Nan Gao 1dd6d05627
fix(extensions): hand compaction observers the live task store and name the task in CompactionEvent (#7831)
* feat(extension-api): add task identity fields to CompactionEvent (0.2.10)

CompactionEvent carried the transform, its hashes and its counts, but
nothing that names the task, run or thread the compaction happened in.
An observer that wants to relate a compaction to the run that produced it
had to match hashes across sessions, which is unreliable.

Append three optional fields, task_id, run_id and thread_id (str | None,
default None). Existing keyword and positional construction is unchanged,
so already-released extensions keep working. The host fills them in the
next commit.

Bump deerflow-extension-api to 0.2.10 and the harness's exact pin with it.

* fix(extensions): hand compaction observers the live task store and its identity

The summarization middleware already recovers the live task store from
the runtime to observe its summary system call, and the registry
allocates that store precisely because a compaction observer is
registered. notify_context_compacted() then discarded it and handed every
observer a detached store, with a docstring claiming there was no live
task.

- The lead run worker and the subagent executor now seed every task store
  they allocate with the task's TaskInfo, not only when a lifecycle
  contributor is registered; the lifecycle notification reuses the seeded
  object. A subagent without a parent run_id still gets no TaskInfo.
- compact_state() and acompact_state() pass the store from
  task_store_from_runtime() to _record_compaction().
- notify_context_compacted() takes an optional task_store. A live store
  goes to the observers and fills the event's task_id/run_id/thread_id
  from its TaskInfo; without one (manual /compact runs outside any run)
  observers still receive a detached store and the ids stay None.

For a background subagent the store keeps its public scope id (the
provider tool_call_id) while TaskInfo.task_id stays the execution id, as
lifecycle contributors already see it; the event follows TaskInfo.

* docs(extensions): document compaction event identity and seeded TaskInfo

The extensions guide and the developer manual still said compaction
observers always receive a detached store because no task is live at the
call site. Describe what the host does now: lead runs and subagents with a
parent run seed every task store with TaskInfo, compaction observers get
the live store, and CompactionEvent's task_id/run_id/thread_id come from
it; only manual /compact falls back to a detached store with None ids.
Adds the 0.2.10 row to the contract version table (PR number pending).

* docs(changelog): note compaction observers receive the live task identity

* docs(extensions): list compaction observers among task-store triggers

* docs: reference #7831 for the compaction event identity change

* docs(extensions): backfill contract history rows 0.2.5 to 0.2.9

The version table jumped from 0.2.4 to 0.2.10 although 0.2.5-0.2.9
shipped. Add those rows, attributing names merged without a bump to
the first release that carried them (#5796 in 0.2.5, #6920 and #5645
in 0.2.8, #7729 in 0.2.10). The page intro now says it documents
0.2.4 plus the 0.2.10 CompactionEvent fields, and points to the
history for the rest.
2026-11-03 15:06:52 +08:00

119 lines
4.7 KiB
TOML

[project]
name = "deerflow-harness"
version = "2.3.0-dev"
description = "DeerFlow agent harness framework"
requires-python = ">=3.12"
dependencies = [
"agent-client-protocol>=0.4.0",
"agent-sandbox>=0.0.30",
"beautifulsoup4>=4.12",
"html5lib>=1.1",
"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==0.2.10",
"dotenv>=0.9.9",
"exa-py>=1.0.0",
"httpx>=0.28.0",
"jsonschema>=4.26.0",
"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-openviking==0.1.0",
"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",
# Standalone Studio's pre-runtime persistence repair is validated against
# the 0.30.0 store lifecycle and must not resolve an older implementation.
"langgraph-runtime-inmem>=0.30.0",
"markdownify>=1.2.2",
"markitdown[all,xlsx]>=0.0.1a2",
"packaging>=24.2",
"pydantic>=2.12.5",
"pyyaml>=6.0.3",
"readabilipy>=0.3.0",
"regex>=2026.4.4",
"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",
# Floor matters: the InMemorySaver delta-history patch was removed once
# 4.2.0 fixed the dropped first post-migration write upstream (#8526) and
# kept its own override, so a 4.1.x resolution would silently reintroduce
# the bug. langgraph's own constraint (langgraph-checkpoint>=4.1.0) does
# not exclude that version.
"langgraph-checkpoint>=4.2.0,<5.0",
"langgraph-checkpoint-sqlite>=3.1.1,<3.2",
"langgraph-sdk>=0.1.51",
"sqlalchemy[asyncio]>=2.0,<3.0",
"aiosqlite>=0.19",
"alembic>=1.13",
"cryptography>=50.0.0",
"e2b-code-interpreter>=2.8.0",
# zoneinfo fallback: ZoneInfo reads the OS zone database first and this
# wheel when the image has none (stripped containers, Windows without
# tzdata), keeping the DEER_FLOW_DATE_TIMEZONE knob portable.
"tzdata>=2025.1",
]
[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",
# 3.1.2 finds plain-value delta seeds (upstream #8535); 3.1.1 walks past
# them to the thread root instead.
"langgraph-checkpoint-postgres>=3.1.2,<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.
# The distribution is ``tenki``; it still ships the ``tenki_sandbox`` module that
# provider.py and sandbox.py import.
tenki = ["tenki>=1.4.0"]
# OpenSandbox remote sandbox provider (deerflow.community.opensandbox). The
# sync SDK is loaded only when this provider is selected.
opensandbox = ["opensandbox>=0.1.15,<0.2.0"]
# 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"]