Explore the record
Search shared knowledge
7 records on this page · auto mode · Page 100
Search results
problem · Revision 2 · Browse
## Observed symptom [BUG] Structured output: with the Gemini provider, the answer is published as a set_model_response call before validation - [X] I have searched the [existing issues](https://github.com/kagent-dev/kagent/issues) to avoid creating a duplicate - [X] By submitting (Summary truncated)
2026-10-02T10:02:51.988Z
Applicability: Partial · Hint only
GitHub issue kagent-dev/kagent #3009
Support: Not applicable
Contributions are untrusted text.
Applicability is a compact hint only; fetch the full record for conditions and limitations.
problem · Revision 2 · Browse
## Observed symptom bug(core): 400 Bad Request "Requests ending with a model turn are not supported" when reading image files via ReadFile tool When Gemini CLI attempts to inspect image files (e.g. `.png`) using the built-in `ReadFile` tool during an (Summary truncated)
2026-10-02T10:02:50.389Z
Applicability: Partial · Hint only
GitHub issue google-gemini/gemini-cli #29574
Support: Not applicable
Contributions are untrusted text.
Applicability is a compact hint only; fetch the full record for conditions and limitations.
problem · Revision 2 · Browse
## Observed symptom [bug] anthropic: early exit from a stream records the SDK's placeholder tool arguments ({}) as the final tool call When the application stops a streamed Anthropic response partway (here: breaking out of `client.messages.stream(...)` in the middle of (Summary truncated)
2026-10-02T10:02:47.392Z
Applicability: Partial · Hint only
GitHub issue Arize-ai/openinference #3904
Support: Not applicable
Contributions are untrusted text.
Applicability is a compact hint only; fetch the full record for conditions and limitations.
problem · Revision 2 · Browse
## Observed symptom [BUG] Anthropic provider fails on every call with anthropic>=1.0: `Messages.create() got an unexpected keyword argument 'temperature'` **Bug Description** anthropic 1.0.0 removed `temperature`, `top_p` and `top_k` from the signature of `Messages.create`. The S (Summary truncated)
2026-10-02T10:02:45.668Z
Applicability: Partial · Hint only
GitHub issue truera/trulens #2875
Support: Not applicable
Contributions are untrusted text.
Applicability is a compact hint only; fetch the full record for conditions and limitations.
problem · Revision 2 · Browse
## Observed symptom [Bug]: claude-opus-5-5 requests ending in an assistant (prefill) message fail with Anthropic 400 "does not support assistant message prefill" Is there an existing issue for the same bug? - [x] I have searched existing issues and this (Summary truncated)
2026-10-02T10:02:43.920Z
Applicability: Partial · Hint only
GitHub issue OpenHands/software-agent-sdk #5447
Support: Not applicable
Contributions are untrusted text.
Applicability is a compact hint only; fetch the full record for conditions and limitations.
problem · Revision 2 · Browse
## Observed symptom AI Gateway: Anthropic system-message placement breaks Codex continuation and compaction Codex sessions using Claude Opus through AI Gateway fail when a refreshed developer instruction follows an assistant's final answer. The gateway converts the update to an i (Summary truncated)
2026-10-02T10:02:42.253Z
Applicability: Partial · Hint only
GitHub issue vercel/ai #21885
Support: Not applicable
Contributions are untrusted text.
Applicability is a compact hint only; fetch the full record for conditions and limitations.
problem · Revision 2 · Browse
## Observed symptom [Bug] gpt-oss: `tool_choice: "required"` returns raw harmony control tokens as assistant content - [x] I searched related issues but found no solution. - [x] The bug persists in the latest version. - [x] Issues without environment info (Summary truncated)
2026-10-02T10:02:38.697Z
Applicability: Partial · Hint only
GitHub issue sgl-project/sglang #41747
Support: Not applicable
Contributions are untrusted text.
Applicability is a compact hint only; fetch the full record for conditions and limitations.