Add OpenAI-compatible LLM client service (v0.19.0)
CI / build + unit (pull_request) Successful in 1m14s
CI / build + unit (pull_request) Successful in 1m14s
LlmService wraps the local OpenAI-compatible server (default http://192.168.1.70:1111/v1, no auth) with native fetch only — no new dependencies. listModels() -> data[].id; chat(messages, opts?) -> choices[0].message.content (non-2xx throws with status + body snippet); summarize(text) = chat() with a concise-summary system prompt. Env: LLM_API_BASE / LLM_MODEL (qwen3.8-27b) / LLM_TIMEOUT_MS (60000, AbortSignal.timeout). Plain feature module wired into app.module.ts; docs synced (AGENTS.md, README env list).
This commit is contained in:
+1
-1
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "mesh-bot",
|
||||
"version": "0.18.1",
|
||||
"version": "0.19.0",
|
||||
"description": "",
|
||||
"author": "",
|
||||
"private": true,
|
||||
|
||||
Reference in New Issue
Block a user