GenarrativeAI/Genarrative
12
0
Fork 0
Code Issues 27 Pull Requests 6 Actions Packages Projects 1 Releases Wiki Activity

接入VectorEngine画布Agent规划

Browse Source 
切换画布 Agent 与通用 LLM 代理到 VectorEngine gpt-5.4-mini。

为画布 Agent 注入上一轮生成结果并默认承接上一张图编辑。

补齐规范图工具分流、规范展板 prompt 要求和 JSON 残片回复兜底。

同步前后端契约、测试脚本、环境示例和项目文档。
This commit is contained in:
段舒康
2026-07-05 17:42:27 +08:00
parent a4a7aed024
commit d7d98acfd4
20 changed files with 945 additions and 116 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+11 -11
View File
@@ -1,11 +1,12 @@
# Server-side OpenAI-compatible LLM endpoint base URL.
LLM_BASE_URL="https://ark.cn-beijing.volces.com/api/v3"
LLM_BASE_URL="https://api.vectorengine.cn/v1"
# Server-side API key used by the local Vite proxy.
# Recommended: set `LLM_API_KEY` or `ARK_API_KEY`.
# Recommended: set `LLM_API_KEY` locally, or use `VECTOR_ENGINE_API_KEY`
# through the Rust api-server proxy.
# Legacy compatibility: `VITE_LLM_API_KEY` is still supported by the proxy,
# but it should not be relied on by browser code.
LLM_API_KEY="YOUR_API_KEY"
LLM_API_KEY=""
# Optional frontend override for the local proxy path.
VITE_LLM_PROXY_BASE_URL="/api/llm"
@@ -116,7 +117,11 @@ WECHAT_MINIPROGRAM_GENERATION_RESULT_TEMPLATE_ID="m5z7BkkBhJGbcH0cdDeHaeRU2tViDE
WECHAT_MINIPROGRAM_SUBSCRIBE_MESSAGE_STATE="formal"
# Model name for chat completions.
VITE_LLM_MODEL="doubao-1-5-pro-32k-character-250715"
VITE_LLM_MODEL="gpt-5.4-mini"
GENARRATIVE_LLM_PROVIDER="openai-compatible"
GENARRATIVE_LLM_BASE_URL="https://api.vectorengine.cn/v1"
GENARRATIVE_LLM_API_KEY=""
GENARRATIVE_LLM_MODEL="gpt-5.4-mini"
# Optional: enable upstream web search for RPG story text generation.
RPG_LLM_WEB_SEARCH_ENABLED="true"
@@ -125,13 +130,8 @@ RPG_LLM_WEB_SEARCH_ENABLED="true"
DASHSCOPE_BASE_URL="https://dashscope.aliyuncs.com/api/v1"
DASHSCOPE_API_KEY="YOUR_DASHSCOPE_API_KEY"
# APIMart Responses config for creative-agent text/multimodal understanding.
APIMART_BASE_URL="https://api.apimart.ai/v1"
APIMART_API_KEY="YOUR_APIMART_API_KEY"
APIMART_IMAGE_REQUEST_TIMEOUT_MS="180000"
# VectorEngine GPT-image-2 / Gemini image generation config.
VECTOR_ENGINE_BASE_URL="https://api.vectorengine.ai"
# VectorEngine LLM and GPT-image-2 / Gemini image generation config.
VECTOR_ENGINE_BASE_URL="https://api.vectorengine.cn"
VECTOR_ENGINE_API_KEY=""
VECTOR_ENGINE_IMAGE_REQUEST_TIMEOUT_MS="1000000"