feat: theme dashboard charts and expose admin UI on HF Spaces

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

feat: surface saved endpoint models and revamp the admin UI

fix: route numbered OpenAI-compatible instance model refs

feat: numbered OpenAI-compatible endpoints admin page

feat: add generic OpenAI-compatible endpoint provider

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

Use codebase .env for server and admin config

Make OpenCode Zen mappings explicit (#1342)

Add Azure OpenAI provider (#1284)

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

feat: add Kilo.ai provider (#1273)

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

Add Google Vertex AI with renewable ADC (#1193)

Add Amazon Bedrock Mantle support (#1192)

Add Kimi Code subscription support (#1183)

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

Add LOG_LEVEL env var to control log verbosity (#1142)

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

Add Ollama Cloud as a first-class provider (#1106)

Add Fable as a first-class Claude routing tier (#1099)

Make proxy authentication bearer-only across every client (#1096)

Expose the Admin startup browser preference (#1091)

Fix cross-drive messaging startup with native Claude plan storage (#1085)

Give messaging clear exact subtree semantics (#1072)

Consolidate OpenAI-compatible provider adapters (#1069)

Preserve user messages during messaging clear (#1068)

Remove the native Anthropic provider transport (#1067)

Make provider capabilities semantic and typed (#1047)

Canonicalize provider failure and retry ownership (#1046)

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)