google.adk.models.lite_llm.LiteLlm._get_completion_inputs builds the litellm kwargs from a fixed allow-list of GenerateContentConfig fields (temperature, max_output_tokens, top_p, top_k, seed, stop_sequences, presence_penalty, frequency_penalty). thinking_config is present in config_dict but never forwarded, so an agent that sets e.g. ThinkingConfig(thinking_level=ThinkingLevel.LOW) gets the backend's default reasoning effort when run through LiteLlm, with no warning.
Verified on 2.8.0 and 2.10.0 (src/google/adk/models/lite_llm.py, the param_mapping / for key in (...) block, around line 3024 in v2.10.0). The only thinking handling in the file is the Anthropic thinking-block parsing on the response side.
litellm already normalises this across providers: reasoning_effort (low / medium / high, translated per provider, e.g. to Gemini thinkingConfig), and thinking={"type": "enabled", "budget_tokens": N} for budget-style providers.
Proposal: in _get_completion_inputs, map
thinking_config.thinking_level → reasoning_effortthinking_config.thinking_budget → thinking={"type": "enabled", "budget_tokens": ...}thinking_config.include_thoughts → the provider's equivalent where litellm exposes one
Related but different: #5712 (thinking blocks dropped when parsing responses), #5805 (thinking_config ignored in run_live).
google.adk.models.lite_llm.LiteLlm._get_completion_inputsbuilds the litellm kwargs from a fixed allow-list ofGenerateContentConfigfields (temperature,max_output_tokens,top_p,top_k,seed,stop_sequences,presence_penalty,frequency_penalty).thinking_configis present inconfig_dictbut never forwarded, so an agent that sets e.g.ThinkingConfig(thinking_level=ThinkingLevel.LOW)gets the backend's default reasoning effort when run throughLiteLlm, with no warning.Verified on 2.8.0 and 2.10.0 (
src/google/adk/models/lite_llm.py, theparam_mapping/for key in (...)block, around line 3024 in v2.10.0). The onlythinkinghandling in the file is the Anthropic thinking-block parsing on the response side.litellm already normalises this across providers:
reasoning_effort(low/medium/high, translated per provider, e.g. to GeminithinkingConfig), andthinking={"type": "enabled", "budget_tokens": N}for budget-style providers.Proposal: in
_get_completion_inputs, mapthinking_config.thinking_level→reasoning_effortthinking_config.thinking_budget→thinking={"type": "enabled", "budget_tokens": ...}thinking_config.include_thoughts→ the provider's equivalent where litellm exposes oneRelated but different: #5712 (thinking blocks dropped when parsing responses), #5805 (
thinking_configignored inrun_live).