Error on <app-all-hands.dev> using opus 4.5. Stopp...
# dev-help
s
Error on app-all-hands.dev using opus 4.5. Stopped the conversation but it could continue after another user message
Copy code
litellm.BadRequestError: Error code: 400 - {'error': {'message': 'litellm.BadRequestError: AnthropicException - {"type":"error","error":{"type":"invalid_request_error","message":"messages.5.content.0.type: Expected `thinking` or `redacted_thinking`, but found `tool_use`. When `thinking` is enabled, a final `assistant` message must start with a thinking block (preceeding the lastmost set of `tool_use` and `tool_result` blocks). We recommend you include thinking blocks from previous turns. To avoid this requirement, disable `thinking`. Please consult our documentation at <https://docs.claude.com/en/docs/build-with-claude/extended-thinking>"},"request_id":"req_011CWQNYsoUKpFYAxF1cKbuU"}No fallback model group found for original model_group=claude-opus-4-5-20251101. Fallbacks=[{\'qwen3-coder-480b\': [\'qwen3-coder-480b-or\']}, {\'glm-4.5\': [\'glm-4.5-or\']}]. Received Model Group=claude-opus-4-5-20251101\nAvailable Model Group Fallbacks=None\nError doing the fallback: litellm.BadRequestError: AnthropicException - {"type":"error","error":{"type":"invalid_request_error","message":"messages.5.content.0.type: Expected `thinking` or `redacted_thinking`, but found `tool_use`. When `thinking` is enabled, a final `assistant` message must start with a thinking block (preceeding the lastmost set of `tool_use` and `tool_result` blocks). We recommend you include thinking blocks from previous turns. To avoid this requirement, disable `thinking`. Please consult our documentation at <https://docs.claude.com/en/docs/build-with-claude/extended-thinking>"},"request_id":"req_011CWQNYsoUKpFYAxF1cKbuU"}No fallback model group found for original model_group=claude-opus-4-5-20251101. Fallbacks=[{\'qwen3-coder-480b\': [\'qwen3-coder-480b-or\']}, {\'glm-4.5\': [\'glm-4.5-or\']}] LiteLLM Retried: 1 times, LiteLLM Max Retries: 2', 'type': None, 'param': None, 'code': '400'}}
c
yes, this is a known issue in the SDK https://github.com/OpenHands/software-agent-sdk/issues/1438 and @wide-doctor-37830 is working on it!
s
There have been a whole bunch of changes in main that I think will require a more thorough test. The last time we ran next-warm-runtimes it blew up, so I would be reluctant to do this today. If you want to create a patch release - the procedure to patch saas will be: • Go to the rel661 branch (Which still has a draft PR) • Update the agent server image: https://github.com/OpenHands/OpenHands/blob/22b149229ee7712597107a8df7056d27c3a5fd72/openhands/app_server/sandbox/sandbox_spec_service.py#L15 • Update the openhands sha / agent server sha to match this in the deploy project and tag - base it on https://github.com/OpenHands/deploy/commit/bc54876123fd86b6027d29f3e82826a1e8f1d0b4 / https://github.com/OpenHands/deploy/releases/tag/0.66.1 • Test on staging • Run the next-warm-runtimes script • Tag the release
I'll release first thing in the morning with Mahmoud's help: • created this PR in OpenHands: https://github.com/OpenHands/OpenHands/pull/12159 • Added to this branch: https://github.com/OpenHands/deploy/tree/test-db