empty commit

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

.github/ISSUE_TEMPLATE/bug_template.yml

@@ -31,6 +31,8 @@ body:
       options:
         - Docker command in README
         - Development workflow
+        - app.all-hands.dev
+        - Other
       default: 0
 
   - type: input

.github/workflows/ghcr-build.yml

@@ -424,9 +424,9 @@ jobs:
             -p 3000:3000 \
             -v /var/run/docker.sock:/var/run/docker.sock \
             --add-host host.docker.internal:host-gateway \
-            -e SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:$SHORT_SHA-nikolaik \
+            -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:$SHORT_SHA-nikolaik \
             --name openhands-app-$SHORT_SHA \
-            ghcr.io/all-hands-ai/runtime:$SHORT_SHA"
+            docker.all-hands.dev/all-hands-ai/openhands:$SHORT_SHA"
 
           PR_BODY=$(gh pr view $PR_NUMBER --json body --jq .body)
 

.github/workflows/openhands-resolver.yml

@@ -11,5 +11,5 @@ jobs:
     uses: All-Hands-AI/openhands-resolver/.github/workflows/openhands-resolver.yml@main
     if: github.event.label.name == 'fix-me'
     with:
-      issue_number: ${{ github.event.issue.number }}
+      max_iterations: 50
     secrets: inherit

Development.md

@@ -100,7 +100,7 @@ poetry run pytest ./tests/unit/test_*.py
 ### 9. Use existing Docker image
 To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker container image. Follow these steps:
 1. Set the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
-2. Example: export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.9-nikolaik
+2. Example: export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.13-nikolaik
 
 ## Develop inside Docker container
 

README.md

@@ -38,15 +38,15 @@ See the [Installation](https://docs.all-hands.dev/modules/usage/installation) gu
 system requirements and more information.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik
 
-docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik \
+docker run -it --pull=always \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik \
     -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:0.12
+    docker.all-hands.dev/all-hands-ai/openhands:0.13
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!

compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.9-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.13-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

config.template.toml

@@ -32,7 +32,8 @@ workspace_base = "./workspace"
 # Enable saving and restoring the session when run from CLI
 #enable_cli_session = false
 
-# Path to store trajectories
+# Path to store trajectories, can be a folder or a file
+# If it's a folder, the session id will be used as the file name
 #trajectories_path="./trajectories"
 
 # File store path

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:0.9-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.13-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/evaluation-harness.md

@@ -161,7 +161,7 @@ Pour créer un workflow d'évaluation pour votre benchmark, suivez ces étapes :
            instruction=instruction,
            test_result=evaluation_result,
            metadata=metadata,
-           history=state.history.compatibility_for_eval_history_pairs(),
+           history=compatibility_for_eval_history_pairs(state.history),
            metrics=state.metrics.get() if state.metrics else None,
            error=state.last_error if state and state.last_error else None,
        )
@@ -260,7 +260,7 @@ def codeact_user_response(state: State | None) -> str:
         # vérifier si l'agent a essayé de parler à l'utilisateur 3 fois, si oui, faire savoir à l'agent qu'il peut abandonner
         user_msgs = [
             event
-            for event in state.history.get_events()
+            for event in state.history
             if isinstance(event, MessageAction) and event.source == 'user'
         ]
         if len(user_msgs) >= 2:
@@ -279,4 +279,3 @@ Cette fonction fait ce qui suit :
 3. Si l'agent a fait plusieurs tentatives, il lui donne la possibilité d'abandonner
 
 En utilisant cette fonction, vous pouvez garantir un comportement cohérent sur plusieurs exécutions d'évaluation et empêcher l'agent de rester bloqué en attendant une entrée humaine.
-

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/evaluation-harness.md

@@ -158,7 +158,7 @@ OpenHands 的主要入口点在 `openhands/core/main.py` 中。以下是它工
            instruction=instruction,
            test_result=evaluation_result,
            metadata=metadata,
-           history=state.history.compatibility_for_eval_history_pairs(),
+           history=compatibility_for_eval_history_pairs(state.history),
            metrics=state.metrics.get() if state.metrics else None,
            error=state.last_error if state and state.last_error else None,
        )
@@ -257,7 +257,7 @@ def codeact_user_response(state: State | None) -> str:
         # 检查代理是否已尝试与用户对话 3 次，如果是，让代理知道它可以放弃
         user_msgs = [
             event
-            for event in state.history.get_events()
+            for event in state.history
             if isinstance(event, MessageAction) and event.source == 'user'
         ]
         if len(user_msgs) >= 2:

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

@@ -58,4 +58,3 @@ docker run -it \
     ghcr.io/all-hands-ai/openhands:0.11 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
-

docs/modules/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:0.12-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.13-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:0.12 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.13 \
     python -m openhands.core.cli
 ```
 

docs/modules/usage/how-to/evaluation-harness.md

@@ -158,7 +158,7 @@ To create an evaluation workflow for your benchmark, follow these steps:
            instruction=instruction,
            test_result=evaluation_result,
            metadata=metadata,
-           history=state.history.compatibility_for_eval_history_pairs(),
+           history=compatibility_for_eval_history_pairs(state.history),
            metrics=state.metrics.get() if state.metrics else None,
            error=state.last_error if state and state.last_error else None,
        )
@@ -257,7 +257,7 @@ def codeact_user_response(state: State | None) -> str:
         # check if the agent has tried to talk to the user 3 times, if so, let the agent know it can give up
         user_msgs = [
             event
-            for event in state.history.get_events()
+            for event in state.history
             if isinstance(event, MessageAction) and event.source == 'user'
         ]
         if len(user_msgs) >= 2:

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

@@ -19,6 +19,15 @@ OpenHands provides a user-friendly Graphical User Interface (GUI) mode for inter
 3. Enter the corresponding `API Key` for your chosen provider.
 4. Click "Save" to apply the settings.
 
+### GitHub Token Setup
+
+OpenHands automatically exports a `GITHUB_TOKEN` to the shell environment if it is available. This can happen in two ways:
+
+1. Locally (OSS): The user directly inputs their GitHub token.
+2. Online (SaaS): The token is obtained through GitHub OAuth authentication.
+
+When you reach the `/app` route, the app checks if a token is present. If it finds one, it sets it in the environment for the agent to use.
+
 ### Advanced Settings
 
 1. Toggle `Advanced Options` to access additional settings.

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

@@ -44,7 +44,7 @@ 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:0.12-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -53,6 +53,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.12 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.13 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```

docs/modules/usage/installation.mdx

@@ -11,15 +11,15 @@
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.13-nikolaik \
     -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:0.12
+    docker.all-hands.dev/all-hands-ai/openhands:0.13
 ```
 
 You can also run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), as an [interactive CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), or using the [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action).

docs/modules/usage/runtimes.md

@@ -60,7 +60,6 @@ docker run # ...
     -e SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.app.all-hands.dev" \
     -e SANDBOX_API_KEY="your-all-hands-api-key" \
     -e SANDBOX_KEEP_REMOTE_RUNTIME_ALIVE="true" \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.11-nikolaik \
     # ...
 ```
 
@@ -75,5 +74,4 @@ docker run # ...
     -e RUNTIME=modal \
     -e MODAL_API_TOKEN_ID="your-id" \
     -e MODAL_API_TOKEN_SECRET="your-secret" \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.11-nikolaik \
 ```

docs/package.json

@@ -15,10 +15,10 @@
     "typecheck": "tsc"
   },
   "dependencies": {
-    "@docusaurus/core": "^3.5.2",
-    "@docusaurus/plugin-content-pages": "^3.5.2",
-    "@docusaurus/preset-classic": "^3.5.2",
-    "@docusaurus/theme-mermaid": "^3.5.2",
+    "@docusaurus/core": "^3.6.0",
+    "@docusaurus/plugin-content-pages": "^3.6.0",
+    "@docusaurus/preset-classic": "^3.6.0",
+    "@docusaurus/theme-mermaid": "^3.6.0",
     "@mdx-js/react": "^3.1.0",
     "clsx": "^2.0.0",
     "prism-react-renderer": "^2.4.0",
@@ -29,7 +29,7 @@
   },
   "devDependencies": {
     "@docusaurus/module-type-aliases": "^3.5.1",
-    "@docusaurus/tsconfig": "^3.5.2",
+    "@docusaurus/tsconfig": "^3.6.0",
     "@docusaurus/types": "^3.5.1",
     "typescript": "~5.6.3"
   },

evaluation/EDA/run_infer.py

@@ -8,6 +8,7 @@ from evaluation.EDA.game import Q20Game, Q20GameCelebrity
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -34,7 +35,8 @@ def codeact_user_response_eda(state: State) -> str:
 
     # retrieve the latest model message from history
     if state.history:
-        model_guess = state.history.get_last_agent_message()
+        last_agent_message = state.get_last_agent_message()
+        model_guess = last_agent_message.content if last_agent_message else ''
 
     assert game is not None, 'Game is not initialized.'
     msg = game.generate_user_response(model_guess)
@@ -139,7 +141,8 @@ def process_instance(
     if state is None:
         raise ValueError('State should not be None.')
 
-    final_message = state.history.get_last_agent_message()
+    last_agent_message = state.get_last_agent_message()
+    final_message = last_agent_message.content if last_agent_message else ''
 
     logger.info(f'Final message: {final_message} | Ground truth: {instance["text"]}')
     test_result = game.reward()
@@ -148,7 +151,7 @@ def process_instance(
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     # Save the output
     output = EvalOutput(

evaluation/README.md

@@ -84,4 +84,3 @@ all the preprocessing/evaluation/analysis scripts.
 - Raw data and experimental records should not be stored within this repo.
 - For model outputs, they should be stored at [this huggingface space](https://huggingface.co/spaces/OpenHands/evaluation) for visualization.
 - Important data files of manageable size and analysis scripts (e.g., jupyter notebooks) can be directly uploaded to this repo.
-

evaluation/agent_bench/run_infer.py

@@ -16,6 +16,7 @@ from evaluation.agent_bench.helper import (
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -242,7 +243,7 @@ def process_instance(
         raw_ans = ''
 
         # retrieve the last agent message or thought
-        for event in state.history.get_events(reverse=True):
+        for event in reversed(state.history):
             if event.source == 'agent':
                 if isinstance(event, AgentFinishAction):
                     raw_ans = event.thought
@@ -271,7 +272,7 @@ def process_instance(
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     metrics = state.metrics.get() if state.metrics else None
 

evaluation/aider_bench/run_infer.py

@@ -15,6 +15,7 @@ from evaluation.aider_bench.helper import (
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -250,7 +251,7 @@ def process_instance(
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
     metrics = state.metrics.get() if state.metrics else None
 
     # Save the output

evaluation/biocoder/run_infer.py

@@ -13,6 +13,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     codeact_user_response,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -299,7 +300,7 @@ def process_instance(
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     test_result['generated'] = test_result['metadata']['1_copy_change_code']
 

evaluation/bird/run_infer.py

@@ -16,6 +16,7 @@ from tqdm import tqdm
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -46,7 +47,7 @@ def codeact_user_response(state: State) -> str:
         # check if the agent has tried to talk to the user 3 times, if so, let the agent know it can give up
         user_msgs = [
             event
-            for event in state.history.get_events()
+            for event in state.history
             if isinstance(event, MessageAction) and event.source == 'user'
         ]
         if len(user_msgs) > 2:
@@ -431,7 +432,7 @@ def process_instance(
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     # Save the output
     output = EvalOutput(

evaluation/browsing_delegation/run_infer.py

@@ -9,6 +9,7 @@ from datasets import load_dataset
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -89,7 +90,7 @@ def process_instance(
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     # find the last delegate action
     last_delegate_action = None

evaluation/discoverybench/run_infer.py

@@ -15,6 +15,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     codeact_user_response,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -173,14 +174,14 @@ def initialize_runtime(runtime: Runtime, data_files: list[str]):
 
 
 def get_last_agent_finish_action(state: State) -> AgentFinishAction:
-    for event in state.history.get_events(reverse=True):
+    for event in reversed(state.history):
         if isinstance(event, AgentFinishAction):
             return event
     return None
 
 
 def get_last_message_action(state: State) -> MessageAction:
-    for event in state.history.get_events(reverse=True):
+    for event in reversed(state.history):
         if isinstance(event, MessageAction):
             return event
     return None
@@ -307,7 +308,7 @@ def process_instance(
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     # DiscoveryBench Evaluation
     eval_rec = run_eval_gold_vs_gen_NL_hypo_workflow(

evaluation/gaia/run_infer.py

@@ -12,6 +12,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     codeact_user_response,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -166,7 +167,7 @@ def process_instance(
 
     model_answer_raw = ''
     # get the last message or thought from the agent
-    for event in state.history.get_events(reverse=True):
+    for event in reversed(state.history):
         if event.source == 'agent':
             if isinstance(event, AgentFinishAction):
                 model_answer_raw = event.thought
@@ -203,7 +204,7 @@ def process_instance(
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     # Save the output
     output = EvalOutput(

evaluation/gorilla/run_infer.py

@@ -10,6 +10,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     codeact_user_response,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -101,7 +102,8 @@ def process_instance(
         raise ValueError('State should not be None.')
 
     # retrieve the last message from the agent
-    model_answer_raw = state.history.get_last_agent_message()
+    last_agent_message = state.get_last_agent_message()
+    model_answer_raw = last_agent_message.content if last_agent_message else ''
 
     # attempt to parse model_answer
     ast_eval_fn = instance['ast_eval']
@@ -114,7 +116,7 @@ def process_instance(
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     output = EvalOutput(
         instance_id=instance_id,

evaluation/gpqa/run_infer.py

@@ -28,6 +28,7 @@ from datasets import load_dataset
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -244,7 +245,7 @@ Ok now its time to start solving the question. Good luck!
         'C': False,
         'D': False,
     }
-    for event in state.history.get_events(reverse=True):
+    for event in reversed(state.history):
         if (
             isinstance(event, AgentFinishAction)
             and event.source != 'user'
@@ -300,7 +301,7 @@ Ok now its time to start solving the question. Good luck!
         instance_id=str(instance.instance_id),
         instruction=instruction,
         metadata=metadata,
-        history=state.history.compatibility_for_eval_history_pairs(),
+        history=compatibility_for_eval_history_pairs(state.history),
         metrics=metrics,
         error=state.last_error if state and state.last_error else None,
         test_result={

evaluation/humanevalfix/run_infer.py

@@ -21,6 +21,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     codeact_user_response,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -255,7 +256,7 @@ def process_instance(
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     # Save the output
     output = EvalOutput(

evaluation/integration_tests/run_infer.py

@@ -13,6 +13,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_llm_config_for_completions_logging,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -55,18 +56,14 @@ def get_config(
         workspace_base=None,
         workspace_mount_path=None,
     )
-    if metadata.llm_config.log_completions:
-        metadata.llm_config.log_completions_folder = os.path.join(
-            metadata.eval_output_dir, 'llm_completions', instance_id
+    config.set_llm_config(
+        update_llm_config_for_completions_logging(
+            metadata.llm_config, metadata.eval_output_dir, instance_id
         )
-        logger.info(
-            f'Logging LLM completions for instance {instance_id} to '
-            f'{metadata.llm_config.log_completions_folder}'
-        )
-    config.set_llm_config(metadata.llm_config)
+    )
     agent_config = AgentConfig(
         codeact_enable_jupyter=True,
-        codeact_enable_browsing_delegate=True,
+        codeact_enable_browsing=True,
         codeact_enable_llm_editor=False,
     )
     config.set_agent_config(agent_config)
@@ -132,7 +129,7 @@ def process_instance(
     # # result evaluation
     # # =============================================
 
-    histories = [event_to_dict(event) for event in state.history.get_events()]
+    histories = [event_to_dict(event) for event in state.history]
     test_result: TestResult = test_class.verify_result(runtime, histories)
     metrics = state.metrics.get() if state.metrics else None
 

evaluation/integration_tests/tests/t06_github_pr_browsing.py

@@ -0,0 +1,44 @@
+from evaluation.integration_tests.tests.base import BaseIntegrationTest, TestResult
+from openhands.events.action import AgentFinishAction, MessageAction
+from openhands.events.event import Event
+from openhands.events.observation import AgentDelegateObservation
+from openhands.runtime.base import Runtime
+
+
+class Test(BaseIntegrationTest):
+    INSTRUCTION = 'Look at https://github.com/All-Hands-AI/OpenHands/pull/8, and tell me what is happening there and what did @asadm suggest.'
+
+    @classmethod
+    def initialize_runtime(cls, runtime: Runtime) -> None:
+        pass
+
+    @classmethod
+    def verify_result(cls, runtime: Runtime, histories: list[Event]) -> TestResult:
+        # check if the "The answer is OpenHands is all you need!" is in any message
+        message_actions = [
+            event
+            for event in histories
+            if isinstance(
+                event, (MessageAction, AgentFinishAction, AgentDelegateObservation)
+            )
+        ]
+        for event in message_actions:
+            if isinstance(event, AgentDelegateObservation):
+                content = event.content
+            elif isinstance(event, AgentFinishAction):
+                content = event.outputs.get('content', '')
+            elif isinstance(event, MessageAction):
+                content = event.content
+            else:
+                raise ValueError(f'Unknown event type: {type(event)}')
+
+            if (
+                'non-commercial' in content
+                or 'MIT' in content
+                or 'Apache 2.0' in content
+            ):
+                return TestResult(success=True)
+        return TestResult(
+            success=False,
+            reason=f'The answer is not found in any message. Total messages: {len(message_actions)}. Messages: {message_actions}',
+        )

evaluation/logic_reasoning/run_infer.py

@@ -8,6 +8,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     codeact_user_response,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -225,7 +226,7 @@ def process_instance(
         raise ValueError('State should not be None.')
 
     final_message = ''
-    for event in state.history.get_events(reverse=True):
+    for event in reversed(state.history):
         if isinstance(event, AgentFinishAction):
             final_message = event.thought
             break
@@ -247,7 +248,7 @@ def process_instance(
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     # Save the output
     output = EvalOutput(

evaluation/miniwob/run_infer.py

@@ -10,10 +10,13 @@ import pandas as pd
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
+    codeact_user_response,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_llm_config_for_completions_logging,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -29,7 +32,10 @@ from openhands.events.action import (
     CmdRunAction,
     MessageAction,
 )
-from openhands.events.observation import CmdOutputObservation
+from openhands.events.observation import (
+    BrowserOutputObservation,
+    CmdOutputObservation,
+)
 from openhands.runtime.base import Runtime
 from openhands.runtime.browser.browser_env import (
     BROWSER_EVAL_GET_GOAL_ACTION,
@@ -37,7 +43,11 @@ from openhands.runtime.browser.browser_env import (
 )
 from openhands.utils.async_utils import call_async_from_sync
 
-SUPPORTED_AGENT_CLS = {'BrowsingAgent'}
+SUPPORTED_AGENT_CLS = {'BrowsingAgent', 'CodeActAgent'}
+
+AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
+    'CodeActAgent': codeact_user_response,
+}
 
 
 def get_config(
@@ -47,25 +57,32 @@ def get_config(
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
-        runtime='eventstream',
+        runtime=os.environ.get('RUNTIME', 'eventstream'),
         max_iterations=metadata.max_iterations,
         sandbox=SandboxConfig(
             base_container_image='xingyaoww/od-eval-miniwob:v1.0',
             enable_auto_lint=True,
             use_host_network=False,
             browsergym_eval_env=env_id,
+            api_key=os.environ.get('ALLHANDS_API_KEY', None),
+            remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
+            keep_remote_runtime_alive=False,
         ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
     )
-    config.set_llm_config(metadata.llm_config)
+    config.set_llm_config(
+        update_llm_config_for_completions_logging(
+            metadata.llm_config, metadata.eval_output_dir, env_id
+        )
+    )
     return config
 
 
 def initialize_runtime(
     runtime: Runtime,
-) -> str:
+) -> tuple[str, BrowserOutputObservation]:
     """Initialize the runtime for the agent.
 
     This function is called before the runtime is used to run the agent.
@@ -85,8 +102,14 @@ def initialize_runtime(
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
     goal = obs.content
 
+    # Run noop to get the initial browser observation (e.g., the page URL & content)
+    action = BrowseInteractiveAction(browser_actions='noop(1000)')
+    logger.info(action, extra={'msg_type': 'ACTION'})
+    obs = runtime.run_action(action)
+    logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
     logger.info(f"{'-' * 50} END Runtime Initialization Fn {'-' * 50}")
-    return goal
+    return goal, obs
 
 
 def complete_runtime(
@@ -117,7 +140,7 @@ def process_instance(
     metadata: EvalMetadata,
     reset_logger: bool = True,
 ) -> EvalOutput:
-    env_id = instance.id
+    env_id = instance.instance_id
     config = get_config(metadata, env_id)
 
     # Setup the logger properly, so you can run multi-processing to parallelize the evaluation
@@ -129,7 +152,12 @@ def process_instance(
 
     runtime = create_runtime(config)
     call_async_from_sync(runtime.connect)
-    task_str = initialize_runtime(runtime)
+    task_str, obs = initialize_runtime(runtime)
+
+    task_str += (
+        f'\nInitial browser state (output of `noop(1000)`):\n{obs.get_agent_obs_text()}'
+    )
+
     state: State | None = asyncio.run(
         run_controller(
             config=config,
@@ -137,6 +165,9 @@ def process_instance(
                 content=task_str
             ),  # take output from initialize_runtime
             runtime=runtime,
+            fake_user_response_fn=AGENT_CLS_TO_FAKE_USER_RESPONSE_FN[
+                metadata.agent_class
+            ],
         )
     )
 
@@ -152,19 +183,19 @@ def process_instance(
 
     # Instruction is the first message from the USER
     instruction = ''
-    for event in state.history.get_events():
+    for event in state.history:
         if isinstance(event, MessageAction):
             instruction = event.content
             break
 
     return_val = complete_runtime(runtime)
     logger.info(f'Return value from complete_runtime: {return_val}')
-    reward = max(return_val['rewards'])
+    reward = max(return_val['rewards'], default=0)
 
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     # Save the output
     output = EvalOutput(

evaluation/mint/run_infer.py

@@ -13,6 +13,7 @@ from evaluation.mint.tasks import Task
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -28,6 +29,7 @@ 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.events.action import (
+    Action,
     CmdRunAction,
     MessageAction,
 )
@@ -45,7 +47,10 @@ def codeact_user_response_mint(state: State, task: Task, task_config: dict[str,
         task=task,
         task_config=task_config,
     )
-    last_action = state.history.get_last_action()
+    last_action = next(
+        (event for event in reversed(state.history) if isinstance(event, Action)),
+        None,
+    )
     result_state: TaskState = env.step(last_action.message or '')
 
     state.extra_data['task_state'] = result_state
@@ -202,7 +207,7 @@ def process_instance(
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     # Save the output
     output = EvalOutput(

evaluation/ml_bench/run_infer.py

@@ -24,6 +24,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     codeact_user_response,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -256,7 +257,7 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     # Save the output
     output = EvalOutput(

evaluation/scienceagentbench/run_infer.py

@@ -10,10 +10,12 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     codeact_user_response,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_llm_config_for_completions_logging,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -76,15 +78,13 @@ def get_config(
         workspace_base=None,
         workspace_mount_path=None,
     )
-    config.set_llm_config(metadata.llm_config)
-    if metadata.llm_config.log_completions:
-        metadata.llm_config.log_completions_folder = os.path.join(
-            metadata.eval_output_dir, 'llm_completions', instance_id
-        )
-        logger.info(
-            f'Logging LLM completions for instance {instance_id} to '
-            f'{metadata.llm_config.log_completions_folder}'
+    config.set_llm_config(
+        update_llm_config_for_completions_logging(
+            metadata.llm_config,
+            metadata.eval_output_dir,
+            instance_id,
         )
+    )
     return config
 
 
@@ -233,7 +233,7 @@ If the program uses some packages that are incompatible, please figure out alter
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     # Save the output
     output = EvalOutput(

evaluation/swe_bench/eval_infer.py

@@ -83,6 +83,7 @@ def get_config(instance: pd.Series) -> AppConfig:
             timeout=1800,
             api_key=os.environ.get('ALLHANDS_API_KEY', None),
             remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
+            remote_runtime_init_timeout=1800,
         ),
         # do not mount workspace
         workspace_base=None,

evaluation/swe_bench/run_infer.py

@@ -20,6 +20,7 @@ from evaluation.utils.shared import (
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
+    update_llm_config_for_completions_logging,
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
@@ -40,6 +41,7 @@ from openhands.utils.async_utils import call_async_from_sync
 
 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 = {
     'CodeActAgent': codeact_user_response,
@@ -79,7 +81,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
             '</pr_description>\n\n'
             'Can you help me implement the necessary changes to the repository so that the requirements specified in the <pr_description> are met?\n'
             "I've already taken care of all changes to any of the test files described in the <pr_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!\n"
-            'Your task is to make the minimal changes to non-tests files in the /repo directory to ensure the <pr_description> is satisfied.\n'
+            'Your task is to make the minimal changes to non-tests files in the /workspace directory to ensure the <pr_description> is satisfied.\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'
@@ -88,6 +90,13 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
             '5. Think about edgecases and make sure your fix handles them as well\n'
             "Your thinking should be thorough and so it's fine if it's very long.\n"
         )
+
+    if RUN_WITH_BROWSING:
+        instruction += (
+            '<IMPORTANT!>\n'
+            'You SHOULD NEVER attempt to browse the web. '
+            '</IMPORTANT!>\n'
+        )
     return instruction
 
 
@@ -137,23 +146,20 @@ def get_config(
             api_key=os.environ.get('ALLHANDS_API_KEY', None),
             remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
             keep_remote_runtime_alive=False,
+            remote_runtime_init_timeout=1800,
         ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
     )
-    if metadata.llm_config.log_completions:
-        metadata.llm_config.log_completions_folder = os.path.join(
-            metadata.eval_output_dir, 'llm_completions', instance['instance_id']
+    config.set_llm_config(
+        update_llm_config_for_completions_logging(
+            metadata.llm_config, metadata.eval_output_dir, instance['instance_id']
         )
-        logger.info(
-            f'Logging LLM completions for instance {instance["instance_id"]} to '
-            f'{metadata.llm_config.log_completions_folder}'
-        )
-    config.set_llm_config(metadata.llm_config)
+    )
     agent_config = AgentConfig(
         codeact_enable_jupyter=False,
-        codeact_enable_browsing_delegate=False,
+        codeact_enable_browsing=RUN_WITH_BROWSING,
         codeact_enable_llm_editor=False,
     )
     config.set_agent_config(agent_config)
@@ -438,7 +444,8 @@ def process_instance(
     if state is None:
         raise ValueError('State should not be None.')
 
-    histories = [event_to_dict(event) for event in state.history.get_events()]
+    # NOTE: this is NO LONGER the event stream, but an agent history that includes delegate agent's events
+    histories = [event_to_dict(event) for event in state.history]
     metrics = state.metrics.get() if state.metrics else None
 
     # Save the output

evaluation/swe_bench/scripts/run_infer.sh

@@ -34,6 +34,11 @@ if [ -z "$USE_INSTANCE_IMAGE" ]; then
   USE_INSTANCE_IMAGE=true
 fi
 
+if [ -z "$RUN_WITH_BROWSING" ]; then
+  echo "RUN_WITH_BROWSING not specified, use default false"
+  RUN_WITH_BROWSING=false
+fi
+
 
 if [ -z "$DATASET" ]; then
   echo "DATASET not specified, use default princeton-nlp/SWE-bench_Lite"
@@ -47,6 +52,8 @@ 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"
 
 get_agent_version
 
@@ -67,6 +74,10 @@ if [ "$USE_HINT_TEXT" = false ]; then
   EVAL_NOTE="$EVAL_NOTE-no-hint"
 fi
 
+if [ "$RUN_WITH_BROWSING" = true ]; then
+  EVAL_NOTE="$EVAL_NOTE-with-browsing"
+fi
+
 if [ -n "$EXP_NAME" ]; then
   EVAL_NOTE="$EVAL_NOTE-$EXP_NAME"
 fi

evaluation/toolqa/run_infer.py

@@ -9,6 +9,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     codeact_user_response,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -126,7 +127,8 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
         raise ValueError('State should not be None.')
 
     # retrieve the last message from the agent
-    model_answer_raw = state.history.get_last_agent_message()
+    last_agent_message = state.get_last_agent_message()
+    model_answer_raw = last_agent_message.content if last_agent_message else ''
 
     # attempt to parse model_answer
     correct = eval_answer(str(model_answer_raw), str(answer))
@@ -137,7 +139,7 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     # Save the output
     output = EvalOutput(

evaluation/utils/shared.py

@@ -18,6 +18,9 @@ from openhands.core.logger import get_console_handler
 from openhands.core.logger import openhands_logger as logger
 from openhands.events.action import Action
 from openhands.events.action.message import MessageAction
+from openhands.events.event import Event
+from openhands.events.serialization.event import event_to_dict
+from openhands.events.utils import get_pairs_from_events
 
 
 class EvalMetadata(BaseModel):
@@ -112,7 +115,14 @@ def codeact_user_response(
     if state.history:
         # check if the last action has an answer, if so, early exit
         if try_parse is not None:
-            last_action = state.history.get_last_action()
+            last_action = next(
+                (
+                    event
+                    for event in reversed(state.history)
+                    if isinstance(event, Action)
+                ),
+                None,
+            )
             ans = try_parse(last_action)
             if ans is not None:
                 return '/exit'
@@ -120,7 +130,7 @@ def codeact_user_response(
         # check if the agent has tried to talk to the user 3 times, if so, let the agent know it can give up
         user_msgs = [
             event
-            for event in state.history.get_events()
+            for event in state.history
             if isinstance(event, MessageAction) and event.source == 'user'
         ]
         if len(user_msgs) >= 2:
@@ -411,3 +421,35 @@ def reset_logger_for_multiprocessing(
     )
     file_handler.setLevel(logging.INFO)
     logger.addHandler(file_handler)
+
+
+def update_llm_config_for_completions_logging(
+    llm_config: LLMConfig,
+    eval_output_dir: str,
+    instance_id: str,
+) -> LLMConfig:
+    """Update the LLM config for logging completions."""
+    if llm_config.log_completions:
+        llm_config.log_completions_folder = os.path.join(
+            eval_output_dir, 'llm_completions', instance_id
+        )
+        logger.info(
+            f'Logging LLM completions for instance {instance_id} to '
+            f'{llm_config.log_completions_folder}'
+        )
+    return llm_config
+
+
+# history is now available as a filtered stream of events, rather than list of pairs of (Action, Observation)
+# we rebuild the pairs here
+# for compatibility with the existing output format in evaluations
+# remove this when it's no longer necessary
+def compatibility_for_eval_history_pairs(
+    history: list[Event],
+) -> list[tuple[dict, dict]]:
+    history_pairs = []
+
+    for action, observation in get_pairs_from_events(history):
+        history_pairs.append((event_to_dict(action), event_to_dict(observation)))
+
+    return history_pairs

evaluation/webarena/run_infer.py

@@ -10,6 +10,7 @@ import pandas as pd
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
+    compatibility_for_eval_history_pairs,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -166,7 +167,7 @@ def process_instance(
 
     # Instruction is the first message from the USER
     instruction = ''
-    for event in state.history.get_events():
+    for event in state.history:
         if isinstance(event, MessageAction):
             instruction = event.content
             break
@@ -178,7 +179,7 @@ def process_instance(
     # history is now available as a stream of events, rather than list of pairs of (Action, Observation)
     # for compatibility with the existing output format, we can remake the pairs here
     # remove when it becomes unnecessary
-    histories = state.history.compatibility_for_eval_history_pairs()
+    histories = compatibility_for_eval_history_pairs(state.history)
 
     # Save the output
     output = EvalOutput(

frontend/.eslintrc

@@ -84,4 +84,4 @@
       }
     }
   ]
-}
+}

frontend/.gitignore

@@ -1,4 +1,9 @@
 # i18n translation files make by script using `make build`
 public/locales/**/*
 src/i18n/declaration.ts
-.env
+.env
+node_modules/
+/test-results/
+/playwright-report/
+/blob-report/
+/playwright/.cache/

frontend/__tests__/components/chat/chat-input.test.tsx

@@ -1,5 +1,5 @@
 import userEvent from "@testing-library/user-event";
-import { render, screen } from "@testing-library/react";
+import { fireEvent, render, screen } from "@testing-library/react";
 import { describe, afterEach, vi, it, expect } from "vitest";
 import { ChatInput } from "#/components/chat-input";
 
@@ -158,4 +158,46 @@ describe("ChatInput", () => {
     await user.tab();
     expect(onBlurMock).toHaveBeenCalledOnce();
   });
+
+  it("should handle text paste correctly", () => {
+    const onSubmit = vi.fn();
+    const onChange = vi.fn();
+
+    render(<ChatInput onSubmit={onSubmit} onChange={onChange} />);
+
+    const input = screen.getByTestId("chat-input").querySelector("textarea");
+    expect(input).toBeTruthy();
+
+    // Fire paste event with text data
+    fireEvent.paste(input!, {
+      clipboardData: {
+        getData: (type: string) => type === 'text/plain' ? 'test paste' : '',
+        files: []
+      }
+    });
+  });
+
+  it("should handle image paste correctly", () => {
+    const onSubmit = vi.fn();
+    const onImagePaste = vi.fn();
+
+    render(<ChatInput onSubmit={onSubmit} onImagePaste={onImagePaste} />);
+
+    const input = screen.getByTestId("chat-input").querySelector("textarea");
+    expect(input).toBeTruthy();
+
+    // Create a paste event with an image file
+    const file = new File(["dummy content"], "image.png", { type: "image/png" });
+
+    // Fire paste event with image data
+    fireEvent.paste(input!, {
+      clipboardData: {
+        getData: () => '',
+        files: [file]
+      }
+    });
+
+    // Verify image paste was handled
+    expect(onImagePaste).toHaveBeenCalledWith([file]);
+  });
 });

frontend/__tests__/components/chat/chat-interface.test.tsx

@@ -1,19 +1,156 @@
-import { afterEach, describe, expect, it, vi } from "vitest";
-import { render, screen, within } from "@testing-library/react";
+import { afterEach, beforeAll, describe, expect, it, vi } from "vitest";
+import { act, screen, waitFor, within } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
+import { renderWithProviders } from "test-utils";
 import { ChatInterface } from "#/components/chat-interface";
-import { SocketProvider } from "#/context/socket";
+import { addUserMessage } from "#/state/chatSlice";
+import { SUGGESTIONS } from "#/utils/suggestions";
+import * as ChatSlice from "#/state/chatSlice";
 
 // eslint-disable-next-line @typescript-eslint/no-unused-vars
 const renderChatInterface = (messages: (Message | ErrorMessage)[]) =>
-  render(<ChatInterface />, { wrapper: SocketProvider });
+  renderWithProviders(<ChatInterface />);
+
+describe("Empty state", () => {
+  const { send: sendMock } = vi.hoisted(() => ({
+    send: vi.fn(),
+  }));
+
+  const { useSocket: useSocketMock } = vi.hoisted(() => ({
+    useSocket: vi.fn(() => ({ send: sendMock, runtimeActive: true })),
+  }));
+
+  beforeAll(() => {
+    vi.mock("#/context/socket", async (importActual) => ({
+      ...(await importActual<typeof import("#/context/socket")>()),
+      useSocket: useSocketMock,
+    }));
+  });
 
-describe.skip("ChatInterface", () => {
   afterEach(() => {
     vi.clearAllMocks();
   });
 
-  it.todo("should render suggestions if empty");
+  it("should render suggestions if empty", () => {
+    const { store } = renderWithProviders(<ChatInterface />, {
+      preloadedState: {
+        chat: { messages: [] },
+      },
+    });
+
+    expect(screen.getByTestId("suggestions")).toBeInTheDocument();
+
+    act(() => {
+      store.dispatch(
+        addUserMessage({
+          content: "Hello",
+          imageUrls: [],
+          timestamp: new Date().toISOString(),
+        }),
+      );
+    });
+
+    expect(screen.queryByTestId("suggestions")).not.toBeInTheDocument();
+  });
+
+  it("should render the default suggestions", () => {
+    renderWithProviders(<ChatInterface />, {
+      preloadedState: {
+        chat: { messages: [] },
+      },
+    });
+
+    const suggestions = screen.getByTestId("suggestions");
+    const repoSuggestions = Object.keys(SUGGESTIONS.repo);
+
+    // check that there are at most 4 suggestions displayed
+    const displayedSuggestions = within(suggestions).getAllByRole("button");
+    expect(displayedSuggestions.length).toBeLessThanOrEqual(4);
+
+    // Check that each displayed suggestion is one of the repo suggestions
+    displayedSuggestions.forEach((suggestion) => {
+      expect(repoSuggestions).toContain(suggestion.textContent);
+    });
+  });
+
+  it.fails(
+    "should load the a user message to the input when selecting",
+    async () => {
+      // this is to test that the message is in the UI before the socket is called
+      useSocketMock.mockImplementation(() => ({
+        send: sendMock,
+        runtimeActive: false, // mock an inactive runtime setup
+      }));
+      const addUserMessageSpy = vi.spyOn(ChatSlice, "addUserMessage");
+      const user = userEvent.setup();
+      const { store } = renderWithProviders(<ChatInterface />, {
+        preloadedState: {
+          chat: { messages: [] },
+        },
+      });
+
+      const suggestions = screen.getByTestId("suggestions");
+      const displayedSuggestions = within(suggestions).getAllByRole("button");
+      const input = screen.getByTestId("chat-input");
+
+      await user.click(displayedSuggestions[0]);
+
+      // user message loaded to input
+      expect(addUserMessageSpy).not.toHaveBeenCalled();
+      expect(screen.queryByTestId("suggestions")).toBeInTheDocument();
+      expect(store.getState().chat.messages).toHaveLength(0);
+      expect(input).toHaveValue(displayedSuggestions[0].textContent);
+    },
+  );
+
+  it.fails(
+    "should send the message to the socket only if the runtime is active",
+    async () => {
+      useSocketMock.mockImplementation(() => ({
+        send: sendMock,
+        runtimeActive: false, // mock an inactive runtime setup
+      }));
+      const user = userEvent.setup();
+      const { rerender } = renderWithProviders(<ChatInterface />, {
+        preloadedState: {
+          chat: { messages: [] },
+        },
+      });
+
+      const suggestions = screen.getByTestId("suggestions");
+      const displayedSuggestions = within(suggestions).getAllByRole("button");
+
+      await user.click(displayedSuggestions[0]);
+      expect(sendMock).not.toHaveBeenCalled();
+
+      useSocketMock.mockImplementation(() => ({
+        send: sendMock,
+        runtimeActive: true, // mock an active runtime setup
+      }));
+      rerender(<ChatInterface />);
+
+      await waitFor(() =>
+        expect(sendMock).toHaveBeenCalledWith(expect.any(String)),
+      );
+    },
+  );
+});
+
+describe.skip("ChatInterface", () => {
+  beforeAll(() => {
+    // mock useScrollToBottom hook
+    vi.mock("#/hooks/useScrollToBottom", () => ({
+      useScrollToBottom: vi.fn(() => ({
+        scrollDomToBottom: vi.fn(),
+        onChatBodyScroll: vi.fn(),
+        hitBottom: vi.fn(),
+      })),
+    }));
+  });
+
+  afterEach(() => {
+    vi.clearAllMocks();
+  });
 
   it("should render messages", () => {
     const messages: Message[] = [
@@ -128,14 +265,14 @@ describe.skip("ChatInterface", () => {
         timestamp: new Date().toISOString(),
       },
       {
-        error: "Woops!",
+        error: true,
+        id: "",
         message: "Something went wrong",
       },
     ];
     renderChatInterface(messages);
 
     const error = screen.getByTestId("error-message");
-    expect(within(error).getByText("Woops!")).toBeInTheDocument();
     expect(within(error).getByText("Something went wrong")).toBeInTheDocument();
   });
 

frontend/__tests__/components/interactive-chat-box.test.tsx

@@ -25,6 +25,21 @@ describe("InteractiveChatBox", () => {
     within(chatBox).getByTestId("upload-image-input");
   });
 
+  it.fails("should set custom values", () => {
+    render(
+      <InteractiveChatBox
+        onSubmit={onSubmitMock}
+        onStop={onStopMock}
+        value="Hello, world!"
+      />,
+    );
+
+    const chatBox = screen.getByTestId("interactive-chat-box");
+    const chatInput = within(chatBox).getByTestId("chat-input");
+
+    expect(chatInput).toHaveValue("Hello, world!");
+  });
+
   it("should display the image previews when images are uploaded", async () => {
     const user = userEvent.setup();
     render(<InteractiveChatBox onSubmit={onSubmitMock} onStop={onStopMock} />);

frontend/__tests__/components/suggestion-item.test.tsx

@@ -0,0 +1,30 @@
+import { render, screen } from "@testing-library/react";
+import userEvent from "@testing-library/user-event";
+import { afterEach, describe, expect, it, vi } from "vitest";
+import { SuggestionItem } from "#/components/suggestion-item";
+
+describe("SuggestionItem", () => {
+  const suggestionItem = { label: "suggestion1", value: "a long text value" };
+  const onClick = vi.fn();
+
+  afterEach(() => {
+    vi.clearAllMocks();
+  });
+
+  it("should render a suggestion", () => {
+    render(<SuggestionItem suggestion={suggestionItem} onClick={onClick} />);
+
+    expect(screen.getByTestId("suggestion")).toBeInTheDocument();
+    expect(screen.getByText(/suggestion1/i)).toBeInTheDocument();
+  });
+
+  it("should call onClick when clicking a suggestion", async () => {
+    const user = userEvent.setup();
+    render(<SuggestionItem suggestion={suggestionItem} onClick={onClick} />);
+
+    const suggestion = screen.getByTestId("suggestion");
+    await user.click(suggestion);
+
+    expect(onClick).toHaveBeenCalledWith("a long text value");
+  });
+});

frontend/__tests__/components/suggestions.test.tsx

@@ -0,0 +1,60 @@
+import { render, screen } from "@testing-library/react";
+import userEvent from "@testing-library/user-event";
+import { afterEach, describe, expect, it, vi } from "vitest";
+import { Suggestions } from "#/components/suggestions";
+
+describe("Suggestions", () => {
+  const firstSuggestion = {
+    label: "first-suggestion",
+    value: "value-of-first-suggestion",
+  };
+  const secondSuggestion = {
+    label: "second-suggestion",
+    value: "value-of-second-suggestion",
+  };
+  const suggestions = [firstSuggestion, secondSuggestion];
+
+  const onSuggestionClickMock = vi.fn();
+
+  afterEach(() => {
+    vi.clearAllMocks();
+  });
+
+  it("should render suggestions", () => {
+    render(
+      <Suggestions
+        suggestions={suggestions}
+        onSuggestionClick={onSuggestionClickMock}
+      />,
+    );
+
+    expect(screen.getByTestId("suggestions")).toBeInTheDocument();
+    const suggestionElements = screen.getAllByTestId("suggestion");
+
+    expect(suggestionElements).toHaveLength(2);
+    expect(suggestionElements[0]).toHaveTextContent("first-suggestion");
+    expect(suggestionElements[1]).toHaveTextContent("second-suggestion");
+  });
+
+  it("should call onSuggestionClick when clicking a suggestion", async () => {
+    const user = userEvent.setup();
+    render(
+      <Suggestions
+        suggestions={suggestions}
+        onSuggestionClick={onSuggestionClickMock}
+      />,
+    );
+
+    const suggestionElements = screen.getAllByTestId("suggestion");
+
+    await user.click(suggestionElements[0]);
+    expect(onSuggestionClickMock).toHaveBeenCalledWith(
+      "value-of-first-suggestion",
+    );
+
+    await user.click(suggestionElements[1]);
+    expect(onSuggestionClickMock).toHaveBeenCalledWith(
+      "value-of-second-suggestion",
+    );
+  });
+});

frontend/__tests__/initial-query.test.tsx

@@ -0,0 +1,17 @@
+import { describe, it, expect } from "vitest";
+import store from "../src/store";
+import { setInitialQuery, clearInitialQuery } from "../src/state/initial-query-slice";
+
+describe("Initial Query Behavior", () => {
+  it("should clear initial query when clearInitialQuery is dispatched", () => {
+    // Set up initial query in the store
+    store.dispatch(setInitialQuery("test query"));
+    expect(store.getState().initalQuery.initialQuery).toBe("test query");
+
+    // Clear the initial query
+    store.dispatch(clearInitialQuery());
+
+    // Verify initial query is cleared
+    expect(store.getState().initalQuery.initialQuery).toBeNull();
+  });
+});

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

@@ -0,0 +1,5 @@
+import { describe, it } from "vitest";
+
+describe("App", () => {
+  it.todo("should render");
+});

frontend/__tests__/utils/cache.test.ts

@@ -0,0 +1,53 @@
+import { afterEach } from "node:test";
+import { beforeEach, describe, expect, it, vi } from "vitest";
+import { cache } from "#/utils/cache";
+
+describe("Cache", () => {
+  const testKey = "key";
+  const testData = { message: "Hello, world!" };
+  const testTTL = 1000; // 1 second
+
+  beforeEach(() => {
+    vi.useFakeTimers();
+  });
+
+  afterEach(() => {
+    vi.useRealTimers();
+  });
+
+  it("gets data from memory if not expired", () => {
+    cache.set(testKey, testData, testTTL);
+
+    expect(cache.get(testKey)).toEqual(testData);
+  });
+
+  it("should expire after 5 minutes by default", () => {
+    cache.set(testKey, testData);
+    expect(cache.get(testKey)).not.toBeNull();
+
+    vi.advanceTimersByTime(5 * 60 * 1000 + 1);
+
+    expect(cache.get(testKey)).toBeNull();
+  });
+
+  it("returns null if cached data is expired", () => {
+    cache.set(testKey, testData, testTTL);
+
+    vi.advanceTimersByTime(testTTL + 1);
+    expect(cache.get(testKey)).toBeNull();
+  });
+
+  it("deletes data from memory", () => {
+    cache.set(testKey, testData, testTTL);
+    cache.delete(testKey);
+    expect(cache.get(testKey)).toBeNull();
+  });
+
+  it("clears all data with the app prefix from memory", () => {
+    cache.set(testKey, testData, testTTL);
+    cache.set("anotherKey", { data: "More data" }, testTTL);
+    cache.clearAll();
+    expect(cache.get(testKey)).toBeNull();
+    expect(cache.get("anotherKey")).toBeNull();
+  });
+});

frontend/__tests__/utils/extractModelAndProvider.test.ts

@@ -78,4 +78,3 @@ describe("extractModelAndProvider", () => {
     });
   });
 });
-

frontend/__tests__/utils/organizeModelsAndProviders.test.ts

@@ -63,4 +63,3 @@ test("organizeModelsAndProviders", () => {
     },
   });
 });
-

frontend/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "openhands-frontend",
-  "version": "0.12.0",
+  "version": "0.13.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "openhands-frontend",
-      "version": "0.12.0",
+      "version": "0.13.0",
       "dependencies": {
         "@monaco-editor/react": "^4.6.0",
         "@nextui-org/react": "^2.4.8",
@@ -26,6 +26,7 @@
         "isbot": "^5.1.17",
         "jose": "^5.9.4",
         "monaco-editor": "^0.52.0",
+        "posthog-js": "^1.176.0",
         "react": "^18.3.1",
         "react-dom": "^18.3.1",
         "react-highlight": "^0.15.0",
@@ -45,6 +46,7 @@
         "ws": "^8.18.0"
       },
       "devDependencies": {
+        "@playwright/test": "^1.48.2",
         "@remix-run/dev": "^2.11.2",
         "@remix-run/testing": "^2.11.2",
         "@tailwindcss/typography": "^0.5.15",
@@ -61,6 +63,7 @@
         "@typescript-eslint/parser": "^7.18.0",
         "@vitest/coverage-v8": "^1.6.0",
         "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",
@@ -3378,6 +3381,21 @@
         "url": "https://opencollective.com/unts"
       }
     },
+    "node_modules/@playwright/test": {
+      "version": "1.48.2",
+      "resolved": "https://registry.npmjs.org/@playwright/test/-/test-1.48.2.tgz",
+      "integrity": "sha512-54w1xCWfXuax7dz4W2M9uw0gDyh+ti/0K/MxcCUxChFh37kkdxPdfZDw5QBbuPUJHr1CiHJ1hXgSs+GgeQc5Zw==",
+      "dev": true,
+      "dependencies": {
+        "playwright": "1.48.2"
+      },
+      "bin": {
+        "playwright": "cli.js"
+      },
+      "engines": {
+        "node": ">=18"
+      }
+    },
     "node_modules/@polka/url": {
       "version": "1.0.0-next.28",
       "resolved": "https://registry.npmjs.org/@polka/url/-/url-1.0.0-next.28.tgz",
@@ -7864,6 +7882,16 @@
         "node": ">=6.6.0"
       }
     },
+    "node_modules/core-js": {
+      "version": "3.38.1",
+      "resolved": "https://registry.npmjs.org/core-js/-/core-js-3.38.1.tgz",
+      "integrity": "sha512-OP35aUorbU3Zvlx7pjsFdu1rGNnD4pgw/CWoYzRY3t2EzoVT7shKHY1dlAy3f41cGIO7ZDPQimhGFTlEYkG/Hw==",
+      "hasInstallScript": true,
+      "funding": {
+        "type": "opencollective",
+        "url": "https://opencollective.com/core-js"
+      }
+    },
     "node_modules/core-util-is": {
       "version": "1.0.3",
       "resolved": "https://registry.npmjs.org/core-util-is/-/core-util-is-1.0.3.tgz",
@@ -7896,6 +7924,24 @@
         }
       }
     },
+    "node_modules/cross-env": {
+      "version": "7.0.3",
+      "resolved": "https://registry.npmjs.org/cross-env/-/cross-env-7.0.3.tgz",
+      "integrity": "sha512-+/HKd6EgcQCJGh2PSjZuUitQBQynKor4wrFbRg4DtAgS1aWO+gU52xpH7M9ScGgXSYmAVS9bIJ8EzuaGw0oNAw==",
+      "dev": true,
+      "dependencies": {
+        "cross-spawn": "^7.0.1"
+      },
+      "bin": {
+        "cross-env": "src/bin/cross-env.js",
+        "cross-env-shell": "src/bin/cross-env-shell.js"
+      },
+      "engines": {
+        "node": ">=10.14",
+        "npm": ">=6",
+        "yarn": ">=1"
+      }
+    },
     "node_modules/cross-fetch": {
       "version": "4.0.0",
       "resolved": "https://registry.npmjs.org/cross-fetch/-/cross-fetch-4.0.0.tgz",
@@ -9666,6 +9712,11 @@
         "url": "https://github.com/sponsors/wooorm"
       }
     },
+    "node_modules/fflate": {
+      "version": "0.4.8",
+      "resolved": "https://registry.npmjs.org/fflate/-/fflate-0.4.8.tgz",
+      "integrity": "sha512-FJqqoDBR00Mdj9ppamLa/Y7vxm+PRmNWA67N846RvsoYVMKB4q3y/de5PA7gUmRMYK/8CMz2GDZQmCRN1wBcWA=="
+    },
     "node_modules/file-entry-cache": {
       "version": "6.0.1",
       "resolved": "https://registry.npmjs.org/file-entry-cache/-/file-entry-cache-6.0.1.tgz",
@@ -19406,6 +19457,50 @@
         "pathe": "^1.1.2"
       }
     },
+    "node_modules/playwright": {
+      "version": "1.48.2",
+      "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.48.2.tgz",
+      "integrity": "sha512-NjYvYgp4BPmiwfe31j4gHLa3J7bD2WiBz8Lk2RoSsmX38SVIARZ18VYjxLjAcDsAhA+F4iSEXTSGgjua0rrlgQ==",
+      "dev": true,
+      "dependencies": {
+        "playwright-core": "1.48.2"
+      },
+      "bin": {
+        "playwright": "cli.js"
+      },
+      "engines": {
+        "node": ">=18"
+      },
+      "optionalDependencies": {
+        "fsevents": "2.3.2"
+      }
+    },
+    "node_modules/playwright-core": {
+      "version": "1.48.2",
+      "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.48.2.tgz",
+      "integrity": "sha512-sjjw+qrLFlriJo64du+EK0kJgZzoQPsabGF4lBvsid+3CNIZIYLgnMj9V6JY5VhM2Peh20DJWIVpVljLLnlawA==",
+      "dev": true,
+      "bin": {
+        "playwright-core": "cli.js"
+      },
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/playwright/node_modules/fsevents": {
+      "version": "2.3.2",
+      "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz",
+      "integrity": "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==",
+      "dev": true,
+      "hasInstallScript": true,
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": "^8.16.0 || ^10.6.0 || >=11.0.0"
+      }
+    },
     "node_modules/possible-typed-array-names": {
       "version": "1.0.0",
       "resolved": "https://registry.npmjs.org/possible-typed-array-names/-/possible-typed-array-names-1.0.0.tgz",
@@ -19653,6 +19748,31 @@
       "resolved": "https://registry.npmjs.org/postcss-value-parser/-/postcss-value-parser-4.2.0.tgz",
       "integrity": "sha512-1NNCs6uurfkVbeXG4S8JFT9t19m45ICnif8zWLd5oPSZ50QnwMfK+H3jv408d4jw/7Bttv5axS5IiHoLaVNHeQ=="
     },
+    "node_modules/posthog-js": {
+      "version": "1.176.0",
+      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.176.0.tgz",
+      "integrity": "sha512-T5XKNtRzp7q6CGb7Vc7wAI76rWap9fiuDUPxPsyPBPDkreKya91x9RIsSapAVFafwD1AEin1QMczCmt9Le9BWw==",
+      "dependencies": {
+        "core-js": "^3.38.1",
+        "fflate": "^0.4.8",
+        "preact": "^10.19.3",
+        "web-vitals": "^4.2.0"
+      }
+    },
+    "node_modules/posthog-js/node_modules/web-vitals": {
+      "version": "4.2.4",
+      "resolved": "https://registry.npmjs.org/web-vitals/-/web-vitals-4.2.4.tgz",
+      "integrity": "sha512-r4DIlprAGwJ7YM11VZp4R884m0Vmgr6EAKe3P+kO0PPj3Unqyvv59rczf6UiGcb9Z8QxZVcqKNwv/g0WNdWwsw=="
+    },
+    "node_modules/preact": {
+      "version": "10.24.3",
+      "resolved": "https://registry.npmjs.org/preact/-/preact-10.24.3.tgz",
+      "integrity": "sha512-Z2dPnBnMUfyQfSQ+GBdsGa16hz35YmLmtTLhM169uW944hYL6xzTYkJjC07j+Wosz733pMWx0fgON3JNw1jJQA==",
+      "funding": {
+        "type": "opencollective",
+        "url": "https://opencollective.com/preact"
+      }
+    },
     "node_modules/prelude-ls": {
       "version": "1.2.1",
       "resolved": "https://registry.npmjs.org/prelude-ls/-/prelude-ls-1.2.1.tgz",

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.12.0",
+  "version": "0.13.0",
   "private": true,
   "type": "module",
   "engines": {
@@ -25,6 +25,7 @@
     "isbot": "^5.1.17",
     "jose": "^5.9.4",
     "monaco-editor": "^0.52.0",
+    "posthog-js": "^1.176.0",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
     "react-highlight": "^0.15.0",
@@ -44,11 +45,12 @@
     "ws": "^8.18.0"
   },
   "scripts": {
-    "dev": "npm run make-i18n && VITE_MOCK_API=false remix vite:dev",
-    "dev:mock": "npm run make-i18n && VITE_MOCK_API=true remix vite:dev",
+    "dev": "npm run make-i18n && cross-env VITE_MOCK_API=false remix vite:dev",
+    "dev:mock": "npm run make-i18n && cross-env VITE_MOCK_API=true remix vite:dev",
     "build": "npm run make-i18n && tsc && remix vite:build",
     "start": "npx sirv-cli build/ --single",
     "test": "vitest run",
+    "test:e2e": "playwright test",
     "test:coverage": "npm run make-i18n && vitest run --coverage",
     "dev_wsl": "VITE_WATCH_USE_POLLING=true vite",
     "preview": "vite preview",
@@ -70,6 +72,7 @@
     ]
   },
   "devDependencies": {
+    "@playwright/test": "^1.48.2",
     "@remix-run/dev": "^2.11.2",
     "@remix-run/testing": "^2.11.2",
     "@tailwindcss/typography": "^0.5.15",
@@ -86,6 +89,7 @@
     "@typescript-eslint/parser": "^7.18.0",
     "@vitest/coverage-v8": "^1.6.0",
     "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",

frontend/playwright.config.ts

@@ -0,0 +1,79 @@
+import { defineConfig, devices } from "@playwright/test";
+
+/**
+ * Read environment variables from file.
+ * https://github.com/motdotla/dotenv
+ */
+// import dotenv from 'dotenv';
+// import path from 'path';
+// dotenv.config({ path: path.resolve(__dirname, '.env') });
+
+/**
+ * See https://playwright.dev/docs/test-configuration.
+ */
+export default defineConfig({
+  testDir: "./tests",
+  /* Run tests in files in parallel */
+  fullyParallel: true,
+  /* Fail the build on CI if you accidentally left test.only in the source code. */
+  forbidOnly: !!process.env.CI,
+  /* Retry on CI only */
+  retries: process.env.CI ? 2 : 0,
+  /* Opt out of parallel tests on CI. */
+  workers: process.env.CI ? 1 : undefined,
+  /* Reporter to use. See https://playwright.dev/docs/test-reporters */
+  reporter: "html",
+  /* Shared settings for all the projects below. See https://playwright.dev/docs/api/class-testoptions. */
+  use: {
+    /* Base URL to use in actions like `await page.goto('/')`. */
+    baseURL: "http://127.0.0.1:3000",
+
+    /* Collect trace when retrying the failed test. See https://playwright.dev/docs/trace-viewer */
+    trace: "on-first-retry",
+  },
+
+  /* Configure projects for major browsers */
+  projects: [
+    {
+      name: "chromium",
+      use: { ...devices["Desktop Chrome"] },
+    },
+
+    {
+      name: "firefox",
+      use: { ...devices["Desktop Firefox"] },
+    },
+
+    {
+      name: "webkit",
+      use: { ...devices["Desktop Safari"] },
+    },
+
+    /* Test against mobile viewports. */
+    // {
+    //   name: 'Mobile Chrome',
+    //   use: { ...devices['Pixel 5'] },
+    // },
+    // {
+    //   name: 'Mobile Safari',
+    //   use: { ...devices['iPhone 12'] },
+    // },
+
+    /* Test against branded browsers. */
+    // {
+    //   name: 'Microsoft Edge',
+    //   use: { ...devices['Desktop Edge'], channel: 'msedge' },
+    // },
+    // {
+    //   name: 'Google Chrome',
+    //   use: { ...devices['Desktop Chrome'], channel: 'chrome' },
+    // },
+  ],
+
+  /* Run your local dev server before starting the tests */
+  webServer: {
+    command: "npm run dev:mock -- --port 3000",
+    url: "http://127.0.0.1:3000",
+    reuseExistingServer: !process.env.CI,
+  },
+});

frontend/src/api/github.ts

@@ -122,6 +122,9 @@ export const retrieveGitHubUser = async (
       id: data.id,
       login: data.login,
       avatar_url: data.avatar_url,
+      company: data.company,
+      name: data.name,
+      email: data.email,
     };
 
     return user;
@@ -136,33 +139,6 @@ export const retrieveGitHubUser = async (
   return error;
 };
 
-/**
- * Given a GitHub token and a repository name, creates a repository for the authenticated user
- * @param token The GitHub token
- * @param repositoryName Name of the repository to create
- * @param description Description of the repository
- * @param isPrivate Boolean indicating if the repository should be private
- * @returns The created repository or an error response
- */
-export const createGitHubRepository = async (
-  token: string,
-  repositoryName: string,
-  description?: string,
-  isPrivate = true,
-): Promise<GitHubRepository | GitHubErrorReponse> => {
-  const response = await fetch("https://api.github.com/user/repos", {
-    method: "POST",
-    headers: generateGitHubAPIHeaders(token),
-    body: JSON.stringify({
-      name: repositoryName,
-      description,
-      private: isPrivate,
-    }),
-  });
-
-  return response.json();
-};
-
 export const retrieveLatestGitHubCommit = async (
   token: string,
   repository: string,

frontend/src/api/open-hands.ts

@@ -1,4 +1,5 @@
 import { request } from "#/services/api";
+import { cache } from "#/utils/cache";
 import {
   SaveFileSuccessResponse,
   FileUploadSuccessResponse,
@@ -15,7 +16,13 @@ class OpenHands {
    * @returns List of models available
    */
   static async getModels(): Promise<string[]> {
-    return request("/api/options/models");
+    const cachedData = cache.get<string[]>("models");
+    if (cachedData) return cachedData;
+
+    const data = await request("/api/options/models");
+    cache.set("models", data);
+
+    return data;
   }
 
   /**
@@ -23,7 +30,13 @@ class OpenHands {
    * @returns List of agents available
    */
   static async getAgents(): Promise<string[]> {
-    return request(`/api/options/agents`);
+    const cachedData = cache.get<string[]>("agents");
+    if (cachedData) return cachedData;
+
+    const data = await request(`/api/options/agents`);
+    cache.set("agents", data);
+
+    return data;
   }
 
   /**
@@ -31,11 +44,23 @@ class OpenHands {
    * @returns List of security analyzers available
    */
   static async getSecurityAnalyzers(): Promise<string[]> {
-    return request(`/api/options/security-analyzers`);
+    const cachedData = cache.get<string[]>("agents");
+    if (cachedData) return cachedData;
+
+    const data = await request(`/api/options/security-analyzers`);
+    cache.set("security-analyzers", data);
+
+    return data;
   }
 
   static async getConfig(): Promise<GetConfigResponse> {
-    return request("/config.json");
+    const cachedData = cache.get<GetConfigResponse>("config");
+    if (cachedData) return cachedData;
+
+    const data = await request("/config.json");
+    cache.set("config", data);
+
+    return data;
   }
 
   /**

frontend/src/assets/arrow-send.svg

@@ -2,4 +2,4 @@
   <path fill-rule="evenodd" clip-rule="evenodd"
     d="M11.5304 6.46978L10.4697 7.53044L6.75006 3.81077L6.75006 17.0001H5.25006L5.25006 3.81077L1.53039 7.53044L0.469727 6.46978L6.00006 0.939453L11.5304 6.46978Z"
     fill="white" />
-</svg>
+</svg>

frontend/src/assets/branding/all-hands-logo-spark.svg

@@ -32,4 +32,4 @@
       <rect width="69" height="46" fill="white" transform="translate(0.5)" />
     </clipPath>
   </defs>
-</svg>
+</svg>

frontend/src/assets/branding/github-logo.svg

@@ -2,4 +2,4 @@
   <path
     d="M15.359 21V17.319C15.3974 16.8654 15.3314 16.4095 15.1651 15.9814C14.9989 15.5534 14.7363 15.1631 14.3949 14.8364C17.6154 14.5035 21 13.3716 21 8.17826C20.9997 6.85027 20.4489 5.57321 19.4615 4.61139C19.9291 3.44954 19.896 2.16532 19.3692 1.02548C19.3692 1.02548 18.159 0.692576 15.359 2.43321C13.0082 1.84237 10.5302 1.84237 8.17949 2.43321C5.37949 0.692576 4.16923 1.02548 4.16923 1.02548C3.64244 2.16532 3.60938 3.44954 4.07692 4.61139C3.08218 5.58034 2.53079 6.86895 2.53846 8.2068C2.53846 13.3621 5.92308 14.494 9.14359 14.865C8.80615 15.1883 8.54591 15.574 8.3798 15.9968C8.2137 16.4196 8.14544 16.8701 8.17949 17.319V21M8.17949 18.1465C3.05128 19.5732 3.05128 15.7686 1 15.293L8.17949 18.1465Z"
     stroke="white" stroke-linecap="round" stroke-linejoin="round" />
-</svg>
+</svg>

frontend/src/assets/clip.svg

@@ -2,4 +2,4 @@
   <path fill-rule="evenodd" clip-rule="evenodd"
     d="M10.5 3.75C9.25736 3.75 8.25 4.75736 8.25 6V16.5C8.25 18.5711 9.92893 20.25 12 20.25C14.0711 20.25 15.75 18.5711 15.75 16.5V7H17.25V16.5C17.25 19.3995 14.8995 21.75 12 21.75C9.1005 21.75 6.75 19.3995 6.75 16.5V6C6.75 3.92893 8.42893 2.25 10.5 2.25C12.5711 2.25 14.25 3.92893 14.25 6V16C14.25 17.2426 13.2426 18.25 12 18.25C10.7574 18.25 9.75 17.2426 9.75 16V7H11.25V16C11.25 16.4142 11.5858 16.75 12 16.75C12.4142 16.75 12.75 16.4142 12.75 16V6C12.75 4.75736 11.7426 3.75 10.5 3.75Z"
     fill="white" />
-</svg>
+</svg>

frontend/src/assets/clipboard.svg

@@ -32,4 +32,4 @@
       <rect width="54" height="75" fill="white" />
     </clipPath>
   </defs>
-</svg>
+</svg>

frontend/src/assets/default-user.svg

@@ -2,4 +2,4 @@
   <path
     d="M13.0919 10.5917C13.9089 9.94891 14.5052 9.06746 14.7979 8.06997C15.0906 7.07249 15.0652 6.00858 14.7251 5.02625C14.385 4.04391 13.7471 3.19202 12.9003 2.58907C12.0535 1.98612 11.0398 1.66211 10.0002 1.66211C8.9607 1.66211 7.947 1.98612 7.10018 2.58907C6.25336 3.19202 5.61553 4.04391 5.27542 5.02625C4.93531 6.00858 4.90984 7.07249 5.20254 8.06997C5.49525 9.06746 6.09158 9.94891 6.90858 10.5917C5.50864 11.1526 4.28715 12.0828 3.37432 13.2833C2.46149 14.4838 1.89154 15.9094 1.72524 17.4084C1.7132 17.5178 1.72284 17.6285 1.7536 17.7342C1.78435 17.8399 1.83563 17.9386 1.9045 18.0245C2.04359 18.1979 2.24589 18.309 2.46691 18.3334C2.68792 18.3577 2.90954 18.2932 3.08301 18.1541C3.25648 18.015 3.3676 17.8127 3.39191 17.5917C3.5749 15.9627 4.35165 14.4582 5.57376 13.3657C6.79587 12.2732 8.37766 11.6692 10.0169 11.6692C11.6562 11.6692 13.2379 12.2732 14.4601 13.3657C15.6822 14.4582 16.4589 15.9627 16.6419 17.5917C16.6646 17.7965 16.7623 17.9856 16.9162 18.1225C17.0701 18.2595 17.2692 18.3346 17.4752 18.3334H17.5669C17.7854 18.3082 17.985 18.1978 18.1224 18.0261C18.2597 17.8544 18.3237 17.6353 18.3002 17.4167C18.1332 15.9135 17.5601 14.4842 16.6426 13.2819C15.7251 12.0795 14.4977 11.1496 13.0919 10.5917ZM10.0002 10C9.34097 10 8.69651 9.80453 8.14834 9.43825C7.60018 9.07198 7.17294 8.55139 6.92064 7.9423C6.66835 7.33321 6.60234 6.66299 6.73096 6.01639C6.85957 5.36979 7.17704 4.77584 7.64322 4.30967C8.10939 3.84349 8.70334 3.52602 9.34994 3.39741C9.99654 3.26879 10.6668 3.3348 11.2759 3.58709C11.8849 3.83938 12.4055 4.26662 12.7718 4.81479C13.1381 5.36295 13.3336 6.00742 13.3336 6.66669C13.3336 7.55074 12.9824 8.39859 12.3573 9.02371C11.7321 9.64883 10.8843 10 10.0002 10Z"
     fill="#262626" />
-</svg>
+</svg>

frontend/src/assets/docs.svg

@@ -24,4 +24,4 @@
       <rect width="23.33" height="18.67" fill="white" transform="translate(2.33496 4.66504)" />
     </clipPath>
   </defs>
-</svg>
+</svg>

frontend/src/assets/external-link.svg

@@ -4,4 +4,4 @@
   <path
     d="M4.33333 3.66667C3.59695 3.66667 3 4.26362 3 5V11.6667C3 12.403 3.59695 13 4.33333 13H11C11.7364 13 12.3333 12.403 12.3333 11.6667V9.66667H11.3333V11.6667C11.3333 11.8508 11.1841 12 11 12H4.33333C4.14924 12 4 11.8508 4 11.6667V5C4 4.81591 4.14924 4.66667 4.33333 4.66667H6.33333V3.66667H4.33333Z"
     fill="#EEEEEE" />
-</svg>
+</svg>

frontend/src/assets/lightbulb.svg

@@ -2,4 +2,4 @@
   <path
     d="M11.3931 1.88021C10.78 1.37593 10.062 1.01489 9.29157 0.823438C8.52113 0.631981 7.71767 0.614934 6.9398 0.773542C5.90405 0.982756 4.95379 1.49492 4.20959 2.24506C3.46538 2.9952 2.96078 3.9495 2.7598 4.98688C2.61303 5.76469 2.6397 6.56531 2.83791 7.33163C3.03611 8.09795 3.40097 8.8111 3.90647 9.42021C4.37559 9.94959 4.64449 10.6266 4.66647 11.3335V13.3335C4.66647 13.864 4.87718 14.3727 5.25225 14.7478C5.62732 15.1228 6.13603 15.3335 6.66647 15.3335H9.33313C9.86356 15.3335 10.3723 15.1228 10.7473 14.7478C11.1224 14.3727 11.3331 13.864 11.3331 13.3335V11.4602C11.3555 10.6797 11.6423 9.92983 12.1465 9.33354C13.0299 8.24073 13.4463 6.84342 13.3052 5.44529C13.1642 4.04716 12.477 2.7612 11.3931 1.86687V1.88021ZM9.9998 13.3335C9.9998 13.5104 9.92956 13.6799 9.80454 13.8049C9.67951 13.93 9.50994 14.0002 9.33313 14.0002H6.66647C6.48965 14.0002 6.32009 13.93 6.19506 13.8049C6.07004 13.6799 5.9998 13.5104 5.9998 13.3335V12.6669H9.9998V13.3335ZM11.1131 8.50688C10.4428 9.30194 10.0517 10.2949 9.9998 11.3335H8.66647V9.33354C8.66647 9.15673 8.59623 8.98716 8.4712 8.86214C8.34618 8.73711 8.17661 8.66688 7.9998 8.66688C7.82299 8.66688 7.65342 8.73711 7.52839 8.86214C7.40337 8.98716 7.33313 9.15673 7.33313 9.33354V11.3335H5.9998C5.98221 10.3123 5.60443 9.33005 4.93313 8.56021C4.49023 8.02954 4.19239 7.39316 4.06867 6.71311C3.94495 6.03306 3.99957 5.33255 4.22719 4.6799C4.45481 4.02724 4.84768 3.4447 5.36748 2.98909C5.88728 2.53348 6.51627 2.22034 7.19313 2.08021C7.77483 1.96044 8.37591 1.9717 8.95271 2.11319C9.52952 2.25467 10.0676 2.52282 10.5278 2.89818C10.9881 3.27353 11.359 3.74666 11.6136 4.28322C11.8682 4.81978 12.0001 5.4063 11.9998 6.00021C12.0047 6.91345 11.6912 7.79985 11.1131 8.50688Z"
     fill="white" />
-</svg>
+</svg>

frontend/src/assets/loading-outer.svg

@@ -1,4 +1,4 @@
 <svg width="66" height="66" viewBox="0 0 66 66" fill="none" xmlns="http://www.w3.org/2000/svg">
   <path d="M63 33C63 16.4315 49.5685 3 33 3C16.4315 3 3 16.4315 3 33C3 49.5685 16.4315 63 33 63"
     stroke="#007AFF" stroke-width="6" stroke-linecap="round" />
-</svg>
+</svg>

frontend/src/assets/message.svg

@@ -2,4 +2,4 @@
   <path
     d="M19.8335 8.16634H8.16683C7.85741 8.16634 7.56066 8.28926 7.34187 8.50805C7.12308 8.72684 7.00016 9.02359 7.00016 9.33301C7.00016 9.64243 7.12308 9.93917 7.34187 10.158C7.56066 10.3768 7.85741 10.4997 8.16683 10.4997H19.8335C20.1429 10.4997 20.4397 10.3768 20.6585 10.158C20.8772 9.93917 21.0002 9.64243 21.0002 9.33301C21.0002 9.02359 20.8772 8.72684 20.6585 8.50805C20.4397 8.28926 20.1429 8.16634 19.8335 8.16634ZM19.8335 12.833H8.16683C7.85741 12.833 7.56066 12.9559 7.34187 13.1747C7.12308 13.3935 7.00016 13.6903 7.00016 13.9997C7.00016 14.3091 7.12308 14.6058 7.34187 14.8246C7.56066 15.0434 7.85741 15.1663 8.16683 15.1663H19.8335C20.1429 15.1663 20.4397 15.0434 20.6585 14.8246C20.8772 14.6058 21.0002 14.3091 21.0002 13.9997C21.0002 13.6903 20.8772 13.3935 20.6585 13.1747C20.4397 12.9559 20.1429 12.833 19.8335 12.833ZM22.1668 2.33301H5.8335C4.90524 2.33301 4.015 2.70176 3.35862 3.35813C2.70225 4.01451 2.3335 4.90475 2.3335 5.83301V17.4997C2.3335 18.4279 2.70225 19.3182 3.35862 19.9745C4.015 20.6309 4.90524 20.9997 5.8335 20.9997H19.3552L23.6718 25.328C23.7808 25.4361 23.9101 25.5217 24.0523 25.5797C24.1944 25.6378 24.3466 25.6672 24.5002 25.6663C24.6532 25.6703 24.805 25.6383 24.9435 25.573C25.1565 25.4855 25.3389 25.3369 25.4677 25.1458C25.5964 24.9548 25.6657 24.73 25.6668 24.4997V5.83301C25.6668 4.90475 25.2981 4.01451 24.6417 3.35813C23.9853 2.70176 23.0951 2.33301 22.1668 2.33301ZM23.3335 21.688L20.6618 19.0047C20.5528 18.8965 20.4235 18.811 20.2814 18.7529C20.1392 18.6949 19.987 18.6655 19.8335 18.6663H5.8335C5.52408 18.6663 5.22733 18.5434 5.00854 18.3246C4.78975 18.1058 4.66683 17.8091 4.66683 17.4997V5.83301C4.66683 5.52359 4.78975 5.22684 5.00854 5.00805C5.22733 4.78926 5.52408 4.66634 5.8335 4.66634H22.1668C22.4762 4.66634 22.773 4.78926 22.9918 5.00805C23.2106 5.22684 23.3335 5.52359 23.3335 5.83301V21.688Z"
     fill="white" />
-</svg>
+</svg>

frontend/src/assets/new-project.svg

@@ -3,4 +3,4 @@
   <path
     d="M20.4165 13.0837H14.9165V7.58366C14.9165 7.34054 14.8199 7.10739 14.648 6.93548C14.4761 6.76357 14.243 6.66699 13.9998 6.66699C13.7567 6.66699 13.5236 6.76357 13.3517 6.93548C13.1797 7.10739 13.0832 7.34054 13.0832 7.58366V13.0837H7.58317C7.34006 13.0837 7.1069 13.1802 6.93499 13.3521C6.76308 13.5241 6.6665 13.7572 6.6665 14.0003C6.6665 14.2434 6.76308 14.4766 6.93499 14.6485C7.1069 14.8204 7.34006 14.917 7.58317 14.917H13.0832V20.417C13.0832 20.6601 13.1797 20.8933 13.3517 21.0652C13.5236 21.2371 13.7567 21.3337 13.9998 21.3337C14.243 21.3337 14.4761 21.2371 14.648 21.0652C14.8199 20.8933 14.9165 20.6601 14.9165 20.417V14.917H20.4165C20.6596 14.917 20.8928 14.8204 21.0647 14.6485C21.2366 14.4766 21.3332 14.2434 21.3332 14.0003C21.3332 13.7572 21.2366 13.5241 21.0647 13.3521C20.8928 13.1802 20.6596 13.0837 20.4165 13.0837Z"
     fill="black" />
-</svg>
+</svg>

frontend/src/assets/refresh.svg

@@ -2,4 +2,4 @@
   <path
     d="M4.26446 0.763647C4.39463 0.633472 4.60569 0.633472 4.73586 0.763647L5.73586 1.76365C5.86604 1.89382 5.86604 2.10488 5.73586 2.23505L4.73586 3.23505C4.60569 3.36523 4.39463 3.36523 4.26446 3.23505C4.13429 3.10488 4.13429 2.89382 4.26446 2.76365L4.69542 2.33268H4.16683C2.98426 2.33268 2.00016 3.31678 2.00016 4.49935C2.00016 5.68192 2.98426 6.66602 4.16683 6.66602C5.3494 6.66602 6.3335 5.68192 6.3335 4.49935C6.3335 4.31525 6.48273 4.16602 6.66683 4.16602C6.85092 4.16602 7.00016 4.31525 7.00016 4.49935C7.00016 6.05011 5.71759 7.33268 4.16683 7.33268C2.61607 7.33268 1.3335 6.05011 1.3335 4.49935C1.3335 2.94859 2.61607 1.66602 4.16683 1.66602H4.69542L4.26446 1.23505C4.13429 1.10488 4.13429 0.893821 4.26446 0.763647Z"
     fill="white" />
-</svg>
+</svg>

frontend/src/components/AgentStatusBar.tsx

@@ -1,6 +1,7 @@
 import React, { useEffect } from "react";
 import { useTranslation } from "react-i18next";
 import { useSelector } from "react-redux";
+import toast from "react-hot-toast";
 import { I18nKey } from "#/i18n/declaration";
 import { RootState } from "#/store";
 import AgentState from "#/types/AgentState";
@@ -16,7 +17,7 @@ enum IndicatorColor {
 }
 
 function AgentStatusBar() {
-  const { t } = useTranslation();
+  const { t, i18n } = useTranslation();
   const { curAgentState } = useSelector((state: RootState) => state.agent);
   const { curStatusMessage } = useSelector((state: RootState) => state.status);
 
@@ -94,15 +95,27 @@ function AgentStatusBar() {
   const [statusMessage, setStatusMessage] = React.useState<string>("");
 
   React.useEffect(() => {
-    if (curAgentState === AgentState.LOADING) {
-      const trimmedCustomMessage = curStatusMessage.status.trim();
-      if (trimmedCustomMessage) {
-        setStatusMessage(t(trimmedCustomMessage));
-        return;
+    let message = curStatusMessage.message || "";
+    if (curStatusMessage?.id) {
+      const id = curStatusMessage.id.trim();
+      if (i18n.exists(id)) {
+        message = t(curStatusMessage.id.trim()) || message;
       }
     }
+    if (curStatusMessage?.type === "error") {
+      toast.error(message);
+      return;
+    }
+    if (curAgentState === AgentState.LOADING && message.trim()) {
+      setStatusMessage(message);
+    } else {
+      setStatusMessage(AgentStatusMap[curAgentState].message);
+    }
+  }, [curStatusMessage.id]);
+
+  React.useEffect(() => {
     setStatusMessage(AgentStatusMap[curAgentState].message);
-  }, [curAgentState, curStatusMessage.status]);
+  }, [curAgentState]);
 
   return (
     <div className="flex flex-col items-center">

frontend/src/components/Jupyter.tsx

@@ -25,7 +25,11 @@ function JupyterCell({ cell }: IJupyterCell): JSX.Element {
           className="scrollbar-custom scrollbar-thumb-gray-500 hover:scrollbar-thumb-gray-400 dark:scrollbar-thumb-white/10 dark:hover:scrollbar-thumb-white/20 overflow-auto px-5"
           style={{ padding: 0, marginBottom: 0, fontSize: "0.75rem" }}
         >
-          <SyntaxHighlighter language="python" style={atomOneDark}>
+          <SyntaxHighlighter
+            language="python"
+            style={atomOneDark}
+            wrapLongLines
+          >
             {code}
           </SyntaxHighlighter>
         </pre>
@@ -78,7 +82,11 @@ function JupyterCell({ cell }: IJupyterCell): JSX.Element {
   );
 }
 
-function JupyterEditor(): JSX.Element {
+interface JupyterEditorProps {
+  maxWidth: number;
+}
+
+function JupyterEditor({ maxWidth }: JupyterEditorProps) {
   const { t } = useTranslation();
 
   const { cells } = useSelector((state: RootState) => state.jupyter);
@@ -88,7 +96,7 @@ function JupyterEditor(): JSX.Element {
     useScrollToBottom(jupyterRef);
 
   return (
-    <div className="flex-1">
+    <div className="flex-1" style={{ maxWidth }}>
       <div
         className="overflow-y-auto h-full"
         ref={jupyterRef}

frontend/src/components/analytics-consent-form-modal.tsx

@@ -0,0 +1,42 @@
+import { useFetcher } from "@remix-run/react";
+import { ModalBackdrop } from "./modals/modal-backdrop";
+import ModalBody from "./modals/ModalBody";
+import ModalButton from "./buttons/ModalButton";
+import {
+  BaseModalTitle,
+  BaseModalDescription,
+} from "./modals/confirmation-modals/BaseModal";
+
+export function AnalyticsConsentFormModal() {
+  const fetcher = useFetcher({ key: "set-consent" });
+
+  return (
+    <ModalBackdrop>
+      <fetcher.Form
+        method="POST"
+        action="/set-consent"
+        className="flex flex-col gap-2"
+      >
+        <ModalBody>
+          <BaseModalTitle title="Your Privacy Preferences" />
+          <BaseModalDescription>
+            We use tools to understand how our application is used to improve
+            your experience. You can enable or disable analytics. Your
+            preferences will be stored and can be updated anytime.
+          </BaseModalDescription>
+
+          <label className="flex gap-2 items-center self-start">
+            <input name="analytics" type="checkbox" defaultChecked />
+            Send anonymous usage data
+          </label>
+
+          <ModalButton
+            type="submit"
+            text="Confirm Preferences"
+            className="bg-primary text-white w-full hover:opacity-80"
+          />
+        </ModalBody>
+      </fetcher.Form>
+    </ModalBackdrop>
+  );
+}

frontend/src/components/buttons/ModalButton.tsx

@@ -2,6 +2,7 @@ import clsx from "clsx";
 import React from "react";
 
 interface ModalButtonProps {
+  testId?: string;
   variant?: "default" | "text-like";
   onClick?: () => void;
   text: string;
@@ -13,6 +14,7 @@ interface ModalButtonProps {
 }
 
 function ModalButton({
+  testId,
   variant = "default",
   onClick,
   text,
@@ -24,6 +26,7 @@ function ModalButton({
 }: ModalButtonProps) {
   return (
     <button
+      data-testid={testId}
       type={type === "submit" ? "submit" : "button"}
       disabled={disabled}
       onClick={onClick}

frontend/src/components/chat-input.tsx

@@ -16,6 +16,7 @@ interface ChatInputProps {
   onChange?: (message: string) => void;
   onFocus?: () => void;
   onBlur?: () => void;
+  onImagePaste?: (files: File[]) => void;
   className?: React.HTMLAttributes<HTMLDivElement>["className"];
 }
 
@@ -32,9 +33,51 @@ export function ChatInput({
   onChange,
   onFocus,
   onBlur,
+  onImagePaste,
   className,
 }: ChatInputProps) {
   const textareaRef = React.useRef<HTMLTextAreaElement>(null);
+  const [isDraggingOver, setIsDraggingOver] = React.useState(false);
+
+  const handlePaste = (event: React.ClipboardEvent<HTMLTextAreaElement>) => {
+    // Only handle paste if we have an image paste handler and there are files
+    if (onImagePaste && event.clipboardData.files.length > 0) {
+      const files = Array.from(event.clipboardData.files).filter((file) =>
+        file.type.startsWith("image/"),
+      );
+      // Only prevent default if we found image files to handle
+      if (files.length > 0) {
+        event.preventDefault();
+        onImagePaste(files);
+      }
+    }
+    // For text paste, let the default behavior handle it
+  };
+
+  const handleDragOver = (event: React.DragEvent<HTMLTextAreaElement>) => {
+    event.preventDefault();
+    if (event.dataTransfer.types.includes("Files")) {
+      setIsDraggingOver(true);
+    }
+  };
+
+  const handleDragLeave = (event: React.DragEvent<HTMLTextAreaElement>) => {
+    event.preventDefault();
+    setIsDraggingOver(false);
+  };
+
+  const handleDrop = (event: React.DragEvent<HTMLTextAreaElement>) => {
+    event.preventDefault();
+    setIsDraggingOver(false);
+    if (onImagePaste && event.dataTransfer.files.length > 0) {
+      const files = Array.from(event.dataTransfer.files).filter((file) =>
+        file.type.startsWith("image/"),
+      );
+      if (files.length > 0) {
+        onImagePaste(files);
+      }
+    }
+  };
 
   const handleSubmitMessage = () => {
     if (textareaRef.current?.value) {
@@ -67,12 +110,20 @@ export function ChatInput({
         onChange={handleChange}
         onFocus={onFocus}
         onBlur={onBlur}
+        onPaste={handlePaste}
+        onDrop={handleDrop}
+        onDragOver={handleDragOver}
+        onDragLeave={handleDragLeave}
         value={value}
         minRows={1}
         maxRows={maxRows}
+        data-dragging-over={isDraggingOver}
         className={cn(
-          "grow text-sm self-center placeholder:text-neutral-400 text-white resize-none bg-transparent outline-none ring-0",
-          "transition-[height] duration-200 ease-in-out",
+          "grow text-sm self-center placeholder:text-neutral-400 text-white resize-none outline-none ring-0",
+          "transition-all duration-200 ease-in-out",
+          isDraggingOver
+            ? "bg-neutral-600/50 rounded-lg px-2"
+            : "bg-transparent",
           className,
         )}
       />

frontend/src/components/chat-interface.tsx

@@ -1,5 +1,6 @@
 import { useDispatch, useSelector } from "react-redux";
 import React from "react";
+import posthog from "posthog-js";
 import { useSocket } from "#/context/socket";
 import { convertImageToBase64 } from "#/utils/convert-image-to-base-64";
 import { ChatMessage } from "./chat-message";
@@ -18,6 +19,9 @@ import ConfirmationButtons from "./chat/ConfirmationButtons";
 import { ErrorMessage } from "./error-message";
 import { ContinueButton } from "./continue-button";
 import { ScrollToBottomButton } from "./scroll-to-bottom-button";
+import { Suggestions } from "./suggestions";
+import { SUGGESTIONS } from "#/utils/suggestions";
+import BuildIt from "#/assets/build-it.svg?react";
 
 const isErrorMessage = (
   message: Message | ErrorMessage,
@@ -37,17 +41,23 @@ export function ChatInterface() {
     "positive" | "negative"
   >("positive");
   const [feedbackModalIsOpen, setFeedbackModalIsOpen] = React.useState(false);
+  const [messageToSend, setMessageToSend] = React.useState<string | null>(null);
 
   const handleSendMessage = async (content: string, files: File[]) => {
+    posthog.capture("user_message_sent", {
+      current_message_count: messages.length,
+    });
     const promises = files.map((file) => convertImageToBase64(file));
     const imageUrls = await Promise.all(promises);
 
     const timestamp = new Date().toISOString();
     dispatch(addUserMessage({ content, imageUrls, timestamp }));
     send(createChatMessage(content, imageUrls, timestamp));
+    setMessageToSend(null);
   };
 
   const handleStop = () => {
+    posthog.capture("stop_button_clicked");
     send(generateAgentStateChangeEvent(AgentState.STOPPED));
   };
 
@@ -64,6 +74,28 @@ export function ChatInterface() {
 
   return (
     <div className="h-full flex flex-col justify-between">
+      {messages.length === 0 && (
+        <div className="flex flex-col gap-6 h-full px-4 items-center justify-center">
+          <div className="flex flex-col items-center p-4 bg-neutral-700 rounded-xl w-full">
+            <BuildIt width={45} height={54} />
+            <span className="font-semibold text-[20px] leading-6 -tracking-[0.01em] gap-1">
+              Let&apos;s start building!
+            </span>
+          </div>
+          <Suggestions
+            suggestions={Object.entries(SUGGESTIONS.repo)
+              .slice(0, 4)
+              .map(([label, value]) => ({
+                label,
+                value,
+              }))}
+            onSuggestionClick={(value) => {
+              setMessageToSend(value);
+            }}
+          />
+        </div>
+      )}
+
       <div
         ref={scrollRef}
         onScroll={(e) => onChatBodyScroll(e.currentTarget)}
@@ -73,7 +105,7 @@ export function ChatInterface() {
           isErrorMessage(message) ? (
             <ErrorMessage
               key={index}
-              error={message.error}
+              id={message.id}
               message={message.message}
             />
           ) : (
@@ -123,6 +155,8 @@ export function ChatInterface() {
             curAgentState === AgentState.AWAITING_USER_CONFIRMATION
           }
           mode={curAgentState === AgentState.RUNNING ? "stop" : "submit"}
+          value={messageToSend ?? undefined}
+          onChange={setMessageToSend}
         />
       </div>
 

frontend/src/components/chat/message.d.ts

@@ -6,6 +6,7 @@ type Message = {
 };
 
 type ErrorMessage = {
-  error: string;
+  error: boolean;
+  id?: string;
   message: string;
 };

frontend/src/components/error-message.tsx

@@ -1,14 +1,41 @@
+import { useState, useEffect } from "react";
+import { useTranslation } from "react-i18next";
+
 interface ErrorMessageProps {
-  error: string;
+  id?: string;
   message: string;
 }
 
-export function ErrorMessage({ error, message }: ErrorMessageProps) {
+export function ErrorMessage({ id, message }: ErrorMessageProps) {
+  const { t, i18n } = useTranslation();
+  const [showDetails, setShowDetails] = useState(true);
+  const [headline, setHeadline] = useState("");
+  const [details, setDetails] = useState(message);
+
+  useEffect(() => {
+    if (id && i18n.exists(id)) {
+      setHeadline(t(id));
+      setDetails(message);
+      setShowDetails(false);
+    }
+  }, [id, message, i18n.language]);
+
   return (
     <div className="flex gap-2 items-center justify-start border-l-2 border-danger pl-2 my-2 py-2">
       <div className="text-sm leading-4 flex flex-col gap-2">
-        <p className="text-danger font-bold">{error}</p>
-        <p className="text-neutral-300">{message}</p>
+        {headline && <p className="text-danger font-bold">{headline}</p>}
+        {headline && (
+          <button
+            type="button"
+            onClick={() => setShowDetails(!showDetails)}
+            className="cursor-pointer text-left"
+          >
+            {showDetails
+              ? t("ERROR_MESSAGE$HIDE_DETAILS")
+              : t("ERROR_MESSAGE$SHOW_DETAILS")}
+          </button>
+        )}
+        {showDetails && <p className="text-neutral-300">{details}</p>}
       </div>
     </div>
   );

frontend/src/components/form/custom-input.tsx

@@ -1,3 +1,6 @@
+import { useTranslation } from "react-i18next";
+import { I18nKey } from "#/i18n/declaration";
+
 interface CustomInputProps {
   name: string;
   label: string;
@@ -13,12 +16,19 @@ export function CustomInput({
   defaultValue,
   type = "text",
 }: CustomInputProps) {
+  const { t } = useTranslation();
+
   return (
     <label htmlFor={name} className="flex flex-col gap-2">
       <span className="text-[11px] leading-4 tracking-[0.5px] font-[500] text-[#A3A3A3]">
         {label}
         {required && <span className="text-[#FF4D4F]">*</span>}
-        {!required && <span className="text-[#A3A3A3]"> (optional)</span>}
+        {!required && (
+          <span className="text-[#A3A3A3]">
+            {" "}
+            {t(I18nKey.CUSTOM_INPUT$OPTIONAL_LABEL)}
+          </span>
+        )}
       </span>
       <input
         id={name}

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

@@ -5,16 +5,18 @@ import {
   Switch,
 } from "@nextui-org/react";
 import { useFetcher, useLocation, useNavigate } from "@remix-run/react";
+import { useTranslation } from "react-i18next";
 import clsx from "clsx";
 import React from "react";
-import { ModalBackdrop } from "#/components/modals/modal-backdrop";
-import { ModelSelector } from "#/components/modals/settings/ModelSelector";
-import { clientAction } from "#/routes/settings";
-import { Settings } from "#/services/settings";
-import { extractModelAndProvider } from "#/utils/extractModelAndProvider";
 import { organizeModelsAndProviders } from "#/utils/organizeModelsAndProviders";
+import { ModelSelector } from "#/components/modals/settings/ModelSelector";
+import { Settings } from "#/services/settings";
+import { ModalBackdrop } from "#/components/modals/modal-backdrop";
+import { clientAction } from "#/routes/settings";
+import { extractModelAndProvider } from "#/utils/extractModelAndProvider";
 import ModalButton from "../buttons/ModalButton";
 import { DangerModal } from "../modals/confirmation-modals/danger-modal";
+import { I18nKey } from "#/i18n/declaration";
 
 interface SettingsFormProps {
   disabled?: boolean;
@@ -35,6 +37,7 @@ export function SettingsForm({
 }: SettingsFormProps) {
   const location = useLocation();
   const navigate = useNavigate();
+  const { t } = useTranslation();
 
   const fetcher = useFetcher<typeof clientAction>();
   const formRef = React.useRef<HTMLFormElement>(null);
@@ -161,7 +164,7 @@ export function SettingsForm({
               label: "text-[#A3A3A3] text-xs",
             }}
           >
-            Advanced Options
+            {t(I18nKey.SETTINGS_FORM$ADVANCED_OPTIONS_LABEL)}
           </Switch>
 
           {showAdvancedOptions && (
@@ -171,7 +174,7 @@ export function SettingsForm({
                   htmlFor="custom-model"
                   className="font-[500] text-[#A3A3A3] text-xs"
                 >
-                  Custom Model
+                  {t(I18nKey.SETTINGS_FORM$CUSTOM_MODEL_LABEL)}
                 </label>
                 <Input
                   isDisabled={disabled}
@@ -190,7 +193,7 @@ export function SettingsForm({
                   htmlFor="base-url"
                   className="font-[500] text-[#A3A3A3] text-xs"
                 >
-                  Base URL
+                  {t(I18nKey.SETTINGS_FORM$BASE_URL_LABEL)}
                 </label>
                 <Input
                   isDisabled={disabled}
@@ -220,7 +223,7 @@ export function SettingsForm({
               htmlFor="api-key"
               className="font-[500] text-[#A3A3A3] text-xs"
             >
-              API Key
+              {t(I18nKey.SETTINGS_FORM$API_KEY_LABEL)}
             </label>
             <Input
               isDisabled={disabled}
@@ -234,14 +237,14 @@ export function SettingsForm({
               }}
             />
             <p className="text-sm text-[#A3A3A3]">
-              Don&apos;t know your API key?{" "}
+              {t(I18nKey.SETTINGS_FORM$DONT_KNOW_API_KEY_LABEL)}{" "}
               <a
                 href="https://docs.all-hands.dev/modules/usage/llms"
                 rel="noreferrer noopener"
                 target="_blank"
                 className="underline underline-offset-2"
               >
-                Click here for instructions
+                {t(I18nKey.SETTINGS_FORM$CLICK_HERE_FOR_INSTRUCTIONS_LABEL)}
               </a>
             </p>
           </fieldset>
@@ -255,7 +258,7 @@ export function SettingsForm({
                 htmlFor="agent"
                 className="font-[500] text-[#A3A3A3] text-xs"
               >
-                Agent
+                {t(I18nKey.SETTINGS_FORM$AGENT_LABEL)}
               </label>
               <Autocomplete
                 isDisabled={disabled}
@@ -291,7 +294,7 @@ export function SettingsForm({
                   htmlFor="security-analyzer"
                   className="font-[500] text-[#A3A3A3] text-xs"
                 >
-                  Security Analyzer (Optional)
+                  {t(I18nKey.SETTINGS_FORM$SECURITY_ANALYZER_LABEL)}
                 </label>
                 <Autocomplete
                   isDisabled={disabled}
@@ -334,7 +337,7 @@ export function SettingsForm({
                   label: "text-[#A3A3A3] text-xs",
                 }}
               >
-                Enable Confirmation Mode
+                {t(I18nKey.SETTINGS_FORM$ENABLE_CONFIRMATION_MODE_LABEL)}
               </Switch>
             </>
           )}
@@ -345,18 +348,18 @@ export function SettingsForm({
             <ModalButton
               disabled={disabled || fetcher.state === "submitting"}
               type="submit"
-              text="Save"
+              text={t(I18nKey.SETTINGS_FORM$SAVE_LABEL)}
               className="bg-[#4465DB] w-full"
             />
             <ModalButton
-              text="Close"
+              text={t(I18nKey.SETTINGS_FORM$CLOSE_LABEL)}
               className="bg-[#737373] w-full"
               onClick={handleCloseClick}
             />
           </div>
           <ModalButton
             disabled={disabled}
-            text="Reset to defaults"
+            text={t(I18nKey.SETTINGS_FORM$RESET_TO_DEFAULTS_LABEL)}
             variant="text-like"
             className="text-danger self-start"
             onClick={() => {
@@ -369,15 +372,17 @@ export function SettingsForm({
       {confirmResetDefaultsModalOpen && (
         <ModalBackdrop>
           <DangerModal
-            title="Are you sure?"
-            description="All saved information in your AI settings will be deleted including any API keys."
+            title={t(I18nKey.SETTINGS_FORM$ARE_YOU_SURE_LABEL)}
+            description={t(
+              I18nKey.SETTINGS_FORM$ALL_INFORMATION_WILL_BE_DELETED_MESSAGE,
+            )}
             buttons={{
               danger: {
-                text: "Reset Defaults",
+                text: t(I18nKey.SETTINGS_FORM$RESET_TO_DEFAULTS_LABEL),
                 onClick: handleConfirmResetSettings,
               },
               cancel: {
-                text: "Cancel",
+                text: t(I18nKey.SETTINGS_FORM$CANCEL_LABEL),
                 onClick: () => setConfirmResetDefaultsModalOpen(false),
               },
             }}
@@ -387,12 +392,17 @@ export function SettingsForm({
       {confirmEndSessionModalOpen && (
         <ModalBackdrop>
           <DangerModal
-            title="End Session"
-            description="Changing your settings will clear your workspace and start a new session. Are you sure you want to continue?"
+            title={t(I18nKey.SETTINGS_FORM$END_SESSION_LABEL)}
+            description={t(
+              I18nKey.SETTINGS_FORM$CHANGING_WORKSPACE_WARNING_MESSAGE,
+            )}
             buttons={{
-              danger: { text: "End Session", onClick: handleConfirmEndSession },
+              danger: {
+                text: t(I18nKey.SETTINGS_FORM$END_SESSION_LABEL),
+                onClick: handleConfirmEndSession,
+              },
               cancel: {
-                text: "Cancel",
+                text: t(I18nKey.SETTINGS_FORM$CANCEL_LABEL),
                 onClick: () => setConfirmEndSessionModalOpen(false),
               },
             }}

frontend/src/components/github-repositories-suggestion-box.tsx

@@ -0,0 +1,94 @@
+import React from "react";
+import {
+  isGitHubErrorReponse,
+  retrieveAllGitHubUserRepositories,
+} from "#/api/github";
+import { SuggestionBox } from "#/routes/_oh._index/suggestion-box";
+import { ConnectToGitHubModal } from "./modals/connect-to-github-modal";
+import { ModalBackdrop } from "./modals/modal-backdrop";
+import { GitHubRepositorySelector } from "#/routes/_oh._index/github-repo-selector";
+import ModalButton from "./buttons/ModalButton";
+import GitHubLogo from "#/assets/branding/github-logo.svg?react";
+
+interface GitHubAuthProps {
+  onConnectToGitHub: () => void;
+  repositories: GitHubRepository[];
+  isLoggedIn: boolean;
+}
+
+function GitHubAuth({
+  onConnectToGitHub,
+  repositories,
+  isLoggedIn,
+}: GitHubAuthProps) {
+  if (isLoggedIn) {
+    return <GitHubRepositorySelector repositories={repositories} />;
+  }
+
+  return (
+    <ModalButton
+      text="Connect to GitHub"
+      icon={<GitHubLogo width={20} height={20} />}
+      className="bg-[#791B80] w-full"
+      onClick={onConnectToGitHub}
+    />
+  );
+}
+
+interface GitHubRepositoriesSuggestionBoxProps {
+  repositories: Awaited<
+    ReturnType<typeof retrieveAllGitHubUserRepositories>
+  > | null;
+  gitHubAuthUrl: string | null;
+  user: GitHubErrorReponse | GitHubUser | null;
+}
+
+export function GitHubRepositoriesSuggestionBox({
+  repositories,
+  gitHubAuthUrl,
+  user,
+}: GitHubRepositoriesSuggestionBoxProps) {
+  const [connectToGitHubModalOpen, setConnectToGitHubModalOpen] =
+    React.useState(false);
+
+  const handleConnectToGitHub = () => {
+    if (gitHubAuthUrl) {
+      window.location.href = gitHubAuthUrl;
+    } else {
+      setConnectToGitHubModalOpen(true);
+    }
+  };
+
+  if (isGitHubErrorReponse(repositories)) {
+    return (
+      <SuggestionBox
+        title="Error Fetching Repositories"
+        content={
+          <p className="text-danger text-center">{repositories.message}</p>
+        }
+      />
+    );
+  }
+
+  return (
+    <>
+      <SuggestionBox
+        title="Open a Repo"
+        content={
+          <GitHubAuth
+            isLoggedIn={!!user && !isGitHubErrorReponse(user)}
+            repositories={repositories || []}
+            onConnectToGitHub={handleConnectToGitHub}
+          />
+        }
+      />
+      {connectToGitHubModalOpen && (
+        <ModalBackdrop onClose={() => setConnectToGitHubModalOpen(false)}>
+          <ConnectToGitHubModal
+            onClose={() => setConnectToGitHubModalOpen(false)}
+          />
+        </ModalBackdrop>
+      )}
+    </>
+  );
+}

frontend/src/components/interactive-chat-box.tsx

@@ -9,6 +9,8 @@ interface InteractiveChatBoxProps {
   mode?: "stop" | "submit";
   onSubmit: (message: string, images: File[]) => void;
   onStop: () => void;
+  value?: string;
+  onChange?: (message: string) => void;
 }
 
 export function InteractiveChatBox({
@@ -16,6 +18,8 @@ export function InteractiveChatBox({
   mode = "submit",
   onSubmit,
   onStop,
+  value,
+  onChange,
 }: InteractiveChatBoxProps) {
   const [images, setImages] = React.useState<File[]>([]);
 
@@ -53,6 +57,13 @@ export function InteractiveChatBox({
         className={cn(
           "flex items-end gap-1",
           "bg-neutral-700 border border-neutral-600 rounded-lg px-2 py-[10px]",
+          "transition-colors duration-200",
+          "hover:border-neutral-500 focus-within:border-neutral-500",
+          "group relative",
+          "before:pointer-events-none before:absolute before:inset-0 before:rounded-lg before:transition-colors",
+          "before:border-2 before:border-dashed before:border-transparent",
+          "[&:has(*:focus-within)]:before:border-neutral-500/50",
+          "[&:has(*[data-dragging-over='true'])]:before:border-neutral-500/50",
         )}
       >
         <UploadImageInput onUpload={handleUpload} />
@@ -60,8 +71,11 @@ export function InteractiveChatBox({
           disabled={isDisabled}
           button={mode}
           placeholder="What do you want to build?"
+          onChange={onChange}
           onSubmit={handleSubmit}
           onStop={onStop}
+          value={value}
+          onImagePaste={handleUpload}
         />
       </div>
     </div>

frontend/src/components/modals/AccountSettingsModal.tsx

@@ -1,5 +1,6 @@
 import { useFetcher, useRouteLoaderData } from "@remix-run/react";
 import React from "react";
+import { useTranslation } from "react-i18next";
 import { BaseModalTitle } from "./confirmation-modals/BaseModal";
 import ModalBody from "./ModalBody";
 import ModalButton from "../buttons/ModalButton";
@@ -9,18 +10,22 @@ import { clientLoader } from "#/routes/_oh";
 import { clientAction as settingsClientAction } from "#/routes/settings";
 import { clientAction as loginClientAction } from "#/routes/login";
 import { AvailableLanguages } from "#/i18n";
+import { I18nKey } from "#/i18n/declaration";
 
 interface AccountSettingsModalProps {
   onClose: () => void;
   selectedLanguage: string;
   gitHubError: boolean;
+  analyticsConsent: string | null;
 }
 
 function AccountSettingsModal({
   onClose,
   selectedLanguage,
   gitHubError,
+  analyticsConsent,
 }: AccountSettingsModalProps) {
+  const { t } = useTranslation();
   const data = useRouteLoaderData<typeof clientLoader>("routes/_oh");
   const settingsFetcher = useFetcher<typeof settingsClientAction>({
     key: "settings",
@@ -32,6 +37,7 @@ function AccountSettingsModal({
     const formData = new FormData(event.currentTarget);
     const language = formData.get("language")?.toString();
     const ghToken = formData.get("ghToken")?.toString();
+    const analytics = formData.get("analytics")?.toString() === "on";
 
     const accountForm = new FormData();
     const loginForm = new FormData();
@@ -44,6 +50,7 @@ function AccountSettingsModal({
       accountForm.append("language", languageKey ?? "en");
     }
     if (ghToken) loginForm.append("ghToken", ghToken);
+    accountForm.append("analytics", analytics.toString());
 
     settingsFetcher.submit(accountForm, {
       method: "POST",
@@ -82,13 +89,13 @@ function AccountSettingsModal({
           />
           {gitHubError && (
             <p className="text-danger text-xs">
-              GitHub token is invalid. Please try again.
+              {t(I18nKey.ACCOUNT_SETTINGS_MODAL$GITHUB_TOKEN_INVALID)}
             </p>
           )}
           {data?.ghToken && !gitHubError && (
             <ModalButton
               variant="text-like"
-              text="Disconnect"
+              text={t(I18nKey.ACCOUNT_SETTINGS_MODAL$DISCONNECT)}
               onClick={() => {
                 settingsFetcher.submit(
                   {},
@@ -101,6 +108,15 @@ function AccountSettingsModal({
           )}
         </div>
 
+        <label className="flex gap-2 items-center self-start">
+          <input
+            name="analytics"
+            type="checkbox"
+            defaultChecked={analyticsConsent === "true"}
+          />
+          Enable analytics
+        </label>
+
         <div className="flex flex-col gap-2 w-full">
           <ModalButton
             disabled={
@@ -109,11 +125,11 @@ function AccountSettingsModal({
             }
             type="submit"
             intent="account"
-            text="Save"
+            text={t(I18nKey.ACCOUNT_SETTINGS_MODAL$SAVE)}
             className="bg-[#4465DB]"
           />
           <ModalButton
-            text="Close"
+            text={t(I18nKey.ACCOUNT_SETTINGS_MODAL$CLOSE)}
             onClick={onClose}
             className="bg-[#737373]"
           />

frontend/src/components/modals/ConnectToGitHubByTokenModal.tsx

@@ -1,4 +1,5 @@
 import { Form, useNavigation } from "@remix-run/react";
+import { useTranslation } from "react-i18next";
 import {
   BaseModalDescription,
   BaseModalTitle,
@@ -7,10 +8,11 @@ import ModalButton from "../buttons/ModalButton";
 import AllHandsLogo from "#/assets/branding/all-hands-logo-spark.svg?react";
 import ModalBody from "./ModalBody";
 import { CustomInput } from "../form/custom-input";
+import { I18nKey } from "#/i18n/declaration";
 
 function ConnectToGitHubByTokenModal() {
   const navigation = useNavigation();
-
+  const { t } = useTranslation();
   return (
     <ModalBody testID="auth-modal">
       <div className="flex flex-col gap-2">
@@ -29,13 +31,18 @@ function ConnectToGitHubByTokenModal() {
             required
           />
           <p className="text-xs text-[#A3A3A3]">
-            By connecting you agree to our{" "}
-            <span className="text-hyperlink">terms of service</span>.
+            {t(
+              I18nKey.CONNECT_TO_GITHUB_BY_TOKEN_MODAL$BY_CONNECTING_YOU_AGREE,
+            )}{" "}
+            <span className="text-hyperlink">
+              {t(I18nKey.CONNECT_TO_GITHUB_BY_TOKEN_MODAL$TERMS_OF_SERVICE)}
+            </span>
+            .
           </p>
         </label>
         <ModalButton
           type="submit"
-          text="Continue"
+          text={t(I18nKey.CONNECT_TO_GITHUB_BY_TOKEN_MODAL$CONTINUE)}
           className="bg-[#791B80] w-full"
           disabled={navigation.state === "loading"}
         />

frontend/src/components/modals/LoadingProject.tsx

@@ -1,6 +1,8 @@
+import { useTranslation } from "react-i18next";
 import LoadingSpinnerOuter from "#/assets/loading-outer.svg?react";
 import { cn } from "#/utils/utils";
 import ModalBody from "./ModalBody";
+import { I18nKey } from "#/i18n/declaration";
 
 interface LoadingSpinnerProps {
   size: "small" | "large";
@@ -28,10 +30,12 @@ interface LoadingProjectModalProps {
 }
 
 function LoadingProjectModal({ message }: LoadingProjectModalProps) {
+  const { t } = useTranslation();
+
   return (
     <ModalBody>
       <span className="text-xl leading-6 -tracking-[0.01em] font-semibold">
-        {message || "Loading..."}
+        {message || t(I18nKey.LOADING_PROJECT$LOADING)}
       </span>
       <LoadingSpinner size="large" />
     </ModalBody>

frontend/src/components/modals/confirmation-modals/BaseModal.tsx

@@ -21,13 +21,17 @@ export function BaseModalTitle({ title }: BaseModalTitleProps) {
 }
 
 interface BaseModalDescriptionProps {
-  description: React.ReactNode;
+  description?: React.ReactNode;
+  children?: React.ReactNode;
 }
 
 export function BaseModalDescription({
   description,
+  children,
 }: BaseModalDescriptionProps) {
-  return <span className="text-xs text-[#A3A3A3]">{description}</span>;
+  return (
+    <span className="text-xs text-[#A3A3A3]">{children || description}</span>
+  );
 }
 
 interface BaseModalProps {

frontend/src/components/modals/connect-to-github-modal.tsx

@@ -1,4 +1,5 @@
 import { useFetcher, useRouteLoaderData } from "@remix-run/react";
+import { useTranslation } from "react-i18next";
 import ModalBody from "./ModalBody";
 import { CustomInput } from "../form/custom-input";
 import ModalButton from "../buttons/ModalButton";
@@ -8,6 +9,7 @@ import {
 } from "./confirmation-modals/BaseModal";
 import { clientLoader } from "#/routes/_oh";
 import { clientAction } from "#/routes/login";
+import { I18nKey } from "#/i18n/declaration";
 
 interface ConnectToGitHubModalProps {
   onClose: () => void;
@@ -16,6 +18,7 @@ interface ConnectToGitHubModalProps {
 export function ConnectToGitHubModal({ onClose }: ConnectToGitHubModalProps) {
   const data = useRouteLoaderData<typeof clientLoader>("routes/_oh");
   const fetcher = useFetcher<typeof clientAction>({ key: "login" });
+  const { t } = useTranslation();
 
   return (
     <ModalBody>
@@ -24,14 +27,14 @@ export function ConnectToGitHubModal({ onClose }: ConnectToGitHubModalProps) {
         <BaseModalDescription
           description={
             <span>
-              Get your token{" "}
+              {t(I18nKey.CONNECT_TO_GITHUB_MODAL$GET_YOUR_TOKEN)}{" "}
               <a
                 href="https://github.com/settings/tokens/new?description=openhands-app&scopes=repo,user,workflow"
                 target="_blank"
                 rel="noreferrer noopener"
                 className="text-[#791B80] underline"
               >
-                here
+                {t(I18nKey.CONNECT_TO_GITHUB_MODAL$HERE)}
               </a>
             </span>
           }
@@ -53,14 +56,15 @@ export function ConnectToGitHubModal({ onClose }: ConnectToGitHubModalProps) {
 
         <div className="flex flex-col gap-2 w-full">
           <ModalButton
+            testId="connect-to-github"
             type="submit"
-            text="Connect"
+            text={t(I18nKey.CONNECT_TO_GITHUB_MODAL$CONNECT)}
             disabled={fetcher.state === "submitting"}
             className="bg-[#791B80] w-full"
           />
           <ModalButton
             onClick={onClose}
-            text="Close"
+            text={t(I18nKey.CONNECT_TO_GITHUB_MODAL$CLOSE)}
             className="bg-[#737373] w-full"
           />
         </div>

frontend/src/components/modals/security/Security.tsx

@@ -1,6 +1,8 @@
 import React from "react";
+import { useTranslation } from "react-i18next";
 import SecurityInvariant from "./invariant/Invariant";
 import BaseModal from "../base-modal/BaseModal";
+import { I18nKey } from "#/i18n/declaration";
 
 interface SecurityProps {
   isOpen: boolean;
@@ -17,11 +19,13 @@ const SecurityAnalyzers: Record<SecurityAnalyzerOption, React.ElementType> = {
 };
 
 function Security({ isOpen, onOpenChange, securityAnalyzer }: SecurityProps) {
+  const { t } = useTranslation();
+
   const AnalyzerComponent =
     securityAnalyzer &&
     SecurityAnalyzers[securityAnalyzer as SecurityAnalyzerOption]
       ? SecurityAnalyzers[securityAnalyzer as SecurityAnalyzerOption]
-      : () => <div>Unknown security analyzer chosen</div>;
+      : () => <div>{t(I18nKey.SECURITY$UNKNOWN_ANALYZER_LABEL)}</div>;
 
   return (
     <BaseModal

frontend/src/components/modals/security/invariant/Invariant.tsx

@@ -123,7 +123,7 @@ function SecurityInvariant(): JSX.Element {
 
   async function exportTraces(): Promise<void> {
     const data = await request(`/api/security/export-trace`);
-    toast.info("Trace exported");
+    toast.info(t(I18nKey.INVARIANT$TRACE_EXPORTED_MESSAGE));
 
     const filename = `openhands-trace-${getFormattedDateTime()}.json`;
     downloadJSON(data, filename);
@@ -134,7 +134,7 @@ function SecurityInvariant(): JSX.Element {
       method: "POST",
       body: JSON.stringify({ policy }),
     });
-    toast.info("Policy updated");
+    toast.info(t(I18nKey.INVARIANT$POLICY_UPDATED_MESSAGE));
   }
 
   async function updateSettings(): Promise<void> {
@@ -143,7 +143,7 @@ function SecurityInvariant(): JSX.Element {
       method: "POST",
       body: JSON.stringify(payload),
     });
-    toast.info("Settings updated");
+    toast.info(t(I18nKey.INVARIANT$SETTINGS_UPDATED_MESSAGE));
   }
 
   const handleExportTraces = useCallback(() => {
@@ -162,9 +162,9 @@ function SecurityInvariant(): JSX.Element {
     logs: (
       <>
         <div className="flex justify-between items-center border-b border-neutral-600 mb-4 p-4">
-          <h2 className="text-2xl">Logs</h2>
+          <h2 className="text-2xl">{t(I18nKey.INVARIANT$LOG_LABEL)}</h2>
           <Button onClick={handleExportTraces} className="bg-neutral-700">
-            Export Trace
+            {t(I18nKey.INVARIANT$EXPORT_TRACE_LABEL)}
           </Button>
         </div>
         <div className="flex-1 p-4 max-h-screen overflow-y-auto" ref={logsRef}>
@@ -195,9 +195,9 @@ function SecurityInvariant(): JSX.Element {
     policy: (
       <>
         <div className="flex justify-between items-center border-b border-neutral-600 mb-4 p-4">
-          <h2 className="text-2xl">Policy</h2>
+          <h2 className="text-2xl">{t(I18nKey.INVARIANT$POLICY_LABEL)}</h2>
           <Button className="bg-neutral-700" onClick={handleUpdatePolicy}>
-            Update Policy
+            {t(I18nKey.INVARIANT$UPDATE_POLICY_LABEL)}
           </Button>
         </div>
         <div className="flex grow items-center justify-center">
@@ -214,14 +214,16 @@ function SecurityInvariant(): JSX.Element {
     settings: (
       <>
         <div className="flex justify-between items-center border-b border-neutral-600 mb-4 p-4">
-          <h2 className="text-2xl">Settings</h2>
+          <h2 className="text-2xl">{t(I18nKey.INVARIANT$SETTINGS_LABEL)}</h2>
           <Button className="bg-neutral-700" onClick={handleUpdateSettings}>
-            Update Settings
+            {t(I18nKey.INVARIANT$UPDATE_SETTINGS_LABEL)}
           </Button>
         </div>
         <div className="flex grow p-4">
           <div className="flex flex-col w-full">
-            <p className="mb-2">Ask for user confirmation on risk severity:</p>
+            <p className="mb-2">
+              {t(I18nKey.INVARIANT$ASK_CONFIRMATION_RISK_SEVERITY_LABEL)}
+            </p>
             <Select
               placeholder="Select risk severity"
               value={selectedRisk}
@@ -264,7 +266,7 @@ function SecurityInvariant(): JSX.Element {
                 key={ActionSecurityRisk.HIGH + 1}
                 aria-label="Don't ask for confirmation"
               >
-                Don&apos;t ask for confirmation
+                {t(I18nKey.INVARIANT$DONT_ASK_FOR_CONFIRMATION_LABEL)}
               </SelectItem>
             </Select>
           </div>
@@ -278,18 +280,17 @@ function SecurityInvariant(): JSX.Element {
       <div className="w-60 bg-neutral-800 border-r border-r-neutral-600 p-4 flex-shrink-0">
         <div className="text-center mb-2">
           <InvariantLogoIcon className="mx-auto mb-1" />
-          <b>Invariant Analyzer</b>
+          <b>{t(I18nKey.INVARIANT$INVARIANT_ANALYZER_LABEL)}</b>
         </div>
         <p className="text-[0.6rem]">
-          Invariant Analyzer continuously monitors your OpenHands agent for
-          security issues.{" "}
+          {t(I18nKey.INVARIANT$INVARIANT_ANALYZER_MESSAGE)}{" "}
           <a
             className="underline"
             href="https://github.com/invariantlabs-ai/invariant"
             target="_blank"
             rel="noreferrer"
           >
-            Click to learn more
+            {t(I18nKey.INVARIANT$CLICK_TO_LEARN_MORE_LABEL)}
           </a>
         </p>
         <hr className="border-t border-neutral-600 my-2" />
@@ -298,19 +299,19 @@ function SecurityInvariant(): JSX.Element {
             className={`cursor-pointer p-2 rounded ${activeSection === "logs" && "bg-neutral-600"}`}
             onClick={() => setActiveSection("logs")}
           >
-            Logs
+            {t(I18nKey.INVARIANT$LOG_LABEL)}
           </div>
           <div
             className={`cursor-pointer p-2 rounded ${activeSection === "policy" && "bg-neutral-600"}`}
             onClick={() => setActiveSection("policy")}
           >
-            Policy
+            {t(I18nKey.INVARIANT$POLICY_LABEL)}
           </div>
           <div
             className={`cursor-pointer p-2 rounded ${activeSection === "settings" && "bg-neutral-600"}`}
             onClick={() => setActiveSection("settings")}
           >
-            Settings
+            {t(I18nKey.INVARIANT$SETTINGS_LABEL)}
           </div>
         </ul>
       </div>

frontend/src/components/project-menu/ProjectMenuCard.tsx

@@ -1,6 +1,7 @@
 import React from "react";
 import { useDispatch } from "react-redux";
 import toast from "react-hot-toast";
+import posthog from "posthog-js";
 import EllipsisH from "#/assets/ellipsis-h.svg?react";
 import { ModalBackdrop } from "../modals/modal-backdrop";
 import { ConnectToGitHubModal } from "../modals/connect-to-github-modal";
@@ -11,6 +12,7 @@ import { ProjectMenuCardContextMenu } from "./project.menu-card-context-menu";
 import { ProjectMenuDetailsPlaceholder } from "./project-menu-details-placeholder";
 import { ProjectMenuDetails } from "./project-menu-details";
 import { downloadWorkspace } from "#/utils/download-workspace";
+import { LoadingSpinner } from "../modals/LoadingProject";
 
 interface ProjectMenuCardProps {
   isConnectedToGitHub: boolean;
@@ -31,18 +33,17 @@ export function ProjectMenuCard({
   const [contextMenuIsOpen, setContextMenuIsOpen] = React.useState(false);
   const [connectToGitHubModalOpen, setConnectToGitHubModalOpen] =
     React.useState(false);
+  const [working, setWorking] = React.useState(false);
 
   const toggleMenuVisibility = () => {
     setContextMenuIsOpen((prev) => !prev);
   };
 
   const handlePushToGitHub = () => {
+    posthog.capture("push_to_github_button_clicked");
     const rawEvent = {
       content: `
-Let's push the code to GitHub.
-If we're currently on the openhands-workspace branch, please create a new branch with a descriptive name.
-Commit any changes and push them to the remote repository.
-Finally, open up a pull request using the GitHub API and the token in the GITHUB_TOKEN environment variable, then show me the URL of the pull request.
+Please push the changes to GitHub and open a pull request.
 `,
       imageUrls: [],
       timestamp: new Date().toISOString(),
@@ -58,20 +59,27 @@ Finally, open up a pull request using the GitHub API and the token in the GITHUB
     setContextMenuIsOpen(false);
   };
 
+  const handleDownloadWorkspace = () => {
+    posthog.capture("download_workspace_button_clicked");
+    try {
+      setWorking(true);
+      downloadWorkspace().then(
+        () => setWorking(false),
+        () => setWorking(false),
+      );
+    } catch (error) {
+      toast.error("Failed to download workspace");
+    }
+  };
+
   return (
     <div className="px-4 py-[10px] w-[337px] rounded-xl border border-[#525252] flex justify-between items-center relative">
-      {contextMenuIsOpen && (
+      {!working && contextMenuIsOpen && (
         <ProjectMenuCardContextMenu
           isConnectedToGitHub={isConnectedToGitHub}
           onConnectToGitHub={() => setConnectToGitHubModalOpen(true)}
           onPushToGitHub={handlePushToGitHub}
-          onDownloadWorkspace={() => {
-            try {
-              downloadWorkspace();
-            } catch (error) {
-              toast.error("Failed to download workspace");
-            }
-          }}
+          onDownloadWorkspace={handleDownloadWorkspace}
           onClose={() => setContextMenuIsOpen(false)}
         />
       )}
@@ -93,7 +101,11 @@ Finally, open up a pull request using the GitHub API and the token in the GITHUB
         onClick={toggleMenuVisibility}
         aria-label="Open project menu"
       >
-        <EllipsisH width={36} height={36} />
+        {working ? (
+          <LoadingSpinner size="small" />
+        ) : (
+          <EllipsisH width={36} height={36} />
+        )}
       </button>
       {connectToGitHubModalOpen && (
         <ModalBackdrop onClose={() => setConnectToGitHubModalOpen(false)}>

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

@@ -1,5 +1,7 @@
+import { useTranslation } from "react-i18next";
 import { cn } from "#/utils/utils";
 import CloudConnection from "#/assets/cloud-connection.svg?react";
+import { I18nKey } from "#/i18n/declaration";
 
 interface ProjectMenuDetailsPlaceholderProps {
   isConnectedToGitHub: boolean;
@@ -10,9 +12,13 @@ export function ProjectMenuDetailsPlaceholder({
   isConnectedToGitHub,
   onConnectToGitHub,
 }: ProjectMenuDetailsPlaceholderProps) {
+  const { t } = useTranslation();
+
   return (
     <div className="flex flex-col">
-      <span className="text-sm leading-6 font-semibold">New Project</span>
+      <span className="text-sm leading-6 font-semibold">
+        {t(I18nKey.PROJECT_MENU_DETAILS_PLACEHOLDER$NEW_PROJECT_LABEL)}
+      </span>
       <button
         type="button"
         onClick={onConnectToGitHub}

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

@@ -1,5 +1,7 @@
+import { useTranslation } from "react-i18next";
 import ExternalLinkIcon from "#/assets/external-link.svg?react";
 import { formatTimeDelta } from "#/utils/format-time-delta";
+import { I18nKey } from "#/i18n/declaration";
 
 interface ProjectMenuDetailsProps {
   repoName: string;
@@ -12,6 +14,7 @@ export function ProjectMenuDetails({
   avatar,
   lastCommit,
 }: ProjectMenuDetailsProps) {
+  const { t } = useTranslation();
   return (
     <div className="flex flex-col">
       <a
@@ -32,7 +35,8 @@ export function ProjectMenuDetails({
       >
         <span>{lastCommit.sha.slice(-7)}</span> <span>&middot;</span>{" "}
         <span>
-          {formatTimeDelta(new Date(lastCommit.commit.author.date))} ago
+          {formatTimeDelta(new Date(lastCommit.commit.author.date))}{" "}
+          {t(I18nKey.PROJECT_MENU_DETAILS$AGO_LABEL)}
         </span>
       </a>
     </div>

frontend/src/components/project-menu/project.menu-card-context-menu.tsx

@@ -1,6 +1,8 @@
+import { useTranslation } from "react-i18next";
 import { useClickOutsideElement } from "#/hooks/useClickOutsideElement";
 import { ContextMenu } from "../context-menu/context-menu";
 import { ContextMenuListItem } from "../context-menu/context-menu-list-item";
+import { I18nKey } from "#/i18n/declaration";
 
 interface ProjectMenuCardContextMenuProps {
   isConnectedToGitHub: boolean;
@@ -18,7 +20,7 @@ export function ProjectMenuCardContextMenu({
   onClose,
 }: ProjectMenuCardContextMenuProps) {
   const menuRef = useClickOutsideElement<HTMLUListElement>(onClose);
-
+  const { t } = useTranslation();
   return (
     <ContextMenu
       ref={menuRef}
@@ -26,16 +28,16 @@ export function ProjectMenuCardContextMenu({
     >
       {!isConnectedToGitHub && (
         <ContextMenuListItem onClick={onConnectToGitHub}>
-          Connect to GitHub
+          {t(I18nKey.PROJECT_MENU_CARD_CONTEXT_MENU$CONNECT_TO_GITHUB_LABEL)}
         </ContextMenuListItem>
       )}
       {isConnectedToGitHub && (
         <ContextMenuListItem onClick={onPushToGitHub}>
-          Push to GitHub
+          {t(I18nKey.PROJECT_MENU_CARD_CONTEXT_MENU$PUSH_TO_GITHUB_LABEL)}
         </ContextMenuListItem>
       )}
       <ContextMenuListItem onClick={onDownloadWorkspace}>
-        Download as .zip
+        {t(I18nKey.PROJECT_MENU_CARD_CONTEXT_MENU$DOWNLOAD_AS_ZIP_LABEL)}
       </ContextMenuListItem>
     </ContextMenu>
   );

frontend/src/components/suggestion-item.tsx

@@ -0,0 +1,21 @@
+export type Suggestion = { label: string; value: string };
+
+interface SuggestionItemProps {
+  suggestion: Suggestion;
+  onClick: (value: string) => void;
+}
+
+export function SuggestionItem({ suggestion, onClick }: SuggestionItemProps) {
+  return (
+    <li className="border border-neutral-600 rounded-xl hover:bg-neutral-700">
+      <button
+        type="button"
+        data-testid="suggestion"
+        onClick={() => onClick(suggestion.value)}
+        className="text-[16px] leading-6 -tracking-[0.01em] text-center w-full p-4 font-semibold"
+      >
+        {suggestion.label}
+      </button>
+    </li>
+  );
+}