ollama - 💡(How to fix) Fix gemini-3-flash-preview:cloud - Function Calling returns 400 [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
ollama/ollama#15785Fetched 2026-04-24 10:36:07
View on GitHub
Comments
0
Participants
1
Timeline
1
Reactions
0
Author
Participants
Timeline (top)
labeled ×1

Fix Action

Fix / Workaround

Is support for Gemini 3 thought_signature in tool/function calling already planned? Is there a recommended workaround in the meantime (e.g. disable tools for Gemini 3, or use a different Gemini model)?

RAW_BUFFERClick to expand / collapse

What is the issue?

Google's Gemini 3 API enforces a thought_signature mechanism: every function call response includes a signature that must be sent back alongside the tool result; omitting it causes 400 errors. Multiple SDKs integrating Gemini 3 have had to add explicit support for thought_signature to make tool calling work. Ollama Cloud currently does not propagate or manage thought_signature for Gemini 3, causing tool integrations that work with other models to fail specifically for gemini-3-flash-preview:cloud. Questions:

Is support for Gemini 3 thought_signature in tool/function calling already planned? Is there a recommended workaround in the meantime (e.g. disable tools for Gemini 3, or use a different Gemini model)?

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

extent analysis

TL;DR

Implementing support for Gemini 3's thought_signature mechanism in Ollama Cloud is likely necessary to resolve the 400 errors encountered during tool integrations.

Guidance

  • Investigate adding explicit support for thought_signature in Ollama Cloud, similar to other SDKs that have already integrated this feature for Gemini 3.
  • Consider a temporary workaround, such as disabling tools for Gemini 3 or using a different Gemini model, until proper support is implemented.
  • Review the Gemini 3 API documentation to understand the specific requirements for the thought_signature mechanism and how it should be propagated and managed.
  • Reach out to the Ollama Cloud development team or community to inquire about planned support for Gemini 3 thought_signature and potential timelines.

Notes

The lack of information about the Ollama version and other system details limits the ability to provide a more tailored solution. Additionally, without specific log output or error messages, it's challenging to identify potential issues beyond the thought_signature mechanism.

Recommendation

Apply a workaround, such as disabling tools for Gemini 3 or using a different model, until explicit support for thought_signature can be implemented in Ollama Cloud. This approach allows for continued functionality with other models while awaiting a more permanent solution.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

ollama - 💡(How to fix) Fix gemini-3-flash-preview:cloud - Function Calling returns 400 [1 participants]