#gemini http 400 function call missing thought_signature

1 messages · Page 1 of 1 (latest)

gritty pike
#

Error: 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:search_files , position 4. Please refer to https://ai.google.dev/gemini-api/docs/thought-signatures for more
details.

--- hermes dump ---
version: 0.10.0 (2026.4.16) [ce089169]
os: Darwin 24.6.0 arm64
python: 3.11.15
openai_sdk: 2.30.0
profile: default
hermes_home: ~/.hermes
model: gemini-3.1-flash-lite-preview
provider: gemini
terminal: local

api_keys:
openrouter set
openai not set
anthropic not set
anthropic_token not set
nous not set
glm/zai not set
zai not set
kimi not set
minimax not set
deepseek not set
dashscope not set
huggingface not set
nvidia set
ai_gateway not set
opencode_zen not set
opencode_go not set
kilocode not set
firecrawl not set
tavily not set
browserbase not set
fal not set
elevenlabs not set
github not set

features:
toolsets: hermes-cli
mcp_servers: 0
memory_provider: built-in
gateway: running (launchd, pid 28201)
platforms: telegram
cron_jobs: 0
skills: 87

config_overrides:
display.streaming: True
--- end dump ---

also quite annoying to change the compression model. not sure why this isn't exposed in the hermes model config

#

by the way, you guys are doing a great job with such a high volume of support requests