fix: remove asyncio.run() from __del__ to prevent production crashes

[bleedblack1]

Fixes #154

Problem

The AgentGraph.__del__ method crashes in production:

def __del__(self) -> None:
    if self.pool:
        asyncio.run(self.close_pool())  #  RuntimeError!

Why it crashes: asyncio.run() cannot be called when an event loop is already running, which is always the case in Chainlit/uvicorn/FastAPI.

Secondary issue: LANGGRAPH_DB_URI is constructed at module import with potentially None values, creating malformed URIs.

Solution

Change	Purpose
Remove del	Eliminates the crash
Add aenter/aexit	Proper async context manager pattern
Add close() method	Explicit, idempotent cleanup
Add _build_langgraph_db_uri()	Lazy URI construction with validation
Add is_initialized/is_closed	State inspection properties
Add create_agent_graph()	Convenience factory function

Related Issues

• Fixes the asyncio.run() crash bug
• Addresses malformed URI construction
• Improves resource management patterns

[adamjohnwright]

Thank you — you both independently found this, which is what made it credible.

Fixed on main in #173, though not with either approach as proposed:

• fix: make AgentGraph destructor loop-safe to prevent connection leaks #147's loop.create_task() is not guaranteed to run when the loop is shutting down, which is exactly when a graph is usually collected — so it would report success while leaking the pool.
• fix: remove asyncio.run() from __del__ to prevent production crashes #156 rewrites more of the module than the bug warrants.

The change closes the pool only when no loop is running, and otherwise warns that it is still open rather than pretending otherwise. Writing the test surfaced that even the warning fails at interpreter shutdown once logging's handlers close — so this is containment, and the real fix is an explicit shutdown hook.

Closing as resolved. Your reports are credited in the commit.