Commit Graph
58 Commits
Author SHA1 Message Date
decolua 827e5c382b # v0.4.71 (2026-06-06)
## Features
- Caveman: add wenyan classical Chinese levels and sync upstream prompts; locale-based visibility on endpoint page
- i18n: endpoint exposure notice across multiple languages + Russian README
- Antigravity: add gemini-3.5-flash-extra-low (Low) model
- xiaomi-tokenplan: add Claude-native MiMo V2.5 Pro alias via dedicated executor
- Qoder: fetch latest model + dashboard import-model button (#1642)
- MiniMax: add MiniMax-M3 + update Quota Tracker coding/CN (#1631)

## Fixes
- Codex: harden streaming timeouts (stall/connect raised to 60s, configurable per-provider), accept `response.done` event, and always emit a terminal `response.failed` + `[DONE]` for Responses passthrough when a stream closes, stalls, or aborts before a terminal event — prevents codex clients from hanging (#1648, #1680, #1688, #1618)
- Codex: durable OAuth refresh lifecycle (#1664)
- Tunnel: skip virtual interfaces to prevent false netchange watchdog
- Claude: fix forced tool_choice 400 on cc/ OAuth route (#1592)
- Proxy: raise Next client body limit to 128MB via `NINEROUTER_PROXY_CLIENT_MAX_BODY_SIZE` (#1529, #1572)
- MiniMax: echo `reasoning_content` on follow-up turns to avoid 400 (#1543)
- Kiro: handle 400 on tool-bearing history without client tools; add mappable "auto" model slot; fix binary EventStream crash + add models & TTS tool filtering
- Antigravity: passthrough tab-autocomplete + mark default agent slot mandatory
- Qoder: allow `qmodel_latest` model key (#1638)
- Providers: restore one-connection guard for compatible/embedding nodes
- Model-test: route image/STT probes to their real endpoints, harden STT ping; add opencode-go + xiaomi-tokenplan to connection test (#1576, #1628)

## Improvements
- Dashboard: reorganize menu actions across sidebar/header/profile
- Translator: add data-driven coverage, bug-exposing cases, and real provider smoke tests
2026-06-06 16:16:40 +07:00
decolua e9ae21a723 # v0.4.66 (2026-05-29)
## Features
- Add Qoder provider: device-flow OAuth, COSY signing, WAF-bypass body encoding, live model catalog, dashboard quota tracker, 11 models (#1372)
- Add new models: Claude Opus 4.8 (Claude Code), GPT 5.4 Mini (Codex)

## Fixes
- DeepSeek thinking mode: echo `reasoning_content` back on follow-up/tool-call turns so OpenCode-free and custom providers no longer 400 with "reasoning_content must be passed back" (#1543)
- Reasoning injector: match deepseek/kimi model ids case-insensitively (covers custom providers using capitalized model names)
- OpenCode suggested-models: include free models without the `-free` suffix, e.g. `big-pickle` (#1535)

## Improvements
- Codex: trim sunset models, keep gpt-5.5 / gpt-5.4 / gpt-5.3-codex family, add gpt-5.4-mini
- volcengine-ark: refresh model list (add DeepSeek-V4-Flash/Pro, drop EOL entries)
- Lower stream stall timeout 35s → 30s for faster hang detection
2026-05-29 17:48:01 +07:00
DelcadoandClaude Opus 4.8 88224b80ca fix: never route GitHub Copilot Gemini/Claude models to /responses (#1062) (#1536)
GitHub Copilot's /responses endpoint only serves OpenAI (gpt/codex)
models. gemini-3.1-pro-preview was failing on /chat/completions with a
"not supported" error, getting cached as a codex model, then escalated
to /responses where it 400s with "does not support Responses API".

Add GithubExecutor.supportsResponsesEndpoint() and gate both the cached
/responses route and the 400-fallback on it, so Gemini/Claude always
stay on /chat/completions and the real upstream error surfaces.

Adds tests/unit/github-responses-routing.test.js (5 tests).

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-29 15:40:42 +07:00
decolua 9742074b38 # v0.4.63 (2026-05-26)
## Fixes
- proxyFetch: restore missing `Readable` import causing runtime `ReferenceError` in DNS-bypass fetch path

## Improvements
- Lower stream stall timeout from 60s → 35s for faster hang detection
2026-05-26 23:16:21 +07:00
decolua ac2fee7305 # v0.4.62 (2026-05-26)
## Fixes
- Codex: auto-retry when upstream drops mid-stream (no more hangs)
- Codex: fix random 400/404 errors, tool-calling failures, and unstable prompt cache
- MITM: support Antigravity 2.x
- Sanitize Read tool args to prevent retry loops from non-Anthropic models (#1144)
- Implement json_schema fallback for OpenAI-compatible providers without native Structured Output (#1343)
- Strip empty Read pages argument in OpenAI-to-Claude translator (#1354)
- Forward Gemini output dimensions for embeddings (#1366)
- Resolve setState-in-effect errors in dashboard components (#1362)
- Gemini CLI: reuse stored OAuth project IDs for quota checks and show clearer setup guidance when the project is missing (#1271, #1428)
2026-05-26 13:15:59 +07:00
decolua 0065bbbdfd # v0.4.62 (2026-05-26)
## Fixes
- Codex: auto-retry when upstream drops mid-stream (no more hangs)
- Codex: fix random 400/404 errors, tool-calling failures, and unstable prompt cache
- MITM: support Antigravity 2.x (updated IDE version detection and DNS/cert flow)
- Sanitize Read tool args to prevent retry loops from non-Anthropic models (#1144)
- Implement json_schema fallback for OpenAI-compatible providers without native Structured Output (#1343)
- Strip empty Read pages argument in OpenAI-to-Claude translator (#1354)
- Forward Gemini output dimensions for embeddings (#1366)
- Resolve setState-in-effect errors in dashboard components (#1362)
- Gemini CLI: reuse stored OAuth project IDs for quota checks and show clearer setup guidance when the project is missing (#1271, #1428)
2026-05-26 12:46:30 +07:00
Delcado dcc46f2eee Reuse Gemini CLI project ID for usage (#1428) 2026-05-26 11:23:47 +07:00
decolua e1b821dd53 # v0.4.59 (2026-05-21)
## Fixes
- OAuth: fix login flow on Windows
2026-05-21 14:33:56 +07:00
decolua f9e68631d1 # v0.4.58 (2026-05-21)
## Features
- xAI Grok provider (OAuth, API key, image)
- Provider limits: paginated accounts with page size controls

## Fixes
- Tailscale: fix connection status on Windows (#1300)
- Tunnel: fix false "checking" when tunnel URL is reachable
- Stream: fix pipe errors on client disconnect/abort
2026-05-21 12:31:30 +07:00
decolua 9dde4858e7 # v0.4.55 (2026-05-18)
## Features
- Xiaomi MiMo Token Plan: region selector (Singapore / China / Europe) — keys are cluster-specific
- Antigravity: risk confirmation dialog before first connection
- Gemini CLI: surface upstream retry delay on 429 errors

## Fixes
- MITM: cannot kill process on macOS under sudo (lsof not found in PATH)
- Stream: false-positive stall timeout on Claude reasoning / Kiro responses
- Tunnel: cannot re-enable after disable (stuck state)
- Tunnel: cloudflared error messages now include log tail for easier debugging
- Language switcher: applies selected locale immediately on close (#1234)
- Antigravity OAuth: metadata now matches the official client
2026-05-18 16:29:41 +07:00
decolua 0e4e58930f Update ChangeLog 2026-05-17 16:40:05 +07:00
decolua 593c788c75 ## Fixes
- Fix duplicate tray icon on macOS when hiding to tray
- Fix tray not showing in background mode on macOS
- Fix hide to tray broken on Windows/Linux
- Fix Shutdown button in web UI not working
2026-05-16 14:06:56 +07:00
decolua 30ff4e3fb0 Update change log 2026-05-16 12:40:02 +07:00
decolua cc971f2402 Update tunnel 2026-05-15 18:22:10 +07:00
decolua 9e87935c0e Update Change Log 2026-05-15 12:04:17 +07:00
decolua a28c5ec98b # v0.4.44 (2026-05-15)
## Features
- Add Blackbox provider with `bb` alias (#1143)
- Add Xiaomi token plan provider
- Enhance model select modal UX + modal traffic lights (#1111)
- Default Usage dashboard period to Today (#1141)

## Fixes
- Fix Cowork model selection and Windows CLI packaging (#1129)
- Update provider name retrieval for compatibility provider (#1135)
- Update JWT_SECRET handling
2026-05-15 12:02:32 +07:00
decoluaandCursor 1c3ab7be23 fix(tui): replace enquirer with readline to remove input lag
- Persistent raw mode across menus avoids per-prompt latency
- Suspend raw temporarily for line-buffered text input
- Update CHANGELOG v0.4.41

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-14 11:13:49 +07:00
decoluaandCursor 2190ff062d feat: v0.4.41 - cli-tools UI redesign + jcode integration
- Add jcode CLI tool (#1047) with auto-configuration
- Redesign CLI Tools dashboard: grid 1/2/3 cols + per-tool detail page
- Sync DeepSeek TUI card style + resize icon 1024->128
- Add official logos: amp, jcode, qwen
- Bump version 0.4.39 -> 0.4.41

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-14 10:46:11 +07:00
decolua 58df17aa91 # v0.4.38 (2026-05-13)
## Features
- Add DeepSeek TUI as CLI tool in dashboard (#1088)

## Fixes
- Fix broken Docker image in v0.4.36/v0.4.37 (#1096, #1097)

## Improvements
- Clean Docker tags + clearer pulls badge
2026-05-13 22:54:40 +07:00
decolua 278951dc61 Update changelog 2026-05-13 21:30:38 +07:00
decolua 15153e658d Update CHANGELOG.md 2026-05-13 20:35:59 +07:00
decolua 992f4db4a0 Fix bug 2026-05-13 20:35:42 +07:00
decolua 7ccf8c5e84 # v0.4.36 (2026-05-13)
## Features
- Add MiniMax TTS provider support (#1043)
- Docker images now published on both GHCR & Docker Hub (decolua/9router) — pull from your preferred registry

## Improvements
- Replace browser confirm dialogs with custom ConfirmModal (#1060)

## Fixes
- Fix Docker `Cannot find module 'next'` error in standalone build
- Restore /app/server.js in Docker standalone build (#1064, #1067)
- Fix CLI TUI menu arrow-key escape sequences leaking (^[[A^[[B)
- Switch macOS/Linux tray to systray2 fork (fixes Kaspersky AV false-positive) (#1080)
- Fix zoom controls contrast in topology view (#1066)
2026-05-13 18:22:31 +07:00
decolua 58788a0d31 TUI Source 2026-05-12 20:26:08 +07:00
decolua 42f0736d28 Update changelog 2026-05-12 09:57:02 +07:00
decolua 8f4d29caa4 # v0.4.30 (2026-05-11)
## Features
- MCP stdio→SSE bridge: expose local stdio MCP plugins over SSE (api/mcp/[plugin]/sse, /message)
- Dynamic Linux cert resolution + NSS DB injection (Debian/Arch/Fedora/openSUSE, Chrome/Chromium/Firefox incl. snap) (#1010)
- Cowork tool: expanded settings UI & API
- GitBook docs (DocsContent, DocsLayout)
## Fixes
- OAuth callback postMessage scoped to expected origins (CWE-1385) (#998)
- Re-enable TLS verification on DNS-bypass fetch (CWE-295) (#998)
- Normalize `developer` role → `system` for OpenAI-format providers (Deepseek, Groq, …) (#1011, closes #773)
- Respect `PORT` env in internal model-test fetch (#1014)
- Dropdown text readability in dark theme on usage page (#997)
## Improvements
- Refactor Claude CLI spoof headers into shared constant
- Tool deduper utility in open-sse handlers
2026-05-12 09:19:50 +07:00
decolua 7ad538bcf2 # v0.4.29 (2026-05-10)
## Features
- Add Cline & Kilo Code tool cards
- Tailscale TUN mode for stable Funnel TLS
- Sort APIKEY providers by usage, collapse to top 20

## Improvements
- Local Material Symbols font (no Google Fonts)
- Docker base: Bun → Node 22-alpine
- MITM reads aliases from JSON cache (no native sqlite)
- Stream stall timeout (2 min) in open-sse

## Fixes
- Fal.ai key test: use stable models endpoint
2026-05-10 21:56:40 +07:00
decolua 530dc9cb3b # v0.4.28 (2026-05-10)
## Features
- Add bun:sqlite adapter with automatic runtime detection (Bun/Node)
- Add bulk API key import (format: `name|sk-key`, one per line)
## Fixes
- Fix add API key for custom providers
2026-05-10 08:44:14 +07:00
decoluaandCursor b39eb61c33 chore: release v0.4.27
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-09 22:48:07 +07:00
decolua b184444f34 Update Changelog 2026-05-09 17:52:52 +07:00
decolua dd15d162fc Update changelog 2026-05-07 23:15:48 +07:00
decolua ca84e988c0 Update changelog 2026-05-07 16:48:33 +07:00
decolua 1c8314252b Update Changelog 2026-05-05 10:36:38 +07:00
decolua 1aedf5cfc0 update changelog 2026-05-04 11:30:40 +07:00
decolua a7a4e851a7 Update ChangeLog 2026-05-03 22:13:17 +07:00
decolua a3a0cc8379 Update changelog 2026-05-03 18:06:24 +07:00
decolua ef3abeacf1 Update ChangeLog 2026-05-01 17:06:27 +07:00
decolua cad31a171b Update changelog 2026-04-30 18:02:17 +07:00
decolua b3fb20e237 Update change log 2026-04-29 17:31:57 +07:00
decolua 10e24a1c95 Update ChangeLog 2026-04-28 17:39:31 +07:00
decolua a331c34eab Update changelog 2026-04-25 17:05:17 +07:00
decolua cca615eaff - Cap maximum cooldown for rate limit handling in account unavailability and single-model chat flows
- Dynamic custom model fetching for model selection
2026-04-24 16:14:18 +07:00
decolua c42c0146ab Update changelog 2026-04-24 11:40:39 +07:00
decolua fd8163e26e chore: update CHANGELOG for v0.4.2 and version bump to 0.4.2
- Added support for Azure OpenAI and built-in Volcengine Ark provider.
- Introduced GPT 5.5 model.
- Enhanced retry logic for HTTP status codes.
2026-04-24 10:10:35 +07:00
decolua 2eebcee4fc chore: update CHANGELOG for v0.4.1
Made-with: Cursor
2026-04-23 17:44:35 +07:00
decolua ab7dd63b22 chore: update CHANGELOG and version to 0.3.98
- Added feature to filter context before sending to LLM to save tokens.
- Updated version in package.json to reflect the new release.
2026-04-22 15:44:20 +07:00
decolua e1a219dba6 update change log 2026-04-22 14:27:37 +07:00
decolua 248efacdaa docs: update changelog for v0.3.96
Made-with: Cursor
2026-04-17 12:54:50 +07:00
decolua 75ad0bef8e Refactor error handling and localDb structure, and fix usage tracking bug. 2026-04-17 12:15:10 +07:00
decolua c3a2bd01b7 Update version 2026-04-14 12:58:31 +07:00