merge: resolve conflicts with develop (telemetry + lockfile)

Keep both Mosaic Telemetry section (from develop) and Matrix Dev
Environment section (from feature branch) in .env.example.
Regenerate pnpm-lock.yaml with both dependency trees merged.

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

apps/api/src/llm/llm.service.spec.ts

@@ -3,6 +3,7 @@ import { Test, TestingModule } from "@nestjs/testing";
 import { ServiceUnavailableException } from "@nestjs/common";
 import { LlmService } from "./llm.service";
 import { LlmManagerService } from "./llm-manager.service";
+import { LlmTelemetryTrackerService } from "./llm-telemetry-tracker.service";
 import type { ChatRequestDto, EmbedRequestDto, ChatResponseDto, EmbedResponseDto } from "./dto";
 import type {
   LlmProviderInterface,
@@ -14,6 +15,9 @@ describe("LlmService", () => {
   let mockManagerService: {
     getDefaultProvider: ReturnType<typeof vi.fn>;
   };
+  let mockTelemetryTracker: {
+    trackLlmCompletion: ReturnType<typeof vi.fn>;
+  };
   let mockProvider: {
     chat: ReturnType<typeof vi.fn>;
     chatStream: ReturnType<typeof vi.fn>;
@@ -41,6 +45,11 @@ describe("LlmService", () => {
       getDefaultProvider: vi.fn().mockResolvedValue(mockProvider),
     };
 
+    // Create mock telemetry tracker
+    mockTelemetryTracker = {
+      trackLlmCompletion: vi.fn(),
+    };
+
     const module: TestingModule = await Test.createTestingModule({
       providers: [
         LlmService,
@@ -48,6 +57,10 @@ describe("LlmService", () => {
           provide: LlmManagerService,
           useValue: mockManagerService,
         },
+        {
+          provide: LlmTelemetryTrackerService,
+          useValue: mockTelemetryTracker,
+        },
       ],
     }).compile();
 
@@ -135,6 +148,45 @@ describe("LlmService", () => {
       expect(result).toEqual(response);
     });
 
+    it("should track telemetry on successful chat", async () => {
+      const response: ChatResponseDto = {
+        model: "llama3.2",
+        message: { role: "assistant", content: "Hello" },
+        done: true,
+        promptEvalCount: 10,
+        evalCount: 20,
+      };
+      mockProvider.chat.mockResolvedValue(response);
+
+      await service.chat(request, "chat");
+
+      expect(mockTelemetryTracker.trackLlmCompletion).toHaveBeenCalledWith(
+        expect.objectContaining({
+          model: "llama3.2",
+          providerType: "ollama",
+          operation: "chat",
+          inputTokens: 10,
+          outputTokens: 20,
+          callingContext: "chat",
+          success: true,
+        })
+      );
+    });
+
+    it("should track telemetry on failed chat", async () => {
+      mockProvider.chat.mockRejectedValue(new Error("Chat failed"));
+
+      await expect(service.chat(request)).rejects.toThrow(ServiceUnavailableException);
+
+      expect(mockTelemetryTracker.trackLlmCompletion).toHaveBeenCalledWith(
+        expect.objectContaining({
+          model: "llama3.2",
+          operation: "chat",
+          success: false,
+        })
+      );
+    });
+
     it("should throw ServiceUnavailableException on error", async () => {
       mockProvider.chat.mockRejectedValue(new Error("Chat failed"));
 
@@ -177,6 +229,94 @@ describe("LlmService", () => {
       expect(chunks[1].message.content).toBe(" world");
     });
 
+    it("should track telemetry after stream completes", async () => {
+      async function* mockGenerator(): AsyncGenerator<ChatResponseDto> {
+        yield {
+          model: "llama3.2",
+          message: { role: "assistant", content: "Hello" },
+          done: false,
+        };
+        yield {
+          model: "llama3.2",
+          message: { role: "assistant", content: " world" },
+          done: true,
+          promptEvalCount: 5,
+          evalCount: 10,
+        };
+      }
+
+      mockProvider.chatStream.mockReturnValue(mockGenerator());
+
+      const chunks: ChatResponseDto[] = [];
+      for await (const chunk of service.chatStream(request, "brain")) {
+        chunks.push(chunk);
+      }
+
+      expect(mockTelemetryTracker.trackLlmCompletion).toHaveBeenCalledWith(
+        expect.objectContaining({
+          model: "llama3.2",
+          providerType: "ollama",
+          operation: "chatStream",
+          inputTokens: 5,
+          outputTokens: 10,
+          callingContext: "brain",
+          success: true,
+        })
+      );
+    });
+
+    it("should estimate tokens when provider does not return counts in stream", async () => {
+      async function* mockGenerator(): AsyncGenerator<ChatResponseDto> {
+        yield {
+          model: "llama3.2",
+          message: { role: "assistant", content: "Hello world" },
+          done: false,
+        };
+        yield {
+          model: "llama3.2",
+          message: { role: "assistant", content: "" },
+          done: true,
+        };
+      }
+
+      mockProvider.chatStream.mockReturnValue(mockGenerator());
+
+      const chunks: ChatResponseDto[] = [];
+      for await (const chunk of service.chatStream(request)) {
+        chunks.push(chunk);
+      }
+
+      // Should use estimated tokens since no actual counts provided
+      expect(mockTelemetryTracker.trackLlmCompletion).toHaveBeenCalledWith(
+        expect.objectContaining({
+          operation: "chatStream",
+          success: true,
+          // Input estimated from "Hi" -> ceil(2/4) = 1
+          inputTokens: 1,
+          // Output estimated from "Hello world" -> ceil(11/4) = 3
+          outputTokens: 3,
+        })
+      );
+    });
+
+    it("should track telemetry on stream failure", async () => {
+      async function* errorGenerator(): AsyncGenerator<ChatResponseDto> {
+        throw new Error("Stream failed");
+      }
+
+      mockProvider.chatStream.mockReturnValue(errorGenerator());
+
+      const generator = service.chatStream(request);
+      await expect(generator.next()).rejects.toThrow(ServiceUnavailableException);
+
+      expect(mockTelemetryTracker.trackLlmCompletion).toHaveBeenCalledWith(
+        expect.objectContaining({
+          operation: "chatStream",
+          success: false,
+        })
+      );
+    });
+
     it("should throw ServiceUnavailableException on error", async () => {
       async function* errorGenerator(): AsyncGenerator<ChatResponseDto> {
         throw new Error("Stream failed");
@@ -210,6 +350,41 @@ describe("LlmService", () => {
       expect(result).toEqual(response);
     });
 
+    it("should track telemetry on successful embed", async () => {
+      const response: EmbedResponseDto = {
+        model: "llama3.2",
+        embeddings: [[0.1, 0.2, 0.3]],
+        totalDuration: 500,
+      };
+      mockProvider.embed.mockResolvedValue(response);
+
+      await service.embed(request, "embed");
+
+      expect(mockTelemetryTracker.trackLlmCompletion).toHaveBeenCalledWith(
+        expect.objectContaining({
+          model: "llama3.2",
+          providerType: "ollama",
+          operation: "embed",
+          outputTokens: 0,
+          callingContext: "embed",
+          success: true,
+        })
+      );
+    });
+
+    it("should track telemetry on failed embed", async () => {
+      mockProvider.embed.mockRejectedValue(new Error("Embedding failed"));
+
+      await expect(service.embed(request)).rejects.toThrow(ServiceUnavailableException);
+
+      expect(mockTelemetryTracker.trackLlmCompletion).toHaveBeenCalledWith(
+        expect.objectContaining({
+          operation: "embed",
+          success: false,
+        })
+      );
+    });
+
     it("should throw ServiceUnavailableException on error", async () => {
       mockProvider.embed.mockRejectedValue(new Error("Embedding failed"));