Merge pull request #610 from diegosouzapw/release/v3.0.2

chore(release): v3.0.2 — Proxy UI fixes & Connection Tag Grouping
Merge pull request #608 from diegosouzapw/release/v3.0.1
2026-07-28 19:02:49 +03:00 · 2026-03-25 09:08:24 -03:00 · 2026-03-25 09:07:27 -03:00 · 2026-03-25 09:02:38 -03:00 · 2026-03-25 08:54:46 -03:00 · 2026-03-25 08:20:04 -03:00
15 changed files with 620 additions and 210 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,6 +4,79 @@

 ---

+## [3.0.2] — 2026-03-25
+
+### 🚀 Enhancements & Features
+
+#### feat(ui): Connection Tag Grouping
+
+- Added a Tag/Group field to `EditConnectionModal` (stored in `providerSpecificData.tag`) without requiring DB schema migrations.
+- Connections in the provider view now dynamically group by tag with visual dividers.
+- Untagged connections appear first without a header, followed by tagged groups in alphabetical order.
+- The tag grouping automatically applies to the Codex/Copilot/Antigravity Limits section since toggles exist inside connection rows.
+
+### 🐛 Bug Fixes
+
+#### fix(ui): Proxy Management UI Stabilization
+
+- **Missing badges on connection cards:** Fixed by using `resolveProxyForConnection()` rather than static mapping.
+- **Test Connection disabled in saved mode:** Enabled the Test button by resolving proxy config from the saved list.
+- **Config Modal freezing:** Added `onClose()` calls after save/clear to prevent the UI from freezing.
+- **Double usage counting:** `ProxyRegistryManager` now loads usage eagerly on mount with deduplication by `scope` + `scopeId`. Usage counts were replaced with a Test button displaying IP/latency inline.
+
+#### fix(translator): `function_call` prefix stripping
+
+- Repaired an incomplete fix from PR #607 where only `tool_use` blocks stripped Claude's `proxy_` tool prefix. Now, clients using the OpenAI Responses API format will also correctly receive tool tools without the `proxy_` prefix.
+
+---
+
+## [3.0.1] — 2026-03-25
+
+### 🔧 Hotfix Patch — Critical Bug Fixes
+
+Three critical regressions reported by users after the v3.0.0 launch have been resolved.
+
+#### fix(translator): strip `proxy_` prefix in non-streaming Claude responses (#605)
+
+The `proxy_` prefix added by Claude OAuth was only stripped from **streaming** responses. In **non-streaming** mode, `translateNonStreamingResponse` had no access to the `toolNameMap`, causing clients to receive mangled tool names like `proxy_read_file` instead of `read_file`.
+
+**Fix:** Added optional `toolNameMap` parameter to `translateNonStreamingResponse` and applied prefix stripping in the Claude `tool_use` block handler. `chatCore.ts` now passes the map through.
+
+#### fix(validation): add LongCat specialty validator to skip /models probe (#592)
+
+LongCat AI does not expose `GET /v1/models`. The generic `validateOpenAICompatibleProvider` validator fell through to a chat-completions fallback only if `validationModelId` was set, which LongCat doesn't configure. This caused provider validation to fail with a misleading error on add/save.
+
+**Fix:** Added `longcat` to the specialty validators map, probing `/chat/completions` directly and treating any non-auth response as a pass.
+
+#### fix(translator): normalize object tool schemas for Anthropic (#595)
+
+MCP tools (e.g. `pencil`, `computer_use`) forward tool definitions with `{type:"object"}` but without a `properties` field. Anthropic's API rejects these with: `object schema missing properties`.
+
+**Fix:** In `openai-to-claude.ts`, inject `properties: {}` as a safe default when `type` is `"object"` and `properties` is absent.
+
+---
+
+### 🔀 Community PRs Merged (2)
+
+| PR       | Author  | Summary                                                                    |
+| -------- | ------- | -------------------------------------------------------------------------- |
+| **#589** | @flobo3 | docs(i18n): fix Russian translation for Playground and Testbed             |
+| **#591** | @rdself | fix(ui): improve Provider Limits light mode contrast and plan tier display |
+
+---
+
+### ✅ Issues Resolved
+
+`#592` `#595` `#605`
+
+---
+
+### 🧪 Tests
+
+- **926 tests, 0 failures** (unchanged from v3.0.0)
+
+---
+
 ## [3.0.0] — 2026-03-24

 ### 🎉 OmniRoute v3.0.0 — The Free AI Gateway, Now with 67+ Providers
@@ -16,39 +89,39 @@

 ### 🆕 New Providers (+31 since v2.9.5)

-| Provider | Alias | Tier | Notes |
-|----------|-------|------|-------|
-| **OpenCode Zen** | `opencode-zen` | Free | 3 models via `opencode.ai/zen/v1` (PR #530 by @kang-heewon) |
-| **OpenCode Go** | `opencode-go` | Paid | 4 models via `opencode.ai/zen/go/v1` (PR #530 by @kang-heewon) |
-| **LongCat AI** | `lc` | Free | 50M tokens/day (Flash-Lite) + 500K/day (Chat/Thinking) during public beta |
-| **Pollinations AI** | `pol` | Free | No API key needed — GPT-5, Claude, Gemini, DeepSeek V3, Llama 4 (1 req/15s) |
-| **Cloudflare Workers AI** | `cf` | Free | 10K Neurons/day — ~150 LLM responses or 500s Whisper audio, edge inference |
-| **Scaleway AI** | `scw` | Free | 1M free tokens for new accounts — EU/GDPR compliant (Paris) |
-| **AI/ML API** | `aiml` | Free | $0.025/day free credits — 200+ models via single endpoint |
-| **Puter AI** | `pu` | Free | 500+ models (GPT-5, Claude Opus 4, Gemini 3 Pro, Grok 4, DeepSeek V3) |
-| **Alibaba Cloud (DashScope)** | `ali` | Paid | International + China endpoints via `alicode`/`alicode-intl` |
-| **Alibaba Coding Plan** | `bcp` | Paid | Alibaba Model Studio with Anthropic-compatible API |
-| **Kimi Coding (API Key)** | `kmca` | Paid | Dedicated API-key-based Kimi access (separate from OAuth) |
-| **MiniMax Coding** | `minimax` | Paid | International endpoint |
-| **MiniMax (China)** | `minimax-cn` | Paid | China-specific endpoint |
-| **Z.AI (GLM-5)** | `zai` | Paid | Zhipu AI next-gen GLM models |
-| **Vertex AI** | `vertex` | Paid | Google Cloud — Service Account JSON or OAuth access_token |
-| **Ollama Cloud** | `ollamacloud` | Paid | Ollama's hosted API service |
-| **Synthetic** | `synthetic` | Paid | Passthrough models gateway |
-| **Kilo Gateway** | `kg` | Paid | Passthrough models gateway |
-| **Perplexity Search** | `pplx-search` | Paid | Dedicated search-grounded endpoint |
-| **Serper Search** | `serper-search` | Paid | Web search API integration |
-| **Brave Search** | `brave-search` | Paid | Brave Search API integration |
-| **Exa Search** | `exa-search` | Paid | Neural search API integration |
-| **Tavily Search** | `tavily-search` | Paid | AI search API integration |
-| **NanoBanana** | `nb` | Paid | Image generation API |
-| **ElevenLabs** | `el` | Paid | Text-to-speech voice synthesis |
-| **Cartesia** | `cartesia` | Paid | Ultra-fast TTS voice synthesis |
-| **PlayHT** | `playht` | Paid | Voice cloning and TTS |
-| **Inworld** | `inworld` | Paid | AI character voice chat |
-| **SD WebUI** | `sdwebui` | Self-hosted | Stable Diffusion local image generation |
-| **ComfyUI** | `comfyui` | Self-hosted | ComfyUI local workflow node-based generation |
-| **GLM Coding** | `glm` | Paid | BigModel/Zhipu coding-specific endpoint |
+| Provider                      | Alias           | Tier        | Notes                                                                       |
+| ----------------------------- | --------------- | ----------- | --------------------------------------------------------------------------- |
+| **OpenCode Zen**              | `opencode-zen`  | Free        | 3 models via `opencode.ai/zen/v1` (PR #530 by @kang-heewon)                 |
+| **OpenCode Go**               | `opencode-go`   | Paid        | 4 models via `opencode.ai/zen/go/v1` (PR #530 by @kang-heewon)              |
+| **LongCat AI**                | `lc`            | Free        | 50M tokens/day (Flash-Lite) + 500K/day (Chat/Thinking) during public beta   |
+| **Pollinations AI**           | `pol`           | Free        | No API key needed — GPT-5, Claude, Gemini, DeepSeek V3, Llama 4 (1 req/15s) |
+| **Cloudflare Workers AI**     | `cf`            | Free        | 10K Neurons/day — ~150 LLM responses or 500s Whisper audio, edge inference  |
+| **Scaleway AI**               | `scw`           | Free        | 1M free tokens for new accounts — EU/GDPR compliant (Paris)                 |
+| **AI/ML API**                 | `aiml`          | Free        | $0.025/day free credits — 200+ models via single endpoint                   |
+| **Puter AI**                  | `pu`            | Free        | 500+ models (GPT-5, Claude Opus 4, Gemini 3 Pro, Grok 4, DeepSeek V3)       |
+| **Alibaba Cloud (DashScope)** | `ali`           | Paid        | International + China endpoints via `alicode`/`alicode-intl`                |
+| **Alibaba Coding Plan**       | `bcp`           | Paid        | Alibaba Model Studio with Anthropic-compatible API                          |
+| **Kimi Coding (API Key)**     | `kmca`          | Paid        | Dedicated API-key-based Kimi access (separate from OAuth)                   |
+| **MiniMax Coding**            | `minimax`       | Paid        | International endpoint                                                      |
+| **MiniMax (China)**           | `minimax-cn`    | Paid        | China-specific endpoint                                                     |
+| **Z.AI (GLM-5)**              | `zai`           | Paid        | Zhipu AI next-gen GLM models                                                |
+| **Vertex AI**                 | `vertex`        | Paid        | Google Cloud — Service Account JSON or OAuth access_token                   |
+| **Ollama Cloud**              | `ollamacloud`   | Paid        | Ollama's hosted API service                                                 |
+| **Synthetic**                 | `synthetic`     | Paid        | Passthrough models gateway                                                  |
+| **Kilo Gateway**              | `kg`            | Paid        | Passthrough models gateway                                                  |
+| **Perplexity Search**         | `pplx-search`   | Paid        | Dedicated search-grounded endpoint                                          |
+| **Serper Search**             | `serper-search` | Paid        | Web search API integration                                                  |
+| **Brave Search**              | `brave-search`  | Paid        | Brave Search API integration                                                |
+| **Exa Search**                | `exa-search`    | Paid        | Neural search API integration                                               |
+| **Tavily Search**             | `tavily-search` | Paid        | AI search API integration                                                   |
+| **NanoBanana**                | `nb`            | Paid        | Image generation API                                                        |
+| **ElevenLabs**                | `el`            | Paid        | Text-to-speech voice synthesis                                              |
+| **Cartesia**                  | `cartesia`      | Paid        | Ultra-fast TTS voice synthesis                                              |
+| **PlayHT**                    | `playht`        | Paid        | Voice cloning and TTS                                                       |
+| **Inworld**                   | `inworld`       | Paid        | AI character voice chat                                                     |
+| **SD WebUI**                  | `sdwebui`       | Self-hosted | Stable Diffusion local image generation                                     |
+| **ComfyUI**                   | `comfyui`       | Self-hosted | ComfyUI local workflow node-based generation                                |
+| **GLM Coding**                | `glm`           | Paid        | BigModel/Zhipu coding-specific endpoint                                     |

 **Total: 67+ providers** (4 Free, 8 OAuth, 55 API Key) + unlimited OpenAI/Anthropic-Compatible custom providers.

@@ -60,15 +133,15 @@

 Auto-generate and issue OmniRoute API keys programmatically with per-provider and per-account quota enforcement.

-| Endpoint | Method | Description |
-|----------|--------|-------------|
-| `/api/v1/registered-keys` | `POST` | Issue a new key — raw key returned **once only** |
-| `/api/v1/registered-keys` | `GET` | List registered keys (masked) |
-| `/api/v1/registered-keys/{id}` | `GET/DELETE` | Get metadata / Revoke |
-| `/api/v1/quotas/check` | `GET` | Pre-validate quota before issuing |
-| `/api/v1/providers/{id}/limits` | `GET/PUT` | Configure per-provider issuance limits |
-| `/api/v1/accounts/{id}/limits` | `GET/PUT` | Configure per-account issuance limits |
-| `/api/v1/issues/report` | `POST` | Report quota events to GitHub Issues |
+| Endpoint                        | Method       | Description                                      |
+| ------------------------------- | ------------ | ------------------------------------------------ |
+| `/api/v1/registered-keys`       | `POST`       | Issue a new key — raw key returned **once only** |
+| `/api/v1/registered-keys`       | `GET`        | List registered keys (masked)                    |
+| `/api/v1/registered-keys/{id}`  | `GET/DELETE` | Get metadata / Revoke                            |
+| `/api/v1/quotas/check`          | `GET`        | Pre-validate quota before issuing                |
+| `/api/v1/providers/{id}/limits` | `GET/PUT`    | Configure per-provider issuance limits           |
+| `/api/v1/accounts/{id}/limits`  | `GET/PUT`    | Configure per-account issuance limits            |
+| `/api/v1/issues/report`         | `POST`       | Report quota events to GitHub Issues             |

 **Security:** Keys stored as SHA-256 hashes. Raw key shown once on creation, never retrievable again.

@@ -83,6 +156,7 @@ Auto-refreshes model lists for connected providers every **24 hours**. Runs on s
 #### 🔀 Per-Model Combo Routing (#563)

 Map model name patterns (glob) to specific combos for automatic routing:
+
 - `claude-sonnet*` → code-combo, `gpt-4o*` → openai-combo, `gemini-*` → google-combo
 - New `model_combo_mappings` table with glob-to-regex matching
 - Dashboard UI section: "Model Routing Rules" with inline add/edit/toggle/delete
@@ -122,12 +196,14 @@ Full media generation playground at `/dashboard/media`: Image Generation, Video,
 ### 🐛 Bug Fixes (40+)

 #### OAuth & Auth
+
 - **#537** — Gemini CLI OAuth: clear actionable error when `GEMINI_OAUTH_CLIENT_SECRET` missing in Docker
 - **#549** — CLI settings routes now resolve real API key from `keyId` (not masked strings)
 - **#574** — Login no longer freezes after skipping wizard password setup
 - **#506** — Cross-platform `machineId` rewritten (Windows REG.exe → macOS ioreg → Linux → hostname fallback)

 #### Providers & Routing
+
 - **#536** — LongCat AI: fixed `baseUrl` and `authHeader`
 - **#535** — Pinned model override: `body.model` correctly set to `pinnedModel`
 - **#570** — Unprefixed Claude models now resolve to Anthropic provider
@@ -137,6 +213,7 @@ Full media generation playground at `/dashboard/media`: Image Generation, Video,
 - **#511** — `<omniModel>` tag injected into first content chunk (not after `[DONE]`)

 #### CLI & Tools
+
 - **#527** — Claude Code + Codex loop: `tool_result` blocks now converted to text
 - **#524** — OpenCode config saved correctly (XDG_CONFIG_HOME, TOML format)
 - **#522** — API Manager: removed misleading "Copy masked key" button
@@ -146,12 +223,14 @@ Full media generation playground at `/dashboard/media`: Image Generation, Video,
 - **#492** — CLI detects `mise`/`nvm`-managed Node when `app/server.js` missing

 #### Streaming & SSE
+
 - **PR #587** — Revert `resolveDataDir` import in responsesTransformer for Cloudflare Workers compat (@k0valik)
 - **PR #495** — Bottleneck 429 infinite wait: drop waiting jobs on rate limit (@xandr0s)
 - **#483** — Stop trailing `data: null` after `[DONE]` signal
 - **#473** — Zombie SSE streams: timeout reduced 300s → 120s for faster fallback

 #### Media & Transcription
+
 - **Transcription** — Deepgram `video/mp4` → `audio/mp4` MIME mapping, auto language detection, punctuation
 - **TTS** — `[object Object]` error display fixed for ElevenLabs-style nested errors
 - **Upload limits** — Media transcription increased to 2GB (nginx `client_max_body_size 2g` + `maxDuration=300`)
@@ -214,27 +293,27 @@ Full media generation playground at `/dashboard/media`: Image Generation, Video,

 ### 🔀 Community PRs Merged (10)

-| PR | Author | Summary |
-|----|--------|---------|
-| **#587** | @k0valik | fix(sse): revert resolveDataDir import for Cloudflare Workers compat |
-| **#582** | @jay77721 | feat(proxy): model name prefix stripping option |
-| **#581** | @jay77721 | fix(npm): link electron-release to npm-publish workflow |
-| **#578** | @hijak | feat: configurable context length in model metadata |
-| **#575** | @zhangqiang8vip | feat: per-model upstream headers, compat PATCH, chat alignment |
-| **#562** | @coobabm | fix: MCP session management, Claude passthrough, detectFormat |
-| **#561** | @zen0bit | fix(i18n): Czech translation corrections |
-| **#555** | @k0valik | fix(sse): centralized `resolveDataDir()` for path resolution |
-| **#546** | @k0valik | fix(cli): `--version` returning `unknown` on Windows |
-| **#544** | @k0valik | fix(cli): secure CLI tool detection via installation paths |
-| **#542** | @rdself | fix(ui): light mode contrast CSS theme variables |
-| **#530** | @kang-heewon | feat: OpenCode Zen + Go providers with `OpencodeExecutor` |
-| **#512** | @zhangqiang8vip | feat: per-protocol model compatibility (`compatByProtocol`) |
-| **#497** | @zhangqiang8vip | fix: dev-mode HMR resource leaks (ZWS v5) |
-| **#495** | @xandr0s | fix: Bottleneck 429 infinite wait (drop waiting jobs) |
-| **#494** | @zhangqiang8vip | feat: MiniMax developer→system role fix |
-| **#480** | @prakersh | fix: stream flush usage extraction |
-| **#479** | @prakersh | feat: Codex 5.3/5.4 and Anthropic pricing entries |
-| **#475** | @only4copilot | feat(i18n): improved Chinese translation |
+| PR       | Author          | Summary                                                              |
+| -------- | --------------- | -------------------------------------------------------------------- |
+| **#587** | @k0valik        | fix(sse): revert resolveDataDir import for Cloudflare Workers compat |
+| **#582** | @jay77721       | feat(proxy): model name prefix stripping option                      |
+| **#581** | @jay77721       | fix(npm): link electron-release to npm-publish workflow              |
+| **#578** | @hijak          | feat: configurable context length in model metadata                  |
+| **#575** | @zhangqiang8vip | feat: per-model upstream headers, compat PATCH, chat alignment       |
+| **#562** | @coobabm        | fix: MCP session management, Claude passthrough, detectFormat        |
+| **#561** | @zen0bit        | fix(i18n): Czech translation corrections                             |
+| **#555** | @k0valik        | fix(sse): centralized `resolveDataDir()` for path resolution         |
+| **#546** | @k0valik        | fix(cli): `--version` returning `unknown` on Windows                 |
+| **#544** | @k0valik        | fix(cli): secure CLI tool detection via installation paths           |
+| **#542** | @rdself         | fix(ui): light mode contrast CSS theme variables                     |
+| **#530** | @kang-heewon    | feat: OpenCode Zen + Go providers with `OpencodeExecutor`            |
+| **#512** | @zhangqiang8vip | feat: per-protocol model compatibility (`compatByProtocol`)          |
+| **#497** | @zhangqiang8vip | fix: dev-mode HMR resource leaks (ZWS v5)                            |
+| **#495** | @xandr0s        | fix: Bottleneck 429 infinite wait (drop waiting jobs)                |
+| **#494** | @zhangqiang8vip | feat: MiniMax developer→system role fix                              |
+| **#480** | @prakersh       | fix: stream flush usage extraction                                   |
+| **#479** | @prakersh       | feat: Codex 5.3/5.4 and Anthropic pricing entries                    |
+| **#475** | @only4copilot   | feat(i18n): improved Chinese translation                             |

 **Thank you to all contributors!** 🙏

@@ -255,11 +334,11 @@ Full media generation playground at `/dashboard/media`: Image Generation, Video,

 ### 📦 Database Migrations

-| Migration | Description |
-|-----------|-------------|
-| **008** | `registered_keys`, `provider_key_limits`, `account_key_limits` tables |
-| **009** | `requested_model` column in `call_logs` |
-| **010** | `model_combo_mappings` table for per-model combo routing |
+| Migration | Description                                                           |
+| --------- | --------------------------------------------------------------------- |
+| **008**   | `registered_keys`, `provider_key_limits`, `account_key_limits` tables |
+| **009**   | `requested_model` column in `call_logs`                               |
+| **010**   | `model_combo_mappings` table for per-model combo routing              |

 ---

@@ -310,6 +389,7 @@ docker pull diegosouzapw/omniroute:3.0.0
 ## [3.0.0-rc.16] — 2026-03-24

 ### ✨ New Features
+
 - Increased media transcription limits
 - Added Model Context Length to registry metadata
 - Added per-model upstream custom headers via configuration UI
--- a/docs/i18n/ru/README.md
+++ b/docs/i18n/ru/README.md
@@ -386,7 +386,7 @@ Claude Code, Codex, Gemini CLI, Copilot — все используют OAuth 2.
 - **Панель управления унифицированными журналами** — 4 вкладки: журналы запросов, журналы прокси, журналы аудита, консоль.
 - **Консольный просмотр журнала** — просмотрщик в режиме терминала в режиме реального времени с уровнями с цветовой кодировкой, автоматической прокруткой, поиском и фильтрацией.
 - **Журналы прокси-сервера SQLite** — постоянные журналы, сохраняющиеся после перезапуска сервера.
- **Площадка переводчика** — 4 режима отладки: Площадка (перевод формата), Тестер чата (туда и обратно), Тестовый стенд (пакетный), Мониторинг в реальном времени (в режиме реального времени).
+- **Площадка транслятора (Translator Playground)** — 4 режима отладки: Площадка (перевод формата), Тестер чата (туда и обратно), Тестовый стенд (пакетный), Мониторинг в реальном времени (в режиме реального времени).
 - **Запрос телеметрии** — задержка p50/p95/p99 + отслеживание X-Request-Id
 - **Журналирование на основе файлов с ротацией** — перехватчик консоли записывает все в журнал JSON с ротацией на основе размера.

@@ -451,7 +451,7 @@ Claude Code, Codex, Gemini CLI, Copilot — все используют OAuth 2.

 - **Оценки LLM** — тестирование золотого набора с 10 предварительно загруженными вариантами, охватывающими приветствия, математику, географию, генерацию кода, соответствие JSON, перевод, уценку, отказ от безопасности.
 - **4 стратегии сопоставления** — `exact`, `contains`, `regex`, `custom` (функция JS)
- **Тестовый стенд Translator Playground** — пакетное тестирование с несколькими входными данными и ожидаемыми результатами, сравнение между поставщиками.
+- **Тестовый стенд (Testbed)** — пакетное тестирование с несколькими входными данными и ожидаемыми результатами, сравнение между поставщиками.
 - **Тестер чата** — полный цикл с визуальным отображением ответов.
 - **Живой монитор** — поток всех запросов, проходящих через прокси, в реальном времени.

@@ -1016,7 +1016,7 @@ OmniRoute включает встроенный фреймворк оценки

 - Приветствия, математика, география, генерация кода
 - Соответствие формату JSON, перевод, markdown
- Отказ от небезопасного контента, подсчёт, булева логика
+- Отказ от небезопасного контента (Safety refusal), подсчёт, булева логика

 ### Стратегии оценки

--- a/docs/openapi.yaml
+++ b/docs/openapi.yaml
@@ -1,7 +1,7 @@
 openapi: 3.1.0
 info:
  title: OmniRoute API
-  version: 3.0.0
+  version: 3.0.2
  description: |
    OmniRoute is a local-first AI API proxy router. It provides an OpenAI-compatible
    endpoint that routes requests to multiple AI providers with load balancing,
--- a/open-sse/handlers/chatCore.ts
+++ b/open-sse/handlers/chatCore.ts
@@ -223,7 +223,8 @@ export async function handleChatCore({

  const endpointPath = String(clientRawRequest?.endpoint || "");
  const sourceFormat = detectFormatFromEndpoint(body, endpointPath);
-  const isResponsesEndpoint = /\/responses(?=\/|$)/i.test(endpointPath) || /^responses(?=\/|$)/i.test(endpointPath);
+  const isResponsesEndpoint =
+    /\/responses(?=\/|$)/i.test(endpointPath) || /^responses(?=\/|$)/i.test(endpointPath);
  const nativeCodexPassthrough = shouldUseNativeCodexPassthrough({
    provider,
    sourceFormat,
@@ -1067,8 +1068,14 @@ export async function handleChatCore({
    }

    // Translate response to client's expected format (usually OpenAI)
+    // Pass toolNameMap so Claude OAuth proxy_ prefix is stripped in tool_use blocks (#605)
    let translatedResponse = needsTranslation(targetFormat, sourceFormat)
-      ? translateNonStreamingResponse(responseBody, targetFormat, sourceFormat)
+      ? translateNonStreamingResponse(
+          responseBody,
+          targetFormat,
+          sourceFormat,
+          toolNameMap as Map<string, string> | null
+        )
      : responseBody;

    // T26: Strip markdown code blocks if provider format is Claude
--- a/open-sse/handlers/responseTranslator.ts
+++ b/open-sse/handlers/responseTranslator.ts
@@ -68,11 +68,14 @@ function findBestMessageText(output: unknown[]): {
 /**
 * Translate non-streaming response to OpenAI format
 * Handles different provider response formats (Gemini, Claude, etc.)
+ *
+ * @param toolNameMap - Optional Map<prefixedName, originalName> for Claude OAuth tool name stripping
 */
 export function translateNonStreamingResponse(
  responseBody: unknown,
  targetFormat: string,
-  sourceFormat: string
+  sourceFormat: string,
+  toolNameMap?: Map<string, string> | null
 ): unknown {
  // If already in source format (usually OpenAI), return as-is
  if (targetFormat === sourceFormat || targetFormat === FORMATS.OPENAI) {
@@ -122,11 +125,14 @@ export function translateNonStreamingResponse(
          typeof itemObj.arguments === "string"
            ? itemObj.arguments
            : JSON.stringify(itemObj.arguments || {});
+        const rawName = toString(itemObj.name);
+        // Strip Claude OAuth proxy_ prefix using toolNameMap (mirrors tool_use fix for #605)
+        const resolvedName = toolNameMap?.get(rawName) ?? rawName;
        toolCalls.push({
          id: callId,
          type: "function",
          function: {
-            name: toString(itemObj.name),
+            name: resolvedName,
            arguments: fnArgs,
          },
        });
@@ -334,11 +340,15 @@ export function translateNonStreamingResponse(
      } else if (blockObj.type === "thinking") {
        thinkingContent += toString(blockObj.thinking);
      } else if (blockObj.type === "tool_use") {
+        // Strip Claude OAuth tool name prefix (proxy_) using the map from request translation.
+        // Fallback to raw name if block wasn't prefixed (disableToolPrefix path).
+        const rawName = toString(blockObj.name);
+        const strippedName = toolNameMap?.get(rawName) ?? rawName;
        toolCalls.push({
          id: toString(blockObj.id, `call_${Date.now()}_${toolCalls.length}`),
          type: "function",
          function: {
-            name: toString(blockObj.name),
+            name: strippedName,
            arguments: JSON.stringify(blockObj.input || {}),
          },
        });
--- a/open-sse/services/usage.ts
+++ b/open-sse/services/usage.ts
@@ -86,7 +86,8 @@ function toDisplayLabel(value: string): string {
    .filter(Boolean)
    .map((part) => {
      if (/^pro\+$/i.test(part)) return "Pro+";
-      if (/^[a-z]{2,}$/.test(part)) return part.charAt(0).toUpperCase() + part.slice(1).toLowerCase();
+      if (/^[a-z]{2,}$/.test(part))
+        return part.charAt(0).toUpperCase() + part.slice(1).toLowerCase();
      return part;
    })
    .join(" ")
@@ -200,7 +201,9 @@ async function getGitHubUsage(accessToken, providerSpecificData) {
    if (dataRecord.quota_snapshots) {
      // Paid plan format
      const snapshots = toRecord(dataRecord.quota_snapshots);
-      const resetAt = parseResetTime(getFieldValue(dataRecord, "quota_reset_date", "quotaResetDate"));
+      const resetAt = parseResetTime(
+        getFieldValue(dataRecord, "quota_reset_date", "quotaResetDate")
+      );
      const premiumQuota = formatGitHubQuotaSnapshot(snapshots.premium_interactions, resetAt);
      const chatQuota = formatGitHubQuotaSnapshot(snapshots.chat, resetAt);
      const completionsQuota = formatGitHubQuotaSnapshot(snapshots.completions, resetAt);
@@ -225,7 +228,11 @@ async function getGitHubUsage(accessToken, providerSpecificData) {
      // Free/limited plan format
      const monthlyQuotas = toRecord(dataRecord.monthly_quotas);
      const usedQuotas = toRecord(dataRecord.limited_user_quotas);
-      const resetDate = getFieldValue(dataRecord, "limited_user_reset_date", "limitedUserResetDate");
+      const resetDate = getFieldValue(
+        dataRecord,
+        "limited_user_reset_date",
+        "limitedUserResetDate"
+      );
      const resetAt = parseResetTime(resetDate);
      const quotas: Record<string, UsageQuota> = {};

@@ -327,11 +334,7 @@ function inferGitHubPlanName(data: JsonRecord, premiumQuota: UsageQuota | null):
    toNumber(getFieldValue(monthlyQuotas, "premium_interactions", "premiumInteractions"), 0);
  const chatTotal = toNumber(getFieldValue(monthlyQuotas, "chat", "chat"), 0);

-  if (
-    combined.includes("PRO+") ||
-    combined.includes("PRO_PLUS") ||
-    combined.includes("PROPLUS")
-  ) {
+  if (combined.includes("PRO+") || combined.includes("PRO_PLUS") || combined.includes("PROPLUS")) {
    return "Copilot Pro+";
  }
  if (combined.includes("ENTERPRISE")) return "Copilot Enterprise";
@@ -655,8 +658,18 @@ async function getClaudeUsage(accessToken) {
        }
      }

+      // Try to extract plan tier from the OAuth response
+      const planRaw =
+        typeof data.tier === "string"
+          ? data.tier
+          : typeof data.plan === "string"
+            ? data.plan
+            : typeof data.subscription_type === "string"
+              ? data.subscription_type
+              : null;
+
      return {
-        plan: "Claude Code",
+        plan: planRaw || "Claude Code",
        quotas,
        extraUsage: data.extra_usage ?? null,
      };
--- a/open-sse/translator/request/openai-to-claude.ts
+++ b/open-sse/translator/request/openai-to-claude.ts
@@ -259,11 +259,19 @@ export function openaiToClaudeRequest(model, body, stream) {
        toolNameMap.set(toolName, originalName);
      }

+      // Normalize input_schema: Anthropic requires `properties` when type is "object" (#595).
+      // MCP tools (e.g. pencil, computer_use) may omit properties on object-type schemas.
+      const rawSchema: Record<string, unknown> =
+        toolData.parameters || toolData.input_schema || { type: "object", properties: {}, required: [] };
+      const normalizedSchema =
+        rawSchema.type === "object" && !rawSchema.properties
+          ? { ...rawSchema, properties: {} }
+          : rawSchema;
+
      return {
        name: toolName,
        description: toolData.description || "",
-        input_schema: toolData.parameters ||
-          toolData.input_schema || { type: "object", properties: {}, required: [] },
+        input_schema: normalizedSchema,
      };
    });

--- a/package-lock.json
+++ b/package-lock.json
@@ -1,12 +1,12 @@
 {
  "name": "omniroute",
-  "version": "3.0.0",
+  "version": "3.0.2",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "omniroute",
-      "version": "3.0.0",
+      "version": "3.0.2",
      "hasInstallScript": true,
      "license": "MIT",
      "workspaces": [
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
  "name": "omniroute",
-  "version": "3.0.0",
+  "version": "3.0.2",
  "description": "Smart AI Router with auto fallback — route to FREE & cheap models, zero downtime. Works with Cursor, Cline, Claude Desktop, Codex, and any OpenAI-compatible tool.",
  "type": "module",
  "bin": {
--- a/src/app/(dashboard)/dashboard/providers/[id]/page.tsx
+++ b/src/app/(dashboard)/dashboard/providers/[id]/page.tsx
@@ -802,6 +802,9 @@ export default function ProviderDetailPage() {
  const userDismissed = useRef(false);
  const [proxyTarget, setProxyTarget] = useState(null);
  const [proxyConfig, setProxyConfig] = useState(null);
+  const [connProxyMap, setConnProxyMap] = useState<
+    Record<string, { proxy: any; level: string } | null>
+  >({});
  const [importingModels, setImportingModels] = useState(false);
  const [showImportModal, setShowImportModal] = useState(false);
  const [importProgress, setImportProgress] = useState({
@@ -938,18 +941,48 @@ export default function ProviderDetailPage() {
  useEffect(() => {
    fetchConnections();
    fetchAliases();
-    // Load proxy config for visual indicators
+    // Load proxy config for visual indicators (provider-level button)
    fetch("/api/settings/proxy")
      .then((r) => (r.ok ? r.json() : null))
      .then((c) => setProxyConfig(c))
      .catch(() => {});
  }, [fetchConnections, fetchAliases]);

+  const loadConnProxies = useCallback(async (conns: { id?: string }[]) => {
+    if (!conns.length) return;
+    try {
+      const results = await Promise.all(
+        conns
+          .filter((c) => c.id)
+          .map((c) =>
+            fetch(`/api/settings/proxy?resolve=${encodeURIComponent(c.id!)}`, { cache: "no-store" })
+              .then((r) => (r.ok ? r.json() : null))
+              .then((data) => [c.id!, data] as [string, any])
+              .catch(() => [c.id!, null] as [string, any])
+          )
+      );
+      const map: Record<string, { proxy: any; level: string } | null> = {};
+      for (const [id, data] of results) {
+        map[id] = data?.proxy ? data : null;
+      }
+      setConnProxyMap(map);
+    } catch {
+      // ignore
+    }
+  }, []);
+
  useEffect(() => {
    if (loading || isSearchProvider) return;
    fetchProviderModelMeta();
  }, [loading, isSearchProvider, fetchProviderModelMeta]);

+  // Load per-connection effective proxy (handles registry assignments)
+  useEffect(() => {
+    if (!loading && connections.length > 0) {
+      void loadConnProxies(connections);
+    }
+  }, [loading, connections, loadConnProxies]);
+
  // Auto-open Add Connection modal when no connections exist (better UX)
  // Only fires once on initial load, not on HMR remounts or after user dismissal
  useEffect(() => {
@@ -1930,68 +1963,153 @@ export default function ProviderDetailPage() {
            )}
          </div>
        ) : (
-          <div className="flex flex-col divide-y divide-black/[0.03] dark:divide-white/[0.03]">
-            {connections
-              .sort((a, b) => (a.priority || 0) - (b.priority || 0))
-              .map((conn, index) => (
-                <ConnectionRow
-                  key={conn.id}
-                  connection={conn}
-                  isOAuth={isOAuth}
-                  isFirst={index === 0}
-                  isLast={index === connections.length - 1}
-                  onMoveUp={() => handleSwapPriority(conn, connections[index - 1])}
-                  onMoveDown={() => handleSwapPriority(conn, connections[index + 1])}
-                  onToggleActive={(isActive) => handleUpdateConnectionStatus(conn.id, isActive)}
-                  onToggleRateLimit={(enabled) => handleToggleRateLimit(conn.id, enabled)}
-                  isCodex={providerId === "codex"}
-                  onToggleCodex5h={(enabled) => handleToggleCodexLimit(conn.id, "use5h", enabled)}
-                  onToggleCodexWeekly={(enabled) =>
-                    handleToggleCodexLimit(conn.id, "useWeekly", enabled)
-                  }
-                  onRetest={() => handleRetestConnection(conn.id)}
-                  isRetesting={retestingId === conn.id}
-                  onEdit={() => {
-                    setSelectedConnection(conn);
-                    setShowEditModal(true);
-                  }}
-                  onDelete={() => handleDelete(conn.id)}
-                  onReauth={isOAuth ? () => setShowOAuthModal(true) : undefined}
-                  onRefreshToken={isOAuth ? () => handleRefreshToken(conn.id) : undefined}
-                  isRefreshing={refreshingId === conn.id}
-                  onProxy={() =>
-                    setProxyTarget({
-                      level: "key",
-                      id: conn.id,
-                      label: conn.name || conn.email || conn.id,
-                    })
-                  }
-                  hasProxy={
-                    !!(
-                      proxyConfig?.keys?.[conn.id] ||
-                      proxyConfig?.providers?.[providerId] ||
-                      proxyConfig?.global
-                    )
-                  }
-                  proxySource={
-                    proxyConfig?.keys?.[conn.id]
-                      ? "key"
-                      : proxyConfig?.providers?.[providerId]
-                        ? "provider"
-                        : proxyConfig?.global
-                          ? "global"
-                          : null
-                  }
-                  proxyHost={
-                    (
-                      proxyConfig?.keys?.[conn.id] ||
-                      proxyConfig?.providers?.[providerId] ||
-                      proxyConfig?.global
-                    )?.host || null
-                  }
-                />
-              ))}
-          </div>
+          (() => {
+            // Group connections by tag (providerSpecificData.tag)
+            const sorted = [...connections].sort((a, b) => (a.priority || 0) - (b.priority || 0));
+            const hasAnyTag = sorted.some((c) => c.providerSpecificData?.tag as string | undefined);
+
+            if (!hasAnyTag) {
+              // No tags — render flat list as before
+              return (
+                <div className="flex flex-col divide-y divide-black/[0.03] dark:divide-white/[0.03]">
+                  {sorted.map((conn, index) => (
+                    <ConnectionRow
+                      key={conn.id}
+                      connection={conn}
+                      isOAuth={isOAuth}
+                      isFirst={index === 0}
+                      isLast={index === sorted.length - 1}
+                      onMoveUp={() => handleSwapPriority(conn, sorted[index - 1])}
+                      onMoveDown={() => handleSwapPriority(conn, sorted[index + 1])}
+                      onToggleActive={(isActive) => handleUpdateConnectionStatus(conn.id, isActive)}
+                      onToggleRateLimit={(enabled) => handleToggleRateLimit(conn.id, enabled)}
+                      isCodex={providerId === "codex"}
+                      onToggleCodex5h={(enabled) =>
+                        handleToggleCodexLimit(conn.id, "use5h", enabled)
+                      }
+                      onToggleCodexWeekly={(enabled) =>
+                        handleToggleCodexLimit(conn.id, "useWeekly", enabled)
+                      }
+                      onRetest={() => handleRetestConnection(conn.id)}
+                      isRetesting={retestingId === conn.id}
+                      onEdit={() => {
+                        setSelectedConnection(conn);
+                        setShowEditModal(true);
+                      }}
+                      onDelete={() => handleDelete(conn.id)}
+                      onReauth={isOAuth ? () => setShowOAuthModal(true) : undefined}
+                      onRefreshToken={isOAuth ? () => handleRefreshToken(conn.id) : undefined}
+                      isRefreshing={refreshingId === conn.id}
+                      onProxy={() =>
+                        setProxyTarget({
+                          level: "key",
+                          id: conn.id,
+                          label: conn.name || conn.email || conn.id,
+                        })
+                      }
+                      hasProxy={!!connProxyMap[conn.id]?.proxy}
+                      proxySource={connProxyMap[conn.id]?.level || null}
+                      proxyHost={connProxyMap[conn.id]?.proxy?.host || null}
+                    />
+                  ))}
+                </div>
+              );
+            }
+
+            // Build ordered tag groups: untagged first, then alphabetically
+            const groupMap = new Map<string, typeof sorted>();
+            for (const conn of sorted) {
+              const tag = (conn.providerSpecificData?.tag as string | undefined)?.trim() || "";
+              if (!groupMap.has(tag)) groupMap.set(tag, []);
+              groupMap.get(tag)!.push(conn);
+            }
+            const groupKeys = Array.from(groupMap.keys()).sort((a, b) => {
+              if (a === "") return -1;
+              if (b === "") return 1;
+              return a.localeCompare(b);
+            });
+
+            return (
+              <div className="flex flex-col gap-0">
+                {groupKeys.map((tag, gi) => {
+                  const groupConns = groupMap.get(tag)!;
+                  return (
+                    <div
+                      key={tag || "__untagged__"}
+                      className={
+                        gi > 0
+                          ? "border-t border-black/[0.06] dark:border-white/[0.06] mt-1 pt-1"
+                          : ""
+                      }
+                    >
+                      {tag && (
+                        <div className="flex items-center gap-2 px-3 pt-2 pb-1">
+                          <span className="material-symbols-outlined text-[13px] text-text-muted/50">
+                            label
+                          </span>
+                          <span className="text-[11px] font-semibold uppercase tracking-widest text-text-muted/60 select-none">
+                            {tag}
+                          </span>
+                          <div className="flex-1 h-px bg-black/[0.04] dark:bg-white/[0.04]" />
+                          <span className="text-[10px] text-text-muted/40">
+                            {groupConns.length}
+                          </span>
+                        </div>
+                      )}
+                      <div className="flex flex-col divide-y divide-black/[0.03] dark:divide-white/[0.03]">
+                        {groupConns.map((conn, index) => (
+                          <ConnectionRow
+                            key={conn.id}
+                            connection={conn}
+                            isOAuth={isOAuth}
+                            isFirst={gi === 0 && index === 0}
+                            isLast={gi === groupKeys.length - 1 && index === groupConns.length - 1}
+                            onMoveUp={() =>
+                              handleSwapPriority(conn, sorted[sorted.indexOf(conn) - 1])
+                            }
+                            onMoveDown={() =>
+                              handleSwapPriority(conn, sorted[sorted.indexOf(conn) + 1])
+                            }
+                            onToggleActive={(isActive) =>
+                              handleUpdateConnectionStatus(conn.id, isActive)
+                            }
+                            onToggleRateLimit={(enabled) => handleToggleRateLimit(conn.id, enabled)}
+                            isCodex={providerId === "codex"}
+                            onToggleCodex5h={(enabled) =>
+                              handleToggleCodexLimit(conn.id, "use5h", enabled)
+                            }
+                            onToggleCodexWeekly={(enabled) =>
+                              handleToggleCodexLimit(conn.id, "useWeekly", enabled)
+                            }
+                            onRetest={() => handleRetestConnection(conn.id)}
+                            isRetesting={retestingId === conn.id}
+                            onEdit={() => {
+                              setSelectedConnection(conn);
+                              setShowEditModal(true);
+                            }}
+                            onDelete={() => handleDelete(conn.id)}
+                            onReauth={isOAuth ? () => setShowOAuthModal(true) : undefined}
+                            onRefreshToken={isOAuth ? () => handleRefreshToken(conn.id) : undefined}
+                            isRefreshing={refreshingId === conn.id}
+                            onProxy={() =>
+                              setProxyTarget({
+                                level: "key",
+                                id: conn.id,
+                                label: conn.name || conn.email || conn.id,
+                              })
+                            }
+                            hasProxy={!!connProxyMap[conn.id]?.proxy}
+                            proxySource={connProxyMap[conn.id]?.level || null}
+                            proxyHost={connProxyMap[conn.id]?.proxy?.host || null}
+                          />
+                        ))}
+                      </div>
+                    </div>
+                  );
+                })}
+              </div>
+            );
+          })()
        )}
      </Card>

@@ -2188,6 +2306,7 @@ export default function ProviderDetailPage() {
          level={proxyTarget.level}
          levelId={proxyTarget.id}
          levelLabel={proxyTarget.label}
+          onSaved={() => void loadConnProxies(connections)}
        />
      )}
      {/* Import Progress Modal */}
@@ -4130,6 +4249,7 @@ function EditConnectionModal({ isOpen, connection, onSave, onClose }: EditConnec
    baseUrl: "",
    region: "",
    validationModelId: "",
+    tag: "",
  });
  const [testing, setTesting] = useState(false);
  const [testResult, setTestResult] = useState(null);
@@ -4159,6 +4279,7 @@ function EditConnectionModal({ isOpen, connection, onSave, onClose }: EditConnec
        baseUrl: existingBaseUrl || (isBailian ? defaultBailianUrl : ""),
        region: existingRegion || (isVertex ? defaultRegion : ""),
        validationModelId: (connection.providerSpecificData?.validationModelId as string) || "",
+        tag: (connection.providerSpecificData?.tag as string) || "",
      });
      // Load existing extra keys from providerSpecificData
      const existing = connection.providerSpecificData?.extraApiKeys;
@@ -4282,6 +4403,7 @@ function EditConnectionModal({ isOpen, connection, onSave, onClose }: EditConnec
        updates.providerSpecificData = {
          ...(connection.providerSpecificData || {}),
          extraApiKeys: extraApiKeys.filter((k) => k.trim().length > 0),
+          tag: formData.tag.trim() || undefined,
        };
        if (formData.validationModelId) {
          updates.providerSpecificData.validationModelId = formData.validationModelId;
@@ -4292,6 +4414,12 @@ function EditConnectionModal({ isOpen, connection, onSave, onClose }: EditConnec
        } else if (isVertex) {
          updates.providerSpecificData.region = formData.region;
        }
+      } else {
+        // Also persist tag for OAuth accounts
+        updates.providerSpecificData = {
+          ...(connection.providerSpecificData || {}),
+          tag: formData.tag.trim() || undefined,
+        };
      }
      const error = (await onSave(updates)) as void | unknown;
      if (error) {
@@ -4322,6 +4450,13 @@ function EditConnectionModal({ isOpen, connection, onSave, onClose }: EditConnec
          onChange={(e) => setFormData({ ...formData, name: e.target.value })}
          placeholder={isOAuth ? t("accountName") : t("productionKey")}
        />
+        <Input
+          label="Tag / Group"
+          value={formData.tag}
+          onChange={(e) => setFormData({ ...formData, tag: e.target.value })}
+          placeholder="e.g. personal, work, team-a"
+          hint="Used to group accounts in the provider view"
+        />
        {isOAuth && connection.email && (
          <div className="bg-sidebar/50 p-3 rounded-lg">
            <p className="text-sm text-text-muted mb-1">{t("email")}</p>
--- a/src/app/(dashboard)/dashboard/settings/components/ProxyRegistryManager.tsx
+++ b/src/app/(dashboard)/dashboard/settings/components/ProxyRegistryManager.tsx
@@ -27,6 +27,14 @@ type HealthInfo = {
  lastSeenAt: string | null;
 };

+type TestResult = {
+  success: boolean;
+  publicIp?: string;
+  latencyMs?: number;
+  country?: string;
+  error?: string;
+};
+
 const EMPTY_FORM = {
  id: "",
  name: "",
@@ -51,6 +59,8 @@ export default function ProxyRegistryManager() {

  const [usageById, setUsageById] = useState<Record<string, UsageInfo>>({});
  const [healthById, setHealthById] = useState<Record<string, HealthInfo>>({});
+  const [testById, setTestById] = useState<Record<string, TestResult | null>>({});
+  const [testingId, setTestingId] = useState<string | null>(null);
  const [migrating, setMigrating] = useState(false);
  const [bulkOpen, setBulkOpen] = useState(false);
  const [bulkSaving, setBulkSaving] = useState(false);
@@ -75,6 +85,36 @@ export default function ProxyRegistryManager() {
    }
  }, []);

+  const loadAllUsage = useCallback(async (proxyIds: string[]) => {
+    if (!proxyIds.length) return;
+    try {
+      const results = await Promise.all(
+        proxyIds.map((id) =>
+          fetch(`/api/settings/proxies/assignments?proxyId=${encodeURIComponent(id)}`)
+            .then((r) => (r.ok ? r.json() : null))
+            .then((data) => {
+              const rawAssignments: Array<{ scope: string; scopeId: string | null }> =
+                Array.isArray(data?.items) ? data.items : [];
+              // Deduplicate by scope+scopeId — prevents double-counting when both
+              // a provider-scope and account-scope row exist for the same proxy
+              const seen = new Set<string>();
+              const assignments = rawAssignments.filter((a) => {
+                const key = `${a.scope}:${a.scopeId ?? ""}`;
+                if (seen.has(key)) return false;
+                seen.add(key);
+                return true;
+              });
+              return [id, { count: assignments.length, assignments }] as [string, UsageInfo];
+            })
+            .catch(() => [id, { count: 0, assignments: [] }] as [string, UsageInfo])
+        )
+      );
+      setUsageById(Object.fromEntries(results));
+    } catch {
+      // ignore
+    }
+  }, []);
+
  const load = useCallback(async () => {
    setLoading(true);
    setError(null);
@@ -86,15 +126,18 @@ export default function ProxyRegistryManager() {
        setItems([]);
        return;
      }
-      setItems(Array.isArray(data?.items) ? data.items : []);
+      const loaded: ProxyItem[] = Array.isArray(data?.items) ? data.items : [];
+      setItems(loaded);
+      const ids = loaded.map((p) => p.id).filter(Boolean);
      void loadHealth();
+      void loadAllUsage(ids);
    } catch (e: any) {
      setError(e?.message || "Failed to load proxy registry");
      setItems([]);
    } finally {
      setLoading(false);
    }
-  }, [loadHealth]);
+  }, [loadHealth, loadAllUsage]);

  useEffect(() => {
    void load();
@@ -130,22 +173,63 @@ export default function ProxyRegistryManager() {
  const loadUsage = async (proxyId: string) => {
    try {
      const res = await fetch(
-        `/api/settings/proxies?id=${encodeURIComponent(proxyId)}&whereUsed=1`
+        `/api/settings/proxies/assignments?proxyId=${encodeURIComponent(proxyId)}`
      );
      const data = await res.json().catch(() => ({}));
      if (!res.ok) return;
+      const rawAssignments: Array<{ scope: string; scopeId: string | null }> = Array.isArray(
+        data?.items
+      )
+        ? data.items
+        : [];
+      const seen = new Set<string>();
+      const assignments = rawAssignments.filter((a) => {
+        const key = `${a.scope}:${a.scopeId ?? ""}`;
+        if (seen.has(key)) return false;
+        seen.add(key);
+        return true;
+      });
      setUsageById((prev) => ({
        ...prev,
-        [proxyId]: {
-          count: Number(data?.count || 0),
-          assignments: Array.isArray(data?.assignments) ? data.assignments : [],
-        },
+        [proxyId]: { count: assignments.length, assignments },
      }));
    } catch {
      // ignore usage loading errors in UI
    }
  };

+  const handleTestProxy = async (item: ProxyItem) => {
+    if (testingId) return;
+    setTestingId(item.id);
+    setTestById((prev) => ({ ...prev, [item.id]: null }));
+    try {
+      const res = await fetch("/api/settings/proxy/test", {
+        method: "POST",
+        headers: { "Content-Type": "application/json" },
+        body: JSON.stringify({
+          proxy: {
+            type: item.type || "http",
+            host: item.host,
+            port: String(item.port || 8080),
+          },
+        }),
+      });
+      const data = await res.json().catch(() => ({}));
+      if (!res.ok) {
+        setTestById((prev) => ({
+          ...prev,
+          [item.id]: { success: false, error: data?.error?.message || "Test failed" },
+        }));
+        return;
+      }
+      setTestById((prev) => ({ ...prev, [item.id]: { success: true, ...data } }));
+    } catch (e: any) {
+      setTestById((prev) => ({ ...prev, [item.id]: { success: false, error: e?.message } }));
+    } finally {
+      setTestingId(null);
+    }
+  };
+
  const handleSave = async () => {
    if (!form.name.trim() || !form.host.trim()) {
      setError("Name and host are required");
@@ -378,27 +462,47 @@ export default function ProxyRegistryManager() {
                        </span>
                      </td>
                      <td className="py-2 pr-3 text-xs text-text-muted">
-                        {health ? (
-                          <div className="flex flex-col gap-0.5">
-                            <span>{health.successRate ?? 0}% success</span>
-                            <span>{health.avgLatencyMs ?? "-"} ms avg</span>
-                          </div>
-                        ) : (
-                          "-"
-                        )}
+                        <div className="flex flex-col gap-0.5">
+                          {health ? (
+                            <>
+                              <span>{health.successRate ?? 0}% success</span>
+                              <span>{health.avgLatencyMs ?? "-"} ms avg</span>
+                            </>
+                          ) : testById[item.id] ? (
+                            testById[item.id]!.success ? (
+                              <>
+                                <span className="text-emerald-400">
+                                  ✓ {testById[item.id]!.publicIp}
+                                </span>
+                                {testById[item.id]!.latencyMs && (
+                                  <span>{testById[item.id]!.latencyMs}ms</span>
+                                )}
+                              </>
+                            ) : (
+                              <span className="text-red-400">
+                                {testById[item.id]!.error || "failed"}
+                              </span>
+                            )
+                          ) : (
+                            <span>—</span>
+                          )}
+                        </div>
                      </td>
                      <td className="py-2 pr-3 text-xs text-text-muted">
-                        {usage ? `${usage.count} assignment(s)` : "-"}
+                        {usageById[item.id] != null
+                          ? `${usageById[item.id].count} assignment(s)`
+                          : "—"}
                      </td>
                      <td className="py-2">
                        <div className="flex items-center gap-1">
                          <Button
                            size="sm"
                            variant="ghost"
-                            icon="visibility"
-                            onClick={() => void loadUsage(item.id)}
+                            icon="speed"
+                            onClick={() => void handleTestProxy(item)}
+                            loading={testingId === item.id}
                          >
-                            Usage
+                            Test
                          </Button>
                          <Button
                            size="sm"
--- a/src/app/(dashboard)/dashboard/usage/components/ProviderLimits/index.tsx
+++ b/src/app/(dashboard)/dashboard/usage/components/ProviderLimits/index.tsx
@@ -412,24 +412,25 @@ export default function ProviderLimits() {

        <div className="flex items-center gap-2">
          {/* Group by toggle */}
-          <div className="flex rounded-lg border border-white/[0.08] overflow-hidden">
+          <div className="flex rounded-lg border border-border overflow-hidden">
            <button
              onClick={() => handleSetGroupBy("none")}
              className="px-2.5 py-1.5 text-[12px] font-medium cursor-pointer border-none"
              style={{
-                background: groupBy === "none" ? "rgba(255,255,255,0.1)" : "transparent",
-                color: groupBy === "none" ? "var(--text-main)" : "var(--text-muted)",
+                background: groupBy === "none" ? "var(--color-bg-subtle)" : "transparent",
+                color: groupBy === "none" ? "var(--color-text-main)" : "var(--color-text-muted)",
              }}
            >
              {t("viewFlat")}
            </button>
            <button
              onClick={() => handleSetGroupBy("environment")}
-              className="px-2.5 py-1.5 text-[12px] font-medium cursor-pointer border-none border-l border-white/[0.08]"
+              className="px-2.5 py-1.5 text-[12px] font-medium cursor-pointer border-none"
              style={{
-                background: groupBy === "environment" ? "rgba(255,255,255,0.1)" : "transparent",
-                color: groupBy === "environment" ? "var(--text-main)" : "var(--text-muted)",
-                borderLeft: "1px solid rgba(255,255,255,0.08)",
+                background: groupBy === "environment" ? "var(--color-bg-subtle)" : "transparent",
+                color:
+                  groupBy === "environment" ? "var(--color-text-main)" : "var(--color-text-muted)",
+                borderLeft: "1px solid var(--color-border)",
              }}
            >
              {t("viewByEnvironment")}
@@ -442,7 +443,7 @@ export default function ProviderLimits() {
              setAutoRefresh(next);
              localStorage.setItem(LS_AUTO_REFRESH, String(next));
            }}
-            className="flex items-center gap-1.5 px-3 py-1.5 rounded-lg border border-white/[0.08] bg-transparent cursor-pointer text-text-main text-[13px]"
+            className="flex items-center gap-1.5 px-3 py-1.5 rounded-lg border border-border bg-transparent cursor-pointer text-text-main text-[13px]"
          >
            <span
              className="material-symbols-outlined text-[18px]"
@@ -459,7 +460,7 @@ export default function ProviderLimits() {
          <button
            onClick={refreshAll}
            disabled={refreshingAll}
-            className="flex items-center gap-1.5 px-3.5 py-1.5 rounded-lg bg-white/[0.06] border border-white/10 text-text-main text-[13px] disabled:opacity-50 disabled:cursor-not-allowed cursor-pointer"
+            className="flex items-center gap-1.5 px-3.5 py-1.5 rounded-lg bg-bg-subtle border border-border text-text-main text-[13px] disabled:opacity-50 disabled:cursor-not-allowed cursor-pointer"
          >
            <span
              className={`material-symbols-outlined text-[16px] ${refreshingAll ? "animate-spin" : ""}`}
@@ -483,10 +484,10 @@ export default function ProviderLimits() {
              className="inline-flex items-center gap-1.5 px-2.5 py-1 rounded-full text-xs font-semibold cursor-pointer"
              style={{
                border: active
-                  ? "1px solid var(--primary, #E54D5E)"
-                  : "1px solid rgba(255,255,255,0.12)",
-                background: active ? "rgba(249,120,21,0.14)" : "transparent",
-                color: active ? "var(--primary, #E54D5E)" : "var(--text-muted)",
+                  ? "1px solid var(--color-primary, #E54D5E)"
+                  : "1px solid var(--color-border)",
+                background: active ? "rgba(229,77,94,0.1)" : "transparent",
+                color: active ? "var(--color-primary, #E54D5E)" : "var(--color-text-muted)",
              }}
            >
              <span>{t(tier.labelKey)}</span>
@@ -497,10 +498,10 @@ export default function ProviderLimits() {
      </div>

      {/* Account rows */}
-      <div className="rounded-xl border border-white/[0.06] overflow-hidden bg-black/15">
+      <div className="rounded-xl border border-border overflow-hidden bg-bg-subtle">
        {/* Table header */}
        <div
-          className="items-center px-4 py-2.5 border-b border-white/[0.06] text-[11px] font-semibold uppercase tracking-wider text-text-muted"
+          className="items-center px-4 py-2.5 border-b border-border text-[11px] font-semibold uppercase tracking-wider text-text-muted"
          style={{ display: "grid", gridTemplateColumns: "280px 1fr 100px 48px" }}
        >
          <div>{t("account")}</div>
@@ -523,11 +524,11 @@ export default function ProviderLimits() {
            return (
              <div
                key={conn.id}
-                className="items-center px-4 py-3.5 transition-[background] duration-150 hover:bg-white/[0.02]"
+                className="items-center px-4 py-3.5 transition-[background] duration-150 hover:bg-black/[0.03] dark:hover:bg-white/[0.02]"
                style={{
                  display: "grid",
                  gridTemplateColumns: "280px 1fr 100px 48px",
-                  borderBottom: !isLast ? "1px solid rgba(255,255,255,0.04)" : "none",
+                  borderBottom: !isLast ? "1px solid var(--color-border)" : "none",
                }}
              >
                {/* Account Info */}
@@ -614,7 +615,7 @@ export default function ProviderLimits() {
                          ) : null}

                          {/* Progress bar */}
-                          <div className="flex-1 h-1.5 rounded-sm bg-white/[0.06] min-w-[60px] overflow-hidden">
+                          <div className="flex-1 h-1.5 rounded-sm bg-black/[0.06] dark:bg-white/[0.06] min-w-[60px] overflow-hidden">
                            <div
                              className="h-full rounded-sm transition-[width] duration-300 ease-out"
                              style={{
@@ -672,13 +673,10 @@ export default function ProviderLimits() {
          if (groupedConnections) {
            const entries = [...groupedConnections.entries()];
            return entries.map(([groupName, conns]) => (
-              <div
-                key={groupName}
-                className="border border-white/[0.08] rounded-lg overflow-hidden mb-2"
-              >
+              <div key={groupName} className="border border-border rounded-lg overflow-hidden mb-2">
                <button
                  onClick={() => toggleGroup(groupName)}
-                  className="w-full flex items-center gap-2 px-4 py-2.5 bg-white/[0.03] hover:bg-white/[0.05] transition-colors text-left border-none cursor-pointer"
+                  className="w-full flex items-center gap-2 px-4 py-2.5 bg-bg-subtle hover:bg-black/[0.04] dark:hover:bg-white/[0.05] transition-colors text-left border-none cursor-pointer"
                >
                  <span className="material-symbols-outlined text-[16px] text-text-muted">
                    {expandedGroups.has(groupName) ? "expand_less" : "expand_more"}
@@ -689,7 +687,7 @@ export default function ProviderLimits() {
                  <span className="text-[12px] font-semibold text-text-main uppercase tracking-wider flex-1">
                    {groupName}
                  </span>
-                  <span className="text-[11px] text-text-muted bg-white/[0.06] px-2 py-0.5 rounded-full">
+                  <span className="text-[11px] text-text-muted bg-black/[0.04] dark:bg-white/[0.06] px-2 py-0.5 rounded-full">
                    {conns.length}
                  </span>
                </button>
--- a/src/app/(dashboard)/dashboard/usage/components/ProviderLimits/utils.tsx
+++ b/src/app/(dashboard)/dashboard/usage/components/ProviderLimits/utils.tsx
@@ -222,6 +222,11 @@ export function normalizePlanTier(plan) {

  const upper = raw.toUpperCase();

+  // Provider names that are not real plan tiers — treat as unknown
+  if (upper === "CLAUDE CODE" || upper === "KIMI CODING" || upper === "KIRO") {
+    return { key: "unknown", label: raw, variant: "default", rank: 0, raw };
+  }
+
  if (upper.includes("PRO+") || upper.includes("PRO PLUS") || upper.includes("PROPLUS")) {
    return { key: "plus", label: "Pro+", variant: "secondary", rank: 4, raw };
  }
--- a/src/lib/providers/validation.ts
+++ b/src/lib/providers/validation.ts
@@ -652,6 +652,27 @@ export async function validateProviderApiKey({ provider, apiKey, providerSpecifi
    elevenlabs: validateElevenLabsProvider,
    inworld: validateInworldProvider,
    "bailian-coding-plan": validateBailianCodingPlanProvider,
+    // LongCat AI — does not expose /v1/models; validate via chat completions directly (#592)
+    longcat: async ({ apiKey }: any) => {
+      try {
+        const res = await fetch("https://longcat.chat/api/v1/chat/completions", {
+          method: "POST",
+          headers: buildBearerHeaders(apiKey),
+          body: JSON.stringify({
+            model: "longcat",
+            messages: [{ role: "user", content: "test" }],
+            max_tokens: 1,
+          }),
+        });
+        if (res.status === 401 || res.status === 403) {
+          return { valid: false, error: "Invalid API key" };
+        }
+        // Any non-auth response (200, 400, 422) means auth passed
+        return { valid: true, error: null };
+      } catch (error: any) {
+        return { valid: false, error: error.message || "Connection failed" };
+      }
+    },
    // Search providers — use factored validator
    ...Object.fromEntries(
      Object.entries(SEARCH_VALIDATOR_CONFIGS).map(([id, configFn]) => [
--- a/src/shared/components/ProxyConfigModal.tsx
+++ b/src/shared/components/ProxyConfigModal.tsx
@@ -245,6 +245,7 @@ export default function ProxyConfigModal({
        setSelectedProxyId("");
      }
      onSaved?.();
+      onClose();
    } catch (error) {
      console.error("Error saving proxy:", error);
      setFormError(error.message || "Failed to save proxy configuration");
@@ -281,6 +282,7 @@ export default function ProxyConfigModal({
      setSelectedProxyId("");
      setTestResult(null);
      onSaved?.();
+      onClose();
    } catch (error) {
      console.error("Error clearing proxy:", error);
      setFormError(error.message || "Failed to clear proxy configuration");
@@ -290,22 +292,49 @@ export default function ProxyConfigModal({
  };

  const handleTest = async () => {
-    if (mode === "saved") {
-      setFormError("Use custom mode to run manual connection test.");
-      return;
-    }
-    if (!host.trim()) return;
    setFormError(null);
    setTesting(true);
    setTestResult(null);
    try {
-      const proxy = {
-        type: proxyType,
-        host: host.trim(),
-        port: port.trim() || getDefaultPort(proxyType),
-        username: username.trim(),
-        password: password.trim(),
-      };
+      let proxy: {
+        type: string;
+        host: string;
+        port: string;
+        username?: string;
+        password?: string;
+      } | null = null;
+
+      if (mode === "saved") {
+        if (!selectedProxyId) {
+          setFormError("Select a saved proxy first.");
+          setTesting(false);
+          return;
+        }
+        const found = (savedProxies as any[]).find((p: any) => p.id === selectedProxyId);
+        if (!found) {
+          setFormError("Selected proxy not found.");
+          setTesting(false);
+          return;
+        }
+        proxy = {
+          type: found.type || "http",
+          host: found.host || "",
+          port: String(found.port || 8080),
+        };
+      } else {
+        if (!host.trim()) {
+          setTesting(false);
+          return;
+        }
+        proxy = {
+          type: proxyType,
+          host: host.trim(),
+          port: port.trim() || getDefaultPort(proxyType),
+          username: username.trim(),
+          password: password.trim(),
+        };
+      }
+
      const res = await fetch("/api/settings/proxy/test", {
        method: "POST",
        headers: { "Content-Type": "application/json" },
@@ -550,7 +579,7 @@ export default function ProxyConfigModal({
                icon="speed"
                onClick={handleTest}
                loading={testing}
-                disabled={mode !== "custom" || !host.trim()}
+                disabled={mode === "saved" ? !selectedProxyId : !host.trim()}
              >
                Test Connection
              </Button>
Author	SHA1	Message	Date
Diego Rodrigues de Sa e Souza	6e7e04839f	Merge pull request #610 from diegosouzapw/release/v3.0.2 chore(release): v3.0.2 — Proxy UI fixes & Connection Tag Grouping	2026-03-25 09:08:24 -03:00
Diego Rodrigues de Sa e Souza	f62dcc12a0	Merge pull request #608 from diegosouzapw/release/v3.0.1 chore(release): v3.0.1 — hotfix for proxy_ prefix, LongCat validation, and MCP tool schemas	2026-03-25 09:07:27 -03:00
diegosouzapw	bef591c2e6	chore(release): v3.0.2 — proxy ui fixes and connection tag grouping	2026-03-25 09:02:38 -03:00
diegosouzapw	5907296d36	fix: proxy UI bugs, connection tag grouping, and function_call prefix stripping ## Proxy UI Bug Fixes - fix: proxy badge on connection cards now uses resolveProxyForConnection() per-connection (covers registry + config-file assignments) - fix: Test Connection button now works in 'saved' proxy mode by resolving proxy config from savedProxies list - fix: ProxyConfigModal now calls onClose() after save/clear (fixes UI freeze) - fix: ProxyRegistryManager loads usage eagerly on mount with deduplication by scope+scopeId to prevent double-counting; adds per-row Test button ## Connection Tag Grouping (new feature) - feat: add Tag/Group field to EditConnectionModal (stored in providerSpecificData.tag, no DB schema change) - feat: connections list groups by tag with visual dividers when any account has a tag; untagged accounts appear first without header ## Post-merge fix from PR #607 review - fix: function_call blocks in translateNonStreamingResponse now also strip Claude OAuth proxy_ prefix via toolNameMap (kilo-code-bot #607 warning) Affects OpenAI Responses API format path — tool_use was fixed in PR #607 but function_call was missed	2026-03-25 08:54:46 -03:00
diegosouzapw	aa2a7d12be	chore(release): v3.0.1 — hotfix for proxy_ prefix, LongCat validation, and MCP tool schemas	2026-03-25 08:20:04 -03:00
Diego Rodrigues de Sa e Souza	33fee5dcc5	fix: strip proxy_ prefix in non-streaming Claude responses & fix LongCat validation (#605 , #592 ) (#607 ) - fix(translator): pass toolNameMap to translateNonStreamingResponse so Claude OAuth proxy_ prefix is correctly stripped from tool_use block names in non-streaming responses (was only stripped in streaming path) - fix(validation): add LongCat specialty validator that probes /chat/completions directly, bypassing the /v1/models endpoint that LongCat does not expose (#592) Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>	2026-03-25 08:16:46 -03:00
Randi	e9ae50be0c	fix: improve Provider Limits light mode contrast and Claude plan tier display (#591 ) - Replace hardcoded rgba(255,255,255,...) borders/backgrounds with theme-aware CSS variables (--color-border, --color-bg-subtle) for proper light mode contrast - Add dark: variants for hover states and progress bar backgrounds - Fix Claude plan tier: try to extract actual plan from OAuth response instead of hardcoding "Claude Code" - Recognize provider names (Claude Code, Kimi Coding, Kiro) as non-plan-tier values in normalizePlanTier() to avoid showing them as tier badges Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>	2026-03-25 08:16:28 -03:00
Flo	5886c0fd5e	docs(i18n): fix russian translation for playground and testbed (#589 ) Co-authored-by: Vladimir Alabov <vladimir.alabov@bsc-ideas.com>	2026-03-25 08:15:59 -03:00