feat: add usage tracking with live throughput rates and analytics dashboard

fix: route numbered OpenAI-compatible instance model refs

feat: numbered OpenAI-compatible endpoints admin page

feat: add key management and provider keypool (# new feature)

Add Azure OpenAI provider (#1284)

Add ChatGPT OAuth as an OpenAI Codex provider (#1279)

Make Kilo discovery and reasoning protocol-correct (#1274)

Make ProviderModelInfo the sole model-catalog contract (#1222)

Make provider model discovery the sole catalog owner (#1221)

Coordinate provider recovery under concurrent load (#1205)

Add Google Vertex AI with renewable ADC (#1193)

Make reasoning policy provider-neutral and client-aware (#1148)

Add searchable model selection to the Admin UI (#1121)

Consolidate OpenAI-compatible provider adapters (#1069)

Remove the native Anthropic provider transport (#1067)

Make provider capabilities semantic and typed (#1047)

Canonicalize provider failure and retry ownership (#1046)

Introduce a typed application boundary for provider execution (#1045)

Replace global runtime resources with explicit ownership (#1042)

Establish single-owner runtime with stream-safe provider hot swaps (#1036)

Move runtime packages under src namespace (#1029)