Vanzeren 42baed8c8c
feat(checkpoint): dual-mode checkpoint storage with LangGraph DeltaChannel (#4292)
* feat(checkpoint): dual-mode checkpoint storage with LangGraph DeltaChannel

Add a restart-required database.checkpoint_channel_mode ("full" default,
"delta") that stores the messages channel via LangGraph 1.2 DeltaChannel,
cutting checkpoint storage from O(n^2) to O(n) for append-only history.
Existing full checkpoints seed delta state transparently; no data migration.

- config: mode schema + freeze-on-first-use with
  CheckpointModeReconfigurationError; mode marker persisted in checkpoint
  metadata; unsafe delta->full downgrade rejected fail-closed with
  CheckpointModeMismatchError (run-level error, failed state read)
- state: delta message state schema; CheckpointStateAccessor centralizes
  materialized reads for all consumers (threads API, branches,
  regeneration, compaction, state updates, memory, goal workers)
- runtime: raw writers (run durations, interrupted title, thread goal)
  parent their checkpoints to the checkpoint they derive from, preserving
  delta ancestry; rollback forks the pre-run lineage through a state
  mutation graph with Overwrite restores; InMemorySaver delta-history
  override delegates to the base walk (fixes dropped first write after
  migration, also present upstream)
- tests: conformance suite over {memory, sqlite, postgres} covering
  migration replay, stable message IDs, storage shape and writer
  preservation; conftest fixture isolates the frozen mode between tests;
  stale config fakes refreshed
- ci: backend unit tests gain a postgres service

* fix(checkpoint): close materialization gaps in goal flow, guard public factory

- Route goal-continuation message reads through CheckpointStateAccessor:
  raw channel_values reads see the delta sentinel in delta mode, which
  disabled goal continuation (stand_down=no_durable_end_of_turn) after
  durable assistant turns. Raw tuples remain for tuple-only metadata
  (checkpoint id, pending_writes).
- Reject checkpoint_channel_mode='delta' + checkpointer in
  create_deerflow_agent at construction: factory-built persisted graphs
  bypass mode-marker injection and the fail-closed gate, reproducing
  silent mixed-mode state loss. Delta without persistence stays allowed.
- Import the postgres saver lazily (pytest.importorskip in the fixture)
  so the documented default install collects the suite; add a CI job
  running pytest --collect-only on uv sync --group dev without extras.
- Fix test_checkpointer fallback test to patch get_app_config at its
  use site (provider module), making it deterministic when a local
  config.yaml selects a persistent backend.

* fix(gateway): preserve extension-owned channels in state mutations, bump config version

- build_state_mutation_graph / build_checkpoint_state_mutation_accessor
  accept an explicit state_schema; branch and POST /state now compile the
  mutation graph from the thread's effective schema
  (graph_state_schema on the assistant graph). The base-ThreadState
  fallback silently discarded channels contributed by custom
  AgentMiddleware.state_schema on branch (data loss) and returned a
  false-success 200 on POST /state.
- POST /state validates values keys against the mutation graph's
  channels and rejects unknown fields with 422 instead of ignoring
  them; reducer detection covers extension channels
  (BinaryOperatorAggregate or DeltaChannel) so Overwrite replace
  semantics work for middleware reducers in both modes.
- Endpoint regression: custom AgentMiddleware.state_schema value
  survives branch, updates through POST /state, and an unknown field
  receives 422.
- config_version 26 -> 27 for the new database.checkpoint_channel_mode
  (example, Helm chart values + README, support-bundle fixture), so
  existing installs get the outdated-config warning and
  make config-upgrade merges the field; covered by a test driving the
  real example file and the real config-upgrade script.

* fix(gateway): resolve assistant schema via one boundary, copy branch reducer values with Overwrite

GET /threads/{id}/state now resolves the thread's assistant_id through a
single reusable boundary (thread metadata -> assistant_id -> effective
graph), so channels contributed by a custom AgentMiddleware.state_schema
are materialized instead of dropped by the default lead schema. POST
/state uses the same boundary instead of resolving the schema ad hoc.

Branch writes wrap every copied reducer channel in Overwrite (derived
from the effective mutation graph: BinaryOperatorAggregate + DeltaChannel),
not just messages, so already-aggregated values are never re-merged.

Regression tests use a real AgentMiddleware.state_schema with a
non-identity reducer in both full and delta modes: GET /state returns the
extension value, POST /state replaces it, branch preserves it
byte-for-byte; the unknown-field 422 is a separate assertion.

* refactor(checkpoint): collapse read-path round-trips and ship dual-mode parity tests

Address review round 4 on PR #4292:

- Push ahistory/history limit through Pregel into checkpointer.alist
  (SQL LIMIT) instead of materializing all rows and breaking in Python
- Fold the read-side mode-compat gate onto the returned snapshot's
  metadata; only writes keep the pre-write tuple fetch (fail-closed)
- Cache factory-built accessor graphs per (assistant_id, mode) with
  factory-identity revalidation; state reads no longer build a lead
  agent per request
- get_thread: one snapshot fetch + one raw pending_writes fetch on the
  resolved checkpoint (post-checkpoint __error__ writes never surface
  in snapshot.tasks; verified empirically)
- DeerFlowClient.get_thread: single checkpointer.list walk collects
  pending_writes per checkpoint instead of N get_tuple calls
- InMemorySaver delta-history patch: stand-down when the upstream
  override disappears, try/except guard, validated-version warning,
  guard tests
- make_lead_agent mode precedence: first freeze is owned by app_config
  (client-supplied configurable key ignored); once frozen, injected
  key/app_config must match or fail closed
- Rollback: lock in non-message channel restoration via fork
  inheritance with a dedicated reducer-channel test
- Add tests/test_threads_checkpoint_mode.py and
  tests/test_gateway_checkpoint_mode.py referenced by AGENTS.md and
  the PR validation section: lifecycle parity (memory + sqlite),
  per-step blob-count storage guard, gateway endpoint parity

Counted-saver tests pin checkpoint round-trips for aget/ahistory so
these regressions cannot silently return.

* fix(checkpoint): precise mode-mismatch HTTP mapping, gate E2E, and accessor resilience

- threads router: map CheckpointModeMismatchError to 409 (with cause and
  thread id) and CheckpointModeReconfigurationError to 503 across all state
  endpoints instead of swallowing both into a generic 500
- gate coverage: seed a real delta checkpoint into AsyncSqliteSaver and
  assert aget/aupdate/ahistory fail closed; assert 409 at the HTTP boundary
  through the real route stack
- rollback: compile the restore mutation graph with the thread's effective
  state schema per the build_state_mutation_graph contract
- inheritance contract locks: rollback and manual compaction preserve
  middleware-contributed channels via checkpoint fork cloning
- services: revalidate the accessor-graph cache against app_config identity
  so config.yaml hot-reloads never serve a stale compiled graph
- services: degrade full-mode state reads to raw checkpointer reads when the
  agent factory is unavailable (delta gate still applies; delta mode has no
  fallback)
- deps: override websockets==16.0 (langgraph-sdk 0.4.2's <16 pin silently
  downgraded 16.0 -> 15.0.1; pin is not grounded in any API incompatibility)
  and bump the langchain lower bound to what the lockfile actually resolves

* fix(checkpoint): include anchor checkpoint in degraded history walk + cover get_thread

- _RawCheckpointReadAccessor.ahistory: alist(before=...) is exclusive while
  pregel's get_state_history treats config.checkpoint_id as the inclusive
  start; fetch the anchor explicitly so both read paths paginate identically
- extend the degraded-path gateway test: GET /thread returns raw values, and
  POST /history with before starts at the anchor checkpoint

* fix(gateway): preserve degraded checkpoint timestamps

* fix(gateway): harden degraded checkpoint access

* fix(gateway): resolve assistants for checkpoint reads

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-07-22 08:33:29 +08:00

84 lines
2.8 KiB
TOML

[project]
name = "deerflow-harness"
version = "2.1.0"
description = "DeerFlow agent harness framework"
requires-python = ">=3.12"
dependencies = [
"agent-client-protocol>=0.4.0",
"agent-sandbox>=0.0.19",
"croniter>=6.0.0",
"dotenv>=0.9.9",
"exa-py>=1.0.0",
"httpx>=0.28.0",
"kubernetes>=30.0.0",
# Lower bound reflects what the lockfile resolves and tests run against
# (langgraph 1.2.9 pulls langchain >=1.3 transitively).
"langchain>=1.3",
"langchain-anthropic>=1.4.1",
"langchain-deepseek>=1.0.1",
"langchain-mcp-adapters>=0.2.2",
"langchain-openai>=1.2.1",
"langfuse>=3.4.1",
"langgraph>=1.2.9,<1.3",
"langgraph-api>=0.8.1",
"langgraph-cli>=0.4.24",
"langgraph-runtime-inmem>=0.28.0",
"markdownify>=1.2.2",
"markitdown[all,xlsx]>=0.0.1a2",
"pydantic>=2.12.5",
"pyyaml>=6.0.3",
"readabilipy>=0.3.0",
"tavily-python>=0.7.17",
"firecrawl-py>=1.15.0",
"tiktoken>=0.8.0",
"ddgs>=9.10.0",
"duckdb>=1.4.4",
"langchain-google-genai>=4.2.1",
"langgraph-checkpoint-sqlite>=3.1.0,<3.2",
"langgraph-sdk>=0.1.51",
"sqlalchemy[asyncio]>=2.0,<3.0",
"aiosqlite>=0.19",
"alembic>=1.13",
"cryptography>=48.0.1",
"e2b-code-interpreter>=2.8.0",
]
[project.scripts]
deerflow = "deerflow.tui.cli:main"
[project.optional-dependencies]
# Terminal workbench (TUI). Kept optional so the core harness install stays lean;
# the `deerflow` console script degrades to headless help when textual is absent.
tui = ["textual>=0.80"]
# GroundRoute needs no extra packages (httpx is already a core dependency). This
# empty extra exists so the documented `uv add 'deerflow-harness[groundroute]'`
# install command resolves cleanly without an "unknown extra" warning.
groundroute = []
ollama = ["langchain-ollama>=0.3.0"]
postgres = [
"asyncpg>=0.29",
"langgraph-checkpoint-postgres>=3.1.0,<3.2",
"psycopg[binary]>=3.3.3",
"psycopg-pool>=3.3.0",
]
# Cross-process SSE stream bridge (stream_bridge.type: redis). Optional so
# single-process / memory-bridge installs do not pull redis. The Docker image
# always installs this extra because Docker defaults to the redis bridge.
redis = ["redis>=5.0.0"]
pymupdf = ["pymupdf4llm>=0.0.17"]
boxlite = ["boxlite>=0.9.7"]
# Agent observability (Monocle). Optional so a default install stays free of the
# OpenTelemetry stack; only pulled in when MONOCLE_TRACING is used.
monocle = ["monocle_apptrace>=0.8.8"]
# Agentic browser control (browser_navigate/click/type/... tool group). Optional
# so the core harness install stays lean; import is lazy inside the private
# Playwright loop. After install, run `playwright install chromium` once.
browser = ["playwright>=1.40"]
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.hatch.build.targets.wheel]
packages = ["deerflow"]