From 55131019e18aedcf25b4ba85e0a025d2a9e0f1f1 Mon Sep 17 00:00:00 2001
From: Alishahryar1 <alishahryar2@gmail.com>
Date: Wed, 22 Apr 2026 17:34:00 -0700
Subject: [PATCH] Sync config defaults and proxy docs

---
 README.md                   | 4 ++++
 config/settings.py          | 4 ++--
 tests/config/test_config.py | 7 ++++++-
 3 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 76ea6ca..cfd4221 100644
--- a/README.md
+++ b/README.md
@@ -487,6 +487,10 @@ Configure via `WHISPER_DEVICE` (`cpu` | `cuda` | `nvidia_nim`) and `WHISPER_MODE
 | `DEEPSEEK_API_KEY`   | DeepSeek API key                                                      | required for DeepSeek                             |
 | `LM_STUDIO_BASE_URL` | LM Studio server URL                                                  | `http://localhost:1234/v1`                        |
 | `LLAMACPP_BASE_URL`  | llama.cpp server URL                                                  | `http://localhost:8080/v1`                        |
+| `NVIDIA_NIM_PROXY`   | Optional proxy URL for NVIDIA NIM requests (`http://...` or `socks5://...`) | `""` |
+| `OPENROUTER_PROXY`   | Optional proxy URL for OpenRouter requests (`http://...` or `socks5://...`) | `""` |
+| `LMSTUDIO_PROXY`     | Optional proxy URL for LM Studio requests (`http://...` or `socks5://...`) | `""` |
+| `LLAMACPP_PROXY`     | Optional proxy URL for llama.cpp requests (`http://...` or `socks5://...`) | `""` |
 
 ### Rate Limiting & Timeouts
 
diff --git a/config/settings.py b/config/settings.py
index 1453909..e15e35d 100644
--- a/config/settings.py
+++ b/config/settings.py
@@ -108,7 +108,7 @@ class Settings(BaseSettings):
     # ==================== Model ====================
     # All Claude model requests are mapped to this single model (fallback)
     # Format: provider_type/model/name
-    model: str = "nvidia_nim/meta/llama3-70b-instruct"
+    model: str = "nvidia_nim/stepfun-ai/step-3.5-flash"
 
     # Per-model overrides (optional, falls back to MODEL)
     # Each can use a different provider
@@ -134,7 +134,7 @@ class Settings(BaseSettings):
 
     # ==================== HTTP Client Timeouts ====================
     http_read_timeout: float = Field(
-        default=300.0, validation_alias="HTTP_READ_TIMEOUT"
+        default=120.0, validation_alias="HTTP_READ_TIMEOUT"
     )
     http_write_timeout: float = Field(
         default=10.0, validation_alias="HTTP_WRITE_TIMEOUT"
diff --git a/tests/config/test_config.py b/tests/config/test_config.py
index 4614f84..d08031a 100644
--- a/tests/config/test_config.py
+++ b/tests/config/test_config.py
@@ -16,16 +16,21 @@ class TestSettings:
         settings = Settings()
         assert settings is not None
 
-    def test_default_values(self):
+    def test_default_values(self, monkeypatch):
         """Test default values are set and have correct types."""
         from config.settings import Settings
 
+        monkeypatch.delenv("MODEL", raising=False)
+        monkeypatch.delenv("HTTP_READ_TIMEOUT", raising=False)
+        monkeypatch.setitem(Settings.model_config, "env_file", ())
         settings = Settings()
+        assert settings.model == "nvidia_nim/stepfun-ai/step-3.5-flash"
         assert isinstance(settings.provider_rate_limit, int)
         assert isinstance(settings.provider_rate_window, int)
         assert isinstance(settings.nim.temperature, float)
         assert isinstance(settings.fast_prefix_detection, bool)
         assert isinstance(settings.enable_thinking, bool)
+        assert settings.http_read_timeout == 120.0
 
     def test_get_settings_cached(self):
         """Test get_settings returns cached instance."""