run-llama / llama-agents / 28474893940

84%

Build Type

push

github

Committed by web-flow

Commit Message

Don't crash ctx.store edits on non-deepcopyable state values (#714)

Every `ctx.store` write copies the whole live state before the edit, so
a concurrent reader keeps seeing the committed state until the
`edit_state` block finishes. The copy is a deep copy, and that is the
problem. State often holds live objects that cannot be deep-copied. A
`Memory` wraps sqlalchemy, aiosqlite, and tiktoken modules. An LLM
client wraps a `threading.Lock`. Deep-copying either one throws:

- `wf.run(memory=Memory.from_defaults(...))` raises `TypeError: cannot
pickle 'module' object` (#709)
- `await ctx.store.set("client", some_client)` raises `TypeError: cannot
pickle '_thread.lock' object` (#710)

The deep copy only exists to isolate data a reader could otherwise catch
mid-edit. A live handle like memory or an LLM client is shared by
reference across the whole run anyway, so copying it gains no isolation.
It just crashes. So copy each entry on its own, and when one will not
deep-copy, keep the reference instead.

Plain data like dicts, lists, and scalars still deep-copies, so edit
isolation is unchanged for anything a reader could actually observe
torn. Typed state that is not a `DictState` still copies whole-model,
falling back to a shallow copy if some field refuses to deep-copy
instead of raising.

Fixes #709, fixes #710.

Coverage Stats

13 of 15 new or added lines in 1 file covered. (86.67%)

1 existing line in 1 file now uncovered.

17711 of 21024 relevant lines covered (84.24%)

1.13 hits per line