hermes - 💡(How to fix) Fix [Bug]: Gemini Model missing thought_signature [8 comments, 7 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
NousResearch/hermes-agent#14488Fetched 2026-04-24 06:16:56
View on GitHub
Comments
8
Participants
7
Timeline
26
Reactions
0
Author
Timeline (top)
commented ×8mentioned ×6subscribed ×6labeled ×4

Error Message

You will get this error ❌ Non-retryable error (HTTP 400): HTTP 400: Gemini HTTP 400 (INVALID_ARGUMENT): Function call is missing a thought_signature in functionCall parts. This is required for tools to work correctly, and missing thought_signature may lead to degraded model performance. Additional data, function call default_api:skill_view , position 5. Please refer to https://ai.google.dev/gemini-api/docs/thought-signatures for more details. ❌ Non-retryable client error (HTTP 400). Aborting.

Additional Logs / Traceback (optional)

Root Cause

Root Cause Analysis (optional)

Fix Action

Fixed

  • Closed with commit: f5af6520d0bfac5b17c9ce460a5a06bf3249972c

Code Example

Non-retryable error (HTTP 400): HTTP 400: Gemini HTTP 400 (INVALID_ARGUMENT): Function call is missing a thought_signature in functionCall parts. This is required for tools to work correctly, and missing thought_signature may lead to degraded model performance. Additional data, function call `default_api:skill_view` , position 5. Please refer to https://ai.google.dev/gemini-api/docs/thought-signatures for more details.
 Non-retryable client error (HTTP 400). Aborting.

---
RAW_BUFFERClick to expand / collapse

Bug Description

With the leatest update I can not reach gemini models anymore Function call is missing a thought_signature in functionCall parts

Steps to Reproduce

Hermes Agent v0.10.0 (2026.4.16)

  1. Pick the gemini model gemini-3.1-pro-preview
  2. Start Hermes
  3. Ask a question

You will get this error Function call is missing a thought_signature in functionCall parts

Expected Behavior

-> Get a reply with Hermes

Actual Behavior

Function call is missing a thought_signature in functionCall parts

Affected Component

Agent Core (conversation loop, context compression, memory)

Messaging Platform (if gateway-related)

No response

Debug Report

❌ Non-retryable error (HTTP 400): HTTP 400: Gemini HTTP 400 (INVALID_ARGUMENT): Function call is missing a thought_signature in functionCall parts. This is required for tools to work correctly, and missing thought_signature may lead to degraded model performance. Additional data, function call `default_api:skill_view` , position 5. Please refer to https://ai.google.dev/gemini-api/docs/thought-signatures for more details.
❌ Non-retryable client error (HTTP 400). Aborting.

Operating System

Ubuntu 24.04

Python Version

3.11.15

Hermes Version

v0.10.0

Additional Logs / Traceback (optional)

Root Cause Analysis (optional)

No response

Proposed Fix (optional)

No response

Are you willing to submit a PR for this?

  • I'd like to fix this myself and submit a PR

extent analysis

TL;DR

The error "Function call is missing a thought_signature in functionCall parts" suggests that the thought_signature parameter is required for the Gemini model to work correctly, and it's missing in the function call.

Guidance

  • Review the Gemini API documentation at https://ai.google.dev/gemini-api/docs/thought-signatures to understand the requirements for the thought_signature parameter.
  • Verify that the thought_signature is correctly configured in the Hermes Agent settings or function call parameters.
  • Check the Hermes Agent version (v0.10.0) and ensure it's compatible with the Gemini model version (gemini-3.1-pro-preview).
  • Investigate the default_api:skill_view function call at position 5, as mentioned in the error message, to determine why the thought_signature is missing.

Example

No code snippet is provided as the issue lacks specific code details.

Notes

The error message suggests a specific issue with the thought_signature parameter, but without more information about the code or configuration, it's difficult to provide a precise fix.

Recommendation

Apply workaround: Update the function call to include the required thought_signature parameter, as described in the Gemini API documentation, to resolve the error and ensure correct model performance.

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

hermes - 💡(How to fix) Fix [Bug]: Gemini Model missing thought_signature [8 comments, 7 participants]