fix: correct invalid OPENROUTER_DEFAULT model ID

google/gemini-flash-2.0 is not a valid OpenRouter model ID (segments reversed).
Every rerank and FunJudge call fails with HTTP 400 when REASONING_PROVIDER=openrouter
and LAST30DAYS_RERANK_MODEL is not explicitly pinned, silently falling back to
local-score heuristics.

OpenRouter error body:
  {"message":"google/gemini-flash-2.0 is not a valid model ID","code":400}

Switching to google/gemini-3.1-flash-lite-preview, which matches the
GEMINI_FLASH_LITE constant already used by the native Gemini provider on
line 12 of the same file. This makes the Gemini and OpenRouter providers
consistent and avoids a future divergence.

Validated with /last30days 'Claude Opus 4.7' --quick:
- Rerank/FunJudge HTTP 400 errors: 1 per run -> 0
- 'Why: fallback-local-score' markers in output: every cluster -> 0
- LLM-generated 'Why:' reasoning lines: 0 -> 11

skills/last30days/scripts/lib/providers.py

@@ -19,7 +19,7 @@ OPENAI_RESPONSES_URL = "https://api.openai.com/v1/responses"
 CODEX_RESPONSES_URL = "https://chatgpt.com/backend-api/codex/responses"
 XAI_RESPONSES_URL = "https://api.x.ai/v1/responses"
 OPENROUTER_URL = "https://openrouter.ai/api/v1/chat/completions"
-OPENROUTER_DEFAULT = "google/gemini-flash-2.0"
+OPENROUTER_DEFAULT = "google/gemini-3.1-flash-lite-preview"
 
 
 class ReasoningClient: