MindWorkAI/AI-Studio
1
0 Fork 0
mirror of https://github.com/MindWorkAI/AI-Studio.git synced 2026-10-17 04:17:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add llmman as a self-hosted host for chat and embedding providers (#947)

Browse Source 
Co-authored-by: Thorsten Sommer <SommerEngineering@users.noreply.github.com>
This commit is contained in:
Eric CurtinandThorsten Sommer authored and GitHub committed 2026-10-13 13:52:43 +02:00
1 parent 2bd3d41421
commit 88d1f4d96a
20 files changed
+270 -89
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

app/Tests/Provider/Reasoning/ReasoningDispatcherTests.cs
+18
View File
@@ -46,11 +46,29 @@ public sealed class ReasoningDispatcherTests
[TestCase(Host.LLAMA_CPP, """ "reasoning_budget": 0 """, ReasoningConfigurationState.EXPLICITLY_DISABLED)]
[TestCase(Host.VLLM, """ "thinking_token_budget": 2048 """, ReasoningConfigurationState.EXPLICITLY_ENABLED)]
[TestCase(Host.VLLM, """ "chat_template_kwargs": { "thinking": true } """, ReasoningConfigurationState.EXPLICITLY_ENABLED)]
[TestCase(Host.LLMMAN, """ "reasoning_budget": 0 """, ReasoningConfigurationState.EXPLICITLY_DISABLED, Description = "llmman serves GGUF models with llama.cpp and hands the budget to it.")]
[TestCase(Host.LLMMAN, """ "thinking_token_budget": 2048 """, ReasoningConfigurationState.EXPLICITLY_ENABLED, Description = "llmman serves other models with vLLM and hands the budget to it.")]
public void EachSelfHostedEngineIsReadInItsOwn(Host host, string parameters, ReasoningConfigurationState wanted)
{
Assert.That(ReasoningDispatcher.WhatTheParametersSay(LLMProviders.SELF_HOSTED, host, parameters), Is.EqualTo(wanted));
}
[Test]
public void LlmmanIsReadInEverythingItsEnginesAreReadIn()
{
//
// llmman decides by itself whether llama.cpp or vLLM serves a model. A dialect either of
// them learns later has to reach llmman as well, or a switch set for llmman goes unseen:
//
var llmman = ReasoningDispatcher.DialectsOf(LLMProviders.SELF_HOSTED, Host.LLMMAN);
Assert.Multiple(() =>
{
Assert.That(llmman, Is.SupersetOf(ReasoningDispatcher.DialectsOf(LLMProviders.SELF_HOSTED, Host.LLAMA_CPP)));
Assert.That(llmman, Is.SupersetOf(ReasoningDispatcher.DialectsOf(LLMProviders.SELF_HOSTED, Host.VLLM)));
});
}
[Test]
public void AProviderIsNotReadInADialectItDoesNotSpeak()
{