refactor(ai): read LLM settings from LlmConfig instead of env

Every LLM env reader now goes through ai::config::llm_config():
build_ollama / build_llamacpp / build_openrouter take config sections
(OPENROUTER_API_KEY is still read from env), and the backend switch,
embedding dim + prefixes, Ollama / llama.cpp / TTS timeouts, TTS voice and
ref length, agentic caps, chat turn timeout and the unified-search model
read their sections. LocalLlm::from_env -> from_config; the
test_daily_summary and populate_knowledge bins take Ollama defaults from
the config. env_max_iterations / env_default_num_ctx are renamed to
max_chat_iterations / default_num_ctx.

The picker still uses picker.include (= LLAMA_SWAP_ALLOWED_MODELS) until
discovery lands. Legacy env vars keep working through the config's
override layer; checked against the deployed .env, which resolves to the
same values. The LLM_BACKEND parsing tests move to ai::config.

llm.example.toml now leaves the embed prefixes empty: copying the
nomic prefixes onto a corpus embedded without them breaks search.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

src/unified_search.rs

@@ -639,15 +639,15 @@ async fn translate<TagD: TagDao>(
     // llama-swap); local only, no hybrid, per the feature's design.
     //
     // Translation-model precedence:
-    //   1. UNIFIED_SEARCH_MODEL env — pin a small, fast model that can stay
+    //   1. `unified_search_model` (llm.toml) — pin a small, fast model that can stay
     //      co-resident with CLIP (and the chat model) so translation never
     //      evicts them. This is the recommended setup on a tight VRAM budget.
     //   2. the client-selected model — routes translation to whatever the user
     //      already has loaded (no swap) when no dedicated model is pinned.
     //   3. None → resolve_backend uses the configured default local model.
-    let translation_model = std::env::var("UNIFIED_SEARCH_MODEL")
-        .ok()
-        .filter(|m| !m.trim().is_empty())
+    let translation_model = crate::ai::config::llm_config()
+        .unified_search_model
+        .clone()
         .or_else(|| query.model.clone())
         .filter(|m| !m.trim().is_empty());
     let overrides = SamplingOverrides {