From 47e7e8e5499097a915776ba795328ab26072186c Mon Sep 17 00:00:00 2001
From: MythEclipse <asepharyanalm001@gmail.com>
Date: Sun, 31 May 2026 20:57:01 +0700
Subject: [PATCH] feat(moderation): implement media analysis caching with
 deterministic keys and database integration

---
 src/moderation/llmModerationClient.ts | 28 +++++++++
 src/moderation/textCacheStore.ts      | 83 +++++++++++++++++++++++++++
 2 files changed, 111 insertions(+)

diff --git a/src/moderation/llmModerationClient.ts b/src/moderation/llmModerationClient.ts
index 0fb469c..d9d0ddc 100644
--- a/src/moderation/llmModerationClient.ts
+++ b/src/moderation/llmModerationClient.ts
@@ -16,6 +16,12 @@ import {
   buildStickerTextOnlyWarning,
   buildStickerVisionPrompt,
 } from "./stickerPrompt.js";
+import {
+  getCachedMediaAnalysis,
+  makeImageCacheKey,
+  makeStickerCacheKey,
+  upsertCachedMediaAnalysis,
+} from "./textCacheStore.js";
 import type {
   AnalysisResult,
   AttachmentRecord,
@@ -767,6 +773,19 @@ export async function runModerationAnalysis(
     messageId: string,
     image: MessageImagePart,
   ): Promise<string | null> => {
+    // ── Build deterministic cache key ──
+    const cacheKey = image.stickerName
+      ? makeStickerCacheKey(image.stickerName)
+      : makeImageCacheKey(image.image_url.url);
+
+    // ── Tier 1: DB cache lookup ──
+    const cached = await getCachedMediaAnalysis(cacheKey);
+    if (cached) {
+      log.debug({ cacheKey }, "Media analysis cache HIT");
+      return `[Media analysis for message ${messageId}] ${image.sourceLabel}: ${cached}`;
+    }
+
+    // ── Tier 2: Vision API call ──
     try {
       const completion = await openai.chat.completions.create({
         model: config.AI_LLM_VISION_MODEL ?? config.AI_LLM_MODEL,
@@ -794,6 +813,15 @@ export async function runModerationAnalysis(
 
       const content = completion.choices[0]?.message?.content?.trim();
       if (!content) return null;
+
+      // ── Cache the result (24h TTL, strips messageId wrapper) ──
+      await upsertCachedMediaAnalysis(
+        cacheKey,
+        content,
+        "vision_llm",
+        Date.now() + 24 * 60 * 60 * 1000,
+      );
+
       return `[Media analysis for message ${messageId}] ${image.sourceLabel}: ${content}`;
     } catch (error) {
       log.warn(
diff --git a/src/moderation/textCacheStore.ts b/src/moderation/textCacheStore.ts
index fe99802..e1c0046 100644
--- a/src/moderation/textCacheStore.ts
+++ b/src/moderation/textCacheStore.ts
@@ -1,3 +1,4 @@
+import { createHash } from "node:crypto";
 import { executeAll, executeGet } from "../database/drizzle.js";
 import { createChildLogger } from "../logger.js";
 
@@ -149,3 +150,85 @@ export async function getTextCacheStats(): Promise<{
     return { total: 0, expired: 0, bySource: {} };
   }
 }
+
+// ---------------------------------------------------------------------------
+// Media / Vision analysis cache helpers (reuses text_analysis_cache table)
+// ---------------------------------------------------------------------------
+
+/**
+ * Generate a deterministic cache key for a sticker.
+ * Same sticker name → same key across sessions and servers.
+ */
+export function makeStickerCacheKey(stickerName: string): string {
+  return `sticker:${stickerName}`;
+}
+
+/**
+ * Generate a deterministic cache key for an image data URL.
+ * Hashes the first 128 chars of the data URL (enough to identify the image
+ * without storing the full base64 string as the key).
+ */
+export function makeImageCacheKey(dataUrl: string): string {
+  const prefix = dataUrl.slice(0, 128);
+  const hash = createHash("sha256").update(prefix).digest("hex").slice(0, 16);
+  return `image:${hash}`;
+}
+
+/**
+ * Lookup a cached media analysis result.
+ * Returns the full cached text (the analysis summary string) or null.
+ */
+export async function getCachedMediaAnalysis(
+  cacheKey: string,
+): Promise<string | null> {
+  try {
+    const row = await executeGet(
+      `SELECT flags, hit_count
+       FROM text_analysis_cache
+       WHERE text = $1 AND expires_at > $2`,
+      [cacheKey, Date.now()],
+    );
+
+    if (!row) return null;
+
+    // flags stores the analysis result for media entries
+    const result = JSON.parse(row.flags) as string;
+    return result || null;
+  } catch (error) {
+    logger.error(
+      { error: error instanceof Error ? error.message : String(error) },
+      "Failed to get cached media analysis",
+    );
+    return null;
+  }
+}
+
+/**
+ * Store a media analysis result in the cache.
+ */
+export async function upsertCachedMediaAnalysis(
+  cacheKey: string,
+  analysisResult: string,
+  source: "vision_llm",
+  expiresAt: number,
+): Promise<void> {
+  const now = Date.now();
+
+  try {
+    await executeAll(
+      `INSERT INTO text_analysis_cache (text, flags, source, analyzed_at, expires_at, hit_count)
+       VALUES ($1, $2, $3, $4, $5, 0)
+       ON CONFLICT (text) DO UPDATE SET
+         flags = EXCLUDED.flags,
+         source = EXCLUDED.source,
+         analyzed_at = EXCLUDED.analyzed_at,
+         expires_at = EXCLUDED.expires_at`,
+      [cacheKey, JSON.stringify(analysisResult), source, now, expiresAt],
+    );
+  } catch (error) {
+    logger.error(
+      { error: error instanceof Error ? error.message : String(error) },
+      "Failed to upsert cached media analysis",
+    );
+  }
+}