fix(checkpoint): revive lc=2 JSON blobs for safe types without allowlist (#7582)

## Summary

Fixes #7498 — `MESSAGE_COERCION_FAILURE` when resuming threads
checkpointed before v1.0.1.

**Root cause:** PR #6269 (v1.0.1) added an `_allowed_json_modules`
security gate to `JsonPlusSerializer._reviver`. The gate defaults to
`None`, so old `"json"`-format checkpoint blobs containing `lc=2`
constructor dicts (the pre-msgpack serialization format for pydantic
objects like `HumanMessage`) are now returned as raw dicts instead of
being reconstructed. Those raw dicts reach `add_messages →
convert_to_messages`, which sees `type="constructor"` and raises
`MESSAGE_COERCION_FAILURE`. Fresh first-turn messages are unaffected
because current `dumps_typed` only writes `"msgpack"` blobs.

**Fix:** `_reviver` now reconstructs `lc=2` blobs whose target class is
already in `SAFE_MSGPACK_TYPES` — the same curated allowlist already
used by the msgpack deserialization path (includes all standard
LangChain message types). Unknown classes are still blocked, preserving
the security intent of #6269.

## Changes

- `libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py` — add
`_is_safe_json_type()` helper; update `_reviver` and
`_check_allowed_json_modules` to allow safe types without an explicit
allowlist
- `libs/checkpoint/tests/test_jsonplus.py` — two new regression tests:
safe-type `lc=2` blobs revive correctly; unknown-type `lc=2` blobs stay
blocked

## Test plan

- [ ] `test_lc2_json_safe_type_revives_without_allowlist` —
`HumanMessage`/`AIMessage` lc=2 JSON blobs round-trip to proper
`BaseMessage` objects with no allowlist configured
- [ ] `test_lc2_json_unknown_type_stays_blocked_without_allowlist` —
`pprint.pprint` lc=2 blob still returns raw dict (not reconstructed)
- [ ] `test_deserde_invalid_module` — existing behaviour unchanged
- [ ] Full `test_jsonplus.py` suite: 93/93 passing

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Sydney Runkle
2026-04-27 09:08:47 -04:00
committed by GitHub
co-authored by Claude Sonnet 4.6
parent 53a9806e65
commit 85cd64ed69
2 changed files with 84 additions and 9 deletions
+51
View File
@@ -333,6 +333,57 @@ def test_serde_jsonplus_bytes() -> None:
assert serde.loads_typed(dumped) == some_bytes
def test_lc2_json_safe_type_revives_without_allowlist() -> None:
"""Old 'json' blobs with lc=2 for safe types must revive without an explicit allowlist.
Regression test for: https://github.com/langchain-ai/langgraph/issues/7498
Threads checkpointed before v1.0.1 (pre-msgpack) stored messages as lc=2 JSON
constructor dicts. Resuming those threads must reconstruct proper BaseMessage objects
rather than returning raw dicts that cause MESSAGE_COERCION_FAILURE in add_messages.
"""
from langchain_core.messages import AIMessage
serde = JsonPlusSerializer() # default: _allowed_json_modules=None
human_blob = {
"lc": 2,
"type": "constructor",
"id": ["langchain_core", "messages", "human", "HumanMessage"],
"kwargs": {"content": "hello", "type": "human"},
}
ai_blob = {
"lc": 2,
"type": "constructor",
"id": ["langchain_core", "messages", "ai", "AIMessage"],
"kwargs": {"content": "hi there", "type": "ai"},
}
result = serde.loads_typed(("json", json.dumps([human_blob, ai_blob]).encode()))
assert len(result) == 2
assert isinstance(result[0], HumanMessage), (
f"Expected HumanMessage, got {type(result[0])}: {result[0]!r}\n"
"lc=2 JSON blobs for safe types must deserialize without an explicit allowlist"
)
assert result[0].content == "hello"
assert isinstance(result[1], AIMessage)
assert result[1].content == "hi there"
def test_lc2_json_unknown_type_stays_blocked_without_allowlist() -> None:
"""lc=2 JSON blobs for types NOT in SAFE_MSGPACK_TYPES still require an allowlist."""
serde = JsonPlusSerializer()
load = {
"lc": 2,
"type": "constructor",
"id": ["pprint", "pprint"],
"kwargs": {"object": "HELLO"},
}
# No allowlist configured → raw dict returned (not raised, not reconstructed)
result = serde.loads_typed(("json", json.dumps(load).encode()))
assert isinstance(result, dict), "Unknown lc=2 type must stay as raw dict"
assert result.get("lc") == 2
def test_deserde_invalid_module() -> None:
serde = JsonPlusSerializer()
load = {