Files
moteva/server/etc/config.yaml
T
root 2f5291a0f9 feat(image): pass reference images to GPT image model for edits
Server: forward canvas/reference images to the image model so extract,
continue, and edit requests stay faithful to the source product.
- Add ImageRequestOptions.Images and route requests with inputs to the
  /v1/images/edits endpoint, via multipart upload (default) or JSON
  image_url payload, selectable through Agent.Image.InputImageTransport.
- Extract reference URLs from prompt directives, inline @image tokens,
  and chat message image/mask contents; fold them into the idempotency
  key and prepend a reference-fidelity instruction to the prompt.

Frontend:
- Shrink CanvasToast to a compact top pill.
- Paste an internal transparent clipboard node instead of re-uploading
  when it matches the clipboard image.
- Keep agent-project polling alive on stream error while streaming.
2026-07-08 01:19:20 +08:00

119 lines
2.8 KiB
YAML

Name: img_infinite_canvas-api
Host: 0.0.0.0
Port: 8888
Timeout: 1200000
MaxBytes: 33554432
Storage:
Driver: postgres
DataSource: postgres://canvas:canvas@localhost:15432/canvas?sslmode=disable
Cache:
Driver: redis
Addr: localhost:16379
Password: ""
DB: 0
TTLSeconds: 300
JobQueue:
Driver: asynq
Addr: localhost:16379
Password: ""
DB: 0
Queue: default
Concurrency: 10
MaxRetry: 3
TimeoutSeconds: 900
ShutdownTimeoutSeconds: 30
Realtime:
Driver: redis
Addr: localhost:16379
Password: ""
DB: 0
ChannelPrefix: canvas:realtime
FallbackPollMillis: 3000
Outbox:
Driver: postgres
DataSource: postgres://canvas:canvas@localhost:15432/canvas?sslmode=disable
PollMillis: 3000
BatchSize: 100
Auth:
Region: global
RegionMode: manual
TokenSecret: local-dev-change-me
TokenTTLSeconds: 604800
RefreshTTLSeconds: 2592000
CodeTTLSeconds: 600
DevReturnCode: true
Email:
Driver: smtp # none|smtp
Host: "smtp.126.com"
Port: 465
Username: "fudaoyuanganhuo@126.com"
Password: "WAFKNILLGRFPJLEL"
FromName: Moteva
FromEmail: fudaoyuanganhuo@126.com
BrandName: Moteva
UseTLS: true
StartTLS: true
InsecureSkipVerify: false
TimeoutSeconds: 10
Turnstile:
Enabled: true
SiteKey: "1x00000000000000000000AA"
SecretKey: "1x0000000000000000000000000000000AA"
SecretKeyEnv: TURNSTILE_SECRET_KEY
SiteVerifyURL: https://challenges.cloudflare.com/turnstile/v0/siteverify
TimeoutSeconds: 5
Google:
ClientID: ""
TokenInfoURL: https://oauth2.googleapis.com/tokeninfo
TimeoutSeconds: 8
Wechat:
AppID: ""
AppSecret: ""
RedirectURI: ""
Scope: snsapi_login
AuthURL: https://open.weixin.qq.com/connect/qrconnect
TokenURL: https://api.weixin.qq.com/sns/oauth2/access_token
TimeoutSeconds: 8
Agent:
Driver: pi
Research:
Driver: duckduckgo
TimeoutSeconds: 10
MaxResults: 10
Text:
Driver: vision
Model: gpt-5.4-mini
TimeoutSeconds: 240
CacheTTLSeconds: 43200
Object:
Driver: vision
Model: gpt-5.4-mini
TimeoutSeconds: 60
Background:
Driver: onnxruntime
ModelPath: model/rmbg1.4.onnx
SharedLibraryPath: /Users/liangxu/.pyenv/versions/anaconda3-2023.09-0/lib/python3.11/site-packages/onnxruntime/capi/libonnxruntime.1.22.1.dylib
ExecutionProvider: auto
InputSize: 0
TimeoutSeconds: 300
Planner:
Driver: vision
Model: gpt-5.5
TimeoutSeconds: 240
Image:
BaseURL: http://154.21.87.3:8080
APIKeyEnv: GPT_IMAGE_API_KEY
APIKey: "sk-0af1835a4e855198ec6e1ff8fb120844c146dd09b0b25b05b30ed8fa5c7be568"
InputImageTransport: file
TimeoutSeconds: 600
ObjectStorage:
Driver: minio
Bucket: canvas-assets
Endpoint: localhost:19000
Region: us-east-1
AccessKey: canvas
SecretKey: canvas-secret
PublicBase: http://localhost:19000/canvas-assets
UseSSL: false
ExpiresIn: 900