mirror of
https://github.com/TauricResearch/TradingAgents.git
synced 2026-09-26 22:42:40 +03:00
Yijia-Xiao
c42a2f2c61
- interface -> router; symbol_utils -> symbols, which also takes safe_ticker_component - utils is split: get_current_date to date_window, the HTTP helpers to net - dataflows imports are absolute; the NoMarketDataError re-export from symbols is gone
100 lines
3.3 KiB
Python
100 lines
3.3 KiB
Python
"""LangGraph checkpoint support for resumable analysis runs.
|
|
|
|
Per-ticker SQLite databases so concurrent tickers don't contend.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import hashlib
|
|
import sqlite3
|
|
from collections.abc import Generator
|
|
from contextlib import contextmanager
|
|
from pathlib import Path
|
|
|
|
from langgraph.checkpoint.sqlite import SqliteSaver
|
|
|
|
from tradingagents.dataflows.symbols import safe_ticker_component
|
|
|
|
|
|
def _db_path(data_dir: str | Path, ticker: str) -> Path:
|
|
"""Return the SQLite checkpoint DB path for a ticker."""
|
|
# Reject ticker values that would escape the checkpoints directory.
|
|
safe = safe_ticker_component(ticker).upper()
|
|
p = Path(data_dir) / "checkpoints"
|
|
p.mkdir(parents=True, exist_ok=True)
|
|
return p / f"{safe}.db"
|
|
|
|
|
|
def thread_id(ticker: str, date: str, signature: str = "") -> str:
|
|
"""Deterministic thread ID for a ticker+date pair.
|
|
|
|
``signature`` folds in graph-shape-affecting run choices so a resume under a
|
|
different graph can't reuse this checkpoint (#1089); omitting it keeps the
|
|
legacy ID.
|
|
"""
|
|
base = f"{ticker.upper()}:{date}"
|
|
if signature:
|
|
base = f"{base}:{signature}"
|
|
return hashlib.sha256(base.encode()).hexdigest()[:16]
|
|
|
|
|
|
@contextmanager
|
|
def get_checkpointer(data_dir: str | Path, ticker: str) -> Generator[SqliteSaver, None, None]:
|
|
"""Context manager yielding a SqliteSaver backed by a per-ticker DB."""
|
|
db = _db_path(data_dir, ticker)
|
|
conn = sqlite3.connect(str(db), check_same_thread=False)
|
|
try:
|
|
saver = SqliteSaver(conn)
|
|
saver.setup()
|
|
yield saver
|
|
finally:
|
|
conn.close()
|
|
|
|
|
|
def checkpoint_step(data_dir: str | Path, ticker: str, date: str, signature: str = "") -> int | None:
|
|
"""Return the step number of the latest checkpoint, or None if none exists."""
|
|
db = _db_path(data_dir, ticker)
|
|
if not db.exists():
|
|
return None
|
|
tid = thread_id(ticker, date, signature)
|
|
with get_checkpointer(data_dir, ticker) as saver:
|
|
config = {"configurable": {"thread_id": tid}}
|
|
cp = saver.get_tuple(config)
|
|
if cp is None:
|
|
return None
|
|
return cp.metadata.get("step")
|
|
|
|
|
|
def clear_all_checkpoints(data_dir: str | Path) -> int:
|
|
"""Remove all checkpoint databases. Returns the number of databases deleted.
|
|
|
|
SQLite keeps committed state in ``-wal`` and ``-shm`` files beside the
|
|
database, so deleting only the ``.db`` leaves a cleared checkpoint with data
|
|
still on disk.
|
|
"""
|
|
cp_dir = Path(data_dir) / "checkpoints"
|
|
if not cp_dir.exists():
|
|
return 0
|
|
dbs = list(cp_dir.glob("*.db"))
|
|
for db in dbs:
|
|
for path in (db, *cp_dir.glob(f"{db.name}-*")):
|
|
path.unlink(missing_ok=True)
|
|
return len(dbs)
|
|
|
|
|
|
def clear_checkpoint(data_dir: str | Path, ticker: str, date: str, signature: str = "") -> None:
|
|
"""Remove checkpoint for a specific ticker+date by deleting the thread's rows."""
|
|
db = _db_path(data_dir, ticker)
|
|
if not db.exists():
|
|
return
|
|
tid = thread_id(ticker, date, signature)
|
|
conn = sqlite3.connect(str(db))
|
|
try:
|
|
for table in ("writes", "checkpoints"):
|
|
conn.execute(f"DELETE FROM {table} WHERE thread_id = ?", (tid,))
|
|
conn.commit()
|
|
except sqlite3.OperationalError:
|
|
pass
|
|
finally:
|
|
conn.close()
|