add hermes agent provider

server/src/llm/streaming.ts

@@ -1,13 +1,15 @@
 import { performance } from "node:perf_hooks";
 import { prisma } from "../db.js";
-import { anthropicClient, openaiClient, xaiClient } from "./providers.js";
+import { anthropicClient, hermesAgentClient, openaiClient, xaiClient } from "./providers.js";
 import {
   buildToolLogMessageData,
+  runPlainChatCompletionsStream,
   runToolAwareChatCompletionsStream,
   runToolAwareOpenAIChatStream,
   type ToolExecutionEvent,
 } from "./chat-tools.js";
 import { buildAnthropicConversationMessage, getAnthropicSystemPrompt } from "./message-content.js";
+import { toPrismaProvider } from "./provider-ids.js";
 import type { MultiplexRequest, Provider } from "./types.js";
 
 type StreamUsage = {
@@ -38,7 +40,7 @@ export async function* runMultiplexStream(req: MultiplexRequest): AsyncGenerator
       ? await prisma.llmCall.create({
           data: {
             chatId,
-            provider: req.provider as any,
+            provider: toPrismaProvider(req.provider) as any,
             model: req.model,
             request: req as any,
           },
@@ -51,14 +53,14 @@ export async function* runMultiplexStream(req: MultiplexRequest): AsyncGenerator
       prisma.chat.update({
         where: { id: chatId },
         data: {
-          lastUsedProvider: req.provider as any,
+          lastUsedProvider: toPrismaProvider(req.provider) as any,
           lastUsedModel: req.model,
         },
       }),
       prisma.chat.updateMany({
         where: { id: chatId, initiatedProvider: null },
         data: {
-          initiatedProvider: req.provider as any,
+          initiatedProvider: toPrismaProvider(req.provider) as any,
           initiatedModel: req.model,
         },
       }),
@@ -72,8 +74,8 @@ export async function* runMultiplexStream(req: MultiplexRequest): AsyncGenerator
   let raw: unknown = { streamed: true };
 
   try {
-    if (req.provider === "openai" || req.provider === "xai") {
-      const client = req.provider === "openai" ? openaiClient() : xaiClient();
+    if (req.provider === "openai" || req.provider === "xai" || req.provider === "hermes-agent") {
+      const client = req.provider === "openai" ? openaiClient() : req.provider === "xai" ? xaiClient() : hermesAgentClient();
       const streamEvents =
         req.provider === "openai"
           ? runToolAwareOpenAIChatStream({
@@ -88,6 +90,19 @@ export async function* runMultiplexStream(req: MultiplexRequest): AsyncGenerator
                 chatId: chatId ?? undefined,
               },
             })
+          : req.provider === "hermes-agent"
+            ? runPlainChatCompletionsStream({
+                client,
+                model: req.model,
+                messages: req.messages,
+                temperature: req.temperature,
+                maxTokens: req.maxTokens,
+                logContext: {
+                  provider: req.provider,
+                  model: req.model,
+                  chatId: chatId ?? undefined,
+                },
+              })
           : runToolAwareChatCompletionsStream({
               client,
               model: req.model,