Fix endpoint compatibility

.gitignore

@@ -149,3 +149,6 @@ cython_debug/
 
 # OS X
 .DS_Store
+
+# User custom folders
+external_component/

app/main.py

@@ -35,7 +35,7 @@ def create_application() -> FastAPI:
     application.add_middleware(
         CORSMiddleware,
         allow_origins=["*"],
-        allow_credentials=True,
+        allow_credentials=False, # Changed to False for better compat with allow_origins=["*"]
         allow_methods=["*"],
         allow_headers=["*"],
     )

implementation_plan.md

@@ -1,51 +0,0 @@
-# Storyline AI Gateway - Implementation Plan
-
-## Project Overview
-A FastAPI-based gateway for e-learning modules (Articulate Storyline) to access LLM services (Gemini, OpenAI) with centralized authentication and rate limiting.
-
-## Tech Stack
-- **Framework**: FastAPI
-- **Server**: Uvicorn
-- **Rate Limiting**: Slowapi (limiter)
-- **Auth**: Header-based API Key (`X-API-Key`)
-- **LLMs**: Google Gemini, OpenAI
-
-## Directory Structure
-- `app/main.py`: Application entry point and middleware configuration.
-- `app/core/`: Configuration and utilities (limiter, settings).
-- `app/api/deps.py`: Shared dependencies (authentication).
-- `app/api/router.py`: API versioning and route aggregation.
-- `app/api/endpoints/`:
-    - `storyline.py`: Generic endpoint.
-    - `gemini.py`: Dedicated Gemini endpoint.
-    - `openai.py`: Dedicated OpenAI endpoint.
-
-## Configuration
-Managed via `.env` file:
-- `API_KEY`: Secret key for Storyline modules.
-- `GOOGLE_API_KEY`: API key for Google Generative AI.
-- `OPENAI_API_KEY`: API key for OpenAI.
-- `PORT`: Server port (default 8000).
-
-## API Endpoints
-All endpoints are versioned under `/api/v1`.
-
-### 1. Gemini Chat
-- **URL**: `/api/v1/gemini/chat`
-- **Method**: POST
-- **Headers**: `X-API-Key: <your_key>`
-- **Body**: `{"prompt": "string", "context": "string"}`
-
-### 2. OpenAI Chat
-- **URL**: `/api/v1/openai/chat`
-- **Method**: POST
-- **Headers**: `X-API-Key: <your_key>`
-- **Body**: `{"prompt": "string", "context": "string"}`
-
-## Rate Limiting
-- Applied globally/per endpoint: **20 calls per minute**.
-
-## Future Steps
-- Add logging (WandB or file-based).
-- Implement response caching.
-- Add more LLM providers (Anthropic, etc.).

update_schema.py

@@ -1,30 +0,0 @@
-from sqlalchemy import create_engine, text
-from app.core.config import settings
-
-def update_schema():
-    engine = create_engine(settings.DATABASE_URL)
-    with engine.connect() as conn:
-        print("Adding token tracking columns to modules table...")
-        try:
-            conn.execute(text("ALTER TABLE modules ADD COLUMN ingress_tokens INTEGER DEFAULT 0"))
-            print("Added ingress_tokens column.")
-        except Exception as e:
-            print(f"ingress_tokens column might already exist: {e}")
-
-        try:
-            conn.execute(text("ALTER TABLE modules ADD COLUMN egress_tokens INTEGER DEFAULT 0"))
-            print("Added egress_tokens column.")
-        except Exception as e:
-            print(f"egress_tokens column might already exist: {e}")
-
-        try:
-            conn.execute(text("ALTER TABLE modules ADD COLUMN total_tokens INTEGER DEFAULT 0"))
-            print("Added total_tokens column.")
-        except Exception as e:
-            print(f"total_tokens column might already exist: {e}")
-            
-        conn.commit()
-        print("Schema update complete.")
-
-if __name__ == "__main__":
-    update_schema()