the current org, repo and branch
 git checkout -b create-widget && git add . && git commit -m "Create widget" && git push -u origin create-widget
 curl -X POST "https://gitlab.com/api/v4/projects/$PROJECT_ID/merge_requests" \
-    -H "PRIVATE-TOKEN: $GITLAB_TOKEN" \
+    -H "Authorization: Bearer $GITLAB_TOKEN" \
     -d '{"source_branch": "create-widget", "target_branch": "openhands-workspace", "title": "Create widget"}'
 ```

openhands/agenthub/codeact_agent/README.md

@@ -53,9 +53,9 @@ The agent provides several built-in tools:
 ## Configuration
 
 Tools can be enabled/disabled through configuration parameters:
-- `codeact_enable_browsing`: Enable browser interaction tools
-- `codeact_enable_jupyter`: Enable IPython code execution
-- `codeact_enable_llm_editor`: Enable LLM-based file editing (falls back to string replacement editor if disabled)
+- `enable_browsing`: Enable browser interaction tools
+- `enable_jupyter`: Enable IPython code execution
+- `enable_llm_editor`: Enable LLM-based file editing (falls back to string replacement editor if disabled)
 
 ## Micro-agents
 

openhands/agenthub/codeact_agent/codeact_agent.py

@@ -69,9 +69,9 @@ class CodeActAgent(Agent):
         self.reset()
 
         built_in_tools = codeact_function_calling.get_tools(
-            codeact_enable_browsing=self.config.codeact_enable_browsing,
-            codeact_enable_jupyter=self.config.codeact_enable_jupyter,
-            codeact_enable_llm_editor=self.config.codeact_enable_llm_editor,
+            enable_browsing=self.config.enable_browsing,
+            enable_jupyter=self.config.enable_jupyter,
+            enable_llm_editor=self.config.enable_llm_editor,
             llm=self.llm,
         )
 

openhands/agenthub/codeact_agent/function_calling.py

@@ -240,9 +240,9 @@ def response_to_actions(response: ModelResponse) -> list[Action]:
 
 
 def get_tools(
-    codeact_enable_browsing: bool = False,
-    codeact_enable_llm_editor: bool = False,
-    codeact_enable_jupyter: bool = False,
+    enable_browsing: bool = False,
+    enable_llm_editor: bool = False,
+    enable_jupyter: bool = False,
     llm: LLM | None = None,
 ) -> list[ChatCompletionToolParam]:
     SIMPLIFIED_TOOL_DESCRIPTION_LLM_SUBSTRS = ['gpt-', 'o3', 'o1']
@@ -259,12 +259,12 @@ def get_tools(
         ThinkTool,
         FinishTool,
     ]
-    if codeact_enable_browsing:
+    if enable_browsing:
         tools.append(WebReadTool)
         tools.append(BrowserTool)
-    if codeact_enable_jupyter:
+    if enable_jupyter:
         tools.append(IPythonTool)
-    if codeact_enable_llm_editor:
+    if enable_llm_editor:
         tools.append(LLMBasedFileEditTool)
     else:
         tools.append(

openhands/core/cli.py

@@ -1,13 +1,27 @@
 import asyncio
 import logging
 import sys
+import time
+from pathlib import Path
+from typing import List, Optional
 from uuid import uuid4
 
+import toml
 from prompt_toolkit import PromptSession, print_formatted_text
-from prompt_toolkit.formatted_text import FormattedText
+from prompt_toolkit.application import Application
+from prompt_toolkit.completion import Completer, Completion
+from prompt_toolkit.formatted_text import HTML, FormattedText
 from prompt_toolkit.key_binding import KeyBindings
+from prompt_toolkit.layout.containers import HSplit, Window
+from prompt_toolkit.layout.controls import FormattedTextControl
+from prompt_toolkit.layout.layout import Layout
+from prompt_toolkit.patch_stdout import patch_stdout
+from prompt_toolkit.shortcuts import clear, print_container
+from prompt_toolkit.styles import Style
+from prompt_toolkit.widgets import Frame, TextArea
 
 import openhands.agenthub  # noqa F401 (we import this to get the agents registered)
+from openhands import __version__
 from openhands.core.config import (
     AppConfig,
     parse_arguments,
@@ -37,89 +51,176 @@ from openhands.events.observation import (
     AgentStateChangedObservation,
     CmdOutputObservation,
     FileEditObservation,
+    FileReadObservation,
 )
 from openhands.io import read_task
+from openhands.llm.metrics import Metrics
 from openhands.mcp import fetch_mcp_tools_from_config
+from openhands.microagent.microagent import BaseMicroagent
 
-prompt_session = PromptSession()
+# Color and styling constants
+COLOR_GOLD = '#FFD700'
+COLOR_GREY = '#808080'
+DEFAULT_STYLE = Style.from_dict(
+    {
+        'gold': COLOR_GOLD,
+        'grey': COLOR_GREY,
+        'prompt': f'{COLOR_GOLD} bold',
+    }
+)
+
+COMMANDS = {
+    '/exit': 'Exit the application',
+    '/help': 'Display available commands',
+    '/init': 'Initialize a new repository',
+}
+
+REPO_MD_CREATE_PROMPT = """
+Please explore this repository. Create the file .openhands/microagents/repo.md with:
+- A description of the project
+- An overview of the file structure
+- Any information on how to run tests or other relevant commands
+- Any other information that would be helpful to a brand new developer
+Keep it short--just a few paragraphs will do.
+"""
 
 
-def display_message(message: str) -> None:
+class CommandCompleter(Completer):
+    """Custom completer for commands."""
+
+    def get_completions(self, document, complete_event):
+        text = document.text
+
+        # Only show completions if the user has typed '/'
+        if text.startswith('/'):
+            # If just '/' is typed, show all commands
+            if text == '/':
+                for command, description in COMMANDS.items():
+                    yield Completion(
+                        command[1:],  # Remove the leading '/' as it's already typed
+                        start_position=0,
+                        display=f'{command} - {description}',
+                    )
+            # Otherwise show matching commands
+            else:
+                for command, description in COMMANDS.items():
+                    if command.startswith(text):
+                        yield Completion(
+                            command[len(text) :],  # Complete the remaining part
+                            start_position=0,
+                            display=f'{command} - {description}',
+                        )
+
+
+class UsageMetrics:
+    def __init__(self):
+        self.total_cost: float = 0.00
+        self.total_input_tokens: int = 0
+        self.total_output_tokens: int = 0
+        self.total_cache_read: int = 0
+        self.total_cache_write: int = 0
+
+
+prompt_session = PromptSession(style=DEFAULT_STYLE, completer=CommandCompleter())
+
+
+def display_message(message: str):
+    message = message.strip()
+
+    if message:
+        print_formatted_text(f'\n{message}\n')
+
+
+def display_command(command: str):
+    container = Frame(
+        TextArea(
+            text=command,
+            read_only=True,
+            style=COLOR_GREY,
+            wrap_lines=True,
+        ),
+        title='Command Run',
+        style=f'fg:{COLOR_GREY}',
+    )
+    print_container(container)
+    print_formatted_text('')
+
+
+def display_confirmation(confirmation_state: ActionConfirmationStatus):
+    status_map = {
+        ActionConfirmationStatus.CONFIRMED: ('ansigreen', '✅'),
+        ActionConfirmationStatus.REJECTED: ('ansired', '❌'),
+        ActionConfirmationStatus.AWAITING_CONFIRMATION: ('ansiyellow', '⏳'),
+    }
+    color, icon = status_map.get(confirmation_state, ('ansiyellow', ''))
+
     print_formatted_text(
         FormattedText(
             [
-                ('ansiyellow', '🤖 '),
-                ('ansiyellow', message),
+                (color, f'{icon} '),
+                (color, str(confirmation_state)),
                 ('', '\n'),
             ]
         )
     )
 
 
-def display_command(command: str) -> None:
-    print_formatted_text(
-        FormattedText(
-            [
-                ('', '❯ '),
-                ('ansigreen', command),
-                ('', '\n'),
-            ]
-        )
-    )
-
-
-def display_confirmation(confirmation_state: ActionConfirmationStatus) -> None:
-    if confirmation_state == ActionConfirmationStatus.CONFIRMED:
-        print_formatted_text(
-            FormattedText(
-                [
-                    ('ansigreen', '✅ '),
-                    ('ansigreen', str(confirmation_state)),
-                    ('', '\n'),
-                ]
-            )
-        )
-    elif confirmation_state == ActionConfirmationStatus.REJECTED:
-        print_formatted_text(
-            FormattedText(
-                [
-                    ('ansired', '❌ '),
-                    ('ansired', str(confirmation_state)),
-                    ('', '\n'),
-                ]
-            )
-        )
-    else:
-        print_formatted_text(
-            FormattedText(
-                [
-                    ('ansiyellow', '⏳ '),
-                    ('ansiyellow', str(confirmation_state)),
-                    ('', '\n'),
-                ]
-            )
-        )
-
-
-def display_command_output(output: str) -> None:
+def display_command_output(output: str):
     lines = output.split('\n')
+    formatted_lines = []
     for line in lines:
         if line.startswith('[Python Interpreter') or line.startswith('openhands@'):
             # TODO: clean this up once we clean up terminal output
             continue
-        print_formatted_text(FormattedText([('ansiblue', line)]))
+        formatted_lines.append(line)
+        formatted_lines.append('\n')
+
+    # Remove the last newline if it exists
+    if formatted_lines:
+        formatted_lines.pop()
+
+    container = Frame(
+        TextArea(
+            text=''.join(formatted_lines),
+            read_only=True,
+            style=COLOR_GREY,
+            wrap_lines=True,
+        ),
+        title='Command Output',
+        style=f'fg:{COLOR_GREY}',
+    )
+    print_container(container)
     print_formatted_text('')
 
 
-def display_file_edit(event: FileEditAction | FileEditObservation) -> None:
-    print_formatted_text(
-        FormattedText(
-            [
-                ('ansigreen', str(event)),
-                ('', '\n'),
-            ]
-        )
+def display_file_edit(event: FileEditAction | FileEditObservation):
+    container = Frame(
+        TextArea(
+            text=f'{event}',
+            read_only=True,
+            style=COLOR_GREY,
+            wrap_lines=True,
+        ),
+        title='File Edit',
+        style=f'fg:{COLOR_GREY}',
     )
+    print_container(container)
+    print_formatted_text('')
+
+
+def display_file_read(event: FileReadObservation):
+    container = Frame(
+        TextArea(
+            text=f'{event}',
+            read_only=True,
+            style=COLOR_GREY,
+            wrap_lines=True,
+        ),
+        title='File Read',
+        style=f'fg:{COLOR_GREY}',
+    )
+    print_container(container)
+    print_formatted_text('')
 
 
 def display_event(event: Event, config: AppConfig) -> None:
@@ -137,10 +238,115 @@ def display_event(event: Event, config: AppConfig) -> None:
         display_file_edit(event)
     if isinstance(event, FileEditObservation):
         display_file_edit(event)
+    if isinstance(event, FileReadObservation):
+        display_file_read(event)
     if hasattr(event, 'confirmation_state') and config.security.confirmation_mode:
         display_confirmation(event.confirmation_state)
 
 
+def display_help(style=DEFAULT_STYLE):
+    print_formatted_text(
+        HTML(f'\n<grey>OpenHands CLI v{__version__}</grey>\n'), style=style
+    )
+
+    print_formatted_text(
+        HTML(
+            '<gold>OpenHands CLI lets you interact with the OpenHands agent from the command line.</gold>'
+        )
+    )
+    print_formatted_text('')
+
+    print_formatted_text('Things that you can try:')
+    print_formatted_text(
+        HTML('• Ask questions about the codebase <grey>> How does main.py work?</grey>')
+    )
+    print_formatted_text(
+        HTML(
+            '• Edit files or add new features <grey>> Add a new function to ...</grey>'
+        )
+    )
+    print_formatted_text(
+        HTML('• Find and fix issues <grey>> Fix the type error in ...</grey>')
+    )
+    print_formatted_text('')
+
+    print_formatted_text('Some tips to get the most out of OpenHands:')
+    print_formatted_text(
+        '• Be as specific as possible about the desired outcome or the problem to be solved.'
+    )
+    print_formatted_text(
+        '• Provide context, including relevant file paths and line numbers if available.'
+    )
+    print_formatted_text('• Break large tasks into smaller, manageable prompts.')
+    print_formatted_text('• Include relevant error messages or logs.')
+    print_formatted_text(
+        '• Specify the programming language or framework, if not obvious.'
+    )
+    print_formatted_text('')
+
+    print_formatted_text(HTML('Interactive commands:'), style=style)
+    for command, description in COMMANDS.items():
+        print_formatted_text(
+            HTML(f'<gold><b>{command}</b></gold> - <grey>{description}</grey>'),
+            style=style,
+        )
+    print_formatted_text('')
+    print_formatted_text(
+        HTML(
+            '<grey>Learn more at: https://docs.all-hands.dev/modules/usage/getting-started</grey>'
+        )
+    )
+    print_formatted_text('')
+
+
+def display_banner(session_id: str, is_loaded: asyncio.Event):
+    print_formatted_text(
+        HTML(r"""<gold>
+     ___                    _   _                 _
+    /  _ \ _ __   ___ _ __ | | | | __ _ _ __   __| |___
+    | | | | '_ \ / _ \ '_ \| |_| |/ _` | '_ \ / _` / __|
+    | |_| | |_) |  __/ | | |  _  | (_| | | | | (_| \__ \
+    \___ /| .__/ \___|_| |_|_| |_|\__,_|_| |_|\__,_|___/
+          |_|
+    </gold>"""),
+        style=DEFAULT_STYLE,
+    )
+
+    print_formatted_text(HTML(f'<grey>OpenHands CLI v{__version__}</grey>'))
+
+    banner_text = (
+        'Initialized session' if is_loaded.is_set() else 'Initializing session'
+    )
+    print_formatted_text(HTML(f'\n<grey>{banner_text} {session_id}</grey>\n'))
+
+
+def display_welcome_message():
+    print_formatted_text(
+        HTML("<gold>Let's start building!</gold>\n"), style=DEFAULT_STYLE
+    )
+    print_formatted_text(
+        HTML('What do you want to build? <grey>Type /help for help</grey>\n'),
+        style=DEFAULT_STYLE,
+    )
+
+
+def display_initialization_animation(text, is_loaded: asyncio.Event):
+    ANIMATION_FRAMES = ['⠋', '⠙', '⠹', '⠸', '⠼', '⠴', '⠦', '⠧', '⠇', '⠏']
+
+    i = 0
+    while not is_loaded.is_set():
+        sys.stdout.write('\n')
+        sys.stdout.write(
+            f'\033[s\033[J\033[38;2;255;215;0m[{ANIMATION_FRAMES[i % len(ANIMATION_FRAMES)]}] {text}\033[0m\033[u\033[1A'
+        )
+        sys.stdout.flush()
+        time.sleep(0.1)
+        i += 1
+
+    sys.stdout.write('\r' + ' ' * (len(text) + 10) + '\r')
+    sys.stdout.flush()
+
+
 async def read_prompt_input(multiline=False):
     try:
         if multiline:
@@ -150,35 +356,292 @@ async def read_prompt_input(multiline=False):
             def _(event):
                 event.current_buffer.validate_and_handle()
 
-            message = await prompt_session.prompt_async(
-                'Enter your message and press Ctrl+D to finish:\n',
-                multiline=True,
-                key_bindings=kb,
-            )
+            with patch_stdout():
+                message = await prompt_session.prompt_async(
+                    'Enter your message and press Ctrl+D to finish:\n',
+                    multiline=True,
+                    key_bindings=kb,
+                )
         else:
-            message = await prompt_session.prompt_async(
-                '>> ',
-            )
+            with patch_stdout():
+                message = await prompt_session.prompt_async(
+                    '> ',
+                )
         return message
     except KeyboardInterrupt:
-        return 'exit'
+        return '/exit'
     except EOFError:
-        return 'exit'
+        return '/exit'
 
 
 async def read_confirmation_input():
     try:
         confirmation = await prompt_session.prompt_async(
-            'Confirm action (possible security risk)? (y/n) >> ',
+            'Confirm action (possible security risk)? (y/n) > ',
         )
         return confirmation.lower() == 'y'
     except (KeyboardInterrupt, EOFError):
         return False
 
 
-async def main(loop: asyncio.AbstractEventLoop) -> None:
+async def init_repository(current_dir: str) -> bool:
+    repo_file_path = Path(current_dir) / '.openhands' / 'microagents' / 'repo.md'
+    init_repo = False
+
+    if repo_file_path.exists():
+        try:
+            content = await asyncio.get_event_loop().run_in_executor(
+                None, read_file, repo_file_path
+            )
+
+            print_formatted_text(
+                'Repository instructions file (repo.md) already exists.\n'
+            )
+
+            container = Frame(
+                TextArea(
+                    text=content,
+                    read_only=True,
+                    style=COLOR_GREY,
+                    wrap_lines=True,
+                ),
+                title='Repository Instructions (repo.md)',
+                style=f'fg:{COLOR_GREY}',
+            )
+            print_container(container)
+            print_formatted_text('')  # Add a newline after the frame
+
+            init_repo = cli_confirm(
+                'Do you want to re-initialize?',
+                ['Yes, re-initialize', 'No, dismiss'],
+            )
+
+            if init_repo:
+                write_to_file(repo_file_path, '')
+        except Exception:
+            print_formatted_text('Error reading repository instructions file (repo.md)')
+            init_repo = False
+    else:
+        print_formatted_text(
+            '\nRepository instructions file will be created by exploring the repository.\n'
+        )
+
+        init_repo = cli_confirm(
+            'Do you want to proceed?',
+            ['Yes, create', 'No, dismiss'],
+        )
+
+    return init_repo
+
+
+def read_file(file_path):
+    with open(file_path, 'r') as f:
+        return f.read()
+
+
+def write_to_file(file_path, content):
+    with open(file_path, 'w') as f:
+        f.write(content)
+
+
+def cli_confirm(question: str = 'Are you sure?', choices: Optional[List[str]] = None):
+    if choices is None:
+        choices = ['Yes', 'No']
+    selected = [0]  # Using list to allow modification in closure
+
+    def get_choice_text():
+        return [
+            ('class:question', f'{question}\n\n'),
+        ] + [
+            (
+                'class:selected' if i == selected[0] else 'class:unselected',
+                f"{'> ' if i == selected[0] else '  '}{choice}\n",
+            )
+            for i, choice in enumerate(choices)
+        ]
+
+    kb = KeyBindings()
+
+    @kb.add('up')
+    def _(event):
+        selected[0] = (selected[0] - 1) % len(choices)
+
+    @kb.add('down')
+    def _(event):
+        selected[0] = (selected[0] + 1) % len(choices)
+
+    @kb.add('enter')
+    def _(event):
+        event.app.exit(result=selected[0] == 0)
+
+    style = Style.from_dict({'selected': COLOR_GOLD, 'unselected': ''})
+
+    layout = Layout(
+        HSplit(
+            [
+                Window(
+                    FormattedTextControl(get_choice_text),
+                    always_hide_cursor=True,
+                )
+            ]
+        )
+    )
+
+    app = Application(
+        layout=layout,
+        key_bindings=kb,
+        style=style,
+        mouse_support=True,
+        full_screen=False,
+    )
+
+    return app.run(in_thread=True)
+
+
+def update_usage_metrics(event: Event, usage_metrics: UsageMetrics):
+    """Updates the UsageMetrics object with data from an event's llm_metrics."""
+    if hasattr(event, 'llm_metrics'):
+        llm_metrics: Metrics | None = getattr(event, 'llm_metrics', None)
+        if llm_metrics:
+            # Safely get accumulated_cost
+            cost = getattr(llm_metrics, 'accumulated_cost', 0)
+            # Ensure cost is a number before adding
+            usage_metrics.total_cost += cost if isinstance(cost, float) else 0
+
+            # Safely get token usage details object/dict
+            token_usage = getattr(llm_metrics, 'accumulated_token_usage', None)
+            if token_usage:
+                # Assume object access using getattr, providing defaults
+                prompt_tokens = getattr(token_usage, 'prompt_tokens', 0)
+                completion_tokens = getattr(token_usage, 'completion_tokens', 0)
+                cache_read = getattr(token_usage, 'cache_read_tokens', 0)
+                cache_write = getattr(token_usage, 'cache_write_tokens', 0)
+
+                # Ensure tokens are numbers before adding
+                usage_metrics.total_input_tokens += (
+                    prompt_tokens if isinstance(prompt_tokens, int) else 0
+                )
+                usage_metrics.total_output_tokens += (
+                    completion_tokens if isinstance(completion_tokens, int) else 0
+                )
+                usage_metrics.total_cache_read += (
+                    cache_read if isinstance(cache_read, int) else 0
+                )
+                usage_metrics.total_cache_write += (
+                    cache_write if isinstance(cache_write, int) else 0
+                )
+
+
+def shutdown(usage_metrics: UsageMetrics, session_id: str):
+    cost_str = f'${usage_metrics.total_cost:.6f}'
+    input_tokens_str = f'{usage_metrics.total_input_tokens:,}'
+    cache_read_str = f'{usage_metrics.total_cache_read:,}'
+    cache_write_str = f'{usage_metrics.total_cache_write:,}'
+    output_tokens_str = f'{usage_metrics.total_output_tokens:,}'
+    total_tokens_str = (
+        f'{usage_metrics.total_input_tokens + usage_metrics.total_output_tokens:,}'
+    )
+
+    labels_and_values = [
+        ('   Total Cost (USD):', cost_str),
+        ('   Total Input Tokens:', input_tokens_str),
+        ('      Cache Hits:', cache_read_str),
+        ('      Cache Writes:', cache_write_str),
+        ('   Total Output Tokens:', output_tokens_str),
+        ('   Total Tokens:', total_tokens_str),
+    ]
+
+    # Calculate max widths for alignment
+    max_label_width = max(len(label) for label, _ in labels_and_values)
+    max_value_width = max(len(value) for _, value in labels_and_values)
+
+    # Construct the summary text with aligned columns
+    summary_lines = [
+        f'{label:<{max_label_width}} {value:>{max_value_width}}'
+        for label, value in labels_and_values
+    ]
+    summary_text = '\n'.join(summary_lines)
+
+    container = Frame(
+        TextArea(
+            text=summary_text,
+            read_only=True,
+            style=COLOR_GREY,
+            wrap_lines=True,
+        ),
+        title='Session Summary',
+        style=f'fg:{COLOR_GREY}',
+    )
+    print_container(container)
+    print_formatted_text(HTML(f'\n<grey>Closed session {session_id}</grey>\n'))
+
+
+def manage_openhands_file(folder_path=None, add_to_trusted=False):
+    openhands_file = Path.home() / '.openhands.toml'
+    default_content: dict = {'trusted_dirs': []}
+
+    if not openhands_file.exists():
+        with open(openhands_file, 'w') as f:
+            toml.dump(default_content, f)
+
+    if folder_path:
+        with open(openhands_file, 'r') as f:
+            try:
+                config = toml.load(f)
+            except Exception:
+                config = default_content
+
+        if 'trusted_dirs' not in config:
+            config['trusted_dirs'] = []
+
+        if folder_path in config['trusted_dirs']:
+            return True
+
+        if add_to_trusted:
+            config['trusted_dirs'].append(folder_path)
+            with open(openhands_file, 'w') as f:
+                toml.dump(config, f)
+
+        return False
+
+    return False
+
+
+def check_folder_security_agreement(current_dir):
+    is_trusted = manage_openhands_file(current_dir)
+
+    if not is_trusted:
+        security_frame = Frame(
+            TextArea(
+                text=(
+                    f'Do you trust the files in this folder?\n\n'
+                    f'{current_dir}\n\n'
+                    'OpenHands may read and execute files in this folder with your permission.'
+                ),
+                style='#ffffff',
+                read_only=True,
+                wrap_lines=True,
+            )
+        )
+
+        clear()
+        print_container(security_frame)
+
+        confirm = cli_confirm('Do you wish to continue?', ['Yes, proceed', 'No, exit'])
+
+        if confirm:
+            manage_openhands_file(current_dir, add_to_trusted=True)
+
+        return confirm
+
+    return True
+
+
+async def main(loop: asyncio.AbstractEventLoop):
     """Runs the agent in CLI mode."""
 
+    reload_microagents = False
+
     args = parse_arguments()
 
     logger.setLevel(logging.WARNING)
@@ -186,6 +649,12 @@ async def main(loop: asyncio.AbstractEventLoop) -> None:
     # Load config from toml and override with command line arguments
     config: AppConfig = setup_config_from_args(args)
 
+    # TODO: Set working directory from config or use current working directory?
+    current_dir = config.workspace_base
+
+    if not current_dir:
+        raise ValueError('Workspace base directory not specified')
+
     # Read task from file, CLI args, or stdin
     task_str = read_task(args, config.cli_multiline_input)
 
@@ -193,7 +662,15 @@ async def main(loop: asyncio.AbstractEventLoop) -> None:
     initial_user_action = MessageAction(content=task_str) if task_str else None
 
     sid = str(uuid4())
-    display_message(f'Session ID: {sid}')
+    is_loaded = asyncio.Event()
+
+    # Show OpenHands banner and session ID
+    display_banner(session_id=sid, is_loaded=is_loaded)
+
+    # Show Initialization loader
+    loop.run_in_executor(
+        None, display_initialization_animation, 'Initializing...', is_loaded
+    )
 
     agent = create_agent(config)
     mcp_tools = await fetch_mcp_tools_from_config(config.mcp)
@@ -209,26 +686,64 @@ async def main(loop: asyncio.AbstractEventLoop) -> None:
 
     event_stream = runtime.event_stream
 
-    async def prompt_for_next_task() -> None:
-        next_message = await read_prompt_input(config.cli_multiline_input)
-        if not next_message.strip():
-            await prompt_for_next_task()
-        if next_message == 'exit':
-            event_stream.add_event(
-                ChangeAgentStateAction(AgentState.STOPPED), EventSource.ENVIRONMENT
-            )
+    usage_metrics = UsageMetrics()
+
+    async def prompt_for_next_task():
+        nonlocal reload_microagents
+        while True:
+            next_message = await read_prompt_input(config.cli_multiline_input)
+
+            if not next_message.strip():
+                continue
+
+            if next_message == '/exit':
+                event_stream.add_event(
+                    ChangeAgentStateAction(AgentState.STOPPED), EventSource.ENVIRONMENT
+                )
+                shutdown(usage_metrics, sid)
+                return
+            elif next_message == '/help':
+                display_help()
+                continue
+            elif next_message == '/init':
+                if config.runtime == 'local':
+                    init_repo = await init_repository(current_dir)
+                    if init_repo:
+                        event_stream.add_event(
+                            MessageAction(content=REPO_MD_CREATE_PROMPT),
+                            EventSource.USER,
+                        )
+                        reload_microagents = True
+                        return
+                else:
+                    print_formatted_text(
+                        '\nRepository initialization through the CLI is only supported for local runtime.\n'
+                    )
+                continue
+
+            action = MessageAction(content=next_message)
+            event_stream.add_event(action, EventSource.USER)
             return
-        action = MessageAction(content=next_message)
-        event_stream.add_event(action, EventSource.USER)
 
     async def on_event_async(event: Event) -> None:
+        nonlocal reload_microagents
         display_event(event, config)
+        update_usage_metrics(event, usage_metrics)
+
         if isinstance(event, AgentStateChangedObservation):
             if event.agent_state in [
                 AgentState.AWAITING_USER_INPUT,
                 AgentState.FINISHED,
             ]:
+                # Reload microagents after initialization of repo.md
+                if reload_microagents:
+                    microagents: list[BaseMicroagent] = (
+                        runtime.get_microagents_from_selected_repo(None)
+                    )
+                    memory.load_user_workspace_microagents(microagents)
+                    reload_microagents = False
                 await prompt_for_next_task()
+
             if event.agent_state == AgentState.AWAITING_USER_CONFIRMATION:
                 user_confirmed = await read_confirmation_input()
                 if user_confirmed:
@@ -266,6 +781,25 @@ async def main(loop: asyncio.AbstractEventLoop) -> None:
         repo_directory=repo_directory,
     )
 
+    # Clear loading animation
+    is_loaded.set()
+
+    if not check_folder_security_agreement(current_dir):
+        # User rejected, exit application
+        event_stream.add_event(
+            ChangeAgentStateAction(AgentState.STOPPED), EventSource.ENVIRONMENT
+        )
+        return
+
+    # Clear the terminal
+    clear()
+
+    # Show OpenHands banner and session ID
+    display_banner(session_id=sid, is_loaded=is_loaded)
+
+    # Show OpenHands welcome
+    display_welcome_message()
+
     if initial_user_action:
         # If there's an initial user action, enqueue it and do not prompt again
         event_stream.add_event(initial_user_action, EventSource.USER)

openhands/core/config/agent_config.py

@@ -10,10 +10,9 @@ class AgentConfig(BaseModel):
     """Configuration for the agent.
 
     Attributes:
-        function_calling: Whether function calling is enabled. Default is True.
-        codeact_enable_browsing: Whether browsing delegate is enabled in the action space. Default is False. Only works with function calling.
-        codeact_enable_llm_editor: Whether LLM editor is enabled in the action space. Default is False. Only works with function calling.
-        codeact_enable_jupyter: Whether Jupyter is enabled in the action space. Default is False.
+        enable_browsing: Whether browsing delegate is enabled in the action space. Default is False. Only works with function calling.
+        enable_llm_editor: Whether LLM editor is enabled in the action space. Default is False. Only works with function calling.
+        enable_jupyter: Whether Jupyter is enabled in the action space. Default is False.
         llm_config: The name of the llm config to use. If specified, this will override global llm config.
         enable_prompt_extensions: Whether to use prompt extensions (e.g., microagents, inject runtime info). Default is True.
         disabled_microagents: A list of microagents to disable (by name, without .py extension, e.g. ["github", "lint"]). Default is None.
@@ -23,9 +22,9 @@ class AgentConfig(BaseModel):
     """
 
     llm_config: str | None = Field(default=None)
-    codeact_enable_browsing: bool = Field(default=True)
-    codeact_enable_llm_editor: bool = Field(default=False)
-    codeact_enable_jupyter: bool = Field(default=True)
+    enable_browsing: bool = Field(default=True)
+    enable_llm_editor: bool = Field(default=False)
+    enable_jupyter: bool = Field(default=True)
     enable_prompt_extensions: bool = Field(default=True)
     disabled_microagents: list[str] = Field(default_factory=list)
     enable_history_truncation: bool = Field(default=True)

openhands/events/stream.py

@@ -160,30 +160,38 @@ class EventStream(EventStore):
             raise ValueError(
                 f'Event already has an ID:{event.id}. It was probably added back to the EventStream from inside a handler, triggering a loop.'
             )
+        event._timestamp = datetime.now().isoformat()
+        event._source = source  # type: ignore [attr-defined]
         with self._lock:
             event._id = self.cur_id  # type: ignore [attr-defined]
             self.cur_id += 1
-        logger.debug(f'Adding {type(event).__name__} id={event.id} from {source.name}')
-        event._timestamp = datetime.now().isoformat()
-        event._source = source  # type: ignore [attr-defined]
-        logger.debug(f'Event to add: {event}')
-        data = event_to_dict(event)
-        data = self._replace_secrets(data)
-        event = event_from_dict(data)
+
+            # Take a copy of the current write page
+            current_write_page = self._write_page_cache
+
+            data = event_to_dict(event)
+            data = self._replace_secrets(data)
+            event = event_from_dict(data)
+            current_write_page.append(data)
+
+            # If the page is full, create a new page for future events / other threads to use
+            if len(current_write_page) == self.cache_size:
+                self._write_page_cache = []
+
         if event.id is not None:
+            # Write the event to the store - this can take some time
             self.file_store.write(
                 self._get_filename_for_id(event.id, self.user_id), json.dumps(data)
             )
-            self._write_page_cache.append(data)
-            self._store_cache_page()
+
+            # Store the cache page last - if it is not present during reads then it will simply be bypassed.
+            self._store_cache_page(current_write_page)
         self._queue.put(event)
 
-    def _store_cache_page(self):
+    def _store_cache_page(self, current_write_page: list[dict]):
         """Store a page in the cache. Reading individual events is slow when there are a lot of them, so we use pages."""
-        current_write_page = self._write_page_cache
         if len(current_write_page) < self.cache_size:
             return
-        self._write_page_cache = []
         start = current_write_page[0]['id']
         end = start + self.cache_size
         contents = json.dumps(current_write_page)

openhands/memory/condenser/impl/llm_attention_condenser.py

@@ -114,8 +114,14 @@ class LLMAttentionCondenser(RollingCondenser):
 
     @classmethod
     def from_config(cls, config: LLMAttentionCondenserConfig) -> LLMAttentionCondenser:
+        # This condenser cannot take advantage of prompt caching. If it happens
+        # to be set, we'll pay for the cache writes but never get a chance to
+        # save on a read.
+        llm_config = config.llm_config.model_copy()
+        llm_config.caching_prompt = False
+
         return LLMAttentionCondenser(
-            llm=LLM(config=config.llm_config),
+            llm=LLM(config=llm_config),
             max_size=config.max_size,
             keep_first=config.keep_first,
         )

openhands/memory/condenser/impl/llm_summarizing_condenser.py

@@ -155,8 +155,14 @@ CURRENT_STATE: Last flip: Heads, Haiku count: 15/20"""
     def from_config(
         cls, config: LLMSummarizingCondenserConfig
     ) -> LLMSummarizingCondenser:
+        # This condenser cannot take advantage of prompt caching. If it happens
+        # to be set, we'll pay for the cache writes but never get a chance to
+        # save on a read.
+        llm_config = config.llm_config.model_copy()
+        llm_config.caching_prompt = False
+
         return LLMSummarizingCondenser(
-            llm=LLM(config=config.llm_config),
+            llm=LLM(config=llm_config),
             max_size=config.max_size,
             keep_first=config.keep_first,
             max_event_length=config.max_event_length,

openhands/memory/condenser/impl/structured_summary_condenser.py

@@ -311,8 +311,14 @@ Capture all relevant information, especially:
     def from_config(
         cls, config: StructuredSummaryCondenserConfig
     ) -> StructuredSummaryCondenser:
+        # This condenser cannot take advantage of prompt caching. If it happens
+        # to be set, we'll pay for the cache writes but never get a chance to
+        # save on a read.
+        llm_config = config.llm_config.model_copy()
+        llm_config.caching_prompt = False
+
         return StructuredSummaryCondenser(
-            llm=LLM(config=config.llm_config),
+            llm=LLM(config=llm_config),
             max_size=config.max_size,
             keep_first=config.keep_first,
             max_event_length=config.max_event_length,

openhands/resolver/send_pull_request.py

@@ -319,6 +319,12 @@ def send_pull_request(
         pr_body += f'\n\n{additional_message}'
     pr_body += '\n\nAutomatic fix generated by [OpenHands](https://github.com/All-Hands-AI/OpenHands/) 🙌'
 
+    # For cross repo pull request, we need to send head parameter like fork_owner:branch as per git documentation here : https://docs.github.com/en/rest/pulls/pulls?apiVersion=2022-11-28#create-a-pull-request
+    # head parameter usage : The name of the branch where your changes are implemented. For cross-repository pull requests in the same network, namespace head with a user like this: username:branch.
+    if fork_owner and platform == Platform.GITHUB:
+        head_branch = f'{fork_owner}:{branch_name}'
+    else:
+        head_branch = branch_name
     # If we are not sending a PR, we can finish early and return the
     # URL for the user to open a PR manually
     if pr_type == 'branch':
@@ -328,7 +334,7 @@ def send_pull_request(
         data = {
             'title': final_pr_title,
             ('body' if platform == Platform.GITHUB else 'description'): pr_body,
-            ('head' if platform == Platform.GITHUB else 'source_branch'): branch_name,
+            ('head' if platform == Platform.GITHUB else 'source_branch'): head_branch,
             ('base' if platform == Platform.GITHUB else 'target_branch'): base_branch,
             'draft': pr_type == 'draft',
         }

openhands/runtime/action_execution_server.py

@@ -18,6 +18,7 @@ from contextlib import asynccontextmanager
 from pathlib import Path
 from zipfile import ZipFile
 
+from binaryornot.check import is_binary
 from fastapi import Depends, FastAPI, HTTPException, Request, UploadFile
 from fastapi.exceptions import RequestValidationError
 from fastapi.responses import FileResponse, HTMLResponse, JSONResponse
@@ -355,6 +356,11 @@ class ActionExecutor:
 
     async def read(self, action: FileReadAction) -> Observation:
         assert self.bash_session is not None
+
+        # Cannot read binary files
+        if is_binary(action.path):
+            return ErrorObservation('ERROR_BINARY_FILE')
+
         if action.impl_source == FileReadSource.OH_ACI:
             result_str, _ = _execute_file_editor(
                 self.file_editor,

openhands/runtime/base.py

@@ -14,7 +14,6 @@ from typing import Callable, cast
 from zipfile import ZipFile
 
 import httpx
-from pydantic import SecretStr
 
 from openhands.core.config import AppConfig, SandboxConfig
 from openhands.core.exceptions import AgentRuntimeDisconnectedError
@@ -151,15 +150,12 @@ class Runtime(FileEditRuntimeMixin):
 
         # Load mixins
         FileEditRuntimeMixin.__init__(
-            self, enable_llm_editor=config.get_agent_config().codeact_enable_llm_editor
+            self, enable_llm_editor=config.get_agent_config().enable_llm_editor
         )
 
         self.user_id = user_id
         self.git_provider_tokens = git_provider_tokens
 
-        # TODO: remove once done debugging expired github token
-        self.prev_token: SecretStr | None = None
-
     def setup_initial_env(self) -> None:
         if self.attach_to_existing:
             return
@@ -257,31 +253,14 @@ class Runtime(FileEditRuntimeMixin):
         if not providers_called:
             return
 
-        logger.info(f'Fetching latest github token for runtime: {self.sid}')
+        logger.info(f'Fetching latest provider tokens for runtime: {self.sid}')
         env_vars = await self.provider_handler.get_env_vars(
             providers=providers_called, expose_secrets=False, get_latest=True
         )
 
-        # This statement is to debug expired github tokens, and will be removed later
-        if ProviderType.GITHUB not in env_vars:
-            logger.error(f'Failed to refresh github token for runtime: {self.sid}')
-            return
-
         if len(env_vars) == 0:
             return
 
-        raw_token = env_vars[ProviderType.GITHUB].get_secret_value()
-        if not self.prev_token:
-            logger.info(
-                f'Setting github token in runtime: {self.sid}\nToken value: {raw_token[0:5]}; length: {len(raw_token)}'
-            )
-        elif self.prev_token.get_secret_value() != raw_token:
-            logger.info(
-                f'Setting new github token in runtime {self.sid}\nToken value: {raw_token[0:5]}; length: {len(raw_token)}'
-            )
-
-        self.prev_token = SecretStr(raw_token)
-
         try:
             await self.provider_handler.set_event_stream_secrets(
                 self.event_stream, env_vars=env_vars

openhands/runtime/impl/action_execution/action_execution_client.py

@@ -39,13 +39,14 @@ from openhands.events.observation import (
 from openhands.events.serialization import event_to_dict, observation_from_dict
 from openhands.events.serialization.action import ACTION_TYPE_TO_CLASS
 from openhands.integrations.provider import PROVIDER_TOKEN_TYPE
-from openhands.mcp import call_tool_mcp as call_tool_mcp_handler, create_mcp_clients, MCPClient
+from openhands.mcp import MCPClient, create_mcp_clients
+from openhands.mcp import call_tool_mcp as call_tool_mcp_handler
 from openhands.runtime.base import Runtime
 from openhands.runtime.plugins import PluginRequirement
 from openhands.runtime.utils.request import send_request
+from openhands.utils.async_utils import call_async_from_sync
 from openhands.utils.http_session import HttpSession
 from openhands.utils.tenacity_stop import stop_if_should_exit
-from openhands.utils.async_utils import call_async_from_sync
 
 
 def _is_retryable_error(exception):
@@ -325,10 +326,11 @@ class ActionExecutionClient(Runtime):
 
     async def call_tool_mcp(self, action: McpAction) -> Observation:
         if self.mcp_clients is None:
-            self.log('debug', f'Creating MCP clients with servers: {self.config.mcp.sse.mcp_servers}')
-            self.mcp_clients = await create_mcp_clients(
-                self.config.mcp.sse.mcp_servers
+            self.log(
+                'debug',
+                f'Creating MCP clients with servers: {self.config.mcp.sse.mcp_servers}',
             )
+            self.mcp_clients = await create_mcp_clients(self.config.mcp.sse.mcp_servers)
         return await call_tool_mcp_handler(self.mcp_clients, action)
 
     async def aclose(self) -> None:

openhands/runtime/impl/docker/docker_runtime.py

@@ -44,7 +44,13 @@ def _is_retryable_wait_until_alive_error(exception):
         return _is_retryable_wait_until_alive_error(cause)
 
     return isinstance(
-        exception, (ConnectionError, httpx.NetworkError, httpx.RemoteProtocolError)
+        exception,
+        (
+            ConnectionError,
+            httpx.NetworkError,
+            httpx.RemoteProtocolError,
+            httpx.HTTPStatusError,
+        ),
     )
 
 

openhands/runtime/plugins/agent_skills/__init__.py

@@ -1,5 +1,7 @@
 from dataclasses import dataclass
 
+from openhands.events.action import Action
+from openhands.events.observation import Observation
 from openhands.runtime.plugins.agent_skills import agentskills
 from openhands.runtime.plugins.requirement import Plugin, PluginRequirement
 
@@ -12,3 +14,11 @@ class AgentSkillsRequirement(PluginRequirement):
 
 class AgentSkillsPlugin(Plugin):
     name: str = 'agent_skills'
+
+    async def initialize(self, username: str) -> None:
+        """Initialize the plugin."""
+        pass
+
+    async def run(self, action: Action) -> Observation:
+        """Run the plugin for a given action."""
+        raise NotImplementedError('AgentSkillsPlugin does not support run method')

openhands/runtime/plugins/jupyter/__init__.py

@@ -1,6 +1,5 @@
+import asyncio
 import os
-import subprocess
-import time
 from dataclasses import dataclass
 
 from openhands.core.logger import openhands_logger as logger
@@ -19,8 +18,14 @@ class JupyterRequirement(PluginRequirement):
 
 class JupyterPlugin(Plugin):
     name: str = 'jupyter'
+    kernel_gateway_port: int
+    kernel_id: str
+    gateway_process: asyncio.subprocess.Process
+    python_interpreter_path: str
 
-    async def initialize(self, username: str, kernel_id: str = 'openhands-default'):
+    async def initialize(
+        self, username: str, kernel_id: str = 'openhands-default'
+    ) -> None:
         self.kernel_gateway_port = find_available_tcp_port(40000, 49999)
         self.kernel_id = kernel_id
         if username in ['root', 'openhands']:
@@ -61,19 +66,22 @@ class JupyterPlugin(Plugin):
         )
         logger.debug(f'Jupyter launch command: {jupyter_launch_command}')
 
-        self.gateway_process = subprocess.Popen(
+        # Using asyncio.create_subprocess_shell instead of subprocess.Popen
+        # to avoid ASYNC101 linting error
+        self.gateway_process = await asyncio.create_subprocess_shell(
             jupyter_launch_command,
-            stderr=subprocess.STDOUT,
-            shell=True,
+            stderr=asyncio.subprocess.STDOUT,
+            stdout=asyncio.subprocess.PIPE,
         )
         # read stdout until the kernel gateway is ready
         output = ''
         while should_continue() and self.gateway_process.stdout is not None:
-            line = self.gateway_process.stdout.readline().decode('utf-8')
+            line_bytes = await self.gateway_process.stdout.readline()
+            line = line_bytes.decode('utf-8')
             output += line
             if 'at' in line:
                 break
-            time.sleep(1)
+            await asyncio.sleep(1)
             logger.debug('Waiting for jupyter kernel gateway to start...')
 
         logger.debug(

openhands/runtime/plugins/jupyter/execute_server.py

@@ -50,22 +50,22 @@ def strip_ansi(o: str) -> str:
 
 
 class JupyterKernel:
-    def __init__(self, url_suffix, convid, lang='python'):
+    def __init__(self, url_suffix: str, convid: str, lang: str = 'python') -> None:
         self.base_url = f'http://{url_suffix}'
         self.base_ws_url = f'ws://{url_suffix}'
         self.lang = lang
-        self.kernel_id = None
-        self.ws = None
+        self.kernel_id: str | None = None
+        self.ws: tornado.websocket.WebSocketClientConnection | None = None
         self.convid = convid
         logging.info(
             f'Jupyter kernel created for conversation {convid} at {url_suffix}'
         )
 
         self.heartbeat_interval = 10000  # 10 seconds
-        self.heartbeat_callback = None
+        self.heartbeat_callback: PeriodicCallback | None = None
         self.initialized = False
 
-    async def initialize(self):
+    async def initialize(self) -> None:
         await self.execute(r'%colors nocolor')
         # pre-defined tools
         self.tools_to_run: list[str] = [
@@ -76,7 +76,7 @@ class JupyterKernel:
             logging.info(f'Tool [{tool}] initialized:\n{res}')
         self.initialized = True
 
-    async def _send_heartbeat(self):
+    async def _send_heartbeat(self) -> None:
         if not self.ws:
             return
         try:
@@ -91,7 +91,7 @@ class JupyterKernel:
                     'ConnectionRefusedError: Failed to reconnect to kernel websocket - Is the kernel still running?'
                 )
 
-    async def _connect(self):
+    async def _connect(self) -> None:
         if self.ws:
             self.ws.close()
             self.ws = None
@@ -138,7 +138,7 @@ class JupyterKernel:
         stop=stop_after_attempt(3),
         wait=wait_fixed(2),
     )
-    async def execute(self, code, timeout=120):
+    async def execute(self, code: str, timeout: int = 120) -> str:
         if not self.ws:
             await self._connect()
 
@@ -170,45 +170,49 @@ class JupyterKernel:
         )
         logging.info(f'Executed code in jupyter kernel:\n{res}')
 
-        outputs = []
+        outputs: list[str] = []
 
-        async def wait_for_messages():
+        async def wait_for_messages() -> bool:
             execution_done = False
             while not execution_done:
                 assert self.ws is not None
                 msg = await self.ws.read_message()
-                msg = json_decode(msg)
-                msg_type = msg['msg_type']
-                parent_msg_id = msg['parent_header'].get('msg_id', None)
+                if msg is None:
+                    continue
+                msg_dict = json_decode(msg)
+                msg_type = msg_dict['msg_type']
+                parent_msg_id = msg_dict['parent_header'].get('msg_id', None)
 
                 if parent_msg_id != msg_id:
                     continue
 
                 if os.environ.get('DEBUG'):
                     logging.info(
-                        f"MSG TYPE: {msg_type.upper()} DONE:{execution_done}\nCONTENT: {msg['content']}"
+                        f"MSG TYPE: {msg_type.upper()} DONE:{execution_done}\nCONTENT: {msg_dict['content']}"
                     )
 
                 if msg_type == 'error':
-                    traceback = '\n'.join(msg['content']['traceback'])
+                    traceback = '\n'.join(msg_dict['content']['traceback'])
                     outputs.append(traceback)
                     execution_done = True
                 elif msg_type == 'stream':
-                    outputs.append(msg['content']['text'])
+                    outputs.append(msg_dict['content']['text'])
                 elif msg_type in ['execute_result', 'display_data']:
-                    outputs.append(msg['content']['data']['text/plain'])
-                    if 'image/png' in msg['content']['data']:
+                    outputs.append(msg_dict['content']['data']['text/plain'])
+                    if 'image/png' in msg_dict['content']['data']:
                         # use markdone to display image (in case of large image)
                         outputs.append(
-                            f"\n![image](data:image/png;base64,{msg['content']['data']['image/png']})\n"
+                            f"\n![image](data:image/png;base64,{msg_dict['content']['data']['image/png']})\n"
                         )
 
                 elif msg_type == 'execute_reply':
                     execution_done = True
             return execution_done
 
-        async def interrupt_kernel():
+        async def interrupt_kernel() -> None:
             client = AsyncHTTPClient()
+            if self.kernel_id is None:
+                return
             interrupt_response = await client.fetch(
                 f'{self.base_url}/api/kernels/{self.kernel_id}/interrupt',
                 method='POST',
@@ -234,7 +238,7 @@ class JupyterKernel:
             logging.info(f'OUTPUT:\n{ret}')
         return ret
 
-    async def shutdown_async(self):
+    async def shutdown_async(self) -> None:
         if self.kernel_id:
             client = AsyncHTTPClient()
             await client.fetch(
@@ -248,10 +252,10 @@ class JupyterKernel:
 
 
 class ExecuteHandler(tornado.web.RequestHandler):
-    def initialize(self, jupyter_kernel):
+    def initialize(self, jupyter_kernel: JupyterKernel) -> None:
         self.jupyter_kernel = jupyter_kernel
 
-    async def post(self):
+    async def post(self) -> None:
         data = json_decode(self.request.body)
         code = data.get('code')
 
@@ -265,10 +269,10 @@ class ExecuteHandler(tornado.web.RequestHandler):
         self.write(output)
 
 
-def make_app():
+def make_app() -> tornado.web.Application:
     jupyter_kernel = JupyterKernel(
-        f"localhost:{os.environ.get('JUPYTER_GATEWAY_PORT')}",
-        os.environ.get('JUPYTER_GATEWAY_KERNEL_ID'),
+        f"localhost:{os.environ.get('JUPYTER_GATEWAY_PORT', '8888')}",
+        os.environ.get('JUPYTER_GATEWAY_KERNEL_ID', 'default'),
     )
     asyncio.get_event_loop().run_until_complete(jupyter_kernel.initialize())
 

openhands/runtime/plugins/requirement.py

@@ -14,7 +14,7 @@ class Plugin:
     name: str
 
     @abstractmethod
-    async def initialize(self, username: str):
+    async def initialize(self, username: str) -> None:
         """Initialize the plugin."""
         pass
 

openhands/runtime/plugins/vscode/__init__.py

@@ -1,10 +1,12 @@
+import asyncio
 import os
-import subprocess
-import time
 import uuid
 from dataclasses import dataclass
+from typing import Optional
 
 from openhands.core.logger import openhands_logger as logger
+from openhands.events.action import Action
+from openhands.events.observation import Observation
 from openhands.runtime.plugins.requirement import Plugin, PluginRequirement
 from openhands.runtime.utils.system import check_port_available
 from openhands.utils.shutdown_listener import should_continue
@@ -17,10 +19,11 @@ class VSCodeRequirement(PluginRequirement):
 
 class VSCodePlugin(Plugin):
     name: str = 'vscode'
-    vscode_port: int | None = None
-    vscode_connection_token: str | None = None
+    vscode_port: Optional[int] = None
+    vscode_connection_token: Optional[str] = None
+    gateway_process: asyncio.subprocess.Process
 
-    async def initialize(self, username: str):
+    async def initialize(self, username: str) -> None:
         if username not in ['root', 'openhands']:
             self.vscode_port = None
             self.vscode_connection_token = None
@@ -41,22 +44,29 @@ class VSCodePlugin(Plugin):
             'EOF'
         )
 
-        self.gateway_process = subprocess.Popen(
+        # Using asyncio.create_subprocess_shell instead of subprocess.Popen
+        # to avoid ASYNC101 linting error
+        self.gateway_process = await asyncio.create_subprocess_shell(
             cmd,
-            stderr=subprocess.STDOUT,
-            shell=True,
+            stderr=asyncio.subprocess.STDOUT,
+            stdout=asyncio.subprocess.PIPE,
         )
         # read stdout until the kernel gateway is ready
         output = ''
         while should_continue() and self.gateway_process.stdout is not None:
-            line = self.gateway_process.stdout.readline().decode('utf-8')
+            line_bytes = await self.gateway_process.stdout.readline()
+            line = line_bytes.decode('utf-8')
             print(line)
             output += line
             if 'at' in line:
                 break
-            time.sleep(1)
+            await asyncio.sleep(1)
             logger.debug('Waiting for VSCode server to start...')
 
         logger.debug(
             f'VSCode server started at port {self.vscode_port}. Output: {output}'
         )
+
+    async def run(self, action: Action) -> Observation:
+        """Run the plugin for a given action."""
+        raise NotImplementedError('VSCodePlugin does not support run method')

openhands/runtime/utils/runtime_templates/Dockerfile.j2

@@ -62,8 +62,7 @@ ARG RELEASE_ORG="gitpod-io"
 # ARG USER_UID=1000
 # ARG USER_GID=1000
 
-RUN --mount=type=cache,target=/var/cache/wget \
-    if [ -z "${RELEASE_TAG}" ]; then \
+RUN if [ -z "${RELEASE_TAG}" ]; then \
         echo "The RELEASE_TAG build arg must be set." >&2 && \
         exit 1; \
     fi && \
@@ -75,15 +74,12 @@ RUN --mount=type=cache,target=/var/cache/wget \
     elif [ "${arch}" = "armv7l" ]; then \
         arch="armhf"; \
     fi && \
-    cd /var/cache/wget && \
-    if [ ! -f "${RELEASE_TAG}-linux-${arch}.tar.gz" ]; then \
-        wget https://github.com/${RELEASE_ORG}/openvscode-server/releases/download/${RELEASE_TAG}/${RELEASE_TAG}-linux-${arch}.tar.gz ; \
-    fi && \
-    cd - && \
-    tar -xzf /var/cache/wget/${RELEASE_TAG}-linux-${arch}.tar.gz && \
+    wget https://github.com/${RELEASE_ORG}/openvscode-server/releases/download/${RELEASE_TAG}/${RELEASE_TAG}-linux-${arch}.tar.gz && \
+    tar -xzf ${RELEASE_TAG}-linux-${arch}.tar.gz && \
     if [ -d "${OPENVSCODE_SERVER_ROOT}" ]; then rm -rf "${OPENVSCODE_SERVER_ROOT}"; fi && \
     mv ${RELEASE_TAG}-linux-${arch} ${OPENVSCODE_SERVER_ROOT} && \
-    cp ${OPENVSCODE_SERVER_ROOT}/bin/remote-cli/openvscode-server ${OPENVSCODE_SERVER_ROOT}/bin/remote-cli/code
+    cp ${OPENVSCODE_SERVER_ROOT}/bin/remote-cli/openvscode-server ${OPENVSCODE_SERVER_ROOT}/bin/remote-cli/code && \
+    rm -f ${RELEASE_TAG}-linux-${arch}.tar.gz
 
 
 

openhands/server/routes/files.py

@@ -135,6 +135,13 @@ async def select_file(file: str, request: Request):
         return {'code': content}
     elif isinstance(observation, ErrorObservation):
         logger.error(f'Error opening file {file}: {observation}')
+
+        if 'ERROR_BINARY_FILE' in observation.message:
+            return JSONResponse(
+                status_code=status.HTTP_415_UNSUPPORTED_MEDIA_TYPE,
+                content={'error': f'Unable to open binary file: {file}'},
+            )
+
         return JSONResponse(
             status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
             content={'error': f'Error opening file: {observation}'},

poetry.lock

@@ -496,18 +496,18 @@ files = [
 
 [[package]]
 name = "boto3"
-version = "1.37.31"
+version = "1.37.33"
 description = "The AWS SDK for Python"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "boto3-1.37.31-py3-none-any.whl", hash = "sha256:cf8997be0742a5cab9d33a138ef56e423a8ebd8881f6f73e95076b26656b36dc"},
-    {file = "boto3-1.37.31.tar.gz", hash = "sha256:dfee02b2f8f632a239a2f4ba6a2d568e2edd7f7464e9afd8a487fdb3fa9a0ad3"},
+    {file = "boto3-1.37.33-py3-none-any.whl", hash = "sha256:7b1b1bc69762975824e5a5d570880abebf634f7594f88b3dc175e8800f35be1a"},
+    {file = "boto3-1.37.33.tar.gz", hash = "sha256:4390317a1578af73f1514651bd180ba25802dcbe0a23deafa13851d54d3c3203"},
 ]
 
 [package.dependencies]
-botocore = ">=1.37.31,<1.38.0"
+botocore = ">=1.37.33,<1.38.0"
 jmespath = ">=0.7.1,<2.0.0"
 s3transfer = ">=0.11.0,<0.12.0"
 
@@ -516,14 +516,14 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"]
 
 [[package]]
 name = "boto3-stubs"
-version = "1.37.31"
-description = "Type annotations for boto3 1.37.31 generated with mypy-boto3-builder 8.10.1"
+version = "1.37.33"
+description = "Type annotations for boto3 1.37.33 generated with mypy-boto3-builder 8.10.1"
 optional = false
 python-versions = ">=3.8"
 groups = ["evaluation"]
 files = [
-    {file = "boto3_stubs-1.37.31-py3-none-any.whl", hash = "sha256:356d5af1e3d8aba5d8068492f11426ee9f41d0a799c099ec548be13462337632"},
-    {file = "boto3_stubs-1.37.31.tar.gz", hash = "sha256:ab2e8f7877fddb97f50f4712f3e6ffafa0b20fbc6a1ac7019400d3b2261936cb"},
+    {file = "boto3_stubs-1.37.33-py3-none-any.whl", hash = "sha256:b811b9c99bb47300efead119af7cfc4496545b9e571dde62e7447901966e74f8"},
+    {file = "boto3_stubs-1.37.33.tar.gz", hash = "sha256:d0561aadb98fa4ecffd34f34c3b8be3abd0a0e5de1367f7d3e985eb4de904c5b"},
 ]
 
 [package.dependencies]
@@ -579,7 +579,7 @@ bedrock-data-automation-runtime = ["mypy-boto3-bedrock-data-automation-runtime (
 bedrock-runtime = ["mypy-boto3-bedrock-runtime (>=1.37.0,<1.38.0)"]
 billing = ["mypy-boto3-billing (>=1.37.0,<1.38.0)"]
 billingconductor = ["mypy-boto3-billingconductor (>=1.37.0,<1.38.0)"]
-boto3 = ["boto3 (==1.37.31)"]
+boto3 = ["boto3 (==1.37.33)"]
 braket = ["mypy-boto3-braket (>=1.37.0,<1.38.0)"]
 budgets = ["mypy-boto3-budgets (>=1.37.0,<1.38.0)"]
 ce = ["mypy-boto3-ce (>=1.37.0,<1.38.0)"]
@@ -943,14 +943,14 @@ xray = ["mypy-boto3-xray (>=1.37.0,<1.38.0)"]
 
 [[package]]
 name = "botocore"
-version = "1.37.31"
+version = "1.37.33"
 description = "Low-level, data-driven core of boto 3."
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "botocore-1.37.31-py3-none-any.whl", hash = "sha256:598a33a7a0e5a014bd1416c999a0b9c634fbbba3d1363e2368e6a92da4544df4"},
-    {file = "botocore-1.37.31.tar.gz", hash = "sha256:eb3dfa44a87187bd82c3b493d568d8436270d4d000f237b49b669a01fcd8a21c"},
+    {file = "botocore-1.37.33-py3-none-any.whl", hash = "sha256:4a167dfecae51e9140de24067de1c339acde5ade3dad524a4600ac2c72055e23"},
+    {file = "botocore-1.37.33.tar.gz", hash = "sha256:09b213b0d0500040f85c7daee912ea767c724e43ed61909e624c803ff6925222"},
 ]
 
 [package.dependencies]
@@ -1781,14 +1781,14 @@ urllib3 = ">=1.25.3,<3.0.0"
 
 [[package]]
 name = "daytona-sdk"
-version = "0.12.1"
+version = "0.13.1"
 description = "Python SDK for Daytona"
 optional = false
 python-versions = ">=3.7"
 groups = ["main"]
 files = [
-    {file = "daytona_sdk-0.12.1-py3-none-any.whl", hash = "sha256:2f7b884a3dbeb237f7d1aa7ec2ad6715eb1389e43ffc69e917ffadbd7eb09c30"},
-    {file = "daytona_sdk-0.12.1.tar.gz", hash = "sha256:133ca80ad192702d01934b44377b21fe11e8262748445a47cebbf3b9a2605307"},
+    {file = "daytona_sdk-0.13.1-py3-none-any.whl", hash = "sha256:9c51429d6f7a22310d5ab79629e8ac6ef85a9263aa496c99f78ae118c9fd3085"},
+    {file = "daytona_sdk-0.13.1.tar.gz", hash = "sha256:42d84e3b134f857e117c5d54a85d3eeae45043e9e136015f45a432689e1c3604"},
 ]
 
 [package.dependencies]
@@ -2662,7 +2662,7 @@ grpcio = {version = ">=1.49.1,<2.0dev", optional = true, markers = "python_versi
 grpcio-status = {version = ">=1.49.1,<2.0.dev0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""}
 proto-plus = [
     {version = ">=1.25.0,<2.0.0dev", markers = "python_version >= \"3.13\""},
-    {version = ">=1.22.3,<2.0.0dev", markers = "python_version < \"3.13\""},
+    {version = ">=1.22.3,<2.0.0dev"},
 ]
 protobuf = ">=3.19.5,<3.20.0 || >3.20.0,<3.20.1 || >3.20.1,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<6.0.0.dev0"
 requests = ">=2.18.0,<3.0.0.dev0"
@@ -2675,14 +2675,14 @@ grpcio-gcp = ["grpcio-gcp (>=0.2.2,<1.0.dev0)"]
 
 [[package]]
 name = "google-api-python-client"
-version = "2.166.0"
+version = "2.167.0"
 description = "Google API Client Library for Python"
 optional = false
 python-versions = ">=3.7"
 groups = ["main"]
 files = [
-    {file = "google_api_python_client-2.166.0-py2.py3-none-any.whl", hash = "sha256:dd8cc74d9fc18538ab05cbd2e93cb4f82382f910c5f6945db06c91f1deae6e45"},
-    {file = "google_api_python_client-2.166.0.tar.gz", hash = "sha256:b8cf843bd9d736c134aef76cf1dc7a47c9283a2ef24267b97207b9dd43b30ef7"},
+    {file = "google_api_python_client-2.167.0-py2.py3-none-any.whl", hash = "sha256:ce25290cc229505d770ca5c8d03850e0ae87d8e998fc6dd743ecece018baa396"},
+    {file = "google_api_python_client-2.167.0.tar.gz", hash = "sha256:a458d402572e1c2caf9db090d8e7b270f43ff326bd9349c731a86b19910e3995"},
 ]
 
 [package.dependencies]
@@ -2876,7 +2876,7 @@ google-auth = ">=2.14.1,<2.24.0 || >2.24.0,<2.25.0 || >2.25.0,<3.0.0dev"
 grpc-google-iam-v1 = ">=0.14.0,<1.0.0dev"
 proto-plus = [
     {version = ">=1.25.0,<2.0.0dev", markers = "python_version >= \"3.13\""},
-    {version = ">=1.22.3,<2.0.0dev"},
+    {version = ">=1.22.3,<2.0.0dev", markers = "python_version < \"3.13\""},
 ]
 protobuf = ">=3.20.2,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<6.0.0dev"
 
@@ -3809,14 +3809,14 @@ files = [
 
 [[package]]
 name = "json-repair"
-version = "0.41.0"
+version = "0.41.1"
 description = "A package to repair broken json strings"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "json_repair-0.41.0-py3-none-any.whl", hash = "sha256:e3be820988fa210fe046e54c8475eafa9e069f1b85d67725f842eb00d1b61f21"},
-    {file = "json_repair-0.41.0.tar.gz", hash = "sha256:c9ee227d949d5da463024942b715e0e331f9f96cb7377e2f85a661b21596c50b"},
+    {file = "json_repair-0.41.1-py3-none-any.whl", hash = "sha256:0e181fd43a696887881fe19fed23422a54b3e4c558b6ff27a86a8c3ddde9ae79"},
+    {file = "json_repair-0.41.1.tar.gz", hash = "sha256:bba404b0888c84a6b86ecc02ec43b71b673cfee463baf6da94e079c55b136565"},
 ]
 
 [[package]]
@@ -4428,14 +4428,14 @@ types-tqdm = "*"
 
 [[package]]
 name = "litellm"
-version = "1.65.5"
+version = "1.66.0"
 description = "Library to easily interface with LLM API providers"
 optional = false
 python-versions = "!=2.7.*,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,!=3.7.*,>=3.8"
 groups = ["main"]
 files = [
-    {file = "litellm-1.65.5-py3-none-any.whl", hash = "sha256:ed954ec575cc1c468418e705fe922c827591dc01c1204abd4caf9c7572c73b5c"},
-    {file = "litellm-1.65.5.tar.gz", hash = "sha256:f8b1e0800ad66a2029c21a3e37456dedf4d1391da2ef5860f0e22268f1557c7c"},
+    {file = "litellm-1.66.0-py3-none-any.whl", hash = "sha256:1e4a2a9e023b12a385e4283b2f7922f7bd9c15b93ee9e64e203333cf8ddbc895"},
+    {file = "litellm-1.66.0.tar.gz", hash = "sha256:15f592bab604233083dc8b79e1e510e7e234f06525efe4c4255732bfc7ceb219"},
 ]
 
 [package.dependencies]
@@ -4453,7 +4453,7 @@ tokenizers = "*"
 
 [package.extras]
 extra-proxy = ["azure-identity (>=1.15.0,<2.0.0)", "azure-keyvault-secrets (>=4.8.0,<5.0.0)", "google-cloud-kms (>=2.21.3,<3.0.0)", "prisma (==0.11.0)", "redisvl (>=0.4.1,<0.5.0) ; python_version >= \"3.9\" and python_version < \"3.14\"", "resend (>=0.8.0,<0.9.0)"]
-proxy = ["PyJWT (>=2.8.0,<3.0.0)", "apscheduler (>=3.10.4,<4.0.0)", "backoff", "boto3 (==1.34.34)", "cryptography (>=43.0.1,<44.0.0)", "fastapi (>=0.115.5,<0.116.0)", "fastapi-sso (>=0.16.0,<0.17.0)", "gunicorn (>=23.0.0,<24.0.0)", "litellm-proxy-extras (==0.1.3)", "mcp (==1.5.0) ; python_version >= \"3.10\"", "orjson (>=3.9.7,<4.0.0)", "pynacl (>=1.5.0,<2.0.0)", "python-multipart (>=0.0.18,<0.0.19)", "pyyaml (>=6.0.1,<7.0.0)", "rq", "uvicorn (>=0.29.0,<0.30.0)", "uvloop (>=0.21.0,<0.22.0)", "websockets (>=13.1.0,<14.0.0)"]
+proxy = ["PyJWT (>=2.8.0,<3.0.0)", "apscheduler (>=3.10.4,<4.0.0)", "backoff", "boto3 (==1.34.34)", "cryptography (>=43.0.1,<44.0.0)", "fastapi (>=0.115.5,<0.116.0)", "fastapi-sso (>=0.16.0,<0.17.0)", "gunicorn (>=23.0.0,<24.0.0)", "litellm-proxy-extras (==0.1.7)", "mcp (==1.5.0) ; python_version >= \"3.10\"", "orjson (>=3.9.7,<4.0.0)", "pynacl (>=1.5.0,<2.0.0)", "python-multipart (>=0.0.18,<0.0.19)", "pyyaml (>=6.0.1,<7.0.0)", "rq", "uvicorn (>=0.29.0,<0.30.0)", "uvloop (>=0.21.0,<0.22.0)", "websockets (>=13.1.0,<14.0.0)"]
 
 [[package]]
 name = "lxml"
@@ -4898,14 +4898,14 @@ files = [
 
 [[package]]
 name = "modal"
-version = "0.73.159"
+version = "0.73.170"
 description = "Python client library for Modal"
 optional = false
 python-versions = ">=3.9"
 groups = ["main", "evaluation"]
 files = [
-    {file = "modal-0.73.159-py3-none-any.whl", hash = "sha256:2363729caaaa4475eba6e0dce90b759fa8a37c82845de5333e9e18eabc52c5c7"},
-    {file = "modal-0.73.159.tar.gz", hash = "sha256:4c9a5f7d37a343420334d4b8436034c75ee47d0976f6677fe52f7c68ea9d32b6"},
+    {file = "modal-0.73.170-py3-none-any.whl", hash = "sha256:d3b9eab82c823c69604fdfd18e970c4b65c76b3aa82f60019e608d4d3166224f"},
+    {file = "modal-0.73.170.tar.gz", hash = "sha256:4df2405efa1a6d41fa42da675516bfdfc14fedb26f1ea905f3e7c49addc355f5"},
 ]
 
 [package.dependencies]
@@ -5276,7 +5276,7 @@ version = "3.4.2"
 description = "Python package for creating and manipulating graphs and networks"
 optional = false
 python-versions = ">=3.10"
-groups = ["main", "evaluation"]
+groups = ["evaluation"]
 files = [
     {file = "networkx-3.4.2-py3-none-any.whl", hash = "sha256:df5d4365b724cf81b8c6a7312509d0c22386097011ad1abe274afd5e9d3bbc5f"},
     {file = "networkx-3.4.2.tar.gz", hash = "sha256:307c3669428c5362aab27c8a1260aa8f47c4e91d3891f48be0141738d8d053e1"},
@@ -5622,14 +5622,14 @@ signedtoken = ["cryptography (>=3.0.0)", "pyjwt (>=2.0.0,<3)"]
 
 [[package]]
 name = "openai"
-version = "1.72.0"
+version = "1.73.0"
 description = "The official Python library for the openai API"
 optional = false
 python-versions = ">=3.8"
 groups = ["main", "evaluation", "test"]
 files = [
-    {file = "openai-1.72.0-py3-none-any.whl", hash = "sha256:34f5496ba5c8cb06c592831d69e847e2d164526a2fb92afdc3b5cf2891c328c3"},
-    {file = "openai-1.72.0.tar.gz", hash = "sha256:f51de971448905cc90ed5175a5b19e92fd94e31f68cde4025762f9f5257150db"},
+    {file = "openai-1.73.0-py3-none-any.whl", hash = "sha256:f52d1f673fb4ce6069a40d544a80fcb062eba1b3f489004fac4f9923a074c425"},
+    {file = "openai-1.73.0.tar.gz", hash = "sha256:b58ea39ba589de07db85c9905557ac12d2fc77600dcd2b92a08b99c9a3dce9e0"},
 ]
 
 [package.dependencies]
@@ -5649,14 +5649,14 @@ voice-helpers = ["numpy (>=2.0.2)", "sounddevice (>=0.5.1)"]
 
 [[package]]
 name = "openhands-aci"
-version = "0.2.8"
+version = "0.2.10"
 description = "An Agent-Computer Interface (ACI) designed for software development agents OpenHands."
 optional = false
 python-versions = "<4.0,>=3.12"
 groups = ["main"]
 files = [
-    {file = "openhands_aci-0.2.8-py3-none-any.whl", hash = "sha256:20df3a846f663bd86d6c73253ef990aa701f8db4595b75fda19a2d7861cf0514"},
-    {file = "openhands_aci-0.2.8.tar.gz", hash = "sha256:557b81ccabbe3df4bb163ad8e941796bd5d61aeb07833ed02931197ab472e71e"},
+    {file = "openhands_aci-0.2.10-py3-none-any.whl", hash = "sha256:0703eb117e24326d80d990b81a0c71e28a364f56999095b95c146c934e40fc55"},
+    {file = "openhands_aci-0.2.10.tar.gz", hash = "sha256:a5e6bf46cbd9a99c5c592548419a9a3b3091c4e82f0227e8aaf470b18a261cc9"},
 ]
 
 [package.dependencies]
@@ -5666,11 +5666,7 @@ charset-normalizer = ">=3.4.1,<4.0.0"
 flake8 = "*"
 gitpython = "*"
 grep-ast = "0.3.3"
-litellm = "*"
-networkx = "*"
-numpy = "*"
-pandas = "*"
-scipy = "*"
+pydantic = ">=2.11.3,<3.0.0"
 tree-sitter = ">=0.24.0,<0.25.0"
 tree-sitter-javascript = ">=0.23.1,<0.24.0"
 tree-sitter-python = ">=0.23.6,<0.24.0"
@@ -5807,7 +5803,7 @@ version = "2.2.3"
 description = "Powerful data structures for data analysis, time series, and statistics"
 optional = false
 python-versions = ">=3.9"
-groups = ["main", "evaluation", "test"]
+groups = ["evaluation", "test"]
 files = [
     {file = "pandas-2.2.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1948ddde24197a0f7add2bdc4ca83bf2b1ef84a1bc8ccffd95eda17fd836ecb5"},
     {file = "pandas-2.2.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:381175499d3802cde0eabbaf6324cce0c4f5d52ca6f8c377c29ad442f50f6348"},
@@ -6527,20 +6523,21 @@ files = [
 
 [[package]]
 name = "pydantic"
-version = "2.10.6"
+version = "2.11.3"
 description = "Data validation using Python type hints"
 optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.9"
 groups = ["main", "evaluation", "test"]
 files = [
-    {file = "pydantic-2.10.6-py3-none-any.whl", hash = "sha256:427d664bf0b8a2b34ff5dd0f5a18df00591adcee7198fbd71981054cef37b584"},
-    {file = "pydantic-2.10.6.tar.gz", hash = "sha256:ca5daa827cce33de7a42be142548b0096bf05a7e7b365aebfa5f8eeec7128236"},
+    {file = "pydantic-2.11.3-py3-none-any.whl", hash = "sha256:a082753436a07f9ba1289c6ffa01cd93db3548776088aa917cc43b63f68fa60f"},
+    {file = "pydantic-2.11.3.tar.gz", hash = "sha256:7471657138c16adad9322fe3070c0116dd6c3ad8d649300e3cbdfe91f4db4ec3"},
 ]
 
 [package.dependencies]
 annotated-types = ">=0.6.0"
-pydantic-core = "2.27.2"
+pydantic-core = "2.33.1"
 typing-extensions = ">=4.12.2"
+typing-inspection = ">=0.4.0"
 
 [package.extras]
 email = ["email-validator (>=2.0.0)"]
@@ -6548,112 +6545,111 @@ timezone = ["tzdata ; python_version >= \"3.9\" and platform_system == \"Windows
 
 [[package]]
 name = "pydantic-core"
-version = "2.27.2"
+version = "2.33.1"
 description = "Core functionality for Pydantic validation and serialization"
 optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.9"
 groups = ["main", "evaluation", "test"]
 files = [
-    {file = "pydantic_core-2.27.2-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:2d367ca20b2f14095a8f4fa1210f5a7b78b8a20009ecced6b12818f455b1e9fa"},
-    {file = "pydantic_core-2.27.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:491a2b73db93fab69731eaee494f320faa4e093dbed776be1a829c2eb222c34c"},
-    {file = "pydantic_core-2.27.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7969e133a6f183be60e9f6f56bfae753585680f3b7307a8e555a948d443cc05a"},
-    {file = "pydantic_core-2.27.2-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:3de9961f2a346257caf0aa508a4da705467f53778e9ef6fe744c038119737ef5"},
-    {file = "pydantic_core-2.27.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e2bb4d3e5873c37bb3dd58714d4cd0b0e6238cebc4177ac8fe878f8b3aa8e74c"},
-    {file = "pydantic_core-2.27.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:280d219beebb0752699480fe8f1dc61ab6615c2046d76b7ab7ee38858de0a4e7"},
-    {file = "pydantic_core-2.27.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47956ae78b6422cbd46f772f1746799cbb862de838fd8d1fbd34a82e05b0983a"},
-    {file = "pydantic_core-2.27.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:14d4a5c49d2f009d62a2a7140d3064f686d17a5d1a268bc641954ba181880236"},
-    {file = "pydantic_core-2.27.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:337b443af21d488716f8d0b6164de833e788aa6bd7e3a39c005febc1284f4962"},
-    {file = "pydantic_core-2.27.2-cp310-cp310-musllinux_1_1_armv7l.whl", hash = "sha256:03d0f86ea3184a12f41a2d23f7ccb79cdb5a18e06993f8a45baa8dfec746f0e9"},
-    {file = "pydantic_core-2.27.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:7041c36f5680c6e0f08d922aed302e98b3745d97fe1589db0a3eebf6624523af"},
-    {file = "pydantic_core-2.27.2-cp310-cp310-win32.whl", hash = "sha256:50a68f3e3819077be2c98110c1f9dcb3817e93f267ba80a2c05bb4f8799e2ff4"},
-    {file = "pydantic_core-2.27.2-cp310-cp310-win_amd64.whl", hash = "sha256:e0fd26b16394ead34a424eecf8a31a1f5137094cabe84a1bcb10fa6ba39d3d31"},
-    {file = "pydantic_core-2.27.2-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:8e10c99ef58cfdf2a66fc15d66b16c4a04f62bca39db589ae8cba08bc55331bc"},
-    {file = "pydantic_core-2.27.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:26f32e0adf166a84d0cb63be85c562ca8a6fa8de28e5f0d92250c6b7e9e2aff7"},
-    {file = "pydantic_core-2.27.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8c19d1ea0673cd13cc2f872f6c9ab42acc4e4f492a7ca9d3795ce2b112dd7e15"},
-    {file = "pydantic_core-2.27.2-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:5e68c4446fe0810e959cdff46ab0a41ce2f2c86d227d96dc3847af0ba7def306"},
-    {file = "pydantic_core-2.27.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d9640b0059ff4f14d1f37321b94061c6db164fbe49b334b31643e0528d100d99"},
-    {file = "pydantic_core-2.27.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:40d02e7d45c9f8af700f3452f329ead92da4c5f4317ca9b896de7ce7199ea459"},
-    {file = "pydantic_core-2.27.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1c1fd185014191700554795c99b347d64f2bb637966c4cfc16998a0ca700d048"},
-    {file = "pydantic_core-2.27.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d81d2068e1c1228a565af076598f9e7451712700b673de8f502f0334f281387d"},
-    {file = "pydantic_core-2.27.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:1a4207639fb02ec2dbb76227d7c751a20b1a6b4bc52850568e52260cae64ca3b"},
-    {file = "pydantic_core-2.27.2-cp311-cp311-musllinux_1_1_armv7l.whl", hash = "sha256:3de3ce3c9ddc8bbd88f6e0e304dea0e66d843ec9de1b0042b0911c1663ffd474"},
-    {file = "pydantic_core-2.27.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:30c5f68ded0c36466acede341551106821043e9afaad516adfb6e8fa80a4e6a6"},
-    {file = "pydantic_core-2.27.2-cp311-cp311-win32.whl", hash = "sha256:c70c26d2c99f78b125a3459f8afe1aed4d9687c24fd677c6a4436bc042e50d6c"},
-    {file = "pydantic_core-2.27.2-cp311-cp311-win_amd64.whl", hash = "sha256:08e125dbdc505fa69ca7d9c499639ab6407cfa909214d500897d02afb816e7cc"},
-    {file = "pydantic_core-2.27.2-cp311-cp311-win_arm64.whl", hash = "sha256:26f0d68d4b235a2bae0c3fc585c585b4ecc51382db0e3ba402a22cbc440915e4"},
-    {file = "pydantic_core-2.27.2-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:9e0c8cfefa0ef83b4da9588448b6d8d2a2bf1a53c3f1ae5fca39eb3061e2f0b0"},
-    {file = "pydantic_core-2.27.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:83097677b8e3bd7eaa6775720ec8e0405f1575015a463285a92bfdfe254529ef"},
-    {file = "pydantic_core-2.27.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:172fce187655fece0c90d90a678424b013f8fbb0ca8b036ac266749c09438cb7"},
-    {file = "pydantic_core-2.27.2-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:519f29f5213271eeeeb3093f662ba2fd512b91c5f188f3bb7b27bc5973816934"},
-    {file = "pydantic_core-2.27.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:05e3a55d124407fffba0dd6b0c0cd056d10e983ceb4e5dbd10dda135c31071d6"},
-    {file = "pydantic_core-2.27.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9c3ed807c7b91de05e63930188f19e921d1fe90de6b4f5cd43ee7fcc3525cb8c"},
-    {file = "pydantic_core-2.27.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6fb4aadc0b9a0c063206846d603b92030eb6f03069151a625667f982887153e2"},
-    {file = "pydantic_core-2.27.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:28ccb213807e037460326424ceb8b5245acb88f32f3d2777427476e1b32c48c4"},
-    {file = "pydantic_core-2.27.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:de3cd1899e2c279b140adde9357c4495ed9d47131b4a4eaff9052f23398076b3"},
-    {file = "pydantic_core-2.27.2-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:220f892729375e2d736b97d0e51466252ad84c51857d4d15f5e9692f9ef12be4"},
-    {file = "pydantic_core-2.27.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:a0fcd29cd6b4e74fe8ddd2c90330fd8edf2e30cb52acda47f06dd615ae72da57"},
-    {file = "pydantic_core-2.27.2-cp312-cp312-win32.whl", hash = "sha256:1e2cb691ed9834cd6a8be61228471d0a503731abfb42f82458ff27be7b2186fc"},
-    {file = "pydantic_core-2.27.2-cp312-cp312-win_amd64.whl", hash = "sha256:cc3f1a99a4f4f9dd1de4fe0312c114e740b5ddead65bb4102884b384c15d8bc9"},
-    {file = "pydantic_core-2.27.2-cp312-cp312-win_arm64.whl", hash = "sha256:3911ac9284cd8a1792d3cb26a2da18f3ca26c6908cc434a18f730dc0db7bfa3b"},
-    {file = "pydantic_core-2.27.2-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:7d14bd329640e63852364c306f4d23eb744e0f8193148d4044dd3dacdaacbd8b"},
-    {file = "pydantic_core-2.27.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:82f91663004eb8ed30ff478d77c4d1179b3563df6cdb15c0817cd1cdaf34d154"},
-    {file = "pydantic_core-2.27.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:71b24c7d61131bb83df10cc7e687433609963a944ccf45190cfc21e0887b08c9"},
-    {file = "pydantic_core-2.27.2-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:fa8e459d4954f608fa26116118bb67f56b93b209c39b008277ace29937453dc9"},
-    {file = "pydantic_core-2.27.2-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ce8918cbebc8da707ba805b7fd0b382816858728ae7fe19a942080c24e5b7cd1"},
-    {file = "pydantic_core-2.27.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:eda3f5c2a021bbc5d976107bb302e0131351c2ba54343f8a496dc8783d3d3a6a"},
-    {file = "pydantic_core-2.27.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bd8086fa684c4775c27f03f062cbb9eaa6e17f064307e86b21b9e0abc9c0f02e"},
-    {file = "pydantic_core-2.27.2-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:8d9b3388db186ba0c099a6d20f0604a44eabdeef1777ddd94786cdae158729e4"},
-    {file = "pydantic_core-2.27.2-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:7a66efda2387de898c8f38c0cf7f14fca0b51a8ef0b24bfea5849f1b3c95af27"},
-    {file = "pydantic_core-2.27.2-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:18a101c168e4e092ab40dbc2503bdc0f62010e95d292b27827871dc85450d7ee"},
-    {file = "pydantic_core-2.27.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:ba5dd002f88b78a4215ed2f8ddbdf85e8513382820ba15ad5ad8955ce0ca19a1"},
-    {file = "pydantic_core-2.27.2-cp313-cp313-win32.whl", hash = "sha256:1ebaf1d0481914d004a573394f4be3a7616334be70261007e47c2a6fe7e50130"},
-    {file = "pydantic_core-2.27.2-cp313-cp313-win_amd64.whl", hash = "sha256:953101387ecf2f5652883208769a79e48db18c6df442568a0b5ccd8c2723abee"},
-    {file = "pydantic_core-2.27.2-cp313-cp313-win_arm64.whl", hash = "sha256:ac4dbfd1691affb8f48c2c13241a2e3b60ff23247cbcf981759c768b6633cf8b"},
-    {file = "pydantic_core-2.27.2-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:d3e8d504bdd3f10835468f29008d72fc8359d95c9c415ce6e767203db6127506"},
-    {file = "pydantic_core-2.27.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:521eb9b7f036c9b6187f0b47318ab0d7ca14bd87f776240b90b21c1f4f149320"},
-    {file = "pydantic_core-2.27.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:85210c4d99a0114f5a9481b44560d7d1e35e32cc5634c656bc48e590b669b145"},
-    {file = "pydantic_core-2.27.2-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d716e2e30c6f140d7560ef1538953a5cd1a87264c737643d481f2779fc247fe1"},
-    {file = "pydantic_core-2.27.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f66d89ba397d92f840f8654756196d93804278457b5fbede59598a1f9f90b228"},
-    {file = "pydantic_core-2.27.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:669e193c1c576a58f132e3158f9dfa9662969edb1a250c54d8fa52590045f046"},
-    {file = "pydantic_core-2.27.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9fdbe7629b996647b99c01b37f11170a57ae675375b14b8c13b8518b8320ced5"},
-    {file = "pydantic_core-2.27.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d262606bf386a5ba0b0af3b97f37c83d7011439e3dc1a9298f21efb292e42f1a"},
-    {file = "pydantic_core-2.27.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:cabb9bcb7e0d97f74df8646f34fc76fbf793b7f6dc2438517d7a9e50eee4f14d"},
-    {file = "pydantic_core-2.27.2-cp38-cp38-musllinux_1_1_armv7l.whl", hash = "sha256:d2d63f1215638d28221f664596b1ccb3944f6e25dd18cd3b86b0a4c408d5ebb9"},
-    {file = "pydantic_core-2.27.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:bca101c00bff0adb45a833f8451b9105d9df18accb8743b08107d7ada14bd7da"},
-    {file = "pydantic_core-2.27.2-cp38-cp38-win32.whl", hash = "sha256:f6f8e111843bbb0dee4cb6594cdc73e79b3329b526037ec242a3e49012495b3b"},
-    {file = "pydantic_core-2.27.2-cp38-cp38-win_amd64.whl", hash = "sha256:fd1aea04935a508f62e0d0ef1f5ae968774a32afc306fb8545e06f5ff5cdf3ad"},
-    {file = "pydantic_core-2.27.2-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:c10eb4f1659290b523af58fa7cffb452a61ad6ae5613404519aee4bfbf1df993"},
-    {file = "pydantic_core-2.27.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:ef592d4bad47296fb11f96cd7dc898b92e795032b4894dfb4076cfccd43a9308"},
-    {file = "pydantic_core-2.27.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c61709a844acc6bf0b7dce7daae75195a10aac96a596ea1b776996414791ede4"},
-    {file = "pydantic_core-2.27.2-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:42c5f762659e47fdb7b16956c71598292f60a03aa92f8b6351504359dbdba6cf"},
-    {file = "pydantic_core-2.27.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4c9775e339e42e79ec99c441d9730fccf07414af63eac2f0e48e08fd38a64d76"},
-    {file = "pydantic_core-2.27.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:57762139821c31847cfb2df63c12f725788bd9f04bc2fb392790959b8f70f118"},
-    {file = "pydantic_core-2.27.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0d1e85068e818c73e048fe28cfc769040bb1f475524f4745a5dc621f75ac7630"},
-    {file = "pydantic_core-2.27.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:097830ed52fd9e427942ff3b9bc17fab52913b2f50f2880dc4a5611446606a54"},
-    {file = "pydantic_core-2.27.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:044a50963a614ecfae59bb1eaf7ea7efc4bc62f49ed594e18fa1e5d953c40e9f"},
-    {file = "pydantic_core-2.27.2-cp39-cp39-musllinux_1_1_armv7l.whl", hash = "sha256:4e0b4220ba5b40d727c7f879eac379b822eee5d8fff418e9d3381ee45b3b0362"},
-    {file = "pydantic_core-2.27.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:5e4f4bb20d75e9325cc9696c6802657b58bc1dbbe3022f32cc2b2b632c3fbb96"},
-    {file = "pydantic_core-2.27.2-cp39-cp39-win32.whl", hash = "sha256:cca63613e90d001b9f2f9a9ceb276c308bfa2a43fafb75c8031c4f66039e8c6e"},
-    {file = "pydantic_core-2.27.2-cp39-cp39-win_amd64.whl", hash = "sha256:77d1bca19b0f7021b3a982e6f903dcd5b2b06076def36a652e3907f596e29f67"},
-    {file = "pydantic_core-2.27.2-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:2bf14caea37e91198329b828eae1618c068dfb8ef17bb33287a7ad4b61ac314e"},
-    {file = "pydantic_core-2.27.2-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:b0cb791f5b45307caae8810c2023a184c74605ec3bcbb67d13846c28ff731ff8"},
-    {file = "pydantic_core-2.27.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:688d3fd9fcb71f41c4c015c023d12a79d1c4c0732ec9eb35d96e3388a120dcf3"},
-    {file = "pydantic_core-2.27.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3d591580c34f4d731592f0e9fe40f9cc1b430d297eecc70b962e93c5c668f15f"},
-    {file = "pydantic_core-2.27.2-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:82f986faf4e644ffc189a7f1aafc86e46ef70372bb153e7001e8afccc6e54133"},
-    {file = "pydantic_core-2.27.2-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:bec317a27290e2537f922639cafd54990551725fc844249e64c523301d0822fc"},
-    {file = "pydantic_core-2.27.2-pp310-pypy310_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:0296abcb83a797db256b773f45773da397da75a08f5fcaef41f2044adec05f50"},
-    {file = "pydantic_core-2.27.2-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:0d75070718e369e452075a6017fbf187f788e17ed67a3abd47fa934d001863d9"},
-    {file = "pydantic_core-2.27.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:7e17b560be3c98a8e3aa66ce828bdebb9e9ac6ad5466fba92eb74c4c95cb1151"},
-    {file = "pydantic_core-2.27.2-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:c33939a82924da9ed65dab5a65d427205a73181d8098e79b6b426bdf8ad4e656"},
-    {file = "pydantic_core-2.27.2-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:00bad2484fa6bda1e216e7345a798bd37c68fb2d97558edd584942aa41b7d278"},
-    {file = "pydantic_core-2.27.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c817e2b40aba42bac6f457498dacabc568c3b7a986fc9ba7c8d9d260b71485fb"},
-    {file = "pydantic_core-2.27.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:251136cdad0cb722e93732cb45ca5299fb56e1344a833640bf93b2803f8d1bfd"},
-    {file = "pydantic_core-2.27.2-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d2088237af596f0a524d3afc39ab3b036e8adb054ee57cbb1dcf8e09da5b29cc"},
-    {file = "pydantic_core-2.27.2-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:d4041c0b966a84b4ae7a09832eb691a35aec90910cd2dbe7a208de59be77965b"},
-    {file = "pydantic_core-2.27.2-pp39-pypy39_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:8083d4e875ebe0b864ffef72a4304827015cff328a1be6e22cc850753bfb122b"},
-    {file = "pydantic_core-2.27.2-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:f141ee28a0ad2123b6611b6ceff018039df17f32ada8b534e6aa039545a3efb2"},
-    {file = "pydantic_core-2.27.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:7d0c8399fcc1848491f00e0314bd59fb34a9c008761bcb422a057670c3f65e35"},
-    {file = "pydantic_core-2.27.2.tar.gz", hash = "sha256:eb026e5a4c1fee05726072337ff51d1efb6f59090b7da90d30ea58625b1ffb39"},
+    {file = "pydantic_core-2.33.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:3077cfdb6125cc8dab61b155fdd714663e401f0e6883f9632118ec12cf42df26"},
+    {file = "pydantic_core-2.33.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8ffab8b2908d152e74862d276cf5017c81a2f3719f14e8e3e8d6b83fda863927"},
+    {file = "pydantic_core-2.33.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5183e4f6a2d468787243ebcd70cf4098c247e60d73fb7d68d5bc1e1beaa0c4db"},
+    {file = "pydantic_core-2.33.1-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:398a38d323f37714023be1e0285765f0a27243a8b1506b7b7de87b647b517e48"},
+    {file = "pydantic_core-2.33.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:87d3776f0001b43acebfa86f8c64019c043b55cc5a6a2e313d728b5c95b46969"},
+    {file = "pydantic_core-2.33.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c566dd9c5f63d22226409553531f89de0cac55397f2ab8d97d6f06cfce6d947e"},
+    {file = "pydantic_core-2.33.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a0d5f3acc81452c56895e90643a625302bd6be351e7010664151cc55b7b97f89"},
+    {file = "pydantic_core-2.33.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d3a07fadec2a13274a8d861d3d37c61e97a816beae717efccaa4b36dfcaadcde"},
+    {file = "pydantic_core-2.33.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:f99aeda58dce827f76963ee87a0ebe75e648c72ff9ba1174a253f6744f518f65"},
+    {file = "pydantic_core-2.33.1-cp310-cp310-musllinux_1_1_armv7l.whl", hash = "sha256:902dbc832141aa0ec374f4310f1e4e7febeebc3256f00dc359a9ac3f264a45dc"},
+    {file = "pydantic_core-2.33.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:fe44d56aa0b00d66640aa84a3cbe80b7a3ccdc6f0b1ca71090696a6d4777c091"},
+    {file = "pydantic_core-2.33.1-cp310-cp310-win32.whl", hash = "sha256:ed3eb16d51257c763539bde21e011092f127a2202692afaeaccb50db55a31383"},
+    {file = "pydantic_core-2.33.1-cp310-cp310-win_amd64.whl", hash = "sha256:694ad99a7f6718c1a498dc170ca430687a39894a60327f548e02a9c7ee4b6504"},
+    {file = "pydantic_core-2.33.1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:6e966fc3caaf9f1d96b349b0341c70c8d6573bf1bac7261f7b0ba88f96c56c24"},
+    {file = "pydantic_core-2.33.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:bfd0adeee563d59c598ceabddf2c92eec77abcb3f4a391b19aa7366170bd9e30"},
+    {file = "pydantic_core-2.33.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:91815221101ad3c6b507804178a7bb5cb7b2ead9ecd600041669c8d805ebd595"},
+    {file = "pydantic_core-2.33.1-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:9fea9c1869bb4742d174a57b4700c6dadea951df8b06de40c2fedb4f02931c2e"},
+    {file = "pydantic_core-2.33.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1d20eb4861329bb2484c021b9d9a977566ab16d84000a57e28061151c62b349a"},
+    {file = "pydantic_core-2.33.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0fb935c5591573ae3201640579f30128ccc10739b45663f93c06796854405505"},
+    {file = "pydantic_core-2.33.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c964fd24e6166420d18fb53996d8c9fd6eac9bf5ae3ec3d03015be4414ce497f"},
+    {file = "pydantic_core-2.33.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:681d65e9011f7392db5aa002b7423cc442d6a673c635668c227c6c8d0e5a4f77"},
+    {file = "pydantic_core-2.33.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:e100c52f7355a48413e2999bfb4e139d2977a904495441b374f3d4fb4a170961"},
+    {file = "pydantic_core-2.33.1-cp311-cp311-musllinux_1_1_armv7l.whl", hash = "sha256:048831bd363490be79acdd3232f74a0e9951b11b2b4cc058aeb72b22fdc3abe1"},
+    {file = "pydantic_core-2.33.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:bdc84017d28459c00db6f918a7272a5190bec3090058334e43a76afb279eac7c"},
+    {file = "pydantic_core-2.33.1-cp311-cp311-win32.whl", hash = "sha256:32cd11c5914d1179df70406427097c7dcde19fddf1418c787540f4b730289896"},
+    {file = "pydantic_core-2.33.1-cp311-cp311-win_amd64.whl", hash = "sha256:2ea62419ba8c397e7da28a9170a16219d310d2cf4970dbc65c32faf20d828c83"},
+    {file = "pydantic_core-2.33.1-cp311-cp311-win_arm64.whl", hash = "sha256:fc903512177361e868bc1f5b80ac8c8a6e05fcdd574a5fb5ffeac5a9982b9e89"},
+    {file = "pydantic_core-2.33.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:1293d7febb995e9d3ec3ea09caf1a26214eec45b0f29f6074abb004723fc1de8"},
+    {file = "pydantic_core-2.33.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:99b56acd433386c8f20be5c4000786d1e7ca0523c8eefc995d14d79c7a081498"},
+    {file = "pydantic_core-2.33.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:35a5ec3fa8c2fe6c53e1b2ccc2454398f95d5393ab398478f53e1afbbeb4d939"},
+    {file = "pydantic_core-2.33.1-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:b172f7b9d2f3abc0efd12e3386f7e48b576ef309544ac3a63e5e9cdd2e24585d"},
+    {file = "pydantic_core-2.33.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9097b9f17f91eea659b9ec58148c0747ec354a42f7389b9d50701610d86f812e"},
+    {file = "pydantic_core-2.33.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cc77ec5b7e2118b152b0d886c7514a4653bcb58c6b1d760134a9fab915f777b3"},
+    {file = "pydantic_core-2.33.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d5e3d15245b08fa4a84cefc6c9222e6f37c98111c8679fbd94aa145f9a0ae23d"},
+    {file = "pydantic_core-2.33.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:ef99779001d7ac2e2461d8ab55d3373fe7315caefdbecd8ced75304ae5a6fc6b"},
+    {file = "pydantic_core-2.33.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:fc6bf8869e193855e8d91d91f6bf59699a5cdfaa47a404e278e776dd7f168b39"},
+    {file = "pydantic_core-2.33.1-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:b1caa0bc2741b043db7823843e1bde8aaa58a55a58fda06083b0569f8b45693a"},
+    {file = "pydantic_core-2.33.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:ec259f62538e8bf364903a7d0d0239447059f9434b284f5536e8402b7dd198db"},
+    {file = "pydantic_core-2.33.1-cp312-cp312-win32.whl", hash = "sha256:e14f369c98a7c15772b9da98987f58e2b509a93235582838bd0d1d8c08b68fda"},
+    {file = "pydantic_core-2.33.1-cp312-cp312-win_amd64.whl", hash = "sha256:1c607801d85e2e123357b3893f82c97a42856192997b95b4d8325deb1cd0c5f4"},
+    {file = "pydantic_core-2.33.1-cp312-cp312-win_arm64.whl", hash = "sha256:8d13f0276806ee722e70a1c93da19748594f19ac4299c7e41237fc791d1861ea"},
+    {file = "pydantic_core-2.33.1-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:70af6a21237b53d1fe7b9325b20e65cbf2f0a848cf77bed492b029139701e66a"},
+    {file = "pydantic_core-2.33.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:282b3fe1bbbe5ae35224a0dbd05aed9ccabccd241e8e6b60370484234b456266"},
+    {file = "pydantic_core-2.33.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4b315e596282bbb5822d0c7ee9d255595bd7506d1cb20c2911a4da0b970187d3"},
+    {file = "pydantic_core-2.33.1-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:1dfae24cf9921875ca0ca6a8ecb4bb2f13c855794ed0d468d6abbec6e6dcd44a"},
+    {file = "pydantic_core-2.33.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:6dd8ecfde08d8bfadaea669e83c63939af76f4cf5538a72597016edfa3fad516"},
+    {file = "pydantic_core-2.33.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2f593494876eae852dc98c43c6f260f45abdbfeec9e4324e31a481d948214764"},
+    {file = "pydantic_core-2.33.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:948b73114f47fd7016088e5186d13faf5e1b2fe83f5e320e371f035557fd264d"},
+    {file = "pydantic_core-2.33.1-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e11f3864eb516af21b01e25fac915a82e9ddad3bb0fb9e95a246067398b435a4"},
+    {file = "pydantic_core-2.33.1-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:549150be302428b56fdad0c23c2741dcdb5572413776826c965619a25d9c6bde"},
+    {file = "pydantic_core-2.33.1-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:495bc156026efafd9ef2d82372bd38afce78ddd82bf28ef5276c469e57c0c83e"},
+    {file = "pydantic_core-2.33.1-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:ec79de2a8680b1a67a07490bddf9636d5c2fab609ba8c57597e855fa5fa4dacd"},
+    {file = "pydantic_core-2.33.1-cp313-cp313-win32.whl", hash = "sha256:ee12a7be1742f81b8a65b36c6921022301d466b82d80315d215c4c691724986f"},
+    {file = "pydantic_core-2.33.1-cp313-cp313-win_amd64.whl", hash = "sha256:ede9b407e39949d2afc46385ce6bd6e11588660c26f80576c11c958e6647bc40"},
+    {file = "pydantic_core-2.33.1-cp313-cp313-win_arm64.whl", hash = "sha256:aa687a23d4b7871a00e03ca96a09cad0f28f443690d300500603bd0adba4b523"},
+    {file = "pydantic_core-2.33.1-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:401d7b76e1000d0dd5538e6381d28febdcacb097c8d340dde7d7fc6e13e9f95d"},
+    {file = "pydantic_core-2.33.1-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7aeb055a42d734c0255c9e489ac67e75397d59c6fbe60d155851e9782f276a9c"},
+    {file = "pydantic_core-2.33.1-cp313-cp313t-win_amd64.whl", hash = "sha256:338ea9b73e6e109f15ab439e62cb3b78aa752c7fd9536794112e14bee02c8d18"},
+    {file = "pydantic_core-2.33.1-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:5ab77f45d33d264de66e1884fca158bc920cb5e27fd0764a72f72f5756ae8bdb"},
+    {file = "pydantic_core-2.33.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e7aaba1b4b03aaea7bb59e1b5856d734be011d3e6d98f5bcaa98cb30f375f2ad"},
+    {file = "pydantic_core-2.33.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7fb66263e9ba8fea2aa85e1e5578980d127fb37d7f2e292773e7bc3a38fb0c7b"},
+    {file = "pydantic_core-2.33.1-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:3f2648b9262607a7fb41d782cc263b48032ff7a03a835581abbf7a3bec62bcf5"},
+    {file = "pydantic_core-2.33.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:723c5630c4259400818b4ad096735a829074601805d07f8cafc366d95786d331"},
+    {file = "pydantic_core-2.33.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d100e3ae783d2167782391e0c1c7a20a31f55f8015f3293647544df3f9c67824"},
+    {file = "pydantic_core-2.33.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:177d50460bc976a0369920b6c744d927b0ecb8606fb56858ff542560251b19e5"},
+    {file = "pydantic_core-2.33.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:a3edde68d1a1f9af1273b2fe798997b33f90308fb6d44d8550c89fc6a3647cf6"},
+    {file = "pydantic_core-2.33.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:a62c3c3ef6a7e2c45f7853b10b5bc4ddefd6ee3cd31024754a1a5842da7d598d"},
+    {file = "pydantic_core-2.33.1-cp39-cp39-musllinux_1_1_armv7l.whl", hash = "sha256:c91dbb0ab683fa0cd64a6e81907c8ff41d6497c346890e26b23de7ee55353f96"},
+    {file = "pydantic_core-2.33.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:9f466e8bf0a62dc43e068c12166281c2eca72121dd2adc1040f3aa1e21ef8599"},
+    {file = "pydantic_core-2.33.1-cp39-cp39-win32.whl", hash = "sha256:ab0277cedb698749caada82e5d099dc9fed3f906a30d4c382d1a21725777a1e5"},
+    {file = "pydantic_core-2.33.1-cp39-cp39-win_amd64.whl", hash = "sha256:5773da0ee2d17136b1f1c6fbde543398d452a6ad2a7b54ea1033e2daa739b8d2"},
+    {file = "pydantic_core-2.33.1-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:5c834f54f8f4640fd7e4b193f80eb25a0602bba9e19b3cd2fc7ffe8199f5ae02"},
+    {file = "pydantic_core-2.33.1-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:049e0de24cf23766f12cc5cc71d8abc07d4a9deb9061b334b62093dedc7cb068"},
+    {file = "pydantic_core-2.33.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1a28239037b3d6f16916a4c831a5a0eadf856bdd6d2e92c10a0da3a59eadcf3e"},
+    {file = "pydantic_core-2.33.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9d3da303ab5f378a268fa7d45f37d7d85c3ec19769f28d2cc0c61826a8de21fe"},
+    {file = "pydantic_core-2.33.1-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:25626fb37b3c543818c14821afe0fd3830bc327a43953bc88db924b68c5723f1"},
+    {file = "pydantic_core-2.33.1-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:3ab2d36e20fbfcce8f02d73c33a8a7362980cff717926bbae030b93ae46b56c7"},
+    {file = "pydantic_core-2.33.1-pp310-pypy310_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:2f9284e11c751b003fd4215ad92d325d92c9cb19ee6729ebd87e3250072cdcde"},
+    {file = "pydantic_core-2.33.1-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:048c01eee07d37cbd066fc512b9d8b5ea88ceeb4e629ab94b3e56965ad655add"},
+    {file = "pydantic_core-2.33.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:5ccd429694cf26af7997595d627dd2637e7932214486f55b8a357edaac9dae8c"},
+    {file = "pydantic_core-2.33.1-pp311-pypy311_pp73-macosx_10_12_x86_64.whl", hash = "sha256:3a371dc00282c4b84246509a5ddc808e61b9864aa1eae9ecc92bb1268b82db4a"},
+    {file = "pydantic_core-2.33.1-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:f59295ecc75a1788af8ba92f2e8c6eeaa5a94c22fc4d151e8d9638814f85c8fc"},
+    {file = "pydantic_core-2.33.1-pp311-pypy311_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:08530b8ac922003033f399128505f513e30ca770527cc8bbacf75a84fcc2c74b"},
+    {file = "pydantic_core-2.33.1-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bae370459da6a5466978c0eacf90690cb57ec9d533f8e63e564ef3822bfa04fe"},
+    {file = "pydantic_core-2.33.1-pp311-pypy311_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e3de2777e3b9f4d603112f78006f4ae0acb936e95f06da6cb1a45fbad6bdb4b5"},
+    {file = "pydantic_core-2.33.1-pp311-pypy311_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:3a64e81e8cba118e108d7126362ea30e021291b7805d47e4896e52c791be2761"},
+    {file = "pydantic_core-2.33.1-pp311-pypy311_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:52928d8c1b6bda03cc6d811e8923dffc87a2d3c8b3bfd2ce16471c7147a24850"},
+    {file = "pydantic_core-2.33.1-pp311-pypy311_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:1b30d92c9412beb5ac6b10a3eb7ef92ccb14e3f2a8d7732e2d739f58b3aa7544"},
+    {file = "pydantic_core-2.33.1-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:f995719707e0e29f0f41a8aa3bcea6e761a36c9136104d3189eafb83f5cec5e5"},
+    {file = "pydantic_core-2.33.1-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:7edbc454a29fc6aeae1e1eecba4f07b63b8d76e76a748532233c4c167b4cb9ea"},
+    {file = "pydantic_core-2.33.1-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:ad05b683963f69a1d5d2c2bdab1274a31221ca737dbbceaa32bcb67359453cdd"},
+    {file = "pydantic_core-2.33.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:df6a94bf9452c6da9b5d76ed229a5683d0306ccb91cca8e1eea883189780d568"},
+    {file = "pydantic_core-2.33.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7965c13b3967909a09ecc91f21d09cfc4576bf78140b988904e94f130f188396"},
+    {file = "pydantic_core-2.33.1-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:3f1fdb790440a34f6ecf7679e1863b825cb5ffde858a9197f851168ed08371e5"},
+    {file = "pydantic_core-2.33.1-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:5277aec8d879f8d05168fdd17ae811dd313b8ff894aeeaf7cd34ad28b4d77e33"},
+    {file = "pydantic_core-2.33.1-pp39-pypy39_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:8ab581d3530611897d863d1a649fb0644b860286b4718db919bfd51ece41f10b"},
+    {file = "pydantic_core-2.33.1-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:0483847fa9ad5e3412265c1bd72aad35235512d9ce9d27d81a56d935ef489672"},
+    {file = "pydantic_core-2.33.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:de9e06abe3cc5ec6a2d5f75bc99b0bdca4f5c719a5b34026f8c57efbdecd2ee3"},
+    {file = "pydantic_core-2.33.1.tar.gz", hash = "sha256:bcc9c6fdb0ced789245b02b7d6603e17d1563064ddcfc36f046b61c0c05dd9df"},
 ]
 
 [package.dependencies]
@@ -7147,14 +7143,14 @@ XlsxWriter = ">=0.5.7"
 
 [[package]]
 name = "python-socketio"
-version = "5.12.1"
+version = "5.13.0"
 description = "Socket.IO server and client for Python"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "python_socketio-5.12.1-py3-none-any.whl", hash = "sha256:24a0ea7cfff0e021eb28c68edbf7914ee4111bdf030b95e4d250c4dc9af7a386"},
-    {file = "python_socketio-5.12.1.tar.gz", hash = "sha256:0299ff1f470b676c09c1bfab1dead25405077d227b2c13cf217a34dadc68ba9c"},
+    {file = "python_socketio-5.13.0-py3-none-any.whl", hash = "sha256:51f68d6499f2df8524668c24bcec13ba1414117cfb3a90115c559b601ab10caf"},
+    {file = "python_socketio-5.13.0.tar.gz", hash = "sha256:ac4e19a0302ae812e23b712ec8b6427ca0521f7c582d6abb096e36e24a263029"},
 ]
 
 [package.dependencies]
@@ -7172,7 +7168,7 @@ version = "2025.1"
 description = "World timezone definitions, modern and historical"
 optional = false
 python-versions = "*"
-groups = ["main", "evaluation", "test"]
+groups = ["evaluation", "test"]
 files = [
     {file = "pytz-2025.1-py2.py3-none-any.whl", hash = "sha256:89dd22dca55b46eac6eda23b2d72721bf1bdfef212645d81513ef5d03038de57"},
     {file = "pytz-2025.1.tar.gz", hash = "sha256:c2db42be2a2518b28e65f9207c4d05e6ff547d1efa4086469ef855e4ab70178e"},
@@ -7967,30 +7963,30 @@ pyasn1 = ">=0.1.3"
 
 [[package]]
 name = "ruff"
-version = "0.11.4"
+version = "0.11.5"
 description = "An extremely fast Python linter and code formatter, written in Rust."
 optional = false
 python-versions = ">=3.7"
 groups = ["dev", "evaluation"]
 files = [
-    {file = "ruff-0.11.4-py3-none-linux_armv6l.whl", hash = "sha256:d9f4a761ecbde448a2d3e12fb398647c7f0bf526dbc354a643ec505965824ed2"},
-    {file = "ruff-0.11.4-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:8c1747d903447d45ca3d40c794d1a56458c51e5cc1bc77b7b64bd2cf0b1626cc"},
-    {file = "ruff-0.11.4-py3-none-macosx_11_0_arm64.whl", hash = "sha256:51a6494209cacca79e121e9b244dc30d3414dac8cc5afb93f852173a2ecfc906"},
-    {file = "ruff-0.11.4-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3f171605f65f4fc49c87f41b456e882cd0c89e4ac9d58e149a2b07930e1d466f"},
-    {file = "ruff-0.11.4-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ebf99ea9af918878e6ce42098981fc8c1db3850fef2f1ada69fb1dcdb0f8e79e"},
-    {file = "ruff-0.11.4-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:edad2eac42279df12e176564a23fc6f4aaeeb09abba840627780b1bb11a9d223"},
-    {file = "ruff-0.11.4-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:f103a848be9ff379fc19b5d656c1f911d0a0b4e3e0424f9532ececf319a4296e"},
-    {file = "ruff-0.11.4-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:193e6fac6eb60cc97b9f728e953c21cc38a20077ed64f912e9d62b97487f3f2d"},
-    {file = "ruff-0.11.4-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7af4e5f69b7c138be8dcffa5b4a061bf6ba6a3301f632a6bce25d45daff9bc99"},
-    {file = "ruff-0.11.4-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:126b1bf13154aa18ae2d6c3c5efe144ec14b97c60844cfa6eb960c2a05188222"},
-    {file = "ruff-0.11.4-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:e8806daaf9dfa881a0ed603f8a0e364e4f11b6ed461b56cae2b1c0cab0645304"},
-    {file = "ruff-0.11.4-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:5d94bb1cc2fc94a769b0eb975344f1b1f3d294da1da9ddbb5a77665feb3a3019"},
-    {file = "ruff-0.11.4-py3-none-musllinux_1_2_i686.whl", hash = "sha256:995071203d0fe2183fc7a268766fd7603afb9996785f086b0d76edee8755c896"},
-    {file = "ruff-0.11.4-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:7a37ca937e307ea18156e775a6ac6e02f34b99e8c23fe63c1996185a4efe0751"},
-    {file = "ruff-0.11.4-py3-none-win32.whl", hash = "sha256:0e9365a7dff9b93af933dab8aebce53b72d8f815e131796268709890b4a83270"},
-    {file = "ruff-0.11.4-py3-none-win_amd64.whl", hash = "sha256:5a9fa1c69c7815e39fcfb3646bbfd7f528fa8e2d4bebdcf4c2bd0fa037a255fb"},
-    {file = "ruff-0.11.4-py3-none-win_arm64.whl", hash = "sha256:d435db6b9b93d02934cf61ef332e66af82da6d8c69aefdea5994c89997c7a0fc"},
-    {file = "ruff-0.11.4.tar.gz", hash = "sha256:f45bd2fb1a56a5a85fae3b95add03fb185a0b30cf47f5edc92aa0355ca1d7407"},
+    {file = "ruff-0.11.5-py3-none-linux_armv6l.whl", hash = "sha256:2561294e108eb648e50f210671cc56aee590fb6167b594144401532138c66c7b"},
+    {file = "ruff-0.11.5-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:ac12884b9e005c12d0bd121f56ccf8033e1614f736f766c118ad60780882a077"},
+    {file = "ruff-0.11.5-py3-none-macosx_11_0_arm64.whl", hash = "sha256:4bfd80a6ec559a5eeb96c33f832418bf0fb96752de0539905cf7b0cc1d31d779"},
+    {file = "ruff-0.11.5-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0947c0a1afa75dcb5db4b34b070ec2bccee869d40e6cc8ab25aca11a7d527794"},
+    {file = "ruff-0.11.5-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ad871ff74b5ec9caa66cb725b85d4ef89b53f8170f47c3406e32ef040400b038"},
+    {file = "ruff-0.11.5-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e6cf918390cfe46d240732d4d72fa6e18e528ca1f60e318a10835cf2fa3dc19f"},
+    {file = "ruff-0.11.5-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:56145ee1478582f61c08f21076dc59153310d606ad663acc00ea3ab5b2125f82"},
+    {file = "ruff-0.11.5-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e5f66f8f1e8c9fc594cbd66fbc5f246a8d91f916cb9667e80208663ec3728304"},
+    {file = "ruff-0.11.5-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:80b4df4d335a80315ab9afc81ed1cff62be112bd165e162b5eed8ac55bfc8470"},
+    {file = "ruff-0.11.5-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3068befab73620b8a0cc2431bd46b3cd619bc17d6f7695a3e1bb166b652c382a"},
+    {file = "ruff-0.11.5-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:f5da2e710a9641828e09aa98b92c9ebbc60518fdf3921241326ca3e8f8e55b8b"},
+    {file = "ruff-0.11.5-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:ef39f19cb8ec98cbc762344921e216f3857a06c47412030374fffd413fb8fd3a"},
+    {file = "ruff-0.11.5-py3-none-musllinux_1_2_i686.whl", hash = "sha256:b2a7cedf47244f431fd11aa5a7e2806dda2e0c365873bda7834e8f7d785ae159"},
+    {file = "ruff-0.11.5-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:81be52e7519f3d1a0beadcf8e974715b2dfc808ae8ec729ecfc79bddf8dbb783"},
+    {file = "ruff-0.11.5-py3-none-win32.whl", hash = "sha256:e268da7b40f56e3eca571508a7e567e794f9bfcc0f412c4b607931d3af9c4afe"},
+    {file = "ruff-0.11.5-py3-none-win_amd64.whl", hash = "sha256:6c6dc38af3cfe2863213ea25b6dc616d679205732dc0fb673356c2d69608f800"},
+    {file = "ruff-0.11.5-py3-none-win_arm64.whl", hash = "sha256:67e241b4314f4eacf14a601d586026a962f4002a475aa702c69980a38087aa4e"},
+    {file = "ruff-0.11.5.tar.gz", hash = "sha256:cae2e2439cb88853e421901ec040a758960b576126dab520fa08e9de431d1bef"},
 ]
 
 [[package]]
@@ -8166,7 +8162,7 @@ version = "1.15.2"
 description = "Fundamental algorithms for scientific computing in Python"
 optional = false
 python-versions = ">=3.10"
-groups = ["main", "evaluation"]
+groups = ["evaluation"]
 files = [
     {file = "scipy-1.15.2-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:a2ec871edaa863e8213ea5df811cd600734f6400b4af272e1c011e69401218e9"},
     {file = "scipy-1.15.2-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:6f223753c6ea76983af380787611ae1291e3ceb23917393079dcc746ba60cfb5"},
@@ -9430,13 +9426,28 @@ files = [
 mypy-extensions = ">=0.3.0"
 typing-extensions = ">=3.7.4"
 
+[[package]]
+name = "typing-inspection"
+version = "0.4.0"
+description = "Runtime typing introspection tools"
+optional = false
+python-versions = ">=3.9"
+groups = ["main", "evaluation", "test"]
+files = [
+    {file = "typing_inspection-0.4.0-py3-none-any.whl", hash = "sha256:50e72559fcd2a6367a19f7a7e610e6afcb9fac940c650290eed893d61386832f"},
+    {file = "typing_inspection-0.4.0.tar.gz", hash = "sha256:9765c87de36671694a67904bf2c96e395be9c6439bb6c87b5142569dcdd65122"},
+]
+
+[package.dependencies]
+typing-extensions = ">=4.12.0"
+
 [[package]]
 name = "tzdata"
 version = "2025.1"
 description = "Provider of IANA time zone data"
 optional = false
 python-versions = ">=2"
-groups = ["main", "evaluation", "test"]
+groups = ["evaluation", "test"]
 files = [
     {file = "tzdata-2025.1-py2.py3-none-any.whl", hash = "sha256:7e127113816800496f027041c570f50bcd464a020098a3b6b199517772303639"},
     {file = "tzdata-2025.1.tar.gz", hash = "sha256:24894909e88cdb28bd1636c6887801df64cb485bd593f2fd83ef29075a81d694"},
@@ -9501,14 +9512,14 @@ zstd = ["zstandard (>=0.18.0)"]
 
 [[package]]
 name = "uvicorn"
-version = "0.34.0"
+version = "0.34.1"
 description = "The lightning-fast ASGI server."
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "uvicorn-0.34.0-py3-none-any.whl", hash = "sha256:023dc038422502fa28a09c7a30bf2b6991512da7dcdb8fd35fe57cfc154126f4"},
-    {file = "uvicorn-0.34.0.tar.gz", hash = "sha256:404051050cd7e905de2c9a7e61790943440b3416f49cb409f965d9dcd0fa73e9"},
+    {file = "uvicorn-0.34.1-py3-none-any.whl", hash = "sha256:984c3a8c7ca18ebaad15995ee7401179212c59521e67bfc390c07fa2b8d2e065"},
+    {file = "uvicorn-0.34.1.tar.gz", hash = "sha256:af981725fc4b7ffc5cb3b0e9eda6258a90c4b52cb2a83ce567ae0a7ae1757afc"},
 ]
 
 [package.dependencies]
@@ -10258,4 +10269,4 @@ testing = ["coverage[toml]", "zope.event", "zope.testing"]
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.12"
-content-hash = "535e002070d94b63adb76e6faad5c1966d177b8b482ea82212555514b95c623c"
+content-hash = "e103d6d899af073c222deec407e7d0f58d445d10b2cfb9b0579243790eefd5be"

pyproject.toml

@@ -62,7 +62,7 @@ runloop-api-client = "0.29.0"
 libtmux = ">=0.37,<0.40"
 pygithub = "^2.5.0"
 joblib = "*"
-openhands-aci = "^0.2.8"
+openhands-aci = "^0.2.10"
 python-socketio = "^5.11.4"
 redis = "^5.2.0"
 sse-starlette = "^2.1.3"
@@ -71,14 +71,14 @@ stripe = ">=11.5,<13.0"
 ipywidgets = "^8.1.5"
 qtconsole = "^5.6.1"
 memory-profiler = "^0.61.0"
-daytona-sdk = "0.12.1"
+daytona-sdk = "0.13.1"
 mcp = "1.6.0"
 python-json-logger = "^3.2.1"
 playwright = "^1.51.0"
 prompt-toolkit = "^3.0.50"
 
 [tool.poetry.group.dev.dependencies]
-ruff = "0.11.4"
+ruff = "0.11.5"
 mypy = "1.15.0"
 pre-commit = "4.2.0"
 build = "*"
@@ -97,6 +97,7 @@ gevent = "^24.2.1"
 [tool.coverage.run]
 concurrency = ["gevent"]
 
+
 [tool.poetry.group.runtime.dependencies]
 jupyterlab = "*"
 notebook = "*"
@@ -125,6 +126,7 @@ ignore = ["D1"]
 [tool.ruff.lint.pydocstyle]
 convention = "google"
 
+
 [tool.poetry.group.evaluation.dependencies]
 streamlit = "*"
 whatthepatch = "*"

tests/runtime/test_aci_edit.py

@@ -200,9 +200,10 @@ def test_str_replace_multi_line_with_tabs(temp_dir, runtime_cls, run_as_openhand
     runtime, config = _load_runtime(temp_dir, runtime_cls, run_as_openhands)
     try:
         test_file = os.path.join(config.workspace_mount_path_in_sandbox, 'test.txt')
-        action = FileWriteAction(
-            content='def test():\n\tprint("Hello, World!")',
+        action = FileEditAction(
+            command='create',
             path=test_file,
+            file_text='def test():\n\tprint("Hello, World!")',
         )
         runtime.run_action(action)
 
@@ -220,7 +221,6 @@ def test_str_replace_multi_line_with_tabs(temp_dir, runtime_cls, run_as_openhand
             == f"""The file {test_file} has been edited. Here's the result of running `cat -n` on a snippet of {test_file}:
      1\tdef test():
      2\t{'\t'.expandtabs()}print("Hello, Universe!")
-     3\t
 Review the changes and make sure they are as expected. Edit the file again if necessary."""
         )
 

tests/runtime/test_stress_remote_runtime.py

@@ -82,9 +82,9 @@ def get_config() -> AppConfig:
         workspace_mount_path=None,
     )
     agent_config = AgentConfig(
-        codeact_enable_jupyter=False,
-        codeact_enable_browsing=False,
-        codeact_enable_llm_editor=False,
+        enable_jupyter=False,
+        enable_browsing=False,
+        enable_llm_editor=False,
     )
     config.set_agent_config(agent_config)
     return config

tests/unit/resolver/github/test_send_pull_request.py

@@ -558,7 +558,7 @@ def test_send_pull_request_target_branch_with_fork(
     post_data = mock_post.call_args[1]['json']
     assert post_data['base'] == target_branch  # PR should target the specified branch
     assert (
-        post_data['head'] == 'openhands-fix-issue-42'
+        post_data['head'] == 'fork-owner:openhands-fix-issue-42'
     )  # Branch name should be standard
 
     # Check that push was to fork

tests/unit/test_cli_basic_prompts.py

@@ -10,10 +10,8 @@ from prompt_toolkit.output import create_output
 
 from openhands.core.cli import main
 from openhands.core.config import AppConfig
-from openhands.core.schema import AgentState
 from openhands.events.action import MessageAction
 from openhands.events.event import EventSource
-from openhands.events.observation import AgentStateChangedObservation
 
 
 class MockEventStream:
@@ -88,6 +86,7 @@ def mock_config():
             mock_config.security.confirmation_mode = False
             mock_config.sandbox = Mock()
             mock_config.sandbox.selected_repo = None
+            mock_config.workspace_base = '/test'
             mock_setup_config.return_value = mock_config
             yield mock_config
 
@@ -126,44 +125,32 @@ def mock_runtime():
 
 
 @pytest.mark.asyncio
-async def test_cli_greeting(
+async def test_cli_basic_prompt(
     mock_runtime, mock_controller, mock_config, mock_agent, mock_memory, mock_read_task
 ):
     buffer = StringIO()
 
-    with create_app_session(
-        input=create_pipe_input(), output=create_output(stdout=buffer)
-    ):
-        mock_controller.status_callback = None
+    with patch('openhands.core.cli.manage_openhands_file', return_value=True):
+        with patch('openhands.core.cli.cli_confirm', return_value=True):
+            with create_app_session(
+                input=create_pipe_input(), output=create_output(stdout=buffer)
+            ):
+                mock_controller.status_callback = None
 
-        main_task = asyncio.create_task(main(asyncio.get_event_loop()))
+                main_task = asyncio.create_task(main(asyncio.get_event_loop()))
 
-        await asyncio.sleep(0.1)
+                await asyncio.sleep(0.1)
 
-        hello_response = MessageAction(content='Ping')
-        hello_response._source = EventSource.AGENT
-        mock_runtime.event_stream.add_event(hello_response, EventSource.AGENT)
+                hello_response = MessageAction(content='Ping')
+                hello_response._source = EventSource.AGENT
+                mock_runtime.event_stream.add_event(hello_response, EventSource.AGENT)
 
-        state_change = AgentStateChangedObservation(
-            content='Awaiting user input', agent_state=AgentState.AWAITING_USER_INPUT
-        )
-        state_change._source = EventSource.AGENT
-        mock_runtime.event_stream.add_event(state_change, EventSource.AGENT)
+                try:
+                    await asyncio.wait_for(main_task, timeout=1.0)
+                except asyncio.TimeoutError:
+                    main_task.cancel()
 
-        stop_event = AgentStateChangedObservation(
-            content='Stop', agent_state=AgentState.STOPPED
-        )
-        stop_event._source = EventSource.AGENT
-        mock_runtime.event_stream.add_event(stop_event, EventSource.AGENT)
+                buffer.seek(0)
+                output = buffer.read()
 
-        mock_controller.state.agent_state = AgentState.STOPPED
-
-        try:
-            await asyncio.wait_for(main_task, timeout=1.0)
-        except asyncio.TimeoutError:
-            main_task.cancel()
-
-        buffer.seek(0)
-        output = buffer.read()
-
-        assert 'Ping' in output
+                assert 'Ping' in output

tests/unit/test_cli_commands.py

@@ -0,0 +1,368 @@
+import asyncio
+from io import StringIO
+from unittest.mock import AsyncMock, Mock, patch
+
+import pytest
+from prompt_toolkit.application import create_app_session
+from prompt_toolkit.input import create_pipe_input
+from prompt_toolkit.output import create_output
+
+from openhands.core.cli import main
+from openhands.core.config import AppConfig
+from openhands.core.schema import AgentState
+from openhands.events.action import ChangeAgentStateAction, MessageAction
+from openhands.events.event import EventSource
+from openhands.events.observation import AgentStateChangedObservation
+
+
+class MockEventStream:
+    def __init__(self):
+        self._subscribers = {}
+        self.cur_id = 0
+        self.events = []
+
+    def subscribe(self, subscriber_id, callback, callback_id=None):
+        if subscriber_id not in self._subscribers:
+            self._subscribers[subscriber_id] = {}
+        self._subscribers[subscriber_id][callback_id] = callback
+        return callback_id
+
+    def unsubscribe(self, subscriber_id, callback_id):
+        if (
+            subscriber_id in self._subscribers
+            and callback_id in self._subscribers[subscriber_id]
+        ):
+            del self._subscribers[subscriber_id][callback_id]
+
+    def add_event(self, event, source):
+        event._id = self.cur_id
+        self.cur_id += 1
+        event._source = source
+        event._timestamp = '2023-01-01T00:00:00'
+        self.events.append((event, source))
+
+        for subscriber_id in self._subscribers:
+            for callback_id, callback in self._subscribers[subscriber_id].items():
+                if asyncio.iscoroutinefunction(callback):
+                    asyncio.create_task(callback(event))
+                else:
+                    callback(event)
+
+
+@pytest.fixture
+def mock_agent():
+    with patch('openhands.core.cli.create_agent') as mock_create_agent:
+        mock_agent_instance = AsyncMock()
+        mock_agent_instance.name = 'test-agent'
+        mock_agent_instance.llm = AsyncMock()
+        mock_agent_instance.llm.config = AsyncMock()
+        mock_agent_instance.llm.config.model = 'test-model'
+        mock_agent_instance.llm.config.base_url = 'http://test'
+        mock_agent_instance.llm.config.max_message_chars = 1000
+        mock_agent_instance.config = AsyncMock()
+        mock_agent_instance.config.disabled_microagents = []
+        mock_agent_instance.sandbox_plugins = []
+        mock_agent_instance.prompt_manager = AsyncMock()
+        mock_create_agent.return_value = mock_agent_instance
+        yield mock_agent_instance
+
+
+@pytest.fixture
+def mock_controller():
+    with patch('openhands.core.cli.create_controller') as mock_create_controller:
+        mock_controller_instance = AsyncMock()
+        mock_controller_instance.state.agent_state = None
+        # Mock run_until_done to finish immediately
+        mock_controller_instance.run_until_done = AsyncMock(return_value=None)
+        mock_create_controller.return_value = (mock_controller_instance, None)
+        yield mock_controller_instance
+
+
+@pytest.fixture
+def mock_config():
+    with patch('openhands.core.cli.parse_arguments') as mock_parse_args:
+        args = Mock()
+        args.file = None
+        args.task = None
+        args.directory = None
+        mock_parse_args.return_value = args
+        with patch('openhands.core.cli.setup_config_from_args') as mock_setup_config:
+            mock_config = AppConfig()
+            mock_config.cli_multiline_input = False
+            mock_config.security = Mock()
+            mock_config.security.confirmation_mode = False
+            mock_config.sandbox = Mock()
+            mock_config.sandbox.selected_repo = None
+            mock_config.workspace_base = '/test'
+            mock_config.runtime = 'local'  # Important for /init test
+            mock_setup_config.return_value = mock_config
+            yield mock_config
+
+
+@pytest.fixture
+def mock_memory():
+    with patch('openhands.core.cli.create_memory') as mock_create_memory:
+        mock_memory_instance = AsyncMock()
+        mock_create_memory.return_value = mock_memory_instance
+        yield mock_memory_instance
+
+
+@pytest.fixture
+def mock_read_task():
+    with patch('openhands.core.cli.read_task') as mock_read_task:
+        mock_read_task.return_value = None
+        yield mock_read_task
+
+
+@pytest.fixture
+def mock_runtime():
+    with patch('openhands.core.cli.create_runtime') as mock_create_runtime:
+        mock_runtime_instance = AsyncMock()
+
+        mock_event_stream = MockEventStream()
+        mock_runtime_instance.event_stream = mock_event_stream
+
+        mock_runtime_instance.connect = AsyncMock()
+
+        # Ensure status_callback is None
+        mock_runtime_instance.status_callback = None
+        # Mock get_microagents_from_selected_repo
+        mock_runtime_instance.get_microagents_from_selected_repo = Mock(return_value=[])
+        mock_create_runtime.return_value = mock_runtime_instance
+        yield mock_runtime_instance
+
+
+@pytest.mark.asyncio
+async def test_help_command(
+    mock_runtime, mock_controller, mock_config, mock_agent, mock_memory, mock_read_task
+):
+    buffer = StringIO()
+
+    with patch('openhands.core.cli.manage_openhands_file', return_value=True):
+        with patch(
+            'openhands.core.cli.check_folder_security_agreement', return_value=True
+        ):
+            with patch('openhands.core.cli.read_prompt_input') as mock_prompt:
+                # Setup to return /help first, then simulate an exit
+                mock_prompt.side_effect = ['/help', '/exit']
+
+                with create_app_session(
+                    input=create_pipe_input(), output=create_output(stdout=buffer)
+                ):
+                    mock_controller.status_callback = None
+
+                    main_task = asyncio.create_task(main(asyncio.get_event_loop()))
+
+                    agent_ready_event = AgentStateChangedObservation(
+                        agent_state=AgentState.AWAITING_USER_INPUT,
+                        content='Agent is ready for user input',
+                    )
+                    mock_runtime.event_stream.add_event(
+                        agent_ready_event, EventSource.AGENT
+                    )
+
+                    await asyncio.sleep(0.1)
+
+                    try:
+                        await asyncio.wait_for(main_task, timeout=0.5)
+                    except asyncio.TimeoutError:
+                        main_task.cancel()
+                        try:
+                            await main_task
+                        except asyncio.CancelledError:
+                            pass
+
+                    buffer.seek(0)
+                    output = buffer.read()
+
+                    # Verify help output was displayed
+                    assert 'OpenHands CLI' in output
+                    assert 'Things that you can try' in output
+                    assert 'Interactive commands' in output
+                    assert '/help' in output
+                    assert '/exit' in output
+
+                    # Verify the help command didn't add a MessageAction to the event stream
+                    message_actions = [
+                        event
+                        for event, _ in mock_runtime.event_stream.events
+                        if isinstance(event, MessageAction)
+                    ]
+                    assert len(message_actions) == 0
+
+
+@pytest.mark.asyncio
+async def test_exit_command(
+    mock_runtime, mock_controller, mock_config, mock_agent, mock_memory, mock_read_task
+):
+    buffer = StringIO()
+
+    with patch('openhands.core.cli.manage_openhands_file', return_value=True):
+        with patch(
+            'openhands.core.cli.check_folder_security_agreement', return_value=True
+        ):
+            with patch('openhands.core.cli.read_prompt_input') as mock_prompt:
+                # First prompt call returns /exit
+                mock_prompt.side_effect = ['/exit']
+
+                with patch('openhands.core.cli.shutdown') as mock_shutdown:
+                    with create_app_session(
+                        input=create_pipe_input(), output=create_output(stdout=buffer)
+                    ):
+                        mock_controller.status_callback = None
+
+                        main_task = asyncio.create_task(main(asyncio.get_event_loop()))
+
+                        agent_ready_event = AgentStateChangedObservation(
+                            agent_state=AgentState.AWAITING_USER_INPUT,
+                            content='Agent is ready for user input',
+                        )
+                        mock_runtime.event_stream.add_event(
+                            agent_ready_event, EventSource.AGENT
+                        )
+
+                        await asyncio.sleep(0.1)
+
+                        try:
+                            await asyncio.wait_for(main_task, timeout=0.5)
+                        except asyncio.TimeoutError:
+                            main_task.cancel()
+                            try:
+                                await main_task
+                            except asyncio.CancelledError:
+                                pass
+
+                        # Verify that the exit command sent a STOPPED state change event
+                        state_change_events = [
+                            event
+                            for event, source in mock_runtime.event_stream.events
+                            if isinstance(event, ChangeAgentStateAction)
+                            and event.agent_state == AgentState.STOPPED
+                            and source == EventSource.ENVIRONMENT
+                        ]
+                        assert len(state_change_events) == 1
+
+                        # Verify shutdown was called
+                        mock_shutdown.assert_called_once()
+
+
+@pytest.mark.asyncio
+async def test_init_command(
+    mock_runtime, mock_controller, mock_config, mock_agent, mock_memory, mock_read_task
+):
+    buffer = StringIO()
+
+    with patch('openhands.core.cli.manage_openhands_file', return_value=True):
+        with patch(
+            'openhands.core.cli.check_folder_security_agreement', return_value=True
+        ):
+            with patch('openhands.core.cli.read_prompt_input') as mock_prompt:
+                # First prompt call returns /init, second call returns /exit
+                mock_prompt.side_effect = ['/init', '/exit']
+
+                with patch('openhands.core.cli.init_repository') as mock_init_repo:
+                    with create_app_session(
+                        input=create_pipe_input(), output=create_output(stdout=buffer)
+                    ):
+                        mock_controller.status_callback = None
+
+                        main_task = asyncio.create_task(main(asyncio.get_event_loop()))
+
+                        agent_ready_event = AgentStateChangedObservation(
+                            agent_state=AgentState.AWAITING_USER_INPUT,
+                            content='Agent is ready for user input',
+                        )
+                        mock_runtime.event_stream.add_event(
+                            agent_ready_event, EventSource.AGENT
+                        )
+
+                        await asyncio.sleep(0.1)
+
+                        try:
+                            await asyncio.wait_for(main_task, timeout=0.5)
+                        except asyncio.TimeoutError:
+                            main_task.cancel()
+                            try:
+                                await main_task
+                            except asyncio.CancelledError:
+                                pass
+
+                        # Verify init_repository was called with the correct directory
+                        mock_init_repo.assert_called_once_with('/test')
+
+                        # Verify that a MessageAction was sent with the repository creation prompt
+                        message_events = [
+                            event
+                            for event, source in mock_runtime.event_stream.events
+                            if isinstance(event, MessageAction)
+                            and 'Please explore this repository' in event.content
+                            and source == EventSource.USER
+                        ]
+                        assert len(message_events) == 1
+
+
+@pytest.mark.asyncio
+async def test_init_command_non_local_runtime(
+    mock_runtime, mock_controller, mock_config, mock_agent, mock_memory, mock_read_task
+):
+    buffer = StringIO()
+
+    # Set runtime to non-local for this test
+    mock_config.runtime = 'remote'
+
+    with patch('openhands.core.cli.manage_openhands_file', return_value=True):
+        with patch(
+            'openhands.core.cli.check_folder_security_agreement', return_value=True
+        ):
+            with patch('openhands.core.cli.read_prompt_input') as mock_prompt:
+                # First prompt call returns /init, second call returns /exit
+                mock_prompt.side_effect = ['/init', '/exit']
+
+                with patch('openhands.core.cli.init_repository') as mock_init_repo:
+                    with create_app_session(
+                        input=create_pipe_input(), output=create_output(stdout=buffer)
+                    ):
+                        mock_controller.status_callback = None
+
+                        main_task = asyncio.create_task(main(asyncio.get_event_loop()))
+
+                        # Send AgentStateChangedObservation to trigger prompt
+                        agent_ready_event = AgentStateChangedObservation(
+                            agent_state=AgentState.AWAITING_USER_INPUT,
+                            content='Agent is ready for user input',
+                        )
+                        mock_runtime.event_stream.add_event(
+                            agent_ready_event, EventSource.AGENT
+                        )
+
+                        await asyncio.sleep(0.1)
+
+                        try:
+                            await asyncio.wait_for(main_task, timeout=0.5)
+                        except asyncio.TimeoutError:
+                            main_task.cancel()
+                            try:
+                                await main_task
+                            except asyncio.CancelledError:
+                                pass
+
+                        buffer.seek(0)
+                        output = buffer.read()
+
+                        # Verify error message was displayed
+                        assert (
+                            'Repository initialization through the CLI is only supported for local runtime'
+                            in output
+                        )
+
+                        # Verify init_repository was not called
+                        mock_init_repo.assert_not_called()
+
+                        # Verify no MessageAction was sent for repository creation
+                        message_events = [
+                            event
+                            for event, _ in mock_runtime.event_stream.events
+                            if isinstance(event, MessageAction)
+                            and 'Please explore this repository' in event.content
+                        ]
+                        assert len(message_events) == 0

tests/unit/test_cli_sid.py

@@ -1,127 +0,0 @@
-import asyncio
-from argparse import Namespace
-from io import StringIO
-from pathlib import Path
-from unittest.mock import AsyncMock, Mock, patch
-
-import pytest
-from prompt_toolkit.application import create_app_session
-from prompt_toolkit.input import create_pipe_input
-from prompt_toolkit.output import create_output
-
-from openhands.core.cli import main
-from openhands.core.config import AppConfig
-from openhands.core.schema import AgentState
-from openhands.events.event import EventSource
-from openhands.events.observation import AgentStateChangedObservation
-
-
-@pytest.fixture
-def mock_runtime():
-    with patch('openhands.core.cli.create_runtime') as mock_create_runtime:
-        mock_runtime_instance = AsyncMock()
-        # Mock the event stream with proper async methods
-        mock_event_stream = AsyncMock()
-        mock_event_stream.subscribe = AsyncMock()
-        mock_event_stream.add_event = AsyncMock()
-        mock_event_stream.get_events = AsyncMock(return_value=[])
-        mock_event_stream.get_latest_event_id = AsyncMock(return_value=0)
-        mock_runtime_instance.event_stream = mock_event_stream
-        # Mock connect method to return immediately
-        mock_runtime_instance.connect = AsyncMock()
-        # Ensure status_callback is None
-        mock_runtime_instance.status_callback = None
-        # Mock get_microagents_from_selected_repo
-        mock_runtime_instance.get_microagents_from_selected_repo = Mock(return_value=[])
-        mock_create_runtime.return_value = mock_runtime_instance
-        yield mock_runtime_instance
-
-
-@pytest.fixture
-def mock_agent():
-    with patch('openhands.core.cli.create_agent') as mock_create_agent:
-        mock_agent_instance = AsyncMock()
-        mock_agent_instance.name = 'test-agent'
-        mock_agent_instance.llm = AsyncMock()
-        mock_agent_instance.llm.config = AsyncMock()
-        mock_agent_instance.llm.config.model = 'test-model'
-        mock_agent_instance.llm.config.base_url = 'http://test'
-        mock_agent_instance.llm.config.max_message_chars = 1000
-        mock_agent_instance.config = AsyncMock()
-        mock_agent_instance.config.disabled_microagents = []
-        mock_agent_instance.sandbox_plugins = []
-        mock_agent_instance.prompt_manager = AsyncMock()
-        mock_create_agent.return_value = mock_agent_instance
-        yield mock_agent_instance
-
-
-@pytest.fixture
-def mock_controller():
-    with patch('openhands.core.cli.create_controller') as mock_create_controller:
-        mock_controller_instance = AsyncMock()
-        # Mock run_until_done to finish immediately
-        mock_controller_instance.run_until_done = AsyncMock(return_value=None)
-        mock_create_controller.return_value = (mock_controller_instance, None)
-        yield mock_controller_instance
-
-
-@pytest.fixture
-def task_file(tmp_path: Path) -> Path:
-    # Create a temporary file with our task
-    task_file = tmp_path / 'task.txt'
-    task_file.write_text('Ask me what your task is')
-    return task_file
-
-
-@pytest.fixture
-def mock_config(task_file: Path):
-    with patch('openhands.core.cli.parse_arguments') as mock_parse_args:
-        # Create a proper Namespace with our temporary task file
-        args = Namespace(file=str(task_file), task=None, directory=None)
-        mock_parse_args.return_value = args
-        with patch('openhands.core.cli.setup_config_from_args') as mock_setup_config:
-            mock_config = AppConfig()
-            mock_setup_config.return_value = mock_config
-            yield mock_config
-
-
-@pytest.mark.asyncio
-async def test_cli_session_id_output(
-    mock_runtime, mock_agent, mock_controller, mock_config
-):
-    # status_callback is set when initializing the runtime
-    mock_controller.status_callback = None
-
-    buffer = StringIO()
-
-    # Use input patch just for the exit command
-    with patch('builtins.input', return_value='exit'):
-        with create_app_session(
-            input=create_pipe_input(), output=create_output(stdout=buffer)
-        ):
-            # Create a task for main
-            main_task = asyncio.create_task(main(asyncio.get_event_loop()))
-
-            # Give it a moment to display the session ID
-            await asyncio.sleep(0.1)
-
-            # Trigger agent state change to STOPPED to end the main loop
-            event = AgentStateChangedObservation(
-                content='Stop', agent_state=AgentState.STOPPED
-            )
-            event._source = EventSource.AGENT
-            await mock_runtime.event_stream.add_event(event)
-
-            # Wait for main to finish with a timeout
-            try:
-                await asyncio.wait_for(main_task, timeout=1.0)
-            except asyncio.TimeoutError:
-                main_task.cancel()
-
-            buffer.seek(0)
-            output = buffer.read()
-
-            # Check the output
-            assert 'Session ID:' in output
-            # Also verify that our task message was processed
-            assert 'Ask me what your task is' in str(mock_runtime.mock_calls)

tests/unit/test_cli_startup.py

@@ -0,0 +1,301 @@
+import asyncio
+from datetime import datetime
+from io import StringIO
+from unittest.mock import AsyncMock, Mock, patch
+
+import pytest
+from prompt_toolkit.application import create_app_session
+from prompt_toolkit.input import create_pipe_input
+from prompt_toolkit.output import create_output
+
+from openhands.core.cli import main
+from openhands.core.config import AppConfig
+
+
+class MockEventStream:
+    def __init__(self):
+        self._subscribers = {}
+        self.cur_id = 0
+
+    def subscribe(self, subscriber_id, callback, callback_id):
+        if subscriber_id not in self._subscribers:
+            self._subscribers[subscriber_id] = {}
+        self._subscribers[subscriber_id][callback_id] = callback
+
+    def unsubscribe(self, subscriber_id, callback_id):
+        if (
+            subscriber_id in self._subscribers
+            and callback_id in self._subscribers[subscriber_id]
+        ):
+            del self._subscribers[subscriber_id][callback_id]
+
+    def add_event(self, event, source):
+        event._id = self.cur_id
+        self.cur_id += 1
+        event._source = source
+        event._timestamp = datetime.now().isoformat()
+
+        for subscriber_id in self._subscribers:
+            for callback_id, callback in self._subscribers[subscriber_id].items():
+                callback(event)
+
+
+@pytest.fixture
+def mock_agent():
+    with patch('openhands.core.cli.create_agent') as mock_create_agent:
+        mock_agent_instance = AsyncMock()
+        mock_agent_instance.name = 'test-agent'
+        mock_agent_instance.llm = AsyncMock()
+        mock_agent_instance.llm.config = AsyncMock()
+        mock_agent_instance.llm.config.model = 'test-model'
+        mock_agent_instance.llm.config.base_url = 'http://test'
+        mock_agent_instance.llm.config.max_message_chars = 1000
+        mock_agent_instance.config = AsyncMock()
+        mock_agent_instance.config.disabled_microagents = []
+        mock_agent_instance.sandbox_plugins = []
+        mock_agent_instance.prompt_manager = AsyncMock()
+        mock_create_agent.return_value = mock_agent_instance
+        yield mock_agent_instance
+
+
+@pytest.fixture
+def mock_controller():
+    with patch('openhands.core.cli.create_controller') as mock_create_controller:
+        mock_controller_instance = AsyncMock()
+        mock_controller_instance.state.agent_state = None
+        # Mock run_until_done to finish immediately
+        mock_controller_instance.run_until_done = AsyncMock(return_value=None)
+        mock_create_controller.return_value = (mock_controller_instance, None)
+        yield mock_controller_instance
+
+
+@pytest.fixture
+def mock_config():
+    with patch('openhands.core.cli.parse_arguments') as mock_parse_args:
+        args = Mock()
+        args.file = None
+        args.task = None
+        args.directory = None
+        mock_parse_args.return_value = args
+        with patch('openhands.core.cli.setup_config_from_args') as mock_setup_config:
+            mock_config = AppConfig()
+            mock_config.cli_multiline_input = False
+            mock_config.security = Mock()
+            mock_config.security.confirmation_mode = False
+            mock_config.sandbox = Mock()
+            mock_config.sandbox.selected_repo = None
+            mock_config.workspace_base = '/test'
+            mock_setup_config.return_value = mock_config
+            yield mock_config
+
+
+@pytest.fixture
+def mock_memory():
+    with patch('openhands.core.cli.create_memory') as mock_create_memory:
+        mock_memory_instance = AsyncMock()
+        mock_create_memory.return_value = mock_memory_instance
+        yield mock_memory_instance
+
+
+@pytest.fixture
+def mock_read_task():
+    with patch('openhands.core.cli.read_task') as mock_read_task:
+        mock_read_task.return_value = None
+        yield mock_read_task
+
+
+@pytest.fixture
+def mock_runtime():
+    with patch('openhands.core.cli.create_runtime') as mock_create_runtime:
+        mock_runtime_instance = AsyncMock()
+
+        mock_event_stream = MockEventStream()
+        mock_runtime_instance.event_stream = mock_event_stream
+
+        mock_runtime_instance.connect = AsyncMock()
+
+        # Ensure status_callback is None
+        mock_runtime_instance.status_callback = None
+        # Mock get_microagents_from_selected_repo
+        mock_runtime_instance.get_microagents_from_selected_repo = Mock(return_value=[])
+        mock_create_runtime.return_value = mock_runtime_instance
+        yield mock_runtime_instance
+
+
+@pytest.mark.asyncio
+async def test_cli_startup_folder_security_confirmation_agree(
+    mock_runtime, mock_controller, mock_config, mock_agent, mock_memory, mock_read_task
+):
+    buffer = StringIO()
+
+    with patch(
+        'openhands.core.cli.manage_openhands_file', return_value=False
+    ) as mock_manage_openhands_file:
+        with patch(
+            'openhands.core.cli.cli_confirm', return_value=True
+        ) as mock_cli_confirm:
+            with create_app_session(
+                input=create_pipe_input(), output=create_output(stdout=buffer)
+            ):
+                mock_controller.status_callback = None
+
+                main_task = asyncio.create_task(main(asyncio.get_event_loop()))
+
+                await asyncio.sleep(0.1)
+
+                try:
+                    await asyncio.wait_for(main_task, timeout=0.1)
+                except Exception:
+                    main_task.cancel()
+
+                buffer.seek(0)
+                output = buffer.read()
+
+                # ASCII art banner
+                assert '___' in output
+
+                # Version information
+                assert 'OpenHands CLI v' in output
+
+                # Session initialization
+                assert 'Initializing session' in output
+
+                # Folder security confirmation
+                assert 'Do you trust the files in this folder?' in output
+                assert '/test' in output
+                assert (
+                    'OpenHands may read and execute files in this folder with your permission.'
+                    in output
+                )
+
+                # Confirmation prompt
+                mock_manage_openhands_file.assert_any_call('/test')
+                mock_cli_confirm.assert_called_once_with(
+                    'Do you wish to continue?', ['Yes, proceed', 'No, exit']
+                )
+                mock_manage_openhands_file.assert_any_call('/test', add_to_trusted=True)
+
+                # Session initialization complete
+                assert 'Initialized session' in output
+
+                # Welcome message
+                assert "Let's start building!" in output
+                assert 'What do you want to build?' in output
+                assert 'Type /help for help' in output
+
+
+@pytest.mark.asyncio
+async def test_cli_startup_folder_security_confirmation_disagree(
+    mock_runtime, mock_controller, mock_config, mock_agent, mock_memory, mock_read_task
+):
+    buffer = StringIO()
+
+    with patch(
+        'openhands.core.cli.manage_openhands_file', return_value=False
+    ) as mock_manage_openhands_file:
+        with patch(
+            'openhands.core.cli.cli_confirm', return_value=False
+        ) as mock_cli_confirm:
+            with create_app_session(
+                input=create_pipe_input(), output=create_output(stdout=buffer)
+            ):
+                mock_controller.status_callback = None
+
+                main_task = asyncio.create_task(main(asyncio.get_event_loop()))
+
+                await asyncio.sleep(0.1)
+
+                try:
+                    await asyncio.wait_for(main_task, timeout=0.1)
+                except Exception:
+                    main_task.cancel()
+
+                buffer.seek(0)
+                output = buffer.read()
+
+                # ASCII art banner
+                assert '___' in output
+
+                # Version information
+                assert 'OpenHands CLI v' in output
+
+                # Session initialization
+                assert 'Initializing session' in output
+
+                # Folder security confirmation
+                assert 'Do you trust the files in this folder?' in output
+                assert '/test' in output
+                assert (
+                    'OpenHands may read and execute files in this folder with your permission.'
+                    in output
+                )
+
+                # Confirmation prompt
+                mock_manage_openhands_file.assert_called_once_with('/test')
+                mock_cli_confirm.assert_called_once_with(
+                    'Do you wish to continue?', ['Yes, proceed', 'No, exit']
+                )
+
+                # Session initialization complete
+                assert 'Initialized session' not in output
+
+                # Welcome message
+                assert "Let's start building!" not in output
+                assert 'What do you want to build?' not in output
+                assert 'Type /help for help' not in output
+
+
+@pytest.mark.asyncio
+async def test_cli_startup_trusted_folder(
+    mock_runtime, mock_controller, mock_config, mock_agent, mock_memory, mock_read_task
+):
+    buffer = StringIO()
+
+    with patch('openhands.core.cli.manage_openhands_file', return_value=True):
+        with patch(
+            'openhands.core.cli.cli_confirm', return_value=True
+        ) as mock_cli_confirm:
+            with create_app_session(
+                input=create_pipe_input(), output=create_output(stdout=buffer)
+            ):
+                mock_controller.status_callback = None
+
+                main_task = asyncio.create_task(main(asyncio.get_event_loop()))
+
+                await asyncio.sleep(0.1)
+
+                try:
+                    await asyncio.wait_for(main_task, timeout=0.1)
+                except Exception:
+                    main_task.cancel()
+
+                buffer.seek(0)
+                output = buffer.read()
+
+                # ASCII art banner
+                assert '___' in output
+
+                # Version information
+                assert 'OpenHands CLI v' in output
+
+                # Session initialization
+                assert 'Initializing session' in output
+
+                # Folder security confirmation should not be shown
+                assert 'Do you trust the files in this folder?' not in output
+                assert '/test' not in output
+                assert (
+                    'OpenHands may read and execute files in this folder with your permission.'
+                    not in output
+                )
+
+                # Confirmation prompt should not be shown
+                mock_cli_confirm.assert_not_called()
+
+                # Session initialization
+                assert 'Initialized session' in output
+
+                # Welcome message
+                assert "Let's start building!" in output
+                assert 'What do you want to build?' in output
+                assert 'Type /help for help' in output

tests/unit/test_codeact_agent.py

@@ -80,9 +80,9 @@ def test_step_with_pending_actions(agent: CodeActAgent):
 
 def test_get_tools_default():
     tools = get_tools(
-        codeact_enable_jupyter=True,
-        codeact_enable_llm_editor=True,
-        codeact_enable_browsing=True,
+        enable_jupyter=True,
+        enable_llm_editor=True,
+        enable_browsing=True,
     )
     assert len(tools) > 0
 
@@ -97,9 +97,9 @@ def test_get_tools_default():
 def test_get_tools_with_options():
     # Test with all options enabled
     tools = get_tools(
-        codeact_enable_browsing=True,
-        codeact_enable_jupyter=True,
-        codeact_enable_llm_editor=True,
+        enable_browsing=True,
+        enable_jupyter=True,
+        enable_llm_editor=True,
     )
     tool_names = [tool['function']['name'] for tool in tools]
     assert 'browser' in tool_names
@@ -108,9 +108,9 @@ def test_get_tools_with_options():
 
     # Test with all options disabled
     tools = get_tools(
-        codeact_enable_browsing=False,
-        codeact_enable_jupyter=False,
-        codeact_enable_llm_editor=False,
+        enable_browsing=False,
+        enable_jupyter=False,
+        enable_llm_editor=False,
     )
     tool_names = [tool['function']['name'] for tool in tools]
     assert 'browser' not in tool_names

tests/unit/test_condenser.py

@@ -331,10 +331,7 @@ def test_llm_summarizing_condenser_from_config():
     config = LLMSummarizingCondenserConfig(
         max_size=50,
         keep_first=10,
-        llm_config=LLMConfig(
-            model='gpt-4o',
-            api_key='test_key',
-        ),
+        llm_config=LLMConfig(model='gpt-4o', api_key='test_key', caching_prompt=True),
     )
     condenser = Condenser.from_config(config)
 
@@ -344,6 +341,10 @@ def test_llm_summarizing_condenser_from_config():
     assert condenser.max_size == 50
     assert condenser.keep_first == 10
 
+    # Since this condenser can't take advantage of caching, we intercept the
+    # passed config and manually flip the caching prompt to False.
+    assert not condenser.llm.config.caching_prompt
+
 
 def test_llm_summarizing_condenser_invalid_config():
     """Test that LLMSummarizingCondenser raises error when keep_first > max_size."""
@@ -474,6 +475,7 @@ def test_llm_attention_condenser_from_config():
         llm_config=LLMConfig(
             model='gpt-4o',
             api_key='test_key',
+            caching_prompt=True,
         ),
     )
     condenser = Condenser.from_config(config)
@@ -484,6 +486,10 @@ def test_llm_attention_condenser_from_config():
     assert condenser.max_size == 50
     assert condenser.keep_first == 10
 
+    # Since this condenser can't take advantage of caching, we intercept the
+    # passed config and manually flip the caching prompt to False.
+    assert not condenser.llm.config.caching_prompt
+
 
 def test_llm_attention_condenser_invalid_config():
     """Test that LLMAttentionCondenser raises an error if the configured LLM doesn't support response schema."""
@@ -614,6 +620,7 @@ def test_structured_summary_condenser_from_config():
         llm_config=LLMConfig(
             model='gpt-4o',
             api_key='test_key',
+            caching_prompt=True,
         ),
     )
     condenser = Condenser.from_config(config)
@@ -624,6 +631,10 @@ def test_structured_summary_condenser_from_config():
     assert condenser.max_size == 50
     assert condenser.keep_first == 10
 
+    # Since this condenser can't take advantage of caching, we intercept the
+    # passed config and manually flip the caching prompt to False.
+    assert not condenser.llm.config.caching_prompt
+
 
 def test_structured_summary_condenser_invalid_config():
     """Test that StructuredSummaryCondenser raises error when keep_first > max_size."""

tests/unit/test_config.py

@@ -834,9 +834,7 @@ def test_api_keys_repr_str():
 
     # Test AgentConfig
     # No attrs in AgentConfig have 'key' or 'token' in their name
-    agent_config = AgentConfig(
-        enable_prompt_extensions=True, codeact_enable_browsing=False
-    )
+    agent_config = AgentConfig(enable_prompt_extensions=True, enable_browsing=False)
     for attr_name in AgentConfig.model_fields.keys():
         if not attr_name.startswith('__'):
             assert (
@@ -941,7 +939,7 @@ max_budget_per_task = 4.0
 enable_prompt_extensions = true
 
 [agent.BrowsingAgent]
-codeact_enable_jupyter = false
+enable_jupyter = false
 """
 
     with open(temp_toml_file, 'w') as f:
@@ -952,7 +950,7 @@ codeact_enable_jupyter = false
     codeact_config = default_config.get_agent_configs().get('CodeActAgent')
     assert codeact_config.enable_prompt_extensions is True
     browsing_config = default_config.get_agent_configs().get('BrowsingAgent')
-    assert browsing_config.codeact_enable_jupyter is False
+    assert browsing_config.enable_jupyter is False
 
 
 def test_get_agent_config_arg(temp_toml_file):
@@ -963,11 +961,11 @@ max_budget_per_task = 4.0
 
 [agent.CodeActAgent]
 enable_prompt_extensions = false
-codeact_enable_browsing = false
+enable_browsing = false
 
 [agent.BrowsingAgent]
 enable_prompt_extensions = true
-codeact_enable_jupyter = false
+enable_jupyter = false
 """
 
     with open(temp_toml_file, 'w') as f:
@@ -975,11 +973,11 @@ codeact_enable_jupyter = false
 
     agent_config = get_agent_config_arg('CodeActAgent', temp_toml_file)
     assert not agent_config.enable_prompt_extensions
-    assert not agent_config.codeact_enable_browsing
+    assert not agent_config.enable_browsing
 
     agent_config2 = get_agent_config_arg('BrowsingAgent', temp_toml_file)
     assert agent_config2.enable_prompt_extensions
-    assert not agent_config2.codeact_enable_jupyter
+    assert not agent_config2.enable_jupyter
 
 
 def test_agent_config_custom_group_name(temp_toml_file):
@@ -1015,8 +1013,8 @@ def test_agent_config_from_toml_section():
     # Test with base config and custom configs
     agent_section = {
         'enable_prompt_extensions': True,
-        'codeact_enable_browsing': True,
-        'CustomAgent1': {'codeact_enable_browsing': False},
+        'enable_browsing': True,
+        'CustomAgent1': {'enable_browsing': False},
         'CustomAgent2': {'enable_prompt_extensions': False},
         'InvalidAgent': {
             'invalid_field': 'some_value'  # This should be skipped but not affect others
@@ -1029,15 +1027,15 @@ def test_agent_config_from_toml_section():
     # Verify the base config was correctly parsed
     assert 'agent' in result
     assert result['agent'].enable_prompt_extensions is True
-    assert result['agent'].codeact_enable_browsing is True
+    assert result['agent'].enable_browsing is True
 
     # Verify custom configs were correctly parsed and inherit from base
     assert 'CustomAgent1' in result
-    assert result['CustomAgent1'].codeact_enable_browsing is False  # Overridden
+    assert result['CustomAgent1'].enable_browsing is False  # Overridden
     assert result['CustomAgent1'].enable_prompt_extensions is True  # Inherited
 
     assert 'CustomAgent2' in result
-    assert result['CustomAgent2'].codeact_enable_browsing is True  # Inherited
+    assert result['CustomAgent2'].enable_browsing is True  # Inherited
     assert result['CustomAgent2'].enable_prompt_extensions is False  # Overridden
 
     # Verify the invalid config was skipped
@@ -1051,10 +1049,10 @@ def test_agent_config_from_toml_section_with_invalid_base():
     # Test with invalid base config but valid custom configs
     agent_section = {
         'invalid_field': 'some_value',  # This should be ignored in base config
-        'codeact_enable_jupyter': 'not_a_bool',  # This should cause validation error
+        'enable_jupyter': 'not_a_bool',  # This should cause validation error
         'CustomAgent': {
-            'codeact_enable_browsing': False,
-            'codeact_enable_jupyter': True,
+            'enable_browsing': False,
+            'enable_jupyter': True,
         },
     }
 
@@ -1063,10 +1061,10 @@ def test_agent_config_from_toml_section_with_invalid_base():
 
     # Verify a default base config was created despite the invalid fields
     assert 'agent' in result
-    assert result['agent'].codeact_enable_browsing is True  # Default value
-    assert result['agent'].codeact_enable_jupyter is True  # Default value
+    assert result['agent'].enable_browsing is True  # Default value
+    assert result['agent'].enable_jupyter is True  # Default value
 
     # Verify custom config was still processed correctly
     assert 'CustomAgent' in result
-    assert result['CustomAgent'].codeact_enable_browsing is False
-    assert result['CustomAgent'].codeact_enable_jupyter is True
+    assert result['CustomAgent'].enable_browsing is False
+    assert result['CustomAgent'].enable_jupyter is True

tests/unit/test_llm.py

@@ -449,35 +449,84 @@ def test_completion_retry_with_llm_no_response_error_nonzero_temp(
     This test verifies that when LLMNoResponseError is raised with a non-zero temperature:
     1. The retry mechanism is triggered
     2. The temperature remains unchanged (not set to 0.2)
-    3. After all retries are exhausted, the exception is propagated
+    3. After all retries are exhausted, the error is raised
     """
-    # Define a side effect function that always raises LLMNoResponseError
     mock_litellm_completion.side_effect = LLMNoResponseError(
         'LLM did not return a response'
     )
 
-    # Create LLM instance and make a completion call with non-zero temperature
     llm = LLM(config=default_config)
-
-    # We expect this to raise an exception after all retries are exhausted
     with pytest.raises(LLMNoResponseError):
         llm.completion(
             messages=[{'role': 'user', 'content': 'Hello!'}],
             stream=False,
-            temperature=0.7,  # Initial temperature is non-zero
+            temperature=0.7,  # Non-zero temperature
         )
 
-    # Verify that litellm_completion was called multiple times (retries happened)
-    # The default_config has num_retries=2, so it should be called 2 times
-    assert mock_litellm_completion.call_count == 2
+    # Verify that litellm_completion was called the expected number of times
+    assert mock_litellm_completion.call_count == default_config.num_retries
 
-    # Check the temperature in the first call (should be 0.7)
-    first_call_kwargs = mock_litellm_completion.call_args_list[0][1]
-    assert first_call_kwargs.get('temperature') == 0.7
+    # Check that all calls used the original temperature
+    for call in mock_litellm_completion.call_args_list:
+        assert call[1].get('temperature') == 0.7
 
-    # Check the temperature in the second call (should remain 0.7, not changed to 0.2)
-    second_call_kwargs = mock_litellm_completion.call_args_list[1][1]
-    assert second_call_kwargs.get('temperature') == 0.7
+
+@patch('openhands.llm.llm.litellm.get_model_info')
+@patch('openhands.llm.llm.httpx.get')
+def test_gemini_25_pro_function_calling(mock_httpx_get, mock_get_model_info):
+    """
+    Test that Gemini 2.5 Pro models have function calling enabled by default.
+    This includes testing various model name formats with different prefixes.
+    """
+    # Mock the model info response
+    mock_get_model_info.return_value = {
+        'max_input_tokens': 8000,
+        'max_output_tokens': 2000,
+    }
+
+    # Mock the httpx response for litellm proxy
+    mock_response = MagicMock()
+    mock_response.json.return_value = {
+        'data': [
+            {
+                'model_name': 'gemini-2.5-pro-preview-03-25',
+                'model_info': {
+                    'max_input_tokens': 8000,
+                    'max_output_tokens': 2000,
+                },
+            }
+        ]
+    }
+    mock_httpx_get.return_value = mock_response
+
+    # Test cases with model names and expected function calling support
+    test_cases = [
+        # Base model names
+        ('gemini-2.5-pro-preview-03-25', True),
+        ('gemini-2.5-pro-exp-03-25', True),
+        # With gemini/ prefix
+        ('gemini/gemini-2.5-pro-preview-03-25', True),
+        ('gemini/gemini-2.5-pro-exp-03-25', True),
+        # With litellm_proxy/ prefix
+        ('litellm_proxy/gemini-2.5-pro-preview-03-25', True),
+        ('litellm_proxy/gemini-2.5-pro-exp-03-25', True),
+        # With openrouter/gemini/ prefix
+        ('openrouter/gemini/gemini-2.5-pro-preview-03-25', True),
+        ('openrouter/gemini/gemini-2.5-pro-exp-03-25', True),
+        # With litellm_proxy/gemini/ prefix
+        ('litellm_proxy/gemini/gemini-2.5-pro-preview-03-25', True),
+        ('litellm_proxy/gemini/gemini-2.5-pro-exp-03-25', True),
+        # Control case - a model that shouldn't have function calling
+        ('gemini-1.0-pro', False),
+    ]
+
+    for model_name, expected_support in test_cases:
+        config = LLMConfig(model=model_name, api_key='test_key')
+        llm = LLM(config)
+
+        assert (
+            llm.is_function_calling_active() == expected_support
+        ), f'Expected function calling support to be {expected_support} for model {model_name}'
 
 
 @patch('openhands.llm.llm.litellm_completion')