Replacve OPENAI_MAX_COMPLETION_TOKENS

Author: sbarrio

tools/issue_handler/README.md

@@ -49,7 +49,7 @@ This creates a `.env` file that you will need to fill with the required tokens a
 **Optional variables** (override defaults):
 - `OPENAI_MODEL` - Model to use (default: `gpt-5.2-chat-latest`)
 - `OPENAI_TEMPERATURE` - Response creativity 0.0-1.0 (default: `0.4`)
-- `OPENAI_MAX_RESPONSE_TOKENS` - Max response length (default: `500`)
+- `OPENAI_MAX_COMPLETION_TOKENS` - Max response length (default: `500`)
 
 ## Usage
 
@@ -82,7 +82,7 @@ The tool runs:
 **Optional GitHub Variables** (override defaults if needed):
 - `OPENAI_MODEL` - Model to use (default: `gpt-5.2-chat-latest`)
 - `OPENAI_TEMPERATURE` - Response creativity 0.0-1.0 (default: `0.4`)
-- `OPENAI_MAX_RESPONSE_TOKENS` - Max response length (default: `500`)
+- `OPENAI_MAX_COMPLETION_TOKENS` - Max response length (default: `500`)
 
 **Automatically Provided**:
 - `GITHUB_TOKEN` - Provided by GitHub Actions

tools/issue_handler/requirements.txt

@@ -1,5 +1,5 @@
 # List of Python dependencies with exact versions
-openai==2.17.0
+openai==2.14.0
 pytest==9.0.2
 requests==2.32.5
 python-dotenv==1.2.1

tools/issue_handler/setup_env.sh

@@ -32,7 +32,7 @@ GITHUB_REPOSITORY=DataDog/dd-sdk-ios
 # Optional: Override OpenAI defaults
 # OPENAI_MODEL=gpt-5.2-chat-latest
 # OPENAI_TEMPERATURE=0.4
-# OPENAI_MAX_RESPONSE_TOKENS=500
+# OPENAI_MAX_COMPLETION_TOKENS=500
 EOL
 
 echo "✨ Created .env file"

tools/issue_handler/src/openai_handler.py

@@ -54,7 +54,7 @@ class OpenAIHandler:
 
     # Content limits to prevent abuse
     MAX_CONTENT_LENGTH = 4000
-    MAX_RESPONSE_TOKENS = int(os.environ.get("OPENAI_MAX_RESPONSE_TOKENS", "500"))
+    MAX_COMPLETION_TOKENS = int(os.environ.get("OPENAI_MAX_COMPLETION_TOKENS", "500"))
 
     def __init__(self, api_key: str):
         """
@@ -118,7 +118,7 @@ def analyze_issue(self, issue: GithubIssue) -> AnalysisResult:
                 model=self.model,
                 messages=messages,
                 # temperature=float(os.environ.get("OPENAI_TEMPERATURE", "0.4")),
-                max_completion_tokens=self.MAX_RESPONSE_TOKENS,
+                max_completion_tokens=self.MAX_COMPLETION_TOKENS,
                 response_format={"type": "json_object"}
             )