mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-08-13 00:08:42 +00:00
1f792d0f4b
* feat(extensions): add middleware plugin foundation * fix(extensions): stop config resolution from masking extension loading `create_app()` resolved the configured plugin list inside the fail-open guard around `load_extensions()`. CI has no `config.yaml` (gitignored and never generated by the workflow), so `get_app_config()` raised `FileNotFoundError` there and was swallowed as an extension failure -- `load_extensions()` never ran at all, and the four `create_app()` tests in `test_extension_app_loading.py` passed locally but failed on every runner. Resolve the plugin list before the guard. Only an absent `config.yaml` is tolerated, mirroring `_resolve_trace_enabled_for_app_construction()`: `create_app()` runs at import time, and lifespan still performs strict config loading before serving. A `config.yaml` that exists but fails to parse or validate now propagates instead of being reported as an extension failure -- reporting it as the latter silently dropped a `required: true` extension rather than failing the boot. Make the tests config-independent with an autouse `stub_app_config` fixture, following the existing pattern in `test_gateway_lifespan_shutdown.py`, and cover both new branches of the config-resolution boundary. * fix(extensions): bind the run's extension snapshot through subagent delegation The lead-agent path resolves one immutable loaded-extension snapshot per run and binds it through task-store allocation and graph construction, but the subagent path re-read the process-wide singleton at execution time. In production both are the same object, yet a `set_loaded_extensions()` between the lead run's start and a subagent's execution (test teardown, a future hot-reload path) would let one run mix two extension generations — exactly what the documented invariant exists to prevent. The graph-build binding is a ContextVar scoped to synchronous construction, so it has already exited by the time a tool delegates; the snapshot has to travel through runtime context instead. The run worker publishes it under the host-internal `EXTENSION_SNAPSHOT_CONTEXT_KEY` (written after the caller merge, popped when the run has none, so a caller-supplied value is never authoritative), `task_tool` reads it back through the type-checking `resolve_run_extensions()`, and `SubagentExecutor` binds it at construction. Callers outside the Gateway run path — embedded `DeerFlowClient`, standalone LangGraph Server — install no snapshot and keep the existing `get_loaded_extensions()` fallback. * refactor(extensions): defer the ordering table by call, not by a lying tuple `CORE_ORDERING_CONSTRAINTS` was a `tuple` subclass that overrode only `__iter__` and resolved into a class-level `_resolved` side channel. A tuple cannot populate its own storage after construction, so the instance stayed the empty tuple it was built as: `len()` was 0, `bool()` was False, `in` was always False, indexing raised, slicing and `reversed()` came back empty, and it compared unequal to the plain tuples tests substitute for it — all while iteration yielded the real constraints. Only `assert_ordering` consumed it, and only by iterating, so the split went unnoticed. The sibling `_AnchorTable(dict)` uses the same idea soundly because dict is mutable: `self.update()` fills the real storage, making every inherited operation correct. That trick does not survive the port to an immutable type. Replace it with `core_ordering_constraints()`, matching how `stack.py` defers the same kind of table via `_anchors()`. The deferral is kept — it is about dependency direction, not just cycles: `extensions/` is the layer the middleware layer calls into, so a module-scope `agents.middlewares` import here points the dependency backwards and closes a cycle as soon as any middleware imports something under `extensions/` at module level. Resolution stays at `assert_ordering` time, which already runs inside the middleware builder. Tests pin both halves: the returned value is a plain tuple whose len/bool/ membership/indexing/reversal/equality agree with iteration, and a subprocess probe asserts importing `extensions.ordering` does not load the middleware layer while calling the function does.
94 lines
3.4 KiB
TOML
94 lines
3.4 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>=0.0.30",
|
|
"croniter>=6.0.0",
|
|
# Exact pin by design (extension-system version contract): the host pins
|
|
# the contract version it implements, extensions declare ranges. A range
|
|
# here would let pip resolve a newer contract package than this harness
|
|
# implements, making newer extensions look supported at runtime.
|
|
"deerflow-extension-api==0.1.0",
|
|
"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"]
|
|
# Tenki cloud sandbox provider (deerflow.community.tenki). Optional so a default
|
|
# install stays free of the Tenki SDK; only pulled in when the provider is used.
|
|
tenki = ["tenki-sandbox>=0.4.0"]
|
|
# 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"]
|
|
# Optional Chinese tokenization for the FTS5 memory retrieval adapter.
|
|
memory-zh = ["jieba>=0.42.1"]
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["deerflow"]
|