mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-08-13 00:08:42 +00:00
fa496c0c8d
* feat(browser): add agentic browser control
* fix(frontend): format browser view changes
* fix(browser): keep browser optional and isolate sidecar layout
* fix(browser): address PR review security and IME findings
- Nginx: add a browser-stream WebSocket location before the generic
/api/threads regex so Live upgrades instead of downgrading to HTTP
(both nginx.conf and nginx.local.conf).
- Ownership: require an existing owned thread for the WS stream and REST
navigate, and tear down the browser session on thread deletion so a
later caller cannot reuse a retained page/cookies by guessing the id.
- SSRF: enforce the URL policy at the browser request boundary via a
context-level route guard covering redirects, popups, iframes, and
subresources (skipped for CDP-attached Chrome).
- IME: skip key forwarding while a composition is active so confirming a
CJK candidate with Enter no longer submits the remote page form.
Adds regression tests for the request guard, session teardown on delete,
and the composing-Enter key decision.
* fix(frontend): smooth streaming in long tool threads
* Revert "fix(frontend): smooth streaming in long tool threads"
This reverts commit f0462516eabe77f138d4027ea1c714fb226683cf.
* fix(browser): address review security and lifecycle findings
- Reject cross-origin WebSocket upgrades on the live browser stream
(Origin allow-list reuse of CORS/same-origin helpers) to close a
WS-CSRF hole, and fail closed when the ownership store is absent.
- Warn when a CDP-attached session runs with the SSRF request guard
off, and drop the unreachable CDP screencast teardown dead code.
- Read browser session launch config from a single canonical source
(browser_navigate) so it is deterministic regardless of call order.
- Bound per-thread Chromium accumulation with idle-timeout eviction
and an LRU max-sessions cap.
- Reset the Live reconnect counter on a successful open so the stream
can't permanently stall after the cumulative attempt cap.
* fix(frontend): reduce long tool thread render stalls
Reuse stable historical message groups during streaming, defer heavy Markdown and browser previews, and lazy-decode message images.
* fix(browser): keep live control responsive during continuous input
Why: Manual browser control felt laggy — a physical click ran the remote
Playwright click three times and each non-move input synchronously awaited a
JPEG screenshot, so events queued behind capture (queue wait up to ~237ms).
The first async attempt used a trailing-edge debounce, which froze the visible
page until a wheel/keyboard gesture stopped ("scroll finishes, then it jumps").
What:
- Frontend forwards one `click` per physical click instead of also emitting
`down`/`up`, so the remote page is not clicked twice per gesture.
- Backend detaches live-frame capture from input dispatch: non-move actions
start a rate-limited background refresh loop (leading frame + bounded cadence)
that keeps emitting frames while input continues and never blocks dispatch.
- Add regression tests: input dispatch no longer awaits the screenshot, rapid
inputs coalesce, and continuous input keeps refreshing before it stops.
Scenarios: Verified in the live Browser panel — a single click completes in
~57ms (was blocked behind a 171ms capture), and a 1.14s sustained wheel gesture
renders ~7 frames throughout the scroll instead of one frame after it ends.
* fix(browser): harden worker and session lifecycle
* fix(browser): address latest review feedback
* fix(frontend): preserve optimistic new-chat message
* test(e2e): preserve mocked message run ids
* fix(browser): address capability review feedback
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
82 lines
2.7 KiB
TOML
82 lines
2.7 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",
|
|
"langchain>=1.2.15",
|
|
"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>=1.1.9",
|
|
"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>=3.0.3",
|
|
"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>=3.0.5",
|
|
"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"]
|