forked from Blendman974/faceclaw
Assistant: add a Hermes agent backend
A "Hermes agent" assistant model talks to a Hermes Agent gateway's OpenAI-compatible API server (streamed /v1/chat/completions), with Hermes URL and key settings under Assistant. Hermes keeps the conversation: each assistant session maps to one X-Hermes-Session-Id and only the latest user message is sent. Faceclaw's own tools are not offered to it, and its reasoning stream is not shown on the glasses. See notes/hermes-assistant.md. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
2bb7b3ea1a
commit
d9924eedcd
9 files changed
+297
-4
No files matched your search
@@ -31,6 +31,8 @@ import type { AssistantContext } from "../../assistant/types";
|
||||
import { SingleNotificationLayer } from "../notifications";
|
||||
import {
|
||||
anthropicApiKeySetting,
|
||||
assistantHermesKeySetting,
|
||||
assistantHermesUrlSetting,
|
||||
assistantBackendSetting,
|
||||
assistantBridgeHostSetting,
|
||||
assistantBridgePortSetting,
|
||||
@@ -1643,6 +1645,8 @@ class Shell {
|
||||
const llm = resolveAssistantModel(model, {
|
||||
anthropic: anthropicApiKeySetting.get(),
|
||||
openai: openAiApiKeySetting.get(),
|
||||
hermesUrl: assistantHermesUrlSetting.get(),
|
||||
hermesKey: assistantHermesKeySetting.get(),
|
||||
});
|
||||
if (llm && reasoning !== "default" && llm.effort) llm.effort = reasoning;
|
||||
return llm ? { kind: "direct", llm } : null;
|
||||
|
||||
Reference in new issue
Block a user