v0.5.12

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