llm-echo 0.5
Which summary reads better? Pick one — models revealed after.Both summaries are AI-generated.
The llm-echo debug plugin now simulates token usage counts for tool calls, system prompts, and reasoning tokens without hitting a live model. This allows you to locally dry-run agent orchestration, token-tracking middleware, and cost-attribution pipelines without incurring API latency or costs. You can now verify how your production system handles complex reasoning outputs and metadata-heavy payloads entirely offline.
The llm-echo plugin now accurately simulates token usage by including tool calls, system prompts, and reasoning tokens, increasing output token counts from negligible to 24 per prompt. This allows developers to better predict and budget for token consumption when debugging LLM-powered workflows, ensuring more accurate cost estimations and resource planning in production environments.