Skip to content

vision food reasoning eval #1385

vision food reasoning eval

vision food reasoning eval #1385

Triggered via pull request November 14, 2025 08:30
Status Success
Total duration 9m 19s
Artifacts 4

ci.yml

on: pull_request
Lint & Type Check
1m 42s
Lint & Type Check
Matrix: test-core
Batch Evaluation Tests
1m 16s
Batch Evaluation Tests
MCP End-to-End Tests
5m 35s
MCP End-to-End Tests
Upload Coverage
5s
Upload Coverage
Fit to window
Zoom out
Zoom in

Annotations

19 errors and 3 warnings
Lint & Type Check
8 errors
Lint & Type Check: eval_protocol/rewards/lean_prover.py#L236
Cannot access attribute "text" for class "ChatCompletionContentPartImageParam"   Attribute "text" is unknown (reportAttributeAccessIssue)
Lint & Type Check: eval_protocol/rewards/lean_prover.py#L61
Cannot access attribute "text" for class "ChatCompletionContentPartImageParam"   Attribute "text" is unknown (reportAttributeAccessIssue)
Lint & Type Check: eval_protocol/rewards/code_execution.py#L944
Cannot access attribute "text" for class "ChatCompletionContentPartImageParam"   Attribute "text" is unknown (reportAttributeAccessIssue)
Lint & Type Check: eval_protocol/rewards/code_execution.py#L177
Cannot access attribute "text" for class "ChatCompletionContentPartImageParam"   Attribute "text" is unknown (reportAttributeAccessIssue)
Lint & Type Check: eval_protocol/pytest/default_pydantic_ai_rollout_processor.py#L150
Cannot access attribute "text" for class "ChatCompletionContentPartImageParam"   Attribute "text" is unknown (reportAttributeAccessIssue)
Lint & Type Check: eval_protocol/pytest/default_pydantic_ai_rollout_processor.py#L143
Cannot access attribute "text" for class "ChatCompletionContentPartImageParam"   Attribute "text" is unknown (reportAttributeAccessIssue)
Lint & Type Check: eval_protocol/proxy/proxy_core/langfuse.py#L421
"Langfuse" is not exported from module "langfuse"   Import from "langfuse._client.client" instead (reportPrivateImportUsage)
Lint & Type Check: eval_protocol/proxy/proxy_core/langfuse.py#L208
"Langfuse" is not exported from module "langfuse"   Import from "langfuse._client.client" instead (reportPrivateImportUsage)
Core Tests (Python 3.10)
Event loop is closed
Core Tests (Python 3.10)
Event loop is closed
Core Tests (Python 3.10)
Event loop is closed
Core Tests (Python 3.10)
Event loop is closed
Core Tests (Python 3.10)
Event loop is closed
Core Tests (Python 3.10)
Event loop is closed
Core Tests (Python 3.10)
Event loop is closed
Core Tests (Python 3.10)
Event loop is closed
Core Tests (Python 3.10)
Event loop is closed
Core Tests (Python 3.10)
Event loop is closed
Lint & Type Check: eval_protocol/mcp/__init__.py#L49
Operation on "__all__" is not supported, so exported symbol list may be incorrect (reportUnsupportedDunderAll)
Lint & Type Check: eval_protocol/mcp/__init__.py#L49
Operation on "__all__" is not supported, so exported symbol list may be incorrect (reportUnsupportedDunderAll)
MCP End-to-End Tests
No files were found with the provided path: coverage.xml. No artifacts will be uploaded.

Artifacts

Produced during runtime
Name Size Digest
coverage-batch-eval Expired
44.6 KB
sha256:aa7b3b66a5e3546edaa2758572110e38180587f35b4e33b2683743a0e0701708
coverage-core-3.10 Expired
58 KB
sha256:9fb7af79dc6b23bcffede69be0e455df9859c9572f7c4891ea5cbdef7f82c5db
coverage-core-3.11 Expired
58 KB
sha256:9c563fe94fdb78446959e822b4faba4b0e0ba8dbc1cb838689abbb08eef110bf
coverage-core-3.12 Expired
58 KB
sha256:11d00bcc2439f76ae792753999a08a7441b34a38bbee724d0b88b88849b63d66