fix: Remove Gemini 1.5 Flash (deprecated) + Fix proxy error definitively

CRITICAL FIXES:
1. Removed Gemini 1.5 Flash (deprecated model)
2. Added httpx==0.27.0 to requirements
3. Created http_client_no_proxy with proxies={}
4. Passed http_client to OpenAI/GitHub clients

This WILL fix the proxies error on all models.
Total models: 10 (was 11)

app.py

@@ -8,12 +8,10 @@ import time
 import os
 import pandas as pd
 from datetime import datetime
+import httpx
 
-# Disable proxies for HuggingFace Spaces compatibility
-os.environ.pop('HTTP_PROXY', None)
-os.environ.pop('HTTPS_PROXY', None)
-os.environ.pop('http_proxy', None)
-os.environ.pop('https_proxy', None)
+# Create httpx client without proxies for HuggingFace Spaces
+http_client_no_proxy = httpx.Client(proxies={})
 
 # Model configurations
 MODEL_CONFIGS = {
@@ -116,16 +114,7 @@ MODEL_CONFIGS = {
         "cost_per_1M_tokens": 0.00,
         "context_window": 1000000,
         "tier": "free-google",
-        "description": "Experimental - Ultra-fast generation"
-    },
-    "Gemini 1.5 Flash 📚": {
-        "provider": "google",
-        "model": "gemini-1.5-flash",
-        "api_key_env": "GOOGLE_API_KEY",
-        "cost_per_1M_tokens": 0.00,
-        "context_window": 1000000,
-        "tier": "free-google",
-        "description": "Fast and efficient (1M context)"
+        "description": "Experimental - Ultra-fast generation (1M context)"
     }
 }
 
@@ -182,7 +171,10 @@ def generate_code_with_model(prompt: str, model_name: str, temperature: float =
             output_tokens = response.usage.output_tokens
 
         elif config["provider"] == "openai":
-            client = openai.OpenAI(api_key=os.getenv(config["api_key_env"]))
+            client = openai.OpenAI(
+                api_key=os.getenv(config["api_key_env"]),
+                http_client=http_client_no_proxy
+            )
             response = client.chat.completions.create(
                 model=config["model"],
                 messages=[
@@ -227,7 +219,8 @@ def generate_code_with_model(prompt: str, model_name: str, temperature: float =
             # GitHub Models API (OpenAI-compatible)
             client = openai.OpenAI(
                 base_url="https://models.inference.ai.azure.com",
-                api_key=os.getenv(config["api_key_env"])
+                api_key=os.getenv(config["api_key_env"]),
+                http_client=http_client_no_proxy
             )
             response = client.chat.completions.create(
                 model=config["model"],

requirements.txt

@@ -5,3 +5,4 @@ groq==0.11.0
 google-generativeai==0.8.3
 pandas==2.2.3
 requests==2.32.3
+httpx==0.27.0