[BUG CLIENT]: Agent cannot handle JSON output format with web search #414
Description
Python -VV
Python 3.10.19 (main, Dec 17 2025, 20:54:19) [Clang 21.1.4 ]Pip Freeze
annotated-types==0.7.0
anyio==4.12.1
attrs==25.4.0
authlib==1.6.9
certifi==2026.2.25
cffi==2.0.0
charset-normalizer==3.4.5
click==8.3.1
colorama==0.4.6
cryptography==46.0.5
eval-type-backport==0.3.1
exceptiongroup==1.3.1
googleapis-common-protos==1.73.0
griffe==1.15.0
h11==0.16.0
httpcore==1.0.9
httpx==0.28.1
httpx-sse==0.4.3
idna==3.11
importlib-metadata==8.7.1
invoke==2.2.1
jsonschema==4.26.0
jsonschema-specifications==2025.9.1
mcp==1.26.0
mistralai==1.12.4
opentelemetry-api==1.40.0
opentelemetry-exporter-otlp-proto-common==1.40.0
opentelemetry-exporter-otlp-proto-http==1.40.0
opentelemetry-proto==1.40.0
opentelemetry-sdk==1.40.0
opentelemetry-semantic-conventions==0.61b0
polars==1.38.1
polars-runtime-32==1.38.1
protobuf==6.33.5
pycparser==3.0
pydantic==2.12.5
pydantic-core==2.41.5
pydantic-settings==2.13.1
pyjwt==2.11.0
python-dateutil==2.9.0.post0
python-dotenv==1.2.2
python-multipart==0.0.22
pyyaml==6.0.3
referencing==0.37.0
requests==2.32.5
rpds-py==0.30.0
six==1.17.0
sse-starlette==3.3.2
starlette==0.52.1
typing-extensions==4.15.0
typing-inspection==0.4.2
urllib3==2.6.3
uvicorn==0.41.0
zipp==3.23.0Reproduction Steps
Setting the response type to json or json-format in the UI for an agent and then calling it using the API via client.beta.conversations.start() leads to
raise models.SDKError("API error occurred", http_res, http_res_text)
mistralai.models.sdkerror.SDKError: API error occurred: Status 500. Body: {"object":"Error","message":"Failed to persist entries.","type":"invalid_request_error","code":3000}
Expected Behavior
As this works in the UI, I would have expected it to work in the API as well?
Additional Context
No response
Suggested Solutions
No response