chore(llm): update callers for renamed model variants

Picks up the registry rename in the front-end and Tauri command layer:

- src/lib/types/app.ts: LlmModelIdStr now lists the four new ids
  (qwen3_5_2b / qwen3_5_4b / qwen3_5_9b / qwen3_6_27b).
- src/lib/pages/SettingsPage.svelte: LLM_MODELS table rebuilt with
  four tiers (Minimal / Standard / High / Maximum), matching subtitles
  and download-size copy. selectedLlmModelId fallback, hardware-warning
  thresholds, tier-availability check, and ensureRecommendedLlmTier
  fallback all retargeted at the new ids. The Maximum tier surfaces a
  64 GB / 24 GB warning so users with mid-range hardware see honest
  expectations.
- src-tauri/src/commands/llm.rs and commands/tasks.rs: doc-comment
  examples refreshed (Qwen3 4B → Qwen3.5 4B, Qwen3's tokenizer →
  Qwen's tokenizer — the BPE family is shared).
- src/lib/stores/llmStatus.svelte.ts: chip-detail example updated.

cargo build --workspace clean. cargo test --workspace clean.
npx svelte-check reports one pre-existing error in vite.config.js
(unused @ts-expect-error directive, dates back to the original
scaffold commit 9926a42); not introduced here, out of scope to fix.

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

src-tauri/src/commands/llm.rs

@@ -159,7 +159,7 @@ pub struct LlmTestResult {
     pub category: String,
     /// `true` when the LLM is healthy and usable after the test.
     pub ok: bool,
-    /// One-line status copy for the Settings chip ("Qwen3 4B ready").
+    /// One-line status copy for the Settings chip ("Qwen3.5 4B ready").
     pub message: String,
     /// Optional actionable next step ("Click Download", "Delete and
     /// re-download", "Pick a smaller tier"). Absent when the state is

src-tauri/src/commands/tasks.rs

@@ -250,7 +250,7 @@ fn to_llm_examples(rows: Vec<FeedbackRow>) -> Vec<LlmFeedbackExample> {
         .collect()
 }
 
-/// Rough character budget for the few-shot block. Qwen3's tokenizer
+/// Rough character budget for the few-shot block. Qwen's tokenizer
 /// averages ~3.5 chars per token in English, so 2000 chars is ~570
 /// tokens — well inside the 64-token reserve + response-token gap
 /// against the 8192-token context cap (see `LlmEngine::generate`).