✨ New Features
- feat(providers): add Grok 4.3 and Xiaomi Mimo TTS provider (#1837)
- feat(core): implement Rate Limit Watchdog with environment override capability to detect and reset stalled queues (#1839)
- feat(providers): add muse-spark-web provider with multiple models and reasoning support (#1843)
- feat(1proxy): integrate 1proxy free proxy marketplace with dashboard management and new MCP tools (closes #1788) (#1847)
🐛 Bug Fixes
- fix(codex): sanitize Responses replay state to prevent internal assistant commentary from leaking (#1868 — thanks @dhaern)
- fix(cli): add capture-backed Gemini CLI fingerprint (#1866)
- fix(ui): hide combo compression controls when the global setting is disabled (#1840)
- fix(db): tolerate missing request_detail_logs table for legacy deployments (#1848)
- fix(core): remove unneeded `store` payload parameter for providers lacking support (closes #1841)
- fix(core): ensure safeOutboundFetch and A2A routers return 503 Service Unavailable when security guardrails are triggered
- fix(usage): correct Unix seconds vs milliseconds parsing logic for Kiro AI quota reset (closes #1849)
- fix(ui): apply robust NaN handling, ensure 24h consistency, and fix missing hour slots in Compression Analytics (closes #1844)
- fix(ui): implement short number formatting for token consumption metrics on cache pages to prevent overflow (closes #1842)
- fix(combo): stabilize provider routing at 500+ connections by bounding semaphore queues and adjusting circuit breaker tracking (closes #1846) (#1854)
- fix(maritalk): update Maritalk model list, use Authorization Key header, and align with latest API endpoints (#1856)
- fix(grok-web): stabilize tool calling (bash, readFile, webSearch) and response parsing by mapping native Grok intents to standard OpenAI payloads (#1857)
- fix(providers): correctly map and expose the Upstage embedding and chat model catalogs (#1855)
- fix(executor): apply proper urlSuffix and custom authHeaders for unknown registry-based providers in DefaultExecutor (closes #1846) (#1861)
🛠️ Maintenance
- fix(workflow): build docker images on version tags (#1838)
What's Changed
- fix: tolerate missing request detail logs table by @bambuvnn in #1848
- feat: integrate 1proxy free proxy marketplace by @oyi77 in #1847
- feat(registry): register muse-spark-web models in provider catalog by @janeza2 in #1843
- Hide combo compression controls when disabled by @rdself in #1840
- fix(workflow): build docker images on version tags by @rdself in #1838
- Add Grok 4.3 + Add Xiaomi Mimo TTS provider by @backryun in #1837
- fix(combo): stabilize provider routing at 500+ connections (Issue #1846) by @oyi77 in #1854
- fix(Upstage):Correcting the Upstage Model List by @backryun in #1855
- fix(maritalk):Update Model list & Implementation of the latest API by @backryun in #1856
- fix(grok-web): stabilize tool calling and response parsing by @dhaern in #1857
- fix(executor): fix urlSuffix and authHeader bugs causing auth failures (Issue #1846) by @oyi77 in #1861
- fix(settings): restore CLI fingerprint toggles by @dhaern in #1863
- feat(usage): add NanoGPT subscription quota tracking to Limits & Quotas dashboard by @Aculeasis in #1865
- build(deps): bump SonarSource/sonarqube-scan-action from 7 to 8 by @dependabot[bot] in #1864
- fix(cli): add capture-backed Gemini CLI fingerprint by @dhaern in #1866
- fix(codex): sanitize Responses replay state by @dhaern in #1868
- Release v3.7.8 by @diegosouzapw in #1851
New Contributors
- @bambuvnn made their first contribution in #1848
- @janeza2 made their first contribution in #1843
- @Aculeasis made their first contribution in #1865
Full Changelog: v3.7.7...v3.7.8