Fix issue #6031: UX: Widen the LLM Model drop-down in AI Provider Configuration panel to better view long LLM model names

CODE_OF_CONDUCT.md

@@ -18,24 +18,24 @@ diverse, inclusive, and healthy community.
 Examples of behavior that contributes to a positive environment for our
 community include:
 
-* Demonstrating empathy and kindness toward other people.
-* Being respectful of differing opinions, viewpoints, and experiences.
-* Giving and gracefully accepting constructive feedback.
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
 * Accepting responsibility and apologizing to those affected by our mistakes,
-  and learning from the experience.
+  and learning from the experience
 * Focusing on what is best not just for us as individuals, but for the overall
-  community.
+  community
 
 Examples of unacceptable behavior include:
 
 * The use of sexualized language or imagery, and sexual attention or advances of
-  any kind.
-* Trolling, insulting or derogatory comments, and personal or political attacks.
-* Public or private harassment.
+  any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
 * Publishing others' private information, such as a physical or email address,
-  without their explicit permission.
+  without their explicit permission
 * Other conduct which could reasonably be considered inappropriate in a
-  professional setting.
+  professional setting
 
 ## Enforcement Responsibilities
 
@@ -61,7 +61,7 @@ representative at an online or offline event.
 
 Instances of abusive, harassing, or otherwise unacceptable behavior may be
 reported to the community leaders responsible for enforcement at
-contact@all-hands.dev.
+contact@all-hands.dev
 All complaints will be reviewed and investigated promptly and fairly.
 
 All community leaders are obligated to respect the privacy and security of the

CONTRIBUTING.md

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

Development.md

@@ -3,7 +3,7 @@ This guide is for people working on OpenHands and editing the source code.
 If you wish to contribute your changes, check out the [CONTRIBUTING.md](https://github.com/All-Hands-AI/OpenHands/blob/main/CONTRIBUTING.md) on how to clone and setup the project initially before moving on.
 Otherwise, you can clone the OpenHands project directly.
 
-## Start the Server for Development
+## Start the server for development
 ### 1. Requirements
 * Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)  [Ubuntu <= 22.04]
 * [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!)
@@ -58,7 +58,7 @@ See [our documentation](https://docs.all-hands.dev/modules/usage/llms) for recom
 
 ### 4. Running the application
 #### Option A: Run the Full Application
-Once the setup is complete, this command starts both the backend and frontend servers, allowing you to interact with OpenHands:
+Once the setup is complete, launching OpenHands is as simple as running a single command. This command starts both the backend and frontend servers seamlessly, allowing you to interact with OpenHands:
 ```bash
 make run
 ```
@@ -75,11 +75,11 @@ make run
     ```
 
 ### 6. LLM Debugging
-If you encounter any issues with the Language Model (LM) or you're simply curious, export DEBUG=1 in the environment and restart the backend.
-OpenHands will log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
+If you encounter any issues with the Language Model (LM) or you're simply curious, you can inspect the actual LLM prompts and responses. To do so, export DEBUG=1 in the environment and restart the backend.
+OpenHands will then log the prompts and responses in the logs/llm/CURRENT_DATE directory, allowing you to identify the causes.
 
 ### 7. Help
-Need help or info on available targets and commands? Use the help command for all the guidance you need with OpenHands.
+Need assistance or information on available targets and commands? The help command provides all the necessary guidance to ensure a smooth experience with OpenHands.
 ```bash
 make help
  ```
@@ -93,14 +93,14 @@ poetry run pytest ./tests/unit/test_*.py
 ```
 
 ### 9. Add or update dependency
-1. Add your dependency in `pyproject.toml` or use `poetry add xxx`.
-2. Update the poetry.lock file via `poetry lock --no-update`.
+1. Add your dependency in `pyproject.toml` or use `poetry add xxx`
+2. Update the poetry.lock file via `poetry lock --no-update`
 
 ### 9. Use existing Docker image
 To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker container image by
 setting the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
 
-Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.19-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.18-nikolaik`
 
 ## Develop inside Docker container
 
@@ -110,7 +110,7 @@ TL;DR
 make docker-dev
 ```
 
-See more details [here](./containers/dev/README.md).
+See more details [here](./containers/dev/README.md)
 
 If you are just interested in running `OpenHands` without installing all the required tools on your host.
 

ISSUE_TRIAGE.md

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

README.md

@@ -43,17 +43,17 @@ See the [Installation](https://docs.all-hands.dev/modules/usage/installation) gu
 system requirements and more information.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.19
+    docker.all-hands.dev/all-hands-ai/openhands:0.18
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!

compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.19-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.18-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

containers/dev/compose.yml

@@ -11,7 +11,7 @@ services:
       - BACKEND_HOST=${BACKEND_HOST:-"0.0.0.0"}
       - SANDBOX_API_HOSTNAME=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.19-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.18-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

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

@@ -52,7 +52,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -61,7 +61,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.19 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
     python -m openhands.core.cli
 ```
 

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

@@ -46,7 +46,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -56,6 +56,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.19 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

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

@@ -13,16 +13,16 @@
 La façon la plus simple d'exécuter OpenHands est avec Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.19
+    docker.all-hands.dev/all-hands-ai/openhands:0.18
 ```
 
 Vous pouvez également exécuter OpenHands en mode [headless scriptable](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), en tant que [CLI interactive](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), ou en utilisant l'[Action GitHub OpenHands](https://docs.all-hands.dev/modules/usage/how-to/github-action).

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

@@ -13,7 +13,7 @@ C'est le Runtime par défaut qui est utilisé lorsque vous démarrez OpenHands.
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

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

@@ -50,7 +50,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -59,7 +59,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.19 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
     python -m openhands.core.cli
 ```
 

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

@@ -47,7 +47,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -57,6 +57,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.19 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

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

@@ -11,16 +11,16 @@
 在 Docker 中运行 OpenHands 是最简单的方式。
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.19
+    docker.all-hands.dev/all-hands-ai/openhands:0.18
 ```
 
 你也可以在可脚本化的[无头模式](https://docs.all-hands.dev/modules/usage/how-to/headless-mode)下运行 OpenHands，作为[交互式 CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode)，或使用 [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action)。

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

@@ -11,7 +11,7 @@
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

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

@@ -35,7 +35,7 @@ To run OpenHands in CLI mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -45,7 +45,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.19 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
     python -m openhands.core.cli
 ```
 

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

@@ -32,7 +32,7 @@ To run OpenHands in Headless mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -43,7 +43,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.19 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.18 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/modules/usage/installation.mdx

@@ -11,17 +11,17 @@
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.19
+    docker.all-hands.dev/all-hands-ai/openhands:0.18
 ```
 
 You'll find OpenHands running at http://localhost:3000!

docs/modules/usage/prompting/customization.md

@@ -1,12 +1,10 @@
-# Repository Micro-Agents
+# Customizing Agent Behavior
 
-OpenHands can be customized to work more effectively with specific repositories by providing repository-specific context
-and guidelines. This section explains how to optimize OpenHands for your project.
+OpenHands can be customized to work more effectively with specific repositories by providing repository-specific context and guidelines. This section explains how to optimize OpenHands for your project.
 
 ## Repository Configuration
 
-You can customize OpenHands' behavior for your repository by creating a `.openhands/microagents/` directory in your repository's root.
-At minimum, it should contain the file
+You can customize OpenHands' behavior for your repository by creating a `.openhands` directory in your repository's root. At minimum, it should contain the file
 `.openhands/microagents/repo.md`, which includes instructions that will
 be given to the agent every time it works with this repository.
 
@@ -41,8 +39,7 @@ Guidelines:
 
 ### Customizing Prompts
 
-You may also add customized prompts to the `.openhands/microagents/repo.md` file when working with a repository.
-These could:
+When working with a repository:
 
 - **Reference Project Standards**: Mention specific coding standards or patterns used in your project.
 - **Include Context**: Reference relevant documentation or existing implementations.
@@ -57,10 +54,14 @@ The component should use our shared styling from src/styles/components.
 
 ### Best Practices for Repository Customization
 
-- **Keep Instructions Updated**: Regularly update your `.openhands/microagents/` directory as your project evolves.
+- **Keep Instructions Updated**: Regularly update your `.openhands` directory as your project evolves.
 - **Be Specific**: Include specific paths, patterns, and requirements unique to your project.
 - **Document Dependencies**: List all tools and dependencies required for development.
 - **Include Examples**: Provide examples of good code patterns from your project.
 - **Specify Conventions**: Document naming conventions, file organization, and code style preferences.
 
 By customizing OpenHands for your repository, you'll get more accurate and consistent results that align with your project's standards and requirements.
+
+## Other Microagents
+You can create other instructions in the `.openhands/microagents/` directory
+that will be sent to the agent if a particular keyword is found, like `test`, `frontend`, or `migration`. See [Micro-Agents](microagents.md) for more information.

docs/modules/usage/prompting/microagents.md

@@ -1,31 +1,17 @@
-# Public Micro-Agents
+# Micro-Agents
 
-OpenHands uses specialized micro-agents to handle specific tasks and contexts efficiently. These micro-agents are small,
-focused components that provide specialized behavior and knowledge for particular scenarios.
+OpenHands uses specialized micro-agents to handle specific tasks and contexts efficiently. These micro-agents are small, focused components that provide specialized behavior and knowledge for particular scenarios.
 
 ## Overview
 
-Public micro-agents are defined in markdown files under the
-[`microagents/knowledge/`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents/knowledge) directory.
-Each micro-agent is configured with:
+Micro-agents are defined in markdown files under the `openhands/agenthub/codeact_agent/micro/` directory. Each micro-agent is configured with:
 
 - A unique name.
 - The agent type (typically CodeActAgent).
 - Trigger keywords that activate the agent.
 - Specific instructions and capabilities.
 
-### Integration
-
-Public micro-agents are automatically integrated into OpenHands' workflow. They:
-- Monitor incoming commands for their trigger words.
-- Activate when relevant triggers are detected.
-- Apply their specialized knowledge and capabilities.
-- Follow their specific guidelines and restrictions.
-
-## Available Public Micro-Agents
-
-For more information about specific micro-agents, refer to their individual documentation files in
-the [`micro-agents`](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents) directory.
+## Available Micro-Agents
 
 ### GitHub Agent
 **File**: `github.md`
@@ -43,14 +29,6 @@ Key features:
 - Git configuration management
 - API-first approach for GitHub operations
 
-Usage Example:
-
-```bash
-git checkout -b feature-branch
-git commit -m "Add new feature"
-git push origin feature-branch
-```
-
 ### NPM Agent
 **File**: `npm.md`
 **Triggers**: `npm`
@@ -60,15 +38,9 @@ Specializes in handling npm package management with specific focus on:
 - Automated confirmation handling using Unix 'yes' command.
 - Package installation automation.
 
-Usage Example:
+### Custom Micro-Agents
 
-```bash
-yes | npm install package-name
-```
-
-### Custom Public Micro-Agents
-
-You can create your own public micro-agents by adding new markdown files to the `microagents/knowledge/` directory.
+You can create your own micro-agents by adding new markdown files to the micro-agents directory.
 Each file should follow this structure:
 
 ```markdown
@@ -83,29 +55,43 @@ triggers:
 Instructions and capabilities for the micro-agent...
 ```
 
-## Working With Public Micro-Agents
+## Best Practices
 
-When working with public micro-agents:
+When working with micro-agents:
 - **Use Appropriate Triggers**: Ensure your commands include the relevant trigger words to activate the correct micro-agent.
 - **Follow Agent Guidelines**: Each agent has specific instructions and limitations. Respect these for optimal results.
 - **API-First Approach**: When available, use API endpoints rather than web interfaces.
 - **Automation Friendly**: Design commands that work well in non-interactive environments.
 
-## Contributing a Public Micro-Agent
+## Integration
 
-Best practices for creating public micro-agents:
+Micro-agents are automatically integrated into OpenHands' workflow. They:
+- Monitor incoming commands for their trigger words.
+- Activate when relevant triggers are detected.
+- Apply their specialized knowledge and capabilities.
+- Follow their specific guidelines and restrictions.
 
-- **Clear Scope**: Keep the micro-agent focused on a specific domain or task.
-- **Explicit Instructions**: Provide clear, unambiguous guidelines.
-- **Useful Examples**: Include practical examples of common use cases.
-- **Safety First**: Include necessary warnings and constraints.
-- **Integration Awareness**: Consider how the micro-agent interacts with other components.
+## Example Usage
 
-To contribute a new micro-agent to OpenHands:
+```bash
+# GitHub agent example
+git checkout -b feature-branch
+git commit -m "Add new feature"
+git push origin feature-branch
 
-### 1. Plan the Public Micro-Agent
+# NPM agent example
+yes | npm install package-name
+```
 
-Before creating a public micro-agent, consider:
+For more information about specific agents, refer to their individual documentation files in the micro-agents directory.
+
+## Contributing a Micro-Agent
+
+To contribute a new micro-agent to OpenHands, follow these guidelines:
+
+### 1. Planning Your Micro-Agent
+
+Before creating a micro-agent, consider:
 - What specific problem or use case will it address?
 - What unique capabilities or knowledge should it have?
 - What trigger words make sense for activating it?
@@ -113,11 +99,11 @@ Before creating a public micro-agent, consider:
 
 ### 2. File Structure
 
-Create a new markdown file in `microagents/knowledge/` with a descriptive name (e.g., `docker.md` for a Docker-focused agent).
+Create a new markdown file in `openhands/agenthub/codeact_agent/micro/` with a descriptive name (e.g., `docker.md` for a Docker-focused agent).
 
 ### 3. Required Components
 
-The micro-agent file must include:
+Your micro-agent file must include:
 
 - **Front Matter**: YAML metadata at the start of the file:
 ```markdown
@@ -147,7 +133,15 @@ Examples of usage:
 [Example 2]
 ```
 
-### 4. Testing the Public Micro-Agent
+### 4. Best Practices for Micro-Agent Development
+
+- **Clear Scope**: Keep the agent focused on a specific domain or task.
+- **Explicit Instructions**: Provide clear, unambiguous guidelines.
+- **Useful Examples**: Include practical examples of common use cases.
+- **Safety First**: Include necessary warnings and constraints.
+- **Integration Awareness**: Consider how the agent interacts with other components.
+
+### 5. Testing Your Micro-Agent
 
 Before submitting:
 - Test the agent with various prompts.
@@ -155,14 +149,7 @@ Before submitting:
 - Ensure instructions are clear and comprehensive.
 - Check for potential conflicts with existing agents.
 
-### 5. Submission Process
-
-Submit a pull request with:
-- The new micro-agent file.
-- Updated documentation if needed.
-- Description of the agent's purpose and capabilities.
-
-### Example Public Micro-Agent Implementation
+### 6. Example Implementation
 
 Here's a template for a new micro-agent:
 
@@ -210,5 +197,14 @@ Remember to:
 - Optimize for build time and image size
 ```
 
+### 7. Submission Process
+
+1. Create your micro-agent file in the correct directory.
+2. Test thoroughly.
+3. Submit a pull request with:
+   - The new micro-agent file.
+   - Updated documentation if needed.
+   - Description of the agent's purpose and capabilities.
+
 Remember that micro-agents are a powerful way to extend OpenHands' capabilities in specific domains. Well-designed
 agents can significantly improve the system's ability to handle specialized tasks.

docs/modules/usage/runtimes.md

@@ -16,7 +16,7 @@ some flags being passed to `docker run` that make this possible:
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.18-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/sidebars.ts

@@ -23,21 +23,15 @@ const sidebars: SidebarsConfig = {
           id: 'usage/prompting/prompting-best-practices',
         },
         {
-          type: 'category',
-          label: 'Micro-Agents',
-          items: [
-            {
-              type: 'doc',
-              label: 'Public',
-              id: 'usage/prompting/microagents-public',
-            },
-            {
-              type: 'doc',
-              label: 'Repository',
-              id: 'usage/prompting/microagents-repo',
-            },
-          ],
-        }
+          type: 'doc',
+          label: 'Customization',
+          id: 'usage/prompting/customization',
+        },
+        {
+          type: 'doc',
+          label: 'Microagents',
+          id: 'usage/prompting/microagents',
+        },
       ],
     },
     {

evaluation/benchmarks/swe_bench/run_infer.py

@@ -15,7 +15,6 @@ from evaluation.utils.shared import (
     EvalOutput,
     assert_and_raise,
     codeact_user_response,
-    get_metrics,
     is_fatal_evaluation_error,
     make_metadata,
     prepare_dataset,
@@ -149,7 +148,6 @@ def get_config(
         codeact_enable_jupyter=False,
         codeact_enable_browsing=RUN_WITH_BROWSING,
         codeact_enable_llm_editor=False,
-        condenser=metadata.condenser_config,
     )
     config.set_agent_config(agent_config)
     return config
@@ -450,7 +448,7 @@ def process_instance(
 
     # NOTE: this is NO LONGER the event stream, but an agent history that includes delegate agent's events
     histories = [event_to_dict(event) for event in state.history]
-    metrics = get_metrics(state)
+    metrics = state.metrics.get() if state.metrics else None
 
     # Save the output
     output = EvalOutput(

evaluation/utils/shared.py

@@ -17,10 +17,6 @@ from tqdm import tqdm
 
 from openhands.controller.state.state import State
 from openhands.core.config import LLMConfig
-from openhands.core.config.condenser_config import (
-    CondenserConfig,
-    NoOpCondenserConfig,
-)
 from openhands.core.exceptions import (
     AgentRuntimeBuildError,
     AgentRuntimeDisconnectedError,
@@ -37,7 +33,6 @@ from openhands.events.action.message import MessageAction
 from openhands.events.event import Event
 from openhands.events.serialization.event import event_to_dict
 from openhands.events.utils import get_pairs_from_events
-from openhands.memory.condenser import get_condensation_metadata
 
 
 class EvalMetadata(BaseModel):
@@ -50,17 +45,11 @@ class EvalMetadata(BaseModel):
     dataset: str | None = None
     data_split: str | None = None
     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):
@@ -68,11 +57,6 @@ class EvalMetadata(BaseModel):
         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)
 
@@ -208,7 +192,6 @@ def make_metadata(
     eval_output_dir: str,
     data_split: str | None = None,
     details: dict[str, Any] | None = None,
-    condenser_config: CondenserConfig | None = None,
 ) -> EvalMetadata:
     model_name = llm_config.model.split('/')[-1]
     model_path = model_name.replace(':', '_').replace('@', '-')
@@ -239,9 +222,6 @@ def make_metadata(
         dataset=dataset_name,
         data_split=data_split,
         details=details,
-        condenser_config=condenser_config
-        if condenser_config
-        else NoOpCondenserConfig(),
     )
     metadata_json = metadata.model_dump_json()
     logger.info(f'Metadata: {metadata_json}')
@@ -571,10 +551,3 @@ def is_fatal_evaluation_error(error: str | None) -> bool:
         return True
 
     return False
-
-
-def get_metrics(state: State) -> dict[str, Any]:
-    """Extract metrics from the state."""
-    metrics = state.metrics.get() if state.metrics else {}
-    metrics['condenser'] = get_condensation_metadata(state)
-    return metrics

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

@@ -3,7 +3,6 @@ import { afterEach, describe, expect, it, test, vi } from "vitest";
 import userEvent from "@testing-library/user-event";
 import { formatTimeDelta } from "#/utils/format-time-delta";
 import { ConversationCard } from "#/components/features/conversation-panel/conversation-card";
-import { clickOnEditButton } from "./utils";
 
 describe("ConversationCard", () => {
   const onClick = vi.fn();
@@ -145,9 +144,7 @@ describe("ConversationCard", () => {
       />,
     );
 
-    const selectedRepository = screen.getByTestId(
-      "conversation-card-selected-repository",
-    );
+    const selectedRepository = screen.getByTestId("conversation-card-selected-repository");
     await user.click(selectedRepository);
 
     expect(onClick).not.toHaveBeenCalled();
@@ -167,14 +164,6 @@ describe("ConversationCard", () => {
     );
 
     const title = screen.getByTestId("conversation-card-title");
-    expect(title).toBeDisabled();
-
-    await clickOnEditButton(user);
-
-    expect(title).toBeEnabled();
-    expect(screen.queryByTestId("context-menu")).not.toBeInTheDocument();
-    // expect to be focused
-    expect(document.activeElement).toBe(title);
 
     await user.clear(title);
     await user.type(title, "New Conversation Name   ");
@@ -182,7 +171,6 @@ describe("ConversationCard", () => {
 
     expect(onChangeTitle).toHaveBeenCalledWith("New Conversation Name");
     expect(title).toHaveValue("New Conversation Name");
-    expect(title).toBeDisabled();
   });
 
   it("should reset title and not call onChangeTitle when the title is empty", async () => {
@@ -198,8 +186,6 @@ describe("ConversationCard", () => {
       />,
     );
 
-    await clickOnEditButton(user);
-
     const title = screen.getByTestId("conversation-card-title");
 
     await user.clear(title);

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

@@ -9,7 +9,6 @@ import userEvent from "@testing-library/user-event";
 import { ConversationPanel } from "#/components/features/conversation-panel/conversation-panel";
 import OpenHands from "#/api/open-hands";
 import { AuthProvider } from "#/context/auth-context";
-import { clickOnEditButton } from "./utils";
 
 describe("ConversationPanel", () => {
   const onCloseMock = vi.fn();
@@ -53,8 +52,6 @@ describe("ConversationPanel", () => {
     renderConversationPanel();
     const cards = await screen.findAllByTestId("conversation-card");
 
-    // NOTE that we filter out conversations that don't have a created_at property
-    // (mock data has 4 conversations, but only 3 have a created_at property)
     expect(cards).toHaveLength(3);
   });
 
@@ -172,8 +169,6 @@ describe("ConversationPanel", () => {
     const cards = await screen.findAllByTestId("conversation-card");
     const title = within(cards[0]).getByTestId("conversation-card-title");
 
-    await clickOnEditButton(user);
-
     await user.clear(title);
     await user.type(title, "Conversation 1 Renamed");
     await user.tab();
@@ -201,8 +196,6 @@ describe("ConversationPanel", () => {
     // Ensure the conversation is not renamed
     expect(updateUserConversationSpy).not.toHaveBeenCalled();
 
-    await clickOnEditButton(user);
-
     await user.type(title, "Conversation 1");
     await user.click(title);
     await user.tab();
@@ -224,4 +217,51 @@ describe("ConversationPanel", () => {
 
     expect(onCloseMock).toHaveBeenCalledOnce();
   });
+
+  describe("New Conversation Button", () => {
+    it("should display a confirmation modal when clicking", async () => {
+      const user = userEvent.setup();
+      renderConversationPanel();
+
+      expect(
+        screen.queryByTestId("confirm-new-conversation-modal"),
+      ).not.toBeInTheDocument();
+
+      const newProjectButton = screen.getByTestId("new-conversation-button");
+      await user.click(newProjectButton);
+
+      const modal = screen.getByTestId("confirm-new-conversation-modal");
+      expect(modal).toBeInTheDocument();
+    });
+
+    it("should call endSession and close panel after confirming", async () => {
+      const user = userEvent.setup();
+      renderConversationPanel();
+
+      const newProjectButton = screen.getByTestId("new-conversation-button");
+      await user.click(newProjectButton);
+
+      const confirmButton = screen.getByText("Confirm");
+      await user.click(confirmButton);
+
+      expect(endSessionMock).toHaveBeenCalledOnce();
+      expect(onCloseMock).toHaveBeenCalledOnce();
+    });
+
+    it("should close the modal when cancelling", async () => {
+      const user = userEvent.setup();
+      renderConversationPanel();
+
+      const newProjectButton = screen.getByTestId("new-conversation-button");
+      await user.click(newProjectButton);
+
+      const cancelButton = screen.getByText("Cancel");
+      await user.click(cancelButton);
+
+      expect(endSessionMock).not.toHaveBeenCalled();
+      expect(
+        screen.queryByTestId("confirm-new-conversation-modal"),
+      ).not.toBeInTheDocument();
+    });
+  });
 });

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

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

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

@@ -115,7 +115,10 @@ describe("ModelSelector", () => {
   it("should have a default value if passed", async () => {
     render(<ModelSelector models={models} currentModel="azure/ada" />);
 
-    expect(screen.getByLabelText("LLM Provider")).toHaveValue("Azure");
-    expect(screen.getByLabelText("LLM Model")).toHaveValue("ada");
+    const providerInput = screen.getByLabelText("LLM Provider");
+    const modelInput = screen.getByLabelText("LLM Model");
+
+    expect(providerInput).toHaveAttribute("value", "Azure");
+    expect(modelInput).toHaveAttribute("value", "ada");
   });
 });

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

@@ -1,30 +0,0 @@
-import { describe, it, expect, vi } from "vitest";
-import { render, screen } from "@testing-library/react";
-import * as ChatSlice from "#/state/chat-slice";
-import {
-  updateStatusWhenErrorMessagePresent,
-} from "#/context/ws-client-provider";
-
-describe("Propagate error message", () => {
-  it("should do nothing when no message was passed from server", () => {
-    const addErrorMessageSpy = vi.spyOn(ChatSlice, "addErrorMessage");
-    updateStatusWhenErrorMessagePresent(null)
-    updateStatusWhenErrorMessagePresent(undefined)
-    updateStatusWhenErrorMessagePresent({})
-    updateStatusWhenErrorMessagePresent({message: null})
-
-    expect(addErrorMessageSpy).not.toHaveBeenCalled();
-  });
-
-  it("should display error to user when present", () => {
-    const message = "We have a problem!"
-    const addErrorMessageSpy = vi.spyOn(ChatSlice, "addErrorMessage")
-    updateStatusWhenErrorMessagePresent({message})
-
-    expect(addErrorMessageSpy).toHaveBeenCalledWith({
-      message,
-      status_update: true,
-      type: 'error'
-     });
-  });
-});

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

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

frontend/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "openhands-frontend",
-  "version": "0.19.0",
+  "version": "0.18.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "openhands-frontend",
-      "version": "0.19.0",
+      "version": "0.18.0",
       "dependencies": {
         "@monaco-editor/react": "^4.7.0-rc.0",
         "@nextui-org/react": "^2.6.10",
@@ -52,7 +52,7 @@
         "@playwright/test": "^1.49.1",
         "@react-router/dev": "^7.1.1",
         "@tailwindcss/typography": "^0.5.15",
-        "@tanstack/eslint-plugin-query": "^5.62.16",
+        "@tanstack/eslint-plugin-query": "^5.62.15",
         "@testing-library/jest-dom": "^6.6.1",
         "@testing-library/react": "^16.1.0",
         "@testing-library/user-event": "^14.5.2",
@@ -5344,9 +5344,9 @@
       }
     },
     "node_modules/@tanstack/eslint-plugin-query": {
-      "version": "5.62.16",
-      "resolved": "https://registry.npmjs.org/@tanstack/eslint-plugin-query/-/eslint-plugin-query-5.62.16.tgz",
-      "integrity": "sha512-VhnHSQ/hc62olLzGhlLJ4BJGWynwjs3cDMsByasKJ3zjW1YZ+6raxOv0gHHISm+VEnAY42pkMowmSWrXfL4NTw==",
+      "version": "5.62.15",
+      "resolved": "https://registry.npmjs.org/@tanstack/eslint-plugin-query/-/eslint-plugin-query-5.62.15.tgz",
+      "integrity": "sha512-24BHoF3LIzyptjrZXc1IpaISno+fhVD3zWWso/HPSB+ZVOyOXoiQSQc2K362T13JKJ07EInhHi1+KyNoRzCCfQ==",
       "dev": true,
       "dependencies": {
         "@typescript-eslint/utils": "^8.18.1"

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.19.0",
+  "version": "0.18.0",
   "private": true,
   "type": "module",
   "engines": {
@@ -79,7 +79,7 @@
     "@playwright/test": "^1.49.1",
     "@react-router/dev": "^7.1.1",
     "@tailwindcss/typography": "^0.5.15",
-    "@tanstack/eslint-plugin-query": "^5.62.16",
+    "@tanstack/eslint-plugin-query": "^5.62.15",
     "@testing-library/jest-dom": "^6.6.1",
     "@testing-library/react": "^16.1.0",
     "@testing-library/user-event": "^14.5.2",

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

@@ -65,7 +65,6 @@ export interface Conversation {
   title: string;
   selected_repository: string | null;
   last_updated_at: string;
-  created_at: string;
   status: ProjectStatus;
 }
 

frontend/src/components/features/conversation-panel/confirm-delete-modal.tsx

@@ -25,14 +25,10 @@ export function ConfirmDeleteModal({
         <div className="flex flex-col gap-2 w-full">
           <ModalButton
             onClick={onConfirm}
-            className="bg-danger font-bold"
+            className="bg-[#4465DB]"
             text="Confirm"
           />
-          <ModalButton
-            onClick={onCancel}
-            className="bg-neutral-500 font-bold"
-            text="Cancel"
-          />
+          <ModalButton onClick={onCancel} className="bg-danger" text="Cancel" />
         </div>
       </ModalBody>
     </ModalBackdrop>

frontend/src/components/features/conversation-panel/conversation-card-context-menu.tsx

@@ -1,32 +0,0 @@
-import { useClickOutsideElement } from "#/hooks/use-click-outside-element";
-import { ContextMenu } from "../context-menu/context-menu";
-import { ContextMenuListItem } from "../context-menu/context-menu-list-item";
-
-interface ConversationCardContextMenuProps {
-  onClose: () => void;
-  onDelete: (event: React.MouseEvent<HTMLButtonElement>) => void;
-  onEdit: (event: React.MouseEvent<HTMLButtonElement>) => void;
-}
-
-export function ConversationCardContextMenu({
-  onClose,
-  onDelete,
-  onEdit,
-}: ConversationCardContextMenuProps) {
-  const ref = useClickOutsideElement<HTMLUListElement>(onClose);
-
-  return (
-    <ContextMenu
-      ref={ref}
-      testId="context-menu"
-      className="left-full float-right"
-    >
-      <ContextMenuListItem testId="delete-button" onClick={onDelete}>
-        Delete
-      </ContextMenuListItem>
-      <ContextMenuListItem testId="edit-button" onClick={onEdit}>
-        Edit Title
-      </ContextMenuListItem>
-    </ContextMenu>
-  );
-}

frontend/src/components/features/conversation-panel/conversation-card.tsx

@@ -5,10 +5,11 @@ import {
   ProjectStatus,
   ConversationStateIndicator,
 } from "./conversation-state-indicator";
+import { ContextMenu } from "../context-menu/context-menu";
+import { ContextMenuListItem } from "../context-menu/context-menu-list-item";
 import { EllipsisButton } from "./ellipsis-button";
-import { ConversationCardContextMenu } from "./conversation-card-context-menu";
 
-interface ConversationCardProps {
+interface ProjectCardProps {
   onClick: () => void;
   onDelete: () => void;
   onChangeTitle: (title: string) => void;
@@ -26,9 +27,8 @@ export function ConversationCard({
   selectedRepository,
   lastUpdatedAt,
   status = "STOPPED",
-}: ConversationCardProps) {
+}: ProjectCardProps) {
   const [contextMenuVisible, setContextMenuVisible] = React.useState(false);
-  const [titleMode, setTitleMode] = React.useState<"view" | "edit">("view");
   const inputRef = React.useRef<HTMLInputElement>(null);
 
   const handleBlur = () => {
@@ -40,8 +40,6 @@ export function ConversationCard({
       // reset the value if it's empty
       inputRef.current!.value = title;
     }
-
-    setTitleMode("view");
   };
 
   const handleKeyUp = (event: React.KeyboardEvent<HTMLInputElement>) => {
@@ -59,18 +57,6 @@ export function ConversationCard({
     onDelete();
   };
 
-  const handleEdit = (event: React.MouseEvent<HTMLButtonElement>) => {
-    event.stopPropagation();
-    setTitleMode("edit");
-    setContextMenuVisible(false);
-  };
-
-  React.useEffect(() => {
-    if (titleMode === "edit") {
-      inputRef.current?.focus();
-    }
-  }, [titleMode]);
-
   return (
     <div
       data-testid="conversation-card"
@@ -79,9 +65,8 @@ export function ConversationCard({
     >
       <div className="flex items-center justify-between space-x-1">
         <input
-          data-testid="conversation-card-title"
           ref={inputRef}
-          disabled={titleMode === "view"}
+          data-testid="conversation-card-title"
           onClick={handleInputClick}
           onBlur={handleBlur}
           onKeyUp={handleKeyUp}
@@ -101,11 +86,11 @@ export function ConversationCard({
         </div>
       </div>
       {contextMenuVisible && (
-        <ConversationCardContextMenu
-          onClose={() => setContextMenuVisible(false)}
-          onDelete={handleDelete}
-          onEdit={handleEdit}
-        />
+        <ContextMenu testId="context-menu" className="left-full float-right">
+          <ContextMenuListItem testId="delete-button" onClick={handleDelete}>
+            Delete
+          </ContextMenuListItem>
+        </ContextMenu>
       )}
       {selectedRepository && (
         <ConversationRepoLink

frontend/src/components/features/conversation-panel/conversation-panel-wrapper.tsx

@@ -1,22 +0,0 @@
-import ReactDOM from "react-dom";
-
-interface ConversationPanelWrapperProps {
-  isOpen: boolean;
-}
-
-export function ConversationPanelWrapper({
-  isOpen,
-  children,
-}: React.PropsWithChildren<ConversationPanelWrapperProps>) {
-  if (!isOpen) return null;
-
-  const portalTarget = document.getElementById("root-outlet");
-  if (!portalTarget) return null;
-
-  return ReactDOM.createPortal(
-    <div className="absolute h-full w-full left-0 top-0 z-20 bg-black/80 rounded-xl">
-      {children}
-    </div>,
-    portalTarget,
-  );
-}

frontend/src/components/features/conversation-panel/conversation-panel.tsx

@@ -1,14 +1,14 @@
 import React from "react";
-import { useNavigate, useParams } from "react-router";
+import { useLocation, useNavigate, useParams } from "react-router";
 import { ConversationCard } from "./conversation-card";
 import { useUserConversations } from "#/hooks/query/use-user-conversations";
 import { useDeleteConversation } from "#/hooks/mutation/use-delete-conversation";
 import { ConfirmDeleteModal } from "./confirm-delete-modal";
+import { NewConversationButton } from "./new-conversation-button";
 import { LoadingSpinner } from "#/components/shared/loading-spinner";
 import { useUpdateConversation } from "#/hooks/mutation/use-update-conversation";
 import { useEndSession } from "#/hooks/use-end-session";
 import { ExitConversationModal } from "./exit-conversation-modal";
-import { useClickOutsideElement } from "#/hooks/use-click-outside-element";
 
 interface ConversationPanelProps {
   onClose: () => void;
@@ -17,8 +17,9 @@ interface ConversationPanelProps {
 export function ConversationPanel({ onClose }: ConversationPanelProps) {
   const { conversationId: cid } = useParams();
   const navigate = useNavigate();
+  const location = useLocation();
+
   const endSession = useEndSession();
-  const ref = useClickOutsideElement<HTMLDivElement>(onClose);
 
   const [confirmDeleteModalVisible, setConfirmDeleteModalVisible] =
     React.useState(false);
@@ -70,11 +71,15 @@ export function ConversationPanel({ onClose }: ConversationPanelProps) {
 
   return (
     <div
-      ref={ref}
       data-testid="conversation-panel"
       className="w-[350px] h-full border border-neutral-700 bg-neutral-800 rounded-xl overflow-y-auto"
     >
       <div className="pt-4 px-4 flex items-center justify-between">
+        {location.pathname.startsWith("/conversation") && (
+          <NewConversationButton
+            onClick={() => setConfirmExitConversationModalVisible(true)}
+          />
+        )}
         {isFetching && <LoadingSpinner size="small" />}
       </div>
       {error && (

frontend/src/components/features/project-menu/project-menu-details.tsx

@@ -16,24 +16,16 @@ export function ProjectMenuDetails({
 }: ProjectMenuDetailsProps) {
   const { t } = useTranslation();
   return (
-    <div className="flex flex-col min-w-0">
+    <div className="flex flex-col">
       <a
         href={`https://github.com/${repoName}`}
         target="_blank"
         rel="noreferrer noopener"
-        className="flex items-center gap-2 min-w-0"
+        className="flex items-center gap-2"
       >
-        {avatar && (
-          <img
-            src={avatar}
-            alt=""
-            className="w-4 h-4 rounded-full flex-shrink-0"
-          />
-        )}
-        <span className="text-sm leading-6 font-semibold truncate flex-1">
-          {repoName}
-        </span>
-        <ExternalLinkIcon width={16} height={16} className="flex-shrink-0" />
+        {avatar && <img src={avatar} alt="" className="w-4 h-4 rounded-full" />}
+        <span className="text-sm leading-6 font-semibold">{repoName}</span>
+        <ExternalLinkIcon width={16} height={16} />
       </a>
       <a
         href={lastCommit.html_url}

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

@@ -1,6 +1,6 @@
 import React from "react";
+import { useLocation } from "react-router";
 import { FaListUl } from "react-icons/fa";
-import { useDispatch } from "react-redux";
 import { useAuth } from "#/context/auth-context";
 import { useGitHubUser } from "#/hooks/query/use-github-user";
 import { useIsAuthed } from "#/hooks/query/use-is-authed";
@@ -11,20 +11,15 @@ import { ExitProjectButton } from "#/components/shared/buttons/exit-project-butt
 import { SettingsButton } from "#/components/shared/buttons/settings-button";
 import { LoadingSpinner } from "#/components/shared/loading-spinner";
 import { AccountSettingsModal } from "#/components/shared/modals/account-settings/account-settings-modal";
+import { ExitProjectConfirmationModal } from "#/components/shared/modals/exit-project-confirmation-modal";
 import { SettingsModal } from "#/components/shared/modals/settings/settings-modal";
 import { useSettingsUpToDate } from "#/context/settings-up-to-date-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";
-import { setCurrentAgentState } from "#/state/agent-slice";
-import { AgentState } from "#/types/agent-state";
-import { TooltipButton } from "#/components/shared/buttons/tooltip-button";
-import { ConversationPanelWrapper } from "../conversation-panel/conversation-panel-wrapper";
 
 export function Sidebar() {
-  const dispatch = useDispatch();
-  const endSession = useEndSession();
+  const location = useLocation();
   const user = useGitHubUser();
   const { data: isAuthed } = useIsAuthed();
   const { logout } = useAuth();
@@ -34,9 +29,20 @@ export function Sidebar() {
   const [accountSettingsModalOpen, setAccountSettingsModalOpen] =
     React.useState(false);
   const [settingsModalIsOpen, setSettingsModalIsOpen] = React.useState(false);
-
+  const [startNewProjectModalIsOpen, setStartNewProjectModalIsOpen] =
+    React.useState(false);
   const [conversationPanelIsOpen, setConversationPanelIsOpen] =
     React.useState(false);
+  const conversationPanelRef = React.useRef<HTMLDivElement | null>(null);
+
+  const handleClick = (event: MouseEvent) => {
+    const conversationPanel = conversationPanelRef.current;
+    if (conversationPanelIsOpen && conversationPanel) {
+      if (!conversationPanel.contains(event.target as Node)) {
+        setConversationPanelIsOpen(false);
+      }
+    }
+  };
 
   React.useEffect(() => {
     // If the github token is invalid, open the account settings modal again
@@ -45,10 +51,12 @@ export function Sidebar() {
     }
   }, [user.isError]);
 
-  const handleEndSession = () => {
-    dispatch(setCurrentAgentState(AgentState.LOADING));
-    endSession();
-  };
+  React.useEffect(() => {
+    document.addEventListener("click", handleClick);
+    return () => {
+      document.removeEventListener("click", handleClick);
+    };
+  }, [conversationPanelIsOpen]);
 
   const handleAccountSettingsModalClose = () => {
     // If the user closes the modal without connecting to GitHub,
@@ -58,30 +66,22 @@ export function Sidebar() {
     setAccountSettingsModalOpen(false);
   };
 
+  const handleClickLogo = () => {
+    if (location.pathname.startsWith("/conversations/"))
+      setStartNewProjectModalIsOpen(true);
+  };
+
   const showSettingsModal =
     isAuthed && (!settingsAreUpToDate || settingsModalIsOpen);
 
   return (
     <>
-      <aside className="h-[40px] md:h-auto px-1 flex flex-row md:flex-col gap-1">
+      <aside className="h-[40px] md:h-auto px-1 flex flex-row md:flex-col gap-1 relative">
         <nav className="flex flex-row md:flex-col items-center gap-[18px]">
-          <div className="w-[34px] h-[34px] flex items-center justify-center mb-7">
-            <AllHandsLogoButton onClick={handleEndSession} />
+          <div className="w-[34px] h-[34px] flex items-center justify-center">
+            <AllHandsLogoButton onClick={handleClickLogo} />
           </div>
           {user.isLoading && <LoadingSpinner size="small" />}
-          <ExitProjectButton onClick={handleEndSession} />
-          {MULTI_CONVERSATION_UI && (
-            <TooltipButton
-              data-testid="toggle-conversation-panel"
-              tooltip="Conversations"
-              ariaLabel="Conversations"
-              onClick={() => setConversationPanelIsOpen((prev) => !prev)}
-            >
-              <FaListUl size={22} />
-            </TooltipButton>
-          )}
-          <DocsButton />
-          <SettingsButton onClick={() => setSettingsModalIsOpen(true)} />
           {!user.isLoading && (
             <UserActions
               user={
@@ -91,14 +91,35 @@ export function Sidebar() {
               onClickAccountSettings={() => setAccountSettingsModalOpen(true)}
             />
           )}
+          <SettingsButton onClick={() => setSettingsModalIsOpen(true)} />
+          {MULTI_CONVERSATION_UI && (
+            <button
+              data-testid="toggle-conversation-panel"
+              type="button"
+              onClick={() => setConversationPanelIsOpen((prev) => !prev)}
+            >
+              <FaListUl
+                width={28}
+                height={28}
+                fill={conversationPanelIsOpen ? "#FFE165" : "#FFFFFF"}
+              />
+            </button>
+          )}
+          <DocsButton />
+          <ExitProjectButton
+            onClick={() => setStartNewProjectModalIsOpen(true)}
+          />
         </nav>
 
         {conversationPanelIsOpen && (
-          <ConversationPanelWrapper isOpen={conversationPanelIsOpen}>
+          <div
+            ref={conversationPanelRef}
+            className="absolute h-full left-[calc(100%+12px)] top-0 z-20" // 12px padding (sidebar parent)
+          >
             <ConversationPanel
               onClose={() => setConversationPanelIsOpen(false)}
             />
-          </ConversationPanelWrapper>
+          </div>
         )}
       </aside>
 
@@ -112,6 +133,11 @@ export function Sidebar() {
             onClose={() => setSettingsModalIsOpen(false)}
           />
         ))}
+      {startNewProjectModalIsOpen && (
+        <ExitProjectConfirmationModal
+          onClose={() => setStartNewProjectModalIsOpen(false)}
+        />
+      )}
     </>
   );
 }

frontend/src/components/features/sidebar/user-avatar.tsx

@@ -1,8 +1,8 @@
+import { Tooltip } from "@nextui-org/react";
 import { LoadingSpinner } from "#/components/shared/loading-spinner";
 import DefaultUserAvatar from "#/icons/default-user.svg?react";
 import { cn } from "#/utils/utils";
 import { Avatar } from "./avatar";
-import { TooltipButton } from "#/components/shared/buttons/tooltip-button";
 
 interface UserAvatarProps {
   onClick: () => void;
@@ -11,11 +11,10 @@ interface UserAvatarProps {
 }
 
 export function UserAvatar({ onClick, avatarUrl, isLoading }: UserAvatarProps) {
-  return (
-    <TooltipButton
-      testId="user-avatar"
-      tooltip="Account settings"
-      ariaLabel="Account settings"
+  const buttonContent = (
+    <button
+      data-testid="user-avatar"
+      type="button"
       onClick={onClick}
       className={cn(
         "w-8 h-8 rounded-full flex items-center justify-center border-2 border-gray-200",
@@ -31,6 +30,12 @@ export function UserAvatar({ onClick, avatarUrl, isLoading }: UserAvatarProps) {
         />
       )}
       {isLoading && <LoadingSpinner size="small" />}
-    </TooltipButton>
+    </button>
+  );
+
+  return (
+    <Tooltip content="Account settings" closeDelay={100}>
+      {buttonContent}
+    </Tooltip>
   );
 }

frontend/src/components/layout/resizable-panel.tsx

@@ -1,11 +1,4 @@
-import React, {
-  CSSProperties,
-  JSX,
-  useCallback,
-  useEffect,
-  useRef,
-  useState,
-} from "react";
+import React, { CSSProperties, JSX, useEffect, useRef, useState } from "react";
 import {
   VscChevronDown,
   VscChevronLeft,
@@ -45,123 +38,129 @@ export function ResizablePanel({
   orientation,
   initialSize,
 }: ResizablePanelProps): JSX.Element {
-  const isHorizontal = orientation === Orientation.HORIZONTAL;
-  const [firstSize, setFirstSize] = useState(initialSize);
+  const [firstSize, setFirstSize] = useState<number>(initialSize);
   const [dividerPosition, setDividerPosition] = useState<number | null>(null);
-  const [collapse, setCollapse] = useState(Collapse.SPLIT);
   const firstRef = useRef<HTMLDivElement>(null);
   const secondRef = useRef<HTMLDivElement>(null);
+  const [collapse, setCollapse] = useState<Collapse>(Collapse.SPLIT);
+  const isHorizontal = orientation === Orientation.HORIZONTAL;
 
   useEffect(() => {
-    if (!dividerPosition) return undefined;
-
+    if (dividerPosition == null || !firstRef.current) {
+      return undefined;
+    }
+    const getFirstSizeFromEvent = (e: MouseEvent) => {
+      const position = isHorizontal ? e.clientX : e.clientY;
+      return firstSize + position - dividerPosition;
+    };
     const onMouseMove = (e: MouseEvent) => {
       e.preventDefault();
-      const delta = (isHorizontal ? e.clientX : e.clientY) - dividerPosition;
-      setFirstSize(firstSize + delta);
-      setDividerPosition(isHorizontal ? e.clientX : e.clientY);
+      const newFirstSize = `${getFirstSizeFromEvent(e)}px`;
+      const { current } = firstRef;
+      if (current) {
+        if (isHorizontal) {
+          current.style.width = newFirstSize;
+          current.style.minWidth = newFirstSize;
+        } else {
+          current.style.height = newFirstSize;
+          current.style.minHeight = newFirstSize;
+        }
+      }
     };
-
     const onMouseUp = (e: MouseEvent) => {
       e.preventDefault();
-      if (firstRef.current) firstRef.current.style.transition = "";
-      if (secondRef.current) secondRef.current.style.transition = "";
-      setFirstSize(
-        firstSize + ((isHorizontal ? e.clientX : e.clientY) - dividerPosition),
-      );
+      if (firstRef.current) {
+        firstRef.current.style.transition = "";
+      }
+      if (secondRef.current) {
+        secondRef.current.style.transition = "";
+      }
+      setFirstSize(getFirstSizeFromEvent(e));
       setDividerPosition(null);
+      document.removeEventListener("mousemove", onMouseMove);
+      document.removeEventListener("mouseup", onMouseUp);
     };
-
     document.addEventListener("mousemove", onMouseMove);
     document.addEventListener("mouseup", onMouseUp);
     return () => {
       document.removeEventListener("mousemove", onMouseMove);
       document.removeEventListener("mouseup", onMouseUp);
     };
-  }, [dividerPosition, firstSize, isHorizontal]);
+  }, [dividerPosition, firstSize, orientation]);
 
   const onMouseDown = (e: React.MouseEvent) => {
     e.preventDefault();
-    if (firstRef.current) firstRef.current.style.transition = "none";
-    if (secondRef.current) secondRef.current.style.transition = "none";
-    setDividerPosition(isHorizontal ? e.clientX : e.clientY);
+    if (firstRef.current) {
+      firstRef.current.style.transition = "none";
+    }
+    if (secondRef.current) {
+      secondRef.current.style.transition = "none";
+    }
+    const position = isHorizontal ? e.clientX : e.clientY;
+    setDividerPosition(position);
   };
 
-  const getPanelStyle = useCallback(
-    (isFirst: boolean): CSSProperties => {
-      const style: CSSProperties = { overflow: "hidden" };
-      const isHidden =
-        (isFirst && collapse === Collapse.COLLAPSED) ||
-        (!isFirst && collapse === Collapse.FILLED);
-
-      const hiddenStyle: CSSProperties = {
-        ...style,
-        opacity: 0,
-        width: 0,
-        minWidth: 0,
-        height: 0,
-        minHeight: 0,
-      };
-
-      const expandedStyle: CSSProperties = { ...style, flexGrow: 1 };
-
-      if (isHidden) {
-        return hiddenStyle;
+  const getStyleForFirst = () => {
+    const style: CSSProperties = { overflow: "hidden" };
+    if (collapse === Collapse.COLLAPSED) {
+      style.opacity = 0;
+      style.width = 0;
+      style.minWidth = 0;
+      style.height = 0;
+      style.minHeight = 0;
+    } else if (collapse === Collapse.SPLIT) {
+      const firstSizePx = `${firstSize}px`;
+      if (isHorizontal) {
+        style.width = firstSizePx;
+        style.minWidth = firstSizePx;
+      } else {
+        style.height = firstSizePx;
+        style.minHeight = firstSizePx;
       }
+    } else {
+      style.flexGrow = 1;
+    }
+    return style;
+  };
 
-      if (collapse !== Collapse.SPLIT) {
-        return expandedStyle;
-      }
+  const getStyleForSecond = () => {
+    const style: CSSProperties = { overflow: "hidden" };
+    if (collapse === Collapse.FILLED) {
+      style.opacity = 0;
+      style.width = 0;
+      style.minWidth = 0;
+      style.height = 0;
+      style.minHeight = 0;
+    } else if (collapse === Collapse.SPLIT) {
+      style.flexGrow = 1;
+    } else {
+      style.flexGrow = 1;
+    }
+    return style;
+  };
 
-      if (isFirst) {
-        const dimension = isHorizontal ? "width" : "height";
-        const minDimension = isHorizontal ? "minWidth" : "minHeight";
-        const maxDimension = isHorizontal ? "maxWidth" : "maxHeight";
+  const onCollapse = () => {
+    if (collapse === Collapse.SPLIT) {
+      setCollapse(Collapse.COLLAPSED);
+    } else {
+      setCollapse(Collapse.SPLIT);
+    }
+  };
 
-        const firstPanelStyle: CSSProperties = {
-          ...style,
-          [dimension]: `${firstSize}px`,
-          [minDimension]: isHorizontal ? "350px" : "300px",
-          [maxDimension]: isHorizontal ? "50%" : "70%",
-          flexShrink: 0,
-        };
-        return firstPanelStyle;
-      }
-
-      const secondPanelStyle: CSSProperties = {
-        ...style,
-        flexGrow: 1,
-        flexShrink: 1,
-        ...(isHorizontal
-          ? {
-              minWidth: "30%",
-              maxWidth: "70%",
-            }
-          : {
-              minHeight: "300px",
-              display: "flex",
-              flexDirection: "column",
-            }),
-      };
-      return secondPanelStyle;
-    },
-    [collapse, firstSize, isHorizontal],
-  );
-
-  const toggleCollapse = () =>
-    setCollapse(
-      collapse === Collapse.SPLIT ? Collapse.COLLAPSED : Collapse.SPLIT,
-    );
-
-  const toggleExpand = () =>
-    setCollapse(collapse === Collapse.SPLIT ? Collapse.FILLED : Collapse.SPLIT);
+  const onExpand = () => {
+    if (collapse === Collapse.SPLIT) {
+      setCollapse(Collapse.FILLED);
+    } else {
+      setCollapse(Collapse.SPLIT);
+    }
+  };
 
   return (
     <div className={twMerge("flex", !isHorizontal && "flex-col", className)}>
       <div
         ref={firstRef}
         className={twMerge(firstClassName, "transition-all ease-soft-spring")}
-        style={getPanelStyle(true)}
+        style={getStyleForFirst()}
       >
         {firstChild}
       </div>
@@ -172,18 +171,18 @@ export function ResizablePanel({
         <IconButton
           icon={isHorizontal ? <VscChevronLeft /> : <VscChevronUp />}
           ariaLabel="Collapse"
-          onClick={toggleCollapse}
+          onClick={onCollapse}
         />
         <IconButton
           icon={isHorizontal ? <VscChevronRight /> : <VscChevronDown />}
           ariaLabel="Expand"
-          onClick={toggleExpand}
+          onClick={onExpand}
         />
       </div>
       <div
         ref={secondRef}
         className={twMerge(secondClassName, "transition-all ease-soft-spring")}
-        style={getPanelStyle(false)}
+        style={getStyleForSecond()}
       >
         {secondChild}
       </div>

frontend/src/components/shared/buttons/all-hands-logo-button.tsx

@@ -12,7 +12,7 @@ export function AllHandsLogoButton({ onClick }: AllHandsLogoButtonProps) {
       ariaLabel="All Hands Logo"
       onClick={onClick}
     >
-      <AllHandsLogo width={44} height={30} />
+      <AllHandsLogo width={34} height={23} />
     </TooltipButton>
   );
 }

frontend/src/components/shared/buttons/exit-project-button.tsx

@@ -13,7 +13,7 @@ export function ExitProjectButton({ onClick }: ExitProjectButtonProps) {
       onClick={onClick}
       testId="new-project-button"
     >
-      <NewProjectIcon width={26} height={26} />
+      <NewProjectIcon width={28} height={28} />
     </TooltipButton>
   );
 }

frontend/src/components/shared/buttons/settings-button.tsx

@@ -1,4 +1,4 @@
-import { FaCog } from "react-icons/fa";
+import CogTooth from "#/assets/cog-tooth";
 import { TooltipButton } from "./tooltip-button";
 
 interface SettingsButtonProps {
@@ -13,7 +13,7 @@ export function SettingsButton({ onClick }: SettingsButtonProps) {
       ariaLabel="Settings"
       onClick={onClick}
     >
-      <FaCog size={24} />
+      <CogTooth />
     </TooltipButton>
   );
 }

frontend/src/components/shared/buttons/tooltip-button.tsx

@@ -1,6 +1,5 @@
 import { Tooltip } from "@nextui-org/react";
-import React, { ReactNode } from "react";
-import { cn } from "#/utils/utils";
+import { ReactNode } from "react";
 
 interface TooltipButtonProps {
   children: ReactNode;
@@ -9,7 +8,6 @@ interface TooltipButtonProps {
   href?: string;
   ariaLabel: string;
   testId?: string;
-  className?: React.HTMLAttributes<HTMLButtonElement>["className"];
 }
 
 export function TooltipButton({
@@ -19,7 +17,6 @@ export function TooltipButton({
   href,
   ariaLabel,
   testId,
-  className,
 }: TooltipButtonProps) {
   const buttonContent = (
     <button
@@ -27,7 +24,7 @@ export function TooltipButton({
       aria-label={ariaLabel}
       data-testid={testId}
       onClick={onClick}
-      className={cn("hover:opacity-80", className)}
+      className="w-8 h-8 rounded-full hover:opacity-80 flex items-center justify-center"
     >
       {children}
     </button>
@@ -38,7 +35,7 @@ export function TooltipButton({
       href={href}
       target="_blank"
       rel="noreferrer noopener"
-      className={cn("hover:opacity-80", className)}
+      className="w-8 h-8 rounded-full hover:opacity-80 flex items-center justify-center"
       aria-label={ariaLabel}
     >
       {children}
@@ -48,7 +45,7 @@ export function TooltipButton({
   );
 
   return (
-    <Tooltip content={tooltip} closeDelay={100} placement="right">
+    <Tooltip content={tooltip} closeDelay={100}>
       {content}
     </Tooltip>
   );

frontend/src/components/shared/modals/settings/model-selector.tsx

@@ -2,6 +2,7 @@ import {
   Autocomplete,
   AutocompleteItem,
   AutocompleteSection,
+  Tooltip,
 } from "@nextui-org/react";
 import React from "react";
 import { mapProvider } from "#/utils/map-provider";
@@ -63,7 +64,7 @@ export function ModelSelector({
   return (
     <div data-testid="model-selector" className="flex flex-col gap-2">
       <div className="flex flex-row gap-3">
-        <fieldset className="flex flex-col gap-2">
+        <fieldset className="flex flex-col gap-2 w-1/2">
           <label htmlFor="agent" className="font-[500] text-[#A3A3A3] text-xs">
             LLM Provider
           </label>
@@ -113,7 +114,7 @@ export function ModelSelector({
           </Autocomplete>
         </fieldset>
 
-        <fieldset className="flex flex-col gap-2">
+        <fieldset className="flex flex-col gap-2 w-1/2">
           <label htmlFor="agent" className="font-[500] text-[#A3A3A3] text-xs">
             LLM Model
           </label>
@@ -142,7 +143,9 @@ export function ModelSelector({
                 .filter((model) => VERIFIED_MODELS.includes(model))
                 .map((model) => (
                   <AutocompleteItem key={model} value={model}>
-                    {model}
+                    <Tooltip content={model}>
+                      <span>{model}</span>
+                    </Tooltip>
                   </AutocompleteItem>
                 ))}
             </AutocompleteSection>
@@ -155,7 +158,9 @@ export function ModelSelector({
                     key={model}
                     value={model}
                   >
-                    {model}
+                    <Tooltip content={model}>
+                      <span>{model}</span>
+                    </Tooltip>
                   </AutocompleteItem>
                 ))}
             </AutocompleteSection>

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

@@ -2,10 +2,7 @@ import posthog from "posthog-js";
 import React from "react";
 import { io, Socket } from "socket.io-client";
 import EventLogger from "#/utils/event-logger";
-import {
-  handleAssistantMessage,
-  handleStatusMessage,
-} from "#/services/actions";
+import { handleAssistantMessage } from "#/services/actions";
 import { useRate } from "#/hooks/use-rate";
 import { OpenHandsParsedEvent } from "#/types/core";
 import {
@@ -67,21 +64,6 @@ interface WsClientProviderProps {
   conversationId: string;
 }
 
-export function updateStatusWhenErrorMessagePresent(data: unknown) {
-  if (
-    data &&
-    typeof data === "object" &&
-    "message" in data &&
-    typeof data.message === "string"
-  ) {
-    handleStatusMessage({
-      type: "error",
-      message: data.message,
-      status_update: true,
-    });
-  }
-}
-
 export function WsClientProvider({
   conversationId,
   children,
@@ -119,7 +101,7 @@ export function WsClientProvider({
     handleAssistantMessage(event);
   }
 
-  function handleDisconnect(data: unknown) {
+  function handleDisconnect() {
     setStatus(WsClientProviderStatus.DISCONNECTED);
     const sio = sioRef.current;
     if (!sio) {
@@ -127,13 +109,11 @@ export function WsClientProvider({
     }
     sio.io.opts.query = sio.io.opts.query || {};
     sio.io.opts.query.latest_event_id = lastEventRef.current?.id;
-    updateStatusWhenErrorMessagePresent(data);
   }
 
-  function handleError(data: unknown) {
-    setStatus(WsClientProviderStatus.DISCONNECTED);
-    updateStatusWhenErrorMessagePresent(data);
+  function handleError() {
     posthog.capture("socket_error");
+    setStatus(WsClientProviderStatus.DISCONNECTED);
   }
 
   React.useEffect(() => {

frontend/src/hooks/mutation/use-create-conversation.ts

@@ -13,18 +13,13 @@ export const useCreateConversation = () => {
   const { gitHubToken } = useAuth();
   const queryClient = useQueryClient();
 
-  const { selectedRepository, files, importedProjectZip } = useSelector(
+  const { selectedRepository, files } = useSelector(
     (state: RootState) => state.initialQuery,
   );
 
   return useMutation({
     mutationFn: (variables: { q?: string }) => {
-      if (
-        !variables.q?.trim() &&
-        !selectedRepository &&
-        files.length === 0 &&
-        !importedProjectZip
-      ) {
+      if (!variables.q?.trim() && !selectedRepository && files.length === 0) {
         throw new Error("No query provided");
       }
 

frontend/src/hooks/mutation/use-upload-files.ts

@@ -1,16 +0,0 @@
-import { useMutation } from "@tanstack/react-query";
-import OpenHands from "#/api/open-hands";
-import { useConversation } from "#/context/conversation-context";
-
-type UploadFilesArgs = {
-  files: File[];
-};
-
-export const useUploadFiles = () => {
-  const { conversationId } = useConversation();
-
-  return useMutation({
-    mutationFn: ({ files }: UploadFilesArgs) =>
-      OpenHands.uploadFiles(conversationId, files),
-  });
-};

frontend/src/mocks/handlers.ts

@@ -1,9 +1,5 @@
 import { delay, http, HttpResponse } from "msw";
-import {
-  GetConfigResponse,
-  Conversation,
-  ResultSet,
-} from "#/api/open-hands.types";
+import { GetConfigResponse, Conversation } from "#/api/open-hands.types";
 import { DEFAULT_SETTINGS } from "#/services/settings";
 
 const userPreferences = {
@@ -24,7 +20,6 @@ const conversations: Conversation[] = [
     title: "My New Project",
     selected_repository: null,
     last_updated_at: new Date().toISOString(),
-    created_at: new Date().toISOString(),
     status: "RUNNING",
   },
   {
@@ -35,7 +30,6 @@ const conversations: Conversation[] = [
     last_updated_at: new Date(
       Date.now() - 2 * 24 * 60 * 60 * 1000,
     ).toISOString(),
-    created_at: new Date(Date.now() - 2 * 24 * 60 * 60 * 1000).toISOString(),
     status: "STOPPED",
   },
   {
@@ -46,7 +40,6 @@ const conversations: Conversation[] = [
     last_updated_at: new Date(
       Date.now() - 5 * 24 * 60 * 60 * 1000,
     ).toISOString(),
-    created_at: new Date(Date.now() - 5 * 24 * 60 * 60 * 1000).toISOString(),
     status: "STOPPED",
   },
 ];
@@ -193,15 +186,12 @@ export const handlers = [
 
   http.get("/api/options/config", () => HttpResponse.json({ APP_MODE: "oss" })),
 
-  http.get("/api/conversations", async () => {
-    const values = Array.from(CONVERSATIONS.values());
-    const results: ResultSet<Conversation> = {
-      results: values,
+  http.get("/api/conversations?limit=9", async () =>
+    HttpResponse.json({
+      results: Array.from(CONVERSATIONS.values()),
       next_page_id: null,
-    };
-
-    return HttpResponse.json(results, { status: 200 });
-  }),
+    }),
+  ),
 
   http.delete("/api/conversations/:conversationId", async ({ params }) => {
     const { conversationId } = params;
@@ -244,7 +234,6 @@ export const handlers = [
       title: "New Conversation",
       selected_repository: null,
       last_updated_at: new Date().toISOString(),
-      created_at: new Date().toISOString(),
       status: "RUNNING",
     };
 

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

@@ -29,7 +29,10 @@ function Home() {
   const latestConversation = localStorage.getItem("latest_conversation_id");
 
   return (
-    <div className="bg-root-secondary h-full rounded-xl flex flex-col items-center justify-center relative overflow-y-auto px-2">
+    <div
+      data-testid="root-index"
+      className="bg-root-secondary h-full rounded-xl flex flex-col items-center justify-center relative overflow-y-auto px-2"
+    >
       <HeroHeading />
       <div className="flex flex-col gap-8 w-full md:w-[600px] items-center">
         <div className="flex flex-col gap-2 w-full">

frontend/src/routes/_oh.app/hooks/use-handle-runtime-active.ts

@@ -1,13 +1,9 @@
 import React from "react";
-import toast from "react-hot-toast";
-import { useDispatch, useSelector } from "react-redux";
+import { useSelector } from "react-redux";
 import { useAuth } from "#/context/auth-context";
 import { useWsClient } from "#/context/ws-client-provider";
 import { getGitHubTokenCommand } from "#/services/terminal-service";
-import { setImportedProjectZip } from "#/state/initial-query-slice";
 import { RootState } from "#/store";
-import { base64ToBlob } from "#/utils/base64-to-blob";
-import { useUploadFiles } from "../../../hooks/mutation/use-upload-files";
 import { useGitHubUser } from "../../../hooks/query/use-github-user";
 import { isGitHubErrorReponse } from "#/api/github-axios-instance";
 import { RUNTIME_INACTIVE_STATES } from "#/types/agent-state";
@@ -15,50 +11,21 @@ import { RUNTIME_INACTIVE_STATES } from "#/types/agent-state";
 export const useHandleRuntimeActive = () => {
   const { gitHubToken } = useAuth();
   const { send } = useWsClient();
-
-  const dispatch = useDispatch();
-
-  const { data: user } = useGitHubUser();
-  const { mutate: uploadFiles } = useUploadFiles();
   const { curAgentState } = useSelector((state: RootState) => state.agent);
 
-  const runtimeActive = !RUNTIME_INACTIVE_STATES.includes(curAgentState);
+  const { data: user } = useGitHubUser();
 
-  const { importedProjectZip } = useSelector(
-    (state: RootState) => state.initialQuery,
-  );
+  const runtimeActive = !RUNTIME_INACTIVE_STATES.includes(curAgentState);
 
   const userId = React.useMemo(() => {
     if (user && !isGitHubErrorReponse(user)) return user.id;
     return null;
   }, [user]);
 
-  const handleUploadFiles = (zip: string) => {
-    const blob = base64ToBlob(zip);
-    const file = new File([blob], "imported-project.zip", {
-      type: blob.type,
-    });
-    uploadFiles(
-      { files: [file] },
-      {
-        onError: () => {
-          toast.error("Failed to upload project files.");
-        },
-      },
-    );
-    dispatch(setImportedProjectZip(null));
-  };
-
   React.useEffect(() => {
     if (runtimeActive && userId && gitHubToken) {
       // Export if the user valid, this could happen mid-session so it is handled here
       send(getGitHubTokenCommand(gitHubToken));
     }
   }, [userId, gitHubToken, runtimeActive]);
-
-  React.useEffect(() => {
-    if (runtimeActive && importedProjectZip) {
-      handleUploadFiles(importedProjectZip);
-    }
-  }, [runtimeActive, importedProjectZip]);
 };

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

@@ -122,7 +122,7 @@ function AppContent() {
       <ResizablePanel
         orientation={Orientation.HORIZONTAL}
         className="grow h-full min-h-0 min-w-0"
-        initialSize={window.innerWidth * 0.3} // 30% of window width
+        initialSize={500}
         firstClassName="rounded-xl overflow-hidden border border-neutral-600 bg-neutral-800"
         secondClassName="flex flex-col overflow-hidden"
         firstChild={<ChatInterface />}
@@ -130,7 +130,7 @@ function AppContent() {
           <ResizablePanel
             orientation={Orientation.VERTICAL}
             className="grow h-full min-h-0 min-w-0"
-            initialSize={window.innerHeight * 0.7} // 70% of window height for workspace, 30% for terminal
+            initialSize={500}
             firstClassName="rounded-xl overflow-hidden border border-neutral-600"
             secondClassName="flex flex-col overflow-hidden"
             firstChild={

frontend/src/routes/_oh/route.tsx

@@ -78,10 +78,7 @@ export default function MainApp() {
     >
       <Sidebar />
 
-      <div
-        id="root-outlet"
-        className="h-[calc(100%-50px)] md:h-full w-full relative"
-      >
+      <div className="h-[calc(100%-50px)] md:h-full w-full relative">
         <Outlet />
       </div>
 

frontend/src/services/actions.ts

@@ -75,7 +75,6 @@ export function handleActionMessage(message: ActionMessage) {
     if (message.args && message.args.thought) {
       store.dispatch(addAssistantMessage(message.args.thought));
     }
-    // Need to convert ActionMessage to RejectAction
     // @ts-expect-error TODO: fix
     store.dispatch(addAssistantAction(message));
   }

frontend/src/state/chat-slice.ts

@@ -73,7 +73,7 @@ export const chatSlice = createSlice({
       state.messages.push(message);
     },
 
-    addAssistantMessage(state: SliceState, action: PayloadAction<string>) {
+    addAssistantMessage(state, action: PayloadAction<string>) {
       const message: Message = {
         type: "thought",
         sender: "assistant",
@@ -85,10 +85,7 @@ export const chatSlice = createSlice({
       state.messages.push(message);
     },
 
-    addAssistantAction(
-      state: SliceState,
-      action: PayloadAction<OpenHandsAction>,
-    ) {
+    addAssistantAction(state, action: PayloadAction<OpenHandsAction>) {
       const actionID = action.payload.action;
       if (!HANDLED_ACTIONS.includes(actionID)) {
         return;
@@ -128,7 +125,7 @@ export const chatSlice = createSlice({
     },
 
     addAssistantObservation(
-      state: SliceState,
+      state,
       observation: PayloadAction<OpenHandsObservation>,
     ) {
       const observationID = observation.payload.observation;
@@ -182,7 +179,7 @@ export const chatSlice = createSlice({
     },
 
     addErrorMessage(
-      state: SliceState,
+      state,
       action: PayloadAction<{ id?: string; message: string }>,
     ) {
       const { id, message } = action.payload;
@@ -195,7 +192,7 @@ export const chatSlice = createSlice({
       });
     },
 
-    clearMessages(state: SliceState) {
+    clearMessages(state) {
       state.messages = [];
     },
   },

frontend/src/types/message.tsx

@@ -43,6 +43,6 @@ export interface ObservationMessage {
 export interface StatusMessage {
   status_update: true;
   type: string;
-  id?: string;
+  id: string;
   message: string;
 }

frontend/src/utils/base64-to-blob.ts

@@ -1,25 +1,19 @@
 export const base64ToBlob = (base64: string) => {
   // Remove the prefix (e.g. data:image/png;base64,)
-  const base64WithoutPrefix = base64.split(",")[1] || base64;
+  const base64WithoutPrefix = base64.split(",")[1];
 
   // Decode to bytes
   const bytes = atob(base64WithoutPrefix);
 
-  // Process in chunks to avoid memory issues
-  const chunkSize = 8192; // Process 8KB at a time
-  const chunks = [];
-
-  for (let i = 0; i < bytes.length; i += chunkSize) {
-    const chunk = bytes.slice(i, i + chunkSize);
-    const array = new Uint8Array(chunk.length);
-
-    for (let j = 0; j < chunk.length; j += 1) {
-      array[j] = chunk.charCodeAt(j);
-    }
-
-    chunks.push(array);
+  // Create an array of byte values
+  const byteNumbers = new Array(bytes.length);
+  for (let i = 0; i < bytes.length; i += 1) {
+    byteNumbers[i] = bytes.charCodeAt(i);
   }
 
-  // Create a Blob from all chunks
-  return new Blob(chunks, { type: "application/zip" });
+  // Convert to Uint8Array
+  const array = new Uint8Array(byteNumbers);
+
+  // Create a Blob
+  return new Blob([array], { type: "application/zip" });
 };

openhands/agenthub/codeact_agent/codeact_agent.py

@@ -24,7 +24,6 @@ from openhands.events.action import (
     MessageAction,
 )
 from openhands.events.observation import (
-    AgentCondensationObservation,
     AgentDelegateObservation,
     BrowserOutputObservation,
     CmdOutputObservation,
@@ -37,7 +36,6 @@ from openhands.events.observation.error import ErrorObservation
 from openhands.events.observation.observation import Observation
 from openhands.events.serialization.event import truncate_content
 from openhands.llm.llm import LLM
-from openhands.memory.condenser import Condenser
 from openhands.runtime.plugins import (
     AgentSkillsRequirement,
     JupyterRequirement,
@@ -117,9 +115,6 @@ class CodeActAgent(Agent):
             disabled_microagents=self.config.disabled_microagents,
         )
 
-        self.condenser = Condenser.from_config(self.config.condenser)
-        logger.debug(f'Using condenser: {self.condenser}')
-
     def get_action_message(
         self,
         action: Action,
@@ -327,9 +322,6 @@ class CodeActAgent(Agent):
             text = 'OBSERVATION:\n' + truncate_content(obs.content, max_message_chars)
             text += '\n[Last action has been rejected by the user]'
             message = Message(role='user', content=[TextContent(text=text)])
-        elif isinstance(obs, AgentCondensationObservation):
-            text = truncate_content(obs.content, max_message_chars)
-            message = Message(role='user', content=[TextContent(text=text)])
         else:
             # If an observation message is not returned, it will cause an error
             # when the LLM tries to return the next message
@@ -450,10 +442,7 @@ class CodeActAgent(Agent):
 
         pending_tool_call_action_messages: dict[str, Message] = {}
         tool_call_id_to_message: dict[str, Message] = {}
-
-        # Condense the events from the state.
-        events = self.condenser.condensed_history(state)
-
+        events = list(state.history)
         for event in events:
             # create a regular message from an event
             if isinstance(event, Action):

openhands/controller/agent_controller.py

@@ -217,7 +217,7 @@ class AgentController:
             reported = RuntimeError(
                 'There was an unexpected error while running the agent. Please '
                 f'report this error to the developers. Your session ID is {self.id}. '
-                f'Error type: {e.__class__.__name__}'
+                f'Exception: {e}.'
             )
             if isinstance(e, litellm.AuthenticationError) or isinstance(
                 e, litellm.BadRequestError
@@ -993,12 +993,10 @@ class AgentController:
 
     def __repr__(self):
         return (
-            f'AgentController(id={getattr(self, "id", "<uninitialized>")}, '
-            f'agent={getattr(self, "agent", "<uninitialized>")!r}, '
-            f'event_stream={getattr(self, "event_stream", "<uninitialized>")!r}, '
-            f'state={getattr(self, "state", "<uninitialized>")!r}, '
-            f'delegate={getattr(self, "delegate", "<uninitialized>")!r}, '
-            f'_pending_action={getattr(self, "_pending_action", "<uninitialized>")!r})'
+            f'AgentController(id={self.id}, agent={self.agent!r}, '
+            f'event_stream={self.event_stream!r}, '
+            f'state={self.state!r}, '
+            f'delegate={self.delegate!r}, _pending_action={self._pending_action!r})'
         )
 
     def _is_awaiting_observation(self):

openhands/core/config/agent_config.py

@@ -1,6 +1,5 @@
-from dataclasses import dataclass, field, fields
+from dataclasses import dataclass, fields
 
-from openhands.core.config.condenser_config import CondenserConfig, NoOpCondenserConfig
 from openhands.core.config.config_utils import get_field_info
 
 
@@ -19,7 +18,6 @@ class AgentConfig:
         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.
         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
@@ -31,7 +29,6 @@ class AgentConfig:
     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."""

openhands/core/config/condenser_config.py

@@ -1,90 +0,0 @@
-from typing import Literal
-
-from pydantic import BaseModel, Field
-
-from openhands.core.config.llm_config import LLMConfig
-
-
-class NoOpCondenserConfig(BaseModel):
-    """Configuration for NoOpCondenser."""
-
-    type: Literal['noop'] = Field('noop')
-
-
-class ObservationMaskingCondenserConfig(BaseModel):
-    """Configuration for ObservationMaskingCondenser."""
-
-    type: Literal['observation_masking'] = Field('observation_masking')
-    attention_window: int = Field(
-        default=10,
-        description='The number of most-recent events where observations will not be masked.',
-        ge=1,
-    )
-
-
-class RecentEventsCondenserConfig(BaseModel):
-    """Configuration for RecentEventsCondenser."""
-
-    type: Literal['recent'] = Field('recent')
-    keep_first: int = Field(
-        default=0,
-        description='The number of initial events to condense.',
-        ge=0,
-    )
-    max_events: int = Field(
-        default=10, description='Maximum number of events to keep.', ge=1
-    )
-
-
-class LLMSummarizingCondenserConfig(BaseModel):
-    """Configuration for LLMCondenser."""
-
-    type: Literal['llm'] = Field('llm')
-    llm_config: LLMConfig = Field(
-        ..., description='Configuration for the LLM to use for condensing.'
-    )
-
-
-class AmortizedForgettingCondenserConfig(BaseModel):
-    """Configuration for AmortizedForgettingCondenser."""
-
-    type: Literal['amortized'] = Field('amortized')
-    max_size: int = Field(
-        default=100,
-        description='Maximum size of the condensed history before triggering forgetting.',
-        ge=2,
-    )
-    keep_first: int = Field(
-        default=0,
-        description='Number of initial events to always keep in history.',
-        ge=0,
-    )
-
-
-class LLMAttentionCondenserConfig(BaseModel):
-    """Configuration for LLMAttentionCondenser."""
-
-    type: Literal['llm_attention'] = Field('llm_attention')
-    llm_config: LLMConfig = Field(
-        ..., description='Configuration for the LLM to use for attention.'
-    )
-    max_size: int = Field(
-        default=100,
-        description='Maximum size of the condensed history before triggering forgetting.',
-        ge=2,
-    )
-    keep_first: int = Field(
-        default=0,
-        description='Number of initial events to always keep in history.',
-        ge=0,
-    )
-
-
-CondenserConfig = (
-    NoOpCondenserConfig
-    | ObservationMaskingCondenserConfig
-    | RecentEventsCondenserConfig
-    | LLMSummarizingCondenserConfig
-    | AmortizedForgettingCondenserConfig
-    | LLMAttentionCondenserConfig
-)

openhands/core/config/sandbox_config.py

@@ -35,8 +35,6 @@ class SandboxConfig:
         remote_runtime_resource_factor: Factor to scale the resource allocation for remote runtime.
             Must be one of [1, 2, 4, 8]. Will only be used if the runtime is remote.
         enable_gpu: Whether to enable GPU.
-        docker_runtime_kwargs: Additional keyword arguments to pass to the Docker runtime when running containers.
-            This should be a JSON string that will be parsed into a dictionary.
     """
 
     remote_runtime_api_url: str = 'http://localhost:8000'
@@ -63,7 +61,6 @@ class SandboxConfig:
     close_delay: int = 900
     remote_runtime_resource_factor: int = 1
     enable_gpu: bool = False
-    docker_runtime_kwargs: 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."""

openhands/core/schema/observation.py

@@ -44,8 +44,5 @@ class ObservationTypeSchema(BaseModel):
 
     USER_REJECTED: str = Field(default='user_rejected')
 
-    CONDENSE: str = Field(default='condense')
-    """Result of a condensation operation."""
-
 
 ObservationType = ObservationTypeSchema()

openhands/events/observation/__init__.py

@@ -1,7 +1,4 @@
-from openhands.events.observation.agent import (
-    AgentCondensationObservation,
-    AgentStateChangedObservation,
-)
+from openhands.events.observation.agent import AgentStateChangedObservation
 from openhands.events.observation.browse import BrowserOutputObservation
 from openhands.events.observation.commands import (
     CmdOutputMetadata,
@@ -35,5 +32,4 @@ __all__ = [
     'AgentDelegateObservation',
     'SuccessObservation',
     'UserRejectObservation',
-    'AgentCondensationObservation',
 ]

openhands/events/observation/agent.py

@@ -14,14 +14,3 @@ class AgentStateChangedObservation(Observation):
     @property
     def message(self) -> str:
         return ''
-
-
-@dataclass
-class AgentCondensationObservation(Observation):
-    """The output of a condensation action."""
-
-    observation: str = ObservationType.CONDENSE
-
-    @property
-    def message(self) -> str:
-        return self.content

openhands/events/serialization/observation.py

@@ -1,9 +1,6 @@
 import copy
 
-from openhands.events.observation.agent import (
-    AgentCondensationObservation,
-    AgentStateChangedObservation,
-)
+from openhands.events.observation.agent import AgentStateChangedObservation
 from openhands.events.observation.browse import BrowserOutputObservation
 from openhands.events.observation.commands import (
     CmdOutputMetadata,
@@ -35,7 +32,6 @@ observations = (
     ErrorObservation,
     AgentStateChangedObservation,
     UserRejectObservation,
-    AgentCondensationObservation,
 )
 
 OBSERVATION_TYPE_TO_CLASS = {

openhands/memory/__init__.py

@@ -1,4 +1,4 @@
-from openhands.memory.condenser import Condenser
+from openhands.memory.condenser import MemoryCondenser
 from openhands.memory.memory import LongTermMemory
 
-__all__ = ['LongTermMemory', 'Condenser']
+__all__ = ['LongTermMemory', 'MemoryCondenser']

openhands/memory/condenser.py

@@ -1,409 +1,24 @@
-from __future__ import annotations
-
-from abc import ABC, abstractmethod
-from contextlib import contextmanager
-from typing import Any
-
-from litellm import supports_response_schema
-from pydantic import BaseModel
-from typing_extensions import override
-
-from openhands.controller.state.state import State
-from openhands.core.config.condenser_config import (
-    AmortizedForgettingCondenserConfig,
-    CondenserConfig,
-    LLMAttentionCondenserConfig,
-    LLMSummarizingCondenserConfig,
-    NoOpCondenserConfig,
-    ObservationMaskingCondenserConfig,
-    RecentEventsCondenserConfig,
-)
 from openhands.core.logger import openhands_logger as logger
-from openhands.events.event import Event
-from openhands.events.observation import AgentCondensationObservation, Observation
 from openhands.llm.llm import LLM
 
-CONDENSER_METADATA_KEY = 'condenser_meta'
-"""Key identifying where metadata is stored in a `State` object's `extra_data` field."""
 
+class MemoryCondenser:
+    def condense(self, summarize_prompt: str, llm: LLM):
+        """Attempts to condense the memory by using the llm
 
-def get_condensation_metadata(state: State) -> list[dict[str, Any]]:
-    """Utility function to retrieve a list of metadata batches from a `State`.
-
-    Args:
-        state: The state to retrieve metadata from.
-
-    Returns:
-        list[dict[str, Any]]: A list of metadata batches, each representing a condensation.
-    """
-    if CONDENSER_METADATA_KEY in state.extra_data:
-        return state.extra_data[CONDENSER_METADATA_KEY]
-    return []
-
-
-class Condenser(ABC):
-    """Abstract condenser interface.
-
-    Condensers take a list of `Event` objects and reduce them into a potentially smaller list.
-
-    Agents can use condensers to reduce the amount of events they need to consider when deciding which action to take. To use a condenser, agents can call the `condensed_history` method on the current `State` being considered and use the results instead of the full history.
-
-    Example usage::
-
-        condenser = Condenser.from_config(condenser_config)
-        events = condenser.condensed_history(state)
-    """
-
-    def __init__(self):
-        self._metadata_batch: dict[str, Any] = {}
-
-    def add_metadata(self, key: str, value: Any) -> None:
-        """Add information to the current metadata batch.
-
-        Any key/value pairs added to the metadata batch will be recorded in the `State` at the end of the current condensation.
-
-        Args:
-            key: The key to store the metadata under.
-
-            value: The metadata to store.
-        """
-        self._metadata_batch[key] = value
-
-    def write_metadata(self, state: State) -> None:
-        """Write the current batch of metadata to the `State`.
-
-        Resets the current metadata batch: any metadata added after this call will be stored in a new batch and written to the `State` at the end of the next condensation.
-        """
-        if CONDENSER_METADATA_KEY not in state.extra_data:
-            state.extra_data[CONDENSER_METADATA_KEY] = []
-        if self._metadata_batch:
-            state.extra_data[CONDENSER_METADATA_KEY].append(self._metadata_batch)
-
-        # Since the batch has been written, clear it for the next condensation
-        self._metadata_batch = {}
-
-    @contextmanager
-    def metadata_batch(self, state: State):
-        """Context manager to ensure batched metadata is always written to the `State`."""
-        try:
-            yield
-        finally:
-            self.write_metadata(state)
-
-    @abstractmethod
-    def condense(self, events: list[Event]) -> list[Event]:
-        """Condense a sequence of events into a potentially smaller list.
-
-        New condenser strategies should override this method to implement their own condensation logic. Call `self.add_metadata` in the implementation to record any relevant per-condensation diagnostic information.
-
-        Args:
-            events: A list of events representing the entire history of the agent.
-
-        Returns:
-            list[Event]: An event sequence representing a condensed history of the agent.
-        """
-
-    def condensed_history(self, state: State) -> list[Event]:
-        """Condense the state's history."""
-        with self.metadata_batch(state):
-            return self.condense(state.history)
-
-    @classmethod
-    def from_config(cls, config: CondenserConfig) -> Condenser:
-        """Create a condenser from a configuration object.
-
-        Args:
-            config: Configuration for the condenser.
-
-        Returns:
-            Condenser: A condenser instance.
+        Parameters:
+        - llm (LLM): llm to be used for summarization
 
         Raises:
-            ValueError: If the condenser type is not recognized.
-        """
-        match config:
-            case NoOpCondenserConfig():
-                return NoOpCondenser()
-
-            case ObservationMaskingCondenserConfig():
-                return ObservationMaskingCondenser(
-                    **config.model_dump(exclude=['type'])
-                )
-
-            case RecentEventsCondenserConfig():
-                return RecentEventsCondenser(**config.model_dump(exclude=['type']))
-
-            case LLMSummarizingCondenserConfig(llm_config=llm_config):
-                return LLMSummarizingCondenser(llm=LLM(config=llm_config))
-
-            case AmortizedForgettingCondenserConfig():
-                return AmortizedForgettingCondenser(
-                    **config.model_dump(exclude=['type'])
-                )
-
-            case LLMAttentionCondenserConfig(llm_config=llm_config):
-                return LLMAttentionCondenser(
-                    llm=LLM(config=llm_config),
-                    **config.model_dump(exclude=['type', 'llm_config']),
-                )
-
-            case _:
-                raise ValueError(f'Unknown condenser config: {config}')
-
-
-class RollingCondenser(Condenser, ABC):
-    """Base class for a specialized condenser strategy that applies condensation to a rolling history.
-
-    The rolling history is computed by appending new events to the most recent condensation. For example, the sequence of calls::
-
-        assert state.history == [event1, event2, event3]
-        condensation = condenser.condensed_history(state)
-
-        # ...new events are added to the state...
-
-        assert state.history == [event1, event2, event3, event4, event5]
-        condenser.condensed_history(state)
-
-    will result in second call to `condensed_history` passing `condensation + [event4, event5]` to the `condense` method.
-    """
-
-    def __init__(self) -> None:
-        self._condensation: list[Event] = []
-        self._last_history_length: int = 0
-
-        super().__init__()
-
-    @override
-    def condensed_history(self, state: State) -> list[Event]:
-        new_events = state.history[self._last_history_length :]
-
-        with self.metadata_batch(state):
-            results = self.condense(self._condensation + new_events)
-
-        self._condensation = results
-        self._last_history_length = len(state.history)
-
-        return results
-
-
-class NoOpCondenser(Condenser):
-    """A condenser that does nothing to the event sequence."""
-
-    def condense(self, events: list[Event]) -> list[Event]:
-        """Returns the list of events unchanged."""
-        return events
-
-
-class ObservationMaskingCondenser(Condenser):
-    """A condenser that masks the values of observations outside of a recent attention window."""
-
-    def __init__(self, attention_window: int = 5):
-        self.attention_window = attention_window
-
-        super().__init__()
-
-    def condense(self, events: list[Event]) -> list[Event]:
-        """Replace the content of observations outside of the attention window with a placeholder."""
-        results: list[Event] = []
-        for i, event in enumerate(events):
-            if (
-                isinstance(event, Observation)
-                and i < len(events) - self.attention_window
-            ):
-                results.append(AgentCondensationObservation('<MASKED>'))
-            else:
-                results.append(event)
-
-        return results
-
-
-class RecentEventsCondenser(Condenser):
-    """A condenser that only keeps a certain number of the most recent events."""
-
-    def __init__(self, keep_first: int = 0, max_events: int = 10):
-        self.keep_first = keep_first
-        self.max_events = max_events
-
-        super().__init__()
-
-    def condense(self, events: list[Event]) -> list[Event]:
-        """Keep only the most recent events (up to `max_events`)."""
-        head = events[: self.keep_first]
-        tail_length = max(0, self.max_events - len(head))
-        tail = events[-tail_length:]
-        return head + tail
-
-
-class LLMSummarizingCondenser(Condenser):
-    """A condenser that relies on a language model to summarize the event sequence as a single event."""
-
-    def __init__(self, llm: LLM):
-        self.llm = llm
-
-        super().__init__()
-
-    def condense(self, events: list[Event]) -> list[Event]:
-        """Applies an LLM to summarize the list of events.
-
-        Raises:
-            Exception: If the LLM is unable to summarize the event sequence.
+        - Exception: the same exception as it got from the llm or processing the response
         """
         try:
-            # Convert events to a format suitable for summarization
-            events_text = '\n'.join(f'{e.timestamp}: {e.message}' for e in events)
-            summarize_prompt = f'Please summarize these events:\n{events_text}'
-
-            resp = self.llm.completion(
-                messages=[{'content': summarize_prompt, 'role': 'user'}]
-            )
-            summary_response = resp.choices[0].message.content
-
-            # Create a new summary event with the condensed content
-            summary_event = AgentCondensationObservation(summary_response)
-
-            # Add metrics to state
-            self.add_metadata('response', resp.model_dump())
-            self.add_metadata('metrics', self.llm.metrics.get())
-
-            return [summary_event]
-
+            messages = [{'content': summarize_prompt, 'role': 'user'}]
+            resp = llm.completion(messages=messages)
+            summary_response = resp['choices'][0]['message']['content']
+            return summary_response
         except Exception as e:
-            logger.error('Error condensing events: %s', str(e), exc_info=False)
-            raise e
+            logger.error('Error condensing thoughts: %s', str(e), exc_info=False)
 
-
-class AmortizedForgettingCondenser(RollingCondenser):
-    """A condenser that maintains a condensed history and forgets old events when it grows too large."""
-
-    def __init__(self, max_size: int = 100, keep_first: int = 0):
-        """Initialize the condenser.
-
-        Args:
-            max_size: Maximum size of history before forgetting.
-            keep_first: Number of initial events to always keep.
-
-        Raises:
-            ValueError: If keep_first is greater than max_size, keep_first is negative, or max_size is non-positive.
-        """
-        if keep_first >= max_size // 2:
-            raise ValueError(
-                f'keep_first ({keep_first}) must be less than half of max_size ({max_size})'
-            )
-        if keep_first < 0:
-            raise ValueError(f'keep_first ({keep_first}) cannot be negative')
-        if max_size < 1:
-            raise ValueError(f'max_size ({keep_first}) cannot be non-positive')
-
-        self.max_size = max_size
-        self.keep_first = keep_first
-
-        super().__init__()
-
-    def condense(self, events: list[Event]) -> list[Event]:
-        """Apply the amortized forgetting strategy to the given list of events."""
-        if len(events) <= self.max_size:
-            return events
-
-        target_size = self.max_size // 2
-        head = events[: self.keep_first]
-
-        events_from_tail = target_size - len(head)
-        tail = events[-events_from_tail:]
-
-        return head + tail
-
-
-class ImportantEventSelection(BaseModel):
-    """Utility class for the `LLMAttentionCondenser` that forces the LLM to return a list of integers."""
-
-    ids: list[int]
-
-
-class LLMAttentionCondenser(RollingCondenser):
-    """Rolling condenser strategy that uses an LLM to select the most important events when condensing the history."""
-
-    def __init__(self, llm: LLM, max_size: int = 100, keep_first: int = 0):
-        if keep_first >= max_size // 2:
-            raise ValueError(
-                f'keep_first ({keep_first}) must be less than half of max_size ({max_size})'
-            )
-        if keep_first < 0:
-            raise ValueError(f'keep_first ({keep_first}) cannot be negative')
-        if max_size < 1:
-            raise ValueError(f'max_size ({keep_first}) cannot be non-positive')
-
-        self.max_size = max_size
-        self.keep_first = keep_first
-        self.llm = llm
-
-        # This condenser relies on the `response_schema` feature, which is not supported by all LLMs
-        if not supports_response_schema(
-            model=self.llm.config.model,
-            custom_llm_provider=self.llm.config.custom_llm_provider,
-        ):
-            raise ValueError(
-                "The LLM model must support the 'response_schema' parameter to use the LLMAttentionCondenser."
-            )
-
-        super().__init__()
-
-    def condense(self, events: list[Event]) -> list[Event]:
-        """If the history is too long, use an LLM to select the most important events."""
-        if len(events) <= self.max_size:
-            return events
-
-        target_size = self.max_size // 2
-        head = events[: self.keep_first]
-
-        events_from_tail = target_size - len(head)
-
-        message: str = """You will be given a list of actions, observations, and thoughts from a coding agent.
-        Each item in the list has an identifier. Please sort the identifiers in order of how important the
-        contents of the item are for the next step of the coding agent's task, from most important to least
-        important."""
-
-        response = self.llm.completion(
-            messages=[
-                {'content': message, 'role': 'user'},
-                *[
-                    {
-                        'content': f'<ID>{e.id}</ID>\n<CONTENT>{e.message}</CONTENT>',
-                        'role': 'user',
-                    }
-                    for e in events
-                ],
-            ],
-            response_format={
-                'type': 'json_schema',
-                'json_schema': {
-                    'name': 'ImportantEventSelection',
-                    'schema': ImportantEventSelection.model_json_schema(),
-                },
-            },
-        )
-
-        response_ids = ImportantEventSelection.model_validate_json(
-            response.choices[0].message.content
-        ).ids
-
-        self.add_metadata('all_event_ids', [event.id for event in events])
-        self.add_metadata('response_ids', response_ids)
-        self.add_metadata('metrics', self.llm.metrics.get())
-
-        # Filter out any IDs from the head and trim the results down
-        head_ids = [event.id for event in head]
-        response_ids = [
-            response_id for response_id in response_ids if response_id not in head_ids
-        ][:events_from_tail]
-
-        # If the response IDs aren't _long_ enough, iterate backwards through the events and add any unfound IDs to the list.
-        for event in reversed(events):
-            if len(response_ids) >= events_from_tail:
-                break
-            if event.id not in response_ids:
-                response_ids.append(event.id)
-
-        # Grab the events associated with the response IDs
-        tail = [event for event in events if event.id in response_ids]
-
-        return head + tail
+            # TODO If the llm fails with ContextWindowExceededError, we can try to condense the memory chunk by chunk
+            raise

openhands/runtime/base.py

@@ -210,11 +210,9 @@ class Runtime(FileEditRuntimeMixin):
         source = event.source if event.source else EventSource.AGENT
         self.event_stream.add_event(observation, source)  # type: ignore[arg-type]
 
-    def clone_repo(self, github_token: str, selected_repository: str):
+    def clone_repo(self, github_token: str | None, selected_repository: str | None):
         if not github_token or not selected_repository:
-            raise ValueError(
-                'github_token and selected_repository must be provided to clone a repository'
-            )
+            return
         url = f'https://{github_token}@github.com/{selected_repository}.git'
         dir_name = selected_repository.split('/')[1]
         # add random branch name to avoid conflicts

openhands/runtime/builder/docker.py

@@ -26,17 +26,6 @@ class DockerRuntimeBuilder(RuntimeBuilder):
 
         self.rolling_logger = RollingLogger(max_lines=10)
 
-    @staticmethod
-    def check_buildx():
-        """Check if Docker Buildx is available"""
-        try:
-            result = subprocess.run(
-                ['docker', 'buildx', 'version'], capture_output=True, text=True
-            )
-            return result.returncode == 0
-        except FileNotFoundError:
-            return False
-
     def build(
         self,
         path: str,
@@ -73,38 +62,6 @@ class DockerRuntimeBuilder(RuntimeBuilder):
                 'Docker server version must be >= 18.09 to use BuildKit'
             )
 
-        if not DockerRuntimeBuilder.check_buildx():
-            # when running openhands in a container, there might not be a "docker"
-            # binary available, in which case we need to download docker binary.
-            # since the official openhands app image is built from debian, we use
-            # debian way to install docker binary
-            logger.info(
-                'No docker binary available inside openhands-app container, trying to download online...'
-            )
-            commands = [
-                'apt-get update',
-                'apt-get install -y ca-certificates curl gnupg',
-                'install -m 0755 -d /etc/apt/keyrings',
-                'curl -fsSL https://download.docker.com/linux/debian/gpg -o /etc/apt/keyrings/docker.asc',
-                'chmod a+r /etc/apt/keyrings/docker.asc',
-                'echo \
-                  "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/debian \
-                  $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
-                  tee /etc/apt/sources.list.d/docker.list > /dev/null',
-                'apt-get update',
-                'apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin',
-            ]
-            for cmd in commands:
-                try:
-                    subprocess.run(
-                        cmd, shell=True, check=True, stdout=subprocess.DEVNULL
-                    )
-                except subprocess.CalledProcessError as e:
-                    logger.error(f'Image build failed:\n{e}')
-                    logger.error(f'Command output:\n{e.output}')
-                    raise
-            logger.info('Downloaded and installed docker binary')
-
         target_image_hash_name = tags[0]
         target_image_repo, target_image_source_tag = target_image_hash_name.split(':')
         target_image_tag = tags[1].split(':')[1] if len(tags) > 1 else None

openhands/runtime/impl/docker/docker_runtime.py

@@ -267,11 +267,13 @@ class DockerRuntime(ActionExecutionClient):
                 environment=environment,
                 volumes=volumes,
                 device_requests=(
-                    [docker.types.DeviceRequest(capabilities=[['gpu']], count=-1)]
+                    [docker.types.DeviceRequest(
+                        capabilities=[['gpu']],
+                        count=-1
+                    )]
                     if self.config.sandbox.enable_gpu
                     else None
                 ),
-                **(self.config.sandbox.docker_runtime_kwargs or {}),
             )
             self.log('debug', f'Container started. Server url: {self.api_url}')
             self.send_status_message('STATUS$CONTAINER_STARTED')

openhands/server/routes/manage_conversations.py

@@ -30,7 +30,9 @@ UPDATED_AT_CALLBACK_ID = 'updated_at_callback_id'
 
 class InitSessionRequest(BaseModel):
     github_token: str | None = None
+    latest_event_id: int = -1
     selected_repository: str | None = None
+    args: dict | None = None
 
 
 @app.post('/conversations')
@@ -51,7 +53,7 @@ async def new_conversation(request: Request, data: InitSessionRequest):
         session_init_args = {**settings.__dict__, **session_init_args}
 
     github_token = getattr(request.state, 'github_token', '')
-    session_init_args['github_token'] = github_token or data.github_token or ''
+    session_init_args['github_token'] = github_token
     session_init_args['selected_repository'] = data.selected_repository
     conversation_init_data = ConversationInitData(**session_init_args)
     logger.info('Loading conversation store')
@@ -66,15 +68,10 @@ async def new_conversation(request: Request, data: InitSessionRequest):
         conversation_id = uuid.uuid4().hex
     logger.info(f'New conversation ID: {conversation_id}')
 
-    conversation_title = (
-        data.selected_repository or f'Conversation {conversation_id[:5]}'
-    )
-
     logger.info(f'Saving metadata for conversation {conversation_id}')
     await conversation_store.save_metadata(
         ConversationMetadata(
             conversation_id=conversation_id,
-            title=conversation_title,
             github_user_id=get_user_id(request),
             selected_repository=data.selected_repository,
         )
@@ -109,7 +106,6 @@ async def search_conversations(
     conversation_ids = set(
         conversation.conversation_id
         for conversation in conversation_metadata_result_set.results
-        if hasattr(conversation, 'created_at')
     )
     running_conversations = await session_manager.get_agent_loop_running(
         set(conversation_ids)

openhands/server/session/agent_session.py

@@ -204,10 +204,7 @@ class AgentSession:
                 )
             return
 
-        if selected_repository:
-            await call_sync_from_async(
-                self.runtime.clone_repo, github_token, selected_repository
-            )
+        self.runtime.clone_repo(github_token, selected_repository)
         if agent.prompt_manager:
             microagents: list[BaseMicroAgent] = await call_sync_from_async(
                 self.runtime.get_microagents_from_selected_repo, selected_repository
@@ -274,25 +271,27 @@ class AgentSession:
             confirmation_mode=confirmation_mode,
             headless_mode=False,
             status_callback=self._status_callback,
-            initial_state=self._maybe_restore_state(),
         )
 
-        return controller
+        # Note: We now attempt to restore the state from session here,
+        # but if it fails, we fall back to None and still initialize the controller
+        # with a fresh state. That way, the controller will always load events from the event stream
+        # even if the state file was corrupt.
 
-    def _maybe_restore_state(self) -> State | None:
-        """Helper method to handle state restore logic."""
         restored_state = None
-
-        # Attempt to restore the state from session.
-        # Use a heuristic to figure out if we should have a state:
-        # if we have events in the stream.
         try:
             restored_state = State.restore_from_session(self.sid, self.file_store)
-            logger.debug(f'Restored state from session, sid: {self.sid}')
         except Exception as e:
             if self.event_stream.get_latest_event_id() > 0:
                 # if we have events, we should have a state
                 logger.warning(f'State could not be restored: {e}')
-            else:
-                logger.debug('No events found, no state to restore')
-        return restored_state
+
+        # Set the initial state through the controller.
+        controller.set_initial_state(restored_state, max_iterations, confirmation_mode)
+        if restored_state:
+            logger.debug(f'Restored agent state from session, sid: {self.sid}')
+        else:
+            logger.debug('New session state created.')
+
+        logger.debug('Agent controller initialized.')
+        return controller

openhands/storage/conversation/file_conversation_store.py

@@ -1,7 +1,6 @@
 from __future__ import annotations
 
 from dataclasses import dataclass
-from pathlib import Path
 
 from pydantic import TypeAdapter
 
@@ -40,9 +39,7 @@ class FileConversationStore(ConversationStore):
         return result
 
     async def delete_metadata(self, conversation_id: str) -> None:
-        path = str(
-            Path(self.get_conversation_metadata_filename(conversation_id)).parent
-        )
+        path = self.get_conversation_metadata_filename(conversation_id)
         await call_sync_from_async(self.file_store.delete, path)
 
     async def exists(self, conversation_id: str) -> bool:

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "openhands-ai"
-version = "0.19.0"
+version = "0.18.0a0"
 description = "OpenHands: Code Less, Make More"
 authors = ["OpenHands"]
 license = "MIT"
@@ -14,7 +14,7 @@ packages = [
 python = "^3.12"
 datasets = "*"
 pandas = "*"
-litellm = "^1.55.4"
+litellm = "^1.54.1"
 google-generativeai = "*" # To use litellm with Gemini Pro API
 google-api-python-client = "*" # For Google Sheets API
 google-auth-httplib2 = "*" # For Google Sheets authentication
@@ -60,9 +60,9 @@ whatthepatch = "^1.0.6"
 protobuf = "^4.21.6,<5.0.0" # chromadb currently fails on 5.0+
 opentelemetry-api = "1.25.0"
 opentelemetry-exporter-otlp-proto-grpc = "1.25.0"
-modal = ">=0.66.26,<0.72.0"
+modal = ">=0.66.26,<0.71.0"
 runloop-api-client = "0.11.0"
-libtmux = ">=0.37,<0.40"
+libtmux = "^0.37.0"
 pygithub = "^2.5.0"
 joblib = "*"
 openhands-aci = "0.1.6"
@@ -82,7 +82,7 @@ voyageai = "*"
 llama-index-embeddings-voyageai = "*"
 
 [tool.poetry.group.dev.dependencies]
-ruff = "0.8.6"
+ruff = "0.8.5"
 mypy = "1.14.1"
 pre-commit = "4.0.1"
 build = "*"
@@ -95,17 +95,20 @@ pytest-forked = "*"
 pytest-xdist = "*"
 flake8 = "*"
 openai = "*"
+opencv-python = "*"
 pandas = "*"
 reportlab = "*"
 
 [tool.coverage.run]
 concurrency = ["gevent"]
 
+
 [tool.poetry.group.runtime.dependencies]
 jupyterlab = "*"
 notebook = "*"
 jupyter_kernel_gateway = "*"
 flake8 = "*"
+opencv-python = "*"
 
 [build-system]
 build-backend = "poetry.core.masonry.api"
@@ -129,6 +132,7 @@ ignore = ["D1"]
 [tool.ruff.lint.pydocstyle]
 convention = "google"
 
+
 [tool.poetry.group.evaluation.dependencies]
 streamlit = "*"
 whatthepatch = "*"

tests/runtime/conftest.py

@@ -215,7 +215,6 @@ def _load_runtime(
     use_workspace: bool | None = None,
     force_rebuild_runtime: bool = False,
     runtime_startup_env_vars: dict[str, str] | None = None,
-    docker_runtime_kwargs: dict[str, str] | None = None,
 ) -> Runtime:
     sid = 'rt_' + str(random.randint(100000, 999999))
 
@@ -227,7 +226,6 @@ def _load_runtime(
     config.run_as_openhands = run_as_openhands
     config.sandbox.force_rebuild_runtime = force_rebuild_runtime
     config.sandbox.keep_runtime_alive = False
-    config.sandbox.docker_runtime_kwargs = docker_runtime_kwargs
     # Folder where all tests create their own folder
     global test_mount_path
     if use_workspace:

tests/runtime/test_stress_docker_runtime.py

@@ -1,21 +1,18 @@
 """Stress tests for the DockerRuntime, which connects to the ActionExecutor running in the sandbox."""
 
-from conftest import _close_test_runtime, _load_runtime
+import pytest
+from conftest import TEST_IN_CI, _close_test_runtime, _load_runtime
 
 from openhands.core.logger import openhands_logger as logger
 from openhands.events.action import CmdRunAction
 
 
+@pytest.mark.skipif(
+    TEST_IN_CI,
+    reason='This test should only be run locally, not in CI.',
+)
 def test_stress_docker_runtime(temp_dir, runtime_cls, repeat=1):
-    runtime = _load_runtime(
-        temp_dir,
-        runtime_cls,
-        docker_runtime_kwargs={
-            'cpu_period': 100000,  # 100ms
-            'cpu_quota': 100000,  # Can use 100ms out of each 100ms period (1 CPU)
-            'mem_limit': '4G',  # 4 GB of memory
-        },
-    )
+    runtime = _load_runtime(temp_dir, runtime_cls)
 
     action = CmdRunAction(
         command='sudo apt-get update && sudo apt-get install -y stress-ng'
@@ -26,9 +23,11 @@ def test_stress_docker_runtime(temp_dir, runtime_cls, repeat=1):
     assert obs.exit_code == 0
 
     for _ in range(repeat):
-        # run stress-ng stress tests for 1 minute
-        action = CmdRunAction(command='stress-ng --all 1 -t 1m')
-        action.timeout = 120
+        # run stress-ng stress tests for 5 minutes
+        # FIXME: this would make Docker daemon die, even though running this
+        # command on its own in the same container is fine
+        action = CmdRunAction(command='stress-ng --all 1 -t 5m')
+        action.timeout = 600
         logger.info(action, extra={'msg_type': 'ACTION'})
         obs = runtime.run_action(action)
         logger.info(obs, extra={'msg_type': 'OBSERVATION'})

tests/unit/test_agent_session.py

@@ -1,186 +0,0 @@
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-
-from openhands.controller.agent import Agent
-from openhands.controller.agent_controller import AgentController
-from openhands.controller.state.state import State
-from openhands.core.config import AppConfig, LLMConfig
-from openhands.events import EventStream, EventStreamSubscriber
-from openhands.llm import LLM
-from openhands.llm.metrics import Metrics
-from openhands.runtime.base import Runtime
-from openhands.server.session.agent_session import AgentSession
-from openhands.storage.memory import InMemoryFileStore
-
-
-@pytest.fixture
-def mock_agent():
-    """Create a properly configured mock agent with all required nested attributes"""
-    # Create the base mocks
-    agent = MagicMock(spec=Agent)
-    llm = MagicMock(spec=LLM)
-    metrics = MagicMock(spec=Metrics)
-    llm_config = MagicMock(spec=LLMConfig)
-
-    # Configure the LLM config
-    llm_config.model = 'test-model'
-    llm_config.base_url = 'http://test'
-    llm_config.draft_editor = None
-    llm_config.max_message_chars = 1000
-
-    # Set up the chain of mocks
-    llm.metrics = metrics
-    llm.config = llm_config
-    agent.llm = llm
-    agent.name = 'test-agent'
-    agent.sandbox_plugins = []
-
-    return agent
-
-
-@pytest.mark.asyncio
-async def test_agent_session_start_with_no_state(mock_agent):
-    """Test that AgentSession.start() works correctly when there's no state to restore"""
-
-    # Setup
-    file_store = InMemoryFileStore({})
-    session = AgentSession(sid='test-session', file_store=file_store)
-
-    # Create a mock runtime and set it up
-    mock_runtime = MagicMock(spec=Runtime)
-
-    # Mock the runtime creation to set up the runtime attribute
-    async def mock_create_runtime(*args, **kwargs):
-        session.runtime = mock_runtime
-
-    session._create_runtime = AsyncMock(side_effect=mock_create_runtime)
-
-    # Create a mock EventStream with no events
-    mock_event_stream = MagicMock(spec=EventStream)
-    mock_event_stream.get_events.return_value = []
-    mock_event_stream.subscribe = MagicMock()
-    mock_event_stream.get_latest_event_id.return_value = 0
-
-    # Inject the mock event stream into the session
-    session.event_stream = mock_event_stream
-
-    # Create a spy on set_initial_state
-    class SpyAgentController(AgentController):
-        set_initial_state_call_count = 0
-        test_initial_state = None
-
-        def set_initial_state(self, *args, state=None, **kwargs):
-            self.set_initial_state_call_count += 1
-            self.test_initial_state = state
-            super().set_initial_state(*args, state=state, **kwargs)
-
-    # Patch AgentController and State.restore_from_session to fail
-    with patch(
-        'openhands.server.session.agent_session.AgentController', SpyAgentController
-    ), patch(
-        'openhands.server.session.agent_session.EventStream',
-        return_value=mock_event_stream,
-    ), patch(
-        'openhands.controller.state.state.State.restore_from_session',
-        side_effect=Exception('No state found'),
-    ):
-        await session.start(
-            runtime_name='test-runtime',
-            config=AppConfig(),
-            agent=mock_agent,
-            max_iterations=10,
-        )
-
-        # Verify EventStream.subscribe was called with correct parameters
-        mock_event_stream.subscribe.assert_called_with(
-            EventStreamSubscriber.AGENT_CONTROLLER,
-            session.controller.on_event,
-            session.controller.id,
-        )
-
-        # Verify set_initial_state was called once with None as state
-        assert session.controller.set_initial_state_call_count == 1
-        assert session.controller.test_initial_state is None
-        assert session.controller.state.max_iterations == 10
-        assert session.controller.agent.name == 'test-agent'
-        assert session.controller.state.start_id == 0
-        assert session.controller.state.end_id == -1
-        assert session.controller.state.truncation_id == -1
-
-
-@pytest.mark.asyncio
-async def test_agent_session_start_with_restored_state(mock_agent):
-    """Test that AgentSession.start() works correctly when there's a state to restore"""
-
-    # Setup
-    file_store = InMemoryFileStore({})
-    session = AgentSession(sid='test-session', file_store=file_store)
-
-    # Create a mock runtime and set it up
-    mock_runtime = MagicMock(spec=Runtime)
-
-    # Mock the runtime creation to set up the runtime attribute
-    async def mock_create_runtime(*args, **kwargs):
-        session.runtime = mock_runtime
-
-    session._create_runtime = AsyncMock(side_effect=mock_create_runtime)
-
-    # Create a mock EventStream with some events
-    mock_event_stream = MagicMock(spec=EventStream)
-    mock_event_stream.get_events.return_value = []
-    mock_event_stream.subscribe = MagicMock()
-    mock_event_stream.get_latest_event_id.return_value = 5  # Indicate some events exist
-
-    # Inject the mock event stream into the session
-    session.event_stream = mock_event_stream
-
-    # Create a mock restored state
-    mock_restored_state = MagicMock(spec=State)
-    mock_restored_state.start_id = -1
-    mock_restored_state.end_id = -1
-    mock_restored_state.truncation_id = -1
-    mock_restored_state.max_iterations = 5
-
-    # Create a spy on set_initial_state by subclassing AgentController
-    class SpyAgentController(AgentController):
-        set_initial_state_call_count = 0
-        test_initial_state = None
-
-        def set_initial_state(self, *args, state=None, **kwargs):
-            self.set_initial_state_call_count += 1
-            self.test_initial_state = state
-            super().set_initial_state(*args, state=state, **kwargs)
-
-    # Patch AgentController and State.restore_from_session to succeed
-    with patch(
-        'openhands.server.session.agent_session.AgentController', SpyAgentController
-    ), patch(
-        'openhands.server.session.agent_session.EventStream',
-        return_value=mock_event_stream,
-    ), patch(
-        'openhands.controller.state.state.State.restore_from_session',
-        return_value=mock_restored_state,
-    ):
-        await session.start(
-            runtime_name='test-runtime',
-            config=AppConfig(),
-            agent=mock_agent,
-            max_iterations=10,
-        )
-
-        # Verify set_initial_state was called once with the restored state
-        assert session.controller.set_initial_state_call_count == 1
-
-        # Verify EventStream.subscribe was called with correct parameters
-        mock_event_stream.subscribe.assert_called_with(
-            EventStreamSubscriber.AGENT_CONTROLLER,
-            session.controller.on_event,
-            session.controller.id,
-        )
-        assert session.controller.test_initial_state is mock_restored_state
-        assert session.controller.state is mock_restored_state
-        assert session.controller.state.max_iterations == 5
-        assert session.controller.state.start_id == 0
-        assert session.controller.state.end_id == -1
-        assert session.controller.state.truncation_id == -1

tests/unit/test_codeact_agent.py

@@ -1,7 +1,6 @@
 from unittest.mock import Mock
 
 import pytest
-from litellm import ChatCompletionMessageToolCall
 
 from openhands.agenthub.codeact_agent.codeact_agent import CodeActAgent
 from openhands.agenthub.codeact_agent.function_calling import (
@@ -16,7 +15,6 @@ from openhands.agenthub.codeact_agent.function_calling import (
     get_tools,
     response_to_actions,
 )
-from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig, LLMConfig
 from openhands.core.exceptions import FunctionCallNotExistsError
 from openhands.core.message import ImageContent, TextContent
@@ -50,15 +48,6 @@ def agent() -> CodeActAgent:
     return agent
 
 
-@pytest.fixture
-def mock_state() -> State:
-    state = Mock(spec=State)
-    state.history = []
-    state.extra_data = {}
-
-    return state
-
-
 def test_cmd_output_observation_message(agent: CodeActAgent):
     agent.config.function_calling = False
     obs = CmdOutputObservation(
@@ -492,7 +481,7 @@ def test_response_to_actions_invalid_tool():
         response_to_actions(mock_response)
 
 
-def test_step_with_no_pending_actions(mock_state: State):
+def test_step_with_no_pending_actions():
     # Mock the LLM response
     mock_response = Mock()
     mock_response.id = 'mock_id'
@@ -513,68 +502,16 @@ def test_step_with_no_pending_actions(mock_state: State):
     agent = CodeActAgent(llm=llm, config=config)
 
     # Test step with no pending actions
-    mock_state.latest_user_message = None
-    mock_state.latest_user_message_id = None
-    mock_state.latest_user_message_timestamp = None
-    mock_state.latest_user_message_cause = None
-    mock_state.latest_user_message_timeout = None
-    mock_state.latest_user_message_llm_metrics = None
-    mock_state.latest_user_message_tool_call_metadata = None
+    state = Mock()
+    state.history = []
+    state.latest_user_message = None
+    state.latest_user_message_id = None
+    state.latest_user_message_timestamp = None
+    state.latest_user_message_cause = None
+    state.latest_user_message_timeout = None
+    state.latest_user_message_llm_metrics = None
+    state.latest_user_message_tool_call_metadata = None
 
-    action = agent.step(mock_state)
+    action = agent.step(state)
     assert isinstance(action, MessageAction)
     assert action.content == 'Task completed'
-
-
-def test_mismatched_tool_call_events(mock_state: State):
-    """Tests that the agent can convert mismatched tool call events (i.e., an observation with no corresponding action) into messages."""
-    agent = CodeActAgent(llm=LLM(LLMConfig()), config=AgentConfig())
-
-    tool_call_metadata = Mock(
-        spec=ToolCallMetadata,
-        model_response=Mock(
-            id='model_response_0',
-            choices=[
-                Mock(
-                    message=Mock(
-                        role='assistant',
-                        content='',
-                        tool_calls=[
-                            Mock(spec=ChatCompletionMessageToolCall, id='tool_call_0')
-                        ],
-                    )
-                )
-            ],
-        ),
-        tool_call_id='tool_call_0',
-        function_name='foo',
-    )
-
-    action = CmdRunAction('foo')
-    action._source = 'agent'
-    action.tool_call_metadata = tool_call_metadata
-
-    observation = CmdOutputObservation(content='', command_id=0, command='foo')
-    observation.tool_call_metadata = tool_call_metadata
-
-    # When both events are provided, the agent should get three messages:
-    # 1. The system message,
-    # 2. The action message, and
-    # 3. The observation message
-    mock_state.history = [action, observation]
-    messages = agent._get_messages(mock_state)
-    assert len(messages) == 3
-
-    # The same should hold if the events are presented out-of-order
-    mock_state.history = [observation, action]
-    messages = agent._get_messages(mock_state)
-    assert len(messages) == 3
-
-    # If only one of the two events is present, then we should just get the system message
-    mock_state.history = [action]
-    messages = agent._get_messages(mock_state)
-    assert len(messages) == 1
-
-    mock_state.history = [observation]
-    messages = agent._get_messages(mock_state)
-    assert len(messages) == 1

tests/unit/test_condenser.py

@@ -1,520 +1,44 @@
-from datetime import datetime
-from typing import Any
-from unittest.mock import MagicMock
+from unittest.mock import Mock, patch
 
 import pytest
 
-from openhands.controller.state.state import State
-from openhands.core.config.condenser_config import (
-    AmortizedForgettingCondenserConfig,
-    LLMAttentionCondenserConfig,
-    LLMSummarizingCondenserConfig,
-    NoOpCondenserConfig,
-    ObservationMaskingCondenserConfig,
-    RecentEventsCondenserConfig,
-)
-from openhands.core.config.llm_config import LLMConfig
-from openhands.events.event import Event, EventSource
-from openhands.events.observation.observation import Observation
-from openhands.llm import LLM
-from openhands.memory.condenser import (
-    AmortizedForgettingCondenser,
-    Condenser,
-    ImportantEventSelection,
-    LLMAttentionCondenser,
-    LLMSummarizingCondenser,
-    NoOpCondenser,
-    ObservationMaskingCondenser,
-    RecentEventsCondenser,
-)
-
-
-def create_test_event(
-    message: str, timestamp: datetime | None = None, id: int | None = None
-) -> Event:
-    """Create a simple test event."""
-    event = Event()
-    event._message = message
-    event.timestamp = timestamp if timestamp else datetime.now()
-    if id:
-        event._id = id
-    event._source = EventSource.USER
-    return event
+from openhands.core.exceptions import LLMResponseError
+from openhands.llm.llm import LLM
+from openhands.memory.condenser import MemoryCondenser
 
 
 @pytest.fixture
-def mock_llm() -> LLM:
-    """Mocks an LLM object with a utility function for setting and resetting response contents in unit tests."""
-    # Create a MagicMock for the LLM object
-    mock_llm = MagicMock(
-        spec=LLM,
-        config=MagicMock(
-            spec=LLMConfig, model='gpt-4o', api_key='test_key', custom_llm_provider=None
-        ),
-        metrics=MagicMock(),
-    )
-    _mock_content = None
-
-    # Set a mock message with the mocked content
-    mock_message = MagicMock()
-    mock_message.content = _mock_content
-
-    def set_mock_response_content(content: Any):
-        """Set the mock response for the LLM."""
-        nonlocal mock_message
-        mock_message.content = content
-
-    mock_choice = MagicMock()
-    mock_choice.message = mock_message
-
-    mock_response = MagicMock()
-    mock_response.choices = [mock_choice]
-
-    mock_llm.completion.return_value = mock_response
-
-    # Attach helper methods to the mock object
-    mock_llm.set_mock_response_content = set_mock_response_content
-
-    return mock_llm
+def memory_condenser():
+    return MemoryCondenser()
 
 
 @pytest.fixture
-def mock_state() -> State:
-    """Mocks a State object with the only parameters needed for testing condensers: history and extra_data."""
-    mock_state = MagicMock(spec=State)
-    mock_state.history = []
-    mock_state.extra_data = {}
-
-    return mock_state
-
-
-def test_noop_condenser_from_config():
-    """Test that the NoOpCondenser objects can be made from config."""
-    config = NoOpCondenserConfig()
-    condenser = Condenser.from_config(config)
-
-    assert isinstance(condenser, NoOpCondenser)
-
-
-def test_noop_condenser():
-    """Test that NoOpCondensers preserve their input events."""
-    events = [
-        create_test_event('Event 1'),
-        create_test_event('Event 2'),
-        create_test_event('Event 3'),
-    ]
-
-    mock_state = MagicMock()
-    mock_state.history = events
-
-    condenser = NoOpCondenser()
-    result = condenser.condensed_history(mock_state)
-
-    assert result == events
-
-
-def test_observation_masking_condenser_from_config():
-    """Test that ObservationMaskingCondenser objects can be made from config."""
-    attention_window = 5
-    config = ObservationMaskingCondenserConfig(attention_window=attention_window)
-    condenser = Condenser.from_config(config)
-
-    assert isinstance(condenser, ObservationMaskingCondenser)
-    assert condenser.attention_window == attention_window
-
-
-def test_observation_masking_condenser_respects_attention_window(mock_state):
-    """Test that ObservationMaskingCondenser only masks events outside the attention window."""
-    attention_window = 3
-    condenser = ObservationMaskingCondenser(attention_window=attention_window)
-
-    events = [
-        create_test_event('Event 1'),
-        Observation('Observation 1'),
-        create_test_event('Event 3'),
-        create_test_event('Event 4'),
-        Observation('Observation 2'),
-    ]
-
-    mock_state.history = events
-    result = condenser.condensed_history(mock_state)
-
-    assert len(result) == len(events)
-
-    for index, (event, condensed_event) in enumerate(zip(events, result)):
-        # If we're outside the attention window, observations should be masked.
-        if index < len(events) - attention_window:
-            if isinstance(event, Observation):
-                assert '<MASKED>' in str(condensed_event)
-
-        # If we're within the attention window, events are unchanged.
-        else:
-            assert event == condensed_event
-
-
-def test_recent_events_condenser_from_config():
-    """Test that RecentEventsCondenser objects can be made from config."""
-    max_events = 5
-    keep_first = True
-    config = RecentEventsCondenserConfig(keep_first=keep_first, max_events=max_events)
-    condenser = Condenser.from_config(config)
-
-    assert isinstance(condenser, RecentEventsCondenser)
-    assert condenser.max_events == max_events
-    assert condenser.keep_first == keep_first
-
-
-def test_recent_events_condenser():
-    """Test that RecentEventsCondensers keep just the most recent events."""
-    events = [
-        create_test_event('Event 1'),
-        create_test_event('Event 2'),
-        create_test_event('Event 3'),
-        create_test_event('Event 4'),
-        create_test_event('Event 5'),
-    ]
-
-    mock_state = MagicMock()
-    mock_state.history = events
-
-    # If the max_events are larger than the number of events, equivalent to a NoOpCondenser.
-    condenser = RecentEventsCondenser(max_events=len(events))
-    result = condenser.condensed_history(mock_state)
-
-    assert result == events
-
-    # If the max_events are smaller than the number of events, only keep the last few.
-    max_events = 2
-    condenser = RecentEventsCondenser(max_events=max_events)
-    result = condenser.condensed_history(mock_state)
-
-    assert len(result) == max_events
-    assert result[0]._message == 'Event 4'
-    assert result[1]._message == 'Event 5'
-
-    # If the keep_first flag is set, the first event will always be present.
-    keep_first = 1
-    max_events = 2
-    condenser = RecentEventsCondenser(keep_first=keep_first, max_events=max_events)
-    result = condenser.condensed_history(mock_state)
-
-    assert len(result) == max_events
-    assert result[0]._message == 'Event 1'
-    assert result[1]._message == 'Event 5'
-
-    # We should be able to keep more of the initial events.
-    keep_first = 2
-    max_events = 3
-    condenser = RecentEventsCondenser(keep_first=keep_first, max_events=max_events)
-    result = condenser.condensed_history(mock_state)
-
-    assert len(result) == max_events
-    assert result[0]._message == 'Event 1'
-    assert result[1]._message == 'Event 2'
-    assert result[2]._message == 'Event 5'
-
-
-def test_llm_condenser_from_config():
-    """Test that LLMCondensers can be made from config."""
-    config = LLMSummarizingCondenserConfig(
-        llm_config=LLMConfig(
-            model='gpt-4o',
-            api_key='test_key',
-        )
-    )
-    condenser = Condenser.from_config(config)
-
-    assert isinstance(condenser, LLMSummarizingCondenser)
-    assert condenser.llm.config.model == 'gpt-4o'
-    assert condenser.llm.config.api_key == 'test_key'
-
-
-def test_llm_condenser(mock_llm, mock_state):
-    """Test that LLMCondensers use the LLM to generate a summary event."""
-    events = [
-        create_test_event('Event 1'),
-        create_test_event('Event 2'),
-    ]
-    mock_state.history = events
-
-    mock_llm.metrics = MagicMock()
-    mock_llm.metrics.get.return_value = {'test_metric': 1.0}
-
-    mock_llm.set_mock_response_content('Summary of events')
-
-    condenser = LLMSummarizingCondenser(llm=mock_llm)
-    result = condenser.condensed_history(mock_state)
-
-    assert len(result) == 1
-    assert result[0].content == 'Summary of events'
-
-    # Verify LLM was called with correct prompt.
-    mock_llm.completion.assert_called_once()
-    call_args = mock_llm.completion.call_args[1]
-    assert 'messages' in call_args
-    assert len(call_args['messages']) == 1
-    assert 'Event 1' in call_args['messages'][0]['content']
-    assert 'Event 2' in call_args['messages'][0]['content']
-
-    # Verify metrics were added to state
-    assert 'condenser_meta' in mock_state.extra_data
-    assert len(mock_state.extra_data['condenser_meta']) == 1
-    assert mock_state.extra_data['condenser_meta'][0]['metrics'] == {'test_metric': 1.0}
-
-
-def test_llm_condenser_error():
-    """Test that LLM errors are propagated during condensation."""
-    events = [create_test_event('Event 1', datetime(2024, 1, 1, 10, 0))]
-
-    mock_state = MagicMock()
-    mock_state.history = events
-
-    mock_llm = MagicMock()
-    mock_llm.completion.side_effect = Exception('LLM error')
-
-    condenser = LLMSummarizingCondenser(llm=mock_llm)
-
-    try:
-        condenser.condensed_history(mock_state)
-        raise AssertionError('Expected exception was not raised.')
-    except Exception as e:
-        assert str(e) == 'LLM error'
-
-
-def test_amortized_forgetting_condenser_from_config():
-    """Test that AmortizedForgettingCondenser objects can be made from config."""
-    max_size = 50
-    keep_first = 10
-    config = AmortizedForgettingCondenserConfig(
-        max_size=max_size, keep_first=keep_first
-    )
-    condenser = Condenser.from_config(config)
-
-    assert isinstance(condenser, AmortizedForgettingCondenser)
-    assert condenser.max_size == max_size
-    assert condenser.keep_first == keep_first
-
-
-def test_amortized_forgetting_condenser_invalid_config():
-    """Test that AmortizedForgettingCondenser raises error when keep_first > max_size."""
-    pytest.raises(ValueError, AmortizedForgettingCondenser, max_size=4, keep_first=2)
-    pytest.raises(ValueError, AmortizedForgettingCondenser, max_size=0)
-    pytest.raises(ValueError, AmortizedForgettingCondenser, keep_first=-1)
-
-
-def test_amortized_forgetting_condenser_grows_to_max_size():
-    """Test that AmortizedForgettingCondenser correctly maintains an event context up to max size."""
-    max_size = 15
-    condenser = AmortizedForgettingCondenser(max_size=max_size)
-
-    mock_state = MagicMock()
-    mock_state.extra_data = {}
-    mock_state.history = []
-
-    for i in range(max_size):
-        event = create_test_event(f'Event {i}')
-        mock_state.history.append(event)
-        results = condenser.condensed_history(mock_state)
-        assert len(results) == i + 1
-
-
-def test_amortized_forgetting_condenser_forgets_when_larger_than_max_size():
-    """Test that the AmortizedForgettingCondenser forgets events when the context grows too large."""
-    max_size = 2
-    condenser = AmortizedForgettingCondenser(max_size=max_size)
-
-    mock_state = MagicMock()
-    mock_state.extra_data = {}
-    mock_state.history = []
-
-    for i in range(max_size * 10):
-        event = create_test_event(f'Event {i}')
-        mock_state.history.append(event)
-        results = condenser.condensed_history(mock_state)
-
-        # The last event in the results is always the event we just added.
-        assert results[-1] == event
-
-        # The number of results should bounce back and forth between 1, 2, 1, 2, ...
-        assert len(results) == (i % 2) + 1
-
-
-def test_amortized_forgetting_condenser_keeps_first_events():
-    """Test that the AmortizedForgettingCondenser keeps the right number of initial events when forgetting."""
-    max_size = 4
-    keep_first = 1
-    condenser = AmortizedForgettingCondenser(max_size=max_size, keep_first=keep_first)
-
-    first_event = create_test_event('Event 0')
-
-    mock_state = MagicMock()
-    mock_state.extra_data = {}
-    mock_state.history = [first_event]
-
-    for i in range(max_size * 10):
-        event = create_test_event(f'Event {i+1}', datetime(2024, 1, 1, 10, i + 1))
-        mock_state.history.append(event)
-        results = condenser.condensed_history(mock_state)
-
-        # The last event is always the event we just added.
-        assert results[-1] == event
-
-        # The first event is always the first event.
-        assert results[0] == first_event
-
-        # The number of results should bounce back between 2, 3, 4, 2, 3, 4, ...
-        print(len(results))
-        assert len(results) == (i % 3) + 2
-
-
-def test_llm_attention_condenser_from_config():
-    """Test that LLMAttentionCondenser objects can be made from config."""
-    config = LLMAttentionCondenserConfig(
-        max_size=50,
-        keep_first=10,
-        llm_config=LLMConfig(
-            model='gpt-4o',
-            api_key='test_key',
-        ),
-    )
-    condenser = Condenser.from_config(config)
-
-    assert isinstance(condenser, LLMAttentionCondenser)
-    assert condenser.llm.config.model == 'gpt-4o'
-    assert condenser.llm.config.api_key == 'test_key'
-    assert condenser.max_size == 50
-    assert condenser.keep_first == 10
-
-
-def test_llm_attention_condenser_invalid_config():
-    """Test that LLMAttentionCondenser raises an error if the configured LLM doesn't support response schema."""
-    config = LLMAttentionCondenserConfig(
-        max_size=50,
-        keep_first=10,
-        llm_config=LLMConfig(
-            model='claude-2',  # Older model that doesn't support response schema
-            api_key='test_key',
-        ),
+def mock_llm():
+    return Mock(spec=LLM)
+
+
+def test_condense_success(memory_condenser, mock_llm):
+    mock_llm.completion.return_value = {
+        'choices': [{'message': {'content': 'Condensed memory'}}]
+    }
+    result = memory_condenser.condense('Summarize this', mock_llm)
+    assert result == 'Condensed memory'
+    mock_llm.completion.assert_called_once_with(
+        messages=[{'content': 'Summarize this', 'role': 'user'}]
     )
 
-    pytest.raises(ValueError, LLMAttentionCondenser.from_config, config)
+
+def test_condense_exception(memory_condenser, mock_llm):
+    mock_llm.completion.side_effect = LLMResponseError('LLM error')
+    with pytest.raises(LLMResponseError, match='LLM error'):
+        memory_condenser.condense('Summarize this', mock_llm)
 
 
-def test_llm_attention_condenser_keeps_first_events(mock_llm, mock_state):
-    """Test that the LLMAttentionCondenser keeps the right number of initial events when forgetting."""
-    max_size = 4
-    condenser = LLMAttentionCondenser(max_size=max_size, keep_first=1, llm=mock_llm)
-
-    first_event = create_test_event('Event 0', id=0)
-    mock_state.history.append(first_event)
-
-    for i in range(max_size * 10):
-        event = create_test_event(f'Event {i+1}', id=i + 1)
-        mock_state.history.append(event)
-
-        mock_llm.set_mock_response_content(
-            ImportantEventSelection(
-                ids=[event.id for event in mock_state.history]
-            ).model_dump_json()
-        )
-        results = condenser.condensed_history(mock_state)
-
-        # The first event is always the first event.
-        assert results[0] == first_event
-
-
-def test_llm_attention_condenser_grows_to_max_size(mock_llm, mock_state):
-    """Test that LLMAttentionCondenser correctly maintains an event context up to max size."""
-    max_size = 15
-    condenser = LLMAttentionCondenser(max_size=max_size, llm=mock_llm)
-
-    for i in range(max_size):
-        event = create_test_event(f'Event {i}')
-        mock_state.history.append(event)
-        mock_llm.set_mock_response_content(
-            ImportantEventSelection(ids=[event.id for event in mock_state.history])
-        )
-        results = condenser.condensed_history(mock_state)
-        assert len(results) == i + 1
-
-
-def test_llm_attention_condenser_forgets_when_larger_than_max_size(
-    mock_llm, mock_state
-):
-    """Test that the LLMAttentionCondenser forgets events when the context grows too large."""
-    max_size = 2
-    condenser = LLMAttentionCondenser(max_size=max_size, llm=mock_llm)
-
-    for i in range(max_size * 10):
-        event = create_test_event(f'Event {i}', id=i)
-        mock_state.history.append(event)
-
-        mock_llm.set_mock_response_content(
-            ImportantEventSelection(
-                ids=[event.id for event in mock_state.history]
-            ).model_dump_json()
-        )
-
-        results = condenser.condensed_history(mock_state)
-
-        # The number of results should bounce back and forth between 1, 2, 1, 2, ...
-        assert len(results) == (i % 2) + 1
-
-
-def test_llm_attention_condenser_handles_events_outside_history(mock_llm, mock_state):
-    """Test that the LLMAttentionCondenser handles event IDs that aren't from the event history."""
-    max_size = 2
-    condenser = LLMAttentionCondenser(max_size=max_size, llm=mock_llm)
-
-    for i in range(max_size * 10):
-        event = create_test_event(f'Event {i}', id=i)
-        mock_state.history.append(event)
-
-        mock_llm.set_mock_response_content(
-            ImportantEventSelection(
-                ids=[event.id for event in mock_state.history] + [-1, -2, -3, -4]
-            ).model_dump_json()
-        )
-        results = condenser.condensed_history(mock_state)
-
-        # The number of results should bounce back and forth between 1, 2, 1, 2, ...
-        assert len(results) == (i % 2) + 1
-
-
-def test_llm_attention_condenser_handles_too_many_events(mock_llm, mock_state):
-    """Test that the LLMAttentionCondenser handles when the response contains too many event IDs."""
-    max_size = 2
-    condenser = LLMAttentionCondenser(max_size=max_size, llm=mock_llm)
-
-    for i in range(max_size * 10):
-        event = create_test_event(f'Event {i}', id=i)
-        mock_state.history.append(event)
-        mock_llm.set_mock_response_content(
-            ImportantEventSelection(
-                ids=[event.id for event in mock_state.history]
-                + [event.id for event in mock_state.history]
-            ).model_dump_json()
-        )
-        results = condenser.condensed_history(mock_state)
-
-        # The number of results should bounce back and forth between 1, 2, 1, 2, ...
-        assert len(results) == (i % 2) + 1
-
-
-def test_llm_attention_condenser_handles_too_few_events(mock_llm, mock_state):
-    """Test that the LLMAttentionCondenser handles when the response contains too few event IDs."""
-    max_size = 2
-    condenser = LLMAttentionCondenser(max_size=max_size, llm=mock_llm)
-
-    for i in range(max_size * 10):
-        event = create_test_event(f'Event {i}', id=i)
-        mock_state.history.append(event)
-
-        mock_llm.set_mock_response_content(
-            ImportantEventSelection(ids=[]).model_dump_json()
-        )
-
-        results = condenser.condensed_history(mock_state)
-
-        # The number of results should bounce back and forth between 1, 2, 1, 2, ...
-        assert len(results) == (i % 2) + 1
+@patch('openhands.memory.condenser.logger')
+def test_condense_logs_error(mock_logger, memory_condenser, mock_llm):
+    mock_llm.completion.side_effect = LLMResponseError('LLM error')
+    with pytest.raises(LLMResponseError):
+        memory_condenser.condense('Summarize this', mock_llm)
+    mock_logger.error.assert_called_once_with(
+        'Error condensing thoughts: %s', 'LLM error', exc_info=False
+    )

tests/unit/test_config.py

@@ -13,9 +13,6 @@ from openhands.core.config import (
     load_from_env,
     load_from_toml,
 )
-from openhands.core.config.condenser_config import (
-    NoOpCondenserConfig,
-)
 from openhands.core.logger import openhands_logger
 
 
@@ -621,13 +618,6 @@ def test_cache_dir_creation(default_config, tmpdir):
     assert os.path.exists(default_config.cache_dir)
 
 
-def test_agent_config_condenser_default():
-    """Test that default agent condenser is NoOpCondenser."""
-    config = AppConfig()
-    agent_config = config.get_agent_config()
-    assert isinstance(agent_config.condenser, NoOpCondenserConfig)
-
-
 def test_api_keys_repr_str():
     # Test LLMConfig
     llm_config = LLMConfig(

tests/unit/test_conversation.py

@@ -6,7 +6,6 @@ from unittest.mock import MagicMock, patch
 import pytest
 
 from openhands.server.routes.manage_conversations import (
-    delete_conversation,
     get_conversation,
     search_conversations,
     update_conversation,
@@ -115,16 +114,3 @@ async def test_update_conversation():
             selected_repository='foobar',
         )
         assert conversation == expected
-
-
-@pytest.mark.asyncio
-async def test_delete_conversation():
-    with _patch_store():
-        await delete_conversation(
-            'some_conversation_id',
-            MagicMock(state=MagicMock(github_token='')),
-        )
-        conversation = await get_conversation(
-            'some_conversation_id', MagicMock(state=MagicMock(github_token=''))
-        )
-        assert conversation is None

tests/unit/test_prompt_caching.py

@@ -75,7 +75,7 @@ def test_get_messages(codeact_agent: CodeActAgent):
 
     codeact_agent.reset()
     messages = codeact_agent._get_messages(
-        Mock(history=history, max_iterations=5, iteration=0, extra_data={})
+        Mock(history=history, max_iterations=5, iteration=0)
     )
 
     assert (
@@ -111,7 +111,7 @@ def test_get_messages_prompt_caching(codeact_agent: CodeActAgent):
 
     codeact_agent.reset()
     messages = codeact_agent._get_messages(
-        Mock(history=history, max_iterations=10, iteration=5, extra_data={})
+        Mock(history=history, max_iterations=10, iteration=5)
     )
 
     # Check that only the last two user messages have cache_prompt=True
@@ -144,7 +144,6 @@ def test_prompt_caching_headers(codeact_agent: CodeActAgent):
     mock_state.history = history
     mock_state.max_iterations = 5
     mock_state.iteration = 0
-    mock_state.extra_data = {}
 
     codeact_agent.reset()