docs: add local mvp runbook

2026-06-21 23:42:37 +08:00
parent 97485aa4e9
commit 489f6604bb
2 changed files with 96 additions and 0 deletions
@@ -117,6 +117,30 @@ flowchart LR
  E -->|pass/warn| G["Exporter"]
 ```

+### LLM Provider Integration
+
+Workflow nodes use a local LLM client abstraction instead of calling a vendor API directly. The first implementation uses DeepSeek by default, while keeping the provider boundary open for later OpenAI-compatible providers.
+
+Environment variables:
+
+```text
+LLM_PROVIDER=deepseek
+DEEPSEEK_API_KEY=
+DEEPSEEK_BASE_URL=https://api.deepseek.com
+DEEPSEEK_MODEL=deepseek-v4-pro
+DEEPSEEK_THINKING=disabled
+```
+
+Rules:
+
+- `src/lib/llm/client.ts` exposes `generateText`, `generateJson<T>`, `isLlmConfigured`, and `getLlmProviderStatus`.
+- `LLM_PROVIDER` defaults to `deepseek` when unset.
+- DeepSeek is accessed through the OpenAI-compatible SDK with `baseURL` set to `https://api.deepseek.com`.
+- `generateJson<T>` must use JSON output mode and prompts that explicitly require valid JSON only.
+- Thinking mode is disabled by default for deterministic article rewrites and structured QA output.
+- Missing credentials use deterministic local fallbacks so the MVP remains testable and usable without a live API key.
+- Provider errors are normalized inside the LLM client before they reach workflow nodes or API routes.
+
 ### InputNormalizer

 Purpose: normalize page input into clean structured data.