a101d5980d
* load default settings instead of loading from agent for summarizer config * update tests to allow use of get_llm_config_from_handle * remove nit comment --------- Co-authored-by: Amy Guan <amy@letta.com>
71 lines
3.1 KiB
Python
71 lines
3.1 KiB
Python
from typing import Literal
|
||
|
||
from pydantic import BaseModel, Field
|
||
|
||
from letta.prompts.summarizer_prompt import ALL_PROMPT, SLIDING_PROMPT
|
||
from letta.schemas.enums import ProviderType
|
||
from letta.schemas.model import ModelSettingsUnion
|
||
from letta.settings import summarizer_settings
|
||
|
||
|
||
def get_default_summarizer_model(provider_type: ProviderType) -> str | None:
|
||
"""Get default model for summarization for given provider type."""
|
||
summarizer_defaults = {
|
||
ProviderType.anthropic: "anthropic/claude-haiku-4-5-20251001",
|
||
ProviderType.openai: "openai/gpt-5-mini",
|
||
ProviderType.google_ai: "google_ai/gemini-2.5-flash",
|
||
}
|
||
return summarizer_defaults.get(provider_type)
|
||
|
||
|
||
def get_default_prompt_for_mode(mode: Literal["all", "sliding_window"]) -> str:
|
||
"""Get the default prompt for a given compaction mode.
|
||
Also used in /summarize endpoint if mode is changed and prompt is not explicitly set."""
|
||
if mode == "all":
|
||
return ALL_PROMPT
|
||
else: # sliding_window
|
||
return SLIDING_PROMPT
|
||
|
||
|
||
class CompactionSettings(BaseModel):
|
||
"""Configuration for conversation compaction / summarization.
|
||
|
||
``model`` is the only required user-facing field – it specifies the summarizer
|
||
model handle (e.g. ``"openai/gpt-4o-mini"``). Per-model settings (temperature,
|
||
max tokens, etc.) are derived from the default configuration for that handle.
|
||
"""
|
||
|
||
# Summarizer model handle (provider/model-name).
|
||
# If None, uses lightweight provider-specific defaults (e.g., haiku for Anthropic, gpt-5-mini for OpenAI).
|
||
model: str | None = Field(
|
||
default=None,
|
||
description="Model handle to use for summarization (format: provider/model-name). If None, uses lightweight provider-specific defaults.",
|
||
)
|
||
|
||
# Optional provider-specific model settings for the summarizer model
|
||
model_settings: ModelSettingsUnion | None = Field(
|
||
default=None,
|
||
description="Optional model settings used to override defaults for the summarizer model.",
|
||
)
|
||
|
||
prompt: str | None = Field(default=None, description="The prompt to use for summarization. If None, uses mode-specific default.")
|
||
prompt_acknowledgement: bool = Field(
|
||
default=False, description="Whether to include an acknowledgement post-prompt (helps prevent non-summary outputs)."
|
||
)
|
||
clip_chars: int | None = Field(
|
||
default=50000, description="The maximum length of the summary in characters. If none, no clipping is performed."
|
||
)
|
||
|
||
mode: Literal["all", "sliding_window", "self"] = Field(default="sliding_window", description="The type of summarization technique use.")
|
||
sliding_window_percentage: float = Field(
|
||
default_factory=lambda: summarizer_settings.partial_evict_summarizer_percentage,
|
||
description="The percentage of the context window to keep post-summarization (only used in sliding window mode).",
|
||
)
|
||
|
||
# Called upon agent creation and if mode is changed in summarize endpoint request
|
||
def set_mode_specific_prompt(self):
|
||
"""Set mode-specific default prompt if none provided."""
|
||
if self.prompt is None:
|
||
self.prompt = get_default_prompt_for_mode(self.mode)
|
||
return self
|