harald/nixcfg
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

refactor(mx): drive opencode bot via direct chat-completions API

Browse source 
The bot no longer shells out to `opencode run`. Instead it POSTs to the
OpenAI-compatible /chat/completions endpoint exposed by llama-server on
halo.hoyer.tail:8000 directly. This removes the Bun/sqlite cold-start
overhead per request, drops the pkgs.opencode runtime dependency, and
eliminates the ExecStartPre dance that materialized config.json into the
service's $HOME.

Conversation history is now stored as a proper OpenAI `messages` list
with system/user/assistant roles, instead of the XML blob that was
inlined into a single `opencode run` argument. The interactive opencode
setup (config/opencode/config.json) is unchanged — only the bot stops
depending on it.

The module gains a `modelBaseUrl` option; `model` is now the bare model
name (`halo-8000`) without the provider/ prefix that the opencode CLI
required.
This commit is contained in:
Harald Hoyer 2026-05-13 16:38:58 +02:00
parent aa3bc3c457
commit 42c52bd87f
3 changed files with 72 additions and 101 deletions
Download patch file Download diff file Expand all files Collapse all files

4
systems/x86_64-linux/mx/nextcloud-opencode-bot/default.nix
View file

@ -6,8 +6,8 @@
enable = true;
nextcloudUrl = "https://nc.hoyer.xyz";
botSecretFile = config.sops.secrets."nextcloud-opencode-bot/secret".path;
opencodeConfig = ../../../../config/opencode/config.json;
model = "halo-8000/halo-8000";
modelBaseUrl = "http://halo.hoyer.tail:8000/v1";
model = "halo-8000";
botName = "Halo";
allowedUsers = [ ];
};