From 7aba42d46eb29f1095070299a8d3067fd7e14a45 Mon Sep 17 00:00:00 2001
From: Alessandro <155005371+3clyp50@users.noreply.github.com>
Date: Tue, 7 Jul 2026 17:01:46 +0200
Subject: [PATCH] Default local providers to chat completions

Force chat-completions transport by default for local and broad OpenAI-compatible chat providers whose Responses API implementations are often missing or unstable.\n\nCovers LM Studio, llama.cpp, Ollama, Ollama Cloud, oMLX, vLLM, and Other OpenAI compatible while leaving embedding provider defaults untouched. Updates provider-default regression coverage for the new chat-only defaults.
---
 conf/model_providers.yaml           |  8 ++++++++
 tests/test_model_config_api_keys.py | 31 +++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)

diff --git a/conf/model_providers.yaml b/conf/model_providers.yaml
index ba3f0ea48..58bb2e7cc 100644
--- a/conf/model_providers.yaml
+++ b/conf/model_providers.yaml
@@ -84,6 +84,7 @@ chat:
       endpoint_url: "/v1/models"
       default_base: "http://host.docker.internal:1234"
     kwargs:
+      a0_api_mode: chat
       api_base: "http://host.docker.internal:1234/v1"
       api_key: "lm-studio"
   llama_cpp:
@@ -93,6 +94,7 @@ chat:
       endpoint_url: "/v1/models"
       default_base: "http://host.docker.internal:8080"
     kwargs:
+      a0_api_mode: chat
       api_base: "http://host.docker.internal:8080/v1"
       api_key: "llama-cpp"
   mistral:
@@ -120,6 +122,7 @@ chat:
       format: "ollama"
       default_base: "http://host.docker.internal:11434"
     kwargs:
+      a0_api_mode: chat
       api_base: "http://host.docker.internal:11434"
   omlx:
     name: oMLX
@@ -128,6 +131,7 @@ chat:
       endpoint_url: "/v1/models"
       default_base: "http://host.docker.internal:8000"
     kwargs:
+      a0_api_mode: chat
       api_base: "http://host.docker.internal:8000/v1"
       api_key: "omlx"
   ollama_cloud:
@@ -136,6 +140,7 @@ chat:
     models_list:
       endpoint_url: "/models"
     kwargs:
+      a0_api_mode: chat
       api_base: https://ollama.com/v1
   openai:
     name: OpenAI
@@ -184,6 +189,7 @@ chat:
       endpoint_url: "/v1/models"
       default_base: "http://host.docker.internal:8000"
     kwargs:
+      a0_api_mode: chat
       api_base: "http://host.docker.internal:8000/v1"
       api_key: "vllm"
   xai:
@@ -208,6 +214,8 @@ chat:
   other:
     name: Other OpenAI compatible
     litellm_provider: openai
+    kwargs:
+      a0_api_mode: chat
 
 embedding:
   huggingface:
diff --git a/tests/test_model_config_api_keys.py b/tests/test_model_config_api_keys.py
index e1f62d2f0..a76c1cd0d 100644
--- a/tests/test_model_config_api_keys.py
+++ b/tests/test_model_config_api_keys.py
@@ -265,6 +265,7 @@ def test_ollama_cloud_provider_config_requires_key_and_base_url():
     ollama_cloud = provider_config["chat"]["ollama_cloud"]
 
     assert ollama_cloud["name"] == "Ollama Cloud"
+    assert ollama_cloud["kwargs"]["a0_api_mode"] == "chat"
     assert ollama_cloud["kwargs"]["api_base"] == "https://ollama.com/v1"
     assert ollama_cloud["models_list"]["endpoint_url"] == "/models"
     assert "api_key_mode" not in ollama_cloud
@@ -298,6 +299,36 @@ def test_direct_venice_chat_provider_defaults_to_chat_completions(monkeypatch):
     assert custom.kwargs["a0_api_mode"] == "responses"
 
 
+def test_local_chat_providers_default_to_chat_completions():
+    import yaml
+
+    provider_path = PROJECT_ROOT / "conf/model_providers.yaml"
+    provider_config = yaml.safe_load(provider_path.read_text(encoding="utf-8"))
+
+    chat_completions_default_providers = (
+        "lm_studio",
+        "llama_cpp",
+        "ollama",
+        "ollama_cloud",
+        "omlx",
+        "other",
+        "vllm",
+    )
+    local_embedding_providers = (
+        "lm_studio",
+        "llama_cpp",
+        "ollama",
+        "omlx",
+        "vllm",
+    )
+
+    for provider in chat_completions_default_providers:
+        assert provider_config["chat"][provider]["kwargs"]["a0_api_mode"] == "chat"
+
+    for provider in local_embedding_providers:
+        assert "a0_api_mode" not in provider_config["embedding"][provider]["kwargs"]
+
+
 def test_missing_api_key_banner_does_not_include_auto_modal_metadata(monkeypatch):
     from plugins._model_config.helpers import model_config