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.

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

@@ -8,13 +8,11 @@ from typing import Any
 
 from langchain_core.runnables import RunnableConfig
 from langgraph.checkpoint.base import (
-    DELTA_SENTINEL,
     WRITES_IDX_MAP,
     ChannelVersions,
     Checkpoint,
     CheckpointMetadata,
     CheckpointTuple,
-    _ChannelWritesHistory,
     get_checkpoint_id,
     get_serializable_checkpoint_metadata,
 )
@@ -25,12 +23,7 @@ from psycopg.types.json import Jsonb
 from psycopg_pool import ConnectionPool
 
 from langgraph.checkpoint.postgres import _internal
-from langgraph.checkpoint.postgres.base import (
-    SELECT_DELTA_BLOBS_SQL,
-    SELECT_DELTA_PARENTS_SQL,
-    SELECT_DELTA_WRITES_SQL,
-    BasePostgresSaver,
-)
+from langgraph.checkpoint.postgres.base import BasePostgresSaver
 from langgraph.checkpoint.postgres.shallow import ShallowPostgresSaver
 
 Conn = _internal.Conn  # For backward compatibility
@@ -437,41 +430,42 @@ class PostgresSaver(BasePostgresSaver):
                 with conn.cursor(binary=True, row_factory=dict_row) as cur:
                     yield cur
 
-    def _get_channel_writes_history(
-        self, config: RunnableConfig, channel: str
-    ) -> _ChannelWritesHistory:
-        """Fast-path override of `BaseCheckpointSaver._get_channel_writes_history`.
-
-        Three indexed roundtrips (`checkpoints`, `checkpoint_writes`,
-        `checkpoint_blobs`) each filtered by `(thread_id, checkpoint_ns)` and
-        the per-table key. Plain SELECTs let the planner pick straight index
-        scans; rationale + benchmark in `notes/delta_channel_query_bench.md`.
-        """
-        thread_id = config["configurable"]["thread_id"]
-        checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
-        checkpoint_id = get_checkpoint_id(config)
-        if checkpoint_id is None:
-            # Caller didn't specify a target — resolve to the latest
-            # checkpoint on the thread. `get_tuple` without `checkpoint_id`
-            # returns the newest; its config carries the resolved id.
-            target = self.get_tuple(config)
-            if target is None:
-                return _ChannelWritesHistory(seed=DELTA_SENTINEL, writes=[])
-            checkpoint_id = target.config["configurable"]["checkpoint_id"]
+    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_DELTA_PARENTS_SQL, (channel, thread_id, checkpoint_ns))
-            parents_rows = cur.fetchall()
-            cur.execute(SELECT_DELTA_WRITES_SQL, (thread_id, checkpoint_ns, channel))
-            writes_rows = cur.fetchall()
-            cur.execute(SELECT_DELTA_BLOBS_SQL, (thread_id, checkpoint_ns, channel))
-            blobs_rows = cur.fetchall()
-        return self._build_delta_channel_writes_history(
-            channel=channel,
-            target_id=checkpoint_id,
-            parents_rows=parents_rows,
-            writes_rows=writes_rows,
-            blobs_rows=blobs_rows,
-        )
+            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:
         """
@@ -485,7 +479,13 @@ class PostgresSaver(BasePostgresSaver):
             including its configuration, metadata, parent checkpoint (if any),
             and pending writes.
         """
-        channel_values = self._load_blobs(value["channel_values"])
+        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": {

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

@@ -8,13 +8,11 @@ from typing import Any
 
 from langchain_core.runnables import RunnableConfig
 from langgraph.checkpoint.base import (
-    DELTA_SENTINEL,
     WRITES_IDX_MAP,
     ChannelVersions,
     Checkpoint,
     CheckpointMetadata,
     CheckpointTuple,
-    _ChannelWritesHistory,
     get_checkpoint_id,
     get_serializable_checkpoint_metadata,
 )
@@ -25,12 +23,7 @@ from psycopg.types.json import Jsonb
 from psycopg_pool import AsyncConnectionPool
 
 from langgraph.checkpoint.postgres import _ainternal
-from langgraph.checkpoint.postgres.base import (
-    SELECT_DELTA_BLOBS_SQL,
-    SELECT_DELTA_PARENTS_SQL,
-    SELECT_DELTA_WRITES_SQL,
-    BasePostgresSaver,
-)
+from langgraph.checkpoint.postgres.base import BasePostgresSaver
 from langgraph.checkpoint.postgres.shallow import AsyncShallowPostgresSaver
 
 Conn = _ainternal.Conn  # For backward compatibility
@@ -398,44 +391,42 @@ class AsyncPostgresSaver(BasePostgresSaver):
                 async with conn.cursor(binary=True, row_factory=dict_row) as cur:
                     yield cur
 
-    async def _aget_channel_writes_history(
-        self, config: RunnableConfig, channel: str
-    ) -> _ChannelWritesHistory:
-        """Fast-path override of `BaseCheckpointSaver._aget_channel_writes_history`.
-
-        Three indexed roundtrips (`checkpoints`, `checkpoint_writes`,
-        `checkpoint_blobs`); rows assembled by the shared pure helper on
-        `BasePostgresSaver`. Rationale + benchmark in
-        `notes/delta_channel_query_bench.md`.
-        """
-        thread_id = config["configurable"]["thread_id"]
-        checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
-        checkpoint_id = get_checkpoint_id(config)
-        if checkpoint_id is None:
-            target = await self.aget_tuple(config)
-            if target is None:
-                return _ChannelWritesHistory(seed=DELTA_SENTINEL, writes=[])
-            checkpoint_id = target.config["configurable"]["checkpoint_id"]
+    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_DELTA_PARENTS_SQL, (channel, thread_id, checkpoint_ns)
+                """
+                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,
+                ),
             )
-            parents_rows = await cur.fetchall()
-            await cur.execute(
-                SELECT_DELTA_WRITES_SQL, (thread_id, checkpoint_ns, channel)
-            )
-            writes_rows = await cur.fetchall()
-            await cur.execute(
-                SELECT_DELTA_BLOBS_SQL, (thread_id, checkpoint_ns, channel)
-            )
-            blobs_rows = await cur.fetchall()
-        return self._build_delta_channel_writes_history(
-            channel=channel,
-            target_id=checkpoint_id,
-            parents_rows=parents_rows,
-            writes_rows=writes_rows,
-            blobs_rows=blobs_rows,
-        )
+            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:
         """
@@ -452,6 +443,7 @@ class AsyncPostgresSaver(BasePostgresSaver):
         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)

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

@@ -8,15 +8,12 @@ from typing import Any, cast
 
 from langchain_core.runnables import RunnableConfig
 from langgraph.checkpoint.base import (
-    DELTA_SENTINEL,
     WRITES_IDX_MAP,
     BaseCheckpointSaver,
     ChannelVersions,
-    PendingWrite,
-    _ChannelWritesHistory,
     get_checkpoint_id,
 )
-from langgraph.checkpoint.serde.types import TASKS, _DeltaSnapshot
+from langgraph.checkpoint.serde.types import TASKS
 from psycopg.types.json import Jsonb
 
 MetadataInput = dict[str, Any] | None
@@ -155,30 +152,6 @@ INSERT_CHECKPOINT_WRITES_SQL = """
     ON CONFLICT (thread_id, checkpoint_ns, checkpoint_id, task_id, idx) DO NOTHING
 """
 
-# DeltaChannel reconstruction: three plain indexed SELECTs per channel.
-# Bench (notes/delta_channel_query_bench.md) showed the prior recursive CTE
-# carried a hidden O(ancestors x blobs_in_thread) join; plain SELECTs are
-# 3x-100x faster in the realistic depth range and the Python walk is O(n).
-SELECT_DELTA_PARENTS_SQL = """
-    SELECT checkpoint_id,
-           parent_checkpoint_id,
-           checkpoint -> 'channel_versions' ->> %s AS ver
-    FROM checkpoints
-    WHERE thread_id = %s AND checkpoint_ns = %s
-"""
-
-SELECT_DELTA_WRITES_SQL = """
-    SELECT checkpoint_id, type, blob, task_id, idx
-    FROM checkpoint_writes
-    WHERE thread_id = %s AND checkpoint_ns = %s AND channel = %s
-"""
-
-SELECT_DELTA_BLOBS_SQL = """
-    SELECT version, type, blob
-    FROM checkpoint_blobs
-    WHERE thread_id = %s AND checkpoint_ns = %s AND channel = %s
-"""
-
 
 class BasePostgresSaver(BaseCheckpointSaver[str]):
     SELECT_SQL = SELECT_SQL
@@ -213,106 +186,22 @@ class BasePostgresSaver(BaseCheckpointSaver[str]):
 
     def _load_blobs(
         self,
-        blob_values: Any,
+        blob_values: list[tuple[bytes, bytes, bytes]],
+        *,
+        thread_id: str = "",
+        checkpoint_ns: str = "",
+        cur: Any = None,
     ) -> dict[str, Any]:
         if not blob_values:
             return {}
         result: dict[str, Any] = {}
         for k, t, v in blob_values:
+            channel = k.decode()
             type_tag = t.decode()
             if type_tag != "empty":
-                result[k.decode()] = self.serde.loads_typed((type_tag, v))
+                result[channel] = self.serde.loads_typed((type_tag, v))
         return result
 
-    def _build_delta_channel_writes_history(
-        self,
-        *,
-        channel: str,
-        target_id: str,
-        parents_rows: Sequence[Any],
-        writes_rows: Sequence[Any],
-        blobs_rows: Sequence[Any],
-    ) -> _ChannelWritesHistory:
-        """Reconstruct one delta channel's history from rows of the three SELECTs.
-
-        Pure data transform shared by sync (`PostgresSaver`) and async
-        (`AsyncPostgresSaver`); both paths run the queries themselves and
-        feed the rows here.
-
-        Walk is newest → oldest from the target's parent. A non-sentinel
-        blob in `checkpoint_blobs` (a pre-delta snapshot) terminates the
-        walk and is returned as the seed so replay starts from it.
-
-        Writes stored at `target_id` itself are pending writes for the next
-        step and are excluded — the walk begins at the target's parent.
-        """
-        parent_of: dict[str, str | None] = {}
-        ver_of: dict[str, str | None] = {}
-        for r in parents_rows:
-            cid = r["checkpoint_id"]
-            parent_of[cid] = r["parent_checkpoint_id"]
-            ver_of[cid] = r["ver"]
-
-        ancestors: list[str] = []
-        cid = parent_of.get(target_id)
-        while cid is not None:
-            ancestors.append(cid)
-            cid = parent_of.get(cid)
-        if not ancestors:
-            return _ChannelWritesHistory(seed=DELTA_SENTINEL, writes=[])
-        ancestor_set = set(ancestors)
-
-        # Group writes by ancestor cid; sort within (task_id DESC, idx DESC)
-        # to match the prior CTE ordering — newest write first per ancestor.
-        writes_by_cid: dict[str, list[tuple[str, bytes, str, int]]] = {}
-        for r in writes_rows:
-            cid = r["checkpoint_id"]
-            if cid not in ancestor_set:
-                continue
-            writes_by_cid.setdefault(cid, []).append(
-                (r["type"], r["blob"], r["task_id"], r["idx"])
-            )
-        for ws in writes_by_cid.values():
-            ws.sort(key=lambda w: (w[2], w[3]), reverse=True)
-
-        blob_by_ver: dict[str, tuple[str, bytes]] = {
-            r["version"]: (r["type"], r["blob"]) for r in blobs_rows
-        }
-
-        collected: list[PendingWrite] = []  # newest first; reversed at the end
-        for cid in ancestors:
-            ver = ver_of.get(cid)
-            if ver is not None:
-                seed_blob = blob_by_ver.get(ver)
-                if seed_blob is not None and seed_blob[0] != "empty":
-                    blob_value = self.serde.loads_typed(seed_blob)
-                    if blob_value is not DELTA_SENTINEL:
-                        if isinstance(blob_value, _DeltaSnapshot):
-                            # Step-based snapshot: collect this ancestor's
-                            # pending_writes first (they encode the NEXT step's
-                            # transition, not subsumed by the snapshot blob).
-                            for (
-                                type_tag,
-                                write_blob,
-                                task_id,
-                                _idx,
-                            ) in writes_by_cid.get(cid, []):
-                                val = self.serde.loads_typed((type_tag, write_blob))
-                                collected.append((task_id, channel, val))
-                            collected.reverse()
-                            return _ChannelWritesHistory(
-                                seed=blob_value, writes=collected
-                            )
-                        # Pre-delta blob: subsumes this ancestor's writes.
-                        collected.reverse()
-                        return _ChannelWritesHistory(seed=blob_value, writes=collected)
-            for type_tag, write_blob, task_id, _idx in writes_by_cid.get(cid, []):
-                val = self.serde.loads_typed((type_tag, write_blob))
-                collected.append((task_id, channel, val))
-
-        collected.reverse()  # oldest → newest
-        return _ChannelWritesHistory(seed=DELTA_SENTINEL, writes=collected)
-
     def _dump_blobs(
         self,
         thread_id: str,

libs/checkpoint-postgres/tests/test_async.py

@@ -361,9 +361,9 @@ async def test_get_checkpoint_no_channel_values(
 
         load_checkpoint_tuple = saver._load_checkpoint_tuple
 
-        async def patched_load_checkpoint_tuple(value):
+        def patched_load_checkpoint_tuple(value):
             value["checkpoint"].pop("channel_values", None)
-            return await load_checkpoint_tuple(value)
+            return load_checkpoint_tuple(value)
 
         monkeypatch.setattr(
             saver, "_load_checkpoint_tuple", patched_load_checkpoint_tuple

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

@@ -1,10 +1,11 @@
 from __future__ import annotations
 
-import contextvars
+import asyncio
 import copy
+import dataclasses
 import logging
 from collections.abc import AsyncIterator, Collection, Iterator, Mapping, Sequence
-from typing import (
+from typing import (  # noqa: UP035
     Any,
     Generic,
     Literal,
@@ -19,31 +20,56 @@ from langgraph.checkpoint.base.id import uuid6
 from langgraph.checkpoint.serde.base import SerializerProtocol, maybe_add_typed_methods
 from langgraph.checkpoint.serde.encrypted import EncryptedSerializer
 from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
-from langgraph.checkpoint.serde.types import (
-    DELTA_SENTINEL as DELTA_SENTINEL,
-)
 from langgraph.checkpoint.serde.types import (
     ERROR,
     INTERRUPT,
     RESUME,
     SCHEDULED,
     ChannelProtocol,
-    _DeltaSnapshot,
 )
 
 V = TypeVar("V", int, float, str)
 PendingWrite = tuple[str, str, Any]
 
-# Task-local guard: ContextVar is copied per asyncio Task, so concurrent
-# requests on the same event-loop thread do not share this flag. A plain
-# `threading.local()` would leak across tasks and let one in-flight
-# reconstruction silently short-circuit another.
-_DELTA_RECONSTRUCTION: contextvars.ContextVar[bool] = contextvars.ContextVar(
-    "_DELTA_RECONSTRUCTION", default=False
-)
+
+@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.
@@ -134,30 +160,6 @@ class CheckpointTuple(NamedTuple):
     pending_writes: list[PendingWrite] | None = None
 
 
-class _ChannelWritesHistory(NamedTuple):
-    """Result of `BaseCheckpointSaver._get_channel_writes_history`.
-
-    Storage-level view of what one channel wrote across the ancestor chain
-    of a target checkpoint:
-
-      * `seed` — the nearest ancestor's stored blob value for this channel,
-        or `DELTA_SENTINEL` if the walk reached the root without finding a
-        stored value. A non-sentinel seed typically indicates a pre-delta
-        snapshot preserved across a channel-type migration (e.g.
-        `BinaryOperatorAggregate` storage extended under `DeltaChannel`).
-      * `writes` — on-path deltas oldest→newest, one `PendingWrite` per
-        step that wrote to this channel. Writes stored at the target
-        checkpoint itself are pending for the next super-step and are
-        excluded.
-
-    Experimental: method surface may change; the NamedTuple shape is the
-    contract.
-    """
-
-    seed: Any
-    writes: list[PendingWrite]
-
-
 class BaseCheckpointSaver(Generic[V]):
     """Base class for creating a graph checkpointer.
 
@@ -496,120 +498,171 @@ class BaseCheckpointSaver(Generic[V]):
         """
         raise NotImplementedError
 
-    def _get_channel_writes_history(
-        self, config: RunnableConfig, channel: str
-    ) -> _ChannelWritesHistory:
-        """**Experimental.** Query one channel's writes along the parent chain.
+    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
 
-        Storage-level query, not channel semantics: returns `(seed, writes)`
-        reflecting what storage knows about a single channel across the
-        ancestor chain of the target checkpoint identified by `config`.
+        thread_id = str(config["configurable"]["thread_id"])
+        checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
+        current_checkpoint_id = checkpoint.get("id")
+        assembled: dict[str, Any] = {}
 
-        * `writes` — on-path deltas oldest→newest as `PendingWrite` tuples.
-          Writes stored at the target `checkpoint_id` itself are pending
-          for the next super-step and are excluded.
-        * `seed` — the nearest ancestor's stored blob value for this
-          channel; `DELTA_SENTINEL` if the walk reached the root without
-          finding a stored value. A non-sentinel seed typically indicates
-          a pre-delta snapshot preserved across a channel-type migration.
+        for spec in plan.channels:
+            value = checkpoint["channel_values"].get(spec.name)
+            if spec.kind != "delta" or not isinstance(value, DeltaValue):
+                continue
 
-        Walks the **parent chain** (not `list(before=...)`): for forked
-        threads, only on-path ancestors contribute.
+            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
 
-        Reference implementation walks `get_tuple` + `parent_config`,
-        inspecting each ancestor's `channel_values[channel]` for the seed
-        terminator. Savers with direct storage access (`InMemorySaver`,
-        `PostgresSaver`) override for performance; the return contract is
-        fixed here.
+        if not assembled:
+            return checkpoint
 
-        Underscore-prefixed because the method surface is experimental.
+        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.
         """
-        # Guard against re-entrant calls: when get_tuple() triggers
-        # reconstruction which calls get_tuple() again, the inner call
-        # short-circuits here.
-        if _DELTA_RECONSTRUCTION.get():
-            return _ChannelWritesHistory(seed=DELTA_SENTINEL, writes=[])
+        return NotImplemented
 
-        token = _DELTA_RECONSTRUCTION.set(True)
-        try:
-            collected: list[PendingWrite] = []  # newest first; reversed at the end
-            target_tuple = self.get_tuple(config)
-            cursor_config: RunnableConfig | None = (
-                target_tuple.parent_config if target_tuple else None
-            )
-            while cursor_config is not None:
-                tup = self.get_tuple(cursor_config)
-                if tup is None:
-                    break
-                # Pre-delta seed terminator: if the ancestor has a stored
-                # (non-sentinel) value for this channel, that snapshot
-                # subsumes any earlier writes on the chain. Stop here.
-                ancestor_value = tup.checkpoint["channel_values"].get(channel)
-                if ancestor_value is not None and ancestor_value is not DELTA_SENTINEL:
-                    if isinstance(ancestor_value, _DeltaSnapshot):
-                        # Step-based snapshot: the blob is state AT this ancestor,
-                        # but pending_writes encode the NEXT step's transition and
-                        # are NOT subsumed — collect them before terminating.
-                        if tup.pending_writes:
-                            for write in reversed(tup.pending_writes):
-                                if write[1] != channel:
-                                    continue
-                                collected.append(write)
-                    # Pre-delta blob: subsumes its own writes — stop immediately.
-                    collected.reverse()
-                    return _ChannelWritesHistory(seed=ancestor_value, writes=collected)
-                if tup.pending_writes:
-                    # Within a superstep, pending_writes are oldest→newest;
-                    # reverse to scan newest-first.
-                    for write in reversed(tup.pending_writes):
-                        if write[1] != channel:
-                            continue
-                        collected.append(write)
-                cursor_config = tup.parent_config
-            collected.reverse()
-            return _ChannelWritesHistory(seed=DELTA_SENTINEL, writes=collected)
-        finally:
-            _DELTA_RECONSTRUCTION.reset(token)
+    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).
 
-    async def _aget_channel_writes_history(
-        self, config: RunnableConfig, channel: str
-    ) -> _ChannelWritesHistory:
-        """Async version of `_get_channel_writes_history`. See docstring there."""
-        if _DELTA_RECONSTRUCTION.get():
-            return _ChannelWritesHistory(seed=DELTA_SENTINEL, writes=[])
+        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.
 
-        token = _DELTA_RECONSTRUCTION.set(True)
-        try:
-            collected: list[PendingWrite] = []
-            target_tuple = await self.aget_tuple(config)
-            cursor_config: RunnableConfig | None = (
-                target_tuple.parent_config if target_tuple else None
-            )
-            while cursor_config is not None:
-                tup = await self.aget_tuple(cursor_config)
-                if tup is None:
-                    break
-                # See sync variant for rationale.
-                ancestor_value = tup.checkpoint["channel_values"].get(channel)
-                if ancestor_value is not None and ancestor_value is not DELTA_SENTINEL:
-                    if isinstance(ancestor_value, _DeltaSnapshot):
-                        if tup.pending_writes:
-                            for write in reversed(tup.pending_writes):
-                                if write[1] != channel:
-                                    continue
-                                collected.append(write)
-                    collected.reverse()
-                    return _ChannelWritesHistory(seed=ancestor_value, writes=collected)
-                if tup.pending_writes:
-                    for write in reversed(tup.pending_writes):
-                        if write[1] != channel:
-                            continue
-                        collected.append(write)
-                cursor_config = tup.parent_config
-            collected.reverse()
-            return _ChannelWritesHistory(seed=DELTA_SENTINEL, writes=collected)
-        finally:
-            _DELTA_RECONSTRUCTION.reset(token)
+        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.
@@ -643,6 +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

@@ -9,25 +9,21 @@ from collections import defaultdict
 from collections.abc import AsyncIterator, Iterator, Sequence
 from contextlib import AbstractAsyncContextManager, AbstractContextManager, ExitStack
 from types import TracebackType
-from typing import Any, cast
+from typing import Any
 
 from langchain_core.runnables import RunnableConfig
 
 from langgraph.checkpoint.base import (
-    DELTA_SENTINEL,
     WRITES_IDX_MAP,
     BaseCheckpointSaver,
     ChannelVersions,
     Checkpoint,
     CheckpointMetadata,
     CheckpointTuple,
-    PendingWrite,
     SerializerProtocol,
-    _ChannelWritesHistory,
     get_checkpoint_id,
     get_checkpoint_metadata,
 )
-from langgraph.checkpoint.serde.types import _DeltaSnapshot
 
 logger = logging.getLogger(__name__)
 
@@ -125,114 +121,50 @@ class InMemorySaver(
         return self.stack.__exit__(__exc_type, __exc_value, __traceback)
 
     def _load_blobs(
-        self,
-        thread_id: str,
-        checkpoint_ns: str,
-        versions: ChannelVersions,
+        self, thread_id: str, checkpoint_ns: str, versions: ChannelVersions
     ) -> dict[str, Any]:
-        result: dict[str, Any] = {}
-        for k, ver in versions.items():
-            kk = (thread_id, checkpoint_ns, k, ver)
+        channel_values: dict[str, Any] = {}
+        for k, v in versions.items():
+            kk = (thread_id, checkpoint_ns, k, v)
             if kk not in self.blobs:
                 continue
             vv = self.blobs[kk]
-            if vv[0] == "empty":
-                continue
-            result[k] = self.serde.loads_typed(vv)
-        return result
+            if vv[0] != "empty":
+                channel_values[k] = self.serde.loads_typed(vv)
+        return channel_values
 
-    def _get_channel_writes_history(
-        self, config: RunnableConfig, channel: str
-    ) -> _ChannelWritesHistory:
-        thread_id = config["configurable"]["thread_id"]
-        checkpoint_ns = config["configurable"].get("checkpoint_ns", "")
-        checkpoint_id = config["configurable"].get("checkpoint_id", "")
+    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, {})
-        # Walk the parent chain newest→oldest. Skip the target itself —
-        # writes stored AT `checkpoint_id` are pending for the next step
-        # (pregel applies them via `apply_writes`; they aren't part of the
-        # snapshot value AT `checkpoint_id`).
-        chain: list[str] = []
-        target_entry = ns_storage.get(checkpoint_id)
-        current: str | None = target_entry[2] if target_entry is not None else None
-        while current is not None:
-            entry = ns_storage.get(current)
-            if entry is None:
-                break
-            chain.append(current)
-            _, _, parent = entry
-            current = parent
-        # Scan newest→oldest. A pre-delta blob on an ancestor terminates the
-        # walk and is bound as `seed`; without this, a thread migrated from
-        # pre-delta storage would replay ancestor writes all the way to the
-        # root AND miss any value that lived only in the old blob (e.g. from
-        # `update_state`).
-        #
-        # At each ancestor, check the blob BEFORE processing its pending
-        # writes: a pre-delta blob represents the state AT that ancestor,
-        # which already subsumes any writes stored under it. Processing
-        # those writes first would fold them into the reconstructed value
-        # twice (once via the blob, once via replay).
-        collected: list[PendingWrite] = []  # newest first
-        for cp_id in chain:  # newest → oldest
-            entry = ns_storage.get(cp_id)
-            if entry is not None:
-                ckpt = self.serde.loads_typed(entry[0])
-                ver = ckpt.get("channel_versions", {}).get(channel)
-                if ver is not None:
-                    blob_entry = self.blobs.get(
-                        (thread_id, checkpoint_ns, channel, ver)
-                    )
-                    if blob_entry is not None and blob_entry[0] != "empty":
-                        blob_value = self.serde.loads_typed(blob_entry)
-                        if blob_value is not DELTA_SENTINEL:
-                            if isinstance(blob_value, _DeltaSnapshot):
-                                # Step-based snapshot: the blob is state AT this
-                                # ancestor, but the ancestor's pending_writes
-                                # encode the NEXT step's transition and are NOT
-                                # subsumed by the snapshot — collect them first.
-                                step_writes = self.writes.get(
-                                    (thread_id, checkpoint_ns, cp_id), {}
-                                )
-                                for (_task_id, _idx), (
-                                    tid,
-                                    ch,
-                                    serialized,
-                                    _,
-                                ) in sorted(step_writes.items(), reverse=True):
-                                    if ch != channel:
-                                        continue
-                                    collected.append(
-                                        (tid, ch, self.serde.loads_typed(serialized))
-                                    )
-                                collected.reverse()
-                                return _ChannelWritesHistory(
-                                    seed=blob_value, writes=collected
-                                )
-                            # Pre-delta blob: state AT this ancestor already
-                            # subsumes its pending_writes — skip them.
-                            collected.reverse()
-                            return _ChannelWritesHistory(
-                                seed=blob_value, writes=collected
-                            )
+        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)
 
-            step_writes = self.writes.get((thread_id, checkpoint_ns, cp_id), {})
-            # Within a superstep, sorted by (task_id, idx) = oldest → newest;
-            # reverse for newest-first scan.
-            for (_task_id, _idx), (tid, ch, serialized, _) in sorted(
-                step_writes.items(), reverse=True
-            ):
-                if ch != channel:
-                    continue
-                val = self.serde.loads_typed(serialized)
-                collected.append((tid, ch, val))
-        collected.reverse()
-        return _ChannelWritesHistory(seed=DELTA_SENTINEL, writes=collected)
-
-    async def _aget_channel_writes_history(
-        self, config: RunnableConfig, channel: str
-    ) -> _ChannelWritesHistory:
-        return self._get_channel_writes_history(config, channel)
+    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.
@@ -255,16 +187,13 @@ class InMemorySaver(
                 checkpoint, metadata, parent_checkpoint_id = saved
                 writes = self.writes[(thread_id, checkpoint_ns, checkpoint_id)].values()
                 checkpoint_: Checkpoint = self.serde.loads_typed(checkpoint)
-                channel_values = self._load_blobs(
-                    thread_id,
-                    checkpoint_ns,
-                    checkpoint_["channel_versions"],
-                )
                 return CheckpointTuple(
                     config=config,
                     checkpoint={
                         **checkpoint_,
-                        "channel_values": channel_values,
+                        "channel_values": self._load_blobs(
+                            thread_id, checkpoint_ns, checkpoint_["channel_versions"]
+                        ),
                     },
                     metadata=self.serde.loads_typed(metadata),
                     pending_writes=[
@@ -288,26 +217,19 @@ class InMemorySaver(
                 checkpoint, metadata, parent_checkpoint_id = checkpoints[checkpoint_id]
                 writes = self.writes[(thread_id, checkpoint_ns, checkpoint_id)].values()
                 checkpoint_ = self.serde.loads_typed(checkpoint)
-                resolved_config = cast(
-                    RunnableConfig,
-                    {
+                return CheckpointTuple(
+                    config={
                         "configurable": {
                             "thread_id": thread_id,
                             "checkpoint_ns": checkpoint_ns,
                             "checkpoint_id": checkpoint_id,
                         }
                     },
-                )
-                channel_values = self._load_blobs(
-                    thread_id,
-                    checkpoint_ns,
-                    checkpoint_["channel_versions"],
-                )
-                return CheckpointTuple(
-                    config=resolved_config,
                     checkpoint={
                         **checkpoint_,
-                        "channel_values": channel_values,
+                        "channel_values": self._load_blobs(
+                            thread_id, checkpoint_ns, checkpoint_["channel_versions"]
+                        ),
                     },
                     metadata=self.serde.loads_typed(metadata),
                     pending_writes=[
@@ -402,27 +324,21 @@ class InMemorySaver(
 
                     checkpoint_: Checkpoint = self.serde.loads_typed(checkpoint)
 
-                    list_config = cast(
-                        RunnableConfig,
-                        {
+                    yield CheckpointTuple(
+                        config={
                             "configurable": {
                                 "thread_id": thread_id,
                                 "checkpoint_ns": checkpoint_ns,
                                 "checkpoint_id": checkpoint_id,
                             }
                         },
-                    )
-                    channel_values = self._load_blobs(
-                        thread_id,
-                        checkpoint_ns,
-                        checkpoint_["channel_versions"],
-                    )
-
-                    yield CheckpointTuple(
-                        config=list_config,
                         checkpoint={
                             **checkpoint_,
-                            "channel_values": channel_values,
+                            "channel_values": self._load_blobs(
+                                thread_id,
+                                checkpoint_ns,
+                                checkpoint_["channel_versions"],
+                            ),
                         },
                         metadata=metadata,
                         parent_config=(
@@ -525,101 +441,6 @@ class InMemorySaver(
                 task_path,
             )
 
-    def prune(
-        self,
-        thread_ids: Sequence[str],
-        *,
-        strategy: str = "keep_latest",
-    ) -> None:
-        """Prune checkpoints for the given threads.
-
-        For DeltaChannel channels, a checkpoint is only deleted if the walk
-        from the latest checkpoint would not need to traverse it — i.e., a
-        `_DeltaSnapshot` blob exists in the kept ancestry that covers all
-        sentinel channels.  Checkpoints that are still in the active walk
-        chain (because no snapshot has been taken yet, e.g. with
-        `snapshot_frequency=None`) are retained.
-
-        Args:
-            thread_ids: Thread IDs to prune.
-            strategy: ``"keep_latest"`` keeps only the most recent checkpoint
-                per namespace; ``"delete"`` removes all checkpoints.
-        """
-        for thread_id in thread_ids:
-            if strategy == "delete":
-                self.delete_thread(thread_id)
-                continue
-
-            if strategy != "keep_latest":
-                raise ValueError(
-                    f"Unknown pruning strategy {strategy!r}. "
-                    "Expected 'keep_latest' or 'delete'."
-                )
-
-            for checkpoint_ns, ns_storage in list(
-                self.storage.get(thread_id, {}).items()
-            ):
-                if not ns_storage:
-                    continue
-
-                # Latest checkpoint (uuid6 IDs are lexicographically monotonic)
-                latest_id = max(ns_storage.keys())
-                latest_data, _, _ = ns_storage[latest_id]
-                latest_cp = self.serde.loads_typed(latest_data)
-
-                # Which channels in the latest checkpoint still have sentinels?
-                sentinel_channels: set[str] = set()
-                for ch, ver in latest_cp.get("channel_versions", {}).items():
-                    blob = self.blobs.get((thread_id, checkpoint_ns, ch, ver))
-                    if blob is not None and blob[0] != "empty":
-                        if self.serde.loads_typed(blob) is DELTA_SENTINEL:
-                            sentinel_channels.add(ch)
-
-                # Walk the parent chain to find the oldest ancestor still needed.
-                # We stop (and mark "safe to prune before here") when all
-                # sentinel channels are covered by a non-sentinel blob.
-                required_ids: set[str] = {latest_id}
-                if sentinel_channels:
-                    _, _, parent_id = ns_storage[latest_id]
-                    remaining = set(sentinel_channels)
-                    while parent_id is not None and remaining:
-                        entry = ns_storage.get(parent_id)
-                        if entry is None:
-                            break
-                        required_ids.add(parent_id)
-                        cp_data, _, grandparent_id = entry
-                        cp = self.serde.loads_typed(cp_data)
-                        resolved: set[str] = set()
-                        for ch in remaining:
-                            ver = cp.get("channel_versions", {}).get(ch)
-                            if ver is None:
-                                continue
-                            blob = self.blobs.get((thread_id, checkpoint_ns, ch, ver))
-                            if blob is not None and blob[0] != "empty":
-                                if self.serde.loads_typed(blob) is not DELTA_SENTINEL:
-                                    resolved.add(ch)
-                        remaining -= resolved
-                        parent_id = grandparent_id
-
-                # Delete everything outside the required set
-                for cp_id in list(ns_storage.keys()):
-                    if cp_id in required_ids:
-                        continue
-                    cp_data, _, _ = ns_storage.pop(cp_id)
-                    self.writes.pop((thread_id, checkpoint_ns, cp_id), None)
-
-                # Clean up blobs no longer referenced by any kept checkpoint
-                live: set[tuple[str, str, str, Any]] = set()
-                for cp_data, _, _ in ns_storage.values():
-                    cp = self.serde.loads_typed(cp_data)
-                    for ch, ver in cp.get("channel_versions", {}).items():
-                        live.add((thread_id, checkpoint_ns, ch, ver))
-                for key in [
-                    k for k in self.blobs if k[:2] == (thread_id, checkpoint_ns)
-                ]:
-                    if key not in live:
-                        del self.blobs[key]
-
     def delete_thread(self, thread_id: str) -> None:
         """Delete all checkpoints and writes associated with a thread ID.
 

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

@@ -33,39 +33,24 @@ from langchain_core.load.load import Reviver
 from langgraph.checkpoint.serde import _msgpack as _lg_msgpack
 from langgraph.checkpoint.serde.base import SerializerProtocol
 from langgraph.checkpoint.serde.event_hooks import emit_serde_event
-from langgraph.checkpoint.serde.types import (
-    DELTA_SENTINEL,
-    SendProtocol,
-    _DeltaSentinel,
-    _DeltaSnapshot,
-)
+from langgraph.checkpoint.serde.types import SendProtocol
 from langgraph.store.base import Item
 
 if TYPE_CHECKING:
     from langgraph.checkpoint.serde._msgpack import (
         AllowedMsgpackModules,
     )
+    from langgraph.checkpoint.serde.types import SendProtocol
 
 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 _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):
@@ -260,6 +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)
@@ -282,6 +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:
@@ -297,16 +291,10 @@ EXT_METHOD_SINGLE_ARG = 3
 EXT_PYDANTIC_V1 = 4
 EXT_PYDANTIC_V2 = 5
 EXT_NUMPY_ARRAY = 6
-EXT_DELTA_SNAPSHOT = 7
-EXT_DELTA_SENTINEL = 8
 
 
 def _msgpack_default(obj: Any) -> str | ormsgpack.Ext:
-    if isinstance(obj, _DeltaSentinel):
-        return ormsgpack.Ext(EXT_DELTA_SENTINEL, b"")
-    elif isinstance(obj, _DeltaSnapshot):
-        return ormsgpack.Ext(EXT_DELTA_SNAPSHOT, _msgpack_enc(obj.value))
-    elif hasattr(obj, "model_dump") and callable(obj.model_dump):  # pydantic v2
+    if hasattr(obj, "model_dump") and callable(obj.model_dump):  # pydantic v2
         return ormsgpack.Ext(
             EXT_PYDANTIC_V2,
             _msgpack_enc(
@@ -561,9 +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 "
@@ -585,9 +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,
@@ -620,15 +604,7 @@ def _create_msgpack_ext_hook(
         return False
 
     def ext_hook(code: int, data: bytes) -> Any:
-        if code == EXT_DELTA_SENTINEL:
-            return DELTA_SENTINEL
-        elif code == EXT_DELTA_SNAPSHOT:
-            return _DeltaSnapshot(
-                ormsgpack.unpackb(
-                    data, ext_hook=ext_hook, option=ormsgpack.OPT_NON_STR_KEYS
-                )
-            )
-        elif code == EXT_CONSTRUCTOR_SINGLE_ARG:
+        if code == EXT_CONSTRUCTOR_SINGLE_ARG:
             try:
                 tup = ormsgpack.unpackb(
                     data, ext_hook=ext_hook, option=ormsgpack.OPT_NON_STR_KEYS

libs/checkpoint/langgraph/checkpoint/serde/types.py

@@ -1,7 +1,6 @@
 from collections.abc import Sequence
 from typing import (
     Any,
-    NamedTuple,
     Protocol,
     TypeVar,
     runtime_checkable,
@@ -15,39 +14,6 @@ INTERRUPT = "__interrupt__"
 RESUME = "__resume__"
 TASKS = "__pregel_tasks"
 
-
-class _DeltaSentinel:
-    """Singleton marker stored (as zero bytes) in checkpoint_blobs for a
-    DeltaChannel field. The actual per-step writes live in checkpoint_writes
-    and are replayed through the reducer at load time.
-
-    Compare with `is DELTA_SENTINEL` — `loads_typed` always returns the same
-    module-level instance.
-    """
-
-    __slots__ = ()
-
-    def __repr__(self) -> str:
-        return "DELTA_SENTINEL"
-
-
-DELTA_SENTINEL = _DeltaSentinel()
-
-
-class _DeltaSnapshot(NamedTuple):
-    """Snapshot blob for a DeltaChannel with finite snapshot_frequency.
-
-    Stored in checkpoint_blobs via the `EXT_DELTA_SNAPSHOT` msgpack ext code.
-    The ancestor walk in `_get_channel_writes_history` terminates when it
-    encounters this type (any non-sentinel blob stops the walk).
-
-    `from_checkpoint` reconstructs the channel value directly from `.value`
-    without replaying writes — the snapshot IS the accumulated state.
-    """
-
-    value: Any
-
-
 Value = TypeVar("Value", covariant=True)
 Update = TypeVar("Update", contravariant=True)
 C = TypeVar("C")

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
 
@@ -582,14 +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
@@ -605,12 +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
 
 
@@ -655,6 +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"))
@@ -672,6 +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")]
     )
@@ -999,14 +985,29 @@ def test_msgpack_nested_pydantic_serializes_as_dict(
     assert result == obj
 
 
-def test_delta_sentinel_serde_round_trip() -> None:
-    from langgraph.checkpoint.base import DELTA_SENTINEL
+def test_delta_value_serde_round_trip() -> None:
+    from langgraph.checkpoint.base import DeltaValue
     from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
 
     serde = JsonPlusSerializer()
-    type_tag, blob = serde.dumps_typed(DELTA_SENTINEL)
-    # Zero-byte "delta" tag — no allowlist change needed.
+    original = DeltaValue(
+        delta=[{"type": "human", "content": "hi"}], prev_checkpoint_id="abc-123"
+    )
+    type_tag, blob = serde.dumps_typed(original)
     assert type_tag == "delta"
-    assert blob == b""
     loaded = serde.loads_typed((type_tag, blob))
-    assert loaded is DELTA_SENTINEL
+    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

@@ -6,32 +6,19 @@ from langchain_core.runnables import RunnableConfig
 from pydantic import BaseModel
 
 from langgraph.checkpoint.base import (
-    DELTA_SENTINEL,
     Checkpoint,
     CheckpointMetadata,
     create_checkpoint,
     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:
@@ -209,6 +196,8 @@ class TestMemorySaver:
 
 
 async def test_memory_saver() -> None:
+    from langgraph.checkpoint.memory import InMemorySaver
+
     memory_saver = InMemorySaver()
     assert isinstance(memory_saver, InMemorySaver)
 
@@ -322,489 +311,33 @@ def test_memory_saver_with_allowlist_proxy_isolated() -> None:
 
 
 class TestInMemorySaverDeltaChannel:
-    def test_load_blobs_returns_sentinel_for_delta_channel(self) -> None:
-        """_load_blobs returns DELTA_SENTINEL for delta channels (reconstruction deferred)."""
+    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"
-        v1 = "00000000000000000000000000000001.0000000000000000"
+        version = "00000000000000000000000000000001.0000000000000000"
+        delta = DeltaValue(delta=[{"content": "hi"}], prev_checkpoint_id=None)
+        saver.blobs[(thread_id, ns, channel, version)] = serde.dumps_typed(delta)
 
-        saver.blobs[(thread_id, ns, channel, v1)] = serde.dumps_typed(DELTA_SENTINEL)
-
-        cp1 = empty_checkpoint()
-        cp1["id"] = "cp1"
-        cp1["channel_versions"][channel] = v1
+        cp = empty_checkpoint()
+        cp["id"] = "cp1"
+        cp["channel_versions"][channel] = version
         saver.storage[thread_id][ns] = {
-            "cp1": (serde.dumps_typed(cp1), serde.dumps_typed({}), None),
+            "cp1": (serde.dumps_typed(cp), serde.dumps_typed({}), None)
         }
 
-        result = saver._load_blobs(thread_id, ns, {channel: v1})
-        assert channel in result
-        assert result[channel] is DELTA_SENTINEL
+        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_writes_collects_ancestor_writes_only(self) -> None:
-        """_get_channel_writes_history collects ancestor writes oldest→newest,
-        and excludes writes stored at the target checkpoint itself (those are
-        pending writes for the next step, applied separately by pregel)."""
+    def test_get_channel_blob_missing(self) -> None:
+        """get_channel_blob returns NotImplemented when checkpoint or channel not found."""
         saver = InMemorySaver()
-        serde = JsonPlusSerializer()
-
-        thread_id, ns, channel = "t1", "", "messages"
-
-        cp1 = empty_checkpoint()
-        cp1["id"] = "cp1"
-        cp2 = empty_checkpoint()
-        cp2["id"] = "cp2"
-        saver.storage[thread_id][ns] = {
-            "cp1": (serde.dumps_typed(cp1), serde.dumps_typed({}), None),
-            "cp2": (serde.dumps_typed(cp2), serde.dumps_typed({}), "cp1"),
-        }
-        # Writes stored at cp1 produced the cp1 snapshot; part of history.
-        saver.writes[(thread_id, ns, "cp1")][("task1", 0)] = (
-            "task1",
-            channel,
-            serde.dumps_typed({"content": "hi"}),
-            "",
-        )
-        # Writes stored at cp2 are pending — they will produce cp3 when the
-        # step that loaded cp2 completes. They MUST NOT appear in the
-        # reconstructed snapshot value at cp2.
-        saver.writes[(thread_id, ns, "cp2")][("task2", 0)] = (
-            "task2",
-            channel,
-            serde.dumps_typed({"content": "pending"}),
-            "",
-        )
-
-        config: RunnableConfig = {
-            "configurable": {
-                "thread_id": thread_id,
-                "checkpoint_ns": ns,
-                "checkpoint_id": "cp2",
-            }
-        }
-        result = saver._get_channel_writes_history(config, channel)
-        assert result.seed is DELTA_SENTINEL
-        values = [v for _, _, v in result.writes]
-        assert values == [{"content": "hi"}]
-
-    def test_get_channel_writes_at_root_returns_empty(self) -> None:
-        """Reconstructing the root checkpoint's state: no ancestors → []."""
-        saver = InMemorySaver()
-        serde = JsonPlusSerializer()
-        thread_id, ns, channel = "t1", "", "messages"
-
-        cp1 = empty_checkpoint()
-        cp1["id"] = "cp1"
-        saver.storage[thread_id][ns] = {
-            "cp1": (serde.dumps_typed(cp1), serde.dumps_typed({}), None),
-        }
-        saver.writes[(thread_id, ns, "cp1")][("task1", 0)] = (
-            "task1",
-            channel,
-            serde.dumps_typed({"content": "pending"}),
-            "",
-        )
-
-        config: RunnableConfig = {
-            "configurable": {
-                "thread_id": thread_id,
-                "checkpoint_ns": ns,
-                "checkpoint_id": "cp1",
-            }
-        }
-        result = saver._get_channel_writes_history(config, channel)
-        assert result.seed is DELTA_SENTINEL
-        assert result.writes == []
-
-
-class TestBaseFallbackGetChannelWrites:
-    """Exercises the `BaseCheckpointSaver._get_channel_writes_history` default
-    implementation — the path third-party savers inherit when they don't
-    override `_get_channel_writes_history` themselves.
-
-    Regression guard for a bug where the fallback passed the caller's config
-    (with `checkpoint_id`) straight to `self.list()`, which most savers
-    collapse to a single row — causing the fallback to return `[]`.
-    """
-
-    def _build_saver_with_chain(self) -> tuple[InMemorySaver, str, str]:
-        """Build an InMemorySaver with a 3-checkpoint chain and per-step writes
-        for a `messages` channel.
-
-        Returns `(saver, thread_id, namespace)`. The saver subclass deletes the
-        InMemorySaver override so the base class fallback is exercised.
-        """
-
-        class _ThirdPartyStyleSaver(InMemorySaver):
-            _get_channel_writes_history = (
-                InMemorySaver.__mro__[1]._get_channel_writes_history  # type: ignore[attr-defined]
-            )
-            _aget_channel_writes_history = (
-                InMemorySaver.__mro__[1]._aget_channel_writes_history  # type: ignore[attr-defined]
-            )
-
-        saver = _ThirdPartyStyleSaver()
-        serde = JsonPlusSerializer()
-        thread_id, ns, channel = "t1", "", "messages"
-
-        cp0 = empty_checkpoint()
-        cp0["id"] = "00000000000000000000000000000001.0000000000000000"
-        cp1 = empty_checkpoint()
-        cp1["id"] = "00000000000000000000000000000002.0000000000000000"
-        cp2 = empty_checkpoint()
-        cp2["id"] = "00000000000000000000000000000003.0000000000000000"
-        saver.storage[thread_id][ns] = {
-            cp0["id"]: (serde.dumps_typed(cp0), serde.dumps_typed({}), None),
-            cp1["id"]: (serde.dumps_typed(cp1), serde.dumps_typed({}), cp0["id"]),
-            cp2["id"]: (serde.dumps_typed(cp2), serde.dumps_typed({}), cp1["id"]),
-        }
-        # Writes under cp0 produced cp1's state; writes under cp1 produced cp2's.
-        saver.writes[(thread_id, ns, cp0["id"])][("task1", 0)] = (
-            "task1",
-            channel,
-            serde.dumps_typed({"content": "first"}),
-            "",
-        )
-        saver.writes[(thread_id, ns, cp1["id"])][("task2", 0)] = (
-            "task2",
-            channel,
-            serde.dumps_typed({"content": "second"}),
-            "",
-        )
-        return saver, thread_id, ns
-
-    def test_fallback_returns_ancestor_writes_oldest_first(self) -> None:
-        saver, thread_id, ns = self._build_saver_with_chain()
-        target_id = "00000000000000000000000000000003.0000000000000000"
-        config: RunnableConfig = {
-            "configurable": {
-                "thread_id": thread_id,
-                "checkpoint_ns": ns,
-                "checkpoint_id": target_id,
-            }
-        }
-
-        result = saver._get_channel_writes_history(config, "messages")
-
-        assert result.seed is DELTA_SENTINEL
-        values = [v for _, _, v in result.writes]
-        assert values == [{"content": "first"}, {"content": "second"}]
-
-    async def test_async_fallback_returns_ancestor_writes_oldest_first(self) -> None:
-        saver, thread_id, ns = self._build_saver_with_chain()
-        target_id = "00000000000000000000000000000003.0000000000000000"
-        config: RunnableConfig = {
-            "configurable": {
-                "thread_id": thread_id,
-                "checkpoint_ns": ns,
-                "checkpoint_id": target_id,
-            }
-        }
-
-        result = await saver._aget_channel_writes_history(config, "messages")
-
-        assert result.seed is DELTA_SENTINEL
-        values = [v for _, _, v in result.writes]
-        assert values == [{"content": "first"}, {"content": "second"}]
-
-    async def test_async_fallback_concurrent_tasks_do_not_interfere(self) -> None:
-        """Regression: the re-entrancy guard must be task-local, not thread-local.
-
-        Two concurrent `_aget_channel_writes_history` calls on the same
-        event-loop thread must each see their full reconstructed writes. A
-        `threading.local()` guard would let whichever task set it first
-        short-circuit the other to `writes=[]`.
-        """
-        import asyncio
-
-        saver, thread_id, ns = self._build_saver_with_chain()
-
-        # Force the two tasks to interleave across the `set(True)` boundary:
-        # each `aget_tuple` yields control, so if the guard were thread-local
-        # the second task would observe `active=True` set by the first.
-        orig_aget_tuple = saver.aget_tuple
-
-        async def slow_aget_tuple(config: RunnableConfig) -> Any:
-            await asyncio.sleep(0)
-            return await orig_aget_tuple(config)
-
-        saver.aget_tuple = slow_aget_tuple  # type: ignore[method-assign]
-
-        target_id = "00000000000000000000000000000003.0000000000000000"
-        config: RunnableConfig = {
-            "configurable": {
-                "thread_id": thread_id,
-                "checkpoint_ns": ns,
-                "checkpoint_id": target_id,
-            }
-        }
-
-        results = await asyncio.gather(
-            saver._aget_channel_writes_history(config, "messages"),
-            saver._aget_channel_writes_history(config, "messages"),
-        )
-
-        expected_values = [{"content": "first"}, {"content": "second"}]
-        for result in results:
-            assert result.seed is DELTA_SENTINEL
-            values = [v for _, _, v in result.writes]
-            assert values == expected_values
-
-
-class TestPreDeltaBlobTerminator:
-    """Verify the pre-delta blob terminator: when the ancestor walk hits a
-    checkpoint whose blob for the channel is a real value (not
-    DELTA_SENTINEL), reconstruction seeds from it and stops. This guards
-
-      * back-compat: a thread written by pre-delta code, then extended under
-        delta — reconstruction must return the correct value without walking
-        past the last pre-delta ancestor;
-      * perf: without the terminator, every reconstruct-after-migration would
-        walk all the way to the thread root.
-    """
-
-    def _build_mixed_thread(self) -> tuple[InMemorySaver, str, str, str, str]:
-        """Three-checkpoint chain: cp1 (pre-delta, blob=[A]), cp2 (delta,
-        write=B), cp3 (delta, write=C). Reconstructing at cp3 must yield
-        seed=[A] + writes=[B, C].
-
-        Returns `(saver, thread_id, ns, channel, cp3_id)`.
-        """
-        saver = InMemorySaver()
-        serde = JsonPlusSerializer()
-        thread_id, ns, channel = "t1", "", "messages"
-
-        v1 = "00000000000000000000000000000001.0"
-        v2 = "00000000000000000000000000000002.0"
-        v3 = "00000000000000000000000000000003.0"
-
-        # Pre-delta: cp1 stored a real blob for the channel.
-        saver.blobs[(thread_id, ns, channel, v1)] = serde.dumps_typed(["A"])
-        # Delta-era: cp2 and cp3 store sentinels; real writes in checkpoint_writes.
-        saver.blobs[(thread_id, ns, channel, v2)] = serde.dumps_typed(DELTA_SENTINEL)
-        saver.blobs[(thread_id, ns, channel, v3)] = serde.dumps_typed(DELTA_SENTINEL)
-
-        cp1 = empty_checkpoint()
-        cp1["id"] = "cp1"
-        cp1["channel_versions"][channel] = v1
-        cp2 = empty_checkpoint()
-        cp2["id"] = "cp2"
-        cp2["channel_versions"][channel] = v2
-        cp3 = empty_checkpoint()
-        cp3["id"] = "cp3"
-        cp3["channel_versions"][channel] = v3
-
-        saver.storage[thread_id][ns] = {
-            "cp1": (serde.dumps_typed(cp1), serde.dumps_typed({}), None),
-            "cp2": (serde.dumps_typed(cp2), serde.dumps_typed({}), "cp1"),
-            "cp3": (serde.dumps_typed(cp3), serde.dumps_typed({}), "cp2"),
-        }
-        # Write under cp1 would be from the pre-delta era and MUST be ignored
-        # (the blob already captures it). We add one and assert it is not
-        # folded into the reconstructed result.
-        saver.writes[(thread_id, ns, "cp1")][("task0", 0)] = (
-            "task0",
-            channel,
-            serde.dumps_typed("PRE-DELTA-WRITE"),
-            "",
-        )
-        saver.writes[(thread_id, ns, "cp2")][("task2", 0)] = (
-            "task2",
-            channel,
-            serde.dumps_typed("B"),
-            "",
-        )
-        saver.writes[(thread_id, ns, "cp3")][("task3", 0)] = (
-            "task3",
-            channel,
-            serde.dumps_typed("PENDING-AT-TARGET"),
-            "",
-        )
-        return saver, thread_id, ns, channel, "cp3"
-
-    def test_seed_from_pre_delta_ancestor_blob(self) -> None:
-        saver, thread_id, ns, channel, target = self._build_mixed_thread()
-        config: RunnableConfig = {
-            "configurable": {
-                "thread_id": thread_id,
-                "checkpoint_ns": ns,
-                "checkpoint_id": target,
-            }
-        }
-
-        result = saver._get_channel_writes_history(config, channel)
-
-        # Seed came from the pre-delta blob at cp1.
-        assert result.seed == ["A"]
-        # Delta-era writes from cp2 replay through the reducer on top of seed.
-        # cp3 is the target — its own write is pending for the NEXT step and
-        # must be excluded.
-        values = [v for _, _, v in result.writes]
-        assert values == ["B"]
-
-    def test_pre_delta_blob_terminates_walk_before_older_writes(self) -> None:
-        """Writes stored at the pre-delta ancestor itself must not be replayed
-        (the blob subsumes them)."""
-        saver, thread_id, ns, channel, target = self._build_mixed_thread()
-        config: RunnableConfig = {
-            "configurable": {
-                "thread_id": thread_id,
-                "checkpoint_ns": ns,
-                "checkpoint_id": target,
-            }
-        }
-
-        result = saver._get_channel_writes_history(config, channel)
-
-        values = [v for _, _, v in result.writes]
-        # The pre-delta write under cp1 must not appear (the blob subsumes it).
-        assert "PRE-DELTA-WRITE" not in values
-        # And the pending write at the target is never folded in.
-        assert "PENDING-AT-TARGET" not in values
-
-
-class TestInMemorySaverPrune:
-    """Tests for InMemorySaver.prune with DeltaChannel awareness."""
-
-    def _build_chain(
-        self,
-        saver: InMemorySaver,
-        thread_id: str,
-        ns: str,
-        channel: str,
-        n: int,
-        *,
-        snapshot_at: set[int] | None = None,
-    ) -> list[str]:
-        """Build a chain of n checkpoints with DELTA_SENTINEL blobs.
-
-        If snapshot_at is provided, writes a _DeltaSnapshot blob at those steps.
-        Returns list of checkpoint IDs in order (oldest first).
-        """
-        from langgraph.checkpoint.serde.types import _DeltaSnapshot
-
-        serde = saver.serde
-        cp_ids = []
-        parent_id = None
-        ver_base = "0000000000000000000000000000000{i}.0000000000000000"
-
-        for i in range(n):
-            cp_id = f"cp{i:04d}"
-            ver = ver_base.format(i=i)
-            cp = empty_checkpoint()
-            cp["id"] = cp_id
-            cp["channel_versions"][channel] = ver
-
-            if snapshot_at and i in snapshot_at:
-                blob = serde.dumps_typed(_DeltaSnapshot(value=[f"msg{i}"]))
-            else:
-                blob = serde.dumps_typed(DELTA_SENTINEL)
-
-            saver.blobs[(thread_id, ns, channel, ver)] = blob
-            saver.storage[thread_id][ns][cp_id] = (
-                serde.dumps_typed(cp),
-                serde.dumps_typed({}),
-                parent_id,
-            )
-            # Add a dummy write for this checkpoint
-            saver.writes[(thread_id, ns, cp_id)][("task", i)] = (
-                "task",
-                channel,
-                serde.dumps_typed(f"write{i}"),
-                "",
-            )
-            cp_ids.append(cp_id)
-            parent_id = cp_id
-
-        return cp_ids
-
-    def test_prune_pure_delta_keeps_all(self) -> None:
-        """With no snapshots, all checkpoints are required for reconstruction."""
-        saver = InMemorySaver()
-        thread_id, ns, channel = "t1", "", "messages"
-        cp_ids = self._build_chain(saver, thread_id, ns, channel, n=5)
-
-        saver.prune([thread_id], strategy="keep_latest")
-
-        # All checkpoints must be retained (walk needs the full chain)
-        remaining = set(saver.storage[thread_id][ns].keys())
-        assert remaining == set(cp_ids)
-
-    def test_prune_with_snapshot_removes_pre_snapshot_checkpoints(self) -> None:
-        """Checkpoints older than the nearest snapshot can be safely pruned."""
-        saver = InMemorySaver()
-        thread_id, ns, channel = "t1", "", "messages"
-        # Snapshot at step 2; steps 3 and 4 are sentinels
-        cp_ids = self._build_chain(saver, thread_id, ns, channel, n=5, snapshot_at={2})
-
-        saver.prune([thread_id], strategy="keep_latest")
-
-        remaining = set(saver.storage[thread_id][ns].keys())
-        # cp0, cp1 (before snapshot) must be gone; cp2, cp3, cp4 must remain
-        assert cp_ids[0] not in remaining  # pre-snapshot
-        assert cp_ids[1] not in remaining  # pre-snapshot
-        assert cp_ids[2] in remaining  # the snapshot itself
-        assert cp_ids[3] in remaining  # sentinel after snapshot
-        assert cp_ids[4] in remaining  # latest
-
-    def test_prune_removes_orphaned_blobs(self) -> None:
-        """Blob entries for pruned checkpoints are cleaned up."""
-        saver = InMemorySaver()
-        thread_id, ns, channel = "t1", "", "messages"
-        self._build_chain(saver, thread_id, ns, channel, n=4, snapshot_at={1})
-        saver.prune([thread_id], strategy="keep_latest")
-
-        # cp0 blob should be gone (pruned); cp1, cp2, cp3 blobs remain
         assert (
-            thread_id,
-            ns,
-            channel,
-            f"0000000000000000000000000000000{0}.0000000000000000",
-        ) not in saver.blobs
-        for i in range(1, 4):
-            ver = f"0000000000000000000000000000000{i}.0000000000000000"
-            assert (thread_id, ns, channel, ver) in saver.blobs
-
-    def test_prune_removes_writes_for_pruned_checkpoints(self) -> None:
-        """checkpoint_writes for pruned checkpoints are deleted."""
-        saver = InMemorySaver()
-        thread_id, ns, channel = "t1", "", "messages"
-        cp_ids = self._build_chain(saver, thread_id, ns, channel, n=4, snapshot_at={1})
-
-        saver.prune([thread_id], strategy="keep_latest")
-
-        # writes for cp0 must be gone
-        assert (thread_id, ns, cp_ids[0]) not in saver.writes
-        # writes for cp1+ must remain (they're in the walk chain)
-        for cp_id in cp_ids[1:]:
-            assert (thread_id, ns, cp_id) in saver.writes
-
-    def test_prune_delete_strategy_removes_everything(self) -> None:
-        """strategy='delete' removes all checkpoints for the thread."""
-        saver = InMemorySaver()
-        thread_id, ns, channel = "t1", "", "messages"
-        self._build_chain(saver, thread_id, ns, channel, n=3)
-
-        saver.prune([thread_id], strategy="delete")
-
-        assert not saver.storage.get(thread_id, {}).get(ns)
-        assert not any(k[0] == thread_id for k in saver.writes)
-        assert not any(k[0] == thread_id for k in saver.blobs)
-
-    def test_prune_non_delta_channel_always_pruneable(self) -> None:
-        """A channel with full snapshot blobs (no sentinels) allows full prune."""
-
-        saver = InMemorySaver()
-        thread_id, ns, channel = "t1", "", "messages"
-        # All snapshots, no sentinels
-        cp_ids = self._build_chain(
-            saver, thread_id, ns, channel, n=4, snapshot_at={0, 1, 2, 3}
+            saver.get_channel_blob("t1", "", "no-such-cp", "messages") is NotImplemented
         )
-
-        saver.prune([thread_id], strategy="keep_latest")
-
-        remaining = set(saver.storage[thread_id][ns].keys())
-        # Only the latest checkpoint is needed (all blobs are snapshots)
-        assert remaining == {cp_ids[-1]}

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__ = "0.4.23"
+__version__ = "0.4.22"

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/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/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

@@ -1,78 +1,97 @@
 from __future__ import annotations
 
-import copy as _copy
+import collections.abc
 from collections.abc import Callable, Sequence
-from typing import Any, Generic
+from copy import copy
+from typing import Any, Generic, Literal
 
-from langgraph.checkpoint.base import DELTA_SENTINEL, PendingWrite
-from langgraph.checkpoint.serde.types import _DeltaSnapshot
+from langgraph.checkpoint.base import DeltaChainValue, DeltaValue
 from typing_extensions import Self
 
-from langgraph._internal._constants import OVERWRITE
 from langgraph._internal._typing import MISSING
 from langgraph.channels.base import BaseChannel, Value
-from langgraph.errors import (
-    EmptyChannelError,
-    ErrorCode,
-    InvalidUpdateError,
-    create_error_message,
-)
-from langgraph.types import Overwrite
+from langgraph.channels.binop import _get_overwrite, _strip_extras
+from langgraph.errors import EmptyChannelError
 
 __all__ = ("DeltaChannel",)
 
 
-def _empty(typ: Any) -> Any:
+def _copy_value(value: Any) -> Any:
+    if value is MISSING:
+        return value
     try:
-        return typ()
-    except Exception:
-        return []
+        return value.copy()
+    except AttributeError:
+        return copy(value)
 
 
-def _get_overwrite(value: Any) -> tuple[bool, Any]:
-    if isinstance(value, Overwrite):
-        return True, value.value
-    if isinstance(value, dict) and set(value.keys()) == {OVERWRITE}:
-        return True, value[OVERWRITE]
-    return False, None
+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).
 
-class DeltaChannel(Generic[Value], BaseChannel[Any, Any, Any]):
-    """Fold-reducer channel with configurable snapshot cadence.
+    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.
 
-    `snapshot_frequency=None` (default): pure delta — stores only
-    `DELTA_SENTINEL` in checkpoint blobs; reads replay all ancestor writes.
+    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.
 
-    `snapshot_frequency=N`: pregel's `create_checkpoint` writes a full
-    `_DeltaSnapshot` blob every N steps (eagerly, even if the channel had
-    no write that step). Reads walk at most N ancestor checkpoints before
-    hitting the snapshot, bounding replay depth to N regardless of thread
-    length.
+    Usage::
 
-    Parameters:
-        operator: Binary reducer `(Value, Value) -> Value`.
-        snapshot_frequency: Every Nth pregel step writes a snapshot blob.
-            `None` (default) = pure delta, never snapshot.
+        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_frequency")
-    value: Value | Any
+    __slots__ = (
+        "value",
+        "operator",
+        "snapshot_every",
+        "_pending",
+        "_base_version",
+        "_last_checkpoint_id",
+        "_overwritten",
+        "_steps_since_snapshot",
+    )
 
     def __init__(
         self,
-        operator: Callable[[Any, Any], Any],
+        operator: Callable[[list[Value], Any], list[Value]],
+        typ: type = list,
         *,
-        snapshot_frequency: int | None = None,
+        snapshot_every: int | None = None,
     ) -> None:
-        super().__init__(list)
+        typ = _strip_extras(typ)
+        if typ in (
+            collections.abc.Sequence,
+            collections.abc.MutableSequence,
+        ):
+            typ = list
+        super().__init__(typ)
         self.operator = operator
-        self.snapshot_frequency = snapshot_frequency
-        self.value: Any = []
+        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_frequency != other.snapshot_frequency:
+        if self.snapshot_every != other.snapshot_every:
             return False
         if (
             self.operator.__name__ != "<lambda>"
@@ -83,85 +102,96 @@ class DeltaChannel(Generic[Value], BaseChannel[Any, Any, Any]):
 
     @property
     def ValueType(self) -> Any:
-        return self.typ
+        return list[self.typ]  # type: ignore[name-defined]
 
     @property
     def UpdateType(self) -> Any:
-        return self.typ
+        return self.typ | list[self.typ]  # type: ignore[name-defined]
 
-    def is_snapshot_step(self, step: int) -> bool:
-        """True if pregel should write a snapshot blob at this step."""
-        return (
-            self.snapshot_frequency is not None and step % self.snapshot_frequency == 0
-        )
-
-    def _clone_empty(self) -> Self:
-        new = self.__class__.__new__(self.__class__)
-        new.typ = self.typ
-        new.key = self.key
-        new.operator = self.operator
-        new.snapshot_frequency = self.snapshot_frequency
-        new.value = MISSING
-        return new
+    @property
+    def checkpoint_hydration_kind(self) -> Literal["delta"]:
+        return "delta"
 
     def copy(self) -> Self:
-        new = self._clone_empty()
-        new.value = self.value if self.value is MISSING else _copy.copy(self.value)
+        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 _apply_write(self, value: Any, write: Any) -> Any:
-        is_overwrite, overwrite_value = _get_overwrite(write)
-        if is_overwrite:
-            return (
-                _copy.copy(overwrite_value)
-                if overwrite_value is not None
-                else _empty(self.typ)
-            )
-        base = _empty(self.typ) if value is MISSING else value
-        return self.operator(base, write)
-
     def from_checkpoint(self, checkpoint: Any) -> Self:
-        """Initialize from a stored blob or sentinel.
-
-        Blob types (dispatched via serde ext code, not dict key inspection):
-          * `DELTA_SENTINEL` / `MISSING`: start empty; caller replays writes.
-          * `_DeltaSnapshot(value)`: restore value directly from snapshot.
-          * plain value (migration from old BinOp blobs): use directly.
-        """
-        new = self._clone_empty()
-        if checkpoint is MISSING or checkpoint is DELTA_SENTINEL:
-            new.value = _empty(new.typ)
-        elif isinstance(checkpoint, _DeltaSnapshot):
-            new.value = checkpoint.value
+        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:
-            new.value = checkpoint
+            # 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 replay_writes(self, writes: Sequence[PendingWrite]) -> None:
-        """Fold ancestor writes oldest→newest into current value."""
-        for _, _, value in writes:
-            self.value = self._apply_write(self.value, value)
-
     def update(self, values: Sequence[Any]) -> bool:
         if not values:
             return False
         seen_overwrite = False
         for value in values:
-            is_overwrite, _ = _get_overwrite(value)
+            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 seen_overwrite:
-                continue
-            self.value = self._apply_write(self.value, value)
+            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) -> Any:
+    def get(self) -> list[Value]:
         if self.value is MISSING:
             raise EmptyChannelError()
         return self.value
@@ -170,12 +200,29 @@ class DeltaChannel(Generic[Value], BaseChannel[Any, Any, Any]):
         return self.value is not MISSING
 
     def checkpoint(self) -> Any:
-        """Return stored representation: always `DELTA_SENTINEL`.
+        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,
+        )
 
-        Snapshot decisions are made by `create_checkpoint` in pregel (which
-        has the step number) via `is_snapshot_step`. `checkpoint()` is only
-        called for non-snapshot steps or when no checkpointer is available.
-        """
-        if self.value is MISSING:
-            return MISSING
-        return DELTA_SENTINEL
+    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/graph/state.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-import collections.abc
 import inspect
 import logging
 import typing
@@ -48,8 +47,7 @@ from langgraph._internal._pydantic import create_model
 from langgraph._internal._runnable import coerce_to_runnable
 from langgraph._internal._typing import EMPTY_SEQ, MISSING, DeprecatedKwargs
 from langgraph.channels.base import BaseChannel
-from langgraph.channels.binop import BinaryOperatorAggregate, _strip_extras
-from langgraph.channels.delta import DeltaChannel
+from langgraph.channels.binop import BinaryOperatorAggregate
 from langgraph.channels.ephemeral_value import EphemeralValue
 from langgraph.channels.last_value import LastValue, LastValueAfterFinish
 from langgraph.channels.named_barrier_value import (
@@ -1084,7 +1082,6 @@ class StateGraph(Generic[StateT, ContextT, InputT, OutputT]):
             CompiledStateGraph: The compiled `StateGraph`.
         """
         checkpointer = ensure_valid_checkpointer(checkpointer)
-
         serde_allowlist: set[tuple[str, ...]] | None = None
         if _serde.STRICT_MSGPACK_ENABLED:
             schema_types: list[type[Any]] = [
@@ -1670,36 +1667,6 @@ def _is_field_channel(typ: type[Any]) -> BaseChannel | None:
         # Search through all annotated medata to find channel annotations
         for item in meta:
             if isinstance(item, BaseChannel):
-                if isinstance(item, DeltaChannel) and hasattr(typ, "__origin__"):
-                    origin = typ.__origin__
-                    # Unwrap parameterized Required[X]/NotRequired[X] to X
-                    # (e.g. Annotated[NotRequired[dict[...]], ...]).
-                    if hasattr(origin, "__origin__") and origin.__origin__ in (
-                        Required,
-                        NotRequired,
-                    ):
-                        origin = origin.__args__[0]
-                    outer = _strip_extras(origin)
-                    if outer in (
-                        collections.abc.Sequence,
-                        collections.abc.MutableSequence,
-                    ):
-                        outer = list
-                    elif outer in (
-                        collections.abc.Mapping,
-                        collections.abc.MutableMapping,
-                    ):
-                        outer = dict
-                    elif outer in (
-                        collections.abc.Set,
-                        collections.abc.MutableSet,
-                    ):
-                        outer = set
-                    item.typ = outer
-                    try:
-                        item.value = outer()
-                    except Exception:
-                        item.value = []
                 return item
             elif isclass(item) and issubclass(item, BaseChannel):
                 # ex, Annotated[int, EphemeralValue, SomeOtherAnnotation]

libs/langgraph/langgraph/pregel/_algo.py

@@ -210,7 +210,7 @@ def local_read(
     return values
 
 
-def increment(current: int | None, channel: None = None) -> int:
+def increment(current: int | None, channel: None) -> int:
     """Default channel versioning function, increments the current int version."""
     return current + 1 if current is not None else 1
 

libs/langgraph/langgraph/pregel/_checkpoint.py

@@ -1,22 +1,33 @@
 from __future__ import annotations
 
-from collections.abc import Callable, Mapping
+from collections.abc import Mapping
 from datetime import datetime, timezone
-from typing import Any
 
-from langchain_core.runnables import RunnableConfig
-from langgraph.checkpoint.base import DELTA_SENTINEL, BaseCheckpointSaver, Checkpoint
+from langgraph.checkpoint.base import (
+    Checkpoint,
+    CheckpointHydrationPlan,
+    IncrementalChannelSpec,
+)
 from langgraph.checkpoint.base.id import uuid6
-from langgraph.checkpoint.serde.types import _DeltaSnapshot
 
 from langgraph._internal._typing import MISSING
 from langgraph.channels.base import BaseChannel
-from langgraph.channels.delta import DeltaChannel
 from langgraph.managed.base import ManagedValueMapping, ManagedValueSpec
 
 LATEST_VERSION = 4
 
-GetNextVersion = Callable[[Any, None], Any]
+
+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:
@@ -37,82 +48,35 @@ def create_checkpoint(
     *,
     id: str | None = None,
     updated_channels: set[str] | None = None,
-    get_next_version: GetNextVersion | None = None,
 ) -> Checkpoint:
-    """Create a checkpoint for the given channels.
-
-    For `DeltaChannel` with `snapshot_frequency=N`, snapshot steps write a
-    `_DeltaSnapshot` blob rather than `DELTA_SENTINEL`, bounding the ancestor
-    walk to at most N steps. Snapshots are eager: even if the channel had no
-    write this step, a version bump is forced (via `get_next_version`) so the
-    blob is stored by `put()`. Without `get_next_version` (e.g. static
-    contexts), snapshot steps gracefully fall back to sentinel.
-    """
+    """Create a checkpoint for the given channels."""
     ts = datetime.now(timezone.utc).isoformat()
     if channels is None:
         values = checkpoint["channel_values"]
-        channel_versions = checkpoint["channel_versions"]
     else:
         values = {}
-        channel_versions = dict(checkpoint["channel_versions"])
         for k in channels:
-            if k not in channel_versions:
+            if k not in checkpoint["channel_versions"]:
                 continue
-            ch = channels[k]
-            if (
-                isinstance(ch, DeltaChannel)
-                and ch.is_snapshot_step(step)
-                and ch.is_available()
-            ):
-                # Eager snapshot: bump version if not already written this step
-                # so put() includes this channel in new_versions and stores blob.
-                if get_next_version is not None and (
-                    updated_channels is None or k not in updated_channels
-                ):
-                    channel_versions[k] = get_next_version(channel_versions[k], None)
-                values[k] = _DeltaSnapshot(ch.get())
-            else:
-                v = ch.checkpoint()
-                if v is not MISSING:
-                    values[k] = v
+            v = channels[k].checkpoint()
+            if v is not MISSING:
+                values[k] = v
     return Checkpoint(
         v=LATEST_VERSION,
         ts=ts,
         id=id or str(uuid6(clock_seq=step)),
         channel_values=values,
-        channel_versions=channel_versions,
+        channel_versions=checkpoint["channel_versions"],
         versions_seen=checkpoint["versions_seen"],
         updated_channels=None if updated_channels is None else sorted(updated_channels),
     )
 
 
-def _needs_replay(spec: BaseChannel, stored: object) -> bool:
-    """True if `spec` is a `DeltaChannel` and the stored blob is a sentinel,
-    requiring an ancestor walk to reconstruct.
-
-    `_DeltaSnapshot` blobs and plain values (migration) resolve directly via
-    `from_checkpoint` — only `DELTA_SENTINEL` / `MISSING` trigger replay.
-    """
-    if not isinstance(spec, DeltaChannel):
-        return False
-    return stored is MISSING or stored is DELTA_SENTINEL
-
-
 def channels_from_checkpoint(
     specs: Mapping[str, BaseChannel | ManagedValueSpec],
     checkpoint: Checkpoint,
-    *,
-    saver: BaseCheckpointSaver | None = None,
-    config: RunnableConfig | None = None,
 ) -> tuple[Mapping[str, BaseChannel], ManagedValueMapping]:
-    """Hydrate channels from a checkpoint.
-
-    For most channels, `spec.from_checkpoint(checkpoint["channel_values"][k])`
-    is sufficient. `DeltaChannel` is the exception: sentinel blobs require an
-    ancestor walk via `saver._get_channel_writes_history`. The walk terminates
-    at the nearest `_DeltaSnapshot` blob (step-based) or a pre-migration plain
-    value, so read depth is bounded by `snapshot_frequency`.
-    """
+    """Get channels from a checkpoint."""
     channel_specs: dict[str, BaseChannel] = {}
     managed_specs: dict[str, ManagedValueSpec] = {}
     for k, v in specs.items():
@@ -120,51 +84,10 @@ def channels_from_checkpoint(
             channel_specs[k] = v
         else:
             managed_specs[k] = v
-
     channels: dict[str, BaseChannel] = {}
-    for k, spec in channel_specs.items():
-        ch: BaseChannel
-        stored = checkpoint["channel_values"].get(k, MISSING)
-        if _needs_replay(spec, stored) and saver is not None and config is not None:
-            assert isinstance(spec, DeltaChannel)
-            history = saver._get_channel_writes_history(config, k)
-            replay_ch = spec.from_checkpoint(history.seed)
-            replay_ch.replay_writes(history.writes)
-            ch = replay_ch
-        else:
-            ch = spec.from_checkpoint(stored)
-        channels[k] = ch
-    return channels, managed_specs
-
-
-async def achannels_from_checkpoint(
-    specs: Mapping[str, BaseChannel | ManagedValueSpec],
-    checkpoint: Checkpoint,
-    *,
-    saver: BaseCheckpointSaver | None = None,
-    config: RunnableConfig | None = None,
-) -> tuple[Mapping[str, BaseChannel], ManagedValueMapping]:
-    """Async version of `channels_from_checkpoint`. See docstring there."""
-    channel_specs: dict[str, BaseChannel] = {}
-    managed_specs: dict[str, ManagedValueSpec] = {}
-    for k, v in specs.items():
-        if isinstance(v, BaseChannel):
-            channel_specs[k] = v
-        else:
-            managed_specs[k] = v
-
-    channels: dict[str, BaseChannel] = {}
-    for k, spec in channel_specs.items():
-        ch: BaseChannel
-        stored = checkpoint["channel_values"].get(k, MISSING)
-        if _needs_replay(spec, stored) and saver is not None and config is not None:
-            assert isinstance(spec, DeltaChannel)
-            history = await saver._aget_channel_writes_history(config, k)
-            replay_ch = spec.from_checkpoint(history.seed)
-            replay_ch.replay_writes(history.writes)
-            ch = replay_ch
-        else:
-            ch = spec.from_checkpoint(stored)
+    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
 

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 (
@@ -25,11 +26,11 @@ from langchain_core.callbacks import AsyncParentRunManager, ParentRunManager
 from langchain_core.runnables import RunnableConfig
 from langgraph.cache.base import BaseCache
 from langgraph.checkpoint.base import (
-    DELTA_SENTINEL,
     WRITES_IDX_MAP,
     BaseCheckpointSaver,
     ChannelVersions,
     Checkpoint,
+    CheckpointHydrationPlan,
     CheckpointMetadata,
     CheckpointTuple,
     PendingWrite,
@@ -93,8 +94,8 @@ from langgraph.pregel._algo import (
     task_path_str,
 )
 from langgraph.pregel._checkpoint import (
-    achannels_from_checkpoint,
     channels_from_checkpoint,
+    checkpoint_hydration_plan,
     copy_checkpoint,
     create_checkpoint,
     empty_checkpoint,
@@ -199,7 +200,6 @@ class PregelLoop:
     checkpoint_pending_writes: list[PendingWrite]
     checkpoint_previous_versions: dict[str, str | float | int]
     prev_checkpoint_config: RunnableConfig | None
-    _pending_write_futs: list[concurrent.futures.Future]
 
     status: Literal[
         "input",
@@ -317,6 +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"],
@@ -409,7 +432,7 @@ class PregelLoop:
                     task = self.tasks.get(task_id)
                 else:
                     task = None
-                fut = self.submit(
+                self.submit(
                     self.checkpointer_put_writes,
                     config,
                     writes_to_save,
@@ -417,13 +440,12 @@ class PregelLoop:
                     task_path_str(task.path) if task else "",
                 )
             else:
-                fut = self.submit(
+                self.submit(
                     self.checkpointer_put_writes,
                     config,
                     writes_to_save,
                     task_id,
                 )
-            self._pending_write_futs.append(fut)
         # output writes
         if hasattr(self, "tasks"):
             self.output_writes(task_id, writes)
@@ -835,18 +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")
@@ -894,10 +906,13 @@ class PregelLoop:
             self.step,
             id=self.checkpoint["id"] if exiting else None,
             updated_channels=self.updated_channels,
-            get_next_version=self.checkpointer_get_next_version
-            if do_checkpoint
-            else None,
         )
+        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()
@@ -934,17 +949,6 @@ class PregelLoop:
             )
             self.checkpoint_previous_versions = channel_versions
 
-            # If the checkpoint has any DELTA_SENTINEL blobs, the sentinel is
-            # only meaningful if checkpoint_writes are durable first.  Flush
-            # pending write futures synchronously before committing the blob so
-            # we never end up with a sentinel blob backed by missing writes.
-            if self._pending_write_futs and any(
-                v is DELTA_SENTINEL for v in self.checkpoint["channel_values"].values()
-            ):
-                for fut in self._pending_write_futs:
-                    fut.result()
-                self._pending_write_futs.clear()
-
             # save it, without blocking
             # if there's a previous checkpoint save in progress, wait for it
             # ensuring checkpointers receive checkpoints in order
@@ -1265,6 +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, []
@@ -1289,13 +1295,9 @@ class SyncPregelLoop(PregelLoop, AbstractContextManager):
             if saved.pending_writes is not None
             else []
         )
-        self._pending_write_futs = []
         self.submit = self.stack.enter_context(BackgroundExecutor(self.config))
         self.channels, self.managed = channels_from_checkpoint(
-            self.specs,
-            self.checkpoint,
-            saver=self.checkpointer,
-            config=self.checkpoint_config,
+            self.specs, self.checkpoint
         )
         self.stack.push(self._suppress_interrupt)
         self.status = "input"
@@ -1471,6 +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, []
@@ -1495,15 +1499,11 @@ class AsyncPregelLoop(PregelLoop, AbstractAsyncContextManager):
             if saved.pending_writes is not None
             else []
         )
-        self._pending_write_futs = []
         self.submit = await self.stack.enter_async_context(
             AsyncBackgroundExecutor(self.config)
         )
-        self.channels, self.managed = await achannels_from_checkpoint(
-            self.specs,
-            self.checkpoint,
-            saver=self.checkpointer,
-            config=self.checkpoint_config,
+        self.channels, self.managed = channels_from_checkpoint(
+            self.specs, self.checkpoint
         )
         self.stack.push(self._suppress_interrupt)
         self.status = "input"

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
@@ -122,8 +123,8 @@ from langgraph.pregel._algo import (
 )
 from langgraph.pregel._call import identifier
 from langgraph.pregel._checkpoint import (
-    achannels_from_checkpoint,
     channels_from_checkpoint,
+    checkpoint_hydration_plan,
     copy_checkpoint,
     create_checkpoint,
     empty_checkpoint,
@@ -729,6 +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:
@@ -1050,17 +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,
-            saver=self.checkpointer
-            if isinstance(self.checkpointer, BaseCheckpointSaver)
-            else None,
-            config=saved.config,
+            checkpoint,
         )
         # tasks for this checkpoint
         next_tasks = prepare_next_tasks(
-            saved.checkpoint,
+            checkpoint,
             saved.pending_writes or [],
             self.nodes,
             channels,
@@ -1173,17 +1219,14 @@ class Pregel(
 
         step = saved.metadata.get("step", -1) + 1
         stop = step + 2
-        channels, managed = await achannels_from_checkpoint(
+        checkpoint = saved.checkpoint
+        channels, managed = channels_from_checkpoint(
             self.channels,
-            saved.checkpoint,
-            saver=self.checkpointer
-            if isinstance(self.checkpointer, BaseCheckpointSaver)
-            else None,
-            config=saved.config,
+            checkpoint,
         )
         # tasks for this checkpoint
         next_tasks = prepare_next_tasks(
-            saved.checkpoint,
+            checkpoint,
             saved.pending_writes or [],
             self.nodes,
             channels,
@@ -1309,7 +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,
@@ -1353,7 +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,
@@ -1407,9 +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
             )
@@ -1461,12 +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
             )
@@ -1526,12 +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 {}
             )
@@ -1550,11 +1604,6 @@ class Pregel(
             channels, managed = channels_from_checkpoint(
                 self.channels,
                 checkpoint,
-                saver=self.checkpointer
-                if saved is not None
-                and isinstance(self.checkpointer, BaseCheckpointSaver)
-                else None,
-                config=saved.config if saved is not None else None,
             )
             values, as_node = updates[0][:2]
 
@@ -1977,12 +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 {}
             )
@@ -1998,14 +2048,9 @@ class Pregel(
             )
             if saved:
                 checkpoint_config = patch_configurable(config, saved.config[CONF])
-            channels, managed = await achannels_from_checkpoint(
+            channels, managed = channels_from_checkpoint(
                 self.channels,
                 checkpoint,
-                saver=self.checkpointer
-                if saved is not None
-                and isinstance(self.checkpointer, BaseCheckpointSaver)
-                else None,
-                config=saved.config if saved is not None else None,
             )
             values, as_node = updates[0][:2]
             # no values, just clear all tasks

libs/langgraph/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "langgraph"
-version = "1.1.9"
+version = "1.1.7a2"
 description = "Building stateful, multi-actor applications with LLMs"
 authors = []
 requires-python = ">=3.10"
@@ -24,7 +24,7 @@ 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>=1.0.9,<1.1.0",

libs/langgraph/tests/test_delta_channel_benchmark.py

@@ -1,27 +1,21 @@
-"""Benchmark: DeltaChannel snapshot_frequency — storage vs. read-depth tradeoff.
+"""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
 
-Part 1 — baseline (original): DeltaChannel(inf) vs add_messages (BinOp).
-Part 2 — snapshot_frequency sweep: shows the storage/read-latency tradeoff
-  across frequencies [1, 5, 10, 50, inf] at scale.
+Simulates realistic multi-turn conversations with paragraph-length messages
+(~100 tokens each) scaling up to 1M-token-equivalent histories.
 
-Key insight:
-  snapshot_frequency=inf  → O(N) storage, O(N) read depth (pure delta)
-  snapshot_frequency=N    → O(N²/N) storage, O(N) read depth bounded by freq
-  snapshot_frequency=1    → O(N²) storage, O(1) read depth (full snapshot)
+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 contextlib
-import math
 import sys
 import time
 from typing import Annotated, Any
 
-import pytest
 from langchain_core.messages import AIMessage, HumanMessage
 from langgraph.checkpoint.memory import MemorySaver
 from typing_extensions import TypedDict
@@ -31,12 +25,13 @@ from langgraph.graph import END, StateGraph
 from langgraph.graph.message import add_messages
 
 try:
-    from langgraph.checkpoint.postgres import PostgresSaver
+    from langgraph.checkpoint.sqlite import SqliteSaver
 
-    _POSTGRES_AVAILABLE = True
-    _POSTGRES_URI = "postgres://sydney_runkle@localhost:5441/postgres?sslmode=disable"
+    _SQLITE_AVAILABLE = True
 except ImportError:
-    _POSTGRES_AVAILABLE = False
+    _SQLITE_AVAILABLE = False
+
+SNAPSHOT_EVERY = 50
 
 # ---------------------------------------------------------------------------
 # Realistic message payload (~100 tokens / ~400 chars each)
@@ -45,9 +40,7 @@ except ImportError:
 _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. "
-    "We've had prior incidents in this area and want to be deliberate. "
-    "What should we prioritize first, and are there known failure modes we should design around from the start?"
+    "and whether we need to refactor the {component} layer before proceeding."
 )
 
 _AI_TEMPLATE = (
@@ -117,16 +110,8 @@ class DeltaState(TypedDict):
     messages: Annotated[list, DeltaChannel(add_messages)]
 
 
-def _make_delta_state(snapshot_frequency: int | float) -> type:
-    """Create a TypedDict with DeltaChannel at the given snapshot_frequency."""
-    channel = DeltaChannel(add_messages, snapshot_frequency=snapshot_frequency)
-    # Use the functional TypedDict form so the Annotated type is stored as an
-    # already-evaluated object rather than a forward-reference string (which
-    # would fail when get_type_hints tries to resolve 'snapshot_frequency').
-    return TypedDict(  # type: ignore[return-value]
-        f"DeltaState_freq{snapshot_frequency}",
-        {"messages": Annotated[list, channel]},
-    )
+class DeltaSnapshotState(TypedDict):
+    messages: Annotated[list, DeltaChannel(add_messages, snapshot_every=SNAPSHOT_EVERY)]
 
 
 # ---------------------------------------------------------------------------
@@ -172,8 +157,9 @@ def _run_turns(
     """Run n_turns conversation turns.
 
     Returns (write_elapsed_s, read_elapsed_s, total_blob_bytes).
-    Read latency is the average of 5 get_state calls after the full history
-    is built — forces state rehydration including ancestor replay if needed.
+    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"}}
@@ -186,16 +172,16 @@ def _run_turns(
         )
     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
 
-    blob_bytes = (
-        _total_blob_bytes(graph.checkpointer)
-        if isinstance(graph.checkpointer, MemorySaver)
-        else -1
-    )
+    if isinstance(graph.checkpointer, MemorySaver):
+        blob_bytes = _total_blob_bytes(graph.checkpointer)
+    else:
+        blob_bytes = -1
     return write_elapsed, read_elapsed, blob_bytes
 
 
@@ -208,6 +194,7 @@ def _fmt_bytes(n: int) -> str:
 
 
 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"
@@ -217,248 +204,146 @@ def _approx_tokens(n_turns: int) -> str:
 
 
 # ---------------------------------------------------------------------------
-# Checkpointer factories
+# Benchmark matrix
 # ---------------------------------------------------------------------------
 
-
-@contextlib.contextmanager
-def _pg_saver(thread_id: str = "bench"):
-    """Context manager that yields a fresh PostgresSaver and cleans up after."""
-    with PostgresSaver.from_conn_string(_POSTGRES_URI) as saver:
-        saver.setup()
-        with saver._cursor() as cur:
-            for tbl in ("checkpoints", "checkpoint_blobs", "checkpoint_writes"):
-                cur.execute(f"DELETE FROM {tbl} WHERE thread_id = %s", (thread_id,))
-        yield saver
-        with saver._cursor() as cur:
-            for tbl in ("checkpoints", "checkpoint_blobs", "checkpoint_writes"):
-                cur.execute(f"DELETE FROM {tbl} WHERE thread_id = %s", (thread_id,))
+# 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 _checkpointers() -> list[tuple[str, Any]]:
-    """Return (label, saver_or_None) pairs for available checkpointers."""
-    result: list[tuple[str, Any]] = [("InMemory", None)]
-    if _POSTGRES_AVAILABLE:
-        try:
-            import psycopg
+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
 
-            psycopg.connect(_POSTGRES_URI).close()
-            result.append(("Postgres", "postgres"))
-        except Exception:
-            pass
-    return result
+        factories.append(("SQLite", tempfile.NamedTemporaryFile(suffix=".db")))
+    return factories
 
 
-# ---------------------------------------------------------------------------
-# Part 1: baseline DeltaChannel(inf) vs add_messages
-# ---------------------------------------------------------------------------
+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()
 
-BASELINE_TURN_COUNTS = [10, 25, 50, 100, 500]
-DELTA_ONLY_TURN_COUNTS = [1000]
+    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_baseline_for_checkpointer(cp_label: str, cp_hint: Any) -> None:
-    W = 72
+def _run_benchmark_for_checkpointer(cp_hint: Any) -> None:
+    import contextlib
+    import tempfile
 
+    @contextlib.contextmanager
     def _make_saver():
         if cp_hint is None:
-            return contextlib.nullcontext(None)
-        return _pg_saver()
+            yield None
+        else:
+            with tempfile.NamedTemporaryFile(suffix=".db") as f:
+                with SqliteSaver.from_conn_string(f.name) as saver:
+                    yield saver
 
-    rows: list[tuple[int, Any, Any, Any, Any, Any, Any]] = []
-    for turns in BASELINE_TURN_COUNTS:
+    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)
-        rows.append((turns, b_bytes, d_bytes, b_rt, d_rt, b_wt, d_wt))
-    for turns in DELTA_ONLY_TURN_COUNTS:
         with _make_saver() as saver:
-            d_wt, d_rt, d_bytes = _run_turns(turns, DeltaState, saver)
-        rows.append((turns, None, d_bytes, None, d_rt, None, d_wt))
+            s_wt, s_rt, s_bytes = _run_turns(turns, DeltaSnapshotState, saver)
 
-    def _bytes_or_na(v: Any) -> str:
-        if v is None or v < 0:
-            return "n/a"
-        return _fmt_bytes(v)
-
-    def _ms_or_na(v: Any) -> str:
-        return "n/a" if v is None else f"{v * 1000:.1f}ms"
-
-    print(f"\n  [{cp_label}] Storage (blob bytes)")
-    print(
-        f"  {'turns':>6}  {'ctx':>10}  {'add_msgs':>12}  {'delta(inf)':>12}  {'savings':>8}"
-    )
-    print("  " + "-" * (W - 2))
-    for turns, b_bytes, d_bytes, b_rt, d_rt, b_wt, d_wt in rows:
-        if b_bytes is None or b_bytes < 0 or d_bytes is None or d_bytes < 0:
-            ratio_str = "n/a"
+        # 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:
-            ratio = b_bytes / d_bytes if d_bytes else float("inf")
-            ratio_str = f"{ratio:.0f}x"
+            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"{_bytes_or_na(b_bytes):>12}  {_bytes_or_na(d_bytes):>12}  {ratio_str:>8}"
+            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(f"\n  [{cp_label}] Read latency (avg of 5 get_state calls)")
-    print(f"  {'turns':>6}  {'ctx':>10}  {'add_msgs':>12}  {'delta(inf)':>12}")
-    print("  " + "-" * (W - 2))
-    for turns, b_bytes, d_bytes, b_rt, d_rt, b_wt, d_wt in rows:
+    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"  {turns:>6}  {_approx_tokens(turns):>10}  "
-            f"{_ms_or_na(b_rt):>12}  {_ms_or_na(d_rt):>12}"
+            f"  Storage:  {_fmt_bytes(b_bytes)} (add_messages)  →  {_fmt_bytes(s_bytes)} (DeltaChannel+snapshot) — {ratio:.0f}x reduction"
         )
-
-
-def run_baseline_benchmark() -> None:
-    print()
-    print("Part 1 — DeltaChannel(inf) vs add_messages: storage & latency")
-    print("=" * 72)
-    for cp_label, cp_hint in _checkpointers():
-        _run_baseline_for_checkpointer(cp_label, cp_hint)
-    print()
-
-
-# ---------------------------------------------------------------------------
-# Part 2: snapshot_frequency sweep
-# ---------------------------------------------------------------------------
-
-# Frequencies to test. 1 = always snapshot (like BinOp), inf = pure delta.
-SNAPSHOT_FREQUENCIES: list[int | float] = [1, 5, 10, 50, math.inf]
-
-# Turn counts for the sweep — high enough to show storage divergence.
-SWEEP_TURN_COUNTS = [50, 100, 500]
-
-
-def _freq_label(freq: int | float) -> str:
-    if freq == math.inf:
-        return "inf"
-    return str(int(freq))
-
-
-def _run_sweep_for_checkpointer(cp_label: str, cp_hint: Any) -> None:
-    def _make_saver():
-        if cp_hint is None:
-            return contextlib.nullcontext(None)
-        return _pg_saver()
-
-    # Collect results: {turns: {freq_label: (write_s, read_s, bytes)}}
-    results: dict[int, dict[str, tuple[float, float, int]]] = {}
-    for turns in SWEEP_TURN_COUNTS:
-        results[turns] = {}
-        for freq in SNAPSHOT_FREQUENCIES:
-            state_cls = _make_delta_state(freq)
-            with _make_saver() as saver:
-                wt, rt, bb = _run_turns(turns, state_cls, saver)
-            results[turns][_freq_label(freq)] = (wt, rt, bb)
-
-    freq_labels = [_freq_label(f) for f in SNAPSHOT_FREQUENCIES]
-    col_w = 12
-
-    header = f"  {'turns':>6}  {'ctx':>10}" + "".join(
-        f"  {f'freq={freq_label}':>{col_w}}" for freq_label in freq_labels
-    )
-
-    print(f"\n  [{cp_label}] Storage (blob bytes) — lower is better")
-    print(header)
-    print("  " + "-" * (len(header) - 2))
-    for turns in SWEEP_TURN_COUNTS:
-        row = f"  {turns:>6}  {_approx_tokens(turns):>10}"
-        for label in freq_labels:
-            _, _, bb = results[turns][label]
-            row += f"  {_fmt_bytes(bb) if bb >= 0 else 'n/a':>{col_w}}"
-        print(row)
-
-    print(f"\n  [{cp_label}] Read latency (avg of 5 get_state) — lower is better")
-    print(header)
-    print("  " + "-" * (len(header) - 2))
-    for turns in SWEEP_TURN_COUNTS:
-        row = f"  {turns:>6}  {_approx_tokens(turns):>10}"
-        for label in freq_labels:
-            _, rt, _ = results[turns][label]
-            row += f"  {f'{rt * 1000:.1f}ms':>{col_w}}"
-        print(row)
-
-    print(
-        f"\n  [{cp_label}] Per-invoke write latency (total / turns) — lower is better"
-    )
-    print(header)
-    print("  " + "-" * (len(header) - 2))
-    for turns in SWEEP_TURN_COUNTS:
-        row = f"  {turns:>6}  {_approx_tokens(turns):>10}"
-        for label in freq_labels:
-            wt, _, _ = results[turns][label]
-            row += f"  {f'{(wt / turns) * 1000:.1f}ms':>{col_w}}"
-        print(row)
-
-
-def run_snapshot_freq_benchmark() -> None:
-    print()
-    print("Part 2 — DeltaChannel snapshot_frequency sweep")
-    print("Lower freq → fewer snapshots → less storage but deeper read replay")
-    print("=" * 80)
-    for cp_label, cp_hint in _checkpointers():
-        _run_sweep_for_checkpointer(cp_label, cp_hint)
-    print()
+        print(
+            f"  Read latency: {b_rt * 1000:.1f}ms (add_messages)  vs  {s_rt * 1000:.1f}ms (DeltaChannel+snapshot)"
+        )
+        print()
     print("Legend:")
     print(
-        "  freq=1    snapshot every write (full blob always — same as add_messages / BinOp)"
+        "  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("  freq=N    snapshot every N writes; read walks at most N ancestor writes")
-    print("  freq=inf  pure delta; read walks entire ancestor chain")
     print()
 
 
 # ---------------------------------------------------------------------------
-# Pytest entry points
+# Pytest entry point
 # ---------------------------------------------------------------------------
 
 
-@pytest.mark.skip(
-    reason="slow benchmark — run manually with: python tests/test_delta_channel_benchmark.py"
-)
-def test_delta_channel_baseline_benchmark(capsys: Any) -> None:
-    """DeltaChannel(inf) uses less storage than add_messages at scale."""
+def test_delta_channel_benchmark(capsys: Any) -> None:
+    """Storage grows O(N²) for add_messages, O(N) for DeltaChannel."""
     with capsys.disabled():
-        run_baseline_benchmark()
+        run_benchmark()
 
-    for turns in [25, 50]:
+    # 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}"
         )
-
-
-@pytest.mark.skip(
-    reason="slow benchmark — run manually with: python tests/test_delta_channel_benchmark.py"
-)
-def test_snapshot_freq_benchmark(capsys: Any) -> None:
-    """snapshot_frequency trades storage for bounded read depth."""
-    with capsys.disabled():
-        run_snapshot_freq_benchmark()
-
-    # Correctness: results at all frequencies should agree on final state.
-    n_turns = 20
-    states: dict[str, list] = {}
-    for freq in SNAPSHOT_FREQUENCIES:
-        state_cls = _make_delta_state(freq)
-        graph = _make_graph(state_cls)
-        config = {"configurable": {"thread_id": "correctness"}}
-        for i in range(n_turns):
-            graph.invoke(
-                {"messages": [HumanMessage(content=_human_content(i), id=f"h{i}")]},
-                config,
-            )
-        state = graph.get_state(config)
-        states[_freq_label(freq)] = [m.id for m in state.values["messages"]]
-
-    ref = states["inf"]
-    for label, msg_ids in states.items():
-        assert msg_ids == ref, (
-            f"freq={label} produced different message IDs than freq=inf"
+        assert s_bytes < b_bytes, (
+            f"DeltaChannel+snapshot should use less storage at {turns} turns, "
+            f"got snapshot={s_bytes} binary={b_bytes}"
         )
 
 
@@ -467,6 +352,5 @@ def test_snapshot_freq_benchmark(capsys: Any) -> None:
 # ---------------------------------------------------------------------------
 
 if __name__ == "__main__":
-    run_baseline_benchmark()
-    run_snapshot_freq_benchmark()
+    run_benchmark()
     sys.exit(0)

libs/langgraph/tests/test_delta_channel_migration.py

@@ -1,504 +0,0 @@
-"""Tests for the BinaryOperatorAggregate -> DeltaChannel migration path.
-
-A thread written under `BinaryOperatorAggregate(...)` must keep working
-after its annotation is swapped to `DeltaChannel(...)` on the same
-checkpointer — pre-migration state visible at each *settled* ancestor
-checkpoint is preserved, and post-migration writes fold on top through
-the reducer.
-
-Mechanism under test: the saver's `_get_channel_writes_history(config,
-channel)` walks the parent chain; when it encounters an ancestor whose
-`channel_values[channel]` is a real value (not `DELTA_SENTINEL`), it
-returns that as the `seed`. `DeltaChannel.from_checkpoint(seed)` uses
-it as the base value, and `replay_writes(writes)` folds on-path deltas.
-
-Scenarios covered:
-
-1. **Basic migration (sync + async)**: build pre-migration state with
-   `BinaryOperatorAggregate`, swap the annotation to `DeltaChannel` on
-   the same checkpointer, and verify that every settled pre-migration
-   super-step boundary (`next=('__start__',)`) round-trips exactly
-   under the delta-channel view.
-2. **Time travel into a pre-migration checkpoint** after migration —
-   `graph.get_state(pre_migration_config)` at a settled ancestor
-   returns the same state as under the binop channel.
-3. **Continuing a migrated thread**: driving one more super-step after
-   migration produces a state that includes the pre-migration settled
-   prefix plus the new delta write — proving `from_checkpoint(seed)` +
-   `replay_writes` correctly fold post-migration deltas onto the
-   pre-migration seed.
-4. **Base-saver fallback path**: a third-party-style subclass that
-   removes the optimized `InMemorySaver` override and falls back to
-   `BaseCheckpointSaver._get_channel_writes_history` must produce the
-   same result as the optimized path.
-5. **Channel-type isolation across threads**: two threads on the same
-   checkpointer under the delta-channel graph — one freshly-started,
-   one migrated from pre-migration state — don't cross-contaminate.
-   The parent-chain walk is scoped to the thread.
-
-TODO: add postgres variants in the existing `libs/checkpoint-postgres`
-test files (different fixture setup; not this file).
-"""
-
-from __future__ import annotations
-
-import operator
-from typing import Annotated, Any
-
-import pytest
-from langgraph.checkpoint.memory import InMemorySaver
-from typing_extensions import TypedDict
-
-from langgraph.channels.binop import BinaryOperatorAggregate
-from langgraph.channels.delta import DeltaChannel
-from langgraph.graph import END, START, StateGraph
-
-pytestmark = pytest.mark.anyio
-
-
-# ---------------------------------------------------------------------------
-# Graph factories
-#
-# A minimal reducer (`operator.add` on lists of str) with a noop node keeps
-# state change localized to the HumanMessage-like payload passed through
-# `invoke`. That isolates the pre/post-migration parity assertions to
-# channel-hydration semantics.
-# ---------------------------------------------------------------------------
-
-
-def _noop(_state: Any) -> dict:
-    return {}
-
-
-def _binop_graph(checkpointer: Any) -> Any:
-    class BinopState(TypedDict):
-        items: Annotated[list, BinaryOperatorAggregate(list, operator.add)]
-
-    return (
-        StateGraph(BinopState)
-        .add_node("noop", _noop)
-        .add_edge(START, "noop")
-        .add_edge("noop", END)
-        .compile(checkpointer=checkpointer)
-    )
-
-
-def _delta_graph(checkpointer: Any) -> Any:
-    class DeltaState(TypedDict):
-        items: Annotated[list, DeltaChannel(operator.add)]
-
-    return (
-        StateGraph(DeltaState)
-        .add_node("noop", _noop)
-        .add_edge(START, "noop")
-        .add_edge("noop", END)
-        .compile(checkpointer=checkpointer)
-    )
-
-
-def _drive(graph: Any, config: dict, tag: str, n: int) -> None:
-    for i in range(n):
-        graph.invoke({"items": [f"{tag}{i}"]}, config)
-
-
-async def _adrive(graph: Any, config: dict, tag: str, n: int) -> None:
-    for i in range(n):
-        await graph.ainvoke({"items": [f"{tag}{i}"]}, config)
-
-
-def _settled_boundaries(history: list) -> list[tuple[dict, list]]:
-    """Return `[(config, items), ...]` for every checkpoint in `history`
-    whose `next == ('__start__',)` — the stable boundaries between invokes.
-    """
-    return [
-        (s.config, list(s.values.get("items", [])))
-        for s in history
-        if s.next == ("__start__",)
-    ]
-
-
-# ---------------------------------------------------------------------------
-# 1. Basic migration (sync + async)
-# ---------------------------------------------------------------------------
-
-
-def test_basic_migration_preserves_pre_migration_state() -> None:
-    """Build state under `BinaryOperatorAggregate`, migrate to
-    `DeltaChannel` on the same checkpointer, and verify that every
-    settled pre-migration super-step boundary round-trips exactly.
-
-    Settled boundaries (`next=('__start__',)`) are the stable hydration
-    targets for the migration path: writes that produced the NEXT
-    super-step are kept as `pending_writes` on the ancestor, so walking
-    from a descendant finds the ancestor's blob as the seed and
-    reconstructs the correct state.
-    """
-
-    checkpointer = InMemorySaver()
-    config = {"configurable": {"thread_id": "basic-sync"}}
-
-    # Pre-migration: accumulate items across 3 invokes.
-    binop = _binop_graph(checkpointer)
-    _drive(binop, config, "u", 3)
-
-    pre_boundaries = _settled_boundaries(list(binop.get_state_history(config)))
-    assert len(pre_boundaries) >= 2, "expected multiple settled boundaries"
-
-    # Migrate: swap the annotation on the same checkpointer.
-    delta = _delta_graph(checkpointer)
-
-    for cfg, items in pre_boundaries:
-        snap = delta.get_state(cfg)
-        assert list(snap.values.get("items", [])) == items, (
-            f"snapshot mismatch at {cfg['configurable']['checkpoint_id']}: "
-            f"expected {items}, got {snap.values.get('items', [])}"
-        )
-
-
-async def test_basic_migration_preserves_pre_migration_state_async() -> None:
-    """Async variant of the basic migration scenario."""
-
-    checkpointer = InMemorySaver()
-    config = {"configurable": {"thread_id": "basic-async"}}
-
-    binop = _binop_graph(checkpointer)
-    await _adrive(binop, config, "u", 3)
-
-    pre_history = [s async for s in binop.aget_state_history(config)]
-    pre_boundaries = _settled_boundaries(pre_history)
-    assert len(pre_boundaries) >= 2
-
-    delta = _delta_graph(checkpointer)
-
-    for cfg, items in pre_boundaries:
-        snap = await delta.aget_state(cfg)
-        assert list(snap.values.get("items", [])) == items, (
-            f"async snapshot mismatch at {cfg['configurable']['checkpoint_id']}"
-        )
-
-
-# ---------------------------------------------------------------------------
-# 2. Time travel into a pre-migration checkpoint after migration
-# ---------------------------------------------------------------------------
-
-
-def test_time_travel_into_pre_migration_checkpoint() -> None:
-    """After migration, `graph.get_state(pre_migration_config)` at a
-    settled ancestor returns the state as stored at that point."""
-
-    checkpointer = InMemorySaver()
-    config = {"configurable": {"thread_id": "time-travel"}}
-
-    binop = _binop_graph(checkpointer)
-    _drive(binop, config, "u", 3)
-
-    pre_boundaries = _settled_boundaries(list(binop.get_state_history(config)))
-    assert pre_boundaries, "no settled ancestors to time-travel to"
-
-    delta = _delta_graph(checkpointer)
-
-    # Pick the oldest non-empty boundary — a long distance to walk back.
-    non_empty = [(cfg, items) for cfg, items in pre_boundaries if items]
-    assert non_empty, "expected at least one non-empty boundary"
-    target_cfg, expected_items = non_empty[-1]
-
-    snap = delta.get_state(target_cfg)
-    assert list(snap.values.get("items", [])) == expected_items
-
-
-# ---------------------------------------------------------------------------
-# 3. Continuing a migrated thread: deltas fold onto pre-migration seed
-# ---------------------------------------------------------------------------
-
-
-def test_continuing_migrated_thread_folds_deltas_on_seed() -> None:
-    """Resume a pre-migration settled ancestor via `invoke(None, cfg)`
-    under the delta-channel graph. Since the pre-migration checkpoint
-    has an existing `pending_writes` entry (the input for the NEXT
-    super-step), re-running from that ancestor reproduces the same
-    post-ancestor state as the original binop run.
-
-    This proves the seed-terminator + write-replay pipeline works
-    end-to-end across the migration boundary.
-    """
-
-    checkpointer = InMemorySaver()
-    config = {"configurable": {"thread_id": "continue"}}
-
-    binop = _binop_graph(checkpointer)
-    _drive(binop, config, "u", 2)
-
-    # Pick the oldest settled boundary with non-empty state.
-    pre_boundaries = _settled_boundaries(list(binop.get_state_history(config)))
-    target_cfg, seed_items = next(
-        (cfg, items) for cfg, items in reversed(pre_boundaries) if items
-    )
-    assert seed_items, "need a non-empty seed boundary"
-
-    # Migrate and resume from the pre-migration ancestor. `invoke(None,
-    # cfg)` replays the pending writes staged at `cfg` under the new
-    # channel; the reducer folds those deltas onto the seed.
-    delta = _delta_graph(checkpointer)
-    result = delta.invoke(None, target_cfg)
-
-    # The resumed state must include the pre-migration seed items in order.
-    result_items = list(result.get("items", []))
-    for idx, prefix_item in enumerate(seed_items):
-        assert result_items[idx] == prefix_item, (
-            f"pre-migration seed item at {idx} not preserved: "
-            f"got {result_items[: idx + 1]}, expected {seed_items}"
-        )
-
-
-# ---------------------------------------------------------------------------
-# 4. Base-saver fallback path
-# ---------------------------------------------------------------------------
-
-
-class _ThirdPartyStyleSaver(InMemorySaver):
-    """Simulates a third-party saver that inherits the reference
-    `_get_channel_writes_history` implementation from
-    `BaseCheckpointSaver` rather than overriding it.
-
-    We rebind the two methods to the base-class versions (via MRO) so
-    the fallback path is exercised even though the storage layer is
-    still the in-memory one.
-    """
-
-    # MRO: [_ThirdPartyStyleSaver, InMemorySaver, BaseCheckpointSaver, ...]
-    _get_channel_writes_history = (  # type: ignore[assignment]
-        InMemorySaver.__mro__[1]._get_channel_writes_history  # type: ignore[attr-defined]
-    )
-    _aget_channel_writes_history = (  # type: ignore[assignment]
-        InMemorySaver.__mro__[1]._aget_channel_writes_history  # type: ignore[attr-defined]
-    )
-
-
-def test_base_saver_fallback_matches_optimized_override() -> None:
-    """The reference `BaseCheckpointSaver` implementation must produce
-    the same migration behavior as the optimized `InMemorySaver`
-    override. We drive the same migration scenario through both savers
-    and assert per-snapshot parity in the delta-channel view."""
-
-    # Fast path: optimized InMemorySaver override.
-    fast_saver = InMemorySaver()
-    fast_config = {"configurable": {"thread_id": "fast"}}
-    fast_binop = _binop_graph(fast_saver)
-    _drive(fast_binop, fast_config, "u", 3)
-    fast_delta = _delta_graph(fast_saver)
-    fast_history = [
-        (s.next, list(s.values.get("items", [])))
-        for s in fast_delta.get_state_history(fast_config)
-    ]
-
-    # Slow path: base-class fallback.
-    slow_saver = _ThirdPartyStyleSaver()
-    slow_config = {"configurable": {"thread_id": "slow"}}
-    slow_binop = _binop_graph(slow_saver)
-    _drive(slow_binop, slow_config, "u", 3)
-    slow_delta = _delta_graph(slow_saver)
-    slow_history = [
-        (s.next, list(s.values.get("items", [])))
-        for s in slow_delta.get_state_history(slow_config)
-    ]
-
-    assert slow_history == fast_history, (
-        "base-saver fallback should match optimized-override behavior; "
-        f"fast={fast_history}, slow={slow_history}"
-    )
-
-
-# ---------------------------------------------------------------------------
-# 5. Thread isolation under mixed-generation storage
-# ---------------------------------------------------------------------------
-
-
-def test_delta_and_migrated_threads_do_not_cross_contaminate() -> None:
-    """Two threads sharing a checkpointer — one migrated from
-    pre-migration state, one freshly-started under DeltaChannel — must
-    maintain independent state. The parent-chain walk in
-    `_get_channel_writes_history` must be scoped to the target thread.
-    """
-
-    checkpointer = InMemorySaver()
-    migrated_cfg = {"configurable": {"thread_id": "migrated"}}
-    fresh_cfg = {"configurable": {"thread_id": "fresh"}}
-
-    # Thread A: pre-migration build-up.
-    binop = _binop_graph(checkpointer)
-    _drive(binop, migrated_cfg, "m", 2)
-
-    # Thread B: fresh delta-channel run.
-    delta = _delta_graph(checkpointer)
-    _drive(delta, fresh_cfg, "f", 2)
-
-    # Thread A: migrate and confirm its state is anchored in its own
-    # thread's pre-migration history (tag 'm'), never mixing in tag 'f'.
-    migrated_boundaries = _settled_boundaries(
-        list(delta.get_state_history(migrated_cfg))
-    )
-    assert migrated_boundaries, "migrated thread has no settled boundaries"
-    for _, items in migrated_boundaries:
-        for it in items:
-            assert it.startswith("m"), (
-                f"migrated thread leaked item from other thread: {it}"
-            )
-
-    # Thread B: settled boundaries must only contain 'f' tags.
-    fresh_boundaries = _settled_boundaries(list(delta.get_state_history(fresh_cfg)))
-    assert fresh_boundaries, "fresh thread has no settled boundaries"
-    for _, items in fresh_boundaries:
-        for it in items:
-            assert it.startswith("f"), (
-                f"fresh thread leaked item from migrated thread: {it}"
-            )
-
-
-# ---------------------------------------------------------------------------
-# 6. Tip-of-pre-migration hydration: the latest checkpoint from a binop-run
-# thread has a real accumulated value in its own `channel_values["items"]`.
-# When hydrated under the delta-channel graph via `get_state(config)` with no
-# `checkpoint_id`, the short-circuit must use that value directly instead of
-# walking ancestors (which would skip the tip's own blob).
-# ---------------------------------------------------------------------------
-
-
-def test_tip_of_pre_migration_hydrates_directly() -> None:
-    """`graph.get_state(config)` at the latest (pre-migration) checkpoint
-    returns the full accumulated list stored in that checkpoint's own
-    `channel_values`. The hydration must not walk ancestors past it."""
-
-    checkpointer = InMemorySaver()
-    config = {"configurable": {"thread_id": "tip-sync"}}
-
-    binop = _binop_graph(checkpointer)
-    _drive(binop, config, "u", 3)
-
-    binop_tip = binop.get_state(config)
-    expected_items = list(binop_tip.values.get("items", []))
-    assert expected_items == ["u0", "u1", "u2"], (
-        f"sanity: pre-migration tip should accumulate all 3 items, got {expected_items}"
-    )
-
-    delta = _delta_graph(checkpointer)
-
-    snap = delta.get_state(config)
-    assert list(snap.values.get("items", [])) == expected_items, (
-        f"tip hydration mismatch: expected {expected_items}, "
-        f"got {snap.values.get('items', [])}"
-    )
-
-
-async def test_tip_of_pre_migration_hydrates_directly_async() -> None:
-    """Async variant of the tip-of-pre-migration hydration scenario."""
-
-    checkpointer = InMemorySaver()
-    config = {"configurable": {"thread_id": "tip-async"}}
-
-    binop = _binop_graph(checkpointer)
-    await _adrive(binop, config, "u", 3)
-
-    binop_tip = await binop.aget_state(config)
-    expected_items = list(binop_tip.values.get("items", []))
-    assert expected_items == ["u0", "u1", "u2"]
-
-    delta = _delta_graph(checkpointer)
-
-    snap = await delta.aget_state(config)
-    assert list(snap.values.get("items", [])) == expected_items, (
-        f"async tip hydration mismatch: expected {expected_items}, "
-        f"got {snap.values.get('items', [])}"
-    )
-
-
-# ---------------------------------------------------------------------------
-# 7. `update_state` after migration writes a real value to the new
-# checkpoint's `channel_values` (not a sentinel). Hydration must use it
-# directly — the ancestor walk would skip this blob and return stale state.
-# ---------------------------------------------------------------------------
-
-
-def test_update_state_after_migration_uses_written_value() -> None:
-    """After migrating and running at least one post-migration super-step
-    (so the thread's tip has a `DELTA_SENTINEL`), `update_state` writes a
-    concrete value to a new checkpoint's `channel_values`. `get_state`
-    must reflect that concrete value."""
-
-    checkpointer = InMemorySaver()
-    config = {"configurable": {"thread_id": "update-state"}}
-
-    # Pre-migration: accumulate a little state.
-    binop = _binop_graph(checkpointer)
-    _drive(binop, config, "u", 2)
-
-    # Migrate and run one more super-step so the tip is a post-migration
-    # checkpoint with `DELTA_SENTINEL` in its own `channel_values`.
-    delta = _delta_graph(checkpointer)
-    delta.invoke({"items": ["post"]}, config)
-
-    # `update_state` writes a concrete value into a new checkpoint's blob
-    # via the reducer against the hydrated prior state.
-    delta.update_state(config, {"items": ["x", "y"]})
-
-    snap = delta.get_state(config)
-    updated_items = list(snap.values.get("items", []))
-    # Must include the "x","y" update; without the hydration fix, the
-    # update_state-written blob would be skipped in favor of an ancestor
-    # walk, and the update values would disappear.
-    assert "x" in updated_items and "y" in updated_items, (
-        f"update_state values missing from snapshot: {updated_items}"
-    )
-    # The "x","y" items should be folded onto the prior accumulated state,
-    # not stand alone. This verifies the update-written blob is used
-    # directly by `get_state` (no ancestor walk past it).
-    assert len(updated_items) >= 4, (
-        f"update_state snapshot should preserve pre-update state, got {updated_items}"
-    )
-    assert updated_items[-2:] == ["x", "y"], (
-        f"update_state deltas should be at the tail, got {updated_items}"
-    )
-
-
-# ---------------------------------------------------------------------------
-# 8. Fork from an `update_state` checkpoint: a new run branched off the
-# update_state-produced checkpoint must see that checkpoint's concrete
-# `channel_values` as its base, with new deltas folded on top.
-# ---------------------------------------------------------------------------
-
-
-def test_fork_from_update_state_checkpoint() -> None:
-    """Branching a new run from the checkpoint produced by `update_state`
-    must use that checkpoint's concrete blob as the base. Additional
-    deltas from the forked run fold onto it through the reducer."""
-
-    checkpointer = InMemorySaver()
-    config = {"configurable": {"thread_id": "fork"}}
-
-    # Pre-migration build-up, then migrate and add one post-migration step.
-    binop = _binop_graph(checkpointer)
-    _drive(binop, config, "u", 2)
-    delta = _delta_graph(checkpointer)
-    delta.invoke({"items": ["post"]}, config)
-
-    # Apply `update_state` and capture the returned config (references
-    # the new checkpoint produced by the update).
-    update_cfg = delta.update_state(config, {"items": ["x", "y"]})
-
-    update_snap = delta.get_state(update_cfg)
-    base_items = list(update_snap.values.get("items", []))
-    assert "x" in base_items and "y" in base_items, (
-        f"update_state values missing from snapshot: {base_items}"
-    )
-    assert base_items[-2:] == ["x", "y"], (
-        f"sanity: update_state deltas should be at the tail, got {base_items}"
-    )
-
-    # Fork: invoke from the update_state checkpoint with a new delta.
-    forked = delta.invoke({"items": ["fork0"]}, update_cfg)
-    forked_items = list(forked.get("items", []))
-    # The fork must see the update_state-written blob as its base (not
-    # walk past it), and the new delta must fold on top of it.
-    assert forked_items[: len(base_items)] == base_items, (
-        f"fork lost update_state base: base={base_items}, forked={forked_items}"
-    )
-    assert forked_items[-1] == "fork0", f"fork delta not appended: {forked_items}"

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

@@ -41,7 +41,6 @@ from typing_extensions import NotRequired, TypedDict
 
 from langgraph._internal._constants import CONFIG_KEY_NODE_FINISHED, ERROR, PULL
 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
 from langgraph.channels.topic import Topic
@@ -9408,6 +9407,7 @@ async def test_delta_channel_end_to_end_inmemory() -> None:
     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
 
@@ -9449,6 +9449,7 @@ async def test_delta_channel_time_travel() -> None:
     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
 
@@ -9506,6 +9507,7 @@ async def test_delta_channel_remove_message_end_to_end() -> None:
     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
 
@@ -9552,6 +9554,7 @@ async def test_delta_channel_update_by_id_end_to_end() -> None:
     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
 
@@ -9584,90 +9587,3 @@ async def test_delta_channel_update_by_id_end_to_end() -> None:
     assert "h1" in ids  # h1 persists (updated, not duplicated)
     assert "h2" in ids
     assert ids.count("h1") == 1, "h1 must not be duplicated"
-
-
-async def test_delta_channel_write_flushed_before_put() -> None:
-    """checkpoint_writes are flushed synchronously before put when DELTA_SENTINEL
-    is present, ensuring writes are durable before the sentinel blob is committed.
-
-    We verify this by intercepting put_writes and put calls and confirming
-    put_writes always completes before put is called for sentinel checkpoints.
-    """
-    import threading
-    from typing import Annotated
-
-    from langchain_core.messages import AIMessage, HumanMessage
-    from langgraph.checkpoint.base import DELTA_SENTINEL
-    from langgraph.checkpoint.memory import InMemorySaver
-
-    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:
-        i = len(state["messages"])
-        return {"messages": [AIMessage(content=f"r{i}", id=f"ai{i}")]}
-
-    order: list[str] = []
-    lock = threading.Lock()
-    original_put_writes = InMemorySaver.put_writes
-    original_put = InMemorySaver.put
-
-    def tracked_put_writes(self, config, writes, task_id, task_path=""):
-        result = original_put_writes(self, config, writes, task_id, task_path)
-        with lock:
-            order.append("put_writes")
-        return result
-
-    def tracked_put(self, config, checkpoint, metadata, new_versions):
-        # Check if this checkpoint has any DELTA_SENTINEL blobs
-        has_sentinel = any(
-            v is DELTA_SENTINEL for v in checkpoint.get("channel_values", {}).values()
-        )
-        if has_sentinel:
-            with lock:
-                order.append("put_sentinel")
-        else:
-            with lock:
-                order.append("put_snapshot")
-        return original_put(self, config, checkpoint, metadata, new_versions)
-
-    InMemorySaver.put_writes = tracked_put_writes
-    InMemorySaver.put = tracked_put
-    try:
-        builder = StateGraph(State)
-        builder.add_node("respond", respond)
-        builder.add_edge(START, "respond")
-        saver = InMemorySaver()
-        graph = builder.compile(checkpointer=saver)
-        config = {"configurable": {"thread_id": "flush-test"}}
-
-        for i in range(3):
-            graph.invoke(
-                {"messages": [HumanMessage(content=f"h{i}", id=f"h{i}")]}, config
-            )
-
-        # For every sentinel put, all preceding put_writes must already be in order
-        for i, event in enumerate(order):
-            if event == "put_sentinel":
-                # All put_writes before this index must appear before this sentinel
-                preceding = order[:i]
-                assert "put_writes" in preceding, (
-                    f"put_sentinel at index {i} had no preceding put_writes: {order}"
-                )
-                # And the most recent put_writes must come before this sentinel
-                last_write_idx = max(
-                    j for j, e in enumerate(order[:i]) if e == "put_writes"
-                )
-                assert last_write_idx < i, (
-                    f"put_writes at {last_write_idx} not before put_sentinel at {i}"
-                )
-    finally:
-        InMemorySaver.put_writes = original_put_writes
-        InMemorySaver.put = original_put
-
-    # Final state must still be correct
-    state = graph.get_state(config)
-    assert len(state.values["messages"]) == 6  # 3 human + 3 AI

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 = "1.3.0"
+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/92/fe/20190232d9b513242899dbb0c2bb77e31b4d61e343743adbe90ebc2603d2/langchain_core-1.3.0.tar.gz", hash = "sha256:14a39f528bf459aa3aa40d0a7f7f1bae7520d435ef991ae14a4ceb74d8c49046", size = 860755, upload-time = "2026-04-17T14:51:38.298Z" }
+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/f8/e2/dbfa347aa072a6dc4cd38d6f9ebfc730b4c14c258c47f480f4c5c546f177/langchain_core-1.3.0-py3-none-any.whl", hash = "sha256:baf16ee028475df177b9ab8869a751c79406d64a6f12125b93802991b566cced", size = 515140, upload-time = "2026-04-17T14:51:36.274Z" },
+    { 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 = "1.1.9"
+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" },
@@ -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 = "1.0.10"
+version = "1.0.9"
 source = { editable = "../prebuilt" }
 dependencies = [
     { name = "langchain-core" },

libs/prebuilt/langgraph/prebuilt/tool_node.py

@@ -808,7 +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,
             )
@@ -843,7 +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,
             )
@@ -1578,7 +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.
@@ -1621,7 +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 = "1.0.10"
+version = "1.0.9"
 description = "Library with high-level APIs for creating and executing LangGraph agents and tools."
 authors = []
 requires-python = ">=3.10"

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_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 ---

libs/prebuilt/uv.lock

@@ -249,7 +249,7 @@ wheels = [
 
 [[package]]
 name = "langchain-core"
-version = "1.3.0"
+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/92/fe/20190232d9b513242899dbb0c2bb77e31b4d61e343743adbe90ebc2603d2/langchain_core-1.3.0.tar.gz", hash = "sha256:14a39f528bf459aa3aa40d0a7f7f1bae7520d435ef991ae14a4ceb74d8c49046", size = 860755, upload-time = "2026-04-17T14:51:38.298Z" }
+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/f8/e2/dbfa347aa072a6dc4cd38d6f9ebfc730b4c14c258c47f480f4c5c546f177/langchain_core-1.3.0-py3-none-any.whl", hash = "sha256:baf16ee028475df177b9ab8869a751c79406d64a6f12125b93802991b566cced", size = 515140, upload-time = "2026-04-17T14:51:36.274Z" },
+    { 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 = "1.1.9"
+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" },
@@ -490,7 +490,7 @@ test = [
 
 [[package]]
 name = "langgraph-prebuilt"
-version = "1.0.10"
+version = "1.0.9"
 source = { editable = "." }
 dependencies = [
     { name = "langchain-core" },

libs/sdk-py/uv.lock

@@ -262,7 +262,7 @@ wheels = [
 
 [[package]]
 name = "langchain-core"
-version = "1.3.0"
+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/92/fe/20190232d9b513242899dbb0c2bb77e31b4d61e343743adbe90ebc2603d2/langchain_core-1.3.0.tar.gz", hash = "sha256:14a39f528bf459aa3aa40d0a7f7f1bae7520d435ef991ae14a4ceb74d8c49046", size = 860755, upload-time = "2026-04-17T14:51:38.298Z" }
+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/f8/e2/dbfa347aa072a6dc4cd38d6f9ebfc730b4c14c258c47f480f4c5c546f177/langchain_core-1.3.0-py3-none-any.whl", hash = "sha256:baf16ee028475df177b9ab8869a751c79406d64a6f12125b93802991b566cced", size = 515140, upload-time = "2026-04-17T14:51:36.274Z" },
+    { 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 = "1.1.9"
+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 = "." },
@@ -413,7 +413,7 @@ test = [
 
 [[package]]
 name = "langgraph-prebuilt"
-version = "1.0.10"
+version = "1.0.9"
 source = { editable = "../prebuilt" }
 dependencies = [
     { name = "langchain-core" },

notes/delta_channel_query_bench.md

@@ -1,137 +0,0 @@
-# Delta-channel reconstruction: query strategy benchmark
-
-**Branch:** `delta-channel-writes-based`
-**Question (Nuno):** Is the recursive CTE the right query shape for reconstructing a delta channel inside `get_tuple`, or would a plain `SELECT WHERE` be cheaper even though it returns more rows?
-**Answer:** Plain `SELECT WHERE` wins at every realistic depth. The recursion isn't the problem — the JSON-expression join inside the CTE is.
-
-## Setup
-
-- Postgres 16 on `localhost:5441` (the `compose-postgres.yml` instance, run directly without docker for this round)
-- Single delta channel `messages`, one write per checkpoint, `DELTA_SENTINEL` blob per checkpoint
-- Linear chain (`branch=1`) and 5-way branching at every step (`branch=5`) — branching is the case where plain over-fetches sibling rows
-- Median of 20 timed runs after 3 warmups, fresh psycopg cursor per strategy
-- Bench script: `bench_get_tuple_strategies.py` at repo root
-
-Three strategies compared:
-
-| name | roundtrips | shape |
-|------|-----------|-------|
-| `cte` | 1 | Current prod: recursive CTE walks ancestors, LEFT JOINs writes + blobs |
-| `plain` | 3 | Nuno's suggestion: thread-wide `SELECT WHERE` per table, Python walks parent chain and filters |
-| `cte+narrow` | 2 | CTE returns ancestor IDs only, then one `UNION ALL` of writes + blobs filtered by `ANY(ids)` |
-
-## Results (ms per get_tuple, median of 20)
-
-```
- depth  branch       cte       plain    cte+narrow   rows_cte   rows_plain   plain/cte
-    10       1     0.14ms      0.26ms       0.24ms          9           30      1.89x
-    10       5     0.21ms      0.23ms       0.17ms          9          110      1.11x
-    50       1     0.89ms      0.27ms       0.33ms         49          150      0.31x
-    50       5     2.35ms      0.66ms       0.51ms         49          550      0.28x
-   200       1    11.61ms      0.78ms       1.30ms        199          600      0.07x
-   200       5    34.79ms      2.33ms       3.07ms        199         2200      0.07x
-  1000       1   274.60ms      2.59ms      13.29ms        999         3000      0.01x
-  1000       5   856.01ms     10.14ms      15.31ms        999        11000      0.01x
-```
-
-Lower is better. `plain/cte < 1` means plain is faster.
-
-### Headline numbers
-
-- depth 50: plain is **3x** faster
-- depth 200: plain is **15x** faster
-- depth 1000: plain is **~100x** faster
-- Branching makes plain over-fetch (3000 rows → 11000 rows at d=1000), but it remains ~85x faster than the CTE
-
-## Why the CTE collapses
-
-`EXPLAIN (ANALYZE, BUFFERS)` of the CTE at depth 1000 (linear). Excerpt with the load-bearing nodes:
-
-```
-Sort  ... actual time=137.798..137.827 rows=999
-  CTE ancestors
-    ->  Recursive Union  ... actual time=0.005..2.443 rows=999
-                                                 ^^^^^^
-                                                 recursion is 2.4 ms — fine
-  ->  Nested Loop Left Join  ... actual time=2.676..137.529 rows=999
-        Join Filter: (cw.checkpoint_id = a.cid)
-        Rows Removed by Join Filter: 998001
-                                     ^^^^^^^
-                                     999 ancestors x ~1000 writes
-        ->  Nested Loop Left Join  ... actual time=2.669..85.061 rows=999
-              Join Filter: (bl.version = ((c.checkpoint -> 'channel_versions'::text) ->> bl.channel))
-              Rows Removed by Join Filter: 998001
-                                           ^^^^^^^
-                                           same quadratic blow-up on the blob join
-```
-
-Two pathological things are happening:
-
-1. **The blob join filter is on a JSON expression**: `bl.version = (c.checkpoint -> 'channel_versions' ->> bl.channel)`. The planner cannot push this into an index lookup, so it materializes `checkpoint_blobs` for the thread and does a nested-loop comparison against every ancestor — a Cartesian product that grows as `O(ancestors × blobs_in_thread)`.
-2. **The writes join is similar**: writes for the thread are materialized once, then nested-loop joined against ancestors with a `Join Filter` rather than a hash/merge join over the indexed `checkpoint_id`.
-
-At depth 1000 that's **~2 million rows evaluated, 99.9% of them discarded**. The recursion itself is a rounding error.
-
-For comparison, the plain Q1 (`SELECT … FROM checkpoints WHERE thread_id=? AND checkpoint_ns=?`) at depth 1000:
-
-```
-Seq Scan on checkpoints  ... actual time=0.012..0.121 rows=1000
-Execution Time: 0.140 ms
-```
-
-A simple seq scan over 57 buffers. Q2 and Q3 follow the same shape and complete in well under 1 ms each.
-
-## Crossover and remote-DB reasoning
-
-- Pure local Postgres: plain wins from depth ~30 onward; CTE wins by fractions of a ms below that
-- Remote Postgres at ~5 ms RTT adds ~10 ms to plain (3 roundtrips vs 1). Crossover shifts to ~depth 30. Above that, the CTE's quadratic SQL cost still dominates the RTT savings.
-
-There is no realistic conversation depth where the CTE wins on a remote DB. At depth 200+ (anything resembling a real multi-turn agent run) plain is faster regardless of network.
-
-## Recommendation
-
-**Switch to plain SELECT WHERE, one delta channel at a time.**
-
-Three indexed queries per delta channel:
-
-```sql
--- Q1: parent chain + per-checkpoint version of this channel
-SELECT checkpoint_id,
-       parent_checkpoint_id,
-       checkpoint -> 'channel_versions' ->> 'channel_name' AS ver
-FROM checkpoints
-WHERE thread_id = ? AND checkpoint_ns = ?;
-
--- Q2: writes for this channel, anywhere in the thread
-SELECT checkpoint_id, type, blob, task_id, idx
-FROM checkpoint_writes
-WHERE thread_id = ? AND checkpoint_ns = ? AND channel = ?;
-
--- Q3: blobs for this channel, anywhere in the thread
-SELECT version, type, blob
-FROM checkpoint_blobs
-WHERE thread_id = ? AND checkpoint_ns = ? AND channel = ?;
-```
-
-Python then:
-- Builds `parent_of: dict[cid, parent_cid]` from Q1
-- Walks from target's parent newest → oldest
-- Filters Q2 rows by `ancestor_set`, processes oldest → newest, applies overwrite-terminator
-- Picks seed blob via the per-ancestor `ver` map, terminates at first non-sentinel blob
-
-All O(n) on n = thread checkpoints, with tight constants (dict lookups). No recursion, no JSON-expression joins, no quadratic plans.
-
-If the 3-roundtrip cost ever shows up on remote-DB benchmarks, fold Q2 + Q3 into one `UNION ALL` to get back to 2 roundtrips. Bench says it isn't worth the SQL complexity right now.
-
-## Bonus: code simplification from single-channel scope
-
-Multi-channel reconstruction in the current `_reconstruct_delta_channels_cur` carries:
-
-- `rows_by_cid` nested dicts, keyed by cid then channel
-- `seen_blob: set[(cid, channel)]` and `seen_write: set[(cid, channel, task_id, idx)]` dedup
-- `collected: dict[channel, list]`, `done: set[channel]`, `seeds: dict[channel, value]`
-- Inner `for ch in channels_list` loops and an early-exit `if len(done) == len(channels_list)`
-
-Single-channel collapses these to a single list, a single bool, and one `Optional[Any]`. Roughly half the Python in that function, plus an obvious shape for splitting pure post-processing into `base.py` so sync and async stop duplicating it.
-
-If multi-channel coalescing turns out to matter later, it can come back as a SQL-level optimization without re-introducing the bookkeeping in Python.