scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-06 08:16:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 78

Add tranlation of context_management

Browse source
This commit is contained in:
Sameer Kankute 2026-02-26 18:05:20 +05:30
parent 3e6b253cd6
commit ca5c0448dd
2 changed files with 61 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
litellm/llms/anthropic/experimental_pass_through/responses_adapters/handler.py
View file

@ -24,7 +24,9 @@ def _build_responses_kwargs(
max_tokens: int,
messages: List[Dict],
model: str,
context_management: Optional[Dict] = None,
metadata: Optional[Dict] = None,
output_config: Optional[Dict] = None,
stop_sequences: Optional[List[str]] = None,
stream: Optional[bool] = False,
system: Optional[str] = None,
@ -42,6 +44,10 @@ def _build_responses_kwargs(
"""
# Build a typed AnthropicMessagesRequest for the adapter
request_data: Dict[str, Any] = {"model": model, "messages": messages, "max_tokens": max_tokens}
if context_management:
request_data["context_management"] = context_management
if output_config:
request_data["output_config"] = output_config
if metadata:
request_data["metadata"] = metadata
if system:
@ -98,7 +104,9 @@ class LiteLLMMessagesToResponsesAPIHandler:
max_tokens: int,
messages: List[Dict],
model: str,
context_management: Optional[Dict] = None,
metadata: Optional[Dict] = None,
output_config: Optional[Dict] = None,
stop_sequences: Optional[List[str]] = None,
stream: Optional[bool] = False,
system: Optional[str] = None,
@ -115,7 +123,9 @@ class LiteLLMMessagesToResponsesAPIHandler:
max_tokens=max_tokens,
messages=messages,
model=model,
context_management=context_management,
metadata=metadata,
output_config=output_config,
stop_sequences=stop_sequences,
stream=stream,
system=system,
@ -145,7 +155,9 @@ class LiteLLMMessagesToResponsesAPIHandler:
max_tokens: int,
messages: List[Dict],
model: str,
context_management: Optional[Dict] = None,
metadata: Optional[Dict] = None,
output_config: Optional[Dict] = None,
stop_sequences: Optional[List[str]] = None,
stream: Optional[bool] = False,
system: Optional[str] = None,
@ -168,7 +180,9 @@ class LiteLLMMessagesToResponsesAPIHandler:
max_tokens=max_tokens,
messages=messages,
model=model,
context_management=context_management,
metadata=metadata,
output_config=output_config,
stop_sequences=stop_sequences,
stream=stream,
system=system,
@ -187,7 +201,9 @@ class LiteLLMMessagesToResponsesAPIHandler:
max_tokens=max_tokens,
messages=messages,
model=model,
context_management=context_management,
metadata=metadata,
output_config=output_config,
stop_sequences=stop_sequences,
stream=stream,
system=system,

47
litellm/llms/anthropic/experimental_pass_through/responses_adapters/transformation.py
View file

@ -191,6 +191,37 @@ class LiteLLMAnthropicToResponsesAPIAdapter:
return {"type": "function", "name": tool_choice.get("name", "")}
return {"type": "auto"}
@staticmethod
def translate_context_management_to_responses_api(
context_management: Dict[str, Any],
) -> Optional[List[Dict[str, Any]]]:
"""
Convert Anthropic context_management dict to OpenAI Responses API array format.
Anthropic format: {"edits": [{"type": "compact_20260112", "trigger": {"type": "input_tokens", "value": 150000}}]}
OpenAI format: [{"type": "compaction", "compact_threshold": 150000}]
"""
if not isinstance(context_management, dict):
return None
edits = context_management.get("edits", [])
if not isinstance(edits, list):
return None
result: List[Dict[str, Any]] = []
for edit in edits:
if not isinstance(edit, dict):
continue
edit_type = edit.get("type", "")
if edit_type == "compact_20260112":
entry: Dict[str, Any] = {"type": "compaction"}
trigger = edit.get("trigger")
if isinstance(trigger, dict) and trigger.get("value") is not None:
entry["compact_threshold"] = int(trigger["value"])
result.append(entry)
return result if result else None
@staticmethod
def translate_thinking_to_reasoning(thinking: Dict[str, Any]) -> Optional[Dict[str, Any]]:
"""
@ -276,8 +307,13 @@ class LiteLLMAnthropicToResponsesAPIAdapter:
if reasoning:
responses_kwargs["reasoning"] = reasoning
# output_format -> text format
# output_format / output_config.format -> text format
# output_format: {"type": "json_schema", "schema": {...}}
# output_config: {"format": {"type": "json_schema", "schema": {...}}}
output_format = anthropic_request.get("output_format")
output_config = anthropic_request.get("output_config")
if not isinstance(output_format, dict) and isinstance(output_config, dict):
output_format = output_config.get("format")
if isinstance(output_format, dict) and output_format.get("type") == "json_schema":
schema = output_format.get("schema")
if schema:
@ -290,10 +326,17 @@ class LiteLLMAnthropicToResponsesAPIAdapter:
}
}
# context_management: Anthropic dict -> OpenAI array
context_management = anthropic_request.get("context_management")
if isinstance(context_management, dict):
openai_cm = self.translate_context_management_to_responses_api(context_management)
if openai_cm is not None:
responses_kwargs["context_management"] = openai_cm
# metadata user_id -> user
metadata = anthropic_request.get("metadata")
if isinstance(metadata, dict) and "user_id" in metadata:
responses_kwargs["user"] = metadata["user_id"]
responses_kwargs["user"] = str(metadata["user_id"])[:64]
return responses_kwargs