chore: temporary fix to get sonnet 3.7 working again (#7140)

.github/dependabot.yml

@@ -10,6 +10,12 @@ updates:
       pre-commit:
         patterns:
           - "pre-commit"
+      llama:
+        patterns:
+          - "llama*"
+      chromadb:
+        patterns:
+          - "chromadb"
       browsergym:
         patterns:
           - "browsergym*"

.github/workflows/dummy-agent-test.yml

@@ -36,7 +36,7 @@ jobs:
           python-version: '3.12'
           cache: 'poetry'
       - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation
+        run: poetry install --without evaluation,llama-index
       - name: Build Environment
         run: make build
       - name: Run tests

.github/workflows/integration-runner.yml

@@ -54,7 +54,7 @@ jobs:
             Hi! I started running the integration tests on your PR. You will receive a comment with the results shortly.
 
       - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation
+        run: poetry install --without evaluation,llama-index
 
       - name: Configure config.toml for testing with Haiku
         env:
@@ -117,6 +117,68 @@ jobs:
           echo "EOF" >> $GITHUB_ENV
 
       # -------------------------------------------------------------
+      # Run DelegatorAgent tests for Haiku, limited to t01 and t02
+      - name: Wait a little bit (again)
+        run: sleep 5
+
+      - name: Configure config.toml for testing DelegatorAgent (Haiku)
+        env:
+          LLM_MODEL: "litellm_proxy/claude-3-5-haiku-20241022"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 30
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+
+      - name: Run integration test evaluation for DelegatorAgent (Haiku)
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD DelegatorAgent '' 30 $N_PROCESSES "t01_fix_simple_typo,t02_add_bash_hello" 'delegator_haiku_run'
+
+          # Find and export the delegator test results
+          REPORT_FILE_DELEGATOR_HAIKU=$(find evaluation/evaluation_outputs/outputs/integration_tests/DelegatorAgent/*haiku*_maxiter_30_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE_DELEGATOR_HAIKU: $REPORT_FILE_DELEGATOR_HAIKU"
+          echo "INTEGRATION_TEST_REPORT_DELEGATOR_HAIKU<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_DELEGATOR_HAIKU >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      # -------------------------------------------------------------
+      # Run DelegatorAgent tests for DeepSeek, limited to t01 and t02
+      - name: Wait a little bit (again)
+        run: sleep 5
+
+      - name: Configure config.toml for testing DelegatorAgent (DeepSeek)
+        env:
+          LLM_MODEL: "litellm_proxy/deepseek-chat"
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
+          MAX_ITERATIONS: 30
+        run: |
+          echo "[llm.eval]" > config.toml
+          echo "model = \"$LLM_MODEL\"" >> config.toml
+          echo "api_key = \"$LLM_API_KEY\"" >> config.toml
+          echo "base_url = \"$LLM_BASE_URL\"" >> config.toml
+          echo "temperature = 0.0" >> config.toml
+      - name: Run integration test evaluation for DelegatorAgent (DeepSeek)
+        env:
+          SANDBOX_FORCE_REBUILD_RUNTIME: True
+        run: |
+          poetry run ./evaluation/integration_tests/scripts/run_infer.sh llm.eval HEAD DelegatorAgent '' 30 $N_PROCESSES "t01_fix_simple_typo,t02_add_bash_hello" 'delegator_deepseek_run'
+
+          # Find and export the delegator test results
+          REPORT_FILE_DELEGATOR_DEEPSEEK=$(find evaluation/evaluation_outputs/outputs/integration_tests/DelegatorAgent/deepseek*_maxiter_30_N* -name "report.md" -type f | head -n 1)
+          echo "REPORT_FILE_DELEGATOR_DEEPSEEK: $REPORT_FILE_DELEGATOR_DEEPSEEK"
+          echo "INTEGRATION_TEST_REPORT_DELEGATOR_DEEPSEEK<<EOF" >> $GITHUB_ENV
+          cat $REPORT_FILE_DELEGATOR_DEEPSEEK >> $GITHUB_ENV
+          echo >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+      # -------------------------------------------------------------
       # Run VisualBrowsingAgent tests for DeepSeek, limited to t05 and t06
       - name: Wait a little bit (again)
         run: sleep 5
@@ -151,7 +213,7 @@ jobs:
         run: |
           TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
           cd evaluation/evaluation_outputs/outputs  # Change to the outputs directory
-          tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/* integration_tests/VisualBrowsingAgent/* # Only include the actual result directories
+          tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/* integration_tests/DelegatorAgent/* integration_tests/VisualBrowsingAgent/* # Only include the actual result directories
 
       - name: Upload evaluation results as artifact
         uses: actions/upload-artifact@v4
@@ -192,6 +254,12 @@ jobs:
               **Integration Tests Report (DeepSeek)**
               DeepSeek LLM Test Results:
               ${{ env.INTEGRATION_TEST_REPORT_DEEPSEEK }}
+              ---
+                **Integration Tests Report Delegator (Haiku)**
+              ${{ env.INTEGRATION_TEST_REPORT_DELEGATOR_HAIKU }}
+              ---
+              **Integration Tests Report Delegator (DeepSeek)**
+              ${{ env.INTEGRATION_TEST_REPORT_DELEGATOR_DEEPSEEK }}
               ---
               **Integration Tests Report VisualBrowsing (DeepSeek)**
               ${{ env.INTEGRATION_TEST_REPORT_VISUALBROWSING_DEEPSEEK }}

.github/workflows/py-unit-tests.yml

@@ -44,11 +44,11 @@ jobs:
           python-version: ${{ matrix.python-version }}
           cache: 'poetry'
       - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation
+        run: poetry install --without evaluation,llama-index
       - name: Build Environment
         run: make build
       - name: Run Tests
-        run: poetry run pytest --forked -n auto --cov=openhands --cov-report=xml -svv ./tests/unit
+        run: poetry run pytest --forked -n auto --cov=openhands --cov-report=xml -svv ./tests/unit --ignore=tests/unit/test_long_term_memory.py
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v5
         env:

Makefile

@@ -133,7 +133,7 @@ install-python-dependencies:
 		export HNSWLIB_NO_NATIVE=1; \
 		poetry run pip install chroma-hnswlib; \
 	fi
-	@poetry install
+	@poetry install --without llama-index
 	@if [ -f "/etc/manjaro-release" ]; then \
 		echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
 		poetry run pip install playwright; \
@@ -265,6 +265,35 @@ setup-config-prompts:
 	@read -p "Enter your LLM base URL [mostly used for local LLMs, leave blank if not needed - example: http://localhost:5001/v1/]: " llm_base_url; \
 	 if [[ ! -z "$$llm_base_url" ]]; then echo "base_url=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; fi
 
+	@echo "Enter your LLM Embedding Model"; \
+		echo "Choices are:"; \
+		echo "  - openai"; \
+		echo "  - azureopenai"; \
+		echo "  - Embeddings available only with OllamaEmbedding:"; \
+		echo "    - llama2"; \
+		echo "    - mxbai-embed-large"; \
+		echo "    - nomic-embed-text"; \
+		echo "    - all-minilm"; \
+		echo "    - stable-code"; \
+		echo "    - bge-m3"; \
+		echo "    - bge-large"; \
+		echo "    - paraphrase-multilingual"; \
+		echo "    - snowflake-arctic-embed"; \
+		echo "  - Leave blank to default to 'BAAI/bge-small-en-v1.5' via huggingface"; \
+		read -p "> " llm_embedding_model; \
+		echo "embedding_model=\"$$llm_embedding_model\"" >> $(CONFIG_FILE).tmp; \
+		if [ "$$llm_embedding_model" = "llama2" ] || [ "$$llm_embedding_model" = "mxbai-embed-large" ] || [ "$$llm_embedding_model" = "nomic-embed-text" ] || [ "$$llm_embedding_model" = "all-minilm" ] || [ "$$llm_embedding_model" = "stable-code" ]; then \
+			read -p "Enter the local model URL for the embedding model (will set llm.embedding_base_url): " llm_embedding_base_url; \
+				echo "embedding_base_url=\"$$llm_embedding_base_url\"" >> $(CONFIG_FILE).tmp; \
+		elif [ "$$llm_embedding_model" = "azureopenai" ]; then \
+			read -p "Enter the Azure endpoint URL (will overwrite llm.base_url): " llm_base_url; \
+				echo "base_url=\"$$llm_base_url\"" >> $(CONFIG_FILE).tmp; \
+			read -p "Enter the Azure LLM Embedding Deployment Name: " llm_embedding_deployment_name; \
+				echo "embedding_deployment_name=\"$$llm_embedding_deployment_name\"" >> $(CONFIG_FILE).tmp; \
+			read -p "Enter the Azure API Version: " llm_api_version; \
+				echo "api_version=\"$$llm_api_version\"" >> $(CONFIG_FILE).tmp; \
+		fi
+
 
 # Develop in container
 docker-dev:

README.md

@@ -12,7 +12,7 @@
   <a href="https://codecov.io/github/All-Hands-AI/OpenHands?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/All-Hands-AI/OpenHands?style=for-the-badge&color=blue"></a>
   <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/github/license/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="MIT License"></a>
   <br/>
-  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2ngejmfw6-9gW4APWOC9XUp1n~SiQ6iw"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
+  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2ypg5jweb-d~6hObZDbXi_HEL8PDrbHg"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
   <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
   <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="Credits"></a>
   <br/>
@@ -96,7 +96,7 @@ troubleshooting resources, and advanced configuration options.
 OpenHands is a community-driven project, and we welcome contributions from everyone. We do most of our communication
 through Slack, so this is the best place to start, but we also are happy to have you contact us on Discord or Github:
 
-- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-2ngejmfw6-9gW4APWOC9XUp1n~SiQ6iw) - Here we talk about research, architecture, and future development.
+- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-2ypg5jweb-d~6hObZDbXi_HEL8PDrbHg) - Here we talk about research, architecture, and future development.
 - [Join our Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
 - [Read or post Github Issues](https://github.com/All-Hands-AI/OpenHands/issues) - Check out the issues we're working on, or add your own ideas.
 

config.template.toml

@@ -132,6 +132,15 @@ api_key = ""
 # Custom LLM provider
 #custom_llm_provider = ""
 
+# Embedding API base URL
+#embedding_base_url = ""
+
+# Embedding deployment name
+#embedding_deployment_name = ""
+
+# Embedding model to use
+embedding_model = "local"
+
 # Maximum number of characters in an observation's content
 #max_message_chars = 10000
 
@@ -218,6 +227,9 @@ codeact_enable_llm_editor = false
 # whether the IPython tool is enabled
 codeact_enable_jupyter = true
 
+# Name of the micro agent to use for this agent
+#micro_agent_name = ""
+
 # Memory enabled
 #memory_enabled = false
 

containers/app/Dockerfile

@@ -26,7 +26,7 @@ RUN apt-get update -y \
 
 COPY ./pyproject.toml ./poetry.lock ./
 RUN touch README.md
-RUN export POETRY_CACHE_DIR && poetry install --without evaluation --no-root && rm -rf $POETRY_CACHE_DIR
+RUN export POETRY_CACHE_DIR && poetry install --without evaluation,llama-index --no-root && rm -rf $POETRY_CACHE_DIR
 
 FROM python:3.12.3-slim AS openhands-app
 

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

@@ -333,6 +333,12 @@ Pour les configurations de développement, vous pouvez également définir des c
 
 Les options de configuration de l'agent sont définies dans les sections `[agent]` et `[agent.<agent_name>]` du fichier `config.toml`.
 
+**Configuration du micro-agent**
+- `micro_agent_name`
+  - Type : `str`
+  - Valeur par défaut : `""`
+  - Description : Nom du micro-agent à utiliser pour cet agent
+
 **Configuration de la mémoire**
 - `memory_enabled`
   - Type : `bool`

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

@@ -42,7 +42,7 @@ Explorez le code source d'OpenHands sur [GitHub](https://github.com/All-Hands-AI
   />
 </a>
 <br></br>
-<a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2ngejmfw6-9gW4APWOC9XUp1n~SiQ6iw">
+<a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2ypg5jweb-d~6hObZDbXi_HEL8PDrbHg">
   <img
     src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge"
     alt="Join our Slack community"

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

@@ -328,6 +328,12 @@ LLM(大语言模型)配置选项在 `config.toml` 文件的 `[llm]` 部分中定
 
 Agent 配置选项在 `config.toml` 文件的 `[agent]` 和 `[agent.<agent_name>]` 部分中定义。
 
+**Microagent 配置**
+- `micro_agent_name`
+  - 类型: `str`
+  - 默认值: `""`
+  - 描述: 用于此 agent 的 micro agent 名称
+
 **内存配置**
 - `memory_enabled`
   - 类型: `bool`

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

@@ -42,7 +42,7 @@ OpenHands 是一个**自主 AI 软件工程师**，能够执行复杂的工程
   />
 </a>
 <br></br>
-<a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2ngejmfw6-9gW4APWOC9XUp1n~SiQ6iw">
+<a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2ypg5jweb-d~6hObZDbXi_HEL8PDrbHg">
   <img
     src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge"
     alt="Join our Slack community"

docs/modules/usage/cloud/cloud-github-resolver.md

@@ -4,30 +4,18 @@ The GitHub Resolver automates code fixes and provides intelligent assistance for
 
 ## Setup
 
-The Cloud GitHub Resolver is available automatically when you
+The Cloud Github Resolver is available automatically when you
 [grant OpenHands Cloud repository access](./openhands-cloud.md#adding-repositories).
 
 ## Usage
 
-After granting OpenHands Cloud repository access, you can use the Cloud GitHub Resolver on the issues and pull requests
-on the repository.
-
 ### Issues
 
-On your repository, label an issue with `openhands`. OpenHands will:
-1. Comment on the issue to let you know it is working on it.
-    - You can click on the link to track the progress on OpenHands Cloud.
-2. Open a pull request if it determines that the issue has been successfully resolved.
-3. Comment on the issue with a summary of the performed tasks and a link to the pull request.
-
+On your repository, label an issue with `openhands`. OpenHands will attempt to fix the issue.
 
 ### Pull Requests
 
-To get OpenHands to work on pull requests, use `@openhands` in top level or inline comments to:
+In order to get OpenHands to work on pull requests, use `@openhands` in top level or single inline comments to:
      - Ask questions
      - Request updates
      - Get code explanations
-
-OpenHands will:
-1. Comment on the PR to let you know it is working on it.
-2. Perform the task.

docs/modules/usage/cloud/openhands-cloud.md

@@ -12,16 +12,14 @@ instructions on how to access it.
 
 After visiting OpenHands Cloud, you will be asked to connect with your GitHub account:
 1. After reading and accepting the terms of service, click `Connect to GitHub`.
-2. Review the permissions requested by OpenHands and then click `Authorize OpenHands AI`.
+2. Review the permissions requested by OpenHands and then click `Authorize OpenHands by All Hands AI`.
    - OpenHands will require some permissions from your GitHub account. To read more about these permissions,
      you can click the `Learn more` link on the GitHub authorize page.
 
-## Repository Access
-
-### Adding Repository Access
+## Adding Repositories
 
 You can grant OpenHands specific repository access:
-1. Click the `Select a GitHub project` dropdown, select `Add more repositories...`.
+1. Under the `Select a GitHub project` dropdown, select `Add more repositories...`.
 2. Select the organization, then choose the specific repositories to grant OpenHands access to.
    - Openhands requests short-lived tokens (8-hour expiry) with these permissions:
      - Actions: Read and write
@@ -36,10 +34,6 @@ You can grant OpenHands specific repository access:
    - Repository access for a user is granted based on:
      - Granted permission for the repository.
      - User's GitHub permissions (owner/collaborator).
-3. Click on `Install & Authorize`.
 
-### Modifying Repository Access
-
-You can modify repository access at any time by:
-* Using the same `Select a GitHub project > Add more repositories` workflow, or
-* Visiting the Settings page and selecting `Configure GitHub Repositories` under the `GitHub Settings` section.
+You can manage repository access any time by following the above workflow or visiting the Settings page and selecting
+`Configure GitHub Repositories` under the `GitHub Settings` section.

docs/modules/usage/configuration-options.md

@@ -197,6 +197,21 @@ For development setups, you can also define custom named LLM configurations. See
   - Default: `""`
   - Description: Custom LLM provider
 
+### Embeddings
+- `embedding_base_url`
+  - Type: `str`
+  - Default: `""`
+  - Description: Embedding API base URL
+
+- `embedding_deployment_name`
+  - Type: `str`
+  - Default: `""`
+  - Description: Embedding deployment name
+
+- `embedding_model`
+  - Type: `str`
+  - Default: `"local"`
+  - Description: Embedding model to use
 
 ### Message Handling
 - `max_message_chars`
@@ -281,6 +296,23 @@ For development setups, you can also define custom named LLM configurations. See
 
 The agent configuration options are defined in the `[agent]` and `[agent.<agent_name>]` sections of the `config.toml` file.
 
+### Microagent Configuration
+- `micro_agent_name`
+  - Type: `str`
+  - Default: `""`
+  - Description: Name of the micro agent to use for this agent
+
+### Memory Configuration
+- `memory_enabled`
+  - Type: `bool`
+  - Default: `false`
+  - Description: Whether long-term memory (embeddings) is enabled
+
+- `memory_max_threads`
+  - Type: `int`
+  - Default: `3`
+  - Description: The maximum number of threads indexing at the same time for embeddings
+
 ### LLM Configuration
 - `llm_config`
   - Type: `str`
@@ -355,7 +387,7 @@ To use these with the docker command, pass in `-e SANDBOX_<option>`. Example: `-
 
 - `runtime_binding_address`
   - Type: `str`
-  - Default: `0.0.0.0`
+  - Default: `127.0.0.1`
   - Description: The binding address for the runtime ports.  It specifies which network interface on the host machine Docker should bind the runtime ports to.
 
 ### Linting and Plugins

docs/modules/usage/feedback.md

@@ -36,7 +36,7 @@ At this time, we will follow the following release process:
 1. All people who contributed public feedback will receive an email describing the data release and being given an opportunity to opt out.
 2. The person or people in charge of the data release will perform quality control of the data, removing low-quality feedback,
 removing email submitter email addresses, and attempting to remove any sensitive information.
-3. The data will be released publicly under the MIT license through commonly used sites such as GitHub or Hugging Face.
+3. The data will be released publicly under the MIT license through commonly used sites such as github or Hugging Face.
 
 ### What if I want my data deleted?
 

docs/modules/usage/how-to/github-action.md

@@ -39,7 +39,7 @@ You can provide custom directions for OpenHands by following the [README for the
 
 ### Custom configurations
 
-GitHub resolver will automatically check for valid [repository secrets](https://docs.github.com/en/actions/security-for-github-actions/security-guides/using-secrets-in-github-actions?tool=webui#creating-secrets-for-a-repository) or [repository variables](https://docs.github.com/en/actions/writing-workflows/choosing-what-your-workflow-does/store-information-in-variables#creating-configuration-variables-for-a-repository) to customize its behavior.
+Github resolver will automatically check for valid [repository secrets](https://docs.github.com/en/actions/security-for-github-actions/security-guides/using-secrets-in-github-actions?tool=webui#creating-secrets-for-a-repository) or [repository variables](https://docs.github.com/en/actions/writing-workflows/choosing-what-your-workflow-does/store-information-in-variables#creating-configuration-variables-for-a-repository) to customize its behavior.
 The customization options you can set are:
 
 | **Attribute name**               | **Type** | **Purpose**                                                                                         | **Example**                                        |

docs/modules/usage/installation.mdx

@@ -76,7 +76,7 @@ You'll find OpenHands running at http://localhost:3000!
 You can also [connect OpenHands to your local filesystem](https://docs.all-hands.dev/modules/usage/runtimes#connecting-to-your-filesystem),
 run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode),
 interact with it via a [friendly CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode),
-or run it on tagged issues with [a GitHub action](https://docs.all-hands.dev/modules/usage/how-to/github-action).
+or run it on tagged issues with [a github action](https://docs.all-hands.dev/modules/usage/how-to/github-action).
 
 ## Setup
 

docs/modules/usage/llms/azure-llms.md

@@ -31,11 +31,17 @@ You will need your ChatGPT deployment name which can be found on the deployments
    - `Base URL` to your Azure API Base URL (e.g. `https://example-endpoint.openai.azure.com`)
    - `API Key` to your Azure API key
 
+## Embeddings
+
+OpenHands uses llama-index for embeddings. You can find their documentation on Azure [here](https://docs.llamaindex.ai/en/stable/api_reference/embeddings/azure_openai/).
+
 ### Azure OpenAI Configuration
 
-When running OpenHands, set the following environment variable using `-e` in the
+When running OpenHands, set the following environment variables using `-e` in the
 [docker run command](/modules/usage/installation#start-the-app):
 
 ```
+LLM_EMBEDDING_MODEL="azureopenai"
+LLM_EMBEDDING_DEPLOYMENT_NAME="<your-embedding-deployment-name>"   # e.g. "TextEmbedding...<etc>"
 LLM_API_VERSION="<api-version>"                                    # e.g. "2024-02-15-preview"
 ```

docs/modules/usage/runtimes.md

@@ -10,9 +10,6 @@ We also support "remote" runtimes, which are typically managed by third-parties.
 They can make setup a bit simpler and more scalable, especially
 if you're running many OpenHands conversations in parallel (e.g. to do evaluation).
 
-Additionally, we provide a "local" runtime that runs directly on your machine without Docker,
-which can be useful in controlled environments like CI pipelines.
-
 ## Docker Runtime
 This is the default Runtime that's used when you start OpenHands. You might notice
 some flags being passed to `docker run` that make this possible:
@@ -59,12 +56,11 @@ any files that are mounted into its workspace.
 This setup can cause some issues with file permissions (hence the `SANDBOX_USER_ID` variable)
 but seems to work well on most systems.
 
-## OpenHands Remote Runtime
+## All Hands Runtime
+The All Hands Runtime is currently in beta. You can request access by joining
+the #remote-runtime-limited-beta channel on Slack ([see the README](https://github.com/All-Hands-AI/OpenHands?tab=readme-ov-file#-how-to-join-the-community) for an invite).
 
-OpenHands Remote Runtime is currently in beta (read [here](https://runtime.all-hands.dev/) for more details), it allows you to launch runtimes in parallel in the cloud.
-Fill out [this form](https://docs.google.com/forms/d/e/1FAIpQLSckVz_JFwg2_mOxNZjCtr7aoBFI2Mwdan3f75J_TrdMS1JV2g/viewform) to apply if you want to try this out!
-
-To use the OpenHands Remote Runtime, set the following environment variables when
+To use the All Hands Runtime, set the following environment variables when
 starting OpenHands:
 
 ```bash
@@ -121,66 +117,3 @@ bash -i <(curl -sL https://get.daytona.io/openhands)
 Once executed, OpenHands should be running locally and ready for use.
 
 For more details and manual initialization, view the entire [README.md](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/impl/daytona/README.md)
-
-## Local Runtime
-
-The Local Runtime allows the OpenHands agent to execute actions directly on your local machine without using Docker. This runtime is primarily intended for controlled environments like CI pipelines or testing scenarios where Docker is not available.
-
-:::caution
-**Security Warning**: The Local Runtime runs without any sandbox isolation. The agent can directly access and modify files on your machine. Only use this runtime in controlled environments or when you fully understand the security implications.
-:::
-
-### Prerequisites
-
-Before using the Local Runtime, ensure you have the following dependencies installed:
-
-1. You have followed the [Development setup instructions](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md).
-2. tmux is available on your system.
-
-### Configuration
-
-To use the Local Runtime, besides required configurations like the model, API key, you'll need to set the following options via environment variables or the [config.toml file](https://github.com/All-Hands-AI/OpenHands/blob/main/config.template.toml) when starting OpenHands:
-
-- Via environment variables:
-
-```bash
-# Required
-export RUNTIME=local
-
-# Optional but recommended
-export WORKSPACE_BASE=/path/to/your/workspace
-```
-
-- Via `config.toml`:
-
-```toml
-[core]
-runtime = "local"
-workspace_base = "/path/to/your/workspace"
-```
-
-If `WORKSPACE_BASE` is not set, the runtime will create a temporary directory for the agent to work in.
-
-### Example Usage
-
-Here's an example of how to start OpenHands with the Local Runtime in Headless Mode:
-
-```bash
-# Set the runtime type to local
-export RUNTIME=local
-
-# Optionally set a workspace directory
-export WORKSPACE_BASE=/path/to/your/project
-
-# Start OpenHands
-poetry run python -m openhands.core.main -t "write a bash script that prints hi"
-```
-
-### Use Cases
-
-The Local Runtime is particularly useful for:
-
-- CI/CD pipelines where Docker is not available.
-- Testing and development of OpenHands itself.
-- Environments where container usage is restricted.
-- Scenarios where direct file system access is required.

docs/src/components/CustomFooter.tsx

@@ -8,7 +8,7 @@ function CustomFooter() {
     <footer className="custom-footer">
       <div className="footer-content">
         <div className="footer-icons">
-          <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2ngejmfw6-9gW4APWOC9XUp1n~SiQ6iw" target="_blank" rel="noopener noreferrer">
+          <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2ypg5jweb-d~6hObZDbXi_HEL8PDrbHg" target="_blank" rel="noopener noreferrer">
             <FaSlack />
           </a>
           <a href="https://discord.gg/ESHStjSjD4" target="_blank" rel="noopener noreferrer">

docs/src/components/HomepageHeader/HomepageHeader.tsx

@@ -46,7 +46,7 @@ export function HomepageHeader() {
           <a href="https://codecov.io/github/All-Hands-AI/OpenHands?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" /></a>
           <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/github/license/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="MIT License" /></a>
           <br/>
-          <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2ngejmfw6-9gW4APWOC9XUp1n~SiQ6iw"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community" /></a>
+          <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2ypg5jweb-d~6hObZDbXi_HEL8PDrbHg"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community" /></a>
           <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community" /></a>
           <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="Credits" /></a>
           <br/>

evaluation/benchmarks/commit0/README.md

@@ -1,6 +1,6 @@
 # Commit0 Evaluation with OpenHands
 
-This folder contains the evaluation harness that we built on top of the original [Commit0](https://commit-0.github.io/) ([paper](https://arxiv.org/abs/2412.01769v1)).
+This folder contains the evaluation harness that we built on top of the original [Commit0](https://commit-0.github.io/) ([paper](TBD)).
 
 The evaluation consists of three steps:
 

evaluation/benchmarks/swe_bench/README.md

@@ -18,20 +18,6 @@ Please follow instruction [here](../../README.md#setup) to setup your local deve
 
 ## Run Inference (Rollout) on SWE-Bench Instances: Generate Patch from Problem Statement
 
-> [!NOTE]
-> **Iterative Evaluation Protocol**
->
-> We have an iterative approach for more stable and reproducible results:
-> - For each instance, we attempt to generate a solution up to 3 times
-> - Each attempt continues until either:
->   1. The agent successfully produces a patch with `AgentFinishAction`, or
->   2. The attempt reaches the maximum iteration limit
-> - If an attempt fails, we retry with a fresh attempt (up to the 3-attempt maximum)
-> - If your LLM config has temperature=0, we will automatically use temperature=0.1 for the 2nd and 3rd attempts
->
-> To enable this iterative protocol, set `export ITERATIVE_EVAL_MODE=true`
-
-
 ### Running Locally with Docker
 
 Make sure your Docker daemon is running, and you have ample disk space (at least 200-500GB, depends on the SWE-Bench set you are running on) for the instance-level docker image.
@@ -59,7 +45,7 @@ to `CodeActAgent`.
 default, the script evaluates the entire SWE-bench_Lite test set (300 issues). Note:
 in order to use `eval_limit`, you must also set `agent`.
 - `max_iter`, e.g. `20`, is the maximum number of iterations for the agent to run. By
-default, it is set to 60.
+default, it is set to 30.
 - `num_workers`, e.g. `3`, is the number of parallel workers to run the evaluation. By
 default, it is set to 1.
 - `dataset`, a huggingface dataset name. e.g. `princeton-nlp/SWE-bench`, `princeton-nlp/SWE-bench_Lite`, or `princeton-nlp/SWE-bench_Verified`, specifies which dataset to evaluate on.

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -1,12 +1,9 @@
-import copy
 import json
 import os
 import subprocess
 import tempfile
 import time
-from dataclasses import dataclass
 from functools import partial
-from typing import Callable
 
 import pandas as pd
 from tqdm import tqdm
@@ -94,22 +91,12 @@ def get_config(metadata: EvalMetadata, instance: pd.Series) -> AppConfig:
     return config
 
 
-@dataclass
-class ConditionalImports:
-    """We instantiate the values in this dataclass differently if we're evaluating SWE-bench or SWE-Gym."""
-
-    get_eval_report: Callable
-    APPLY_PATCH_FAIL: str
-    APPLY_PATCH_PASS: str
-
-
 def process_instance(
     instance: pd.Series,
     metadata: EvalMetadata,
     reset_logger: bool = True,
     log_dir: str | None = None,
     runtime_failure_count: int = 0,
-    conditional_imports: ConditionalImports | None = None,
 ) -> EvalOutput:
     """
     Evaluate agent performance on a SWE-bench problem instance.
@@ -121,18 +108,9 @@ def process_instance(
         log_dir (str | None, default=None): Path to directory where log files will be written. Must
         be provided if `reset_logger` is set.
 
-        conditional_imports: A dataclass containing values that are imported differently based on
-        whether we're evaluating SWE-bench or SWE-Gym.
-
     Raises:
         AssertionError: if the `reset_logger` flag is set without a provided log directory.
-
-        AssertionError: if `conditional_imports` is not provided.
     """
-    assert (
-        conditional_imports is not None
-    ), 'conditional_imports must be provided to run process_instance using multiprocessing'
-
     # Setup the logger properly, so you can run multi-processing to parallelize the evaluation
     if reset_logger:
         assert (
@@ -146,7 +124,7 @@ def process_instance(
     config = get_config(metadata, instance)
     instance_id = instance.instance_id
     model_patch = instance['model_patch']
-    test_spec = instance['test_spec']
+    test_spec: TestSpec = instance['test_spec']
     logger.info(f'Starting evaluation for instance {instance_id}.')
 
     if 'test_result' not in instance.keys():
@@ -176,11 +154,6 @@ def process_instance(
         logger.warning(
             f'This is the {runtime_failure_count + 1}th attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
         )
-    metadata = copy.deepcopy(metadata)
-    metadata.details['runtime_failure_count'] = runtime_failure_count
-    metadata.details['remote_runtime_resource_factor'] = (
-        config.sandbox.remote_runtime_resource_factor
-    )
 
     try:
         runtime = create_runtime(config)
@@ -223,9 +196,7 @@ def process_instance(
         instance['test_result']['apply_patch_output'] = apply_patch_output
 
         if 'APPLY_PATCH_FAIL' in apply_patch_output:
-            logger.info(
-                f'[{instance_id}] {conditional_imports.APPLY_PATCH_FAIL}:\n{apply_patch_output}'
-            )
+            logger.info(f'[{instance_id}] {APPLY_PATCH_FAIL}:\n{apply_patch_output}')
             instance['test_result']['report']['failed_apply_patch'] = True
 
             return EvalOutput(
@@ -234,9 +205,7 @@ def process_instance(
                 metadata=metadata,
             )
         elif 'APPLY_PATCH_PASS' in apply_patch_output:
-            logger.info(
-                f'[{instance_id}] {conditional_imports.APPLY_PATCH_PASS}:\n{apply_patch_output}'
-            )
+            logger.info(f'[{instance_id}] {APPLY_PATCH_PASS}:\n{apply_patch_output}')
 
             # Run eval script in background and save output to log file
             log_file = '/tmp/eval_output.log'
@@ -302,20 +271,14 @@ def process_instance(
                         with open(test_output_path, 'w') as f:
                             f.write(test_output)
                         try:
-                            extra_kwargs = {}
-                            if 'SWE-Gym' in metadata.dataset:
-                                # SWE-Gym uses a different version of the package, hence a different eval report argument
-                                extra_kwargs['log_path'] = test_output_path
-                            else:
-                                extra_kwargs['test_log_path'] = test_output_path
-                            _report = conditional_imports.get_eval_report(
+                            _report = get_eval_report(
                                 test_spec=test_spec,
                                 prediction={
                                     'model_patch': model_patch,
                                     'instance_id': instance_id,
                                 },
+                                test_log_path=test_output_path,
                                 include_tests_status=True,
-                                **extra_kwargs,
                             )
                             report = _report[instance_id]
                             logger.info(
@@ -382,6 +345,7 @@ if __name__ == '__main__':
         )
         from swegym.harness.test_spec import (
             SWEbenchInstance,
+            TestSpec,
             make_test_spec,
         )
         from swegym.harness.utils import load_swebench_dataset
@@ -393,6 +357,7 @@ if __name__ == '__main__':
         )
         from swebench.harness.test_spec.test_spec import (
             SWEbenchInstance,
+            TestSpec,
             make_test_spec,
         )
         from swebench.harness.utils import load_swebench_dataset
@@ -475,21 +440,12 @@ if __name__ == '__main__':
             .decode('utf-8')
             .strip(),  # Current commit
             dataset=args.dataset,  # Dataset name from args
-            details={},
         )
 
     # The evaluation harness constrains the signature of `process_instance_func` but we need to
     # pass extra information. Build a new function object to avoid issues with multiprocessing.
     process_instance_func = partial(
-        process_instance,
-        log_dir=output_file.replace('.jsonl', '.logs'),
-        # We have to explicitly pass these imports to the process_instance function, otherwise
-        # they won't be available in the multiprocessing context.
-        conditional_imports=ConditionalImports(
-            get_eval_report=get_eval_report,
-            APPLY_PATCH_FAIL=APPLY_PATCH_FAIL,
-            APPLY_PATCH_PASS=APPLY_PATCH_PASS,
-        ),
+        process_instance, log_dir=output_file.replace('.jsonl', '.logs')
     )
 
     run_evaluation(

evaluation/benchmarks/swe_bench/resource/mapping.py

@@ -23,7 +23,7 @@ def get_resource_mapping(dataset_name: str) -> dict[str, float]:
     if dataset_name not in _global_resource_mapping:
         file_path = os.path.join(CUR_DIR, f'{dataset_name}.json')
         if not os.path.exists(file_path):
-            logger.info(f'Resource mapping for {dataset_name} not found.')
+            logger.warning(f'Resource mapping for {dataset_name} not found.')
             return None
 
         with open(file_path, 'r') as f:

evaluation/benchmarks/swe_bench/run_infer.py

@@ -1,5 +1,4 @@
 import asyncio
-import copy
 import json
 import os
 import tempfile
@@ -37,10 +36,9 @@ from openhands.core.config import (
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
-from openhands.critic import AgentFinishedCritic
 from openhands.events.action import CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation, ErrorObservation
-from openhands.events.serialization.event import event_from_dict, event_to_dict
+from openhands.events.serialization.event import event_to_dict
 from openhands.runtime.base import Runtime
 from openhands.utils.async_utils import call_async_from_sync
 from openhands.utils.shutdown_listener import sleep_if_should_continue
@@ -60,91 +58,62 @@ def _get_swebench_workspace_dir_name(instance: pd.Series) -> str:
 
 def get_instruction(instance: pd.Series, metadata: EvalMetadata):
     workspace_dir_name = _get_swebench_workspace_dir_name(instance)
-    instruction = f"""
-<uploaded_files>
-/workspace/{workspace_dir_name}
-</uploaded_files>
-
-I've uploaded a python code repository in the directory {workspace_dir_name}. Consider the following issue description:
-
-<issue_description>
-{instance.problem_statement}
-</issue_description>
-
-Can you help me implement the necessary changes to the repository so that the requirements specified in the <issue_description> are met?
-I've already taken care of all changes to any of the test files described in the <issue_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!
-Also the development Python environment is already set up for you (i.e., all dependencies already installed), so you don't need to install other packages.
-Your task is to make the minimal changes to non-test files in the /workspace/{workspace_dir_name} directory to ensure the <issue_description> is satisfied.
-
-Follow these steps to resolve the issue:
-
-1. EXPLORATION: First, thoroughly explore the repository structure using tools like `find` and `grep`.
-   - Identify all files mentioned in the problem statement
-   - Locate where the issue occurs in the codebase
-   - Understand the surrounding context and dependencies
-   - Use `grep` to search for relevant functions, classes, or error messages
-
-2. ANALYSIS: Based on your exploration, think carefully about the problem and propose 2-5 possible approaches to fix the issue.
-   - Analyze the root cause of the problem
-   - Consider trade-offs between different solutions
-   - Select the most promising approach and explain your reasoning
-
-3. TEST CREATION: Before implementing any fix, create a script to reproduce and verify the issue.
-   - Look at existing test files in the repository to understand the test format/structure
-   - Create a minimal reproduction script that demonstrates the issue
-   - Run your script to confirm the error exists
-
-4. IMPLEMENTATION: Edit the source code to implement your chosen solution.
-   - Make minimal, focused changes to fix the issue
-
-5. VERIFICATION: Test your implementation thoroughly.
-   - Run your reproduction script to verify the fix works
-   - Add edge cases to your test script to ensure comprehensive coverage
-   - Run existing tests related to the modified code to ensure you haven't broken anything
-
-6. FINAL REVIEW: Carefully re-read the problem description and compare your changes with the base commit {instance["base_commit"]}.
-   - Ensure you've fully addressed all requirements
-   - Run any tests in the repository related to:
-     * The issue you are fixing
-     * The files you modified
-     * The functions you changed
-   - If any tests fail, revise your implementation until all tests pass
-
-Be thorough in your exploration, testing, and reasoning. It's fine if your thinking process is lengthy - quality and completeness are more important than brevity.
-"""
+    # Instruction based on Anthropic's official trajectory
+    # https://github.com/eschluntz/swe-bench-experiments/tree/main/evaluation/verified/20241022_tools_claude-3-5-sonnet-updated/trajs
+    instruction = (
+        '<uploaded_files>\n'
+        f'/workspace/{workspace_dir_name}\n'
+        '</uploaded_files>\n'
+        f"I've uploaded a python code repository in the directory {workspace_dir_name}. Consider the following issue description:\n\n"
+        f'<issue_description>\n'
+        f'{instance.problem_statement}\n'
+        '</issue_description>\n\n'
+        'Can you help me implement the necessary changes to the repository so that the requirements specified in the <issue_description> are met?\n'
+        "I've already taken care of all changes to any of the test files described in the <issue_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!\n"
+        "Also the development Python environment is already set up for you (i.e., all dependencies already installed), so you don't need to install other packages.\n"
+        'Your task is to make the minimal changes to non-test files in the /workspace directory to ensure the <issue_description> is satisfied.\n'
+        'Follow these steps to resolve the issue:\n'
+        '1. As a first step, it might be a good idea to explore the repo to familiarize yourself with its structure.\n'
+        '2. Create a script to reproduce the error and execute it with `python <filename.py>` using the BashTool, to confirm the error\n'
+        '3. Edit the sourcecode of the repo to resolve the issue\n'
+        '4. Rerun your reproduce script and confirm that the error is fixed!\n'
+        '5. Think about edgecases, add comprehensive tests for them in your reproduce script, and run them to make sure your fix handles them as well\n'
+        f'6. Once you are done with the initial implementation, please carefully re-read the problem description and check the difference between the current code and the base commit {instance["base_commit"]}. Do you think that the issue has been completely and comprehensively solved? Write tests to check the correctness of the solution, specifically focusing on tests that may point out any remaining problems that are not yet solved. Run all of the tests in the repo and check if any of them fail, and if they do fix the code. Repeat this process of carefully reading the problem description and current implementation, testing, and fixing any problems until you are confident that the current implementation is correct. Find and run any tests in the repo that are related to:\n'
+        '   - The issue you are fixing\n'
+        '   - The files you modified\n'
+        '   - The functions you changed\n'
+        '   Make sure all these tests pass with your changes.\n'
+        "Your thinking should be thorough and so it's fine if it's very long.\n"
+    )
 
     if RUN_WITH_BROWSING:
-        instruction += """
-<IMPORTANT!>
-You SHOULD NEVER attempt to browse the web.
-</IMPORTANT!>
-"""
+        instruction += (
+            '<IMPORTANT!>\n'
+            'You SHOULD NEVER attempt to browse the web. '
+            '</IMPORTANT!>\n'
+        )
     return instruction
 
 
 # TODO: migrate all swe-bench docker to ghcr.io/openhands
-DEFAULT_DOCKER_IMAGE_PREFIX = os.environ.get(
-    'EVAL_DOCKER_IMAGE_PREFIX', 'docker.io/xingyaoww/'
-)
-logger.info(f'Default docker image prefix: {DEFAULT_DOCKER_IMAGE_PREFIX}')
+DOCKER_IMAGE_PREFIX = os.environ.get('EVAL_DOCKER_IMAGE_PREFIX', 'docker.io/xingyaoww/')
+logger.info(f'Using docker image prefix: {DOCKER_IMAGE_PREFIX}')
 
 
 def get_instance_docker_image(instance_id: str, official_image: bool = False) -> str:
     if official_image:
         # Official SWE-Bench image
         # swebench/sweb.eval.x86_64.django_1776_django-11333:v1
-        docker_image_prefix = 'docker.io/swebench/'
         repo, name = instance_id.split('__')
         image_name = f'sweb.eval.x86_64.{repo}_1776_{name}:latest'
         logger.warning(f'Using official SWE-Bench image: {image_name}')
     else:
         # OpenHands version of the image
-        docker_image_prefix = DEFAULT_DOCKER_IMAGE_PREFIX
         image_name = 'sweb.eval.x86_64.' + instance_id
         image_name = image_name.replace(
             '__', '_s_'
         )  # to comply with docker image naming convention
-    return (docker_image_prefix.rstrip('/') + '/' + image_name).lower()
+    return (DOCKER_IMAGE_PREFIX.rstrip('/') + '/' + image_name).lower()
 
 
 def get_config(
@@ -153,8 +122,7 @@ def get_config(
 ) -> AppConfig:
     # We use a different instance image for the each instance of swe-bench eval
     use_official_image = bool(
-        ('verified' in metadata.dataset.lower() or 'lite' in metadata.dataset.lower())
-        and 'swe-gym' not in metadata.dataset.lower()
+        'verified' in metadata.dataset.lower() or 'lite' in metadata.dataset.lower()
     )
     base_container_image = get_instance_docker_image(
         instance['instance_id'], use_official_image
@@ -480,13 +448,6 @@ def process_instance(
         logger.warning(
             f'This is the {runtime_failure_count + 1}th attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
         )
-
-    metadata = copy.deepcopy(metadata)
-    metadata.details['runtime_failure_count'] = runtime_failure_count
-    metadata.details['remote_runtime_resource_factor'] = (
-        config.sandbox.remote_runtime_resource_factor
-    )
-
     runtime = create_runtime(config)
     call_async_from_sync(runtime.connect)
 
@@ -572,6 +533,20 @@ def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
     return dataset
 
 
+# A list of instances that are known to be tricky to infer
+# (will cause runtime failure even with resource factor = 8)
+SWEGYM_EXCLUDE_IDS = [
+    'dask__dask-10422',
+    'pandas-dev__pandas-50548',
+    'pandas-dev__pandas-53672',
+    'pandas-dev__pandas-54174',
+    'pandas-dev__pandas-55518',
+    'pandas-dev__pandas-58383',
+    'pydata__xarray-6721',
+    'pytest-dev__pytest-10081',
+    'pytest-dev__pytest-7236',
+]
+
 if __name__ == '__main__':
     parser = get_parser()
     parser.add_argument(
@@ -596,20 +571,11 @@ if __name__ == '__main__':
         f'Loaded dataset {args.dataset} with split {args.split}: {len(swe_bench_tests)} tasks'
     )
     if 'SWE-Gym' in args.dataset:
-        with open(
-            os.path.join(
-                os.path.dirname(os.path.abspath(__file__)),
-                'split',
-                'swegym_verified_instances.json',
-            ),
-            'r',
-        ) as f:
-            swegym_verified_instances = json.load(f)
-            swe_bench_tests = swe_bench_tests[
-                swe_bench_tests['instance_id'].isin(swegym_verified_instances)
-            ]
+        swe_bench_tests = swe_bench_tests[
+            ~swe_bench_tests['instance_id'].isin(SWEGYM_EXCLUDE_IDS)
+        ]
         logger.info(
-            f'{len(swe_bench_tests)} tasks left after filtering for SWE-Gym verified instances'
+            f'{len(swe_bench_tests)} tasks left after excluding SWE-Gym excluded tasks'
         )
 
     llm_config = None
@@ -640,132 +606,20 @@ if __name__ == '__main__':
 
     output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
     print(f'### OUTPUT FILE: {output_file} ###')
+    instances = prepare_dataset(swe_bench_tests, output_file, args.eval_n_limit)
 
-    # Run evaluation in iterative mode:
-    # If a rollout fails to output AgentFinishAction, we will try again until it succeeds OR total 3 attempts have been made.
-    ITERATIVE_EVAL_MODE = (
-        os.environ.get('ITERATIVE_EVAL_MODE', 'false').lower() == 'true'
+    if len(instances) > 0 and not isinstance(
+        instances['PASS_TO_PASS'][instances['PASS_TO_PASS'].index[0]], str
+    ):
+        for col in ['PASS_TO_PASS', 'FAIL_TO_PASS']:
+            instances[col] = instances[col].apply(lambda x: str(x))
+
+    run_evaluation(
+        instances,
+        metadata,
+        output_file,
+        args.eval_num_workers,
+        process_instance,
+        timeout_seconds=8 * 60 * 60,  # 8 hour PER instance should be more than enough
+        max_retries=5,
     )
-    ITERATIVE_EVAL_MODE_MAX_ATTEMPTS = int(
-        os.environ.get('ITERATIVE_EVAL_MODE_MAX_ATTEMPTS', '3')
-    )
-
-    if not ITERATIVE_EVAL_MODE:
-        # load the dataset
-        instances = prepare_dataset(swe_bench_tests, output_file, args.eval_n_limit)
-        if len(instances) > 0 and not isinstance(
-            instances['PASS_TO_PASS'][instances['PASS_TO_PASS'].index[0]], str
-        ):
-            for col in ['PASS_TO_PASS', 'FAIL_TO_PASS']:
-                instances[col] = instances[col].apply(lambda x: str(x))
-
-        run_evaluation(
-            instances,
-            metadata,
-            output_file,
-            args.eval_num_workers,
-            process_instance,
-            timeout_seconds=8
-            * 60
-            * 60,  # 8 hour PER instance should be more than enough
-            max_retries=5,
-        )
-    else:
-        critic = AgentFinishedCritic()
-
-        def get_cur_output_file_path(attempt: int) -> str:
-            return (
-                f'{output_file.removesuffix(".jsonl")}.critic_attempt_{attempt}.jsonl'
-            )
-
-        eval_ids = None
-        for attempt in range(1, ITERATIVE_EVAL_MODE_MAX_ATTEMPTS + 1):
-            cur_output_file = get_cur_output_file_path(attempt)
-            logger.info(
-                f'Running evaluation with critic {critic.__class__.__name__} for attempt {attempt} of {ITERATIVE_EVAL_MODE_MAX_ATTEMPTS}.'
-            )
-
-            # For deterministic eval, we set temperature to 0.1 for (>1) attempt
-            # so hopefully we get slightly different results
-            if attempt > 1 and metadata.llm_config.temperature == 0:
-                logger.info(
-                    f'Detected temperature is 0 for (>1) attempt {attempt}. Setting temperature to 0.1...'
-                )
-                metadata.llm_config.temperature = 0.1
-
-            # Load instances - at first attempt, we evaluate all instances
-            # On subsequent attempts, we only evaluate the instances that failed the previous attempt determined by critic
-            instances = prepare_dataset(
-                swe_bench_tests, cur_output_file, args.eval_n_limit, eval_ids=eval_ids
-            )
-            if len(instances) > 0 and not isinstance(
-                instances['PASS_TO_PASS'][instances['PASS_TO_PASS'].index[0]], str
-            ):
-                for col in ['PASS_TO_PASS', 'FAIL_TO_PASS']:
-                    instances[col] = instances[col].apply(lambda x: str(x))
-
-            # Run evaluation - but save them to cur_output_file
-            logger.info(
-                f'Evaluating {len(instances)} instances for attempt {attempt}...'
-            )
-            run_evaluation(
-                instances,
-                metadata,
-                cur_output_file,
-                args.eval_num_workers,
-                process_instance,
-                timeout_seconds=8
-                * 60
-                * 60,  # 8 hour PER instance should be more than enough
-                max_retries=5,
-            )
-
-            # When eval is done, we update eval_ids to the instances that failed the current attempt
-            instances_failed = []
-            logger.info(
-                f'Use critic {critic.__class__.__name__} to check {len(instances)} instances for attempt {attempt}...'
-            )
-            with open(cur_output_file, 'r') as f:
-                for line in f:
-                    instance = json.loads(line)
-                    history = [event_from_dict(event) for event in instance['history']]
-                    critic_result = critic.evaluate(history)
-                    if not critic_result.success:
-                        instances_failed.append(instance['instance_id'])
-            logger.info(
-                f'{len(instances_failed)} instances failed the current attempt {attempt}: {instances_failed}'
-            )
-            eval_ids = instances_failed
-
-            # If no instances failed, we break
-            if len(instances_failed) == 0:
-                break
-
-        # Then we should aggregate the results from all attempts into the original output file
-        # and remove the intermediate files
-        logger.info(
-            'Aggregating results from all attempts into the original output file...'
-        )
-        fout = open(output_file, 'w')
-        added_instance_ids = set()
-        for attempt in reversed(range(1, ITERATIVE_EVAL_MODE_MAX_ATTEMPTS + 1)):
-            cur_output_file = get_cur_output_file_path(attempt)
-            if not os.path.exists(cur_output_file):
-                logger.warning(
-                    f'Intermediate output file {cur_output_file} does not exist. Skipping...'
-                )
-                continue
-
-            with open(cur_output_file, 'r') as f:
-                for line in f:
-                    instance = json.loads(line)
-                    if instance['instance_id'] not in added_instance_ids:
-                        fout.write(line)
-                        added_instance_ids.add(instance['instance_id'])
-            logger.info(
-                f'Aggregated instances from {cur_output_file}. Total instances added so far: {len(added_instance_ids)}'
-            )
-        fout.close()
-        logger.info(
-            f'Done! Total {len(added_instance_ids)} instances added to {output_file}'
-        )

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

@@ -9,7 +9,7 @@ parser.add_argument(
     '--dataset_name',
     type=str,
     help='Name of the dataset to download',
-    default='princeton-nlp/SWE-bench_Verified',
+    default='princeton-nlp/SWE-bench_Lite',
 )
 parser.add_argument('--split', type=str, help='Split to download', default='test')
 args = parser.parse_args()
@@ -20,12 +20,7 @@ print(
     f'Downloading gold patches from {args.dataset_name} (split: {args.split}) to {output_filepath}'
 )
 patches = [
-    {
-        'instance_id': row['instance_id'],
-        'model_patch': row['patch'],
-        'model_name_or_path': 'gold',
-    }
-    for row in dataset
+    {'instance_id': row['instance_id'], 'model_patch': row['patch']} for row in dataset
 ]
 print(f'{len(patches)} gold patches loaded')
 pd.DataFrame(patches).to_json(output_filepath, lines=True, orient='records')

evaluation/benchmarks/swe_bench/scripts/run_infer.sh

@@ -25,8 +25,8 @@ if [ -z "$AGENT" ]; then
 fi
 
 if [ -z "$MAX_ITER" ]; then
-  echo "MAX_ITER not specified, use default 60"
-  MAX_ITER=60
+  echo "MAX_ITER not specified, use default 100"
+  MAX_ITER=100
 fi
 
 if [ -z "$RUN_WITH_BROWSING" ]; then

evaluation/integration_tests/run_infer.py

@@ -34,6 +34,7 @@ from openhands.utils.async_utils import call_async_from_sync
 
 FAKE_RESPONSES = {
     'CodeActAgent': fake_user_response,
+    'DelegatorAgent': fake_user_response,
     'VisualBrowsingAgent': fake_user_response,
 }
 

frontend/__tests__/components/features/payment/payment-form.test.tsx

@@ -4,10 +4,8 @@ import userEvent from "@testing-library/user-event";
 import { afterEach, beforeEach, describe, expect, it, test, vi } from "vitest";
 import OpenHands from "#/api/open-hands";
 import { PaymentForm } from "#/components/features/payment/payment-form";
-import * as featureFlags from "#/utils/feature-flags";
 
 describe("PaymentForm", () => {
-  const billingSettingsSpy = vi.spyOn(featureFlags, "BILLING_SETTINGS");
   const getBalanceSpy = vi.spyOn(OpenHands, "getBalance");
   const createCheckoutSessionSpy = vi.spyOn(OpenHands, "createCheckoutSession");
   const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
@@ -28,7 +26,6 @@ describe("PaymentForm", () => {
       GITHUB_CLIENT_ID: "123",
       POSTHOG_CLIENT_KEY: "456",
     });
-    billingSettingsSpy.mockReturnValue(true);
   });
 
   afterEach(() => {

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

@@ -2,13 +2,11 @@ import { createRoutesStub } from "react-router";
 import { afterEach, beforeAll, describe, expect, it, vi } from "vitest";
 import { renderWithProviders } from "test-utils";
 import { screen, waitFor } from "@testing-library/react";
+import toast from "react-hot-toast";
 import App from "#/routes/_oh.app/route";
 import OpenHands from "#/api/open-hands";
-import * as CustomToast from "#/utils/custom-toast-handlers";
 
 describe("App", () => {
-  const errorToastSpy = vi.spyOn(CustomToast, "displayErrorToast");
-
   const RouteStub = createRoutesStub([
     { Component: App, path: "/conversation/:conversationId" },
   ]);
@@ -36,19 +34,26 @@ describe("App", () => {
     await screen.findByTestId("app-route");
   });
 
-  it("should call endSession if the user does not have permission to view conversation", async () => {
-    const getConversationSpy = vi.spyOn(OpenHands, "getConversation");
+  it(
+    "should call endSession if the user does not have permission to view conversation",
+    async () => {
+      const errorToastSpy = vi.spyOn(toast, "error");
+      const getConversationSpy = vi.spyOn(OpenHands, "getConversation");
 
-    getConversationSpy.mockResolvedValue(null);
-    renderWithProviders(<RouteStub initialEntries={["/conversation/9999"]} />);
+      getConversationSpy.mockResolvedValue(null);
+      renderWithProviders(
+        <RouteStub initialEntries={["/conversation/9999"]} />,
+      );
 
-    await waitFor(() => {
-      expect(endSessionMock).toHaveBeenCalledOnce();
-      expect(errorToastSpy).toHaveBeenCalledOnce();
-    });
-  });
+      await waitFor(() => {
+        expect(endSessionMock).toHaveBeenCalledOnce();
+        expect(errorToastSpy).toHaveBeenCalledOnce();
+      });
+    },
+  );
 
   it("should not call endSession if the user has permission", async () => {
+    const errorToastSpy = vi.spyOn(toast, "error");
     const getConversationSpy = vi.spyOn(OpenHands, "getConversation");
 
     getConversationSpy.mockResolvedValue({

frontend/__tests__/routes/home.test.tsx

@@ -8,7 +8,6 @@ import MainApp from "#/routes/_oh/route";
 import SettingsScreen from "#/routes/settings";
 import Home from "#/routes/_oh._index/route";
 import OpenHands from "#/api/open-hands";
-import * as FeatureFlags from "#/utils/feature-flags";
 
 const createAxiosNotFoundErrorObject = () =>
   new AxiosError(
@@ -26,32 +25,32 @@ const createAxiosNotFoundErrorObject = () =>
     },
   );
 
-const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-
-const RouterStub = createRoutesStub([
-  {
-    // layout route
-    Component: MainApp,
-    path: "/",
-    children: [
-      {
-        // home route
-        Component: Home,
-        path: "/",
-      },
-      {
-        Component: SettingsScreen,
-        path: "/settings",
-      },
-    ],
-  },
-]);
-
-afterEach(() => {
-  vi.clearAllMocks();
-});
-
 describe("Home Screen", () => {
+  const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
+
+  const RouterStub = createRoutesStub([
+    {
+      // layout route
+      Component: MainApp,
+      path: "/",
+      children: [
+        {
+          // home route
+          Component: Home,
+          path: "/",
+        },
+        {
+          Component: SettingsScreen,
+          path: "/settings",
+        },
+      ],
+    },
+  ]);
+
+  afterEach(() => {
+    vi.clearAllMocks();
+  });
+
   it("should render the home screen", () => {
     renderWithProviders(<RouterStub initialEntries={["/"]} />);
   });
@@ -78,82 +77,41 @@ describe("Home Screen", () => {
     const settingsScreen = await screen.findByTestId("settings-screen");
     expect(settingsScreen).toBeInTheDocument();
   });
-});
 
-describe("Settings 404", () => {
-  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+  describe("Settings 404", () => {
+    it("should open the settings modal if GET /settings fails with a 404", async () => {
+      const error = createAxiosNotFoundErrorObject();
+      getSettingsSpy.mockRejectedValue(error);
 
-  it("should open the settings modal if GET /settings fails with a 404", async () => {
-    const error = createAxiosNotFoundErrorObject();
-    getSettingsSpy.mockRejectedValue(error);
+      renderWithProviders(<RouterStub initialEntries={["/"]} />);
 
-    renderWithProviders(<RouterStub initialEntries={["/"]} />);
-
-    const settingsModal = await screen.findByTestId("ai-config-modal");
-    expect(settingsModal).toBeInTheDocument();
-  });
-
-  it("should navigate to the settings screen when clicking the advanced settings button", async () => {
-    const error = createAxiosNotFoundErrorObject();
-    getSettingsSpy.mockRejectedValue(error);
-
-    const user = userEvent.setup();
-    renderWithProviders(<RouterStub initialEntries={["/"]} />);
-
-    const settingsScreen = screen.queryByTestId("settings-screen");
-    expect(settingsScreen).not.toBeInTheDocument();
-
-    const settingsModal = await screen.findByTestId("ai-config-modal");
-    expect(settingsModal).toBeInTheDocument();
-
-    const advancedSettingsButton = await screen.findByTestId(
-      "advanced-settings-link",
-    );
-    await user.click(advancedSettingsButton);
-
-    const settingsScreenAfter = await screen.findByTestId("settings-screen");
-    expect(settingsScreenAfter).toBeInTheDocument();
-
-    const settingsModalAfter = screen.queryByTestId("ai-config-modal");
-    expect(settingsModalAfter).not.toBeInTheDocument();
-  });
-
-  it("should not open the settings modal if GET /settings fails but is SaaS mode", async () => {
-    // TODO: Remove HIDE_LLM_SETTINGS check once released
-    vi.spyOn(FeatureFlags, "HIDE_LLM_SETTINGS").mockReturnValue(true);
-    // @ts-expect-error - we only need APP_MODE for this test
-    getConfigSpy.mockResolvedValue({ APP_MODE: "saas" });
-    const error = createAxiosNotFoundErrorObject();
-    getSettingsSpy.mockRejectedValue(error);
-
-    renderWithProviders(<RouterStub initialEntries={["/"]} />);
-
-    // small hack to wait for the modal to not appear
-    await expect(
-      screen.findByTestId("ai-config-modal", {}, { timeout: 1000 }),
-    ).rejects.toThrow();
-  });
-});
-
-describe("Setup Payment modal", () => {
-  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-
-  afterEach(() => {
-    vi.resetAllMocks();
-  });
-
-  it("should only render if SaaS mode and is new user", async () => {
-    // @ts-expect-error - we only need the APP_MODE for this test
-    getConfigSpy.mockResolvedValue({
-      APP_MODE: "saas",
+      const settingsModal = await screen.findByTestId("ai-config-modal");
+      expect(settingsModal).toBeInTheDocument();
     });
-    vi.spyOn(FeatureFlags, "BILLING_SETTINGS").mockReturnValue(true);
-    const error = createAxiosNotFoundErrorObject();
-    getSettingsSpy.mockRejectedValue(error);
 
-    renderWithProviders(<RouterStub initialEntries={["/"]} />);
+    it("should navigate to the settings screen when clicking the advanced settings button", async () => {
+      const error = createAxiosNotFoundErrorObject();
+      getSettingsSpy.mockRejectedValue(error);
 
-    const setupPaymentModal = await screen.findByTestId("proceed-to-stripe-button");
-    expect(setupPaymentModal).toBeInTheDocument();
+      const user = userEvent.setup();
+      renderWithProviders(<RouterStub initialEntries={["/"]} />);
+
+      const settingsScreen = screen.queryByTestId("settings-screen");
+      expect(settingsScreen).not.toBeInTheDocument();
+
+      const settingsModal = await screen.findByTestId("ai-config-modal");
+      expect(settingsModal).toBeInTheDocument();
+
+      const advancedSettingsButton = await screen.findByTestId(
+        "advanced-settings-link",
+      );
+      await user.click(advancedSettingsButton);
+
+      const settingsScreenAfter = await screen.findByTestId("settings-screen");
+      expect(settingsScreenAfter).toBeInTheDocument();
+
+      const settingsModalAfter = screen.queryByTestId("ai-config-modal");
+      expect(settingsModalAfter).not.toBeInTheDocument();
+    });
   });
 });

frontend/__tests__/routes/settings.test.tsx

@@ -1,15 +1,6 @@
 import { render, screen, waitFor, within } from "@testing-library/react";
 import { createRoutesStub } from "react-router";
-import {
-  afterEach,
-  beforeAll,
-  beforeEach,
-  describe,
-  expect,
-  it,
-  test,
-  vi,
-} from "vitest";
+import { afterEach, describe, expect, it, test, vi } from "vitest";
 import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
 import userEvent, { UserEvent } from "@testing-library/user-event";
 import OpenHands from "#/api/open-hands";
@@ -20,7 +11,6 @@ import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
 import { PostApiSettings } from "#/types/settings";
 import * as ConsentHandlers from "#/utils/handle-capture-consent";
 import AccountSettings from "#/routes/account-settings";
-import * as FeatureFlags from "#/utils/feature-flags";
 
 const toggleAdvancedSettings = async (user: UserEvent) => {
   const advancedSwitch = await screen.findByTestId("advanced-settings-switch");
@@ -39,11 +29,6 @@ describe("Settings Screen", () => {
     useAppLogout: vi.fn().mockReturnValue({ handleLogout: handleLogoutMock }),
   }));
 
-  beforeAll(() => {
-    // TODO: Remove this once we release
-    vi.spyOn(FeatureFlags, "HIDE_LLM_SETTINGS").mockReturnValue(true);
-  });
-
   afterEach(() => {
     vi.clearAllMocks();
   });
@@ -82,23 +67,12 @@ describe("Settings Screen", () => {
   });
 
   describe("Account Settings", () => {
-    beforeEach(() => {
-      getConfigSpy.mockResolvedValue({
-        APP_MODE: "oss",
-        GITHUB_CLIENT_ID: "123",
-        POSTHOG_CLIENT_KEY: "456",
-      });
-    });
-
     it("should render the account settings", async () => {
       renderSettingsScreen();
 
       await waitFor(() => {
         screen.getByTestId("github-token-input");
-        // Check for GitHub link instead of the help anchor
-        screen.getByRole("link", { name: "GitHub" });
-        // Check for documentation link
-        screen.getByRole("link", { name: "documentation" });
+        screen.getByTestId("github-token-help-anchor");
         screen.getByTestId("language-input");
         screen.getByTestId("enable-analytics-switch");
       });
@@ -240,12 +214,10 @@ describe("Settings Screen", () => {
 
       await waitFor(() => {
         const input = screen.queryByTestId("github-token-input");
-        const githubLink = screen.queryByText("GitHub");
-        const documentationLink = screen.queryByText("documentation");
+        const helpAnchor = screen.queryByTestId("github-token-help-anchor");
 
         expect(input).not.toBeInTheDocument();
-        expect(githubLink).not.toBeInTheDocument();
-        expect(documentationLink).not.toBeInTheDocument();
+        expect(helpAnchor).not.toBeInTheDocument();
       });
     });
 
@@ -308,14 +280,6 @@ describe("Settings Screen", () => {
   });
 
   describe("LLM Settings", () => {
-    beforeEach(() => {
-      getConfigSpy.mockResolvedValue({
-        APP_MODE: "oss",
-        GITHUB_CLIENT_ID: "123",
-        POSTHOG_CLIENT_KEY: "456",
-      });
-    });
-
     it("should render the basic LLM settings by default", async () => {
       renderSettingsScreen();
 
@@ -463,7 +427,8 @@ describe("Settings Screen", () => {
         expect(input).not.toBeInTheDocument();
       });
 
-      it.skip("should render the runtime settings input if SaaS mode", async () => {
+      it("should render the runtime settings input if SaaS mode", async () => {
+        const user = userEvent.setup();
         getConfigSpy.mockResolvedValue({
           APP_MODE: "saas",
           GITHUB_CLIENT_ID: "123",
@@ -471,10 +436,12 @@ describe("Settings Screen", () => {
         });
 
         renderSettingsScreen();
-        await screen.findByTestId("runtime-settings-input");
+
+        await toggleAdvancedSettings(user);
+        screen.getByTestId("runtime-settings-input");
       });
 
-      it.skip("should set the default runtime setting set", async () => {
+      it("should set the default runtime setting set", async () => {
         getConfigSpy.mockResolvedValue({
           APP_MODE: "saas",
           GITHUB_CLIENT_ID: "123",
@@ -488,11 +455,13 @@ describe("Settings Screen", () => {
 
         renderSettingsScreen();
 
+        await toggleAdvancedSettings(userEvent.setup());
+
         const input = await screen.findByTestId("runtime-settings-input");
         expect(input).toHaveValue("1x (2 core, 8G)");
       });
 
-      it.skip("should always have the runtime input disabled", async () => {
+      it("should always have the runtime input disabled", async () => {
         getConfigSpy.mockResolvedValue({
           APP_MODE: "saas",
           GITHUB_CLIENT_ID: "123",
@@ -501,6 +470,8 @@ describe("Settings Screen", () => {
 
         renderSettingsScreen();
 
+        await toggleAdvancedSettings(userEvent.setup());
+
         const input = await screen.findByTestId("runtime-settings-input");
         expect(input).toBeDisabled();
       });
@@ -519,6 +490,8 @@ describe("Settings Screen", () => {
 
         renderSettingsScreen();
 
+        await toggleAdvancedSettings(user);
+
         const input = await screen.findByTestId("runtime-settings-input");
         await user.click(input);
 
@@ -726,7 +699,7 @@ describe("Settings Screen", () => {
       expect(saveSettingsSpy).toHaveBeenCalledWith(
         expect.objectContaining({
           llm_api_key: "", // empty because it's not set previously
-          provider_tokens: undefined,
+          github_token: undefined,
           language: "no",
         }),
       );
@@ -763,7 +736,7 @@ describe("Settings Screen", () => {
 
       expect(saveSettingsSpy).toHaveBeenCalledWith(
         expect.objectContaining({
-          provider_tokens: undefined,
+          github_token: undefined,
           llm_api_key: "", // empty because it's not set previously
           llm_model: "openai/gpt-4o",
         }),
@@ -806,7 +779,7 @@ describe("Settings Screen", () => {
 
       expect(saveSettingsSpy).toHaveBeenCalledWith({
         ...mockCopy,
-        provider_tokens: undefined, // not set
+        github_token: undefined, // not set
         llm_api_key: "", // reset as well
       });
       expect(screen.queryByTestId("reset-modal")).not.toBeInTheDocument();
@@ -980,104 +953,4 @@ describe("Settings Screen", () => {
       );
     });
   });
-
-  describe("SaaS mode", () => {
-    beforeEach(() => {
-      getConfigSpy.mockResolvedValue({
-        APP_MODE: "saas",
-        GITHUB_CLIENT_ID: "123",
-        POSTHOG_CLIENT_KEY: "456",
-      });
-    });
-
-    it("should hide the entire LLM section", async () => {
-      renderSettingsScreen();
-
-      await waitFor(() => {
-        screen.getByTestId("account-settings-form"); // wait for the account settings form to render
-
-        const llmSection = screen.queryByTestId("llm-settings-section");
-        expect(llmSection).not.toBeInTheDocument();
-      });
-    });
-
-    it("should not render LLM Provider, LLM Model, and LLM API Key inputs", async () => {
-      renderSettingsScreen();
-
-      await waitFor(() => {
-        screen.getByTestId("account-settings-form"); // wait for the account settings form to render
-
-        const providerInput = screen.queryByTestId("llm-provider-input");
-        const modelInput = screen.queryByTestId("llm-model-input");
-        const apiKeyInput = screen.queryByTestId("llm-api-key-input");
-        const llmApiKeyHelpAnchor = screen.queryByTestId(
-          "llm-api-key-help-anchor",
-        );
-        const advancedSettingsSwitch = screen.queryByTestId(
-          "advanced-settings-switch",
-        );
-
-        expect(providerInput).not.toBeInTheDocument();
-        expect(modelInput).not.toBeInTheDocument();
-        expect(apiKeyInput).not.toBeInTheDocument();
-        expect(llmApiKeyHelpAnchor).not.toBeInTheDocument();
-        expect(advancedSettingsSwitch).not.toBeInTheDocument();
-      });
-    });
-
-    // We might want to bring this back if users wish to set advanced settings
-    it.skip("should render advanced settings by default", async () => {
-      renderSettingsScreen();
-
-      await waitFor(() => {
-        screen.getByTestId("account-settings-form"); // wait for the account settings form to render
-
-        const agentInput = screen.getByTestId("agent-input"); // this is only rendered in advanced mode
-        expect(agentInput).toBeInTheDocument();
-
-        // we should not allow the user to change these fields
-        const customModelInput = screen.queryByTestId("llm-custom-model-input");
-        const baseUrlInput = screen.queryByTestId("base-url-input");
-
-        expect(customModelInput).not.toBeInTheDocument();
-        expect(baseUrlInput).not.toBeInTheDocument();
-      });
-    });
-
-    it("should not submit the unwanted fields when saving", async () => {
-      const user = userEvent.setup();
-      renderSettingsScreen();
-
-      const saveButton = await screen.findByText("Save Changes");
-      await user.click(saveButton);
-
-      expect(saveSettingsSpy).toHaveBeenCalledWith(
-        expect.objectContaining({
-          llm_api_key: undefined,
-          llm_base_url: undefined,
-          llm_model: undefined,
-        }),
-      );
-    });
-
-    it("should not submit the unwanted fields when resetting", async () => {
-      const user = userEvent.setup();
-      renderSettingsScreen();
-
-      const resetButton = await screen.findByText("Reset to defaults");
-      await user.click(resetButton);
-
-      const modal = await screen.findByTestId("reset-modal");
-      const confirmButton = within(modal).getByText("Reset");
-      await user.click(confirmButton);
-
-      expect(saveSettingsSpy).toHaveBeenCalledWith(
-        expect.objectContaining({
-          llm_api_key: undefined,
-          llm_base_url: undefined,
-          llm_model: undefined,
-        }),
-      );
-    });
-  });
 });

frontend/__tests__/services/actions.test.ts

@@ -1,9 +1,7 @@
 import { describe, it, expect, vi, beforeEach } from "vitest";
-import { handleStatusMessage, handleActionMessage } from "#/services/actions";
+import { handleStatusMessage } from "#/services/actions";
 import store from "#/store";
 import { trackError } from "#/utils/error-handler";
-import ActionType from "#/types/action-type";
-import { ActionMessage } from "#/types/message";
 
 // Mock dependencies
 vi.mock("#/utils/error-handler", () => ({
@@ -58,89 +56,4 @@ describe("Actions Service", () => {
       }));
     });
   });
-
-  describe("handleActionMessage", () => {
-    it("should use first-person perspective for task completion messages", () => {
-      // Test partial completion
-      const messagePartial: ActionMessage = {
-        id: 1,
-        action: ActionType.FINISH,
-        source: "agent",
-        message: "",
-        timestamp: new Date().toISOString(),
-        args: {
-          final_thought: "",
-          task_completed: "partial",
-          outputs: "",
-          thought: ""
-        }
-      };
-
-      // Mock implementation to capture the message
-      let capturedPartialMessage = "";
-      (store.dispatch as any).mockImplementation((action: any) => {
-        if (action.type === "chat/addAssistantMessage" && 
-            action.payload.includes("believe that the task was **completed partially**")) {
-          capturedPartialMessage = action.payload;
-        }
-      });
-
-      handleActionMessage(messagePartial);
-      expect(capturedPartialMessage).toContain("I believe that the task was **completed partially**");
-      
-      // Test not completed
-      const messageNotCompleted: ActionMessage = {
-        id: 2,
-        action: ActionType.FINISH,
-        source: "agent",
-        message: "",
-        timestamp: new Date().toISOString(),
-        args: {
-          final_thought: "",
-          task_completed: "false",
-          outputs: "",
-          thought: ""
-        }
-      };
-
-      // Mock implementation to capture the message
-      let capturedNotCompletedMessage = "";
-      (store.dispatch as any).mockImplementation((action: any) => {
-        if (action.type === "chat/addAssistantMessage" && 
-            action.payload.includes("believe that the task was **not completed**")) {
-          capturedNotCompletedMessage = action.payload;
-        }
-      });
-
-      handleActionMessage(messageNotCompleted);
-      expect(capturedNotCompletedMessage).toContain("I believe that the task was **not completed**");
-      
-      // Test completed successfully
-      const messageCompleted: ActionMessage = {
-        id: 3,
-        action: ActionType.FINISH,
-        source: "agent",
-        message: "",
-        timestamp: new Date().toISOString(),
-        args: {
-          final_thought: "",
-          task_completed: "true",
-          outputs: "",
-          thought: ""
-        }
-      };
-
-      // Mock implementation to capture the message
-      let capturedCompletedMessage = "";
-      (store.dispatch as any).mockImplementation((action: any) => {
-        if (action.type === "chat/addAssistantMessage" && 
-            action.payload.includes("believe that the task was **completed successfully**")) {
-          capturedCompletedMessage = action.payload;
-        }
-      });
-
-      handleActionMessage(messageCompleted);
-      expect(capturedCompletedMessage).toContain("I believe that the task was **completed successfully**");
-    });
-  });
 });

frontend/__tests__/utils/error-handler.test.ts

@@ -1,12 +1,8 @@
 import { describe, it, expect, vi, beforeEach, afterEach } from "vitest";
+import { trackError, showErrorToast, showChatError } from "#/utils/error-handler";
 import posthog from "posthog-js";
-import {
-  trackError,
-  showErrorToast,
-  showChatError,
-} from "#/utils/error-handler";
+import toast from "react-hot-toast";
 import * as Actions from "#/services/actions";
-import * as CustomToast from "#/utils/custom-toast-handlers";
 
 vi.mock("posthog-js", () => ({
   default: {
@@ -14,6 +10,12 @@ vi.mock("posthog-js", () => ({
   },
 }));
 
+vi.mock("react-hot-toast", () => ({
+  default: {
+    error: vi.fn(),
+  },
+}));
+
 vi.mock("#/services/actions", () => ({
   handleStatusMessage: vi.fn(),
 }));
@@ -36,12 +38,9 @@ describe("Error Handler", () => {
 
       trackError(error);
 
-      expect(posthog.captureException).toHaveBeenCalledWith(
-        new Error("Test error"),
-        {
-          error_source: "test",
-        },
-      );
+      expect(posthog.captureException).toHaveBeenCalledWith(new Error("Test error"), {
+        error_source: "test",
+      });
     });
 
     it("should include additional metadata in PostHog event", () => {
@@ -56,19 +55,15 @@ describe("Error Handler", () => {
 
       trackError(error);
 
-      expect(posthog.captureException).toHaveBeenCalledWith(
-        new Error("Test error"),
-        {
-          error_source: "test",
-          extra: "info",
-          details: { foo: "bar" },
-        },
-      );
+      expect(posthog.captureException).toHaveBeenCalledWith(new Error("Test error"), {
+        error_source: "test",
+        extra: "info",
+        details: { foo: "bar" },
+      });
     });
   });
 
   describe("showErrorToast", () => {
-    const errorToastSpy = vi.spyOn(CustomToast, "displayErrorToast");
     it("should log error and show toast", () => {
       const error = {
         message: "Toast error",
@@ -78,15 +73,12 @@ describe("Error Handler", () => {
       showErrorToast(error);
 
       // Verify PostHog logging
-      expect(posthog.captureException).toHaveBeenCalledWith(
-        new Error("Toast error"),
-        {
-          error_source: "toast-test",
-        },
-      );
+      expect(posthog.captureException).toHaveBeenCalledWith(new Error("Toast error"), {
+        error_source: "toast-test",
+      });
 
       // Verify toast was shown
-      expect(errorToastSpy).toHaveBeenCalled();
+      expect(toast.error).toHaveBeenCalled();
     });
 
     it("should include metadata in PostHog event when showing toast", () => {
@@ -98,13 +90,10 @@ describe("Error Handler", () => {
 
       showErrorToast(error);
 
-      expect(posthog.captureException).toHaveBeenCalledWith(
-        new Error("Toast error"),
-        {
-          error_source: "toast-test",
-          context: "testing",
-        },
-      );
+      expect(posthog.captureException).toHaveBeenCalledWith(new Error("Toast error"), {
+        error_source: "toast-test",
+        context: "testing",
+      });
     });
 
     it("should log errors from different sources with appropriate metadata", () => {
@@ -115,13 +104,10 @@ describe("Error Handler", () => {
         metadata: { id: "error.agent" },
       });
 
-      expect(posthog.captureException).toHaveBeenCalledWith(
-        new Error("Agent error"),
-        {
-          error_source: "agent-status",
-          id: "error.agent",
-        },
-      );
+      expect(posthog.captureException).toHaveBeenCalledWith(new Error("Agent error"), {
+        error_source: "agent-status",
+        id: "error.agent",
+      });
 
       showErrorToast({
         message: "Server error",
@@ -129,14 +115,11 @@ describe("Error Handler", () => {
         metadata: { error_code: 500, details: "Internal error" },
       });
 
-      expect(posthog.captureException).toHaveBeenCalledWith(
-        new Error("Server error"),
-        {
-          error_source: "server",
-          error_code: 500,
-          details: "Internal error",
-        },
-      );
+      expect(posthog.captureException).toHaveBeenCalledWith(new Error("Server error"), {
+        error_source: "server",
+        error_code: 500,
+        details: "Internal error",
+      });
     });
 
     it("should log feedback submission errors with conversation context", () => {
@@ -147,14 +130,11 @@ describe("Error Handler", () => {
         metadata: { conversationId: "123", error },
       });
 
-      expect(posthog.captureException).toHaveBeenCalledWith(
-        new Error("Feedback submission failed"),
-        {
-          error_source: "feedback",
-          conversationId: "123",
-          error,
-        },
-      );
+      expect(posthog.captureException).toHaveBeenCalledWith(new Error("Feedback submission failed"), {
+        error_source: "feedback",
+        conversationId: "123",
+        error,
+      });
     });
   });
 
@@ -169,12 +149,9 @@ describe("Error Handler", () => {
       showChatError(error);
 
       // Verify PostHog logging
-      expect(posthog.captureException).toHaveBeenCalledWith(
-        new Error("Chat error"),
-        {
-          error_source: "chat-test",
-        },
-      );
+      expect(posthog.captureException).toHaveBeenCalledWith(new Error("Chat error"), {
+        error_source: "chat-test",
+      });
 
       // Verify error message was shown in chat
       expect(Actions.handleStatusMessage).toHaveBeenCalledWith({

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.28.1",
+  "version": "0.28.0",
   "private": true,
   "type": "module",
   "engines": {
@@ -9,43 +9,43 @@
   "dependencies": {
     "@heroui/react": "2.7.4",
     "@monaco-editor/react": "^4.7.0-rc.0",
-    "@react-router/node": "^7.3.0",
-    "@react-router/serve": "^7.3.0",
-    "@react-types/shared": "^3.28.0",
+    "@react-router/node": "^7.2.0",
+    "@react-router/serve": "^7.2.0",
+    "@react-types/shared": "^3.27.0",
     "@reduxjs/toolkit": "^2.6.0",
-    "@stripe/react-stripe-js": "^3.3.0",
-    "@stripe/stripe-js": "^5.10.0",
-    "@tanstack/react-query": "^5.67.2",
+    "@stripe/react-stripe-js": "^3.1.1",
+    "@stripe/stripe-js": "^5.7.0",
+    "@tanstack/react-query": "^5.66.11",
     "@vitejs/plugin-react": "^4.3.2",
     "@xterm/addon-fit": "^0.10.0",
     "@xterm/xterm": "^5.4.0",
-    "axios": "^1.8.2",
+    "axios": "^1.8.1",
     "clsx": "^2.1.1",
     "eslint-config-airbnb-typescript": "^18.0.0",
-    "framer-motion": "^12.4.10",
+    "framer-motion": "^12.4.7",
     "i18next": "^24.2.2",
     "i18next-browser-languagedetector": "^8.0.4",
     "i18next-http-backend": "^3.0.2",
     "isbot": "^5.1.23",
     "jose": "^6.0.8",
     "monaco-editor": "^0.52.2",
-    "posthog-js": "^1.229.3",
+    "posthog-js": "^1.225.1",
     "react": "^19.0.0",
     "react-dom": "^19.0.0",
     "react-highlight": "^0.15.0",
     "react-hot-toast": "^2.5.1",
     "react-i18next": "^15.4.1",
     "react-icons": "^5.5.0",
-    "react-markdown": "^10.1.0",
+    "react-markdown": "^10.0.1",
     "react-redux": "^9.2.0",
-    "react-router": "^7.3.0",
+    "react-router": "^7.2.0",
     "react-syntax-highlighter": "^15.6.1",
     "react-textarea-autosize": "^8.5.7",
     "remark-gfm": "^4.0.1",
     "sirv-cli": "^3.0.1",
     "socket.io-client": "^4.8.1",
     "tailwind-merge": "^3.0.2",
-    "vite": "^6.2.1",
+    "vite": "^6.2.0",
     "web-vitals": "^3.5.2",
     "ws": "^8.18.1"
   },
@@ -80,29 +80,29 @@
   },
   "devDependencies": {
     "@mswjs/socket.io-binding": "^0.1.1",
-    "@playwright/test": "^1.51.0",
-    "@react-router/dev": "^7.3.0",
+    "@playwright/test": "^1.50.1",
+    "@react-router/dev": "^7.2.0",
     "@tailwindcss/typography": "^0.5.16",
-    "@tanstack/eslint-plugin-query": "^5.67.2",
+    "@tanstack/eslint-plugin-query": "^5.66.1",
     "@testing-library/dom": "^10.4.0",
     "@testing-library/jest-dom": "^6.6.1",
     "@testing-library/react": "^16.2.0",
     "@testing-library/user-event": "^14.6.1",
-    "@types/node": "^22.13.9",
+    "@types/node": "^22.13.8",
     "@types/react": "^19.0.8",
     "@types/react-dom": "^19.0.3",
     "@types/react-highlight": "^0.12.8",
     "@types/react-syntax-highlighter": "^15.5.13",
-    "@types/ws": "^8.18.0",
+    "@types/ws": "^8.5.14",
     "@typescript-eslint/eslint-plugin": "^7.18.0",
     "@typescript-eslint/parser": "^7.18.0",
-    "@vitest/coverage-v8": "^3.0.8",
+    "@vitest/coverage-v8": "^3.0.7",
     "autoprefixer": "^10.4.20",
     "cross-env": "^7.0.3",
     "eslint": "^8.57.0",
     "eslint-config-airbnb": "^19.0.4",
     "eslint-config-airbnb-typescript": "^18.0.0",
-    "eslint-config-prettier": "^10.1.1",
+    "eslint-config-prettier": "^10.0.2",
     "eslint-plugin-import": "^2.29.1",
     "eslint-plugin-jsx-a11y": "^6.10.2",
     "eslint-plugin-prettier": "^5.2.3",

frontend/public/mockServiceWorker.js

@@ -8,7 +8,7 @@
  * - Please do NOT serve this file on production.
  */
 
-const PACKAGE_VERSION = '2.7.3'
+const PACKAGE_VERSION = '2.7.0'
 const INTEGRITY_CHECKSUM = '00729d72e3b82faf54ca8b9621dbb96f'
 const IS_MOCKED_RESPONSE = Symbol('isMockedResponse')
 const activeClientIds = new Set()

frontend/src/api/open-hands.ts

@@ -281,13 +281,6 @@ class OpenHands {
     return data.redirect_url;
   }
 
-  static async createBillingSessionResponse(): Promise<string> {
-    const { data } = await openHands.post(
-      "/api/billing/create-customer-setup-session",
-    );
-    return data.redirect_url;
-  }
-
   static async getBalance(): Promise<string> {
     const { data } = await openHands.get<{ credits: string }>(
       "/api/billing/credits",

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

@@ -48,7 +48,6 @@ export interface GetConfigResponse {
   APP_SLUG?: string;
   GITHUB_CLIENT_ID: string;
   POSTHOG_CLIENT_KEY: string;
-  STRIPE_PUBLISHABLE_KEY?: string;
 }
 
 export interface GetVSCodeUrlResponse {

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

@@ -1,4 +1,5 @@
 import { useDispatch, useSelector } from "react-redux";
+import toast from "react-hot-toast";
 import React from "react";
 import posthog from "posthog-js";
 import { useParams } from "react-router";
@@ -22,7 +23,6 @@ import { ScrollToBottomButton } from "#/components/shared/buttons/scroll-to-bott
 import { LoadingSpinner } from "#/components/shared/loading-spinner";
 import { useGetTrajectory } from "#/hooks/mutation/use-get-trajectory";
 import { downloadTrajectory } from "#/utils/download-files";
-import { displayErrorToast } from "#/utils/custom-toast-handlers";
 
 function getEntryPoint(
   hasRepository: boolean | null,
@@ -98,7 +98,7 @@ export function ChatInterface() {
 
   const onClickExportTrajectoryButton = () => {
     if (!params.conversationId) {
-      displayErrorToast("ConversationId unknown, cannot download trajectory");
+      toast.error("ConversationId unknown, cannot download trajectory");
       return;
     }
 
@@ -110,7 +110,7 @@ export function ChatInterface() {
         );
       },
       onError: (error) => {
-        displayErrorToast(error.message);
+        toast.error(error.message);
       },
     });
   };

frontend/src/components/features/payment/setup-payment-modal.tsx

@@ -1,48 +0,0 @@
-import { useMutation } from "@tanstack/react-query";
-import { Trans, useTranslation } from "react-i18next";
-import AllHandsLogo from "#/assets/branding/all-hands-logo.svg?react";
-import { ModalBackdrop } from "#/components/shared/modals/modal-backdrop";
-import { ModalBody } from "#/components/shared/modals/modal-body";
-import OpenHands from "#/api/open-hands";
-import { BrandButton } from "../settings/brand-button";
-import { displayErrorToast } from "#/utils/custom-toast-handlers";
-
-export function SetupPaymentModal() {
-  const { t } = useTranslation();
-  const { mutate, isPending } = useMutation({
-    mutationFn: OpenHands.createBillingSessionResponse,
-    onSuccess: (data) => {
-      window.location.href = data;
-    },
-    onError: () => {
-      displayErrorToast(t("BILLING$ERROR_WHILE_CREATING_SESSION"));
-    },
-  });
-
-  return (
-    <ModalBackdrop>
-      <ModalBody className="border border-tertiary">
-        <AllHandsLogo width={68} height={46} />
-        <div className="flex flex-col gap-2 w-full items-center text-center">
-          <h1 className="text-2xl font-bold">{t("BILLING$YOUVE_GOT_50")}</h1>
-          <p>
-            <Trans
-              i18nKey="BILLING$CLAIM_YOUR_50"
-              components={{ b: <strong /> }}
-            />
-          </p>
-        </div>
-        <BrandButton
-          testId="proceed-to-stripe-button"
-          type="submit"
-          variant="primary"
-          className="w-full"
-          isDisabled={isPending}
-          onClick={mutate}
-        >
-          {t("BILLING$PROCEED_TO_STRIPE")}
-        </BrandButton>
-      </ModalBody>
-    </ModalBackdrop>
-  );
-}

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

@@ -2,6 +2,7 @@ import React from "react";
 import { FaListUl } from "react-icons/fa";
 import { useDispatch } from "react-redux";
 import posthog from "posthog-js";
+import toast from "react-hot-toast";
 import { NavLink, useLocation } from "react-router";
 import { useGitHubUser } from "#/hooks/query/use-github-user";
 import { UserActions } from "./user-actions";
@@ -9,6 +10,7 @@ import { AllHandsLogoButton } from "#/components/shared/buttons/all-hands-logo-b
 import { DocsButton } from "#/components/shared/buttons/docs-button";
 import { ExitProjectButton } from "#/components/shared/buttons/exit-project-button";
 import { SettingsButton } from "#/components/shared/buttons/settings-button";
+import { LoadingSpinner } from "#/components/shared/loading-spinner";
 import { SettingsModal } from "#/components/shared/modals/settings/settings-modal";
 import { useCurrentSettings } from "#/context/settings-context";
 import { useSettings } from "#/hooks/query/use-settings";
@@ -21,8 +23,6 @@ import { ConversationPanelWrapper } from "../conversation-panel/conversation-pan
 import { useLogout } from "#/hooks/mutation/use-logout";
 import { useConfig } from "#/hooks/query/use-config";
 import { cn } from "#/utils/utils";
-import { displayErrorToast } from "#/utils/custom-toast-handlers";
-import { HIDE_LLM_SETTINGS } from "#/utils/feature-flags";
 
 export function Sidebar() {
   const location = useLocation();
@@ -43,12 +43,7 @@ export function Sidebar() {
   const [conversationPanelIsOpen, setConversationPanelIsOpen] =
     React.useState(false);
 
-  // TODO: Remove HIDE_LLM_SETTINGS check once released
-  const isSaas = HIDE_LLM_SETTINGS() && config?.APP_MODE === "saas";
-
   React.useEffect(() => {
-    if (isSaas) return;
-
     if (location.pathname === "/settings") {
       setSettingsModalIsOpen(false);
     } else if (
@@ -58,10 +53,10 @@ export function Sidebar() {
     ) {
       // We don't show toast errors for settings in the global error handler
       // because we have a special case for 404 errors
-      displayErrorToast(
+      toast.error(
         "Something went wrong while fetching settings. Please reload the page.",
       );
-    } else if (config?.APP_MODE === "oss" && settingsError?.status === 404) {
+    } else if (settingsError?.status === 404) {
       setSettingsModalIsOpen(true);
     }
   }, [
@@ -116,13 +111,15 @@ export function Sidebar() {
             >
               <SettingsButton />
             </NavLink>
-            <UserActions
-              user={
-                user.data ? { avatar_url: user.data.avatar_url } : undefined
-              }
-              onLogout={handleLogout}
-              isLoading={user.isFetching}
-            />
+            {!user.isLoading && (
+              <UserActions
+                user={
+                  user.data ? { avatar_url: user.data.avatar_url } : undefined
+                }
+                onLogout={handleLogout}
+              />
+            )}
+            {user.isLoading && <LoadingSpinner size="small" />}
           </div>
         </nav>
 

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

@@ -5,10 +5,9 @@ import { AccountSettingsContextMenu } from "../context-menu/account-settings-con
 interface UserActionsProps {
   onLogout: () => void;
   user?: { avatar_url: string };
-  isLoading?: boolean;
 }
 
-export function UserActions({ onLogout, user, isLoading }: UserActionsProps) {
+export function UserActions({ onLogout, user }: UserActionsProps) {
   const [accountContextMenuIsVisible, setAccountContextMenuIsVisible] =
     React.useState(false);
 
@@ -27,11 +26,7 @@ export function UserActions({ onLogout, user, isLoading }: UserActionsProps) {
 
   return (
     <div data-testid="user-actions" className="w-8 h-8 relative">
-      <UserAvatar
-        avatarUrl={user?.avatar_url}
-        onClick={toggleAccountMenu}
-        isLoading={isLoading}
-      />
+      <UserAvatar avatarUrl={user?.avatar_url} onClick={toggleAccountMenu} />
 
       {accountContextMenuIsVisible && (
         <AccountSettingsContextMenu

frontend/src/context/settings-context.tsx

@@ -1,10 +1,10 @@
 import React from "react";
 import { MutateOptions } from "@tanstack/react-query";
+import toast from "react-hot-toast";
 import { useSettings } from "#/hooks/query/use-settings";
 import { useSaveSettings } from "#/hooks/mutation/use-save-settings";
 import { PostSettings, Settings } from "#/types/settings";
 import { retrieveAxiosErrorMessage } from "#/utils/retrieve-axios-error-message";
-import { displayErrorToast } from "#/utils/custom-toast-handlers";
 
 type SaveUserSettingsConfig = {
   onSuccess: MutateOptions<void, Error, Partial<PostSettings>>["onSuccess"];
@@ -47,7 +47,7 @@ export function SettingsProvider({ children }: SettingsProviderProps) {
       onSuccess: config?.onSuccess,
       onError: (error) => {
         const errorMessage = retrieveAxiosErrorMessage(error);
-        displayErrorToast(errorMessage);
+        toast.error(errorMessage);
       },
     });
   };

frontend/src/hooks/mutation/use-save-settings.ts

@@ -17,7 +17,7 @@ const saveSettingsMutationFn = async (settings: Partial<PostSettings>) => {
       ? ""
       : settings.LLM_API_KEY?.trim() || undefined,
     remote_runtime_resource_factor: settings.REMOTE_RUNTIME_RESOURCE_FACTOR,
-    provider_tokens: settings.provider_tokens,
+    github_token: settings.github_token,
     unset_github_token: settings.unset_github_token,
     enable_default_condenser: settings.ENABLE_DEFAULT_CONDENSER,
     enable_sound_notifications: settings.ENABLE_SOUND_NOTIFICATIONS,

frontend/src/hooks/mutation/use-submit-feedback.ts

@@ -1,8 +1,8 @@
 import { useMutation } from "@tanstack/react-query";
+import toast from "react-hot-toast";
 import { Feedback } from "#/api/open-hands.types";
 import OpenHands from "#/api/open-hands";
 import { useConversation } from "#/context/conversation-context";
-import { displayErrorToast } from "#/utils/custom-toast-handlers";
 
 type SubmitFeedbackArgs = {
   feedback: Feedback;
@@ -14,7 +14,7 @@ export const useSubmitFeedback = () => {
     mutationFn: ({ feedback }: SubmitFeedbackArgs) =>
       OpenHands.submitFeedback(conversationId, feedback),
     onError: (error) => {
-      displayErrorToast(error.message);
+      toast.error(error.message);
     },
   });
 };

frontend/src/hooks/query/use-ai-config-options.ts

@@ -11,6 +11,4 @@ export const useAIConfigOptions = () =>
   useQuery({
     queryKey: ["ai-config-options"],
     queryFn: fetchAiConfigOptions,
-    staleTime: 1000 * 60 * 5, // 5 minutes
-    gcTime: 1000 * 60 * 15, // 15 minutes
   });

frontend/src/hooks/query/use-app-installations.ts

@@ -14,7 +14,5 @@ export const useAppInstallations = () => {
       githubTokenIsSet &&
       !!config?.GITHUB_CLIENT_ID &&
       config?.APP_MODE === "saas",
-    staleTime: 1000 * 60 * 5, // 5 minutes
-    gcTime: 1000 * 60 * 15, // 15 minutes
   });
 };

frontend/src/hooks/query/use-app-repositories.ts

@@ -50,8 +50,6 @@ export const useAppRepositories = () => {
       Array.isArray(installations) &&
       installations.length > 0 &&
       config?.APP_MODE === "saas",
-    staleTime: 1000 * 60 * 5, // 5 minutes
-    gcTime: 1000 * 60 * 15, // 15 minutes
   });
 
   // TODO: Once we create our custom dropdown component, we should fetch data onEndReached

frontend/src/hooks/query/use-balance.ts

@@ -1,7 +1,6 @@
 import { useQuery } from "@tanstack/react-query";
 import { useConfig } from "./use-config";
 import OpenHands from "#/api/open-hands";
-import { BILLING_SETTINGS } from "#/utils/feature-flags";
 
 export const useBalance = () => {
   const { data: config } = useConfig();
@@ -9,6 +8,6 @@ export const useBalance = () => {
   return useQuery({
     queryKey: ["user", "balance"],
     queryFn: OpenHands.getBalance,
-    enabled: config?.APP_MODE === "saas" && BILLING_SETTINGS(),
+    enabled: config?.APP_MODE === "saas",
   });
 };

frontend/src/hooks/query/use-config.ts

@@ -5,6 +5,4 @@ export const useConfig = () =>
   useQuery({
     queryKey: ["config"],
     queryFn: OpenHands.getConfig,
-    staleTime: 1000 * 60 * 5, // 5 minutes
-    gcTime: 1000 * 60 * 15, // 15 minutes
   });

frontend/src/hooks/query/use-conversation-config.ts

@@ -18,8 +18,6 @@ export const useConversationConfig = () => {
       return OpenHands.getRuntimeId(conversationId);
     },
     enabled: status !== WsClientProviderStatus.DISCONNECTED && !!conversationId,
-    staleTime: 1000 * 60 * 5, // 5 minutes
-    gcTime: 1000 * 60 * 15, // 15 minutes
   });
 
   React.useEffect(() => {

frontend/src/hooks/query/use-github-user.ts

@@ -19,8 +19,6 @@ export const useGitHubUser = () => {
     queryFn: OpenHands.getGitHubUser,
     enabled: githubTokenIsSet && !!config?.APP_MODE,
     retry: false,
-    staleTime: 1000 * 60 * 5, // 5 minutes
-    gcTime: 1000 * 60 * 15, // 15 minutes
   });
 
   React.useEffect(() => {

frontend/src/hooks/query/use-is-authed.ts

@@ -15,7 +15,6 @@ export const useIsAuthed = () => {
     queryFn: () => OpenHands.authenticate(appMode!),
     enabled: !!appMode,
     staleTime: 1000 * 60 * 5, // 5 minutes
-    gcTime: 1000 * 60 * 15, // 15 minutes
     retry: false,
     meta: {
       disableToast: true,

frontend/src/hooks/query/use-list-files.ts

@@ -23,7 +23,5 @@ export const useListFiles = (config: UseListFilesConfig = DEFAULT_CONFIG) => {
     queryKey: ["files", conversationId, config?.path],
     queryFn: () => OpenHands.getFiles(conversationId, config?.path),
     enabled: !!(isActive && config?.enabled),
-    staleTime: 1000 * 60 * 5, // 5 minutes
-    gcTime: 1000 * 60 * 15, // 15 minutes
   });
 };

frontend/src/hooks/query/use-search-repositories.ts

@@ -7,7 +7,5 @@ export function useSearchRepositories(query: string) {
     queryFn: () => OpenHands.searchGitHubRepositories(query, 3),
     enabled: !!query,
     select: (data) => data.map((repo) => ({ ...repo, is_public: true })),
-    staleTime: 1000 * 60 * 5, // 5 minutes
-    gcTime: 1000 * 60 * 15, // 15 minutes
   });
 }

frontend/src/hooks/query/use-settings.ts

@@ -21,8 +21,6 @@ const getSettingsQueryFn = async () => {
     ENABLE_DEFAULT_CONDENSER: apiSettings.enable_default_condenser,
     ENABLE_SOUND_NOTIFICATIONS: apiSettings.enable_sound_notifications,
     USER_CONSENTS_TO_ANALYTICS: apiSettings.user_consents_to_analytics,
-    PROVIDER_TOKENS: apiSettings.provider_tokens,
-    IS_NEW_USER: false,
   };
 };
 
@@ -36,8 +34,6 @@ export const useSettings = () => {
     // would want to show the modal immediately if the
     // settings are not found
     retry: (_, error) => error.status !== 404,
-    staleTime: 1000 * 60 * 5, // 5 minutes
-    gcTime: 1000 * 60 * 15, // 15 minutes
     meta: {
       disableToast: true,
     },

frontend/src/hooks/query/use-user-conversation.ts

@@ -7,6 +7,4 @@ export const useUserConversation = (cid: string | null) =>
     queryFn: () => OpenHands.getConversation(cid!),
     enabled: !!cid,
     retry: false,
-    staleTime: 1000 * 60 * 5, // 5 minutes
-    gcTime: 1000 * 60 * 15, // 15 minutes
   });

frontend/src/hooks/query/use-user-conversations.ts

@@ -9,5 +9,6 @@ export const useUserConversations = () => {
     queryKey: ["user", "conversations"],
     queryFn: OpenHands.getUserConversations,
     enabled: !!userIsAuthenticated,
+    staleTime: 0,
   });
 };

frontend/src/hooks/query/use-user-repositories.ts

@@ -15,8 +15,6 @@ export const useUserRepositories = () => {
     initialPageParam: 1,
     getNextPageParam: (lastPage) => lastPage.nextPage,
     enabled: githubTokenIsSet && config?.APP_MODE === "oss",
-    staleTime: 1000 * 60 * 5, // 5 minutes
-    gcTime: 1000 * 60 * 15, // 15 minutes
   });
 
   // TODO: Once we create our custom dropdown component, we should fetch data onEndReached

frontend/src/hooks/query/use-vscode-url.ts

@@ -13,8 +13,6 @@ export const useVSCodeUrl = (config: { enabled: boolean }) => {
     },
     enabled: !!conversationId && config.enabled,
     refetchOnMount: false,
-    staleTime: 1000 * 60 * 5, // 5 minutes
-    gcTime: 1000 * 60 * 15, // 15 minutes
   });
 
   return data;

frontend/src/i18n/declaration.ts

@@ -312,9 +312,4 @@ export enum I18nKey {
   BUTTON$MARK_NOT_HELPFUL = "BUTTON$MARK_NOT_HELPFUL",
   BUTTON$EXPORT_CONVERSATION = "BUTTON$EXPORT_CONVERSATION",
   BILLING$CLICK_TO_TOP_UP = "BILLING$CLICK_TO_TOP_UP",
-  BILLING$YOUVE_GOT_50 = "BILLING$YOUVE_GOT_50",
-  BILLING$ERROR_WHILE_CREATING_SESSION = "BILLING$ERROR_WHILE_CREATING_SESSION",
-  BILLING$CLAIM_YOUR_50 = "BILLING$CLAIM_YOUR_50",
-  BILLING$PROCEED_TO_STRIPE = "BILLING$PROCEED_TO_STRIPE",
-  BILLING$YOURE_IN = "BILLING$YOURE_IN",
 }

frontend/src/i18n/translation.json

@@ -4647,80 +4647,5 @@
         "fr": "Ajouter des fonds à votre compte",
         "tr": "Hesabınıza bakiye ekleyin",
         "de": "Guthaben zu Ihrem Konto hinzufügen"
-    },
-    "BILLING$YOUVE_GOT_50": {
-        "en": "You've got $50 in free OpenHands credits",
-        "ja": "OpenHandsの無料クレジット$50を獲得しました",
-        "zh-CN": "您获得了 $50 的 OpenHands 免费额度",
-        "zh-TW": "您獲得了 $50 的 OpenHands 免費額度",
-        "ko-KR": "OpenHands 무료 크레딧 $50를 받았습니다",
-        "no": "Du har fått $50 i gratis OpenHands-kreditter",
-        "it": "Hai ottenuto $50 in crediti gratuiti OpenHands",
-        "pt": "Você ganhou $50 em créditos gratuitos OpenHands",
-        "es": "Has recibido $50 en créditos gratuitos de OpenHands",
-        "ar": "لديك 50$ من رصيد OpenHands المجاني",
-        "fr": "Vous avez reçu $50 de crédits OpenHands gratuits",
-        "tr": "OpenHands'de $50 ücretsiz kredi kazandınız",
-        "de": "Sie haben $50 in kostenlosen OpenHands-Guthaben erhalten"
-    },
-    "BILLING$ERROR_WHILE_CREATING_SESSION": {
-        "en": "Error occurred while setting up your payment session. Please try again later.",
-        "ja": "お支払いセッションの設定中にエラーが発生しました。後ほど再度お試しください。",
-        "zh-CN": "设置支付会话时发生错误。请稍后再试。",
-        "zh-TW": "設置支付會話時發生錯誤。請稍後再試。",
-        "ko-KR": "결제 세션 설정 중 오류가 발생했습니다. 나중에 다시 시도해 주세요.",
-        "no": "Det oppstod en feil under oppsett av betalingsøkten. Vennligst prøv igjen senere.",
-        "it": "Si è verificato un errore durante la configurazione della sessione di pagamento. Si prega di riprovare più tardi.",
-        "pt": "Ocorreu um erro ao configurar sua sessão de pagamento. Por favor, tente novamente mais tarde.",
-        "es": "Se produjo un error al configurar tu sesión de pago. Por favor, inténtalo de nuevo más tarde.",
-        "ar": "حدث خطأ أثناء إعداد جلسة الدفع الخاصة بك. يرجى المحاولة مرة أخرى لاحقًا.",
-        "fr": "Une erreur s'est produite lors de la configuration de votre session de paiement. Veuillez réessayer plus tard.",
-        "tr": "Ödeme oturumunuz kurulurken bir hata oluştu. Lütfen daha sonra tekrar deneyin.",
-        "de": "Beim Einrichten Ihrer Zahlungssitzung ist ein Fehler aufgetreten. Bitte versuchen Sie es später erneut."
-    },
-    "BILLING$CLAIM_YOUR_50": {
-        "en": "Add a credit card with Stripe to claim your $50. <b>We won't charge you without asking first!</b>",
-        "ja": "Stripeでクレジットカードを追加して$50を獲得。<b>事前の確認なしで請求することはありません！</b>",
-        "zh-CN": "添加 Stripe 信用卡以领取 $50。<b>我们不会在未经您同意的情况下收费！</b>",
-        "zh-TW": "添加 Stripe 信用卡以領取 $50。<b>我們不會在未經您同意的情況下收費！</b>",
-        "ko-KR": "Stripe에 신용카드를 추가하여 $50를 받으세요. <b>사전 동의 없이 요금이 청구되지 않습니다!</b>",
-        "no": "Legg til et kredittkort med Stripe for å få $50. <b>Vi belaster deg ikke uten å spørre først!</b>",
-        "it": "Aggiungi una carta di credito con Stripe per ottenere $50. <b>Non ti addebiteremo nulla senza chiedere prima!</b>",
-        "pt": "Adicione um cartão de crédito com Stripe para receber $50. <b>Não cobraremos sem perguntar primeiro!</b>",
-        "es": "Añade una tarjeta de crédito con Stripe para reclamar tus $50. <b>¡No te cobraremos sin preguntarte primero!</b>",
-        "ar": "أضف بطاقة ائتمان مع Stripe للحصول على 50$. <b>لن نقوم بالخصم دون إذن مسبق!</b>",
-        "fr": "Ajoutez une carte de crédit avec Stripe pour obtenir 50$. <b>Nous ne vous facturerons pas sans vous demander d'abord !</b>",
-        "tr": "50$ almak için Stripe ile kredi kartı ekleyin. <b>Önce sormadan ücret almayacağız!</b>",
-        "de": "Fügen Sie eine Kreditkarte mit Stripe hinzu, um $50 zu erhalten. <b>Wir belasten Sie nicht ohne vorherige Zustimmung!</b>"
-    },
-    "BILLING$PROCEED_TO_STRIPE": {
-        "en": "Add Billing Info",
-        "ja": "請求情報を追加",
-        "zh-CN": "添加账单信息",
-        "zh-TW": "添加帳單資訊",
-        "ko-KR": "결제 정보 추가",
-        "no": "Legg til betalingsinformasjon",
-        "it": "Aggiungi informazioni di fatturazione",
-        "pt": "Adicionar informações de pagamento",
-        "es": "Añadir información de facturación",
-        "ar": "إضافة معلومات الفواتير",
-        "fr": "Ajouter les informations de facturation",
-        "tr": "Fatura Bilgisi Ekle",
-        "de": "Zahlungsinformationen hinzufügen"
-    },
-    "BILLING$YOURE_IN": {
-        "en": "You're in! You can start using your $50 in free credits now.",
-        "ja": "登録完了！$50分の無料クレジットを今すぐご利用いただけます。",
-        "zh-CN": "您已加入！现在可以开始使用$50的免费额度了。",
-        "zh-TW": "您已加入！現在可以開始使用$50的免費額度了。",
-        "ko-KR": "가입 완료! 지금 바로 $50 상당의 무료 크레딧을 사용하실 수 있습니다.",
-        "no": "Du er med! Du kan begynne å bruke dine $50 i gratis kreditter nå.",
-        "it": "Ci sei! Puoi iniziare a utilizzare i tuoi $50 in crediti gratuiti ora.",
-        "pt": "Você está dentro! Você pode começar a usar seus $50 em créditos gratuitos agora.",
-        "es": "¡Ya estás dentro! Puedes empezar a usar tus $50 en créditos gratuitos ahora.",
-        "ar": "أنت معنا! يمكنك البدء في استخدام رصيدك المجاني البالغ 50 دولارًا الآن.",
-        "fr": "C'est fait ! Vous pouvez commencer à utiliser vos 50 $ de crédits gratuits maintenant.",
-        "tr": "Başardın! Şimdi $50 değerindeki ücretsiz kredilerini kullanmaya başlayabilirsin.",
-        "de": "Du bist dabei! Du kannst jetzt deine $50 an kostenlosen Guthaben nutzen."
     }
 }

frontend/src/icons/close.svg

@@ -1,3 +1,5 @@
-<svg width="25" height="24" viewBox="0 0 25 24" fill="none" xmlns="http://www.w3.org/2000/svg">
-<path d="M12.5 13.0602L16.2123 16.7725L17.273 15.7118L13.5607 11.9995L17.273 8.28723L16.2123 7.22657L12.5 10.9389L8.78771 7.22656L7.72705 8.28722L11.4394 11.9995L7.72706 15.7119L8.78772 16.7725L12.5 13.0602Z" fill="white"/>
+<svg width="11" height="11" viewBox="0 0 11 11" fill="none" xmlns="http://www.w3.org/2000/svg">
+  <path fill-rule="evenodd" clip-rule="evenodd"
+    d="M5.69949 5.72974L7.91965 7.9505L8.35077 7.51999L6.13001 5.29922L8.35077 3.07907L7.92026 2.64795L5.69949 4.86871L3.47934 2.64795L3.04883 3.07907L5.26898 5.29922L3.04883 7.51938L3.47934 7.9505L5.69949 5.72974Z"
+    fill="black" />
 </svg>

frontend/src/mocks/billing-handlers.ts

@@ -1,4 +1,8 @@
 import { delay, http, HttpResponse } from "msw";
+import Stripe from "stripe";
+
+const TEST_STRIPE_SECRET_KEY = "";
+const PRICE_ID = "";
 
 export const STRIPE_BILLING_HANDLERS = [
   http.get("/api/billing/credits", async () => {
@@ -6,17 +10,27 @@ export const STRIPE_BILLING_HANDLERS = [
     return HttpResponse.json({ credits: "100" });
   }),
 
-  http.post("/api/billing/create-checkout-session", async () => {
+  http.post("/api/billing/create-checkout-session", async ({ request }) => {
     await delay();
-    return HttpResponse.json({
-      redirect_url: "https://stripe.com/some-checkout",
-    });
-  }),
+    const body = await request.json();
 
-  http.post("/api/billing/create-customer-setup-session", async () => {
-    await delay();
-    return HttpResponse.json({
-      redirect_url: "https://stripe.com/some-customer-setup",
-    });
+    if (body && typeof body === "object" && body.amount) {
+      const stripe = new Stripe(TEST_STRIPE_SECRET_KEY);
+      const session = await stripe.checkout.sessions.create({
+        line_items: [
+          {
+            price: PRICE_ID,
+            quantity: body.amount,
+          },
+        ],
+        mode: "payment",
+        success_url: "http://localhost:3001/settings/billing/?checkout=success",
+        cancel_url: "http://localhost:3001/settings/billing/?checkout=cancel",
+      });
+
+      if (session.url) return HttpResponse.json({ redirect_url: session.url });
+    }
+
+    return HttpResponse.json({ message: "Invalid request" }, { status: 400 });
   }),
 ];

frontend/src/mocks/handlers.ts

@@ -22,13 +22,12 @@ export const MOCK_DEFAULT_USER_SETTINGS: ApiSettings | PostApiSettings = {
   enable_default_condenser: DEFAULT_SETTINGS.ENABLE_DEFAULT_CONDENSER,
   enable_sound_notifications: DEFAULT_SETTINGS.ENABLE_SOUND_NOTIFICATIONS,
   user_consents_to_analytics: DEFAULT_SETTINGS.USER_CONSENTS_TO_ANALYTICS,
-  provider_tokens: DEFAULT_SETTINGS.PROVIDER_TOKENS,
 };
 
 const MOCK_USER_PREFERENCES: {
-  settings: ApiSettings | PostApiSettings | null;
+  settings: ApiSettings | PostApiSettings;
 } = {
-  settings: null,
+  settings: MOCK_DEFAULT_USER_SETTINGS,
 };
 
 const conversations: Conversation[] = [
@@ -175,24 +174,22 @@ export const handlers = [
   ),
   http.get("/api/options/config", () => {
     const mockSaas = import.meta.env.VITE_MOCK_SAAS === "true";
-
     const config: GetConfigResponse = {
       APP_MODE: mockSaas ? "saas" : "oss",
       GITHUB_CLIENT_ID: "fake-github-client-id",
       POSTHOG_CLIENT_KEY: "fake-posthog-client-key",
-      STRIPE_PUBLISHABLE_KEY: "",
     };
 
     return HttpResponse.json(config);
   }),
   http.get("/api/settings", async () => {
     await delay();
-    const { settings } = MOCK_USER_PREFERENCES;
-
-    if (!settings) return HttpResponse.json(null, { status: 404 });
-
-    if (Object.keys(settings.provider_tokens).length > 0)
-      settings.github_token_is_set = true;
+    const settings: ApiSettings = {
+      ...MOCK_USER_PREFERENCES.settings,
+      language: "no",
+    };
+    // @ts-expect-error - mock types
+    if (settings.github_token) settings.github_token_is_set = true;
 
     return HttpResponse.json(settings);
   }),
@@ -204,19 +201,17 @@ export const handlers = [
       if (typeof body === "object") {
         newSettings = { ...body };
         if (newSettings.unset_github_token) {
-          newSettings.provider_tokens = { github: "", gitlab: "" };
+          newSettings.github_token = undefined;
           newSettings.github_token_is_set = false;
           delete newSettings.unset_github_token;
         }
       }
 
-      const fullSettings = {
-        ...MOCK_DEFAULT_USER_SETTINGS,
+      MOCK_USER_PREFERENCES.settings = {
         ...MOCK_USER_PREFERENCES.settings,
         ...newSettings,
       };
 
-      MOCK_USER_PREFERENCES.settings = fullSettings;
       return HttpResponse.json(null, { status: 200 });
     }
 

frontend/src/query-client-config.ts

@@ -3,8 +3,8 @@ import {
   QueryCache,
   MutationCache,
 } from "@tanstack/react-query";
+import toast from "react-hot-toast";
 import { retrieveAxiosErrorMessage } from "./utils/retrieve-axios-error-message";
-import { displayErrorToast } from "./utils/custom-toast-handlers";
 
 const shownErrors = new Set<string>();
 export const queryClientConfig: QueryClientConfig = {
@@ -14,7 +14,7 @@ export const queryClientConfig: QueryClientConfig = {
         const errorMessage = retrieveAxiosErrorMessage(error);
 
         if (!shownErrors.has(errorMessage)) {
-          displayErrorToast(errorMessage || "An error occurred");
+          toast.error(errorMessage || "An error occurred");
           shownErrors.add(errorMessage);
 
           setTimeout(() => {
@@ -28,8 +28,14 @@ export const queryClientConfig: QueryClientConfig = {
     onError: (error, _, __, mutation) => {
       if (!mutation?.meta?.disableToast) {
         const message = retrieveAxiosErrorMessage(error);
-        displayErrorToast(message);
+        toast.error(message);
       }
     },
   }),
+  defaultOptions: {
+    queries: {
+      staleTime: 1000 * 60 * 5, // 5 minutes
+      gcTime: 1000 * 60 * 15, // 15 minutes
+    },
+  },
 };

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

@@ -24,10 +24,7 @@ function Home() {
   });
 
   return (
-    <div
-      data-testid="home-screen"
-      className="bg-base-secondary h-full rounded-xl flex flex-col items-center justify-center relative overflow-y-auto px-2"
-    >
+    <div className="bg-base-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

@@ -1,4 +1,5 @@
 import React from "react";
+import toast from "react-hot-toast";
 import { useDispatch, useSelector } from "react-redux";
 import { setImportedProjectZip } from "#/state/initial-query-slice";
 import { RootState } from "#/store";
@@ -6,7 +7,6 @@ import { base64ToBlob } from "#/utils/base64-to-blob";
 import { useUploadFiles } from "../../../hooks/mutation/use-upload-files";
 
 import { RUNTIME_INACTIVE_STATES } from "#/types/agent-state";
-import { displayErrorToast } from "#/utils/custom-toast-handlers";
 
 export const useHandleRuntimeActive = () => {
   const dispatch = useDispatch();
@@ -29,7 +29,7 @@ export const useHandleRuntimeActive = () => {
       { files: [file] },
       {
         onError: () => {
-          displayErrorToast("Failed to upload project files.");
+          toast.error("Failed to upload project files.");
         },
       },
     );

frontend/src/routes/_oh.app/hooks/use-handle-ws-events.ts

@@ -1,4 +1,5 @@
 import React from "react";
+import toast from "react-hot-toast";
 import { useDispatch } from "react-redux";
 import { useWsClient } from "#/context/ws-client-provider";
 import { generateAgentStateChangeEvent } from "#/services/agent-state-service";
@@ -6,7 +7,6 @@ import { addErrorMessage } from "#/state/chat-slice";
 import { AgentState } from "#/types/agent-state";
 import { ErrorObservation } from "#/types/core/observations";
 import { useEndSession } from "../../../hooks/use-end-session";
-import { displayErrorToast } from "#/utils/custom-toast-handlers";
 
 interface ServerError {
   error: boolean | string;
@@ -32,15 +32,15 @@ export const useHandleWSEvents = () => {
 
     if (isServerError(event)) {
       if (event.error_code === 401) {
-        displayErrorToast("Session expired.");
+        toast.error("Session expired.");
         endSession();
         return;
       }
 
       if (typeof event.error === "string") {
-        displayErrorToast(event.error);
+        toast.error(event.error);
       } else {
-        displayErrorToast(event.message);
+        toast.error(event.message);
       }
       return;
     }

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

@@ -3,6 +3,7 @@ import React from "react";
 import { Outlet } from "react-router";
 import { useDispatch, useSelector } from "react-redux";
 import { FaServer } from "react-icons/fa";
+import toast from "react-hot-toast";
 import { useTranslation } from "react-i18next";
 import { I18nKey } from "#/i18n/declaration";
 import {
@@ -35,7 +36,6 @@ import { TerminalStatusLabel } from "#/components/features/terminal/terminal-sta
 import { useSettings } from "#/hooks/query/use-settings";
 import { clearFiles, clearInitialPrompt } from "#/state/initial-query-slice";
 import { RootState } from "#/store";
-import { displayErrorToast } from "#/utils/custom-toast-handlers";
 
 function AppContent() {
   useConversationConfig();
@@ -66,7 +66,7 @@ function AppContent() {
 
   React.useEffect(() => {
     if (isFetched && !conversation) {
-      displayErrorToast(
+      toast.error(
         "This conversation does not exist, or you do not have permission to access it.",
       );
       endSession();

frontend/src/routes/_oh/route.tsx

@@ -1,13 +1,5 @@
 import React from "react";
-import {
-  useRouteError,
-  isRouteErrorResponse,
-  Outlet,
-  useNavigate,
-  useLocation,
-  useSearchParams,
-} from "react-router";
-import { useTranslation } from "react-i18next";
+import { useRouteError, isRouteErrorResponse, Outlet } from "react-router";
 import i18n from "#/i18n";
 import { useGitHubAuthUrl } from "#/hooks/use-github-auth-url";
 import { useIsAuthed } from "#/hooks/query/use-is-authed";
@@ -18,10 +10,6 @@ import { AnalyticsConsentFormModal } from "#/components/features/analytics/analy
 import { useSettings } from "#/hooks/query/use-settings";
 import { useAuth } from "#/context/auth-context";
 import { useMigrateUserConsent } from "#/hooks/use-migrate-user-consent";
-import { useBalance } from "#/hooks/query/use-balance";
-import { SetupPaymentModal } from "#/components/features/payment/setup-payment-modal";
-import { BILLING_SETTINGS } from "#/utils/feature-flags";
-import { displaySuccessToast } from "#/utils/custom-toast-handlers";
 
 export function ErrorBoundary() {
   const error = useRouteError();
@@ -56,14 +44,11 @@ export function ErrorBoundary() {
 }
 
 export default function MainApp() {
-  const navigate = useNavigate();
-  const { pathname } = useLocation();
-  const [searchParams] = useSearchParams();
   const { githubTokenIsSet } = useAuth();
   const { data: settings } = useSettings();
-  const { error, isFetching } = useBalance();
   const { migrateUserConsent } = useMigrateUserConsent();
-  const { t } = useTranslation();
+
+  const [consentFormIsOpen, setConsentFormIsOpen] = React.useState(false);
 
   const config = useConfig();
   const {
@@ -77,8 +62,6 @@ export default function MainApp() {
     gitHubClientId: config.data?.GITHUB_CLIENT_ID || null,
   });
 
-  const [consentFormIsOpen, setConsentFormIsOpen] = React.useState(false);
-
   React.useEffect(() => {
     if (settings?.LANGUAGE) {
       i18n.changeLanguage(settings.LANGUAGE);
@@ -101,17 +84,6 @@ export default function MainApp() {
     });
   }, []);
 
-  React.useEffect(() => {
-    // Don't allow users to use the app if it 402s
-    if (error?.status === 402 && pathname !== "/") {
-      navigate("/");
-    } else if (!isFetching && searchParams.get("free_credits") === "success") {
-      displaySuccessToast(t("BILLING$YOURE_IN"));
-      searchParams.delete("free_credits");
-      navigate("/");
-    }
-  }, [error?.status, pathname, isFetching]);
-
   const userIsAuthed = !!isAuthed && !authError;
   const renderWaitlistModal =
     !isFetchingAuth && !userIsAuthed && config.data?.APP_MODE === "saas";
@@ -144,10 +116,6 @@ export default function MainApp() {
           }}
         />
       )}
-
-      {BILLING_SETTINGS() &&
-        config.data?.APP_MODE === "saas" &&
-        settings?.IS_NEW_USER && <SetupPaymentModal />}
     </div>
   );
 }

frontend/src/routes/account-settings.tsx

@@ -25,8 +25,6 @@ import {
   displayErrorToast,
   displaySuccessToast,
 } from "#/utils/custom-toast-handlers";
-import { PostSettings } from "#/types/settings";
-import { HIDE_LLM_SETTINGS } from "#/utils/feature-flags";
 
 const REMOTE_RUNTIME_OPTIONS = [
   { key: 1, label: "1x (2 core, 8G)" },
@@ -52,25 +50,18 @@ function AccountSettings() {
   const isFetching = isFetchingSettings || isFetchingResources;
   const isSuccess = isSuccessfulSettings && isSuccessfulResources;
 
-  const isSaas = config?.APP_MODE === "saas";
-  const shouldHandleSpecialSaasCase = HIDE_LLM_SETTINGS() && isSaas;
-
   const determineWhetherToToggleAdvancedSettings = () => {
-    if (shouldHandleSpecialSaasCase) return true;
-
     if (isSuccess) {
       return (
         isCustomModel(resources.models, settings.LLM_MODEL) ||
-        hasAdvancedSettingsSet({
-          ...settings,
-          PROVIDER_TOKENS: settings.PROVIDER_TOKENS || {},
-        })
+        hasAdvancedSettingsSet(settings)
       );
     }
 
     return false;
   };
 
+  const isSaas = config?.APP_MODE === "saas";
   const hasAppSlug = !!config?.APP_SLUG;
   const isGitHubTokenSet = settings?.GITHUB_TOKEN_IS_SET;
   const isLLMKeySet = settings?.LLM_API_KEY === "**********";
@@ -115,81 +106,58 @@ function AccountSettings() {
       formData.get("enable-memory-condenser-switch")?.toString() === "on";
     const enableSoundNotifications =
       formData.get("enable-sound-notifications-switch")?.toString() === "on";
-    const llmBaseUrl = formData.get("base-url-input")?.toString() || "";
-    const llmApiKey =
-      formData.get("llm-api-key-input")?.toString() ||
-      (isLLMKeySet
-        ? undefined // don't update if it's already set
-        : ""); // reset if it's first time save to avoid 500 error
 
-    // we don't want the user to be able to modify these settings in SaaS
-    const finalLlmModel = shouldHandleSpecialSaasCase
-      ? undefined
-      : customLlmModel || fullLlmModel;
-    const finalLlmBaseUrl = shouldHandleSpecialSaasCase
-      ? undefined
-      : llmBaseUrl;
-    const finalLlmApiKey = shouldHandleSpecialSaasCase ? undefined : llmApiKey;
-
-    const githubToken = formData.get("github-token-input")?.toString();
-    const newSettings = {
-      github_token: githubToken,
-      provider_tokens: githubToken
-        ? {
-            github: githubToken,
-            gitlab: "",
-          }
-        : undefined,
-      LANGUAGE: languageValue,
-      user_consents_to_analytics: userConsentsToAnalytics,
-      ENABLE_DEFAULT_CONDENSER: enableMemoryCondenser,
-      ENABLE_SOUND_NOTIFICATIONS: enableSoundNotifications,
-      LLM_MODEL: finalLlmModel,
-      LLM_BASE_URL: finalLlmBaseUrl,
-      LLM_API_KEY: finalLlmApiKey,
-      AGENT: formData.get("agent-input")?.toString(),
-      SECURITY_ANALYZER:
-        formData.get("security-analyzer-input")?.toString() || "",
-      REMOTE_RUNTIME_RESOURCE_FACTOR:
-        remoteRuntimeResourceFactor ||
-        DEFAULT_SETTINGS.REMOTE_RUNTIME_RESOURCE_FACTOR,
-      CONFIRMATION_MODE: confirmationModeIsEnabled,
-    };
-
-    saveSettings(newSettings, {
-      onSuccess: () => {
-        handleCaptureConsent(userConsentsToAnalytics);
-        displaySuccessToast("Settings saved");
-        setLlmConfigMode(isAdvancedSettingsSet ? "advanced" : "basic");
+    saveSettings(
+      {
+        github_token:
+          formData.get("github-token-input")?.toString() || undefined,
+        LANGUAGE: languageValue,
+        user_consents_to_analytics: userConsentsToAnalytics,
+        ENABLE_DEFAULT_CONDENSER: enableMemoryCondenser,
+        ENABLE_SOUND_NOTIFICATIONS: enableSoundNotifications,
+        LLM_MODEL: customLlmModel || fullLlmModel,
+        LLM_BASE_URL: formData.get("base-url-input")?.toString() || "",
+        LLM_API_KEY:
+          formData.get("llm-api-key-input")?.toString() ||
+          (isLLMKeySet
+            ? undefined // don't update if it's already set
+            : ""), // reset if it's first time save to avoid 500 error
+        AGENT: formData.get("agent-input")?.toString(),
+        SECURITY_ANALYZER:
+          formData.get("security-analyzer-input")?.toString() || "",
+        REMOTE_RUNTIME_RESOURCE_FACTOR:
+          remoteRuntimeResourceFactor ||
+          DEFAULT_SETTINGS.REMOTE_RUNTIME_RESOURCE_FACTOR,
+        CONFIRMATION_MODE: confirmationModeIsEnabled,
       },
-      onError: (error) => {
-        const errorMessage = retrieveAxiosErrorMessage(error);
-        displayErrorToast(errorMessage);
+      {
+        onSuccess: () => {
+          handleCaptureConsent(userConsentsToAnalytics);
+          displaySuccessToast("Settings saved");
+          setLlmConfigMode(isAdvancedSettingsSet ? "advanced" : "basic");
+        },
+        onError: (error) => {
+          const errorMessage = retrieveAxiosErrorMessage(error);
+          displayErrorToast(errorMessage);
+        },
       },
-    });
+    );
   };
 
   const handleReset = () => {
-    const newSettings: Partial<PostSettings> = {
-      ...DEFAULT_SETTINGS,
-      LLM_API_KEY: "", // reset LLM API key
-    };
-
-    // we don't want the user to be able to modify these settings in SaaS
-    // and we should make sure they aren't included in the reset
-    if (shouldHandleSpecialSaasCase) {
-      delete newSettings.LLM_API_KEY;
-      delete newSettings.LLM_BASE_URL;
-      delete newSettings.LLM_MODEL;
-    }
-
-    saveSettings(newSettings, {
-      onSuccess: () => {
-        displaySuccessToast("Settings reset");
-        setResetSettingsModalIsOpen(false);
-        setLlmConfigMode(isAdvancedSettingsSet ? "advanced" : "basic");
+    saveSettings(
+      {
+        ...DEFAULT_SETTINGS,
+        LLM_API_KEY: "", // reset LLM API key
       },
-    });
+      {
+        onSuccess: () => {
+          displaySuccessToast("Settings reset");
+          setResetSettingsModalIsOpen(false);
+          setLlmConfigMode(isAdvancedSettingsSet ? "advanced" : "basic");
+        },
+      },
+    );
   };
 
   React.useEffect(() => {
@@ -222,162 +190,150 @@ function AccountSettings() {
   return (
     <>
       <form
-        data-testid="account-settings-form"
         ref={formRef}
         action={onSubmit}
         className="flex flex-col grow overflow-auto"
       >
         <div className="flex flex-col gap-12 px-11 py-9">
-          {!shouldHandleSpecialSaasCase && (
-            <section
-              data-testid="llm-settings-section"
-              className="flex flex-col gap-6"
-            >
-              <div className="flex items-center gap-7">
-                <h2 className="text-[28px] leading-8 tracking-[-0.02em] font-bold">
-                  LLM Settings
-                </h2>
-                {!shouldHandleSpecialSaasCase && (
-                  <SettingsSwitch
-                    testId="advanced-settings-switch"
-                    defaultIsToggled={isAdvancedSettingsSet}
-                    onToggle={onToggleAdvancedMode}
-                  >
-                    Advanced
-                  </SettingsSwitch>
-                )}
-              </div>
+          <section className="flex flex-col gap-6">
+            <div className="flex items-center gap-7">
+              <h2 className="text-[28px] leading-8 tracking-[-0.02em] font-bold">
+                LLM Settings
+              </h2>
+              <SettingsSwitch
+                testId="advanced-settings-switch"
+                defaultIsToggled={isAdvancedSettingsSet}
+                onToggle={onToggleAdvancedMode}
+              >
+                Advanced
+              </SettingsSwitch>
+            </div>
 
-              {llmConfigMode === "basic" && !shouldHandleSpecialSaasCase && (
-                <ModelSelector
-                  models={modelsAndProviders}
-                  currentModel={settings.LLM_MODEL}
-                />
-              )}
+            {llmConfigMode === "basic" && (
+              <ModelSelector
+                models={modelsAndProviders}
+                currentModel={settings.LLM_MODEL}
+              />
+            )}
 
-              {llmConfigMode === "advanced" && !shouldHandleSpecialSaasCase && (
-                <SettingsInput
-                  testId="llm-custom-model-input"
-                  name="llm-custom-model-input"
-                  label="Custom Model"
-                  defaultValue={settings.LLM_MODEL}
-                  placeholder="anthropic/claude-3-5-sonnet-20241022"
-                  type="text"
-                  className="w-[680px]"
-                />
-              )}
-              {llmConfigMode === "advanced" && !shouldHandleSpecialSaasCase && (
-                <SettingsInput
-                  testId="base-url-input"
-                  name="base-url-input"
-                  label="Base URL"
-                  defaultValue={settings.LLM_BASE_URL}
-                  placeholder="https://api.openai.com"
-                  type="text"
-                  className="w-[680px]"
-                />
-              )}
+            {llmConfigMode === "advanced" && (
+              <SettingsInput
+                testId="llm-custom-model-input"
+                name="llm-custom-model-input"
+                label="Custom Model"
+                defaultValue={settings.LLM_MODEL}
+                placeholder="anthropic/claude-3-5-sonnet-20241022"
+                type="text"
+                className="w-[680px]"
+              />
+            )}
+            {llmConfigMode === "advanced" && (
+              <SettingsInput
+                testId="base-url-input"
+                name="base-url-input"
+                label="Base URL"
+                defaultValue={settings.LLM_BASE_URL}
+                placeholder="https://api.openai.com"
+                type="text"
+                className="w-[680px]"
+              />
+            )}
 
-              {!shouldHandleSpecialSaasCase && (
-                <SettingsInput
-                  testId="llm-api-key-input"
-                  name="llm-api-key-input"
-                  label="API Key"
-                  type="password"
-                  className="w-[680px]"
-                  startContent={
-                    isLLMKeySet && <KeyStatusIcon isSet={isLLMKeySet} />
-                  }
-                  placeholder={isLLMKeySet ? "**********" : ""}
-                />
-              )}
+            <SettingsInput
+              testId="llm-api-key-input"
+              name="llm-api-key-input"
+              label="API Key"
+              type="password"
+              className="w-[680px]"
+              startContent={
+                isLLMKeySet && <KeyStatusIcon isSet={isLLMKeySet} />
+              }
+              placeholder={isLLMKeySet ? "**********" : ""}
+            />
 
-              {!shouldHandleSpecialSaasCase && (
-                <HelpLink
-                  testId="llm-api-key-help-anchor"
-                  text="Don't know your API key?"
-                  linkText="Click here for instructions"
-                  href="https://docs.all-hands.dev/modules/usage/llms"
-                />
-              )}
+            <HelpLink
+              testId="llm-api-key-help-anchor"
+              text="Don't know your API key?"
+              linkText="Click here for instructions"
+              href="https://docs.all-hands.dev/modules/usage/llms"
+            />
 
-              {llmConfigMode === "advanced" && (
+            {llmConfigMode === "advanced" && (
+              <SettingsDropdownInput
+                testId="agent-input"
+                name="agent-input"
+                label="Agent"
+                items={
+                  resources?.agents.map((agent) => ({
+                    key: agent,
+                    label: agent,
+                  })) || []
+                }
+                defaultSelectedKey={settings.AGENT}
+                isClearable={false}
+              />
+            )}
+
+            {isSaas && llmConfigMode === "advanced" && (
+              <SettingsDropdownInput
+                testId="runtime-settings-input"
+                name="runtime-settings-input"
+                label={
+                  <>
+                    Runtime Settings (
+                    <a href="mailto:contact@all-hands.dev">
+                      get in touch for access
+                    </a>
+                    )
+                  </>
+                }
+                items={REMOTE_RUNTIME_OPTIONS}
+                defaultSelectedKey={settings.REMOTE_RUNTIME_RESOURCE_FACTOR?.toString()}
+                isDisabled
+                isClearable={false}
+              />
+            )}
+
+            {llmConfigMode === "advanced" && (
+              <SettingsSwitch
+                testId="enable-confirmation-mode-switch"
+                onToggle={setConfirmationModeIsEnabled}
+                defaultIsToggled={!!settings.CONFIRMATION_MODE}
+                isBeta
+              >
+                Enable confirmation mode
+              </SettingsSwitch>
+            )}
+
+            {llmConfigMode === "advanced" && (
+              <SettingsSwitch
+                testId="enable-memory-condenser-switch"
+                name="enable-memory-condenser-switch"
+                defaultIsToggled={!!settings.ENABLE_DEFAULT_CONDENSER}
+              >
+                Enable memory condensation
+              </SettingsSwitch>
+            )}
+
+            {llmConfigMode === "advanced" && confirmationModeIsEnabled && (
+              <div>
                 <SettingsDropdownInput
-                  testId="agent-input"
-                  name="agent-input"
-                  label="Agent"
+                  testId="security-analyzer-input"
+                  name="security-analyzer-input"
+                  label="Security Analyzer"
                   items={
-                    resources?.agents.map((agent) => ({
-                      key: agent,
-                      label: agent,
+                    resources?.securityAnalyzers.map((analyzer) => ({
+                      key: analyzer,
+                      label: analyzer,
                     })) || []
                   }
-                  defaultSelectedKey={settings.AGENT}
-                  isClearable={false}
+                  defaultSelectedKey={settings.SECURITY_ANALYZER}
+                  isClearable
+                  showOptionalTag
                 />
-              )}
-
-              {isSaas && llmConfigMode === "advanced" && (
-                <SettingsDropdownInput
-                  testId="runtime-settings-input"
-                  name="runtime-settings-input"
-                  label={
-                    <>
-                      Runtime Settings (
-                      <a href="mailto:contact@all-hands.dev">
-                        get in touch for access
-                      </a>
-                      )
-                    </>
-                  }
-                  items={REMOTE_RUNTIME_OPTIONS}
-                  defaultSelectedKey={settings.REMOTE_RUNTIME_RESOURCE_FACTOR?.toString()}
-                  isDisabled
-                  isClearable={false}
-                />
-              )}
-
-              {llmConfigMode === "advanced" && (
-                <SettingsSwitch
-                  testId="enable-confirmation-mode-switch"
-                  onToggle={setConfirmationModeIsEnabled}
-                  defaultIsToggled={!!settings.CONFIRMATION_MODE}
-                  isBeta
-                >
-                  Enable confirmation mode
-                </SettingsSwitch>
-              )}
-
-              {llmConfigMode === "advanced" && (
-                <SettingsSwitch
-                  testId="enable-memory-condenser-switch"
-                  name="enable-memory-condenser-switch"
-                  defaultIsToggled={!!settings.ENABLE_DEFAULT_CONDENSER}
-                >
-                  Enable memory condensation
-                </SettingsSwitch>
-              )}
-
-              {llmConfigMode === "advanced" && confirmationModeIsEnabled && (
-                <div>
-                  <SettingsDropdownInput
-                    testId="security-analyzer-input"
-                    name="security-analyzer-input"
-                    label="Security Analyzer"
-                    items={
-                      resources?.securityAnalyzers.map((analyzer) => ({
-                        key: analyzer,
-                        label: analyzer,
-                      })) || []
-                    }
-                    defaultSelectedKey={settings.SECURITY_ANALYZER}
-                    isClearable
-                    showOptionalTag
-                  />
-                </div>
-              )}
-            </section>
-          )}
+              </div>
+            )}
+          </section>
 
           <section className="flex flex-col gap-6">
             <h2 className="text-[28px] leading-8 tracking-[-0.02em] font-bold">
@@ -410,31 +366,12 @@ function AccountSettings() {
                   placeholder={isGitHubTokenSet ? "**********" : ""}
                 />
 
-                <p className="text-xs">
-                  Generate a token on{" "}
-                  <b>
-                    <a
-                      href="https://github.com/settings/tokens/new?description=openhands-app&scopes=repo,user,workflow"
-                      target="_blank"
-                      className="underline underline-offset-2"
-                      rel="noopener noreferrer"
-                    >
-                      GitHub
-                    </a>{" "}
-                  </b>
-                  or see the{" "}
-                  <b>
-                    <a
-                      href="https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/creating-a-personal-access-token"
-                      target="_blank"
-                      className="underline underline-offset-2"
-                      rel="noopener noreferrer"
-                    >
-                      documentation
-                    </a>
-                  </b>
-                  .
-                </p>
+                <HelpLink
+                  testId="github-token-help-anchor"
+                  text="Get your token"
+                  linkText="here"
+                  href="https://github.com/settings/tokens/new?description=openhands-app&scopes=repo,user,workflow"
+                />
               </>
             )}
 

frontend/src/services/actions.ts

@@ -62,12 +62,13 @@ const messageActions = {
     let successPrediction = "";
     if (message.args.task_completed === "partial") {
       successPrediction =
-        "I believe that the task was **completed partially**.";
+        "The agent thinks that the task was **completed partially**.";
     } else if (message.args.task_completed === "false") {
-      successPrediction = "I believe that the task was **not completed**.";
+      successPrediction =
+        "The agent thinks that the task was **not completed**.";
     } else if (message.args.task_completed === "true") {
       successPrediction =
-        "I believe that the task was **completed successfully**.";
+        "The agent thinks that the task was **completed successfully**.";
     }
     if (successPrediction) {
       // if final_thought is not empty, add a new line before the success prediction

frontend/src/services/settings.ts

@@ -15,11 +15,6 @@ export const DEFAULT_SETTINGS: Settings = {
   ENABLE_DEFAULT_CONDENSER: true,
   ENABLE_SOUND_NOTIFICATIONS: false,
   USER_CONSENTS_TO_ANALYTICS: false,
-  PROVIDER_TOKENS: {
-    github: "",
-    gitlab: "",
-  },
-  IS_NEW_USER: true,
 };
 
 /**

frontend/src/types/core/variances.ts

@@ -21,6 +21,7 @@ export interface InitConfig {
     LLM_MODEL: string;
   };
   token?: string;
+  github_token?: string;
   latest_event_id?: unknown; // Not sure what this is
 }
 

frontend/src/types/settings.ts

@@ -1,5 +1,3 @@
-export type Provider = "github" | "gitlab";
-
 export type Settings = {
   LLM_MODEL: string;
   LLM_BASE_URL: string;
@@ -13,8 +11,6 @@ export type Settings = {
   ENABLE_DEFAULT_CONDENSER: boolean;
   ENABLE_SOUND_NOTIFICATIONS: boolean;
   USER_CONSENTS_TO_ANALYTICS: boolean | null;
-  PROVIDER_TOKENS: Record<Provider, string>;
-  IS_NEW_USER?: boolean;
 };
 
 export type ApiSettings = {
@@ -30,17 +26,16 @@ export type ApiSettings = {
   enable_default_condenser: boolean;
   enable_sound_notifications: boolean;
   user_consents_to_analytics: boolean | null;
-  provider_tokens: Record<Provider, string>;
 };
 
 export type PostSettings = Settings & {
-  provider_tokens: Record<Provider, string>;
+  github_token: string;
   unset_github_token: boolean;
   user_consents_to_analytics: boolean | null;
 };
 
 export type PostApiSettings = ApiSettings & {
-  provider_tokens: Record<Provider, string>;
+  github_token: string;
   unset_github_token: boolean;
   user_consents_to_analytics: boolean | null;
 };

frontend/src/utils/custom-toast-handlers.ts

@@ -0,0 +1,25 @@
+import toast from "react-hot-toast";
+
+export const displayErrorToast = (error: string) => {
+  toast.error(error, {
+    position: "top-right",
+    style: {
+      background: "#454545",
+      border: "1px solid #717888",
+      color: "#fff",
+      borderRadius: "4px",
+    },
+  });
+};
+
+export const displaySuccessToast = (message: string) => {
+  toast.success(message, {
+    position: "top-right",
+    style: {
+      background: "#454545",
+      border: "1px solid #717888",
+      color: "#fff",
+      borderRadius: "4px",
+    },
+  });
+};

frontend/src/utils/custom-toast-handlers.tsx

@@ -1,22 +0,0 @@
-import { CSSProperties } from "react";
-import toast, { ToastOptions } from "react-hot-toast";
-
-const TOAST_STYLE: CSSProperties = {
-  background: "#454545",
-  border: "1px solid #717888",
-  color: "#fff",
-  borderRadius: "4px",
-};
-
-const TOAST_OPTIONS: ToastOptions = {
-  position: "top-right",
-  style: TOAST_STYLE,
-};
-
-export const displayErrorToast = (error: string) => {
-  toast.error(error, TOAST_OPTIONS);
-};
-
-export const displaySuccessToast = (message: string) => {
-  toast.success(message, TOAST_OPTIONS);
-};

frontend/src/utils/error-handler.ts

@@ -1,6 +1,6 @@
 import posthog from "posthog-js";
+import toast from "react-hot-toast";
 import { handleStatusMessage } from "#/services/actions";
-import { displayErrorToast } from "./custom-toast-handlers";
 
 interface ErrorDetails {
   message: string;
@@ -23,7 +23,7 @@ export function showErrorToast({
   metadata = {},
 }: ErrorDetails) {
   trackError({ message, source, metadata });
-  displayErrorToast(message);
+  toast.error(message);
 }
 
 export function showChatError({

frontend/src/utils/feature-flags.ts

@@ -13,4 +13,3 @@ function loadFeatureFlag(
 }
 
 export const BILLING_SETTINGS = () => loadFeatureFlag("BILLING_SETTINGS");
-export const HIDE_LLM_SETTINGS = () => loadFeatureFlag("HIDE_LLM_SETTINGS");

frontend/src/utils/settings-utils.ts

@@ -59,18 +59,6 @@ export const extractSettings = (formData: FormData): Partial<Settings> => {
     ENABLE_DEFAULT_CONDENSER,
   } = extractAdvancedFormData(formData);
 
-  // Extract provider tokens
-  const githubToken = formData.get("github-token")?.toString();
-  const gitlabToken = formData.get("gitlab-token")?.toString();
-  const providerTokens: Record<string, string> = {};
-
-  if (githubToken) {
-    providerTokens.github = githubToken;
-  }
-  if (gitlabToken) {
-    providerTokens.gitlab = gitlabToken;
-  }
-
   return {
     LLM_MODEL: CUSTOM_LLM_MODEL || LLM_MODEL,
     LLM_API_KEY,
@@ -80,6 +68,5 @@ export const extractSettings = (formData: FormData): Partial<Settings> => {
     CONFIRMATION_MODE,
     SECURITY_ANALYZER,
     ENABLE_DEFAULT_CONDENSER,
-    PROVIDER_TOKENS: providerTokens,
   };
 };

frontend/tailwind.config.js

@@ -17,7 +17,6 @@ export default {
         tertiary: "#454545", // gray, used for inputs
         "tertiary-light": "#B7BDC2", // lighter gray, used for borders and placeholder text
         content: "#ECEDEE", // light gray, used mostly for text
-        "content-2": "#F9FBFE",
       },
     },
   },

microagents/knowledge/github.md

@@ -14,8 +14,6 @@ the GitHub API.
 You can use `curl` with the `GITHUB_TOKEN` to interact with GitHub's API.
 ALWAYS use the GitHub API for operations instead of a web browser.
 
-If you encounter authentication issues when pushing to GitHub (such as password prompts or permission errors), the old token may have expired. In such case, update the remote URL to include the current token: `git remote set-url origin https://${GITHUB_TOKEN}@github.com/username/repo.git`
-
 Here are some instructions for pushing, but ONLY do this if the user asks you to:
 * NEVER push directly to the `main` or `master` branch
 * Git config (username and email) is pre-set. Do not modify.

microagents/knowledge/swift-linux.md

@@ -1,83 +0,0 @@
----
- name: swift-linux
- type: knowledge
- agent: CodeActAgent
- version: 1.0.0
- triggers:
- - swift-linux
- - swift-debian
- - swift-installation
----
-
-# Swift Installation Guide for Debian Linux
-
-This document provides instructions for installing Swift on Debian 12 (Bookworm).
-
-> This setup is intended for non-UI development tasks on Swift on Linux.
-
-## Prerequisites
-
-Before installing Swift, you need to install the required dependencies for your system. You can find the most up-to-date list of dependencies for your specific Linux distribution and version at the [Swift.org tarball installation guide](https://www.swift.org/install/linux/tarball/).
-
-FOR EXAMPLE, the dependencies you may need to install for Debian 12 could be:
-
-```bash
-sudo apt-get update
-sudo apt-get install -y \
-  binutils-gold \
-  gcc \
-  git \
-  libcurl4-openssl-dev \
-  libedit-dev \
-  libicu-dev \
-  libncurses-dev \
-  libpython3-dev \
-  libsqlite3-dev \
-  libxml2-dev \
-  pkg-config \
-  tzdata \
-  uuid-dev
-```
-
-## Download and Install Swift
-
-1. Find the latest Swift version for Debian:
-
-   Go to the [Swift.org download page](https://www.swift.org/download/) to find the latest Swift version compatible with Debian 12 (Bookworm).
-
-   Look for a tarball named something like `swift-<VERSION>-RELEASE-debian12.tar.gz` (e.g., `swift-6.0.3-RELEASE-debian12.tar.gz`).
-
-   The URL pattern is typically:
-   ```
-   https://download.swift.org/swift-<VERSION>-release/debian12/swift-<VERSION>-RELEASE/swift-<VERSION>-RELEASE-debian12.tar.gz
-   ```
-
-   Where `<VERSION>` is the Swift version number (e.g., `6.0.3`).
-
-2. Download the Swift binary for Debian 12:
-
-```bash
-cd /workspace
-wget https://download.swift.org/swift-6.0.3-release/debian12/swift-6.0.3-RELEASE/swift-6.0.3-RELEASE-debian12.tar.gz
-```
-
-3. Extract the archive:
-
-> **Note**: Make sure to install Swift in the `/workspace` directory, but outside the git repository to avoid committing the Swift binaries.
-
-4. Add Swift to your PATH by adding the following line to your `~/.bashrc` file:
-
-```bash
-echo 'export PATH=/workspace/swift-6.0.3-RELEASE-debian12/usr/bin:$PATH' >> ~/.bashrc
-source ~/.bashrc
-```
-
-> **Note**: Make sure to update the version number in the PATH to match the version you downloaded.
-
-## Verify Installation
-
-Verify that Swift is correctly installed by running:
-
-```bash
-swift --version
-```

openhands/agenthub/__init__.py

@@ -1,20 +1,39 @@
 from dotenv import load_dotenv
 
+from openhands.agenthub.micro.agent import MicroAgent
+from openhands.agenthub.micro.registry import all_microagents
+from openhands.controller.agent import Agent
+
 load_dotenv()
 
 
 from openhands.agenthub import (  # noqa: E402
     browsing_agent,
     codeact_agent,
+    delegator_agent,
     dummy_agent,
     visualbrowsing_agent,
 )
-from openhands.controller.agent import Agent  # noqa: E402
 
 __all__ = [
-    'Agent',
     'codeact_agent',
+    'delegator_agent',
     'dummy_agent',
     'browsing_agent',
     'visualbrowsing_agent',
 ]
+
+for agent in all_microagents.values():
+    name = agent['name']
+    prompt = agent['prompt']
+
+    anon_class = type(
+        name,
+        (MicroAgent,),
+        {
+            'prompt': prompt,
+            'agent_definition': agent,
+        },
+    )
+
+    Agent.register(name, anon_class)

openhands/agenthub/codeact_agent/codeact_agent.py

@@ -1,6 +1,8 @@
+import json
 import os
 from collections import deque
 
+import openhands
 import openhands.agenthub.codeact_agent.function_calling as codeact_function_calling
 from openhands.controller.agent import Agent
 from openhands.controller.state.state import State
@@ -70,17 +72,23 @@ class CodeActAgent(Agent):
             codeact_enable_browsing=self.config.codeact_enable_browsing,
             codeact_enable_jupyter=self.config.codeact_enable_jupyter,
             codeact_enable_llm_editor=self.config.codeact_enable_llm_editor,
-            llm=self.llm,
         )
         logger.debug(
-            f"TOOLS loaded for CodeActAgent: {', '.join([tool.get('function').get('name') for tool in self.tools])}"
+            f'TOOLS loaded for CodeActAgent: {json.dumps(self.tools, indent=2, ensure_ascii=False).replace("\\n", "\n")}'
         )
         self.prompt_manager = PromptManager(
+            microagent_dir=os.path.join(
+                os.path.dirname(os.path.dirname(openhands.__file__)),
+                'microagents',
+            )
+            if self.config.enable_prompt_extensions
+            else None,
             prompt_dir=os.path.join(os.path.dirname(__file__), 'prompts'),
+            disabled_microagents=self.config.disabled_microagents,
         )
 
         # Create a ConversationMemory instance
-        self.conversation_memory = ConversationMemory(self.config, self.prompt_manager)
+        self.conversation_memory = ConversationMemory(self.prompt_manager)
 
         self.condenser = Condenser.from_config(self.config.condenser)
         logger.debug(f'Using condenser: {type(self.condenser)}')
@@ -160,7 +168,7 @@ class CodeActAgent(Agent):
         if not self.prompt_manager:
             raise Exception('Prompt Manager not instantiated.')
 
-        # Use ConversationMemory to process initial messages
+        # Use conversation_memory to process events instead of calling events_to_messages directly
         messages = self.conversation_memory.process_initial_messages(
             with_caching=self.llm.is_caching_prompt_active()
         )
@@ -172,12 +180,12 @@ class CodeActAgent(Agent):
             f'Processing {len(events)} events from a total of {len(state.history)} events'
         )
 
-        # Use ConversationMemory to process events
         messages = self.conversation_memory.process_events(
             condensed_history=events,
             initial_messages=messages,
             max_message_chars=self.llm.config.max_message_chars,
             vision_is_active=self.llm.vision_is_active(),
+            enable_som_visual_browsing=self.config.enable_som_visual_browsing,
         )
 
         messages = self._enhance_messages(messages)
@@ -208,7 +216,14 @@ class CodeActAgent(Agent):
                 # compose the first user message with examples
                 self.prompt_manager.add_examples_to_initial_message(msg)
 
-            elif msg.role == 'user':
+                # and/or repo/runtime info
+                if self.config.enable_prompt_extensions:
+                    self.prompt_manager.add_info_to_initial_message(msg)
+
+            # enhance the user message with additional context based on keywords matched
+            if msg.role == 'user':
+                self.prompt_manager.enhance_message(msg)
+
                 # Add double newline between consecutive user messages
                 if prev_role == 'user' and len(msg.content) > 0:
                     # Find the first TextContent in the message to add newlines

openhands/agenthub/codeact_agent/function_calling.py

@@ -12,13 +12,13 @@ from litellm import (
 
 from openhands.agenthub.codeact_agent.tools import (
     BrowserTool,
+    CmdRunTool,
     FinishTool,
     IPythonTool,
     LLMBasedFileEditTool,
+    StrReplaceEditorTool,
     ThinkTool,
     WebReadTool,
-    create_cmd_run_tool,
-    create_str_replace_editor_tool,
 )
 from openhands.core.exceptions import (
     FunctionCallNotExistsError,
@@ -39,7 +39,6 @@ from openhands.events.action import (
 )
 from openhands.events.event import FileEditSource, FileReadSource
 from openhands.events.tool import ToolCallMetadata
-from openhands.llm import LLM
 
 
 def combine_thought(action: Action, thought: str) -> Action:
@@ -81,7 +80,7 @@ def response_to_actions(response: ModelResponse) -> list[Action]:
             # CmdRunTool (Bash)
             # ================================================
 
-            if tool_call.function.name == create_cmd_run_tool()['function']['name']:
+            if tool_call.function.name == CmdRunTool['function']['name']:
                 if 'command' not in arguments:
                     raise FunctionCallValidationError(
                         f'Missing required argument "command" in tool call {tool_call.function.name}'
@@ -132,10 +131,7 @@ def response_to_actions(response: ModelResponse) -> list[Action]:
                     start=arguments.get('start', 1),
                     end=arguments.get('end', -1),
                 )
-            elif (
-                tool_call.function.name
-                == create_str_replace_editor_tool()['function']['name']
-            ):
+            elif tool_call.function.name == StrReplaceEditorTool['function']['name']:
                 if 'command' not in arguments:
                     raise FunctionCallValidationError(
                         f'Missing required argument "command" in tool call {tool_call.function.name}'
@@ -223,22 +219,8 @@ def get_tools(
     codeact_enable_browsing: bool = False,
     codeact_enable_llm_editor: bool = False,
     codeact_enable_jupyter: bool = False,
-    llm: LLM | None = None,
 ) -> list[ChatCompletionToolParam]:
-    SIMPLIFIED_TOOL_DESCRIPTION_LLM_SUBSTRS = ['gpt-', 'o3', 'o1']
-
-    use_simplified_tool_desc = False
-    if llm is not None:
-        use_simplified_tool_desc = any(
-            model_substr in llm.config.model
-            for model_substr in SIMPLIFIED_TOOL_DESCRIPTION_LLM_SUBSTRS
-        )
-
-    tools = [
-        create_cmd_run_tool(use_simplified_description=use_simplified_tool_desc),
-        ThinkTool,
-        FinishTool,
-    ]
+    tools = [CmdRunTool, ThinkTool, FinishTool]
     if codeact_enable_browsing:
         tools.append(WebReadTool)
         tools.append(BrowserTool)
@@ -247,9 +229,5 @@ def get_tools(
     if codeact_enable_llm_editor:
         tools.append(LLMBasedFileEditTool)
     else:
-        tools.append(
-            create_str_replace_editor_tool(
-                use_simplified_description=use_simplified_tool_desc
-            )
-        )
+        tools.append(StrReplaceEditorTool)
     return tools

openhands/agenthub/codeact_agent/prompts/additional_info.j2

@@ -1,6 +1,6 @@
 {% if repository_info %}
 <REPOSITORY_INFO>
-At the user's request, repository {{ repository_info.repo_name }} has been cloned to the current working directory {{ repository_info.repo_directory }}.
+At the user's request, repository {{ repository_info.repo_name }} has been cloned to directory {{ repository_info.repo_directory }}.
 </REPOSITORY_INFO>
 {% endif %}
 {% if repository_instructions -%}
@@ -20,8 +20,6 @@ When starting a web server, use the corresponding ports. You should also
 set any options to allow iframes and CORS requests, and allow the server to
 be accessed from any host (e.g. 0.0.0.0).
 {% endif %}
-{% if runtime_info.additional_agent_instructions %}
 {{ runtime_info.additional_agent_instructions }}
-{% endif %}
 </RUNTIME_INFORMATION>
 {% endif %}

openhands/agenthub/codeact_agent/prompts/microagent_info.j2

@@ -1,8 +1,8 @@
 {% for agent_info in triggered_agents %}
 <EXTRA_INFO>
-The following information has been included based on a keyword match for "{{ agent_info.trigger }}".
+The following information has been included based on a keyword match for "{{ agent_info.trigger_word }}".
 It may or may not be relevant to the user's request.
 
-{{ agent_info.content }}
+{{ agent_info.agent.content }}
 </EXTRA_INFO>
 {% endfor %}

openhands/agenthub/codeact_agent/prompts/system_prompt.j2

@@ -1,63 +1,11 @@
 You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.
-
-<ROLE>
-Your primary role is to assist users by executing commands, modifying code, and solving technical problems effectively. You should be thorough, methodical, and prioritize quality over speed.
-* If the user asks a question, like "why is X happening", don't try to fix the problem. Just give an answer to the question.
-</ROLE>
-
-<EFFICIENCY>
-* Each action you take is somewhat expensive. Wherever possible, combine multiple actions into a single action, e.g. combine multiple bash commands into one, using sed and grep to edit/view multiple files at once.
-* When exploring the codebase, use efficient tools like find, grep, and git commands with appropriate filters to minimize unnecessary operations.
-</EFFICIENCY>
-
-<FILE_SYSTEM_GUIDELINES>
-* When a user provides a file path, do NOT assume it's relative to the current working directory. First explore the file system to locate the file before working on it.
-* If asked to edit a file, edit the file directly, rather than creating a new file with a different filename.
-* For global search-and-replace operations, consider using `sed` instead of opening file editors multiple times.
-</FILE_SYSTEM_GUIDELINES>
-
-<CODE_QUALITY>
-* Write clean, efficient code with minimal comments. Avoid redundancy in comments: Do not repeat information that can be easily inferred from the code itself.
-* When implementing solutions, focus on making the minimal changes needed to solve the problem.
-* Before implementing any changes, first thoroughly understand the codebase through exploration.
-* If you are adding a lot of code to a function or file, consider splitting the function or file into smaller pieces when appropriate.
-</CODE_QUALITY>
-
-<VERSION_CONTROL>
+<IMPORTANT>
+* If user provides a path, you should NOT assume it's relative to the current working directory. Instead, you should explore the file system to find the file before working on it.
 * When configuring git credentials, use "openhands" as the user.name and "openhands@all-hands.dev" as the user.email by default, unless explicitly instructed otherwise.
-* Exercise caution with git operations. Do NOT make potentially dangerous changes (e.g., pushing to main, deleting repositories) unless explicitly asked to do so.
-</VERSION_CONTROL>
-
-<PROBLEM_SOLVING_WORKFLOW>
-1. EXPLORATION: Thoroughly explore relevant files and understand the context before proposing solutions
-2. ANALYSIS: Consider multiple approaches and select the most promising one
-3. TESTING:
-   * For bug fixes: Create tests to verify issues before implementing fixes
-   * For new features: Consider test-driven development when appropriate
-   * If the repository lacks testing infrastructure and implementing tests would require extensive setup, consult with the user before investing time in building testing infrastructure
-4. IMPLEMENTATION: Make focused, minimal changes to address the problem
-5. VERIFICATION: Test your implementation thoroughly, including edge cases
-</PROBLEM_SOLVING_WORKFLOW>
-
-<SECURITY>
-* Only use GITHUB_TOKEN and other credentials in ways the user has explicitly requested and would expect.
+* You MUST NOT include comments in the code unless they are necessary to describe non-obvious behavior.
+* If the user asks you to edit a file, you should edit the file directly, do NOT create a new file with the updated content unless the user explicitly instructs you to do so.
+* When you are doing global search-and-replace, consider using `sed` instead of running file editor multiple times.
+* Only use GITHUB_TOKEN and other credentials in ways that the user has asked for and would expect. Do NOT make potentially dangerous changes (e.g. pushing to main, deleting a repository) unless explicitly asked to do so.
 * Use APIs to work with GitHub or other platforms, unless the user asks otherwise or your task requires browsing.
-</SECURITY>
-
-<ENVIRONMENT_SETUP>
-* When user asks you to run an application, don't stop if the application is not installed. Instead, please install the application and run the command again.
-* If you encounter missing dependencies:
-  1. First, look around in the repository for existing dependency files (requirements.txt, pyproject.toml, package.json, Gemfile, etc.)
-  2. If dependency files exist, use them to install all dependencies at once (e.g., `pip install -r requirements.txt`, `npm install`, etc.)
-  3. Only install individual packages directly if no dependency files are found or if only specific packages are needed
-* Similarly, if you encounter missing dependencies for essential tools requested by the user, install them when possible.
-</ENVIRONMENT_SETUP>
-
-<TROUBLESHOOTING>
-* If you've made repeated attempts to solve a problem but tests still fail or the user reports it's still broken:
-  1. Step back and reflect on 5-7 different possible sources of the problem
-  2. Assess the likelihood of each possible cause
-  3. Methodically address the most likely causes, starting with the highest probability
-  4. Document your reasoning process
-* When you run into any major issue while executing a plan from the user, please don't try to directly work around it. Instead, propose a new plan and confirm with the user before proceeding.
-</TROUBLESHOOTING>
+* If you've made repeated attempts to solve a problem, but the tests won't pass or the user says it's still broken, reflect on 5-7 different possible sources of the problem. Assess the likelihood of these options, and proceed with fixing the most likely one.
+</IMPORTANT>

openhands/agenthub/codeact_agent/tools/__init__.py

@@ -1,19 +1,19 @@
-from .bash import create_cmd_run_tool
+from .bash import CmdRunTool
 from .browser import BrowserTool
 from .finish import FinishTool
 from .ipython import IPythonTool
 from .llm_based_edit import LLMBasedFileEditTool
-from .str_replace_editor import create_str_replace_editor_tool
+from .str_replace_editor import StrReplaceEditorTool
 from .think import ThinkTool
 from .web_read import WebReadTool
 
 __all__ = [
     'BrowserTool',
-    'create_cmd_run_tool',
+    'CmdRunTool',
     'FinishTool',
     'IPythonTool',
     'LLMBasedFileEditTool',
-    'create_str_replace_editor_tool',
+    'StrReplaceEditorTool',
     'WebReadTool',
     'ThinkTool',
 ]

openhands/agenthub/codeact_agent/tools/bash.py

@@ -1,60 +1,30 @@
 from litellm import ChatCompletionToolParam, ChatCompletionToolParamFunctionChunk
 
-_DETAILED_BASH_DESCRIPTION = """Execute a bash command in the terminal within a persistent shell session.
-
-### Command Execution
-* One command at a time: You can only execute one bash command at a time. If you need to run multiple commands sequentially, use `&&` or `;` to chain them together.
-* Persistent session: Commands execute in a persistent shell session where environment variables, virtual environments, and working directory persist between commands.
-* Timeout: Commands have a soft timeout of 120 seconds, once that's reached, you have the option to continue or interrupt the command (see section below for details)
-
-### Running and Interacting with Processes
-* Long running commands: For commands that may run indefinitely, run them in the background and redirect output to a file, e.g. `python3 app.py > server.log 2>&1 &`.
-* Interact with running process: If a bash command returns exit code `-1`, this means the process is not yet finished. By setting `is_input` to `true`, you can:
-  - Send empty `command` to retrieve additional logs
-  - Send text (set `command` to the text) to STDIN of the running process
-  - Send control commands like `C-c` (Ctrl+C), `C-d` (Ctrl+D), or `C-z` (Ctrl+Z) to interrupt the process
-
-### Best Practices
-* Directory verification: Before creating new directories or files, first verify the parent directory exists and is the correct location.
-* Directory management: Try to maintain working directory by using absolute paths and avoiding excessive use of `cd`.
-
-### Output Handling
-* Output truncation: If the output exceeds a maximum length, it will be truncated before being returned.
-"""
-
-_SIMPLIFIED_BASH_DESCRIPTION = """Execute a bash command in the terminal.
+_BASH_DESCRIPTION = """Execute a bash command in the terminal.
 * Long running commands: For commands that may run indefinitely, it should be run in the background and the output should be redirected to a file, e.g. command = `python3 app.py > server.log 2>&1 &`.
 * Interact with running process: If a bash command returns exit code `-1`, this means the process is not yet finished. By setting `is_input` to `true`, the assistant can interact with the running process and send empty `command` to retrieve any additional logs, or send additional text (set `command` to the text) to STDIN of the running process, or send command like `C-c` (Ctrl+C), `C-d` (Ctrl+D), `C-z` (Ctrl+Z) to interrupt the process.
-* One command at a time: You can only execute one bash command at a time. If you need to run multiple commands sequentially, you can use `&&` or `;` to chain them together."""
+* One command at a time: You can only execute one bash command at a time. If you need to run multiple commands sequentially, you can use `&&` or `;` to chain them together.
+"""
 
-
-def create_cmd_run_tool(
-    use_simplified_description: bool = False,
-) -> ChatCompletionToolParam:
-    description = (
-        _SIMPLIFIED_BASH_DESCRIPTION
-        if use_simplified_description
-        else _DETAILED_BASH_DESCRIPTION
-    )
-    return ChatCompletionToolParam(
-        type='function',
-        function=ChatCompletionToolParamFunctionChunk(
-            name='execute_bash',
-            description=description,
-            parameters={
-                'type': 'object',
-                'properties': {
-                    'command': {
-                        'type': 'string',
-                        'description': 'The bash command to execute. Can be empty string to view additional logs when previous exit code is `-1`. Can be `C-c` (Ctrl+C) to interrupt the currently running process. Note: You can only execute one bash command at a time. If you need to run multiple commands sequentially, you can use `&&` or `;` to chain them together.',
-                    },
-                    'is_input': {
-                        'type': 'string',
-                        'description': 'If True, the command is an input to the running process. If False, the command is a bash command to be executed in the terminal. Default is False.',
-                        'enum': ['true', 'false'],
-                    },
+CmdRunTool = ChatCompletionToolParam(
+    type='function',
+    function=ChatCompletionToolParamFunctionChunk(
+        name='execute_bash',
+        description=_BASH_DESCRIPTION,
+        parameters={
+            'type': 'object',
+            'properties': {
+                'command': {
+                    'type': 'string',
+                    'description': 'The bash command to execute. Can be empty string to view additional logs when previous exit code is `-1`. Can be `C-c` (Ctrl+C) to interrupt the currently running process. Note: You can only execute one bash command at a time. If you need to run multiple commands sequentially, you can use `&&` or `;` to chain them together.',
+                },
+                'is_input': {
+                    'type': 'string',
+                    'description': 'If True, the command is an input to the running process. If False, the command is a bash command to be executed in the terminal. Default is False.',
+                    'enum': ['true', 'false'],
                 },
-                'required': ['command'],
             },
-        ),
-    )
+            'required': ['command'],
+        },
+    ),
+)

openhands/agenthub/codeact_agent/tools/str_replace_editor.py

@@ -1,103 +1,58 @@
 from litellm import ChatCompletionToolParam, ChatCompletionToolParamFunctionChunk
 
-_DETAILED_STR_REPLACE_EDITOR_DESCRIPTION = """Custom editing tool for viewing, creating and editing files in plain-text format
+_STR_REPLACE_EDITOR_DESCRIPTION = """Custom editing tool for viewing, creating and editing files in plain-text format
 * State is persistent across command calls and discussions with the user
 * If `path` is a file, `view` displays the result of applying `cat -n`. If `path` is a directory, `view` lists non-hidden files and directories up to 2 levels deep
 * The `create` command cannot be used if the specified `path` already exists as a file
 * If a `command` generates a long output, it will be truncated and marked with `<response clipped>`
 * The `undo_edit` command will revert the last edit made to the file at `path`
 
-
-Before using this tool:
-1. Use the view tool to understand the file's contents and context
-2. Verify the directory path is correct (only applicable when creating new files):
-   - Use the view tool to verify the parent directory exists and is the correct location
-
-When making edits:
-   - Ensure the edit results in idiomatic, correct code
-   - Do not leave the code in a broken state
-   - Always use absolute file paths (starting with /)
-
-CRITICAL REQUIREMENTS FOR USING THIS TOOL:
-
-1. EXACT MATCHING: The `old_str` parameter must match EXACTLY one or more consecutive lines from the file, including all whitespace and indentation. The tool will fail if `old_str` matches multiple locations or doesn't match exactly with the file content.
-
-2. UNIQUENESS: The `old_str` must uniquely identify a single instance in the file:
-   - Include sufficient context before and after the change point (3-5 lines recommended)
-   - If not unique, the replacement will not be performed
-
-3. REPLACEMENT: The `new_str` parameter should contain the edited lines that replace the `old_str`. Both strings must be different.
-
-Remember: when making multiple file edits in a row to the same file, you should prefer to send all edits in a single message with multiple calls to this tool, rather than multiple messages with a single call each.
-"""
-
-_SIMPLIFIED_STR_REPLACE_EDITOR_DESCRIPTION = """Custom editing tool for viewing, creating and editing files in plain-text format
-* State is persistent across command calls and discussions with the user
-* If `path` is a file, `view` displays the result of applying `cat -n`. If `path` is a directory, `view` lists non-hidden files and directories up to 2 levels deep
-* The `create` command cannot be used if the specified `path` already exists as a file
-* If a `command` generates a long output, it will be truncated and marked with `<response clipped>`
-* The `undo_edit` command will revert the last edit made to the file at `path`
 Notes for using the `str_replace` command:
 * The `old_str` parameter should match EXACTLY one or more consecutive lines from the original file. Be mindful of whitespaces!
 * If the `old_str` parameter is not unique in the file, the replacement will not be performed. Make sure to include enough context in `old_str` to make it unique
 * The `new_str` parameter should contain the edited lines that should replace the `old_str`
 """
 
-
-def create_str_replace_editor_tool(
-    use_simplified_description: bool = False,
-) -> ChatCompletionToolParam:
-    description = (
-        _SIMPLIFIED_STR_REPLACE_EDITOR_DESCRIPTION
-        if use_simplified_description
-        else _DETAILED_STR_REPLACE_EDITOR_DESCRIPTION
-    )
-    return ChatCompletionToolParam(
-        type='function',
-        function=ChatCompletionToolParamFunctionChunk(
-            name='str_replace_editor',
-            description=description,
-            parameters={
-                'type': 'object',
-                'properties': {
-                    'command': {
-                        'description': 'The commands to run. Allowed options are: `view`, `create`, `str_replace`, `insert`, `undo_edit`.',
-                        'enum': [
-                            'view',
-                            'create',
-                            'str_replace',
-                            'insert',
-                            'undo_edit',
-                        ],
-                        'type': 'string',
-                    },
-                    'path': {
-                        'description': 'Absolute path to file or directory, e.g. `/workspace/file.py` or `/workspace`.',
-                        'type': 'string',
-                    },
-                    'file_text': {
-                        'description': 'Required parameter of `create` command, with the content of the file to be created.',
-                        'type': 'string',
-                    },
-                    'old_str': {
-                        'description': 'Required parameter of `str_replace` command containing the string in `path` to replace.',
-                        'type': 'string',
-                    },
-                    'new_str': {
-                        'description': 'Optional parameter of `str_replace` command containing the new string (if not given, no string will be added). Required parameter of `insert` command containing the string to insert.',
-                        'type': 'string',
-                    },
-                    'insert_line': {
-                        'description': 'Required parameter of `insert` command. The `new_str` will be inserted AFTER the line `insert_line` of `path`.',
-                        'type': 'integer',
-                    },
-                    'view_range': {
-                        'description': 'Optional parameter of `view` command when `path` points to a file. If none is given, the full file is shown. If provided, the file will be shown in the indicated line number range, e.g. [11, 12] will show lines 11 and 12. Indexing at 1 to start. Setting `[start_line, -1]` shows all lines from `start_line` to the end of the file.',
-                        'items': {'type': 'integer'},
-                        'type': 'array',
-                    },
+StrReplaceEditorTool = ChatCompletionToolParam(
+    type='function',
+    function=ChatCompletionToolParamFunctionChunk(
+        name='str_replace_editor',
+        description=_STR_REPLACE_EDITOR_DESCRIPTION,
+        parameters={
+            'type': 'object',
+            'properties': {
+                'command': {
+                    'description': 'The commands to run. Allowed options are: `view`, `create`, `str_replace`, `insert`, `undo_edit`.',
+                    'enum': ['view', 'create', 'str_replace', 'insert', 'undo_edit'],
+                    'type': 'string',
+                },
+                'path': {
+                    'description': 'Absolute path to file or directory, e.g. `/workspace/file.py` or `/workspace`.',
+                    'type': 'string',
+                },
+                'file_text': {
+                    'description': 'Required parameter of `create` command, with the content of the file to be created.',
+                    'type': 'string',
+                },
+                'old_str': {
+                    'description': 'Required parameter of `str_replace` command containing the string in `path` to replace.',
+                    'type': 'string',
+                },
+                'new_str': {
+                    'description': 'Optional parameter of `str_replace` command containing the new string (if not given, no string will be added). Required parameter of `insert` command containing the string to insert.',
+                    'type': 'string',
+                },
+                'insert_line': {
+                    'description': 'Required parameter of `insert` command. The `new_str` will be inserted AFTER the line `insert_line` of `path`.',
+                    'type': 'integer',
+                },
+                'view_range': {
+                    'description': 'Optional parameter of `view` command when `path` points to a file. If none is given, the full file is shown. If provided, the file will be shown in the indicated line number range, e.g. [11, 12] will show lines 11 and 12. Indexing at 1 to start. Setting `[start_line, -1]` shows all lines from `start_line` to the end of the file.',
+                    'items': {'type': 'integer'},
+                    'type': 'array',
                 },
-                'required': ['command', 'path'],
             },
-        ),
-    )
+            'required': ['command', 'path'],
+        },
+    ),
+)

openhands/agenthub/delegator_agent/__init__.py

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

openhands/agenthub/delegator_agent/agent.py

@@ -0,0 +1,87 @@
+from openhands.controller.agent import Agent
+from openhands.controller.state.state import State
+from openhands.core.config import AgentConfig
+from openhands.events.action import Action, AgentDelegateAction, AgentFinishAction
+from openhands.events.observation import AgentDelegateObservation, Observation
+from openhands.llm.llm import LLM
+
+
+class DelegatorAgent(Agent):
+    VERSION = '1.0'
+    """
+    The Delegator Agent is responsible for delegating tasks to other agents based on the current task.
+    """
+
+    current_delegate: str = ''
+
+    def __init__(self, llm: LLM, config: AgentConfig):
+        """Initialize the Delegator Agent with an LLM
+
+        Parameters:
+        - llm (LLM): The llm to be used by this agent
+        """
+        super().__init__(llm, config)
+
+    def step(self, state: State) -> Action:
+        """Checks to see if current step is completed, returns AgentFinishAction if True.
+        Otherwise, delegates the task to the next agent in the pipeline.
+
+        Parameters:
+        - state (State): The current state given the previous actions and observations
+
+        Returns:
+        - AgentFinishAction: If the last state was 'completed', 'verified', or 'abandoned'
+        - AgentDelegateAction: The next agent to delegate the task to
+        """
+        if self.current_delegate == '':
+            self.current_delegate = 'study'
+            task, _ = state.get_current_user_intent()
+            return AgentDelegateAction(
+                agent='StudyRepoForTaskAgent', inputs={'task': task}
+            )
+
+        # last observation in history should be from the delegate
+        last_observation = None
+        for event in reversed(state.history):
+            if isinstance(event, Observation):
+                last_observation = event
+                break
+
+        if not isinstance(last_observation, AgentDelegateObservation):
+            raise Exception('Last observation is not an AgentDelegateObservation')
+
+        goal, _ = state.get_current_user_intent()
+        if self.current_delegate == 'study':
+            self.current_delegate = 'coder'
+            return AgentDelegateAction(
+                agent='CoderAgent',
+                inputs={
+                    'task': goal,
+                    'summary': last_observation.outputs['summary'],
+                },
+            )
+        elif self.current_delegate == 'coder':
+            self.current_delegate = 'verifier'
+            return AgentDelegateAction(
+                agent='VerifierAgent',
+                inputs={
+                    'task': goal,
+                },
+            )
+        elif self.current_delegate == 'verifier':
+            if (
+                'completed' in last_observation.outputs
+                and last_observation.outputs['completed']
+            ):
+                return AgentFinishAction()
+            else:
+                self.current_delegate = 'coder'
+                return AgentDelegateAction(
+                    agent='CoderAgent',
+                    inputs={
+                        'task': goal,
+                        'summary': last_observation.outputs['summary'],
+                    },
+                )
+        else:
+            raise Exception('Invalid delegate state')