Fix terminal command echo issue (#6661) and update tests

Co-authored-by: Xingyao Wang <xingyao@all-hands.dev>

.github/dependabot.yml

@@ -10,12 +10,6 @@ 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,llama-index
+        run: poetry install --without evaluation
       - 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,llama-index
+        run: poetry install --without evaluation
 
       - name: Configure config.toml for testing with Haiku
         env:
@@ -117,68 +117,6 @@ 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" >> $GITHUB_ENV
-      # -------------------------------------------------------------
       # Run VisualBrowsingAgent tests for DeepSeek, limited to t05 and t06
       - name: Wait a little bit (again)
         run: sleep 5
@@ -213,7 +151,7 @@ jobs:
         run: |
           TIMESTAMP=$(date +'%y-%m-%d-%H-%M')
           cd evaluation/evaluation_outputs/outputs  # Change to the outputs directory
-          tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/* integration_tests/DelegatorAgent/* integration_tests/VisualBrowsingAgent/* # Only include the actual result directories
+          tar -czvf ../../../integration_tests_${TIMESTAMP}.tar.gz integration_tests/CodeActAgent/* integration_tests/VisualBrowsingAgent/* # Only include the actual result directories
 
       - name: Upload evaluation results as artifact
         uses: actions/upload-artifact@v4
@@ -254,12 +192,6 @@ 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,llama-index
+        run: poetry install --without evaluation
       - name: Build Environment
         run: make build
       - name: Run Tests
-        run: poetry run pytest --forked -n auto --cov=openhands --cov-report=xml -svv ./tests/unit --ignore=tests/unit/test_long_term_memory.py
+        run: poetry run pytest --forked -n auto --cov=openhands --cov-report=xml -svv ./tests/unit
       - 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 --without llama-index
+	@poetry install
 	@if [ -f "/etc/manjaro-release" ]; then \
 		echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
 		poetry run pip install playwright; \
@@ -265,35 +265,6 @@ 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:

config.template.toml

@@ -132,15 +132,6 @@ 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
 
@@ -227,9 +218,6 @@ 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,llama-index --no-root && rm -rf $POETRY_CACHE_DIR
+RUN export POETRY_CACHE_DIR && poetry install --without evaluation --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

@@ -333,12 +333,6 @@ 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/zh-Hans/docusaurus-plugin-content-docs/current/usage/configuration-options.md

@@ -328,12 +328,6 @@ 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/modules/usage/cloud/cloud-github-resolver.md

@@ -4,18 +4,30 @@ 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 attempt to fix the issue.
+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.
+
 
 ### Pull Requests
 
-In order to get OpenHands to work on pull requests, use `@openhands` in top level or single inline comments to:
+To get OpenHands to work on pull requests, use `@openhands` in top level or 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

@@ -12,14 +12,16 @@ 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 by All Hands AI`.
+2. Review the permissions requested by OpenHands and then click `Authorize OpenHands 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.
 
-## Adding Repositories
+## Repository Access
+
+### Adding Repository Access
 
 You can grant OpenHands specific repository access:
-1. Under the `Select a GitHub project` dropdown, select `Add more repositories...`.
+1. Click 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
@@ -34,6 +36,10 @@ 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`.
 
-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.
+### 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.

docs/modules/usage/configuration-options.md

@@ -197,21 +197,6 @@ 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`
@@ -296,23 +281,6 @@ 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`

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

@@ -31,17 +31,11 @@ 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 variables using `-e` in the
+When running OpenHands, set the following environment variable 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

@@ -10,6 +10,9 @@ 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:
@@ -56,11 +59,12 @@ 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.
 
-## 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
 
-To use the All Hands Runtime, set the following environment variables when
+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
 starting OpenHands:
 
 ```bash
@@ -117,3 +121,66 @@ 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.

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](TBD)).
+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)).
 
 The evaluation consists of three steps:
 

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -3,7 +3,9 @@ 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
@@ -91,12 +93,22 @@ 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.
@@ -108,9 +120,18 @@ 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 (
@@ -124,7 +145,7 @@ def process_instance(
     config = get_config(metadata, instance)
     instance_id = instance.instance_id
     model_patch = instance['model_patch']
-    test_spec: TestSpec = instance['test_spec']
+    test_spec = instance['test_spec']
     logger.info(f'Starting evaluation for instance {instance_id}.')
 
     if 'test_result' not in instance.keys():
@@ -196,7 +217,9 @@ 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}] {APPLY_PATCH_FAIL}:\n{apply_patch_output}')
+            logger.info(
+                f'[{instance_id}] {conditional_imports.APPLY_PATCH_FAIL}:\n{apply_patch_output}'
+            )
             instance['test_result']['report']['failed_apply_patch'] = True
 
             return EvalOutput(
@@ -205,7 +228,9 @@ def process_instance(
                 metadata=metadata,
             )
         elif 'APPLY_PATCH_PASS' in apply_patch_output:
-            logger.info(f'[{instance_id}] {APPLY_PATCH_PASS}:\n{apply_patch_output}')
+            logger.info(
+                f'[{instance_id}] {conditional_imports.APPLY_PATCH_PASS}:\n{apply_patch_output}'
+            )
 
             # Run eval script in background and save output to log file
             log_file = '/tmp/eval_output.log'
@@ -271,7 +296,7 @@ def process_instance(
                         with open(test_output_path, 'w') as f:
                             f.write(test_output)
                         try:
-                            _report = get_eval_report(
+                            _report = conditional_imports.get_eval_report(
                                 test_spec=test_spec,
                                 prediction={
                                     'model_patch': model_patch,
@@ -345,7 +370,6 @@ if __name__ == '__main__':
         )
         from swegym.harness.test_spec import (
             SWEbenchInstance,
-            TestSpec,
             make_test_spec,
         )
         from swegym.harness.utils import load_swebench_dataset
@@ -357,7 +381,6 @@ if __name__ == '__main__':
         )
         from swebench.harness.test_spec.test_spec import (
             SWEbenchInstance,
-            TestSpec,
             make_test_spec,
         )
         from swebench.harness.utils import load_swebench_dataset
@@ -445,7 +468,15 @@ if __name__ == '__main__':
     # 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')
+        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,
+        ),
     )
 
     run_evaluation(

evaluation/benchmarks/swe_bench/run_infer.py

@@ -121,24 +121,26 @@ You SHOULD NEVER attempt to browse the web.
 
 
 # TODO: migrate all swe-bench docker to ghcr.io/openhands
-DOCKER_IMAGE_PREFIX = os.environ.get('EVAL_DOCKER_IMAGE_PREFIX', 'docker.io/xingyaoww/')
-logger.info(f'Using docker image prefix: {DOCKER_IMAGE_PREFIX}')
+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}')
 
 
 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(

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

@@ -4,8 +4,10 @@ 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");
@@ -26,6 +28,7 @@ describe("PaymentForm", () => {
       GITHUB_CLIENT_ID: "123",
       POSTHOG_CLIENT_KEY: "456",
     });
+    billingSettingsSpy.mockReturnValue(true);
   });
 
   afterEach(() => {

frontend/__tests__/hooks/use-terminal.test.tsx

@@ -72,8 +72,10 @@ describe("useTerminal", () => {
       wrapper: Wrapper,
     });
 
-    expect(mockTerminal.writeln).toHaveBeenNthCalledWith(1, "echo hello");
-    expect(mockTerminal.writeln).toHaveBeenNthCalledWith(2, "hello");
+    // Input commands should be displayed
+    expect(mockTerminal.writeln).toHaveBeenCalledWith("echo hello");
+    // Output commands should be displayed
+    expect(mockTerminal.writeln).toHaveBeenCalledWith("hello");
   });
 
   it("should hide secrets in the terminal", () => {
@@ -97,13 +99,31 @@ describe("useTerminal", () => {
       },
     );
 
-    // BUG: `vi.clearAllMocks()` does not clear the number of calls
-    // therefore, we need to assume the order of the calls based
-    // on the test order
-    expect(mockTerminal.writeln).toHaveBeenNthCalledWith(
-      3,
+    // Input command should be displayed with secrets masked
+    expect(mockTerminal.writeln).toHaveBeenCalledWith(
       `export GITHUB_TOKEN=${"*".repeat(10)},${"*".repeat(10)},${"*".repeat(10)}`,
     );
-    expect(mockTerminal.writeln).toHaveBeenNthCalledWith(4, "*".repeat(10));
+    
+    // Output command should be displayed with secrets masked
+    expect(mockTerminal.writeln).toHaveBeenCalledWith("*".repeat(10));
+  });
+  
+  it("should prevent duplicate command display", () => {
+    const inputCommand = "ls -la";
+    const commands: Command[] = [
+      { content: inputCommand, type: "input" },
+      { content: `${inputCommand}\nfile1.txt\nfile2.txt`, type: "output" },
+    ];
+
+    render(<TestTerminalComponent commands={commands} secrets={[]} />, {
+      wrapper: Wrapper,
+    });
+
+    // Input command should be displayed
+    expect(mockTerminal.writeln).toHaveBeenCalledWith(inputCommand);
+    
+    // Output should not be displayed since it starts with the input command
+    // This prevents the duplicate display of the command
+    expect(mockTerminal.writeln).not.toHaveBeenCalledWith(`${inputCommand}\nfile1.txt\nfile2.txt`);
   });
 });

frontend/__tests__/routes/home.test.tsx

@@ -26,33 +26,32 @@ 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 getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-
-  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={["/"]} />);
   });
@@ -79,57 +78,82 @@ describe("Home Screen", () => {
     const settingsScreen = await screen.findByTestId("settings-screen");
     expect(settingsScreen).toBeInTheDocument();
   });
+});
 
-  describe("Settings 404", () => {
-    it("should open the settings modal if GET /settings fails with a 404", async () => {
-      const error = createAxiosNotFoundErrorObject();
-      getSettingsSpy.mockRejectedValue(error);
+describe("Settings 404", () => {
+  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
 
-      renderWithProviders(<RouterStub initialEntries={["/"]} />);
+  it("should open the settings modal if GET /settings fails with a 404", async () => {
+    const error = createAxiosNotFoundErrorObject();
+    getSettingsSpy.mockRejectedValue(error);
 
-      const settingsModal = await screen.findByTestId("ai-config-modal");
-      expect(settingsModal).toBeInTheDocument();
-    });
+    renderWithProviders(<RouterStub initialEntries={["/"]} />);
 
-    it("should navigate to the settings screen when clicking the advanced settings button", async () => {
-      const error = createAxiosNotFoundErrorObject();
-      getSettingsSpy.mockRejectedValue(error);
+    const settingsModal = await screen.findByTestId("ai-config-modal");
+    expect(settingsModal).toBeInTheDocument();
+  });
 
-      const user = userEvent.setup();
-      renderWithProviders(<RouterStub initialEntries={["/"]} />);
+  it("should navigate to the settings screen when clicking the advanced settings button", async () => {
+    const error = createAxiosNotFoundErrorObject();
+    getSettingsSpy.mockRejectedValue(error);
 
-      const settingsScreen = screen.queryByTestId("settings-screen");
-      expect(settingsScreen).not.toBeInTheDocument();
+    const user = userEvent.setup();
+    renderWithProviders(<RouterStub initialEntries={["/"]} />);
 
-      const settingsModal = await screen.findByTestId("ai-config-modal");
-      expect(settingsModal).toBeInTheDocument();
+    const settingsScreen = screen.queryByTestId("settings-screen");
+    expect(settingsScreen).not.toBeInTheDocument();
 
-      const advancedSettingsButton = await screen.findByTestId(
-        "advanced-settings-link",
-      );
-      await user.click(advancedSettingsButton);
+    const settingsModal = await screen.findByTestId("ai-config-modal");
+    expect(settingsModal).toBeInTheDocument();
 
-      const settingsScreenAfter = await screen.findByTestId("settings-screen");
-      expect(settingsScreenAfter).toBeInTheDocument();
+    const advancedSettingsButton = await screen.findByTestId(
+      "advanced-settings-link",
+    );
+    await user.click(advancedSettingsButton);
 
-      const settingsModalAfter = screen.queryByTestId("ai-config-modal");
-      expect(settingsModalAfter).not.toBeInTheDocument();
-    });
+    const settingsScreenAfter = await screen.findByTestId("settings-screen");
+    expect(settingsScreenAfter).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);
+    const settingsModalAfter = screen.queryByTestId("ai-config-modal");
+    expect(settingsModalAfter).not.toBeInTheDocument();
+  });
 
-      renderWithProviders(<RouterStub initialEntries={["/"]} />);
+  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);
 
-      // small hack to wait for the modal to not appear
-      await expect(
-        screen.findByTestId("ai-config-modal", {}, { timeout: 1000 }),
-      ).rejects.toThrow();
-    });
+    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",
+    });
+    vi.spyOn(FeatureFlags, "BILLING_SETTINGS").mockReturnValue(true);
+    const error = createAxiosNotFoundErrorObject();
+    getSettingsSpy.mockRejectedValue(error);
+
+    renderWithProviders(<RouterStub initialEntries={["/"]} />);
+
+    const setupPaymentModal = await screen.findByTestId("proceed-to-stripe-button");
+    expect(setupPaymentModal).toBeInTheDocument();
   });
 });

frontend/__tests__/routes/settings.test.tsx

@@ -721,7 +721,7 @@ describe("Settings Screen", () => {
       expect(saveSettingsSpy).toHaveBeenCalledWith(
         expect.objectContaining({
           llm_api_key: "", // empty because it's not set previously
-          github_token: undefined,
+          provider_tokens: undefined,
           language: "no",
         }),
       );
@@ -758,7 +758,7 @@ describe("Settings Screen", () => {
 
       expect(saveSettingsSpy).toHaveBeenCalledWith(
         expect.objectContaining({
-          github_token: undefined,
+          provider_tokens: undefined,
           llm_api_key: "", // empty because it's not set previously
           llm_model: "openai/gpt-4o",
         }),
@@ -801,7 +801,7 @@ describe("Settings Screen", () => {
 
       expect(saveSettingsSpy).toHaveBeenCalledWith({
         ...mockCopy,
-        github_token: undefined, // not set
+        provider_tokens: undefined, // not set
         llm_api_key: "", // reset as well
       });
       expect(screen.queryByTestId("reset-modal")).not.toBeInTheDocument();

frontend/__tests__/services/actions.test.ts

@@ -1,7 +1,9 @@
 import { describe, it, expect, vi, beforeEach } from "vitest";
-import { handleStatusMessage } from "#/services/actions";
+import { handleStatusMessage, handleActionMessage } 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", () => ({
@@ -56,4 +58,89 @@ 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/public/mockServiceWorker.js

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

frontend/src/api/open-hands.ts

@@ -281,6 +281,13 @@ 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

@@ -48,6 +48,7 @@ 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/payment/setup-payment-modal.tsx

@@ -0,0 +1,48 @@
+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

@@ -61,7 +61,7 @@ export function Sidebar() {
       displayErrorToast(
         "Something went wrong while fetching settings. Please reload the page.",
       );
-    } else if (settingsError?.status === 404) {
+    } else if (config?.APP_MODE === "oss" && settingsError?.status === 404) {
       setSettingsModalIsOpen(true);
     }
   }, [

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,
-    github_token: settings.github_token,
+    provider_tokens: settings.provider_tokens,
     unset_github_token: settings.unset_github_token,
     enable_default_condenser: settings.ENABLE_DEFAULT_CONDENSER,
     enable_sound_notifications: settings.ENABLE_SOUND_NOTIFICATIONS,

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

@@ -11,4 +11,6 @@ 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

@@ -14,5 +14,7 @@ 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

@@ -50,6 +50,8 @@ 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

@@ -1,6 +1,7 @@
 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();
@@ -8,6 +9,6 @@ export const useBalance = () => {
   return useQuery({
     queryKey: ["user", "balance"],
     queryFn: OpenHands.getBalance,
-    enabled: config?.APP_MODE === "saas",
+    enabled: config?.APP_MODE === "saas" && BILLING_SETTINGS(),
   });
 };

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

@@ -5,4 +5,6 @@ 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

@@ -18,6 +18,8 @@ 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

@@ -19,6 +19,8 @@ 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

@@ -15,6 +15,7 @@ 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

@@ -23,5 +23,7 @@ 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

@@ -7,5 +7,7 @@ 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

@@ -21,6 +21,8 @@ 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,
   };
 };
 
@@ -34,6 +36,8 @@ 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

@@ -7,4 +7,6 @@ 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

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

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

@@ -15,6 +15,8 @@ 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

@@ -13,6 +13,8 @@ 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/hooks/use-terminal.ts

@@ -86,6 +86,8 @@ export const useTerminal = ({
 
   const handleEnter = (command: string) => {
     terminal.current?.write("\r\n");
+    // Send the command to the backend but don't echo it back in the terminal
+    // The backend will include the command in its response
     send(getTerminalCommand(command));
   };
 
@@ -131,10 +133,26 @@ export const useTerminal = ({
           content = content.replaceAll(secret, "*".repeat(10));
         });
 
-        terminal.current?.writeln(
-          parseTerminalOutput(content.replaceAll("\n", "\r\n").trim()),
-        );
+        // Check if this is an output that starts with the previous input command
+        // This happens when the backend echoes back the command in the output
+        let shouldDisplayContent = true;
+        if (type === "output" && i > 0 && commands[i - 1].type === "input") {
+          const prevInputCommand = commands[i - 1].content.trim();
+          // If the output starts with the input command, remove it to avoid duplication
+          if (content.trim().startsWith(prevInputCommand)) {
+            // Skip displaying this part as it's a duplicate of the user's input
+            // that's already shown in the terminal
+            shouldDisplayContent = false;
+          }
+        }
 
+        if (shouldDisplayContent) {
+          terminal.current?.writeln(
+            parseTerminalOutput(content.replaceAll("\n", "\r\n").trim()),
+          );
+        }
+
+        // Add a new prompt after the output
         if (type === "output") {
           terminal.current.write(`\n$ `);
         }

frontend/src/i18n/declaration.ts

@@ -312,4 +312,9 @@ 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

@@ -4647,5 +4647,80 @@
         "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/mocks/billing-handlers.ts

@@ -1,8 +1,4 @@
 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 () => {
@@ -10,27 +6,17 @@ export const STRIPE_BILLING_HANDLERS = [
     return HttpResponse.json({ credits: "100" });
   }),
 
-  http.post("/api/billing/create-checkout-session", async ({ request }) => {
+  http.post("/api/billing/create-checkout-session", async () => {
     await delay();
-    const body = await request.json();
+    return HttpResponse.json({
+      redirect_url: "https://stripe.com/some-checkout",
+    });
+  }),
 
-    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 });
+  http.post("/api/billing/create-customer-setup-session", async () => {
+    await delay();
+    return HttpResponse.json({
+      redirect_url: "https://stripe.com/some-customer-setup",
+    });
   }),
 ];

frontend/src/mocks/handlers.ts

@@ -22,12 +22,13 @@ 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;
+  settings: ApiSettings | PostApiSettings | null;
 } = {
-  settings: MOCK_DEFAULT_USER_SETTINGS,
+  settings: null,
 };
 
 const conversations: Conversation[] = [
@@ -174,22 +175,24 @@ 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: ApiSettings = {
-      ...MOCK_USER_PREFERENCES.settings,
-      language: "no",
-    };
-    // @ts-expect-error - mock types
-    if (settings.github_token) settings.github_token_is_set = true;
+    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;
 
     return HttpResponse.json(settings);
   }),
@@ -201,17 +204,19 @@ export const handlers = [
       if (typeof body === "object") {
         newSettings = { ...body };
         if (newSettings.unset_github_token) {
-          newSettings.github_token = undefined;
+          newSettings.provider_tokens = { github: "", gitlab: "" };
           newSettings.github_token_is_set = false;
           delete newSettings.unset_github_token;
         }
       }
 
-      MOCK_USER_PREFERENCES.settings = {
+      const fullSettings = {
+        ...MOCK_DEFAULT_USER_SETTINGS,
         ...MOCK_USER_PREFERENCES.settings,
         ...newSettings,
       };
 
+      MOCK_USER_PREFERENCES.settings = fullSettings;
       return HttpResponse.json(null, { status: 200 });
     }
 

frontend/src/query-client-config.ts

@@ -32,10 +32,4 @@ export const queryClientConfig: QueryClientConfig = {
       }
     },
   }),
-  defaultOptions: {
-    queries: {
-      staleTime: 1000 * 60 * 5, // 5 minutes
-      gcTime: 1000 * 60 * 15, // 15 minutes
-    },
-  },
 };

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

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

@@ -1,5 +1,13 @@
 import React from "react";
-import { useRouteError, isRouteErrorResponse, Outlet } from "react-router";
+import {
+  useRouteError,
+  isRouteErrorResponse,
+  Outlet,
+  useNavigate,
+  useLocation,
+  useSearchParams,
+} from "react-router";
+import { useTranslation } from "react-i18next";
 import i18n from "#/i18n";
 import { useGitHubAuthUrl } from "#/hooks/use-github-auth-url";
 import { useIsAuthed } from "#/hooks/query/use-is-authed";
@@ -10,6 +18,10 @@ 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();
@@ -44,11 +56,14 @@ 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 [consentFormIsOpen, setConsentFormIsOpen] = React.useState(false);
+  const { t } = useTranslation();
 
   const config = useConfig();
   const {
@@ -62,6 +77,8 @@ 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);
@@ -84,6 +101,17 @@ 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";
@@ -116,6 +144,10 @@ export default function MainApp() {
           }}
         />
       )}
+
+      {BILLING_SETTINGS() &&
+        config.data?.APP_MODE === "saas" &&
+        settings?.IS_NEW_USER && <SetupPaymentModal />}
     </div>
   );
 }

frontend/src/routes/account-settings.tsx

@@ -61,7 +61,10 @@ function AccountSettings() {
     if (isSuccess) {
       return (
         isCustomModel(resources.models, settings.LLM_MODEL) ||
-        hasAdvancedSettingsSet(settings)
+        hasAdvancedSettingsSet({
+          ...settings,
+          PROVIDER_TOKENS: settings.PROVIDER_TOKENS || {},
+        })
       );
     }
 
@@ -128,37 +131,42 @@ function AccountSettings() {
       : llmBaseUrl;
     const finalLlmApiKey = shouldHandleSpecialSaasCase ? undefined : llmApiKey;
 
-    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: 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,
+    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");
       },
-      {
-        onSuccess: () => {
-          handleCaptureConsent(userConsentsToAnalytics);
-          displaySuccessToast("Settings saved");
-          setLlmConfigMode(isAdvancedSettingsSet ? "advanced" : "basic");
-        },
-        onError: (error) => {
-          const errorMessage = retrieveAxiosErrorMessage(error);
-          displayErrorToast(errorMessage);
-        },
+      onError: (error) => {
+        const errorMessage = retrieveAxiosErrorMessage(error);
+        displayErrorToast(errorMessage);
       },
-    );
+    });
   };
 
   const handleReset = () => {

frontend/src/services/actions.ts

@@ -62,13 +62,12 @@ const messageActions = {
     let successPrediction = "";
     if (message.args.task_completed === "partial") {
       successPrediction =
-        "The agent thinks that the task was **completed partially**.";
+        "I believe that the task was **completed partially**.";
     } else if (message.args.task_completed === "false") {
-      successPrediction =
-        "The agent thinks that the task was **not completed**.";
+      successPrediction = "I believe that the task was **not completed**.";
     } else if (message.args.task_completed === "true") {
       successPrediction =
-        "The agent thinks that the task was **completed successfully**.";
+        "I believe 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

@@ -15,6 +15,11 @@ 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

@@ -21,7 +21,6 @@ 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

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

frontend/src/utils/settings-utils.ts

@@ -59,6 +59,18 @@ 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,
@@ -68,5 +80,6 @@ export const extractSettings = (formData: FormData): Partial<Settings> => {
     CONFIRMATION_MODE,
     SECURITY_ANALYZER,
     ENABLE_DEFAULT_CONDENSER,
+    PROVIDER_TOKENS: providerTokens,
   };
 };

frontend/tailwind.config.js

@@ -17,45 +17,7 @@ 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
-      },
-    },
-    animation: {
-      enter: "toastIn 400ms cubic-bezier(0.21, 1.02, 0.73, 1)",
-      leave: "toastOut 100ms ease-in forwards",
-    },
-    keyframes: {
-      toastIn: {
-        "0%": {
-          opacity: "0",
-          transform: "translateY(-100%) scale(0.8)",
-        },
-        "80%": {
-          opacity: "1",
-          transform: "translateY(0) scale(1.02)",
-        },
-        "100%": {
-          opacity: "1",
-          transform: "translateY(0) scale(1)",
-        },
-      },
-      toastOut: {
-        "0%": {
-          opacity: "1",
-          transform: "translateY(0) scale(1)",
-        },
-        "100%": {
-          opacity: "0",
-          transform: "translateY(-100%) scale(0.9)",
-        },
-      },
-      colors: {
-        primary: "#C9B974", // nice yellow
-        base: "#171717", // dark background (neutral-900)
-        "base-secondary": "#262626", // lighter background (neutral-800); also used for tooltips
-        danger: "#E76A5E",
-        success: "#A5E75E",
-        tertiary: "#454545", // gray, used for inputs
-        "tertiary-light": "#B7BDC2", // lighter gray, used for borders and placeholder text
+        "content-2": "#F9FBFE",
       },
     },
   },

microagents/knowledge/github.md

@@ -14,6 +14,8 @@ 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

@@ -0,0 +1,83 @@
+---
+ 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

@@ -1,9 +1,5 @@
 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()
 
 
@@ -14,26 +10,13 @@ from openhands.agenthub import (  # noqa: E402
     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/micro/README.md

@@ -1,17 +0,0 @@
-## Introduction
-
-This package contains definitions of micro-agents. A micro-agent is defined
-in the following structure:
-
-```
-[AgentName]
-├── agent.yaml
-└── prompt.md
-```
-
-Note that `prompt.md` could use jinja2 template syntax. During runtime, `prompt.md`
-is loaded and rendered, and used together with `agent.yaml` to initialize a
-micro-agent.
-
-Micro-agents can be used independently. You can also use `ManagerAgent` which knows
-how to coordinate the agents and collaboratively finish a task.

openhands/agenthub/micro/_instructions/actions/browse.md

@@ -1,2 +0,0 @@
-* `browse` - opens a web page. Arguments:
-  * `url` - the URL to open

openhands/agenthub/micro/_instructions/actions/delegate.md

@@ -1,3 +0,0 @@
-* `delegate` - send a task to another agent from the list provided. Arguments:
-  * `agent` - the agent to which the task is delegated. MUST match a name in the list of agents provided.
-  * `inputs` - a dictionary of input parameters to the agent, as specified in the list

openhands/agenthub/micro/_instructions/actions/finish.md

@@ -1,2 +0,0 @@
-* `finish` - if you're absolutely certain that you've completed your task, use the finish action to stop working. Arguments:
-  * `outputs` - a dictionary representing the outputs of your task, if any

openhands/agenthub/micro/_instructions/actions/message.md

@@ -1,3 +0,0 @@
-* `message` - make a plan, set a goal, record your thoughts, or ask for more input from the user. Arguments:
-  * `content` - the thought to record
-  * `wait_for_response` - set to `true` to wait for the user to respond before proceeding

openhands/agenthub/micro/_instructions/actions/read.md

@@ -1,2 +0,0 @@
-* `read` - reads the content of a file. Arguments:
-  * `path` - the path of the file to read

openhands/agenthub/micro/_instructions/actions/reject.md

@@ -1,2 +0,0 @@
-* `reject` - reject the task. Arguments:
-  * `outputs` - a dictionary with only a `reason` attribute

openhands/agenthub/micro/_instructions/actions/run.md

@@ -1,2 +0,0 @@
-* `run` - runs a command on the command line in a Linux shell. Arguments:
-  * `command` - the command to run

openhands/agenthub/micro/_instructions/actions/write.md

@@ -1,3 +0,0 @@
-* `write` - writes the content to a file. Arguments:
-  * `path` - the path of the file to write
-  * `content` - the content to write to the file

openhands/agenthub/micro/_instructions/format/action.md

@@ -1,5 +0,0 @@
-Your response MUST be in JSON format. It must be an object, and it must contain two fields:
-* `action`, which is one of the actions specified here
-* `args`, which is a map of key-value pairs, specifying the arguments for that action
-
-You MUST NOT include any other text besides the JSON response

openhands/agenthub/micro/_instructions/history_truncated.md

@@ -1,4 +0,0 @@
-Here is a recent history of actions you've taken in service of this plan,
-as well as observations you've made. This only includes the MOST RECENT
-actions and observations--more may have happened before that.
-They are time-ordered, with your most recent action at the bottom.

openhands/agenthub/micro/agent.py

@@ -1,88 +0,0 @@
-from jinja2 import BaseLoader, Environment
-
-from openhands.agenthub.micro.instructions import instructions
-from openhands.agenthub.micro.registry import all_microagents
-from openhands.controller.agent import Agent
-from openhands.controller.state.state import State
-from openhands.core.config import AgentConfig
-from openhands.core.message import ImageContent, Message, TextContent
-from openhands.events.action import Action
-from openhands.events.event import Event
-from openhands.events.serialization.action import action_from_dict
-from openhands.events.serialization.event import event_to_memory
-from openhands.io import json
-from openhands.llm.llm import LLM
-
-
-def parse_response(orig_response: str) -> Action:
-    # attempt to load the JSON dict from the response
-    action_dict = json.loads(orig_response)
-
-    # load the action from the dict
-    return action_from_dict(action_dict)
-
-
-def to_json(obj: object, **kwargs: dict) -> str:
-    """Serialize an object to str format"""
-    return json.dumps(obj, **kwargs)
-
-
-class MicroAgent(Agent):
-    VERSION = '1.0'
-    prompt = ''
-    agent_definition: dict = {}
-
-    def history_to_json(
-        self, history: list[Event], max_events: int = 20, **kwargs: dict
-    ) -> str:
-        """
-        Serialize and simplify history to str format
-        """
-        processed_history = []
-        event_count = 0
-
-        for event in reversed(history):
-            if event_count >= max_events:
-                break
-            processed_history.append(
-                event_to_memory(event, self.llm.config.max_message_chars)
-            )
-            event_count += 1
-
-        # history is in reverse order, let's fix it
-        processed_history.reverse()
-
-        # everything starts with a message
-        # the first message is already in the prompt as the task
-        # TODO: so we don't need to include it in the history
-
-        return json.dumps(processed_history, **kwargs)
-
-    def __init__(self, llm: LLM, config: AgentConfig):
-        super().__init__(llm, config)
-        if 'name' not in self.agent_definition:
-            raise ValueError('Agent definition must contain a name')
-        self.prompt_template = Environment(loader=BaseLoader()).from_string(self.prompt)
-        self.delegates = all_microagents.copy()
-        del self.delegates[self.agent_definition['name']]
-
-    def step(self, state: State) -> Action:
-        last_user_message, last_image_urls = state.get_current_user_intent()
-        prompt = self.prompt_template.render(
-            state=state,
-            instructions=instructions,
-            to_json=to_json,
-            history_to_json=self.history_to_json,
-            delegates=self.delegates,
-            latest_user_message=last_user_message,
-        )
-        content: list[TextContent | ImageContent] = [TextContent(text=prompt)]
-        if self.llm.vision_is_active() and last_image_urls:
-            content.append(ImageContent(image_urls=last_image_urls))
-        message = Message(role='user', content=content)
-        resp = self.llm.completion(
-            messages=self.llm.format_messages_for_llm(message),
-        )
-        action_resp = resp['choices'][0]['message']['content']
-        action = parse_response(action_resp)
-        return action

openhands/agenthub/micro/coder/agent.yaml

@@ -1,6 +0,0 @@
-name: CoderAgent
-description: Given a particular task, and a detailed description of the codebase, accomplishes the task
-inputs:
-  task: string
-  summary: string
-outputs: {}

openhands/agenthub/micro/coder/prompt.md

@@ -1,27 +0,0 @@
-# Task
-You are a software engineer. You've inherited an existing codebase, which you
-need to modify to complete this task:
-
-{{ state.inputs.task }}
-
-{% if state.inputs.summary %}
-Here's a summary of the codebase, as it relates to this task:
-
-{{ state.inputs.summary }}
-{% endif %}
-
-## Available Actions
-{{ instructions.actions.run }}
-{{ instructions.actions.write }}
-{{ instructions.actions.read }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-Do NOT finish until you have completed the tasks.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}

openhands/agenthub/micro/commit_writer/README.md

@@ -1,25 +0,0 @@
-## Introduction
-
-CommitWriterAgent can help write git commit message. Example:
-
-```bash
-WORKSPACE_MOUNT_PATH="`PWD`" \
-  poetry run python openhands/core/main.py -t "dummy task" -c CommitWriterAgent -d ./
-```
-
-This agent is special in the sense that it doesn't need a task. Once called,
-it attempts to read all diff in the git staging area and write a good commit
-message.
-
-## Future work
-
-### Feedback loop
-
-The commit message could be (optionally) shown to the customer or
-other agents, so that CommitWriterAgent could gather feedback to further
-improve the commit message.
-
-### Task rejection
-
-When the agent cannot compile a commit message (e.g. not git repository), it
-should reject the task with an explanation.

openhands/agenthub/micro/commit_writer/agent.yaml

@@ -1,6 +0,0 @@
-name: CommitWriterAgent
-description: "Write a git commit message for files in the git staging area"
-inputs: {}
-outputs:
-  answer: string
-  reason: string

openhands/agenthub/micro/commit_writer/prompt.md

@@ -1,33 +0,0 @@
-# Task
-You are a responsible software engineer and always write good commit messages.
-
-Please analyze the diff in the staging area, understand the context and content
-of the updates from the diff only. Identify key elements like:
-- Which files are affected?
-- What types of changes were made (e.g., new features, bug fixes, refactoring, documentation, testing)?
-
-Then you should generate a commit message that succinctly summarizes the staged
-changes. The commit message should include:
-- A summary line that clearly states the purpose of the changes.
-- Optionally, a detailed description if the changes are complex or need further explanation.
-
-You should first use `git status` to check whether it's a valid git repo and there
-is diff in the staging area. If not, please call the `reject` action.
-
-If it is a valid git repo and there is diff in the staging area, you should find
-the diff using `git diff --cached`, compile a commit message, and call the `finish`
-action with `outputs.answer` set to the answer.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-If the last item in the history is an error, you should try to fix it.
-
-## Available Actions
-{{ instructions.actions.run }}
-{{ instructions.actions.reject }}
-{{ instructions.actions.finish }}
-
-## Format
-{{ instructions.format.action }}

openhands/agenthub/micro/instructions.py

@@ -1,22 +0,0 @@
-import os
-
-instructions: dict = {}
-
-base_dir = os.path.dirname(os.path.abspath(__file__)) + '/_instructions'
-for root, dirs, files in os.walk(base_dir):
-    if len(files) == 0:
-        continue
-    if root == base_dir:
-        obj = instructions
-    else:
-        rel_base = os.path.relpath(root, base_dir)
-        keys = rel_base.split('/')
-        obj = instructions
-        for key in keys:
-            if key not in obj:
-                obj[key] = {}
-            obj = obj[key]
-    for file in files:
-        without_ext = os.path.splitext(file)[0]
-        with open(os.path.join(root, file), 'r') as f:
-            obj[without_ext] = f.read()

openhands/agenthub/micro/manager/agent.yaml

@@ -1,8 +0,0 @@
-name: ManagerAgent
-description: Delegates tasks to microagents based on their area of expertise
-generates: Action
-inputs:
-  task: string
-outputs:
-  summary: string # if finished
-  reason: string # if rejected

openhands/agenthub/micro/manager/prompt.md

@@ -1,42 +0,0 @@
-# Task
-You are in charge of accomplishing the following task:
-{% set goal = latest_user_message if latest_user_message is not none else state.inputs.task %}
-{{ goal }}
-
-In order to accomplish this goal, you must delegate tasks to one or more agents, who
-can do the actual work. A description of each agent is provided below. You MUST
-select one of the delegates below to move towards accomplishing the task, and you MUST
-provide the correct inputs for the delegate you select.
-
-Note: the delegated agent either returns "finish" or "reject".
-- If the action is "finish", but the full task is not done yet, you should
-continue to delegate to one of the agents below to until the full task is finished.
-- If the action is "reject", it means the delegated agent is not capable of the
-task you send to. You should revisit the input you send to the delegate, and consider
-whether any other delegate would be able to solve the task. If you cannot find
-a proper delegate agent, or the delegate attempts keep failing, call the `reject`
-action. In `reason` attribute, make sure you include your attempts (e.g. what agent
-you have delegated to, and why they failed).
-
-## Agents
-{% for name, details in delegates.items() %}
-### {{ name }}
-{{ details.description }}
-#### Inputs
-{{ to_json(details.inputs) }}
-{% endfor %}
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-If the last item in the history is an error, you should try to fix it. If you
-cannot fix it, call the `reject` action.
-
-## Available Actions
-{{ instructions.actions.delegate }}
-{{ instructions.actions.finish }}
-{{ instructions.actions.reject }}
-
-## Format
-{{ instructions.format.action }}

openhands/agenthub/micro/math_agent/agent.yaml

@@ -1,24 +0,0 @@
-name: MathAgent
-description: "Solves simple and complex math problems using python"
-container: python:3.12.3-bookworm
-inputs:
-  task: string
-outputs:
-  answer: string
-examples:
-  - inputs:
-      task: "What is 2 + 2?"
-    outputs:
-      answer: "4"
-  - inputs:
-      task: "What is the area of a circle with radius 7.324 inches?"
-    output:
-      answer: "168.518 square inches"
-  - inputs:
-      task: "What day of the week is 2099-01-01?"
-    outputs:
-      answer: "Saturday"
-  - inputs:
-      task: "What is the integral of sin(x^2) evaluated from -1 to 1?"
-    outputs:
-      answer: "0.603848"

openhands/agenthub/micro/math_agent/prompt.md

@@ -1,23 +0,0 @@
-# Task
-You are a brilliant mathematician and programmer. You've been given the following problem to solve:
-
-`{{ state.inputs.task }}`
-
-Please write a python script that solves this problem, and prints the answer to stdout.
-ONLY print the answer to stdout, nothing else.
-You should then run the python script with `python3`,
-and call the `finish` action with `outputs.answer` set to the answer.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-If the last item in the history is an error, you should try to fix it.
-
-## Available Actions
-{{ instructions.actions.write }}
-{{ instructions.actions.run }}
-{{ instructions.actions.finish }}
-
-## Format
-{{ instructions.format.action }}

openhands/agenthub/micro/postgres_agent/agent.yaml

@@ -1,5 +0,0 @@
-name: PostgresAgent
-description: Writes and maintains PostgreSQL migrations
-inputs:
-  task: string
-outputs: {}

openhands/agenthub/micro/postgres_agent/prompt.md

@@ -1,24 +0,0 @@
-# Task
-You are a database engineer. You are working on an existing Postgres project, and have been given
-the following task:
-
-{{ state.inputs.task }}
-
-You must:
-* Investigate the existing migrations to understand the current schema
-* Write a new migration to accomplish the task above
-* Test that the migrations work properly
-
-## Actions
-You may take any of the following actions:
-{{ instructions.actions.message }}
-{{ instructions.actions.read }}
-{{ instructions.actions.write }}
-{{ instructions.actions.run }}
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}

openhands/agenthub/micro/registry.py

@@ -1,27 +0,0 @@
-import os
-
-import yaml
-
-all_microagents = {}
-
-# Get the list of directories and sort them to preserve determinism
-dirs = sorted(os.listdir(os.path.dirname(__file__)))
-
-for dir in dirs:
-    base = os.path.dirname(__file__) + '/' + dir
-    if os.path.isfile(base):
-        continue
-    if dir.startswith('_'):
-        continue
-    promptFile = base + '/prompt.md'
-    agentFile = base + '/agent.yaml'
-    if not os.path.isfile(promptFile) or not os.path.isfile(agentFile):
-        raise Exception(f'Missing prompt or agent file in {base}. Please create them.')
-    with open(promptFile, 'r') as f:
-        prompt = f.read()
-    with open(agentFile, 'r') as f:
-        agent = yaml.safe_load(f)
-    if 'name' not in agent:
-        raise Exception(f'Missing name in {agentFile}')
-    agent['prompt'] = prompt
-    all_microagents[agent['name']] = agent

openhands/agenthub/micro/repo_explorer/agent.yaml

@@ -1,5 +0,0 @@
-name: RepoExplorerAgent
-description: Generates a detailed summary of an existing codebase
-inputs: {}
-outputs:
-  summary: string

openhands/agenthub/micro/repo_explorer/prompt.md

@@ -1,26 +0,0 @@
-# Task
-You are a software engineer. You've inherited an existing codebase, which you're
-learning about for the first time. Your goal is to produce a detailed summary
-of the codebase, including:
-* The overall purpose of the project
-* The directory structure
-* The main components of the codebase
-* How the components fit together
-
-## Available Actions
-{{ instructions.actions.run }}
-{{ instructions.actions.read }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-You should ONLY `run` commands that have no side-effects, like `ls` and `grep`.
-
-Do NOT finish until you have a complete understanding of the codebase.
-When you're done, put your summary into the output of the `finish` action.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}

openhands/agenthub/micro/study_repo_for_task/agent.yaml

@@ -1,6 +0,0 @@
-name: StudyRepoForTaskAgent
-description: Given a particular task, finds and describes all relevant parts of the codebase
-inputs:
-  task: string
-outputs:
-  summary: string

openhands/agenthub/micro/study_repo_for_task/prompt.md

@@ -1,62 +0,0 @@
-# Task
-You are a software architect. Your team has inherited an existing codebase, and
-need to finish a project:
-
-{{ state.inputs.task }}
-
-As an architect, you need to study the codebase to find all the information that
-might be helpful for your software engineering team.
-
-## Available Actions
-{{ instructions.actions.run }}
-{{ instructions.actions.read }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-You must ONLY `run` commands that have no side-effects, like `ls` and `grep`. You
-MUST NOT modify or write to any file.
-
-Do NOT finish until you have a complete understanding of which parts of the
-codebase are relevant to the project, including particular files, functions, and classes.
-When you're done, put your summary in `outputs.summary` in the `finish` action.
-Remember, your task is to explore and study the current repository, not actually
-implement the solution. If the codebase is empty, you should call the `finish` action.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}
-
-## Examples
-
-Here is an example of how you can interact with the environment for task solving:
-
---- START OF EXAMPLE ---
-
-USER: Can you create a list of numbers from 1 to 10, and create a web page to display them at port 5000?
-
-ASSISTANT:
-{
-  "action": "run",
-  "args": {
-    "command": "ls"
-  }
-}
-
-USER:
-OBSERVATION:
-[]
-
-ASSISTANT:
-{
-  "action": "finish",
-  "args": {
-    "outputs": {
-      "summary": "The codebase appears to be empty. Engineers should start everything from scratch."
-    }
-  }
-}
-
---- END OF EXAMPLE ---

openhands/agenthub/micro/typo_fixer_agent/agent.yaml

@@ -1,6 +0,0 @@
-name: TypoFixerAgent
-description: Fixes typos in files in the current working directory
-inputs:
-  task: string
-outputs:
-  summary: string

openhands/agenthub/micro/typo_fixer_agent/prompt.md

@@ -1,54 +0,0 @@
-# Task
-You are a proofreader tasked with fixing typos in the files in your current working directory.
-
-{% if state.inputs.task %}
-Specifically, your task is:
-{{ state.inputs.task }}
-{% endif %}
-
-To achieve this goal, you should:
-
-1. Scan the files for typos
-2. Overwrite the files with the typos fixed
-3. Provide a summary of the typos fixed
-
-## Available Actions
-{{ instructions.actions.read }}
-{{ instructions.actions.write }}
-{{ instructions.actions.run }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-To complete this task:
-1. Use the `read` action to read the contents of the files in your current working directory. Make sure to provide the file path in the format `'./file_name.ext'`.
-2. Use the `message` action to analyze the contents and identify typos.
-3. Use the `write` action to create new versions of the files with the typos fixed.
-  - Overwrite the original files with the corrected content. Make sure to provide the file path in the format `'./file_name.ext'`.
-4. Use the `message` action to generate a summary of the typos fixed, including the original and fixed versions of each typo, and the file(s) they were found in.
-5. Use the `finish` action to return the summary in the `outputs.summary` field.
-
-Do NOT finish until you have fixed all the typos and generated a summary.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=10) }}
-
-## Format
-{{ instructions.format.action }}
-
-For example, if you want to use the read action to read the contents of a file named example.txt, your response should look like this:
-{
-  "action": "read",
-  "args": {
-    "path": "./example.txt"
-  }
-}
-
-Similarly, if you want to use the write action to write content to a file named output.txt, your response should look like this:
-{
-  "action": "write",
-  "args": {
-    "path": "./output.txt",
-    "content": "This is the content to be written to the file."
-  }
-}

openhands/agenthub/micro/verifier/agent.yaml

@@ -1,7 +0,0 @@
-name: VerifierAgent
-description: Given a particular task, verifies that the task has been completed
-inputs:
-  task: string
-outputs:
-  completed: boolean
-  summary: string

openhands/agenthub/micro/verifier/prompt.md

@@ -1,28 +0,0 @@
-# Task
-You are a quality assurance engineer. Another engineer has made changes to the
-codebase which are supposed to solve this task:
-
-{{ state.inputs.task }}
-
-Note the changes might have already been applied in-line. You should focus on
-validating if the task is solved, nothing else.
-
-## Available Actions
-{{ instructions.actions.run }}
-{{ instructions.actions.read }}
-{{ instructions.actions.message }}
-{{ instructions.actions.finish }}
-
-You must ONLY `run` commands that have no side-effects, like `ls`, `grep`, and test scripts.
-
-Do NOT finish until you know whether the task is complete and correct.
-When you're done, add a `completed` boolean to the `outputs` of the `finish` action.
-If `completed` is `false`, you MUST also provide a `summary` in the `outputs` of the `finish` action
-explaining what the problem is.
-
-## History
-{{ instructions.history_truncated }}
-{{ history_to_json(state.history, max_events=20) }}
-
-## Format
-{{ instructions.format.action }}

openhands/controller/agent_controller.py

@@ -53,6 +53,7 @@ from openhands.events.observation import (
 )
 from openhands.events.serialization.event import event_to_trajectory, truncate_content
 from openhands.llm.llm import LLM
+from openhands.llm.metrics import Metrics, TokenUsage
 
 # note: RESUME is only available on web GUI
 TRAFFIC_CONTROL_REMINDER = (
@@ -733,6 +734,10 @@ class AgentController:
                 == ActionConfirmationStatus.AWAITING_CONFIRMATION
             ):
                 await self.set_agent_state_to(AgentState.AWAITING_USER_CONFIRMATION)
+
+            # Create and log metrics for frontend display
+            self._prepare_metrics_for_frontend(action)
+
             self.event_stream.add_event(action, action._source)  # type: ignore [attr-defined]
 
         await self.update_state_after_step()
@@ -1086,6 +1091,44 @@ class AgentController:
 
         return self._stuck_detector.is_stuck(self.headless_mode)
 
+    def _prepare_metrics_for_frontend(self, action: Action) -> None:
+        """Create a minimal metrics object for frontend display and log it.
+
+        To avoid performance issues with long conversations, we only keep:
+        - accumulated_cost: The current total cost
+        - latest token_usage: Token statistics from the most recent API call
+
+        Args:
+            action: The action to attach metrics to
+        """
+        metrics = Metrics(model_name=self.agent.llm.metrics.model_name)
+        metrics.accumulated_cost = self.agent.llm.metrics.accumulated_cost
+        if self.agent.llm.metrics.token_usages:
+            latest_usage = self.agent.llm.metrics.token_usages[-1]
+            metrics.add_token_usage(
+                prompt_tokens=latest_usage.prompt_tokens,
+                completion_tokens=latest_usage.completion_tokens,
+                cache_read_tokens=latest_usage.cache_read_tokens,
+                cache_write_tokens=latest_usage.cache_write_tokens,
+                response_id=latest_usage.response_id,
+            )
+        action.llm_metrics = metrics
+
+        # Log the metrics information for frontend display
+        log_usage: TokenUsage | None = (
+            metrics.token_usages[-1] if metrics.token_usages else None
+        )
+        self.log(
+            'debug',
+            f'Action metrics - accumulated_cost: {metrics.accumulated_cost}, '
+            f'tokens (prompt/completion/cache_read/cache_write): '
+            f'{log_usage.prompt_tokens if log_usage else 0}/'
+            f'{log_usage.completion_tokens if log_usage else 0}/'
+            f'{log_usage.cache_read_tokens if log_usage else 0}/'
+            f'{log_usage.cache_write_tokens if log_usage else 0}',
+            extra={'msg_type': 'METRICS'},
+        )
+
     def __repr__(self):
         return (
             f'AgentController(id={getattr(self, "id", "<uninitialized>")}, '

openhands/controller/state/state.py

@@ -14,6 +14,7 @@ from openhands.events.action.agent import AgentFinishAction
 from openhands.events.event import Event, EventSource
 from openhands.llm.metrics import Metrics
 from openhands.storage.files import FileStore
+from openhands.storage.locations import get_conversation_agent_state_filename
 
 
 class TrafficControlState(str, Enum):
@@ -106,7 +107,7 @@ class State:
         logger.debug(f'Saving state to session {sid}:{self.agent_state}')
         encoded = base64.b64encode(pickled).decode('utf-8')
         try:
-            file_store.write(f'sessions/{sid}/agent_state.pkl', encoded)
+            file_store.write(get_conversation_agent_state_filename(sid), encoded)
         except Exception as e:
             logger.error(f'Failed to save state to session: {e}')
             raise e
@@ -114,7 +115,7 @@ class State:
     @staticmethod
     def restore_from_session(sid: str, file_store: FileStore) -> 'State':
         try:
-            encoded = file_store.read(f'sessions/{sid}/agent_state.pkl')
+            encoded = file_store.read(get_conversation_agent_state_filename(sid))
             pickled = base64.b64decode(encoded)
             state = pickle.loads(pickled)
         except Exception as e: