deer-flow/scripts/serve.sh
DanielWalnut cd5bedaa74
feat: MiniMax provider for image/video/podcast skills + new music-generation skill (#3437)
* docs(spec): MiniMax integration for generation skills + new music skill

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs(plan): MiniMax generation providers implementation plan

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(skills): add importlib loader + FakeResp for skill tests

* test(skills): register loaded module in sys.modules; raise requests.HTTPError in FakeResp

* feat(image-generation): add MiniMax provider with env auto-detect

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor(image-generation): guard unknown provider, derive ref MIME, strengthen tests

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(video-generation): add MiniMax provider with async poll/download

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor(video-generation): surface base_resp errors while polling; add timeout test

* feat(podcast-generation): add MiniMax t2a_v2 provider with env auto-detect

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor(podcast-generation): restore TTS credential guard; add volcengine + voice tests

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(music-generation): new MiniMax music skill via skill-creator

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* refactor(music-generation): treat empty lyrics as absent; test no-audio-data path

* refactor(skills): add request timeouts to MiniMax network calls

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Potential fix for pull request finding 'Explicit returns mixed with implicit (fall through) returns'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

* fix(models): strip inconsistent user-message names for MiniMax chat

DeerFlow middlewares tag user messages with provenance names (user-input, summary, loop_warning); langchain serializes them into the OpenAI-compatible payload and MiniMax rejects mismatched user-message names with "user name must be consistent (2013)". PatchedChatMiniMax now drops the per-message name from user-role messages. Point the config.example MiniMax models at PatchedChatMiniMax so they also get reasoning_content mapping.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(image-generation): MiniMax sends JSON prompt field, guard 1500-char limit

MiniMax image-01 takes one text string capped at 1500 chars, but the skill was sending the whole structured JSON. The MiniMax provider now extracts the JSON `prompt` field (relying on prompt_optimizer to expand it) and fails fast with a clear error before calling the API when that field exceeds 1500 chars. Authoring stays provider-agnostic; Gemini still receives the full JSON.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(podcast-generation): per-provider TTS concurrency and retry/backoff

Each TTS provider owns its concurrency internally — MiniMax runs single-threaded to reduce rate-limit failures, Volcengine keeps 4 workers — with automatic retry and backoff on transient HTTP and base_resp errors. No caller-facing concurrency knob.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(skills): address Copilot review comments on generation skills

- video: add raise_for_status + timeout to the Gemini download/POST/poll calls so non-2xx responses surface as clear HTTP errors instead of JSON/KeyError or hangs
- video: check the task Fail status before the generic base_resp check so the failure keeps its task_id context
- video/image: create the output file parent directory before writing (matching music-generation) so nested output paths do not raise FileNotFoundError
- music: require a non-empty prompt and fail fast with ValueError instead of sending an empty prompt to the API

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(scripts): reclaim dev ports across worktrees in make stop/dev

All deer-flow worktrees (main checkout + linked worktrees) hardcode the same dev ports (8001/3000/2026), so a service started from any worktree must be reclaimable from another. stop_all now resolves the set of worktree roots (DEERFLOW_ROOTS) and treats a process as deer-flow-owned when its open files live under any of them. It also force-kills survivors on 2026 alongside 8001/3000, fixing `make dev` aborting on the nginx port preflight when a prior nginx lingered on 2026.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(view-image): hide the injected image-context message from the UI

ViewImageMiddleware injects a HumanMessage (text + base64 images) so the vision model can see viewed images, but it was the only internal injector that set neither hide_from_ui nor a hidden name, so it leaked into the chat UI (and IM channels) as a user bubble reading "Here are the images you've viewed:". Mark it with additional_kwargs={"hide_from_ui": True}, matching todo/dynamic_context injections, which the frontend isHiddenFromUIMessage and the channel sender already honor. The model still receives the full content.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(minimax): mark M2.7 models as text-only (no vision)

MiniMax M2.7 / M2.7-highspeed do not support vision; only M3 does. The
provider config asserted vision support for M2.7 in four places.

- config.example.yaml: 4 M2.7 entries -> supports_vision: false
- backend/docs/CONFIGURATION.md: M2.7 + highspeed -> supports_vision: false
- wizard: add LLMProvider.model_vision_overrides + extra_config_for() so
  selecting an M2.7 model writes supports_vision: false while M3 (default)
  keeps vision; wire it through setup_wizard.py
- tests: M2.7-highspeed fixture -> supports_vision=False; add
  test_minimax_vision_is_per_model

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>
2026-06-08 22:04:38 +08:00

460 lines
16 KiB
Bash
Executable File

#!/usr/bin/env bash
#
# serve.sh — Unified DeerFlow service launcher
#
# Usage:
# ./scripts/serve.sh [--dev|--prod] [--daemon] [--stop|--restart]
#
# Modes:
# --dev Development mode with hot-reload (default)
# --prod Production mode, pre-built frontend, no hot-reload
# --daemon Run all services in background (nohup), exit after startup
#
# Actions:
# --skip-install Skip dependency installation (faster restart)
# --stop Stop all running services and exit
# --restart Stop all services, then start with the given mode flags
#
# Examples:
# ./scripts/serve.sh --dev # Gateway dev, hot reload
# ./scripts/serve.sh --prod # Gateway prod
# ./scripts/serve.sh --dev --daemon # Gateway dev, background
# ./scripts/serve.sh --stop # Stop all services
# ./scripts/serve.sh --restart --dev # Restart dev services
#
# Must be run from the repo root directory.
set -e
REPO_ROOT="$(builtin cd "$(dirname "${BASH_SOURCE[0]}")/.." >/dev/null 2>&1 && pwd -P)"
cd "$REPO_ROOT"
# ── Load .env ────────────────────────────────────────────────────────────────
if [ -f "$REPO_ROOT/.env" ]; then
set -a
source "$REPO_ROOT/.env"
set +a
fi
# ── Argument parsing ─────────────────────────────────────────────────────────
DEV_MODE=true
DAEMON_MODE=false
SKIP_INSTALL=false
ACTION="start" # start | stop | restart
for arg in "$@"; do
case "$arg" in
--dev) DEV_MODE=true ;;
--prod) DEV_MODE=false ;;
--daemon) DAEMON_MODE=true ;;
--skip-install) SKIP_INSTALL=true ;;
--stop) ACTION="stop" ;;
--restart) ACTION="restart" ;;
*)
echo "Unknown argument: $arg"
echo "Usage: $0 [--dev|--prod] [--daemon] [--skip-install] [--stop|--restart]"
exit 1
;;
esac
done
# ── Stop helper ──────────────────────────────────────────────────────────────
# Every deer-flow worktree (the main checkout + each linked worktree) hardcodes
# the same dev ports (8001/3000/2026), so a service started from ANY of them
# must be reclaimable from here — otherwise `make stop`/`make dev` in this
# worktree can neither kill nor take over a port held by a sibling worktree.
# DEERFLOW_ROOTS is that set of roots; processes living outside all of them
# (e.g. an unrelated project on port 3000) are still never touched.
# Sorted most-specific-first (longest path first): a linked worktree lives
# under the main checkout, so both roots are substrings of its files — checking
# the deeper root first attributes a reclaimed port to the right worktree.
DEERFLOW_ROOTS="$(
{
printf '%s\n' "$REPO_ROOT"
git -C "$REPO_ROOT" worktree list --porcelain 2>/dev/null |
awk '/^worktree /{print $2}'
} | awk 'NF && !seen[$0]++ {print length($0)"\t"$0}' | sort -rn | sed 's/^[0-9]*\t//'
)"
# True if PID has an open file/cwd under any deer-flow worktree root. The
# trailing slash keeps a sibling dir like ".../deer-flow-notes" from matching
# the ".../deer-flow" root.
_is_deerflow_pid() {
local pid=$1 files root
files=$(lsof -p "$pid" 2>/dev/null) || return 1
while IFS= read -r root; do
[ -n "$root" ] || continue
case "$files" in
*"$root"/*) return 0 ;;
esac
done <<< "$DEERFLOW_ROOTS"
return 1
}
# Report ports about to be reclaimed from a *different* worktree, so stopping
# (or starting, which stops first) isn't silently killing someone else's run.
_report_reclaimed_ports() {
local port pid files root owner
for port in 8001 3000 2026; do
for pid in $(lsof -nP -iTCP:"$port" -sTCP:LISTEN -t 2>/dev/null); do
_is_deerflow_pid "$pid" || continue
files=$(lsof -p "$pid" 2>/dev/null)
case "$files" in *"$REPO_ROOT"/*) continue ;; esac # this worktree — normal
owner=""
while IFS= read -r root; do
[ -n "$root" ] || continue
case "$files" in *"$root"/*) owner="$root"; break ;; esac
done <<< "$DEERFLOW_ROOTS"
echo " ↻ Reclaiming port $port from another worktree: ${owner:-?}"
break
done
done
}
_kill_repo_processes() {
local pattern=$1
local pid
local pids=""
while IFS= read -r pid; do
if [ -n "$pid" ] && _is_deerflow_pid "$pid"; then
case " $pids " in
*" $pid "*) ;;
*) pids="$pids $pid" ;;
esac
fi
done < <(pgrep -f "$pattern" 2>/dev/null || true)
if [ -n "$pids" ]; then
kill $pids 2>/dev/null || true
fi
}
_kill_repo_port() {
local port=$1
local pid
local pids=""
while IFS= read -r pid; do
if [ -n "$pid" ] && _is_deerflow_pid "$pid"; then
case " $pids " in
*" $pid "*) ;;
*) pids="$pids $pid" ;;
esac
fi
done < <(lsof -nP -iTCP:"$port" -sTCP:LISTEN -t 2>/dev/null || true)
if [ -n "$pids" ]; then
kill -9 $pids 2>/dev/null || true
fi
}
_is_port_listening() {
local port=$1
if command -v lsof >/dev/null 2>&1; then
if lsof -nP -iTCP:"$port" -sTCP:LISTEN -t >/dev/null 2>&1; then
return 0
fi
fi
if command -v ss >/dev/null 2>&1; then
if ss -ltn "( sport = :$port )" 2>/dev/null | tail -n +2 | grep -q .; then
return 0
fi
fi
if command -v netstat >/dev/null 2>&1; then
if netstat -ltn 2>/dev/null | awk '{print $4}' | grep -Eq "(^|[.:])${port}$"; then
return 0
fi
fi
return 1
}
_is_repo_nginx_pid() {
local pid=$1
local command
local args
command=$(ps -p "$pid" -o comm= 2>/dev/null) || return 1
case "$command" in
nginx|*/nginx) ;;
*) return 1 ;;
esac
args=$(ps -p "$pid" -o args= 2>/dev/null) || return 1
local root
while IFS= read -r root; do
[ -n "$root" ] || continue
case "$args" in
*"$root"/docker/nginx/nginx.local.conf*|*"$root"/*) return 0 ;;
esac
done <<< "$DEERFLOW_ROOTS"
_is_deerflow_pid "$pid"
}
_kill_repo_nginx() {
local pid
local pids=""
if [ -f "$REPO_ROOT/logs/nginx.pid" ]; then
read -r pid < "$REPO_ROOT/logs/nginx.pid" || true
if [ -n "$pid" ] && _is_repo_nginx_pid "$pid"; then
pids="$pids $pid"
fi
fi
while IFS= read -r pid; do
if [ -n "$pid" ] && _is_repo_nginx_pid "$pid"; then
case " $pids " in
*" $pid "*) ;;
*) pids="$pids $pid" ;;
esac
fi
done < <(pgrep -f nginx 2>/dev/null || true)
if [ -n "$pids" ]; then
kill -9 $pids 2>/dev/null || true
fi
}
stop_all() {
echo "Stopping all services..."
_report_reclaimed_ports
_kill_repo_processes "uvicorn app.gateway.app:app"
_kill_repo_processes "next dev"
_kill_repo_processes "next start"
_kill_repo_processes "next-server"
nginx -c "$REPO_ROOT/docker/nginx/nginx.local.conf" -p "$REPO_ROOT" -s quit 2>/dev/null || true
sleep 1
_kill_repo_nginx
# Force-kill any survivors still holding the service ports. 2026 is included
# so a lingering nginx (or any deer-flow process) that _kill_repo_nginx did
# not match by name still gets reclaimed — otherwise `make dev` fails its
# nginx port preflight.
_kill_repo_port 8001
_kill_repo_port 3000
_kill_repo_port 2026
./scripts/cleanup-containers.sh deer-flow-sandbox 2>/dev/null || true
echo "✓ All services stopped"
}
# ── Action routing ───────────────────────────────────────────────────────────
if [ "$ACTION" = "stop" ]; then
stop_all
exit 0
fi
ALREADY_STOPPED=false
if [ "$ACTION" = "restart" ]; then
stop_all
sleep 1
ALREADY_STOPPED=true
fi
# Mode label for banner
if $DEV_MODE; then
MODE_LABEL="DEV (Gateway runtime, hot-reload enabled)"
else
MODE_LABEL="PROD (Gateway runtime, optimized)"
fi
if $DAEMON_MODE; then
MODE_LABEL="$MODE_LABEL [daemon]"
fi
# Frontend command
if $DEV_MODE; then
FRONTEND_CMD="pnpm run dev"
else
if command -v python3 >/dev/null 2>&1; then
PYTHON_BIN="python3"
elif command -v python >/dev/null 2>&1; then
PYTHON_BIN="python"
else
echo "Python is required to generate BETTER_AUTH_SECRET."
exit 1
fi
FRONTEND_CMD="env BETTER_AUTH_SECRET=$($PYTHON_BIN -c 'import secrets; print(secrets.token_hex(16))') pnpm run preview"
fi
# Extra flags for uvicorn
if $DEV_MODE && ! $DAEMON_MODE; then
GATEWAY_EXTRA_FLAGS="--reload --reload-include='*.yaml' --reload-include='.env' --reload-exclude='*.pyc' --reload-exclude='__pycache__' --reload-exclude='sandbox/' --reload-exclude='.deer-flow/'"
else
GATEWAY_EXTRA_FLAGS=""
fi
# ── Stop existing services (skip if restart already did it) ──────────────────
if ! $ALREADY_STOPPED; then
stop_all
sleep 1
fi
# ── Config check ─────────────────────────────────────────────────────────────
if ! { \
[ -n "$DEER_FLOW_CONFIG_PATH" ] && [ -f "$DEER_FLOW_CONFIG_PATH" ] || \
[ -f backend/config.yaml ] || \
[ -f config.yaml ]; \
}; then
echo "✗ No DeerFlow config file found."
echo " Run 'make setup' (recommended) or 'make config' to generate config.yaml."
exit 1
fi
"$REPO_ROOT/scripts/config-upgrade.sh"
# ── Install dependencies ────────────────────────────────────────────────────
# Pick a Python for the extras detector. Falls back to plain `python` for
# Windows/Git Bash where only `python` is on PATH.
if command -v python3 >/dev/null 2>&1; then
DETECT_PYTHON="python3"
elif command -v python >/dev/null 2>&1; then
DETECT_PYTHON="python"
else
DETECT_PYTHON=""
fi
# Resolve uv extras (postgres, etc.) from UV_EXTRAS or config.yaml so that
# `uv sync` does not wipe out optional dependencies on every restart. See
# scripts/detect_uv_extras.py and Issue #2754 for context. The detector
# whitelists extra names against `^[A-Za-z][A-Za-z0-9_-]*$`, so the unquoted
# splat below only sees valid uv argument tokens.
#
# Stderr is intentionally NOT redirected so the user sees:
# - whitelist warnings (e.g. "ignoring invalid UV_EXTRAS entry ';'");
# - detector crashes (e.g. unexpected Python error).
# `|| true` keeps `set -e` from killing dev startup on a detector failure;
# the result is just an empty UV_EXTRAS_FLAGS, which means "no extras".
UV_EXTRAS_FLAGS=""
if [ -n "$DETECT_PYTHON" ]; then
UV_EXTRAS_FLAGS=$("$DETECT_PYTHON" "$REPO_ROOT/scripts/detect_uv_extras.py" || { echo "[serve.sh] detect_uv_extras.py failed (exit $?) — proceeding without extras" >&2; echo ""; })
fi
if ! $SKIP_INSTALL; then
echo "Syncing dependencies..."
if [ -n "$UV_EXTRAS_FLAGS" ]; then
echo " • uv extras: $UV_EXTRAS_FLAGS"
fi
# `--all-packages` propagates extras into workspace members (deerflow-harness
# in particular). Required for postgres extras — see PR #2584.
# Intentionally unquoted to splat multiple `--extra X` pairs.
(cd backend && uv sync --quiet --all-packages $UV_EXTRAS_FLAGS) || { echo "✗ Backend dependency install failed"; exit 1; }
(cd frontend && pnpm install --silent) || { echo "✗ Frontend dependency install failed"; exit 1; }
echo "✓ Dependencies synced"
else
echo "⏩ Skipping dependency install (--skip-install)"
fi
# ── Banner ───────────────────────────────────────────────────────────────────
echo ""
echo "=========================================="
echo " Starting DeerFlow"
echo "=========================================="
echo ""
echo " Mode: $MODE_LABEL"
echo ""
echo " Services:"
echo " Gateway → localhost:8001 (REST API + agent runtime)"
echo " Frontend → localhost:3000 (Next.js)"
echo " Nginx → localhost:2026 (reverse proxy)"
echo ""
# ── Cleanup handler ──────────────────────────────────────────────────────────
cleanup() {
local status="${1:-0}"
trap - INT TERM
echo ""
stop_all
exit "$status"
}
trap 'cleanup 130' INT
trap 'cleanup 143' TERM
# ── Helper: start a service ──────────────────────────────────────────────────
# run_service NAME COMMAND PORT TIMEOUT
# In daemon mode, wraps with nohup. Waits for port to be ready.
run_service() {
local name="$1" cmd="$2" port="$3" timeout="$4"
if _is_port_listening "$port"; then
echo "$name cannot start because port $port is already in use."
echo " If it belongs to this worktree, run 'make stop'; otherwise free the port manually."
cleanup 1
fi
echo "Starting $name..."
if $DAEMON_MODE; then
nohup sh -c "$cmd" > /dev/null 2>&1 &
else
sh -c "$cmd" &
fi
./scripts/wait-for-port.sh "$port" "$timeout" "$name" || {
local logfile="logs/$(echo "$name" | tr '[:upper:]' '[:lower:]' | tr ' ' '-').log"
echo "$name failed to start."
[ -f "$logfile" ] && tail -20 "$logfile"
cleanup 1
}
echo "$name started on localhost:$port"
}
# ── Start services ───────────────────────────────────────────────────────────
mkdir -p logs
mkdir -p temp/client_body_temp temp/proxy_temp temp/fastcgi_temp temp/uwsgi_temp temp/scgi_temp
# 1. Gateway API
run_service "Gateway" \
"cd backend && PYTHONPATH=. uv run uvicorn app.gateway.app:app --host 0.0.0.0 --port 8001 $GATEWAY_EXTRA_FLAGS > ../logs/gateway.log 2>&1" \
8001 30
# 2. Frontend
run_service "Frontend" \
"cd frontend && $FRONTEND_CMD > ../logs/frontend.log 2>&1" \
3000 120
# 3. Nginx
run_service "Nginx" \
"nginx -g 'daemon off;' -c '$REPO_ROOT/docker/nginx/nginx.local.conf' -p '$REPO_ROOT' > logs/nginx.log 2>&1" \
2026 10
# ── Ready ────────────────────────────────────────────────────────────────────
echo ""
echo "=========================================="
echo " ✓ DeerFlow is running! [$MODE_LABEL]"
echo "=========================================="
echo ""
echo " 🌐 http://localhost:2026"
echo ""
echo " Routing: Frontend → Nginx → Gateway"
echo " API: /api/langgraph/* → Gateway agent runtime"
echo " /api/* → Gateway REST API (8001)"
echo ""
echo " 📋 Logs: logs/{gateway,frontend,nginx}.log"
echo ""
if $DAEMON_MODE; then
echo " 🛑 Stop: make stop"
# Detach — trap is no longer needed
trap - INT TERM
else
echo " Press Ctrl+C to stop all services"
wait
fi