# Gemini 3.0 Flash Error - "missing a 'thought\_signature'" when handling parallel function call results **URL:** \ **Category:** Support Help\ **Created:** [February 5, 2026, 7:04pm UTC](https://community.retellai.com/t/gemini-3-0-flash-error-missing-a-thought-signature-when-handling-parallel-function-call-results/785 "2026-02-05T19:04:27Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![tyec](https://avatars.discourse-cdn.com/v4/letter/t/3bc359/32.png) [@tyec](https://community.retellai.com/u/tyec)\ **Post date:** [February 5, 2026, 7:04pm UTC](https://community.retellai.com/t/gemini-3-0-flash-error-missing-a-thought-signature-when-handling-parallel-function-call-results/785/1 "2026-02-05T19:04:27Z")
### Environment - **LLM Provider** : Gemini 3.0 Flash (via Retell) - **Issue Type** : LLM Integration Bug - **Severity** : High (blocking voice conversations) ### Problem Description When Retell sends **parallel function calls** (multiple functions executed simultaneously) and our backend returns successful results for all of them, the Gemini 3.0 Flash LLM fails with the following error: ```auto Unable to submit request because function call 'default_api:lock_state' in the 11. content block is missing a 'thought_signature' ``` This causes the voice conversation to hang/fail after the function calls complete successfully. ### Steps to Reproduce 1. Configure a Retell agent with Gemini 3.0 Flash as the LLM 2. Define custom functions that can be called in parallel 3. During a conversation, trigger multiple function calls simultaneously 4. All functions execute successfully and return valid responses 5. **Error** : Gemini rejects the function results with `thought_signature` error ### Expected Behavior The LLM should process the function call results and continue the conversation. ### Actual Behavior The conversation hangs. Dashboard logs show: ```auto error: Error encountered in LLM call: Failed to get response from any LLM provider: {"error":{"message":"Unable to submit request because function call `default_api:lock_state` in the 11. content block is missing a `thought_signature`"}} ``` ### Additional Context - The `thought_signature` appears to be a Gemini-specific requirement related to their extended thinking feature - Individual function calls work fine; the issue only occurs with parallel function call results - Our backend successfully executes all functions and returns valid JSON responses ---
**Author:** ![support2](https://yyz2.discourse-cdn.com/flex008/user_avatar/community.retellai.com/support2/32/15_2.png) [@support2](https://community.retellai.com/u/support2)\ **Post date:** [February 5, 2026, 7:04pm UTC](https://community.retellai.com/t/gemini-3-0-flash-error-missing-a-thought-signature-when-handling-parallel-function-call-results/785/2 "2026-02-05T19:04:50Z")
* * * The Gemini 3.0 Flash `thought_signature` error you’re encountering with parallel function calls isn’t directly addressed in the available Retell AI documentation. However, I can provide context based on what’s documented about function calling behavior. Retell AI’s function calling implementation has specific behaviors around parallel execution. When you create a Retell LLM, you can configure `tool_call_strict_mode` which affects how tool calls are handled[(1)](https://docs.retellai.com/api-references/create-retell-llm). Based on community discussions, there have been reported issues with the LLM calling functions without waiting for previous function completion[(2)](https://discord.com/channels/1186424376300679209/1308943238106841180). One user reported: “this directly conflicts with your documentation: When there’re tools being called, the model would not be able to make any new tool calls until the current tool call is completed”[(2)](https://discord.com/channels/1186424376300679209/1308943238106841180). For your specific Gemini 3.0 Flash issue with the `thought_signature` error during parallel function calls, this appears to be a Gemini-specific requirement that may not be fully compatible with Retell’s current implementation. **Recommended actions:** 1. **Try enabling `tool_call_strict_mode`** when creating your Retell LLM[(1)](https://docs.retellai.com/api-references/create-retell-llm) 2. **Consider switching to a different model** - Retell supports multiple LLM options including GPT-4.1, GPT-5 models, and Claude variants[(1)](https://docs.retellai.com/api-references/create-retell-llm) 3. **Contact Retell support directly** through their [Discord](https://discord.com/invite/wxtjkjj2zp) or [Contact Sales](https://retellai.octolane.com/)[(3)](https://www.retellai.com/changelog) The `thought_signature` requirement appears to be specific to Gemini’s extended thinking feature and may require Retell to update their Gemini integration to properly handle this parameter during parallel function call responses. ---
**Author:** ![Omar\_Ashraf](https://yyz2.discourse-cdn.com/flex008/user_avatar/community.retellai.com/omar_ashraf/32/102_2.png) [@Omar\_Ashraf](https://community.retellai.com/u/Omar_Ashraf)\ **Post date:** [February 5, 2026, 8:59pm UTC](https://community.retellai.com/t/gemini-3-0-flash-error-missing-a-thought-signature-when-handling-parallel-function-call-results/785/3 "2026-02-05T20:59:26Z")
Hello @tyec Can you share the call id that has this issue? ---
**Author:** ![sebastien](https://yyz2.discourse-cdn.com/flex008/user_avatar/community.retellai.com/sebastien/32/2307_2.png) [@sebastien](https://community.retellai.com/u/sebastien)\ **Post date:** [July 9, 2026, 5:26pm UTC](https://community.retellai.com/t/gemini-3-0-flash-error-missing-a-thought-signature-when-handling-parallel-function-call-results/785/4 "2026-07-09T17:26:41Z")
I’ve found this related topic with a solution : [Fix Gemini 400 "missing thought\_signature" in function calls](https://manifest.build/errors/gemini/400-missing-thought-signature/) Maybe it helps..