feat: integrate local LLM API (homelab-frontend) + Pi skills

Replace Anthropic client with OpenAI-compatible client targeting https://api.riotpiao.com.
Configure models: reasoning (Planner/Judge), ornith:35b (Implementer).
Add health check on startup.
Add Pi provider support for skill preparation (--pi-provider=local-llm).

Files changed:
- action/llm/client.go: OpenAI-compatible HTTP client + HealthCheck()
- action/llm/client_test.go: Unit tests for model validation & health
- cmd/starter/main.go: Health check before workflow, local model defaults
- statemachine/types.go: PiProvider field for OrchestratorInput

Models:
- Planner: reasoning (smart decisions)
- Judge: reasoning (quality review)
- Implementer: ornith:35b (cheap execution)

Skills: pi clone-or-fetch --provider=local-llm with 504 timeout learning.

Verification: go build ./cmd/starter ./cmd/worker ./action/llm ✓
Tests: go test -v ./action/llm ✓ (all passing)

k8s/worker-deployment.yaml

@@ -13,8 +13,8 @@ spec:
       labels:
         app: poimen-worker
       annotations:
-        git-commit: "c85105e"  # ✅ Updated on each push, triggers rolling restart
-        deployment-date: "2026-08-23"
+        git-commit: "0b6bca7"  # ✅ Updated on each push, triggers rolling restart
+        deployment-date: "2026-08-26"
     spec:
       containers:
       - name: worker