Starstruk Logo MarkStarstruk

v0.5.12

tinyauthapp/tinyauthv0.5.12Jun 26, 2026by decolua

AI Summary

Adds a token-saver dashboard, integrates Venice AI, overhauls the Blackbox catalog, and fixes various provider compatibility issues including DeepSeek, Gemini, and streaming usage.

Key Highlights

  • Token-saver dashboard
  • Venice AI provider integration
  • Blackbox provider catalog overhaul
  • Streaming usage fixes
  • Docker headroom support

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
  • Provider thinking compatibility fixes
  • Usage logging dedupe to reduce stats churn
  • Prevent non-JSON SSE lines from breaking clients
  • Resolve Gemini TTS models from catalog
  • Support Kiro IDC organization token import
  • Preserve forced streaming for JSON clients
  • Preserve Responses text format
  • Support Gemini native TTS generateContent endpoint
  • CodeBuddy reasoning params handling
  • Custom provider models in combo picker
  • Docker-compose with headroom enabled by default
  • Token diagnostics clarification
  • Translate openai-responses input through OpenAI
  • Claude Opus 4.7 context window reporting
  • Antigravity retry transient upstream failures
  • Handle strip rules without match/drop
  • Translator custom provider prefix in debug endpoint
  • Token-saver full width card layout

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