feat(#383): Streaming AI responses via Matrix message edits

- Add MatrixStreamingService with editMessage, setTypingIndicator, streamResponse
- Rate-limited edits (500ms) for incremental streaming output
- Typing indicator management during generation
- Graceful error handling and fallback for non-streaming scenarios
- Add optional editMessage to IChatProvider interface
- Add getClient() accessor to MatrixService for streaming service
- Register MatrixStreamingService in BridgeModule
- Tests: 20 tests pass

Refs #383

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

apps/api/src/bridge/bridge.module.ts

@@ -2,6 +2,7 @@ import { Logger, Module } from "@nestjs/common";
 import { DiscordService } from "./discord/discord.service";
 import { MatrixService } from "./matrix/matrix.service";
 import { MatrixRoomService } from "./matrix/matrix-room.service";
+import { MatrixStreamingService } from "./matrix/matrix-streaming.service";
 import { CommandParserService } from "./parser/command-parser.service";
 import { StitcherModule } from "../stitcher/stitcher.module";
 import { CHAT_PROVIDERS } from "./bridge.constants";
@@ -31,6 +32,7 @@ const logger = new Logger("BridgeModule");
   providers: [
     CommandParserService,
     MatrixRoomService,
+    MatrixStreamingService,
     DiscordService,
     MatrixService,
     {
@@ -57,6 +59,13 @@ const logger = new Logger("BridgeModule");
       inject: [DiscordService, MatrixService],
     },
   ],
-  exports: [DiscordService, MatrixService, MatrixRoomService, CommandParserService, CHAT_PROVIDERS],
+  exports: [
+    DiscordService,
+    MatrixService,
+    MatrixRoomService,
+    MatrixStreamingService,
+    CommandParserService,
+    CHAT_PROVIDERS,
+  ],
 })
 export class BridgeModule {}