deer-flow/scripts/setup_wizard.py
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

166 lines
6.2 KiB
Python

#!/usr/bin/env python3
"""DeerFlow Interactive Setup Wizard.
Usage:
uv run python scripts/setup_wizard.py
"""
from __future__ import annotations
import sys
from pathlib import Path
# Make the scripts/ directory importable so wizard.* works
sys.path.insert(0, str(Path(__file__).resolve().parent))
def _is_interactive() -> bool:
return sys.stdin.isatty() and sys.stdout.isatty()
def main() -> int:
try:
if not _is_interactive():
print(
"Non-interactive environment detected.\n"
"Please edit config.yaml and .env directly, or run 'make setup' in a terminal."
)
return 1
from wizard.ui import (
ask_yes_no,
bold,
cyan,
green,
print_header,
print_info,
print_success,
yellow,
)
from wizard.writer import write_config_yaml, write_env_file
project_root = Path(__file__).resolve().parents[1]
config_path = project_root / "config.yaml"
env_path = project_root / ".env"
print()
print(bold("Welcome to DeerFlow Setup!"))
print("This wizard will help you configure DeerFlow in a few minutes.")
print()
if config_path.exists():
print(yellow("Existing configuration detected."))
print()
should_reconfigure = ask_yes_no("Do you want to reconfigure?", default=False)
if not should_reconfigure:
print()
print_info("Keeping existing config. Run 'make doctor' to verify your setup.")
return 0
print()
total_steps = 4
from wizard.steps.llm import run_llm_step
llm = run_llm_step(f"Step 1/{total_steps}")
from wizard.steps.search import run_search_step
search = run_search_step(f"Step 2/{total_steps}")
search_provider = search.search_provider
search_api_key = search.search_api_key
fetch_provider = search.fetch_provider
fetch_api_key = search.fetch_api_key
from wizard.steps.execution import run_execution_step
execution = run_execution_step(f"Step 3/{total_steps}")
print_header(f"Step {total_steps}/{total_steps} · Writing configuration")
write_config_yaml(
config_path,
provider_use=llm.provider.use,
model_name=llm.model_name,
display_name=f"{llm.provider.display_name} / {llm.model_name}",
api_key_field=llm.provider.api_key_field,
env_var=llm.provider.env_var,
extra_model_config=llm.provider.extra_config_for(llm.model_name) or None,
base_url=llm.base_url,
search_use=search_provider.use if search_provider else None,
search_tool_name=search_provider.tool_name if search_provider else "web_search",
search_extra_config=search_provider.extra_config if search_provider else None,
web_fetch_use=fetch_provider.use if fetch_provider else None,
web_fetch_tool_name=fetch_provider.tool_name if fetch_provider else "web_fetch",
web_fetch_extra_config=fetch_provider.extra_config if fetch_provider else None,
sandbox_use=execution.sandbox_use,
allow_host_bash=execution.allow_host_bash,
include_bash_tool=execution.include_bash_tool,
include_write_tools=execution.include_write_tools,
)
print_success(f"Config written to: {config_path.relative_to(project_root)}")
if not env_path.exists():
env_example = project_root / ".env.example"
if env_example.exists():
import shutil
shutil.copyfile(env_example, env_path)
env_pairs: dict[str, str] = {}
if llm.api_key:
env_pairs[llm.provider.env_var] = llm.api_key
if search_api_key and search_provider and search_provider.env_var:
env_pairs[search_provider.env_var] = search_api_key
if fetch_api_key and fetch_provider and fetch_provider.env_var:
env_pairs[fetch_provider.env_var] = fetch_api_key
if env_pairs:
write_env_file(env_path, env_pairs)
print_success(f"API keys written to: {env_path.relative_to(project_root)}")
frontend_env = project_root / "frontend" / ".env"
frontend_env_example = project_root / "frontend" / ".env.example"
if not frontend_env.exists() and frontend_env_example.exists():
import shutil
shutil.copyfile(frontend_env_example, frontend_env)
print_success("frontend/.env created from example")
print_header("Setup complete!")
print(f" {green('')} LLM: {llm.provider.display_name} / {llm.model_name}")
if search_provider:
print(f" {green('')} Web search: {search_provider.display_name}")
else:
print(f" {'':>3} Web search: not configured")
if fetch_provider:
print(f" {green('')} Web fetch: {fetch_provider.display_name}")
else:
print(f" {'':>3} Web fetch: not configured")
sandbox_label = "Local sandbox" if execution.sandbox_use.endswith("LocalSandboxProvider") else "Container sandbox"
print(f" {green('')} Execution: {sandbox_label}")
if execution.include_bash_tool:
bash_label = "enabled"
if execution.allow_host_bash:
bash_label += " (host bash)"
print(f" {green('')} Bash: {bash_label}")
else:
print(f" {'':>3} Bash: disabled")
if execution.include_write_tools:
print(f" {green('')} File write: enabled")
else:
print(f" {'':>3} File write: disabled")
print()
print("Next steps:")
print(f" {cyan('make install')} # Install dependencies (first time only)")
print(f" {cyan('make dev')} # Start DeerFlow")
print()
print(f"Run {cyan('make doctor')} to verify your setup at any time.")
print()
return 0
except KeyboardInterrupt:
print("\n\nSetup cancelled.")
return 130
if __name__ == "__main__":
sys.exit(main())