mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-11 11:13:51 +00:00
* feat(gateway): implement LangGraph Platform API in Gateway, replace langgraph-cli
Implement all core LangGraph Platform API endpoints in the Gateway,
allowing it to fully replace the langgraph-cli dev server for local
development. This eliminates a heavyweight dependency and simplifies
the development stack.
Changes:
- Add runs lifecycle endpoints (create, stream, wait, cancel, join)
- Add threads CRUD and search endpoints
- Add assistants compatibility endpoints (search, get, graph, schemas)
- Add StreamBridge (in-memory pub/sub for SSE) and async provider
- Add RunManager with atomic create_or_reject (eliminates TOCTOU race)
- Add worker with interrupt/rollback cancel actions and runtime context injection
- Route /api/langgraph/* to Gateway in nginx config
- Skip langgraph-cli startup by default (SKIP_LANGGRAPH_SERVER=0 to restore)
- Add unit tests for RunManager, SSE format, and StreamBridge
* fix: drain bridge queue on client disconnect to prevent backpressure
When on_disconnect=continue, keep consuming events from the bridge
without yielding, so the worker is not blocked by a full queue.
Only on_disconnect=cancel breaks out immediately.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix: remove pytest import
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix: Fix default stream_mode to ["values", "messages-tuple"]
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix: Remove unused if_exists field from ThreadCreateRequest
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix: address review comments on gateway LangGraph API
- Mount runs.py router in app.py (missing include_router)
- Normalize interrupt_before/after "*" to node list before run_agent()
- Use entry.id for SSE event ID instead of counter
- Drain bridge queue on disconnect when on_disconnect=continue
- Reuse serialization helper in wait_run() for consistent wire format
- Reject unsupported multitask_strategy with 400
- Remove SKIP_LANGGRAPH_SERVER fallback, always use Gateway
* feat: extract app.state access into deps.py
Encapsulate read/write operations for singleton objects (RunManager,
StreamBridge, checkpointer) held in app.state into a shared utility,
reducing repeated access patterns across router modules.
* feat: extract deerflow.runtime.serialization module with tests
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: replace duplicated serialization with deerflow.runtime.serialization
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: extract app/gateway/services.py with run lifecycle logic
Create a service layer that centralizes SSE formatting, input/config
normalization, and run lifecycle management. Router modules will delegate
to these functions instead of using private cross-imported helpers.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: wire routers to use services layer, remove cross-module private imports
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* style: apply ruff formatting to refactored files
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(runtime): support LangGraph dev server and add compat route
- Enable official LangGraph dev server for local development workflow
- Decouple runtime components from agents package for better separation
- Provide gateway-backed fallback route when dev server is skipped
- Simplify lifecycle management using context manager in gateway
* feat(runtime): add Store providers with auto-backend selection
- Add async_provider.py and provider.py under deerflow/runtime/store/
- Support memory, sqlite, postgres backends matching checkpointer config
- Integrate into FastAPI lifespan via AsyncExitStack in deps.py
- Replace hardcoded InMemoryStore with config-driven factory
* refactor(gateway): migrate thread management from checkpointer to Store and resolve multiple endpoint failures
- Add Store-backed CRUD helpers (_store_get, _store_put, _store_upsert)
- Replace checkpoint-scanning search with two-phase strategy:
phase 1 reads Store (O(threads)), phase 2 backfills from checkpointer
for legacy/LangGraph Server threads with lazy migration
- Extend Store record schema with values field for title persistence
- Sync thread title from checkpoint to Store after run completion
- Fix /threads/{id}/runs/{run_id}/stream 405 by accepting both
GET and POST methods; POST handles interrupt/rollback actions
- Fix /threads/{id}/state 500 by separating read_config and
write_config, adding checkpoint_ns to configurable, and
shallow-copying checkpoint/metadata before mutation
- Sync title to Store on state update for immediate search reflection
- Move _upsert_thread_in_store into services.py, remove duplicate logic
- Add _sync_thread_title_after_run: await run task, read final
checkpoint title, write back to Store record
- Spawn title sync as background task from start_run when Store exists
* refactor(runtime): deduplicate store and checkpointer provider logic
Extract _ensure_sqlite_parent_dir() helper into checkpointer/provider.py
and use it in all three places that previously inlined the same mkdir logic.
Consolidate duplicate error constants in store/async_provider.py by importing
from store/provider.py instead of redefining them.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(runtime): move SQLite helpers to runtime/store, checkpointer imports from store
_resolve_sqlite_conn_str and _ensure_sqlite_parent_dir now live in
runtime/store/provider.py. agents/checkpointer/provider and
agents/checkpointer/async_provider import from there, reversing the
previous dependency direction (store → checkpointer becomes
checkpointer → store).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(runtime): extract SQLite helpers into runtime/store/_sqlite_utils.py
Move resolve_sqlite_conn_str and ensure_sqlite_parent_dir out of
checkpointer/provider.py into a dedicated _sqlite_utils module.
Functions are now public (no underscore prefix), making cross-module
imports semantically correct. All four provider files import from
the single shared location.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(gateway): use adelete_thread to fully remove thread checkpoints on delete
AsyncSqliteSaver has no adelete method — the previous hasattr check
always evaluated to False, silently leaving all checkpoint rows in the
database. Switch to adelete_thread(thread_id) which deletes every
checkpoint and pending-write row for the thread across all namespaces
(including sub-graph checkpoints).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(gateway): remove dead bridge_cm/ckpt_cm code and fix StrEnum lint
app.py had unreachable code after the async-with lifespan refactor:
bridge_cm and ckpt_cm were referenced but never defined (F821), and
the channel service startup/shutdown was outside the langgraph_runtime
block so it never ran. Move channel service lifecycle inside the
async-with block where it belongs.
Replace str+Enum inheritance in RunStatus and DisconnectMode with
StrEnum as suggested by UP042.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* style: format with ruff
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: JeffJiang <for-eleven@hotmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
91 lines
3.1 KiB
Python
91 lines
3.1 KiB
Python
"""In-memory stream bridge backed by :class:`asyncio.Queue`."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import logging
|
|
import time
|
|
from collections.abc import AsyncIterator
|
|
from typing import Any
|
|
|
|
from .base import END_SENTINEL, HEARTBEAT_SENTINEL, StreamBridge, StreamEvent
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
_PUBLISH_TIMEOUT = 30.0 # seconds to wait when queue is full
|
|
|
|
|
|
class MemoryStreamBridge(StreamBridge):
|
|
"""Per-run ``asyncio.Queue`` implementation.
|
|
|
|
Each *run_id* gets its own queue on first :meth:`publish` call.
|
|
"""
|
|
|
|
def __init__(self, *, queue_maxsize: int = 256) -> None:
|
|
self._maxsize = queue_maxsize
|
|
self._queues: dict[str, asyncio.Queue[StreamEvent]] = {}
|
|
self._counters: dict[str, int] = {}
|
|
|
|
# -- helpers ---------------------------------------------------------------
|
|
|
|
def _get_or_create_queue(self, run_id: str) -> asyncio.Queue[StreamEvent]:
|
|
if run_id not in self._queues:
|
|
self._queues[run_id] = asyncio.Queue(maxsize=self._maxsize)
|
|
self._counters[run_id] = 0
|
|
return self._queues[run_id]
|
|
|
|
def _next_id(self, run_id: str) -> str:
|
|
self._counters[run_id] = self._counters.get(run_id, 0) + 1
|
|
ts = int(time.time() * 1000)
|
|
seq = self._counters[run_id] - 1
|
|
return f"{ts}-{seq}"
|
|
|
|
# -- StreamBridge API ------------------------------------------------------
|
|
|
|
async def publish(self, run_id: str, event: str, data: Any) -> None:
|
|
queue = self._get_or_create_queue(run_id)
|
|
entry = StreamEvent(id=self._next_id(run_id), event=event, data=data)
|
|
try:
|
|
await asyncio.wait_for(queue.put(entry), timeout=_PUBLISH_TIMEOUT)
|
|
except TimeoutError:
|
|
logger.warning("Stream bridge queue full for run %s — dropping event %s", run_id, event)
|
|
|
|
async def publish_end(self, run_id: str) -> None:
|
|
queue = self._get_or_create_queue(run_id)
|
|
try:
|
|
await asyncio.wait_for(queue.put(END_SENTINEL), timeout=_PUBLISH_TIMEOUT)
|
|
except TimeoutError:
|
|
logger.warning("Stream bridge queue full for run %s — dropping END sentinel", run_id)
|
|
|
|
async def subscribe(
|
|
self,
|
|
run_id: str,
|
|
*,
|
|
last_event_id: str | None = None,
|
|
heartbeat_interval: float = 15.0,
|
|
) -> AsyncIterator[StreamEvent]:
|
|
if last_event_id is not None:
|
|
logger.debug("last_event_id=%s accepted but ignored (memory bridge has no replay)", last_event_id)
|
|
|
|
queue = self._get_or_create_queue(run_id)
|
|
while True:
|
|
try:
|
|
entry = await asyncio.wait_for(queue.get(), timeout=heartbeat_interval)
|
|
except TimeoutError:
|
|
yield HEARTBEAT_SENTINEL
|
|
continue
|
|
if entry is END_SENTINEL:
|
|
yield END_SENTINEL
|
|
return
|
|
yield entry
|
|
|
|
async def cleanup(self, run_id: str, *, delay: float = 0) -> None:
|
|
if delay > 0:
|
|
await asyncio.sleep(delay)
|
|
self._queues.pop(run_id, None)
|
|
self._counters.pop(run_id, None)
|
|
|
|
async def close(self) -> None:
|
|
self._queues.clear()
|
|
self._counters.clear()
|