feat(ai): few-shot exemplars + sticky Ollama preference

- Few-shot injection on /insights/generate/agentic: compresses prior
  training_messages into trajectory blocks (tool calls + result summaries)
  and injects into the system prompt. Hardcoded default ids with optional
  request override.
- New fewshot_source_ids column on photo_insights (+ migration) to track
  which exemplars influenced a given row, for downstream training-set
  filtering. Chat amend rows stamp None with a lineage note.
- Ollama client now remembers which server (primary/fallback) most
  recently succeeded and tries it first on the next call, via a shared
  Arc<AtomicBool>. Avoids re-404ing the primary on every agent iteration
  when the chosen model only lives on the fallback.
- Demote noisy logs: daily_summary "Summary match" lines to debug;
  inner chat_with_tools non-2xx body log from error to warn (outer
  layer owns the terminal-error signal).
- Drift-guard tests for summarize_tool_result covering the success /
  empty / error / unknown shape for every tool.
- Tidy: three pre-existing clippy warnings cleaned up.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/ai/openrouter.rs

@@ -452,8 +452,7 @@ impl LlmClient for OpenRouterClient {
                 // SSE frames are delimited by a blank line. Walk the buffer
                 // for "\n\n" markers; anything before them is a complete
                 // frame (possibly multi-line).
-                loop {
-                    let Some(sep) = find_double_newline(&buf) else { break };
+                while let Some(sep) = find_double_newline(&buf) {
                     let frame = buf.drain(..sep + 2).collect::<Vec<_>>();
                     let frame_str = match std::str::from_utf8(&frame) {
                         Ok(s) => s,