add hermes agent provider

server/src/llm/multiplexer.ts

@@ -1,13 +1,13 @@
 import { performance } from "node:perf_hooks";
 import { prisma } from "../db.js";
-import { anthropicClient, openaiClient, xaiClient } from "./providers.js";
-import { buildToolLogMessageData, runToolAwareChatCompletions, runToolAwareOpenAIChat } from "./chat-tools.js";
+import { anthropicClient, hermesAgentClient, openaiClient, xaiClient } from "./providers.js";
+import { buildToolLogMessageData, runPlainChatCompletions, runToolAwareChatCompletions, runToolAwareOpenAIChat } from "./chat-tools.js";
 import { buildAnthropicConversationMessage, getAnthropicSystemPrompt } from "./message-content.js";
+import { toPrismaProvider } from "./provider-ids.js";
 import type { MultiplexRequest, MultiplexResponse, Provider } from "./types.js";
 
 function asProviderEnum(p: Provider) {
-  // Prisma enum values match these strings.
-  return p;
+  return toPrismaProvider(p);
 }
 
 export async function runMultiplex(req: MultiplexRequest): Promise<MultiplexResponse> {
@@ -84,6 +84,23 @@ export async function runMultiplex(req: MultiplexRequest): Promise<MultiplexResp
       outText = r.text;
       usage = r.usage;
       toolMessages = r.toolEvents.map((event) => buildToolLogMessageData(call.chatId, event));
+    } else if (req.provider === "hermes-agent") {
+      const client = hermesAgentClient();
+      const r = await runPlainChatCompletions({
+        client,
+        model: req.model,
+        messages: req.messages,
+        temperature: req.temperature,
+        maxTokens: req.maxTokens,
+        logContext: {
+          provider: req.provider,
+          model: req.model,
+          chatId,
+        },
+      });
+      raw = r.raw;
+      outText = r.text;
+      usage = r.usage;
     } else if (req.provider === "anthropic") {
       const client = anthropicClient();