Resolve merge conflicts with main

- Combined dependencies from both branches in pyproject.toml
- Removed explicit mcp dependency to avoid conflict with fastmcp
- Added both proxy_agent and loc_agent to agenthub imports
- Included a2a_client in agent skills
- Fixed mypy type errors in proxy agent and a2a client
- Regenerated poetry.lock file

.devcontainer/devcontainer.json

@@ -12,5 +12,8 @@
 		"ghcr.io/devcontainers/features/node:1": {},
 	},
 	"postCreateCommand": ".devcontainer/setup.sh",
-	"runArgs": ["--network=host"],
+	"runArgs": ["--add-host=host.docker.internal:host-gateway"],
+	"containerEnv": {
+		"DOCKER_HOST_ADDR": "host.docker.internal"
+	},
 }

containers/dev/compose.yml

@@ -10,13 +10,13 @@ services:
     environment:
       - BACKEND_HOST=${BACKEND_HOST:-"0.0.0.0"}
       - SANDBOX_API_HOSTNAME=host.docker.internal
+      - DOCKER_HOST_ADDR=host.docker.internal
       #
       - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.43-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:
       - "3000:3000"
-    network_mode: host
     extra_hosts:
       - "host.docker.internal:host-gateway"
     volumes:

docs/usage/local-setup.mdx

@@ -10,6 +10,7 @@ description: Getting started with running OpenHands on your own.
 - MacOS with [Docker Desktop support](https://docs.docker.com/desktop/setup/install/mac-install/#system-requirements)
 - Linux
 - Windows with [WSL](https://learn.microsoft.com/en-us/windows/wsl/install) and [Docker Desktop support](https://docs.docker.com/desktop/setup/install/windows-install/#system-requirements)
+- Windows without WSL (see [Windows Without WSL Guide](/usage/windows-without-wsl))
 
 A system with a modern processor and a minimum of **4GB RAM** is recommended to run OpenHands.
 
@@ -55,6 +56,10 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
   The docker command below to start the app must be run inside the WSL terminal.
   </Note>
 
+  **Alternative: Windows without WSL**
+
+  If you prefer to run OpenHands on Windows without WSL or Docker, see our [Windows Without WSL Guide](/usage/windows-without-wsl).
+
 </Accordion>
 
 </AccordionGroup>

docs/usage/windows-without-wsl.mdx

@@ -0,0 +1,200 @@
+---
+title: Windows Without WSL
+description: Running OpenHands GUI on Windows without using WSL or Docker
+---
+
+# Running OpenHands GUI on Windows Without WSL
+
+This guide provides step-by-step instructions for running OpenHands on a Windows machine without using WSL or Docker.
+
+## Prerequisites
+
+1. **Windows 10/11** - A modern Windows operating system
+2. **PowerShell 7+** - While Windows PowerShell comes pre-installed on Windows 10/11, PowerShell 7+ is strongly recommended to avoid compatibility issues (see Troubleshooting section for "System.Management.Automation" errors)
+3. **.NET Core Runtime** - Required for the PowerShell integration via pythonnet
+4. **Python 3.12 or 3.13** - Python 3.12 or 3.13 is required (Python 3.14 is not supported due to pythonnet compatibility)
+5. **Git** - For cloning the repository and version control
+6. **Node.js and npm** - For running the frontend
+
+## Step 1: Install Required Software
+
+1. **Install Python 3.12 or 3.13**
+   - Download Python 3.12.x or 3.13.x from [python.org](https://www.python.org/downloads/)
+   - During installation, check "Add Python to PATH"
+   - Verify installation by opening PowerShell and running:
+     ```powershell
+     python --version
+     ```
+
+2. **Install PowerShell 7**
+   - Download and install PowerShell 7 from the [official PowerShell GitHub repository](https://github.com/PowerShell/PowerShell/releases)
+   - Choose the MSI installer appropriate for your system (x64 for most modern computers)
+   - Run the installer with default options
+   - Verify installation by opening a new terminal and running:
+     ```powershell
+     pwsh --version
+     ```
+   - Using PowerShell 7 (pwsh) instead of Windows PowerShell will help avoid "System.Management.Automation" errors
+
+3. **Install .NET Core Runtime**
+   - Download and install the .NET Core Runtime from [Microsoft's .NET download page](https://dotnet.microsoft.com/download)
+   - Choose the latest .NET Core Runtime (not SDK)
+   - Verify installation by opening PowerShell and running:
+     ```powershell
+     dotnet --info
+     ```
+   - This step is required for the PowerShell integration via pythonnet. Without it, OpenHands will fall back to a more limited PowerShell implementation.
+
+4. **Install Git**
+   - Download Git from [git-scm.com](https://git-scm.com/download/win)
+   - Use default installation options
+   - Verify installation:
+     ```powershell
+     git --version
+     ```
+
+5. **Install Node.js and npm**
+   - Download Node.js from [nodejs.org](https://nodejs.org/) (LTS version recommended)
+   - During installation, accept the default options which will install npm as well
+   - Verify installation:
+     ```powershell
+     node --version
+     npm --version
+     ```
+
+6. **Install Poetry**
+   - Open PowerShell as Administrator and run:
+     ```powershell
+     (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
+     ```
+   - Add Poetry to your PATH:
+     ```powershell
+     $env:Path += ";$env:APPDATA\Python\Scripts"
+     ```
+   - Verify installation:
+     ```powershell
+     poetry --version
+     ```
+
+## Step 2: Clone and Set Up OpenHands
+
+1. **Clone the Repository**
+   ```powershell
+   git clone https://github.com/All-Hands-AI/OpenHands.git
+   cd OpenHands
+   ```
+
+2. **Install Dependencies**
+   ```powershell
+   poetry install
+   ```
+
+   This will install all required dependencies, including:
+   - pythonnet - Required for Windows PowerShell integration
+   - All other OpenHands dependencies
+
+## Step 3: Run OpenHands
+
+1. **Build the Frontend**
+   ```powershell
+   cd frontend
+   npm install
+   npm run build
+   cd ..
+   ```
+
+   This will build the frontend files that the backend will serve.
+
+2. **Start the Backend**
+   ```powershell
+   # Make sure to use PowerShell 7 (pwsh) instead of Windows PowerShell
+   pwsh
+   $env:RUNTIME="local"; poetry run uvicorn openhands.server.listen:app --host 0.0.0.0 --port 3000 --reload --reload-exclude "./workspace"
+   ```
+
+   This will start the OpenHands app using the local runtime with PowerShell integration, available at `localhost:3000`.
+
+   > **Note**: If you encounter a `RuntimeError: Directory './frontend/build' does not exist` error, make sure you've built the frontend first using the command above.
+
+   > **Important**: Using PowerShell 7 (pwsh) instead of Windows PowerShell is recommended to avoid "System.Management.Automation" errors. If you encounter this error, see the Troubleshooting section below.
+
+3. **Alternatively, Run the Frontend in Development Mode (in a separate PowerShell window)**
+   ```powershell
+   cd frontend
+   npm run dev
+   ```
+
+4. **Access the OpenHands GUI**
+
+   Open your browser and navigate to:
+   ```
+   http://localhost:3000
+   ```
+
+   > **Note**: If you're running the frontend in development mode (using `npm run dev`), use port 3001 instead: `http://localhost:3001`
+
+## Limitations on Windows
+
+When running OpenHands on Windows without WSL or Docker, be aware of the following limitations:
+
+1. **Browser Tool Not Supported**: The browser tool is not currently supported on Windows.
+
+2. **.NET Core Requirement**: The PowerShell integration requires .NET Core Runtime to be installed. If .NET Core is not available, OpenHands will automatically fall back to a more limited PowerShell implementation with reduced functionality.
+
+3. **Interactive Shell Commands**: Some interactive shell commands may not work as expected. The PowerShell session implementation has limitations compared to the bash session used on Linux/macOS.
+
+4. **Path Handling**: Windows uses backslashes (`\`) in paths, which may require adjustments when working with code examples designed for Unix-like systems.
+
+## Troubleshooting
+
+### "System.Management.Automation" Not Found Error
+
+If you encounter an error message stating that "System.Management.Automation" was not found, this typically indicates that you have a minimal version of PowerShell installed or that the .NET components required for PowerShell integration are missing.
+
+> **IMPORTANT**: This error is most commonly caused by using the built-in Windows PowerShell (powershell.exe) instead of PowerShell 7 (pwsh.exe). Even if you installed PowerShell 7 during the prerequisites, you may still be using the older Windows PowerShell by default.
+
+To resolve this issue:
+
+1. **Install the latest version of PowerShell 7** from the official Microsoft repository:
+   - Visit [https://github.com/PowerShell/PowerShell/releases](https://github.com/PowerShell/PowerShell/releases)
+   - Download and install the latest MSI package for your system architecture (x64 for most systems)
+   - During installation, ensure you select the following options:
+     - "Add PowerShell to PATH environment variable"
+     - "Register Windows PowerShell 7 as the default shell"
+     - "Enable PowerShell remoting"
+   - The installer will place PowerShell 7 in `C:\Program Files\PowerShell\7` by default
+
+2. **Restart your terminal or command prompt** to ensure the new PowerShell is available
+
+3. **Verify the installation** by running:
+   ```powershell
+   pwsh --version
+   ```
+
+   You should see output indicating PowerShell 7.x.x
+
+4. **Run OpenHands using PowerShell 7** instead of Windows PowerShell:
+   ```powershell
+   pwsh
+   cd path\to\openhands
+   $env:RUNTIME="local"; poetry run uvicorn openhands.server.listen:app --host 0.0.0.0 --port 3000 --reload --reload-exclude "./workspace"
+   ```
+
+   > **Note**: Make sure you're explicitly using `pwsh` (PowerShell 7) and not `powershell` (Windows PowerShell). The command prompt or terminal title should say "PowerShell 7" rather than just "Windows PowerShell".
+
+5. **If the issue persists**, ensure that you have the .NET Runtime installed:
+   - Download and install the latest .NET Runtime from [Microsoft's .NET download page](https://dotnet.microsoft.com/download)
+   - Choose ".NET Runtime" (not SDK) version 6.0 or later
+   - After installation, verify it's properly installed by running:
+     ```powershell
+     dotnet --info
+     ```
+   - Restart your computer after installation
+   - Try running OpenHands again
+
+6. **Ensure that the .NET Framework is properly installed** on your system:
+   - Go to Control Panel > Programs > Programs and Features > Turn Windows features on or off
+   - Make sure ".NET Framework 4.8 Advanced Services" is enabled
+   - Click OK and restart if prompted
+
+This error occurs because OpenHands uses the pythonnet package to interact with PowerShell, which requires the System.Management.Automation assembly from the .NET framework. A minimal PowerShell installation or older Windows PowerShell (rather than PowerShell 7+) might not include all the necessary components for this integration.

evaluation/benchmarks/swe_bench/prompts/swe_claude.j2

@@ -0,0 +1,65 @@
+<uploaded_files>
+/workspace/{{ workspace_dir_name }}
+</uploaded_files>
+
+I've uploaded a python code repository in the directory {{ workspace_dir_name }}. Consider the following issue description:
+
+<issue_description>
+{{ instance.problem_statement }}
+</issue_description>
+
+Can you help me implement the necessary changes to the repository so that the requirements specified in the <issue_description> are met?
+I've already taken care of all changes to any of the test files described in the <issue_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!
+Also the development Python environment is already set up for you (i.e., all dependencies already installed), so you don't need to install other packages.
+Your task is to make the minimal changes to non-test files in the /workspace/{{ workspace_dir_name }} directory to ensure the <issue_description> is satisfied.
+
+Follow these phases to resolve the issue:
+
+Phase 1. READING: read the problem and reword it in clearer terms
+   1.1 If there are code or config snippets. Express in words any best practices or conventions in them.
+   1.2 Hightlight message errors, method names, variables, file names, stack traces, and technical details.
+   1.3 Explain the problem in clear terms.
+   1.4 Enumerate the steps to reproduce the problem.
+   1.5 Hightlight any best practices to take into account when testing and fixing the issue
+
+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
+
+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.
+   3.2 Identify all files related to the problem statement.
+   3.3 Propose the methods and files to fix the issue and explain why.
+   3.4 From the possible file locations, select the most likely location to fix the issue.
+
+Phase 4. TEST CREATION: before implementing any fix, create a script to reproduce and verify the issue.
+   4.1 Look at existing test files in the repository to understand the test format/structure.
+   4.2 Create a minimal reproduction script that reproduces the located issue.
+   4.3 Run the reproduction script to confirm you are reproducing the issue.
+   4.4 Adjust the reproduction script as necessary.
+
+Phase 5. FIX ANALYSIS: state clearly the problem and how to fix it
+   5.1 State clearly what the problem is.
+   5.2 State clearly where the problem is located.
+   5.3 State clearly how the test reproduces the issue.
+   5.4 State clearly the best practices to take into account in the fix.
+   5.5 State clearly how to fix the problem.
+
+Phase 6. FIX IMPLEMENTATION: Edit the source code to implement your chosen solution.
+   6.1 Make minimal, focused changes to fix the issue.
+
+Phase 7. VERIFICATION: Test your implementation thoroughly.
+   7.1 Run your reproduction script to verify the fix works.
+   7.2 Add edge cases to your test script to ensure comprehensive coverage.
+   7.3 Run existing tests related to the modified code to ensure you haven't broken anything.
+
+8. FINAL REVIEW: Carefully re-read the problem description and compare your changes with the base commit {{ instance.base_commit }}.
+   8.1 Ensure you've fully addressed all requirements.
+   8.2 Run any tests in the repository related to:
+     8.2.1 The issue you are fixing
+     8.2.2 The files you modified
+     8.2.3 The functions you changed
+   8.3 If any tests fail, revise your implementation until all tests pass
+
+Be thorough in your exploration, testing, and reasoning. It's fine if your thinking process is lengthy - quality and completeness are more important than brevity.

evaluation/benchmarks/swe_bench/prompts/swe_default.j2

@@ -0,0 +1,65 @@
+<uploaded_files>
+/workspace/{{ workspace_dir_name }}
+</uploaded_files>
+
+I've uploaded a python code repository in the directory {{ workspace_dir_name }}. Consider the following issue description:
+
+<issue_description>
+{{ instance.problem_statement }}
+</issue_description>
+
+Can you help me implement the necessary changes to the repository so that the requirements specified in the <issue_description> are met?
+I've already taken care of all changes to any of the test files described in the <issue_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!
+Also the development Python environment is already set up for you (i.e., all dependencies already installed), so you don't need to install other packages.
+Your task is to make the minimal changes to non-test files in the /workspace/{{ workspace_dir_name }} directory to ensure the <issue_description> is satisfied.
+
+Follow these phases to resolve the issue:
+
+Phase 1. READING: read the problem and reword it in clearer terms
+   1.1 If there are code or config snippets. Express in words any best practices or conventions in them.
+   1.2 Hightlight message errors, method names, variables, file names, stack traces, and technical details.
+   1.3 Explain the problem in clear terms.
+   1.4 Enumerate the steps to reproduce the problem.
+   1.5 Hightlight any best practices to take into account when testing and fixing the issue
+
+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
+
+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.
+   3.2 Identify all files related to the problem statement.
+   3.3 Propose the methods and files to fix the issue and explain why.
+   3.4 From the possible file locations, select the most likely location to fix the issue.
+
+Phase 4. TEST CREATION: before implementing any fix, create a script to reproduce and verify the issue.
+   4.1 Look at existing test files in the repository to understand the test format/structure.
+   4.2 Create a minimal reproduction script that reproduces the located issue.
+   4.3 Run the reproduction script to confirm you are reproducing the issue.
+   4.4 Adjust the reproduction script as necessary.
+
+Phase 5. FIX ANALYSIS: state clearly the problem and how to fix it
+   5.1 State clearly what the problem is.
+   5.2 State clearly where the problem is located.
+   5.3 State clearly how the test reproduces the issue.
+   5.4 State clearly the best practices to take into account in the fix.
+   5.5 State clearly how to fix the problem.
+
+Phase 6. FIX IMPLEMENTATION: Edit the source code to implement your chosen solution.
+   6.1 Make minimal, focused changes to fix the issue.
+
+Phase 7. VERIFICATION: Test your implementation thoroughly.
+   7.1 Run your reproduction script to verify the fix works.
+   7.2 Add edge cases to your test script to ensure comprehensive coverage.
+   7.3 Run existing tests related to the modified code to ensure you haven't broken anything.
+
+8. FINAL REVIEW: Carefully re-read the problem description and compare your changes with the base commit {{ instance.base_commit }}.
+   8.1 Ensure you've fully addressed all requirements.
+   8.2 Run any tests in the repository related to:
+     8.2.1 The issue you are fixing
+     8.2.2 The files you modified
+     8.2.3 The functions you changed
+   8.3 If any tests fail, revise your implementation until all tests pass
+
+Be thorough in your exploration, testing, and reasoning. It's fine if your thinking process is lengthy - quality and completeness are more important than brevity.

evaluation/benchmarks/swe_bench/prompts/swe_gemini.j2

@@ -0,0 +1,45 @@
+# Task: Fix Issue in Python Repository
+
+## Repository Context
+You are provided with a Python code repository that contains an issue requiring your attention. The repository is located in a sandboxed environment, and you have access to the codebase to implement the necessary changes.
+The code repository is located at: `/workspace/{{ workspace_dir_name }}`
+(This path is provided for context; use file system tools to confirm paths before access).
+
+## Goal
+Your goal is to fix the issue described in the **Issue Description** section below. Implement the necessary changes to **non-test files only** within the repository, ensuring that **all relevant tests pass** after your changes.
+
+## Key Requirements & Constraints
+
+1.  **Understand the problem** very well: it is a bug report, and you know humans don't always write good descriptions. Explore the codebase to understand the related code and the problem in depth. It is possible that the solution needs to be a bit more extensive than just the stated text. Don't exagerate though: don't do unrelated refactoring, but also don't interpret the description too strictly.
+2.  **Focus on the issues:** Implement the fix focusing on non-test files related to the issue.
+2.  **Environment Ready:** The Python environment is pre-configured with all dependencies. Do not install packages.
+3.  **Mandatory Testing Procedure:**
+    *   **Create Test to Reproduce the Issue:** *Before* implementing any fix, you MUST create a *new test* (separate from existing tests) that specifically reproduces the issue.
+            * Take existing tests as example to understand the testing format/structure.
+            * Enhance this test with edge cases.
+            * Run this test to confirm reproduction.
+    *   **Verify Fix:** After implementing the fix, run your test again to verify the issue is resolved.
+    *   **Identify ALL Relevant Tests:** You MUST perform a **dedicated search and analysis** to identify **all** existing unit tests potentially affected by your changes. This includes:
+        *   Tests in the same module/directory as the changed files (e.g., `tests/` subdirectories).
+        *   Tests explicitly importing or using the modified code/classes/functions.
+        *   Tests mentioned in the issue description or related documentation.
+        *   Tests covering functionalities that *depend on* the modified code (analyze callers/dependencies if necessary).
+        **If you cannot confidently identify a specific subset, you MUST identify and plan to run the entire test suite for the modified application or module(s). State your identified test scope clearly.**
+    *   **Run Identified Relevant Tests:** You MUST execute the **complete set** of relevant existing unit tests you identified in the previous step. Ensure you are running the *correct and comprehensive set* of tests. You MUST NOT modify these existing tests.
+    *   **Final Check & Verification:** Before finishing, ensure **all** identified relevant existing tests pass. **Explicitly confirm that you have considered potential omissions in your test selection and believe the executed tests comprehensively cover the impact of your changes.** Failing to identify and run the *complete* relevant set constitutes a failure. If any identified tests fail, revise your fix. Passing all relevant tests is the primary measure of success.
+4.  **Defensive Programming:** Actively practice defensive programming: anticipate and handle potential edge cases, unexpected inputs, and different ways the affected code might be called **to ensure the fix works reliably and allows relevant tests to pass.** Analyze the potential impact on other parts of the codebase.
+5.  **Final Review:** Compare your solution against the original issue and the base commit ({{ instance.base_commit }}) to ensure completeness and test passage.
+
+## General Workflow Guidance
+
+*   Prioritize understanding the problem, exploring the code, planning your fix, implementing it carefully using the required diff format, and **thoroughly testing** according to the **Mandatory Testing Procedure**.
+*   Consider trade-offs between different solutions. The goal is a **robust change that makes the relevant tests pass.** Quality, correctness, and reliability are key.
+*   Actively practice defensive programming: anticipate and handle potential edge cases, unexpected inputs, and different ways the affected code might be called **to ensure the fix works reliably and allows relevant tests to pass.** Analyze the potential impact on other parts of the codebase.
+
+*   IMPORTANT: Your solution will be tested by additional hidden tests, so do not assume the task is complete just because visible tests pass! Refine the solution until you are confident that it is robust and comprehensive according to the **Defensive Programming** requirement.
+
+## Final Note
+Be thorough in your exploration, testing, and reasoning. It's fine if your thinking process is lengthy - quality and completeness are more important than brevity.
+
+## Issue Description
+{{ instance.problem_statement }}

evaluation/benchmarks/swe_bench/prompts/swe_gpt4.j2

@@ -0,0 +1,80 @@
+You will be tasked to fix an issue from an open-source repository.
+
+Your thinking should be thorough and so it's fine if it's very long. You can think step by step before and after each action you decide to take.
+
+You MUST iterate and keep going until the problem is solved.
+
+You already have everything you need to solve this problem in the /workspace/{{ workspace_dir_name }} folder, even without internet connection. I want you to fully solve this autonomously before coming back to me.
+
+Only terminate your turn when you are sure that the problem is solved. Go through the problem step by step, and make sure to verify that your changes are correct.
+NEVER end your turn without having solved the problem, and when you say you are going to make a tool call, make sure you ACTUALLY make the tool call, instead of ending your turn.
+
+THE PROBLEM CAN DEFINITELY BE SOLVED WITHOUT THE INTERNET.
+
+Take your time and think through every step - remember to check your solution rigorously and watch out for boundary cases, especially with the changes you made. Your solution must be perfect. If not, continue working on it.
+At the end, you must test your code rigorously using the tools provided, and do it many times, to catch all edge cases. If it is not robust, iterate more and make it perfect. Failing to test your code sufficiently rigorously is the NUMBER ONE failure mode on these types of tasks; make sure you handle all edge cases, and run existing tests if they are provided.
+
+You MUST plan extensively before each function call, and reflect extensively on the outcomes of the previous function calls. DO NOT do this entire process by making function calls only, as this can impair your ability to solve the problem and think insightfully.
+
+# Workflow
+
+## High-Level Problem Solving Strategy
+
+1. Understand the problem deeply. Carefully read the issue and think critically about what is required.
+2. Investigate the codebase. Explore relevant files, search for key functions, and gather context.
+3. Develop a clear, step-by-step plan. Break down the fix into manageable, incremental steps.
+4. Implement the fix incrementally. Make small, testable code changes.
+5. Debug as needed. Use debugging techniques to isolate and resolve issues.
+6. Test frequently. Run tests after each change to verify correctness.
+7. Iterate until the root cause is fixed and all tests pass.
+8. Reflect and validate comprehensively. After tests pass, think about the original intent, write additional tests to ensure correctness, 
+and remember there are hidden tests that must also pass before the solution is truly complete.
+
+Refer to the detailed sections below for more information on each step.
+
+## 1. Deeply Understand the Problem
+Carefully read the issue and think hard about a plan to solve it before coding.
+
+## 2. Codebase Investigation
+- Explore relevant files and directories.
+- Search for key functions, classes, or variables related to the issue.
+- Read and understand relevant code snippets.
+- Identify the root cause of the problem.
+- Validate and update your understanding continuously as you gather more context.
+
+## 3. Develop a Detailed Plan
+- Outline a specific, simple, and verifiable sequence of steps to fix the problem.
+- Break down the fix into small, incremental changes.
+
+## 4. Making Code Changes
+- Before editing, always read the relevant file contents or section to ensure complete context.
+- If a patch is not applied correctly, attempt to reapply it.
+- Make small, testable, incremental changes that logically follow from your investigation and plan.
+
+## 5. Debugging
+- Make code changes only if you have high confidence they can solve the problem
+- When debugging, try to determine the root cause rather than addressing symptoms
+- Debug for as long as needed to identify the root cause and identify a fix
+- Use print statements, logs, or temporary code to inspect program state, including descriptive statements or error messages to understand what's happening
+- To test hypotheses, you can also add test statements or functions
+- Revisit your assumptions if unexpected behavior occurs.
+
+## 6. Testing
+- Run tests frequently using `python3 run_tests.py` (or equivalent).
+- After each change, verify correctness by running relevant tests.
+- If tests fail, analyze failures and revise your patch.
+- Write additional tests if needed to capture important behaviors or edge cases.
+- Ensure all tests pass before finalizing.
+
+## 7. Final Verification
+- Confirm the root cause is fixed.
+- Review your solution for logic correctness and robustness.
+- Iterate until you are extremely confident the fix is complete and all tests pass.
+
+## 8. Final Reflection and Additional Testing
+- Reflect carefully on the original intent of the user and the problem statement.
+- Think about potential edge cases or scenarios that may not be covered by existing tests.
+- Write additional tests that would need to pass to fully validate the correctness of your solution.
+- Run these new tests and ensure they all pass.
+- Be aware that there are additional hidden tests that must also pass for the solution to be successful.
+- Do not assume the task is complete just because the visible tests pass; continue refining until you are confident the fix is robust and comprehensive.

evaluation/benchmarks/swe_bench/prompts/swt.j2

@@ -0,0 +1,19 @@
+<uploaded_files>
+/workspace/{{ workspace_dir_name }}
+</uploaded_files>
+I've uploaded a python code repository in the directory {{ workspace_dir_name }}. Consider the following issue description:
+
+<issue_description>
+{{ instance.problem_statement }}
+</issue_description>
+
+
+Can you help me implement the necessary changes to the repository to test whether the issue in <issue_description> was resolved?
+I will take care of all changes to any of the non-test files. This means you DON'T have to modify the actual logic and ONLY have to update test logic and tests!
+Your task is to make the minimal changes to tests files in the /workspace directory to reproduce the issue in the <issue_description>, i.e., such that the generated tests fail in the current state (where the issue is unresolved) and pass when the issue will be resolved.
+Follow these steps to reproduce the issue:
+1. As a first step, it might be a good idea to explore the repo to familiarize yourself with its structure.
+2. Create a script `reproduction.py` to reproduce the error and execute it with `python reproduction.py` using the BashTool, to confirm the error
+3. Edit the sourcecode of the repo to integrate your reproduction script into the test framework
+4. Run the test framework and make sure your tests fail! Only submit FAILING tests! Never submit passing tests.
+{{ test_instructions }}Your thinking should be thorough and so it's fine if it's very long.

evaluation/benchmarks/swe_bench/run_infer.py

@@ -8,6 +8,7 @@ from typing import Any, Literal
 import pandas as pd
 import toml
 from datasets import load_dataset
+from jinja2 import Environment, FileSystemLoader
 
 import openhands.agenthub
 from evaluation.benchmarks.swe_bench.binary_patch_utils import (
@@ -78,101 +79,48 @@ def _get_swebench_workspace_dir_name(instance: pd.Series) -> str:
 def get_instruction(instance: pd.Series, metadata: EvalMetadata) -> MessageAction:
     workspace_dir_name = _get_swebench_workspace_dir_name(instance)
     mode = metadata.details['mode']
+    llm_model = metadata.llm_config.model
+
+    # Determine the template file based on mode and LLM
     if mode.startswith('swt'):
-        test_instructions = (
-            f'The following command can be used to run the tests: `{list(MAP_REPO_TO_TEST_FRAMEWORK_VERBOSE[instance.repo].values())[0]}`. Make sure they fail in the expected way.\n'
-            if mode.endswith('ci')
-            else ''
-        )
-        instruction = f"""\
-<uploaded_files>
-/workspace/{workspace_dir_name}
-</uploaded_files>
-I've uploaded a python code repository in the directory {workspace_dir_name}. Consider the following issue description:
-
-<issue_description>
-{instance.problem_statement}
-</issue_description>
-
-
-Can you help me implement the necessary changes to the repository to test whether the issue in <issue_description> was resolved?
-I will take care of all changes to any of the non-test files. This means you DON'T have to modify the actual logic and ONLY have to update test logic and tests!
-Your task is to make the minimal changes to tests files in the /workspace directory to reproduce the issue in the <issue_description>, i.e., such that the generated tests fail in the current state (where the issue is unresolved) and pass when the issue will be resolved.
-Follow these steps to reproduce the issue:
-1. As a first step, it might be a good idea to explore the repo to familiarize yourself with its structure.
-2. Create a script `reproduction.py` to reproduce the error and execute it with `python reproduction.py` using the BashTool, to confirm the error
-3. Edit the sourcecode of the repo to integrate your reproduction script into the test framework
-4. Run the test framework and make sure your tests fail! Only submit FAILING tests! Never submit passing tests.
-{test_instructions}Your thinking should be thorough and so it's fine if it's very long.
-"""
+        template_name = 'swt.j2'
+    elif mode == 'swe':
+        if 'claude' in llm_model:
+            template_name = 'swe_claude.j2'
+        elif 'gemini' in llm_model:
+            template_name = 'swe_gemini.j2'
+        elif 'gpt-4.1' in llm_model:
+            template_name = 'swe_gpt4.j2'
+        else:
+            template_name = 'swe_default.j2'  # Default for 'swe' mode (regular swe-bench)
     else:
-        instruction = f"""
-<uploaded_files>
-/workspace/{workspace_dir_name}
-</uploaded_files>
+        # Fallback or error handling if mode is unexpected
+        logger.error(f"Unexpected evaluation mode: {mode}. Falling back to default.")
+        template_name = 'swe_default.j2'
 
-I've uploaded a python code repository in the directory {workspace_dir_name}. Consider the following issue description:
+    # Set up Jinja2 environment
+    # Assuming templates are in 'evaluation/benchmarks/swe_bench/prompts' relative to this script
+    prompts_dir = os.path.join(os.path.dirname(__file__), 'prompts')
+    env = Environment(loader=FileSystemLoader(prompts_dir))
+    template = env.get_template(template_name)
 
-<issue_description>
-{instance.problem_statement}
-</issue_description>
+    # Prepare context for rendering
+    context = {
+        'instance': instance,
+        'workspace_dir_name': workspace_dir_name,
+        'metadata': metadata,  # Pass metadata if needed in templates
+    }
 
-Can you help me implement the necessary changes to the repository so that the requirements specified in the <issue_description> are met?
-I've already taken care of all changes to any of the test files described in the <issue_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!
-Also the development Python environment is already set up for you (i.e., all dependencies already installed), so you don't need to install other packages.
-Your task is to make the minimal changes to non-test files in the /workspace/{workspace_dir_name} directory to ensure the <issue_description> is satisfied.
+    # Add specific context for swt-ci mode if needed
+    if mode == 'swt-ci':
+        context['test_instructions'] = (
+            f'The following command can be used to run the tests: `{list(MAP_REPO_TO_TEST_FRAMEWORK_VERBOSE[instance.repo].values())[0]}`. Make sure they fail in the expected way.\n'
+        )
+    else:
+        context['test_instructions'] = '' # Ensure it's defined for other modes
 
-Follow these phases to resolve the issue:
-
-Phase 1. READING: read the problem and reword it in clearer terms
-   1.1 If there are code or config snippets. Express in words any best practices or conventions in them.
-   1.2 Hightlight message errors, method names, variables, file names, stack traces, and technical details.
-   1.3 Explain the problem in clear terms.
-   1.4 Enumerate the steps to reproduce the problem.
-   1.5 Hightlight any best practices to take into account when testing and fixing the issue
-
-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
-
-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.
-   3.2 Identify all files related to the problem statement.
-   3.3 Propose the methods and files to fix the issue and explain why.
-   3.4 From the possible file locations, select the most likely location to fix the issue.
-
-Phase 4. TEST CREATION: before implementing any fix, create a script to reproduce and verify the issue.
-   4.1 Look at existing test files in the repository to understand the test format/structure.
-   4.2 Create a minimal reproduction script that reproduces the located issue.
-   4.3 Run the reproduction script to confirm you are reproducing the issue.
-   4.4 Adjust the reproduction script as necessary.
-
-Phase 5. FIX ANALYSIS: state clearly the problem and how to fix it
-   5.1 State clearly what the problem is.
-   5.2 State clearly where the problem is located.
-   5.3 State clearly how the test reproduces the issue.
-   5.4 State clearly the best practices to take into account in the fix.
-   5.5 State clearly how to fix the problem.
-
-Phase 6. FIX IMPLEMENTATION: Edit the source code to implement your chosen solution.
-   6.1 Make minimal, focused changes to fix the issue.
-
-Phase 7. VERIFICATION: Test your implementation thoroughly.
-   7.1 Run your reproduction script to verify the fix works.
-   7.2 Add edge cases to your test script to ensure comprehensive coverage.
-   7.3 Run existing tests related to the modified code to ensure you haven't broken anything.
-
-8. FINAL REVIEW: Carefully re-read the problem description and compare your changes with the base commit {instance['base_commit']}.
-   8.1 Ensure you've fully addressed all requirements.
-   8.2 Run any tests in the repository related to:
-     8.2.1 The issue you are fixing
-     8.2.2 The files you modified
-     8.2.3 The functions you changed
-   8.3 If any tests fail, revise your implementation until all tests pass
-
-Be thorough in your exploration, testing, and reasoning. It's fine if your thinking process is lengthy - quality and completeness are more important than brevity.
-"""
+    # Render the instruction
+    instruction = template.render(context)
 
     if RUN_WITH_BROWSING:
         instruction += (

evaluation/benchmarks/testgeneval/constants.py

@@ -921,7 +921,7 @@ SPECS_PYDICOM.update(
 
 SPECS_HUMANEVAL = {k: {'python': '3.9', 'test_cmd': 'python'} for k in ['1.0']}
 
-# Constants - Task Instance Instllation Environment
+# Constants - Task Instance Installation Environment
 MAP_REPO_VERSION_TO_SPECS: dict[str, dict[str, Any]] = {
     'astropy/astropy': SPECS_ASTROPY,
     'dbt-labs/dbt-core': SPECS_DBT_CORE,

evaluation/benchmarks/testgeneval/run_infer.py

@@ -539,7 +539,7 @@ if __name__ == '__main__':
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
         llm_config.log_completions = True
-        # modify_params must be False for evaluation purpose, for reproducibility and accurancy of results
+        # modify_params must be False for evaluation purpose, for reproducibility and accuracy of results
         llm_config.modify_params = False
 
     if llm_config is None:

frontend/public/mockServiceWorker.js

@@ -5,24 +5,23 @@
  * Mock Service Worker.
  * @see https://github.com/mswjs/msw
  * - Please do NOT modify this file.
- * - Please do NOT serve this file on production.
  */
 
-const PACKAGE_VERSION = '2.8.4'
-const INTEGRITY_CHECKSUM = '00729d72e3b82faf54ca8b9621dbb96f'
+const PACKAGE_VERSION = '2.10.2'
+const INTEGRITY_CHECKSUM = 'f5825c521429caf22a4dd13b66e243af'
 const IS_MOCKED_RESPONSE = Symbol('isMockedResponse')
 const activeClientIds = new Set()
 
-self.addEventListener('install', function () {
+addEventListener('install', function () {
   self.skipWaiting()
 })
 
-self.addEventListener('activate', function (event) {
+addEventListener('activate', function (event) {
   event.waitUntil(self.clients.claim())
 })
 
-self.addEventListener('message', async function (event) {
-  const clientId = event.source.id
+addEventListener('message', async function (event) {
+  const clientId = Reflect.get(event.source || {}, 'id')
 
   if (!clientId || !self.clients) {
     return
@@ -94,17 +93,18 @@ self.addEventListener('message', async function (event) {
   }
 })
 
-self.addEventListener('fetch', function (event) {
-  const { request } = event
-
+addEventListener('fetch', function (event) {
   // Bypass navigation requests.
-  if (request.mode === 'navigate') {
+  if (event.request.mode === 'navigate') {
     return
   }
 
   // Opening the DevTools triggers the "only-if-cached" request
   // that cannot be handled by the worker. Bypass such requests.
-  if (request.cache === 'only-if-cached' && request.mode !== 'same-origin') {
+  if (
+    event.request.cache === 'only-if-cached' &&
+    event.request.mode !== 'same-origin'
+  ) {
     return
   }
 
@@ -115,48 +115,62 @@ self.addEventListener('fetch', function (event) {
     return
   }
 
-  // Generate unique request ID.
   const requestId = crypto.randomUUID()
   event.respondWith(handleRequest(event, requestId))
 })
 
+/**
+ * @param {FetchEvent} event
+ * @param {string} requestId
+ */
 async function handleRequest(event, requestId) {
   const client = await resolveMainClient(event)
+  const requestCloneForEvents = event.request.clone()
   const response = await getResponse(event, client, requestId)
 
   // Send back the response clone for the "response:*" life-cycle events.
   // Ensure MSW is active and ready to handle the message, otherwise
   // this message will pend indefinitely.
   if (client && activeClientIds.has(client.id)) {
-    ;(async function () {
-      const responseClone = response.clone()
+    const serializedRequest = await serializeRequest(requestCloneForEvents)
 
-      sendToClient(
-        client,
-        {
-          type: 'RESPONSE',
-          payload: {
-            requestId,
-            isMockedResponse: IS_MOCKED_RESPONSE in response,
+    // Clone the response so both the client and the library could consume it.
+    const responseClone = response.clone()
+
+    sendToClient(
+      client,
+      {
+        type: 'RESPONSE',
+        payload: {
+          isMockedResponse: IS_MOCKED_RESPONSE in response,
+          request: {
+            id: requestId,
+            ...serializedRequest,
+          },
+          response: {
             type: responseClone.type,
             status: responseClone.status,
             statusText: responseClone.statusText,
-            body: responseClone.body,
             headers: Object.fromEntries(responseClone.headers.entries()),
+            body: responseClone.body,
           },
         },
-        [responseClone.body],
-      )
-    })()
+      },
+      responseClone.body ? [serializedRequest.body, responseClone.body] : [],
+    )
   }
 
   return response
 }
 
-// Resolve the main client for the given event.
-// Client that issues a request doesn't necessarily equal the client
-// that registered the worker. It's with the latter the worker should
-// communicate with during the response resolving phase.
+/**
+ * Resolve the main client for the given event.
+ * Client that issues a request doesn't necessarily equal the client
+ * that registered the worker. It's with the latter the worker should
+ * communicate with during the response resolving phase.
+ * @param {FetchEvent} event
+ * @returns {Promise<Client | undefined>}
+ */
 async function resolveMainClient(event) {
   const client = await self.clients.get(event.clientId)
 
@@ -184,12 +198,16 @@ async function resolveMainClient(event) {
     })
 }
 
+/**
+ * @param {FetchEvent} event
+ * @param {Client | undefined} client
+ * @param {string} requestId
+ * @returns {Promise<Response>}
+ */
 async function getResponse(event, client, requestId) {
-  const { request } = event
-
   // Clone the request because it might've been already used
   // (i.e. its body has been read and sent to the client).
-  const requestClone = request.clone()
+  const requestClone = event.request.clone()
 
   function passthrough() {
     // Cast the request headers to a new Headers instance
@@ -230,29 +248,17 @@ async function getResponse(event, client, requestId) {
   }
 
   // Notify the client that a request has been intercepted.
-  const requestBuffer = await request.arrayBuffer()
+  const serializedRequest = await serializeRequest(event.request)
   const clientMessage = await sendToClient(
     client,
     {
       type: 'REQUEST',
       payload: {
         id: requestId,
-        url: request.url,
-        mode: request.mode,
-        method: request.method,
-        headers: Object.fromEntries(request.headers.entries()),
-        cache: request.cache,
-        credentials: request.credentials,
-        destination: request.destination,
-        integrity: request.integrity,
-        redirect: request.redirect,
-        referrer: request.referrer,
-        referrerPolicy: request.referrerPolicy,
-        body: requestBuffer,
-        keepalive: request.keepalive,
+        ...serializedRequest,
       },
     },
-    [requestBuffer],
+    [serializedRequest.body],
   )
 
   switch (clientMessage.type) {
@@ -268,6 +274,12 @@ async function getResponse(event, client, requestId) {
   return passthrough()
 }
 
+/**
+ * @param {Client} client
+ * @param {any} message
+ * @param {Array<Transferable>} transferrables
+ * @returns {Promise<any>}
+ */
 function sendToClient(client, message, transferrables = []) {
   return new Promise((resolve, reject) => {
     const channel = new MessageChannel()
@@ -280,14 +292,18 @@ function sendToClient(client, message, transferrables = []) {
       resolve(event.data)
     }
 
-    client.postMessage(
-      message,
-      [channel.port2].concat(transferrables.filter(Boolean)),
-    )
+    client.postMessage(message, [
+      channel.port2,
+      ...transferrables.filter(Boolean),
+    ])
   })
 }
 
-async function respondWithMock(response) {
+/**
+ * @param {Response} response
+ * @returns {Response}
+ */
+function respondWithMock(response) {
   // Setting response status code to 0 is a no-op.
   // However, when responding with a "Response.error()", the produced Response
   // instance will have status code set to 0. Since it's not possible to create
@@ -305,3 +321,24 @@ async function respondWithMock(response) {
 
   return mockedResponse
 }
+
+/**
+ * @param {Request} request
+ */
+async function serializeRequest(request) {
+  return {
+    url: request.url,
+    mode: request.mode,
+    method: request.method,
+    headers: Object.fromEntries(request.headers.entries()),
+    cache: request.cache,
+    credentials: request.credentials,
+    destination: request.destination,
+    integrity: request.integrity,
+    redirect: request.redirect,
+    referrer: request.referrer,
+    referrerPolicy: request.referrerPolicy,
+    body: await request.arrayBuffer(),
+    keepalive: request.keepalive,
+  }
+}

openhands/agenthub/__init__.py

@@ -8,6 +8,7 @@ from openhands.agenthub import (  # noqa: E402
     codeact_agent,
     dummy_agent,
     loc_agent,
+    proxy_agent,
     readonly_agent,
     visualbrowsing_agent,
 )
@@ -19,6 +20,7 @@ __all__ = [
     'dummy_agent',
     'browsing_agent',
     'visualbrowsing_agent',
+    'proxy_agent',
     'readonly_agent',
     'loc_agent',
 ]

openhands/agenthub/codeact_agent/prompts/system_prompt.j2

@@ -14,7 +14,6 @@ Your primary role is to assist users by executing commands, modifying code, and
 * When a user provides a file path, do NOT assume it's relative to the current working directory. First explore the file system to locate the file before working on it.
 * If asked to edit a file, edit the file directly, rather than creating a new file with a different filename.
 * For global search-and-replace operations, consider using `sed` instead of opening file editors multiple times.
-* Temporary or utility files should go into /tmp instead of /workspace.
 </FILE_SYSTEM_GUIDELINES>
 
 <CODE_QUALITY>

openhands/agenthub/proxy_agent/README.md

@@ -0,0 +1,54 @@
+# Proxy Agent
+
+This folder is an implementation of a Proxy Agent.
+The Proxy Agent delegates a given task to an appropriate agent capable of accomplishing it.
+The list of available agents is defined in agent_list.json, located in this directory.
+
+A key feature of the Proxy Agent is that, in addition to delegating task to different agents available locally within OpenHands, it can also send messages to agents hosted on different server, using A2A Protocol.
+
+## How to run
+### Set as the initial agent
+This agent is designed to be the initial agent that receives user input at the start of a session.
+Configure the Proxy Agent as the initial agent of a session.
+```mermaid
+flowchart LR
+    u((User)) --> A
+
+    subgraph Server1
+        A["Proxy Agent"]
+        B["Other Agents<br>(e.g. CodeActAgent)"]
+        A -->|delegate| B
+    end
+
+    subgraph Server2
+        D["Other Agents"]
+    end
+
+    A --->|Remote Delegation| D
+
+```
+
+### Place agent_list.json
+Place agent_list.json under openhands/agenthub/proxy_agent. Below is an example of its structure:
+```json
+{
+    "local": {
+        "CodeActAgent": {
+            "agent_name": "CodeActAgent",
+            "description": "A helpful AI assistant that can interact with a computer to solve tasks."
+        }
+    },
+    "remote": {
+        "FooAgent": {
+            "agent_name": "FooAgent",
+            "url": "http(s)://IP or FQDN:port",
+            "description": "A brief description of FooAgent.",
+            "protocol": "A2A"
+        }
+    }
+}
+```
+The contents of this JSON file are simply passed as a string to the agent as part of its prompt, assisting the LLM in selecting the most suitable agent.
+Therefore, there areno strict formatting requirements, but please keep the following points in mind:
+- Clearly specify whether the agent is available locally within the same instance or hosted on a different instance.
+- If an agent is hosted on a different instance, explicitly provide the URL where that instance is hosted.

openhands/agenthub/proxy_agent/__init__.py

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

openhands/agenthub/proxy_agent/function_calling.py

@@ -0,0 +1,180 @@
+import json
+
+from litellm import (
+    ChatCompletionToolParam,
+    ChatCompletionToolParamFunctionChunk,
+    ModelResponse,
+)
+
+from openhands.core.exceptions import (
+    FunctionCallNotExistsError,
+    FunctionCallValidationError,
+)
+from openhands.core.logger import openhands_logger as logger
+from openhands.events.action import (
+    Action,
+    AgentDelegateAction,
+    AgentFinishAction,
+    IPythonRunCellAction,
+    MessageAction,
+)
+from openhands.events.tool import ToolCallMetadata
+
+_DELEGATE_LOCAL = """Delegate a task to a local agent hosted on a same instance.
+"""
+
+DelegateLocalTool = ChatCompletionToolParam(
+    type='function',
+    function=ChatCompletionToolParamFunctionChunk(
+        name='delegate_local',
+        description=_DELEGATE_LOCAL,
+        parameters={
+            'type': 'object',
+            'properties': {
+                'agent_name': {
+                    'type': 'string',
+                    'description': 'The name of the agent to delegate to.',
+                },
+                'task': {
+                    'type': 'string',
+                    'description': 'The task to delegate.',
+                },
+            },
+            'required': ['agent_name', 'task'],
+        },
+    ),
+)
+
+_DELEGATE_REMOTE = """Delegate a task to a remote agent hosted on a remote server using A2A Protocol.
+"""
+
+DelegateRemoteTool = ChatCompletionToolParam(
+    type='function',
+    function=ChatCompletionToolParamFunctionChunk(
+        name='delegate_remote',
+        description=_DELEGATE_REMOTE,
+        parameters={
+            'type': 'object',
+            'properties': {
+                'url': {
+                    'type': 'string',
+                    'description': 'The URL of the remote agent.',
+                },
+                'task': {
+                    'type': 'string',
+                    'description': 'The task to delegate.',
+                },
+                'session_id': {
+                    'type': 'string',
+                    'description': 'The session id of the remote agent.',
+                },
+                'task_id': {
+                    'type': 'string',
+                    'description': 'The task id of the remote agent.',
+                }
+            },
+            'required': ['url', 'task'],
+        },
+    ),
+)
+
+_FINISH_DESCRIPTION = """Finish the interaction when the task is complete OR if the assistant cannot proceed further with the task."""
+
+FinishTool = ChatCompletionToolParam(
+    type='function',
+    function=ChatCompletionToolParamFunctionChunk(
+        name='finish',
+        description=_FINISH_DESCRIPTION,
+    ),
+)
+
+
+def combine_thought(action: Action, thought: str) -> Action:
+    if not hasattr(action, 'thought'):
+        return action
+    if thought:
+        action.thought = thought
+    return action
+
+
+def response_to_action(response: ModelResponse) -> Action:
+    action: Action = None  # type: ignore
+    assert len(response.choices) == 1, 'Only one choice is supported for now'
+    assistant_msg = response.choices[0].message
+    if assistant_msg.tool_calls:
+        # Check if there's assistant_msg.content. If so, add it to the thought
+        thought = ''
+        if isinstance(assistant_msg.content, str):
+            thought = assistant_msg.content
+        elif isinstance(assistant_msg.content, list):
+            for msg in assistant_msg.content:
+                if msg['type'] == 'text':
+                    thought += msg['text']
+
+        # Assume only one tool call is returned
+        if len(assistant_msg.tool_calls) != 1:
+            logger.info(
+                f'Expected only one tool call, but got {len(assistant_msg.tool_calls)}'
+            )
+        tool_call = assistant_msg.tool_calls[0]
+        try:
+            arguments = json.loads(tool_call.function.arguments)
+        except json.decoder.JSONDecodeError as e:
+            raise RuntimeError(
+                f'Failed to parse tool call arguments: {tool_call.function.arguments}'
+            ) from e
+
+        if tool_call.function.name == 'delegate_remote':
+            for k in ['url', 'task']:
+                if k not in arguments:
+                    raise FunctionCallValidationError(
+                        f'Missing required argument "{k}" in tool call {tool_call.function.name}'
+                    )
+            
+            message = arguments['task']
+            message = message.replace('\n', '\\\n')
+            url = arguments['url']
+            session_id = arguments.get('session_id')
+            task_id = arguments.get('task_id')
+            if session_id and task_id:
+                code = (
+                    f'await send_task_A2A('
+                    f'message="{message}", '
+                    f'url="{url}", '
+                    f'session_id="{session_id}", '
+                    f'task_id="{task_id}")'
+                )
+            else:
+                code = (
+                    f'await send_task_A2A('
+                    f'message="{message}", '
+                    f'url="{url}")'
+                )
+
+            action = IPythonRunCellAction(code=code, include_extra=False)
+        
+        elif tool_call.function.name == 'finish':
+            action = AgentFinishAction()
+        else:
+            raise FunctionCallNotExistsError(
+                f'Tool {tool_call.function.name} is not registered. (arguments: {arguments}). Please check the tool name and retry with an existing tool.'
+            )
+
+        action = combine_thought(action, thought)
+        # Add metadata for tool calling
+        action.tool_call_metadata = ToolCallMetadata(
+            tool_call_id=tool_call.id,
+            function_name=tool_call.function.name,
+            model_response=response,
+            total_calls_in_response=len(assistant_msg.tool_calls),
+        )
+
+    else:
+        action = MessageAction(content=assistant_msg.content, wait_for_response=True)
+
+    return action
+
+
+def get_tools() -> list[ChatCompletionToolParam]:
+    tools = [DelegateLocalTool, DelegateRemoteTool, FinishTool]
+    return tools

openhands/agenthub/proxy_agent/prompts/system_prompt.j2

@@ -0,0 +1,6 @@
+You are a Proxy Agent, a helpful AI assistant which is responsible for delegating tasks to other agents.
+You delegate tasks to agents that exist locally or are hosted remotely on another server.
+<IMPORTANT>
+* Never execute an action again once the action has been completed.
+* When you delegate a task to a remote-host agent, you must read the response of the remote agent and return a message to the user as if you were that agent.
+</IMPORTANT>

openhands/agenthub/proxy_agent/proxy_agent.py

@@ -0,0 +1,126 @@
+import json
+import os
+
+import openhands.agenthub.proxy_agent.function_calling as proxy_function_calling
+from openhands.controller.agent import Agent
+from openhands.controller.state.state import State
+from openhands.core.config import AgentConfig
+from openhands.core.logger import openhands_logger as logger
+from openhands.core.message import Message, TextContent
+from openhands.events.action import Action, MessageAction
+from openhands.events.event import Event
+from openhands.llm.llm import LLM
+from openhands.memory.conversation_memory import ConversationMemory
+from openhands.microagent.prompt_manager import PromptManager
+from openhands.runtime.plugins import (
+    AgentSkillsRequirement,
+    JupyterRequirement,
+    PluginRequirement,
+)
+
+
+class ProxyAgent(Agent):
+    sandbox_plugins: list[PluginRequirement] = [
+        AgentSkillsRequirement(),
+        JupyterRequirement(),
+    ]
+
+    def __init__(self, llm: LLM, config: AgentConfig) -> None:
+        super().__init__(llm, config)
+        self.reset()
+
+        self.mock_function_calling = False
+        if not self.llm.is_function_calling_active():
+            logger.info(
+                f'Function calling not enabled for model {self.llm.config.model}. '
+                'Mocking function calling via prompting.'
+            )
+            self.mock_function_calling = True
+
+        # Function calling mode
+        self.tools = proxy_function_calling.get_tools()
+
+        self._prompt_manager = PromptManager(
+            prompt_dir=os.path.join(os.path.dirname(__file__), 'prompts'),
+        )
+
+        # Create a ConversationMemory instance
+        # _prompt_manager is guaranteed to be set at this point
+        assert self._prompt_manager is not None
+        self.conversation_memory = ConversationMemory(self.config, self._prompt_manager)
+
+        agent_list_path = os.path.join(os.path.dirname(__file__), 'agent_list.json')
+        if not os.path.exists(agent_list_path):
+            raise FileNotFoundError('agent list file not found')
+        with open(agent_list_path, 'r') as f:
+            self.agent_list = json.load(f)
+            if self.agent_list == {}:
+                raise ValueError('agent list file is empty')
+
+    def step(self, state: State) -> Action:
+        # Prepare the message to send to the LLM
+        initial_user_message = self._get_initial_user_message(state.history)
+        messages = self._get_messages(state.history, initial_user_message)
+
+        params: dict = {
+            'messages': self.llm.format_messages_for_llm(messages),
+        }
+        params['tools'] = self.tools
+        if self.mock_function_calling:
+            params['mock_function_calling'] = True
+        response = self.llm.completion(**params)
+
+        # Assume only one tool call is returned
+        action = proxy_function_calling.response_to_action(response)
+        return action
+
+    def _get_initial_user_message(self, history: list[Event]) -> MessageAction:
+        """Finds the initial user message action from the full history."""
+        initial_user_message: MessageAction | None = None
+        for event in history:
+            if isinstance(event, MessageAction) and event.source == 'user':
+                initial_user_message = event
+                break
+
+        if initial_user_message is None:
+            # This should not happen in a valid conversation
+            raise ValueError(
+                'Initial user message not found in history. Please report this issue.'
+            )
+        return initial_user_message
+
+    def _get_messages(
+        self, events: list[Event], initial_user_message: MessageAction
+    ) -> list[Message]:
+        if not self.prompt_manager:
+            raise Exception('Prompt Manager not instantiated.')
+
+        # Use ConversationMemory to process events (including SystemMessageAction)
+        messages = self.conversation_memory.process_events(
+            condensed_history=events,
+            initial_user_action=initial_user_message,
+            max_message_chars=self.llm.config.max_message_chars,
+            vision_is_active=self.llm.vision_is_active(),
+        )
+
+        agent_list_message = Message(
+            role='system',
+            content=[
+                TextContent(
+                    text='Available agents are the following:'
+                    + json.dumps(self.agent_list)
+                )
+            ],
+        )
+        if len(messages) > 1:
+            messages.insert(1, agent_list_message)
+        else:
+            messages.append(agent_list_message)
+
+        if self.llm.is_caching_prompt_active():
+            self.conversation_memory.apply_prompt_caching(messages)
+
+        return messages
+
+    def reset(self) -> None:
+        super().reset()

openhands/integrations/gitlab/gitlab_service.py

@@ -470,7 +470,6 @@ class GitLabService(BaseGitService, GitService):
             target_branch: The name of the branch you want the changes merged into
             title: The title of the merge request (optional, defaults to a generic title)
             description: The description of the merge request (optional)
-            draft: Whether to create the MR as a draft (optional, defaults to False)
 
         Returns:
             - MR URL when successful

openhands/runtime/plugins/agent_skills/a2a_client/README.md

@@ -0,0 +1,11 @@
+# A2A Client
+This is an implementation of an A2A Client, called by agents within runtime container.  
+
+This directory contains code from [A2A](https://github.com/google/A2A), originally licensed under the Apache License 2.0.
+The original source has been modified to fit the needs of this project.
+See third_party_license/LICENSE for the full license text.
+
+## Modifications
+
+- Removed unused components (e.g. PushNotfication) from original code.
+- Implemented 'send_task_a2a' with customed I/O to make it more convenient for AI Agent

openhands/runtime/plugins/agent_skills/a2a_client/__init__.py

@@ -0,0 +1,9 @@
+from openhands.runtime.plugins.agent_skills.a2a_client import a2a_client
+from openhands.runtime.plugins.agent_skills.utils.dependency import import_functions
+
+import_functions(
+    module=a2a_client,
+    function_names=a2a_client.__all__,
+    target_globals=globals(),
+)
+__all__ = a2a_client.__all__

openhands/runtime/plugins/agent_skills/a2a_client/a2a_client.py

@@ -0,0 +1,80 @@
+from uuid import uuid4
+
+from openhands.runtime.plugins.agent_skills.a2a_client.common.client import (
+    A2ACardResolver,
+    A2AClient,
+)
+from openhands.runtime.plugins.agent_skills.a2a_client.common.types import (
+    TaskState,
+)
+
+
+async def send_task_A2A(url, message, session_id=0, task_id=0):
+    """
+    Send a task to an agent hosted on remote server, compatible with A2A protocol.
+    """
+    ## Get the agent card
+    card_resolver = A2ACardResolver(url)
+    card = card_resolver.get_agent_card()
+
+    print('======= Agent Card ========')
+    print(card.model_dump_json(exclude_none=True))
+
+    client = A2AClient(agent_card=card)
+
+    if session_id == 0:
+        session_id = uuid4().hex
+    if task_id == 0:
+        task_id = uuid4().hex
+
+    streaming = card.capabilities.streaming
+    print('======= Session ID and Task ID ========')
+    print(f'Session ID: {session_id}')
+    print(f'Task ID: {task_id}')
+    print('If you want to send more input, use the same session ID and task ID.')
+
+    print('=========  starting a task ======== ')
+    await completeTask(client, message, streaming, task_id, session_id)
+
+
+async def completeTask(client: A2AClient, message, streaming, task_id, session_id):
+    prompt = message
+
+    message = {
+        'role': 'user',
+        'parts': [
+            {
+                'type': 'text',
+                'text': prompt,
+            }
+        ],
+    }
+
+    payload = {
+        'id': task_id,
+        'sessionId': session_id,
+        'acceptedOutputModes': ['text'],
+        'message': message,
+    }
+
+    taskResult = None
+    if streaming:
+        response_stream = client.send_task_streaming(payload)
+        async for result in response_stream:
+            print(f'stream event => {result.model_dump_json(exclude_none=True)}')
+        taskResult = await client.get_task({'id': task_id})
+    else:
+        taskResult = await client.send_task(payload)
+        print(f'\n{taskResult.model_dump_json(exclude_none=True)}')
+
+    ## if the result is that more input is required, tell the user and exit.
+    if taskResult.result:
+        state = TaskState(taskResult.result.status.state)
+        if state.name == TaskState.INPUT_REQUIRED.name:
+            print('Task requires more input. Use this tool again to provide it.')
+        else:
+            ## task is complete
+            return True
+
+
+__all__ = ['send_task_A2A']

openhands/runtime/plugins/agent_skills/a2a_client/common/client/__init__.py

@@ -0,0 +1,4 @@
+from .client import A2AClient
+from .card_resolver import A2ACardResolver
+
+__all__ = ["A2AClient", "A2ACardResolver"]

openhands/runtime/plugins/agent_skills/a2a_client/common/client/card_resolver.py

@@ -0,0 +1,21 @@
+import httpx
+from openhands.runtime.plugins.agent_skills.a2a_client.common.types import (
+    AgentCard,
+    A2AClientJSONError,
+)
+import json
+
+
+class A2ACardResolver:
+    def __init__(self, base_url, agent_card_path="/.well-known/agent.json"):
+        self.base_url = base_url.rstrip("/")
+        self.agent_card_path = agent_card_path.lstrip("/")
+
+    def get_agent_card(self) -> AgentCard:
+        with httpx.Client() as client:
+            response = client.get(self.base_url + "/" + self.agent_card_path)
+            response.raise_for_status()
+            try:
+                return AgentCard(**response.json())
+            except json.JSONDecodeError as e:
+                raise A2AClientJSONError(str(e)) from e

openhands/runtime/plugins/agent_skills/a2a_client/common/client/client.py

@@ -0,0 +1,88 @@
+import json
+from typing import Any, AsyncIterable
+
+import httpx
+from httpx_sse import connect_sse
+
+from openhands.runtime.plugins.agent_skills.a2a_client.common.types import (
+    A2AClientHTTPError,
+    A2AClientJSONError,
+    AgentCard,
+    CancelTaskRequest,
+    CancelTaskResponse,
+    GetTaskPushNotificationRequest,
+    GetTaskPushNotificationResponse,
+    GetTaskRequest,
+    GetTaskResponse,
+    JSONRPCRequest,
+    SendTaskRequest,
+    SendTaskResponse,
+    SendTaskStreamingRequest,
+    SendTaskStreamingResponse,
+    SetTaskPushNotificationRequest,
+    SetTaskPushNotificationResponse,
+)
+
+
+class A2AClient:
+    def __init__(self, agent_card: AgentCard | None = None, url: str | None = None):
+        if agent_card:
+            self.url = agent_card.url
+        elif url:
+            self.url = url
+        else:
+            raise ValueError('Must provide either agent_card or url')
+
+    async def send_task(self, payload: dict[str, Any]) -> SendTaskResponse:
+        request = SendTaskRequest(params=payload)
+        return SendTaskResponse(**await self._send_request(request))
+
+    async def send_task_streaming(
+        self, payload: dict[str, Any]
+    ) -> AsyncIterable[SendTaskStreamingResponse]:
+        request = SendTaskStreamingRequest(params=payload)
+        with httpx.Client(timeout=None) as client:
+            with connect_sse(
+                client, 'POST', self.url, json=request.model_dump()
+            ) as event_source:
+                try:
+                    for sse in event_source.iter_sse():
+                        yield SendTaskStreamingResponse(**json.loads(sse.data))
+                except json.JSONDecodeError as e:
+                    raise A2AClientJSONError(str(e)) from e
+                except httpx.RequestError as e:
+                    raise A2AClientHTTPError(400, str(e)) from e
+
+    async def _send_request(self, request: JSONRPCRequest) -> dict[str, Any]:
+        async with httpx.AsyncClient() as client:
+            try:
+                # Image generation could take time, adding timeout
+                response = await client.post(
+                    self.url, json=request.model_dump(), timeout=30
+                )
+                response.raise_for_status()
+                return response.json()
+            except httpx.HTTPStatusError as e:
+                raise A2AClientHTTPError(e.response.status_code, str(e)) from e
+            except json.JSONDecodeError as e:
+                raise A2AClientJSONError(str(e)) from e
+
+    async def get_task(self, payload: dict[str, Any]) -> GetTaskResponse:
+        request = GetTaskRequest(params=payload)
+        return GetTaskResponse(**await self._send_request(request))
+
+    async def cancel_task(self, payload: dict[str, Any]) -> CancelTaskResponse:
+        request = CancelTaskRequest(params=payload)
+        return CancelTaskResponse(**await self._send_request(request))
+
+    async def set_task_callback(
+        self, payload: dict[str, Any]
+    ) -> SetTaskPushNotificationResponse:
+        request = SetTaskPushNotificationRequest(params=payload)
+        return SetTaskPushNotificationResponse(**await self._send_request(request))
+
+    async def get_task_callback(
+        self, payload: dict[str, Any]
+    ) -> GetTaskPushNotificationResponse:
+        request = GetTaskPushNotificationRequest(params=payload)
+        return GetTaskPushNotificationResponse(**await self._send_request(request))

openhands/runtime/plugins/agent_skills/a2a_client/common/types.py

@@ -0,0 +1,365 @@
+from typing import Union, Any
+from pydantic import BaseModel, Field, TypeAdapter
+from typing import Literal, List, Annotated, Optional
+from datetime import datetime
+from pydantic import model_validator, ConfigDict, field_serializer
+from uuid import uuid4
+from enum import Enum
+from typing_extensions import Self
+
+
+class TaskState(str, Enum):
+    SUBMITTED = "submitted"
+    WORKING = "working"
+    INPUT_REQUIRED = "input-required"
+    COMPLETED = "completed"
+    CANCELED = "canceled"
+    FAILED = "failed"
+    UNKNOWN = "unknown"
+
+
+class TextPart(BaseModel):
+    type: Literal["text"] = "text"
+    text: str
+    metadata: dict[str, Any] | None = None
+
+
+class FileContent(BaseModel):
+    name: str | None = None
+    mimeType: str | None = None
+    bytes: str | None = None
+    uri: str | None = None
+
+    @model_validator(mode="after")
+    def check_content(self) -> Self:
+        if not (self.bytes or self.uri):
+            raise ValueError("Either 'bytes' or 'uri' must be present in the file data")
+        if self.bytes and self.uri:
+            raise ValueError(
+                "Only one of 'bytes' or 'uri' can be present in the file data"
+            )
+        return self
+
+
+class FilePart(BaseModel):
+    type: Literal["file"] = "file"
+    file: FileContent
+    metadata: dict[str, Any] | None = None
+
+
+class DataPart(BaseModel):
+    type: Literal["data"] = "data"
+    data: dict[str, Any]
+    metadata: dict[str, Any] | None = None
+
+
+Part = Annotated[Union[TextPart, FilePart, DataPart], Field(discriminator="type")]
+
+
+class Message(BaseModel):
+    role: Literal["user", "agent"]
+    parts: List[Part]
+    metadata: dict[str, Any] | None = None
+
+
+class TaskStatus(BaseModel):
+    state: TaskState
+    message: Message | None = None
+    timestamp: datetime = Field(default_factory=datetime.now)
+
+    @field_serializer("timestamp")
+    def serialize_dt(self, dt: datetime, _info):
+        return dt.isoformat()
+
+
+class Artifact(BaseModel):
+    name: str | None = None
+    description: str | None = None
+    parts: List[Part]
+    metadata: dict[str, Any] | None = None
+    index: int = 0
+    append: bool | None = None
+    lastChunk: bool | None = None
+
+
+class Task(BaseModel):
+    id: str
+    sessionId: str | None = None
+    status: TaskStatus
+    artifacts: List[Artifact] | None = None
+    history: List[Message] | None = None
+    metadata: dict[str, Any] | None = None
+
+
+class TaskStatusUpdateEvent(BaseModel):
+    id: str
+    status: TaskStatus
+    final: bool = False
+    metadata: dict[str, Any] | None = None
+
+
+class TaskArtifactUpdateEvent(BaseModel):
+    id: str
+    artifact: Artifact    
+    metadata: dict[str, Any] | None = None
+
+
+class AuthenticationInfo(BaseModel):
+    model_config = ConfigDict(extra="allow")
+
+    schemes: List[str]
+    credentials: str | None = None
+
+
+class PushNotificationConfig(BaseModel):
+    url: str
+    token: str | None = None
+    authentication: AuthenticationInfo | None = None
+
+
+class TaskIdParams(BaseModel):
+    id: str
+    metadata: dict[str, Any] | None = None
+
+
+class TaskQueryParams(TaskIdParams):
+    historyLength: int | None = None
+
+
+class TaskSendParams(BaseModel):
+    id: str
+    sessionId: str = Field(default_factory=lambda: uuid4().hex)
+    message: Message
+    acceptedOutputModes: Optional[List[str]] = None
+    pushNotification: PushNotificationConfig | None = None
+    historyLength: int | None = None
+    metadata: dict[str, Any] | None = None
+
+
+class TaskPushNotificationConfig(BaseModel):
+    id: str
+    pushNotificationConfig: PushNotificationConfig
+
+
+## RPC Messages
+
+
+class JSONRPCMessage(BaseModel):
+    jsonrpc: Literal["2.0"] = "2.0"
+    id: int | str | None = Field(default_factory=lambda: uuid4().hex)
+
+
+class JSONRPCRequest(JSONRPCMessage):
+    method: str
+    params: dict[str, Any] | None = None
+
+
+class JSONRPCError(BaseModel):
+    code: int
+    message: str
+    data: Any | None = None
+
+
+class JSONRPCResponse(JSONRPCMessage):
+    result: Any | None = None
+    error: JSONRPCError | None = None
+
+
+class SendTaskRequest(JSONRPCRequest):
+    method: Literal["tasks/send"] = "tasks/send"
+    params: TaskSendParams
+
+
+class SendTaskResponse(JSONRPCResponse):
+    result: Task | None = None
+
+
+class SendTaskStreamingRequest(JSONRPCRequest):
+    method: Literal["tasks/sendSubscribe"] = "tasks/sendSubscribe"
+    params: TaskSendParams
+
+
+class SendTaskStreamingResponse(JSONRPCResponse):
+    result: TaskStatusUpdateEvent | TaskArtifactUpdateEvent | None = None
+
+
+class GetTaskRequest(JSONRPCRequest):
+    method: Literal["tasks/get"] = "tasks/get"
+    params: TaskQueryParams
+
+
+class GetTaskResponse(JSONRPCResponse):
+    result: Task | None = None
+
+
+class CancelTaskRequest(JSONRPCRequest):
+    method: Literal["tasks/cancel",] = "tasks/cancel"
+    params: TaskIdParams
+
+
+class CancelTaskResponse(JSONRPCResponse):
+    result: Task | None = None
+
+
+class SetTaskPushNotificationRequest(JSONRPCRequest):
+    method: Literal["tasks/pushNotification/set",] = "tasks/pushNotification/set"
+    params: TaskPushNotificationConfig
+
+
+class SetTaskPushNotificationResponse(JSONRPCResponse):
+    result: TaskPushNotificationConfig | None = None
+
+
+class GetTaskPushNotificationRequest(JSONRPCRequest):
+    method: Literal["tasks/pushNotification/get",] = "tasks/pushNotification/get"
+    params: TaskIdParams
+
+
+class GetTaskPushNotificationResponse(JSONRPCResponse):
+    result: TaskPushNotificationConfig | None = None
+
+
+class TaskResubscriptionRequest(JSONRPCRequest):
+    method: Literal["tasks/resubscribe",] = "tasks/resubscribe"
+    params: TaskIdParams
+
+
+A2ARequest = TypeAdapter(
+    Annotated[
+        Union[
+            SendTaskRequest,
+            GetTaskRequest,
+            CancelTaskRequest,
+            SetTaskPushNotificationRequest,
+            GetTaskPushNotificationRequest,
+            TaskResubscriptionRequest,
+            SendTaskStreamingRequest,
+        ],
+        Field(discriminator="method"),
+    ]
+)
+
+## Error types
+
+
+class JSONParseError(JSONRPCError):
+    code: int = -32700
+    message: str = "Invalid JSON payload"
+    data: Any | None = None
+
+
+class InvalidRequestError(JSONRPCError):
+    code: int = -32600
+    message: str = "Request payload validation error"
+    data: Any | None = None
+
+
+class MethodNotFoundError(JSONRPCError):
+    code: int = -32601
+    message: str = "Method not found"
+    data: None = None
+
+
+class InvalidParamsError(JSONRPCError):
+    code: int = -32602
+    message: str = "Invalid parameters"
+    data: Any | None = None
+
+
+class InternalError(JSONRPCError):
+    code: int = -32603
+    message: str = "Internal error"
+    data: Any | None = None
+
+
+class TaskNotFoundError(JSONRPCError):
+    code: int = -32001
+    message: str = "Task not found"
+    data: None = None
+
+
+class TaskNotCancelableError(JSONRPCError):
+    code: int = -32002
+    message: str = "Task cannot be canceled"
+    data: None = None
+
+
+class PushNotificationNotSupportedError(JSONRPCError):
+    code: int = -32003
+    message: str = "Push Notification is not supported"
+    data: None = None
+
+
+class UnsupportedOperationError(JSONRPCError):
+    code: int = -32004
+    message: str = "This operation is not supported"
+    data: None = None
+
+
+class ContentTypeNotSupportedError(JSONRPCError):
+    code: int = -32005
+    message: str = "Incompatible content types"
+    data: None = None
+
+
+class AgentProvider(BaseModel):
+    organization: str
+    url: str | None = None
+
+
+class AgentCapabilities(BaseModel):
+    streaming: bool = False
+    pushNotifications: bool = False
+    stateTransitionHistory: bool = False
+
+
+class AgentAuthentication(BaseModel):
+    schemes: List[str]
+    credentials: str | None = None
+
+
+class AgentSkill(BaseModel):
+    id: str
+    name: str
+    description: str | None = None
+    tags: List[str] | None = None
+    examples: List[str] | None = None
+    inputModes: List[str] | None = None
+    outputModes: List[str] | None = None
+
+
+class AgentCard(BaseModel):
+    name: str
+    description: str | None = None
+    url: str
+    provider: AgentProvider | None = None
+    version: str
+    documentationUrl: str | None = None
+    capabilities: AgentCapabilities
+    authentication: AgentAuthentication | None = None
+    defaultInputModes: List[str] = ["text"]
+    defaultOutputModes: List[str] = ["text"]
+    skills: List[AgentSkill]
+
+
+class A2AClientError(Exception):
+    pass
+
+
+class A2AClientHTTPError(A2AClientError):
+    def __init__(self, status_code: int, message: str):
+        self.status_code = status_code
+        self.message = message
+        super().__init__(f"HTTP Error {status_code}: {message}")
+
+
+class A2AClientJSONError(A2AClientError):
+    def __init__(self, message: str):
+        self.message = message
+        super().__init__(f"JSON Error: {message}")
+
+
+class MissingAPIKeyError(Exception):
+    """Exception for missing API key."""
+
+    pass

openhands/runtime/plugins/agent_skills/a2a_client/third_party_license/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

openhands/runtime/plugins/agent_skills/agentskills.py

@@ -1,6 +1,10 @@
 from inspect import signature
 
-from openhands.runtime.plugins.agent_skills import file_ops, file_reader
+from openhands.runtime.plugins.agent_skills import (
+    a2a_client,
+    file_ops,
+    file_reader,
+)
 from openhands.runtime.plugins.agent_skills.utils.dependency import import_functions
 
 import_functions(
@@ -9,8 +13,13 @@ import_functions(
 import_functions(
     module=file_reader, function_names=file_reader.__all__, target_globals=globals()
 )
+import_functions(
+    module=a2a_client,
+    function_names=a2a_client.__all__,
+    target_globals=globals(),
+)
 
-__all__ = file_ops.__all__ + file_reader.__all__
+__all__ = file_ops.__all__ + file_reader.__all__ + a2a_client.__all__
 
 try:
     from openhands.runtime.plugins.agent_skills import repo_ops

openhands/runtime/utils/runtime_templates/Dockerfile.j2

@@ -117,7 +117,7 @@ RUN /openhands/micromamba/bin/micromamba run -n openhands poetry install --only
 
 # Install playwright and its dependencies
 RUN apt-get update && \
-    /openhands/micromamba/bin/micromamba run -n openhands poetry run pip install playwright && \
+    /openhands/micromamba/bin/micromamba run -n openhands poetry run pip install playwright httpx httpx-sse pydantic && \
     /openhands/micromamba/bin/micromamba run -n openhands poetry run playwright install --with-deps chromium
 
 # Set environment variables and permissions

openhands/server/routes/mcp.py

@@ -87,6 +87,7 @@ async def create_pr(
     target_branch: Annotated[str, Field(description='Target branch on repo')],
     title: Annotated[str, Field(description='PR Title')],
     body: Annotated[str | None, Field(description='PR body')],
+    draft: Annotated[bool, Field(description='Whether PR opened is a draft')] = True
 ) -> str:
     """Open a PR in GitHub"""
 
@@ -126,6 +127,7 @@ async def create_pr(
             target_branch=target_branch,
             title=title,
             body=body,
+            draft=draft
         )
 
         if conversation_id:
@@ -146,7 +148,7 @@ async def create_mr(
     ],
     source_branch: Annotated[str, Field(description='Source branch on repo')],
     target_branch: Annotated[str, Field(description='Target branch on repo')],
-    title: Annotated[str, Field(description='MR Title')],
+    title: Annotated[str, Field(description='MR Title. Start title with `DRAFT:` or `WIP:` if applicable.')],
     description: Annotated[str | None, Field(description='MR description')],
 ) -> str:
     """Open a MR in GitLab"""

poetry.lock

@@ -26,98 +26,98 @@ files = [
 
 [[package]]
 name = "aiohttp"
-version = "3.12.11"
+version = "3.12.12"
 description = "Async http client/server framework (asyncio)"
 optional = false
 python-versions = ">=3.9"
 groups = ["main", "evaluation"]
 files = [
-    {file = "aiohttp-3.12.11-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:ff576cb82b995ff213e58255bc776a06ebd5ebb94a587aab2fb5df8ee4e3f967"},
-    {file = "aiohttp-3.12.11-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:fe3a9ae8a7c93bec5b7cfacfbc781ed5ae501cf6a6113cf3339b193af991eaf9"},
-    {file = "aiohttp-3.12.11-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:efafc6f8c7c49ff567e0f02133b4d50eef5183cf96d4b0f1c7858d478e9751f6"},
-    {file = "aiohttp-3.12.11-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c6866da6869cc60d84921b55330d23cbac4f243aebfabd9da47bbc40550e6548"},
-    {file = "aiohttp-3.12.11-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:14aa6f41923324618687bec21adf1d5e8683264ccaa6266c38eb01aeaa404dea"},
-    {file = "aiohttp-3.12.11-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e4aec7c3ccf2ed6b55db39e36eb00ad4e23f784fca2d38ea02e6514c485866dc"},
-    {file = "aiohttp-3.12.11-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:efd174af34bd80aa07813a69fee000ce8745962e2d3807c560bdf4972b5748e4"},
-    {file = "aiohttp-3.12.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fb02a172c073b0aaf792f0b78d02911f124879961d262d3163119a3e91eec31d"},
-    {file = "aiohttp-3.12.11-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bcf5791dcd63e1fc39f5b0d4d16fe5e6f2b62f0f3b0f1899270fa4f949763317"},
-    {file = "aiohttp-3.12.11-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:47f7735b7e44965bd9c4bde62ca602b1614292278315e12fa5afbcc9f9180c28"},
-    {file = "aiohttp-3.12.11-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:d211453930ab5995e99e3ffa7c5c33534852ad123a11761f1bf7810cd853d3d8"},
-    {file = "aiohttp-3.12.11-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:104f1f9135be00c8a71c5fc53ac7d49c293a8eb310379d2171f0e41172277a09"},
-    {file = "aiohttp-3.12.11-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:e6cbaf3c02ef605b6f251d8bb71b06632ba24e365c262323a377b639bcfcbdae"},
-    {file = "aiohttp-3.12.11-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:9d9922bc6cca3bc7a8f8b60a3435f6bca6e33c8f9490f6079a023cfb4ee65af0"},
-    {file = "aiohttp-3.12.11-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:554f4338611155e7d2f0dc01e71e71e5f6741464508cbc31a74eb35c9fb42982"},
-    {file = "aiohttp-3.12.11-cp310-cp310-win32.whl", hash = "sha256:421ca03e2117d8756479e04890659f6b356d6399bbdf07af5a32d5c8b4ace5ac"},
-    {file = "aiohttp-3.12.11-cp310-cp310-win_amd64.whl", hash = "sha256:cd58a0fae0d13a44456953d43706f9457b231879c4b3c9d0a1e0c6e2a4913d46"},
-    {file = "aiohttp-3.12.11-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:a7603f3998cd2893801d254072aaf1b5117183fcf5e726b6c27fc4239dc8c30a"},
-    {file = "aiohttp-3.12.11-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:afe8c1860fb0df6e94725339376628e915b2b85e734eca4d14281ed5c11275b0"},
-    {file = "aiohttp-3.12.11-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f014d909931e34f81b0080b289642d4fc4f4a700a161bd694a5cebdd77882ab5"},
-    {file = "aiohttp-3.12.11-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:734e64ceb8918b3d7099b2d000e174d8d944fb7d494de522cecb0fa45ffcb0cd"},
-    {file = "aiohttp-3.12.11-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:4b603513b4596a8b80bfbedcb33e9f8ed93f44d3dfaac97db0bb9185a6d2c5c0"},
-    {file = "aiohttp-3.12.11-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:196fbd7951b89d9a4be3a09e1f49b3534eb0b764989df66b429e8685138f8d27"},
-    {file = "aiohttp-3.12.11-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1585fefa6a62a1140bf3e439f9648cb5bf360be2bbe76d057dddd175c030e30c"},
-    {file = "aiohttp-3.12.11-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:22e2874e665c771e6c87e81f8d4ac64d999da5e1a110b3ae0088b035529a08d5"},
-    {file = "aiohttp-3.12.11-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f6563fa3bfb79f892a24d3f39ca246c7409cf3b01a3a84c686e548a69e4fc1bf"},
-    {file = "aiohttp-3.12.11-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:f31bfeb53cfc5e028a0ade48ef76a3580016b92007ceb8311f5bd1b4472b7007"},
-    {file = "aiohttp-3.12.11-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:fa806cdb0b7e99fb85daea0de0dda3895eea6a624f962f3800dfbbfc07f34fb6"},
-    {file = "aiohttp-3.12.11-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:210470f8078ecd1f596247a70f17d88c4e785ffa567ab909939746161f304444"},
-    {file = "aiohttp-3.12.11-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:cb9af1ce647cda1707d7b7e23b36eead3104ed959161f14f4ebc51d9b887d4a2"},
-    {file = "aiohttp-3.12.11-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:ccef35cc9e96bb3fcd79f3ef9d6ae4f72c06585c2e818deafc4a499a220904a1"},
-    {file = "aiohttp-3.12.11-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:e8ccb376eaf184bcecd77711697861095bc3352c912282e33d065222682460da"},
-    {file = "aiohttp-3.12.11-cp311-cp311-win32.whl", hash = "sha256:7c345f7e7f10ac21a48ffd387c04a17da06f96bd087d55af30d1af238e9e164d"},
-    {file = "aiohttp-3.12.11-cp311-cp311-win_amd64.whl", hash = "sha256:b461f7918c8042e927f629eccf7c120197135bd2eb14cc12fffa106b937d051b"},
-    {file = "aiohttp-3.12.11-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:3d222c693342ccca64320410ada8f06a47c4762ff82de390f3357a0e51ca102c"},
-    {file = "aiohttp-3.12.11-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:f50c10bd5799d82a9effe90d5d5840e055a2c94e208b76f9ed9e6373ca2426fe"},
-    {file = "aiohttp-3.12.11-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a01a21975b0fd5160886d9f2cd6ed13cdfc8d59f2a51051708ed729afcc2a2fb"},
-    {file = "aiohttp-3.12.11-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:39d29b6888ddd5a120dba1d52c78c0b45f5f34e227a23696cbece684872e62bd"},
-    {file = "aiohttp-3.12.11-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:1df121c3ffcc5f7381cd4c84e8554ff121f558e92c318f48e049843b47ee9f1b"},
-    {file = "aiohttp-3.12.11-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:644f74197757e26266a5f57af23424f8cd506c1ef70d9b288e21244af69d6fdc"},
-    {file = "aiohttp-3.12.11-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:726d9a15a1fd1058b2d27d094b1fec627e9fd92882ca990d90ded9b7c550bd21"},
-    {file = "aiohttp-3.12.11-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:405a60b979da942cec2c26381683bc230f3bcca346bf23a59c1dfc397e44b17b"},
-    {file = "aiohttp-3.12.11-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:27e75e96a4a747756c2f59334e81cbb9a398e015bc9e08b28f91090e5f3a85ef"},
-    {file = "aiohttp-3.12.11-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:15e1da30ac8bf92fb3f8c245ff53ace3f0ea1325750cc2f597fb707140dfd950"},
-    {file = "aiohttp-3.12.11-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:0329934d4df1500f13449c1db205d662123d9d0ee1c9d0c8c0cb997cdac75710"},
-    {file = "aiohttp-3.12.11-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:2a06b2a031d6c828828317ee951f07d8a0455edc9cd4fc0e0432fd6a4dfd612d"},
-    {file = "aiohttp-3.12.11-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:87ece62697b8792e595627c4179f0eca4b038f39b0b354e67a149fa6f83d9493"},
-    {file = "aiohttp-3.12.11-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:5c981b7659379b5cb3b149e480295adfcdf557b5892a792519a56badbe9f33ef"},
-    {file = "aiohttp-3.12.11-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:e6fb2170cb0b9abbe0bee2767b08bb4a3dbf01583880ecea97bca9f3f918ea78"},
-    {file = "aiohttp-3.12.11-cp312-cp312-win32.whl", hash = "sha256:f20e4ec84a26f91adc8c54345a383095248d11851f257c816e8f1d853a6cef4c"},
-    {file = "aiohttp-3.12.11-cp312-cp312-win_amd64.whl", hash = "sha256:b54d4c3cd77cf394e71a7ad5c3b8143a5bfe105a40fc693bcdfe472a286f1d95"},
-    {file = "aiohttp-3.12.11-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:5fadc4b67f972a701805aa501cd9d22cdbeda21f9c9ae85e60678f84b1727a16"},
-    {file = "aiohttp-3.12.11-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:144d67c29ae36f052584fc45a363e92798441a5af5762d83037aade3e2aa9dc5"},
-    {file = "aiohttp-3.12.11-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:6b73299e4bf37d14c6e4ca5ce7087b44914a8d9e1f40faedc271f28d64ec277e"},
-    {file = "aiohttp-3.12.11-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1226325e98e6d3cdfdaca639efdc3af8e82cd17287ae393626d1bd60626b0e93"},
-    {file = "aiohttp-3.12.11-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7a0ecae011f2f779271407f2959877230670de3c48f67e5db9fbafa9fddbfa3a"},
-    {file = "aiohttp-3.12.11-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a8a711883eedcd55f2e1ba218d8224b9f20f1dfac90ffca28e78daf891667e3a"},
-    {file = "aiohttp-3.12.11-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2601c1fcd9b67e632548cfd3c760741b31490502f6f3e5e21287678c1c6fa1b2"},
-    {file = "aiohttp-3.12.11-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8d5b11ea794ee54b33d0d817a1aec0ef0dd2026f070b493bc5a67b7e413b95d4"},
-    {file = "aiohttp-3.12.11-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:109b3544138ce8a5aca598d5e7ff958699e3e19ee3675d27d5ee9c2e30765a4a"},
-    {file = "aiohttp-3.12.11-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:b795085d063d24c6d09300c85ddd6b9c49816d5c498b40b6899ca24584e936e4"},
-    {file = "aiohttp-3.12.11-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:ebcbc113f40e4c9c0f8d2b6b31a2dd2a9768f3fa5f623b7e1285684e24f5159f"},
-    {file = "aiohttp-3.12.11-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:590e5d792150d75fa34029d0555b126e65ad50d66818a996303de4af52b65b32"},
-    {file = "aiohttp-3.12.11-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:9c2a4dec596437b02f0c34f92ea799d6e300184a0304c1e54e462af52abeb0a8"},
-    {file = "aiohttp-3.12.11-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:aace119abc495cc4ced8745e3faceb0c22e8202c60b55217405c5f389b569576"},
-    {file = "aiohttp-3.12.11-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:cd749731390520a2dc1ce215bcf0ee1018c3e2e3cd834f966a02c0e71ad7d637"},
-    {file = "aiohttp-3.12.11-cp313-cp313-win32.whl", hash = "sha256:65952736356d1fbc9efdd17492dce36e2501f609a14ccb298156e392d3ad8b83"},
-    {file = "aiohttp-3.12.11-cp313-cp313-win_amd64.whl", hash = "sha256:854132093e12dd77f5c07975581c42ae51a6a8868dcbbb509c77d1963c3713b7"},
-    {file = "aiohttp-3.12.11-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:4f1f92cde9d9a470121a0912566585cf989f0198718477d73f3ae447a6911644"},
-    {file = "aiohttp-3.12.11-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:f36958b508e03d6c5b2ed3562f517feb415d7cc3a9b2255f319dcedb1517561a"},
-    {file = "aiohttp-3.12.11-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:06e18aaa360d59dd25383f18454f79999915d063b7675cf0ac6e7146d1f19fd1"},
-    {file = "aiohttp-3.12.11-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:019d6075bc18fdc1e47e9dabaf339c9cc32a432aca4894b55e23536919640d87"},
-    {file = "aiohttp-3.12.11-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:063b0de9936ed9b9222aa9bdf34b1cc731d34138adfc4dbb1e4bbde1ab686778"},
-    {file = "aiohttp-3.12.11-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8437e3d8041d4a0d73a48c563188d5821067228d521805906e92f25576076f95"},
-    {file = "aiohttp-3.12.11-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:340ee38cecd533b48f1fe580aa4eddfb9c77af2a80c58d9ff853b9675adde416"},
-    {file = "aiohttp-3.12.11-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f672d8dbca49e9cf9e43de934ee9fd6716740263a7e37c1a3155d6195cdef285"},
-    {file = "aiohttp-3.12.11-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b4a36ae8bebb71276f1aaadb0c08230276fdadad88fef35efab11d17f46b9885"},
-    {file = "aiohttp-3.12.11-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:b63b3b5381791f96b07debbf9e2c4e909c87ecbebe4fea9dcdc82789c7366234"},
-    {file = "aiohttp-3.12.11-cp39-cp39-musllinux_1_2_armv7l.whl", hash = "sha256:8d353c5396964a79b505450e8efbfd468b0a042b676536505e8445d9ab1ef9ae"},
-    {file = "aiohttp-3.12.11-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:8ddd775457180d149ca0dbc4ebff5616948c09fa914b66785e5f23227fec5a05"},
-    {file = "aiohttp-3.12.11-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:29f642b386daf2fadccbcd2bc8a3d6541a945c0b436f975c3ce0ec318b55ad6e"},
-    {file = "aiohttp-3.12.11-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:cb907dcd8899084a56bb13a74e9fdb49070aed06229ae73395f49a9ecddbd9b1"},
-    {file = "aiohttp-3.12.11-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:760846271518d649be968cee1b245b84d348afe896792279312ca758511d798f"},
-    {file = "aiohttp-3.12.11-cp39-cp39-win32.whl", hash = "sha256:d28f7d2b68f4ef4006ca92baea02aa2dce2b8160cf471e4c3566811125f5c8b9"},
-    {file = "aiohttp-3.12.11-cp39-cp39-win_amd64.whl", hash = "sha256:2af98debfdfcc52cae5713bbfbfe3328fc8591c6f18c93cf3b61749de75f6ef2"},
-    {file = "aiohttp-3.12.11.tar.gz", hash = "sha256:a5149ae1b11ce4cf8b122846bfa3d7c5f29fe3bfe6745ab21b3eea9615bc5564"},
+    {file = "aiohttp-3.12.12-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:6f25e9d274d6abbb15254f76f100c3984d6b9ad6e66263cc60a465dd5c7e48f5"},
+    {file = "aiohttp-3.12.12-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:b8ec3c1a1c13d24941b5b913607e57b9364e4c0ea69d5363181467492c4b2ba6"},
+    {file = "aiohttp-3.12.12-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:81ef2f9253c327c211cb7b06ea2edd90e637cf21c347b894d540466b8d304e08"},
+    {file = "aiohttp-3.12.12-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:28ded835c3663fd41c9ad44685811b11e34e6ac9a7516a30bfce13f6abba4496"},
+    {file = "aiohttp-3.12.12-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:a4b78ccf254fc10605b263996949a94ca3f50e4f9100e05137d6583e266b711e"},
+    {file = "aiohttp-3.12.12-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4f4a5af90d5232c41bb857568fe7d11ed84408653ec9da1ff999cc30258b9bd1"},
+    {file = "aiohttp-3.12.12-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ffa5205c2f53f1120e93fdf2eca41b0f6344db131bc421246ee82c1e1038a14a"},
+    {file = "aiohttp-3.12.12-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f68301660f0d7a3eddfb84f959f78a8f9db98c76a49b5235508fa16edaad0f7c"},
+    {file = "aiohttp-3.12.12-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:db874d3b0c92fdbb553751af9d2733b378c25cc83cd9dfba87f12fafd2dc9cd5"},
+    {file = "aiohttp-3.12.12-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:5e53cf9c201b45838a2d07b1f2d5f7fec9666db7979240002ce64f9b8a1e0cf2"},
+    {file = "aiohttp-3.12.12-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:8687cc5f32b4e328c233acd387d09a1b477007896b2f03c1c823a0fd05f63883"},
+    {file = "aiohttp-3.12.12-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:5ee537ad29de716a3d8dc46c609908de0c25ffeebf93cd94a03d64cdc07d66d0"},
+    {file = "aiohttp-3.12.12-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:411f821be5af6af11dc5bed6c6c1dc6b6b25b91737d968ec2756f9baa75e5f9b"},
+    {file = "aiohttp-3.12.12-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:f90319d94cf5f9786773237f24bd235a7b5959089f1af8ec1154580a3434b503"},
+    {file = "aiohttp-3.12.12-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:73b148e606f34e9d513c451fd65efe1091772659ca5703338a396a99f60108ff"},
+    {file = "aiohttp-3.12.12-cp310-cp310-win32.whl", hash = "sha256:d40e7bfd577fdc8a92b72f35dfbdd3ec90f1bc8a72a42037fefe34d4eca2d4a1"},
+    {file = "aiohttp-3.12.12-cp310-cp310-win_amd64.whl", hash = "sha256:65c7804a2343893d6dea9fce69811aea0a9ac47f68312cf2e3ee1668cd9a387f"},
+    {file = "aiohttp-3.12.12-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:38823fe0d8bc059b3eaedb263fe427d887c7032e72b4ef92c472953285f0e658"},
+    {file = "aiohttp-3.12.12-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:10237f2c34711215d04ed21da63852ce023608299554080a45c576215d9df81c"},
+    {file = "aiohttp-3.12.12-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:563ec477c0dc6d56fc7f943a3475b5acdb399c7686c30f5a98ada24bb7562c7a"},
+    {file = "aiohttp-3.12.12-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f3d05c46a61aca7c47df74afff818bc06a251ab95d95ff80b53665edfe1e0bdf"},
+    {file = "aiohttp-3.12.12-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:277c882916759b4a6b6dc7e2ceb124aad071b3c6456487808d9ab13e1b448d57"},
+    {file = "aiohttp-3.12.12-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:216abf74b324b0f4e67041dd4fb2819613909a825904f8a51701fbcd40c09cd7"},
+    {file = "aiohttp-3.12.12-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:65d6cefad286459b68e7f867b9586a821fb7f121057b88f02f536ef570992329"},
+    {file = "aiohttp-3.12.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:feaaaff61966b5f4b4eae0b79fc79427f49484e4cfa5ab7d138ecd933ab540a8"},
+    {file = "aiohttp-3.12.12-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a05917780b7cad1755784b16cfaad806bc16029a93d15f063ca60185b7d9ba05"},
+    {file = "aiohttp-3.12.12-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:082c5ec6d262c1b2ee01c63f4fb9152c17f11692bf16f0f100ad94a7a287d456"},
+    {file = "aiohttp-3.12.12-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:b265a3a8b379b38696ac78bdef943bdc4f4a5d6bed1a3fb5c75c6bab1ecea422"},
+    {file = "aiohttp-3.12.12-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:2e0f2e208914ecbc4b2a3b7b4daa759d0c587d9a0b451bb0835ac47fae7fa735"},
+    {file = "aiohttp-3.12.12-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:9923b025845b72f64d167bca221113377c8ffabd0a351dc18fb839d401ee8e22"},
+    {file = "aiohttp-3.12.12-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:1ebb213445900527831fecc70e185bf142fdfe5f2a691075f22d63c65ee3c35a"},
+    {file = "aiohttp-3.12.12-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:6fc369fb273a8328077d37798b77c1e65676709af5c182cb74bd169ca9defe81"},
+    {file = "aiohttp-3.12.12-cp311-cp311-win32.whl", hash = "sha256:58ecd10fda6a44c311cd3742cfd2aea8c4c600338e9f27cb37434d9f5ca9ddaa"},
+    {file = "aiohttp-3.12.12-cp311-cp311-win_amd64.whl", hash = "sha256:b0066e88f30be00badffb5ef8f2281532b9a9020863d873ae15f7c147770b6ec"},
+    {file = "aiohttp-3.12.12-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:98451ce9ce229d092f278a74a7c2a06b3aa72984673c87796126d7ccade893e9"},
+    {file = "aiohttp-3.12.12-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:adbac7286d89245e1aff42e948503fdc6edf6d5d65c8e305a67c40f6a8fb95f4"},
+    {file = "aiohttp-3.12.12-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0728882115bfa85cbd8d0f664c8ccc0cfd5bd3789dd837596785450ae52fac31"},
+    {file = "aiohttp-3.12.12-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6bf3b9d9e767f9d0e09fb1a31516410fc741a62cc08754578c40abc497d09540"},
+    {file = "aiohttp-3.12.12-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:c944860e86b9f77a462321a440ccf6fa10f5719bb9d026f6b0b11307b1c96c7b"},
+    {file = "aiohttp-3.12.12-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3b1979e1f0c98c06fd0cd940988833b102fa3aa56751f6c40ffe85cabc51f6fd"},
+    {file = "aiohttp-3.12.12-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:120b7dd084e96cfdad85acea2ce1e7708c70a26db913eabb8d7b417c728f5d84"},
+    {file = "aiohttp-3.12.12-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0e58f5ae79649ffa247081c2e8c85e31d29623cf2a3137dda985ae05c9478aae"},
+    {file = "aiohttp-3.12.12-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9aa5f049e3e2745b0141f13e5a64e7c48b1a1427ed18bbb7957b348f282fee56"},
+    {file = "aiohttp-3.12.12-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:7163cc9cf3722d90f1822f8a38b211e3ae2fc651c63bb55449f03dc1b3ff1d44"},
+    {file = "aiohttp-3.12.12-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:ef97c4d035b721de6607f3980fa3e4ef0ec3aca76474b5789b7fac286a8c4e23"},
+    {file = "aiohttp-3.12.12-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:1c14448d6a86acadc3f7b2f4cc385d1fb390acb6f37dce27f86fe629410d92e3"},
+    {file = "aiohttp-3.12.12-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:a1b6df6255cfc493454c79221183d64007dd5080bcda100db29b7ff181b8832c"},
+    {file = "aiohttp-3.12.12-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:60fc7338dfb0626c2927bfbac4785de3ea2e2bbe3d328ba5f3ece123edda4977"},
+    {file = "aiohttp-3.12.12-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:d2afc72207ef4c9d4ca9fcd00689a6a37ef2d625600c3d757b5c2b80c9d0cf9a"},
+    {file = "aiohttp-3.12.12-cp312-cp312-win32.whl", hash = "sha256:8098a48f93b2cbcdb5778e7c9a0e0375363e40ad692348e6e65c3b70d593b27c"},
+    {file = "aiohttp-3.12.12-cp312-cp312-win_amd64.whl", hash = "sha256:d1c1879b2e0fc337d7a1b63fe950553c2b9e93c071cf95928aeea1902d441403"},
+    {file = "aiohttp-3.12.12-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:ea5d604318234427929d486954e3199aded65f41593ac57aa0241ab93dda3d15"},
+    {file = "aiohttp-3.12.12-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:e03ff38250b8b572dce6fcd7b6fb6ee398bb8a59e6aa199009c5322d721df4fc"},
+    {file = "aiohttp-3.12.12-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:71125b1fc2b6a94bccc63bbece620906a4dead336d2051f8af9cbf04480bc5af"},
+    {file = "aiohttp-3.12.12-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:784a66f9f853a22c6b8c2bd0ff157f9b879700f468d6d72cfa99167df08c5c9c"},
+    {file = "aiohttp-3.12.12-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:a5be0b58670b54301404bd1840e4902570a1c3be00358e2700919cb1ea73c438"},
+    {file = "aiohttp-3.12.12-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ce8f13566fc7bf5a728275b434bc3bdea87a7ed3ad5f734102b02ca59d9b510f"},
+    {file = "aiohttp-3.12.12-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d736e57d1901683bc9be648aa308cb73e646252c74b4c639c35dcd401ed385ea"},
+    {file = "aiohttp-3.12.12-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e2007eaa7aae9102f211c519d1ec196bd3cecb1944a095db19eeaf132b798738"},
+    {file = "aiohttp-3.12.12-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2a813e61583cab6d5cdbaa34bc28863acdb92f9f46e11de1b3b9251a1e8238f6"},
+    {file = "aiohttp-3.12.12-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:e408293aa910b0aea48b86a28eace41d497a85ba16c20f619f0c604597ef996c"},
+    {file = "aiohttp-3.12.12-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:f3d31faf290f5a30acba46b388465b67c6dbe8655d183e9efe2f6a1d594e6d9d"},
+    {file = "aiohttp-3.12.12-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:0b84731697325b023902aa643bd1726d999f5bc7854bc28b17ff410a81151d4b"},
+    {file = "aiohttp-3.12.12-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:a324c6852b6e327811748446e56cc9bb6eaa58710557922183175816e82a4234"},
+    {file = "aiohttp-3.12.12-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:22fd867fbd72612dcf670c90486dbcbaf702cb807fb0b42bc0b7a142a573574a"},
+    {file = "aiohttp-3.12.12-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:3e092f1a970223794a4bf620a26c0e4e4e8e36bccae9b0b5da35e6d8ee598a03"},
+    {file = "aiohttp-3.12.12-cp313-cp313-win32.whl", hash = "sha256:7f5f5eb8717ef8ba15ab35fcde5a70ad28bbdc34157595d1cddd888a985f5aae"},
+    {file = "aiohttp-3.12.12-cp313-cp313-win_amd64.whl", hash = "sha256:ace2499bdd03c329c054dc4b47361f2b19d5aa470f7db5c7e0e989336761b33c"},
+    {file = "aiohttp-3.12.12-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:0d0b1c27c05a7d39a50e946ec5f94c3af4ffadd33fa5f20705df42fb0a72ca14"},
+    {file = "aiohttp-3.12.12-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:e5928847e6f7b7434921fbabf73fa5609d1f2bf4c25d9d4522b1fcc3b51995cb"},
+    {file = "aiohttp-3.12.12-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:7678147c3c85a7ae61559b06411346272ed40a08f54bc05357079a63127c9718"},
+    {file = "aiohttp-3.12.12-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f50057f36f2a1d8e750b273bb966bec9f69ee1e0a20725ae081610501f25d555"},
+    {file = "aiohttp-3.12.12-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:e5e834f0f11ff5805d11f0f22b627c75eadfaf91377b457875e4e3affd0b924f"},
+    {file = "aiohttp-3.12.12-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f94b2e2dea19d09745ef02ed483192260750f18731876a5c76f1c254b841443a"},
+    {file = "aiohttp-3.12.12-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b434bfb49564dc1c318989a0ab1d3000d23e5cfd00d8295dc9d5a44324cdd42d"},
+    {file = "aiohttp-3.12.12-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8ed76bc80177ddb7c5c93e1a6440b115ed2c92a3063420ac55206fd0832a6459"},
+    {file = "aiohttp-3.12.12-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e1282a9acd378f2aed8dc79c01e702b1d5fd260ad083926a88ec7e987c4e0ade"},
+    {file = "aiohttp-3.12.12-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:09a213c13fba321586edab1528b530799645b82bd64d79b779eb8d47ceea155a"},
+    {file = "aiohttp-3.12.12-cp39-cp39-musllinux_1_2_armv7l.whl", hash = "sha256:72eae16a9233561d315e72ae78ed9fc65ab3db0196e56cb2d329c755d694f137"},
+    {file = "aiohttp-3.12.12-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:f25990c507dbbeefd5a6a17df32a4ace634f7b20a38211d1b9609410c7f67a24"},
+    {file = "aiohttp-3.12.12-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:3a2aa255417c8ccf1b39359cd0a3d63ae3b5ced83958dbebc4d9113327c0536a"},
+    {file = "aiohttp-3.12.12-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:a4c53b89b3f838e9c25f943d1257efff10b348cb56895f408ddbcb0ec953a2ad"},
+    {file = "aiohttp-3.12.12-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:b5a49c2dcb32114455ad503e8354624d85ab311cbe032da03965882492a9cb98"},
+    {file = "aiohttp-3.12.12-cp39-cp39-win32.whl", hash = "sha256:74fddc0ba8cea6b9c5bd732eb9d97853543586596b86391f8de5d4f6c2a0e068"},
+    {file = "aiohttp-3.12.12-cp39-cp39-win_amd64.whl", hash = "sha256:ddf40ba4a1d0b4d232dc47d2b98ae7e937dcbc40bb5f2746bce0af490a64526f"},
+    {file = "aiohttp-3.12.12.tar.gz", hash = "sha256:05875595d2483d96cb61fa9f64e75262d7ac6251a7e3c811d8e26f7d721760bd"},
 ]
 
 [package.dependencies]
@@ -213,14 +213,14 @@ files = [
 
 [[package]]
 name = "anthropic"
-version = "0.53.0"
+version = "0.54.0"
 description = "The official Python library for the anthropic API"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "anthropic-0.53.0-py3-none-any.whl", hash = "sha256:b3a84751885a81d96bbddef180c3ce559c9140f7f230cdd825385405bd6d312e"},
-    {file = "anthropic-0.53.0.tar.gz", hash = "sha256:f5d1499fc45b2e05801fcbbeae25679f72f7479763e3c706126a7a7c8de06eff"},
+    {file = "anthropic-0.54.0-py3-none-any.whl", hash = "sha256:c1062a0a905daeec17ca9c06c401e4b3f24cb0495841d29d752568a1d4018d56"},
+    {file = "anthropic-0.54.0.tar.gz", hash = "sha256:5e6f997d97ce8e70eac603c3ec2e7f23addeff953fbbb76b19430562bb6ba815"},
 ]
 
 [package.dependencies]
@@ -581,18 +581,18 @@ files = [
 
 [[package]]
 name = "boto3"
-version = "1.38.33"
+version = "1.38.36"
 description = "The AWS SDK for Python"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "boto3-1.38.33-py3-none-any.whl", hash = "sha256:25d0717489c658f7ae6c3c7f0f7e1b4d611b30b2f08f0fcef6455ac6864a8768"},
-    {file = "boto3-1.38.33.tar.gz", hash = "sha256:6467909c1ae01ff67981f021bb2568592211765ec8a9a1d2c4529191e46c3541"},
+    {file = "boto3-1.38.36-py3-none-any.whl", hash = "sha256:34c27d7317cadb62c0e9856e5d5aa0271ef47202d340584831048bc7ac904136"},
+    {file = "boto3-1.38.36.tar.gz", hash = "sha256:efe0aaa060f8fedd76e5c942055f051aee0432fc722d79d8830a9fd9db83593e"},
 ]
 
 [package.dependencies]
-botocore = ">=1.38.33,<1.39.0"
+botocore = ">=1.38.36,<1.39.0"
 jmespath = ">=0.7.1,<2.0.0"
 s3transfer = ">=0.13.0,<0.14.0"
 
@@ -601,14 +601,14 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"]
 
 [[package]]
 name = "boto3-stubs"
-version = "1.38.33"
-description = "Type annotations for boto3 1.38.33 generated with mypy-boto3-builder 8.11.0"
+version = "1.38.36"
+description = "Type annotations for boto3 1.38.36 generated with mypy-boto3-builder 8.11.0"
 optional = false
 python-versions = ">=3.8"
 groups = ["evaluation"]
 files = [
-    {file = "boto3_stubs-1.38.33-py3-none-any.whl", hash = "sha256:ec1487c0d47c865f95287f07e78398b8a1e833cc825aff207c0070e19e1ab6b6"},
-    {file = "boto3_stubs-1.38.33.tar.gz", hash = "sha256:67c9151e8c3e755bc0315be14853d9abf8fd16d1d0e805e7cafa5d58555410bf"},
+    {file = "boto3_stubs-1.38.36-py3-none-any.whl", hash = "sha256:1f79b85f93772df94854e9e570a917f1d762f4080a88ed16b9f2e4b98b24f1f1"},
+    {file = "boto3_stubs-1.38.36.tar.gz", hash = "sha256:8de916b9433e9224f3bd4a79ed41e508dc532bfee7db34bfd3752901bcd7e69f"},
 ]
 
 [package.dependencies]
@@ -664,7 +664,7 @@ bedrock-data-automation-runtime = ["mypy-boto3-bedrock-data-automation-runtime (
 bedrock-runtime = ["mypy-boto3-bedrock-runtime (>=1.38.0,<1.39.0)"]
 billing = ["mypy-boto3-billing (>=1.38.0,<1.39.0)"]
 billingconductor = ["mypy-boto3-billingconductor (>=1.38.0,<1.39.0)"]
-boto3 = ["boto3 (==1.38.33)"]
+boto3 = ["boto3 (==1.38.36)"]
 braket = ["mypy-boto3-braket (>=1.38.0,<1.39.0)"]
 budgets = ["mypy-boto3-budgets (>=1.38.0,<1.39.0)"]
 ce = ["mypy-boto3-ce (>=1.38.0,<1.39.0)"]
@@ -1028,14 +1028,14 @@ xray = ["mypy-boto3-xray (>=1.38.0,<1.39.0)"]
 
 [[package]]
 name = "botocore"
-version = "1.38.33"
+version = "1.38.36"
 description = "Low-level, data-driven core of boto 3."
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "botocore-1.38.33-py3-none-any.whl", hash = "sha256:ad25233e93dcebe95809b1f9393c1f11a639696327793d166295fb78dd7bc597"},
-    {file = "botocore-1.38.33.tar.gz", hash = "sha256:dbe8fea9d0426c644c89ef2018ead886ccbcc22901a02b377b4e65ce1cb69a2b"},
+    {file = "botocore-1.38.36-py3-none-any.whl", hash = "sha256:b6a50b853f6d23af9edfed89a59800c6bc1687a947cdd3492879f7d64e002d30"},
+    {file = "botocore-1.38.36.tar.gz", hash = "sha256:4a1ced1a4218bdff0ed5b46abb54570d473154ddefafa5d121a8d96e4b76ebc1"},
 ]
 
 [package.dependencies]
@@ -3011,14 +3011,14 @@ grpcio-gcp = ["grpcio-gcp (>=0.2.2,<1.0.0)"]
 
 [[package]]
 name = "google-api-python-client"
-version = "2.171.0"
+version = "2.172.0"
 description = "Google API Client Library for Python"
 optional = false
 python-versions = ">=3.7"
 groups = ["main"]
 files = [
-    {file = "google_api_python_client-2.171.0-py3-none-any.whl", hash = "sha256:c9c9b76f561e9d9ac14e54a9e2c0842876201d5b96e69e48f967373f0784cbe9"},
-    {file = "google_api_python_client-2.171.0.tar.gz", hash = "sha256:057a5c08d28463c6b9eb89746355de5f14b7ed27a65c11fdbf1d06c66bb66b23"},
+    {file = "google_api_python_client-2.172.0-py3-none-any.whl", hash = "sha256:9f1b9a268d5dc1228207d246c673d3a09ee211b41a11521d38d9212aeaa43af7"},
+    {file = "google_api_python_client-2.172.0.tar.gz", hash = "sha256:dcb3b7e067154b2aa41f1776cf86584a5739c0ac74e6ff46fc665790dca0e6a6"},
 ]
 
 [package.dependencies]
@@ -3093,14 +3093,14 @@ tool = ["click (>=6.0.0)"]
 
 [[package]]
 name = "google-cloud-aiplatform"
-version = "1.96.0"
+version = "1.97.0"
 description = "Vertex AI API client library"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "google_cloud_aiplatform-1.96.0-py2.py3-none-any.whl", hash = "sha256:fca9edab98caf354f415285bbcf4a282b7015b58b82fab7fb422d2a535940b8f"},
-    {file = "google_cloud_aiplatform-1.96.0.tar.gz", hash = "sha256:c704bf2409d3aca548df5cf036e6e54adf6acf8c114b01a926925e4c65085a53"},
+    {file = "google_cloud_aiplatform-1.97.0-py2.py3-none-any.whl", hash = "sha256:4db9455308110b1e8c1b587bd3ff34449fa459fda45c4466b9b2d9ae259a7af6"},
+    {file = "google_cloud_aiplatform-1.97.0.tar.gz", hash = "sha256:01277ac5648abe7d2af688b123d7d050c1a34922e9f4297e51e44d165cb79b45"},
 ]
 
 [package.dependencies]
@@ -3127,8 +3127,8 @@ autologging = ["mlflow (>=1.27.0,<=2.16.0)"]
 cloud-profiler = ["tensorboard-plugin-profile (>=2.4.0,<2.18.0)", "werkzeug (>=2.0.0,<4.0.0)"]
 datasets = ["pyarrow (>=10.0.1) ; python_version == \"3.11\"", "pyarrow (>=14.0.0) ; python_version >= \"3.12\"", "pyarrow (>=3.0.0,<8.0.0) ; python_version < \"3.11\""]
 endpoint = ["requests (>=2.28.1)", "requests-toolbelt (<=1.0.0)"]
-evaluation = ["jsonschema", "pandas (>=1.0.0)", "ruamel.yaml", "scikit-learn (<1.6.0) ; python_version <= \"3.10\"", "scikit-learn ; python_version > \"3.10\"", "tqdm (>=4.23.0)"]
-full = ["docker (>=5.0.3)", "explainable-ai-sdk (>=1.0.0)", "fastapi (>=0.71.0,<=0.114.0)", "google-cloud-bigquery", "google-cloud-bigquery-storage", "google-vizier (>=0.1.6)", "httpx (>=0.23.0,<=0.28.1)", "immutabledict", "jsonschema", "lit-nlp (==0.4.0)", "mlflow (>=1.27.0,<=2.16.0)", "numpy (>=1.15.0)", "pandas (>=1.0.0)", "pyarrow (>=10.0.1) ; python_version == \"3.11\"", "pyarrow (>=14.0.0) ; python_version >= \"3.12\"", "pyarrow (>=3.0.0,<8.0.0) ; python_version < \"3.11\"", "pyarrow (>=6.0.1)", "pyyaml (>=5.3.1,<7)", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<2.10.dev0 || ==2.33.* || >=2.42.dev0,<=2.42.0) ; python_version < \"3.11\"", "ray[default] (>=2.5,<=2.42.0) ; python_version == \"3.11\"", "requests (>=2.28.1)", "requests-toolbelt (<=1.0.0)", "ruamel.yaml", "scikit-learn (<1.6.0) ; python_version <= \"3.10\"", "scikit-learn ; python_version > \"3.10\"", "setuptools (<70.0.0)", "starlette (>=0.17.1)", "tensorboard-plugin-profile (>=2.4.0,<2.18.0)", "tensorflow (>=2.3.0,<3.0.0)", "tensorflow (>=2.3.0,<3.0.0)", "tqdm (>=4.23.0)", "urllib3 (>=1.21.1,<1.27)", "uvicorn[standard] (>=0.16.0)", "werkzeug (>=2.0.0,<4.0.0)"]
+evaluation = ["jsonschema", "pandas (>=1.0.0)", "pyyaml", "ruamel.yaml", "scikit-learn (<1.6.0) ; python_version <= \"3.10\"", "scikit-learn ; python_version > \"3.10\"", "tqdm (>=4.23.0)"]
+full = ["docker (>=5.0.3)", "explainable-ai-sdk (>=1.0.0)", "fastapi (>=0.71.0,<=0.114.0)", "google-cloud-bigquery", "google-cloud-bigquery-storage", "google-vizier (>=0.1.6)", "httpx (>=0.23.0,<=0.28.1)", "immutabledict", "jsonschema", "lit-nlp (==0.4.0)", "mlflow (>=1.27.0,<=2.16.0)", "numpy (>=1.15.0)", "pandas (>=1.0.0)", "pyarrow (>=10.0.1) ; python_version == \"3.11\"", "pyarrow (>=14.0.0) ; python_version >= \"3.12\"", "pyarrow (>=3.0.0,<8.0.0) ; python_version < \"3.11\"", "pyarrow (>=6.0.1)", "pyyaml", "pyyaml (>=5.3.1,<7)", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<2.10.dev0 || ==2.33.* || >=2.42.dev0,<=2.42.0) ; python_version < \"3.11\"", "ray[default] (>=2.5,<=2.42.0) ; python_version == \"3.11\"", "requests (>=2.28.1)", "requests-toolbelt (<=1.0.0)", "ruamel.yaml", "scikit-learn (<1.6.0) ; python_version <= \"3.10\"", "scikit-learn ; python_version > \"3.10\"", "setuptools (<70.0.0)", "starlette (>=0.17.1)", "tensorboard-plugin-profile (>=2.4.0,<2.18.0)", "tensorflow (>=2.3.0,<3.0.0)", "tensorflow (>=2.3.0,<3.0.0)", "tqdm (>=4.23.0)", "urllib3 (>=1.21.1,<1.27)", "uvicorn[standard] (>=0.16.0)", "werkzeug (>=2.0.0,<4.0.0)"]
 langchain = ["langchain (>=0.3,<0.4)", "langchain-core (>=0.3,<0.4)", "langchain-google-vertexai (>=2.0.22,<3)", "langgraph (>=0.2.45,<0.4)", "openinference-instrumentation-langchain (>=0.1.19,<0.2)"]
 langchain-testing = ["absl-py", "cloudpickle (>=3.0,<4.0)", "google-cloud-trace (<2)", "langchain (>=0.3,<0.4)", "langchain-core (>=0.3,<0.4)", "langchain-google-vertexai (>=2.0.22,<3)", "langgraph (>=0.2.45,<0.4)", "openinference-instrumentation-langchain (>=0.1.19,<0.2)", "opentelemetry-exporter-gcp-trace (<2)", "opentelemetry-sdk (<2)", "pydantic (>=2.11.1,<3)", "pytest-xdist", "typing_extensions"]
 lit = ["explainable-ai-sdk (>=1.0.0)", "lit-nlp (==0.4.0)", "pandas (>=1.0.0)", "tensorflow (>=2.3.0,<3.0.0)"]
@@ -3142,7 +3142,7 @@ ray = ["google-cloud-bigquery", "google-cloud-bigquery-storage", "immutabledict"
 ray-testing = ["google-cloud-bigquery", "google-cloud-bigquery-storage", "immutabledict", "pandas (>=1.0.0)", "pyarrow (>=6.0.1)", "pytest-xdist", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<2.10.dev0 || ==2.33.* || >=2.42.dev0,<=2.42.0) ; python_version < \"3.11\"", "ray[default] (>=2.5,<=2.42.0) ; python_version == \"3.11\"", "ray[train]", "scikit-learn (<1.6.0)", "setuptools (<70.0.0)", "tensorflow", "torch (>=2.0.0,<2.1.0)", "xgboost", "xgboost_ray"]
 reasoningengine = ["cloudpickle (>=3.0,<4.0)", "google-cloud-trace (<2)", "opentelemetry-exporter-gcp-trace (<2)", "opentelemetry-sdk (<2)", "pydantic (>=2.11.1,<3)", "typing_extensions"]
 tensorboard = ["tensorboard-plugin-profile (>=2.4.0,<2.18.0)", "werkzeug (>=2.0.0,<4.0.0)"]
-testing = ["aiohttp", "bigframes ; python_version >= \"3.10\"", "docker (>=5.0.3)", "explainable-ai-sdk (>=1.0.0)", "fastapi (>=0.71.0,<=0.114.0)", "google-api-core (>=2.11,<3.0.0)", "google-cloud-bigquery", "google-cloud-bigquery-storage", "google-vizier (>=0.1.6)", "google-vizier (>=0.1.6)", "grpcio-testing", "httpx (>=0.23.0,<=0.28.1)", "immutabledict", "immutabledict", "ipython", "jsonschema", "kfp (>=2.6.0,<3.0.0)", "lit-nlp (==0.4.0)", "mlflow (>=1.27.0,<=2.16.0)", "nltk", "numpy (>=1.15.0)", "pandas (>=1.0.0)", "protobuf (<=5.29.4)", "pyarrow (>=10.0.1) ; python_version == \"3.11\"", "pyarrow (>=14.0.0) ; python_version >= \"3.12\"", "pyarrow (>=3.0.0,<8.0.0) ; python_version < \"3.11\"", "pyarrow (>=6.0.1)", "pytest-asyncio", "pytest-xdist", "pyyaml (>=5.3.1,<7)", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<2.10.dev0 || ==2.33.* || >=2.42.dev0,<=2.42.0) ; python_version < \"3.11\"", "ray[default] (>=2.5,<=2.42.0) ; python_version == \"3.11\"", "requests (>=2.28.1)", "requests-toolbelt (<=1.0.0)", "requests-toolbelt (<=1.0.0)", "ruamel.yaml", "scikit-learn (<1.6.0) ; python_version <= \"3.10\"", "scikit-learn (<1.6.0) ; python_version <= \"3.10\"", "scikit-learn ; python_version > \"3.10\"", "scikit-learn ; python_version > \"3.10\"", "sentencepiece (>=0.2.0)", "setuptools (<70.0.0)", "starlette (>=0.17.1)", "tensorboard-plugin-profile (>=2.4.0,<2.18.0)", "tensorboard-plugin-profile (>=2.4.0,<2.18.0)", "tensorflow (==2.14.1) ; python_version <= \"3.11\"", "tensorflow (==2.19.0) ; python_version > \"3.11\"", "tensorflow (>=2.3.0,<3.0.0)", "tensorflow (>=2.3.0,<3.0.0)", "torch (>=2.0.0,<2.1.0) ; python_version <= \"3.11\"", "torch (>=2.2.0) ; python_version > \"3.11\"", "tqdm (>=4.23.0)", "urllib3 (>=1.21.1,<1.27)", "uvicorn[standard] (>=0.16.0)", "werkzeug (>=2.0.0,<4.0.0)", "werkzeug (>=2.0.0,<4.0.0)", "xgboost"]
+testing = ["aiohttp", "bigframes ; python_version >= \"3.10\"", "docker (>=5.0.3)", "explainable-ai-sdk (>=1.0.0)", "fastapi (>=0.71.0,<=0.114.0)", "google-api-core (>=2.11,<3.0.0)", "google-cloud-bigquery", "google-cloud-bigquery-storage", "google-vizier (>=0.1.6)", "google-vizier (>=0.1.6)", "grpcio-testing", "httpx (>=0.23.0,<=0.28.1)", "immutabledict", "immutabledict", "ipython", "jsonschema", "kfp (>=2.6.0,<3.0.0)", "lit-nlp (==0.4.0)", "mlflow (>=1.27.0,<=2.16.0)", "nltk", "numpy (>=1.15.0)", "pandas (>=1.0.0)", "protobuf (<=5.29.4)", "pyarrow (>=10.0.1) ; python_version == \"3.11\"", "pyarrow (>=14.0.0) ; python_version >= \"3.12\"", "pyarrow (>=3.0.0,<8.0.0) ; python_version < \"3.11\"", "pyarrow (>=6.0.1)", "pytest-asyncio", "pytest-xdist", "pyyaml", "pyyaml (>=5.3.1,<7)", "ray[default] (>=2.4,<2.5.dev0 || >2.9.0,!=2.9.1,!=2.9.2,<2.10.dev0 || ==2.33.* || >=2.42.dev0,<=2.42.0) ; python_version < \"3.11\"", "ray[default] (>=2.5,<=2.42.0) ; python_version == \"3.11\"", "requests (>=2.28.1)", "requests-toolbelt (<=1.0.0)", "requests-toolbelt (<=1.0.0)", "ruamel.yaml", "scikit-learn (<1.6.0) ; python_version <= \"3.10\"", "scikit-learn (<1.6.0) ; python_version <= \"3.10\"", "scikit-learn ; python_version > \"3.10\"", "scikit-learn ; python_version > \"3.10\"", "sentencepiece (>=0.2.0)", "setuptools (<70.0.0)", "starlette (>=0.17.1)", "tensorboard-plugin-profile (>=2.4.0,<2.18.0)", "tensorboard-plugin-profile (>=2.4.0,<2.18.0)", "tensorflow (==2.14.1) ; python_version <= \"3.11\"", "tensorflow (==2.19.0) ; python_version > \"3.11\"", "tensorflow (>=2.3.0,<3.0.0)", "tensorflow (>=2.3.0,<3.0.0)", "torch (>=2.0.0,<2.1.0) ; python_version <= \"3.11\"", "torch (>=2.2.0) ; python_version > \"3.11\"", "tqdm (>=4.23.0)", "urllib3 (>=1.21.1,<1.27)", "uvicorn[standard] (>=0.16.0)", "werkzeug (>=2.0.0,<4.0.0)", "werkzeug (>=2.0.0,<4.0.0)", "xgboost"]
 tokenization = ["sentencepiece (>=0.2.0)"]
 vizier = ["google-vizier (>=0.1.6)"]
 xai = ["tensorflow (>=2.3.0,<3.0.0)"]
@@ -4966,14 +4966,14 @@ types-tqdm = "*"
 
 [[package]]
 name = "litellm"
-version = "1.72.2"
+version = "1.72.4"
 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-1.72.2-py3-none-any.whl", hash = "sha256:51e70f5cd98748a603d725ef29ede0ecad3d55e1a89cbbcec8d12d6fff55bff4"},
-    {file = "litellm-1.72.2.tar.gz", hash = "sha256:b50c7f7a0df67117889479264a12b0dea9c566a02173d4c3159540a13760d38b"},
+    {file = "litellm-1.72.4-py3-none-any.whl", hash = "sha256:f98ca994420ed649c466d423655a6e0f2aeecab4564ed372b3378a949e491dc2"},
+    {file = "litellm-1.72.4.tar.gz", hash = "sha256:8855de30f78bcb1f37af244519b37a37faaaf579401b1414400b5b5e5b616d57"},
 ]
 
 [package.dependencies]
@@ -4990,6 +4990,7 @@ tiktoken = ">=0.7.0"
 tokenizers = "*"
 
 [package.extras]
+caching = ["diskcache (>=5.6.1,<6.0.0)"]
 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-enterprise (==0.1.7)", "litellm-proxy-extras (==0.2.3)", "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)", "rich (==13.7.1)", "rq", "uvicorn (>=0.29.0,<0.30.0)", "uvloop (>=0.21.0,<0.22.0) ; sys_platform != \"win32\"", "websockets (>=13.1.0,<14.0.0)"]
 utils = ["numpydoc"]
@@ -5421,7 +5422,7 @@ version = "0.61.0"
 description = "A module for monitoring memory usage of a python program"
 optional = false
 python-versions = ">=3.5"
-groups = ["runtime"]
+groups = ["main", "runtime"]
 files = [
     {file = "memory_profiler-0.61.0-py3-none-any.whl", hash = "sha256:400348e61031e3942ad4d4109d18753b2fb08c2f6fb8290671c5513a34182d84"},
     {file = "memory_profiler-0.61.0.tar.gz", hash = "sha256:4e5b73d7864a1d1292fb76a03e82a3e78ef934d06828a698d9dada76da2067b0"},
@@ -5463,14 +5464,14 @@ files = [
 
 [[package]]
 name = "modal"
-version = "0.77.0"
+version = "1.0.3"
 description = "Python client library for Modal"
 optional = false
 python-versions = ">=3.9"
 groups = ["main", "evaluation"]
 files = [
-    {file = "modal-0.77.0-py3-none-any.whl", hash = "sha256:f646d47e9950b929a03918124c4b12663fdc146287af3c0bd96de3ce23776399"},
-    {file = "modal-0.77.0.tar.gz", hash = "sha256:0a3c2b438a5d26c4b2a1100a7cecdd47e09f715e2a6e0de2a50aad235ddc92c3"},
+    {file = "modal-1.0.3-py3-none-any.whl", hash = "sha256:16cc4f98f755cfc0d0c84b069a0239eb4a9a634e105d38bfa0666301e918544d"},
+    {file = "modal-1.0.3.tar.gz", hash = "sha256:7f27553c93529f5ac27f3d2ab2f7c0c2c0053314a35984ad25ebf8ede193ad14"},
 ]
 
 [package.dependencies]
@@ -5480,7 +5481,7 @@ click = ">=8.1.0,<8.2.0"
 grpclib = "0.4.7"
 protobuf = ">=3.19,<4.24.0 || >4.24.0,<7.0"
 rich = ">=12.0.0"
-synchronicity = ">=0.9.12,<0.10.0"
+synchronicity = ">=0.9.13,<0.10.0"
 toml = "*"
 typer = ">=0.9"
 types-certifi = "*"
@@ -6031,67 +6032,63 @@ test = ["pytest", "pytest-console-scripts", "pytest-jupyter", "pytest-tornasync"
 
 [[package]]
 name = "numpy"
-version = "2.2.6"
+version = "2.3.0"
 description = "Fundamental package for array computing in Python"
 optional = false
-python-versions = ">=3.10"
+python-versions = ">=3.11"
 groups = ["main", "evaluation", "test"]
 files = [
-    {file = "numpy-2.2.6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:b412caa66f72040e6d268491a59f2c43bf03eb6c96dd8f0307829feb7fa2b6fb"},
-    {file = "numpy-2.2.6-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8e41fd67c52b86603a91c1a505ebaef50b3314de0213461c7a6e99c9a3beff90"},
-    {file = "numpy-2.2.6-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:37e990a01ae6ec7fe7fa1c26c55ecb672dd98b19c3d0e1d1f326fa13cb38d163"},
-    {file = "numpy-2.2.6-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:5a6429d4be8ca66d889b7cf70f536a397dc45ba6faeb5f8c5427935d9592e9cf"},
-    {file = "numpy-2.2.6-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:efd28d4e9cd7d7a8d39074a4d44c63eda73401580c5c76acda2ce969e0a38e83"},
-    {file = "numpy-2.2.6-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fc7b73d02efb0e18c000e9ad8b83480dfcd5dfd11065997ed4c6747470ae8915"},
-    {file = "numpy-2.2.6-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:74d4531beb257d2c3f4b261bfb0fc09e0f9ebb8842d82a7b4209415896adc680"},
-    {file = "numpy-2.2.6-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:8fc377d995680230e83241d8a96def29f204b5782f371c532579b4f20607a289"},
-    {file = "numpy-2.2.6-cp310-cp310-win32.whl", hash = "sha256:b093dd74e50a8cba3e873868d9e93a85b78e0daf2e98c6797566ad8044e8363d"},
-    {file = "numpy-2.2.6-cp310-cp310-win_amd64.whl", hash = "sha256:f0fd6321b839904e15c46e0d257fdd101dd7f530fe03fd6359c1ea63738703f3"},
-    {file = "numpy-2.2.6-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f9f1adb22318e121c5c69a09142811a201ef17ab257a1e66ca3025065b7f53ae"},
-    {file = "numpy-2.2.6-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:c820a93b0255bc360f53eca31a0e676fd1101f673dda8da93454a12e23fc5f7a"},
-    {file = "numpy-2.2.6-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:3d70692235e759f260c3d837193090014aebdf026dfd167834bcba43e30c2a42"},
-    {file = "numpy-2.2.6-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:481b49095335f8eed42e39e8041327c05b0f6f4780488f61286ed3c01368d491"},
-    {file = "numpy-2.2.6-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b64d8d4d17135e00c8e346e0a738deb17e754230d7e0810ac5012750bbd85a5a"},
-    {file = "numpy-2.2.6-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba10f8411898fc418a521833e014a77d3ca01c15b0c6cdcce6a0d2897e6dbbdf"},
-    {file = "numpy-2.2.6-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:bd48227a919f1bafbdda0583705e547892342c26fb127219d60a5c36882609d1"},
-    {file = "numpy-2.2.6-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:9551a499bf125c1d4f9e250377c1ee2eddd02e01eac6644c080162c0c51778ab"},
-    {file = "numpy-2.2.6-cp311-cp311-win32.whl", hash = "sha256:0678000bb9ac1475cd454c6b8c799206af8107e310843532b04d49649c717a47"},
-    {file = "numpy-2.2.6-cp311-cp311-win_amd64.whl", hash = "sha256:e8213002e427c69c45a52bbd94163084025f533a55a59d6f9c5b820774ef3303"},
-    {file = "numpy-2.2.6-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:41c5a21f4a04fa86436124d388f6ed60a9343a6f767fced1a8a71c3fbca038ff"},
-    {file = "numpy-2.2.6-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:de749064336d37e340f640b05f24e9e3dd678c57318c7289d222a8a2f543e90c"},
-    {file = "numpy-2.2.6-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:894b3a42502226a1cac872f840030665f33326fc3dac8e57c607905773cdcde3"},
-    {file = "numpy-2.2.6-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:71594f7c51a18e728451bb50cc60a3ce4e6538822731b2933209a1f3614e9282"},
-    {file = "numpy-2.2.6-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f2618db89be1b4e05f7a1a847a9c1c0abd63e63a1607d892dd54668dd92faf87"},
-    {file = "numpy-2.2.6-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fd83c01228a688733f1ded5201c678f0c53ecc1006ffbc404db9f7a899ac6249"},
-    {file = "numpy-2.2.6-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:37c0ca431f82cd5fa716eca9506aefcabc247fb27ba69c5062a6d3ade8cf8f49"},
-    {file = "numpy-2.2.6-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:fe27749d33bb772c80dcd84ae7e8df2adc920ae8297400dabec45f0dedb3f6de"},
-    {file = "numpy-2.2.6-cp312-cp312-win32.whl", hash = "sha256:4eeaae00d789f66c7a25ac5f34b71a7035bb474e679f410e5e1a94deb24cf2d4"},
-    {file = "numpy-2.2.6-cp312-cp312-win_amd64.whl", hash = "sha256:c1f9540be57940698ed329904db803cf7a402f3fc200bfe599334c9bd84a40b2"},
-    {file = "numpy-2.2.6-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0811bb762109d9708cca4d0b13c4f67146e3c3b7cf8d34018c722adb2d957c84"},
-    {file = "numpy-2.2.6-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:287cc3162b6f01463ccd86be154f284d0893d2b3ed7292439ea97eafa8170e0b"},
-    {file = "numpy-2.2.6-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:f1372f041402e37e5e633e586f62aa53de2eac8d98cbfb822806ce4bbefcb74d"},
-    {file = "numpy-2.2.6-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:55a4d33fa519660d69614a9fad433be87e5252f4b03850642f88993f7b2ca566"},
-    {file = "numpy-2.2.6-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f92729c95468a2f4f15e9bb94c432a9229d0d50de67304399627a943201baa2f"},
-    {file = "numpy-2.2.6-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1bc23a79bfabc5d056d106f9befb8d50c31ced2fbc70eedb8155aec74a45798f"},
-    {file = "numpy-2.2.6-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:e3143e4451880bed956e706a3220b4e5cf6172ef05fcc397f6f36a550b1dd868"},
-    {file = "numpy-2.2.6-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:b4f13750ce79751586ae2eb824ba7e1e8dba64784086c98cdbbcc6a42112ce0d"},
-    {file = "numpy-2.2.6-cp313-cp313-win32.whl", hash = "sha256:5beb72339d9d4fa36522fc63802f469b13cdbe4fdab4a288f0c441b74272ebfd"},
-    {file = "numpy-2.2.6-cp313-cp313-win_amd64.whl", hash = "sha256:b0544343a702fa80c95ad5d3d608ea3599dd54d4632df855e4c8d24eb6ecfa1c"},
-    {file = "numpy-2.2.6-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:0bca768cd85ae743b2affdc762d617eddf3bcf8724435498a1e80132d04879e6"},
-    {file = "numpy-2.2.6-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:fc0c5673685c508a142ca65209b4e79ed6740a4ed6b2267dbba90f34b0b3cfda"},
-    {file = "numpy-2.2.6-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:5bd4fc3ac8926b3819797a7c0e2631eb889b4118a9898c84f585a54d475b7e40"},
-    {file = "numpy-2.2.6-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:fee4236c876c4e8369388054d02d0e9bb84821feb1a64dd59e137e6511a551f8"},
-    {file = "numpy-2.2.6-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e1dda9c7e08dc141e0247a5b8f49cf05984955246a327d4c48bda16821947b2f"},
-    {file = "numpy-2.2.6-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f447e6acb680fd307f40d3da4852208af94afdfab89cf850986c3ca00562f4fa"},
-    {file = "numpy-2.2.6-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:389d771b1623ec92636b0786bc4ae56abafad4a4c513d36a55dce14bd9ce8571"},
-    {file = "numpy-2.2.6-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:8e9ace4a37db23421249ed236fdcdd457d671e25146786dfc96835cd951aa7c1"},
-    {file = "numpy-2.2.6-cp313-cp313t-win32.whl", hash = "sha256:038613e9fb8c72b0a41f025a7e4c3f0b7a1b5d768ece4796b674c8f3fe13efff"},
-    {file = "numpy-2.2.6-cp313-cp313t-win_amd64.whl", hash = "sha256:6031dd6dfecc0cf9f668681a37648373bddd6421fff6c66ec1624eed0180ee06"},
-    {file = "numpy-2.2.6-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:0b605b275d7bd0c640cad4e5d30fa701a8d59302e127e5f79138ad62762c3e3d"},
-    {file = "numpy-2.2.6-pp310-pypy310_pp73-macosx_14_0_x86_64.whl", hash = "sha256:7befc596a7dc9da8a337f79802ee8adb30a552a94f792b9c9d18c840055907db"},
-    {file = "numpy-2.2.6-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ce47521a4754c8f4593837384bd3424880629f718d87c5d44f8ed763edd63543"},
-    {file = "numpy-2.2.6-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:d042d24c90c41b54fd506da306759e06e568864df8ec17ccc17e9e884634fd00"},
-    {file = "numpy-2.2.6.tar.gz", hash = "sha256:e29554e2bef54a90aa5cc07da6ce955accb83f21ab5de01a62c8478897b264fd"},
+    {file = "numpy-2.3.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c3c9fdde0fa18afa1099d6257eb82890ea4f3102847e692193b54e00312a9ae9"},
+    {file = "numpy-2.3.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:46d16f72c2192da7b83984aa5455baee640e33a9f1e61e656f29adf55e406c2b"},
+    {file = "numpy-2.3.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:a0be278be9307c4ab06b788f2a077f05e180aea817b3e41cebbd5aaf7bd85ed3"},
+    {file = "numpy-2.3.0-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:99224862d1412d2562248d4710126355d3a8db7672170a39d6909ac47687a8a4"},
+    {file = "numpy-2.3.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:2393a914db64b0ead0ab80c962e42d09d5f385802006a6c87835acb1f58adb96"},
+    {file = "numpy-2.3.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:7729c8008d55e80784bd113787ce876ca117185c579c0d626f59b87d433ea779"},
+    {file = "numpy-2.3.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:06d4fb37a8d383b769281714897420c5cc3545c79dc427df57fc9b852ee0bf58"},
+    {file = "numpy-2.3.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:c39ec392b5db5088259c68250e342612db82dc80ce044cf16496cf14cf6bc6f8"},
+    {file = "numpy-2.3.0-cp311-cp311-win32.whl", hash = "sha256:ee9d3ee70d62827bc91f3ea5eee33153212c41f639918550ac0475e3588da59f"},
+    {file = "numpy-2.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:43c55b6a860b0eb44d42341438b03513cf3879cb3617afb749ad49307e164edd"},
+    {file = "numpy-2.3.0-cp311-cp311-win_arm64.whl", hash = "sha256:2e6a1409eee0cb0316cb64640a49a49ca44deb1a537e6b1121dc7c458a1299a8"},
+    {file = "numpy-2.3.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:389b85335838155a9076e9ad7f8fdba0827496ec2d2dc32ce69ce7898bde03ba"},
+    {file = "numpy-2.3.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:9498f60cd6bb8238d8eaf468a3d5bb031d34cd12556af53510f05fcf581c1b7e"},
+    {file = "numpy-2.3.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:622a65d40d8eb427d8e722fd410ac3ad4958002f109230bc714fa551044ebae2"},
+    {file = "numpy-2.3.0-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:b9446d9d8505aadadb686d51d838f2b6688c9e85636a0c3abaeb55ed54756459"},
+    {file = "numpy-2.3.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:50080245365d75137a2bf46151e975de63146ae6d79f7e6bd5c0e85c9931d06a"},
+    {file = "numpy-2.3.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:c24bb4113c66936eeaa0dc1e47c74770453d34f46ee07ae4efd853a2ed1ad10a"},
+    {file = "numpy-2.3.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:4d8d294287fdf685281e671886c6dcdf0291a7c19db3e5cb4178d07ccf6ecc67"},
+    {file = "numpy-2.3.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:6295f81f093b7f5769d1728a6bd8bf7466de2adfa771ede944ce6711382b89dc"},
+    {file = "numpy-2.3.0-cp312-cp312-win32.whl", hash = "sha256:e6648078bdd974ef5d15cecc31b0c410e2e24178a6e10bf511e0557eed0f2570"},
+    {file = "numpy-2.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:0898c67a58cdaaf29994bc0e2c65230fd4de0ac40afaf1584ed0b02cd74c6fdd"},
+    {file = "numpy-2.3.0-cp312-cp312-win_arm64.whl", hash = "sha256:bd8df082b6c4695753ad6193018c05aac465d634834dca47a3ae06d4bb22d9ea"},
+    {file = "numpy-2.3.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:5754ab5595bfa2c2387d241296e0381c21f44a4b90a776c3c1d39eede13a746a"},
+    {file = "numpy-2.3.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:d11fa02f77752d8099573d64e5fe33de3229b6632036ec08f7080f46b6649959"},
+    {file = "numpy-2.3.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:aba48d17e87688a765ab1cd557882052f238e2f36545dfa8e29e6a91aef77afe"},
+    {file = "numpy-2.3.0-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:4dc58865623023b63b10d52f18abaac3729346a7a46a778381e0e3af4b7f3beb"},
+    {file = "numpy-2.3.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:df470d376f54e052c76517393fa443758fefcdd634645bc9c1f84eafc67087f0"},
+    {file = "numpy-2.3.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:87717eb24d4a8a64683b7a4e91ace04e2f5c7c77872f823f02a94feee186168f"},
+    {file = "numpy-2.3.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:d8fa264d56882b59dcb5ea4d6ab6f31d0c58a57b41aec605848b6eb2ef4a43e8"},
+    {file = "numpy-2.3.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:e651756066a0eaf900916497e20e02fe1ae544187cb0fe88de981671ee7f6270"},
+    {file = "numpy-2.3.0-cp313-cp313-win32.whl", hash = "sha256:e43c3cce3b6ae5f94696669ff2a6eafd9a6b9332008bafa4117af70f4b88be6f"},
+    {file = "numpy-2.3.0-cp313-cp313-win_amd64.whl", hash = "sha256:81ae0bf2564cf475f94be4a27ef7bcf8af0c3e28da46770fc904da9abd5279b5"},
+    {file = "numpy-2.3.0-cp313-cp313-win_arm64.whl", hash = "sha256:c8738baa52505fa6e82778580b23f945e3578412554d937093eac9205e845e6e"},
+    {file = "numpy-2.3.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:39b27d8b38942a647f048b675f134dd5a567f95bfff481f9109ec308515c51d8"},
+    {file = "numpy-2.3.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:0eba4a1ea88f9a6f30f56fdafdeb8da3774349eacddab9581a21234b8535d3d3"},
+    {file = "numpy-2.3.0-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:b0f1f11d0a1da54927436505a5a7670b154eac27f5672afc389661013dfe3d4f"},
+    {file = "numpy-2.3.0-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:690d0a5b60a47e1f9dcec7b77750a4854c0d690e9058b7bef3106e3ae9117808"},
+    {file = "numpy-2.3.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:8b51ead2b258284458e570942137155978583e407babc22e3d0ed7af33ce06f8"},
+    {file = "numpy-2.3.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:aaf81c7b82c73bd9b45e79cfb9476cb9c29e937494bfe9092c26aece812818ad"},
+    {file = "numpy-2.3.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:f420033a20b4f6a2a11f585f93c843ac40686a7c3fa514060a97d9de93e5e72b"},
+    {file = "numpy-2.3.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:d344ca32ab482bcf8735d8f95091ad081f97120546f3d250240868430ce52555"},
+    {file = "numpy-2.3.0-cp313-cp313t-win32.whl", hash = "sha256:48a2e8eaf76364c32a1feaa60d6925eaf32ed7a040183b807e02674305beef61"},
+    {file = "numpy-2.3.0-cp313-cp313t-win_amd64.whl", hash = "sha256:ba17f93a94e503551f154de210e4d50c5e3ee20f7e7a1b5f6ce3f22d419b93bb"},
+    {file = "numpy-2.3.0-cp313-cp313t-win_arm64.whl", hash = "sha256:f14e016d9409680959691c109be98c436c6249eaf7f118b424679793607b5944"},
+    {file = "numpy-2.3.0-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:80b46117c7359de8167cc00a2c7d823bdd505e8c7727ae0871025a86d668283b"},
+    {file = "numpy-2.3.0-pp311-pypy311_pp73-macosx_14_0_arm64.whl", hash = "sha256:5814a0f43e70c061f47abd5857d120179609ddc32a613138cbb6c4e9e2dbdda5"},
+    {file = "numpy-2.3.0-pp311-pypy311_pp73-macosx_14_0_x86_64.whl", hash = "sha256:ef6c1e88fd6b81ac6d215ed71dc8cd027e54d4bf1d2682d362449097156267a2"},
+    {file = "numpy-2.3.0-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:33a5a12a45bb82d9997e2c0b12adae97507ad7c347546190a18ff14c28bbca12"},
+    {file = "numpy-2.3.0-pp311-pypy311_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:54dfc8681c1906d239e95ab1508d0a533c4a9505e52ee2d71a5472b04437ef97"},
+    {file = "numpy-2.3.0-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:e017a8a251ff4d18d71f139e28bdc7c31edba7a507f72b1414ed902cbe48c74d"},
+    {file = "numpy-2.3.0.tar.gz", hash = "sha256:581f87f9e9e9db2cba2141400e160e9dd644ee248788d6f90636eeb8fd9260a6"},
 ]
 
 [[package]]
@@ -6335,14 +6332,14 @@ signedtoken = ["cryptography (>=3.0.0)", "pyjwt (>=2.0.0,<3)"]
 
 [[package]]
 name = "openai"
-version = "1.85.0"
+version = "1.86.0"
 description = "The official Python library for the openai API"
 optional = false
 python-versions = ">=3.8"
 groups = ["main", "evaluation", "test"]
 files = [
-    {file = "openai-1.85.0-py3-none-any.whl", hash = "sha256:7dc3e839cb8bb8747979a90c63ad4cb25a8e0cbec17b53eec009532c9965cecf"},
-    {file = "openai-1.85.0.tar.gz", hash = "sha256:6ba76e4ebc5725f71f2f6126c7cb5169ca8de60dd5aa61f350f9448ad162c913"},
+    {file = "openai-1.86.0-py3-none-any.whl", hash = "sha256:c8889c39410621fe955c230cc4c21bfe36ec887f4e60a957de05f507d7e1f349"},
+    {file = "openai-1.86.0.tar.gz", hash = "sha256:c64d5b788359a8fdf69bd605ae804ce41c1ce2e78b8dd93e2542e0ee267f1e4b"},
 ]
 
 [package.dependencies]
@@ -6438,14 +6435,14 @@ et-xmlfile = "*"
 
 [[package]]
 name = "opentelemetry-api"
-version = "1.34.0"
+version = "1.34.1"
 description = "OpenTelemetry Python API"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "opentelemetry_api-1.34.0-py3-none-any.whl", hash = "sha256:390b81984affe4453180820ca518de55e3be051111e70cc241bb3b0071ca3a2c"},
-    {file = "opentelemetry_api-1.34.0.tar.gz", hash = "sha256:48d167589134799093005b7f7f347c69cc67859c693b17787f334fbe8871279f"},
+    {file = "opentelemetry_api-1.34.1-py3-none-any.whl", hash = "sha256:b7df4cb0830d5a6c29ad0c0691dbae874d8daefa934b8b1d642de48323d32a8c"},
+    {file = "opentelemetry_api-1.34.1.tar.gz", hash = "sha256:64f0bd06d42824843731d05beea88d4d4b6ae59f9fe347ff7dfa2cc14233bbb3"},
 ]
 
 [package.dependencies]
@@ -6454,29 +6451,29 @@ typing-extensions = ">=4.5.0"
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-common"
-version = "1.34.0"
+version = "1.34.1"
 description = "OpenTelemetry Protobuf encoding"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "opentelemetry_exporter_otlp_proto_common-1.34.0-py3-none-any.whl", hash = "sha256:a5ab7a9b7c3c7ba957c8ddcb08c0c93b1d732e066f544682a250ecf4d7a9ceef"},
-    {file = "opentelemetry_exporter_otlp_proto_common-1.34.0.tar.gz", hash = "sha256:5916d9ceda8c733adbec5e9cecf654fbf359e9f619ff43214277076fba888557"},
+    {file = "opentelemetry_exporter_otlp_proto_common-1.34.1-py3-none-any.whl", hash = "sha256:8e2019284bf24d3deebbb6c59c71e6eef3307cd88eff8c633e061abba33f7e87"},
+    {file = "opentelemetry_exporter_otlp_proto_common-1.34.1.tar.gz", hash = "sha256:b59a20a927facd5eac06edaf87a07e49f9e4a13db487b7d8a52b37cb87710f8b"},
 ]
 
 [package.dependencies]
-opentelemetry-proto = "1.34.0"
+opentelemetry-proto = "1.34.1"
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-grpc"
-version = "1.34.0"
+version = "1.34.1"
 description = "OpenTelemetry Collector Protobuf over gRPC Exporter"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "opentelemetry_exporter_otlp_proto_grpc-1.34.0-py3-none-any.whl", hash = "sha256:31c41017af85833242d49beb07bde7341b0a145f0b898ee383f3e3019037afb1"},
-    {file = "opentelemetry_exporter_otlp_proto_grpc-1.34.0.tar.gz", hash = "sha256:a634425340f506d5ebf641c92d88eb873754d4c5259b5b816afb234c6f87b37d"},
+    {file = "opentelemetry_exporter_otlp_proto_grpc-1.34.1-py3-none-any.whl", hash = "sha256:04bb8b732b02295be79f8a86a4ad28fae3d4ddb07307a98c7aa6f331de18cca6"},
+    {file = "opentelemetry_exporter_otlp_proto_grpc-1.34.1.tar.gz", hash = "sha256:7c841b90caa3aafcfc4fee58487a6c71743c34c6dc1787089d8b0578bbd794dd"},
 ]
 
 [package.dependencies]
@@ -6486,21 +6483,21 @@ grpcio = [
     {version = ">=1.63.2,<2.0.0", markers = "python_version < \"3.13\""},
 ]
 opentelemetry-api = ">=1.15,<2.0"
-opentelemetry-exporter-otlp-proto-common = "1.34.0"
-opentelemetry-proto = "1.34.0"
-opentelemetry-sdk = ">=1.34.0,<1.35.0"
+opentelemetry-exporter-otlp-proto-common = "1.34.1"
+opentelemetry-proto = "1.34.1"
+opentelemetry-sdk = ">=1.34.1,<1.35.0"
 typing-extensions = ">=4.5.0"
 
 [[package]]
 name = "opentelemetry-proto"
-version = "1.34.0"
+version = "1.34.1"
 description = "OpenTelemetry Python Proto"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "opentelemetry_proto-1.34.0-py3-none-any.whl", hash = "sha256:ffb1f1b27552fda5a1cd581e34243cc0b6f134fb14c1c2a33cc3b4b208c9bf97"},
-    {file = "opentelemetry_proto-1.34.0.tar.gz", hash = "sha256:73e40509b692630a47192888424f7e0b8fb19d9ecf2f04e6f708170cd3346dfe"},
+    {file = "opentelemetry_proto-1.34.1-py3-none-any.whl", hash = "sha256:eb4bb5ac27f2562df2d6857fc557b3a481b5e298bc04f94cc68041f00cebcbd2"},
+    {file = "opentelemetry_proto-1.34.1.tar.gz", hash = "sha256:16286214e405c211fc774187f3e4bbb1351290b8dfb88e8948af209ce85b719e"},
 ]
 
 [package.dependencies]
@@ -6508,35 +6505,35 @@ protobuf = ">=5.0,<6.0"
 
 [[package]]
 name = "opentelemetry-sdk"
-version = "1.34.0"
+version = "1.34.1"
 description = "OpenTelemetry Python SDK"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "opentelemetry_sdk-1.34.0-py3-none-any.whl", hash = "sha256:7850bcd5b5c95f9aae48603d6592bdad5c7bdef50c03e06393f8f457d891fe32"},
-    {file = "opentelemetry_sdk-1.34.0.tar.gz", hash = "sha256:719559622afcd515c2aec462ccb749ba2e70075a01df45837623643814d33716"},
+    {file = "opentelemetry_sdk-1.34.1-py3-none-any.whl", hash = "sha256:308effad4059562f1d92163c61c8141df649da24ce361827812c40abb2a1e96e"},
+    {file = "opentelemetry_sdk-1.34.1.tar.gz", hash = "sha256:8091db0d763fcd6098d4781bbc80ff0971f94e260739aa6afe6fd379cdf3aa4d"},
 ]
 
 [package.dependencies]
-opentelemetry-api = "1.34.0"
-opentelemetry-semantic-conventions = "0.55b0"
+opentelemetry-api = "1.34.1"
+opentelemetry-semantic-conventions = "0.55b1"
 typing-extensions = ">=4.5.0"
 
 [[package]]
 name = "opentelemetry-semantic-conventions"
-version = "0.55b0"
+version = "0.55b1"
 description = "OpenTelemetry Semantic Conventions"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "opentelemetry_semantic_conventions-0.55b0-py3-none-any.whl", hash = "sha256:63bb15b67377700e51c422d0d24092ca6ce9f3a4cb6f032375aa8af1fc2aab65"},
-    {file = "opentelemetry_semantic_conventions-0.55b0.tar.gz", hash = "sha256:933d2e20c2dbc0f9b2f4f52138282875b4b14c66c491f5273bcdef1781368e9c"},
+    {file = "opentelemetry_semantic_conventions-0.55b1-py3-none-any.whl", hash = "sha256:5da81dfdf7d52e3d37f8fe88d5e771e191de924cfff5f550ab0b8f7b2409baed"},
+    {file = "opentelemetry_semantic_conventions-0.55b1.tar.gz", hash = "sha256:ef95b1f009159c28d7a7849f5cbc71c4c34c845bb514d66adfdf1b3fff3598b3"},
 ]
 
 [package.dependencies]
-opentelemetry-api = "1.34.0"
+opentelemetry-api = "1.34.1"
 typing-extensions = ">=4.5.0"
 
 [[package]]
@@ -7858,19 +7855,20 @@ testing = ["coverage (>=6.2)", "hypothesis (>=5.7.1)"]
 
 [[package]]
 name = "pytest-cov"
-version = "6.1.1"
+version = "6.2.1"
 description = "Pytest plugin for measuring coverage."
 optional = false
 python-versions = ">=3.9"
 groups = ["test"]
 files = [
-    {file = "pytest_cov-6.1.1-py3-none-any.whl", hash = "sha256:bddf29ed2d0ab6f4df17b4c55b0a657287db8684af9c42ea546b21b1041b3dde"},
-    {file = "pytest_cov-6.1.1.tar.gz", hash = "sha256:46935f7aaefba760e716c2ebfbe1c216240b9592966e7da99ea8292d4d3e2a0a"},
+    {file = "pytest_cov-6.2.1-py3-none-any.whl", hash = "sha256:f5bc4c23f42f1cdd23c70b1dab1bbaef4fc505ba950d53e0081d0730dd7e86d5"},
+    {file = "pytest_cov-6.2.1.tar.gz", hash = "sha256:25cc6cc0a5358204b8108ecedc51a9b57b34cc6b8c967cc2c01a4e00d8a67da2"},
 ]
 
 [package.dependencies]
 coverage = {version = ">=7.5", extras = ["toml"]}
-pytest = ">=4.6"
+pluggy = ">=1.2"
+pytest = ">=6.2.5"
 
 [package.extras]
 testing = ["fields", "hunter", "process-tests", "pytest-xdist", "virtualenv"]
@@ -8949,14 +8947,14 @@ files = [
 
 [[package]]
 name = "runloop-api-client"
-version = "0.39.0"
+version = "0.42.0"
 description = "The official Python library for the runloop API"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "runloop_api_client-0.39.0-py3-none-any.whl", hash = "sha256:afdeba4c9a66fc282885f0c1a1979587baa1710612892d605e9121a8172dc18f"},
-    {file = "runloop_api_client-0.39.0.tar.gz", hash = "sha256:dfad1dd189d281f86ac858ef13daf01e458f877b9e5d0e3cafeb8c04507cc71a"},
+    {file = "runloop_api_client-0.42.0-py3-none-any.whl", hash = "sha256:3e66f00a078311d716df6bbd49318d43ccce013f62f63b80ef3b7d766d3d50fd"},
+    {file = "runloop_api_client-0.42.0.tar.gz", hash = "sha256:cc6f4137e39b5fa1f114d742ef33e32cc83c7bc4f16193c897d44e97bcfdc6ca"},
 ]
 
 [package.dependencies]
@@ -9683,14 +9681,14 @@ dev = ["hypothesis (>=6.70.0)", "pytest (>=7.1.0)"]
 
 [[package]]
 name = "synchronicity"
-version = "0.9.12"
+version = "0.9.15"
 description = "Export blocking and async library versions from a single async implementation"
 optional = false
 python-versions = ">=3.8"
 groups = ["main", "evaluation"]
 files = [
-    {file = "synchronicity-0.9.12-py3-none-any.whl", hash = "sha256:b006f57bd216d55e578316096a11b6dc16016d6b48e2766bcffabe40c88f9793"},
-    {file = "synchronicity-0.9.12.tar.gz", hash = "sha256:977f3ed8f6e35de4d1a3f0aeee4937143ba8d913f531d33e8df7c539b2792fb8"},
+    {file = "synchronicity-0.9.15-py3-none-any.whl", hash = "sha256:6e3008f54795d73d59fbd133c812734e7c83f4a6f44257cc2a3251237ee8921b"},
+    {file = "synchronicity-0.9.15.tar.gz", hash = "sha256:9451d0caef3509e9f980ba62885a3b8ba7ab247845618e9d9c9c8d11da7ee84b"},
 ]
 
 [package.dependencies]
@@ -11666,4 +11664,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.12,<3.14"
-content-hash = "beb348a8a07835531e5dba2c8807fdf68669fe239c630d0420dc204b3b2648ed"
+content-hash = "0b8da1a7da2d598f9ca4a8933245c99495f7a34bb26e1221eebd7ba2fa1d6ddc"

pyproject.toml

@@ -52,8 +52,8 @@ whatthepatch = "^1.0.6"
 protobuf = "^5.0.0,<6.0.0"                         # Updated to support newer opentelemetry
 opentelemetry-api = "^1.33.1"
 opentelemetry-exporter-otlp-proto-grpc = "^1.33.1"
-modal = ">=0.66.26,<0.78.0"
-runloop-api-client = "0.39.0"
+modal = ">=0.66.26,<1.1.0"
+runloop-api-client = "0.42.0"
 libtmux = ">=0.37,<0.40"
 pygithub = "^2.5.0"
 joblib = "*"
@@ -71,6 +71,11 @@ python-frontmatter = "^1.1.0"
 # TODO: Should these go into the runtime group?
 ipywidgets = "^8.1.5"
 qtconsole = "^5.6.1"
+memory-profiler = "^0.61.0"
+playwright = "^1.51.0"
+pydantic = "^2.11.3"
+httpx = "^0.28.1"
+httpx-sse = "^0.4.0"
 PyPDF2 = "*"
 python-pptx = "*"
 pylatexenc = "*"

tests/unit/test_a2a_client.py

@@ -0,0 +1,471 @@
+import json
+from unittest.mock import AsyncMock, MagicMock, Mock, patch
+
+import pytest
+from httpx import HTTPStatusError, Request, Response
+from httpx_sse import ServerSentEvent
+
+from openhands.runtime.plugins.agent_skills.a2a_client.a2a_client import (
+    completeTask,
+    send_task_A2A,
+)
+from openhands.runtime.plugins.agent_skills.a2a_client.common.client import (
+    A2ACardResolver,
+    A2AClient,
+)
+from openhands.runtime.plugins.agent_skills.a2a_client.common.types import (
+    A2AClientHTTPError,
+    A2AClientJSONError,
+    AgentCard,
+    CancelTaskRequest,
+    CancelTaskResponse,
+    GetTaskPushNotificationRequest,
+    GetTaskPushNotificationResponse,
+    JSONRPCRequest,
+    SendTaskRequest,
+    SendTaskResponse,
+    SetTaskPushNotificationRequest,
+    SetTaskPushNotificationResponse,
+    TaskIdParams,
+    TaskPushNotificationConfig,
+    TaskSendParams,
+    TaskState,
+    TaskStatus,
+    TaskStatusUpdateEvent,
+)
+
+# Tests for openhands/runtime/plugins/agent_skills/a2a_client/a2a_client.py
+
+
+@pytest.mark.asyncio
+@patch('openhands.runtime.plugins.agent_skills.a2a_client.a2a_client.A2ACardResolver')
+@patch('openhands.runtime.plugins.agent_skills.a2a_client.a2a_client.A2AClient')
+async def test_send_task_A2A(mock_a2a_client, mock_card_resolver):
+    # Mock: card resolver, agent card, A2A Client and completeTask
+    mock_card = Mock()
+    mock_card.capabilities.streaming = False
+    mock_card.model_dump_json.return_value = '{}'
+    mock_card_resolver.return_value.get_agent_card.return_value = mock_card
+
+    mock_client = Mock()
+    mock_a2a_client.return_value = mock_client
+
+    with patch(
+        'openhands.runtime.plugins.agent_skills.a2a_client.a2a_client.completeTask',
+        new=AsyncMock(),
+    ) as mock_complete_task:
+        await send_task_A2A('http://example.com', 'test message')
+
+        mock_card_resolver.assert_called_once_with('http://example.com')
+        mock_card_resolver.return_value.get_agent_card.assert_called_once()
+        mock_a2a_client.assert_called_once_with(agent_card=mock_card)
+
+        mock_complete_task.assert_called_once()
+        _, _, streaming, task_id, session_id = mock_complete_task.call_args[0]
+        assert streaming is False
+        assert len(task_id) > 0
+        assert len(session_id) > 0
+
+
+@pytest.mark.asyncio
+@patch('openhands.runtime.plugins.agent_skills.a2a_client.a2a_client.A2AClient')
+async def test_completeTask_non_streaming(mock_a2a_client):
+    # Mock: A2AClient
+    mock_client = Mock()
+    mock_client.send_task = AsyncMock(
+        return_value=Mock(result=Mock(status=Mock(state=TaskState.COMPLETED.value)))
+    )
+    mock_a2a_client.return_value = mock_client
+
+    result = await completeTask(
+        mock_client, 'test message', False, 'task_id', 'session_id'
+    )
+
+    mock_client.send_task.assert_called_once()
+    payload = mock_client.send_task.call_args[0][0]
+    assert payload['id'] == 'task_id'
+    assert payload['sessionId'] == 'session_id'
+    assert payload['message']['role'] == 'user'
+    assert payload['message']['parts'][0]['text'] == 'test message'
+    assert result is True
+
+
+@pytest.mark.asyncio
+@patch('openhands.runtime.plugins.agent_skills.a2a_client.a2a_client.A2AClient')
+async def test_completeTask_streaming(mock_a2a_client):
+    # Mock A2AClient
+    mock_client = Mock()
+    mock_client.send_task_streaming = Mock(return_value=AsyncMock())
+    mock_client.get_task = AsyncMock(
+        return_value=Mock(result=Mock(status=Mock(state=TaskState.COMPLETED.value)))
+    )
+    mock_a2a_client.return_value = mock_client
+
+    result = await completeTask(
+        mock_client, 'test message', True, 'task_id', 'session_id'
+    )
+
+    mock_client.send_task_streaming.assert_called_once()
+    mock_client.get_task.assert_called_once_with({'id': 'task_id'})
+    assert result is True
+
+
+@pytest.mark.asyncio
+@patch('openhands.runtime.plugins.agent_skills.a2a_client.a2a_client.A2AClient')
+async def test_completeTask_input_required(mock_a2a_client):
+    # Mock A2AClient
+    mock_client = Mock()
+    mock_client.send_task = AsyncMock(
+        return_value=Mock(
+            result=Mock(status=Mock(state=TaskState.INPUT_REQUIRED.value))
+        )
+    )
+    mock_a2a_client.return_value = mock_client
+
+    result = await completeTask(
+        mock_client, 'test message', False, 'task_id', 'session_id'
+    )
+
+    assert result is None
+
+
+# Tests for openhands/runtime/plugins/agent_skills/a2a_client/common/client/client.py
+TEST_URL = 'https://example.com'
+
+
+def make_mock_request() -> JSONRPCRequest:
+    return JSONRPCRequest(
+        jsonrpc='2.0',
+        id='1',
+        method='test_method',
+        params={},
+    )
+
+
+@pytest.mark.asyncio
+async def test__send_request_success():
+    mock_request = make_mock_request()
+    mock_response_data = {
+        'jsonrpc': '2.0',
+        'id': '1',
+        'method': 'test_method',
+        'result': {},
+    }
+
+    client = A2AClient(url=TEST_URL)
+
+    mock_response = Mock()
+    mock_response.raise_for_status = Mock()
+    mock_response.json.return_value = mock_response_data
+
+    mock_post = AsyncMock(return_value=mock_response)
+
+    with patch('httpx.AsyncClient.post', mock_post):
+        result = await client._send_request(mock_request)
+
+    assert result == mock_response_data
+    mock_post.assert_awaited_once_with(
+        TEST_URL, json=mock_request.model_dump(), timeout=30
+    )
+
+
+@pytest.mark.asyncio
+async def test__send_request_http_error():
+    mock_request = make_mock_request()
+    client = A2AClient(url=TEST_URL)
+
+    bad_request_response = Response(status_code=400, request=Request('POST', TEST_URL))
+
+    mock_response = Mock()
+    mock_response.raise_for_status.side_effect = HTTPStatusError(
+        message='Bad Request',
+        request=bad_request_response.request,
+        response=bad_request_response,
+    )
+    mock_response.json.return_value = {}
+
+    mock_post = AsyncMock(return_value=mock_response)
+
+    with patch('httpx.AsyncClient.post', mock_post):
+        with pytest.raises(A2AClientHTTPError) as exc_info:
+            await client._send_request(mock_request)
+
+    assert exc_info.value.status_code == 400
+    assert 'Bad Request' in str(exc_info.value)
+
+
+@pytest.mark.asyncio
+async def test__send_request_json_error():
+    mock_request = make_mock_request()
+    client = A2AClient(url=TEST_URL)
+
+    mock_response = Mock()
+    mock_response.raise_for_status = Mock()
+    mock_response.json.side_effect = json.JSONDecodeError(
+        msg='Expecting value', doc='', pos=0
+    )
+
+    mock_post = AsyncMock(return_value=mock_response)
+
+    with patch('httpx.AsyncClient.post', mock_post):
+        with pytest.raises(A2AClientJSONError) as exc_info:
+            await client._send_request(mock_request)
+
+    assert 'Expecting value' in str(exc_info.value)
+
+
+@pytest.mark.asyncio
+async def test_send_task():
+    mock_payload = {
+        'id': 'test-task-id',
+        'sessionId': 'test-session-id',
+        'message': {
+            'role': 'user',
+            'parts': [
+                {
+                    'type': 'text',
+                    'text': 'Hello, world!',
+                }
+            ],
+        },
+    }
+    mock_response_data = {
+        'jsonrpc': '2.0',
+        'id': '1',
+        'result': {
+            'id': 'test-task-id',
+            'sessionId': 'test-session-id',
+            'status': {
+                'state': 'submitted',
+                'timestamp': '2025-01-01T00:00:00Z',
+            },
+        },
+    }
+
+    client = A2AClient(url=TEST_URL)
+
+    with patch.object(
+        client, '_send_request', AsyncMock(return_value=mock_response_data)
+    ) as mock_send:
+        result = await client.send_task(mock_payload)
+
+    assert isinstance(result, SendTaskResponse)
+    assert result == SendTaskResponse(**mock_response_data)
+    mock_send.assert_awaited_once()
+    sent_arg = mock_send.call_args.args[0]
+    assert isinstance(sent_arg, SendTaskRequest)
+    assert sent_arg.params == TaskSendParams(**mock_payload)
+
+
+@pytest.mark.asyncio
+async def test_cancel_task():
+    mock_payload = {'id': 'test-task-id'}
+    mock_response_data = {
+        'jsonrpc': '2.0',
+        'id': '1',
+        'result': {
+            'id': 'test-task-id',
+            'status': {
+                'state': 'canceled',
+                'timestamp': '2025-01-01T00:00:00Z',
+            },
+        },
+    }
+
+    client = A2AClient(url=TEST_URL)
+
+    with patch.object(
+        client, '_send_request', AsyncMock(return_value=mock_response_data)
+    ) as mock_send:
+        result = await client.cancel_task(mock_payload)
+
+    assert isinstance(result, CancelTaskResponse)
+    assert result == CancelTaskResponse(**mock_response_data)
+    mock_send.assert_awaited_once()
+    sent_arg = mock_send.call_args.args[0]
+    assert isinstance(sent_arg, CancelTaskRequest)
+    assert sent_arg.params == TaskIdParams(**mock_payload)
+
+
+@pytest.mark.asyncio
+async def test_set_task_callback():
+    mock_payload = {
+        'id': 'test-task-id',
+        'pushNotificationConfig': {'url': 'https://callback.example.com'},
+    }
+    mock_response_data = {
+        'jsonrpc': '2.0',
+        'id': '1',
+        'result': {
+            'id': 'test-task-id',
+            'pushNotificationConfig': {
+                'url': 'https://callback.example.com',
+            },
+        },
+    }
+
+    client = A2AClient(url=TEST_URL)
+
+    with patch.object(
+        client, '_send_request', AsyncMock(return_value=mock_response_data)
+    ) as mock_send:
+        result = await client.set_task_callback(mock_payload)
+
+    assert isinstance(result, SetTaskPushNotificationResponse)
+    assert result == SetTaskPushNotificationResponse(**mock_response_data)
+    mock_send.assert_awaited_once()
+    sent_arg = mock_send.call_args.args[0]
+    assert isinstance(sent_arg, SetTaskPushNotificationRequest)
+    assert sent_arg.params == TaskPushNotificationConfig(**mock_payload)
+
+
+@pytest.mark.asyncio
+async def test_get_task_callback():
+    mock_payload = {'id': 'test-task-id'}
+    mock_response_data = {
+        'jsonrpc': '2.0',
+        'id': '1',
+        'result': {
+            'id': 'test-task-id',
+            'pushNotificationConfig': {
+                'url': 'https://callback.example.com',
+            },
+        },
+    }
+
+    client = A2AClient(url=TEST_URL)
+
+    with patch.object(
+        client, '_send_request', AsyncMock(return_value=mock_response_data)
+    ) as mock_send:
+        result = await client.get_task_callback(mock_payload)
+
+    assert isinstance(result, GetTaskPushNotificationResponse)
+    assert result == GetTaskPushNotificationResponse(**mock_response_data)
+    mock_send.assert_awaited_once()
+    sent_arg = mock_send.call_args.args[0]
+    assert isinstance(sent_arg, GetTaskPushNotificationRequest)
+    assert sent_arg.params == TaskIdParams(**mock_payload)
+
+
+@pytest.mark.asyncio
+async def test_send_task_streaming():
+    mock_event_source = MagicMock()
+    mock_event_source.iter_sse.return_value = iter(
+        [
+            ServerSentEvent(
+                data=json.dumps(
+                    {
+                        'jsonrpc': '2.0',
+                        'id': '1',
+                        'result': {
+                            'id': 'test-task-id',
+                            'status': {
+                                'state': 'submitted',
+                                'timestamp': '2025-01-01T00:00:00Z',
+                            },
+                        },
+                    }
+                )
+            ),
+            ServerSentEvent(
+                data=json.dumps(
+                    {
+                        'jsonrpc': '2.0',
+                        'id': '1',
+                        'result': {
+                            'id': 'test-task-id',
+                            'status': {
+                                'state': 'working',
+                                'timestamp': '2025-01-01T00:01:00Z',
+                            },
+                        },
+                    }
+                )
+            ),
+        ]
+    )
+
+    with patch(
+        'openhands.runtime.plugins.agent_skills.a2a_client.common.client.client.connect_sse'
+    ) as mock_connect_sse:
+        mock_connect_sse.return_value.__enter__.return_value = mock_event_source
+
+        client = A2AClient(url='http://mock.url')
+        payload = {
+            'id': 'test-task-id',
+            'message': {'role': 'user', 'parts': [{'type': 'text', 'text': 'Hi'}]},
+        }
+
+        responses = []
+        async for res in client.send_task_streaming(payload):
+            responses.append(res)
+
+        assert responses[0].result == TaskStatusUpdateEvent(
+            id='test-task-id',
+            status=TaskStatus(
+                state='submitted',
+                timestamp='2025-01-01T00:00:00Z',
+            ),
+            final=False,
+        )
+
+        assert responses[1].result == TaskStatusUpdateEvent(
+            id='test-task-id',
+            status=TaskStatus(
+                state='working',
+                timestamp='2025-01-01T00:01:00Z',
+            ),
+            final=False,
+        )
+
+
+# Tests for openhands/runtime/plugins/agent_skills/a2a_client/common/card_resolver.py
+
+
+def test_get_agent_card_success():
+    mock_response = MagicMock()
+    mock_response.json.return_value = {
+        'name': 'TestAgent',
+        'version': '1.0',
+        'capabilities': {
+            'streaming': True,
+        },
+        'url': 'http://example.com',
+        'skills': [
+            {
+                'id': 'test_skill_id',
+                'name': 'test_skill_name',
+            }
+        ],
+    }
+    mock_response.raise_for_status.return_value = None
+
+    with patch(
+        'openhands.runtime.plugins.agent_skills.a2a_client.common.client.client.httpx.Client'
+    ) as mock_client_cls:
+        mock_client = mock_client_cls.return_value.__enter__.return_value
+        mock_client.get.return_value = mock_response
+
+        resolver = A2ACardResolver('http://example.com')
+        result = resolver.get_agent_card()
+
+        assert isinstance(result, AgentCard)
+        assert result.name == 'TestAgent'
+        assert result.version == '1.0'
+
+
+def test_get_agent_card_json_error():
+    mock_response = MagicMock()
+    mock_response.json.side_effect = json.JSONDecodeError('msg', 'doc', 0)
+    mock_response.raise_for_status.return_value = None
+
+    with patch(
+        'openhands.runtime.plugins.agent_skills.a2a_client.common.client.client.httpx.Client'
+    ) as mock_client_cls:
+        mock_client = mock_client_cls.return_value.__enter__.return_value
+        mock_client.get.return_value = mock_response
+
+        resolver = A2ACardResolver('http://example.com')
+        with pytest.raises(A2AClientJSONError):
+            resolver.get_agent_card()

tests/unit/test_proxy_agent.py

@@ -0,0 +1,133 @@
+from unittest.mock import Mock
+
+import pytest
+
+from openhands.agenthub.proxy_agent.function_calling import (
+    DelegateLocalTool,
+    DelegateRemoteTool,
+    FinishTool,
+    get_tools,
+    response_to_action,
+)
+from openhands.agenthub.proxy_agent.proxy_agent import ProxyAgent
+from openhands.controller.state.state import State
+from openhands.core.config import AgentConfig, LLMConfig
+from openhands.core.exceptions import FunctionCallNotExistsError
+from openhands.events.action import (
+    MessageAction,
+)
+from openhands.llm.llm import LLM
+
+
+@pytest.fixture
+def agent() -> ProxyAgent:
+    config = AgentConfig()
+    agent = ProxyAgent(llm=LLM(LLMConfig()), config=config)
+    agent.llm = Mock()
+    agent.llm.config = Mock()
+    agent.llm.config.max_message_chars = 1000
+    return agent
+
+
+@pytest.fixture
+def mock_state() -> State:
+    state = Mock(spec=State)
+    state.history = []
+    state.extra_data = {}
+
+    return state
+
+
+def test_get_tools():
+    tools = get_tools()
+
+    assert len(tools) > 0
+
+    # Check required tools are present
+    tool_names = [tool['function']['name'] for tool in tools]
+    assert 'delegate_local' in tool_names
+    assert 'delegate_remote' in tool_names
+    assert 'finish' in tool_names
+
+
+def test_delegate_local_tool():
+    assert DelegateLocalTool['type'] == 'function'
+    assert DelegateLocalTool['function']['name'] == 'delegate_local'
+    assert list(DelegateLocalTool['function']['parameters']['properties'].keys()) == [
+        'agent_name',
+        'task',
+    ]
+    assert DelegateLocalTool['function']['parameters']['required'] == [
+        'agent_name',
+        'task',
+    ]
+
+
+def test_delegate_remote_tool():
+    assert DelegateRemoteTool['type'] == 'function'
+    assert DelegateRemoteTool['function']['name'] == 'delegate_remote'
+    assert list(DelegateRemoteTool['function']['parameters']['properties'].keys()) == [
+        'url',
+        'task',
+        'session_id',
+        'task_id',
+    ]
+    assert DelegateRemoteTool['function']['parameters']['required'] == [
+        'url',
+        'task',
+    ]
+
+
+def test_finish_tool():
+    assert FinishTool['type'] == 'function'
+    assert FinishTool['function']['name'] == 'finish'
+
+
+def test_response_to_action_invalid_tool():
+    # Test response with invalid tool call
+    mock_response = Mock()
+    mock_response.choices = [Mock()]
+    mock_response.choices[0].message = Mock()
+    mock_response.choices[0].message.content = 'Invalid tool'
+    mock_response.choices[0].message.tool_calls = [Mock()]
+    mock_response.choices[0].message.tool_calls[0].id = 'tool_call_10'
+    mock_response.choices[0].message.tool_calls[0].function = Mock()
+    mock_response.choices[0].message.tool_calls[0].function.name = 'invalid_tool'
+    mock_response.choices[0].message.tool_calls[0].function.arguments = '{}'
+
+    with pytest.raises(FunctionCallNotExistsError):
+        response_to_action(mock_response)
+
+
+def test_step(mock_state: State):
+    # Mock the LLM response
+    mock_response = Mock()
+    mock_response.id = 'mock_id'
+    mock_response.total_calls_in_response = 1
+    mock_response.choices = [Mock()]
+    mock_response.choices[0].message = Mock()
+    mock_response.choices[0].message.content = 'Task completed'
+    mock_response.choices[0].message.tool_calls = []
+
+    llm = Mock()
+    llm.completion = Mock(return_value=mock_response)
+    llm.is_function_calling_active = Mock(return_value=True)  # Enable function calling
+    llm.is_caching_prompt_active = Mock(return_value=False)
+
+    # Create agent with mocked LLM
+    config = AgentConfig()
+    config.enable_prompt_extensions = False
+    agent = ProxyAgent(llm=llm, config=config)
+
+    # Test step with no pending actions
+    mock_state.latest_user_message = None
+    mock_state.latest_user_message_id = None
+    mock_state.latest_user_message_timestamp = None
+    mock_state.latest_user_message_cause = None
+    mock_state.latest_user_message_timeout = None
+    mock_state.latest_user_message_llm_metrics = None
+    mock_state.latest_user_message_tool_call_metadata = None
+
+    action = agent.step(mock_state)
+    assert isinstance(action, MessageAction)
+    assert action.content == 'Task completed'