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

feat: track local-path usage and enrich analytics dashboard

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

fix: cache-bust admin UI and show the running version

fix: make model combobox editable and searchable in Model Routing

feat: fetch models from OpenAI-compatible endpoints in admin UI

feat: numbered OpenAI-compatible endpoints admin page

feat: add generic OpenAI-compatible endpoint provider

feat: admin dedicated pages, pool key management, keypool quotas (#1350)

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

Use codebase .env for server and admin config

Make OpenCode Zen mappings explicit (#1342)

Preserve empty reasoning state across native tool turns (#1339)

Restore OpenCode reasoning replay for tool turns (#1328)

Restore OpenAI subscription generation compatibility (#1326)

Restore Claude Code client controls for OpenAI Responses (#1311)

Keep tool names portable across OpenAI transports (#1309)

Add Codex App model catalog support (#1297)

Add Azure OpenAI provider (#1284)

fix: detect NIM 500 context overflow as context_window_exceeded (#1280)

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

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

feat: add Kilo.ai provider (#1273)

Close interrupted tool turns before new user input (#1271)

Preserve gateway model identity in Anthropic responses (#1270)

Contain MiniMax native tool markup across NIM streams (#1259)

Make the FCC logo background transparent (#1257)

Make the FCC terminal mark square (#1256)

Add a native Free Claude Code app icon (#1252)

Report provider permission denials as HTTP 403 (#1249)

Recover MiniMax-M3 native tool calls on NVIDIA NIM (#1246)

Preserve Claude feature flags in interactive clients (#1239)

Add a native FCC desktop launcher for Windows and macOS (#1225)

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

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

Remove obsolete init and server alias commands (#1220)

Recover Claude sessions from provider context overflow (#1215)

Keep FCC-local traffic off outbound proxies (#1214)

Give Google reasoning controls one owner (#1211)

Coordinate provider recovery under concurrent load (#1205)

Add Google Vertex AI with renewable ADC (#1193)

Add Amazon Bedrock Mantle support (#1192)

Add Kimi Code subscription support (#1183)

Report output-limit truncation as incomplete Responses (#1180)

Prevent the admin UI from being served from cache (#1160)

Honor reasoning tiers on numeric-budget providers (#1150)

Keep inline system reminders cache-stable across providers (#1154)

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