Improve proxy-side tool instructions so models more reliably emit structured tool actions, and add focused tests covering prompt guidance and default action limits.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Add a proxy-side tool emulation layer so Lingma requests can surface stable OpenAI tool_calls and Anthropic tool_use blocks even when upstream tool events are missing or inconsistent.
Constraint: Keep native Lingma tool event bridging as the first path and layer emulation as a fallback
Rejected: Depend exclusively on Lingma native tool/invoke events | tool visibility remains inconsistent across models and transports
Confidence: high
Scope-risk: moderate
