feat(retry): AiWorker unreachable/timeout 무한 retry — 15분 cap (#2 v0.2.3)

src/main/ai/AiWorker.ts

@@ -37,6 +37,7 @@ export interface AiTelemetryEmitter {
 
 export interface AiWorkerOptions {
   backoffsMs?: number[];
+  unreachableBackoffsMs?: number[];
   onUpdate?: (note: Note) => void;
   logger?: {
     info: (msg: string, meta?: Record<string, unknown>) => void;
@@ -54,6 +55,8 @@ export class AiWorker {
   private running = false;
   private drainResolvers: Array<() => void> = [];
   private backoffsMs: number[];
+  private unreachableBackoffsMs: number[];
+  private unreachableBackoffStep = 0;
   private onUpdate?: (note: Note) => void;
   private logger: NonNullable<AiWorkerOptions['logger']>;
   private now: () => Date;
@@ -65,6 +68,7 @@ export class AiWorker {
     opts: AiWorkerOptions = {}
   ) {
     this.backoffsMs = opts.backoffsMs ?? [0, 30_000, 120_000];
+    this.unreachableBackoffsMs = opts.unreachableBackoffsMs ?? [30_000, 60_000, 120_000, 240_000, 480_000, 900_000];
     this.onUpdate = opts.onUpdate;
     this.logger = opts.logger ?? { info: () => {}, warn: () => {}, error: () => {} };
     this.now = opts.now ?? (() => new Date());
@@ -139,6 +143,7 @@ export class AiWorker {
           provider: this.provider.name,
           dueDate: res.dueDate ?? null
         });
+        this.unreachableBackoffStep = 0;  // 성공 시 step reset
         this.logger.info('ai.done', {
           noteId: job.noteId,
           attempt,
@@ -158,9 +163,22 @@ export class AiWorker {
         this.emit(job.noteId);
         return;
       } catch (err) {
-        const isLast = attempt === max - 1;
+        const reason = classifyReason(err);
         const msg = (err as Error).message;
-        this.logger.warn('ai.retry', { noteId: job.noteId, attempt, err: msg });
+        this.logger.warn('ai.retry', { noteId: job.noteId, attempt, err: msg, reason });
+        if (reason === 'unreachable' || reason === 'timeout') {
+          // 무한 retry: attempts 증가 안 함, in-place loop + sleep.
+          // markAiFailed / ai_failed emit 안 함 — ratio 통계는 schema/other 만 누적.
+          const sleepMs = this.nextBackoffMs(this.unreachableBackoffStep);
+          this.unreachableBackoffStep = Math.min(this.unreachableBackoffStep + 1, this.unreachableBackoffsMs.length - 1);
+          const nextRunAt = new Date(Date.now() + sleepMs).toISOString();
+          this.repo.setNextRunAt(job.noteId, nextRunAt, msg);
+          await this.sleep(sleepMs);
+          attempt -= 1;  // for 루프 attempt++ 상쇄 — 같은 attempt 인덱스로 재시도
+          continue;
+        }
+        // schema / other: 기존 max 3 retry 정책
+        const isLast = attempt === max - 1;
         const nextRunAt = new Date(Date.now() + (this.backoffsMs[attempt + 1] ?? 0)).toISOString();
         this.repo.incrementJobAttempt(job.noteId, nextRunAt, msg);
         if (isLast) {
@@ -171,7 +189,7 @@ export class AiWorker {
               kind: 'ai_failed',
               payload: {
                 noteId: job.noteId,
-                reason: classifyReason(err),
+                reason,
                 attempts: attempt + 1
               }
             }).catch(() => {});
@@ -184,6 +202,11 @@ export class AiWorker {
     }
   }
 
+  private nextBackoffMs(step: number): number {
+    const idx = Math.min(step, this.unreachableBackoffsMs.length - 1);
+    return this.unreachableBackoffsMs[idx]!;
+  }
+
   private emit(noteId: string): void {
     if (!this.onUpdate) return;
     const note = this.repo.findById(noteId);