v0.5.12

alibaba/MNNv0.5.12Jun 26, 2026by decolua

AI Summary

This release focuses on dashboard enhancements, introducing a token-saver page and bulk delete functionality, while adding support for Venice AI and overhauling the Blackbox provider catalog. It also includes numerous fixes for streaming, model compatibility, and authentication flows.

Key Highlights

Addition of the token-saver dashboard page for monitoring.
New Venice AI provider integration.
Overhaul of the Blackbox provider catalog with WebUI test support.
Addition of bulk delete capability for provider connections.
Resolves GitHub Copilot model catalog from upstream.

New Features

Token-saver dashboard page
Bulk delete for provider connections
Venice AI provider
Kiro external_idp import for Microsoft SSO
Blackbox provider catalog overhaul
Antigravity retry transient upstream failures

Full Release Notes

Features:
- Add token-saver dashboard page — decolua
- Add bulk delete for provider connections — teddytkz
- Resolve GitHub Copilot model catalog from upstream — caiqinzhou
- Add Venice AI provider — Brokenc0de
- Add Kiro external_idp import for Microsoft SSO (CLIProxyAPI) — Stevanus Pangau
- Overhaul Blackbox provider catalog + WebUI test support — suryacagur

Fixes:
- Provider thinking compatibility (DeepSeek/Gemini) — Mink Nguyen
- Stop double-counting streaming usage at source — decolua
- Usage logging dedupe to reduce stats churn — Mink Nguyen
- Prevent non-JSON SSE lines / duplicate [DONE] from breaking clients (PR #2046) — qianze
- Resolve Gemini TTS models from catalog — nguyenha935
- Support Kiro IDC (organization) token import — quanturbo
- Preserve forced streaming for JSON clients (#2031) — Joseph Yaksich
- Preserve Responses text format (Codex) — tenglong
- Support Gemini native TTS generateContent endpoint — nguyenha935
- Add missing zh-CN endpoint key label (i18n) — weimaozhen
- CodeBuddy: only send reasoning params when client requests reasoning (#2071) — Rex
- Show custom provider models in combo picker — Sapto
- Docker: add docker-compose.yml with headroom enabled by default — nitsuahlabs
- Clarify token diagnostics vs provider billing (headroom, #1998) — Sutarto Jordan Chrisfivo
- Translate openai-responses input through OpenAI for compression (#1998) — Ankit
- Kiro: report 1M context window for claude-opus-4.8 — EdisonPVE
- Avoid stale redirects after auth changes (#2100) — Emirhan
- Mark Claude Opus 4.7 (dashed id) as 1M context — Brokenc0de
- Preserve reasoning effort through Codex translations — ntdung6868
- Token-saver: full width card layout — decolua
- Antigravity: retry transient upstream failures — Sutarto Jordan Chrisfivo
- Param-support: handle strip rules without match/drop (#1960) — Joseph Yaksich
- Translator: resolve custom provider prefix in debug endpoint (#1083) — hamsa0x7