Salastil/odysseus
1
0
Fork 0
mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-06-28 15:45:22 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat(discovery): detect llama.cpp servers and label local providers (#4729)

Browse Source 
* feat(discovery): detect llama.cpp servers and label local providers

Scan port 8080 (llama-server) and 11435 (APFEL) during discovery, fingerprint
llama.cpp via its native /props endpoint, and label well-known local serving
ports (8080 llama.cpp, 8000 vLLM, 1234 LM Studio, 11434 Ollama) consistently
in both the Python provider helper and the JS endpoint UI. Adds a llama.cpp
hint to the /setup slash command.

* fix(discovery): don't infer the serving tool from the port alone

Per review: vLLM, SGLang, llama.cpp and plain OpenAI-compatible servers all
share 8000/8080, so labeling by port mislabels real setups (a vLLM box on 8080
shown as llama.cpp). Drop the port->tool assertions from _provider_label and
providerLabel; the authoritative signal is the /props fingerprint done during
discovery, which is unchanged. Loopback now reads a neutral 'local endpoint' /
'Local'. Tests updated to assert the neutral labels.
This commit is contained in:
Joel Alejandro Escareño Fernández
2026-06-23 23:39:56 +02:00
committed by GitHub
parent 72c0bde8a9
commit e0ccf250a4
9 changed files with 330 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
static/js/slashCommands.js
+8
View File
@@ -208,6 +208,8 @@ function _showSetupEndpointChoices() {
'<pre style="margin:4px 0 0;"><code class="setup-clickable-code" style="cursor:pointer;text-decoration:underline;" title="Click to fill in chat">http://localhost:11434/v1</code></pre>' +
'<div style="margin-top:4px;">or</div>' +
'<pre style="margin:2px 0 0;"><code class="setup-clickable-code" style="cursor:pointer;text-decoration:underline;" title="Click to fill in chat">http://llm-host.local:8000/v1</code></pre>' +
'<div style="margin-top:4px;">or llama.cpp (llama-server):</div>' +
'<pre style="margin:2px 0 0;"><code class="setup-clickable-code" style="cursor:pointer;text-decoration:underline;" title="Click to fill in chat">http://localhost:8080/v1</code></pre>' +
'</div>' +
'<div style="border:1px solid var(--border);border-radius:8px;padding:10px 12px;background:color-mix(in srgb,var(--bg) 88%,var(--fg) 12%);">' +
'<div style="font-weight:700;margin-bottom:6px;">' + SETUP_API_ICON + 'API setup</div>' +
@@ -238,6 +240,12 @@ function _showSetupEndpointChoicesStreamed(options = {}) {
text: 'http://llm-host.local:8000/v1',
copyText: 'http://llm-host.local:8000/v1',
},
{ kind: 'p', text: 'or llama.cpp (llama-server):' },
{
kind: 'code',
text: 'http://localhost:8080/v1',
copyText: 'http://localhost:8080/v1',
},
{ kind: 'heading', html: SETUP_API_ICON + 'API setup' },
{ kind: 'p', text: 'Paste provider name then API key (example):' },
{