48d560a209
Differentiate MCP servers from generic 'item' (flat 15) — they actually
cost 500+ tokens per turn for protocol metadata and tool schemas.
estimateTokens(bytes, 'mcp', {toolCount}) returns max of:
- 500 token floor (base overhead)
- ceil(bytes / 3.5) (json-rate when bytes known)
- 500 + toolCount * 200 (when tool count is detected; Step 14 wires this)
Caller-side migration in next commit (Step 5).
Tests: +4 cases for mcp kind.
|
||
|---|---|---|
| .. | ||
| ai-psychosis | ||
| config-audit | ||
| graceful-handoff | ||
| linkedin-thought-leadership | ||
| llm-security | ||
| ms-ai-architect | ||
| okr | ||
| ultra-cc-architect | ||
| ultraplan-local | ||