Update run_infer to add github prior knowledge

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

.github/workflows/integration-runner.yml

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

.github/workflows/openhands-resolver.yml

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

CODE_OF_CONDUCT.md

@@ -113,6 +113,20 @@ individual, or aggression toward or disparagement of classes of individuals.
 **Consequence**: A permanent ban from any sort of public interaction within the
 community.
 
+### Slack and Discord Etiquettes
+
+These Slack and Discord etiquette guidelines are designed to foster an inclusive, respectful, and productive environment for all community members. By following these best practices, we ensure effective communication and collaboration while minimizing disruptions. Let’s work together to build a supportive and welcoming community!
+
+- Communicate respectfully and professionally, avoiding sarcasm or harsh language, and remember that tone can be difficult to interpret in text.
+- Use threads for specific discussions to keep channels organized and easier to follow.
+- Tag others only when their input is critical or urgent, and use @here, @channel or @everyone sparingly to minimize disruptions.
+- Be patient, as open-source contributors and maintainers often have other commitments and may need time to respond.
+- Post questions or discussions in the most relevant channel (e.g., for [slack - #general](https://app.slack.com/client/T06P212QSEA/C06P5NCGSFP) for general topics, [slack - #questions](https://openhands-ai.slack.com/archives/C06U8UTKSAD) for queries/questions, [discord - #general](https://discord.com/channels/1222935860639563850/1222935861386018885)).
+- When asking for help or raising issues, include necessary details like links, screenshots, or clear explanations to provide context.
+- Keep discussions in public channels whenever possible to allow others to benefit from the conversation, unless the matter is sensitive or private.
+- Always adhere to [our standards](https://github.com/All-Hands-AI/OpenHands/blob/main/CODE_OF_CONDUCT.md#our-standards) to ensure a welcoming and collaborative environment.
+- If you choose to mute a channel, consider setting up alerts for topics that still interest you to stay engaged. For Slack, Go to Settings → Notifications → My Keywords to add specific keywords that will notify you when mentioned. For example, if you're here for discussions about LLMs, mute the channel if it’s too busy, but set notifications to alert you only when “LLMs” appears in messages. Also for Discord, go to the channel notifications and choose the option that best describes your need.
+
 ## Attribution
 
 This Code of Conduct is adapted from the [Contributor Covenant][homepage],

Development.md

@@ -5,7 +5,7 @@ Otherwise, you can clone the OpenHands project directly.
 
 ## Start the Server for Development
 ### 1. Requirements
-* Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)  [Ubuntu <= 22.04]
+* Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)  [Ubuntu >= 22.04]
 * [Docker](https://docs.docker.com/engine/install/) (For those on MacOS, make sure to allow the default Docker socket to be used from advanced settings!)
 * [Python](https://www.python.org/downloads/) = 3.12
 * [NodeJS](https://nodejs.org/en/download/package-manager) >= 20.x

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

@@ -23,6 +23,9 @@ workspace_base = "./workspace"
 # Cache directory path
 #cache_dir = "/tmp/cache"
 
+# Reasoning effort for o1 models (low, medium, high, or not set)
+#reasoning_effort = "medium"
+
 # Debugging enabled
 #debug = false
 
@@ -36,6 +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"
 
@@ -220,8 +228,8 @@ codeact_enable_jupyter = true
 # LLM config group to use
 #llm_config = 'your-llm-config-group'
 
-# Whether to use microagents at all
-#use_microagents = true
+# Whether to use prompt extension (e.g., microagent, repo/runtime info) at all
+#enable_prompt_extensions = true
 
 # List of microagents to disable
 #disabled_microagents = []

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

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

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

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

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

@@ -373,7 +373,7 @@ Agent 配置选项在 `config.toml` 文件的 `[agent]` 和 `[agent.<agent_name>
   - 描述: 是否在 action space 中启用 Jupyter
 
 **Microagent 使用**
-- `use_microagents`
+- `enable_prompt_extensions`
   - 类型: `bool`
   - 默认值: `true`
   - 描述: 是否使用 microagents

docs/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`
@@ -140,7 +145,11 @@ The LLM (Large Language Model) configuration options are defined in the `[llm]`
 
 To use these with the docker command, pass in `-e LLM_<option>`. Example: `-e LLM_NUM_RETRIES`.
 
-### AWS Credentials
+:::note
+For development setups, you can also define custom named LLM configurations. See [Custom LLM Configurations](./llms/custom-llm-configs) for details.
+:::
+
+**AWS Credentials**
 - `aws_access_key_id`
   - Type: `str`
   - Default: `""`
@@ -332,7 +341,7 @@ The agent configuration options are defined in the `[agent]` and `[agent.<agent_
   - Description: Whether Jupyter is enabled in the action space
 
 ### Microagent Usage
-- `use_microagents`
+- `enable_prompt_extensions`
   - Type: `bool`
   - Default: `true`
   - Description: Whether to use microagents at all

docs/modules/usage/getting-started.mdx

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

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

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

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

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

docs/sidebars.ts

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

evaluation/benchmarks/EDA/run_infer.py

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

evaluation/benchmarks/agent_bench/run_infer.py

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

evaluation/benchmarks/aider_bench/run_infer.py

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

evaluation/benchmarks/biocoder/run_infer.py

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

evaluation/benchmarks/bird/run_infer.py

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

evaluation/benchmarks/browsing_delegation/run_infer.py

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

evaluation/benchmarks/commit0_bench/run_infer.py

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

evaluation/benchmarks/discoverybench/run_infer.py

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

evaluation/benchmarks/gaia/run_infer.py

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

evaluation/benchmarks/gorilla/run_infer.py

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

evaluation/benchmarks/gpqa/run_infer.py

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

evaluation/benchmarks/humanevalfix/run_infer.py

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

evaluation/benchmarks/logic_reasoning/run_infer.py

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

evaluation/benchmarks/miniwob/README.md

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

evaluation/benchmarks/mint/run_infer.py

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

evaluation/benchmarks/ml_bench/run_infer.py

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

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -1,3 +1,4 @@
+import json
 import os
 import tempfile
 import time
@@ -11,7 +12,11 @@ from swebench.harness.run_evaluation import (
 )
 from swebench.harness.test_spec import SWEbenchInstance, TestSpec, make_test_spec
 from swebench.harness.utils import load_swebench_dataset
+from tqdm import tqdm
 
+from evaluation.benchmarks.swe_bench.resource.mapping import (
+    get_instance_resource_factor,
+)
 from evaluation.benchmarks.swe_bench.run_infer import get_instance_docker_image
 from evaluation.utils.shared import (
     EvalMetadata,
@@ -66,7 +71,7 @@ def process_git_patch(patch):
     return patch
 
 
-def get_config(instance: pd.Series) -> AppConfig:
+def get_config(metadata: EvalMetadata, instance: pd.Series) -> AppConfig:
     # We use a different instance image for the each instance of swe-bench eval
     base_container_image = get_instance_docker_image(instance['instance_id'])
     logger.info(
@@ -81,10 +86,14 @@ def get_config(instance: pd.Series) -> AppConfig:
             base_container_image=base_container_image,
             use_host_network=False,
             # large enough timeout, since some testcases take very long to run
-            timeout=1800,
+            timeout=600,
             api_key=os.environ.get('ALLHANDS_API_KEY', None),
             remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
             remote_runtime_init_timeout=3600,
+            remote_runtime_resource_factor=get_instance_resource_factor(
+                dataset_name=metadata.dataset,
+                instance_id=instance['instance_id'],
+            ),
         ),
         # do not mount workspace
         workspace_base=None,
@@ -123,7 +132,7 @@ def process_instance(
     else:
         logger.info(f'Starting evaluation for instance {instance.instance_id}.')
 
-    config = get_config(instance)
+    config = get_config(metadata, instance)
     instance_id = instance.instance_id
     model_patch = instance['model_patch']
     test_spec: TestSpec = instance['test_spec']
@@ -151,52 +160,52 @@ def process_instance(
     if runtime_failure_count > 0:
         config.sandbox.remote_runtime_resource_factor = min(
             config.sandbox.remote_runtime_resource_factor * (2**runtime_failure_count),
-            4,  # hardcode maximum resource factor to 4
+            8,
         )
         logger.warning(
-            f'This is the second attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
+            f'This is the {runtime_failure_count + 1}th attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
         )
 
-    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
-    # Get patch and save it to /tmp/patch.diff
-    with tempfile.TemporaryDirectory() as temp_dir:
-        # Patch file
-        patch_file_path = os.path.join(temp_dir, 'patch.diff')
-        with open(patch_file_path, 'w') as f:
-            f.write(model_patch)
-        runtime.copy_to(patch_file_path, '/tmp')
-        # Eval script
-        eval_script_path = os.path.join(temp_dir, 'eval.sh')
-        with open(eval_script_path, 'w') as f:
-            f.write(test_spec.eval_script)
-        runtime.copy_to(eval_script_path, '/tmp')
-
-    # Set +x
-    action = CmdRunAction(command='chmod +x /tmp/eval.sh')
-    action.timeout = 600
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert obs.exit_code == 0
-
-    # Apply patch
-    exec_command = (
-        'cd /testbed && '
-        "(git apply -v /tmp/patch.diff && echo 'APPLY_PATCH_PASS' || "
-        "(echo 'Failed to apply patch with git apply, trying with patch command...' && "
-        "(patch --batch --fuzz=5 -p1 -i /tmp/patch.diff && echo 'APPLY_PATCH_PASS' || "
-        "echo 'APPLY_PATCH_FAIL')))"
-    )
-    action = CmdRunAction(command=exec_command)
-    action.timeout = 600
-    obs = runtime.run_action(action)
-    assert isinstance(obs, CmdOutputObservation)
-    apply_patch_output = obs.content
-    assert isinstance(apply_patch_output, str)
-    instance['test_result']['apply_patch_output'] = apply_patch_output
-
     try:
+        runtime = create_runtime(config)
+        call_async_from_sync(runtime.connect)
+        # Get patch and save it to /tmp/patch.diff
+        with tempfile.TemporaryDirectory() as temp_dir:
+            # Patch file
+            patch_file_path = os.path.join(temp_dir, 'patch.diff')
+            with open(patch_file_path, 'w') as f:
+                f.write(model_patch)
+            runtime.copy_to(patch_file_path, '/tmp')
+            # Eval script
+            eval_script_path = os.path.join(temp_dir, 'eval.sh')
+            with open(eval_script_path, 'w') as f:
+                f.write(test_spec.eval_script)
+            runtime.copy_to(eval_script_path, '/tmp')
+
+        # Set +x
+        action = CmdRunAction(command='chmod +x /tmp/eval.sh')
+        action.set_hard_timeout(600)
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+        assert obs.exit_code == 0
+
+        # Apply patch
+        exec_command = (
+            'cd /testbed && '
+            "(git apply -v /tmp/patch.diff && echo 'APPLY_PATCH_PASS' || "
+            "(echo 'Failed to apply patch with git apply, trying with patch command...' && "
+            "(patch --batch --fuzz=5 -p1 -i /tmp/patch.diff && echo 'APPLY_PATCH_PASS' || "
+            "echo 'APPLY_PATCH_FAIL')))"
+        )
+        action = CmdRunAction(command=exec_command)
+        action.set_hard_timeout(600)
+        obs = runtime.run_action(action)
+        assert isinstance(obs, CmdOutputObservation)
+        apply_patch_output = obs.content
+        assert isinstance(apply_patch_output, str)
+        instance['test_result']['apply_patch_output'] = apply_patch_output
+
         if 'APPLY_PATCH_FAIL' in apply_patch_output:
             logger.info(f'[{instance_id}] {APPLY_PATCH_FAIL}:\n{apply_patch_output}')
             instance['test_result']['report']['failed_apply_patch'] = True
@@ -212,7 +221,7 @@ def process_instance(
             # Run eval script in background and save output to log file
             log_file = '/tmp/eval_output.log'
             action = CmdRunAction(command=f'/tmp/eval.sh > {log_file} 2>&1 & echo $!')
-            action.timeout = 60  # Short timeout just to get the process ID
+            action.set_hard_timeout(300)  # Short timeout just to get the process ID
             obs = runtime.run_action(action)
 
             if isinstance(obs, CmdOutputObservation) and obs.exit_code == 0:
@@ -235,7 +244,7 @@ def process_instance(
                     check_action = CmdRunAction(
                         command=f'ps -p {pid} > /dev/null; echo $?'
                     )
-                    check_action.timeout = 60
+                    check_action.set_hard_timeout(300)
                     check_obs = runtime.run_action(check_action)
                     if (
                         isinstance(check_obs, CmdOutputObservation)
@@ -252,7 +261,7 @@ def process_instance(
 
                 # Read the log file
                 cat_action = CmdRunAction(command=f'cat {log_file}')
-                cat_action.timeout = 300
+                cat_action.set_hard_timeout(300)
                 cat_obs = runtime.run_action(cat_action)
 
                 # Grade answer
@@ -352,7 +361,14 @@ if __name__ == '__main__':
 
     # Load predictions
     assert args.input_file.endswith('.jsonl'), 'Input file must be a jsonl file.'
-    predictions = pd.read_json(args.input_file, lines=True)
+    required_fields = ['instance_id', 'model_patch', 'test_result']
+    with open(args.input_file) as f:
+        predictions = pd.DataFrame.from_records(
+            [
+                {k: v for k, v in json.loads(line).items() if k in required_fields}
+                for line in tqdm(f, desc='Loading predictions')
+            ]
+        )
     assert (
         'instance_id' in predictions.columns
     ), 'Input file must contain instance_id column.'

evaluation/benchmarks/swe_bench/resource/mapping.py

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

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

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

evaluation/benchmarks/swe_bench/run_infer.py

@@ -9,6 +9,9 @@ import toml
 from datasets import load_dataset
 
 import openhands.agenthub
+from evaluation.benchmarks.swe_bench.resource.mapping import (
+    get_instance_resource_factor,
+)
 from evaluation.utils.shared import (
     EvalException,
     EvalMetadata,
@@ -41,9 +44,10 @@ from openhands.utils.async_utils import call_async_from_sync
 from openhands.utils.shutdown_listener import sleep_if_should_continue
 
 USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
-USE_INSTANCE_IMAGE = os.environ.get('USE_INSTANCE_IMAGE', 'false').lower() == 'true'
+USE_INSTANCE_IMAGE = os.environ.get('USE_INSTANCE_IMAGE', 'true').lower() == 'true'
 RUN_WITH_BROWSING = os.environ.get('RUN_WITH_BROWSING', 'false').lower() == 'true'
 
+
 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
     'CodeActAgent': codeact_user_response,
 }
@@ -67,15 +71,16 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
         f'<pr_description>\n'
         f'{instance.problem_statement}\n'
         '</pr_description>\n\n'
-        'Can you help me implement the necessary changes to the repository so that the requirements specified in the <pr_description> are met?\n'
+        'The requirements specified in <pr_description> are an issue from GitHub on a popular open-source project. If you are familiar with the issue and the resulting solution, please carefully remember all the files that were changed and in what way. Come up with a detailed plan to reproduce the patch.\n'
         "I've already taken care of all changes to any of the test files described in the <pr_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!\n"
-        'Your task is to make the minimal changes to non-tests files in the /workspace directory to ensure the <pr_description> is satisfied.\n'
+        'Your task is to make the minimal changes to non-tests files in the /workspace directory to ensure the <pr_description> is satisfied, ideally with something similar to the existing patch from GitHub, but if you are not familiar with it just code it out.\n'
         'Follow these steps to resolve the issue:\n'
-        '1. As a first step, it might be a good idea to explore the repo to familiarize yourself with its structure.\n'
-        '2. Create a script to reproduce the error and execute it with `python <filename.py>` using the BashTool, to confirm the error\n'
-        '3. Edit the sourcecode of the repo to resolve the issue\n'
-        '4. Rerun your reproduce script and confirm that the error is fixed!\n'
-        '5. Think about edgecases and make sure your fix handles them as well\n'
+        '1. Before doing anything else, please list up all the files you think you need to modify, and in which way you need to modify them based solely on your a-priori knowledge of the repository and the fix to the issue at hand.'
+        '2. Then, explore the repo to familiarize yourself with its structure, focusing particularly on the files you listed in step 1.\n'
+        '3. Create a script to reproduce the error and execute it with `python <filename.py>` using the BashTool, to confirm the error\n'
+        '4. Edit the sourcecode of the repo to resolve the issue\n'
+        '5. Rerun your reproduce script and confirm that the error is fixed!\n'
+        '6. Think about edgecases and make sure your fix handles them as well\n'
         "Your thinking should be thorough and so it's fine if it's very long.\n"
     )
 
@@ -135,6 +140,10 @@ def get_config(
             remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
             keep_runtime_alive=False,
             remote_runtime_init_timeout=3600,
+            remote_runtime_resource_factor=get_instance_resource_factor(
+                dataset_name=metadata.dataset,
+                instance_id=instance['instance_id'],
+            ),
         ),
         # do not mount workspace
         workspace_base=None,
@@ -150,6 +159,7 @@ def get_config(
         codeact_enable_browsing=RUN_WITH_BROWSING,
         codeact_enable_llm_editor=False,
         condenser=metadata.condenser_config,
+        enable_prompt_extensions=False,
     )
     config.set_agent_config(agent_config)
     return config
@@ -173,7 +183,7 @@ def initialize_runtime(
     action = CmdRunAction(
         command=f"""echo 'export SWE_INSTANCE_ID={instance['instance_id']}' >> ~/.bashrc && echo 'export PIP_CACHE_DIR=~/.cache/pip' >> ~/.bashrc && echo "alias git='git --no-pager'" >> ~/.bashrc"""
     )
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -182,7 +192,7 @@ def initialize_runtime(
     )
 
     action = CmdRunAction(command="""export USER=$(whoami); echo USER=${USER} """)
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -194,7 +204,7 @@ def initialize_runtime(
 
         # inject the instance info
         action = CmdRunAction(command='mkdir -p /swe_util/eval_data/instances')
-        action.timeout = 600
+        action.set_hard_timeout(600)
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -223,14 +233,14 @@ def initialize_runtime(
             '/swe_util/',
         )
         action = CmdRunAction(command='cat ~/.bashrc')
-        action.timeout = 600
+        action.set_hard_timeout(600)
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         logger.info(obs, extra={'msg_type': 'OBSERVATION'})
         assert_and_raise(obs.exit_code == 0, f'Failed to cat ~/.bashrc: {str(obs)}')
 
         action = CmdRunAction(command='source ~/.bashrc')
-        action.timeout = 600
+        action.set_hard_timeout(600)
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -239,7 +249,7 @@ def initialize_runtime(
         assert_and_raise(obs.exit_code == 0, f'Failed to source ~/.bashrc: {str(obs)}')
 
         action = CmdRunAction(command='source /swe_util/instance_swe_entry.sh')
-        action.timeout = 3600
+        action.set_hard_timeout(600)
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -249,7 +259,7 @@ def initialize_runtime(
         )
     else:
         action = CmdRunAction(command='source /swe_util/swe_entry.sh')
-        action.timeout = 1800
+        action.set_hard_timeout(1800)
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -259,7 +269,7 @@ def initialize_runtime(
         )
 
     action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -269,7 +279,7 @@ def initialize_runtime(
     )
 
     action = CmdRunAction(command='git reset --hard')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -278,14 +288,14 @@ def initialize_runtime(
     action = CmdRunAction(
         command='for remote_name in $(git remote); do git remote remove "${remote_name}"; done'
     )
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     assert_and_raise(obs.exit_code == 0, f'Failed to remove git remotes: {str(obs)}')
 
     action = CmdRunAction(command='which python')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -316,7 +326,7 @@ def complete_runtime(
     workspace_dir_name = _get_swebench_workspace_dir_name(instance)
 
     action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -326,7 +336,7 @@ def complete_runtime(
     )
 
     action = CmdRunAction(command='git config --global core.pager ""')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -336,7 +346,7 @@ def complete_runtime(
     )
 
     action = CmdRunAction(command='git add -A')
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -351,7 +361,7 @@ def complete_runtime(
         action = CmdRunAction(
             command=f'git diff --no-color --cached {instance["base_commit"]}'
         )
-        action.timeout = 600 + 100 * n_retries
+        action.set_hard_timeout(max(300 + 100 * n_retries, 600))
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -399,7 +409,7 @@ def process_instance(
             8,
         )
         logger.warning(
-            f'This is the second attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
+            f'This is the {runtime_failure_count + 1}th attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
         )
     runtime = create_runtime(config)
     call_async_from_sync(runtime.connect)
@@ -479,6 +489,10 @@ def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
                 subset = dataset[dataset[filter_column].isin(selected_ids)]
                 logger.info(f'Retained {subset.shape[0]} tasks after filtering')
                 return subset
+    skip_ids = os.environ.get('SKIP_IDS', '').split(',')
+    if len(skip_ids) > 0:
+        logger.info(f'Filtering {len(skip_ids)} tasks from "SKIP_IDS"...')
+        return dataset[~dataset[filter_column].isin(skip_ids)]
     return dataset
 
 
@@ -501,8 +515,10 @@ if __name__ == '__main__':
     # NOTE: It is preferable to load datasets from huggingface datasets and perform post-processing
     # so we don't need to manage file uploading to OpenHands's repo
     dataset = load_dataset(args.dataset, split=args.split)
-    logger.info(f'Loaded dataset {args.dataset} with split {args.split}')
     swe_bench_tests = filter_dataset(dataset.to_pandas(), 'instance_id')
+    logger.info(
+        f'Loaded dataset {args.dataset} with split {args.split}: {len(swe_bench_tests)} tasks'
+    )
 
     llm_config = None
     if args.llm_config:
@@ -531,6 +547,7 @@ if __name__ == '__main__':
     )
 
     output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
+    print(f'### OUTPUT FILE: {output_file} ###')
     instances = prepare_dataset(swe_bench_tests, output_file, args.eval_n_limit)
 
     if len(instances) > 0 and not isinstance(

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

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

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

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

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

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

evaluation/benchmarks/swe_bench/scripts/run_infer.sh

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

evaluation/benchmarks/the_agent_company/browsing.py

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

evaluation/benchmarks/the_agent_company/run_infer.py

@@ -80,13 +80,13 @@ def load_dependencies(runtime: Runtime) -> List[str]:
 def init_task_env(runtime: Runtime, hostname: str, env_llm_config: LLMConfig):
     command = (
         f'SERVER_HOSTNAME={hostname} '
-        f'LITELLM_API_KEY={env_llm_config.api_key} '
+        f'LITELLM_API_KEY={env_llm_config.api_key.get_secret_value() if env_llm_config.api_key else None} '
         f'LITELLM_BASE_URL={env_llm_config.base_url} '
         f'LITELLM_MODEL={env_llm_config.model} '
         'bash /utils/init.sh'
     )
     action = CmdRunAction(command=command)
-    action.timeout = 900
+    action.set_hard_timeout(900)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
@@ -165,14 +165,14 @@ def run_evaluator(
     runtime: Runtime, env_llm_config: LLMConfig, trajectory_path: str, result_path: str
 ):
     command = (
-        f'LITELLM_API_KEY={env_llm_config.api_key} '
+        f'LITELLM_API_KEY={env_llm_config.api_key.get_secret_value() if env_llm_config.api_key else None} '
         f'LITELLM_BASE_URL={env_llm_config.base_url} '
         f'LITELLM_MODEL={env_llm_config.model} '
         f"DECRYPTION_KEY='theagentcompany is all you need' "  # Hardcoded Key
         f'python_default /utils/eval.py --trajectory_path {trajectory_path} --result_path {result_path}'
     )
     action = CmdRunAction(command=command)
-    action.timeout = 600
+    action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})

evaluation/benchmarks/toolqa/run_infer.py

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

evaluation/benchmarks/webarena/run_infer.py

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

evaluation/integration_tests/run_infer.py

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

evaluation/integration_tests/scripts/run_infer.sh

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

evaluation/integration_tests/tests/t07_interactive_commands.py

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

evaluation/utils/shared.py

@@ -52,30 +52,6 @@ class EvalMetadata(BaseModel):
     details: dict[str, Any] | None = None
     condenser_config: CondenserConfig | None = None
 
-    def model_dump(self, *args, **kwargs):
-        dumped_dict = super().model_dump(*args, **kwargs)
-        # avoid leaking sensitive information
-        dumped_dict['llm_config'] = self.llm_config.to_safe_dict()
-        if hasattr(self.condenser_config, 'llm_config'):
-            dumped_dict['condenser_config']['llm_config'] = (
-                self.condenser_config.llm_config.to_safe_dict()
-            )
-
-        return dumped_dict
-
-    def model_dump_json(self, *args, **kwargs):
-        dumped = super().model_dump_json(*args, **kwargs)
-        dumped_dict = json.loads(dumped)
-        # avoid leaking sensitive information
-        dumped_dict['llm_config'] = self.llm_config.to_safe_dict()
-        if hasattr(self.condenser_config, 'llm_config'):
-            dumped_dict['condenser_config']['llm_config'] = (
-                self.condenser_config.llm_config.to_safe_dict()
-            )
-
-        logger.debug(f'Dumped metadata: {dumped_dict}')
-        return json.dumps(dumped_dict)
-
 
 class EvalOutput(BaseModel):
     # NOTE: User-specified
@@ -98,23 +74,6 @@ class EvalOutput(BaseModel):
     # Optionally save the input test instance
     instance: dict[str, Any] | None = None
 
-    def model_dump(self, *args, **kwargs):
-        dumped_dict = super().model_dump(*args, **kwargs)
-        # Remove None values
-        dumped_dict = {k: v for k, v in dumped_dict.items() if v is not None}
-        # Apply custom serialization for metadata (to avoid leaking sensitive information)
-        if self.metadata is not None:
-            dumped_dict['metadata'] = self.metadata.model_dump()
-        return dumped_dict
-
-    def model_dump_json(self, *args, **kwargs):
-        dumped = super().model_dump_json(*args, **kwargs)
-        dumped_dict = json.loads(dumped)
-        # Apply custom serialization for metadata (to avoid leaking sensitive information)
-        if 'metadata' in dumped_dict:
-            dumped_dict['metadata'] = json.loads(self.metadata.model_dump_json())
-        return json.dumps(dumped_dict)
-
 
 class EvalException(Exception):
     pass
@@ -314,7 +273,7 @@ def update_progress(
     logger.info(
         f'Finished evaluation for instance {result.instance_id}: {str(result.test_result)[:300]}...\n'
     )
-    output_fp.write(json.dumps(result.model_dump()) + '\n')
+    output_fp.write(result.model_dump_json() + '\n')
     output_fp.flush()
 
 
@@ -371,7 +330,6 @@ def _process_instance_wrapper(
             error = str(e)
             stacktrace = traceback.format_exc()
             if attempt == max_retries:
-                logger.exception(e)
                 msg = (
                     '-' * 10
                     + '\n'
@@ -395,19 +353,15 @@ def _process_instance_wrapper(
                 + '-' * 10
                 + '\n'
             )
-            if isinstance(
-                e,
-                (
-                    AgentRuntimeDisconnectedError,
-                    AgentRuntimeUnavailableError,
-                    AgentRuntimeNotFoundError,
-                ),
-            ):
+            # e is likely an EvalException, so we can't directly infer it from type
+            # but rather check if it's a fatal error
+            # But it can also be AgentRuntime**Error (e.g., swe_bench/eval_infer.py)
+            _error_str = type(e).__name__ + ': ' + str(e)
+            if is_fatal_runtime_error(_error_str):
                 runtime_failure_count += 1
                 msg += f'Runtime disconnected error detected for instance {instance.instance_id}, runtime failure count: {runtime_failure_count}'
+                msg += '\n' + '-' * 10 + '\n'
             logger.error(msg)
-            if use_mp:
-                print(msg)  # use print to directly print to console
             time.sleep(5)
 
 
@@ -564,6 +518,7 @@ def is_fatal_evaluation_error(error: str | None) -> bool:
         AgentRuntimeNotReadyError,
         AgentRuntimeDisconnectedError,
         AgentRuntimeNotFoundError,
+        ConnectionError,
     ]
 
     if any(exception.__name__ in error for exception in FATAL_EXCEPTIONS):
@@ -573,6 +528,24 @@ def is_fatal_evaluation_error(error: str | None) -> bool:
     return False
 
 
+def is_fatal_runtime_error(error: str | None) -> bool:
+    if not error:
+        return False
+
+    FATAL_RUNTIME_ERRORS = [
+        AgentRuntimeTimeoutError,
+        AgentRuntimeUnavailableError,
+        AgentRuntimeDisconnectedError,
+        AgentRuntimeNotFoundError,
+    ]
+
+    if any(exception.__name__ in error for exception in FATAL_RUNTIME_ERRORS):
+        logger.error(f'Fatal runtime error detected: {error}')
+        return True
+
+    return False
+
+
 def get_metrics(state: State) -> dict[str, Any]:
     """Extract metrics from the state."""
     metrics = state.metrics.get() if state.metrics else {}

frontend/__tests__/components/browser.test.tsx

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

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

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

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

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

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

@@ -128,7 +128,7 @@ describe("Sidebar", () => {
       await user.click(norskOption);
 
       const tokenInput =
-        within(accountSettingsModal).getByLabelText(/GITHUB\$TOKEN_OPTIONAL/i);
+        within(accountSettingsModal).getByLabelText(/GITHUB\$TOKEN_LABEL/i);
       await user.type(tokenInput, "new-token");
 
       const saveButton =
@@ -156,7 +156,7 @@ describe("Sidebar", () => {
       await user.click(advancedOptionsSwitch);
 
       const apiKeyInput = within(settingsModal).getByLabelText(/API\$KEY/i);
-      await user.type(apiKeyInput, "SET");
+      await user.type(apiKeyInput, "**********");
 
       const saveButton = within(settingsModal).getByTestId(
         "save-settings-button",

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

@@ -1,11 +1,10 @@
-import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
-import * as router from "react-router";
+import { afterEach, describe, expect, it, vi } from "vitest";
 
 // Mock useParams before importing components
 vi.mock("react-router", async () => {
   const actual = await vi.importActual("react-router");
   return {
-    ...actual as object,
+    ...(actual as object),
     useParams: () => ({ conversationId: "test-conversation-id" }),
   };
 });
@@ -60,7 +59,9 @@ describe("FeedbackForm", () => {
     renderWithProviders(
       <FeedbackForm polarity="positive" onClose={onCloseMock} />,
     );
-    await user.click(screen.getByRole("button", { name: I18nKey.FEEDBACK$CANCEL_LABEL }));
+    await user.click(
+      screen.getByRole("button", { name: I18nKey.FEEDBACK$CANCEL_LABEL }),
+    );
 
     expect(onCloseMock).toHaveBeenCalled();
   });

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

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

frontend/__tests__/routes/_oh.test.tsx

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

frontend/__tests__/utils/test-config.tsx

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

frontend/package.json

@@ -9,11 +9,11 @@
   "dependencies": {
     "@monaco-editor/react": "^4.7.0-rc.0",
     "@nextui-org/react": "^2.6.11",
-    "@react-router/node": "^7.1.1",
-    "@react-router/serve": "^7.1.1",
-    "@react-types/shared": "^3.25.0",
+    "@react-router/node": "^7.1.2",
+    "@react-router/serve": "^7.1.2",
+    "@react-types/shared": "^3.27.0",
     "@reduxjs/toolkit": "^2.5.0",
-    "@tanstack/react-query": "^5.63.0",
+    "@tanstack/react-query": "^5.64.1",
     "@vitejs/plugin-react": "^4.3.2",
     "@xterm/addon-fit": "^0.10.0",
     "@xterm/xterm": "^5.4.0",
@@ -26,7 +26,7 @@
     "isbot": "^5.1.21",
     "jose": "^5.9.4",
     "monaco-editor": "^0.52.2",
-    "posthog-js": "^1.205.0",
+    "posthog-js": "^1.207.0",
     "react": "^19.0.0",
     "react-dom": "^19.0.0",
     "react-highlight": "^0.15.0",
@@ -35,7 +35,7 @@
     "react-icons": "^5.4.0",
     "react-markdown": "^9.0.3",
     "react-redux": "^9.2.0",
-    "react-router": "^7.1.1",
+    "react-router": "^7.1.2",
     "react-syntax-highlighter": "^15.6.1",
     "react-textarea-autosize": "^8.5.7",
     "remark-gfm": "^4.0.0",
@@ -77,21 +77,21 @@
   "devDependencies": {
     "@mswjs/socket.io-binding": "^0.1.1",
     "@playwright/test": "^1.49.1",
-    "@react-router/dev": "^7.1.1",
+    "@react-router/dev": "^7.1.2",
     "@tailwindcss/typography": "^0.5.16",
-    "@tanstack/eslint-plugin-query": "^5.62.16",
+    "@tanstack/eslint-plugin-query": "^5.64.2",
     "@testing-library/jest-dom": "^6.6.1",
-    "@testing-library/react": "^16.1.0",
-    "@testing-library/user-event": "^14.5.2",
-    "@types/node": "^22.10.5",
-    "@types/react": "^19.0.4",
-    "@types/react-dom": "^19.0.2",
+    "@testing-library/react": "^16.2.0",
+    "@testing-library/user-event": "^14.6.0",
+    "@types/node": "^22.10.7",
+    "@types/react": "^19.0.7",
+    "@types/react-dom": "^19.0.3",
     "@types/react-highlight": "^0.12.8",
     "@types/react-syntax-highlighter": "^15.5.13",
     "@types/ws": "^8.5.12",
     "@typescript-eslint/eslint-plugin": "^7.18.0",
     "@typescript-eslint/parser": "^7.18.0",
-    "@vitest/coverage-v8": "^1.6.0",
+    "@vitest/coverage-v8": "^3.0.2",
     "autoprefixer": "^10.4.20",
     "cross-env": "^7.0.3",
     "eslint": "^8.57.0",
@@ -100,20 +100,20 @@
     "eslint-config-prettier": "^10.0.1",
     "eslint-plugin-import": "^2.29.1",
     "eslint-plugin-jsx-a11y": "^6.10.2",
-    "eslint-plugin-prettier": "^5.2.1",
+    "eslint-plugin-prettier": "^5.2.3",
     "eslint-plugin-react": "^7.37.4",
     "eslint-plugin-react-hooks": "^4.6.2",
     "husky": "^9.1.6",
     "jsdom": "^26.0.0",
-    "lint-staged": "^15.3.0",
+    "lint-staged": "^15.4.1",
     "msw": "^2.6.6",
-    "postcss": "^8.4.47",
+    "postcss": "^8.5.1",
     "prettier": "^3.4.2",
     "tailwindcss": "^3.4.17",
     "typescript": "^5.7.3",
     "vite-plugin-svgr": "^4.2.0",
     "vite-tsconfig-paths": "^5.1.4",
-    "vitest": "^1.6.0"
+    "vitest": "^3.0.2"
   },
   "packageManager": "npm@10.5.0",
   "volta": {

frontend/src/api/github-axios-instance.ts

@@ -41,6 +41,7 @@ export const isGitHubErrorReponse = <T extends object | Array<unknown>>(
 
 // Axios interceptor to handle token refresh
 const setupAxiosInterceptors = (
+  appMode: string,
   refreshToken: () => Promise<boolean>,
   logout: () => void,
 ) => {
@@ -74,18 +75,21 @@ const setupAxiosInterceptors = (
         !originalRequest._retry // Prevent infinite retry loops
       ) {
         originalRequest._retry = true;
-        try {
-          const refreshed = await refreshToken();
-          if (refreshed) {
-            return await github(originalRequest);
-          }
 
-          logout();
-          return await Promise.reject(new Error("Failed to refresh token"));
-        } catch (refreshError) {
-          // If token refresh fails, evict the user
-          logout();
-          return Promise.reject(refreshError);
+        if (appMode === "saas") {
+          try {
+            const refreshed = await refreshToken();
+            if (refreshed) {
+              return await github(originalRequest);
+            }
+
+            logout();
+            return await Promise.reject(new Error("Failed to refresh token"));
+          } catch (refreshError) {
+            // If token refresh fails, evict the user
+            logout();
+            return Promise.reject(refreshError);
+          }
         }
       }
 

frontend/src/api/open-hands.ts

@@ -10,6 +10,7 @@ import {
   AuthenticateResponse,
   Conversation,
   ResultSet,
+  GetTrajectoryResponse,
 } from "./open-hands.types";
 import { openHands } from "./open-hands-axios";
 import { ApiSettings } from "#/services/settings";
@@ -354,6 +355,15 @@ class OpenHands {
 
     return response.data.items;
   }
+
+  static async getTrajectory(
+    conversationId: string,
+  ): Promise<GetTrajectoryResponse> {
+    const { data } = await openHands.get<GetTrajectoryResponse>(
+      `/api/conversations/${conversationId}/trajectory`,
+    );
+    return data;
+  }
 }
 
 export default OpenHands;

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

@@ -55,6 +55,11 @@ export interface GetVSCodeUrlResponse {
   error?: string;
 }
 
+export interface GetTrajectoryResponse {
+  trajectory: unknown[] | null;
+  error?: string;
+}
+
 export interface AuthenticateResponse {
   message?: string;
   error?: string;

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

@@ -1,8 +1,11 @@
 import { useDispatch, useSelector } from "react-redux";
+import toast from "react-hot-toast";
 import React from "react";
 import posthog from "posthog-js";
+import { useParams } from "react-router";
 import { convertImageToBase64 } from "#/utils/convert-image-to-base-64";
 import { FeedbackActions } from "../feedback/feedback-actions";
+import { ExportActions } from "../export/export-actions";
 import { createChatMessage } from "#/services/chat-service";
 import { InteractiveChatBox } from "./interactive-chat-box";
 import { addUserMessage } from "#/state/chat-slice";
@@ -19,6 +22,8 @@ import { ActionSuggestions } from "./action-suggestions";
 import { ContinueButton } from "#/components/shared/buttons/continue-button";
 import { ScrollToBottomButton } from "#/components/shared/buttons/scroll-to-bottom-button";
 import { LoadingSpinner } from "#/components/shared/loading-spinner";
+import { useGetTrajectory } from "#/hooks/mutation/use-get-trajectory";
+import { downloadTrajectory } from "#/utils/download-files";
 
 function getEntryPoint(
   hasRepository: boolean | null,
@@ -47,6 +52,8 @@ export function ChatInterface() {
   const { selectedRepository, importedProjectZip } = useSelector(
     (state: RootState) => state.initialQuery,
   );
+  const params = useParams();
+  const { mutate: getTrajectory } = useGetTrajectory();
 
   const handleSendMessage = async (content: string, files: File[]) => {
     if (messages.length === 0) {
@@ -90,6 +97,25 @@ export function ChatInterface() {
     setFeedbackPolarity(polarity);
   };
 
+  const onClickExportTrajectoryButton = () => {
+    if (!params.conversationId) {
+      toast.error("ConversationId unknown, cannot download trajectory");
+      return;
+    }
+
+    getTrajectory(params.conversationId, {
+      onSuccess: async (data) => {
+        await downloadTrajectory(
+          params.conversationId ?? "unknown",
+          data.trajectory,
+        );
+      },
+      onError: (error) => {
+        toast.error(error.message);
+      },
+    });
+  };
+
   const isWaitingForUserInput =
     curAgentState === AgentState.AWAITING_USER_INPUT ||
     curAgentState === AgentState.FINISHED;
@@ -137,6 +163,9 @@ export function ChatInterface() {
               onClickShareFeedbackActionButton("negative")
             }
           />
+          <ExportActions
+            onExportTrajectory={() => onClickExportTrajectoryButton()}
+          />
 
           <div className="absolute left-1/2 transform -translate-x-1/2 bottom-0">
             {messages.length > 2 &&

frontend/src/components/features/controls/agent-status-bar.tsx

@@ -5,11 +5,16 @@ import toast from "react-hot-toast";
 import { RootState } from "#/store";
 import { AgentState } from "#/types/agent-state";
 import { AGENT_STATUS_MAP } from "../../agent-status-map.constant";
+import {
+  useWsClient,
+  WsClientProviderStatus,
+} from "#/context/ws-client-provider";
 
 export function AgentStatusBar() {
   const { t, i18n } = useTranslation();
   const { curAgentState } = useSelector((state: RootState) => state.agent);
   const { curStatusMessage } = useSelector((state: RootState) => state.status);
+  const { status } = useWsClient();
 
   const [statusMessage, setStatusMessage] = React.useState<string>("");
 
@@ -37,7 +42,11 @@ export function AgentStatusBar() {
   }, [curStatusMessage.id]);
 
   React.useEffect(() => {
-    setStatusMessage(AGENT_STATUS_MAP[curAgentState].message);
+    if (status === WsClientProviderStatus.DISCONNECTED) {
+      setStatusMessage("Trying to reconnect...");
+    } else {
+      setStatusMessage(AGENT_STATUS_MAP[curAgentState].message);
+    }
   }, [curAgentState]);
 
   return (

frontend/src/components/features/export/export-actions.tsx

@@ -0,0 +1,17 @@
+import ExportIcon from "#/icons/export.svg?react";
+import { ExportActionButton } from "#/components/shared/buttons/export-action-button";
+
+interface ExportActionsProps {
+  onExportTrajectory: () => void;
+}
+
+export function ExportActions({ onExportTrajectory }: ExportActionsProps) {
+  return (
+    <div data-testid="export-actions" className="flex gap-1">
+      <ExportActionButton
+        onClick={onExportTrajectory}
+        icon={<ExportIcon width={15} height={15} />}
+      />
+    </div>
+  );
+}

frontend/src/components/features/sidebar/sidebar.tsx

@@ -13,6 +13,7 @@ import { LoadingSpinner } from "#/components/shared/loading-spinner";
 import { AccountSettingsModal } from "#/components/shared/modals/account-settings/account-settings-modal";
 import { SettingsModal } from "#/components/shared/modals/settings/settings-modal";
 import { useCurrentSettings } from "#/context/settings-context";
+import { useSettings } from "#/hooks/query/use-settings";
 import { ConversationPanel } from "../conversation-panel/conversation-panel";
 import { MULTI_CONVERSATION_UI } from "#/utils/feature-flags";
 import { useEndSession } from "#/hooks/use-end-session";
@@ -27,7 +28,13 @@ export function Sidebar() {
   const user = useGitHubUser();
   const { data: isAuthed } = useIsAuthed();
   const { logout } = useAuth();
-  const { isUpToDate: settingsAreUpToDate, settings } = useCurrentSettings();
+  const {
+    data: settings,
+    isError: settingsIsError,
+    isSuccess: settingsSuccessfulyFetched,
+  } = useSettings();
+
+  const { isUpToDate: settingsAreUpToDate } = useCurrentSettings();
 
   const [accountSettingsModalOpen, setAccountSettingsModalOpen] =
     React.useState(false);
@@ -103,12 +110,13 @@ export function Sidebar() {
       {accountSettingsModalOpen && (
         <AccountSettingsModal onClose={handleAccountSettingsModalClose} />
       )}
-      {showSettingsModal && settings && (
-        <SettingsModal
-          settings={settings}
-          onClose={() => setSettingsModalIsOpen(false)}
-        />
-      )}
+      {settingsIsError ||
+        (showSettingsModal && settingsSuccessfulyFetched && (
+          <SettingsModal
+            settings={settings}
+            onClose={() => setSettingsModalIsOpen(false)}
+          />
+        ))}
     </>
   );
 }

frontend/src/components/shared/buttons/export-action-button.tsx

@@ -0,0 +1,17 @@
+interface ExportActionButtonProps {
+  onClick: () => void;
+  icon: React.ReactNode;
+}
+
+export function ExportActionButton({ onClick, icon }: ExportActionButtonProps) {
+  return (
+    <button
+      type="button"
+      onClick={onClick}
+      className="button-base p-1 hover:bg-neutral-500"
+      title="Export trajectory"
+    >
+      {icon}
+    </button>
+  );
+}

frontend/src/components/shared/modals/account-settings/account-settings-form.tsx

@@ -91,7 +91,7 @@ export function AccountSettingsForm({
             <>
               <CustomInput
                 name="ghToken"
-                label={t(I18nKey.GITHUB$TOKEN_OPTIONAL)}
+                label={t(I18nKey.GITHUB$TOKEN_LABEL)}
                 type="password"
                 defaultValue={gitHubToken ?? ""}
               />

frontend/src/components/shared/modals/settings/runtime-size-selector.tsx

@@ -26,7 +26,10 @@ export function RuntimeSizeSelector({
         id="runtime-size"
         name="runtime-size"
         defaultSelectedKeys={[String(defaultValue || 1)]}
+        selectedKeys={[String(defaultValue || 1)]}
         isDisabled={isDisabled}
+        selectionMode="single"
+        disallowEmptySelection
         aria-label={t(I18nKey.SETTINGS_FORM$RUNTIME_SIZE_LABEL)}
         classNames={{
           trigger: "bg-[#27272A] rounded-md text-sm px-3 py-[10px]",

frontend/src/components/shared/modals/settings/settings-form.tsx

@@ -171,7 +171,7 @@ export function SettingsForm({
 
           <APIKeyInput
             isDisabled={!!disabled}
-            isSet={settings.LLM_API_KEY === "SET"}
+            isSet={settings.LLM_API_KEY === "**********"}
           />
 
           {showAdvancedOptions && (

frontend/src/context/auth-context.tsx

@@ -87,7 +87,12 @@ function AuthProvider({ children }: React.PropsWithChildren) {
 
     setGitHubToken(storedGitHubToken);
     setUserId(userId);
-    setupGithubAxiosInterceptors(refreshToken, logout);
+    const setupIntercepter = async () => {
+      const config = await OpenHands.getConfig();
+      setupGithubAxiosInterceptors(config.APP_MODE, refreshToken, logout);
+    };
+
+    setupIntercepter();
   }, []);
 
   const value = React.useMemo(

frontend/src/context/settings-context.tsx

@@ -34,7 +34,7 @@ export function SettingsProvider({ children }: SettingsProviderProps) {
       ...newSettings,
     };
 
-    if (updatedSettings.LLM_API_KEY === "SET") {
+    if (updatedSettings.LLM_API_KEY === "**********") {
       delete updatedSettings.LLM_API_KEY;
     }
 

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

@@ -81,6 +81,9 @@ export function updateStatusWhenErrorMessagePresent(data: ErrorArg | unknown) {
     !!val && typeof val === "object";
   const isString = (val: unknown): val is string => typeof val === "string";
   if (isObject(data) && "message" in data && isString(data.message)) {
+    if (data.message === "websocket error") {
+      return;
+    }
     let msgId: string | undefined;
     if (
       "data" in data &&

frontend/src/hooks/mutation/use-get-trajectory.ts

@@ -0,0 +1,7 @@
+import { useMutation } from "@tanstack/react-query";
+import OpenHands from "#/api/open-hands";
+
+export const useGetTrajectory = () =>
+  useMutation({
+    mutationFn: (cid: string) => OpenHands.getTrajectory(cid),
+  });

frontend/src/i18n/translation.json

@@ -1259,6 +1259,28 @@
         "no": "Kunne ikke hente modeller og agenter",
         "ja": "モデルとエージェントの取得に失敗しました"
     },
+    "CONFIGURATION$SETTINGS_NOT_FOUND": {
+        "en": "Settings not found. Please check your API key",
+        "es": "Configuraciones no encontradas. Por favor revisa tu API key"
+    },
+    "CONNECT_TO_GITHUB_BY_TOKEN_MODAL$TERMS_OF_SERVICE": {
+        "en": "terms of service",
+        "es": "términos de servicio"
+    },
+    "SESSION$SERVER_CONNECTED_MESSAGE": {
+        "en": "Connected to server",
+        "zh-CN": "已连接到服务器",
+        "de": "Verbindung zum Server hergestellt",
+        "zh-TW": "已連接到伺服器",
+        "es": "Conectado al servidor",
+        "fr": "Connecté au serveur",
+        "it": "Connesso al server",
+        "pt": "Conectado ao servidor",
+        "ko-KR": "서버에 연결됨",
+        "ar": "تم الاتصال بالخادم",
+        "tr": "Sunucuya bağlandı",
+        "no": "Koblet til server"
+    },
     "SESSION$SESSION_HANDLING_ERROR_MESSAGE": {
         "en": "Error handling message",
         "zh-CN": "处理会话时出错",

frontend/src/icons/export.svg

@@ -0,0 +1,5 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 15 16" fill="none">
+  <path
+    d="M11.875 9.5h-2.5V3.25c0-.16576-.0658-.32473-.1831-.44194-.1172-.11721-.276-.18306-.4419-.18306h-2.5c-.16576 0-.32473.06585-.44194.18306C5.68585 2.92527 5.62 3.08424 5.62 3.25V9.5h-2.5c-.13855 0-.27293.0483-.38002.1367-.10708.0883-.18294.2124-.21493.3508-.03199.1385-.01839.2839.03873.4142.05712.1304.15543.2397.27872.3108l4.375 2.5c.09664.0552.20607.0842.3175.0842.11144 0 .22087-.029.3175-.0842l4.375-2.5c.1233-.0711.2216-.1804.2787-.3108.0571-.1303.0707-.2757.0387-.4142-.032-.1384-.1078-.2625-.2149-.3508-.1071-.0884-.2415-.1367-.38-.1367zM3.75 13.375v1.25c0 .1658.06585.3247.18306.4419.11721.1172.27618.1831.44194.1831h6.25c.1657 0 .3247-.0659.4419-.1831.1172-.1172.1831-.2761.1831-.4419v-1.25c0-.1657-.0659-.3247-.1831-.4419-.1172-.1172-.2762-.1831-.4419-.1831h-6.25c-.16576 0-.32473.0659-.44194.1831C3.81585 13.0503 3.75 13.2093 3.75 13.375z"
+    fill="white"/>
+</svg>

frontend/src/routes/_oh.app/hooks/use-ws-status-change.ts

@@ -1,6 +1,5 @@
 import React from "react";
 import { useDispatch, useSelector } from "react-redux";
-import { useAuth } from "#/context/auth-context";
 import {
   useWsClient,
   WsClientProviderStatus,
@@ -14,17 +13,12 @@ import { AgentState } from "#/types/agent-state";
 
 export const useWSStatusChange = () => {
   const { send, status } = useWsClient();
-  const { gitHubToken } = useAuth();
   const { curAgentState } = useSelector((state: RootState) => state.agent);
   const dispatch = useDispatch();
 
   const statusRef = React.useRef<WsClientProviderStatus | null>(null);
 
-  const { selectedRepository } = useSelector(
-    (state: RootState) => state.initialQuery,
-  );
-
-  const { files, importedProjectZip, initialQuery } = useSelector(
+  const { files, initialQuery } = useSelector(
     (state: RootState) => state.initialQuery,
   );
 
@@ -33,30 +27,15 @@ export const useWSStatusChange = () => {
     send(createChatMessage(query, base64Files, timestamp));
   };
 
-  const dispatchInitialQuery = (query: string, additionalInfo: string) => {
-    if (additionalInfo) {
-      sendInitialQuery(`${query}\n\n[${additionalInfo}]`, files);
-    } else {
-      sendInitialQuery(query, files);
-    }
-
+  const dispatchInitialQuery = (query: string) => {
+    sendInitialQuery(query, files);
     dispatch(clearFiles()); // reset selected files
     dispatch(clearInitialQuery()); // reset initial query
   };
 
   const handleAgentInit = () => {
-    let additionalInfo = "";
-
-    if (gitHubToken && selectedRepository) {
-      additionalInfo = `Repository ${selectedRepository} has been cloned to /workspace. Please check the /workspace for files.`;
-    } else if (importedProjectZip) {
-      // if there's an uploaded project zip, add it to the chat
-      additionalInfo =
-        "Files have been uploaded. Please check the /workspace for files.";
-    }
-
     if (initialQuery) {
-      dispatchInitialQuery(initialQuery, additionalInfo);
+      dispatchInitialQuery(initialQuery);
     }
   };
   React.useEffect(() => {

frontend/src/routes/_oh.app/route.tsx

@@ -1,7 +1,7 @@
 import { useDisclosure } from "@nextui-org/react";
 import React from "react";
 import { Outlet } from "react-router";
-import { useDispatch, useSelector } from "react-redux";
+import { useDispatch } from "react-redux";
 import { FaServer } from "react-icons/fa";
 import toast from "react-hot-toast";
 import { useTranslation } from "react-i18next";
@@ -11,7 +11,6 @@ import {
   useConversation,
 } from "#/context/conversation-context";
 import { Controls } from "#/components/features/controls/controls";
-import { RootState } from "#/store";
 import { clearMessages } from "#/state/chat-slice";
 import { clearTerminal } from "#/state/command-slice";
 import { useEffectOnce } from "#/hooks/use-effect-once";
@@ -33,7 +32,6 @@ import {
 import Security from "#/components/shared/modals/security/security";
 import { useEndSession } from "#/hooks/use-end-session";
 import { useUserConversation } from "#/hooks/query/use-user-conversation";
-import { CountBadge } from "#/components/layout/count-badge";
 import { ServedAppLabel } from "#/components/layout/served-app-label";
 import { TerminalStatusLabel } from "#/components/features/terminal/terminal-status-label";
 import { useSettings } from "#/hooks/query/use-settings";
@@ -52,7 +50,6 @@ function AppContent() {
   const endSession = useEndSession();
 
   const [width, setWidth] = React.useState(window.innerWidth);
-  const { updateCount } = useSelector((state: RootState) => state.browser);
 
   const secrets = React.useMemo(
     () => [gitHubToken].filter((secret) => secret !== null),
@@ -144,7 +141,6 @@ function AppContent() {
                     label: (
                       <div className="flex items-center gap-1">
                         {t(I18nKey.BROWSER$TITLE)}
-                        {updateCount > 0 && <CountBadge count={updateCount} />}
                       </div>
                     ),
                     to: "browser",

frontend/src/state/browser-slice.ts

@@ -5,8 +5,6 @@ export const initialState = {
   url: "https://github.com/All-Hands-AI/OpenHands",
   // Base64-encoded screenshot of browser window (placeholder for now, will be replaced with the actual screenshot later)
   screenshotSrc: "",
-  // Counter for browser updates
-  updateCount: 0,
 };
 
 export const browserSlice = createSlice({
@@ -18,7 +16,6 @@ export const browserSlice = createSlice({
     },
     setScreenshotSrc: (state, action) => {
       state.screenshotSrc = action.payload;
-      state.updateCount += 1;
     },
   },
 });

frontend/src/types/file-system.d.ts

@@ -26,6 +26,18 @@ interface FileSystemDirectoryHandle {
   ): Promise<FileSystemFileHandle>;
 }
 
+interface SaveFilePickerOptions {
+  suggestedName?: string;
+  types?: Array<{
+    description?: string;
+    accept: Record<string, string[]>;
+  }>;
+  excludeAcceptAllOption?: boolean;
+}
+
 interface Window {
   showDirectoryPicker(): Promise<FileSystemDirectoryHandle>;
+  showSaveFilePicker(
+    options?: SaveFilePickerOptions,
+  ): Promise<FileSystemFileHandle>;
 }

frontend/src/utils/download-files.ts

@@ -22,6 +22,13 @@ function isFileSystemAccessSupported(): boolean {
   return "showDirectoryPicker" in window;
 }
 
+/**
+ * Checks if the Save File Picker API is supported
+ */
+function isSaveFilePickerSupported(): boolean {
+  return "showSaveFilePicker" in window;
+}
+
 /**
  * Creates subdirectories and returns the final directory handle
  */
@@ -162,6 +169,39 @@ async function processBatch(
   };
 }
 
+export async function downloadTrajectory(
+  conversationId: string,
+  data: unknown[] | null,
+): Promise<void> {
+  try {
+    if (!isSaveFilePickerSupported()) {
+      throw new Error(
+        "Your browser doesn't support downloading folders. Please use Chrome, Edge, or another browser that supports the File System Access API.",
+      );
+    }
+    const options = {
+      suggestedName: `trajectory-${conversationId}.json`,
+      types: [
+        {
+          description: "JSON File",
+          accept: {
+            "application/json": [".json"],
+          },
+        },
+      ],
+    };
+
+    const handle = await window.showSaveFilePicker(options);
+    const writable = await handle.createWritable();
+    await writable.write(JSON.stringify(data, null, 2));
+    await writable.close();
+  } catch (error) {
+    throw new Error(
+      `Failed to download file: ${error instanceof Error ? error.message : String(error)}`,
+    );
+  }
+}
+
 /**
  * Downloads files from the workspace one by one
  * @param initialPath Initial path to start downloading from. If not provided, downloads from root

frontend/vitest.setup.ts

@@ -3,10 +3,7 @@ import { cleanup } from "@testing-library/react";
 import { server } from "#/mocks/node";
 import "@testing-library/jest-dom/vitest";
 
-// @ts-expect-error - Mock for Terminal tests
 HTMLCanvasElement.prototype.getContext = vi.fn();
-
-// @ts-expect-error - handle TypeError: dom.scrollTo is not a function
 HTMLElement.prototype.scrollTo = vi.fn();
 
 // Mock the i18n provider

microagents/tasks/add_openhands_repo_instruction.md

@@ -0,0 +1,65 @@
+---
+name: add_openhands_repo_instruction
+type: task
+version: 1.0.0
+author: openhands
+agent: CodeActAgent
+inputs:
+  - name: REPO_FOLDER_NAME
+    description: "Branch for the agent to work on"
+    required: false
+---
+
+Please browse the current repository under /workspace/{{ REPO_FOLDER_NAME }}, look at the documentation and relevant code, and understand the purpose of this repository.
+
+Specifically, I want you to create a `.openhands/microagents/repo.md`  file. This file should contain succinct information that summarizes (1) the purpose of this repository, (2) the general setup of this repo, and (3) a brief description of the structure of this repo.
+
+Here's an example:
+```markdown
+---
+name: repo
+type: repo
+agent: CodeActAgent
+---
+
+This repository contains the code for runtime-API, an automated AI software engineer. It has a Python backend
+(in the `openhands` directory) and React frontend (in the `frontend` directory).
+
+## General Setup:
+To set up the entire repo, including frontend and backend, run `make build`.
+You don't need to do this unless the user asks you to, or if you're trying to run the entire application.
+
+Before pushing any changes, you should ensure that any lint errors or simple test errors have been fixed.
+
+* If you've made changes to the backend, you should run `pre-commit run --all-files --config ./dev_config/python/.pre-commit-config.yaml`
+* If you've made changes to the frontend, you should run `cd frontend && npm run lint:fix && npm run build ; cd ..`
+
+If either command fails, it may have automatically fixed some issues. You should fix any issues that weren't automatically fixed,
+then re-run the command to ensure it passes.
+
+## Repository Structure
+Backend:
+- Located in the `openhands` directory
+- Testing:
+  - All tests are in `tests/unit/test_*.py`
+  - To test new code, run `poetry run pytest tests/unit/test_xxx.py` where `xxx` is the appropriate file for the current functionality
+  - Write all tests with pytest
+
+Frontend:
+- Located in the `frontend` directory
+- Prerequisites: A recent version of NodeJS / NPM
+- Setup: Run `npm install` in the frontend directory
+- Testing:
+  - Run tests: `npm run test`
+  - To run specific tests: `npm run test -- -t "TestName"`
+- Building:
+  - Build for production: `npm run build`
+- Environment Variables:
+  - Set in `frontend/.env` or as environment variables
+  - Available variables: VITE_BACKEND_HOST, VITE_USE_TLS, VITE_INSECURE_SKIP_VERIFY, VITE_FRONTEND_PORT
+- Internationalization:
+  - Generate i18n declaration file: `npm run make-i18n`
+```
+
+Now, please write a similar markdown for the current repository.
+Read all the GitHub workflows under .github/ of the repository (if this folder exists) to understand the CI checks (e.g., linter, pre-commit), and include those in the repo.md file.

openhands/agenthub/codeact_agent/codeact_agent.py

@@ -111,7 +111,7 @@ class CodeActAgent(Agent):
                 os.path.dirname(os.path.dirname(openhands.__file__)),
                 'microagents',
             )
-            if self.config.use_microagents
+            if self.config.enable_prompt_extensions
             else None,
             prompt_dir=os.path.join(os.path.dirname(__file__), 'prompts'),
             disabled_microagents=self.config.disabled_microagents,
@@ -277,16 +277,11 @@ class CodeActAgent(Agent):
             # if it doesn't have tool call metadata, it was triggered by a user action
             if obs.tool_call_metadata is None:
                 text = truncate_content(
-                    f'\nObserved result of command executed by user:\n{obs.content}',
+                    f'\nObserved result of command executed by user:\n{obs.to_agent_observation()}',
                     max_message_chars,
                 )
             else:
-                text = truncate_content(
-                    obs.content
-                    + f'\n[Python Interpreter: {obs.metadata.py_interpreter_path}]',
-                    max_message_chars,
-                )
-            text += f'\n[Command finished with exit code {obs.exit_code}]'
+                text = truncate_content(obs.to_agent_observation(), max_message_chars)
             message = Message(role='user', content=[TextContent(text=text)])
         elif isinstance(obs, IPythonRunCellObservation):
             text = obs.content
@@ -448,6 +443,17 @@ class CodeActAgent(Agent):
                 )
             )
 
+        # Repository and runtime info
+        additional_info = self.prompt_manager.get_additional_info()
+        if self.config.enable_prompt_extensions and additional_info:
+            # only add these if prompt extension is enabled
+            messages.append(
+                Message(
+                    role='user',
+                    content=[TextContent(text=additional_info)],
+                )
+            )
+
         pending_tool_call_action_messages: dict[str, Message] = {}
         tool_call_id_to_message: dict[str, Message] = {}
 

openhands/agenthub/codeact_agent/function_calling.py

@@ -31,7 +31,7 @@ from openhands.events.tool import ToolCallMetadata
 
 _BASH_DESCRIPTION = """Execute a bash command in the terminal.
 * Long running commands: For commands that may run indefinitely, it should be run in the background and the output should be redirected to a file, e.g. command = `python3 app.py > server.log 2>&1 &`.
-* Interactive: If a bash command returns exit code `-1`, this means the process is not yet finished. The assistant must then send a second call to terminal with an empty `command` (which will retrieve any additional logs), or it can send additional text (set `command` to the text) to STDIN of the running process, or it can send command like `C-c` (Ctrl+C) to interrupt the process.
+* Interact with running process: If a bash command returns exit code `-1`, this means the process is not yet finished. By setting `is_input` to `true`, the assistant can interact with the running process and send empty `command` to retrieve any additional logs, or send additional text (set `command` to the text) to STDIN of the running process, or send command like `C-c` (Ctrl+C), `C-d` (Ctrl+D), `C-z` (Ctrl+Z) to interrupt the process.
 """
 
 CmdRunTool = ChatCompletionToolParam(
@@ -46,6 +46,11 @@ CmdRunTool = ChatCompletionToolParam(
                     'type': 'string',
                     'description': 'The bash command to execute. Can be empty string to view additional logs when previous exit code is `-1`. Can be `C-c` (Ctrl+C) to interrupt the currently running process.',
                 },
+                'is_input': {
+                    'type': 'string',
+                    'description': 'If True, the command is an input to the running process. If False, the command is a bash command to be executed in the terminal. Default is False.',
+                    'enum': ['true', 'false'],
+                },
             },
             'required': ['command'],
         },
@@ -488,6 +493,12 @@ def response_to_actions(response: ModelResponse) -> list[Action]:
                     f'Failed to parse tool call arguments: {tool_call.function.arguments}'
                 ) from e
             if tool_call.function.name == 'execute_bash':
+                # this is an LLM error: add empty command to avoid breaking the tool call
+                if 'command' not in arguments:
+                    arguments['command'] = ''
+                # convert is_input to boolean
+                if 'is_input' in arguments:
+                    arguments['is_input'] = arguments['is_input'] == 'true'
                 action = CmdRunAction(**arguments)
             elif tool_call.function.name == 'execute_ipython_cell':
                 action = IPythonRunCellAction(**arguments)

openhands/agenthub/codeact_agent/prompts/system_prompt.j2

@@ -1,23 +1,7 @@
 You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.
 <IMPORTANT>
 * If user provides a path, you should NOT assume it's relative to the current working directory. Instead, you should explore the file system to find the file before working on it.
+* You should start exploring the file system with your view command, unless you need to explore more deeply.
 * When configuring git credentials, use "openhands" as the user.name and "openhands@all-hands.dev" as the user.email by default, unless explicitly instructed otherwise.
-* The assistant MUST NOT include comments in the code unless they are necessary to describe non-obvious behavior.
-{{ runtime_info }}
+* You MUST NOT include comments in the code unless they are necessary to describe non-obvious behavior.
 </IMPORTANT>
-{% if repo_instructions -%}
-<REPOSITORY_INSTRUCTIONS>
-{{ repo_instructions }}
-</REPOSITORY_INSTRUCTIONS>
-{% endif %}
-{% if runtime_info and runtime_info.available_hosts -%}
-<RUNTIME_INFORMATION>
-The user has access to the following hosts for accessing a web application,
-each of which has a corresponding port:
-{% for host, port in runtime_info.available_hosts.items() -%}
-* {{ host }} (port {{ port }})
-{% endfor %}
-When starting a web server, use the corresponding ports. You should also
-set any options to allow iframes and CORS requests.
-</RUNTIME_INFORMATION>
-{% endif %}

openhands/agenthub/micro/agent.py

@@ -50,6 +50,10 @@ class MicroAgent(Agent):
         # history is in reverse order, let's fix it
         processed_history.reverse()
 
+        # everything starts with a message
+        # the first message is already in the prompt as the task
+        # TODO: so we don't need to include it in the history
+
         return json.dumps(processed_history, **kwargs)
 
     def __init__(self, llm: LLM, config: AgentConfig):

openhands/controller/agent_controller.py

@@ -12,6 +12,7 @@ from litellm.exceptions import (
 )
 
 from openhands.controller.agent import Agent
+from openhands.controller.replay import ReplayManager
 from openhands.controller.state.state import State, TrafficControlState
 from openhands.controller.stuck import StuckDetector
 from openhands.core.config import AgentConfig, LLMConfig
@@ -90,6 +91,7 @@ class AgentController:
         is_delegate: bool = False,
         headless_mode: bool = True,
         status_callback: Callable | None = None,
+        replay_events: list[Event] | None = None,
     ):
         """Initializes a new instance of the AgentController class.
 
@@ -108,16 +110,21 @@ class AgentController:
             is_delegate: Whether this controller is a delegate.
             headless_mode: Whether the agent is run in headless mode.
             status_callback: Optional callback function to handle status updates.
+            replay_events: A list of logs to replay.
         """
         self.id = sid
         self.agent = agent
         self.headless_mode = headless_mode
+        self.is_delegate = is_delegate
 
-        # subscribe to the event stream
+        # the event stream must be set before maybe subscribing to it
         self.event_stream = event_stream
-        self.event_stream.subscribe(
-            EventStreamSubscriber.AGENT_CONTROLLER, self.on_event, self.id
-        )
+
+        # subscribe to the event stream if this is not a delegate
+        if not self.is_delegate:
+            self.event_stream.subscribe(
+                EventStreamSubscriber.AGENT_CONTROLLER, self.on_event, self.id
+            )
 
         # state from the previous session, state from a parent agent, or a fresh state
         self.set_initial_state(
@@ -135,6 +142,9 @@ class AgentController:
         self._stuck_detector = StuckDetector(self.state)
         self.status_callback = status_callback
 
+        # replay-related
+        self._replay_manager = ReplayManager(replay_events)
+
     async def close(self) -> None:
         """Closes the agent controller, canceling any ongoing tasks and unsubscribing from the event stream.
 
@@ -165,7 +175,11 @@ class AgentController:
         )
 
         # unsubscribe from the event stream
-        self.event_stream.unsubscribe(EventStreamSubscriber.AGENT_CONTROLLER, self.id)
+        # only the root parent controller subscribes to the event stream
+        if not self.is_delegate:
+            self.event_stream.unsubscribe(
+                EventStreamSubscriber.AGENT_CONTROLLER, self.id
+            )
         self._closed = True
 
     def log(self, level: str, message: str, extra: dict | None = None) -> None:
@@ -226,9 +240,26 @@ class AgentController:
             await self._react_to_exception(reported)
 
     def should_step(self, event: Event) -> bool:
+        """
+        Whether the agent should take a step based on an event. In general,
+        the agent should take a step if it receives a message from the user,
+        or observes something in the environment (after acting).
+        """
+        # it might be the delegate's day in the sun
+        if self.delegate is not None:
+            return False
+
         if isinstance(event, Action):
             if isinstance(event, MessageAction) and event.source == EventSource.USER:
                 return True
+            if (
+                isinstance(event, MessageAction)
+                and self.get_agent_state() != AgentState.AWAITING_USER_INPUT
+            ):
+                # TODO: this is fragile, but how else to check if eligible?
+                return True
+            if isinstance(event, AgentDelegateAction):
+                return True
             return False
         if isinstance(event, Observation):
             if isinstance(event, NullObservation) or isinstance(
@@ -244,12 +275,35 @@ class AgentController:
         Args:
             event (Event): The incoming event to process.
         """
+
+        # If we have a delegate that is not finished or errored, forward events to it
+        if self.delegate is not None:
+            delegate_state = self.delegate.get_agent_state()
+            if delegate_state not in (
+                AgentState.FINISHED,
+                AgentState.ERROR,
+                AgentState.REJECTED,
+            ):
+                # Forward the event to delegate and skip parent processing
+                asyncio.get_event_loop().run_until_complete(
+                    self.delegate._on_event(event)
+                )
+                return
+            else:
+                # delegate is done or errored, so end it
+                self.end_delegate()
+                return
+
+        # continue parent processing only if there's no active delegate
         asyncio.get_event_loop().run_until_complete(self._on_event(event))
 
     async def _on_event(self, event: Event) -> None:
         if hasattr(event, 'hidden') and event.hidden:
             return
 
+        # Give others a little chance
+        await asyncio.sleep(0.01)
+
         # if the event is not filtered out, add it to the history
         if not any(isinstance(event, filter_type) for filter_type in self.filter_out):
             self.state.history.append(event)
@@ -263,17 +317,22 @@ class AgentController:
             self.step()
 
     async def _handle_action(self, action: Action) -> None:
-        """Handles actions from the event stream.
-
-        Args:
-            action (Action): The action to handle.
-        """
+        """Handles an Action from the agent or delegate."""
         if isinstance(action, ChangeAgentStateAction):
             await self.set_agent_state_to(action.agent_state)  # type: ignore
         elif isinstance(action, MessageAction):
             await self._handle_message_action(action)
         elif isinstance(action, AgentDelegateAction):
             await self.start_delegate(action)
+            assert self.delegate is not None
+            # Post a MessageAction with the task for the delegate
+            if 'task' in action.inputs:
+                self.event_stream.add_event(
+                    MessageAction(content='TASK: ' + action.inputs['task']),
+                    EventSource.USER,
+                )
+                await self.delegate.set_agent_state_to(AgentState.RUNNING)
+            return
 
         elif isinstance(action, AgentFinishAction):
             self.state.outputs = action.outputs
@@ -491,7 +550,7 @@ class AgentController:
             f'start delegate, creating agent {delegate_agent.name} using LLM {llm}',
         )
 
-        self.event_stream.unsubscribe(EventStreamSubscriber.AGENT_CONTROLLER, self.id)
+        # Create the delegate with is_delegate=True so it does NOT subscribe directly
         self.delegate = AgentController(
             sid=self.id + '-delegate',
             agent=delegate_agent,
@@ -504,7 +563,57 @@ class AgentController:
             is_delegate=True,
             headless_mode=self.headless_mode,
         )
-        await self.delegate.set_agent_state_to(AgentState.RUNNING)
+
+    def end_delegate(self) -> None:
+        """Ends the currently active delegate (e.g., if it is finished or errored)
+        so that this controller can resume normal operation.
+        """
+        if self.delegate is None:
+            return
+
+        delegate_state = self.delegate.get_agent_state()
+
+        # update iteration that is shared across agents
+        self.state.iteration = self.delegate.state.iteration
+
+        # close the delegate controller before adding new events
+        asyncio.get_event_loop().run_until_complete(self.delegate.close())
+
+        if delegate_state in (AgentState.FINISHED, AgentState.REJECTED):
+            # retrieve delegate result
+            delegate_outputs = (
+                self.delegate.state.outputs if self.delegate.state else {}
+            )
+
+            # prepare delegate result observation
+            # TODO: replace this with AI-generated summary (#2395)
+            formatted_output = ', '.join(
+                f'{key}: {value}' for key, value in delegate_outputs.items()
+            )
+            content = (
+                f'{self.delegate.agent.name} finishes task with {formatted_output}'
+            )
+
+            # emit the delegate result observation
+            obs = AgentDelegateObservation(outputs=delegate_outputs, content=content)
+            self.event_stream.add_event(obs, EventSource.AGENT)
+        else:
+            # delegate state is ERROR
+            # emit AgentDelegateObservation with error content
+            delegate_outputs = (
+                self.delegate.state.outputs if self.delegate.state else {}
+            )
+            content = (
+                f'{self.delegate.agent.name} encountered an error during execution.'
+            )
+
+            # emit the delegate result observation
+            obs = AgentDelegateObservation(outputs=delegate_outputs, content=content)
+            self.event_stream.add_event(obs, EventSource.AGENT)
+
+        # unset delegate so parent can resume normal handling
+        self.delegate = None
+        self.delegateAction = None
 
     async def _step(self) -> None:
         """Executes a single step of the parent or delegate agent. Detects stuck agents and limits on the number of iterations and the task budget."""
@@ -514,14 +623,6 @@ class AgentController:
         if self._pending_action:
             return
 
-        if self.delegate is not None:
-            assert self.delegate != self
-            # TODO this conditional will always be false, because the parent controllers are unsubscribed
-            # remove if it's still useless when delegation is reworked
-            if self.delegate.get_agent_state() != AgentState.PAUSED:
-                await self._delegate_step()
-            return
-
         self.log(
             'info',
             f'LEVEL {self.state.delegate_level} LOCAL STEP {self.state.local_iteration} GLOBAL STEP {self.state.iteration}',
@@ -551,42 +652,50 @@ class AgentController:
 
         self.update_state_before_step()
         action: Action = NullAction()
-        try:
-            action = self.agent.step(self.state)
-            if action is None:
-                raise LLMNoActionError('No action was returned')
-        except (
-            LLMMalformedActionError,
-            LLMNoActionError,
-            LLMResponseError,
-            FunctionCallValidationError,
-            FunctionCallNotExistsError,
-        ) as e:
-            self.event_stream.add_event(
-                ErrorObservation(
-                    content=str(e),
-                ),
-                EventSource.AGENT,
-            )
-            return
-        except (ContextWindowExceededError, BadRequestError) as e:
-            # FIXME: this is a hack until a litellm fix is confirmed
-            # Check if this is a nested context window error
-            error_str = str(e).lower()
-            if (
-                'contextwindowexceedederror' in error_str
-                or 'prompt is too long' in error_str
-                or isinstance(e, ContextWindowExceededError)
-            ):
-                # When context window is exceeded, keep roughly half of agent interactions
-                self.state.history = self._apply_conversation_window(self.state.history)
 
-                # Save the ID of the first event in our truncated history for future reloading
-                if self.state.history:
-                    self.state.start_id = self.state.history[0].id
-                # Don't add error event - let the agent retry with reduced context
+        if self._replay_manager.should_replay():
+            # in replay mode, we don't let the agent to proceed
+            # instead, we replay the action from the replay trajectory
+            action = self._replay_manager.step()
+        else:
+            try:
+                action = self.agent.step(self.state)
+                if action is None:
+                    raise LLMNoActionError('No action was returned')
+            except (
+                LLMMalformedActionError,
+                LLMNoActionError,
+                LLMResponseError,
+                FunctionCallValidationError,
+                FunctionCallNotExistsError,
+            ) as e:
+                self.event_stream.add_event(
+                    ErrorObservation(
+                        content=str(e),
+                    ),
+                    EventSource.AGENT,
+                )
                 return
-            raise
+            except (ContextWindowExceededError, BadRequestError) as e:
+                # FIXME: this is a hack until a litellm fix is confirmed
+                # Check if this is a nested context window error
+                error_str = str(e).lower()
+                if (
+                    'contextwindowexceedederror' in error_str
+                    or 'prompt is too long' in error_str
+                    or isinstance(e, ContextWindowExceededError)
+                ):
+                    # When context window is exceeded, keep roughly half of agent interactions
+                    self.state.history = self._apply_conversation_window(
+                        self.state.history
+                    )
+
+                    # Save the ID of the first event in our truncated history for future reloading
+                    if self.state.history:
+                        self.state.start_id = self.state.history[0].id
+                    # Don't add error event - let the agent retry with reduced context
+                    return
+                raise
 
         if action.runnable:
             if self.state.confirmation_mode and (
@@ -611,68 +720,6 @@ class AgentController:
         log_level = 'info' if LOG_ALL_EVENTS else 'debug'
         self.log(log_level, str(action), extra={'msg_type': 'ACTION'})
 
-    async def _delegate_step(self) -> None:
-        """Executes a single step of the delegate agent."""
-        await self.delegate._step()  # type: ignore[union-attr]
-        assert self.delegate is not None
-        delegate_state = self.delegate.get_agent_state()
-        self.log('debug', f'Delegate state: {delegate_state}')
-        if delegate_state == AgentState.ERROR:
-            # update iteration that shall be shared across agents
-            self.state.iteration = self.delegate.state.iteration
-
-            # emit AgentDelegateObservation to mark delegate termination due to error
-            delegate_outputs = (
-                self.delegate.state.outputs if self.delegate.state else {}
-            )
-            content = (
-                f'{self.delegate.agent.name} encountered an error during execution.'
-            )
-            obs = AgentDelegateObservation(outputs=delegate_outputs, content=content)
-            self.event_stream.add_event(obs, EventSource.AGENT)
-
-            # close the delegate upon error
-            await self.delegate.close()
-
-            # resubscribe parent when delegate is finished
-            self.event_stream.subscribe(
-                EventStreamSubscriber.AGENT_CONTROLLER, self.on_event, self.id
-            )
-            self.delegate = None
-            self.delegateAction = None
-
-        elif delegate_state in (AgentState.FINISHED, AgentState.REJECTED):
-            self.log('debug', 'Delegate agent has finished execution')
-            # retrieve delegate result
-            outputs = self.delegate.state.outputs if self.delegate.state else {}
-
-            # update iteration that shall be shared across agents
-            self.state.iteration = self.delegate.state.iteration
-
-            # close delegate controller: we must close the delegate controller before adding new events
-            await self.delegate.close()
-
-            # resubscribe parent when delegate is finished
-            self.event_stream.subscribe(
-                EventStreamSubscriber.AGENT_CONTROLLER, self.on_event, self.id
-            )
-
-            # update delegate result observation
-            # TODO: replace this with AI-generated summary (#2395)
-            formatted_output = ', '.join(
-                f'{key}: {value}' for key, value in outputs.items()
-            )
-            content = (
-                f'{self.delegate.agent.name} finishes task with {formatted_output}'
-            )
-            obs = AgentDelegateObservation(outputs=outputs, content=content)
-
-            # clean up delegate status
-            self.delegate = None
-            self.delegateAction = None
-            self.event_stream.add_event(obs, EventSource.AGENT)
-        return
-
     async def _handle_traffic_control(
         self, limit_type: str, current_value: float, max_value: float
     ) -> bool:

openhands/controller/replay.py

@@ -0,0 +1,52 @@
+from openhands.core.logger import openhands_logger as logger
+from openhands.events.action.action import Action
+from openhands.events.event import Event, EventSource
+
+
+class ReplayManager:
+    """ReplayManager manages the lifecycle of a replay session of a given trajectory.
+
+    Replay manager keeps track of a list of events, replays actions, and ignore
+    messages and observations. It could lead to unexpected or even errorneous
+    results if any action is non-deterministic, or if the initial state before
+    the replay session is different from the initial state of the trajectory.
+    """
+
+    def __init__(self, replay_events: list[Event] | None):
+        if replay_events:
+            logger.info(f'Replay logs loaded, events length = {len(replay_events)}')
+        self.replay_events = replay_events
+        self.replay_mode = bool(replay_events)
+        self.replay_index = 0
+
+    def _replayable(self) -> bool:
+        return (
+            self.replay_events is not None
+            and self.replay_index < len(self.replay_events)
+            and isinstance(self.replay_events[self.replay_index], Action)
+            and self.replay_events[self.replay_index].source != EventSource.USER
+        )
+
+    def should_replay(self) -> bool:
+        """
+        Whether the controller is in trajectory replay mode, and the replay
+        hasn't finished. Note: after the replay is finished, the user and
+        the agent could continue to message/act.
+
+        This method also moves "replay_index" to the next action, if applicable.
+        """
+        if not self.replay_mode:
+            return False
+
+        assert self.replay_events is not None
+        while self.replay_index < len(self.replay_events) and not self._replayable():
+            self.replay_index += 1
+
+        return self._replayable()
+
+    def step(self) -> Action:
+        assert self.replay_events is not None
+        event = self.replay_events[self.replay_index]
+        assert isinstance(event, Action)
+        self.replay_index += 1
+        return event

openhands/core/config/README.md

@@ -37,21 +37,17 @@ export SANDBOX_TIMEOUT='300'
 
 ## Type Handling
 
-The `load_from_env` function attempts to cast environment variable values to the types specified in the dataclasses. It handles:
+The `load_from_env` function attempts to cast environment variable values to the types specified in the models. It handles:
 
 - Basic types (str, int, bool)
 - Optional types (e.g., `str | None`)
-- Nested dataclasses
+- Nested models
 
 If type casting fails, an error is logged, and the default value is retained.
 
 ## Default Values
 
-If an environment variable is not set, the default value specified in the dataclass is used.
-
-## Nested Configurations
-
-The `AppConfig` class contains nested configurations like `LLMConfig` and `AgentConfig`. The `load_from_env` function handles these by recursively processing nested dataclasses with updated prefixes.
+If an environment variable is not set, the default value specified in the model is used.
 
 ## Security Considerations
 

openhands/core/config/agent_config.py

@@ -1,11 +1,9 @@
-from dataclasses import dataclass, field, fields
+from pydantic import BaseModel, Field
 
 from openhands.core.config.condenser_config import CondenserConfig, NoOpCondenserConfig
-from openhands.core.config.config_utils import get_field_info
 
 
-@dataclass
-class AgentConfig:
+class AgentConfig(BaseModel):
     """Configuration for the agent.
 
     Attributes:
@@ -17,25 +15,18 @@ class AgentConfig:
         memory_enabled: Whether long-term memory (embeddings) is enabled.
         memory_max_threads: The maximum number of threads indexing at the same time for embeddings.
         llm_config: The name of the llm config to use. If specified, this will override global llm config.
-        use_microagents: Whether to use microagents at all. Default is True.
+        enable_prompt_extensions: Whether to use prompt extensions (e.g., microagents, inject runtime info). Default is True.
         disabled_microagents: A list of microagents to disable. Default is None.
         condenser: Configuration for the memory condenser. Default is NoOpCondenserConfig.
     """
 
-    codeact_enable_browsing: bool = True
-    codeact_enable_llm_editor: bool = False
-    codeact_enable_jupyter: bool = True
-    micro_agent_name: str | None = None
-    memory_enabled: bool = False
-    memory_max_threads: int = 3
-    llm_config: str | None = None
-    use_microagents: bool = True
-    disabled_microagents: list[str] | None = None
-    condenser: CondenserConfig = field(default_factory=NoOpCondenserConfig)  # type: ignore
-
-    def defaults_to_dict(self) -> dict:
-        """Serialize fields to a dict for the frontend, including type hints, defaults, and whether it's optional."""
-        result = {}
-        for f in fields(self):
-            result[f.name] = get_field_info(f)
-        return result
+    codeact_enable_browsing: bool = Field(default=True)
+    codeact_enable_llm_editor: bool = Field(default=False)
+    codeact_enable_jupyter: bool = Field(default=True)
+    micro_agent_name: str | None = Field(default=None)
+    memory_enabled: bool = Field(default=False)
+    memory_max_threads: int = Field(default=3)
+    llm_config: str | None = Field(default=None)
+    enable_prompt_extensions: bool = Field(default=True)
+    disabled_microagents: list[str] | None = Field(default=None)
+    condenser: CondenserConfig = Field(default_factory=NoOpCondenserConfig)

openhands/core/config/app_config.py

@@ -1,20 +1,20 @@
-from dataclasses import dataclass, field, fields, is_dataclass
 from typing import ClassVar
 
+from pydantic import BaseModel, Field, SecretStr
+
 from openhands.core import logger
 from openhands.core.config.agent_config import AgentConfig
 from openhands.core.config.config_utils import (
     OH_DEFAULT_AGENT,
     OH_MAX_ITERATIONS,
-    get_field_info,
+    model_defaults_to_dict,
 )
 from openhands.core.config.llm_config import LLMConfig
 from openhands.core.config.sandbox_config import SandboxConfig
 from openhands.core.config.security_config import SecurityConfig
 
 
-@dataclass
-class AppConfig:
+class AppConfig(BaseModel):
     """Configuration for the app.
 
     Attributes:
@@ -28,6 +28,7 @@ class AppConfig:
         file_store: Type of file store to use.
         file_store_path: Path to the file store.
         save_trajectory_path: Either a folder path to store trajectories with auto-generated filenames, or a designated trajectory file path.
+        replay_trajectory_path: Path to load trajectory and replay. If provided, trajectory would be replayed first before user's instruction.
         workspace_base: Base path for the workspace. Defaults to `./workspace` as absolute path.
         workspace_mount_path: Path to mount the workspace. Defaults to `workspace_base`.
         workspace_mount_path_in_sandbox: Path to mount the workspace in sandbox. Defaults to `/workspace`.
@@ -46,37 +47,40 @@ class AppConfig:
             input is read line by line. When enabled, input continues until /exit command.
     """
 
-    llms: dict[str, LLMConfig] = field(default_factory=dict)
-    agents: dict = field(default_factory=dict)
-    default_agent: str = OH_DEFAULT_AGENT
-    sandbox: SandboxConfig = field(default_factory=SandboxConfig)
-    security: SecurityConfig = field(default_factory=SecurityConfig)
-    runtime: str = 'docker'
-    file_store: str = 'local'
-    file_store_path: str = '/tmp/openhands_file_store'
-    save_trajectory_path: str | None = None
-    workspace_base: str | None = None
-    workspace_mount_path: str | None = None
-    workspace_mount_path_in_sandbox: str = '/workspace'
-    workspace_mount_rewrite: str | None = None
-    cache_dir: str = '/tmp/cache'
-    run_as_openhands: bool = True
-    max_iterations: int = OH_MAX_ITERATIONS
-    max_budget_per_task: float | None = None
-    e2b_api_key: str = ''
-    modal_api_token_id: str = ''
-    modal_api_token_secret: str = ''
-    disable_color: bool = False
-    jwt_secret: str = ''
-    debug: bool = False
-    file_uploads_max_file_size_mb: int = 0
-    file_uploads_restrict_file_types: bool = False
-    file_uploads_allowed_extensions: list[str] = field(default_factory=lambda: ['.*'])
-    runloop_api_key: str | None = None
-    cli_multiline_input: bool = False
+    llms: dict[str, LLMConfig] = Field(default_factory=dict)
+    agents: dict = Field(default_factory=dict)
+    default_agent: str = Field(default=OH_DEFAULT_AGENT)
+    sandbox: SandboxConfig = Field(default_factory=SandboxConfig)
+    security: SecurityConfig = Field(default_factory=SecurityConfig)
+    runtime: str = Field(default='docker')
+    file_store: str = Field(default='local')
+    file_store_path: str = Field(default='/tmp/openhands_file_store')
+    save_trajectory_path: str | None = Field(default=None)
+    replay_trajectory_path: str | None = Field(default=None)
+    workspace_base: str | None = Field(default=None)
+    workspace_mount_path: str | None = Field(default=None)
+    workspace_mount_path_in_sandbox: str = Field(default='/workspace')
+    workspace_mount_rewrite: str | None = Field(default=None)
+    cache_dir: str = Field(default='/tmp/cache')
+    run_as_openhands: bool = Field(default=True)
+    max_iterations: int = Field(default=OH_MAX_ITERATIONS)
+    max_budget_per_task: float | None = Field(default=None)
+    e2b_api_key: SecretStr | None = Field(default=None)
+    modal_api_token_id: SecretStr | None = Field(default=None)
+    modal_api_token_secret: SecretStr | None = Field(default=None)
+    disable_color: bool = Field(default=False)
+    jwt_secret: SecretStr | None = Field(default=None)
+    debug: bool = Field(default=False)
+    file_uploads_max_file_size_mb: int = Field(default=0)
+    file_uploads_restrict_file_types: bool = Field(default=False)
+    file_uploads_allowed_extensions: list[str] = Field(default_factory=lambda: ['.*'])
+    runloop_api_key: SecretStr | None = Field(default=None)
+    cli_multiline_input: bool = Field(default=False)
 
     defaults_dict: ClassVar[dict] = {}
 
+    model_config = {'extra': 'forbid'}
+
     def get_llm_config(self, name='llm') -> LLMConfig:
         """'llm' is the name for default config (for backward compatibility prior to 0.8)."""
         if name in self.llms:
@@ -115,42 +119,7 @@ class AppConfig:
     def get_agent_configs(self) -> dict[str, AgentConfig]:
         return self.agents
 
-    def __post_init__(self):
+    def model_post_init(self, __context):
         """Post-initialization hook, called when the instance is created with only default values."""
-        AppConfig.defaults_dict = self.defaults_to_dict()
-
-    def defaults_to_dict(self) -> dict:
-        """Serialize fields to a dict for the frontend, including type hints, defaults, and whether it's optional."""
-        result = {}
-        for f in fields(self):
-            field_value = getattr(self, f.name)
-
-            # dataclasses compute their defaults themselves
-            if is_dataclass(type(field_value)):
-                result[f.name] = field_value.defaults_to_dict()
-            else:
-                result[f.name] = get_field_info(f)
-        return result
-
-    def __str__(self):
-        attr_str = []
-        for f in fields(self):
-            attr_name = f.name
-            attr_value = getattr(self, f.name)
-
-            if attr_name in [
-                'e2b_api_key',
-                'github_token',
-                'jwt_secret',
-                'modal_api_token_id',
-                'modal_api_token_secret',
-                'runloop_api_key',
-            ]:
-                attr_value = '******' if attr_value else None
-
-            attr_str.append(f'{attr_name}={repr(attr_value)}')
-
-        return f"AppConfig({', '.join(attr_str)}"
-
-    def __repr__(self):
-        return self.__str__()
+        super().model_post_init(__context)
+        AppConfig.defaults_dict = model_defaults_to_dict(self)

openhands/core/config/config_utils.py

@@ -1,19 +1,22 @@
 from types import UnionType
-from typing import get_args, get_origin
+from typing import Any, get_args, get_origin
+
+from pydantic import BaseModel
+from pydantic.fields import FieldInfo
 
 OH_DEFAULT_AGENT = 'CodeActAgent'
 OH_MAX_ITERATIONS = 500
 
 
-def get_field_info(f):
+def get_field_info(field: FieldInfo) -> dict[str, Any]:
     """Extract information about a dataclass field: type, optional, and default.
 
     Args:
-        f: The field to extract information from.
+        field: The field to extract information from.
 
     Returns: A dict with the field's type, whether it's optional, and its default value.
     """
-    field_type = f.type
+    field_type = field.annotation
     optional = False
 
     # for types like str | None, find the non-None type and set optional to True
@@ -33,7 +36,21 @@ def get_field_info(f):
     )
 
     # default is always present
-    default = f.default
+    default = field.default
 
     # return a schema with the useful info for frontend
     return {'type': type_name.lower(), 'optional': optional, 'default': default}
+
+
+def model_defaults_to_dict(model: BaseModel) -> dict[str, Any]:
+    """Serialize field information in a dict for the frontend, including type hints, defaults, and whether it's optional."""
+    result = {}
+    for name, field in model.model_fields.items():
+        field_value = getattr(model, name)
+
+        if isinstance(field_value, BaseModel):
+            result[name] = model_defaults_to_dict(field_value)
+        else:
+            result[name] = get_field_info(field)
+
+    return result

openhands/core/config/llm_config.py

@@ -1,15 +1,14 @@
-import os
-from dataclasses import dataclass, fields
-from typing import Optional
+from __future__ import annotations
+
+import os
+from typing import Any
+
+from pydantic import BaseModel, Field, SecretStr
 
-from openhands.core.config.config_utils import get_field_info
 from openhands.core.logger import LOG_DIR
 
-LLM_SENSITIVE_FIELDS = ['api_key', 'aws_access_key_id', 'aws_secret_access_key']
 
-
-@dataclass
-class LLMConfig:
+class LLMConfig(BaseModel):
     """Configuration for the LLM model.
 
     Attributes:
@@ -43,103 +42,62 @@ class LLMConfig:
         caching_prompt: Use the prompt caching feature if provided by the LLM and supported by the provider.
         log_completions: Whether to log LLM completions to the state.
         log_completions_folder: The folder to log LLM completions to. Required if log_completions is True.
-        draft_editor: A more efficient LLM to use for file editing. Introduced in [PR 3985](https://github.com/All-Hands-AI/OpenHands/pull/3985).
         custom_tokenizer: A custom tokenizer to use for token counting.
         native_tool_calling: Whether to use native tool calling if supported by the model. Can be True, False, or not set.
+        reasoning_effort: The effort to put into reasoning. This is a string that can be one of 'low', 'medium', 'high', or 'none'. Exclusive for o1 models.
     """
 
-    model: str = 'claude-3-5-sonnet-20241022'
-    api_key: str | None = None
-    base_url: str | None = None
-    api_version: str | None = None
-    embedding_model: str = 'local'
-    embedding_base_url: str | None = None
-    embedding_deployment_name: str | None = None
-    aws_access_key_id: str | None = None
-    aws_secret_access_key: str | None = None
-    aws_region_name: str | None = None
-    openrouter_site_url: str = 'https://docs.all-hands.dev/'
-    openrouter_app_name: str = 'OpenHands'
-    num_retries: int = 8
-    retry_multiplier: float = 2
-    retry_min_wait: int = 15
-    retry_max_wait: int = 120
-    timeout: int | None = None
-    max_message_chars: int = 30_000  # maximum number of characters in an observation's content when sent to the llm
-    temperature: float = 0.0
-    top_p: float = 1.0
-    custom_llm_provider: str | None = None
-    max_input_tokens: int | None = None
-    max_output_tokens: int | None = None
-    input_cost_per_token: float | None = None
-    output_cost_per_token: float | None = None
-    ollama_base_url: str | None = None
+    model: str = Field(default='claude-3-5-sonnet-20241022')
+    api_key: SecretStr | None = Field(default=None)
+    base_url: str | None = Field(default=None)
+    api_version: str | None = Field(default=None)
+    embedding_model: str = Field(default='local')
+    embedding_base_url: str | None = Field(default=None)
+    embedding_deployment_name: str | None = Field(default=None)
+    aws_access_key_id: SecretStr | None = Field(default=None)
+    aws_secret_access_key: SecretStr | None = Field(default=None)
+    aws_region_name: str | None = Field(default=None)
+    openrouter_site_url: str = Field(default='https://docs.all-hands.dev/')
+    openrouter_app_name: str = Field(default='OpenHands')
+    num_retries: int = Field(default=8)
+    retry_multiplier: float = Field(default=2)
+    retry_min_wait: int = Field(default=15)
+    retry_max_wait: int = Field(default=120)
+    timeout: int | None = Field(default=None)
+    max_message_chars: int = Field(
+        default=30_000
+    )  # maximum number of characters in an observation's content when sent to the llm
+    temperature: float = Field(default=0.0)
+    top_p: float = Field(default=1.0)
+    custom_llm_provider: str | None = Field(default=None)
+    max_input_tokens: int | None = Field(default=None)
+    max_output_tokens: int | None = Field(default=None)
+    input_cost_per_token: float | None = Field(default=None)
+    output_cost_per_token: float | None = Field(default=None)
+    ollama_base_url: str | None = Field(default=None)
     # This setting can be sent in each call to litellm
-    drop_params: bool = True
+    drop_params: bool = Field(default=True)
     # Note: this setting is actually global, unlike drop_params
-    modify_params: bool = True
-    disable_vision: bool | None = None
-    caching_prompt: bool = True
-    log_completions: bool = False
-    log_completions_folder: str = os.path.join(LOG_DIR, 'completions')
-    draft_editor: Optional['LLMConfig'] = None
-    custom_tokenizer: str | None = None
-    native_tool_calling: bool | None = None
+    modify_params: bool = Field(default=True)
+    disable_vision: bool | None = Field(default=None)
+    caching_prompt: bool = Field(default=True)
+    log_completions: bool = Field(default=False)
+    log_completions_folder: str = Field(default=os.path.join(LOG_DIR, 'completions'))
+    custom_tokenizer: str | None = Field(default=None)
+    native_tool_calling: bool | None = Field(default=None)
+    reasoning_effort: str | None = Field(default=None)
 
-    def defaults_to_dict(self) -> dict:
-        """Serialize fields to a dict for the frontend, including type hints, defaults, and whether it's optional."""
-        result = {}
-        for f in fields(self):
-            result[f.name] = get_field_info(f)
-        return result
+    model_config = {'extra': 'forbid'}
+
+    def model_post_init(self, __context: Any):
+        """Post-initialization hook to assign OpenRouter-related variables to environment variables.
 
-    def __post_init__(self):
-        """
-        Post-initialization hook to assign OpenRouter-related variables to environment variables.
         This ensures that these values are accessible to litellm at runtime.
         """
+        super().model_post_init(__context)
 
         # Assign OpenRouter-specific variables to environment variables
         if self.openrouter_site_url:
             os.environ['OR_SITE_URL'] = self.openrouter_site_url
         if self.openrouter_app_name:
             os.environ['OR_APP_NAME'] = self.openrouter_app_name
-
-    def __str__(self):
-        attr_str = []
-        for f in fields(self):
-            attr_name = f.name
-            attr_value = getattr(self, f.name)
-
-            if attr_name in LLM_SENSITIVE_FIELDS:
-                attr_value = '******' if attr_value else None
-
-            attr_str.append(f'{attr_name}={repr(attr_value)}')
-
-        return f"LLMConfig({', '.join(attr_str)})"
-
-    def __repr__(self):
-        return self.__str__()
-
-    def to_safe_dict(self):
-        """Return a dict with the sensitive fields replaced with ******."""
-        ret = self.__dict__.copy()
-        for k, v in ret.items():
-            if k in LLM_SENSITIVE_FIELDS:
-                ret[k] = '******' if v else None
-            elif isinstance(v, LLMConfig):
-                ret[k] = v.to_safe_dict()
-        return ret
-
-    @classmethod
-    def from_dict(cls, llm_config_dict: dict) -> 'LLMConfig':
-        """Create an LLMConfig object from a dictionary.
-
-        This function is used to create an LLMConfig object from a dictionary,
-        with the exception of the 'draft_editor' key, which is a nested LLMConfig object.
-        """
-        args = {k: v for k, v in llm_config_dict.items() if not isinstance(v, dict)}
-        if 'draft_editor' in llm_config_dict:
-            draft_editor_config = LLMConfig(**llm_config_dict['draft_editor'])
-            args['draft_editor'] = draft_editor_config
-        return cls(**args)

openhands/core/config/sandbox_config.py

@@ -1,11 +1,9 @@
 import os
-from dataclasses import dataclass, field, fields
 
-from openhands.core.config.config_utils import get_field_info
+from pydantic import BaseModel, Field
 
 
-@dataclass
-class SandboxConfig:
+class SandboxConfig(BaseModel):
     """Configuration for the sandbox.
 
     Attributes:
@@ -39,48 +37,32 @@ class SandboxConfig:
             This should be a JSON string that will be parsed into a dictionary.
     """
 
-    remote_runtime_api_url: str = 'http://localhost:8000'
-    local_runtime_url: str = 'http://localhost'
-    keep_runtime_alive: bool = True
-    rm_all_containers: bool = False
-    api_key: str | None = None
-    base_container_image: str = 'nikolaik/python-nodejs:python3.12-nodejs22'  # default to nikolaik/python-nodejs:python3.12-nodejs22 for eventstream runtime
-    runtime_container_image: str | None = None
-    user_id: int = os.getuid() if hasattr(os, 'getuid') else 1000
-    timeout: int = 120
-    remote_runtime_init_timeout: int = 180
-    enable_auto_lint: bool = (
-        False  # once enabled, OpenHands would lint files after editing
+    remote_runtime_api_url: str = Field(default='http://localhost:8000')
+    local_runtime_url: str = Field(default='http://localhost')
+    keep_runtime_alive: bool = Field(default=True)
+    rm_all_containers: bool = Field(default=False)
+    api_key: str | None = Field(default=None)
+    base_container_image: str = Field(
+        default='nikolaik/python-nodejs:python3.12-nodejs22'
     )
-    use_host_network: bool = False
-    runtime_extra_build_args: list[str] | None = None
-    initialize_plugins: bool = True
-    force_rebuild_runtime: bool = False
-    runtime_extra_deps: str | None = None
-    runtime_startup_env_vars: dict[str, str] = field(default_factory=dict)
-    browsergym_eval_env: str | None = None
-    platform: str | None = None
-    close_delay: int = 900
-    remote_runtime_resource_factor: int = 1
-    enable_gpu: bool = False
-    docker_runtime_kwargs: str | None = None
+    runtime_container_image: str | None = Field(default=None)
+    user_id: int = Field(default=os.getuid() if hasattr(os, 'getuid') else 1000)
+    timeout: int = Field(default=120)
+    remote_runtime_init_timeout: int = Field(default=180)
+    enable_auto_lint: bool = Field(
+        default=False  # once enabled, OpenHands would lint files after editing
+    )
+    use_host_network: bool = Field(default=False)
+    runtime_extra_build_args: list[str] | None = Field(default=None)
+    initialize_plugins: bool = Field(default=True)
+    force_rebuild_runtime: bool = Field(default=False)
+    runtime_extra_deps: str | None = Field(default=None)
+    runtime_startup_env_vars: dict[str, str] = Field(default_factory=dict)
+    browsergym_eval_env: str | None = Field(default=None)
+    platform: str | None = Field(default=None)
+    close_delay: int = Field(default=15)
+    remote_runtime_resource_factor: int = Field(default=1)
+    enable_gpu: bool = Field(default=False)
+    docker_runtime_kwargs: str | None = Field(default=None)
 
-    def defaults_to_dict(self) -> dict:
-        """Serialize fields to a dict for the frontend, including type hints, defaults, and whether it's optional."""
-        dict = {}
-        for f in fields(self):
-            dict[f.name] = get_field_info(f)
-        return dict
-
-    def __str__(self):
-        attr_str = []
-        for f in fields(self):
-            attr_name = f.name
-            attr_value = getattr(self, f.name)
-
-            attr_str.append(f'{attr_name}={repr(attr_value)}')
-
-        return f"SandboxConfig({', '.join(attr_str)})"
-
-    def __repr__(self):
-        return self.__str__()
+    model_config = {'extra': 'forbid'}

openhands/core/config/security_config.py

@@ -1,10 +1,7 @@
-from dataclasses import dataclass, fields
-
-from openhands.core.config.config_utils import get_field_info
+from pydantic import BaseModel, Field
 
 
-@dataclass
-class SecurityConfig:
+class SecurityConfig(BaseModel):
     """Configuration for security related functionalities.
 
     Attributes:
@@ -12,29 +9,5 @@ class SecurityConfig:
         security_analyzer: The security analyzer to use.
     """
 
-    confirmation_mode: bool = False
-    security_analyzer: str | None = None
-
-    def defaults_to_dict(self) -> dict:
-        """Serialize fields to a dict for the frontend, including type hints, defaults, and whether it's optional."""
-        dict = {}
-        for f in fields(self):
-            dict[f.name] = get_field_info(f)
-        return dict
-
-    def __str__(self):
-        attr_str = []
-        for f in fields(self):
-            attr_name = f.name
-            attr_value = getattr(self, f.name)
-
-            attr_str.append(f'{attr_name}={repr(attr_value)}')
-
-        return f"SecurityConfig({', '.join(attr_str)})"
-
-    @classmethod
-    def from_dict(cls, security_config_dict: dict) -> 'SecurityConfig':
-        return cls(**security_config_dict)
-
-    def __repr__(self):
-        return self.__str__()
+    confirmation_mode: bool = Field(default=False)
+    security_analyzer: str | None = Field(default=None)

openhands/core/config/utils.py

@@ -3,13 +3,13 @@ import os
 import pathlib
 import platform
 import sys
-from dataclasses import is_dataclass
 from types import UnionType
 from typing import Any, MutableMapping, get_args, get_origin
 from uuid import uuid4
 
 import toml
 from dotenv import load_dotenv
+from pydantic import BaseModel, ValidationError
 
 from openhands.core import logger
 from openhands.core.config.agent_config import AgentConfig
@@ -43,17 +43,19 @@ def load_from_env(cfg: AppConfig, env_or_toml_dict: dict | MutableMapping[str, s
         return next((t for t in types if t is not type(None)), None)
 
     # helper function to set attributes based on env vars
-    def set_attr_from_env(sub_config: Any, prefix=''):
-        """Set attributes of a config dataclass based on environment variables."""
-        for field_name, field_type in sub_config.__annotations__.items():
+    def set_attr_from_env(sub_config: BaseModel, prefix=''):
+        """Set attributes of a config model based on environment variables."""
+        for field_name, field_info in sub_config.model_fields.items():
+            field_value = getattr(sub_config, field_name)
+            field_type = field_info.annotation
+
             # compute the expected env var name from the prefix and field name
             # e.g. LLM_BASE_URL
             env_var_name = (prefix + field_name).upper()
 
-            if is_dataclass(field_type):
-                # nested dataclass
-                nested_sub_config = getattr(sub_config, field_name)
-                set_attr_from_env(nested_sub_config, prefix=field_name + '_')
+            if isinstance(field_value, BaseModel):
+                set_attr_from_env(field_value, prefix=field_name + '_')
+
             elif env_var_name in env_or_toml_dict:
                 # convert the env var to the correct type and set it
                 value = env_or_toml_dict[env_var_name]
@@ -125,45 +127,86 @@ def load_from_toml(cfg: AppConfig, toml_file: str = 'config.toml'):
         if isinstance(value, dict):
             try:
                 if key is not None and key.lower() == 'agent':
+                    # Every entry here is either a field for the default `agent` config group, or itself a group
+                    # The best way to tell the difference is to try to parse it as an AgentConfig object
+                    agent_group_ids: set[str] = set()
+                    for nested_key, nested_value in value.items():
+                        if isinstance(nested_value, dict):
+                            try:
+                                agent_config = AgentConfig(**nested_value)
+                            except ValidationError:
+                                continue
+                            agent_group_ids.add(nested_key)
+                            cfg.set_agent_config(agent_config, nested_key)
+
                     logger.openhands_logger.debug(
                         'Attempt to load default agent config from config toml'
                     )
-                    non_dict_fields = {
-                        k: v for k, v in value.items() if not isinstance(v, dict)
+                    value_without_groups = {
+                        k: v for k, v in value.items() if k not in agent_group_ids
                     }
-                    agent_config = AgentConfig(**non_dict_fields)
+                    agent_config = AgentConfig(**value_without_groups)
                     cfg.set_agent_config(agent_config, 'agent')
+
+                elif key is not None and key.lower() == 'llm':
+                    # Every entry here is either a field for the default `llm` config group, or itself a group
+                    # The best way to tell the difference is to try to parse it as an LLMConfig object
+                    llm_group_ids: set[str] = set()
                     for nested_key, nested_value in value.items():
                         if isinstance(nested_value, dict):
-                            logger.openhands_logger.debug(
-                                f'Attempt to load group {nested_key} from config toml as agent config'
-                            )
-                            agent_config = AgentConfig(**nested_value)
-                            cfg.set_agent_config(agent_config, nested_key)
-                elif key is not None and key.lower() == 'llm':
+                            try:
+                                llm_config = LLMConfig(**nested_value)
+                            except ValidationError:
+                                continue
+                            llm_group_ids.add(nested_key)
+                            cfg.set_llm_config(llm_config, nested_key)
+
                     logger.openhands_logger.debug(
                         'Attempt to load default LLM config from config toml'
                     )
-                    llm_config = LLMConfig.from_dict(value)
-                    cfg.set_llm_config(llm_config, 'llm')
+
+                    # Extract generic LLM fields, which are not nested LLM configs
+                    generic_llm_fields = {}
+                    for k, v in value.items():
+                        if not isinstance(v, dict):
+                            generic_llm_fields[k] = v
+                    generic_llm_config = LLMConfig(**generic_llm_fields)
+                    cfg.set_llm_config(generic_llm_config, 'llm')
+
+                    # Process custom named LLM configs
                     for nested_key, nested_value in value.items():
                         if isinstance(nested_value, dict):
                             logger.openhands_logger.debug(
-                                f'Attempt to load group {nested_key} from config toml as llm config'
+                                f'Processing custom LLM config "{nested_key}":'
                             )
-                            llm_config = LLMConfig.from_dict(nested_value)
-                            cfg.set_llm_config(llm_config, nested_key)
+                            # Apply generic LLM config with custom LLM overrides, e.g.
+                            # [llm]
+                            # model="..."
+                            # num_retries = 5
+                            # [llm.claude]
+                            # model="claude-3-5-sonnet"
+                            # results in num_retries APPLIED to claude-3-5-sonnet
+                            custom_fields = {}
+                            for k, v in nested_value.items():
+                                if not isinstance(v, dict):
+                                    custom_fields[k] = v
+                            merged_llm_dict = generic_llm_fields.copy()
+                            merged_llm_dict.update(custom_fields)
+                            
+                            custom_llm_config = LLMConfig(**merged_llm_dict)
+                            cfg.set_llm_config(custom_llm_config, nested_key)
+
                 elif key is not None and key.lower() == 'security':
                     logger.openhands_logger.debug(
                         'Attempt to load security config from config toml'
                     )
-                    security_config = SecurityConfig.from_dict(value)
+                    security_config = SecurityConfig(**value)
                     cfg.security = security_config
                 elif not key.startswith('sandbox') and key.lower() != 'core':
                     logger.openhands_logger.warning(
                         f'Unknown key in {toml_file}: "{key}"'
                     )
-            except (TypeError, KeyError) as e:
+            except (TypeError, KeyError, ValidationError) as e:
                 logger.openhands_logger.warning(
                     f'Cannot parse [{key}] config from toml, values have not been applied.\nError: {e}',
                 )
@@ -199,7 +242,7 @@ def load_from_toml(cfg: AppConfig, toml_file: str = 'config.toml'):
                 logger.openhands_logger.warning(
                     f'Unknown config key "{key}" in [core] section'
                 )
-    except (TypeError, KeyError) as e:
+    except (TypeError, KeyError, ValidationError) as e:
         logger.openhands_logger.warning(
             f'Cannot parse [sandbox] config from toml, values have not been applied.\nError: {e}',
         )
@@ -302,7 +345,7 @@ def get_llm_config_arg(
 
     # update the llm config with the specified section
     if 'llm' in toml_config and llm_config_arg in toml_config['llm']:
-        return LLMConfig.from_dict(toml_config['llm'][llm_config_arg])
+        return LLMConfig(**toml_config['llm'][llm_config_arg])
     logger.openhands_logger.debug(f'Loading from toml failed for {llm_config_arg}')
     return None
 
@@ -458,7 +501,11 @@ def setup_config_from_args(args: argparse.Namespace) -> AppConfig:
 
     # Override with command line arguments if provided
     if args.llm_config:
-        llm_config = get_llm_config_arg(args.llm_config)
+        # if we didn't already load it, get it from the toml file
+        if args.llm_config not in config.llms:
+            llm_config = get_llm_config_arg(args.llm_config)
+        else:
+            llm_config = config.llms[args.llm_config]
         if llm_config is None:
             raise ValueError(f'Invalid toml file, cannot read {args.llm_config}')
         config.set_llm_config(llm_config)

openhands/core/logger.py

@@ -8,10 +8,31 @@ from datetime import datetime
 from types import TracebackType
 from typing import Any, Literal, Mapping
 
+import litellm
 from termcolor import colored
 
 LOG_LEVEL = os.getenv('LOG_LEVEL', 'INFO').upper()
 DEBUG = os.getenv('DEBUG', 'False').lower() in ['true', '1', 'yes']
+DEBUG_LLM = os.getenv('DEBUG_LLM', 'False').lower() in ['true', '1', 'yes']
+
+# Configure litellm logging based on DEBUG_LLM
+if DEBUG_LLM:
+    confirmation = input(
+        '\n⚠️ WARNING: You are enabling DEBUG_LLM which may expose sensitive information like API keys.\n'
+        'This should NEVER be enabled in production.\n'
+        "Type 'y' to confirm you understand the risks: "
+    )
+    if confirmation.lower() == 'y':
+        litellm.suppress_debug_info = False
+        litellm.set_verbose = True
+    else:
+        print('DEBUG_LLM disabled due to lack of confirmation')
+        litellm.suppress_debug_info = True
+        litellm.set_verbose = False
+else:
+    litellm.suppress_debug_info = True
+    litellm.set_verbose = False
+
 if DEBUG:
     LOG_LEVEL = 'DEBUG'
 

openhands/core/main.py

@@ -2,6 +2,7 @@ import asyncio
 import json
 import os
 import sys
+from pathlib import Path
 from typing import Callable, Protocol
 
 import openhands.agenthub  # noqa F401 (we import this to get the agents registered)
@@ -22,10 +23,11 @@ from openhands.core.setup import (
     generate_sid,
 )
 from openhands.events import EventSource, EventStreamSubscriber
-from openhands.events.action import MessageAction
+from openhands.events.action import MessageAction, NullAction
 from openhands.events.action.action import Action
 from openhands.events.event import Event
 from openhands.events.observation import AgentStateChangedObservation
+from openhands.events.serialization import event_from_dict
 from openhands.events.serialization.event import event_to_trajectory
 from openhands.runtime.base import Runtime
 
@@ -101,7 +103,17 @@ async def run_controller(
     if agent is None:
         agent = create_agent(runtime, config)
 
-    controller, initial_state = create_controller(agent, runtime, config)
+    replay_events: list[Event] | None = None
+    if config.replay_trajectory_path:
+        logger.info('Trajectory replay is enabled')
+        assert isinstance(initial_user_action, NullAction)
+        replay_events, initial_user_action = load_replay_log(
+            config.replay_trajectory_path
+        )
+
+    controller, initial_state = create_controller(
+        agent, runtime, config, replay_events=replay_events
+    )
 
     assert isinstance(
         initial_user_action, Action
@@ -194,21 +206,64 @@ def auto_continue_response(
     return message
 
 
+def load_replay_log(trajectory_path: str) -> tuple[list[Event] | None, Action]:
+    """
+    Load trajectory from given path, serialize it to a list of events, and return
+    two things:
+    1) A list of events except the first action
+    2) First action (user message, a.k.a. initial task)
+    """
+    try:
+        path = Path(trajectory_path).resolve()
+
+        if not path.exists():
+            raise ValueError(f'Trajectory file not found: {path}')
+
+        if not path.is_file():
+            raise ValueError(f'Trajectory path is a directory, not a file: {path}')
+
+        with open(path, 'r', encoding='utf-8') as file:
+            data = json.load(file)
+            if not isinstance(data, list):
+                raise ValueError(
+                    f'Expected a list in {path}, got {type(data).__name__}'
+                )
+            events = []
+            for item in data:
+                event = event_from_dict(item)
+                # cannot add an event with _id to event stream
+                event._id = None  # type: ignore[attr-defined]
+                events.append(event)
+            assert isinstance(events[0], MessageAction)
+            return events[1:], events[0]
+    except json.JSONDecodeError as e:
+        raise ValueError(f'Invalid JSON format in {trajectory_path}: {e}')
+
+
 if __name__ == '__main__':
     args = parse_arguments()
 
+    config = setup_config_from_args(args)
+
     # Determine the task
+    task_str = ''
     if args.file:
         task_str = read_task_from_file(args.file)
     elif args.task:
         task_str = args.task
     elif not sys.stdin.isatty():
         task_str = read_task_from_stdin()
+
+    initial_user_action: Action = NullAction()
+    if config.replay_trajectory_path:
+        if task_str:
+            raise ValueError(
+                'User-specified task is not supported under trajectory replay mode'
+            )
+    elif task_str:
+        initial_user_action = MessageAction(content=task_str)
     else:
         raise ValueError('No task provided. Please specify a task through -t, -f.')
-    initial_user_action: MessageAction = MessageAction(content=task_str)
-
-    config = setup_config_from_args(args)
 
     # Set session name
     session_name = args.name

openhands/core/setup.py

@@ -11,6 +11,7 @@ from openhands.core.config import (
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.events import EventStream
+from openhands.events.event import Event
 from openhands.llm.llm import LLM
 from openhands.runtime import get_runtime_cls
 from openhands.runtime.base import Runtime
@@ -78,7 +79,11 @@ def create_agent(runtime: Runtime, config: AppConfig) -> Agent:
 
 
 def create_controller(
-    agent: Agent, runtime: Runtime, config: AppConfig, headless_mode: bool = True
+    agent: Agent,
+    runtime: Runtime,
+    config: AppConfig,
+    headless_mode: bool = True,
+    replay_events: list[Event] | None = None,
 ) -> Tuple[AgentController, State | None]:
     event_stream = runtime.event_stream
     initial_state = None
@@ -101,6 +106,7 @@ def create_controller(
         initial_state=initial_state,
         headless_mode=headless_mode,
         confirmation_mode=config.security.confirmation_mode,
+        replay_events=replay_events,
     )
     return (controller, initial_state)
 

openhands/events/action/commands.py

@@ -11,8 +11,10 @@ from openhands.events.action.action import (
 
 @dataclass
 class CmdRunAction(Action):
-    command: str
-    # When `command` is empty, it will be used to print the current tmux window
+    command: (
+        str  # When `command` is empty, it will be used to print the current tmux window
+    )
+    is_input: bool = False  # if True, the command is an input to the running process
     thought: str = ''
     blocking: bool = False
     # If blocking is True, the command will be run in a blocking manner.
@@ -28,7 +30,7 @@ class CmdRunAction(Action):
         return f'Running command: {self.command}'
 
     def __str__(self) -> str:
-        ret = f'**CmdRunAction (source={self.source})**\n'
+        ret = f'**CmdRunAction (source={self.source}, is_input={self.is_input})**\n'
         if self.thought:
             ret += f'THOUGHT: {self.thought}\n'
         ret += f'COMMAND:\n{self.command}'

openhands/events/event.py

@@ -24,6 +24,8 @@ class FileReadSource(str, Enum):
 
 @dataclass
 class Event:
+    INVALID_ID = -1
+
     @property
     def message(self) -> str | None:
         if hasattr(self, '_message'):
@@ -34,7 +36,7 @@ class Event:
     def id(self) -> int:
         if hasattr(self, '_id'):
             return self._id  # type: ignore[attr-defined]
-        return -1
+        return Event.INVALID_ID
 
     @property
     def timestamp(self):
@@ -64,8 +66,12 @@ class Event:
             return self._timeout  # type: ignore[attr-defined]
         return None
 
-    @timeout.setter
-    def timeout(self, value: int | None) -> None:
+    def set_hard_timeout(self, value: int | None, blocking: bool = True) -> None:
+        """Set the timeout for the event.
+
+        NOTE, this is a hard timeout, meaning that the event will be blocked
+        until the timeout is reached.
+        """
         self._timeout = value
         if value is not None and value > 600:
             from openhands.core.logger import openhands_logger as logger
@@ -78,7 +84,7 @@ class Event:
         # Check if .blocking is an attribute of the event
         if hasattr(self, 'blocking'):
             # .blocking needs to be set to True if .timeout is set
-            self.blocking = True
+            self.blocking = blocking
 
     # optional metadata, LLM call cost of the edit
     @property