feat: AI Self-Loop 專案骨架 — 爬站健檢版
完整實作建構順序 1-8(rule-based): - Task Queue(SQLite):tasks/attempts/results + claim 防重複 - LLM 後端:OllamaBackend(num_ctx=32768) + LLMRouter - Prompt Builder(YAML+Jinja2,重試注入 feedback) - Context Assembler / Output Judge / Feedback Builder - Loop Controller + Circuit Breaker - Driver 層(BaseDriver + ApiClientDriver) - Agent 層(BaseAgent + SiteHealthAgent:爬站/健檢/issue 生成) - pipeline.py 入口,驗收:pending→done,output/ 落地 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
4
specs/site_health.example.json
Normal file
4
specs/site_health.example.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"_comment": "site_health 任務的輸入範例。實際 start_url 以 config/environments.yaml 為準;這裡只是說明 payload 形狀。",
|
||||
"start_url": "https://www.pluspay.com.tw/"
|
||||
}
|
||||
Reference in New Issue
Block a user