Files
hack/tools/scripts/llm-key-hunter/results/_cache/content/cha3343954211_mathoi-mcmagent.json
T
OpenCode 68a9071cf1 feat: reconcile local master with origin (exa/hot-platform hunters, leaks ledger, latest results)
Local branch had diverged from origin/master (sibling commits on the same base). Rewrote local history linearly on top of origin/master, folding in all local content: exa/hot-platform discovery hunters, leaks ledger, nightly sweep orchestrator, updated .gitignore and skill docs, plus the latest hunt output and vault state. Remote-only files (vault keys, channel scripts) were restored rather than dropped, so the resulting tree is a full union of both sides.
2026-08-07 12:53:47 +08:00

1 line
2.6 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{"repo": "cha3343954211/mathoi-mcmagent", "files": {"backend/.env.example": {"8bce61d4e315d7fd3b2fb31ede5f2399aafc8544": {"t": 1786068617.622536, "n": 1832, "h": "21cf0e653b580402", "c": "# ============== 全局 ==============\nAPP_HOST=0.0.0.0\nAPP_PORT=8000\nLOG_LEVEL=INFO\nWORKSPACE_DIR=./workspace\n# 生产环境建议填写具体域名,如 https://example.com; 开发/内网 可用 *\nCORS_ORIGINS=*\n\n# ============== Redis(可选,未配置则使用内存存储) ==============\nREDIS_URL=\n\n# ============== 数据库 ==============\n# 默认 SQLite(零配置);上云推荐:postgresql+asyncpg://user:pass@host:5432/dbname\nDATABASE_URL=sqlite+aiosqlite:///./mathoi.db\n\n# ============== 认证 ==============\nJWT_SECRET=change-me-please-use-a-long-random-string\nJWT_ALGORITHM=HS256\nJWT_EXPIRE_MINUTES=10080\n# 是否允许公开注册(false 则仅管理员可创建用户)\nALLOW_REGISTER=true\n\n# 默认管理员(首次启动自动创建,已存在则忽略)\nDEFAULT_ADMIN_USERNAME=admin\nDEFAULT_ADMIN_PASSWORD=admin123\nDEFAULT_ADMIN_EMAIL=admin@example.com\n\n# ============== LLM 后端 ==============\n# openai = OpenAI 兼容协议直连; litellm = 统一通过 LiteLLM 转发\nLLM_BACKEND=openai\n\n# ============== 默认模型(兜底) ==============\nDEFAULT_BASE_URL=https://api.deepseek.com/v1\nDEFAULT_API_KEY=sk-your-key-here\nDEFAULT_MODEL=deepseek-chat\nDEFAULT_TEMPERATURE=0.3\n\n# ============== 多模型协同(每个 Agent 可独立覆盖) ==============\n# Modeler:建模 / 数学推理,建议用强推理模型\nMODELER_MODEL=\nMODELER_BASE_URL=\nMODELER_API_KEY=\nMODELER_TEMPERATURE=0.2\n\n# Coder:代码生成 / 数据分析,建议用代码能力强的模型\nCODER_MODEL=\nCODER_BASE_URL=\nCODER_API_KEY=\nCODER_TEMPERATURE=0.1\n\n# Writer:论文撰写,建议用语言流畅的模型\nWRITER_MODEL=\nWRITER_BASE_URL=\nWRITER_API_KEY=\nWRITER_TEMPERATURE=0.5\n\n# ============== 沙箱 ==============\nSANDBOX_TIMEOUT=120\nSANDBOX_KERNEL=python3\n\n# ============== 工作流 ==============\nMAX_CODER_ITERATIONS=8\nMAX_REVISION_ROUNDS=2\n\n# ============== 联网搜索(Coder web_search 工具)==============\n# 搜索引擎:duckduckgo(无需配置,直接可用)| searxng(自建,推荐服务器部署)\nSEARCH_PROVIDER=duckduckgo\n# SearXNG 本地地址(仅 SEARCH_PROVIDER=searxng 时生效)\n# Docker 部署示例:docker run -d -p 127.0.0.1:8080:8080 searxng/searxng\nSEARXNG_BASE_URL=\n# 每次请求超时秒数(默认 8)\nSEARXNG_TIMEOUT=8\n# 每次搜索返回条数(默认 6)\nSEARCH_MAX_RESULTS=6\n"}}}}