feat(ai B.1 #15 + A.1 #28): cleanup presets and sequential-GPU guard

Two new Settings → AI knobs that compose cleanly with what already
shipped (aiTier, LLM model, translator prompt framing).

**B.1 #15 — Named cleanup presets.** LlmPromptPreset enum
(Default / Email / Notes / Code) appends a short context hint onto
the CLEANUP_PROMPT just before generation. Presets shape tone and
structure ("email paragraph", "bulleted meeting notes", "preserve
technical terms") without licensing the content-editing the
translator-not-editor framing forbids. cleanup_transcript_text_cmd
now takes `preset: Option<String>` which runs through the new
LlmPromptPreset::parse (normalises aliases like "meeting-notes",
collapses unknown values to Default).

**A.1 #28 — Sequential-GPU guard.** New LocalEngine::unload drops
the backend + model_id so a subsequent load actually reclaims VRAM.
load_llm_model, load_model, and load_parakeet_model Tauri commands
grow an optional `concurrent: bool` argument. When concurrent is
Some(false), loading LLM first unloads whisper+parakeet, and vice
versa — prevents VRAM OOM on tight-VRAM setups. Default is the
previous parallel behaviour so nothing changes for multi-GB cards.
Transcribe-in-progress paths (transcribe_pcm, transcribe_file, live)
pass None, so mid-dictation model loads don't accidentally tear
down the LLM.

Settings UI (AI section):
- Cleanup preset segmented button + descriptive copy for each option.
- GPU concurrency segmented button with explicit trade-off text
  ("faster transitions vs fits in tight VRAM").

Frontend wiring:
- settings.llmPromptPreset flows from DictationPage's
  cleanupTranscriptIfEnabled into the Tauri command.
- settings.aiGpuConcurrency flows from both DictationPage (auto-load
  on record) and SettingsPage (manual load/unload buttons) as
  `concurrent: "parallel" === true` to the load commands.

Tests: three new preset cases in crates/ai-formatting/src/llm_client.rs
(parse aliases, suffix non-empty for non-default, default suffix
empty). All 139 existing lib tests still pass.

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

src/lib/pages/DictationPage.svelte

@@ -239,7 +239,13 @@
     try {
       const status = await invoke("check_llm_model", { modelId: settings.llmModelId });
       if (status?.downloaded && !status.loaded) {
-        await invoke("load_llm_model", { modelId: settings.llmModelId });
+        await invoke("load_llm_model", {
+          modelId: settings.llmModelId,
+          // Sequential-GPU guard (brief item A.1 #28): frees whisper
+          // before loading the LLM on tight-VRAM setups. "parallel"
+          // keeps both resident (default, safe on multi-GB cards).
+          concurrent: settings.aiGpuConcurrency === "parallel",
+        });
       }
     } catch (err) {
       console.warn("ensureLlmModelLoaded failed", err);
@@ -257,10 +263,15 @@
     error = "";
 
     try {
+      // concurrent flag mirrors settings.aiGpuConcurrency (brief A.1 #28).
+      const concurrent = settings.aiGpuConcurrency === "parallel";
       if (settings.engine === "parakeet") {
-        await invoke("load_parakeet_model", { name: "ctc-int8" });
+        await invoke("load_parakeet_model", { name: "ctc-int8", concurrent });
       } else {
-        await invoke("load_model", { size: settings.modelSize.toLowerCase() });
+        await invoke("load_model", {
+          size: settings.modelSize.toLowerCase(),
+          concurrent,
+        });
       }
       await refreshRuntimeCapabilities();
       modelReady = true;
@@ -460,6 +471,7 @@
       const cleaned = await invoke("cleanup_transcript_text_cmd", {
         transcript: text,
         profileId: profilesStore.activeProfileId,
+        preset: settings.llmPromptPreset,
       });
       markGenerationDone(true);
       return cleaned?.trim() ? cleaned.trim() : text;

src/lib/pages/SettingsPage.svelte

@@ -531,7 +531,11 @@
     const modelId = selectedLlmModelId();
     llmStatus = "Loading...";
     try {
-      await invoke("load_llm_model", { modelId });
+      await invoke("load_llm_model", {
+        modelId,
+        // Sequential-GPU guard (brief item A.1 #28).
+        concurrent: settings.aiGpuConcurrency === "parallel",
+      });
       await refreshLlmStatus();
       await refreshGlobalLlmStatus(settings.aiTier);
     } catch (err) {
@@ -740,7 +744,10 @@
     engineStatus = "Loading...";
     engineOk = false;
     try {
-      await invoke("load_model", { size });
+      await invoke("load_model", {
+        size,
+        concurrent: settings.aiGpuConcurrency === "parallel",
+      });
       await refreshRuntimeCapabilities();
       engineOk = true;
       engineStatus = `${settings.modelSize} model loaded`;
@@ -796,7 +803,10 @@
     parakeetStatus = "Loading...";
     parakeetOk = false;
     try {
-      await invoke("load_parakeet_model", { name: "ctc-int8" });
+      await invoke("load_parakeet_model", {
+        name: "ctc-int8",
+        concurrent: settings.aiGpuConcurrency === "parallel",
+      });
       await refreshRuntimeCapabilities();
       parakeetOk = true;
       parakeetStatus = "Model loaded";
@@ -1505,6 +1515,48 @@
                 {/if}
               </p>
             </div>
+
+            <!-- Cleanup preset (brief item B.1 #15). Shapes the tone /
+                 structure of LLM cleanup output; composes on top of the
+                 active profile's initial prompt. -->
+            <div class="mt-5">
+              <p class="text-[10px] font-medium text-text-tertiary uppercase tracking-wider mb-2">Cleanup preset</p>
+              <SegmentedButton
+                options={["default", "email", "notes", "code"]}
+                bind:value={settings.llmPromptPreset}
+              />
+              <p class="text-[11px] text-text-tertiary mt-2">
+                {#if settings.llmPromptPreset === "email"}
+                  Formats output as an email paragraph — tight sentences, no markdown, no auto-added greeting or signoff.
+                {:else if settings.llmPromptPreset === "notes"}
+                  Formats action items as a bullet list led by imperative verbs; keeps prose informational sentences as prose.
+                {:else if settings.llmPromptPreset === "code"}
+                  Preserves technical terms, variable names, file paths, and symbols exactly as spoken. No translation of identifiers.
+                {:else}
+                  No preset — the active profile's prompt governs tone alone.
+                {/if}
+              </p>
+            </div>
+
+            <!-- Sequential-GPU guard (brief item A.1 #28). On a tight-
+                 VRAM single-GPU system, loading LLM + Whisper together
+                 can OOM. Sequential mode unloads one before loading the
+                 other; adds reload latency between transcribe and
+                 cleanup phases. -->
+            <div class="mt-5">
+              <p class="text-[10px] font-medium text-text-tertiary uppercase tracking-wider mb-2">GPU concurrency</p>
+              <SegmentedButton
+                options={["parallel", "sequential"]}
+                bind:value={settings.aiGpuConcurrency}
+              />
+              <p class="text-[11px] text-text-tertiary mt-2">
+                {#if settings.aiGpuConcurrency === "sequential"}
+                  On tight-VRAM cards (≤6 GB), loading Whisper + LLM together OOMs. Sequential mode frees the other model before loading; adds a small reload pause between transcribe and cleanup.
+                {:else}
+                  Both models stay resident in GPU memory. Faster transitions, but needs enough VRAM to hold both at once.
+                {/if}
+              </p>
+            </div>
           </div>
         {/if}
       </div>

src/lib/stores/page.svelte.ts

@@ -61,6 +61,8 @@ const defaults: SettingsState = {
   fontSize: 14,
   aiTier: "cleanup",
   llmModelId: null,
+  llmPromptPreset: "default",
+  aiGpuConcurrency: "parallel",
   saveAudio: false,
   outputFolder: "",
   globalHotkey: "Ctrl+Shift+R",

src/lib/types/app.ts

@@ -12,6 +12,8 @@ export type WhisperModelSize =
   | "Distil-L";
 export type AiTier = "off" | "cleanup" | "tasks";
 export type LlmModelIdStr = "qwen3_1_7b" | "qwen3_4b_instruct_2507" | "qwen3_14b";
+export type LlmPromptPreset = "default" | "email" | "notes" | "code";
+export type AiGpuConcurrency = "parallel" | "sequential";
 export type TaskBucket = "inbox" | "today" | "soon" | "later";
 export type ToastSeverity = "info" | "success" | "warn" | "error";
 
@@ -47,6 +49,8 @@ export interface SettingsState {
   fontSize: number;
   aiTier: AiTier;
   llmModelId: LlmModelIdStr | null;
+  llmPromptPreset: LlmPromptPreset;
+  aiGpuConcurrency: AiGpuConcurrency;
   saveAudio: boolean;
   outputFolder: string;
   globalHotkey: string;