Summarize: LAN primary with local-Ollama rescue + in-app failure guidance

- Engine: when the primary summarizer is out of retries (or misconfigured),
  run_summarize now finishes the job on the configured rescue provider
  (SHONAR_LLM_FALLBACK_*), tags the summary with the provider that wrote it,
  and stores a human note in job.error; success clears stale notes.
- App (auto/lan): passes Ollama as the rescue provider when it is up.
- Detail screen: shows the rescue-swap note in plain words, a red
  'Summary failed' line with Settings -> Summarizer fix instructions and a
  Retry summary button on hard failure.
- Settings copy explains the fallback. 3 new pytest cases (14/14 pass);
  live E2E on 2026-09-18: sarcastic summary v6 via LAN on attempt 2.

backend/shonar/services/ai/__init__.py

@@ -160,3 +160,32 @@ def get_llm_provider(settings: Settings) -> LlmProvider | None:
             model=settings.llm_model,
         )
     raise ProviderConfigError(f"Unknown LLM provider: {settings.llm_provider!r}")
+
+
+def get_llm_fallback_provider(settings: Settings) -> LlmProvider | None:
+    """Rescue provider tried when the primary summarize fails mid-job.
+
+    None means "no fallback configured" — the primary's error stands.
+    Same kinds as get_llm_provider, built from the llm_fallback_* settings.
+    """
+    kind = settings.llm_fallback_provider.strip().lower()
+    if kind in ("", "none"):
+        return None
+    if kind == "openai_compat":
+        from shonar.services.ai.openai_compat import OpenAICompatProvider
+
+        return OpenAICompatProvider(
+            base_url=settings.llm_fallback_base_url,
+            model=settings.llm_fallback_model,
+            api_key=settings.llm_fallback_api_key,
+        )
+    if kind == "ollama":
+        from shonar.services.ai.ollama import OllamaProvider
+
+        return OllamaProvider(
+            base_url=settings.llm_fallback_base_url,
+            model=settings.llm_fallback_model,
+        )
+    raise ProviderConfigError(
+        f"Unknown LLM fallback provider: {settings.llm_fallback_provider!r}"
+    )