temperature=0.0 silently ignored from 2nd turn onward in multi-turn chat (falsy value treated as unset)

[ken12313451]

Environment details

- Programming language: Python 3.13
- OS: Windows 11
- Language runtime version: Python 3.13
- Package version: google-genai (latest as of March 2026)

Summary

In multi-turn chat, temperature=0.0 works correctly on the first send_message
call, but from the 2nd turn onward it appears to be treated as "unset" (falsy),
causing the model to fall back to default temperature (1.0). Setting
temperature=0.01 works correctly on all turns.

This is a critical issue for applications requiring deterministic output across a
full multi-turn session.

Steps to reproduce

1. Create a chat session with GenerateContentConfig(temperature=0.0, seed=12345)
2. First send_message — works as expected (deterministic output)
3. Second send_message with same config (temperature=0.0) — output becomes
   non-deterministic, as if temperature is unset
4. Change to temperature=0.01 on the 2nd turn — output becomes near-deterministic
   again

Expected behavior

temperature=0.0 should be respected on all turns, not just the first.

Actual behavior

temperature=0.0 works on the 1st turn but is silently ignored from the 2nd turn
onward, likely due to falsy value handling (0.0 == False in Python). The model
falls back to default temperature, producing highly variable output.

Workaround

None. Even setting temperature=0.01 as a workaround does not fully resolve the
issue — it still requires finding specific seed values that produce acceptable
results, and complete determinism is never guaranteed. We strongly request a fix for
this bug.

[ken12313451]

Related: The same issue has been reported in the Go SDK as well:
googleapis/go-genai#196

This suggests the root cause may be in the API server side, not specific to the
Python SDK.

It appears this was partially fixed for single-turn requests
(googleapis/go-genai#196), but the same falsy handling issue persists in multi-turn
chat from the 2nd turn onward. The fix likely did not cover the send_message code
path.

[paulandrewfinch-cyber]

Duplicate of #2137

[Venkaiahbabuneelam]

Hi @ken12313451, Thanks for reaching out us!

Kindly please let me know the issue still perstit, i would see the 2137 merged successfully, To handle the issue reported.

Thanks