Merge branch 'main' into enyst/task-cli

README.md

@@ -39,7 +39,7 @@ Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or jump to the [
 ## ⚡ Quick Start
 
 The easiest way to run OpenHands is in Docker.
-See the [Installation](https://docs.all-hands.dev/modules/usage/installation) guide for
+See the [Running OpenHands](https://docs.all-hands.dev/modules/usage/installation) guide for
 system requirements and more information.
 
 ```bash
@@ -69,7 +69,7 @@ run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules
 interact with it via a [friendly CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode),
 or run it on tagged issues with [a github action](https://docs.all-hands.dev/modules/usage/how-to/github-action).
 
-Visit [Installation](https://docs.all-hands.dev/modules/usage/installation) for more information and setup instructions.
+Visit [Running OpenHands](https://docs.all-hands.dev/modules/usage/installation) for more information and setup instructions.
 
 > [!CAUTION]
 > OpenHands is meant to be run by a single user on their local workstation.

config.template.toml

@@ -39,6 +39,11 @@ workspace_base = "./workspace"
 # If it's a folder, the session id will be used as the file name
 #save_trajectory_path="./trajectories"
 
+# Path to replay a trajectory, must be a file path
+# If provided, trajectory will be loaded and replayed before the
+# agent responds to any user instruction
+#replay_trajectory_path = ""
+
 # File store path
 #file_store_path = "/tmp/file_store"
 

docs/modules/usage/configuration-options.md

@@ -55,6 +55,11 @@ The core configuration options are defined in the `[core]` section of the `confi
   - Default: `"./trajectories"`
   - Description: Path to store trajectories (can be a folder or a file). If it's a folder, the trajectories will be saved in a file named with the session id name and .json extension, in that folder.
 
+- `replay_trajectory_path`
+  - Type: `str`
+  - Default: `""`
+  - Description: Path to load a trajectory and replay. If given, must be a path to the trajectory file in JSON format. The actions in the trajectory file would be replayed first before any user instruction is executed.
+
 ### File Store
 - `file_store_path`
   - Type: `str`

docs/modules/usage/getting-started.mdx

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

docs/modules/usage/installation.mdx

@@ -1,12 +1,51 @@
-# Installation
+# Running OpenHands
 
 ## System Requirements
 
-- Docker version 26.0.0+ or Docker Desktop 4.31.0+.
-- You must be using Linux or Mac OS.
-  - If you are on Windows, you must use [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
+- MacOS with [Docker Desktop support](https://docs.docker.com/desktop/setup/install/mac-install/#system-requirements)
+- Linux
+- Windows with [WSL](https://learn.microsoft.com/en-us/windows/wsl/install) and [Docker Desktop support](https://docs.docker.com/desktop/setup/install/windows-install/#system-requirements)
 
-## Start the app
+## Prerequisites
+
+<details>
+  <summary>MacOS</summary>
+  ### Docker Desktop
+
+  1. [Install Docker Desktop on Mac](https://docs.docker.com/desktop/setup/install/mac-install).
+  2. Open Docker Desktop, go to `Settings > Advanced` and ensure `Allow the default Docker socket to be used` is enabled.
+</details>
+
+<details>
+  <summary>Linux</summary>
+
+  :::note
+  Tested with Ubuntu 22.04.
+  :::
+
+  ### Docker Desktop
+
+  1. [Install Docker Desktop on Linux](https://docs.docker.com/desktop/setup/install/linux/).
+
+</details>
+
+<details>
+  <summary>Windows</summary>
+  ### WSL
+
+  1. [Install WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
+  2. Run `wsl --version` in powershell and confirm `Default Version: 2`.
+
+  ### Docker Desktop
+
+  1. [Install Docker Desktop on Windows](https://docs.docker.com/desktop/setup/install/windows-install).
+  2. Open Docker Desktop, go to `Settings` and confirm the following:
+  - General: `Use the WSL 2 based engine` is enabled.
+  - Resources > WSL Integration: `Enable integration with my default WSL distro` is enabled.
+
+</details>
+
+## Start the App
 
 The easiest way to run OpenHands is in Docker.
 

docs/sidebars.ts

@@ -5,7 +5,7 @@ const sidebars: SidebarsConfig = {
   docsSidebar: [
     {
       type: 'doc',
-      label: 'Installation',
+      label: 'Running OpenHands',
       id: 'usage/installation',
     },
     {

evaluation/utils/shared.py

@@ -355,7 +355,9 @@ def _process_instance_wrapper(
             )
             # e is likely an EvalException, so we can't directly infer it from type
             # but rather check if it's a fatal error
-            if is_fatal_runtime_error(str(e)):
+            # But it can also be AgentRuntime**Error (e.g., swe_bench/eval_infer.py)
+            _error_str = type(e).__name__ + ': ' + str(e)
+            if is_fatal_runtime_error(_error_str):
                 runtime_failure_count += 1
                 msg += f'Runtime disconnected error detected for instance {instance.instance_id}, runtime failure count: {runtime_failure_count}'
                 msg += '\n' + '-' * 10 + '\n'
@@ -531,6 +533,7 @@ def is_fatal_runtime_error(error: str | None) -> bool:
         return False
 
     FATAL_RUNTIME_ERRORS = [
+        AgentRuntimeTimeoutError,
         AgentRuntimeUnavailableError,
         AgentRuntimeDisconnectedError,
         AgentRuntimeNotFoundError,