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: cache-bust admin UI and show the running version

fix: make model combobox editable and searchable in Model Routing

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

Restore OpenAI subscription generation compatibility (#1326)

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

Add Codex App model catalog support (#1297)

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

Preserve gateway model identity in Anthropic responses (#1270)

Report provider permission denials as HTTP 403 (#1249)

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

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

Recover Claude sessions from provider context overflow (#1215)

Coordinate provider recovery under concurrent load (#1205)

Add Google Vertex AI with renewable ADC (#1193)

Add Amazon Bedrock Mantle support (#1192)

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

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

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

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

Add an explicit searchable model dropdown (#1133)

Preserve mid-conversation system messages through provider conversion (#1125)

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)

Fix Auto Mode classifier responses when stream is omitted (#1098)

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

Expose the Admin startup browser preference (#1091)

Remove the native Anthropic provider transport (#1067)

Make response stream lifetimes explicit (#1060)

Use installed metadata as the single package version source (#1051)

Make provider capabilities semantic and typed (#1047)

Canonicalize provider failure and retry ownership (#1046)

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

Move protocol models to their protocol owners (#1044)

Replace global runtime resources with explicit ownership (#1042)

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

Restore protocol-correct provider errors without client retry loops (#1033)

Move runtime packages under src namespace (#1029)

Preserve messaging transcript on stop

Fix pre-start stream failures returning HTTP 200 (#1026)

Use batch delete boundary for messaging (#996)

add telegram proxy support (#988)

Update GLM 5.2 model references

Add SambaNova Cloud provider (#990)