Skip to main content

CODITECT Claude API Executor

Multi-model AI execution framework - Claude (Anthropic) provider implementation. Provides standardized interface for executing prompts against Claude models with streaming support, token tracking, and error handling.

Features:

  • Claude 3.5 Sonnet, Claude 3 Opus, Claude 3 Haiku support
  • Streaming and batch response modes
  • Token usage tracking and cost estimation
  • Automatic retry with exponential backoff
  • Rate limiting and quota management
  • Structured output parsing (JSON mode)
  • Context window management

Usage: from core.execute_claude import ClaudeExecutor

executor = ClaudeExecutor(model="claude-3-5-sonnet-20241022")
response = executor.execute("Explain quantum computing")

# Streaming
for chunk in executor.stream("Write a poem"):
    print(chunk, end="")

Environment Variables: ANTHROPIC_API_KEY - Required API key CLAUDE_MODEL - Default model (optional) CLAUDE_MAX_TOKENS - Default max tokens (optional)

Author: AZ1.AI INC. Framework: CODITECT Copyright: © 2025 AZ1.AI INC. All rights reserved.

File: execute_claude.py

Classes​

ExecutionResult​

Result from Claude execution.

ClaudeExecutor​

Claude API executor with standardized interface.

Functions​

main()​

CLI interface for Claude executor.

to_dict()​

No description

execute(prompt, system, messages, max_tokens, temperature, json_mode)​

Execute prompt against Claude model.

stream(prompt, system, messages, max_tokens)​

Stream response from Claude model.

Usage​

python execute_claude.py