[Bug]: When using DeepSeek in the [Ai Profive Configuration] option, the default configuration is incorrect: 'others/deepseek-chat' should be 'deepseek/deepseek-chat' .（Including Fix）

[Simon-CHOU]

Is there an existing issue for the same bug?

• I have checked the existing issues.

Describe the bug and reproduction steps

Step 1: After Docker starts fresh, access http://localhost:3000/ to configure the AI Provider.

docker pull docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik

docker run -it --rm --pull=always \
  -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.17-nikolaik \
  -e LOG_ALL_EVENTS=true \
  -v /var/run/docker.sock:/var/run/docker.sock \
  -v ~/.openhands-state:/.openhands-state \
  -p 3000:3000 \
  --add-host host.docker.internal:host-gateway \
  --name openhands-app \
  docker.all-hands.dev/all-hands-ai/openhands:0.17

Step 2: Select others/deepseek-chat.
Step 3: Configure the API Key.
Step 4: Configure the GitHub token and enter a code repository.
Step 5: Send any message.

Expected: Normal response.
Actual: The chat box reports an error as follows：
completion(model='huggingface/starcoder',..) Learn more: https://docs.litellm.ai/docs/providers

Fix Method:
Go to [Ai Profive Configuration] -> [Customer Mode], change others/deepseek-chat to deepseek/deepseek-chat, save, and restart the session.

Referrence: https://docs.litellm.ai/docs/providers/deepseek

OpenHands Installation

Docker command in README

OpenHands Version

all-hands-ai/openhands:0.17

Operating System

WSL on Windows

Logs, Errors, Screenshots, and Additional Context

Default Configuration which is wrong

Chat Error with default config other/deep

Fix Configuration according to https://docs.litellm.ai/docs/providers/deepseek

Chat works well after fixed config.

[mamoodi]

Thanks! Looks like we need to revisit those basic settings dropdowns.