update

Use typ() instead of [] throughout DeltaChannel so reducers over dict
(and other non-list types) work correctly. fromCheckpoint(MISSING) now
leaves value as typ() from __init__ instead of overwriting with MISSING.
copy() uses value.copy() to handle dicts. update() initialises base from
typ() when value is MISSING. Add four tests covering the deepagents-style
dict-merge / file-deletion reducer pattern.

.github/workflows/_integration_test.yml

@@ -121,8 +121,8 @@ jobs:
             exit 1
           fi
           LANGCHAIN_OPENAI_VERSION=$(docker run --rm --entrypoint "" langgraph-test-h python -c "import sys; from importlib.metadata import version; v = version('langchain-openai'); print(v);")
-          if [ "$LANGCHAIN_OPENAI_VERSION" != "1.1.14" ]; then
-            echo "LANGCHAIN_OPENAI_VERSION != 1.1.14; $LANGCHAIN_OPENAI_VERSION"
+          if [ "$LANGCHAIN_OPENAI_VERSION" != "1.0.1" ]; then
+            echo "LANGCHAIN_OPENAI_VERSION != 1.0.1; $LANGCHAIN_OPENAI_VERSION"
             exit 1
           fi
           LANGCHAIN_ANTHROPIC_VERSION=$(docker run --rm --entrypoint "" langgraph-test-h python -c "import sys; from importlib.metadata import version; v = version('langchain-anthropic'); print(v);")

.gitignore

@@ -100,3 +100,4 @@ dmypy.json
 .turbo
 .editorconfig
 .scratch
+.worktrees/

docs/superpowers/specs/2026-04-17-diff-channel-design.md

@@ -0,0 +1,405 @@
+# DiffChannel: Incremental Checkpoint Storage for Append-Style Reducers
+
+**Date:** 2026-04-17  
+**Status:** Approved for implementation  
+**Scope:** `libs/checkpoint`, `libs/langgraph`, `libs/checkpoint-postgres`
+
+---
+
+## Motivation
+
+LangGraph checkpoints today store the **full accumulated value** of every channel on every step. For a `messages` channel backed by `add_messages`, this means each checkpoint blob contains the entire conversation history. Storage cost grows O(N²) in the number of turns: step 1 stores 1 message, step 100 stores 100 messages, step 1000 stores 1000 messages. For long-running agentic conversations with high-token messages this is untenable.
+
+The fix is to store only the **delta** (new writes) per step, reconstructing the full accumulated value at load time by replaying the chain. This is an opt-in mechanism — existing graphs are unaffected.
+
+---
+
+## Non-Goals
+
+- **Compaction / materialized snapshots**: deferred. Load cost stays O(N) blob fetches but those fetches are batched into a single query — acceptable for now.
+- **SQLite saver support**: SQLite stores all channel values inline in one row (no per-channel blob table). Deferred to a follow-up.
+- **Automatic migration** of existing `BinaryOperatorAggregate` channels: users opt in explicitly. Old checkpoints load correctly via the backwards-compatibility path in `from_checkpoint`.
+
+---
+
+## Architecture Overview
+
+```
+User state definition
+  └── Annotated[list[AnyMessage], DiffChannel(add_messages)]
+
+Write path (per superstep)
+  DiffChannel.update()       — apply operator, accumulate writes in _pending
+  DiffChannel.checkpoint()   — return DiffDelta(delta=_pending, prev_version=_base_version)
+  serde.dumps_typed()        — serialize DiffDelta as ("diff", msgpack_bytes)
+  saver.put()                — store blob at (thread_id, ns, "messages", version_N)
+  DiffChannel.after_checkpoint(version_N) — advance _base_version, clear _pending
+
+Read path (on graph load or time-travel)
+  saver.get_tuple()          — fetch current-version blob per channel
+  saver._load_blobs()        — detect "diff" type → follow chain to reconstruct DiffChainValue
+  DiffChannel.from_checkpoint(DiffChainValue) — replay deltas with operator → full list
+  DiffChannel.after_checkpoint(version_N)     — set _base_version for next write
+```
+
+The pregel layer (`_checkpoint.py`, `_loop.py`) is unchanged except for two small additions to call the new `after_checkpoint` hook. The saver public interface (`BaseCheckpointSaver`) gains no new methods. All chain-following logic lives inside each saver's private `_load_blobs`.
+
+---
+
+## New Protocol Types
+
+**Location:** `libs/checkpoint/langgraph/checkpoint/base/__init__.py`
+
+Two dataclasses form the contract between `DiffChannel` and savers:
+
+```python
+@dataclass
+class DiffDelta:
+    """Returned by DiffChannel.checkpoint(). Written to the blob store."""
+    delta: list[Any]           # raw writes passed to update() this step
+    prev_version: str | None   # version of the previous diff blob; None = chain root
+```
+
+```python
+@dataclass
+class DiffChainValue:
+    """Passed to DiffChannel.from_checkpoint(). Assembled by _load_blobs()."""
+    base: list[Any] | None     # starting accumulated value (None = empty start)
+    deltas: list[list[Any]]    # write-sets ordered oldest → newest
+```
+
+`DiffDelta` lives in the checkpoint base package (not the channel module) so savers can import it without creating a circular dependency. `DiffChainValue` is there for the same reason.
+
+---
+
+## `BaseChannel.after_checkpoint()` Hook
+
+**Location:** `libs/langgraph/langgraph/channels/base.py`
+
+```python
+def after_checkpoint(self, version: Any) -> None:
+    """Called after checkpoint() (with the new version) and after from_checkpoint()
+    (with the current version). No-op by default; DiffChannel overrides."""
+    pass
+```
+
+This is a **non-abstract, no-op default** — fully backwards compatible. All existing channels inherit it silently. It is NOT in the abstract interface.
+
+---
+
+## `DiffChannel[V]`
+
+**Location:** `libs/langgraph/langgraph/channels/diff.py` (new file)
+
+### Internal state
+
+| Attribute | Type | Description |
+|---|---|---|
+| `value` | `list[V]` | Full accumulated value (the reconstructed list) |
+| `operator` | `Callable` | The binary reducer (e.g. `add_messages`) |
+| `_pending` | `list[Any]` | Raw writes accumulated since last `after_checkpoint` call |
+| `_base_version` | `str \| None` | Version this channel was last checkpointed at (= `prev_version` for next delta) |
+| `_overwritten` | `bool` | True if an `Overwrite` was applied since last `after_checkpoint`; makes next blob a chain root |
+
+### `update(values)`
+
+Mirrors `BinaryOperatorAggregate.update()` with two additions:
+
+1. For each non-Overwrite value: apply `self.operator(self.value, value)` as before; **also append the raw incoming value to `self._pending`**.
+2. For an `Overwrite(v)` value: set `self.value = v`; set `self._pending = list(v)` (full value becomes the new delta); set `self._overwritten = True`.
+
+The key: `_pending` stores the **incoming writes** (what was passed to `update()`), not the diff of `self.value`. This is important because `add_messages` handles removal and update-by-ID — replaying the writes with `operator` during reconstruction applies that logic correctly.
+
+### `checkpoint()`
+
+```python
+def checkpoint(self) -> DiffDelta:
+    return DiffDelta(
+        delta=self._pending[:],
+        prev_version=None if self._overwritten else self._base_version,
+    )
+```
+
+- Normal step: `prev_version = self._base_version` → chain link
+- After Overwrite: `prev_version = None` → chain root (reconstruction stops here and uses `delta` as the full base value)
+
+Returns `DiffDelta`, never the raw accumulated list. The serde handles serialization.
+
+### `from_checkpoint(checkpoint)`
+
+```python
+def from_checkpoint(self, checkpoint) -> Self:
+    new = DiffChannel(self.typ, self.operator)
+    new.key = self.key
+    if checkpoint is MISSING:
+        new.value = []
+    elif isinstance(checkpoint, DiffChainValue):
+        accumulated = checkpoint.base or []
+        for step_writes in checkpoint.deltas:
+            # Mirror update() exactly: apply each write individually so operator
+            # semantics (e.g. add_messages ID-based removal) are respected.
+            for write in step_writes:
+                accumulated = new.operator(accumulated, write)
+        new.value = accumulated
+    elif isinstance(checkpoint, DiffDelta):
+        # Unsupported saver: _load_blobs returned a raw DiffDelta instead of
+        # assembling a DiffChainValue. Raise rather than silently losing history.
+        raise ValueError(
+            "DiffChannel received a raw DiffDelta from the checkpoint saver. "
+            "Your saver does not support incremental channel storage. "
+            "Use InMemorySaver or PostgresSaver."
+        )
+    else:
+        # Backwards compat: plain list from old BinaryOperatorAggregate checkpoint.
+        new.value = checkpoint
+    new._pending = []
+    new._base_version = None  # set by the subsequent after_checkpoint() call
+    return new
+```
+
+The operator is available on `self` (the channel spec) so reconstruction is correct for any reducer — the saver never needs to know about `add_messages`.
+
+`_pending` stores **individual writes** (each `value` from `update()`'s `values` sequence), so each `step_writes` list in `DiffChainValue.deltas` is replayed write-by-write — identical to the `update()` loop.
+
+### `after_checkpoint(version)`
+
+```python
+def after_checkpoint(self, version: Any) -> None:
+    if version != self._base_version:
+        self._base_version = version
+        self._pending = []
+        self._overwritten = False
+```
+
+No-op when `version == self._base_version` (channel wasn't updated this step — blob was not written). Clears `_pending` and advances `_base_version` when the channel was actually checkpointed.
+
+### Opt-in API
+
+```python
+from langgraph.channels.diff import DiffChannel
+
+class State(TypedDict):
+    messages: Annotated[list[AnyMessage], DiffChannel(add_messages)]
+```
+
+`StateGraph` already handles `BaseChannel` instances as annotation metadata — `DiffChannel` inherits this without any changes to `StateGraph`.
+
+---
+
+## Serde Extension
+
+**Location:** `libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py`
+
+Add one branch to `dumps_typed` (before the `else` msgpack fallback), using the existing module-level `_msgpack_enc` so message ext-types (Pydantic v2, etc.) are handled correctly:
+
+```python
+elif isinstance(obj, DiffDelta):
+    return "diff", _msgpack_enc({"d": obj.delta, "p": obj.prev_version})
+```
+
+Add one branch to `loads_typed` so savers can decode diff blobs without importing `ormsgpack` directly:
+
+```python
+elif type_ == "diff":
+    return ormsgpack.unpackb(
+        data_, ext_hook=self._unpack_ext_hook, option=ormsgpack.OPT_NON_STR_KEYS
+    )
+    # returns {"d": [writes...], "p": prev_version_str_or_none}
+```
+
+Savers call `serde.loads_typed(("diff", raw_bytes))` to decode a diff blob into `{"d": ..., "p": ...}`, then check `type_tag == "diff"` to trigger chain traversal. The serde layer is the only place that knows about `ormsgpack`.
+
+---
+
+## Saver Changes
+
+### InMemorySaver
+
+**`put()` — `libs/checkpoint/langgraph/checkpoint/memory/__init__.py`**
+
+No change needed. The existing `self.serde.dumps_typed(values[k])` call already handles `DiffDelta` via the new serde branch above, storing it as `("diff", bytes)`.
+
+**`_load_blobs()` — same file**
+
+After checking `vv[0] != "empty"`, add a branch for `"diff"` before calling `serde.loads_typed`:
+
+```python
+def _load_blobs(self, thread_id, checkpoint_ns, versions):
+    channel_values = {}
+    diff_channels = {}  # channel_name -> current_version for diff channels
+
+    for k, v in versions.items():
+        kk = (thread_id, checkpoint_ns, k, v)
+        if kk not in self.blobs:
+            continue
+        type_tag, blob_bytes = self.blobs[kk]
+        if type_tag == "diff":
+            diff_channels[k] = v  # handle below
+        elif type_tag != "empty":
+            channel_values[k] = self.serde.loads_typed((type_tag, blob_bytes))
+
+    for k, current_version in diff_channels.items():
+        # Follow chain: newest → oldest, then reverse
+        chain_deltas = []
+        base = None
+        version = current_version
+        while version is not None:
+            kk = (thread_id, checkpoint_ns, k, version)
+            if kk not in self.blobs:
+                break
+            type_tag, blob_bytes = self.blobs[kk]
+            if type_tag == "diff":
+                # Use serde so we don't need to import ormsgpack directly
+                payload = self.serde.loads_typed((type_tag, blob_bytes))
+                chain_deltas.append(payload["d"])
+                version = payload["p"]  # prev_version; None = root
+            else:
+                # Old non-diff blob encountered: treat as base accumulated value
+                base = self.serde.loads_typed((type_tag, blob_bytes))
+                break
+        chain_deltas.reverse()
+        channel_values[k] = DiffChainValue(base=base, deltas=chain_deltas)
+
+    return channel_values
+```
+
+Each blob lookup is O(1) on the dict. Total: N dict lookups for a chain of depth N. Memory usage is identical to loading a single full-list blob (same total bytes, split across N entries).
+
+### PostgresSaver
+
+**`_load_blobs()` — `libs/checkpoint-postgres/langgraph/checkpoint/postgres/base.py`**
+
+The existing `SELECT_SQL` fetches one blob per channel via a JOIN. After running that query, detect any `"diff"` channels in the result and issue one additional range query:
+
+```python
+def _load_blobs(self, blob_values):
+    if not blob_values:
+        return {}
+
+    result = {}
+    diff_channels = {}  # channel_name -> current_version (as str)
+
+    for k, t, v in blob_values:
+        channel = k.decode()
+        type_tag = t.decode()
+        if type_tag == "diff":
+            # Decode via serde — no direct ormsgpack import needed
+            payload = self.serde.loads_typed((type_tag, v))
+            diff_channels[channel] = payload  # store for chain fetch
+        elif type_tag != "empty":
+            result[channel] = self.serde.loads_typed((type_tag, v))
+
+    if diff_channels:
+        result.update(self._load_diff_chains(diff_channels))
+
+    return result
+```
+
+`_load_diff_chains` issues one SQL query per diff channel (typically just `messages`):
+
+```sql
+SELECT version, type, blob
+FROM checkpoint_blobs
+WHERE thread_id = %s
+  AND checkpoint_ns = %s
+  AND channel = %s
+  AND version <= %s
+ORDER BY version ASC
+```
+
+In Python, iterate rows in ascending version order: if `type = "diff"`, accumulate the delta; if any other type is encountered, treat it as the base accumulated value and stop. Return `DiffChainValue(base=..., deltas=[...])`.
+
+This results in **at most 2 queries total** for a graph with one `DiffChannel` — existing behaviour for all other channels is unchanged.
+
+**`put()` / `_dump_blobs()`**
+
+No change needed. `_dump_blobs` calls `self.serde.dumps_typed(v)` for each channel value in `new_versions`. When `v` is a `DiffDelta`, the serde produces `("diff", bytes)` which is stored as `type = "diff"` in `checkpoint_blobs`. The `ON CONFLICT DO NOTHING` semantics are preserved.
+
+### SQLite
+
+Deferred. `SqliteSaver` stores the entire checkpoint as a single serialized row — it has no per-channel blob table. Supporting `DiffChannel` on SQLite would require adding a new blobs table, which is a separate migration tracked separately.
+
+---
+
+## Pregel Layer Changes
+
+### `channels_from_checkpoint` — `libs/langgraph/langgraph/pregel/_checkpoint.py`
+
+After constructing each channel from its checkpoint value, call `after_checkpoint` so the channel records its current version:
+
+```python
+channels = {}
+for k, v in channel_specs.items():
+    ch = v.from_checkpoint(checkpoint["channel_values"].get(k, MISSING))
+    ch.after_checkpoint(checkpoint["channel_versions"].get(k))
+    channels[k] = ch
+return channels, managed_specs
+```
+
+Existing channels get the no-op `after_checkpoint`. `DiffChannel` uses it to set `_base_version`.
+
+### `PregelLoop._put_checkpoint` — `libs/langgraph/langgraph/pregel/_loop.py`
+
+After `create_checkpoint(self.checkpoint, self.channels, self.step, ...)` returns and `do_checkpoint is True` and `self.channels is not None`, iterate channels and notify:
+
+```python
+if do_checkpoint and self.channels:
+    for k, ch in self.channels.items():
+        ch.after_checkpoint(self.checkpoint["channel_versions"].get(k))
+```
+
+This is called after `create_checkpoint` updates `self.checkpoint["channel_versions"]`, so `get(k)` returns the new version for updated channels and the old version for unchanged ones. `DiffChannel.after_checkpoint` only clears `_pending` when `version != _base_version`, so unchanged channels are no-ops.
+
+---
+
+## Backwards Compatibility
+
+| Scenario | Behaviour |
+|---|---|
+| Existing graph using `add_messages` (BinaryOperatorAggregate) | Unaffected — no code changes, no data migration |
+| New graph with `DiffChannel`, loading old checkpoint blobs | `from_checkpoint` receives a plain `list` → used directly as accumulated value |
+| `DiffChannel` with `InMemorySaver` or `PostgresSaver` | Fully supported |
+| `DiffChannel` with `SqliteSaver` | `from_checkpoint` receives a raw `DiffDelta` (SqliteSaver stores channel_values inline), raises `ValueError` with a clear message pointing to supported savers |
+| Time-travel / fork to past checkpoint | Chain traversal uses the version at that checkpoint → reconstruction is correct |
+| `update_state` | Treated as a normal step: writes are deltas chained to history |
+| `Overwrite` value | Resets chain: next blob has `prev_version=None`; reconstruction starts fresh |
+
+---
+
+## Testing Strategy
+
+1. **Unit tests for `DiffChannel`** (`libs/langgraph/tests/`):
+   - `update` → `checkpoint` → `after_checkpoint` → `checkpoint` lifecycle (2 steps, verify delta isolation)
+   - `from_checkpoint(DiffChainValue)` correctly replays multi-step chains using the operator
+   - `from_checkpoint(plain_list)` backwards-compat path
+   - `Overwrite` creates a root blob (`prev_version=None`) and reconstruction ignores prior chain
+   - `after_checkpoint` no-ops when version is unchanged
+
+2. **Integration tests with `InMemorySaver`** (`libs/langgraph/tests/`):
+   - 10-step conversation: verify final loaded state equals full accumulated messages
+   - Time-travel: fork to step 5, verify only messages 1–5 are present
+   - Mixed graph: some channels `BinaryOperatorAggregate`, one `DiffChannel` — both reconstruct correctly
+
+3. **Serde tests** (`libs/checkpoint/tests/`):
+   - `DiffDelta` round-trips through `dumps_typed` / saver storage
+   - Old `"msgpack"` blob for a channel → `DiffChannel.from_checkpoint` handles it
+
+4. **Postgres integration tests** (`libs/checkpoint-postgres/tests/`):
+   - Range query reconstructs correct full list after N steps
+   - Time-travel to checkpoint M reconstructs correct list of M messages
+
+---
+
+## Files Changed
+
+| File | Change |
+|---|---|
+| `libs/checkpoint/langgraph/checkpoint/base/__init__.py` | Add `DiffDelta`, `DiffChainValue` dataclasses |
+| `libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py` | Add `"diff"` branch in `dumps_typed` |
+| `libs/checkpoint/langgraph/checkpoint/memory/__init__.py` | Chain traversal in `_load_blobs` |
+| `libs/langgraph/langgraph/channels/base.py` | Add no-op `after_checkpoint` method |
+| `libs/langgraph/langgraph/channels/diff.py` | **New file** — `DiffChannel` implementation |
+| `libs/langgraph/langgraph/channels/__init__.py` | Export `DiffChannel` |
+| `libs/langgraph/langgraph/pregel/_checkpoint.py` | Call `after_checkpoint` in `channels_from_checkpoint` |
+| `libs/langgraph/langgraph/pregel/_loop.py` | Call `after_checkpoint` after `create_checkpoint` |
+| `libs/checkpoint-postgres/langgraph/checkpoint/postgres/base.py` | Range-query chain reconstruction in `_load_blobs` |

libs/checkpoint-postgres/langgraph/checkpoint/postgres/__init__.py

@@ -430,6 +430,43 @@ class PostgresSaver(BasePostgresSaver):
                 with conn.cursor(binary=True, row_factory=dict_row) as cur:
                     yield cur
 
+    def get_channel_blob(
+        self,
+        thread_id: str,
+        checkpoint_ns: str,
+        checkpoint_id: str,
+        channel: str,
+    ) -> Any:
+        """Look up a channel blob by checkpoint ID + channel via checkpoint_blobs."""
+        with self._cursor() as cur:
+            cur.execute(
+                """
+                SELECT cb.type, cb.blob
+                FROM checkpoint_blobs cb
+                WHERE cb.thread_id = %s
+                  AND cb.checkpoint_ns = %s
+                  AND cb.channel = %s
+                  AND cb.version = (
+                      SELECT checkpoint->'channel_versions'->>%s
+                      FROM checkpoints
+                      WHERE thread_id = %s AND checkpoint_ns = %s AND checkpoint_id = %s
+                  )
+                """,
+                (
+                    thread_id,
+                    checkpoint_ns,
+                    channel,
+                    channel,
+                    thread_id,
+                    checkpoint_ns,
+                    checkpoint_id,
+                ),
+            )
+            row = cur.fetchone()
+        if row is None:
+            return NotImplemented
+        return self.serde.loads_typed((row["type"], row["blob"]))
+
     def _load_checkpoint_tuple(self, value: DictRow) -> CheckpointTuple:
         """
         Convert a database row into a CheckpointTuple object.
@@ -442,6 +479,13 @@ class PostgresSaver(BasePostgresSaver):
             including its configuration, metadata, parent checkpoint (if any),
             and pending writes.
         """
+        with self._cursor() as cur:
+            channel_values = self._load_blobs(
+                value["channel_values"],
+                thread_id=value["thread_id"],
+                checkpoint_ns=value["checkpoint_ns"],
+                cur=cur,
+            )
         return CheckpointTuple(
             {
                 "configurable": {
@@ -454,7 +498,7 @@ class PostgresSaver(BasePostgresSaver):
                 **value["checkpoint"],
                 "channel_values": {
                     **(value["checkpoint"].get("channel_values") or {}),
-                    **self._load_blobs(value["channel_values"]),
+                    **channel_values,
                 },
             },
             value["metadata"],

libs/checkpoint-postgres/langgraph/checkpoint/postgres/aio.py

@@ -391,6 +391,43 @@ class AsyncPostgresSaver(BasePostgresSaver):
                 async with conn.cursor(binary=True, row_factory=dict_row) as cur:
                     yield cur
 
+    async def aget_channel_blob(
+        self,
+        thread_id: str,
+        checkpoint_ns: str,
+        checkpoint_id: str,
+        channel: str,
+    ) -> Any:
+        """Async look up of a channel blob by checkpoint ID + channel name."""
+        async with self._cursor() as cur:
+            await cur.execute(
+                """
+                SELECT cb.type, cb.blob
+                FROM checkpoint_blobs cb
+                WHERE cb.thread_id = %s
+                  AND cb.checkpoint_ns = %s
+                  AND cb.channel = %s
+                  AND cb.version = (
+                      SELECT checkpoint->'channel_versions'->>%s
+                      FROM checkpoints
+                      WHERE thread_id = %s AND checkpoint_ns = %s AND checkpoint_id = %s
+                  )
+                """,
+                (
+                    thread_id,
+                    checkpoint_ns,
+                    channel,
+                    channel,
+                    thread_id,
+                    checkpoint_ns,
+                    checkpoint_id,
+                ),
+            )
+            row = await cur.fetchone()
+        if row is None:
+            return NotImplemented
+        return self.serde.loads_typed((row["type"], row["blob"]))
+
     async def _load_checkpoint_tuple(self, value: DictRow) -> CheckpointTuple:
         """
         Convert a database row into a CheckpointTuple object.
@@ -403,11 +440,19 @@ class AsyncPostgresSaver(BasePostgresSaver):
             including its configuration, metadata, parent checkpoint (if any),
             and pending writes.
         """
+        thread_id = value["thread_id"]
+        checkpoint_ns = value["checkpoint_ns"]
+        blob_values = value["channel_values"]
+
+        channel_values: dict[str, Any] = {}
+        if blob_values:
+            channel_values = self._load_blobs(blob_values)
+
         return CheckpointTuple(
             {
                 "configurable": {
-                    "thread_id": value["thread_id"],
-                    "checkpoint_ns": value["checkpoint_ns"],
+                    "thread_id": thread_id,
+                    "checkpoint_ns": checkpoint_ns,
                     "checkpoint_id": value["checkpoint_id"],
                 }
             },
@@ -415,15 +460,15 @@ class AsyncPostgresSaver(BasePostgresSaver):
                 **value["checkpoint"],
                 "channel_values": {
                     **(value["checkpoint"].get("channel_values") or {}),
-                    **self._load_blobs(value["channel_values"]),
+                    **channel_values,
                 },
             },
             value["metadata"],
             (
                 {
                     "configurable": {
-                        "thread_id": value["thread_id"],
-                        "checkpoint_ns": value["checkpoint_ns"],
+                        "thread_id": thread_id,
+                        "checkpoint_ns": checkpoint_ns,
                         "checkpoint_id": value["parent_checkpoint_id"],
                     }
                 }

libs/checkpoint-postgres/langgraph/checkpoint/postgres/base.py

@@ -185,15 +185,22 @@ class BasePostgresSaver(BaseCheckpointSaver[str]):
         )
 
     def _load_blobs(
-        self, blob_values: list[tuple[bytes, bytes, bytes]]
+        self,
+        blob_values: list[tuple[bytes, bytes, bytes]],
+        *,
+        thread_id: str = "",
+        checkpoint_ns: str = "",
+        cur: Any = None,
     ) -> dict[str, Any]:
         if not blob_values:
             return {}
-        return {
-            k.decode(): self.serde.loads_typed((t.decode(), v))
-            for k, t, v in blob_values
-            if t.decode() != "empty"
-        }
+        result: dict[str, Any] = {}
+        for k, t, v in blob_values:
+            channel = k.decode()
+            type_tag = t.decode()
+            if type_tag != "empty":
+                result[channel] = self.serde.loads_typed((type_tag, v))
+        return result
 
     def _dump_blobs(
         self,

libs/checkpoint-postgres/tests/test_async.py

@@ -371,3 +371,47 @@ async def test_get_checkpoint_no_channel_values(
 
         checkpoint = await saver.aget_tuple(config)
         assert checkpoint.checkpoint["channel_values"] == {}
+
+
+@pytest.mark.parametrize("saver_name", ["base", "pool", "pipe"])
+async def test_delta_channel_chain_reconstruction(saver_name: str) -> None:
+    """AsyncPostgresSaver reconstructs DeltaChannel chain via point-lookup traversal."""
+    pytest.importorskip(
+        "langgraph.channels.delta", reason="langgraph core not installed"
+    )
+
+    from typing import Annotated
+
+    from langchain_core.messages import AIMessage, HumanMessage
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph import START, StateGraph
+    from langgraph.graph.message import add_messages
+    from typing_extensions import TypedDict
+
+    class State(TypedDict):
+        messages: Annotated[list, DeltaChannel(add_messages)]
+
+    def respond(state: State) -> dict:
+        n = len(state["messages"])
+        return {"messages": [AIMessage(content=f"reply-{n}", id=f"ai-{n}")]}
+
+    builder = StateGraph(State)
+    builder.add_node("respond", respond)
+    builder.add_edge(START, "respond")
+
+    async with _saver(saver_name) as saver:
+        graph = builder.compile(checkpointer=saver)
+        config = {"configurable": {"thread_id": "diff-channel-test-1"}}
+
+        await graph.ainvoke({"messages": [HumanMessage(content="hi", id="h1")]}, config)
+        await graph.ainvoke(
+            {"messages": [HumanMessage(content="there", id="h2")]}, config
+        )
+
+        state = await graph.aget_state(config)
+        msgs = state.values["messages"]
+        assert len(msgs) == 4, f"expected 4, got {len(msgs)}: {msgs}"
+        assert msgs[0].content == "hi"
+        assert msgs[1].content == "reply-1"
+        assert msgs[2].content == "there"
+        assert msgs[3].content == "reply-3"

libs/checkpoint-postgres/uv.lock

@@ -259,7 +259,7 @@ wheels = [
 
 [[package]]
 name = "langgraph-checkpoint"
-version = "4.0.3"
+version = "4.0.2"
 source = { editable = "../checkpoint" }
 dependencies = [
     { name = "langchain-core" },

libs/checkpoint-sqlite/uv.lock

@@ -268,7 +268,7 @@ wheels = [
 
 [[package]]
 name = "langgraph-checkpoint"
-version = "4.0.3"
+version = "4.0.2"
 source = { editable = "../checkpoint" }
 dependencies = [
     { name = "langchain-core" },

libs/checkpoint/langgraph/checkpoint/base/__init__.py

@@ -1,6 +1,8 @@
 from __future__ import annotations
 
+import asyncio
 import copy
+import dataclasses
 import logging
 from collections.abc import AsyncIterator, Collection, Iterator, Mapping, Sequence
 from typing import (  # noqa: UP035
@@ -28,7 +30,46 @@ from langgraph.checkpoint.serde.types import (
 
 V = TypeVar("V", int, float, str)
 PendingWrite = tuple[str, str, Any]
+
+
+@dataclasses.dataclass
+class DeltaValue:
+    """Returned by DeltaChannel.checkpoint(). Represents one step's writes."""
+
+    delta: list[Any]
+    prev_checkpoint_id: (
+        str | None
+    )  # ID of checkpoint containing previous blob; None = chain root
+
+
+@dataclasses.dataclass
+class DeltaChainValue:
+    """Passed to DeltaChannel.from_checkpoint(). Assembled during checkpoint hydration."""
+
+    base: list[Any] | None  # starting accumulated value; None = start from empty
+    deltas: list[list[Any]]  # per-step write-sets, ordered oldest → newest
+
+
+CheckpointHydrationKind = Literal["delta"]
+
+
+@dataclasses.dataclass(frozen=True)
+class IncrementalChannelSpec:
+    """Describes a checkpoint field that needs saver-side materialization."""
+
+    name: str
+    kind: CheckpointHydrationKind
+
+
+@dataclasses.dataclass(frozen=True)
+class CheckpointHydrationPlan:
+    """Lists the checkpoint fields eligible for saver-side materialization."""
+
+    channels: tuple[IncrementalChannelSpec, ...]
+
+
 logger = logging.getLogger(__name__)
+_MISSING_SENTINEL = object()
 
 
 # Marked as total=False to allow for future expansion.
@@ -457,6 +498,172 @@ class BaseCheckpointSaver(Generic[V]):
         """
         raise NotImplementedError
 
+    def materialize_checkpoint(
+        self,
+        config: RunnableConfig,
+        checkpoint: Checkpoint,
+        plan: CheckpointHydrationPlan | None = None,
+    ) -> Checkpoint:
+        """Materialize any saver-managed incremental values in a checkpoint."""
+        if plan is None or not plan.channels:
+            return checkpoint
+
+        thread_id = str(config["configurable"]["thread_id"])
+        checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
+        current_checkpoint_id = checkpoint.get("id")
+        assembled: dict[str, Any] = {}
+
+        for spec in plan.channels:
+            value = checkpoint["channel_values"].get(spec.name)
+            if spec.kind != "delta" or not isinstance(value, DeltaValue):
+                continue
+
+            assembled_value = self._materialize_delta_channel(
+                thread_id=thread_id,
+                checkpoint_ns=checkpoint_ns,
+                current_checkpoint_id=current_checkpoint_id,
+                channel=spec.name,
+                value=value,
+            )
+            if assembled_value is not None:
+                assembled[spec.name] = assembled_value
+
+        if not assembled:
+            return checkpoint
+
+        return {
+            **checkpoint,
+            "channel_values": {**checkpoint["channel_values"], **assembled},
+        }
+
+    def materialize_checkpoint_tuple(
+        self,
+        value: CheckpointTuple,
+        plan: CheckpointHydrationPlan | None = None,
+    ) -> CheckpointTuple:
+        """Materialize incremental values for a single checkpoint tuple."""
+        checkpoint = self.materialize_checkpoint(value.config, value.checkpoint, plan)
+        if checkpoint is value.checkpoint:
+            return value
+        return value._replace(checkpoint=checkpoint)
+
+    def materialize_checkpoint_tuples(
+        self,
+        values: Sequence[CheckpointTuple],
+        plan: CheckpointHydrationPlan | None = None,
+    ) -> Sequence[CheckpointTuple]:
+        """Materialize incremental values for a batch of checkpoint tuples."""
+        return [self.materialize_checkpoint_tuple(value, plan) for value in values]
+
+    async def amaterialize_checkpoint(
+        self,
+        config: RunnableConfig,
+        checkpoint: Checkpoint,
+        plan: CheckpointHydrationPlan | None = None,
+    ) -> Checkpoint:
+        """Async materialization hook for saver-managed incremental values."""
+        if plan is None or not plan.channels:
+            return checkpoint
+
+        thread_id = str(config["configurable"]["thread_id"])
+        checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
+        current_checkpoint_id = checkpoint.get("id")
+
+        targets = [
+            (spec, checkpoint["channel_values"][spec.name])
+            for spec in plan.channels
+            if spec.kind == "delta"
+            and isinstance(checkpoint["channel_values"].get(spec.name), DeltaValue)
+        ]
+        if not targets:
+            return checkpoint
+
+        # Walks for independent channels can run concurrently — each has its own chain.
+        results = await asyncio.gather(
+            *(
+                self._amaterialize_delta_channel(
+                    thread_id=thread_id,
+                    checkpoint_ns=checkpoint_ns,
+                    current_checkpoint_id=current_checkpoint_id,
+                    channel=spec.name,
+                    value=value,
+                )
+                for spec, value in targets
+            )
+        )
+        assembled = {
+            spec.name: result
+            for (spec, _), result in zip(targets, results, strict=True)
+            if result is not None
+        }
+
+        if not assembled:
+            return checkpoint
+
+        return {
+            **checkpoint,
+            "channel_values": {**checkpoint["channel_values"], **assembled},
+        }
+
+    async def amaterialize_checkpoint_tuple(
+        self,
+        value: CheckpointTuple,
+        plan: CheckpointHydrationPlan | None = None,
+    ) -> CheckpointTuple:
+        """Async materialization hook for a single checkpoint tuple."""
+        checkpoint = await self.amaterialize_checkpoint(
+            value.config, value.checkpoint, plan
+        )
+        if checkpoint is value.checkpoint:
+            return value
+        return value._replace(checkpoint=checkpoint)
+
+    async def amaterialize_checkpoint_tuples(
+        self,
+        values: Sequence[CheckpointTuple],
+        plan: CheckpointHydrationPlan | None = None,
+    ) -> Sequence[CheckpointTuple]:
+        """Async materialization hook for a batch of checkpoint tuples."""
+        return [
+            await self.amaterialize_checkpoint_tuple(value, plan) for value in values
+        ]
+
+    def get_channel_blob(
+        self,
+        thread_id: str,
+        checkpoint_ns: str,
+        checkpoint_id: str,
+        channel: str,
+    ) -> Any:
+        """Look up a single channel blob by checkpoint ID + channel name.
+
+        Returns NotImplemented if this saver does not support efficient
+        per-channel-version blob lookup. The pregel layer will fall back to
+        get_tuple() traversal in that case.
+
+        Savers with a dedicated blob store (InMemorySaver, PostgresSaver)
+        should override this for O(1) performance.
+        """
+        return NotImplemented
+
+    async def aget_channel_blob(
+        self,
+        thread_id: str,
+        checkpoint_ns: str,
+        checkpoint_id: str,
+        channel: str,
+    ) -> Any:
+        """Look up a single channel blob by checkpoint ID + channel name (async).
+
+        Returns NotImplemented if this saver does not support efficient
+        per-channel-version blob lookup. The pregel layer will fall back to
+        aget_tuple() traversal in that case.
+
+        Savers with a dedicated blob store (InMemorySaver, PostgresSaver)
+        should override this for O(1) performance.
+        """
+        return NotImplemented
+
     def get_next_version(self, current: V | None, channel: None) -> V:
         """Generate the next version ID for a channel.
 
@@ -489,6 +696,138 @@ class BaseCheckpointSaver(Generic[V]):
         clone.serde = maybe_add_typed_methods(serde)
         return clone
 
+    def _materialize_delta_channel(
+        self,
+        *,
+        thread_id: str,
+        checkpoint_ns: str,
+        current_checkpoint_id: str | None,
+        channel: str,
+        value: DeltaValue,
+    ) -> DeltaChainValue | None:
+        chain_deltas: list[list[Any]] = []
+        base: list[Any] | None = None
+        cursor: DeltaValue = value
+        visited: set[str] = {current_checkpoint_id} if current_checkpoint_id else set()
+
+        while True:
+            chain_deltas.append(cursor.delta)
+            prev_id = cursor.prev_checkpoint_id
+            if prev_id is None:
+                break
+            if prev_id in visited:
+                logger.warning(
+                    "DeltaChannel chain cycle at checkpoint %r for channel %r; breaking",
+                    prev_id,
+                    channel,
+                )
+                break
+            visited.add(prev_id)
+
+            blob = self.get_channel_blob(thread_id, checkpoint_ns, prev_id, channel)
+            if blob is not NotImplemented:
+                if isinstance(blob, DeltaValue):
+                    cursor = blob
+                    continue
+                base = blob
+                break
+
+            parent_config: RunnableConfig = {
+                "configurable": {
+                    "thread_id": thread_id,
+                    "checkpoint_ns": checkpoint_ns,
+                    "checkpoint_id": prev_id,
+                }
+            }
+            parent_tuple = self.get_tuple(parent_config)
+            if parent_tuple is None:
+                logger.warning(
+                    "DeltaChannel chain broken: checkpoint %r not found for channel %r",
+                    prev_id,
+                    channel,
+                )
+                break
+            prev_val = parent_tuple.checkpoint["channel_values"].get(
+                channel, _MISSING_SENTINEL
+            )
+            if prev_val is _MISSING_SENTINEL:
+                break
+            if isinstance(prev_val, DeltaValue):
+                cursor = prev_val
+            else:
+                base = prev_val
+                break
+
+        chain_deltas.reverse()
+        return DeltaChainValue(base=base, deltas=chain_deltas)
+
+    async def _amaterialize_delta_channel(
+        self,
+        *,
+        thread_id: str,
+        checkpoint_ns: str,
+        current_checkpoint_id: str | None,
+        channel: str,
+        value: DeltaValue,
+    ) -> DeltaChainValue | None:
+        chain_deltas: list[list[Any]] = []
+        base: list[Any] | None = None
+        cursor: DeltaValue = value
+        visited: set[str] = {current_checkpoint_id} if current_checkpoint_id else set()
+
+        while True:
+            chain_deltas.append(cursor.delta)
+            prev_id = cursor.prev_checkpoint_id
+            if prev_id is None:
+                break
+            if prev_id in visited:
+                logger.warning(
+                    "DeltaChannel chain cycle at checkpoint %r for channel %r; breaking",
+                    prev_id,
+                    channel,
+                )
+                break
+            visited.add(prev_id)
+
+            blob = await self.aget_channel_blob(
+                thread_id, checkpoint_ns, prev_id, channel
+            )
+            if blob is not NotImplemented:
+                if isinstance(blob, DeltaValue):
+                    cursor = blob
+                    continue
+                base = blob
+                break
+
+            parent_config: RunnableConfig = {
+                "configurable": {
+                    "thread_id": thread_id,
+                    "checkpoint_ns": checkpoint_ns,
+                    "checkpoint_id": prev_id,
+                }
+            }
+            parent_tuple = await self.aget_tuple(parent_config)
+            if parent_tuple is None:
+                logger.warning(
+                    "DeltaChannel chain broken: checkpoint %r not found for channel %r",
+                    prev_id,
+                    channel,
+                )
+                break
+            prev_val = parent_tuple.checkpoint["channel_values"].get(
+                channel, _MISSING_SENTINEL
+            )
+            if prev_val is _MISSING_SENTINEL:
+                break
+            if isinstance(prev_val, DeltaValue):
+                cursor = prev_val
+            else:
+                base = prev_val
+                break
+
+        chain_deltas.reverse()
+        return DeltaChainValue(base=base, deltas=chain_deltas)
+
 
 def _with_msgpack_allowlist(
     serde: SerializerProtocol, extra_allowlist: Collection[tuple[str, ...]]

libs/checkpoint/langgraph/checkpoint/memory/__init__.py

@@ -126,12 +126,46 @@ class InMemorySaver(
         channel_values: dict[str, Any] = {}
         for k, v in versions.items():
             kk = (thread_id, checkpoint_ns, k, v)
-            if kk in self.blobs:
-                vv = self.blobs[kk]
-                if vv[0] != "empty":
-                    channel_values[k] = self.serde.loads_typed(vv)
+            if kk not in self.blobs:
+                continue
+            vv = self.blobs[kk]
+            if vv[0] != "empty":
+                channel_values[k] = self.serde.loads_typed(vv)
         return channel_values
 
+    def get_channel_blob(
+        self,
+        thread_id: str,
+        checkpoint_ns: str,
+        checkpoint_id: str,
+        channel: str,
+    ) -> Any:
+        """Fast-path blob lookup: checkpoint → channel version → blob."""
+        ns_storage = self.storage.get(thread_id, {}).get(checkpoint_ns, {})
+        entry = ns_storage.get(checkpoint_id)
+        if entry is None:
+            return NotImplemented
+        checkpoint = self.serde.loads_typed(entry[0])
+        version = checkpoint["channel_versions"].get(channel)
+        if version is None:
+            return NotImplemented
+        kk = (thread_id, checkpoint_ns, channel, version)
+        if kk not in self.blobs:
+            return NotImplemented
+        vv = self.blobs[kk]
+        if vv[0] == "empty":
+            return NotImplemented
+        return self.serde.loads_typed(vv)
+
+    async def aget_channel_blob(
+        self,
+        thread_id: str,
+        checkpoint_ns: str,
+        checkpoint_id: str,
+        channel: str,
+    ) -> Any:
+        return self.get_channel_blob(thread_id, checkpoint_ns, checkpoint_id, channel)
+
     def get_tuple(self, config: RunnableConfig) -> CheckpointTuple | None:
         """Get a checkpoint tuple from the in-memory storage.
 

libs/checkpoint/langgraph/checkpoint/serde/_msgpack.py

@@ -80,6 +80,8 @@ SAFE_MSGPACK_TYPES: frozenset[tuple[str, ...]] = frozenset(
         ("langgraph.types", "Overwrite"),
         ("langgraph.store.base", "Item"),
         ("langgraph.store.base", "GetOp"),
+        # DeltaChannel checkpoint value type
+        ("langgraph.checkpoint.base", "DeltaValue"),
     }
 )
 

libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py

@@ -46,35 +46,11 @@ LC_REVIVER = Reviver()
 EMPTY_BYTES = b""
 logger = logging.getLogger(__name__)
 
-# Dedup log warnings across process lifetime; cap bounds state if types are
-# dynamically generated (also acts as a circuit breaker on warning volume).
-# Dedup is best-effort: racing threads may each emit once for the same key,
-# and warnings are silently dropped once _MAX_WARNED_TYPES is reached.
-_MAX_WARNED_TYPES = 1000
-_warned_unregistered_types: set[tuple[str, str]] = set()
-_warned_blocked_types: set[tuple[str, str]] = set()
 
+def _is_delta_value(obj: Any) -> bool:
+    from langgraph.checkpoint.base import DeltaValue  # lazy import avoids circular dep
 
-def _is_safe_json_type(id_list: list[str]) -> bool:
-    """Return True if an lc=2 id refers to a type in SAFE_MSGPACK_TYPES.
-
-    Safe types bypass the ``allowed_json_modules`` gate so that old "json" format
-    checkpoints (written before the msgpack migration) can be resumed without
-    requiring users to configure an explicit allowlist.
-    """
-    if len(id_list) < 2:
-        return False
-    module_name = ".".join(id_list[:-1])
-    return (module_name, id_list[-1]) in _lg_msgpack.SAFE_MSGPACK_TYPES
-
-
-def _warn_once(
-    seen: set[tuple[str, str]], key: tuple[str, str], msg: str, *args: object
-) -> None:
-    if key in seen or len(seen) >= _MAX_WARNED_TYPES:
-        return
-    seen.add(key)
-    logger.warning(msg, *args)
+    return isinstance(obj, DeltaValue)
 
 
 class JsonPlusSerializer(SerializerProtocol):
@@ -177,23 +153,19 @@ class JsonPlusSerializer(SerializerProtocol):
         return out
 
     def _reviver(self, value: dict[str, Any]) -> Any:
-        if (
+        if self._allowed_json_modules and (
             value.get("lc", None) == 2
             and value.get("type", None) == "constructor"
             and value.get("id", None) is not None
         ):
-            id_list = value["id"]
-            is_safe = _is_safe_json_type(id_list)
-            if self._allowed_json_modules or is_safe:
-                try:
-                    return self._revive_lc2(value)
-                except InvalidModuleError as e:
-                    if not is_safe:
-                        logger.warning(
-                            "Object %s is not in the deserialization allowlist.\n%s",
-                            value["id"],
-                            e.message,
-                        )
+            try:
+                return self._revive_lc2(value)
+            except InvalidModuleError as e:
+                logger.warning(
+                    "Object %s is not in the deserialization allowlist.\n%s",
+                    value["id"],
+                    e.message,
+                )
 
         return LC_REVIVER(value)
 
@@ -241,13 +213,6 @@ class JsonPlusSerializer(SerializerProtocol):
             method_display = "<init>"
 
         dotted = ".".join(needed)
-        # Safe types (the same set already allowed for msgpack deserialization) are
-        # permitted without an explicit allowlist — they are known-safe LangGraph and
-        # LangChain types.  This restores backwards-compat for old "json" checkpoints
-        # that pre-date the msgpack migration without reopening the broader security gate.
-        if _is_safe_json_type(list(needed)):
-            return
-
         if not self._allowed_json_modules:
             raise InvalidModuleError(
                 f"Refused to deserialize JSON constructor: {dotted} (method: {method_display}). "
@@ -280,6 +245,8 @@ class JsonPlusSerializer(SerializerProtocol):
             return "bytes", obj
         elif isinstance(obj, bytearray):
             return "bytearray", obj
+        elif _is_delta_value(obj):
+            return "delta", _msgpack_enc({"d": obj.delta, "c": obj.prev_checkpoint_id})
         else:
             try:
                 return "msgpack", _msgpack_enc(obj)
@@ -302,6 +269,13 @@ class JsonPlusSerializer(SerializerProtocol):
             return ormsgpack.unpackb(
                 data_, ext_hook=self._unpack_ext_hook, option=ormsgpack.OPT_NON_STR_KEYS
             )
+        elif type_ == "delta":
+            from langgraph.checkpoint.base import DeltaValue  # lazy import
+
+            raw = ormsgpack.unpackb(
+                data_, ext_hook=self._unpack_ext_hook, option=ormsgpack.OPT_NON_STR_KEYS
+            )
+            return DeltaValue(delta=raw["d"], prev_checkpoint_id=raw.get("c"))
         elif self.pickle_fallback and type_ == "pickle":
             return pickle.loads(data_)
         else:
@@ -575,9 +549,7 @@ def _create_msgpack_ext_hook(
                     "name": name,
                 }
             )
-            _warn_once(
-                _warned_unregistered_types,
-                key,
+            logger.warning(
                 "Deserializing unregistered type %s.%s from checkpoint. "
                 "This will be blocked in a future version. "
                 "Set LANGGRAPH_STRICT_MSGPACK=true to block now, or add "
@@ -599,9 +571,7 @@ def _create_msgpack_ext_hook(
                 "name": name,
             }
         )
-        _warn_once(
-            _warned_blocked_types,
-            key,
+        logger.warning(
             "Blocked deserialization of %s.%s - not in allowed_msgpack_modules. "
             "Add to allowed_msgpack_modules to allow: [(%r, %r)]",
             module,

libs/checkpoint/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "langgraph-checkpoint"
-version = "4.0.3"
+version = "4.0.2"
 description = "Library with base interfaces for LangGraph checkpoint savers."
 authors = []
 requires-python = ">=3.10"

libs/checkpoint/tests/test_encrypted.py

@@ -29,8 +29,6 @@ from langgraph.checkpoint.serde.jsonplus import (
     EXT_METHOD_SINGLE_ARG,
     JsonPlusSerializer,
     _msgpack_enc,
-    _warned_blocked_types,
-    _warned_unregistered_types,
 )
 
 
@@ -104,13 +102,6 @@ def test_msgpack_method_pathlib_blocked_encrypted_strict(
 class TestEncryptedSerializerMsgpackAllowlist:
     """Test msgpack allowlist behavior through EncryptedSerializer."""
 
-    @pytest.fixture(autouse=True)
-    def _reset_warned_types(self) -> None:
-        # Warning dedup state is process-global; reset per-test so each case
-        # sees a fresh slate and assertions about warning emission are stable.
-        _warned_unregistered_types.clear()
-        _warned_blocked_types.clear()
-
     def test_safe_types_no_warning(self, caplog: pytest.LogCaptureFixture) -> None:
         """Test safe types deserialize without warnings through encryption."""
         serde = _make_encrypted_serde()

libs/checkpoint/tests/test_jsonplus.py

@@ -35,8 +35,6 @@ from langgraph.checkpoint.serde.jsonplus import (
     JsonPlusSerializer,
     _msgpack_enc,
     _msgpack_ext_hook_to_json,
-    _warned_blocked_types,
-    _warned_unregistered_types,
 )
 from langgraph.store.base import Item
 
@@ -333,57 +331,6 @@ 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 = {
@@ -633,14 +580,6 @@ def test_msgpack_safe_types_no_warning(caplog: pytest.LogCaptureFixture) -> None
         assert result is not None
 
 
-@pytest.fixture(autouse=True)
-def _reset_warned_types() -> None:
-    # Warning dedup state is process-global; reset per-test so each case sees
-    # a fresh slate and assertions about warning emission are stable.
-    _warned_unregistered_types.clear()
-    _warned_blocked_types.clear()
-
-
 def test_msgpack_pydantic_warns_by_default(caplog: pytest.LogCaptureFixture) -> None:
     """Pydantic models not in allowlist should log warning but still deserialize."""
     current = _lg_msgpack.STRICT_MSGPACK_ENABLED
@@ -656,12 +595,6 @@ def test_msgpack_pydantic_warns_by_default(caplog: pytest.LogCaptureFixture) ->
     assert "unregistered type" in caplog.text.lower()
     assert "allowed_msgpack_modules" in caplog.text
     assert result == obj
-
-    # Second deserialization of the same type should NOT produce another warning
-    caplog.clear()
-    result2 = serde.loads_typed(dumped)
-    assert "unregistered type" not in caplog.text.lower()
-    assert result2 == obj
     _lg_msgpack.STRICT_MSGPACK_ENABLED = current
 
 
@@ -706,6 +639,7 @@ def test_msgpack_allowlist_silences_warning(caplog: pytest.LogCaptureFixture) ->
 
 def test_msgpack_none_blocks_unregistered(caplog: pytest.LogCaptureFixture) -> None:
     """allowed_msgpack_modules=None should block unregistered types."""
+
     serde = JsonPlusSerializer(allowed_msgpack_modules=None)
 
     obj = MyPydantic(foo="test", bar=42, inner=InnerPydantic(hello="world"))
@@ -723,6 +657,7 @@ def test_msgpack_allowlist_blocks_non_listed(
     caplog: pytest.LogCaptureFixture,
 ) -> None:
     """Allowlists should block unregistered types even if msgpack is enabled."""
+
     serde = JsonPlusSerializer(
         allowed_msgpack_modules=[("tests.test_jsonplus", "MyPydantic")]
     )
@@ -1048,3 +983,31 @@ def test_msgpack_nested_pydantic_serializes_as_dict(
     # No blocking should occur - inner is serialized as dict, not ext
     assert "blocked" not in caplog.text.lower()
     assert result == obj
+
+
+def test_delta_value_serde_round_trip() -> None:
+    from langgraph.checkpoint.base import DeltaValue
+    from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
+
+    serde = JsonPlusSerializer()
+    original = DeltaValue(
+        delta=[{"type": "human", "content": "hi"}], prev_checkpoint_id="abc-123"
+    )
+    type_tag, blob = serde.dumps_typed(original)
+    assert type_tag == "delta"
+    loaded = serde.loads_typed((type_tag, blob))
+    assert isinstance(loaded, DeltaValue)
+    assert loaded.delta == original.delta
+    assert loaded.prev_checkpoint_id == "abc-123"
+
+
+def test_delta_value_serde_chain_root() -> None:
+    from langgraph.checkpoint.base import DeltaValue
+    from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
+
+    serde = JsonPlusSerializer()
+    original = DeltaValue(delta=[], prev_checkpoint_id=None)
+    type_tag, blob = serde.dumps_typed(original)
+    loaded = serde.loads_typed((type_tag, blob))
+    assert isinstance(loaded, DeltaValue)
+    assert loaded.prev_checkpoint_id is None

libs/checkpoint/tests/test_memory.py

@@ -12,25 +12,13 @@ from langgraph.checkpoint.base import (
     empty_checkpoint,
 )
 from langgraph.checkpoint.memory import InMemorySaver
-from langgraph.checkpoint.serde.jsonplus import (
-    JsonPlusSerializer,
-    _warned_blocked_types,
-    _warned_unregistered_types,
-)
+from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
 
 
 class MemoryPydantic(BaseModel):
     foo: str
 
 
-@pytest.fixture(autouse=True)
-def _reset_warned_types() -> None:
-    # Warning dedup state is process-global; reset per-test so each case sees
-    # a fresh slate and assertions about warning emission are stable.
-    _warned_unregistered_types.clear()
-    _warned_blocked_types.clear()
-
-
 class TestMemorySaver:
     @pytest.fixture(autouse=True)
     def setup(self) -> None:
@@ -320,3 +308,36 @@ def test_memory_saver_with_allowlist_proxy_isolated() -> None:
     assert direct is not None
     expected = obj.model_dump() if hasattr(obj, "model_dump") else obj.dict()
     assert direct.checkpoint["channel_values"]["foo"] == expected
+
+
+class TestInMemorySaverDeltaChannel:
+    def test_get_channel_blob(self) -> None:
+        """get_channel_blob returns the deserialized blob for a checkpoint+channel."""
+        from langgraph.checkpoint.base import DeltaValue, empty_checkpoint
+
+        saver = InMemorySaver()
+        serde = JsonPlusSerializer()
+
+        thread_id, ns, channel = "t1", "", "messages"
+        version = "00000000000000000000000000000001.0000000000000000"
+        delta = DeltaValue(delta=[{"content": "hi"}], prev_checkpoint_id=None)
+        saver.blobs[(thread_id, ns, channel, version)] = serde.dumps_typed(delta)
+
+        cp = empty_checkpoint()
+        cp["id"] = "cp1"
+        cp["channel_versions"][channel] = version
+        saver.storage[thread_id][ns] = {
+            "cp1": (serde.dumps_typed(cp), serde.dumps_typed({}), None)
+        }
+
+        result = saver.get_channel_blob(thread_id, ns, "cp1", channel)
+        assert isinstance(result, DeltaValue)
+        assert result.delta == [{"content": "hi"}]
+        assert result.prev_checkpoint_id is None
+
+    def test_get_channel_blob_missing(self) -> None:
+        """get_channel_blob returns NotImplemented when checkpoint or channel not found."""
+        saver = InMemorySaver()
+        assert (
+            saver.get_channel_blob("t1", "", "no-such-cp", "messages") is NotImplemented
+        )

libs/checkpoint/uv.lock

@@ -286,7 +286,7 @@ wheels = [
 
 [[package]]
 name = "langgraph-checkpoint"
-version = "4.0.3"
+version = "4.0.2"
 source = { editable = "." }
 dependencies = [
     { name = "langchain-core" },

libs/cli/examples/graph_prerelease_reqs/deps/zuper_deps/pyproject.toml

@@ -5,5 +5,5 @@ description = "Test for prerelease stuff"
 readme = "README.md"
 requires-python = ">=3.10"
 dependencies = [
-  "langchain-openai==1.1.14"
+  "langchain-openai==1.0.1"
 ]

libs/cli/examples/graph_prerelease_reqs/pyproject.toml

@@ -5,7 +5,7 @@ description = "Test for prerelease stuff"
 readme = "README.md"
 requires-python = ">=3.10"
 dependencies = [
-  "langchain-openai==1.1.14",
+  "langchain-openai==1.0.0a2",
   "langchain-anthropic==1.0.0a5",
   "langgraph==1.1.5"
 ]

libs/cli/examples/graph_prerelease_reqs_fail/pyproject.toml

@@ -5,7 +5,7 @@ description = "Test for prerelease stuff"
 readme = "README.md"
 requires-python = ">=3.10"
 dependencies = [
-  "langchain-openai==1.1.14",
+  "langchain-openai==1.0.0a2",
   "langgraph==1.1.2",
   "langchain_community>=0.3.0",
 ]

libs/cli/langgraph_cli/__init__.py

@@ -1 +1 @@
-__version__ = "0.4.24"
+__version__ = "0.4.22"

libs/cli/langgraph_cli/_ignore.py

@@ -1,124 +0,0 @@
-"""Shared ignore-file handling for local source filtering."""
-
-import pathlib
-from dataclasses import dataclass
-
-import pathspec
-
-_ALWAYS_EXCLUDE = [
-    "__pycache__/",
-    ".git/",
-    ".venv/",
-    "venv/",
-    "node_modules/",
-    ".tox/",
-    ".mypy_cache/",
-]
-_ALWAYS_EXCLUDE_NAMES = frozenset(
-    pattern.rstrip("/").split("/")[-1] for pattern in _ALWAYS_EXCLUDE
-)
-_GLOB_CHARS = frozenset("*?[")
-
-
-@dataclass(frozen=True, slots=True)
-class _NegatedDockerignoreHints:
-    exact_dirs: frozenset[pathlib.PurePosixPath] = frozenset()
-    wildcard_prefixes: frozenset[pathlib.PurePosixPath] = frozenset()
-    recurse_all: bool = False
-
-    def requires_dir_walk(self, path: pathlib.PurePosixPath) -> bool:
-        if self.recurse_all or path in self.exact_dirs:
-            return True
-        return any(
-            path == prefix or path in prefix.parents or prefix in path.parents
-            for prefix in self.wildcard_prefixes
-        )
-
-
-def _build_ignore_spec(
-    directory: pathlib.Path, *, include_gitignore: bool = True
-) -> pathspec.PathSpec:
-    """Build a PathSpec combining built-in exclusions with ignore files.
-
-    Always excludes common non-source directories (`_ALWAYS_EXCLUDE`). On top
-    of that, patterns from `.dockerignore` are merged in. `.gitignore` patterns
-    are optional because some callers need Docker build-context semantics,
-    while archive creation wants both files.
-    """
-    lines: list[str] = list(_ALWAYS_EXCLUDE)
-    ignore_files = [".dockerignore"]
-    if include_gitignore:
-        ignore_files.append(".gitignore")
-    for name in ignore_files:
-        ignore_file = directory / name
-        if ignore_file.is_file():
-            lines.extend(ignore_file.read_text(encoding="utf-8").splitlines())
-    return pathspec.PathSpec.from_lines("gitwildmatch", lines)
-
-
-def _is_always_excluded(path: pathlib.PurePosixPath, *, is_dir: bool) -> bool:
-    """Whether `path` lives inside a built-in excluded directory."""
-    parent_parts = path.parts if is_dir else path.parts[:-1]
-    return any(part in _ALWAYS_EXCLUDE_NAMES for part in parent_parts)
-
-
-def _build_dockerignore_negation_hints(
-    directory: pathlib.Path,
-) -> _NegatedDockerignoreHints:
-    """Summarize which ignored directories must still be traversed.
-
-    Most negations only require walking a small, concrete chain of parent
-    directories (for example `!assets/keep.txt` requires entering `assets/`).
-    Broader glob negations may force a wider walk.
-    """
-    ignore_file = directory / ".dockerignore"
-    if not ignore_file.is_file():
-        return _NegatedDockerignoreHints()
-
-    exact_dirs: set[pathlib.PurePosixPath] = set()
-    wildcard_prefixes: set[pathlib.PurePosixPath] = set()
-    recurse_all = False
-
-    for raw_line in ignore_file.read_text(encoding="utf-8").splitlines():
-        line = raw_line.strip()
-        if not line or line.startswith("#") or line.startswith("\\!"):
-            continue
-        if line.startswith("\\#"):
-            line = line[1:]
-        if not line.startswith("!"):
-            continue
-
-        pattern = line[1:].lstrip("/")
-        while pattern.startswith("./"):
-            pattern = pattern[2:]
-        pattern = pattern.rstrip("/")
-        parts = [part for part in pattern.split("/") if part and part != "."]
-        if not parts:
-            recurse_all = True
-            continue
-
-        wildcard_index = next(
-            (
-                idx
-                for idx, part in enumerate(parts)
-                if any(char in part for char in _GLOB_CHARS)
-            ),
-            None,
-        )
-        if wildcard_index is not None:
-            literal_parts = parts[:wildcard_index]
-            if not literal_parts:
-                recurse_all = True
-                continue
-            wildcard_prefixes.add(pathlib.PurePosixPath(*literal_parts))
-            continue
-
-        parent_parts = parts[:-1]
-        for idx in range(1, len(parent_parts) + 1):
-            exact_dirs.add(pathlib.PurePosixPath(*parent_parts[:idx]))
-
-    return _NegatedDockerignoreHints(
-        exact_dirs=frozenset(exact_dirs),
-        wildcard_prefixes=frozenset(wildcard_prefixes),
-        recurse_all=recurse_all,
-    )

libs/cli/langgraph_cli/archive.py

@@ -9,12 +9,35 @@ from contextlib import contextmanager
 import click
 import pathspec
 
-from langgraph_cli._ignore import _build_ignore_spec
 from langgraph_cli.config import Config, _assemble_local_deps
 
 _WARN_SIZE = 50 * 1024 * 1024  # 50 MB
 _MAX_SIZE = 200 * 1024 * 1024  # 200 MB
 
+_ALWAYS_EXCLUDE = [
+    "__pycache__/",
+    ".git/",
+    ".venv/",
+    "venv/",
+    "node_modules/",
+    ".tox/",
+    ".mypy_cache/",
+]
+
+
+def _build_ignore_spec(directory: pathlib.Path) -> pathspec.PathSpec:
+    """Build a PathSpec combining built-in exclusions with .dockerignore and .gitignore.
+
+    Always excludes common non-source directories (_ALWAYS_EXCLUDE).  On top of
+    that, patterns from .dockerignore and .gitignore (if present) are merged in.
+    """
+    lines: list[str] = list(_ALWAYS_EXCLUDE)
+    for name in (".dockerignore", ".gitignore"):
+        ignore_file = directory / name
+        if ignore_file.is_file():
+            lines.extend(ignore_file.read_text(encoding="utf-8").splitlines())
+    return pathspec.PathSpec.from_lines("gitwildmatch", lines)
+
 
 def _tar_filter(tarinfo: tarfile.TarInfo) -> tarfile.TarInfo | None:
     """Strip symlinks, hardlinks, and traversal paths from archive."""

libs/cli/langgraph_cli/uv_lock.py

@@ -10,13 +10,7 @@ except ModuleNotFoundError:  # pragma: no cover - exercised on Python 3.10.
     import tomli as tomllib
 
 import click
-import pathspec
 
-from langgraph_cli._ignore import (
-    _build_dockerignore_negation_hints,
-    _build_ignore_spec,
-    _is_always_excluded,
-)
 from langgraph_cli.schemas import Config
 
 
@@ -446,32 +440,16 @@ def _container_root_for_uv_lock_package(
 
 
 def _uv_lock_package_copy_items(
-    package: UvLockPackage,
-    plan: UvLockPlan,
-    ignore_spec: pathspec.PathSpec,
+    package: UvLockPackage, plan: UvLockPlan
 ) -> tuple[tuple[pathlib.PurePosixPath, pathlib.PurePosixPath], ...]:
-    # Skip entries that .dockerignore / built-in exclusions would strip from
-    # the build context. Emitting `ADD <path>` for a file that Docker has
-    # filtered out causes the build to fail with
-    # "failed to compute cache key: <path> not found".
     if package.root != plan.project_root:
         relative_root = pathlib.PurePosixPath(
             *package.root.relative_to(plan.project_root).parts
         )
-        if _is_always_excluded(relative_root, is_dir=True) or ignore_spec.match_file(
-            f"{relative_root.as_posix()}/"
-        ):
-            raise click.UsageError(
-                f"Workspace member '{package.name}' at {relative_root} is "
-                "excluded from the Docker build context, but uv.lock requires "
-                "it to be copied into the build context. Remove the matching "
-                "pattern or drop the member from [tool.uv.workspace].members."
-            )
         return ((relative_root, plan.container_roots[package.root]),)
 
     root_container = plan.container_roots[package.root]
     workspace_member_roots = plan.all_workspace_roots - {plan.project_root}
-    negated_dockerignore_hints = _build_dockerignore_negation_hints(plan.project_root)
 
     def iter_entries(
         current_dir: pathlib.Path,
@@ -483,32 +461,18 @@ def _uv_lock_package_copy_items(
                 # and excluded entirely otherwise.
                 continue
 
+            descendant_member_roots = [
+                ws_root
+                for ws_root in workspace_member_roots
+                if child in ws_root.parents
+            ]
+            if child.is_dir() and descendant_member_roots:
+                entries.extend(iter_entries(child))
+                continue
+
             relative_child = pathlib.PurePosixPath(
                 *child.relative_to(plan.project_root).parts
             )
-            is_dir = child.is_dir()
-            if _is_always_excluded(relative_child, is_dir=is_dir):
-                continue
-            ignored = ignore_spec.match_file(
-                f"{relative_child.as_posix()}/" if is_dir else relative_child.as_posix()
-            )
-            is_workspace_parent = is_dir and any(
-                child in ws_root.parents for ws_root in workspace_member_roots
-            )
-
-            if is_workspace_parent:
-                entries.extend(iter_entries(child))
-                continue
-            if (
-                is_dir
-                and ignored
-                and negated_dockerignore_hints.requires_dir_walk(relative_child)
-            ):
-                entries.extend(iter_entries(child))
-                continue
-            if ignored:
-                continue
-
             entries.append(
                 (relative_child, root_container.joinpath(*relative_child.parts))
             )
@@ -992,13 +956,10 @@ def python_config_to_docker_uv_lock(
     docker_plan.add_raw("# -- End of uv.lock dependencies install --")
     docker_plan.add_blank()
 
-    ignore_spec = _build_ignore_spec(plan.project_root, include_gitignore=False)
     for package in plan.install_order:
         package_label = package.root.relative_to(plan.project_root).as_posix() or "."
         docker_plan.add_raw(f"# -- Adding workspace package {package_label} --")
-        for source, destination in _uv_lock_package_copy_items(
-            package, plan, ignore_spec
-        ):
+        for source, destination in _uv_lock_package_copy_items(package, plan):
             docker_plan.add_raw(copy_from_project_root(source, destination.as_posix()))
         docker_plan.add_instruction(
             "WORKDIR", plan.container_roots[package.root].as_posix()

libs/cli/pyproject.toml

@@ -23,7 +23,7 @@ dependencies = [
 path = "langgraph_cli/__init__.py"
 [project.optional-dependencies]
 inmem = [
-    "langgraph-api>=0.5.35,<0.9.0 ; python_version >= '3.11'",
+    "langgraph-api>=0.5.35,<0.8.0 ; python_version >= '3.11'",
     "langgraph-runtime-inmem>=0.7 ; python_version >= '3.11'",
 ]
 

libs/cli/tests/unit_tests/test_archive.py

@@ -99,13 +99,6 @@ class TestBuildIgnoreSpec:
         assert spec.match_file("app.log")
         assert spec.match_file("mod.pyc")
 
-    def test_can_skip_gitignore(self, tmp_path):
-        (tmp_path / ".dockerignore").write_text("*.log\n")
-        (tmp_path / ".gitignore").write_text("*.pyc\n")
-        spec = _build_ignore_spec(tmp_path, include_gitignore=False)
-        assert spec.match_file("app.log")
-        assert not spec.match_file("mod.pyc")
-
     def test_no_ignore_files_only_builtins(self, tmp_path):
         spec = _build_ignore_spec(tmp_path)
         assert spec.match_file("__pycache__/")

libs/cli/tests/unit_tests/test_config.py

@@ -4,7 +4,6 @@ import os
 import pathlib
 import tempfile
 import textwrap
-from unittest.mock import patch
 
 import click
 import pytest
@@ -1856,364 +1855,6 @@ def test_config_to_docker_uv_lock_supports_single_uv_project_root():
         assert additional_contexts == {}
 
 
-def test_config_to_docker_uv_lock_skips_dockerignore_entries():
-    """Entries filtered by .dockerignore / built-in excludes must not appear
-    as ADD lines. Docker fails to compute the cache key for paths that the
-    build context has stripped."""
-    with tempfile.TemporaryDirectory() as tmpdir:
-        tmpdir_path = pathlib.Path(tmpdir)
-        project_root = tmpdir_path / "single"
-        project_root.mkdir()
-        (project_root / "uv.lock").write_text("# uv lock file\n")
-        (project_root / "pyproject.toml").write_text(
-            textwrap.dedent(
-                """
-                [project]
-                name = "single-app"
-                version = "0.1.0"
-                dependencies = ["httpx>=0.28"]
-
-                [build-system]
-                requires = ["setuptools>=61"]
-                build-backend = "setuptools.build_meta"
-                """
-            ).strip()
-            + "\n"
-        )
-        (project_root / "langgraph.json").write_text("{}\n")
-        (project_root / "src").mkdir()
-        (project_root / "src" / "agent.py").write_text("graph = object()\n")
-        (project_root / "README.md").write_text("# hi\n")
-
-        # Built-in exclusions — must never appear as ADD lines.
-        (project_root / ".git").mkdir()
-        (project_root / ".git" / "HEAD").write_text("ref: refs/heads/main\n")
-        (project_root / ".venv").mkdir()
-        (project_root / ".venv" / "pyvenv.cfg").write_text("home = /usr\n")
-        (project_root / "__pycache__").mkdir()
-        (project_root / "__pycache__" / "x.cpython-311.pyc").write_bytes(b"\x00")
-
-        # .dockerignore excludes .gitignore and a custom path.
-        (project_root / ".dockerignore").write_text(".gitignore\nsecrets.env\n")
-        (project_root / ".gitignore").write_text("*.pyc\n")
-        (project_root / "secrets.env").write_text("TOKEN=abc\n")
-
-        config = validate_config(
-            {
-                "python_version": "3.11",
-                "graphs": {"agent": "./src/agent.py:graph"},
-                "source": {"kind": "uv"},
-            }
-        )
-        docker, _ = config_to_docker(
-            project_root / "langgraph.json",
-            config,
-            base_image="langchain/langgraph-api:0.2.47",
-        )
-
-        for excluded in (
-            "ADD .git ",
-            "ADD .gitignore ",
-            "ADD .venv ",
-            "ADD __pycache__ ",
-            "ADD secrets.env ",
-        ):
-            assert excluded not in docker, (
-                f"{excluded!r} should be filtered out of Dockerfile:\n{docker}"
-            )
-
-        # The .dockerignore itself is still part of the context and should be
-        # ADDed (Docker needs it at build time, and archive.py includes it).
-        assert "ADD .dockerignore /deps/workspace/.dockerignore" in docker
-        assert "ADD src /deps/workspace/src" in docker
-        assert "ADD README.md /deps/workspace/README.md" in docker
-
-
-def test_config_to_docker_uv_lock_does_not_apply_gitignore():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        tmpdir_path = pathlib.Path(tmpdir)
-        project_root = tmpdir_path / "single"
-        project_root.mkdir()
-        (project_root / "uv.lock").write_text("# uv lock file\n")
-        (project_root / "pyproject.toml").write_text(
-            textwrap.dedent(
-                """
-                [project]
-                name = "single-app"
-                version = "0.1.0"
-                dependencies = ["httpx>=0.28"]
-
-                [build-system]
-                requires = ["setuptools>=61"]
-                build-backend = "setuptools.build_meta"
-                """
-            ).strip()
-            + "\n"
-        )
-        (project_root / "langgraph.json").write_text("{}\n")
-        (project_root / "src").mkdir()
-        (project_root / "src" / "agent.py").write_text("graph = object()\n")
-        (project_root / "README.md").write_text("# hi\n")
-        (project_root / ".gitignore").write_text("README.md\n")
-
-        config = validate_config(
-            {
-                "python_version": "3.11",
-                "graphs": {"agent": "./src/agent.py:graph"},
-                "source": {"kind": "uv"},
-            }
-        )
-        docker, _ = config_to_docker(
-            project_root / "langgraph.json",
-            config,
-            base_image="langchain/langgraph-api:0.2.47",
-        )
-
-        assert "ADD README.md /deps/workspace/README.md" in docker
-
-
-def test_config_to_docker_uv_lock_skips_dockerignore_entries_in_workspace():
-    """Multi-member workspace: ignore patterns must filter root-level entries
-    AND entries encountered while recursing into directories that contain
-    workspace members (the `descendant_member_roots` branch)."""
-    with tempfile.TemporaryDirectory() as tmpdir:
-        tmpdir_path = pathlib.Path(tmpdir)
-        project_root, config_path = _write_uv_lock_workspace(
-            tmpdir_path,
-            agent_dependencies=["workspace-root", "shared", "httpx>=0.28"],
-            root_sources="[tool.uv.sources]\nshared = { workspace = true }\nworkspace-root = { workspace = true }",
-            agent_sources="[tool.uv.sources]\nshared = { workspace = true }\nworkspace-root = { workspace = true }",
-        )
-        root_src = project_root / "src" / "workspace_root"
-        root_src.mkdir(parents=True)
-        (root_src / "__init__.py").write_text("__all__ = []\n")
-        (project_root / "README.md").write_text("workspace root package\n")
-
-        # A non-member sibling of the `apps/agent` member that should be
-        # filtered out via .dockerignore. This exercises the recursion into
-        # `apps/` where `apps/agent` is kept (it's a member) but its sibling is
-        # filtered.
-        (project_root / "apps" / "scratch.txt").write_text("scratch\n")
-        # A root-level path that .dockerignore excludes.
-        (project_root / "secrets.env").write_text("TOKEN=abc\n")
-        (project_root / ".dockerignore").write_text("secrets.env\napps/scratch.txt\n")
-
-        config = validate_config(
-            {
-                "python_version": "3.11",
-                "graphs": {
-                    "agent": "../../apps/agent/src/agent/graph.py:graph",
-                },
-                "source": {"kind": "uv", "root": "../..", "package": "agent"},
-            }
-        )
-        docker, _ = config_to_docker(
-            config_path, config, base_image="langchain/langgraph-api:0.2.47"
-        )
-
-        assert "COPY --from=uv-workspace-root src /deps/workspace/src" in docker
-        assert (
-            "COPY --from=uv-workspace-root README.md /deps/workspace/README.md"
-            in docker
-        )
-        assert (
-            "COPY --from=uv-workspace-root .dockerignore /deps/workspace/.dockerignore"
-            in docker
-        )
-        assert "secrets.env" not in docker
-        assert "apps/scratch.txt" not in docker
-        # Workspace members themselves are still copied via their own per-member
-        # COPY line — the sibling filter must not disturb this.
-        assert (
-            "COPY --from=uv-workspace-root apps/agent /deps/workspace/apps/agent"
-            in docker
-        )
-
-
-def test_config_to_docker_uv_lock_preserves_negated_dockerignore_descendants():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        tmpdir_path = pathlib.Path(tmpdir)
-        project_root = tmpdir_path / "single"
-        project_root.mkdir()
-        (project_root / "uv.lock").write_text("# uv lock file\n")
-        (project_root / "pyproject.toml").write_text(
-            textwrap.dedent(
-                """
-                [project]
-                name = "single-app"
-                version = "0.1.0"
-                dependencies = ["httpx>=0.28"]
-
-                [build-system]
-                requires = ["setuptools>=61"]
-                build-backend = "setuptools.build_meta"
-                """
-            ).strip()
-            + "\n"
-        )
-        (project_root / "langgraph.json").write_text("{}\n")
-        (project_root / "src").mkdir()
-        (project_root / "src" / "agent.py").write_text("graph = object()\n")
-        (project_root / "assets").mkdir()
-        (project_root / "assets" / "keep.txt").write_text("keep\n")
-        (project_root / "assets" / "drop.txt").write_text("drop\n")
-        (project_root / ".dockerignore").write_text("assets/\n!assets/keep.txt\n")
-
-        config = validate_config(
-            {
-                "python_version": "3.11",
-                "graphs": {"agent": "./src/agent.py:graph"},
-                "source": {"kind": "uv"},
-            }
-        )
-        docker, _ = config_to_docker(
-            project_root / "langgraph.json",
-            config,
-            base_image="langchain/langgraph-api:0.2.47",
-        )
-
-        assert "ADD assets /deps/workspace/assets" not in docker
-        assert "ADD assets/keep.txt /deps/workspace/assets/keep.txt" in docker
-        assert "assets/drop.txt" not in docker
-
-
-def test_config_to_docker_uv_lock_prunes_unrelated_ignored_subtrees():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        tmpdir_path = pathlib.Path(tmpdir)
-        project_root = tmpdir_path / "single"
-        project_root.mkdir()
-        (project_root / "uv.lock").write_text("# uv lock file\n")
-        (project_root / "pyproject.toml").write_text(
-            textwrap.dedent(
-                """
-                [project]
-                name = "single-app"
-                version = "0.1.0"
-                dependencies = ["httpx>=0.28"]
-
-                [build-system]
-                requires = ["setuptools>=61"]
-                build-backend = "setuptools.build_meta"
-                """
-            ).strip()
-            + "\n"
-        )
-        (project_root / "langgraph.json").write_text("{}\n")
-        (project_root / "src").mkdir()
-        (project_root / "src" / "agent.py").write_text("graph = object()\n")
-        (project_root / "assets").mkdir()
-        (project_root / "assets" / "keep.txt").write_text("keep\n")
-        (project_root / "vendor").mkdir()
-        (project_root / "vendor" / "huge.txt").write_text("large\n")
-        (project_root / ".dockerignore").write_text(
-            "vendor/\nassets/\n!assets/keep.txt\n"
-        )
-
-        config = validate_config(
-            {
-                "python_version": "3.11",
-                "graphs": {"agent": "./src/agent.py:graph"},
-                "source": {"kind": "uv"},
-            }
-        )
-
-        original_iterdir = pathlib.Path.iterdir
-
-        def guarded_iterdir(self):
-            if self == project_root / "vendor":
-                raise AssertionError("should not walk unrelated ignored subtree")
-            return original_iterdir(self)
-
-        with patch.object(
-            pathlib.Path, "iterdir", autospec=True, side_effect=guarded_iterdir
-        ):
-            docker, _ = config_to_docker(
-                project_root / "langgraph.json",
-                config,
-                base_image="langchain/langgraph-api:0.2.47",
-            )
-
-        assert "ADD assets/keep.txt /deps/workspace/assets/keep.txt" in docker
-        assert "vendor/huge.txt" not in docker
-
-
-def test_config_to_docker_uv_lock_never_reincludes_always_excluded_subtrees():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        tmpdir_path = pathlib.Path(tmpdir)
-        project_root = tmpdir_path / "single"
-        project_root.mkdir()
-        (project_root / "uv.lock").write_text("# uv lock file\n")
-        (project_root / "pyproject.toml").write_text(
-            textwrap.dedent(
-                """
-                [project]
-                name = "single-app"
-                version = "0.1.0"
-                dependencies = ["httpx>=0.28"]
-
-                [build-system]
-                requires = ["setuptools>=61"]
-                build-backend = "setuptools.build_meta"
-                """
-            ).strip()
-            + "\n"
-        )
-        (project_root / "langgraph.json").write_text("{}\n")
-        (project_root / "src").mkdir()
-        (project_root / "src" / "agent.py").write_text("graph = object()\n")
-        (project_root / ".venv" / "pkg").mkdir(parents=True)
-        (project_root / ".venv" / "pkg" / "keep.txt").write_text("keep\n")
-        (project_root / "node_modules" / "pkg").mkdir(parents=True)
-        (project_root / "node_modules" / "pkg" / "package.json").write_text("{}\n")
-        (project_root / ".dockerignore").write_text(
-            "!.venv/pkg/keep.txt\n!node_modules/pkg/package.json\n"
-        )
-
-        config = validate_config(
-            {
-                "python_version": "3.11",
-                "graphs": {"agent": "./src/agent.py:graph"},
-                "source": {"kind": "uv"},
-            }
-        )
-        docker, _ = config_to_docker(
-            project_root / "langgraph.json",
-            config,
-            base_image="langchain/langgraph-api:0.2.47",
-        )
-
-        assert ".venv/pkg/keep.txt" not in docker
-        assert "node_modules/pkg/package.json" not in docker
-        assert "ADD src /deps/workspace/src" in docker
-
-
-def test_config_to_docker_uv_lock_rejects_ignored_workspace_member():
-    """A workspace member matched by .dockerignore cannot be copied into the
-    build context — uv.lock requires it, so fail loudly with a clear message."""
-    with tempfile.TemporaryDirectory() as tmpdir:
-        tmpdir_path = pathlib.Path(tmpdir)
-        project_root, config_path = _write_uv_lock_workspace(
-            tmpdir_path,
-            agent_sources="[tool.uv.sources]\nshared = { workspace = true }",
-        )
-        (project_root / ".dockerignore").write_text("libs/shared\n")
-
-        config = validate_config(
-            {
-                "python_version": "3.11",
-                "graphs": {"agent": "../../apps/agent/src/agent/graph.py:graph"},
-                "source": {"kind": "uv", "root": "../..", "package": "agent"},
-                "auth": {"path": "../../libs/shared/src/shared/auth.py:create_auth"},
-            }
-        )
-        with pytest.raises(
-            click.UsageError, match=r"Workspace member 'shared' at libs/shared"
-        ):
-            config_to_docker(
-                config_path, config, base_image="langchain/langgraph-api:0.2.47"
-            )
-
-
 def test_config_to_docker_uv_lock_rejects_invalid_source_package_type():
     with tempfile.TemporaryDirectory() as tmpdir:
         tmpdir_path = pathlib.Path(tmpdir)

libs/langgraph/langgraph/callbacks.py

@@ -245,6 +245,15 @@ class _GraphCallbackManager(BaseCallbackManager):
             run_id=run_id,
         )
 
+    def add_handler(
+        self,
+        handler: BaseCallbackHandler,
+        inherit: bool = True,  # noqa: FBT001,FBT002
+    ) -> None:
+        if not isinstance(handler, GraphCallbackHandler):
+            raise TypeError("handlers must inherit GraphCallbackHandler")
+        super().add_handler(handler, inherit=inherit)
+
     def copy(
         self,
         *,
@@ -312,6 +321,15 @@ class _AsyncGraphCallbackManager(BaseCallbackManager):
             run_id=run_id,
         )
 
+    def add_handler(
+        self,
+        handler: BaseCallbackHandler,
+        inherit: bool = True,  # noqa: FBT001,FBT002
+    ) -> None:
+        if not isinstance(handler, GraphCallbackHandler):
+            raise TypeError("handlers must inherit GraphCallbackHandler")
+        super().add_handler(handler, inherit=inherit)
+
     def copy(
         self,
         *,

libs/langgraph/langgraph/channels/__init__.py

@@ -1,6 +1,7 @@
 from langgraph.channels.any_value import AnyValue
 from langgraph.channels.base import BaseChannel
 from langgraph.channels.binop import BinaryOperatorAggregate
+from langgraph.channels.delta import DeltaChannel
 from langgraph.channels.ephemeral_value import EphemeralValue
 from langgraph.channels.last_value import LastValue, LastValueAfterFinish
 from langgraph.channels.named_barrier_value import (
@@ -20,6 +21,7 @@ __all__ = (
     "UntrackedValue",
     "EphemeralValue",
     "BinaryOperatorAggregate",
+    "DeltaChannel",
     "NamedBarrierValue",
     "NamedBarrierValueAfterFinish",
     # topics

libs/langgraph/langgraph/channels/base.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 from abc import ABC, abstractmethod
 from collections.abc import Sequence
-from typing import Any, Generic, TypeVar
+from typing import Any, Generic, Literal, TypeVar
 
 from typing_extensions import Self
 
@@ -119,3 +119,17 @@ class BaseChannel(Generic[Value, Update, Checkpoint], ABC):
         Returns `True` if the channel was updated, `False` otherwise.
         """
         return False
+
+    def after_checkpoint(self, version: Any, checkpoint_id: str | None = None) -> None:
+        """Called after checkpoint() with the assigned version, and after
+        from_checkpoint() with the current channel version.
+
+        No-op by default. Override in channels that track their own version
+        for incremental checkpointing (e.g. DeltaChannel).
+        """
+        pass
+
+    @property
+    def checkpoint_hydration_kind(self) -> Literal["delta"] | None:
+        """Return the saver hydration kind for this channel, if any."""
+        return None

libs/langgraph/langgraph/channels/delta.py

@@ -0,0 +1,228 @@
+from __future__ import annotations
+
+import collections.abc
+from collections.abc import Callable, Sequence
+from copy import copy
+from typing import Any, Generic, Literal
+
+from langgraph.checkpoint.base import DeltaChainValue, DeltaValue
+from typing_extensions import Self
+
+from langgraph._internal._typing import MISSING
+from langgraph.channels.base import BaseChannel, Value
+from langgraph.channels.binop import _get_overwrite, _strip_extras
+from langgraph.errors import EmptyChannelError
+
+__all__ = ("DeltaChannel",)
+
+
+def _copy_value(value: Any) -> Any:
+    if value is MISSING:
+        return value
+    try:
+        return value.copy()
+    except AttributeError:
+        return copy(value)
+
+
+class DeltaChannel(Generic[Value], BaseChannel[list[Value], Value, DeltaValue]):
+    """A channel that stores only per-step write deltas in checkpoints.
+
+    Reconstructs the full accumulated list at load time by replaying the
+    chain of deltas through the operator. Use with append-style reducers
+    (e.g. `add_messages`) on long-running threads to reduce checkpoint
+    storage from O(N²) to O(N).
+
+    Works with all checkpointers. Savers with a dedicated blob store
+    (InMemorySaver, PostgresSaver) use an O(1) fast-path per chain step;
+    all others (SQLite, MongoDB, etc.) fall back to get_tuple traversal.
+
+    Use `snapshot_every=N` to cap chain traversal depth at N steps. Every N
+    steps a full snapshot is written as the chain root; subsequent deltas
+    chain back to it, so `get_state` / reload never traverses more than N
+    checkpoints regardless of thread length. Recommended for savers without
+    a dedicated blob store.
+
+    Usage::
+
+        class State(TypedDict):
+            messages: Annotated[list[AnyMessage], DeltaChannel(add_messages)]
+            # Cap reconstruction depth (recommended for SQLite / MongoDB savers):
+            messages: Annotated[list[AnyMessage], DeltaChannel(add_messages, snapshot_every=50)]
+    """
+
+    __slots__ = (
+        "value",
+        "operator",
+        "snapshot_every",
+        "_pending",
+        "_base_version",
+        "_last_checkpoint_id",
+        "_overwritten",
+        "_steps_since_snapshot",
+    )
+
+    def __init__(
+        self,
+        operator: Callable[[list[Value], Any], list[Value]],
+        typ: type = list,
+        *,
+        snapshot_every: int | None = None,
+    ) -> None:
+        typ = _strip_extras(typ)
+        if typ in (
+            collections.abc.Sequence,
+            collections.abc.MutableSequence,
+        ):
+            typ = list
+        super().__init__(typ)
+        self.operator = operator
+        self.snapshot_every = snapshot_every
+        try:
+            self.value: list[Value] = typ()
+        except Exception:
+            self.value = []
+        self._pending: list[Any] = []
+        self._base_version: str | None = None
+        self._last_checkpoint_id: str | None = None
+        self._overwritten: bool = False
+        self._steps_since_snapshot: int = 0
+
+    def __eq__(self, other: object) -> bool:
+        if not isinstance(other, DeltaChannel):
+            return False
+        if self.snapshot_every != other.snapshot_every:
+            return False
+        if (
+            self.operator.__name__ != "<lambda>"
+            and other.operator.__name__ != "<lambda>"
+        ):
+            return self.operator is other.operator
+        return True
+
+    @property
+    def ValueType(self) -> Any:
+        return list[self.typ]  # type: ignore[name-defined]
+
+    @property
+    def UpdateType(self) -> Any:
+        return self.typ | list[self.typ]  # type: ignore[name-defined]
+
+    @property
+    def checkpoint_hydration_kind(self) -> Literal["delta"]:
+        return "delta"
+
+    def copy(self) -> Self:
+        new = DeltaChannel(self.operator, self.typ, snapshot_every=self.snapshot_every)
+        new.key = self.key
+        new.value = _copy_value(self.value)
+        new._pending = self._pending[:]
+        new._base_version = self._base_version
+        new._last_checkpoint_id = self._last_checkpoint_id
+        new._overwritten = self._overwritten
+        new._steps_since_snapshot = self._steps_since_snapshot
+        return new
+
+    def from_checkpoint(self, checkpoint: Any) -> Self:
+        new = DeltaChannel(self.operator, self.typ, snapshot_every=self.snapshot_every)
+        new.key = self.key
+        if checkpoint is MISSING:
+            pass
+        elif isinstance(checkpoint, DeltaChainValue):
+            accumulated: list[Value] = (
+                checkpoint.base if checkpoint.base is not None else new.typ()
+            )
+            for step_writes in checkpoint.deltas:
+                for write in step_writes:
+                    accumulated = new.operator(accumulated, write)
+            new.value = accumulated
+            # Seed the counter from actual chain depth so rehydration fires at
+            # the right time regardless of how many prior invocations there were.
+            new._steps_since_snapshot = len(checkpoint.deltas)
+        elif isinstance(checkpoint, DeltaValue):
+            # Should never reach here — checkpoint hydration should assemble
+            # DeltaValues into DeltaChainValue before calling from_checkpoint.
+            raise AssertionError(
+                "DeltaChannel.from_checkpoint received a raw DeltaValue. "
+                "This is a bug in checkpoint hydration — chain assembly should "
+                "have occurred before from_checkpoint was called."
+            )
+        else:
+            # Backwards compat: plain value from old BinaryOperatorAggregate checkpoint
+            # or a full snapshot emitted by DeltaChannel.
+            new.value = _copy_value(checkpoint)
+        new._pending = []
+        new._base_version = None  # set by the subsequent after_checkpoint() call
+        new._overwritten = False
+        return new
+
+    def update(self, values: Sequence[Any]) -> bool:
+        if not values:
+            return False
+        seen_overwrite = False
+        for value in values:
+            is_overwrite, overwrite_value = _get_overwrite(value)
+            if is_overwrite:
+                if seen_overwrite:
+                    from langgraph.errors import (
+                        ErrorCode,
+                        InvalidUpdateError,
+                        create_error_message,
+                    )
+
+                    msg = create_error_message(
+                        message="Can receive only one Overwrite value per super-step.",
+                        error_code=ErrorCode.INVALID_CONCURRENT_GRAPH_UPDATE,
+                    )
+                    raise InvalidUpdateError(msg)
+                self.value = (
+                    _copy_value(overwrite_value)
+                    if overwrite_value is not None
+                    else self.typ()
+                )
+                self._pending = (
+                    [] if overwrite_value is None else [_copy_value(self.value)]
+                )
+                self._overwritten = True
+                seen_overwrite = True
+            elif not seen_overwrite:
+                base = self.typ() if self.value is MISSING else self.value
+                self.value = self.operator(base, value)
+                self._pending.append(value)
+        return True
+
+    def get(self) -> list[Value]:
+        if self.value is MISSING:
+            raise EmptyChannelError()
+        return self.value
+
+    def is_available(self) -> bool:
+        return self.value is not MISSING
+
+    def checkpoint(self) -> Any:
+        if (
+            self.snapshot_every is not None
+            and self._steps_since_snapshot >= self.snapshot_every
+        ):
+            # Emit a full snapshot to cap chain depth at snapshot_every.
+            # The saver stores this as a plain (non-diff) blob, so future
+            # deltas will chain back to it and traversal depth resets to 1.
+            return _copy_value(self.value)
+        return DeltaValue(
+            delta=self._pending[:],
+            prev_checkpoint_id=None if self._overwritten else self._last_checkpoint_id,
+        )
+
+    def after_checkpoint(self, version: Any, checkpoint_id: str | None = None) -> None:
+        if version != self._base_version:
+            if self._base_version is None:
+                pass  # First call after from_checkpoint — anchor without counting a step.
+            elif self.snapshot_every is not None:
+                if self._steps_since_snapshot >= self.snapshot_every:
+                    self._steps_since_snapshot = 0
+                else:
+                    self._steps_since_snapshot += 1
+            self._base_version = version
+            self._last_checkpoint_id = checkpoint_id
+            self._pending = []
+            self._overwritten = False

libs/langgraph/langgraph/pregel/_checkpoint.py

@@ -3,7 +3,11 @@ from __future__ import annotations
 from collections.abc import Mapping
 from datetime import datetime, timezone
 
-from langgraph.checkpoint.base import Checkpoint
+from langgraph.checkpoint.base import (
+    Checkpoint,
+    CheckpointHydrationPlan,
+    IncrementalChannelSpec,
+)
 from langgraph.checkpoint.base.id import uuid6
 
 from langgraph._internal._typing import MISSING
@@ -13,6 +17,19 @@ from langgraph.managed.base import ManagedValueMapping, ManagedValueSpec
 LATEST_VERSION = 4
 
 
+def checkpoint_hydration_plan(
+    specs: Mapping[str, BaseChannel | ManagedValueSpec],
+) -> CheckpointHydrationPlan | None:
+    """Build a saver hydration plan from channel specs."""
+    channels = tuple(
+        IncrementalChannelSpec(name=name, kind=channel.checkpoint_hydration_kind)
+        for name, channel in specs.items()
+        if isinstance(channel, BaseChannel)
+        and channel.checkpoint_hydration_kind is not None
+    )
+    return CheckpointHydrationPlan(channels=channels) if channels else None
+
+
 def empty_checkpoint() -> Checkpoint:
     return Checkpoint(
         v=LATEST_VERSION,
@@ -67,13 +84,12 @@ def channels_from_checkpoint(
             channel_specs[k] = v
         else:
             managed_specs[k] = v
-    return (
-        {
-            k: v.from_checkpoint(checkpoint["channel_values"].get(k, MISSING))
-            for k, v in channel_specs.items()
-        },
-        managed_specs,
-    )
+    channels: dict[str, BaseChannel] = {}
+    for k, v in channel_specs.items():
+        ch = v.from_checkpoint(checkpoint["channel_values"].get(k, MISSING))
+        ch.after_checkpoint(checkpoint["channel_versions"].get(k), checkpoint.get("id"))
+        channels[k] = ch
+    return channels, managed_specs
 
 
 def copy_checkpoint(checkpoint: Checkpoint) -> Checkpoint:

libs/langgraph/langgraph/pregel/_loop.py

@@ -12,6 +12,7 @@ from contextlib import (
     ExitStack,
 )
 from datetime import datetime, timezone
+from functools import cached_property
 from inspect import signature
 from types import TracebackType
 from typing import (
@@ -29,6 +30,7 @@ from langgraph.checkpoint.base import (
     BaseCheckpointSaver,
     ChannelVersions,
     Checkpoint,
+    CheckpointHydrationPlan,
     CheckpointMetadata,
     CheckpointTuple,
     PendingWrite,
@@ -93,6 +95,7 @@ from langgraph.pregel._algo import (
 )
 from langgraph.pregel._checkpoint import (
     channels_from_checkpoint,
+    checkpoint_hydration_plan,
     copy_checkpoint,
     create_checkpoint,
     empty_checkpoint,
@@ -314,6 +317,29 @@ class PregelLoop:
         )
         self.prev_checkpoint_config = None
 
+    @cached_property
+    def _checkpoint_hydration_plan(self) -> CheckpointHydrationPlan | None:
+        """Build the saver hydration plan from this loop's channel specs."""
+        return checkpoint_hydration_plan(self.specs)
+
+    def _materialize_saved_checkpoint(
+        self, saved: CheckpointTuple | None
+    ) -> CheckpointTuple | None:
+        if saved is None or self.checkpointer is None:
+            return saved
+        return self.checkpointer.materialize_checkpoint_tuple(
+            saved, self._checkpoint_hydration_plan
+        )
+
+    async def _amaterialize_saved_checkpoint(
+        self, saved: CheckpointTuple | None
+    ) -> CheckpointTuple | None:
+        if saved is None or self.checkpointer is None:
+            return saved
+        return await self.checkpointer.amaterialize_checkpoint_tuple(
+            saved, self._checkpoint_hydration_plan
+        )
+
     def _push_graph_lifecycle_event(
         self,
         kind: Literal["resume", "interrupt"],
@@ -831,18 +857,8 @@ class PregelLoop:
             # parent. For forks (source=update/fork), use the fork's parent
             # checkpoint ID since the fork was created after the subgraph's
             # checkpoints from the original execution.
-            #
-            # Only gate on is_time_traveling (not is_replaying). When the
-            # client resumes with an explicit checkpoint_id that happens to
-            # point at the current head (e.g. LangGraph Studio sending
-            # `checkpoint: {checkpoint_id}` alongside Command(resume=...)),
-            # is_replaying is True but is_time_traveling is False. In that
-            # case subgraphs should load their latest checkpoint normally,
-            # not go through ReplayState's before-bound lookup which would
-            # miss subgraph checkpoints created during processing of the
-            # current parent step.
             replay_state: ReplayState | None = None
-            if is_time_traveling:
+            if self.is_replaying:
                 replay_checkpoint_id = self.checkpoint["id"]
                 if (
                     self.checkpoint_metadata.get("source")
@@ -891,6 +907,12 @@ class PregelLoop:
             id=self.checkpoint["id"] if exiting else None,
             updated_channels=self.updated_channels,
         )
+        if do_checkpoint and self.channels:
+            for k, ch in self.channels.items():
+                ch.after_checkpoint(
+                    self.checkpoint["channel_versions"].get(k),
+                    self.checkpoint.get("id"),
+                )
         # sanitize TASK channel in the checkpoint before saving (durability=="exit")
         if TASKS in self.checkpoint["channel_values"] and any(
             isinstance(channel, UntrackedValue) for channel in self.channels.values()
@@ -1247,6 +1269,8 @@ class SyncPregelLoop(PregelLoop, AbstractContextManager):
             # graph/thread. Returns None on first invocation.
             saved = self.checkpointer.get_tuple(self.checkpoint_config)
 
+        saved = self._materialize_saved_checkpoint(saved)
+
         if saved is None:
             saved = CheckpointTuple(
                 self.checkpoint_config, empty_checkpoint(), {"step": -2}, None, []
@@ -1449,6 +1473,8 @@ class AsyncPregelLoop(PregelLoop, AbstractAsyncContextManager):
             # graph/thread. Returns None on first invocation.
             saved = await self.checkpointer.aget_tuple(self.checkpoint_config)
 
+        saved = await self._amaterialize_saved_checkpoint(saved)
+
         if saved is None:
             saved = CheckpointTuple(
                 self.checkpoint_config, empty_checkpoint(), {"step": -2}, None, []

libs/langgraph/langgraph/pregel/_messages.py

@@ -14,7 +14,7 @@ from langchain_core.messages import BaseMessage
 from langchain_core.outputs import ChatGeneration, ChatGenerationChunk, LLMResult
 from pydantic import BaseModel
 
-from langgraph._internal._constants import NS_SEP
+from langgraph._internal._constants import NS_END, NS_SEP
 from langgraph.constants import TAG_HIDDEN, TAG_NOSTREAM
 from langgraph.pregel.protocol import StreamChunk
 from langgraph.types import Command
@@ -132,15 +132,23 @@ class StreamMessagesHandler(BaseCallbackHandler, _StreamingCallbackHandler):
         **kwargs: Any,
     ) -> Any:
         if metadata and (not tags or (TAG_NOSTREAM not in tags)):
-            ns = tuple(cast(str, metadata["langgraph_checkpoint_ns"]).split(NS_SEP))[
-                :-1
-            ]
+            task_checkpoint_ns = cast(str, metadata["langgraph_checkpoint_ns"])
+            checkpoint_ns = (
+                f"{task_checkpoint_ns.rsplit(NS_END, 1)[0]}{NS_END}"
+                if NS_END in task_checkpoint_ns
+                else task_checkpoint_ns
+            )
+            ns = tuple(task_checkpoint_ns.split(NS_SEP))[:-1]
             if not self.subgraphs and len(ns) > 0 and ns != self.parent_ns:
                 return
+            stream_metadata = dict(metadata)
+            stream_metadata["langgraph_checkpoint_ns"] = checkpoint_ns
+            # Preserve backwards-compatible streamed checkpoint metadata shape.
+            stream_metadata["checkpoint_ns"] = checkpoint_ns
             if tags:
                 if filtered_tags := [t for t in tags if not t.startswith("seq:step")]:
-                    metadata["tags"] = filtered_tags
-            self.metadata[run_id] = (ns, metadata)
+                    stream_metadata["tags"] = filtered_tags
+            self.metadata[run_id] = (ns, stream_metadata)
 
     def on_llm_new_token(
         self,

libs/langgraph/langgraph/pregel/main.py

@@ -17,7 +17,7 @@ from collections.abc import (
     Sequence,
 )
 from dataclasses import is_dataclass, replace
-from functools import partial
+from functools import cached_property, partial
 from inspect import isclass
 from typing import (
     Any,
@@ -44,6 +44,7 @@ from langgraph.cache.base import BaseCache
 from langgraph.checkpoint.base import (
     BaseCheckpointSaver,
     Checkpoint,
+    CheckpointHydrationPlan,
     CheckpointTuple,
 )
 from langgraph.store.base import BaseStore
@@ -123,6 +124,7 @@ from langgraph.pregel._algo import (
 from langgraph.pregel._call import identifier
 from langgraph.pregel._checkpoint import (
     channels_from_checkpoint,
+    checkpoint_hydration_plan,
     copy_checkpoint,
     create_checkpoint,
     empty_checkpoint,
@@ -728,6 +730,54 @@ class Pregel(
             return checkpointer
         return _serde.apply_checkpointer_allowlist(checkpointer, self._serde_allowlist)
 
+    @cached_property
+    def _checkpoint_hydration_plan(self) -> CheckpointHydrationPlan | None:
+        return checkpoint_hydration_plan(self.channels)
+
+    def _materialize_saved_checkpoint(
+        self,
+        checkpointer: BaseCheckpointSaver | None,
+        saved: CheckpointTuple | None,
+    ) -> CheckpointTuple | None:
+        if saved is None or checkpointer is None:
+            return saved
+        return checkpointer.materialize_checkpoint_tuple(
+            saved, self._checkpoint_hydration_plan
+        )
+
+    async def _amaterialize_saved_checkpoint(
+        self,
+        checkpointer: BaseCheckpointSaver | None,
+        saved: CheckpointTuple | None,
+    ) -> CheckpointTuple | None:
+        if saved is None or checkpointer is None:
+            return saved
+        return await checkpointer.amaterialize_checkpoint_tuple(
+            saved, self._checkpoint_hydration_plan
+        )
+
+    def _materialize_saved_checkpoints(
+        self,
+        checkpointer: BaseCheckpointSaver | None,
+        saved: Sequence[CheckpointTuple],
+    ) -> list[CheckpointTuple]:
+        if checkpointer is None or not saved:
+            return list(saved)
+        return checkpointer.materialize_checkpoint_tuples(
+            saved, self._checkpoint_hydration_plan
+        )
+
+    async def _amaterialize_saved_checkpoints(
+        self,
+        checkpointer: BaseCheckpointSaver | None,
+        saved: Sequence[CheckpointTuple],
+    ) -> list[CheckpointTuple]:
+        if checkpointer is None or not saved:
+            return list(saved)
+        return await checkpointer.amaterialize_checkpoint_tuples(
+            saved, self._checkpoint_hydration_plan
+        )
+
     def get_graph(
         self, config: RunnableConfig | None = None, *, xray: int | bool = False
     ) -> Graph:
@@ -1049,13 +1099,14 @@ class Pregel(
 
         step = saved.metadata.get("step", -1) + 1
         stop = step + 2
+        checkpoint = saved.checkpoint
         channels, managed = channels_from_checkpoint(
             self.channels,
-            saved.checkpoint,
+            checkpoint,
         )
         # tasks for this checkpoint
         next_tasks = prepare_next_tasks(
-            saved.checkpoint,
+            checkpoint,
             saved.pending_writes or [],
             self.nodes,
             channels,
@@ -1168,13 +1219,14 @@ class Pregel(
 
         step = saved.metadata.get("step", -1) + 1
         stop = step + 2
+        checkpoint = saved.checkpoint
         channels, managed = channels_from_checkpoint(
             self.channels,
-            saved.checkpoint,
+            checkpoint,
         )
         # tasks for this checkpoint
         next_tasks = prepare_next_tasks(
-            saved.checkpoint,
+            checkpoint,
             saved.pending_writes or [],
             self.nodes,
             channels,
@@ -1300,7 +1352,9 @@ class Pregel(
         if not isinstance(thread_id, str):
             config[CONF][CONFIG_KEY_THREAD_ID] = str(thread_id)
 
-        saved = checkpointer.get_tuple(config)
+        saved = self._materialize_saved_checkpoint(
+            checkpointer, checkpointer.get_tuple(config)
+        )
         return self._prepare_state_snapshot(
             config,
             saved,
@@ -1344,7 +1398,9 @@ class Pregel(
         if not isinstance(thread_id, str):
             config[CONF][CONFIG_KEY_THREAD_ID] = str(thread_id)
 
-        saved = await checkpointer.aget_tuple(config)
+        saved = await self._amaterialize_saved_checkpoint(
+            checkpointer, await checkpointer.aget_tuple(config)
+        )
         return await self._aprepare_state_snapshot(
             config,
             saved,
@@ -1398,9 +1454,11 @@ class Pregel(
             },
         )
         # eagerly consume list() to avoid holding up the db cursor
-        for checkpoint_tuple in list(
-            checkpointer.list(config, before=before, limit=limit, filter=filter)
-        ):
+        checkpoint_tuples = self._materialize_saved_checkpoints(
+            checkpointer,
+            list(checkpointer.list(config, before=before, limit=limit, filter=filter)),
+        )
+        for checkpoint_tuple in checkpoint_tuples:
             yield self._prepare_state_snapshot(
                 checkpoint_tuple.config, checkpoint_tuple
             )
@@ -1452,12 +1510,16 @@ class Pregel(
             },
         )
         # eagerly consume list() to avoid holding up the db cursor
-        for checkpoint_tuple in [
-            c
-            async for c in checkpointer.alist(
-                config, before=before, limit=limit, filter=filter
-            )
-        ]:
+        checkpoint_tuples = await self._amaterialize_saved_checkpoints(
+            checkpointer,
+            [
+                c
+                async for c in checkpointer.alist(
+                    config, before=before, limit=limit, filter=filter
+                )
+            ],
+        )
+        for checkpoint_tuple in checkpoint_tuples:
             yield await self._aprepare_state_snapshot(
                 checkpoint_tuple.config, checkpoint_tuple
             )
@@ -1517,12 +1579,13 @@ class Pregel(
         ) -> RunnableConfig:
             # get last checkpoint
             config = ensure_config(self.config, input_config)
-            saved = checkpointer.get_tuple(config)
+            saved = self._materialize_saved_checkpoint(
+                checkpointer, checkpointer.get_tuple(config)
+            )
             if saved is not None:
                 self._migrate_checkpoint(saved.checkpoint)
-            checkpoint = (
-                copy_checkpoint(saved.checkpoint) if saved else empty_checkpoint()
-            )
+            base_checkpoint = saved.checkpoint if saved else empty_checkpoint()
+            checkpoint = copy_checkpoint(base_checkpoint) if saved else base_checkpoint
             checkpoint_previous_versions = (
                 saved.checkpoint["channel_versions"].copy() if saved else {}
             )
@@ -1963,12 +2026,13 @@ class Pregel(
         ) -> RunnableConfig:
             # get last checkpoint
             config = ensure_config(self.config, input_config)
-            saved = await checkpointer.aget_tuple(config)
+            saved = await self._amaterialize_saved_checkpoint(
+                checkpointer, await checkpointer.aget_tuple(config)
+            )
             if saved is not None:
                 self._migrate_checkpoint(saved.checkpoint)
-            checkpoint = (
-                copy_checkpoint(saved.checkpoint) if saved else empty_checkpoint()
-            )
+            base_checkpoint = saved.checkpoint if saved else empty_checkpoint()
+            checkpoint = copy_checkpoint(base_checkpoint) if saved else base_checkpoint
             checkpoint_previous_versions = (
                 saved.checkpoint["channel_versions"].copy() if saved else {}
             )

libs/langgraph/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "langgraph"
-version = "1.1.10"
+version = "1.1.7a2"
 description = "Building stateful, multi-actor applications with LLMs"
 authors = []
 requires-python = ">=3.10"
@@ -24,10 +24,10 @@ classifiers = [
     'Programming Language :: Python :: 3.13',
 ]
 dependencies = [
-    "langchain-core>=1.3.0,<2",
+    "langchain-core==1.3.0a2",
     "langgraph-checkpoint>=2.1.0,<5.0.0",
     "langgraph-sdk>=0.3.0,<0.4.0",
-    "langgraph-prebuilt>=1.0.12,<1.1.0",
+    "langgraph-prebuilt>=1.0.9,<1.1.0",
     "xxhash>=3.5.0",
     "pydantic>=2.7.4",
 ]

libs/langgraph/tests/test_channels.py

@@ -117,3 +117,609 @@ def test_untracked_value() -> None:
     new_channel = UntrackedValue(dict).from_checkpoint(checkpoint)
     with pytest.raises(EmptyChannelError):
         new_channel.get()
+
+
+def test_delta_channel_basic_two_steps() -> None:
+    from langchain_core.messages import AIMessage, HumanMessage
+    from langgraph.checkpoint.base import DeltaValue
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph.message import add_messages
+
+    ch = DeltaChannel(add_messages).from_checkpoint(MISSING)
+    ch.after_checkpoint(None)
+
+    # Step 1: one message added
+    ch.update([HumanMessage(content="hi", id="h1")])
+    d1 = ch.checkpoint()
+    assert isinstance(d1, DeltaValue)
+    assert len(d1.delta) == 1
+    assert d1.prev_checkpoint_id is None  # first ever step
+    ch.after_checkpoint("v1", checkpoint_id="cid1")
+
+    # Step 2: another message
+    ch.update([AIMessage(content="hello", id="a1")])
+    d2 = ch.checkpoint()
+    assert d2.prev_checkpoint_id == "cid1"
+    assert len(d2.delta) == 1
+    ch.after_checkpoint("v2")
+
+    # Full accumulated value is preserved in memory
+    assert len(ch.get()) == 2
+    assert ch.get()[0].content == "hi"
+    assert ch.get()[1].content == "hello"
+
+
+def test_delta_channel_after_checkpoint_no_op_when_unchanged() -> None:
+    from langchain_core.messages import HumanMessage
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph.message import add_messages
+
+    ch = DeltaChannel(add_messages).from_checkpoint(MISSING)
+    ch.after_checkpoint(None)
+    ch.update([HumanMessage(content="hi", id="h1")])
+    ch.after_checkpoint("v1")
+
+    # Same version: no-op
+    ch.after_checkpoint("v1")
+    assert ch._base_version == "v1"
+    assert ch._pending == []
+
+
+def test_delta_channel_from_checkpoint_chain() -> None:
+    from langchain_core.messages import AIMessage, HumanMessage
+    from langgraph.checkpoint.base import DeltaChainValue
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph.message import add_messages
+
+    spec = DeltaChannel(add_messages)
+    chain = DeltaChainValue(
+        base=None,
+        deltas=[
+            [HumanMessage(content="hi", id="h1")],
+            [AIMessage(content="hello", id="a1")],
+            [HumanMessage(content="bye", id="h2")],
+        ],
+    )
+    ch = spec.from_checkpoint(chain)
+    msgs = ch.get()
+    assert len(msgs) == 3
+    assert msgs[0].content == "hi"
+    assert msgs[1].content == "hello"
+    assert msgs[2].content == "bye"
+
+
+def test_delta_channel_from_checkpoint_backwards_compat() -> None:
+    from langchain_core.messages import HumanMessage
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph.message import add_messages
+
+    # Old BinaryOperatorAggregate checkpoint: plain list
+    spec = DeltaChannel(add_messages)
+    old_value = [HumanMessage(content="old", id="h1")]
+    ch = spec.from_checkpoint(old_value)
+    assert ch.get() == old_value
+
+
+def test_delta_channel_overwrite_resets_chain() -> None:
+    from langchain_core.messages import HumanMessage
+    from langgraph.checkpoint.base import DeltaChainValue, DeltaValue
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph.message import add_messages
+    from langgraph.types import Overwrite
+
+    ch = DeltaChannel(add_messages).from_checkpoint(MISSING)
+    ch.after_checkpoint(None)
+    ch.update([HumanMessage(content="old", id="h1")])
+    ch.after_checkpoint("v1")
+
+    # Overwrite should create a root blob (prev_checkpoint_id=None)
+    ch.update([Overwrite([HumanMessage(content="new", id="h2")])])
+    d = ch.checkpoint()
+    assert isinstance(d, DeltaValue)
+    assert d.prev_checkpoint_id is None  # chain root
+    assert len(d.delta) == 1
+    assert len(d.delta[0]) == 1
+    assert d.delta[0][0].content == "new"
+
+    spec = DeltaChannel(add_messages)
+    replayed = spec.from_checkpoint(DeltaChainValue(base=None, deltas=[d.delta]))
+    assert replayed.get()[0].content == "new"
+
+
+def test_delta_channel_assembly_fallback_via_get_tuple() -> None:
+    """Materialization falls back to get_tuple for savers without get_channel_blob."""
+    from langgraph.checkpoint.base import (
+        BaseCheckpointSaver,
+        CheckpointHydrationPlan,
+        CheckpointTuple,
+        DeltaChainValue,
+        DeltaValue,
+        IncrementalChannelSpec,
+        empty_checkpoint,
+    )
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph.message import add_messages
+
+    msg1 = {"type": "human", "content": "hello"}
+    msg2 = {"type": "ai", "content": "world"}
+
+    cp1 = empty_checkpoint()
+    cp1["id"] = "cp1"
+    cp1["channel_values"]["messages"] = [msg1]
+
+    cp2 = empty_checkpoint()
+    cp2["id"] = "cp2"
+    cp2["channel_values"]["messages"] = DeltaValue(
+        delta=[msg2], prev_checkpoint_id="cp1"
+    )
+
+    class TestSaver(BaseCheckpointSaver[str]):
+        def get_tuple(self, config):
+            return CheckpointTuple(
+                config={
+                    "configurable": {
+                        "thread_id": "t1",
+                        "checkpoint_ns": "",
+                        "checkpoint_id": "cp1",
+                    }
+                },
+                checkpoint=cp1,
+                metadata={},
+                parent_config=None,
+                pending_writes=[],
+            )
+
+        def list(self, config, *, filter=None, before=None, limit=None):
+            raise NotImplementedError
+
+        def put(self, config, checkpoint, metadata, new_versions):
+            raise NotImplementedError
+
+    saver = TestSaver()
+
+    config = {"configurable": {"thread_id": "t1", "checkpoint_ns": ""}}
+    materialized = saver.materialize_checkpoint(
+        config,
+        cp2,
+        CheckpointHydrationPlan(
+            channels=(IncrementalChannelSpec(name="messages", kind="delta"),)
+        ),
+    )
+
+    chain = materialized["channel_values"]["messages"]
+    assert isinstance(chain, DeltaChainValue)
+    assert chain.base == [msg1]
+    assert chain.deltas == [[msg2]]
+
+    from langchain_core.messages import AIMessage, HumanMessage
+
+    spec = DeltaChannel(add_messages)
+    ch = spec.from_checkpoint(chain)
+    result = ch.get()
+    assert len(result) == 2
+    assert isinstance(result[0], HumanMessage) and result[0].content == "hello"
+    assert isinstance(result[1], AIMessage) and result[1].content == "world"
+
+
+def test_delta_channel_remove_message_delta_and_replay() -> None:
+    """RemoveMessage stored in a delta must round-trip correctly through the chain."""
+    from langchain_core.messages import AIMessage, HumanMessage, RemoveMessage
+    from langgraph.checkpoint.base import DeltaChainValue, DeltaValue
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph.message import add_messages
+
+    spec = DeltaChannel(add_messages)
+    ch = spec.from_checkpoint(MISSING)
+    ch.after_checkpoint(None)
+
+    # Step 1: add two messages
+    ch.update([HumanMessage(content="hi", id="h1")])
+    ch.update([AIMessage(content="hello", id="a1")])
+    d1 = ch.checkpoint()
+    assert isinstance(d1, DeltaValue)
+    ch.after_checkpoint("v1", checkpoint_id="cid1")
+    assert ch.get() == [
+        HumanMessage(content="hi", id="h1"),
+        AIMessage(content="hello", id="a1"),
+    ]
+
+    # Step 2: remove the AI message
+    ch.update([RemoveMessage(id="a1")])
+    d2 = ch.checkpoint()
+    assert isinstance(d2, DeltaValue)
+    assert d2.prev_checkpoint_id == "cid1"
+    assert any(isinstance(w, RemoveMessage) for w in d2.delta)
+    ch.after_checkpoint("v2", checkpoint_id="cid2")
+    assert ch.get() == [HumanMessage(content="hi", id="h1")]
+
+    # Replay the full chain from scratch — must reproduce the post-remove state
+    chain = DeltaChainValue(base=None, deltas=[d1.delta, d2.delta])
+    ch2 = spec.from_checkpoint(chain)
+    assert ch2.get() == [HumanMessage(content="hi", id="h1")]
+
+
+def test_delta_channel_update_by_id_delta_and_replay() -> None:
+    """Updating a message by ID stored in a delta must round-trip correctly."""
+    from langchain_core.messages import HumanMessage
+    from langgraph.checkpoint.base import DeltaChainValue, DeltaValue
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph.message import add_messages
+
+    spec = DeltaChannel(add_messages)
+    ch = spec.from_checkpoint(MISSING)
+    ch.after_checkpoint(None)
+
+    # Step 1: add a message
+    ch.update([HumanMessage(content="original", id="h1")])
+    d1 = ch.checkpoint()
+    assert isinstance(d1, DeltaValue)
+    ch.after_checkpoint("v1", checkpoint_id="cid1")
+
+    # Step 2: update the same message by ID
+    ch.update([HumanMessage(content="updated", id="h1")])
+    d2 = ch.checkpoint()
+    assert isinstance(d2, DeltaValue)
+    assert d2.prev_checkpoint_id == "cid1"
+    ch.after_checkpoint("v2", checkpoint_id="cid2")
+    assert ch.get() == [HumanMessage(content="updated", id="h1")]
+
+    # Replay the full chain — must produce the updated message, not the original
+    chain = DeltaChainValue(base=None, deltas=[d1.delta, d2.delta])
+    ch2 = spec.from_checkpoint(chain)
+    assert len(ch2.get()) == 1
+    assert ch2.get()[0].content == "updated"
+
+
+def test_delta_channel_snapshot_every_emits_plain_list() -> None:
+    """snapshot_every=N causes a plain-list snapshot after N steps; next deltas chain to it."""
+    from langchain_core.messages import HumanMessage
+    from langgraph.checkpoint.base import DeltaValue
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph.message import add_messages
+
+    SNAP = 3
+    spec = DeltaChannel(add_messages, snapshot_every=SNAP)
+    ch = spec.from_checkpoint(MISSING)
+    # First after_checkpoint anchors _base_version without counting a step.
+    ch.after_checkpoint("v0", checkpoint_id="cid0")
+
+    # Steps 1..SNAP: each should stay as DeltaValue; counter increments each step.
+    for i in range(1, SNAP + 1):
+        ch.update([HumanMessage(content=f"m{i}", id=f"h{i}")])
+        ckpt = ch.checkpoint()
+        assert isinstance(ckpt, DeltaValue), f"expected DeltaValue at step {i}"
+        ch.after_checkpoint(f"v{i}", checkpoint_id=f"cid{i}")
+
+    # Step SNAP+1: _steps_since_snapshot == SNAP → snapshot fires
+    ch.update([HumanMessage(content="snap", id="hsnap")])
+    snap = ch.checkpoint()
+    assert isinstance(snap, list), "expected plain-list snapshot at snapshot_every step"
+    assert len(snap) == SNAP + 1
+
+    # After snapshot, counter resets — next step is DeltaValue again
+    ch.after_checkpoint("vsnap", checkpoint_id="cidsnap")
+    ch.update([HumanMessage(content="post", id="hpost")])
+    post = ch.checkpoint()
+    assert isinstance(post, DeltaValue)
+    assert post.prev_checkpoint_id == "cidsnap"
+
+
+def test_delta_channel_snapshot_every_end_to_end() -> None:
+    """Graph with snapshot_every: get_state returns correct accumulated value after snapshot."""
+    from typing import Annotated
+
+    from langchain_core.messages import AIMessage, HumanMessage
+    from langgraph.checkpoint.memory import InMemorySaver
+    from typing_extensions import TypedDict
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph import START, StateGraph
+    from langgraph.graph.message import add_messages
+
+    class State(TypedDict):
+        messages: Annotated[list, DeltaChannel(add_messages, snapshot_every=2)]
+
+    counter = {"n": 0}
+
+    def respond(state: State) -> dict:
+        counter["n"] += 1
+        return {
+            "messages": [
+                AIMessage(content=f"ai-{counter['n']}", id=f"ai-{counter['n']}")
+            ]
+        }
+
+    builder = StateGraph(State)
+    builder.add_node("respond", respond)
+    builder.add_edge(START, "respond")
+    graph = builder.compile(checkpointer=InMemorySaver())
+    config = {"configurable": {"thread_id": "snap-test"}}
+
+    # Run 5 turns — snapshot fires after 2 steps, then again after 2 more
+    for i in range(5):
+        graph.invoke({"messages": [HumanMessage(content=f"h{i}", id=f"h{i}")]}, config)
+
+    state = graph.get_state(config)
+    msgs = state.values["messages"]
+    # 5 human + 5 AI = 10 total
+    assert len(msgs) == 10, f"expected 10 messages, got {len(msgs)}: {msgs}"
+
+
+def test_delta_channel_dict_reducer_overwrite_preserves_mapping() -> None:
+    """Overwrite should preserve dict values instead of coercing them to keys."""
+    from langgraph.checkpoint.base import DeltaChainValue, DeltaValue
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.types import Overwrite
+
+    def merge_dicts(left: dict, right: dict) -> dict:
+        return {**left, **right}
+
+    ch = DeltaChannel(merge_dicts, dict).from_checkpoint(MISSING)
+    ch.after_checkpoint(None)
+    ch.update([{"a": 1}])
+    ch.after_checkpoint("v1", checkpoint_id="cid1")
+
+    ch.update([Overwrite({"b": 2})])
+    d = ch.checkpoint()
+    assert isinstance(d, DeltaValue)
+    assert d.prev_checkpoint_id is None
+    assert d.delta == [{"b": 2}]
+    assert ch.get() == {"b": 2}
+
+    spec = DeltaChannel(merge_dicts, dict)
+    replayed = spec.from_checkpoint(DeltaChainValue(base=None, deltas=[d.delta]))
+    assert replayed.get() == {"b": 2}
+
+
+def test_delta_channel_dict_snapshot_every_round_trip() -> None:
+    """Full snapshots should preserve non-list reducers across reload."""
+    from langgraph.checkpoint.base import DeltaValue
+
+    from langgraph.channels.delta import DeltaChannel
+
+    def merge_dicts(left: dict, right: dict) -> dict:
+        return {**left, **right}
+
+    ch = DeltaChannel(merge_dicts, dict, snapshot_every=1).from_checkpoint(MISSING)
+    ch.after_checkpoint("v0", checkpoint_id="cid0")
+
+    ch.update([{"a": 1}])
+    first = ch.checkpoint()
+    assert isinstance(first, DeltaValue)
+    ch.after_checkpoint("v1", checkpoint_id="cid1")
+
+    ch.update([{"b": 2}])
+    snap = ch.checkpoint()
+    assert isinstance(snap, dict)
+    assert snap == {"a": 1, "b": 2}
+
+    rehydrated = DeltaChannel(merge_dicts, dict, snapshot_every=1).from_checkpoint(snap)
+    assert rehydrated.get() == {"a": 1, "b": 2}
+
+
+def test_delta_channel_assembly_fast_path_returns_delta_value() -> None:
+    """get_channel_blob returning a DeltaValue continues chain traversal (fast-path)."""
+    from langgraph.checkpoint.base import (
+        BaseCheckpointSaver,
+        CheckpointHydrationPlan,
+        DeltaChainValue,
+        DeltaValue,
+        IncrementalChannelSpec,
+        empty_checkpoint,
+    )
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph.message import add_messages
+
+    msg1 = {"type": "human", "content": "one"}
+    msg2 = {"type": "ai", "content": "two"}
+    msg3 = {"type": "human", "content": "three"}
+
+    # cp3 → cp2 (DeltaValue) → cp1 (base list)
+    dv_cp2 = DeltaValue(delta=[msg2], prev_checkpoint_id="cp1")
+    cp3 = empty_checkpoint()
+    cp3["id"] = "cp3"
+    cp3["channel_values"]["messages"] = DeltaValue(
+        delta=[msg3], prev_checkpoint_id="cp2"
+    )
+
+    class TestSaver(BaseCheckpointSaver[str]):
+        def get_tuple(self, config):
+            raise NotImplementedError
+
+        def list(self, config, *, filter=None, before=None, limit=None):
+            raise NotImplementedError
+
+        def put(self, config, checkpoint, metadata, new_versions):
+            raise NotImplementedError
+
+        def get_channel_blob(self, thread_id, checkpoint_ns, checkpoint_id, channel):
+            if checkpoint_id == "cp2":
+                return dv_cp2
+            if checkpoint_id == "cp1":
+                return [msg1]
+            return NotImplemented
+
+    saver = TestSaver()
+
+    config = {"configurable": {"thread_id": "t1", "checkpoint_ns": ""}}
+    materialized = saver.materialize_checkpoint(
+        config,
+        cp3,
+        CheckpointHydrationPlan(
+            channels=(IncrementalChannelSpec(name="messages", kind="delta"),)
+        ),
+    )
+
+    chain = materialized["channel_values"]["messages"]
+    assert isinstance(chain, DeltaChainValue)
+    assert chain.base == [msg1]
+    assert chain.deltas == [[msg2], [msg3]]
+
+    spec = DeltaChannel(add_messages)
+    ch = spec.from_checkpoint(chain)
+    # add_messages converts dicts to message objects; check by type and content
+
+    result = ch.get()
+    assert len(result) == 3
+    assert result[0].content == "one"
+    assert result[1].content == "two"
+    assert result[2].content == "three"
+
+
+def test_delta_channel_dict_reducer_fresh_channel() -> None:
+    """DeltaChannel with a dict reducer starts as empty dict on MISSING checkpoint."""
+    from langgraph.channels.delta import DeltaChannel
+
+    def merge_dicts(left: dict, right: dict) -> dict:
+        return {**left, **right}
+
+    ch = DeltaChannel(merge_dicts, dict).from_checkpoint(MISSING)
+    # Should be available (not raise EmptyChannelError) and start empty
+    assert ch.is_available()
+    assert ch.get() == {}
+
+
+def test_delta_channel_dict_reducer_basic_updates() -> None:
+    """DeltaChannel with a dict reducer accumulates key/value pairs across steps."""
+    from langgraph.checkpoint.base import DeltaValue
+
+    from langgraph.channels.delta import DeltaChannel
+
+    def merge_dicts(left: dict, right: dict) -> dict:
+        return {**left, **right}
+
+    ch = DeltaChannel(merge_dicts, dict).from_checkpoint(MISSING)
+    ch.after_checkpoint(None)
+
+    ch.update([{"a": 1}])
+    d1 = ch.checkpoint()
+    assert isinstance(d1, DeltaValue)
+    assert d1.delta == [{"a": 1}]
+    ch.after_checkpoint("v1", checkpoint_id="cid1")
+
+    ch.update([{"b": 2}])
+    d2 = ch.checkpoint()
+    assert d2.delta == [{"b": 2}]
+    assert d2.prev_checkpoint_id == "cid1"
+    ch.after_checkpoint("v2")
+
+    assert ch.get() == {"a": 1, "b": 2}
+
+
+def test_delta_channel_dict_reducer_chain_reconstruction() -> None:
+    """DeltaChainValue replays correctly through a dict merge reducer."""
+    from langgraph.checkpoint.base import DeltaChainValue
+
+    from langgraph.channels.delta import DeltaChannel
+
+    def merge_dicts(left: dict, right: dict) -> dict:
+        return {**left, **right}
+
+    spec = DeltaChannel(merge_dicts, dict)
+    chain = DeltaChainValue(
+        base={"a": 1},
+        deltas=[[{"b": 2}], [{"c": 3}]],
+    )
+    ch = spec.from_checkpoint(chain)
+    assert ch.get() == {"a": 1, "b": 2, "c": 3}
+    assert ch._steps_since_snapshot == 2
+
+
+def test_delta_channel_dict_reducer_with_deletions() -> None:
+    """Dict reducer that treats None values as deletions works end-to-end (deepagents pattern)."""
+    from langgraph.checkpoint.base import DeltaChainValue
+
+    from langgraph.channels.delta import DeltaChannel
+
+    def merge_files(left: dict | None, right: dict) -> dict:
+        if left is None:
+            return {k: v for k, v in right.items() if v is not None}
+        result = {**left}
+        for k, v in right.items():
+            if v is None:
+                result.pop(k, None)
+            else:
+                result[k] = v
+        return result
+
+    ch = DeltaChannel(merge_files, dict).from_checkpoint(MISSING)
+    ch.after_checkpoint(None)
+
+    ch.update([{"file1.py": "content1", "file2.py": "content2"}])
+    ch.after_checkpoint("v1", checkpoint_id="cid1")
+
+    # Delete file1, add file3
+    ch.update([{"file1.py": None, "file3.py": "content3"}])
+    ch.after_checkpoint("v2", checkpoint_id="cid2")
+
+    assert ch.get() == {"file2.py": "content2", "file3.py": "content3"}
+
+    # Confirm chain reconstruction produces the same result
+    chain = DeltaChainValue(
+        base={},
+        deltas=[
+            [{"file1.py": "content1", "file2.py": "content2"}],
+            [{"file1.py": None, "file3.py": "content3"}],
+        ],
+    )
+    spec = DeltaChannel(merge_files, dict)
+    ch2 = spec.from_checkpoint(chain)
+    assert ch2.get() == {"file2.py": "content2", "file3.py": "content3"}
+
+
+def test_delta_channel_assembly_broken_chain_logs_warning() -> None:
+    """If a prev_checkpoint_id points to a missing checkpoint, log a warning and use partial chain."""
+    from langgraph.checkpoint.base import (
+        BaseCheckpointSaver,
+        CheckpointHydrationPlan,
+        DeltaValue,
+        IncrementalChannelSpec,
+        empty_checkpoint,
+    )
+
+    cp = empty_checkpoint()
+    cp["id"] = "cp2"
+    cp["channel_values"]["messages"] = DeltaValue(
+        delta=["msg2"], prev_checkpoint_id="cp-missing"
+    )
+
+    class TestSaver(BaseCheckpointSaver[str]):
+        def get_tuple(self, config):
+            return None
+
+        def list(self, config, *, filter=None, before=None, limit=None):
+            raise NotImplementedError
+
+        def put(self, config, checkpoint, metadata, new_versions):
+            raise NotImplementedError
+
+    saver = TestSaver()
+
+    config = {"configurable": {"thread_id": "t1", "checkpoint_ns": ""}}
+
+    materialized = saver.materialize_checkpoint(
+        config,
+        cp,
+        CheckpointHydrationPlan(
+            channels=(IncrementalChannelSpec(name="messages", kind="delta"),)
+        ),
+    )
+
+    # Should still assemble — with partial chain (just the current delta, base=None)
+    from langgraph.checkpoint.base import DeltaChainValue
+
+    chain = materialized["channel_values"]["messages"]
+    assert isinstance(chain, DeltaChainValue)
+    assert chain.base is None
+    assert chain.deltas == [["msg2"]]

libs/langgraph/tests/test_delta_channel_benchmark.py

@@ -0,0 +1,356 @@
+"""Benchmark: DeltaChannel vs BinaryOperatorAggregate storage and time.
+
+Run directly:  python tests/test_delta_channel_benchmark.py
+Run via pytest: pytest tests/test_delta_channel_benchmark.py -s
+
+Simulates realistic multi-turn conversations with paragraph-length messages
+(~100 tokens each) scaling up to 1M-token-equivalent histories.
+
+Token estimates: 1 token ≈ 4 chars; each turn ≈ 200 tokens (human + AI).
+A 1M-token conversation ≈ 5,000 turns of realistic messages.
+"""
+
+from __future__ import annotations
+
+import sys
+import time
+from typing import Annotated, Any
+
+from langchain_core.messages import AIMessage, HumanMessage
+from langgraph.checkpoint.memory import MemorySaver
+from typing_extensions import TypedDict
+
+from langgraph.channels.delta import DeltaChannel
+from langgraph.graph import END, StateGraph
+from langgraph.graph.message import add_messages
+
+try:
+    from langgraph.checkpoint.sqlite import SqliteSaver
+
+    _SQLITE_AVAILABLE = True
+except ImportError:
+    _SQLITE_AVAILABLE = False
+
+SNAPSHOT_EVERY = 50
+
+# ---------------------------------------------------------------------------
+# Realistic message payload (~100 tokens / ~400 chars each)
+# ---------------------------------------------------------------------------
+
+_HUMAN_TEMPLATE = (
+    "I need help understanding the implications of {topic} on our system architecture. "
+    "Specifically, I'm concerned about how this interacts with our existing {concern} "
+    "and whether we need to refactor the {component} layer before proceeding."
+)
+
+_AI_TEMPLATE = (
+    "Great question about {topic}. The key insight here is that {concern} introduces "
+    "a subtle ordering dependency that most teams overlook until they hit it in production. "
+    "For your {component} layer specifically, I'd recommend starting with a careful audit "
+    "of the interface boundaries before making any structural changes. This will give you "
+    "a clear picture of the blast radius and let you sequence the migration safely."
+)
+
+_TOPICS = [
+    "distributed tracing",
+    "eventual consistency",
+    "schema migration",
+    "backpressure handling",
+    "idempotency guarantees",
+    "cache invalidation",
+    "connection pooling",
+    "rate limiting",
+    "circuit breaking",
+    "observability pipelines",
+]
+
+_CONCERNS = [
+    "concurrency model",
+    "retry semantics",
+    "state management",
+    "error propagation",
+    "latency budget",
+]
+
+_COMPONENTS = [
+    "persistence",
+    "routing",
+    "ingestion",
+    "aggregation",
+    "serialization",
+]
+
+
+def _human_content(i: int) -> str:
+    return _HUMAN_TEMPLATE.format(
+        topic=_TOPICS[i % len(_TOPICS)],
+        concern=_CONCERNS[i % len(_CONCERNS)],
+        component=_COMPONENTS[i % len(_COMPONENTS)],
+    )
+
+
+def _ai_content(i: int) -> str:
+    return _AI_TEMPLATE.format(
+        topic=_TOPICS[i % len(_TOPICS)],
+        concern=_CONCERNS[i % len(_CONCERNS)],
+        component=_COMPONENTS[i % len(_COMPONENTS)],
+    )
+
+
+# ---------------------------------------------------------------------------
+# State definitions
+# ---------------------------------------------------------------------------
+
+
+class BinaryState(TypedDict):
+    messages: Annotated[list, add_messages]
+
+
+class DeltaState(TypedDict):
+    messages: Annotated[list, DeltaChannel(add_messages)]
+
+
+class DeltaSnapshotState(TypedDict):
+    messages: Annotated[list, DeltaChannel(add_messages, snapshot_every=SNAPSHOT_EVERY)]
+
+
+# ---------------------------------------------------------------------------
+# Graph factory
+# ---------------------------------------------------------------------------
+
+
+def _make_graph(state_cls: type, checkpointer: Any = None) -> Any:
+    def human_node(state: Any) -> dict:
+        return {}
+
+    def ai_node(state: Any) -> dict:
+        i = len(state["messages"]) // 2
+        return {"messages": [AIMessage(content=_ai_content(i), id=f"a{i}")]}
+
+    g = StateGraph(state_cls)
+    g.add_node("human", human_node)
+    g.add_node("ai", ai_node)
+    g.add_edge("human", "ai")
+    g.add_edge("ai", END)
+    g.set_entry_point("human")
+    return g.compile(checkpointer=checkpointer or MemorySaver())
+
+
+# ---------------------------------------------------------------------------
+# Measurement helpers
+# ---------------------------------------------------------------------------
+
+
+def _total_blob_bytes(saver: MemorySaver) -> int:
+    total = 0
+    for (_, _, _, _), (type_tag, blob) in saver.blobs.items():
+        if blob is not None:
+            total += len(blob)
+    return total
+
+
+def _run_turns(
+    n_turns: int,
+    state_cls: type,
+    checkpointer: Any = None,
+) -> tuple[float, float, int]:
+    """Run n_turns conversation turns.
+
+    Returns (write_elapsed_s, read_elapsed_s, total_blob_bytes).
+    blob_bytes is -1 for savers without in-memory blob stores (e.g. SQLite).
+    Read latency is measured as the time to invoke the graph with no new
+    messages after the full history is built — this forces state rehydration.
+    """
+    graph = _make_graph(state_cls, checkpointer)
+    config = {"configurable": {"thread_id": "bench"}}
+
+    t0 = time.perf_counter()
+    for i in range(n_turns):
+        graph.invoke(
+            {"messages": [HumanMessage(content=_human_content(i), id=f"h{i}")]},
+            config,
+        )
+    write_elapsed = time.perf_counter() - t0
+
+    # Measure read/rehydration: get_state forces the channel to rebuild
+    t1 = time.perf_counter()
+    for _ in range(5):
+        graph.get_state(config)
+    read_elapsed = (time.perf_counter() - t1) / 5
+
+    if isinstance(graph.checkpointer, MemorySaver):
+        blob_bytes = _total_blob_bytes(graph.checkpointer)
+    else:
+        blob_bytes = -1
+    return write_elapsed, read_elapsed, blob_bytes
+
+
+def _fmt_bytes(n: int) -> str:
+    if n >= 1_000_000:
+        return f"{n / 1_000_000:.1f} MB"
+    if n >= 1_000:
+        return f"{n / 1_000:.1f} KB"
+    return f"{n} B"
+
+
+def _approx_tokens(n_turns: int) -> str:
+    # ~100 tokens human + ~100 tokens AI per turn
+    tokens = n_turns * 200
+    if tokens >= 1_000_000:
+        return f"~{tokens / 1_000_000:.1f}M tok"
+    if tokens >= 1_000:
+        return f"~{tokens / 1_000:.0f}K tok"
+    return f"~{tokens} tok"
+
+
+# ---------------------------------------------------------------------------
+# Benchmark matrix
+# ---------------------------------------------------------------------------
+
+# Turn counts chosen to span from a short session to a long-running agent conversation.
+# Storage and time complexity differences are clearly visible by 500 turns.
+# Extrapolation: 5,000 turns × ~200 tokens/turn ≈ 1M tokens (Claude's full context window).
+TURN_COUNTS = [50, 100, 200, 500]
+
+
+def _checkpointer_factories() -> list[tuple[str, Any]]:
+    """Return (label, context_manager_or_none) pairs for available checkpointers."""
+    factories: list[tuple[str, Any]] = [("InMemory", None)]
+    if _SQLITE_AVAILABLE:
+        import tempfile
+
+        factories.append(("SQLite", tempfile.NamedTemporaryFile(suffix=".db")))
+    return factories
+
+
+def run_benchmark() -> None:
+    print()
+    print(
+        "DeltaChannel vs add_messages (BinaryOperatorAggregate) — checkpoint storage & latency"
+    )
+    print("Simulating realistic multi-turn conversations up to ~1M-token histories")
+    print("(5,000 turns × ~200 tokens/turn ≈ 1M tokens — Claude's full context window)")
+    print()
+
+    checkpointers: list[tuple[str, Any]] = [("InMemory (fast-path)", None)]
+    if _SQLITE_AVAILABLE:
+        checkpointers.append(("SQLite (get_tuple fallback)", "sqlite"))
+
+    for cp_label, cp_hint in checkpointers:
+        print(f"--- Checkpointer: {cp_label} ---")
+        _run_benchmark_for_checkpointer(cp_hint)
+
+
+def _run_benchmark_for_checkpointer(cp_hint: Any) -> None:
+    import contextlib
+    import tempfile
+
+    @contextlib.contextmanager
+    def _make_saver():
+        if cp_hint is None:
+            yield None
+        else:
+            with tempfile.NamedTemporaryFile(suffix=".db") as f:
+                with SqliteSaver.from_conn_string(f.name) as saver:
+                    yield saver
+
+    W = 120
+    print("=" * W)
+    header = (
+        f"{'turns':>6}  {'ctx size':>10}  "
+        f"{'add_msgs (bytes)':>18}  {'delta (bytes)':>15}  {'delta+snap (bytes)':>18}  "
+        f"{'storage saved':>14}  "
+        f"{'read: add_msgs':>14}  {'read: delta+snap':>16}"
+    )
+    print(header)
+    print("-" * W)
+
+    results = []
+    for turns in TURN_COUNTS:
+        with _make_saver() as saver:
+            b_wt, b_rt, b_bytes = _run_turns(turns, BinaryState, saver)
+        with _make_saver() as saver:
+            d_wt, d_rt, d_bytes = _run_turns(turns, DeltaState, saver)
+        with _make_saver() as saver:
+            s_wt, s_rt, s_bytes = _run_turns(turns, DeltaSnapshotState, saver)
+
+        # For non-InMemory savers, blob_bytes are unavailable (-1); use read times only
+        if b_bytes < 0 or s_bytes < 0:
+            b_bytes_str = "n/a"
+            d_bytes_str = "n/a"
+            s_bytes_str = "n/a"
+            storage_ratio_str = "n/a"
+        else:
+            storage_ratio = b_bytes / s_bytes if s_bytes else float("inf")
+            b_bytes_str = _fmt_bytes(b_bytes)
+            d_bytes_str = _fmt_bytes(d_bytes)
+            s_bytes_str = _fmt_bytes(s_bytes)
+            storage_ratio_str = f"{storage_ratio:.1f}x"
+            results.append((turns, b_bytes, s_bytes, b_rt, s_rt, storage_ratio))
+
+        print(
+            f"{turns:>6}  {_approx_tokens(turns):>10}  "
+            f"{b_bytes_str:>18}  {d_bytes_str:>15}  {s_bytes_str:>18}  "
+            f"{storage_ratio_str:>14}  "
+            f"{b_rt * 1000:>12.1f}ms  {s_rt * 1000:>14.1f}ms"
+        )
+
+    print("=" * W)
+    print()
+
+    if results:
+        best = results[-1]
+        turns, b_bytes, s_bytes, b_rt, s_rt, ratio = best
+        print(f"Key findings at max scale ({turns} turns):")
+        print(
+            f"  Storage:  {_fmt_bytes(b_bytes)} (add_messages)  →  {_fmt_bytes(s_bytes)} (DeltaChannel+snapshot) — {ratio:.0f}x reduction"
+        )
+        print(
+            f"  Read latency: {b_rt * 1000:.1f}ms (add_messages)  vs  {s_rt * 1000:.1f}ms (DeltaChannel+snapshot)"
+        )
+        print()
+    print("Legend:")
+    print(
+        "  add_msgs      = Annotated[list, add_messages]  — current default, O(N²) storage"
+    )
+    print(
+        "  delta         = DeltaChannel(add_messages)     — O(N) storage, unbounded chain at read"
+    )
+    print(
+        f"  delta+snap    = DeltaChannel(add_messages, snapshot_every={SNAPSHOT_EVERY})  — O(N) storage, O(1) read depth"
+    )
+    print()
+
+
+# ---------------------------------------------------------------------------
+# Pytest entry point
+# ---------------------------------------------------------------------------
+
+
+def test_delta_channel_benchmark(capsys: Any) -> None:
+    """Storage grows O(N²) for add_messages, O(N) for DeltaChannel."""
+    with capsys.disabled():
+        run_benchmark()
+
+    # Correctness assertion: DeltaChannel must use less storage at scale.
+    for turns in [100, 200]:
+        _, _, b_bytes = _run_turns(turns, BinaryState)
+        _, _, d_bytes = _run_turns(turns, DeltaState)
+        _, _, s_bytes = _run_turns(turns, DeltaSnapshotState)
+        assert d_bytes < b_bytes, (
+            f"DeltaChannel should use less storage at {turns} turns, "
+            f"got delta={d_bytes} binary={b_bytes}"
+        )
+        assert s_bytes < b_bytes, (
+            f"DeltaChannel+snapshot should use less storage at {turns} turns, "
+            f"got snapshot={s_bytes} binary={b_bytes}"
+        )
+
+
+# ---------------------------------------------------------------------------
+# Script entry point
+# ---------------------------------------------------------------------------
+
+if __name__ == "__main__":
+    run_benchmark()
+    sys.exit(0)

libs/langgraph/tests/test_graph_callbacks.py

@@ -275,70 +275,3 @@ def test_graph_callbacks_accept_base_callback_manager() -> None:
 
     assert "__interrupt__" in first
     assert len(graph_handler.interrupt_events) == 1
-
-
-def test_non_graph_handler_via_add_handler_does_not_crash() -> None:
-    """Non-GraphCallbackHandler added via add_handler should not raise.
-
-    Libraries like opentelemetry-instrumentation-langchain monkey-patch
-    BaseCallbackManager.__init__ and inject handlers via add_handler().
-    These handlers inherit from BaseCallbackHandler, not
-    GraphCallbackHandler. They must be silently accepted — graph lifecycle
-    events will simply not be dispatched to them.
-    """
-    from langgraph.callbacks import _GraphCallbackManager
-
-    manager = _GraphCallbackManager()
-    plain_handler = _LangChainCustomEventHandler()
-
-    manager.add_handler(plain_handler, inherit=True)
-    assert plain_handler in manager.handlers
-
-
-def test_non_graph_handler_does_not_receive_lifecycle_events() -> None:
-    """Non-GraphCallbackHandler added alongside a GraphCallbackHandler
-    should not interfere with lifecycle event dispatch."""
-    graph = _build_interrupt_graph()
-    graph_handler = _GraphEventHandler()
-    plain_handler = _LangChainCustomEventHandler()
-
-    config = {
-        "configurable": {"thread_id": "graph-callback-mixed-handlers"},
-        "callbacks": [plain_handler, graph_handler],
-    }
-
-    first = graph.invoke({"answer": None}, config)
-    assert "__interrupt__" in first
-
-    assert len(graph_handler.interrupt_events) == 1
-    assert plain_handler.events == []
-
-    resumed = graph.invoke(Command(resume="done"), config)
-    assert resumed == {"answer": "done"}
-    assert len(graph_handler.resume_events) == 1
-    assert plain_handler.events == []
-
-
-@pytest.mark.anyio
-@NEEDS_CONTEXTVARS
-async def test_non_graph_handler_does_not_receive_lifecycle_events_async() -> None:
-    """Async variant: non-GraphCallbackHandler should not interfere."""
-    graph = _build_interrupt_graph()
-    graph_handler = _GraphEventHandler()
-    plain_handler = _LangChainCustomEventHandler()
-
-    config = {
-        "configurable": {"thread_id": "graph-callback-mixed-handlers-async"},
-        "callbacks": [plain_handler, graph_handler],
-    }
-
-    first = await graph.ainvoke({"answer": None}, config)
-    assert "__interrupt__" in first
-
-    assert len(graph_handler.interrupt_events) == 1
-    assert plain_handler.events == []
-
-    resumed = await graph.ainvoke(Command(resume="done"), config)
-    assert resumed == {"answer": "done"}
-    assert len(graph_handler.resume_events) == 1
-    assert plain_handler.events == []

libs/langgraph/tests/test_pregel.py

@@ -9400,3 +9400,190 @@ def test_fork_does_not_apply_pending_writes(
 
     # Should be: 1 (input) + 20 (forked node_a) + 100 (node_b) = 121
     assert result == {"value": 121}
+
+
+async def test_delta_channel_end_to_end_inmemory() -> None:
+    """Full graph run: DeltaChannel accumulates correctly across multiple turns."""
+    from langchain_core.messages import AIMessage, HumanMessage
+    from langgraph.checkpoint.memory import InMemorySaver
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph import START, StateGraph
+    from langgraph.graph.message import add_messages
+
+    class State(TypedDict):
+        messages: Annotated[list, DeltaChannel(add_messages)]
+
+    def respond(state: State) -> dict:
+        n = len(state["messages"])
+        return {"messages": [AIMessage(content=f"reply-{n}", id=f"ai-{n}")]}
+
+    builder = StateGraph(State)
+    builder.add_node("respond", respond)
+    builder.add_edge(START, "respond")
+    graph = builder.compile(checkpointer=InMemorySaver())
+
+    config = {"configurable": {"thread_id": "diff-test-1"}}
+
+    # Turn 1
+    graph.invoke({"messages": [HumanMessage(content="hello", id="h1")]}, config)
+    # Turn 2
+    graph.invoke({"messages": [HumanMessage(content="world", id="h2")]}, config)
+    # Turn 3
+    graph.invoke({"messages": [HumanMessage(content="bye", id="h3")]}, config)
+
+    state = graph.get_state(config)
+    msgs = state.values["messages"]
+    # 3 human + 3 AI = 6 total
+    assert len(msgs) == 6, f"expected 6 messages, got {len(msgs)}: {msgs}"
+    assert msgs[0].content == "hello"
+    assert msgs[2].content == "world"
+    assert msgs[4].content == "bye"
+    assert msgs[1].content == "reply-1"
+    assert msgs[3].content == "reply-3"
+    assert msgs[5].content == "reply-5"
+
+
+async def test_delta_channel_time_travel() -> None:
+    """Time-travel back to turn-1 checkpoint and resume; continuation must not include turn-2 deltas."""
+    from langchain_core.messages import AIMessage, HumanMessage
+    from langgraph.checkpoint.memory import InMemorySaver
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph import START, StateGraph
+    from langgraph.graph.message import add_messages
+
+    class State(TypedDict):
+        messages: Annotated[list, DeltaChannel(add_messages)]
+
+    counter = {"n": 0}
+
+    def respond(state: State) -> dict:
+        counter["n"] += 1
+        return {
+            "messages": [
+                AIMessage(content=f"ai-{counter['n']}", id=f"ai-{counter['n']}")
+            ]
+        }
+
+    builder = StateGraph(State)
+    builder.add_node("respond", respond)
+    builder.add_edge(START, "respond")
+    saver = InMemorySaver()
+    graph = builder.compile(checkpointer=saver)
+
+    config = {"configurable": {"thread_id": "diff-time-travel"}}
+
+    # Run 2 turns: h1→ai-1, h2→ai-2
+    graph.invoke({"messages": [HumanMessage(content="h1", id="h1")]}, config)
+    graph.invoke({"messages": [HumanMessage(content="h2", id="h2")]}, config)
+
+    # Find the checkpoint after turn 1 (2 messages: h1 + ai-1)
+    history = list(graph.get_state_history(config))
+    after_turn1 = next(h for h in history if len(h.values.get("messages", [])) == 2)
+
+    assert len(after_turn1.values["messages"]) == 2
+    assert after_turn1.values["messages"][0].content == "h1"
+    assert after_turn1.values["messages"][1].content == "ai-1"
+
+    # Resume from turn-1 checkpoint: inject h3, expect 3 messages total (h1, ai-1, ai-N)
+    # NOT 5 messages (turn-2 deltas must not bleed into the resumed run)
+    result = graph.invoke(
+        {"messages": [HumanMessage(content="h3", id="h3")]},
+        after_turn1.config,
+    )
+    msgs = result["messages"]
+    # Should be: h1, ai-1, h3, ai-N — 4 messages total
+    assert len(msgs) == 4, (
+        f"expected 4 messages after time-travel resume, got {len(msgs)}: {msgs}"
+    )
+    assert msgs[0].content == "h1"
+    assert msgs[1].content == "ai-1"
+    assert msgs[2].content == "h3"
+
+
+async def test_delta_channel_remove_message_end_to_end() -> None:
+    """RemoveMessage inside a DeltaChannel graph must persist and reload correctly."""
+    from langchain_core.messages import AIMessage, HumanMessage, RemoveMessage
+    from langgraph.checkpoint.memory import InMemorySaver
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph import START, StateGraph
+    from langgraph.graph.message import add_messages
+
+    class State(TypedDict):
+        messages: Annotated[list, DeltaChannel(add_messages)]
+
+    def respond(state: State) -> dict:
+        return {"messages": [AIMessage(content="reply", id="ai-1")]}
+
+    def delete_first(state: State) -> dict:
+        # removes the first message
+        return {"messages": [RemoveMessage(id=state["messages"][0].id)]}
+
+    builder = StateGraph(State)
+    builder.add_node("respond", respond)
+    builder.add_node("delete_first", delete_first)
+    builder.add_edge(START, "respond")
+    builder.add_edge("respond", "delete_first")
+    graph = builder.compile(checkpointer=InMemorySaver())
+
+    config = {"configurable": {"thread_id": "diff-remove-test"}}
+    graph.invoke({"messages": [HumanMessage(content="hello", id="h1")]}, config)
+
+    state = graph.get_state(config)
+    msgs = state.values["messages"]
+    # h1 was removed, only ai-1 should remain
+    assert len(msgs) == 1, f"expected 1 message, got {len(msgs)}: {msgs}"
+    assert msgs[0].id == "ai-1"
+
+    # A subsequent turn must reconstruct from the checkpoint correctly
+    graph.invoke({"messages": [HumanMessage(content="again", id="h2")]}, config)
+    state = graph.get_state(config)
+    msgs = state.values["messages"]
+    # ai-1 + h2 + ai-1(second reply, same id overwrites) + h2 removed
+    # more simply: after second run we expect ai-1 updated + h2 remaining minus deleted h2
+    # just assert h1 is still gone
+    assert all(m.id != "h1" for m in msgs), (
+        "h1 should still be absent after second turn"
+    )
+
+
+async def test_delta_channel_update_by_id_end_to_end() -> None:
+    """Updating a message by ID via DeltaChannel must persist and reload correctly."""
+    from langchain_core.messages import HumanMessage
+    from langgraph.checkpoint.memory import InMemorySaver
+
+    from langgraph.channels.delta import DeltaChannel
+    from langgraph.graph import START, StateGraph
+    from langgraph.graph.message import add_messages
+
+    class State(TypedDict):
+        messages: Annotated[list, DeltaChannel(add_messages)]
+
+    def update_msg(state: State) -> dict:
+        # re-send h1 with updated content
+        return {"messages": [HumanMessage(content="updated", id="h1")]}
+
+    builder = StateGraph(State)
+    builder.add_node("update_msg", update_msg)
+    builder.add_edge(START, "update_msg")
+    graph = builder.compile(checkpointer=InMemorySaver())
+
+    config = {"configurable": {"thread_id": "diff-update-id-test"}}
+    graph.invoke({"messages": [HumanMessage(content="original", id="h1")]}, config)
+
+    state = graph.get_state(config)
+    msgs = state.values["messages"]
+    assert len(msgs) == 1, f"expected 1 message, got {len(msgs)}: {msgs}"
+    assert msgs[0].content == "updated"
+    assert msgs[0].id == "h1"
+
+    # Second turn: verify the updated state is the base for further accumulation
+    graph.invoke({"messages": [HumanMessage(content="new", id="h2")]}, config)
+    state = graph.get_state(config)
+    msgs = state.values["messages"]
+    ids = [m.id for m in msgs]
+    assert "h1" in ids  # h1 persists (updated, not duplicated)
+    assert "h2" in ids
+    assert ids.count("h1") == 1, "h1 must not be duplicated"

libs/langgraph/tests/test_rehydrate_sweep.py

@@ -0,0 +1,185 @@
+"""Sweep snapshot_every values to find the storage vs. time-travel tradeoff.
+
+Run directly:  python tests/test_rehydrate_sweep.py
+Run via pytest: pytest tests/test_rehydrate_sweep.py -s
+"""
+
+from __future__ import annotations
+
+import sys
+import time
+from typing import Annotated, Any
+
+from langchain_core.messages import AIMessage, HumanMessage
+from langgraph.checkpoint.memory import MemorySaver
+from typing_extensions import TypedDict
+
+from langgraph.channels.delta import DeltaChannel
+from langgraph.graph import END, StateGraph
+from langgraph.graph.message import add_messages
+
+# ---------------------------------------------------------------------------
+# Config
+# ---------------------------------------------------------------------------
+
+REHYDRATE_SWEEP = [5, 10, 25, 50, 100, None]  # None = no rehydration (pure diff)
+TURN_COUNTS = [50, 100, 250, 500]
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+
+def _make_state(snapshot_every: int | None) -> type:
+    channel = DeltaChannel(add_messages, snapshot_every=snapshot_every)
+    return TypedDict("S", {"messages": Annotated[list, channel]})
+
+
+def _make_graph(state_cls: type) -> Any:
+    def human_node(state: Any) -> dict:
+        return {}
+
+    def ai_node(state: Any) -> dict:
+        last = state["messages"][-1]
+        return {"messages": [AIMessage(content=f"reply-to-{last.id}")]}
+
+    g = StateGraph(state_cls)
+    g.add_node("human", human_node)
+    g.add_node("ai", ai_node)
+    g.add_edge("human", "ai")
+    g.add_edge("ai", END)
+    g.set_entry_point("human")
+    return g.compile(checkpointer=MemorySaver())
+
+
+def _total_blob_bytes(saver: MemorySaver) -> int:
+    total = 0
+    for (_, _, _, _), (type_tag, blob) in saver.blobs.items():
+        if blob is not None:
+            total += len(blob)
+    return total
+
+
+def _measure_time_travel_ms(graph: Any, config: dict) -> float:
+    """Time how long it takes to get state at the very first checkpoint (worst case)."""
+    history = list(graph.get_state_history(config))
+    if not history:
+        return 0.0
+    oldest = history[-1]
+    t0 = time.perf_counter()
+    graph.get_state(oldest.config)
+    return (time.perf_counter() - t0) * 1000
+
+
+def _run(n_turns: int, snapshot_every: int | None) -> tuple[float, int, float]:
+    """Returns (write_ms, blob_bytes, time_travel_ms)."""
+    state_cls = _make_state(snapshot_every)
+    graph = _make_graph(state_cls)
+    saver: MemorySaver = graph.checkpointer  # type: ignore[assignment]
+    config = {"configurable": {"thread_id": "sweep"}}
+
+    t0 = time.perf_counter()
+    for i in range(n_turns):
+        graph.invoke(
+            {"messages": [HumanMessage(content=f"msg-{i}", id=f"h{i}")]}, config
+        )
+    write_ms = (time.perf_counter() - t0) * 1000
+
+    blob_bytes = _total_blob_bytes(saver)
+    tt_ms = _measure_time_travel_ms(graph, config)
+    return write_ms, blob_bytes, tt_ms
+
+
+# ---------------------------------------------------------------------------
+# ASCII sparkline
+# ---------------------------------------------------------------------------
+
+
+def _sparkline(values: list[float], width: int = 20) -> str:
+    bars = " ▁▂▃▄▅▆▇█"
+    lo, hi = min(values), max(values)
+    span = hi - lo or 1
+    chars = [bars[round((v - lo) / span * (len(bars) - 1))] for v in values]
+    return "".join(chars).ljust(width)
+
+
+# ---------------------------------------------------------------------------
+# Main
+# ---------------------------------------------------------------------------
+
+
+def run_sweep() -> None:
+    label = {v: (str(v) if v is not None else "None(∞)") for v in REHYDRATE_SWEEP}
+
+    print()
+    print("snapshot_every sweep — storage vs time-travel cost")
+    print("=" * 90)
+
+    for turns in TURN_COUNTS:
+        print(f"\n--- {turns} turns ---")
+        col_w = 12
+        header = (
+            f"{'snapshot_every':>18}  "
+            f"{'blob_bytes':>{col_w}}  "
+            f"{'write_ms':>{col_w}}  "
+            f"{'time_travel_ms':>{col_w}}"
+        )
+        print(header)
+        print("-" * 60)
+
+        tt_vals: list[float] = []
+        byte_vals: list[int] = []
+        write_vals: list[float] = []
+        rows: list[tuple] = []
+
+        for rv in REHYDRATE_SWEEP:
+            write_ms, blob_bytes, tt_ms = _run(turns, rv)
+            rows.append((rv, blob_bytes, write_ms, tt_ms))
+            byte_vals.append(blob_bytes)
+            write_vals.append(write_ms)
+            tt_vals.append(tt_ms)
+
+        for rv, blob_bytes, write_ms, tt_ms in rows:
+            print(
+                f"{label[rv]:>18}  "
+                f"{blob_bytes:>{col_w},}  "
+                f"{write_ms:>{col_w}.1f}  "
+                f"{tt_ms:>{col_w}.2f}"
+            )
+
+        print()
+        print(
+            f"  bytes       spark: [{_sparkline(byte_vals)}]  "
+            f"lo={min(byte_vals):,}  hi={max(byte_vals):,}"
+        )
+        print(
+            f"  time-travel spark: [{_sparkline(tt_vals)}]  "
+            f"lo={min(tt_vals):.2f}ms  hi={max(tt_vals):.2f}ms"
+        )
+        print(
+            f"  write       spark: [{_sparkline(write_vals)}]  "
+            f"lo={min(write_vals):.1f}ms  hi={max(write_vals):.1f}ms"
+        )
+
+    print()
+    print("=" * 90)
+    print(
+        "snapshot_every=None means pure diff (no snapshots) — "
+        "lowest storage, highest time-travel cost."
+    )
+    print(
+        "Lower snapshot_every = more frequent full snapshots = "
+        "faster time-travel, more storage."
+    )
+    print()
+
+
+def test_rehydrate_sweep(capsys: Any) -> None:
+    with capsys.disabled():
+        run_sweep()
+
+
+if __name__ == "__main__":
+    run_sweep()
+    sys.exit(0)

libs/langgraph/tests/test_time_travel.py

@@ -1113,70 +1113,6 @@ def test_subgraph_interrupt_replay_from_parent_then_resume(
     ]
 
 
-def test_subgraph_interrupt_resume_with_explicit_head_checkpoint_id(
-    sync_checkpointer: BaseCheckpointSaver,
-) -> None:
-    """Resume with Command(resume=...) plus the current head checkpoint_id
-    in config. The subgraph must continue from the interrupted node, not
-    restart from scratch. Explicit checkpoint_id triggers is_replaying but
-    this is a resume, not a time-travel, so ReplayState should not apply."""
-
-    called: list[str] = []
-
-    def step_a(state: State) -> State:
-        called.append("step_a")
-        return {"value": ["sub_a"]}
-
-    def ask_human(state: State) -> State:
-        called.append("ask_human")
-        answer = interrupt("Provide input:")
-        return {"value": [f"human:{answer}"]}
-
-    def step_b(state: State) -> State:
-        called.append("step_b")
-        return {"value": ["sub_b"]}
-
-    subgraph = (
-        StateGraph(State)
-        .add_node("step_a", step_a)
-        .add_node("ask_human", ask_human)
-        .add_node("step_b", step_b)
-        .add_edge(START, "step_a")
-        .add_edge("step_a", "ask_human")
-        .add_edge("ask_human", "step_b")
-        .compile(checkpointer=True)
-    )
-
-    graph = (
-        StateGraph(State)
-        .add_node("subgraph_node", subgraph)
-        .add_edge(START, "subgraph_node")
-        .compile(checkpointer=sync_checkpointer)
-    )
-
-    config = {"configurable": {"thread_id": "1"}}
-
-    # Run until interrupt fires in subgraph
-    graph.invoke({"value": []}, config)
-    assert called == ["step_a", "ask_human"]
-
-    # Resume with explicit head checkpoint_id in config
-    head_checkpoint_id = graph.get_state(config).config["configurable"]["checkpoint_id"]
-    called.clear()
-    resume_config = {
-        "configurable": {
-            "thread_id": "1",
-            "checkpoint_id": head_checkpoint_id,
-            "checkpoint_ns": "",
-        }
-    }
-    result = graph.invoke(Command(resume="answer"), resume_config)
-
-    assert called == ["ask_human", "step_b"]
-    assert "__interrupt__" not in result
-    assert result["value"] == ["sub_a", "human:answer", "sub_b"]
-
-
 def test_subgraph_replay_loads_accumulated_state_then_resume(
     sync_checkpointer: BaseCheckpointSaver,
 ) -> None:

libs/langgraph/uv.lock

@@ -1348,7 +1348,7 @@ wheels = [
 
 [[package]]
 name = "langchain-core"
-version = "1.3.1"
+version = "1.3.0a2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "jsonpatch" },
@@ -1360,14 +1360,14 @@ dependencies = [
     { name = "typing-extensions" },
     { name = "uuid-utils" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/f4/fe/abeae8d0d2899e191d67c6c7f065f7e52a953f30b21ef327fa49084e4af9/langchain_core-1.3.1.tar.gz", hash = "sha256:41b384055799f93f34520df6bf7b80e2e5e23153cdfd46874251c6c9916ea030", size = 862403, upload-time = "2026-04-23T18:54:01.857Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/af/bc/0bff31fcaff174d86031cc713471a3e85ed4ec8e5cd95ad0217f2aced20e/langchain_core-1.3.0a2.tar.gz", hash = "sha256:52d978c84552b74b9a3f16c1fced84f9e27cc96d7a67c601925ce6cbc4ea3cf9", size = 854580, upload-time = "2026-04-13T14:37:55.745Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/a1/c2/8493be505921857988db068b7c027f28a9b1587b4425c6a32b1221c9c9fe/langchain_core-1.3.1-py3-none-any.whl", hash = "sha256:8b13d19d3bed3f4768df12c7f6932d2ada715f3ac9fd020c63d28c693968269e", size = 515879, upload-time = "2026-04-23T18:53:59.94Z" },
+    { url = "https://files.pythonhosted.org/packages/0e/14/03c09686602567059f26af29de0c44546a83af2f2aa29925e61040e43ea2/langchain_core-1.3.0a2-py3-none-any.whl", hash = "sha256:9e929a34f0b0c6c1255e395a1de34f8626893ceb4cdae550a22a0bd18c87be54", size = 510233, upload-time = "2026-04-13T14:37:54.277Z" },
 ]
 
 [[package]]
 name = "langgraph"
-version = "1.1.10"
+version = "1.1.7a2"
 source = { editable = "." }
 dependencies = [
     { name = "langchain-core" },
@@ -1439,7 +1439,7 @@ test = [
 
 [package.metadata]
 requires-dist = [
-    { name = "langchain-core", specifier = ">=1.3.0,<2" },
+    { name = "langchain-core", specifier = "==1.3.0a2" },
     { name = "langgraph-checkpoint", editable = "../checkpoint" },
     { name = "langgraph-prebuilt", editable = "../prebuilt" },
     { name = "langgraph-sdk", editable = "../sdk-py" },
@@ -1548,7 +1548,7 @@ wheels = [
 
 [[package]]
 name = "langgraph-checkpoint"
-version = "4.0.3"
+version = "4.0.2"
 source = { editable = "../checkpoint" }
 dependencies = [
     { name = "langchain-core" },
@@ -1706,7 +1706,7 @@ inmem = [
 requires-dist = [
     { name = "click", specifier = ">=8.1.7" },
     { name = "httpx", specifier = ">=0.24.0" },
-    { name = "langgraph-api", marker = "python_full_version >= '3.11' and extra == 'inmem'", specifier = ">=0.5.35,<0.9.0" },
+    { name = "langgraph-api", marker = "python_full_version >= '3.11' and extra == 'inmem'", specifier = ">=0.5.35,<0.8.0" },
     { name = "langgraph-runtime-inmem", marker = "python_full_version >= '3.11' and extra == 'inmem'", specifier = ">=0.7" },
     { name = "langgraph-sdk", marker = "python_full_version >= '3.11'", specifier = ">=0.1.0" },
     { name = "pathspec", specifier = ">=0.11.0" },
@@ -1742,7 +1742,7 @@ test = [
 
 [[package]]
 name = "langgraph-prebuilt"
-version = "1.0.12"
+version = "1.0.9"
 source = { editable = "../prebuilt" }
 dependencies = [
     { name = "langchain-core" },
@@ -1751,7 +1751,7 @@ dependencies = [
 
 [package.metadata]
 requires-dist = [
-    { name = "langchain-core", specifier = ">=1.3.1" },
+    { name = "langchain-core", specifier = ">=1.0.0" },
     { name = "langgraph-checkpoint", editable = "../checkpoint" },
 ]
 
@@ -2140,7 +2140,7 @@ wheels = [
 
 [[package]]
 name = "nbconvert"
-version = "7.17.1"
+version = "7.17.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "beautifulsoup4" },
@@ -2158,9 +2158,9 @@ dependencies = [
     { name = "pygments" },
     { name = "traitlets" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/01/b1/708e53fe2e429c103c6e6e159106bcf0357ac41aa4c28772bd8402339051/nbconvert-7.17.1.tar.gz", hash = "sha256:34d0d0a7e73ce3cbab6c5aae8f4f468797280b01fd8bd2ca746da8569eddd7d2", size = 865311, upload-time = "2026-04-08T00:44:14.914Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/38/47/81f886b699450d0569f7bc551df2b1673d18df7ff25cc0c21ca36ed8a5ff/nbconvert-7.17.0.tar.gz", hash = "sha256:1b2696f1b5be12309f6c7d707c24af604b87dfaf6d950794c7b07acab96dda78", size = 862855, upload-time = "2026-01-29T16:37:48.478Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/67/f8/bb0a9d5f46819c821dc1f004aa2cc29b1d91453297dbf5ff20470f00f193/nbconvert-7.17.1-py3-none-any.whl", hash = "sha256:aa85c087b435e7bf1ffd03319f658e285f2b89eccab33bc1ba7025495ab3e7c8", size = 261927, upload-time = "2026-04-08T00:44:12.845Z" },
+    { url = "https://files.pythonhosted.org/packages/0d/4b/8d5f796a792f8a25f6925a96032f098789f448571eb92011df1ae59e8ea8/nbconvert-7.17.0-py3-none-any.whl", hash = "sha256:4f99a63b337b9a23504347afdab24a11faa7d86b405e5c8f9881cd313336d518", size = 261510, upload-time = "2026-01-29T16:37:46.322Z" },
 ]
 
 [[package]]
@@ -3018,11 +3018,11 @@ wheels = [
 
 [[package]]
 name = "python-dotenv"
-version = "1.2.2"
+version = "1.2.1"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/82/ed/0301aeeac3e5353ef3d94b6ec08bbcabd04a72018415dcb29e588514bba8/python_dotenv-1.2.2.tar.gz", hash = "sha256:2c371a91fbd7ba082c2c1dc1f8bf89ca22564a087c2c287cd9b662adde799cf3", size = 50135, upload-time = "2026-03-01T16:00:26.196Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/f0/26/19cadc79a718c5edbec86fd4919a6b6d3f681039a2f6d66d14be94e75fb9/python_dotenv-1.2.1.tar.gz", hash = "sha256:42667e897e16ab0d66954af0e60a9caa94f0fd4ecf3aaf6d2d260eec1aa36ad6", size = 44221, upload-time = "2025-10-26T15:12:10.434Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/0b/d7/1959b9648791274998a9c3526f6d0ec8fd2233e4d4acce81bbae76b44b2a/python_dotenv-1.2.2-py3-none-any.whl", hash = "sha256:1d8214789a24de455a8b8bd8ae6fe3c6b69a5e3d64aa8a8e5d68e694bbcb285a", size = 22101, upload-time = "2026-03-01T16:00:25.09Z" },
+    { url = "https://files.pythonhosted.org/packages/14/1b/a298b06749107c305e1fe0f814c6c74aea7b2f1e10989cb30f544a1b3253/python_dotenv-1.2.1-py3-none-any.whl", hash = "sha256:b81ee9561e9ca4004139c6cbba3a238c32b03e4894671e181b671e8cb8425d61", size = 21230, upload-time = "2025-10-26T15:12:09.109Z" },
 ]
 
 [[package]]

libs/prebuilt/langgraph/prebuilt/tool_node.py

@@ -82,7 +82,6 @@ from langchain_core.tools.base import (
     _is_injected_arg_type,
     get_all_basemodel_annotations,
 )
-from langgraph._internal._constants import CONF, CONFIG_KEY_READ
 from langgraph._internal._runnable import RunnableCallable
 from langgraph.errors import GraphBubbleUp
 from langgraph.graph.message import REMOVE_ALL_MESSAGES
@@ -801,7 +800,7 @@ class ToolNode(RunnableCallable):
         # Construct ToolRuntime instances at the top level for each tool call
         tool_runtimes = []
         for call, cfg in zip(tool_calls, config_list, strict=False):
-            state = self._extract_state(input, cfg)
+            state = self._extract_state(input)
             tool_runtime = ToolRuntime(
                 state=state,
                 tool_call_id=call["id"],
@@ -809,7 +808,6 @@ class ToolNode(RunnableCallable):
                 context=runtime.context,
                 store=runtime.store,
                 stream_writer=runtime.stream_writer,
-                tools=list(self.tools_by_name.values()),
                 execution_info=runtime.execution_info,
                 server_info=runtime.server_info,
             )
@@ -836,7 +834,7 @@ class ToolNode(RunnableCallable):
         # Construct ToolRuntime instances at the top level for each tool call
         tool_runtimes = []
         for call, cfg in zip(tool_calls, config_list, strict=False):
-            state = self._extract_state(input, cfg)
+            state = self._extract_state(input)
             tool_runtime = ToolRuntime(
                 state=state,
                 tool_call_id=call["id"],
@@ -844,7 +842,6 @@ class ToolNode(RunnableCallable):
                 context=runtime.context,
                 store=runtime.store,
                 stream_writer=runtime.stream_writer,
-                tools=list(self.tools_by_name.values()),
                 execution_info=runtime.execution_info,
                 server_info=runtime.server_info,
             )
@@ -860,30 +857,14 @@ class ToolNode(RunnableCallable):
 
     def _combine_tool_outputs(
         self,
-        outputs: list[ToolMessage | Command | list[ToolMessage | Command]],
+        outputs: list[ToolMessage | Command],
         input_type: Literal["list", "dict", "tool_calls"],
     ) -> list[Command | list[ToolMessage] | dict[str, list[ToolMessage]]]:
-        # Flatten list entries from tools that returned multiple items
-        flat_outputs: list[ToolMessage | Command]
-        if any(isinstance(output, list) for output in outputs):
-            flat_outputs = []
-            for output in outputs:
-                if isinstance(output, list):
-                    flat_outputs.extend(output)
-                else:
-                    flat_outputs.append(output)
-        else:
-            flat_outputs = cast("list[ToolMessage | Command]", outputs)
-
         # preserve existing behavior for non-command tool outputs for backwards
         # compatibility
-        if not any(isinstance(output, Command) for output in flat_outputs):
+        if not any(isinstance(output, Command) for output in outputs):
             # TypedDict, pydantic, dataclass, etc. should all be able to load from dict
-            return (
-                flat_outputs
-                if input_type == "list"
-                else {self._messages_key: flat_outputs}
-            )
+            return outputs if input_type == "list" else {self._messages_key: outputs}
 
         # LangGraph will automatically handle list of Command and non-command node
         # updates
@@ -893,7 +874,7 @@ class ToolNode(RunnableCallable):
 
         # combine all parent commands with goto into a single parent command
         parent_command: Command | None = None
-        for output in flat_outputs:
+        for output in outputs:
             if isinstance(output, Command):
                 if (
                     output.graph is Command.PARENT
@@ -923,7 +904,7 @@ class ToolNode(RunnableCallable):
         request: ToolCallRequest,
         input_type: Literal["list", "dict", "tool_calls"],
         config: RunnableConfig,
-    ) -> ToolMessage | Command | list[Command | ToolMessage]:
+    ) -> ToolMessage | Command:
         """Execute tool call with configured error handling.
 
         Args:
@@ -932,7 +913,7 @@ class ToolNode(RunnableCallable):
             config: Runnable configuration.
 
         Returns:
-            ToolMessage, Command, or list of Command/ToolMessage.
+            ToolMessage or Command.
 
         Raises:
             Exception: If tool fails and handle_tool_errors is False.
@@ -964,11 +945,6 @@ class ToolNode(RunnableCallable):
                     call["name"], exc, call["args"], filtered_errors
                 ) from exc
 
-            # Inside try so validation errors route through _handle_tool_errors
-            return self._normalize_tool_response(
-                response, request.tool_call, input_type
-            )
-
         # GraphInterrupt is a special exception that will always be raised.
         # It can be triggered in the following scenarios,
         # Where GraphInterrupt(GraphBubbleUp) is raised from an `interrupt` invocation
@@ -1010,12 +986,23 @@ class ToolNode(RunnableCallable):
                 status="error",
             )
 
+        # Process successful response
+        if isinstance(response, Command):
+            # Validate Command before returning to handler
+            return self._validate_tool_command(response, request.tool_call, input_type)
+        if isinstance(response, ToolMessage):
+            response.content = cast("str | list", msg_content_output(response.content))
+            return response
+
+        msg = f"Tool {call['name']} returned unexpected type: {type(response)}"
+        raise TypeError(msg)
+
     def _run_one(
         self,
         call: ToolCall,
         input_type: Literal["list", "dict", "tool_calls"],
         tool_runtime: ToolRuntime,
-    ) -> ToolMessage | Command | list[Command | ToolMessage]:
+    ) -> ToolMessage | Command:
         """Execute single tool call with wrap_tool_call wrapper if configured.
 
         Args:
@@ -1070,7 +1057,7 @@ class ToolNode(RunnableCallable):
         request: ToolCallRequest,
         input_type: Literal["list", "dict", "tool_calls"],
         config: RunnableConfig,
-    ) -> ToolMessage | Command | list[Command | ToolMessage]:
+    ) -> ToolMessage | Command:
         """Execute tool call asynchronously with configured error handling.
 
         Args:
@@ -1079,7 +1066,7 @@ class ToolNode(RunnableCallable):
             config: Runnable configuration.
 
         Returns:
-            ToolMessage, Command, or list of Command/ToolMessage.
+            ToolMessage or Command.
 
         Raises:
             Exception: If tool fails and handle_tool_errors is False.
@@ -1111,11 +1098,6 @@ class ToolNode(RunnableCallable):
                     call["name"], exc, call["args"], filtered_errors
                 ) from exc
 
-            # Inside try so validation errors route through _handle_tool_errors
-            return self._normalize_tool_response(
-                response, request.tool_call, input_type
-            )
-
         # GraphInterrupt is a special exception that will always be raised.
         # It can be triggered in the following scenarios,
         # Where GraphInterrupt(GraphBubbleUp) is raised from an `interrupt` invocation
@@ -1157,12 +1139,23 @@ class ToolNode(RunnableCallable):
                 status="error",
             )
 
+        # Process successful response
+        if isinstance(response, Command):
+            # Validate Command before returning to handler
+            return self._validate_tool_command(response, request.tool_call, input_type)
+        if isinstance(response, ToolMessage):
+            response.content = cast("str | list", msg_content_output(response.content))
+            return response
+
+        msg = f"Tool {call['name']} returned unexpected type: {type(response)}"
+        raise TypeError(msg)
+
     async def _arun_one(
         self,
         call: ToolCall,
         input_type: Literal["list", "dict", "tool_calls"],
         tool_runtime: ToolRuntime,
-    ) -> ToolMessage | Command | list[Command | ToolMessage]:
+    ) -> ToolMessage | Command:
         """Execute single tool call asynchronously with awrap_tool_call wrapper if configured.
 
         Args:
@@ -1278,37 +1271,18 @@ class ToolNode(RunnableCallable):
         return None
 
     def _extract_state(
-        self,
-        input: list[AnyMessage] | dict[str, Any] | BaseModel,
-        config: RunnableConfig,
+        self, input: list[AnyMessage] | dict[str, Any] | BaseModel
     ) -> list[AnyMessage] | dict[str, Any] | BaseModel:
-        """Extract state from input.
+        """Extract state from input, handling ToolCallWithContext if present.
 
-        Three input shapes:
+        Args:
+            input: The input which may be raw state or ToolCallWithContext.
 
-        - `ToolCallWithContext` dict — legacy Send payload carrying an inlined
-          state snapshot; return `input["state"]`.
-        - list of `ToolCall` dicts — new Send payload with no inlined state;
-          hydrate state from channels via `CONFIG_KEY_READ`.
-        - regular graph state (dict/list/BaseModel) — return `input` as-is.
+        Returns:
+            The actual state to pass to wrap_tool_call wrappers.
         """
         if isinstance(input, dict) and input.get("__type") == "tool_call_with_context":
             return input["state"]
-        if (
-            isinstance(input, list)
-            and input
-            and isinstance(input[-1], dict)
-            and input[-1].get("type") == "tool_call"
-        ):
-            read = config.get(CONF, {}).get(CONFIG_KEY_READ)
-            if read is None:
-                return {}
-            # Pregel installs CONFIG_KEY_READ as
-            # `functools.partial(local_read, scratchpad, channels, managed, task)`.
-            # Match the previous inlined-state contract by reading channels only;
-            # managed values have their own injection path (`ToolRuntime.context`).
-            channels = read.args[1]
-            return cast("dict[str, Any]", read(list(channels), True))
         return input
 
     def _inject_tool_args(
@@ -1428,84 +1402,11 @@ class ToolNode(RunnableCallable):
         tool_call_copy["args"] = {**stripped_args, **injected_args}
         return tool_call_copy
 
-    def _normalize_tool_response(
-        self,
-        response: Any,
-        tool_call: ToolCall,
-        input_type: Literal["list", "dict", "tool_calls"],
-    ) -> ToolMessage | Command | list[Command | ToolMessage]:
-        """Validate and normalize a tool's raw return value."""
-        if isinstance(response, Command):
-            return self._validate_tool_command(response, tool_call, input_type)
-        if isinstance(response, ToolMessage):
-            response.content = cast("str | list", msg_content_output(response.content))
-            return response
-        if isinstance(response, list):
-            if all(isinstance(r, (Command, ToolMessage)) for r in response):
-                return self._validate_tool_command_list(response, tool_call, input_type)
-            msg = (
-                f"Tool {tool_call['name']} returned a list with invalid element "
-                "types: expected all Command or ToolMessage"
-            )
-            raise TypeError(msg)
-        msg = f"Tool {tool_call['name']} returned unexpected type: {type(response)}"
-        raise TypeError(msg)
-
-    def _validate_tool_command_list(
-        self,
-        response: list[Command | ToolMessage],
-        tool_call: ToolCall,
-        input_type: Literal["list", "dict", "tool_calls"],
-    ) -> list[Command | ToolMessage]:
-        """Validate a list of Command/ToolMessage returned by a single tool call.
-
-        Requires exactly one terminating ToolMessage (matching the outer tool_call_id)
-        across the list — either as a top-level element or nested in a
-        Command.update["messages"].
-        """
-        expected_id = tool_call["id"]
-
-        terminator_count = 0
-        for item in response:
-            if isinstance(item, ToolMessage):
-                if item.tool_call_id == expected_id:
-                    terminator_count += 1
-            elif isinstance(item, Command) and isinstance(item.update, dict):
-                for msg in item.update.get(self._messages_key, []):
-                    if isinstance(msg, ToolMessage) and msg.tool_call_id == expected_id:
-                        terminator_count += 1
-
-        if terminator_count != 1:
-            msg = (
-                f"Tool {tool_call['name']} returned a list with "
-                f"{terminator_count} messages bound to tool_call_id "
-                f"{expected_id!r}; expected exactly one terminating ToolMessage."
-            )
-            raise ValueError(msg)
-
-        # Per-Command normalization still runs, but the list-level count above
-        # already guarantees exactly one terminator, so individual Commands may
-        # lack one.
-        validated: list[Command | ToolMessage] = []
-        for item in response:
-            if isinstance(item, Command):
-                validated.append(
-                    self._validate_tool_command(
-                        item, tool_call, input_type, require_terminator=False
-                    )
-                )
-            else:
-                item.content = cast("str | list", msg_content_output(item.content))
-                validated.append(item)
-        return validated
-
     def _validate_tool_command(
         self,
         command: Command,
         call: ToolCall,
         input_type: Literal["list", "dict", "tool_calls"],
-        *,
-        require_terminator: bool = True,
     ) -> Command:
         if isinstance(command.update, dict):
             # input type is dict when ToolNode is invoked with a dict input
@@ -1555,11 +1456,7 @@ class ToolNode(RunnableCallable):
 
         # validate that we always have a ToolMessage matching the tool call in
         # Command.update if command is sent to the CURRENT graph
-        if (
-            require_terminator
-            and updated_command.graph is None
-            and not has_matching_tool_message
-        ):
+        if updated_command.graph is None and not has_matching_tool_message:
             example_update = (
                 '`Command(update={"messages": '
                 '[ToolMessage("Success", tool_call_id=tool_call_id), ...]}, ...)`'
@@ -1679,7 +1576,6 @@ class ToolRuntime(_DirectlyInjectedToolArg, Generic[ContextT, StateT]):
     - `context`: Runtime context (shared with `Runtime`)
     - `store`: `BaseStore` instance for persistent storage (shared with `Runtime`)
     - `stream_writer`: `StreamWriter` for streaming output (shared with `Runtime`)
-    - `tools`: List of all available `BaseTool` instances
 
     No `Annotated` wrapper is needed - just use `runtime: ToolRuntime`
     as a parameter.
@@ -1722,7 +1618,6 @@ class ToolRuntime(_DirectlyInjectedToolArg, Generic[ContextT, StateT]):
     context: ContextT
     config: RunnableConfig
     stream_writer: StreamWriter
-    tools: list[BaseTool]
     tool_call_id: str | None
     store: BaseStore | None
     execution_info: ExecutionInfo | None = None

libs/prebuilt/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "langgraph-prebuilt"
-version = "1.0.12"
+version = "1.0.9"
 description = "Library with high-level APIs for creating and executing LangGraph agents and tools."
 authors = []
 requires-python = ">=3.10"
@@ -25,7 +25,7 @@ classifiers = [
 ]
 dependencies = [
     "langgraph-checkpoint>=2.1.0,<5.0.0",
-    "langchain-core>=1.3.1",
+    "langchain-core>=1.0.0",
 ]
 
 [project.urls]

libs/prebuilt/tests/test_injected_state_not_required.py

@@ -4,7 +4,7 @@ This tests the fix for https://github.com/langchain-ai/langchain/issues/35585
 
 When using InjectedState(<field>) on a tool parameter, and the referenced field is
 declared as NotRequired in the custom state schema, the ToolNode should gracefully
-handle missing fields by injecting None instead of raising KeyError.
+handle missing fields without raising KeyError so the tool's default can apply.
 """
 
 import sys
@@ -45,6 +45,14 @@ def get_weather(city: Annotated[str | None, InjectedState("city")] = None) -> st
     return f"It's always sunny in {city}!"
 
 
+@tool
+def get_weather_with_default(
+    city: Annotated[str, InjectedState("city")] = "Boston",
+) -> str:
+    """Get weather for a given city, defaulting when state omits the field."""
+    return f"It's always sunny in {city}!"
+
+
 def _create_mock_runtime(
     state: dict | None = None,
     store=None,
@@ -69,7 +77,6 @@ def _create_config_with_runtime(store=None, state=None):
         context={},
         store=store,
         stream_writer=None,
-        tools=[],
         tool_call_id="test_id",
     )
     return {
@@ -85,7 +92,7 @@ def _create_config_with_runtime(store=None, state=None):
     reason="InjectedState field extraction from Optional[Annotated[...]] not supported on Python <3.11",
 )
 def test_injected_state_not_required_field_missing_injects_none():
-    """Test that InjectedState with NotRequired field injects None when field is missing.
+    """Test that missing optional InjectedState leaves the tool default in place.
 
     This verifies the fix for https://github.com/langchain-ai/langchain/issues/35585
     """
@@ -115,6 +122,37 @@ def test_injected_state_not_required_field_missing_injects_none():
     assert "No city provided" in tool_msg.content
 
 
+@pytest.mark.skipif(
+    sys.version_info < (3, 11),
+    reason="InjectedState field extraction from Optional[Annotated[...]] not supported on Python <3.11",
+)
+def test_injected_state_not_required_field_missing_preserves_tool_default():
+    """Test that missing optional InjectedState preserves a non-None tool default."""
+    tool_node = ToolNode([get_weather_with_default])
+
+    tool_call = {
+        "name": "get_weather_with_default",
+        "args": {},
+        "id": "call_1",
+        "type": "tool_call",
+    }
+    ai_msg = AIMessage("Let me check the weather", tool_calls=[tool_call])
+
+    state_without_city: CustomAgentStateWithNotRequired = {
+        "messages": [HumanMessage("What's the weather?"), ai_msg],
+    }
+
+    result = tool_node.invoke(
+        state_without_city,
+        config=_create_config_with_runtime(state=state_without_city),
+    )
+
+    assert len(result["messages"]) == 1
+    tool_msg = result["messages"][0]
+    assert isinstance(tool_msg, ToolMessage)
+    assert "Boston" in tool_msg.content
+
+
 @pytest.mark.skipif(
     sys.version_info < (3, 11),
     reason="InjectedState field extraction from Optional[Annotated[...]] not supported on Python <3.11",

libs/prebuilt/tests/test_on_tool_call.py

@@ -1320,98 +1320,6 @@ async def test_state_extraction_with_tool_call_with_context_async() -> None:
     assert "tool_call" not in state_seen[0]
 
 
-def _config_with_channel_read(
-    channel_values: dict[str, object],
-    store: BaseStore | None = None,
-) -> RunnableConfig:
-    """Build a config that mimics `CONFIG_KEY_READ` as Pregel installs it.
-
-    Pregel always installs a `functools.partial(local_read, scratchpad,
-    channels, managed, task)`, and `ToolNode` introspects that partial to
-    learn channel names. The stub matches the shape: partial whose second and
-    third positional args are `channels` and `managed` mappings.
-    """
-    import functools
-
-    channels_stub = {k: None for k in channel_values}
-    managed_stub: dict[str, object] = {}
-
-    # Shape matches pregel's real partial:
-    # functools.partial(local_read, scratchpad, channels, managed, task)
-    def _read(scratchpad, channels, managed, task, select, fresh):  # noqa: ARG001
-        if isinstance(select, str):
-            return channel_values[select]
-        return {k: channel_values[k] for k in select if k in channel_values}
-
-    read = functools.partial(_read, None, channels_stub, managed_stub, None)
-    cfg = _create_config_with_runtime(store)
-    cfg["configurable"]["__pregel_read"] = read
-    return cfg
-
-
-def test_list_form_send_hydrates_state_from_channel_read() -> None:
-    """Send('tools', [tool_call]) with no inlined state should hydrate
-    ToolRuntime.state from CONFIG_KEY_READ (full state read)."""
-    state_seen = []
-
-    def state_inspector_handler(
-        request: ToolCallRequest,
-        execute: Callable[[ToolCallRequest], ToolMessage | Command],
-    ) -> ToolMessage | Command:
-        state_seen.append(request.state)
-        return execute(request)
-
-    channel_values = {
-        "messages": [AIMessage("from channels")],
-        "files": {"/a.md": "body"},
-    }
-
-    tool_node = ToolNode([add], wrap_tool_call=state_inspector_handler)
-
-    tool_call: ToolCall = {
-        "name": "add",
-        "args": {"a": 1, "b": 2},
-        "id": "call_1",
-        "type": "tool_call",
-    }
-
-    tool_node.invoke([tool_call], config=_config_with_channel_read(channel_values))
-
-    assert len(state_seen) == 1
-    got = state_seen[0]
-    assert got == channel_values
-    assert "messages" in got and "files" in got
-
-
-async def test_list_form_send_hydrates_state_async() -> None:
-    state_seen = []
-
-    def state_inspector_handler(
-        request: ToolCallRequest,
-        execute: Callable[[ToolCallRequest], ToolMessage | Command],
-    ) -> ToolMessage | Command:
-        state_seen.append(request.state)
-        return execute(request)
-
-    channel_values = {"messages": [AIMessage("from channels")], "files": {}}
-
-    tool_node = ToolNode([add], wrap_tool_call=state_inspector_handler)
-
-    tool_call: ToolCall = {
-        "name": "add",
-        "args": {"a": 1, "b": 2},
-        "id": "call_1",
-        "type": "tool_call",
-    }
-
-    await tool_node.ainvoke(
-        [tool_call], config=_config_with_channel_read(channel_values)
-    )
-
-    assert len(state_seen) == 1
-    assert state_seen[0] == channel_values
-
-
 def test_tool_call_request_is_frozen() -> None:
     """Test that ToolCallRequest raises deprecation warnings on direct attribute reassignment."""
     tool_call: ToolCall = {"name": "add", "args": {"a": 1, "b": 2}, "id": "call_1"}

libs/prebuilt/tests/test_tool_node.py

@@ -2016,8 +2016,8 @@ async def test_tool_node_inject_runtime_dynamic_tool_via_wrap_tool_call_async()
     assert tool_message.tool_call_id == "call_dynamic_2"
 
 
-def test_tool_runtime_forwards_execution_info_server_info_and_tools() -> None:
-    """Test that execution_info, server_info, and tools are forwarded from Runtime to ToolRuntime."""
+def test_tool_runtime_forwards_execution_info_and_server_info() -> None:
+    """Test that execution_info and server_info are forwarded from Runtime to ToolRuntime."""
     from langgraph.runtime import ExecutionInfo, ServerInfo
 
     exec_info = ExecutionInfo(
@@ -2043,15 +2043,9 @@ def test_tool_runtime_forwards_execution_info_server_info_and_tools() -> None:
         """Tool that captures runtime info."""
         captured["execution_info"] = runtime.execution_info
         captured["server_info"] = runtime.server_info
-        captured["tools"] = runtime.tools
         return "ok"
 
-    @dec_tool
-    def other_tool(y: int) -> str:
-        """Another tool available to the runtime."""
-        return str(y)
-
-    node = ToolNode([info_tool, other_tool])
+    node = ToolNode([info_tool])
     tool_call = {
         "name": "info_tool",
         "args": {"x": 1},
@@ -2060,21 +2054,17 @@ def test_tool_runtime_forwards_execution_info_server_info_and_tools() -> None:
     }
     msg = AIMessage("", tool_calls=[tool_call])
     config: RunnableConfig = {"configurable": {"__pregel_runtime": mock_runtime}}
-    result = node.invoke({"messages": [msg]}, config=config)
+    node.invoke({"messages": [msg]}, config=config)
 
-    assert result["messages"][-1].content == "ok"
     assert captured["execution_info"] is exec_info
     assert captured["execution_info"].thread_id == "t-1"
     assert captured["execution_info"].task_id == "tk-1"
     assert captured["server_info"] is server_info
     assert captured["server_info"].assistant_id == "asst-1"
-    assert [tool.name for tool in captured["tools"]] == ["info_tool", "other_tool"]
 
 
-async def test_tool_runtime_forwards_execution_info_server_info_and_tools_async() -> (
-    None
-):
-    """Test that execution_info, server_info, and tools are forwarded in async path."""
+async def test_tool_runtime_forwards_execution_info_and_server_info_async() -> None:
+    """Test that execution_info and server_info are forwarded in async path."""
     from langgraph.runtime import ExecutionInfo, ServerInfo
 
     exec_info = ExecutionInfo(
@@ -2100,15 +2090,9 @@ async def test_tool_runtime_forwards_execution_info_server_info_and_tools_async(
         """Async tool that captures runtime info."""
         captured["execution_info"] = runtime.execution_info
         captured["server_info"] = runtime.server_info
-        captured["tools"] = runtime.tools
         return "ok"
 
-    @dec_tool
-    async def other_tool_async(y: int) -> str:
-        """Another async tool available to the runtime."""
-        return str(y)
-
-    node = ToolNode([info_tool_async, other_tool_async])
+    node = ToolNode([info_tool_async])
     tool_call = {
         "name": "info_tool_async",
         "args": {"x": 1},
@@ -2117,17 +2101,12 @@ async def test_tool_runtime_forwards_execution_info_server_info_and_tools_async(
     }
     msg = AIMessage("", tool_calls=[tool_call])
     config: RunnableConfig = {"configurable": {"__pregel_runtime": mock_runtime}}
-    result = await node.ainvoke({"messages": [msg]}, config=config)
+    await node.ainvoke({"messages": [msg]}, config=config)
 
-    assert result["messages"][-1].content == "ok"
     assert captured["execution_info"] is exec_info
     assert captured["execution_info"].thread_id == "t-2"
     assert captured["server_info"] is server_info
     assert captured["server_info"].graph_id == "graph-2"
-    assert [tool.name for tool in captured["tools"]] == [
-        "info_tool_async",
-        "other_tool_async",
-    ]
 
 
 # --- InjectedToolArg security tests ---
@@ -2223,195 +2202,3 @@ def test_tool_node_injected_state_overwrites_llm_value() -> None:
     )
     tool_message = result["messages"][-1]
     assert tool_message.content == "PUBLIC_DATA"
-
-
-class _ReturningTool(BaseTool):
-    """A tool that returns a configured value verbatim."""
-
-    name: str = "list_tool"
-    description: str = "Returns a configured value"
-    return_value: Any = None
-
-    def _run(self, **kwargs: Any) -> Any:
-        return self.return_value
-
-    async def _arun(self, **kwargs: Any) -> Any:
-        return self.return_value
-
-
-def _list_tool_call(outer_id: str = "call-1") -> dict[str, Any]:
-    return {"name": "list_tool", "args": {}, "id": outer_id, "type": "tool_call"}
-
-
-def _invoke_returning(
-    return_value: Any,
-    *,
-    outer_id: str = "call-1",
-    handle_tool_errors: bool = True,
-) -> Any:
-    node = ToolNode(
-        [_ReturningTool(return_value=return_value)],
-        handle_tool_errors=handle_tool_errors,
-    )
-    return node.invoke(
-        {"messages": [AIMessage("", tool_calls=[_list_tool_call(outer_id)])]},
-        config=_create_config_with_runtime(),
-    )
-
-
-def test_tool_node_list_return_command_and_tool_message() -> None:
-    """Valid: tool returns [Command(update={...}), ToolMessage(...)]."""
-    outer_id = "call-1"
-    result = _invoke_returning(
-        [
-            Command(update={"foo": "bar"}),
-            ToolMessage(content="done", tool_call_id=outer_id),
-        ]
-    )
-    assert isinstance(result, list)
-    commands = [r for r in result if isinstance(r, Command)]
-    assert len(commands) == 1
-    assert commands[0].update == {"foo": "bar"}
-    non_commands = [r for r in result if not isinstance(r, Command)]
-    assert len(non_commands) == 1
-    assert isinstance(non_commands[0], dict)
-    msgs = non_commands[0]["messages"]
-    assert len(msgs) == 1
-    assert isinstance(msgs[0], ToolMessage)
-    assert msgs[0].content == "done"
-    assert msgs[0].tool_call_id == outer_id
-
-
-def test_tool_node_list_return_nested_terminator() -> None:
-    """Valid: terminator nested inside Command.update['messages']."""
-    outer_id = "call-1"
-    result = _invoke_returning(
-        [
-            Command(update={"foo": "bar"}),
-            Command(
-                update={
-                    "messages": [ToolMessage(content="done", tool_call_id=outer_id)]
-                }
-            ),
-        ]
-    )
-    assert isinstance(result, list)
-    commands = [r for r in result if isinstance(r, Command)]
-    assert len(commands) == 2
-    updates = [c.update for c in commands]
-    assert {"foo": "bar"} in updates
-    msgs_update = next(u for u in updates if "messages" in (u or {}))
-    assert any(
-        isinstance(m, ToolMessage) and m.tool_call_id == outer_id
-        for m in msgs_update["messages"]
-    )
-
-
-def test_tool_node_list_return_parent_goto_with_terminator() -> None:
-    """Valid: [Command(graph=PARENT, goto=[Send(...)]), ToolMessage(...)]."""
-    outer_id = "call-1"
-    result = _invoke_returning(
-        [
-            Command(graph=Command.PARENT, goto=[Send("child", {})]),
-            ToolMessage(content="ok", tool_call_id=outer_id),
-        ]
-    )
-    assert isinstance(result, list)
-    parent_cmds = [
-        r for r in result if isinstance(r, Command) and r.graph is Command.PARENT
-    ]
-    assert len(parent_cmds) == 1
-    assert isinstance(parent_cmds[0].goto, list)
-    assert any(isinstance(s, Send) for s in parent_cmds[0].goto)
-    non_commands = [r for r in result if not isinstance(r, Command)]
-    assert len(non_commands) == 1
-
-
-def test_tool_node_list_return_no_terminator_raises() -> None:
-    """Invalid: list with no terminating ToolMessage."""
-    with pytest.raises(ValueError, match="0 messages bound to tool_call_id"):
-        _invoke_returning([Command(update={"foo": "bar"})], handle_tool_errors=False)
-
-
-def test_tool_node_list_return_multiple_terminators_raises() -> None:
-    """Invalid: list with two terminating ToolMessages."""
-    outer_id = "call-1"
-    with pytest.raises(ValueError, match="2 messages bound to tool_call_id"):
-        _invoke_returning(
-            [
-                ToolMessage(content="a", tool_call_id=outer_id),
-                ToolMessage(content="b", tool_call_id=outer_id),
-            ],
-            handle_tool_errors=False,
-        )
-
-
-def test_tool_node_list_return_validation_error_handled() -> None:
-    """handle_tool_errors=True converts validation errors to an error ToolMessage."""
-    result = _invoke_returning([Command(update={"foo": "bar"})])
-    assert isinstance(result, dict)
-    msg = result["messages"][0]
-    assert isinstance(msg, ToolMessage)
-    assert msg.status == "error"
-    assert "0 messages bound to tool_call_id" in msg.content
-
-
-async def test_tool_node_list_return_async_smoke() -> None:
-    """Async path parallels sync for the happy case."""
-    outer_id = "call-1"
-    node = ToolNode(
-        [
-            _ReturningTool(
-                return_value=[
-                    Command(update={"foo": "bar"}),
-                    ToolMessage(content="done", tool_call_id=outer_id),
-                ]
-            )
-        ]
-    )
-    result = await node.ainvoke(
-        {"messages": [AIMessage("", tool_calls=[_list_tool_call(outer_id)])]},
-        config=_create_config_with_runtime(),
-    )
-    assert isinstance(result, list)
-    commands = [r for r in result if isinstance(r, Command)]
-    assert len(commands) == 1 and commands[0].update == {"foo": "bar"}
-
-
-def test_tool_node_list_return_mixed_with_regular_tool() -> None:
-    """List-returning tool and a regular tool dispatched from the same AIMessage."""
-    list_tool_id = "call-list"
-    regular_tool_id = "call-regular"
-    list_tool = _ReturningTool(
-        return_value=[
-            Command(update={"foo": "bar"}),
-            ToolMessage(content="list done", tool_call_id=list_tool_id),
-        ]
-    )
-
-    def regular_tool(x: int) -> str:
-        """A normal tool."""
-        return f"regular: {x}"
-
-    tool_calls = [
-        {"name": "list_tool", "args": {}, "id": list_tool_id, "type": "tool_call"},
-        {
-            "name": "regular_tool",
-            "args": {"x": 7},
-            "id": regular_tool_id,
-            "type": "tool_call",
-        },
-    ]
-    node = ToolNode([list_tool, regular_tool])
-    result = node.invoke(
-        {"messages": [AIMessage("", tool_calls=tool_calls)]},
-        config=_create_config_with_runtime(),
-    )
-    assert isinstance(result, list)
-    commands = [r for r in result if isinstance(r, Command)]
-    assert len(commands) == 1
-    assert commands[0].update == {"foo": "bar"}
-    all_msgs = [m for r in result if isinstance(r, dict) for m in r["messages"]]
-    tool_call_ids = {m.tool_call_id for m in all_msgs}
-    assert list_tool_id in tool_call_ids
-    assert regular_tool_id in tool_call_ids

libs/prebuilt/uv.lock

@@ -249,7 +249,7 @@ wheels = [
 
 [[package]]
 name = "langchain-core"
-version = "1.3.1"
+version = "1.3.0a2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "jsonpatch" },
@@ -261,14 +261,14 @@ dependencies = [
     { name = "typing-extensions" },
     { name = "uuid-utils" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/f4/fe/abeae8d0d2899e191d67c6c7f065f7e52a953f30b21ef327fa49084e4af9/langchain_core-1.3.1.tar.gz", hash = "sha256:41b384055799f93f34520df6bf7b80e2e5e23153cdfd46874251c6c9916ea030", size = 862403, upload-time = "2026-04-23T18:54:01.857Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/af/bc/0bff31fcaff174d86031cc713471a3e85ed4ec8e5cd95ad0217f2aced20e/langchain_core-1.3.0a2.tar.gz", hash = "sha256:52d978c84552b74b9a3f16c1fced84f9e27cc96d7a67c601925ce6cbc4ea3cf9", size = 854580, upload-time = "2026-04-13T14:37:55.745Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/a1/c2/8493be505921857988db068b7c027f28a9b1587b4425c6a32b1221c9c9fe/langchain_core-1.3.1-py3-none-any.whl", hash = "sha256:8b13d19d3bed3f4768df12c7f6932d2ada715f3ac9fd020c63d28c693968269e", size = 515879, upload-time = "2026-04-23T18:53:59.94Z" },
+    { url = "https://files.pythonhosted.org/packages/0e/14/03c09686602567059f26af29de0c44546a83af2f2aa29925e61040e43ea2/langchain_core-1.3.0a2-py3-none-any.whl", hash = "sha256:9e929a34f0b0c6c1255e395a1de34f8626893ceb4cdae550a22a0bd18c87be54", size = 510233, upload-time = "2026-04-13T14:37:54.277Z" },
 ]
 
 [[package]]
 name = "langgraph"
-version = "1.1.10"
+version = "1.1.7a2"
 source = { editable = "../langgraph" }
 dependencies = [
     { name = "langchain-core" },
@@ -281,7 +281,7 @@ dependencies = [
 
 [package.metadata]
 requires-dist = [
-    { name = "langchain-core", specifier = ">=1.3.0,<2" },
+    { name = "langchain-core", specifier = "==1.3.0a2" },
     { name = "langgraph-checkpoint", editable = "../checkpoint" },
     { name = "langgraph-prebuilt", editable = "." },
     { name = "langgraph-sdk", editable = "../sdk-py" },
@@ -352,7 +352,7 @@ test = [
 
 [[package]]
 name = "langgraph-checkpoint"
-version = "4.0.3"
+version = "4.0.2"
 source = { editable = "../checkpoint" }
 dependencies = [
     { name = "langchain-core" },
@@ -490,7 +490,7 @@ test = [
 
 [[package]]
 name = "langgraph-prebuilt"
-version = "1.0.12"
+version = "1.0.9"
 source = { editable = "." }
 dependencies = [
     { name = "langchain-core" },
@@ -535,7 +535,7 @@ test = [
 
 [package.metadata]
 requires-dist = [
-    { name = "langchain-core", specifier = ">=1.3.1" },
+    { name = "langchain-core", specifier = ">=1.0.0" },
     { name = "langgraph-checkpoint", editable = "../checkpoint" },
 ]
 

libs/sdk-py/uv.lock

@@ -262,7 +262,7 @@ wheels = [
 
 [[package]]
 name = "langchain-core"
-version = "1.3.1"
+version = "1.3.0a2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "jsonpatch" },
@@ -274,14 +274,14 @@ dependencies = [
     { name = "typing-extensions" },
     { name = "uuid-utils" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/f4/fe/abeae8d0d2899e191d67c6c7f065f7e52a953f30b21ef327fa49084e4af9/langchain_core-1.3.1.tar.gz", hash = "sha256:41b384055799f93f34520df6bf7b80e2e5e23153cdfd46874251c6c9916ea030", size = 862403, upload-time = "2026-04-23T18:54:01.857Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/af/bc/0bff31fcaff174d86031cc713471a3e85ed4ec8e5cd95ad0217f2aced20e/langchain_core-1.3.0a2.tar.gz", hash = "sha256:52d978c84552b74b9a3f16c1fced84f9e27cc96d7a67c601925ce6cbc4ea3cf9", size = 854580, upload-time = "2026-04-13T14:37:55.745Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/a1/c2/8493be505921857988db068b7c027f28a9b1587b4425c6a32b1221c9c9fe/langchain_core-1.3.1-py3-none-any.whl", hash = "sha256:8b13d19d3bed3f4768df12c7f6932d2ada715f3ac9fd020c63d28c693968269e", size = 515879, upload-time = "2026-04-23T18:53:59.94Z" },
+    { url = "https://files.pythonhosted.org/packages/0e/14/03c09686602567059f26af29de0c44546a83af2f2aa29925e61040e43ea2/langchain_core-1.3.0a2-py3-none-any.whl", hash = "sha256:9e929a34f0b0c6c1255e395a1de34f8626893ceb4cdae550a22a0bd18c87be54", size = 510233, upload-time = "2026-04-13T14:37:54.277Z" },
 ]
 
 [[package]]
 name = "langgraph"
-version = "1.1.10"
+version = "1.1.7a2"
 source = { editable = "../langgraph" }
 dependencies = [
     { name = "langchain-core" },
@@ -294,7 +294,7 @@ dependencies = [
 
 [package.metadata]
 requires-dist = [
-    { name = "langchain-core", specifier = ">=1.3.0,<2" },
+    { name = "langchain-core", specifier = "==1.3.0a2" },
     { name = "langgraph-checkpoint", editable = "../checkpoint" },
     { name = "langgraph-prebuilt", editable = "../prebuilt" },
     { name = "langgraph-sdk", editable = "." },
@@ -365,7 +365,7 @@ test = [
 
 [[package]]
 name = "langgraph-checkpoint"
-version = "4.0.3"
+version = "4.0.2"
 source = { editable = "../checkpoint" }
 dependencies = [
     { name = "langchain-core" },
@@ -413,7 +413,7 @@ test = [
 
 [[package]]
 name = "langgraph-prebuilt"
-version = "1.0.12"
+version = "1.0.9"
 source = { editable = "../prebuilt" }
 dependencies = [
     { name = "langchain-core" },
@@ -422,7 +422,7 @@ dependencies = [
 
 [package.metadata]
 requires-dist = [
-    { name = "langchain-core", specifier = ">=1.3.1" },
+    { name = "langchain-core", specifier = ">=1.0.0" },
     { name = "langgraph-checkpoint", editable = "../checkpoint" },
 ]