deer-flow/backend/pyproject.toml
Ryker_Feng fa496c0c8d
feat(browser): add agentic browser control (#4187)
* 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>
2026-07-21 11:46:33 +08:00

69 lines
2.1 KiB
TOML

[project]
name = "deer-flow"
version = "2.1.0"
description = "LangGraph-based AI agent system with sandbox execution capabilities"
readme = "README.md"
requires-python = ">=3.12"
dependencies = [
"deerflow-harness",
"fastapi>=0.115.0",
"httpx>=0.28.0",
"python-multipart>=0.0.31",
"sse-starlette>=2.1.0",
"uvicorn[standard]>=0.34.0",
"lark-oapi>=1.4.0",
"slack-sdk>=3.33.0",
"python-telegram-bot>=21.0",
"langgraph-sdk>=0.1.51",
"markdown-to-mrkdwn>=0.3.1",
"wecom-aibot-python-sdk>=0.1.6",
"dingtalk-stream>=0.24.3",
"bcrypt>=4.0.0",
"pyjwt>=2.13.0",
"email-validator>=2.0.0",
"e2b-code-interpreter>=2.8.1",
]
[project.optional-dependencies]
postgres = ["deerflow-harness[postgres]"]
redis = ["deerflow-harness[redis]"]
discord = ["discord.py>=2.7.0"]
monocle = ["deerflow-harness[monocle]"]
browser = ["deerflow-harness[browser]"]
[dependency-groups]
dev = [
"blockbuster>=1.5.26,<1.6",
"jsonschema>=4.26.0",
"prompt-toolkit>=3.0.0",
"pytest>=9.0.3",
"pytest-asyncio>=1.3.0",
"ruff>=0.14.11",
# Monocle tracer (also the deerflow-harness[monocle] extra); kept in the dev
# group so the tracing tests can import it without forcing it onto installs.
"monocle_apptrace>=0.8.8",
# redis is an optional runtime extra (deerflow-harness[redis]); pin it in the
# dev group so the stream-bridge tests can always import/exercise the redis
# bridge without forcing it onto production installs.
"redis>=5.0.0",
# TUI runtime dep (also declared as the deerflow-harness[tui] extra); kept in
# the dev group so the terminal workbench can be run and tested locally / in CI.
"textual>=0.80",
]
[tool.pytest.ini_options]
markers = [
"no_auto_user: disable the conftest autouse contextvar fixture for this test",
"allow_blocking_io: opt out of the strict Blockbuster gate in tests/blocking_io/",
"integration: tests that require an external service (e.g. Redis); skipped when unavailable",
]
[tool.uv]
index-url = "https://pypi.org/simple"
[tool.uv.workspace]
members = ["packages/harness"]
[tool.uv.sources]
deerflow-harness = { workspace = true }