Fix frontend tests for GitHub token documentation changes

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: openhands <openhands@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:

Development.md

@@ -100,7 +100,7 @@ poetry run pytest ./tests/unit/test_*.py
 To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker container image by
 setting the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
 
-Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.27-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.28-nikolaik`
 
 ## Develop inside Docker container
 

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:

README.md

@@ -12,7 +12,7 @@
   <a href="https://codecov.io/github/All-Hands-AI/OpenHands?branch=main"><img alt="CodeCov" src="https://img.shields.io/codecov/c/github/All-Hands-AI/OpenHands?style=for-the-badge&color=blue"></a>
   <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/github/license/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="MIT License"></a>
   <br/>
-  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2ypg5jweb-d~6hObZDbXi_HEL8PDrbHg"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
+  <a href="https://join.slack.com/t/openhands-ai/shared_invite/zt-2ngejmfw6-9gW4APWOC9XUp1n~SiQ6iw"><img src="https://img.shields.io/badge/Slack-Join%20Us-red?logo=slack&logoColor=white&style=for-the-badge" alt="Join our Slack community"></a>
   <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community"></a>
   <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="Credits"></a>
   <br/>
@@ -43,17 +43,17 @@ See the [Running OpenHands](https://docs.all-hands.dev/modules/usage/installatio
 system requirements and more information.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.27
+    docker.all-hands.dev/all-hands-ai/openhands:0.28
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
@@ -96,7 +96,7 @@ troubleshooting resources, and advanced configuration options.
 OpenHands is a community-driven project, and we welcome contributions from everyone. We do most of our communication
 through Slack, so this is the best place to start, but we also are happy to have you contact us on Discord or Github:
 
-- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-2ypg5jweb-d~6hObZDbXi_HEL8PDrbHg) - Here we talk about research, architecture, and future development.
+- [Join our Slack workspace](https://join.slack.com/t/openhands-ai/shared_invite/zt-2ngejmfw6-9gW4APWOC9XUp1n~SiQ6iw) - Here we talk about research, architecture, and future development.
 - [Join our Discord server](https://discord.gg/ESHStjSjD4) - This is a community-run server for general discussion, questions, and feedback.
 - [Read or post Github Issues](https://github.com/All-Hands-AI/OpenHands/issues) - Check out the issues we're working on, or add your own ideas.
 

config.template.toml

@@ -132,15 +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
 

containers/dev/compose.yml

@@ -11,7 +11,7 @@ services:
       - BACKEND_HOST=${BACKEND_HOST:-"0.0.0.0"}
       - SANDBOX_API_HOSTNAME=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.27-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.28-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docker-compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik}
       #- SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234} # enable this only if you want a specific non-root sandbox user but you will have to manually adjust permissions of openhands-state for this user
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

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

@@ -52,7 +52,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -61,7 +61,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.28 \
     python -m openhands.core.cli
 ```
 

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

@@ -46,7 +46,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -56,6 +56,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.28 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

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

@@ -13,16 +13,16 @@
 La façon la plus simple d'exécuter OpenHands est avec Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.27
+    docker.all-hands.dev/all-hands-ai/openhands:0.28
 ```
 
 Vous pouvez également exécuter OpenHands en mode [headless scriptable](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), en tant que [CLI interactive](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), ou en utilisant l'[Action GitHub OpenHands](https://docs.all-hands.dev/modules/usage/how-to/github-action).

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

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

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

@@ -13,7 +13,7 @@ C'est le Runtime par défaut qui est utilisé lorsque vous démarrez OpenHands.
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

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

@@ -50,7 +50,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -59,7 +59,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.28 \
     python -m openhands.core.cli
 ```
 

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

@@ -47,7 +47,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -57,6 +57,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.28 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

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

@@ -11,16 +11,16 @@
 在 Docker 中运行 OpenHands 是最简单的方式。
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.27
+    docker.all-hands.dev/all-hands-ai/openhands:0.28
 ```
 
 你也可以在可脚本化的[无头模式](https://docs.all-hands.dev/modules/usage/how-to/headless-mode)下运行 OpenHands，作为[交互式 CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode)，或使用 [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action)。

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

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

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

@@ -11,7 +11,7 @@
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

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`
@@ -387,7 +355,7 @@ To use these with the docker command, pass in `-e SANDBOX_<option>`. Example: `-
 
 - `runtime_binding_address`
   - Type: `str`
-  - Default: `127.0.0.1`
+  - Default: `0.0.0.0`
   - Description: The binding address for the runtime ports.  It specifies which network interface on the host machine Docker should bind the runtime ports to.
 
 ### Linting and Plugins

docs/modules/usage/feedback.md

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

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

@@ -35,7 +35,7 @@ To run OpenHands in CLI mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -45,7 +45,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.28 \
     python -m openhands.core.cli
 ```
 

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/how-to/headless-mode.md

@@ -32,7 +32,7 @@ To run OpenHands in Headless mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -43,7 +43,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.28 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/modules/usage/installation.mdx

@@ -58,17 +58,17 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.27
+    docker.all-hands.dev/all-hands-ai/openhands:0.28
 ```
 
 You'll find OpenHands running at http://localhost:3000!
@@ -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

@@ -10,13 +10,16 @@ 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:
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```
@@ -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.

docs/package-lock.json

@@ -24,7 +24,7 @@
         "@docusaurus/module-type-aliases": "^3.5.1",
         "@docusaurus/tsconfig": "^3.7.0",
         "@docusaurus/types": "^3.5.1",
-        "typescript": "~5.7.3"
+        "typescript": "~5.8.2"
       },
       "engines": {
         "node": ">=18.0"
@@ -17638,9 +17638,9 @@
       }
     },
     "node_modules/typescript": {
-      "version": "5.7.3",
-      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.7.3.tgz",
-      "integrity": "sha512-84MVSjMEHP+FQRPy3pX9sTVV/INIex71s9TL2Gm5FG/WG1SqXeKyZ0k7/blY/4FdOzI12CBy1vGc4og/eus0fw==",
+      "version": "5.8.2",
+      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.8.2.tgz",
+      "integrity": "sha512-aJn6wq13/afZp/jT9QZmwEjDqqvSGp1VT5GVg+f/t6/oVyrgXM6BY1h9BRh/O5p3PlUPAe+WuiEZOmb/49RqoQ==",
       "license": "Apache-2.0",
       "bin": {
         "tsc": "bin/tsc",

docs/package.json

@@ -31,7 +31,7 @@
     "@docusaurus/module-type-aliases": "^3.5.1",
     "@docusaurus/tsconfig": "^3.7.0",
     "@docusaurus/types": "^3.5.1",
-    "typescript": "~5.7.3"
+    "typescript": "~5.8.2"
   },
   "browserslist": {
     "production": [

docs/src/components/CustomFooter.tsx

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

docs/src/components/HomepageHeader/HomepageHeader.tsx

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

evaluation/benchmarks/aider_bench/README.md

@@ -56,9 +56,10 @@ You can update the arguments in the script
 ./evaluation/benchmarks/aider_bench/scripts/run_infer.sh eval_gpt35_turbo HEAD CodeActAgent 100 1 "1,3,10"
 ```
 
-### Run Inference on `RemoteRuntime` (experimental)
+### Run Inference on `RemoteRuntime`
+
+This is in beta. 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!
 
-This is in limited beta. Contact Xingyao over slack if you want to try this out!
 
 ```bash
 ./evaluation/benchmarks/aider_bench/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [eval-num-workers] [eval_ids]

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:
 
@@ -23,10 +23,10 @@ Make sure your Docker daemon is running, and you have ample disk space (at least
 When the `run_infer.sh` script is started, it will automatically pull the `lite` split in Commit0. For example, for instance ID `commit-0/minitorch`, it will try to pull our pre-build docker image `wentingzhao/minitorch` from DockerHub. This image will be used create an OpenHands runtime image where the agent will operate on.
 
 ```bash
-./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh [repo_split] [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split]
+./evaluation/benchmarks/commit0/scripts/run_infer.sh [repo_split] [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split]
 
 # Example
-./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 16 100 8 wentingzhao/commit0_combined test
+./evaluation/benchmarks/commit0/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 16 100 8 wentingzhao/commit0_combined test
 ```
 
 where `model_config` is mandatory, and the rest are optional.
@@ -48,26 +48,25 @@ default, it is set to 1.
 - `dataset`, a huggingface dataset name. e.g. `wentingzhao/commit0_combined`, specifies which dataset to evaluate on.
 - `dataset_split`, split for the huggingface dataset. Notice only `test` is supported for Commit0.
 
-Note that the `USE_INSTANCE_IMAGE` environment variable is always set to `true` for Commit0.
-
 Let's say you'd like to run 10 instances using `llm.eval_sonnet` and CodeActAgent,
 
 then your command would be:
 
 ```bash
-./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 10 30 1 wentingzhao/commit0_combined test
+./evaluation/benchmarks/commit0/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 10 30 1 wentingzhao/commit0_combined test
 ```
 
-### Run Inference on `RemoteRuntime` (experimental)
+### Run Inference on `RemoteRuntime`
+
+This is in beta. 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!
 
-This is in limited beta. Contact Xingyao over slack if you want to try this out!
 
 ```bash
-./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh [repo_split] [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split]
+./evaluation/benchmarks/commit0/scripts/run_infer.sh [repo_split] [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split]
 
 # Example - This runs evaluation on CodeActAgent for 10 instances on "wentingzhao/commit0_combined"'s test set, with max 30 iteration per instances, with 1 number of workers running in parallel
 ALLHANDS_API_KEY="YOUR-API-KEY" RUNTIME=remote SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev" EVAL_DOCKER_IMAGE_PREFIX="docker.io/wentingzhao" \
-./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 10 30 1 wentingzhao/commit0_combined test
+./evaluation/benchmarks/commit0/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 10 30 1 wentingzhao/commit0_combined test
 ```
 
 To clean-up all existing runtime you've already started, run:

evaluation/benchmarks/commit0/run_infer.py

@@ -39,7 +39,6 @@ from openhands.utils.async_utils import call_async_from_sync
 from openhands.utils.shutdown_listener import sleep_if_should_continue
 
 USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
-USE_INSTANCE_IMAGE = os.environ.get('USE_INSTANCE_IMAGE', 'false').lower() == 'true'
 RUN_WITH_BROWSING = os.environ.get('RUN_WITH_BROWSING', 'false').lower() == 'true'
 
 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
@@ -105,7 +104,6 @@ def get_config(
     instance: pd.Series,
     metadata: EvalMetadata,
 ) -> AppConfig:
-    assert USE_INSTANCE_IMAGE
     repo_name = instance['repo'].split('/')[1]
     base_container_image = get_instance_docker_image(repo_name)
     logger.info(
@@ -303,16 +301,6 @@ def complete_runtime(
     pytest_exit_code = obs.content.strip()
     # logger.info(f'Pytest exit code: {pytest_exit_code}')
 
-    # Read the test report
-    action = CmdRunAction(command='cat report.json')
-    action.set_hard_timeout(600)
-    logger.info(action, extra={'msg_type': 'ACTION'})
-    obs = runtime.run_action(action)
-    # logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-    assert_and_raise(
-        isinstance(obs, CmdOutputObservation),
-        f'Failed to read test report: {str(obs)}',
-    )
     # Get test IDs from instance
     repo_name = instance['repo'].split('/')[1]
     repo_name = repo_name.replace('.', '-')
@@ -323,8 +311,20 @@ def complete_runtime(
     # logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     test_ids = obs.content.strip().split('\n')
 
+    # Read the test report
+    action = CmdRunAction(command='cat report.json')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    # logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        isinstance(obs, CmdOutputObservation),
+        f'Failed to read test report: {str(obs)}',
+    )
+    json_report = obs.content.strip()
+
     try:
-        report = json.loads(obs.content)
+        report = json.loads(json_report)
         tests = {x['nodeid']: x['call'] for x in report['tests'] if 'call' in x}
 
         # Calculate test statistics

evaluation/benchmarks/commit0/scripts/run_infer.sh

@@ -30,11 +30,6 @@ if [ -z "$MAX_ITER" ]; then
   MAX_ITER=100
 fi
 
-if [ -z "$USE_INSTANCE_IMAGE" ]; then
-  echo "USE_INSTANCE_IMAGE not specified, use default true"
-  USE_INSTANCE_IMAGE=true
-fi
-
 if [ -z "$RUN_WITH_BROWSING" ]; then
   echo "RUN_WITH_BROWSING not specified, use default false"
   RUN_WITH_BROWSING=false
@@ -56,8 +51,6 @@ if [ -z "$SPLIT" ]; then
   SPLIT="test"
 fi
 
-export USE_INSTANCE_IMAGE=$USE_INSTANCE_IMAGE
-echo "USE_INSTANCE_IMAGE: $USE_INSTANCE_IMAGE"
 export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
 echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
 
@@ -91,7 +84,7 @@ fi
 
 function run_eval() {
   local eval_note=$1
-  COMMAND="poetry run python evaluation/benchmarks/commit0_bench/run_infer.py \
+  COMMAND="poetry run python evaluation/benchmarks/commit0/run_infer.py \
     --agent-cls $AGENT \
     --llm-config $MODEL_CONFIG \
     --max-iterations $MAX_ITER \

evaluation/benchmarks/miniwob/README.md

@@ -19,9 +19,10 @@ Access with browser the above MiniWoB URLs and see if they load correctly.
 ./evaluation/benchmarks/miniwob/scripts/run_infer.sh llm.claude-35-sonnet-eval
 ```
 
-### Run Inference on `RemoteRuntime` (experimental)
+### Run Inference on `RemoteRuntime`
+
+This is in beta. 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!
 
-This is in limited beta. Contact Xingyao over slack if you want to try this out!
 
 ```bash
 ./evaluation/benchmarks/miniwob/scripts/run_infer.sh [model_config] [git-version] [agent] [note] [eval_limit] [num_workers]

evaluation/benchmarks/swe_bench/README.md

@@ -2,11 +2,13 @@
 
 This folder contains the evaluation harness that we built on top of the original [SWE-Bench benchmark](https://www.swebench.com/) ([paper](https://arxiv.org/abs/2310.06770)).
 
+**UPDATE (2/18/2025): We now support running SWE-Gym using the same evaluation harness here. For more details, checkout [this README](./SWE-Gym.md).
+
 **UPDATE (7/1/2024): We now support the official SWE-Bench dockerized evaluation as announced [here](https://github.com/princeton-nlp/SWE-bench/blob/main/docs/20240627_docker/README.md).**
 
 The evaluation consists of three steps:
 
-1. Environment setup: [install python environment](../../README.md#development-environment), [configure LLM config](../../README.md#configure-openhands-and-your-llm), and [pull docker](#openhands-swe-bench-instance-level-docker-support).
+1. Environment setup: [install python environment](../../README.md#development-environment) and [configure LLM config](../../README.md#configure-openhands-and-your-llm).
 2. [Run inference](#run-inference-on-swe-bench-instances): Generate a edit patch for each Github issue
 3. [Evaluate patches using SWE-Bench docker](#evaluate-generated-patches)
 
@@ -14,22 +16,35 @@ The evaluation consists of three steps:
 
 Please follow instruction [here](../../README.md#setup) to setup your local development environment and LLM.
 
-## OpenHands SWE-Bench Instance-level Docker Support
+## Run Inference (Rollout) on SWE-Bench Instances: Generate Patch from Problem Statement
 
-OpenHands now support using the [official evaluation docker](https://github.com/princeton-nlp/SWE-bench/blob/main/docs/20240627_docker/README.md) for both **[inference](#run-inference-on-swe-bench-instances) and [evaluation](#evaluate-generated-patches)**.
-This is now the default behavior.
+> [!NOTE]
+> **Iterative Evaluation Protocol**
+>
+> We have an iterative approach for more stable and reproducible results:
+> - For each instance, we attempt to generate a solution up to 3 times
+> - Each attempt continues until either:
+>   1. The agent successfully produces a patch with `AgentFinishAction`, or
+>   2. The attempt reaches the maximum iteration limit
+> - If an attempt fails, we retry with a fresh attempt (up to the 3-attempt maximum)
+> - If your LLM config has temperature=0, we will automatically use temperature=0.1 for the 2nd and 3rd attempts
+>
+> To enable this iterative protocol, set `export ITERATIVE_EVAL_MODE=true`
 
-## Run Inference on SWE-Bench Instances
 
-Make sure your Docker daemon is running, and you have ample disk space (at least 200-500GB, depends on the SWE-Bench set you are running on) for the [instance-level docker image](#openhands-swe-bench-instance-level-docker-support).
+### Running Locally with Docker
 
-When the `run_infer.sh` script is started, it will automatically pull the relevant SWE-Bench images. For example, for instance ID `django_django-11011`, it will try to pull our pre-build docker image `sweb.eval.x86_64.django_s_django-11011` from DockerHub. This image will be used create an OpenHands runtime image where the agent will operate on.
+Make sure your Docker daemon is running, and you have ample disk space (at least 200-500GB, depends on the SWE-Bench set you are running on) for the instance-level docker image.
+
+When the `run_infer.sh` script is started, it will automatically pull the relevant SWE-Bench images.
+For example, for instance ID `django_django-11011`, it will try to pull our pre-build docker image `sweb.eval.x86_64.django_s_django-11011` from DockerHub.
+This image will be used create an OpenHands runtime image where the agent will operate on.
 
 ```bash
 ./evaluation/benchmarks/swe_bench/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split]
 
 # Example
-./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.eval_gpt4_1106_preview HEAD CodeActAgent 300 30 1 princeton-nlp/SWE-bench_Lite test
+./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.eval_gpt4_1106_preview HEAD CodeActAgent 500 100 1 princeton-nlp/SWE-bench_Verified test
 ```
 
 where `model_config` is mandatory, and the rest are optional.
@@ -44,17 +59,19 @@ to `CodeActAgent`.
 default, the script evaluates the entire SWE-bench_Lite test set (300 issues). Note:
 in order to use `eval_limit`, you must also set `agent`.
 - `max_iter`, e.g. `20`, is the maximum number of iterations for the agent to run. By
-default, it is set to 30.
+default, it is set to 60.
 - `num_workers`, e.g. `3`, is the number of parallel workers to run the evaluation. By
 default, it is set to 1.
-- `dataset`, a huggingface dataset name. e.g. `princeton-nlp/SWE-bench` or `princeton-nlp/SWE-bench_Lite`, specifies which dataset to evaluate on.
+- `dataset`, a huggingface dataset name. e.g. `princeton-nlp/SWE-bench`, `princeton-nlp/SWE-bench_Lite`, or `princeton-nlp/SWE-bench_Verified`, specifies which dataset to evaluate on.
 - `dataset_split`, split for the huggingface dataset. e.g., `test`, `dev`. Default to `test`.
 
-There are also two optional environment variables you can set.
+> [!CAUTION]
+> Setting `num_workers` larger than 1 is not officially tested, YMMV.
+
+There is also one optional environment variable you can set.
 
 ```bash
 export USE_HINT_TEXT=true # if you want to use hint text in the evaluation. Default to false. Ignore this if you are not sure.
-export USE_INSTANCE_IMAGE=true # if you want to use instance-level docker images. Default to true
 ```
 
 Let's say you'd like to run 10 instances using `llm.eval_gpt4_1106_preview` and CodeActAgent,
@@ -65,9 +82,11 @@ then your command would be:
 ./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.eval_gpt4_1106_preview HEAD CodeActAgent 10
 ```
 
-### Run Inference on `RemoteRuntime` (experimental)
+### Running in parallel with RemoteRuntime
 
-This is in limited beta. Contact Xingyao over slack if you want to try this out!
+OpenHands Remote Runtime is currently in beta (read [here](https://runtime.all-hands.dev/) for more details), it allows you to run rollout in parallel in the cloud, so you don't need a powerful machine to run evaluation.
+
+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!
 
 ```bash
 ./evaluation/benchmarks/swe_bench/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split]
@@ -100,41 +119,14 @@ After running the inference, you will obtain a `output.jsonl` (by default it wil
 
 ## Evaluate Generated Patches
 
-### Download Docker Images
-
-**(Recommended for reproducibility)** If you have extra local space (e.g., 200GB), you can try pull the [instance-level docker images](https://github.com/princeton-nlp/SWE-bench/blob/main/docs/20240627_docker/README.md#choosing-the-right-cache_level) we've prepared by running:
-
-```bash
-evaluation/benchmarks/swe_bench/scripts/docker/pull_all_eval_docker.sh instance
-```
-
-If you want to save disk space a bit (e.g., with ~50GB free disk space), while speeding up the image pre-build process, you can pull the environment-level docker images:
-
-```bash
-evaluation/benchmarks/swe_bench/scripts/docker/pull_all_eval_docker.sh env
-```
-
-If you want to evaluate on the full SWE-Bench test set:
-
-```bash
-evaluation/benchmarks/swe_bench/scripts/docker/pull_all_eval_docker.sh instance full
-```
-
-### Run evaluation
+### Run evaluation with official SWE-Bench harness (Recommend if you have local disk space)
 
 With `output.jsonl` file, you can run `eval_infer.sh` to evaluate generated patches, and produce a fine-grained report.
-
 **This evaluation is performed using the official dockerized evaluation announced [here](https://github.com/princeton-nlp/SWE-bench/blob/main/docs/20240627_docker/README.md).**
 
-> If you want to evaluate existing results, you should first run this to clone existing outputs
->
->```bash
->git clone https://huggingface.co/spaces/OpenHands/evaluation evaluation/evaluation_outputs
->```
+> [!NOTE]
+> This process will automatically download docker images from SWE-Bench official docker hub, please make sure you have enough disk space!
 
-NOTE, you should have already pulled the instance-level OR env-level docker images following [this section](#openhands-swe-bench-instance-level-docker-support).
-
-Then you can run the following:
 
 ```bash
 ./evaluation/benchmarks/swe_bench/scripts/eval_infer.sh $YOUR_OUTPUT_JSONL [instance_id] [dataset_name] [split]
@@ -163,9 +155,10 @@ The final results will be saved to `evaluation/evaluation_outputs/outputs/swe_be
 - `report.json`: a JSON file that contains keys like `"resolved_ids"` pointing to instance IDs that are resolved by the agent.
 - `logs/`: a directory of test logs
 
-### Run evaluation with `RemoteRuntime` (experimental)
+### Run evaluation with `RemoteRuntime`
 
-This is in limited beta. Contact Xingyao over slack if you want to try this out!
+OpenHands Remote Runtime is currently in beta (read [here](https://runtime.all-hands.dev/) for more details), it allows you to run rollout in parallel in the cloud, so you don't need a powerful machine to run evaluation.
+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!
 
 ```bash
 ./evaluation/benchmarks/swe_bench/scripts/eval_infer_remote.sh [output.jsonl filepath] [num_workers]
@@ -180,35 +173,3 @@ To clean-up all existing runtimes that you've already started, run:
 ```bash
 ALLHANDS_API_KEY="YOUR-API-KEY" ./evaluation/utils/scripts/cleanup_remote_runtime.sh
 ```
-
-## Visualize Results
-
-First you need to clone `https://huggingface.co/spaces/OpenHands/evaluation` and add your own running results from openhands into the `outputs` of the cloned repo.
-
-```bash
-git clone https://huggingface.co/spaces/OpenHands/evaluation
-```
-
-**(optional) setup streamlit environment with conda**:
-
-```bash
-cd evaluation
-conda create -n streamlit python=3.10
-conda activate streamlit
-pip install -r requirements.txt
-```
-
-**run the visualizer**:
-Then, in a separate Python environment with `streamlit` library, you can run the following:
-
-```bash
-# Make sure you are inside the cloned `evaluation` repo
-conda activate streamlit # if you follow the optional conda env setup above
-streamlit run app.py --server.port 8501 --server.address 0.0.0.0
-```
-
-Then you can access the SWE-Bench trajectory visualizer at `localhost:8501`.
-
-## Submit your evaluation results
-
-You can start your own fork of [our huggingface evaluation outputs](https://huggingface.co/spaces/OpenHands/evaluation) and submit a PR of your evaluation results following the guide [here](https://huggingface.co/docs/hub/en/repositories-pull-requests-discussions#pull-requests-and-discussions).

evaluation/benchmarks/swe_bench/SWE-Gym.md

@@ -0,0 +1,128 @@
+<h1 align="center"> Training Software Engineering Agents and Verifiers with SWE-Gym </h1>
+
+<p align="center">
+  <a href="https://www.jiayipan.com/" style="text-decoration: none;">Jiayi Pan<sup>*,1</sup></a>,
+  <a href="https://xwang.dev/" style="text-decoration: none;">Xingyao Wang<sup>*,2</sup></a>,
+  <a href="https://www.phontron.com/" style="text-decoration: none;">Graham Neubig<sup>3</sup></a>,
+  <a href="https://www.cs.toronto.edu/~ndjaitly/" style="text-decoration: none;">Navdeep Jaitly<sup>4</sup></a>,
+  <a href="https://blender.cs.illinois.edu/hengji.html" style="text-decoration: none;">Heng Ji<sup>2</sup></a>,
+  <a href="https://www.alanesuhr.com/" style="text-decoration: none;">Alane Suhr<sup>^,1</sup></a>,
+  <a href="https://dreasysnail.github.io/" style="text-decoration: none;">Yizhe Zhang<sup>^,4</sup></a>
+</p>
+
+<p align="center">
+  <sup>1</sup>UC Berkeley, <sup>2</sup>UIUC, <sup>3</sup>CMU, <sup>4</sup>Apple </br>
+  <sub><sup>*</sup>Equal contribution, <sup>^</sup>Equal supervision</sub>
+</p>
+
+<p align="center">
+<a href="https://arxiv.org/abs/2412.21139">📃 Paper</a>
+•
+<a href="https://huggingface.co/SWE-Gym" >🤗 Data & Models</a>
+</p>
+
+We present **SWE-Gym**, the first environment for training real-world software engineering agents.
+We use it to train strong LM agents that achieve state-of-the-art open results on SWE-Bench, with early, promising scaling characteristics as we increase training and inference-time compute.
+
+<p align="center">
+  <img src="https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/teaser.jpg?raw=true" width="100%" alt="teaser">
+</p>
+
+---
+# Run SWE-Gym with OpenHands
+
+The process of running SWE-Gym is very similar to how you'd run SWE-Bench evaluation.
+
+
+1. First, clone OpenHands repo `git clone https://github.com/All-Hands-AI/OpenHands.git`
+2. Then setup the repo following [Development.md](https://github.com/All-Hands-AI/OpenHands/blob/main/Development.md)
+3. Then you can simply serve your own model as an OpenAI compatible endpoint, put those info in config.toml. You can do this by following instruction [here](../../README.md#setup).
+4. And then simply do the following to sample for 16x parallelism:
+
+```bash
+export ALLHANDS_API_KEY=ah-yourkey  # You don't need to set this when running these in local docker container
+./evaluation/benchmarks/swe_bench/scripts/rollout_swegym.sh llm.mymodel-temp05 'train-t05' 16
+```
+
+NOTE: SWE-Gym sampling with parallelism is currently only tested with AllHands RemoteRuntime (limited beta). Fill [this form](https://docs.google.com/forms/d/e/1FAIpQLSckVz_JFwg2_mOxNZjCtr7aoBFI2Mwdan3f75J_TrdMS1JV2g/viewform) to apply for access.
+
+
+5. When `rollout_swegym.sh` finishes, you will get a file called `output.with_completions.jsonl.gz`. Then you can use [`./scripts/swegym/convert_data.ipynb`](./scripts/swegym/convert_data.ipynb) to convert them into SFT data format.
+
+---
+# More info about SWE-Gym
+
+Progress in agents for software engineering has been limited by the lack of training environments that both include rigorous verification for reinforcement learning and cover the expansive tasks encountered in real-world repository-level engineering.
+
+We introduce SWE-Gym: An Open Environment for Training Software Engineering Agents & Verifiers.
+Our baselines achieve new open SOTA - 32%/26% on SWE-Bench Verified/Lite, with promising scaling trends.
+
+![SWE-Gym Scaling](https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/scaling.jpg?raw=true)
+*SWE-Gym enables scalable improvements for software engineering agents at both training and inference time. Our current results is primarily bottlenecked by training and inference compute, rather than the size of our environment.*
+
+## SWE-Gym Environment
+
+We create SWE-Gym, the first environment for training SWE agents, with **2.4K real tasks from 11 Python repos** & a Lite split of 234 instances. SWE-Gym combines real-world Python tasks, repository context, executable environments, and test verification to train agents for solving software engineering problems.
+
+![SWE-Gym Repo Distribution](https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/swe-gym.jpg?raw=true)
+
+
+## SWE-Gym trains LMs as agents
+
+When fine-tuned on less than 500 agent-environment interaction trajectories sampled from it from GPT-4o and Claude 3.5 Sonnet, we achieve **+14%** absolute gains on SWE-Bench Verified with an 32B LM-powered OpenHands agent.
+
+![OpenHands Performance diff before and after training](https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/oh-agent.jpg?raw=true)
+
+
+## SWE-Gym enables self-improvement
+
+SWE-Gym is also effective across agent scaffolds. With rejection sampling fine-tuning and MoatlessTools scaffold, our 32B and 7B models achieve 20% and 10% respectively on SWE-Bench Lite through self-improvement.
+
+<p align="center">
+  <img src="https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/ml-agent.jpg?raw=true" width="80%" alt="Moatless self-improvement">
+</p>
+
+
+
+## SWE-Gym enables inference-time scaling
+
+SWE-Gym enables inference-time scaling through verifiers trained on agent trajectories.
+These verifiers identify most promising solutions via best-of-n selection, together with our learned agents, they achieve 32%/26% on SWE-Bench Verified/Lite, a new open SoTA.
+
+
+![Inference Time Scaling for Moatless Agent](https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/inference-ml.jpg?raw=true)
+*Inference Time Scaling for Moatless Agent*
+
+![Inference Time Scaling for OpenHands Agent](https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/inference-oh.jpg?raw=true)
+*Inference Time Scaling for OpenHands Agent*
+
+
+## Our baselines on SWE-Gym shows strong scaling trends
+
+Lastly, our ablations reveal strong scaling trends - performance is now bottlenecked by train and inference compute, rather than the size of our dataset. Pushing and improving these scaling trends further is an exciting direction for future work.
+
+![](https://github.com/SWE-Gym/SWE-Gym/blob/main/assets/images/scaling.jpg?raw=true)
+
+## Reproducing Results
+**The Dataset**
+
+To access SWE-Gym dataset, checkout our huggingface hub page [SWE-Gym](https://huggingface.co/SWE-Gym)
+
+The environment constants are currently saved at [SWE-Bench-Fork](https://github.com/SWE-Gym/SWE-Bench-Fork)
+
+We also have pre-built docker images for each instance under [xingyaoww/sweb.eval.x86_64](https://hub.docker.com/search?q=xingyaoww%2Fsweb.eval.x86_64.) prefix at docker hub.
+
+
+## 📚 Citation
+
+```bibtex
+@misc{pan2024trainingsoftwareengineeringagents,
+      title={Training Software Engineering Agents and Verifiers with SWE-Gym},
+      author={Jiayi Pan and Xingyao Wang and Graham Neubig and Navdeep Jaitly and Heng Ji and Alane Suhr and Yizhe Zhang},
+      year={2024},
+      eprint={2412.21139},
+      archivePrefix={arXiv},
+      primaryClass={cs.SE},
+      url={https://arxiv.org/abs/2412.21139},
+}
+```

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -1,22 +1,14 @@
+import copy
 import json
 import os
 import subprocess
 import tempfile
 import time
+from dataclasses import dataclass
 from functools import partial
+from typing import Callable
 
 import pandas as pd
-from swebench.harness.grading import get_eval_report
-from swebench.harness.run_evaluation import (
-    APPLY_PATCH_FAIL,
-    APPLY_PATCH_PASS,
-)
-from swebench.harness.test_spec.test_spec import (
-    SWEbenchInstance,
-    TestSpec,
-    make_test_spec,
-)
-from swebench.harness.utils import load_swebench_dataset
 from tqdm import tqdm
 
 from evaluation.benchmarks.swe_bench.resource.mapping import (
@@ -102,12 +94,22 @@ 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.
@@ -119,9 +121,18 @@ 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 (
@@ -135,7 +146,7 @@ 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():
@@ -165,6 +176,11 @@ def process_instance(
         logger.warning(
             f'This is the {runtime_failure_count + 1}th attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
         )
+    metadata = copy.deepcopy(metadata)
+    metadata.details['runtime_failure_count'] = runtime_failure_count
+    metadata.details['remote_runtime_resource_factor'] = (
+        config.sandbox.remote_runtime_resource_factor
+    )
 
     try:
         runtime = create_runtime(config)
@@ -207,7 +223,9 @@ 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(
@@ -216,7 +234,9 @@ 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'
@@ -282,14 +302,20 @@ def process_instance(
                         with open(test_output_path, 'w') as f:
                             f.write(test_output)
                         try:
-                            _report = get_eval_report(
+                            extra_kwargs = {}
+                            if 'SWE-Gym' in metadata.dataset:
+                                # SWE-Gym uses a different version of the package, hence a different eval report argument
+                                extra_kwargs['log_path'] = test_output_path
+                            else:
+                                extra_kwargs['test_log_path'] = test_output_path
+                            _report = conditional_imports.get_eval_report(
                                 test_spec=test_spec,
                                 prediction={
                                     'model_patch': model_patch,
                                     'instance_id': instance_id,
                                 },
-                                test_log_path=test_output_path,
                                 include_tests_status=True,
+                                **extra_kwargs,
                             )
                             report = _report[instance_id]
                             logger.info(
@@ -348,6 +374,29 @@ if __name__ == '__main__':
     )
     args, _ = parser.parse_known_args()
 
+    if 'SWE-Gym' in args.dataset:
+        from swegym.harness.grading import get_eval_report
+        from swegym.harness.run_evaluation import (
+            APPLY_PATCH_FAIL,
+            APPLY_PATCH_PASS,
+        )
+        from swegym.harness.test_spec import (
+            SWEbenchInstance,
+            make_test_spec,
+        )
+        from swegym.harness.utils import load_swebench_dataset
+    else:  # Newer version of SWE-Bench have different import paths
+        from swebench.harness.grading import get_eval_report
+        from swebench.harness.run_evaluation import (
+            APPLY_PATCH_FAIL,
+            APPLY_PATCH_PASS,
+        )
+        from swebench.harness.test_spec.test_spec import (
+            SWEbenchInstance,
+            make_test_spec,
+        )
+        from swebench.harness.utils import load_swebench_dataset
+
     # Load SWE-Bench dataset
     full_dataset: list[SWEbenchInstance] = load_swebench_dataset(
         args.dataset, args.split
@@ -426,12 +475,21 @@ if __name__ == '__main__':
             .decode('utf-8')
             .strip(),  # Current commit
             dataset=args.dataset,  # Dataset name from args
+            details={},
         )
 
     # The evaluation harness constrains the signature of `process_instance_func` but we need to
     # pass extra information. Build a new function object to avoid issues with multiprocessing.
     process_instance_func = partial(
-        process_instance, log_dir=output_file.replace('.jsonl', '.logs')
+        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/resource/mapping.py

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

evaluation/benchmarks/swe_bench/run_infer.py

@@ -1,4 +1,5 @@
 import asyncio
+import copy
 import json
 import os
 import tempfile
@@ -36,15 +37,15 @@ from openhands.core.config import (
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
+from openhands.critic import AgentFinishedCritic
 from openhands.events.action import CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation, ErrorObservation
-from openhands.events.serialization.event import event_to_dict
+from openhands.events.serialization.event import event_from_dict, event_to_dict
 from openhands.runtime.base import Runtime
 from openhands.utils.async_utils import call_async_from_sync
 from openhands.utils.shutdown_listener import sleep_if_should_continue
 
 USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
-USE_INSTANCE_IMAGE = os.environ.get('USE_INSTANCE_IMAGE', 'true').lower() == 'true'
 RUN_WITH_BROWSING = os.environ.get('RUN_WITH_BROWSING', 'false').lower() == 'true'
 
 
@@ -59,85 +60,110 @@ def _get_swebench_workspace_dir_name(instance: pd.Series) -> str:
 
 def get_instruction(instance: pd.Series, metadata: EvalMetadata):
     workspace_dir_name = _get_swebench_workspace_dir_name(instance)
-    # Instruction based on Anthropic's official trajectory
-    # https://github.com/eschluntz/swe-bench-experiments/tree/main/evaluation/verified/20241022_tools_claude-3-5-sonnet-updated/trajs
-    instruction = (
-        '<uploaded_files>\n'
-        f'/workspace/{workspace_dir_name}\n'
-        '</uploaded_files>\n'
-        f"I've uploaded a python code repository in the directory {workspace_dir_name}. Consider the following issue description:\n\n"
-        f'<issue_description>\n'
-        f'{instance.problem_statement}\n'
-        '</issue_description>\n\n'
-        'Can you help me implement the necessary changes to the repository so that the requirements specified in the <issue_description> are met?\n'
-        "I've already taken care of all changes to any of the test files described in the <issue_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!\n"
-        "Also the development Python environment is already set up for you (i.e., all dependencies already installed), so you don't need to install other packages.\n"
-        'Your task is to make the minimal changes to non-test files in the /workspace directory to ensure the <issue_description> is satisfied.\n'
-        'Follow these steps to resolve the issue:\n'
-        '1. As a first step, it might be a good idea to explore the repo to familiarize yourself with its structure.\n'
-        '2. Create a script to reproduce the error and execute it with `python <filename.py>` using the BashTool, to confirm the error\n'
-        '3. Edit the sourcecode of the repo to resolve the issue\n'
-        '4. Rerun your reproduce script and confirm that the error is fixed!\n'
-        '5. Think about edgecases, add comprehensive tests for them in your reproduce script, and run them to make sure your fix handles them as well\n'
-        f'6. Once you are done with the initial implementation, please carefully re-read the problem description and check the difference between the current code and the base commit {instance["base_commit"]}. Do you think that the issue has been completely and comprehensively solved? Write tests to check the correctness of the solution, specifically focusing on tests that may point out any remaining problems that are not yet solved. Run all of the tests in the repo and check if any of them fail, and if they do fix the code. Repeat this process of carefully reading the problem description and current implementation, testing, and fixing any problems until you are confident that the current implementation is correct. Find and run any tests in the repo that are related to:\n'
-        '   - The issue you are fixing\n'
-        '   - The files you modified\n'
-        '   - The functions you changed\n'
-        '   Make sure all these tests pass with your changes.\n'
-        "Your thinking should be thorough and so it's fine if it's very long.\n"
-    )
+    instruction = f"""
+<uploaded_files>
+/workspace/{workspace_dir_name}
+</uploaded_files>
+
+I've uploaded a python code repository in the directory {workspace_dir_name}. Consider the following issue description:
+
+<issue_description>
+{instance.problem_statement}
+</issue_description>
+
+Can you help me implement the necessary changes to the repository so that the requirements specified in the <issue_description> are met?
+I've already taken care of all changes to any of the test files described in the <issue_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!
+Also the development Python environment is already set up for you (i.e., all dependencies already installed), so you don't need to install other packages.
+Your task is to make the minimal changes to non-test files in the /workspace/{workspace_dir_name} directory to ensure the <issue_description> is satisfied.
+
+Follow these steps to resolve the issue:
+
+1. EXPLORATION: First, thoroughly explore the repository structure using tools like `find` and `grep`.
+   - Identify all files mentioned in the problem statement
+   - Locate where the issue occurs in the codebase
+   - Understand the surrounding context and dependencies
+   - Use `grep` to search for relevant functions, classes, or error messages
+
+2. ANALYSIS: Based on your exploration, think carefully about the problem and propose 2-5 possible approaches to fix the issue.
+   - Analyze the root cause of the problem
+   - Consider trade-offs between different solutions
+   - Select the most promising approach and explain your reasoning
+
+3. TEST CREATION: Before implementing any fix, create a script to reproduce and verify the issue.
+   - Look at existing test files in the repository to understand the test format/structure
+   - Create a minimal reproduction script that demonstrates the issue
+   - Run your script to confirm the error exists
+
+4. IMPLEMENTATION: Edit the source code to implement your chosen solution.
+   - Make minimal, focused changes to fix the issue
+
+5. VERIFICATION: Test your implementation thoroughly.
+   - Run your reproduction script to verify the fix works
+   - Add edge cases to your test script to ensure comprehensive coverage
+   - Run existing tests related to the modified code to ensure you haven't broken anything
+
+6. FINAL REVIEW: Carefully re-read the problem description and compare your changes with the base commit {instance["base_commit"]}.
+   - Ensure you've fully addressed all requirements
+   - Run any tests in the repository related to:
+     * The issue you are fixing
+     * The files you modified
+     * The functions you changed
+   - If any tests fail, revise your implementation until all tests pass
+
+Be thorough in your exploration, testing, and reasoning. It's fine if your thinking process is lengthy - quality and completeness are more important than brevity.
+"""
 
     if RUN_WITH_BROWSING:
-        instruction += (
-            '<IMPORTANT!>\n'
-            'You SHOULD NEVER attempt to browse the web. '
-            '</IMPORTANT!>\n'
-        )
+        instruction += """
+<IMPORTANT!>
+You SHOULD NEVER attempt to browse the web.
+</IMPORTANT!>
+"""
     return instruction
 
 
 # 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(
     instance: pd.Series,
     metadata: EvalMetadata,
 ) -> AppConfig:
-    SWE_BENCH_CONTAINER_IMAGE = 'ghcr.io/opendevin/eval-swe-bench:full-v1.2.1'
-    if USE_INSTANCE_IMAGE:
-        # We use a different instance image for the each instance of swe-bench eval
-        use_official_image = bool(
-            'verified' in metadata.dataset.lower() or 'lite' in metadata.dataset.lower()
-        )
-        base_container_image = get_instance_docker_image(
-            instance['instance_id'], use_official_image
-        )
-        logger.info(
-            f'Using instance container image: {base_container_image}. '
-            f'Please make sure this image exists. '
-            f'Submit an issue on https://github.com/All-Hands-AI/OpenHands if you run into any issues.'
-        )
-    else:
-        base_container_image = SWE_BENCH_CONTAINER_IMAGE
-        logger.info(f'Using swe-bench container image: {base_container_image}')
+    # We use a different instance image for the each instance of swe-bench eval
+    use_official_image = bool(
+        ('verified' in metadata.dataset.lower() or 'lite' in metadata.dataset.lower())
+        and 'swe-gym' not in metadata.dataset.lower()
+    )
+    base_container_image = get_instance_docker_image(
+        instance['instance_id'], use_official_image
+    )
+    logger.info(
+        f'Using instance container image: {base_container_image}. '
+        f'Please make sure this image exists. '
+        f'Submit an issue on https://github.com/All-Hands-AI/OpenHands if you run into any issues.'
+    )
 
     sandbox_config = get_default_sandbox_config_for_eval()
     sandbox_config.base_container_image = base_container_image
@@ -209,75 +235,65 @@ def initialize_runtime(
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     assert_and_raise(obs.exit_code == 0, f'Failed to export USER: {str(obs)}')
 
-    if USE_INSTANCE_IMAGE:
-        # inject the init script
-        script_dir = os.path.dirname(__file__)
+    # inject the init script
+    script_dir = os.path.dirname(__file__)
 
-        # inject the instance info
-        action = CmdRunAction(command='mkdir -p /swe_util/eval_data/instances')
-        action.set_hard_timeout(600)
-        logger.info(action, extra={'msg_type': 'ACTION'})
-        obs = runtime.run_action(action)
-        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-        assert_and_raise(
-            obs.exit_code == 0,
-            f'Failed to create /swe_util/eval_data/instances: {str(obs)}',
-        )
+    # inject the instance info
+    action = CmdRunAction(command='mkdir -p /swe_util/eval_data/instances')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0,
+        f'Failed to create /swe_util/eval_data/instances: {str(obs)}',
+    )
 
-        swe_instance_json_name = 'swe-bench-instance.json'
-        with tempfile.TemporaryDirectory() as temp_dir:
-            # Construct the full path for the desired file name within the temporary directory
-            temp_file_path = os.path.join(temp_dir, swe_instance_json_name)
-            # Write to the file with the desired name within the temporary directory
-            with open(temp_file_path, 'w') as f:
-                if not isinstance(instance, dict):
-                    json.dump([instance.to_dict()], f)
-                else:
-                    json.dump([instance], f)
+    swe_instance_json_name = 'swe-bench-instance.json'
+    with tempfile.TemporaryDirectory() as temp_dir:
+        # Construct the full path for the desired file name within the temporary directory
+        temp_file_path = os.path.join(temp_dir, swe_instance_json_name)
+        # Write to the file with the desired name within the temporary directory
+        with open(temp_file_path, 'w') as f:
+            if not isinstance(instance, dict):
+                json.dump([instance.to_dict()], f)
+            else:
+                json.dump([instance], f)
 
-            # Copy the file to the desired location
-            runtime.copy_to(temp_file_path, '/swe_util/eval_data/instances/')
+        # Copy the file to the desired location
+        runtime.copy_to(temp_file_path, '/swe_util/eval_data/instances/')
 
         # inject the instance swe entry
         runtime.copy_to(
             str(os.path.join(script_dir, 'scripts/setup/instance_swe_entry.sh')),
             '/swe_util/',
         )
-        action = CmdRunAction(command='cat ~/.bashrc')
-        action.set_hard_timeout(600)
-        logger.info(action, extra={'msg_type': 'ACTION'})
-        obs = runtime.run_action(action)
-        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-        assert_and_raise(obs.exit_code == 0, f'Failed to cat ~/.bashrc: {str(obs)}')
 
-        action = CmdRunAction(command='source ~/.bashrc')
-        action.set_hard_timeout(600)
-        logger.info(action, extra={'msg_type': 'ACTION'})
-        obs = runtime.run_action(action)
-        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-        if isinstance(obs, ErrorObservation):
-            logger.error(f'Failed to source ~/.bashrc: {str(obs)}')
-        assert_and_raise(obs.exit_code == 0, f'Failed to source ~/.bashrc: {str(obs)}')
+    action = CmdRunAction(command='cat ~/.bashrc')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(obs.exit_code == 0, f'Failed to cat ~/.bashrc: {str(obs)}')
 
-        action = CmdRunAction(command='source /swe_util/instance_swe_entry.sh')
-        action.set_hard_timeout(600)
-        logger.info(action, extra={'msg_type': 'ACTION'})
-        obs = runtime.run_action(action)
-        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-        assert_and_raise(
-            obs.exit_code == 0,
-            f'Failed to source /swe_util/instance_swe_entry.sh: {str(obs)}',
-        )
-    else:
-        action = CmdRunAction(command='source /swe_util/swe_entry.sh')
-        action.set_hard_timeout(1800)
-        logger.info(action, extra={'msg_type': 'ACTION'})
-        obs = runtime.run_action(action)
-        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
-        assert_and_raise(
-            obs.exit_code == 0,
-            f'Failed to source /swe_util/swe_entry.sh: {str(obs)}',
-        )
+    action = CmdRunAction(command='source ~/.bashrc')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    if isinstance(obs, ErrorObservation):
+        logger.error(f'Failed to source ~/.bashrc: {str(obs)}')
+    assert_and_raise(obs.exit_code == 0, f'Failed to source ~/.bashrc: {str(obs)}')
+
+    action = CmdRunAction(command='source /swe_util/instance_swe_entry.sh')
+    action.set_hard_timeout(600)
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+    assert_and_raise(
+        obs.exit_code == 0,
+        f'Failed to source /swe_util/instance_swe_entry.sh: {str(obs)}',
+    )
 
     action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
     action.set_hard_timeout(600)
@@ -464,6 +480,13 @@ def process_instance(
         logger.warning(
             f'This is the {runtime_failure_count + 1}th attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
         )
+
+    metadata = copy.deepcopy(metadata)
+    metadata.details['runtime_failure_count'] = runtime_failure_count
+    metadata.details['remote_runtime_resource_factor'] = (
+        config.sandbox.remote_runtime_resource_factor
+    )
+
     runtime = create_runtime(config)
     call_async_from_sync(runtime.connect)
 
@@ -572,6 +595,22 @@ if __name__ == '__main__':
     logger.info(
         f'Loaded dataset {args.dataset} with split {args.split}: {len(swe_bench_tests)} tasks'
     )
+    if 'SWE-Gym' in args.dataset:
+        with open(
+            os.path.join(
+                os.path.dirname(os.path.abspath(__file__)),
+                'split',
+                'swegym_verified_instances.json',
+            ),
+            'r',
+        ) as f:
+            swegym_verified_instances = json.load(f)
+            swe_bench_tests = swe_bench_tests[
+                swe_bench_tests['instance_id'].isin(swegym_verified_instances)
+            ]
+        logger.info(
+            f'{len(swe_bench_tests)} tasks left after filtering for SWE-Gym verified instances'
+        )
 
     llm_config = None
     if args.llm_config:
@@ -601,20 +640,132 @@ if __name__ == '__main__':
 
     output_file = os.path.join(metadata.eval_output_dir, 'output.jsonl')
     print(f'### OUTPUT FILE: {output_file} ###')
-    instances = prepare_dataset(swe_bench_tests, output_file, args.eval_n_limit)
 
-    if len(instances) > 0 and not isinstance(
-        instances['PASS_TO_PASS'][instances['PASS_TO_PASS'].index[0]], str
-    ):
-        for col in ['PASS_TO_PASS', 'FAIL_TO_PASS']:
-            instances[col] = instances[col].apply(lambda x: str(x))
-
-    run_evaluation(
-        instances,
-        metadata,
-        output_file,
-        args.eval_num_workers,
-        process_instance,
-        timeout_seconds=120 * 60,  # 2 hour PER instance should be more than enough
-        max_retries=5,
+    # Run evaluation in iterative mode:
+    # If a rollout fails to output AgentFinishAction, we will try again until it succeeds OR total 3 attempts have been made.
+    ITERATIVE_EVAL_MODE = (
+        os.environ.get('ITERATIVE_EVAL_MODE', 'false').lower() == 'true'
     )
+    ITERATIVE_EVAL_MODE_MAX_ATTEMPTS = int(
+        os.environ.get('ITERATIVE_EVAL_MODE_MAX_ATTEMPTS', '3')
+    )
+
+    if not ITERATIVE_EVAL_MODE:
+        # load the dataset
+        instances = prepare_dataset(swe_bench_tests, output_file, args.eval_n_limit)
+        if len(instances) > 0 and not isinstance(
+            instances['PASS_TO_PASS'][instances['PASS_TO_PASS'].index[0]], str
+        ):
+            for col in ['PASS_TO_PASS', 'FAIL_TO_PASS']:
+                instances[col] = instances[col].apply(lambda x: str(x))
+
+        run_evaluation(
+            instances,
+            metadata,
+            output_file,
+            args.eval_num_workers,
+            process_instance,
+            timeout_seconds=8
+            * 60
+            * 60,  # 8 hour PER instance should be more than enough
+            max_retries=5,
+        )
+    else:
+        critic = AgentFinishedCritic()
+
+        def get_cur_output_file_path(attempt: int) -> str:
+            return (
+                f'{output_file.removesuffix(".jsonl")}.critic_attempt_{attempt}.jsonl'
+            )
+
+        eval_ids = None
+        for attempt in range(1, ITERATIVE_EVAL_MODE_MAX_ATTEMPTS + 1):
+            cur_output_file = get_cur_output_file_path(attempt)
+            logger.info(
+                f'Running evaluation with critic {critic.__class__.__name__} for attempt {attempt} of {ITERATIVE_EVAL_MODE_MAX_ATTEMPTS}.'
+            )
+
+            # For deterministic eval, we set temperature to 0.1 for (>1) attempt
+            # so hopefully we get slightly different results
+            if attempt > 1 and metadata.llm_config.temperature == 0:
+                logger.info(
+                    f'Detected temperature is 0 for (>1) attempt {attempt}. Setting temperature to 0.1...'
+                )
+                metadata.llm_config.temperature = 0.1
+
+            # Load instances - at first attempt, we evaluate all instances
+            # On subsequent attempts, we only evaluate the instances that failed the previous attempt determined by critic
+            instances = prepare_dataset(
+                swe_bench_tests, cur_output_file, args.eval_n_limit, eval_ids=eval_ids
+            )
+            if len(instances) > 0 and not isinstance(
+                instances['PASS_TO_PASS'][instances['PASS_TO_PASS'].index[0]], str
+            ):
+                for col in ['PASS_TO_PASS', 'FAIL_TO_PASS']:
+                    instances[col] = instances[col].apply(lambda x: str(x))
+
+            # Run evaluation - but save them to cur_output_file
+            logger.info(
+                f'Evaluating {len(instances)} instances for attempt {attempt}...'
+            )
+            run_evaluation(
+                instances,
+                metadata,
+                cur_output_file,
+                args.eval_num_workers,
+                process_instance,
+                timeout_seconds=8
+                * 60
+                * 60,  # 8 hour PER instance should be more than enough
+                max_retries=5,
+            )
+
+            # When eval is done, we update eval_ids to the instances that failed the current attempt
+            instances_failed = []
+            logger.info(
+                f'Use critic {critic.__class__.__name__} to check {len(instances)} instances for attempt {attempt}...'
+            )
+            with open(cur_output_file, 'r') as f:
+                for line in f:
+                    instance = json.loads(line)
+                    history = [event_from_dict(event) for event in instance['history']]
+                    critic_result = critic.evaluate(history)
+                    if not critic_result.success:
+                        instances_failed.append(instance['instance_id'])
+            logger.info(
+                f'{len(instances_failed)} instances failed the current attempt {attempt}: {instances_failed}'
+            )
+            eval_ids = instances_failed
+
+            # If no instances failed, we break
+            if len(instances_failed) == 0:
+                break
+
+        # Then we should aggregate the results from all attempts into the original output file
+        # and remove the intermediate files
+        logger.info(
+            'Aggregating results from all attempts into the original output file...'
+        )
+        fout = open(output_file, 'w')
+        added_instance_ids = set()
+        for attempt in reversed(range(1, ITERATIVE_EVAL_MODE_MAX_ATTEMPTS + 1)):
+            cur_output_file = get_cur_output_file_path(attempt)
+            if not os.path.exists(cur_output_file):
+                logger.warning(
+                    f'Intermediate output file {cur_output_file} does not exist. Skipping...'
+                )
+                continue
+
+            with open(cur_output_file, 'r') as f:
+                for line in f:
+                    instance = json.loads(line)
+                    if instance['instance_id'] not in added_instance_ids:
+                        fout.write(line)
+                        added_instance_ids.add(instance['instance_id'])
+            logger.info(
+                f'Aggregated instances from {cur_output_file}. Total instances added so far: {len(added_instance_ids)}'
+            )
+        fout.close()
+        logger.info(
+            f'Done! Total {len(added_instance_ids)} instances added to {output_file}'
+        )

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

@@ -24,7 +24,7 @@ def load_completions(output_dir: str, instance_id: str):
     # create messages
     messages = result['messages']
     messages.append(result['response']['choices'][0]['message'])
-    tools = result['kwargs']['tools']
+    tools = result['kwargs'].get('tools', [])
     return {
         'messages': messages,
         'tools': tools,

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

@@ -75,7 +75,7 @@ def load_completions(instance_id: str):
     # create messages
     messages = result['messages']
     messages.append(result['response']['choices'][0]['message'])
-    tools = result['kwargs']['tools']
+    tools = result['kwargs'].get('tools', None)
     return {
         'messages': messages,
         'tools': tools,

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

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

evaluation/benchmarks/swe_bench/scripts/rollout_swegym.sh

@@ -0,0 +1,132 @@
+#!/bin/bash
+
+# NOTE: this script is for rolling out the SWE-Gym dataset for **TRAINING**
+# For more information, please refer to
+# 1. the Github Repo: https://github.com/SWE-Gym/SWE-Gym
+# 2. the paper: https://arxiv.org/abs/2412.21139
+
+MODEL=$1  # eg your llm config name in config.toml (eg: "llm.claude-3-5-sonnet-20241022-t05")
+EXP_NAME=$2 # "train-t05"
+N_WORKERS=${3:-64}
+N_RUNS=${4:-1}
+
+export EXP_NAME=$EXP_NAME
+# use 2x resources for rollout since some codebases are pretty resource-intensive
+export DEFAULT_RUNTIME_RESOURCE_FACTOR=2
+echo "MODEL: $MODEL"
+echo "EXP_NAME: $EXP_NAME"
+DATASET="SWE-Gym/SWE-Gym"  # change this to the "/SWE-Gym-Lite" if you want to rollout the lite subset
+SPLIT="train"
+
+if [ -z "$ALLHANDS_API_KEY" ]; then
+    echo "ALLHANDS_API_KEY is not set. Will rollout and evaluate locally using Docker. WARNING: A large value of N_WORKERS will result in a large number of Docker containers being spun up and may crash your machine."
+    export RUNTIME=docker
+else
+    echo "ALLHANDS_API_KEY is set. Continuing rollout and evaluation with remote runtime..."
+    export RUNTIME=remote
+    export SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev"
+    export EVAL_DOCKER_IMAGE_PREFIX="us-central1-docker.pkg.dev/evaluation-092424/swe-bench-images"
+fi
+
+EVAL_LIMIT=3000
+MAX_ITER=100
+
+
+# ===== Run inference =====
+source "evaluation/utils/version_control.sh"
+get_openhands_version
+
+echo "OPENHANDS_VERSION: $OPENHANDS_VERSION"
+echo "MODEL_CONFIG: $MODEL_CONFIG"
+echo "DATASET: $DATASET"
+echo "SPLIT: $SPLIT"
+
+# Default to NOT use Hint
+export USE_INSTANCE_IMAGE=true
+export USE_HINT_TEXT=false
+export RUN_WITH_BROWSING=false
+echo "USE_HINT_TEXT: $USE_HINT_TEXT"
+EVAL_NOTE="$OPENHANDS_VERSION-no-hint-$EXP_NAME"
+
+function run_eval() {
+  local eval_note=$1
+  COMMAND="poetry run python evaluation/benchmarks/swe_bench/run_infer.py \
+    --agent-cls CodeActAgent \
+    --llm-config $MODEL \
+    --max-iterations $MAX_ITER \
+    --eval-num-workers $N_WORKERS \
+    --eval-note $eval_note \
+    --dataset $DATASET \
+    --split $SPLIT"
+
+  if [ -n "$EVAL_LIMIT" ]; then
+    echo "EVAL_LIMIT: $EVAL_LIMIT"
+    COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
+  fi
+
+  # Run the command
+  eval $COMMAND
+}
+
+for run_idx in $(seq 1 $N_RUNS); do
+
+    while true; do
+        echo "### Running inference... ###"
+        unset SANDBOX_ENV_GITHUB_TOKEN # prevent the agent from using the github token to push
+        current_eval_note="$EVAL_NOTE-run_$run_idx"
+        echo "EVAL_NOTE: $current_eval_note"
+        INFER_OUTPUT=$(run_eval $current_eval_note)
+        INFER_STATUS=$?  # Capture the exit status of run_infer.sh
+        echo "INFER_STATUS: $INFER_STATUS"
+
+        echo "### Cleaning up remote runtime... ###"
+        ./evaluation/utils/scripts/cleanup_remote_runtime.sh
+
+        if [ $INFER_STATUS -eq 0 ]; then
+            echo "### Inference completed successfully. ###"
+            break
+        else
+            echo "### Inference failed with exit code $INFER_STATUS. Retrying... ###"
+        fi
+    done
+
+    # Extract the output directory using the special delimiters
+    OUTPUT_FILE=$(echo "$INFER_OUTPUT" | grep -o '### OUTPUT FILE:.* ###' | sed 's/### OUTPUT FILE: \(.*\) ###/\1/')
+    echo "Got OUTPUT_FILE: $OUTPUT_FILE"
+
+    while true; do
+        echo "### Evaluating on $OUTPUT_FILE ... ###"
+        COMMAND="poetry run python evaluation/benchmarks/swe_bench/eval_infer.py \
+        --eval-num-workers $((N_WORKERS * 2)) \
+        --input-file $OUTPUT_FILE \
+        --dataset $DATASET \
+        --split $SPLIT"
+
+        if [ -n "$EVAL_LIMIT" ]; then
+        echo "EVAL_LIMIT: $EVAL_LIMIT"
+        COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
+        fi
+        echo "Running command: $COMMAND"
+        # Run the command
+        eval $COMMAND
+        EVAL_STATUS=$?
+        if [ $EVAL_STATUS -eq 0 ]; then
+            echo "### Evaluation completed successfully. ###"
+            break
+        else
+            echo "### Evaluation failed with exit code $EVAL_STATUS. Retrying... ###"
+        fi
+
+        ./evaluation/utils/scripts/cleanup_remote_runtime.sh
+    done
+
+    # update the output with evaluation results
+    echo "### Updating the output with evaluation results... ###"
+    poetry run python evaluation/benchmarks/swe_bench/scripts/eval/update_output_with_eval.py $OUTPUT_FILE
+
+    echo "### Combining the final completions... ###"
+    poetry run python evaluation/benchmarks/swe_bench/scripts/eval/combine_final_completions.py $OUTPUT_FILE
+
+    echo "### DONE for run $run_idx! ###"
+    echo "You can find the final output at $(dirname $OUTPUT_FILE)/$FINAL_OUTPUT_FILE"
+done

evaluation/benchmarks/swe_bench/scripts/run_infer.sh

@@ -25,13 +25,8 @@ if [ -z "$AGENT" ]; then
 fi
 
 if [ -z "$MAX_ITER" ]; then
-  echo "MAX_ITER not specified, use default 100"
-  MAX_ITER=100
-fi
-
-if [ -z "$USE_INSTANCE_IMAGE" ]; then
-  echo "USE_INSTANCE_IMAGE not specified, use default true"
-  USE_INSTANCE_IMAGE=true
+  echo "MAX_ITER not specified, use default 60"
+  MAX_ITER=60
 fi
 
 if [ -z "$RUN_WITH_BROWSING" ]; then
@@ -50,8 +45,6 @@ if [ -z "$SPLIT" ]; then
   SPLIT="test"
 fi
 
-export USE_INSTANCE_IMAGE=$USE_INSTANCE_IMAGE
-echo "USE_INSTANCE_IMAGE: $USE_INSTANCE_IMAGE"
 export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
 echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
 

evaluation/benchmarks/swe_bench/scripts/swegym/convert_data.ipynb

@@ -0,0 +1,287 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "import pandas as pd\n",
+    "from tqdm import tqdm\n",
+    "\n",
+    "tqdm.pandas()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# 1. Load raw data and convert to training data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import gzip\n",
+    "import json\n",
+    "\n",
+    "from tqdm import tqdm\n",
+    "\n",
+    "FILE_PATHS = [\n",
+    "    'YOURPATH-no-hint-train-t05-run_1/output.with_completions.jsonl.gz',\n",
+    "    'YOURPATH-no-hint-train-t05-run_2/output.with_completions.jsonl.gz',\n",
+    "]\n",
+    "\n",
+    "# More memory efficient for large files\n",
+    "# Initialize lists to store the data\n",
+    "data = []\n",
+    "\n",
+    "\n",
+    "# Read file line by line\n",
+    "for FILE_PATH in FILE_PATHS:\n",
+    "    with gzip.open(FILE_PATH, 'rb') as f:  # Use 'rb' for gzipped files\n",
+    "        for i, line in tqdm(\n",
+    "            enumerate(f), desc=f\"Processing {FILE_PATH.split('/')[-1]}\"\n",
+    "        ):\n",
+    "            # Parse only the fields we need\n",
+    "            raw_data = json.loads(line)\n",
+    "            data.append(\n",
+    "                {\n",
+    "                    'resolved': raw_data['report']['resolved'],\n",
+    "                    'messages': raw_data['raw_completions']['messages']\n",
+    "                    if raw_data['raw_completions'] is not None\n",
+    "                    else None,\n",
+    "                    'git_patch': raw_data['test_result'].get('git_patch', ''),\n",
+    "                    'tools': raw_data['raw_completions']['tools']\n",
+    "                    if raw_data['raw_completions'] is not None\n",
+    "                    and 'tools' in raw_data['raw_completions']\n",
+    "                    else None,\n",
+    "                }\n",
+    "            )\n",
+    "\n",
+    "# Convert to DataFrame after collecting all data\n",
+    "df = pd.DataFrame(data)\n",
+    "print(f'#total amount of data={len(df)}')\n",
+    "df = df[~df['messages'].isna()]\n",
+    "print(f'#total amount of data after removing nan={len(df)}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Filter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def _contains_multiple_tool_calls(messages: list[dict]) -> bool:\n",
+    "    return any(\n",
+    "        message.get('tool_calls') and len(message['tool_calls']) > 1\n",
+    "        for message in messages\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "df['contains_multiple_tool_calls'] = df['messages'].apply(_contains_multiple_tool_calls)\n",
+    "display(df.groupby(['contains_multiple_tool_calls'])['resolved'].sum())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import copy\n",
+    "\n",
+    "# Convert function calling messages to non-function calling messages\n",
+    "from openhands.llm.fn_call_converter import (\n",
+    "    FunctionCallConversionError,\n",
+    "    convert_fncall_messages_to_non_fncall_messages,\n",
+    "    convert_from_multiple_tool_calls_to_single_tool_call_messages,\n",
+    ")\n",
+    "\n",
+    "total_failed = 0\n",
+    "\n",
+    "\n",
+    "def _convert_messages(messages: list[dict], tools: list[dict]) -> list[dict]:\n",
+    "    global total_failed\n",
+    "    message_copy = copy.deepcopy(messages)\n",
+    "    for message in message_copy:\n",
+    "        if message['content'] is None:\n",
+    "            message['content'] = ''\n",
+    "    try:\n",
+    "        return convert_fncall_messages_to_non_fncall_messages(\n",
+    "            message_copy, tools, add_in_context_learning_example=False\n",
+    "        )\n",
+    "    except FunctionCallConversionError:\n",
+    "        total_failed += 1\n",
+    "        # print(f'Failed to convert messages: {messages}\\nTools: {tools}')\n",
+    "        # traceback.print_exc()\n",
+    "        return None\n",
+    "\n",
+    "\n",
+    "df['converted_messages'] = df.apply(\n",
+    "    lambda row: convert_from_multiple_tool_calls_to_single_tool_call_messages(\n",
+    "        row['messages'], ignore_final_tool_result=True\n",
+    "    ),\n",
+    "    axis=1,\n",
+    ")\n",
+    "df['nonfncall_messages'] = df.apply(\n",
+    "    lambda row: _convert_messages(row['converted_messages'], row['tools']), axis=1\n",
+    ")\n",
+    "print('total nan', df['nonfncall_messages'].isna().sum())\n",
+    "df = df[~df['nonfncall_messages'].isna()]\n",
+    "print(f'Total failed: {total_failed}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Tokenization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pandarallel import pandarallel\n",
+    "from transformers import AutoTokenizer\n",
+    "\n",
+    "os.environ['TOKENIZERS_PARALLELISM'] = 'false'\n",
+    "pandarallel.initialize(progress_bar=True, verbose=1, nb_workers=16)\n",
+    "tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen2.5-7B-Instruct')\n",
+    "df['n_tokens'] = df['rm_conv'].parallel_apply(\n",
+    "    lambda x: len(tokenizer.apply_chat_template(x))\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(f'BEFORE: #total={len(df)}')\n",
+    "df_selected = df[df['n_tokens'] < 131072]\n",
+    "print(f'AFTER(truncated to 128k): #total={len(df_selected)}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_selected['n_tokens'].describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ecdf of n_tokens\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "\n",
+    "display(df.groupby(['resolved'])['n_tokens'].describe())\n",
+    "sns.ecdfplot(x='n_tokens', data=df, hue='resolved')\n",
+    "plt.show()\n",
+    "\n",
+    "print(f'#total={len(df)}')\n",
+    "df_selected = df[df['n_tokens'] < 131072]\n",
+    "print(f'#selected={len(df_selected)}')\n",
+    "display(df_selected.groupby(['resolved'])['n_tokens'].describe())\n",
+    "sns.ecdfplot(x='n_tokens', data=df_selected, hue='resolved')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_selected[~df_selected['resolved']]['n_tokens'].describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_selected['resolved'].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_selected.groupby(['resolved'])['n_tokens'].describe()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Save Resolved Messages for SFT"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_selected[df_selected['resolved']][['nonfncall_messages']].rename(\n",
+    "    columns={'nonfncall_messages': 'messages'}\n",
+    ").to_json(\n",
+    "    os.path.join(\n",
+    "        'YOUR_OUTPUT_FOLDER',\n",
+    "        f'policy_traj_128k_swegym_{df_selected[\"resolved\"].value_counts()[True]}i.jsonl',\n",
+    "    ),\n",
+    "    lines=True,\n",
+    "    orient='records',\n",
+    ")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "openhands-ai-CPy6G0pU-py3.12",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

evaluation/integration_tests/run_infer.py

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

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

@@ -4,8 +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__/routes/_oh.app.test.tsx

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

frontend/__tests__/routes/home.test.tsx

@@ -8,6 +8,7 @@ import MainApp from "#/routes/_oh/route";
 import SettingsScreen from "#/routes/settings";
 import Home from "#/routes/_oh._index/route";
 import OpenHands from "#/api/open-hands";
+import * as FeatureFlags from "#/utils/feature-flags";
 
 const createAxiosNotFoundErrorObject = () =>
   new AxiosError(
@@ -25,32 +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 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={["/"]} />);
   });
@@ -77,41 +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();
+
+    const settingsModalAfter = screen.queryByTestId("ai-config-modal");
+    expect(settingsModalAfter).not.toBeInTheDocument();
+  });
+
+  it("should not open the settings modal if GET /settings fails but is SaaS mode", async () => {
+    // TODO: Remove HIDE_LLM_SETTINGS check once released
+    vi.spyOn(FeatureFlags, "HIDE_LLM_SETTINGS").mockReturnValue(true);
+    // @ts-expect-error - we only need APP_MODE for this test
+    getConfigSpy.mockResolvedValue({ APP_MODE: "saas" });
+    const error = createAxiosNotFoundErrorObject();
+    getSettingsSpy.mockRejectedValue(error);
+
+    renderWithProviders(<RouterStub initialEntries={["/"]} />);
+
+    // small hack to wait for the modal to not appear
+    await expect(
+      screen.findByTestId("ai-config-modal", {}, { timeout: 1000 }),
+    ).rejects.toThrow();
+  });
+});
+
+describe("Setup Payment modal", () => {
+  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+
+  afterEach(() => {
+    vi.resetAllMocks();
+  });
+
+  it("should only render if SaaS mode and is new user", async () => {
+    // @ts-expect-error - we only need the APP_MODE for this test
+    getConfigSpy.mockResolvedValue({
+      APP_MODE: "saas",
+    });
+    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

@@ -1,6 +1,15 @@
 import { render, screen, waitFor, within } from "@testing-library/react";
 import { createRoutesStub } from "react-router";
-import { afterEach, describe, expect, it, test, vi } from "vitest";
+import {
+  afterEach,
+  beforeAll,
+  beforeEach,
+  describe,
+  expect,
+  it,
+  test,
+  vi,
+} from "vitest";
 import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
 import userEvent, { UserEvent } from "@testing-library/user-event";
 import OpenHands from "#/api/open-hands";
@@ -11,6 +20,7 @@ import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
 import { PostApiSettings } from "#/types/settings";
 import * as ConsentHandlers from "#/utils/handle-capture-consent";
 import AccountSettings from "#/routes/account-settings";
+import * as FeatureFlags from "#/utils/feature-flags";
 
 const toggleAdvancedSettings = async (user: UserEvent) => {
   const advancedSwitch = await screen.findByTestId("advanced-settings-switch");
@@ -29,6 +39,11 @@ describe("Settings Screen", () => {
     useAppLogout: vi.fn().mockReturnValue({ handleLogout: handleLogoutMock }),
   }));
 
+  beforeAll(() => {
+    // TODO: Remove this once we release
+    vi.spyOn(FeatureFlags, "HIDE_LLM_SETTINGS").mockReturnValue(true);
+  });
+
   afterEach(() => {
     vi.clearAllMocks();
   });
@@ -67,12 +82,23 @@ describe("Settings Screen", () => {
   });
 
   describe("Account Settings", () => {
+    beforeEach(() => {
+      getConfigSpy.mockResolvedValue({
+        APP_MODE: "oss",
+        GITHUB_CLIENT_ID: "123",
+        POSTHOG_CLIENT_KEY: "456",
+      });
+    });
+
     it("should render the account settings", async () => {
       renderSettingsScreen();
 
       await waitFor(() => {
         screen.getByTestId("github-token-input");
-        screen.getByTestId("github-token-help-anchor");
+        // Check for GitHub link instead of the help anchor
+        screen.getByRole("link", { name: "GitHub" });
+        // Check for documentation link
+        screen.getByRole("link", { name: "documentation" });
         screen.getByTestId("language-input");
         screen.getByTestId("enable-analytics-switch");
       });
@@ -214,10 +240,12 @@ describe("Settings Screen", () => {
 
       await waitFor(() => {
         const input = screen.queryByTestId("github-token-input");
-        const helpAnchor = screen.queryByTestId("github-token-help-anchor");
+        const githubLink = screen.queryByText("GitHub");
+        const documentationLink = screen.queryByText("documentation");
 
         expect(input).not.toBeInTheDocument();
-        expect(helpAnchor).not.toBeInTheDocument();
+        expect(githubLink).not.toBeInTheDocument();
+        expect(documentationLink).not.toBeInTheDocument();
       });
     });
 
@@ -280,6 +308,14 @@ describe("Settings Screen", () => {
   });
 
   describe("LLM Settings", () => {
+    beforeEach(() => {
+      getConfigSpy.mockResolvedValue({
+        APP_MODE: "oss",
+        GITHUB_CLIENT_ID: "123",
+        POSTHOG_CLIENT_KEY: "456",
+      });
+    });
+
     it("should render the basic LLM settings by default", async () => {
       renderSettingsScreen();
 
@@ -427,8 +463,7 @@ describe("Settings Screen", () => {
         expect(input).not.toBeInTheDocument();
       });
 
-      it("should render the runtime settings input if SaaS mode", async () => {
-        const user = userEvent.setup();
+      it.skip("should render the runtime settings input if SaaS mode", async () => {
         getConfigSpy.mockResolvedValue({
           APP_MODE: "saas",
           GITHUB_CLIENT_ID: "123",
@@ -436,12 +471,10 @@ describe("Settings Screen", () => {
         });
 
         renderSettingsScreen();
-
-        await toggleAdvancedSettings(user);
-        screen.getByTestId("runtime-settings-input");
+        await screen.findByTestId("runtime-settings-input");
       });
 
-      it("should set the default runtime setting set", async () => {
+      it.skip("should set the default runtime setting set", async () => {
         getConfigSpy.mockResolvedValue({
           APP_MODE: "saas",
           GITHUB_CLIENT_ID: "123",
@@ -455,13 +488,11 @@ describe("Settings Screen", () => {
 
         renderSettingsScreen();
 
-        await toggleAdvancedSettings(userEvent.setup());
-
         const input = await screen.findByTestId("runtime-settings-input");
         expect(input).toHaveValue("1x (2 core, 8G)");
       });
 
-      it("should always have the runtime input disabled", async () => {
+      it.skip("should always have the runtime input disabled", async () => {
         getConfigSpy.mockResolvedValue({
           APP_MODE: "saas",
           GITHUB_CLIENT_ID: "123",
@@ -470,8 +501,6 @@ describe("Settings Screen", () => {
 
         renderSettingsScreen();
 
-        await toggleAdvancedSettings(userEvent.setup());
-
         const input = await screen.findByTestId("runtime-settings-input");
         expect(input).toBeDisabled();
       });
@@ -490,8 +519,6 @@ describe("Settings Screen", () => {
 
         renderSettingsScreen();
 
-        await toggleAdvancedSettings(user);
-
         const input = await screen.findByTestId("runtime-settings-input");
         await user.click(input);
 
@@ -699,7 +726,7 @@ 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",
         }),
       );
@@ -736,7 +763,7 @@ 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",
         }),
@@ -779,7 +806,7 @@ 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();
@@ -953,4 +980,104 @@ describe("Settings Screen", () => {
       );
     });
   });
+
+  describe("SaaS mode", () => {
+    beforeEach(() => {
+      getConfigSpy.mockResolvedValue({
+        APP_MODE: "saas",
+        GITHUB_CLIENT_ID: "123",
+        POSTHOG_CLIENT_KEY: "456",
+      });
+    });
+
+    it("should hide the entire LLM section", async () => {
+      renderSettingsScreen();
+
+      await waitFor(() => {
+        screen.getByTestId("account-settings-form"); // wait for the account settings form to render
+
+        const llmSection = screen.queryByTestId("llm-settings-section");
+        expect(llmSection).not.toBeInTheDocument();
+      });
+    });
+
+    it("should not render LLM Provider, LLM Model, and LLM API Key inputs", async () => {
+      renderSettingsScreen();
+
+      await waitFor(() => {
+        screen.getByTestId("account-settings-form"); // wait for the account settings form to render
+
+        const providerInput = screen.queryByTestId("llm-provider-input");
+        const modelInput = screen.queryByTestId("llm-model-input");
+        const apiKeyInput = screen.queryByTestId("llm-api-key-input");
+        const llmApiKeyHelpAnchor = screen.queryByTestId(
+          "llm-api-key-help-anchor",
+        );
+        const advancedSettingsSwitch = screen.queryByTestId(
+          "advanced-settings-switch",
+        );
+
+        expect(providerInput).not.toBeInTheDocument();
+        expect(modelInput).not.toBeInTheDocument();
+        expect(apiKeyInput).not.toBeInTheDocument();
+        expect(llmApiKeyHelpAnchor).not.toBeInTheDocument();
+        expect(advancedSettingsSwitch).not.toBeInTheDocument();
+      });
+    });
+
+    // We might want to bring this back if users wish to set advanced settings
+    it.skip("should render advanced settings by default", async () => {
+      renderSettingsScreen();
+
+      await waitFor(() => {
+        screen.getByTestId("account-settings-form"); // wait for the account settings form to render
+
+        const agentInput = screen.getByTestId("agent-input"); // this is only rendered in advanced mode
+        expect(agentInput).toBeInTheDocument();
+
+        // we should not allow the user to change these fields
+        const customModelInput = screen.queryByTestId("llm-custom-model-input");
+        const baseUrlInput = screen.queryByTestId("base-url-input");
+
+        expect(customModelInput).not.toBeInTheDocument();
+        expect(baseUrlInput).not.toBeInTheDocument();
+      });
+    });
+
+    it("should not submit the unwanted fields when saving", async () => {
+      const user = userEvent.setup();
+      renderSettingsScreen();
+
+      const saveButton = await screen.findByText("Save Changes");
+      await user.click(saveButton);
+
+      expect(saveSettingsSpy).toHaveBeenCalledWith(
+        expect.objectContaining({
+          llm_api_key: undefined,
+          llm_base_url: undefined,
+          llm_model: undefined,
+        }),
+      );
+    });
+
+    it("should not submit the unwanted fields when resetting", async () => {
+      const user = userEvent.setup();
+      renderSettingsScreen();
+
+      const resetButton = await screen.findByText("Reset to defaults");
+      await user.click(resetButton);
+
+      const modal = await screen.findByTestId("reset-modal");
+      const confirmButton = within(modal).getByText("Reset");
+      await user.click(confirmButton);
+
+      expect(saveSettingsSpy).toHaveBeenCalledWith(
+        expect.objectContaining({
+          llm_api_key: undefined,
+          llm_base_url: undefined,
+          llm_model: undefined,
+        }),
+      );
+    });
+  });
 });

frontend/__tests__/services/actions.test.ts

@@ -1,7 +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/__tests__/utils/error-handler.test.ts

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

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.27.0",
+  "version": "0.28.1",
   "private": true,
   "type": "module",
   "engines": {
@@ -9,43 +9,43 @@
   "dependencies": {
     "@heroui/react": "2.7.4",
     "@monaco-editor/react": "^4.7.0-rc.0",
-    "@react-router/node": "^7.2.0",
-    "@react-router/serve": "^7.2.0",
-    "@react-types/shared": "^3.27.0",
+    "@react-router/node": "^7.3.0",
+    "@react-router/serve": "^7.3.0",
+    "@react-types/shared": "^3.28.0",
     "@reduxjs/toolkit": "^2.6.0",
-    "@stripe/react-stripe-js": "^3.1.1",
-    "@stripe/stripe-js": "^5.7.0",
-    "@tanstack/react-query": "^5.66.11",
+    "@stripe/react-stripe-js": "^3.3.0",
+    "@stripe/stripe-js": "^5.10.0",
+    "@tanstack/react-query": "^5.67.2",
     "@vitejs/plugin-react": "^4.3.2",
     "@xterm/addon-fit": "^0.10.0",
     "@xterm/xterm": "^5.4.0",
-    "axios": "^1.8.1",
+    "axios": "^1.8.2",
     "clsx": "^2.1.1",
     "eslint-config-airbnb-typescript": "^18.0.0",
-    "framer-motion": "^12.4.7",
+    "framer-motion": "^12.4.10",
     "i18next": "^24.2.2",
     "i18next-browser-languagedetector": "^8.0.4",
     "i18next-http-backend": "^3.0.2",
     "isbot": "^5.1.23",
     "jose": "^6.0.8",
     "monaco-editor": "^0.52.2",
-    "posthog-js": "^1.225.1",
+    "posthog-js": "^1.229.3",
     "react": "^19.0.0",
     "react-dom": "^19.0.0",
     "react-highlight": "^0.15.0",
     "react-hot-toast": "^2.5.1",
     "react-i18next": "^15.4.1",
     "react-icons": "^5.5.0",
-    "react-markdown": "^10.0.1",
+    "react-markdown": "^10.1.0",
     "react-redux": "^9.2.0",
-    "react-router": "^7.2.0",
+    "react-router": "^7.3.0",
     "react-syntax-highlighter": "^15.6.1",
     "react-textarea-autosize": "^8.5.7",
     "remark-gfm": "^4.0.1",
     "sirv-cli": "^3.0.1",
     "socket.io-client": "^4.8.1",
     "tailwind-merge": "^3.0.2",
-    "vite": "^6.2.0",
+    "vite": "^6.2.1",
     "web-vitals": "^3.5.2",
     "ws": "^8.18.1"
   },
@@ -80,29 +80,29 @@
   },
   "devDependencies": {
     "@mswjs/socket.io-binding": "^0.1.1",
-    "@playwright/test": "^1.50.1",
-    "@react-router/dev": "^7.2.0",
+    "@playwright/test": "^1.51.0",
+    "@react-router/dev": "^7.3.0",
     "@tailwindcss/typography": "^0.5.16",
-    "@tanstack/eslint-plugin-query": "^5.66.1",
+    "@tanstack/eslint-plugin-query": "^5.67.2",
     "@testing-library/dom": "^10.4.0",
     "@testing-library/jest-dom": "^6.6.1",
     "@testing-library/react": "^16.2.0",
     "@testing-library/user-event": "^14.6.1",
-    "@types/node": "^22.13.8",
+    "@types/node": "^22.13.9",
     "@types/react": "^19.0.8",
     "@types/react-dom": "^19.0.3",
     "@types/react-highlight": "^0.12.8",
     "@types/react-syntax-highlighter": "^15.5.13",
-    "@types/ws": "^8.5.14",
+    "@types/ws": "^8.18.0",
     "@typescript-eslint/eslint-plugin": "^7.18.0",
     "@typescript-eslint/parser": "^7.18.0",
-    "@vitest/coverage-v8": "^3.0.7",
+    "@vitest/coverage-v8": "^3.0.8",
     "autoprefixer": "^10.4.20",
     "cross-env": "^7.0.3",
     "eslint": "^8.57.0",
     "eslint-config-airbnb": "^19.0.4",
     "eslint-config-airbnb-typescript": "^18.0.0",
-    "eslint-config-prettier": "^10.0.2",
+    "eslint-config-prettier": "^10.1.1",
     "eslint-plugin-import": "^2.29.1",
     "eslint-plugin-jsx-a11y": "^6.10.2",
     "eslint-plugin-prettier": "^5.2.3",

frontend/public/mockServiceWorker.js

@@ -8,7 +8,7 @@
  * - Please do NOT serve this file on production.
  */
 
-const PACKAGE_VERSION = '2.7.0'
+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/chat/chat-interface.tsx

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

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

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

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

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

frontend/src/context/settings-context.tsx

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

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

@@ -17,7 +17,7 @@ const saveSettingsMutationFn = async (settings: Partial<PostSettings>) => {
       ? ""
       : settings.LLM_API_KEY?.trim() || undefined,
     remote_runtime_resource_factor: settings.REMOTE_RUNTIME_RESOURCE_FACTOR,
-    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/mutation/use-submit-feedback.ts

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

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/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/icons/close.svg

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

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

@@ -3,8 +3,8 @@ import {
   QueryCache,
   MutationCache,
 } from "@tanstack/react-query";
-import toast from "react-hot-toast";
 import { retrieveAxiosErrorMessage } from "./utils/retrieve-axios-error-message";
+import { displayErrorToast } from "./utils/custom-toast-handlers";
 
 const shownErrors = new Set<string>();
 export const queryClientConfig: QueryClientConfig = {
@@ -14,7 +14,7 @@ export const queryClientConfig: QueryClientConfig = {
         const errorMessage = retrieveAxiosErrorMessage(error);
 
         if (!shownErrors.has(errorMessage)) {
-          toast.error(errorMessage || "An error occurred");
+          displayErrorToast(errorMessage || "An error occurred");
           shownErrors.add(errorMessage);
 
           setTimeout(() => {
@@ -28,14 +28,8 @@ export const queryClientConfig: QueryClientConfig = {
     onError: (error, _, __, mutation) => {
       if (!mutation?.meta?.disableToast) {
         const message = retrieveAxiosErrorMessage(error);
-        toast.error(message);
+        displayErrorToast(message);
       }
     },
   }),
-  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.app/hooks/use-handle-runtime-active.ts

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

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

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

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

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

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>
   );
 }