feat(v031): AiWorker vision integration — note.media + visionModel + 5MB cap

src/main/ai/AiWorker.ts

@@ -1,6 +1,9 @@
+import { readFile } from 'node:fs/promises';
 import type { NoteRepository } from '../repository/NoteRepository.js';
 import type { Note } from '@shared/types';
 import type { AiFailedReason } from '../services/telemetryEvents.js';
+import type { SettingsService } from '../services/SettingsService.js';
+import type { MediaStore } from '../services/MediaStore.js';
 import { ProviderHolder } from './ProviderHolder.js';
 import { parseAllCandidates } from '../services/dueDateParser.js';
 import { ZodError } from 'zod';
@@ -41,6 +44,10 @@ export interface AiWorkerOptions {
   };
   now?: () => Date;
   telemetry?: AiTelemetryEmitter;
+  /** v0.3.1 Cut F — vision 지원. 미전달 시 vision 비활성. */
+  settings?: Pick<SettingsService, 'getVisionModel'>;
+  /** v0.3.1 Cut F — 첨부 이미지 절대경로 변환. settings 와 함께 전달 시 vision 활성. */
+  mediaStore?: Pick<MediaStore, 'absolutePath'>;
 }
 
 interface Job { noteId: string; attempts: number; }
@@ -56,6 +63,8 @@ export class AiWorker {
   private logger: NonNullable<AiWorkerOptions['logger']>;
   private now: () => Date;
   private telemetry?: AiTelemetryEmitter;
+  private settings?: Pick<SettingsService, 'getVisionModel'>;
+  private mediaStore?: Pick<MediaStore, 'absolutePath'>;
 
   constructor(
     private repo: NoteRepository,
@@ -68,6 +77,8 @@ export class AiWorker {
     this.logger = opts.logger ?? { info: () => {}, warn: () => {}, error: () => {} };
     this.now = opts.now ?? (() => new Date());
     this.telemetry = opts.telemetry;
+    this.settings = opts.settings;
+    this.mediaStore = opts.mediaStore;
   }
 
   async enqueue(noteId: string): Promise<void> {
@@ -128,12 +139,24 @@ export class AiWorker {
         const todayIso = kstTodayIso(nowDate);
         const candidates = parseAllCandidates(note.rawText, todayDate);
         const vocab = this.repo.getTopUsedTags(VOCAB_TOP_N);
-        const res = await this.holder.get().generate({
-          text: note.rawText,
-          todayKst: todayIso,
-          dueDateCandidates: candidates,
-          vocab
-        });
+        // v0.3.1 Cut F — vision path: visionModel + note.media → base64 images
+        const visionModel = this.settings ? await this.settings.getVisionModel() : null;
+        let images: Array<{ base64: string; mime: string }> | undefined;
+        if (visionModel && note.media.length > 0 && this.mediaStore) {
+          images = await Promise.all(
+            note.media.map(async (m) => {
+              const buf = await readFile(this.mediaStore!.absolutePath(m.relPath));
+              if (buf.byteLength > 5 * 1024 * 1024) {
+                throw new Error(`image ${m.relPath} exceeds 5MB cap`);
+              }
+              return { base64: buf.toString('base64'), mime: m.mime };
+            })
+          );
+        }
+        const res = await this.holder.get().generate(
+          { text: note.rawText, images, todayKst: todayIso, dueDateCandidates: candidates, vocab },
+          { visionModel: visionModel ?? undefined }
+        );
         // AI primary: AI's dueDate is final (no rule merge)
         this.repo.updateAiResult(job.noteId, {
           title: res.title,

src/main/index.ts

@@ -149,7 +149,10 @@ app.whenReady().then(async () => {
       refreshTray({ todayCount: repo.countToday() });
     },
     logger,
-    telemetry
+    telemetry,
+    // v0.3.1 Cut F — vision 지원
+    settings: settingsSvc,
+    mediaStore: store
   });
 
   const notify = new NotificationService({

tests/unit/AiWorker.test.ts

@@ -449,9 +449,10 @@ describe('AiWorker — vocab fetch + per-tag hit/miss (v0.2.3 #3 T7)', () => {
     });
     await w.enqueue(id);
     await w.drain();
-    expect(generateMock).toHaveBeenCalledWith(expect.objectContaining({
-      vocab: expect.arrayContaining(['design'])
-    }));
+    expect(generateMock).toHaveBeenCalledWith(
+      expect.objectContaining({ vocab: expect.arrayContaining(['design']) }),
+      expect.anything()
+    );
   });
 
   it('emits tag_vocab_hit for vocab tags + tag_vocab_miss for new tags', async () => {

tests/unit/AiWorker.vision.test.ts

@@ -0,0 +1,125 @@
+import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest';
+import { writeFile, mkdtemp, mkdir, rm } from 'node:fs/promises';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+import Database from 'better-sqlite3';
+import { runMigrations } from '@main/db/migrations/index.js';
+import { NoteRepository } from '@main/repository/NoteRepository.js';
+import { AiWorker } from '@main/ai/AiWorker.js';
+import { ProviderHolder } from '@main/ai/ProviderHolder.js';
+import { MediaStore } from '@main/services/MediaStore.js';
+import type { AiResponse } from '@main/ai/schema.js';
+import type { InferenceProvider } from '@main/ai/InferenceProvider.js';
+
+describe('AiWorker — vision path (v0.3.1 Cut F)', () => {
+  let db: Database.Database;
+  let repo: NoteRepository;
+  let workDir: string;
+  let mediaStore: MediaStore;
+
+  beforeEach(async () => {
+    db = new Database(':memory:');
+    db.pragma('foreign_keys = ON');
+    runMigrations(db);
+    repo = new NoteRepository(db);
+    workDir = await mkdtemp(join(tmpdir(), 'inkling-vision-'));
+    mediaStore = new MediaStore(workDir);
+  });
+
+  afterEach(async () => {
+    db.close();
+    await rm(workDir, { recursive: true, force: true });
+  });
+
+  function makeWorker(
+    generate: (input: Parameters<InferenceProvider['generate']>[0], opts?: Parameters<InferenceProvider['generate']>[1]) => Promise<AiResponse>,
+    getVisionModel: () => Promise<string | null>
+  ): AiWorker {
+    const provider: InferenceProvider = {
+      name: 'fake',
+      generate,
+      abort: () => {},
+      healthCheck: vi.fn(async () => ({ ok: true }))
+    };
+    const holder = new ProviderHolder(provider);
+    const settings = { getVisionModel };
+    const logger = { info: vi.fn(), warn: vi.fn(), error: vi.fn() };
+    return new AiWorker(repo, holder, {
+      backoffsMs: [0, 0, 0],
+      logger,
+      settings,
+      mediaStore,
+      now: () => new Date('2026-05-10T05:00:00Z')
+    });
+  }
+
+  it('visionModel + media 있음 → provider.generate 가 images + opts 받음', async () => {
+    const { id } = repo.create({ rawText: '이미지 메모' });
+    await mkdir(join(workDir, 'media', id), { recursive: true });
+    await writeFile(join(workDir, 'media', id, '1.png'), Buffer.from([0x89, 0x50, 0x4e, 0x47]));
+    repo.insertMedia([{ noteId: id, kind: 'image', relPath: `media/${id}/1.png`, mime: 'image/png', bytes: 4 }]);
+
+    const calls: Array<Parameters<InferenceProvider['generate']>> = [];
+    const generate = vi.fn(async (
+      input: Parameters<InferenceProvider['generate']>[0],
+      opts?: Parameters<InferenceProvider['generate']>[1]
+    ): Promise<AiResponse> => {
+      calls.push([input, opts]);
+      return { title: 't', summary: 'a\nb\nc', tags: [], dueDate: null };
+    });
+    const getVisionModel = vi.fn(async (): Promise<string | null> => 'gemma3:12b-vision');
+    const worker = makeWorker(generate, getVisionModel);
+    await worker.enqueue(id);
+    await worker.drain();
+
+    expect(calls.length).toBeGreaterThan(0);
+    const [callInput, callOpts] = calls[0]!;
+    expect(callInput.images).toHaveLength(1);
+    expect(callInput.images![0]!.mime).toBe('image/png');
+    expect(callOpts?.visionModel).toBe('gemma3:12b-vision');
+  });
+
+  it('visionModel null이면 text-only (images undefined)', async () => {
+    const { id } = repo.create({ rawText: 'just text' });
+    const calls: Array<Parameters<InferenceProvider['generate']>> = [];
+    const generate = vi.fn(async (
+      input: Parameters<InferenceProvider['generate']>[0],
+      opts?: Parameters<InferenceProvider['generate']>[1]
+    ): Promise<AiResponse> => {
+      calls.push([input, opts]);
+      return { title: 't', summary: 'a\nb\nc', tags: [], dueDate: null };
+    });
+    const getVisionModel = vi.fn(async (): Promise<string | null> => null);
+    const worker = makeWorker(generate, getVisionModel);
+    await worker.enqueue(id);
+    await worker.drain();
+
+    expect(calls.length).toBeGreaterThan(0);
+    expect(calls[0]![0].images).toBeUndefined();
+  });
+
+  it('5MB 초과 이미지 → throw → AiWorker 의 fail 분기 (generate 미호출)', async () => {
+    const { id } = repo.create({ rawText: 'big image' });
+    await mkdir(join(workDir, 'media', id), { recursive: true });
+    await writeFile(join(workDir, 'media', id, '1.png'), Buffer.alloc(6 * 1024 * 1024));
+    repo.insertMedia([{ noteId: id, kind: 'image', relPath: `media/${id}/1.png`, mime: 'image/png', bytes: 6 * 1024 * 1024 }]);
+
+    const calls: Array<Parameters<InferenceProvider['generate']>> = [];
+    const generate = vi.fn(async (
+      input: Parameters<InferenceProvider['generate']>[0],
+      opts?: Parameters<InferenceProvider['generate']>[1]
+    ): Promise<AiResponse> => {
+      calls.push([input, opts]);
+      return { title: 't', summary: 'a\nb\nc', tags: [], dueDate: null };
+    });
+    const getVisionModel = vi.fn(async (): Promise<string | null> => 'gemma3:12b-vision');
+    const worker = makeWorker(generate, getVisionModel);
+    await worker.enqueue(id);
+    await worker.drain();
+
+    expect(calls.length).toBe(0);
+    // AiWorker catch 분기가 처리 — note 는 여전히 DB 에 존재
+    const note = repo.findById(id);
+    expect(note).toBeTruthy();
+  });
+});