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
..
2026-01-14 09:58:53 +08:00
2026-02-10 22:07:25 +08:00

DeerFlow Frontend

Like the original DeerFlow 1.0, we would love to give the community a minimalistic and easy-to-use web interface with a more modern and flexible architecture.

Switching accounts reloads projects, custom agents, models, and other cached workspace data for the new account. Logging out immediately hides the previous account's data; refreshing the same account preserves its cache.

Tech Stack

Quick Start

Prerequisites

  • Node.js 22+
  • pnpm 10.26.2+

Installation

# Install dependencies
pnpm install

# Copy environment variables
cp .env.example .env
# Edit .env with your configuration

Development

# Start development server
pnpm dev

# The app will be available at http://localhost:3000

Build & Test

# Type check
pnpm typecheck

# Check formatting
pnpm format

# Apply formatting
pnpm format:write

# Lint
pnpm lint

# Run unit tests
pnpm test

# One-time setup: install Playwright Chromium browser
pnpm exec playwright install chromium

# Run E2E tests (builds and starts production server automatically)
pnpm test:e2e

# Build for production
pnpm build

# Start production server
pnpm start

Production builds recreate public/_pagefind/ from the current documentation, with separate English and Chinese indexes. The index step replaces its generated output directory to prevent old assets accumulating. Mobile docs search results scroll inside the menu and close it after selection, including the section already open.

Site Map

├── /                    # Landing page
├── /chats               # Chat list
├── /chats/new           # New chat page
└── /chats/[thread_id]   # A specific chat page

Configuration

Environment Variables

Key environment variables (see .env.example for full list):

# Backend API URL (optional, uses local Next.js/nginx proxy by default)
NEXT_PUBLIC_BACKEND_BASE_URL="http://localhost:8001"
# LangGraph-compatible API URL (optional, uses local Next.js/nginx proxy by default)
NEXT_PUBLIC_LANGGRAPH_BASE_URL="http://localhost:8001/api"

Project Structure

tests/
├── e2e/                    # E2E tests (Playwright, Chromium, mocked backend)
└── unit/                   # Unit tests (mirrors src/ layout)
src/
├── app/                    # Next.js App Router pages
│   ├── api/                # API routes
│   ├── showcase/           # Allowlisted public read-only demos
│   ├── workspace/          # Main workspace pages
│   └── mock/               # Mock/demo pages
├── components/             # React components
│   ├── ui/                 # Reusable UI components
│   ├── workspace/          # Workspace-specific components
│   ├── landing/            # Landing page components
│   └── ai-elements/        # AI-related UI elements
├── core/                   # Core business logic
│   ├── api/                # API client & data fetching
│   ├── artifacts/          # Artifact management
│   ├── config/              # App configuration
│   ├── i18n/               # Internationalization
│   ├── mcp/                # MCP integration
│   ├── messages/           # Message handling
│   ├── models/             # Data models & types
│   ├── settings/           # User settings
│   ├── skills/             # Skills system
│   ├── threads/            # Thread management
│   ├── todos/              # Todo system
│   └── utils/              # Utility functions
├── hooks/                  # Custom React hooks
├── lib/                    # Shared libraries & utilities
├── server/                 # Server-side code
│   └── better-auth/        # Authentication setup and session helpers
└── styles/                 # Global styles

Scripts

Command Description
pnpm dev Start development server with Webpack
pnpm build Build for production
pnpm start Start production server
pnpm test Run unit tests with Rstest
pnpm test:e2e Run E2E tests with Playwright
pnpm format Check formatting with Prettier
pnpm format:write Apply formatting with Prettier
pnpm lint Run ESLint
pnpm lint:fix Fix ESLint issues
pnpm typecheck Run TypeScript type checking
pnpm check Run both lint and typecheck

Development Notes

HTML artifact previews keep an opaque iframe sandbox. Static sibling images, responsive image sources, classic scripts, stylesheets, CSS imports and CSS url() resources in the same thread's artifact route are fetched by the authenticated parent and inlined as data URLs. Existing external resources and external <base> URLs retain their browser behavior. Resource preparation is capped at 32 resources, 4 MiB per resource, 16 MiB total, eight nested CSS imports, 24 MiB of expanded references and ten seconds; unavailable or oversized resources show a partial-preview notice. Switching artifacts cancels preparation and releases the generated document Blob URL. Resource 401 responses remain local to the partial preview; only the document load uses the application's login-redirect policy. Preparation preserves the original doctype (including its absence) and handles inline SVG styles.

This supports static generated reports rather than a complete website runtime. ES module imports, resources created dynamically by JavaScript, fetch()/XHR, iframes and navigation still follow opaque-origin browser restrictions and do not receive the parent session. View source or download the files when a report requires those features.

  • Uses pnpm workspaces (see packageManager in package.json)
  • Webpack is the default development bundler until the upstream Turbopack PostCSS worker leak is fixed in a stable Next.js release (#5132). Set DEER_FLOW_DEV_BUNDLER=turbo to opt in to Turbopack for local diagnosis, or DEER_FLOW_DEV_BUNDLER=webpack to select Webpack explicitly. Reconsider the default after the stable fix is verified on macOS arm64 and Linux.
  • Environment validation can be skipped with SKIP_ENV_VALIDATION=1 (useful for Docker)
  • Backend API URLs are optional; nginx proxy is used by default in development

License

MIT License. See LICENSE for details.