3tears-langgraph

Three-tier LangGraph checkpoint saver: L1 (SQLite) -> L2 (NATS KV) -> L3 (PostgreSQL).

L1 and L2 are optional cache layers that degrade gracefully on failure. L3 (PostgreSQL) is the source of truth, reached through the AsyncQueryExecutor protocol so the same saver serves trusted services (direct asyncpg pool) and sandboxed agents (NATS L3 proxy).

L3 failures reach the caller, with one channel-scoped carve-out: aput_writes is called from LangGraph's executor teardown, where raising kills a turn that has already answered, so a failed crash-recovery write is logged and degraded. Writes on LangGraph's control channels (__interrupt__, __resume__, __error__, __scheduled__) still raise: losing one changes what the run does, and a lost __interrupt__ would silently skip a human-approval gate. A control-channel write also overwrites an earlier write on the same channel, matching the reference saver, so a second Command(resume=...) replaces the first rather than being dropped.

Installation

pip install 3tears-langgraph

Usage

from threetears.langgraph import (
    AsyncpgPoolAdapter,
    CheckpointScope,
    ThreeTierCheckpointSaver,
)

# Trusted service with direct asyncpg.Pool: wrap once
saver = ThreeTierCheckpointSaver(
    executor=AsyncpgPoolAdapter(pool),
    scope=CheckpointScope.for_customer(customer_id),
)

# Sandboxed agent: NatsProxyL3Backend already implements
# AsyncQueryExecutor, pass it straight through
saver = ThreeTierCheckpointSaver(
    executor=nats_l3_backend,
    scope=CheckpointScope.for_customer(customer_id),
)

graph = builder.compile(checkpointer=saver)

Scope is required

scope has no default. A saver either names the customer whose checkpoints it addresses, or says in writing that it deliberately names none:

saver = ThreeTierCheckpointSaver(
    executor=AsyncpgPoolAdapter(pool),
    scope=CheckpointScope.unscoped(reason="single-tenant deployment"),
)

CheckpointScope.for_customer(...) folds the customer into the stored thread_id, and therefore into the L3 bound parameter, the L2 bucket key, and the L1 thread key — a saver scoped to one customer cannot name another customer's row at any tier. It also unlocks adelete_customer_threads(), the whole-tenant purge, which refuses on an unscoped saver.

CheckpointScope.unscoped(...) is a legitimate answer, not a placeholder: it produces byte-identical keys and statements to a pre-tenancy saver, so an existing deployment adopts the required parameter by adding this one argument and migrating no data. The reason is mandatory, logged at WARNING on construction, and greppable in source, so "which deployments still run unscoped, and why" has an answer.

Adopting a real customer later is a data change rather than a code change: existing rows live under a bare thread id and a scoped saver will not find them, so they must be re-keyed (UPDATE checkpoints SET thread_id = $customer || '/' || thread_id, likewise checkpoint_writes, plus L2 invalidation). No re-key script ships here and none can — which customer owns which thread lives in the host's own tables, which this library has never seen.

Middleware

The package ships platform-level AgentMiddleware for langchain.agents.create_agent — the framework-aligned successor to the old hand-rolled AgentNodeHook / ToolNodeHook protocols. Consumer-specific policy lives in each consumer as its own middleware; only the reusable platform seams live here:

  • PromptCachingMiddleware (wrap_model_call) — annotates a leading bare-string system message with Anthropic cache_control={"type": "ephemeral"} when the model supports it, then normalizes cache-hit/creation counters onto usage_metadata["cache_usage"]. Non-Anthropic adapters degrade silently to bare-string system messages.
  • ToolResultOffloadMiddleware (wrap_tool_call) — when a ToolResultOffloader is injected on config["configurable"] and a tool result exceeds offload_threshold_chars, stores the full content out-of-band and shows the model "<summary>\n\n[ctx:<handle>]" (the structured artifact is preserved). Opt-in: no offloader ⇒ byte-for-byte no-op.
  • ObjectCatalogMiddleware (wrap_tool_call) — when a tool returns an ObjectHandle in its result artifact and an ObjectCataloger is injected, persists a catalog record under the verified call identity. Soft-fail side-effect: a catalog error never breaks the tool result.
from langchain.agents import create_agent

from threetears.langgraph import (
    ObjectCatalogMiddleware,
    PromptCachingMiddleware,
    ToolResultOffloadMiddleware,
)

agent = create_agent(
    model=chat_anthropic,
    tools=tools,
    middleware=[
        PromptCachingMiddleware(),
        ToolResultOffloadMiddleware(),
        ObjectCatalogMiddleware(),
    ],
)
# after a run, PromptCachingMiddleware has stamped:
# message.usage_metadata["cache_usage"]
# == {"cache_read_input_tokens": ..., "cache_creation_input_tokens": ..., "cached_tokens": ...}

The offload / catalog contracts (ToolResultOffloader, ObjectCataloger) are pure structural Protocols exported from threetears.langgraph.offload / threetears.langgraph.catalog; a consumer injects a concrete implementation on config["configurable"] (e.g. tool_result_offloader, object_cataloger) without the package taking any dependency on the consumer's context store.

See 3tears/docs/prompt-caching.md for the full caching contract, summarization interaction, downstream wiring checklist, and a worked example.

Streaming

The package ships StreamingResponse, a transport-agnostic primitive that owns the lifecycle of one streaming response: start -> any number of emit_token / emit_tool_call_* -> mutually-exclusive end (success) or error (failure) terminal. run_graph(compiled_graph, state, config) consumes a LangGraph astream_events(version="v2") loop with the start/end ordering managed; on graph exception it fires error(code="AGENT_FAILED", ...) and re-raises so the caller still sees the failure on the synchronous path.

The wire vocabulary is fixed: StreamStartEvent / StreamTokenEvent / StreamEndEvent / StreamErrorEvent / ToolCallStartEvent / ToolCallEndEvent / ToolCallProgressEvent, dispatched via the StreamEvent discriminated union and the parse_stream_event(payload) adapter. The transport seam is the StreamTransport Protocol -- one method, async def publish(self, payload: bytes) -> None. Any wire (NATS subject, websocket, chunked HTTP body) satisfies it.

from threetears.langgraph import StreamingResponse, StreamTransport

class WebSocketStreamTransport:
    """example transport for a websocket consumer."""
    def __init__(self, ws): self._ws = ws
    async def publish(self, payload: bytes) -> None:
        await self._ws.send_bytes(payload)

stream = StreamingResponse(
    transport=WebSocketStreamTransport(ws),
    correlation_id=correlation_id,
    conversation_id=conversation_id,
    start_time_monotonic=request_start,
)
final_state = await stream.run_graph(compiled_graph, state, config)

A reference adapter can bind the primitive to a per-correlation-id stream subject via nc.publish_raw. Tool-call observation envelopes flow through ToolCallProgressHook reading the active StreamingResponse from config["configurable"]["streaming_response"].

Project links

Data verified by PyPI on Sep 11, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.41.4)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for pace from gravatar.com pace

Credits

Author: pace

GitHub Statistics

Data verified by PyPI on Sep 11, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License expression

MIT
View SPDX License List

Requires

Python >=3.14

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

3tears_langgraph-0.38.0.tar.gz (163.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

3tears_langgraph-0.38.0-py3-none-any.whl (110.4 kB view details)

Uploaded Python 3

File details

Details for the file 3tears_langgraph-0.38.0.tar.gz.

File metadata

  • Download URL: 3tears_langgraph-0.38.0.tar.gz
  • Upload date:
  • Size: 163.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for 3tears_langgraph-0.38.0.tar.gz
Algorithm Hash digest
SHA256 f8dcd2a3aec15273ee7b31cdcf211529d53a359ed16170a9b31c2a5bc221456d
MD5 73097969b4c03ec7e9e8f7e297b2e5c6
BLAKE2b-256 347831b3be49250e1b92e7ce7c8e1c1c8485a200c18f73228f91a81bfb9f038a

See more details on using hashes here.

Provenance

The following attestation bundles were made for 3tears_langgraph-0.38.0.tar.gz:

Publisher: release.yml on pacepace/3tears

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file 3tears_langgraph-0.38.0-py3-none-any.whl.

File metadata

File hashes

Hashes for 3tears_langgraph-0.38.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0860789966f61ca1eb9a9af683bc13f44507273675b5cf0c4c0dc111b9770b6a
MD5 fe597e2a51278202e308dc6252b643a9
BLAKE2b-256 ecf03eee55ba7ab442f11b290192d2f48cccb03c53d1e253adb906f10fa738b8

See more details on using hashes here.

Provenance

The following attestation bundles were made for 3tears_langgraph-0.38.0-py3-none-any.whl:

Publisher: release.yml on pacepace/3tears

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.41.4

2 files

0.41.3

2 files

0.41.2

2 files

0.41.1

2 files

0.41.0

2 files

0.40.0

2 files

0.39.0

2 files

This release

0.38.0 This release

2 files

0.37.0

2 files

0.36.0

2 files

0.35.1

2 files

0.35.0

2 files

0.34.0

2 files

0.33.0

2 files

0.32.1

2 files

0.32.0

2 files

0.31.0

2 files

0.30.1

2 files

0.30.0

2 files

0.29.0

2 files

0.28.0

2 files

0.27.0

2 files

0.26.1

2 files

0.26.0

2 files

0.25.0

2 files

0.24.7

2 files

0.24.6

2 files

0.24.5

2 files

0.24.4

2 files

0.24.3

2 files

0.24.2

2 files

0.24.1

2 files

0.24.0

2 files

0.23.11

2 files

0.23.10

2 files

0.23.9

2 files

0.23.8

2 files

0.23.7

2 files

0.23.6

2 files

0.23.5

2 files

0.23.3

2 files

0.23.2

2 files

0.23.1

2 files

0.23.0

2 files

0.22.5

2 files

0.22.4

2 files

0.22.3

2 files

0.22.2

2 files

0.22.1

2 files

0.22.0

2 files

0.21.0

2 files

0.20.0

2 files

0.19.4

2 files

0.19.3

2 files

0.19.2

2 files

0.19.1

2 files

0.19.0

2 files

0.18.0

2 files

0.17.9

2 files

0.17.8

2 files

0.17.7

2 files

0.17.6

2 files

0.17.5

2 files

0.17.4

2 files

0.17.3

2 files

0.17.2

2 files

0.17.1

2 files

0.17.0

2 files

0.16.1

2 files

0.16.0

2 files

0.15.0

2 files

0.14.1

2 files

0.14.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page