feat: add context token budget validation

.env.example

@@ -5,4 +5,5 @@ SHOW_USAGE=True
 TEMPERATURE=0
 TOP_P=1
 MAX_TOKENS=1000
+MAX_CONTEXT_TOKENS=8192
 MEMORY_KEEP_COUNT=10

.github/workflows/tests.yml

@@ -0,0 +1,35 @@
+name: Tests
+
+on:
+  push:
+  pull_request:
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    name: Python ${{ matrix.python-version }}
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v7
+
+      - name: Set up Python
+        uses: actions/setup-python@v7
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+
+      - name: Install dependencies
+        run: python -m pip install -r requirements.txt
+
+      - name: Run tests
+        run: python -m unittest discover -v

main.py

@@ -1,6 +1,6 @@
 from openai import OpenAI, OpenAIError
 
-from utils import get_required_config, read_input
+from utils import calculate_input_token_budget, get_required_config, read_input
 
 
 def trim_history(messages, keep_count):
@@ -26,6 +26,11 @@ def main():
         temperature = get_required_config("TEMPERATURE", cast=float)
         top_p = get_required_config("TOP_P", cast=float)
         memory_keep_count = get_required_config("MEMORY_KEEP_COUNT", cast=int)
+        max_context_tokens = get_required_config(
+            "MAX_CONTEXT_TOKENS",
+            cast=int,
+        )
+        calculate_input_token_budget(max_context_tokens, max_tokens)
 
         if memory_keep_count < 0:
             raise ValueError("MEMORY_KEEP_COUNT must be 0 or greater")

utils.py

@@ -23,4 +23,18 @@ def read_input(prompt):
         return None
 
 
-__all__ = ["get_required_config", "read_input"]
+def calculate_input_token_budget(context_limit, output_limit):
+    """Calculate how many tokens are available for input messages."""
+    if context_limit <= 0:
+        raise ValueError("MAX_CONTEXT_TOKENS must be greater than 0")
+
+    if output_limit <= 0:
+        raise ValueError("MAX_TOKENS must be greater than 0")
+
+    if output_limit >= context_limit:
+        raise ValueError("MAX_TOKENS must be smaller than MAX_CONTEXT_TOKENS")
+
+    return context_limit - output_limit
+
+
+__all__ = ["calculate_input_token_budget", "get_required_config", "read_input"]