OpenCode
68a9071cf1
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.
1 line
1.8 KiB
JSON
1 line
1.8 KiB
JSON
{"repo": "arbenapura/wiki-reader-ai", "files": {".env.example": {"e41243dd036aa329d25e3997241b2d7bbb0c1178": {"t": 1786068200.8532782, "n": 1635, "h": "329fe4c72e4f432e", "c": "# ------------------------------------------------------------------\n# Wiki Reader AI — environment configuration\n# Copy this file to .env and fill in the keys for the features you use.\n# The web app (reader + wiki) runs without any keys; keys are only\n# needed for the AI-powered features.\n# ------------------------------------------------------------------\n\n# --- CHAT / PIPELINE LLM (required for wiki generation + chat) ---\n# DashScope (Qwen) — default provider, OpenAI-compatible endpoint\nQWEN_API_KEY=\nQWEN_BASE_URL=https://dashscope-intl.aliyuncs.com/compatible-mode/v1\n\n# DeepSeek — model names prefixed with \"deepseek-\" route here\nDEEPSEEK_API_KEY=\nDEEPSEEK_BASE_URL=https://api.deepseek.com\n\n# OpenRouter — any \"vendor/model\" name routes here\nOPENROUTER_API_KEY=\nOPENROUTER_BASE_URL=https://openrouter.ai/api/v1\n\n# Default model for the whole pipeline.\n# No prefix -> DashScope (e.g. qwen3.5-flash)\n# deepseek- prefix -> DeepSeek (e.g. deepseek-v4-flash)\n# vendor/model -> OpenRouter (e.g. meta-llama/llama-4-scout)\nLLM_MODEL=deepseek-v4-flash\n\n# --- IMAGE GENERATION (entity portraits, DashScope) ---\n# Uses QWEN_API_KEY above when unset; IMAGE_MODEL selects the DashScope model.\nIMAGE_MODEL=z-image-turbo\n\n# --- EMBEDDINGS (vector store for RAG; default: DashScope) ---\nEMBED_API_KEY=\nEMBED_BASE_URL=https://dashscope-intl.aliyuncs.com/compatible-mode/v1\nEMBED_MODEL=text-embedding-v4\n\n# --- OPTIONAL TUNING ---\n# Bump to invalidate the LLM response disk cache (cache/.llm-cache)\n# PROMPT_VERSION=v1\n# Override database paths\n# WIKI_DB_PATH=./books/wiki.sqlite\n# VEC_DB_PATH=./books/vectors.sqlite\n"}}}} |