scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

Add adaptive thiking for bedrock converse

Browse source
This commit is contained in:
Sameer Kankute 2026-02-06 09:40:16 +05:30
parent bfd410704b
commit e0b2791ef0
5 changed files with 45 additions and 40 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

63
litellm/llms/anthropic/chat/transformation.py
View file

@ -170,7 +170,8 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
tool_call["caller"] = cast(Dict[str, Any], anthropic_tool_content["caller"]) # type: ignore[typeddict-item]
return tool_call
def _is_claude_opus_4_6(self, model: str) -> bool:
@staticmethod
def _is_claude_opus_4_6(model: str) -> bool:
"""Check if the model is Claude Opus 4.5."""
return "opus-4-6" in model.lower() or "opus_4_6" in model.lower()
@ -650,32 +651,38 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
@staticmethod
def _map_reasoning_effort(
reasoning_effort: Optional[Union[REASONING_EFFORT, str]],
reasoning_effort: Optional[Union[REASONING_EFFORT, str]],
model: str,
) -> Optional[AnthropicThinkingParam]:
if reasoning_effort is None:
return None
elif reasoning_effort == "low":
if AnthropicConfig._is_claude_opus_4_6(model):
return AnthropicThinkingParam(
type="enabled",
budget_tokens=DEFAULT_REASONING_EFFORT_LOW_THINKING_BUDGET,
)
elif reasoning_effort == "medium":
return AnthropicThinkingParam(
type="enabled",
budget_tokens=DEFAULT_REASONING_EFFORT_MEDIUM_THINKING_BUDGET,
)
elif reasoning_effort == "high":
return AnthropicThinkingParam(
type="enabled",
budget_tokens=DEFAULT_REASONING_EFFORT_HIGH_THINKING_BUDGET,
)
elif reasoning_effort == "minimal":
return AnthropicThinkingParam(
type="enabled",
budget_tokens=DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET,
type="adaptive",
)
else:
raise ValueError(f"Unmapped reasoning effort: {reasoning_effort}")
if reasoning_effort is None:
return None
elif reasoning_effort == "low":
return AnthropicThinkingParam(
type="enabled",
budget_tokens=DEFAULT_REASONING_EFFORT_LOW_THINKING_BUDGET,
)
elif reasoning_effort == "medium":
return AnthropicThinkingParam(
type="enabled",
budget_tokens=DEFAULT_REASONING_EFFORT_MEDIUM_THINKING_BUDGET,
)
elif reasoning_effort == "high":
return AnthropicThinkingParam(
type="enabled",
budget_tokens=DEFAULT_REASONING_EFFORT_HIGH_THINKING_BUDGET,
)
elif reasoning_effort == "minimal":
return AnthropicThinkingParam(
type="enabled",
budget_tokens=DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET,
)
else:
raise ValueError(f"Unmapped reasoning effort: {reasoning_effort}")
def _extract_json_schema_from_response_format(
self, value: Optional[dict]
@ -851,13 +858,9 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
if param == "thinking":
optional_params["thinking"] = value
elif param == "reasoning_effort" and isinstance(value, str):
# For Claude Opus 4.6, map reasoning_effort to new adaptive thinking type
if self._is_claude_opus_4_6(model):
optional_params["thinking"] = {"type": "adaptive"}
else:
optional_params["thinking"] = AnthropicConfig._map_reasoning_effort(
value
)
optional_params["thinking"] = AnthropicConfig._map_reasoning_effort(
reasoning_effort=value, model=model
)
elif param == "web_search_options" and isinstance(value, dict):
hosted_web_search_tool = self.map_web_search_tool(
cast(OpenAIWebSearchOptions, value)

3
litellm/llms/bedrock/chat/converse_transformation.py
View file

@ -66,6 +66,7 @@ from ..common_utils import (
BedrockModelInfo,
get_anthropic_beta_from_headers,
get_bedrock_tool_name,
is_claude_4_5_on_bedrock,
)
# Computer use tool prefixes supported by Bedrock
@ -391,7 +392,7 @@ class AmazonConverseConfig(BaseConfig):
else:
# Anthropic and other models: convert to thinking parameter
optional_params["thinking"] = AnthropicConfig._map_reasoning_effort(
reasoning_effort
reasoning_effort=reasoning_effort, model=model
)
def get_supported_openai_params(self, model: str) -> List[str]:

3
litellm/llms/databricks/chat/transformation.py
View file

@ -298,7 +298,8 @@ class DatabricksConfig(DatabricksBase, OpenAILikeChatConfig, AnthropicConfig):
if "reasoning_effort" in non_default_params and "claude" in model:
optional_params["thinking"] = AnthropicConfig._map_reasoning_effort(
non_default_params.get("reasoning_effort")
reasoning_effort=non_default_params.get("reasoning_effort"),
model=model
)
optional_params.pop("reasoning_effort", None)
## handle thinking tokens

8
litellm/model_prices_and_context_window_backup.json
View file

@ -872,7 +872,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 159
},
"anthropic.claude-opus-4-6-v1:0": {
"anthropic.claude-opus-4-6-v1": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_read_input_token_cost": 5e-07,
@ -932,7 +932,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346
},
"global.anthropic.claude-opus-4-6-v1:0": {
"global.anthropic.claude-opus-4-6-v1": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_read_input_token_cost": 5e-07,
@ -1052,7 +1052,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346
},
"eu.anthropic.claude-opus-4-6-v1:0": {
"eu.anthropic.claude-opus-4-6-v1": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
@ -1112,7 +1112,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346
},
"apac.anthropic.claude-opus-4-6-v1:0": {
"apac.anthropic.claude-opus-4-6-v1": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,

8
model_prices_and_context_window.json
View file

@ -872,7 +872,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 159
},
"anthropic.claude-opus-4-6-v1:0": {
"anthropic.claude-opus-4-6-v1": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_read_input_token_cost": 5e-07,
@ -932,7 +932,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346
},
"global.anthropic.claude-opus-4-6-v1:0": {
"global.anthropic.claude-opus-4-6-v1": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_read_input_token_cost": 5e-07,
@ -1052,7 +1052,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346
},
"eu.anthropic.claude-opus-4-6-v1:0": {
"eu.anthropic.claude-opus-4-6-v1": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,
@ -1112,7 +1112,7 @@
"supports_vision": true,
"tool_use_system_prompt_tokens": 346
},
"apac.anthropic.claude-opus-4-6-v1:0": {
"apac.anthropic.claude-opus-4-6-v1": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.375e-05,
"cache_read_input_token_cost": 5.5e-07,