mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-06-10 17:35:57 +00:00
Ryker_Feng
167ef4512f
* feat(memory): add memory.token_counting config to avoid tiktoken network dependency (#3429) Add a `memory.token_counting` option (`tiktoken` | `char`) so deployments in network-restricted environments can opt out of tiktoken entirely. In `char` mode the memory-injection budget uses a network-free character-based estimate and never triggers the BPE download from openaipublic.blob.core.windows.net, which could otherwise block for tens of minutes (see #3402). Also harden the default `tiktoken` path: - cache an in-flight LOADING sentinel so concurrent callers fall back immediately instead of spawning more blocking get_encoding threads when the first load is still running (e.g. under the 5s startup warm-up timeout); - cache failures with a timestamp and retry after a cooldown so a transient network outage self-heals back to accurate counting without a restart; - skip startup warm-up entirely in char mode. The new config is surfaced via the memory config API and config.example.yaml (config_version bumped). Default remains `tiktoken`, so existing deployments are unaffected. * fix(memory): use CJK-aware char token estimate and address review feedback - Replace the flat len(text)//4 fallback with a CJK-aware estimate so Chinese/Japanese/Korean memory content does not over-fill the injection budget - Document the internal tiktoken retry cooldown and char-mode escape hatch - Sync CLAUDE.md / config.example.yaml / MEMORY_IMPROVEMENTS.md wording - Fix MemoryConfigResponse mocks/assertions and add CJK estimate tests
97 lines
3.2 KiB
Python
97 lines
3.2 KiB
Python
"""Configuration for memory mechanism."""
|
|
|
|
from typing import Literal
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
|
|
class MemoryConfig(BaseModel):
|
|
"""Configuration for global memory mechanism."""
|
|
|
|
enabled: bool = Field(
|
|
default=True,
|
|
description="Whether to enable memory mechanism",
|
|
)
|
|
storage_path: str = Field(
|
|
default="",
|
|
description=(
|
|
"Path to store memory data. "
|
|
"If empty, defaults to per-user memory at `{base_dir}/users/{user_id}/memory.json`. "
|
|
"Absolute paths are used as-is and opt out of per-user isolation "
|
|
"(all users share the same file). "
|
|
"Relative paths are resolved against `Paths.base_dir` "
|
|
"(not the backend working directory). "
|
|
"Note: if you previously set this to `.deer-flow/memory.json`, "
|
|
"the file will now be resolved as `{base_dir}/.deer-flow/memory.json`; "
|
|
"migrate existing data or use an absolute path to preserve the old location."
|
|
),
|
|
)
|
|
storage_class: str = Field(
|
|
default="deerflow.agents.memory.storage.FileMemoryStorage",
|
|
description="The class path for memory storage provider",
|
|
)
|
|
debounce_seconds: int = Field(
|
|
default=30,
|
|
ge=1,
|
|
le=300,
|
|
description="Seconds to wait before processing queued updates (debounce)",
|
|
)
|
|
model_name: str | None = Field(
|
|
default=None,
|
|
description="Model name to use for memory updates (None = use default model)",
|
|
)
|
|
max_facts: int = Field(
|
|
default=100,
|
|
ge=10,
|
|
le=500,
|
|
description="Maximum number of facts to store",
|
|
)
|
|
fact_confidence_threshold: float = Field(
|
|
default=0.7,
|
|
ge=0.0,
|
|
le=1.0,
|
|
description="Minimum confidence threshold for storing facts",
|
|
)
|
|
injection_enabled: bool = Field(
|
|
default=True,
|
|
description="Whether to inject memory into system prompt",
|
|
)
|
|
max_injection_tokens: int = Field(
|
|
default=2000,
|
|
ge=100,
|
|
le=8000,
|
|
description="Maximum tokens to use for memory injection",
|
|
)
|
|
token_counting: Literal["tiktoken", "char"] = Field(
|
|
default="tiktoken",
|
|
description=(
|
|
"Token counting strategy for memory-injection budgeting. "
|
|
"'tiktoken' is accurate but the encoding's BPE data may be "
|
|
"downloaded from a public network endpoint on first use, which "
|
|
"can block for a long time in network-restricted environments "
|
|
"(see issue #3402/#3429). 'char' uses a network-free "
|
|
"CJK-aware character-based estimate and never touches tiktoken."
|
|
),
|
|
)
|
|
|
|
|
|
# Global configuration instance
|
|
_memory_config: MemoryConfig = MemoryConfig()
|
|
|
|
|
|
def get_memory_config() -> MemoryConfig:
|
|
"""Get the current memory configuration."""
|
|
return _memory_config
|
|
|
|
|
|
def set_memory_config(config: MemoryConfig) -> None:
|
|
"""Set the memory configuration."""
|
|
global _memory_config
|
|
_memory_config = config
|
|
|
|
|
|
def load_memory_config_from_dict(config_dict: dict) -> None:
|
|
"""Load memory configuration from a dictionary."""
|
|
global _memory_config
|
|
_memory_config = MemoryConfig(**config_dict)
|