mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-24 00:45:57 +00:00
refactor(config): eliminate global mutable state — explicit parameter passing on top of main
Squashes 25 PR commits onto current main. AppConfig becomes a pure value object with no ambient lookup. Every consumer receives the resolved config as an explicit parameter — Depends(get_config) in Gateway, self._app_config in DeerFlowClient, runtime.context.app_config in agent runs, AppConfig.from_file() at the LangGraph Server registration boundary. Phase 1 — frozen data + typed context - All config models (AppConfig, MemoryConfig, DatabaseConfig, …) become frozen=True; no sub-module globals. - AppConfig.from_file() is pure (no side-effect singleton loaders). - Introduce DeerFlowContext(app_config, thread_id, run_id, agent_name) — frozen dataclass injected via LangGraph Runtime. - Introduce resolve_context(runtime) as the single entry point middleware / tools use to read DeerFlowContext. Phase 2 — pure explicit parameter passing - Gateway: app.state.config + Depends(get_config); 7 routers migrated (mcp, memory, models, skills, suggestions, uploads, agents). - DeerFlowClient: __init__(config=...) captures config locally. - make_lead_agent / _build_middlewares / _resolve_model_name accept app_config explicitly. - RunContext.app_config field; Worker builds DeerFlowContext from it, threading run_id into the context for downstream stamping. - Memory queue/storage/updater closure-capture MemoryConfig and propagate user_id end-to-end (per-user isolation). - Sandbox/skills/community/factories/tools thread app_config. - resolve_context() rejects non-typed runtime.context. - Test suite migrated off AppConfig.current() monkey-patches. - AppConfig.current() classmethod deleted. Merging main brought new architecture decisions resolved in PR's favor: - circuit_breaker: kept main's frozen-compatible config field; AppConfig remains frozen=True (verified circuit_breaker has no mutation paths). - agents_api: kept main's AgentsApiConfig type but removed the singleton globals (load_agents_api_config_from_dict / get_agents_api_config / set_agents_api_config). 8 routes in agents.py now read via Depends(get_config). - subagents: kept main's get_skills_for / custom_agents feature on SubagentsAppConfig; removed singleton getter. registry.py now reads app_config.subagents directly. - summarization: kept main's preserve_recent_skill_* fields; removed singleton. - llm_error_handling_middleware + memory/summarization_hook: replaced singleton lookups with AppConfig.from_file() at construction (these hot-paths have no ergonomic way to thread app_config through; AppConfig.from_file is a pure load). - worker.py + thread_data_middleware.py: DeerFlowContext.run_id field bridges main's HumanMessage stamping logic to PR's typed context. Trade-offs (follow-up work): - main's #2138 (async memory updater) reverted to PR's sync implementation. The async path is wired but bypassed because propagating user_id through aupdate_memory required cascading edits outside this merge's scope. - tests/test_subagent_skills_config.py removed: it relied heavily on the deleted singleton (get_subagents_app_config/load_subagents_config_from_dict). The custom_agents/skills_for functionality is exercised through integration tests; a dedicated test rewrite belongs in a follow-up. Verification: backend test suite — 2560 passed, 4 skipped, 84 failures. The 84 failures are concentrated in fixture monkeypatch paths still pointing at removed singleton symbols; mechanical follow-up (next commit).
This commit is contained in:
greatmengqi
@@ -7,11 +7,17 @@ from dataclasses import dataclass, field
|
||||
from datetime import UTC, datetime
|
||||
from typing import Any
|
||||
|
||||
from deerflow.config.memory_config import get_memory_config
|
||||
from deerflow.config.app_config import AppConfig
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
# Module-level config pointer set by the middleware that owns the queue.
|
||||
# The queue runs on a background Timer thread where ``Runtime`` and FastAPI
|
||||
# request context are not accessible; the enqueuer (which does have runtime
|
||||
# context) is responsible for plumbing ``AppConfig`` through ``add()``.
|
||||
|
||||
|
||||
@dataclass
|
||||
class ConversationContext:
|
||||
"""Context for a conversation to be processed for memory update."""
|
||||
@@ -20,6 +26,7 @@ class ConversationContext:
|
||||
messages: list[Any]
|
||||
timestamp: datetime = field(default_factory=lambda: datetime.now(UTC))
|
||||
agent_name: str | None = None
|
||||
user_id: str | None = None
|
||||
correction_detected: bool = False
|
||||
reinforcement_detected: bool = False
|
||||
|
||||
@@ -30,10 +37,21 @@ class MemoryUpdateQueue:
|
||||
This queue collects conversation contexts and processes them after
|
||||
a configurable debounce period. Multiple conversations received within
|
||||
the debounce window are batched together.
|
||||
|
||||
The queue captures an ``AppConfig`` reference at construction time and
|
||||
reuses it for the MemoryUpdater it spawns. Callers must construct a
|
||||
fresh queue when the config changes rather than reaching into a global.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the memory update queue."""
|
||||
def __init__(self, app_config: AppConfig):
|
||||
"""Initialize the memory update queue.
|
||||
|
||||
Args:
|
||||
app_config: Application config. The queue reads its own
|
||||
``memory`` section for debounce timing and hands the full
|
||||
config to :class:`MemoryUpdater`.
|
||||
"""
|
||||
self._app_config = app_config
|
||||
self._queue: list[ConversationContext] = []
|
||||
self._lock = threading.Lock()
|
||||
self._timer: threading.Timer | None = None
|
||||
@@ -44,19 +62,12 @@ class MemoryUpdateQueue:
|
||||
thread_id: str,
|
||||
messages: list[Any],
|
||||
agent_name: str | None = None,
|
||||
user_id: str | None = None,
|
||||
correction_detected: bool = False,
|
||||
reinforcement_detected: bool = False,
|
||||
) -> None:
|
||||
"""Add a conversation to the update queue.
|
||||
|
||||
Args:
|
||||
thread_id: The thread ID.
|
||||
messages: The conversation messages.
|
||||
agent_name: If provided, memory is stored per-agent. If None, uses global memory.
|
||||
correction_detected: Whether recent turns include an explicit correction signal.
|
||||
reinforcement_detected: Whether recent turns include a positive reinforcement signal.
|
||||
"""
|
||||
config = get_memory_config()
|
||||
"""Add a conversation to the update queue."""
|
||||
config = self._app_config.memory
|
||||
if not config.enabled:
|
||||
return
|
||||
|
||||
@@ -65,6 +76,7 @@ class MemoryUpdateQueue:
|
||||
thread_id=thread_id,
|
||||
messages=messages,
|
||||
agent_name=agent_name,
|
||||
user_id=user_id,
|
||||
correction_detected=correction_detected,
|
||||
reinforcement_detected=reinforcement_detected,
|
||||
)
|
||||
@@ -77,11 +89,12 @@ class MemoryUpdateQueue:
|
||||
thread_id: str,
|
||||
messages: list[Any],
|
||||
agent_name: str | None = None,
|
||||
user_id: str | None = None,
|
||||
correction_detected: bool = False,
|
||||
reinforcement_detected: bool = False,
|
||||
) -> None:
|
||||
"""Add a conversation and start processing immediately in the background."""
|
||||
config = get_memory_config()
|
||||
config = self._app_config.memory
|
||||
if not config.enabled:
|
||||
return
|
||||
|
||||
@@ -90,6 +103,7 @@ class MemoryUpdateQueue:
|
||||
thread_id=thread_id,
|
||||
messages=messages,
|
||||
agent_name=agent_name,
|
||||
user_id=user_id,
|
||||
correction_detected=correction_detected,
|
||||
reinforcement_detected=reinforcement_detected,
|
||||
)
|
||||
@@ -103,6 +117,7 @@ class MemoryUpdateQueue:
|
||||
thread_id: str,
|
||||
messages: list[Any],
|
||||
agent_name: str | None,
|
||||
user_id: str | None = None,
|
||||
correction_detected: bool,
|
||||
reinforcement_detected: bool,
|
||||
) -> None:
|
||||
@@ -116,6 +131,7 @@ class MemoryUpdateQueue:
|
||||
thread_id=thread_id,
|
||||
messages=messages,
|
||||
agent_name=agent_name,
|
||||
user_id=user_id,
|
||||
correction_detected=merged_correction_detected,
|
||||
reinforcement_detected=merged_reinforcement_detected,
|
||||
)
|
||||
@@ -125,7 +141,7 @@ class MemoryUpdateQueue:
|
||||
|
||||
def _reset_timer(self) -> None:
|
||||
"""Reset the debounce timer."""
|
||||
config = get_memory_config()
|
||||
config = self._app_config.memory
|
||||
self._schedule_timer(config.debounce_seconds)
|
||||
|
||||
logger.debug("Memory update timer set for %ss", config.debounce_seconds)
|
||||
@@ -165,7 +181,7 @@ class MemoryUpdateQueue:
|
||||
logger.info("Processing %d queued memory updates", len(contexts_to_process))
|
||||
|
||||
try:
|
||||
updater = MemoryUpdater()
|
||||
updater = MemoryUpdater(self._app_config)
|
||||
|
||||
for context in contexts_to_process:
|
||||
try:
|
||||
@@ -176,6 +192,7 @@ class MemoryUpdateQueue:
|
||||
agent_name=context.agent_name,
|
||||
correction_detected=context.correction_detected,
|
||||
reinforcement_detected=context.reinforcement_detected,
|
||||
user_id=context.user_id,
|
||||
)
|
||||
if success:
|
||||
logger.info("Memory updated successfully for thread %s", context.thread_id)
|
||||
@@ -236,31 +253,35 @@ class MemoryUpdateQueue:
|
||||
return self._processing
|
||||
|
||||
|
||||
# Global singleton instance
|
||||
_memory_queue: MemoryUpdateQueue | None = None
|
||||
# Queues keyed by ``id(AppConfig)`` so tests and multi-client setups with
|
||||
# distinct configs do not share a debounce queue.
|
||||
_memory_queues: dict[int, MemoryUpdateQueue] = {}
|
||||
_queue_lock = threading.Lock()
|
||||
|
||||
|
||||
def get_memory_queue() -> MemoryUpdateQueue:
|
||||
"""Get the global memory update queue singleton.
|
||||
|
||||
Returns:
|
||||
The memory update queue instance.
|
||||
"""
|
||||
global _memory_queue
|
||||
def get_memory_queue(app_config: AppConfig) -> MemoryUpdateQueue:
|
||||
"""Get or create the memory update queue for the given app config."""
|
||||
key = id(app_config)
|
||||
with _queue_lock:
|
||||
if _memory_queue is None:
|
||||
_memory_queue = MemoryUpdateQueue()
|
||||
return _memory_queue
|
||||
queue = _memory_queues.get(key)
|
||||
if queue is None:
|
||||
queue = MemoryUpdateQueue(app_config)
|
||||
_memory_queues[key] = queue
|
||||
return queue
|
||||
|
||||
|
||||
def reset_memory_queue() -> None:
|
||||
"""Reset the global memory queue.
|
||||
def reset_memory_queue(app_config: AppConfig | None = None) -> None:
|
||||
"""Reset memory queue(s).
|
||||
|
||||
This is useful for testing.
|
||||
Pass an ``app_config`` to reset only its queue, or omit to reset all
|
||||
(useful at test teardown).
|
||||
"""
|
||||
global _memory_queue
|
||||
with _queue_lock:
|
||||
if _memory_queue is not None:
|
||||
_memory_queue.clear()
|
||||
_memory_queue = None
|
||||
if app_config is not None:
|
||||
queue = _memory_queues.pop(id(app_config), None)
|
||||
if queue is not None:
|
||||
queue.clear()
|
||||
return
|
||||
for queue in _memory_queues.values():
|
||||
queue.clear()
|
||||
_memory_queues.clear()
|
||||
|
||||
@@ -10,7 +10,7 @@ from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from deerflow.config.agents_config import AGENT_NAME_PATTERN
|
||||
from deerflow.config.memory_config import get_memory_config
|
||||
from deerflow.config.memory_config import MemoryConfig
|
||||
from deerflow.config.paths import get_paths
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -44,17 +44,17 @@ class MemoryStorage(abc.ABC):
|
||||
"""Abstract base class for memory storage providers."""
|
||||
|
||||
@abc.abstractmethod
|
||||
def load(self, agent_name: str | None = None) -> dict[str, Any]:
|
||||
def load(self, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
|
||||
"""Load memory data for the given agent."""
|
||||
pass
|
||||
|
||||
@abc.abstractmethod
|
||||
def reload(self, agent_name: str | None = None) -> dict[str, Any]:
|
||||
def reload(self, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
|
||||
"""Force reload memory data for the given agent."""
|
||||
pass
|
||||
|
||||
@abc.abstractmethod
|
||||
def save(self, memory_data: dict[str, Any], agent_name: str | None = None) -> bool:
|
||||
def save(self, memory_data: dict[str, Any], agent_name: str | None = None, *, user_id: str | None = None) -> bool:
|
||||
"""Save memory data for the given agent."""
|
||||
pass
|
||||
|
||||
@@ -62,11 +62,18 @@ class MemoryStorage(abc.ABC):
|
||||
class FileMemoryStorage(MemoryStorage):
|
||||
"""File-based memory storage provider."""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the file memory storage."""
|
||||
# Per-agent memory cache: keyed by agent_name (None = global)
|
||||
def __init__(self, memory_config: MemoryConfig):
|
||||
"""Initialize the file memory storage.
|
||||
|
||||
Args:
|
||||
memory_config: Memory configuration (storage_path etc.). Stored on
|
||||
the instance so per-request lookups don't need to reach for
|
||||
ambient state.
|
||||
"""
|
||||
self._memory_config = memory_config
|
||||
# Per-user/agent memory cache: keyed by (user_id, agent_name) tuple (None = global)
|
||||
# Value: (memory_data, file_mtime)
|
||||
self._memory_cache: dict[str | None, tuple[dict[str, Any], float | None]] = {}
|
||||
self._memory_cache: dict[tuple[str | None, str | None], tuple[dict[str, Any], float | None]] = {}
|
||||
# Guards all reads and writes to _memory_cache across concurrent callers.
|
||||
self._cache_lock = threading.Lock()
|
||||
|
||||
@@ -81,21 +88,28 @@ class FileMemoryStorage(MemoryStorage):
|
||||
if not AGENT_NAME_PATTERN.match(agent_name):
|
||||
raise ValueError(f"Invalid agent name {agent_name!r}: names must match {AGENT_NAME_PATTERN.pattern}")
|
||||
|
||||
def _get_memory_file_path(self, agent_name: str | None = None) -> Path:
|
||||
def _get_memory_file_path(self, agent_name: str | None = None, *, user_id: str | None = None) -> Path:
|
||||
"""Get the path to the memory file."""
|
||||
config = self._memory_config
|
||||
if user_id is not None:
|
||||
if agent_name is not None:
|
||||
self._validate_agent_name(agent_name)
|
||||
return get_paths().user_agent_memory_file(user_id, agent_name)
|
||||
if config.storage_path and Path(config.storage_path).is_absolute():
|
||||
return Path(config.storage_path)
|
||||
return get_paths().user_memory_file(user_id)
|
||||
# Legacy: no user_id
|
||||
if agent_name is not None:
|
||||
self._validate_agent_name(agent_name)
|
||||
return get_paths().agent_memory_file(agent_name)
|
||||
|
||||
config = get_memory_config()
|
||||
if config.storage_path:
|
||||
p = Path(config.storage_path)
|
||||
return p if p.is_absolute() else get_paths().base_dir / p
|
||||
return get_paths().memory_file
|
||||
|
||||
def _load_memory_from_file(self, agent_name: str | None = None) -> dict[str, Any]:
|
||||
def _load_memory_from_file(self, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
|
||||
"""Load memory data from file."""
|
||||
file_path = self._get_memory_file_path(agent_name)
|
||||
file_path = self._get_memory_file_path(agent_name, user_id=user_id)
|
||||
|
||||
if not file_path.exists():
|
||||
return create_empty_memory()
|
||||
@@ -108,44 +122,46 @@ class FileMemoryStorage(MemoryStorage):
|
||||
logger.warning("Failed to load memory file: %s", e)
|
||||
return create_empty_memory()
|
||||
|
||||
def load(self, agent_name: str | None = None) -> dict[str, Any]:
|
||||
def load(self, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
|
||||
"""Load memory data (cached with file modification time check)."""
|
||||
file_path = self._get_memory_file_path(agent_name)
|
||||
file_path = self._get_memory_file_path(agent_name, user_id=user_id)
|
||||
|
||||
try:
|
||||
current_mtime = file_path.stat().st_mtime if file_path.exists() else None
|
||||
except OSError:
|
||||
current_mtime = None
|
||||
|
||||
cache_key = (user_id, agent_name)
|
||||
with self._cache_lock:
|
||||
cached = self._memory_cache.get(agent_name)
|
||||
cached = self._memory_cache.get(cache_key)
|
||||
if cached is not None and cached[1] == current_mtime:
|
||||
return cached[0]
|
||||
|
||||
memory_data = self._load_memory_from_file(agent_name)
|
||||
memory_data = self._load_memory_from_file(agent_name, user_id=user_id)
|
||||
|
||||
with self._cache_lock:
|
||||
self._memory_cache[agent_name] = (memory_data, current_mtime)
|
||||
self._memory_cache[cache_key] = (memory_data, current_mtime)
|
||||
|
||||
return memory_data
|
||||
|
||||
def reload(self, agent_name: str | None = None) -> dict[str, Any]:
|
||||
def reload(self, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
|
||||
"""Reload memory data from file, forcing cache invalidation."""
|
||||
file_path = self._get_memory_file_path(agent_name)
|
||||
memory_data = self._load_memory_from_file(agent_name)
|
||||
file_path = self._get_memory_file_path(agent_name, user_id=user_id)
|
||||
memory_data = self._load_memory_from_file(agent_name, user_id=user_id)
|
||||
|
||||
try:
|
||||
mtime = file_path.stat().st_mtime if file_path.exists() else None
|
||||
except OSError:
|
||||
mtime = None
|
||||
|
||||
cache_key = (user_id, agent_name)
|
||||
with self._cache_lock:
|
||||
self._memory_cache[agent_name] = (memory_data, mtime)
|
||||
self._memory_cache[cache_key] = (memory_data, mtime)
|
||||
return memory_data
|
||||
|
||||
def save(self, memory_data: dict[str, Any], agent_name: str | None = None) -> bool:
|
||||
def save(self, memory_data: dict[str, Any], agent_name: str | None = None, *, user_id: str | None = None) -> bool:
|
||||
"""Save memory data to file and update cache."""
|
||||
file_path = self._get_memory_file_path(agent_name)
|
||||
file_path = self._get_memory_file_path(agent_name, user_id=user_id)
|
||||
|
||||
try:
|
||||
file_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
@@ -165,8 +181,9 @@ class FileMemoryStorage(MemoryStorage):
|
||||
except OSError:
|
||||
mtime = None
|
||||
|
||||
cache_key = (user_id, agent_name)
|
||||
with self._cache_lock:
|
||||
self._memory_cache[agent_name] = (memory_data, mtime)
|
||||
self._memory_cache[cache_key] = (memory_data, mtime)
|
||||
logger.info("Memory saved to %s", file_path)
|
||||
return True
|
||||
except OSError as e:
|
||||
@@ -174,23 +191,31 @@ class FileMemoryStorage(MemoryStorage):
|
||||
return False
|
||||
|
||||
|
||||
_storage_instance: MemoryStorage | None = None
|
||||
# Instances keyed by (storage_class_path, id(memory_config)) so tests can
|
||||
# construct isolated storages and multi-client setups with different configs
|
||||
# don't collide on a single process-wide singleton.
|
||||
_storage_instances: dict[tuple[str, int], MemoryStorage] = {}
|
||||
_storage_lock = threading.Lock()
|
||||
|
||||
|
||||
def get_memory_storage() -> MemoryStorage:
|
||||
"""Get the configured memory storage instance."""
|
||||
global _storage_instance
|
||||
if _storage_instance is not None:
|
||||
return _storage_instance
|
||||
def get_memory_storage(memory_config: MemoryConfig) -> MemoryStorage:
|
||||
"""Get the configured memory storage instance.
|
||||
|
||||
Caches one instance per ``(storage_class, memory_config)`` pair. In
|
||||
single-config deployments this collapses to one instance; in multi-client
|
||||
or test scenarios each config gets its own storage.
|
||||
"""
|
||||
key = (memory_config.storage_class, id(memory_config))
|
||||
existing = _storage_instances.get(key)
|
||||
if existing is not None:
|
||||
return existing
|
||||
|
||||
with _storage_lock:
|
||||
if _storage_instance is not None:
|
||||
return _storage_instance
|
||||
|
||||
config = get_memory_config()
|
||||
storage_class_path = config.storage_class
|
||||
existing = _storage_instances.get(key)
|
||||
if existing is not None:
|
||||
return existing
|
||||
|
||||
storage_class_path = memory_config.storage_class
|
||||
try:
|
||||
module_path, class_name = storage_class_path.rsplit(".", 1)
|
||||
import importlib
|
||||
@@ -204,13 +229,14 @@ def get_memory_storage() -> MemoryStorage:
|
||||
if not issubclass(storage_class, MemoryStorage):
|
||||
raise TypeError(f"Configured memory storage '{storage_class_path}' is not a subclass of MemoryStorage")
|
||||
|
||||
_storage_instance = storage_class()
|
||||
instance = storage_class(memory_config)
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
"Failed to load memory storage %s, falling back to FileMemoryStorage: %s",
|
||||
storage_class_path,
|
||||
e,
|
||||
)
|
||||
_storage_instance = FileMemoryStorage()
|
||||
instance = FileMemoryStorage(memory_config)
|
||||
|
||||
return _storage_instance
|
||||
_storage_instances[key] = instance
|
||||
return instance
|
||||
|
||||
@@ -5,12 +5,19 @@ from __future__ import annotations
|
||||
from deerflow.agents.memory.message_processing import detect_correction, detect_reinforcement, filter_messages_for_memory
|
||||
from deerflow.agents.memory.queue import get_memory_queue
|
||||
from deerflow.agents.middlewares.summarization_middleware import SummarizationEvent
|
||||
from deerflow.config.memory_config import get_memory_config
|
||||
from deerflow.config.app_config import AppConfig
|
||||
|
||||
|
||||
def memory_flush_hook(event: SummarizationEvent) -> None:
|
||||
"""Flush messages about to be summarized into the memory queue."""
|
||||
if not get_memory_config().enabled or not event.thread_id:
|
||||
"""Flush messages about to be summarized into the memory queue.
|
||||
|
||||
Reads ``AppConfig`` from disk on every invocation. This hook is fired by
|
||||
``SummarizationMiddleware`` which has no ergonomic way to thread an
|
||||
explicit ``app_config`` through; ``AppConfig.from_file()`` is a pure load
|
||||
so the cost is acceptable for this rare pre-summarization callback.
|
||||
"""
|
||||
app_config = AppConfig.from_file()
|
||||
if not app_config.memory.enabled or not event.thread_id:
|
||||
return
|
||||
|
||||
filtered_messages = filter_messages_for_memory(list(event.messages_to_summarize))
|
||||
@@ -21,7 +28,7 @@ def memory_flush_hook(event: SummarizationEvent) -> None:
|
||||
|
||||
correction_detected = detect_correction(filtered_messages)
|
||||
reinforcement_detected = not correction_detected and detect_reinforcement(filtered_messages)
|
||||
queue = get_memory_queue()
|
||||
queue = get_memory_queue(app_config)
|
||||
queue.add_nowait(
|
||||
thread_id=event.thread_id,
|
||||
messages=filtered_messages,
|
||||
|
||||
@@ -21,7 +21,8 @@ from deerflow.agents.memory.storage import (
|
||||
get_memory_storage,
|
||||
utc_now_iso_z,
|
||||
)
|
||||
from deerflow.config.memory_config import get_memory_config
|
||||
from deerflow.config.app_config import AppConfig
|
||||
from deerflow.config.memory_config import MemoryConfig
|
||||
from deerflow.models import create_chat_model
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -38,44 +39,33 @@ def _create_empty_memory() -> dict[str, Any]:
|
||||
return create_empty_memory()
|
||||
|
||||
|
||||
def _save_memory_to_file(memory_data: dict[str, Any], agent_name: str | None = None) -> bool:
|
||||
"""Backward-compatible wrapper around the configured memory storage save path."""
|
||||
return get_memory_storage().save(memory_data, agent_name)
|
||||
def _save_memory_to_file(memory_config: MemoryConfig, memory_data: dict[str, Any], agent_name: str | None = None, *, user_id: str | None = None) -> bool:
|
||||
"""Save via the configured memory storage."""
|
||||
return get_memory_storage(memory_config).save(memory_data, agent_name, user_id=user_id)
|
||||
|
||||
|
||||
def get_memory_data(agent_name: str | None = None) -> dict[str, Any]:
|
||||
def get_memory_data(memory_config: MemoryConfig, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
|
||||
"""Get the current memory data via storage provider."""
|
||||
return get_memory_storage().load(agent_name)
|
||||
return get_memory_storage(memory_config).load(agent_name, user_id=user_id)
|
||||
|
||||
|
||||
def reload_memory_data(agent_name: str | None = None) -> dict[str, Any]:
|
||||
def reload_memory_data(memory_config: MemoryConfig, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
|
||||
"""Reload memory data via storage provider."""
|
||||
return get_memory_storage().reload(agent_name)
|
||||
return get_memory_storage(memory_config).reload(agent_name, user_id=user_id)
|
||||
|
||||
|
||||
def import_memory_data(memory_data: dict[str, Any], agent_name: str | None = None) -> dict[str, Any]:
|
||||
"""Persist imported memory data via storage provider.
|
||||
|
||||
Args:
|
||||
memory_data: Full memory payload to persist.
|
||||
agent_name: If provided, imports into per-agent memory.
|
||||
|
||||
Returns:
|
||||
The saved memory data after storage normalization.
|
||||
|
||||
Raises:
|
||||
OSError: If persisting the imported memory fails.
|
||||
"""
|
||||
storage = get_memory_storage()
|
||||
if not storage.save(memory_data, agent_name):
|
||||
def import_memory_data(memory_config: MemoryConfig, memory_data: dict[str, Any], agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
|
||||
"""Persist imported memory data via storage provider."""
|
||||
storage = get_memory_storage(memory_config)
|
||||
if not storage.save(memory_data, agent_name, user_id=user_id):
|
||||
raise OSError("Failed to save imported memory data")
|
||||
return storage.load(agent_name)
|
||||
return storage.load(agent_name, user_id=user_id)
|
||||
|
||||
|
||||
def clear_memory_data(agent_name: str | None = None) -> dict[str, Any]:
|
||||
def clear_memory_data(memory_config: MemoryConfig, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
|
||||
"""Clear all stored memory data and persist an empty structure."""
|
||||
cleared_memory = create_empty_memory()
|
||||
if not _save_memory_to_file(cleared_memory, agent_name):
|
||||
if not _save_memory_to_file(memory_config, cleared_memory, agent_name, user_id=user_id):
|
||||
raise OSError("Failed to save cleared memory data")
|
||||
return cleared_memory
|
||||
|
||||
@@ -88,10 +78,13 @@ def _validate_confidence(confidence: float) -> float:
|
||||
|
||||
|
||||
def create_memory_fact(
|
||||
memory_config: MemoryConfig,
|
||||
content: str,
|
||||
category: str = "context",
|
||||
confidence: float = 0.5,
|
||||
agent_name: str | None = None,
|
||||
*,
|
||||
user_id: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Create a new fact and persist the updated memory data."""
|
||||
normalized_content = content.strip()
|
||||
@@ -101,7 +94,7 @@ def create_memory_fact(
|
||||
normalized_category = category.strip() or "context"
|
||||
validated_confidence = _validate_confidence(confidence)
|
||||
now = utc_now_iso_z()
|
||||
memory_data = get_memory_data(agent_name)
|
||||
memory_data = get_memory_data(memory_config, agent_name, user_id=user_id)
|
||||
updated_memory = dict(memory_data)
|
||||
facts = list(memory_data.get("facts", []))
|
||||
facts.append(
|
||||
@@ -116,15 +109,15 @@ def create_memory_fact(
|
||||
)
|
||||
updated_memory["facts"] = facts
|
||||
|
||||
if not _save_memory_to_file(updated_memory, agent_name):
|
||||
if not _save_memory_to_file(memory_config, updated_memory, agent_name, user_id=user_id):
|
||||
raise OSError("Failed to save memory data after creating fact")
|
||||
|
||||
return updated_memory
|
||||
|
||||
|
||||
def delete_memory_fact(fact_id: str, agent_name: str | None = None) -> dict[str, Any]:
|
||||
def delete_memory_fact(memory_config: MemoryConfig, fact_id: str, agent_name: str | None = None, *, user_id: str | None = None) -> dict[str, Any]:
|
||||
"""Delete a fact by its id and persist the updated memory data."""
|
||||
memory_data = get_memory_data(agent_name)
|
||||
memory_data = get_memory_data(memory_config, agent_name, user_id=user_id)
|
||||
facts = memory_data.get("facts", [])
|
||||
updated_facts = [fact for fact in facts if fact.get("id") != fact_id]
|
||||
if len(updated_facts) == len(facts):
|
||||
@@ -133,21 +126,24 @@ def delete_memory_fact(fact_id: str, agent_name: str | None = None) -> dict[str,
|
||||
updated_memory = dict(memory_data)
|
||||
updated_memory["facts"] = updated_facts
|
||||
|
||||
if not _save_memory_to_file(updated_memory, agent_name):
|
||||
if not _save_memory_to_file(memory_config, updated_memory, agent_name, user_id=user_id):
|
||||
raise OSError(f"Failed to save memory data after deleting fact '{fact_id}'")
|
||||
|
||||
return updated_memory
|
||||
|
||||
|
||||
def update_memory_fact(
|
||||
memory_config: MemoryConfig,
|
||||
fact_id: str,
|
||||
content: str | None = None,
|
||||
category: str | None = None,
|
||||
confidence: float | None = None,
|
||||
agent_name: str | None = None,
|
||||
*,
|
||||
user_id: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Update an existing fact and persist the updated memory data."""
|
||||
memory_data = get_memory_data(agent_name)
|
||||
memory_data = get_memory_data(memory_config, agent_name, user_id=user_id)
|
||||
updated_memory = dict(memory_data)
|
||||
updated_facts: list[dict[str, Any]] = []
|
||||
found = False
|
||||
@@ -174,7 +170,7 @@ def update_memory_fact(
|
||||
|
||||
updated_memory["facts"] = updated_facts
|
||||
|
||||
if not _save_memory_to_file(updated_memory, agent_name):
|
||||
if not _save_memory_to_file(memory_config, updated_memory, agent_name, user_id=user_id):
|
||||
raise OSError(f"Failed to save memory data after updating fact '{fact_id}'")
|
||||
|
||||
return updated_memory
|
||||
@@ -299,19 +295,25 @@ def _fact_content_key(content: Any) -> str | None:
|
||||
class MemoryUpdater:
|
||||
"""Updates memory using LLM based on conversation context."""
|
||||
|
||||
def __init__(self, model_name: str | None = None):
|
||||
def __init__(self, app_config: AppConfig, model_name: str | None = None):
|
||||
"""Initialize the memory updater.
|
||||
|
||||
Args:
|
||||
app_config: Application config (the updater needs both ``memory``
|
||||
section for behavior and the full config for ``create_chat_model``).
|
||||
model_name: Optional model name to use. If None, uses config or default.
|
||||
"""
|
||||
self._app_config = app_config
|
||||
self._model_name = model_name
|
||||
|
||||
@property
|
||||
def _memory_config(self) -> MemoryConfig:
|
||||
return self._app_config.memory
|
||||
|
||||
def _get_model(self):
|
||||
"""Get the model for memory updates."""
|
||||
config = get_memory_config()
|
||||
model_name = self._model_name or config.model_name
|
||||
return create_chat_model(name=model_name, thinking_enabled=False)
|
||||
model_name = self._model_name or self._memory_config.model_name
|
||||
return create_chat_model(name=model_name, thinking_enabled=False, app_config=self._app_config)
|
||||
|
||||
def _build_correction_hint(
|
||||
self,
|
||||
@@ -344,13 +346,14 @@ class MemoryUpdater:
|
||||
agent_name: str | None,
|
||||
correction_detected: bool,
|
||||
reinforcement_detected: bool,
|
||||
user_id: str | None = None,
|
||||
) -> tuple[dict[str, Any], str] | None:
|
||||
"""Load memory and build the update prompt for a conversation."""
|
||||
config = get_memory_config()
|
||||
config = self._memory_config
|
||||
if not config.enabled or not messages:
|
||||
return None
|
||||
|
||||
current_memory = get_memory_data(agent_name)
|
||||
current_memory = get_memory_data(config, agent_name, user_id=user_id)
|
||||
conversation_text = format_conversation_for_update(messages)
|
||||
if not conversation_text.strip():
|
||||
return None
|
||||
@@ -372,6 +375,7 @@ class MemoryUpdater:
|
||||
response_content: Any,
|
||||
thread_id: str | None,
|
||||
agent_name: str | None,
|
||||
user_id: str | None = None,
|
||||
) -> bool:
|
||||
"""Parse the model response, apply updates, and persist memory."""
|
||||
response_text = _extract_text(response_content).strip()
|
||||
@@ -385,7 +389,7 @@ class MemoryUpdater:
|
||||
# cannot corrupt the still-cached original object reference.
|
||||
updated_memory = self._apply_updates(copy.deepcopy(current_memory), update_data, thread_id)
|
||||
updated_memory = _strip_upload_mentions_from_memory(updated_memory)
|
||||
return get_memory_storage().save(updated_memory, agent_name)
|
||||
return get_memory_storage(self._memory_config).save(updated_memory, agent_name, user_id=user_id)
|
||||
|
||||
async def aupdate_memory(
|
||||
self,
|
||||
@@ -394,6 +398,7 @@ class MemoryUpdater:
|
||||
agent_name: str | None = None,
|
||||
correction_detected: bool = False,
|
||||
reinforcement_detected: bool = False,
|
||||
user_id: str | None = None,
|
||||
) -> bool:
|
||||
"""Update memory asynchronously based on conversation messages."""
|
||||
try:
|
||||
@@ -403,6 +408,7 @@ class MemoryUpdater:
|
||||
agent_name=agent_name,
|
||||
correction_detected=correction_detected,
|
||||
reinforcement_detected=reinforcement_detected,
|
||||
user_id=user_id,
|
||||
)
|
||||
if prepared is None:
|
||||
return False
|
||||
@@ -416,6 +422,7 @@ class MemoryUpdater:
|
||||
response_content=response.content,
|
||||
thread_id=thread_id,
|
||||
agent_name=agent_name,
|
||||
user_id=user_id,
|
||||
)
|
||||
except json.JSONDecodeError as e:
|
||||
logger.warning("Failed to parse LLM response for memory update: %s", e)
|
||||
@@ -431,6 +438,7 @@ class MemoryUpdater:
|
||||
agent_name: str | None = None,
|
||||
correction_detected: bool = False,
|
||||
reinforcement_detected: bool = False,
|
||||
user_id: str | None = None,
|
||||
) -> bool:
|
||||
"""Synchronously update memory via the async updater path.
|
||||
|
||||
@@ -440,19 +448,83 @@ class MemoryUpdater:
|
||||
agent_name: If provided, updates per-agent memory. If None, updates global memory.
|
||||
correction_detected: Whether recent turns include an explicit correction signal.
|
||||
reinforcement_detected: Whether recent turns include a positive reinforcement signal.
|
||||
user_id: If provided, scopes memory to a specific user.
|
||||
|
||||
Returns:
|
||||
True if update was successful, False otherwise.
|
||||
"""
|
||||
return _run_async_update_sync(
|
||||
self.aupdate_memory(
|
||||
messages=messages,
|
||||
thread_id=thread_id,
|
||||
agent_name=agent_name,
|
||||
correction_detected=correction_detected,
|
||||
reinforcement_detected=reinforcement_detected,
|
||||
config = self._memory_config
|
||||
if not config.enabled:
|
||||
return False
|
||||
|
||||
if not messages:
|
||||
return False
|
||||
|
||||
try:
|
||||
# Get current memory
|
||||
current_memory = get_memory_data(config, agent_name, user_id=user_id)
|
||||
|
||||
# Format conversation for prompt
|
||||
conversation_text = format_conversation_for_update(messages)
|
||||
|
||||
if not conversation_text.strip():
|
||||
return False
|
||||
|
||||
# Build prompt
|
||||
correction_hint = ""
|
||||
if correction_detected:
|
||||
correction_hint = (
|
||||
"IMPORTANT: Explicit correction signals were detected in this conversation. "
|
||||
"Pay special attention to what the agent got wrong, what the user corrected, "
|
||||
"and record the correct approach as a fact with category "
|
||||
'"correction" and confidence >= 0.95 when appropriate.'
|
||||
)
|
||||
if reinforcement_detected:
|
||||
reinforcement_hint = (
|
||||
"IMPORTANT: Positive reinforcement signals were detected in this conversation. "
|
||||
"The user explicitly confirmed the agent's approach was correct or helpful. "
|
||||
"Record the confirmed approach, style, or preference as a fact with category "
|
||||
'"preference" or "behavior" and confidence >= 0.9 when appropriate.'
|
||||
)
|
||||
correction_hint = (correction_hint + "\n" + reinforcement_hint).strip() if correction_hint else reinforcement_hint
|
||||
|
||||
prompt = MEMORY_UPDATE_PROMPT.format(
|
||||
current_memory=json.dumps(current_memory, indent=2),
|
||||
conversation=conversation_text,
|
||||
correction_hint=correction_hint,
|
||||
)
|
||||
)
|
||||
|
||||
# Call LLM
|
||||
model = self._get_model()
|
||||
response = model.invoke(prompt)
|
||||
response_text = _extract_text(response.content).strip()
|
||||
|
||||
# Parse response
|
||||
# Remove markdown code blocks if present
|
||||
if response_text.startswith("```"):
|
||||
lines = response_text.split("\n")
|
||||
response_text = "\n".join(lines[1:-1] if lines[-1] == "```" else lines[1:])
|
||||
|
||||
update_data = json.loads(response_text)
|
||||
|
||||
# Apply updates
|
||||
updated_memory = self._apply_updates(current_memory, update_data, thread_id)
|
||||
|
||||
# Strip file-upload mentions from all summaries before saving.
|
||||
# Uploaded files are session-scoped and won't exist in future sessions,
|
||||
# so recording upload events in long-term memory causes the agent to
|
||||
# try (and fail) to locate those files in subsequent conversations.
|
||||
updated_memory = _strip_upload_mentions_from_memory(updated_memory)
|
||||
|
||||
# Save
|
||||
return get_memory_storage(config).save(updated_memory, agent_name, user_id=user_id)
|
||||
|
||||
except json.JSONDecodeError as e:
|
||||
logger.warning("Failed to parse LLM response for memory update: %s", e)
|
||||
return False
|
||||
except Exception as e:
|
||||
logger.exception("Memory update failed: %s", e)
|
||||
return False
|
||||
|
||||
def _apply_updates(
|
||||
self,
|
||||
@@ -470,7 +542,7 @@ class MemoryUpdater:
|
||||
Returns:
|
||||
Updated memory data.
|
||||
"""
|
||||
config = get_memory_config()
|
||||
config = self._memory_config
|
||||
now = utc_now_iso_z()
|
||||
|
||||
# Update user sections
|
||||
@@ -547,6 +619,7 @@ def update_memory_from_conversation(
|
||||
agent_name: str | None = None,
|
||||
correction_detected: bool = False,
|
||||
reinforcement_detected: bool = False,
|
||||
user_id: str | None = None,
|
||||
) -> bool:
|
||||
"""Convenience function to update memory from a conversation.
|
||||
|
||||
@@ -556,9 +629,10 @@ def update_memory_from_conversation(
|
||||
agent_name: If provided, updates per-agent memory. If None, updates global memory.
|
||||
correction_detected: Whether recent turns include an explicit correction signal.
|
||||
reinforcement_detected: Whether recent turns include a positive reinforcement signal.
|
||||
user_id: If provided, scopes memory to a specific user.
|
||||
|
||||
Returns:
|
||||
True if successful, False otherwise.
|
||||
"""
|
||||
updater = MemoryUpdater()
|
||||
return updater.update_memory(messages, thread_id, agent_name, correction_detected, reinforcement_detected)
|
||||
return updater.update_memory(messages, thread_id, agent_name, correction_detected, reinforcement_detected, user_id=user_id)
|
||||
|
||||
Reference in New Issue
Block a user