refactor: invert hide_zero_spend → show_zero_spend, default False

Changes the API from opt-in hiding (hide_zero_spend) to opt-in showing
(show_zero_spend). Default behavior now hides sub-bash.001 models and
shows the summary line — cleaner for the common case where free-tier
models dominate the breakdown.

- Renamed parameter: hide_zero_spend → show_zero_spend
- Inverted logic: default False means hide by default
- Updated docstrings, README, ARCHITECTURE.md

README.md

@@ -13,7 +13,7 @@ Get LiteLLM cost breakdown for a date range. Returns per-model and per-day spend
 **Parameters:**
 - `start_date` (str, required): Start date — YYYY-MM-DD or natural language shortcut (e.g. "2026-06-01", "today", "yesterday", "monday", "last monday", "two days ago", "this week", "last month")
 - `end_date` (str, required): End date — YYYY-MM-DD or natural language shortcut
-- `hide_zero_spend` (bool, default false): Hide models with sub-$0.001 spend. Useful when free-tier or subscription models (e.g. Ollama Cloud) dominate the breakdown with high token counts but negligible cost.
+- `show_zero_spend` (bool, default false): Show models with sub-$0.001 spend. When false, these models are hidden and summarized as "... (N model(s) with sub-$0.001 spend hidden)". Useful when free-tier or subscription models (e.g. Ollama Cloud) dominate the breakdown with high token counts but negligible cost.
 
 ### `litellm_history`
 Get recent LiteLLM request history. Returns the most recent N requests with model, call type, status, duration, token counts, cache hit %, and per-request cost. Useful for understanding which models are being called and how much individual requests cost.