mirror of
https://github.com/langchain-ai/langgraph.git
synced 2026-08-17 21:25:46 +02:00
Elior Nataf LackritzandGitHub
36a505ac65
Depends on #8535 `libs/checkpoint-conformance/tests/` only validates `InMemorySaver`. `checkpoint-sqlite` has had a `test_conformance_delta.py` for a while, but it guards on `importorskip("langgraph.checkpoint.conformance")` and the package was never in its test environment — so it has been skipping silently every run. `checkpoint-postgres` had no runner at all. Net effect: the shared checkpointer contract was effectively unenforced everywhere except in-memory. ### Change Adds `langgraph-checkpoint-conformance` to the `test` dependency group of both packages, with a path source like the existing `langgraph-checkpoint` entry. That alone is what makes sqlite's runner start executing. Postgres gets the equivalent runner. Both pass the `delta_channel_history` capability. ### Why it's stacked Against `main`'s Postgres, the new runner fails: ``` Capability delta_channel_history failed: test_history_migration_plain_value_as_seed ``` That is exactly the bug #8535 fixes, and it had been failing unnoticed precisely because nothing ran the suite there. So this is based on that branch rather than `main` — the diff here is the one conformance commit, and it will retarget once #8535 lands. Reasonable to read that as the change justifying itself: the first thing turning the suite on did was catch a real bug that had been sitting in `main`. ### Verified `checkpoint-postgres` 270 passed on PG 15 and 16, `checkpoint-sqlite` 118 passed, lint and `ty` clean in both. The `uv.lock` updates are the conformance package entry only. ### Note The sync `PostgresSaver` and `SqliteSaver` aren't covered — the conformance harness reports every capability as `detected=False` for them, so only the async savers are exercised. Pre-existing and not addressed here, but worth knowing the coverage isn't total.