feat(gmw): moderation explainability + semantic message search

- Persist structured verdict (flags/severity/confidence/evidence) on
  moderation_actions so the public web can show WHY a message was moderated.
- Add a persistent Qdrant archive collection (gmw_message_archive); embed
  every captured message at capture time (fire-and-forget, best-effort).
- Public semantic search over the archive (backend oRPC + FE toggle on the
  messages view). Both features are read-only/public and fully automatic.

Migration: 0015_add_moderation_explainability.sql

services/backend/src/modules/messages/embed.ts

@@ -0,0 +1,43 @@
+import { config } from "@/shared/config/index.js";
+import { createChildLogger } from "@/shared/logger/index.js";
+
+const logger = createChildLogger("messages-embed");
+
+/**
+ * Embed a search query with the configured OpenAI-compatible embedding model.
+ * Uses raw fetch (the backend has no openai SDK dependency) and returns null
+ * when embeddings are not configured (search unavailable).
+ *
+ * encoding_format: "float" is REQUIRED — Nvidia-backed models reject base64.
+ */
+export async function embedQuery(text: string): Promise<number[] | null> {
+  if (!config.AI_LLM_API_KEY || !config.AI_LLM_EMBEDDING_MODEL) return null;
+  try {
+    const res = await fetch(`${config.AI_LLM_BASE_URL}/embeddings`, {
+      method: "POST",
+      headers: {
+        "Content-Type": "application/json",
+        Authorization: `Bearer ${config.AI_LLM_API_KEY}`,
+      },
+      body: JSON.stringify({
+        model: config.AI_LLM_EMBEDDING_MODEL,
+        input: text,
+        encoding_format: "float",
+      }),
+    });
+    if (!res.ok) {
+      logger.warn({ status: res.status }, "query embed HTTP error");
+      return null;
+    }
+    const json = (await res.json()) as {
+      data?: Array<{ embedding?: number[] }>;
+    };
+    return json.data?.[0]?.embedding ?? null;
+  } catch (error) {
+    logger.warn(
+      { error: error instanceof Error ? error.message : String(error) },
+      "query embed failed",
+    );
+    return null;
+  }
+}

services/backend/src/modules/messages/messages.schema.ts

@@ -41,3 +41,11 @@ export const messageUpdateSchema = z.object({
 export type MessageQuery = z.infer<typeof messageQuerySchema>;
 export type MessageCreate = z.infer<typeof messageCreateSchema>;
 export type MessageUpdate = z.infer<typeof messageUpdateSchema>;
+
+export const semanticSearchSchema = z.object({
+  query: z.string().min(1).max(500),
+  limit: z.coerce.number().int().positive().max(50).default(10),
+  guildId: z.string().optional(),
+});
+
+export type SemanticSearchQuery = z.infer<typeof semanticSearchSchema>;

services/backend/src/modules/messages/messages.service.ts

@@ -1,7 +1,9 @@
 import { NotFoundError, ValidationError } from "@/shared/errors/index";
 import { createChildLogger } from "@/shared/logger/index";
+import { embedQuery } from "./embed.js";
 import { messagesRepository } from "./messages.repository.js";
-import type { MessageQuery } from "./messages.schema.js";
+import type { MessageQuery, SemanticSearchQuery } from "./messages.schema.js";
+import { searchArchive } from "./qdrant.js";
 
 const logger = createChildLogger("messages.service");
 
@@ -78,6 +80,40 @@ export class MessagesService {
     logger.debug({ channelId, limit }, "Getting review messages");
     return messagesRepository.getReviewMessages(channelId, limit);
   }
+
+  /**
+   * Public, read-only semantic search over the persistent message archive.
+   * Embeds the query, searches Qdrant, returns text + metadata. Best-effort:
+   * if embeddings/Qdrant are unavailable, returns an empty result set.
+   */
+  async semanticSearch(
+    input: SemanticSearchQuery,
+  ): Promise<{ results: ReturnType<typeof mapSearchHit>[]; nextCursor: null }> {
+    const vector = await embedQuery(input.query);
+    if (!vector) {
+      logger.debug(
+        { query: input.query },
+        "semantic search skipped: no embedder",
+      );
+      return { results: [], nextCursor: null };
+    }
+    const hits = await searchArchive(vector, input.limit, 0.6);
+    const results = hits.map((h) => mapSearchHit(h));
+    return { results, nextCursor: null };
+  }
+}
+
+/** Shape returned to the frontend (text + metadata from the archive payload). */
+function mapSearchHit(hit: {
+  score: number;
+  payload: { text: string; content_hash?: string; analyzed_at: number };
+}) {
+  return {
+    message_id: hit.payload.content_hash ?? null,
+    content: hit.payload.text,
+    score: hit.score,
+    created_at: hit.payload.analyzed_at,
+  };
 }
 
 export const messagesService = new MessagesService();

services/backend/src/modules/messages/qdrant.ts

@@ -0,0 +1,95 @@
+import { config } from "@/shared/config/index.js";
+import { createChildLogger } from "@/shared/logger/index.js";
+
+const logger = createChildLogger("messages-qdrant");
+
+export interface ArchiveHit {
+  score: number;
+  payload: {
+    text: string;
+    content_hash?: string;
+    analyzed_at: number;
+    expires_at: number;
+  };
+}
+
+function baseUrl(): string {
+  return (config.QDRANT_URL ?? "http://100.121.180.82:6333").replace(
+    /\/+$/,
+    "",
+  );
+}
+
+function headers(): Record<string, string> {
+  const h: Record<string, string> = { "Content-Type": "application/json" };
+  if (config.QDRANT_API_KEY) h["api-key"] = config.QDRANT_API_KEY;
+  return h;
+}
+
+export const ARCHIVE_COLLECTION =
+  config.QDRANT_ARCHIVE_COLLECTION ?? "gmw_message_archive";
+
+async function request(
+  method: string,
+  path: string,
+  body?: unknown,
+  timeoutMs = 10_000,
+): Promise<unknown> {
+  const controller = new AbortController();
+  const timer = setTimeout(() => controller.abort(), timeoutMs);
+  try {
+    const res = await fetch(`${baseUrl()}${path}`, {
+      method,
+      headers: headers(),
+      body: body === undefined ? undefined : JSON.stringify(body),
+      signal: controller.signal,
+    });
+    const text = await res.text();
+    if (!res.ok) {
+      throw new Error(
+        `Qdrant ${method} ${path} -> ${res.status}: ${text.slice(0, 200)}`,
+      );
+    }
+    return text ? JSON.parse(text) : null;
+  } finally {
+    clearTimeout(timer);
+  }
+}
+
+/** Search the archive collection for the nearest vectors to `vector`. */
+export async function searchArchive(
+  vector: number[],
+  limit: number,
+  scoreThreshold: number,
+): Promise<ArchiveHit[]> {
+  if (!config.QDRANT_URL) return [];
+  try {
+    const json = (await request(
+      "POST",
+      `/collections/${ARCHIVE_COLLECTION}/points/search`,
+      {
+        vector,
+        limit,
+        score_threshold: scoreThreshold,
+        with_payload: true,
+      },
+    )) as {
+      result?: Array<{
+        score?: number;
+        payload?: ArchiveHit["payload"];
+      }>;
+    };
+    return (json.result ?? [])
+      .filter((h) => h.payload?.text)
+      .map((h) => ({
+        score: h.score ?? 0,
+        payload: h.payload as ArchiveHit["payload"],
+      }));
+  } catch (error) {
+    logger.warn(
+      { error: error instanceof Error ? error.message : String(error) },
+      "archive search failed",
+    );
+    return [];
+  }
+}

services/backend/src/modules/moderation/moderation.repository.ts

@@ -17,6 +17,20 @@ const ACTION_TYPES = [
 ] as const;
 const STATUSES = ["pending", "executed", "failed"] as const;
 
+/** Parse a JSON-stringified array column (e.g. flags/categories/evidence).
+ *  Returns null on empty/malformed input so the FE can treat it as "no data". */
+function parseJsonArray(value: unknown): string[] | null {
+  if (value == null) return null;
+  const str = typeof value === "string" ? value : String(value);
+  if (str.length === 0) return null;
+  try {
+    const parsed = JSON.parse(str);
+    return Array.isArray(parsed) ? (parsed as string[]) : null;
+  } catch {
+    return null;
+  }
+}
+
 export class ModerationRepository {
   async getStats() {
     const db = getDatabase();
@@ -103,6 +117,13 @@ export class ModerationRepository {
         a.error,
         a.created_at,
         a.executed_at,
+        a.flags,
+        a.categories,
+        a.severity,
+        a.confidence,
+        a.score,
+        a.evidence,
+        a.policy_version,
         m.username,
         LEFT(m.content, 300) AS content
       FROM moderation_actions a
@@ -126,6 +147,13 @@ export class ModerationRepository {
       error: r.error ? String(r.error) : null,
       created_at: r.created_at ? Number(r.created_at) : null,
       executed_at: r.executed_at ? Number(r.executed_at) : null,
+      flags: parseJsonArray(r.flags),
+      categories: parseJsonArray(r.categories),
+      severity: r.severity ? String(r.severity) : null,
+      confidence: r.confidence != null ? Number(r.confidence) : null,
+      score: r.score != null ? Number(r.score) : null,
+      evidence: parseJsonArray(r.evidence),
+      policy_version: r.policy_version ? String(r.policy_version) : null,
       username: r.username ? String(r.username) : null,
       content: r.content ? String(r.content) : null,
     }));

services/backend/src/orpc/router.ts

@@ -16,7 +16,10 @@ import {
   skip,
   stop,
 } from "../modules/media/media.service";
-import { messageQuerySchema } from "../modules/messages/messages.schema";
+import {
+  messageQuerySchema,
+  semanticSearchSchema,
+} from "../modules/messages/messages.schema";
 import { messagesService } from "../modules/messages/messages.service";
 import { moderationService } from "../modules/moderation/moderation.service";
 import { recordingsService } from "../modules/recordings/recordings.service";
@@ -136,6 +139,10 @@ const messagesRouter = {
       );
       return { results: rows, limit: input.limit, cursor: null };
     }),
+  // Public, read-only semantic search over the message archive.
+  semanticSearch: os
+    .input(semanticSearchSchema)
+    .handler(({ input }) => messagesService.semanticSearch(input)),
 };
 
 // ── Moderation ───────────────────────────────────────────────────

services/backend/src/shared/config/index.ts

@@ -134,6 +134,7 @@ export const configSchema = z
       .default("https://9router.asepharyana.my.id/v1"),
     AI_LLM_MODEL: z.string().default("text"),
     AI_LLM_VISION_MODEL: z.string().optional(),
+    AI_LLM_EMBEDDING_MODEL: z.string().optional(),
     AI_LLM_MAX_CONCURRENT: z.coerce.number().int().positive().default(5),
     AI_LLM_IMAGE_MAX_DIMENSION: z.coerce
       .number()
@@ -208,6 +209,11 @@ export const configSchema = z
       .default("https://api.openai.com/v1"),
     OPENAI_MODERATION_MODEL: z.string().default("omni-moderation-latest"),
 
+    // ── Qdrant (message archive for semantic search) ──────────────────
+    QDRANT_URL: z.string().optional(),
+    QDRANT_API_KEY: z.string().optional(),
+    QDRANT_ARCHIVE_COLLECTION: z.string().default("gmw_message_archive"),
+
     // ── Auto Delete ─────────────────────────────────────────────────────
     AUTO_DELETE_FLAGGED_ENABLED: z
       .string()