From 4a1acb1446b152aab66a6427e8246915278ef74a Mon Sep 17 00:00:00 2001 From: diegosouzapw Date: Sun, 1 Mar 2026 21:42:39 -0300 Subject: [PATCH] =?UTF-8?q?feat(release):=20v1.7.3=20=E2=80=94=20model=20d?= =?UTF-8?q?eprecation,=20background=20degradation,=20rate=20limit=20persis?= =?UTF-8?q?tence,=20thinking=20improvements,=20circuit=20breaker?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Features: - Model Deprecation Auto-Forward (10+ built-in aliases + custom via UI) - Background Task Smart Degradation (19 patterns, degradation map) - Rate Limit Persistence (SQLite, 60s debounce, 24h staleness) - thinkingLevel string → budget conversion (high/medium/low/none) - Claude -thinking model auto-injection - Gemini 3.0/3.1 model registry distinction - Token Refresh Circuit Breaker (5 failures → 30min cooldown) Tests: 561 total (40+ new), 0 failures --- CHANGELOG.md | 31 +++ README.md | 4 + README.pt-BR.md | 54 ++-- docs/FEATURES.md | 2 +- open-sse/config/providerRegistry.ts | 14 +- open-sse/services/backgroundTaskDetector.ts | 187 +++++++++++++ open-sse/services/modelDeprecation.ts | 125 +++++++++ open-sse/services/rateLimitManager.ts | 87 ++++++ open-sse/services/thinkingBudget.ts | 106 ++++++- open-sse/services/tokenRefresh.ts | 121 +++++++- package.json | 2 +- .../components/BackgroundDegradationTab.tsx | 261 ++++++++++++++++++ .../settings/components/ModelAliasesTab.tsx | 179 ++++++++++++ .../(dashboard)/dashboard/settings/page.tsx | 4 + .../settings/background-degradation/route.ts | 60 ++++ src/app/api/settings/model-aliases/route.ts | 90 ++++++ tests/unit/background-task-detector.test.mjs | 130 +++++++++ tests/unit/model-deprecation.test.mjs | 105 +++++++ tests/unit/thinking-budget.test.mjs | 125 +++++++++ 19 files changed, 1638 insertions(+), 49 deletions(-) create mode 100644 open-sse/services/backgroundTaskDetector.ts create mode 100644 open-sse/services/modelDeprecation.ts create mode 100644 src/app/(dashboard)/dashboard/settings/components/BackgroundDegradationTab.tsx create mode 100644 src/app/(dashboard)/dashboard/settings/components/ModelAliasesTab.tsx create mode 100644 src/app/api/settings/background-degradation/route.ts create mode 100644 src/app/api/settings/model-aliases/route.ts create mode 100644 tests/unit/background-task-detector.test.mjs create mode 100644 tests/unit/model-deprecation.test.mjs diff --git a/CHANGELOG.md b/CHANGELOG.md index d5da33d7f5..577f7b8a5b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -7,6 +7,37 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 --- +## [1.7.3] — 2026-03-01 + +### ✨ New Features + +- **Model Deprecation Auto-Forward** — New `modelDeprecation.ts` service with 10+ built-in aliases for legacy Gemini, Claude, and OpenAI models. Deprecated model IDs (e.g., `gemini-pro`, `claude-2`) are automatically forwarded to their current replacements. Custom aliases configurable via new Settings → Routing → Model Aliases UI tab with full CRUD API (`/api/settings/model-aliases`) +- **Background Task Smart Degradation** — New `backgroundTaskDetector.ts` service detects background/utility requests (title generation, summarization, etc.) via 19 system prompt patterns and `X-Request-Priority` header, and automatically reroutes them to cheaper models. Configurable degradation map and detection patterns via new Settings → Routing → Background Degradation UI tab. Disabled by default (opt-in) +- **Rate Limit Persistence** — Learned rate limits from API response headers are now persisted to SQLite with 60-second debouncing and restored on startup (24h staleness filter). Rate limits survive server restarts instead of being lost in memory +- **thinkingLevel String Conversion** — `applyThinkingBudget()` now handles string-based `thinkingLevel` inputs (`"high"`, `"medium"`, `"low"`, `"none"`) by converting them to numeric token budgets. Supports `thinkingLevel`, `thinking_level`, and Gemini's `generationConfig.thinkingConfig.thinkingLevel` fields +- **Claude -thinking Model Auto-Injection** — Models ending with `-thinking` suffix (e.g., `claude-opus-4-6-thinking`) automatically get thinking parameters injected to prevent API errors. `hasThinkingCapableModel()` updated to recognize these suffixes +- **Gemini 3.0/3.1 Model Registry** — Updated provider registry to explicitly distinguish Gemini 3.1 (Pro, Flash) from 3.0 Preview variants across `gemini`, `gemini-cli`, and `antigravity` providers with clear naming conventions +- **Token Refresh Circuit Breaker** — Per-provider circuit breaker in `refreshWithRetry()`: 5 consecutive failures trigger a 30-minute cooldown to prevent infinite retry loops. Added 30-second timeout wrapper per refresh attempt. Exported `isProviderBlocked()` and `getCircuitBreakerStatus()` for diagnostics + +### 🧪 Tests + +- **40+ new unit tests** across 3 files: `model-deprecation.test.mjs` (14 tests), `background-task-detector.test.mjs` (14 tests), extended `thinking-budget.test.mjs` (+13 tests). Total suite: **561 tests, 0 failures** + +### 📁 New Files + +| File | Purpose | +| ---------------------------------------------------------------------- | --------------------------------------------------------------------- | +| `open-sse/services/modelDeprecation.ts` | Model deprecation alias resolver with built-in + custom aliases | +| `open-sse/services/backgroundTaskDetector.ts` | Background task detection with pattern matching and model degradation | +| `src/app/api/settings/model-aliases/route.ts` | CRUD API for model alias management | +| `src/app/api/settings/background-degradation/route.ts` | API for background degradation config | +| `src/app/(dashboard)/settings/components/ModelAliasesTab.tsx` | Settings UI for model alias management | +| `src/app/(dashboard)/settings/components/BackgroundDegradationTab.tsx` | Settings UI for background degradation | +| `tests/unit/model-deprecation.test.mjs` | 14 unit tests for model deprecation | +| `tests/unit/background-task-detector.test.mjs` | 14 unit tests for background task detection | + +--- + ## [1.7.2] — 2026-03-01 ### ✨ New Features diff --git a/README.md b/README.md index 7cde85ba01..873c23a49a 100644 --- a/README.md +++ b/README.md @@ -607,6 +607,8 @@ When minimized, OmniRoute lives in your system tray with quick actions: | 🧩 **Custom Models** | Add any model ID to any provider | | 🌐 **Wildcard Router** | Route `provider/*` patterns to any provider dynamically | | 🧠 **Thinking Budget** | Passthrough, auto, custom, and adaptive modes for reasoning models | +| 🔀 **Model Aliases** | Auto-forward deprecated model IDs to current replacements (built-in + custom) | +| ⚡ **Background Degradation** | Auto-route background tasks (titles, summaries) to cheaper models | | 💬 **System Prompt Injection** | Global system prompt applied across all requests | | 📄 **Responses API** | Full OpenAI Responses API (`/v1/responses`) support for Codex | @@ -634,6 +636,8 @@ When minimized, OmniRoute lives in your system tray with quick actions: | 🔒 **TLS Fingerprint Spoofing** | Bypass TLS-based bot detection via wreq-js | | 🌐 **IP Filtering** | Allowlist/blocklist for API access control | | 📊 **Editable Rate Limits** | Configurable RPM, min gap, and max concurrent at system level | +| 💾 **Rate Limit Persistence** | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness | +| 🔄 **Token Refresh Resilience** | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt | | 🛡 **API Endpoint Protection** | Auth gating + provider blocking for the `/models` endpoint | | 🔒 **Proxy Visibility** | Color-coded badges: 🟢 global, 🟡 provider, 🔵 per-connection with IP display | | 🌐 **3-Level Proxy Config** | Configure proxies at global, per-provider, or per-connection level | diff --git a/README.pt-BR.md b/README.pt-BR.md index f9bb92f581..469ee97f87 100644 --- a/README.pt-BR.md +++ b/README.pt-BR.md @@ -574,19 +574,21 @@ Quando minimizado, o OmniRoute fica na bandeja do sistema com ações rápidas: ### 🧠 Roteamento e Inteligência -| Funcionalidade | O que Faz | -| ----------------------------------------- | ------------------------------------------------------------------------------- | -| 🎯 **Fallback Inteligente 4 Tiers** | Auto-roteamento: Assinatura → API Key → Barato → Gratuito | -| 📊 **Rastreamento de Cota em Tempo Real** | Contagem de tokens ao vivo + countdown de reset por provedor | -| 🔄 **Tradução de Formato** | OpenAI ↔ Claude ↔ Gemini ↔ Cursor ↔ Kiro transparente | -| 👥 **Suporte Multi-Conta** | Múltiplas contas por provedor com seleção inteligente | -| 🔄 **Renovação Automática de Token** | Tokens OAuth renovam automaticamente com retry | -| 🎨 **Combos Personalizados** | 6 estratégias: fill-first, round-robin, p2c, random, least-used, cost-optimized | -| 🧩 **Modelos Personalizados** | Adicione qualquer ID de modelo a qualquer provedor | -| 🌐 **Roteador Wildcard** | Roteie padrões `provider/*` para qualquer provedor dinamicamente | -| 🧠 **Budget de Raciocínio** | Modos passthrough, auto, custom e adaptativo para modelos de raciocínio | -| 💬 **Injeção de System Prompt** | System prompt global aplicado em todas as requisições | -| 📄 **API Responses** | Suporte completo à API Responses da OpenAI (`/v1/responses`) para Codex | +| Funcionalidade | O que Faz | +| ----------------------------------------- | ---------------------------------------------------------------------------------- | +| 🎯 **Fallback Inteligente 4 Tiers** | Auto-roteamento: Assinatura → API Key → Barato → Gratuito | +| 📊 **Rastreamento de Cota em Tempo Real** | Contagem de tokens ao vivo + countdown de reset por provedor | +| 🔄 **Tradução de Formato** | OpenAI ↔ Claude ↔ Gemini ↔ Cursor ↔ Kiro transparente | +| 👥 **Suporte Multi-Conta** | Múltiplas contas por provedor com seleção inteligente | +| 🔄 **Renovação Automática de Token** | Tokens OAuth renovam automaticamente com retry | +| 🎨 **Combos Personalizados** | 6 estratégias: fill-first, round-robin, p2c, random, least-used, cost-optimized | +| 🧩 **Modelos Personalizados** | Adicione qualquer ID de modelo a qualquer provedor | +| 🌐 **Roteador Wildcard** | Roteie padrões `provider/*` para qualquer provedor dinamicamente | +| 🧠 **Budget de Raciocínio** | Modos passthrough, auto, custom e adaptativo para modelos de raciocínio | +| � **Aliases de Modelo** | Redireciona IDs de modelos depreciados para substitutos atuais (built-in + custom) | +| ⚡ **Degradação em Background** | Redireciona tarefas em background (títulos, resumos) para modelos mais baratos | +| �💬 **Injeção de System Prompt** | System prompt global aplicado em todas as requisições | +| 📄 **API Responses** | Suporte completo à API Responses da OpenAI (`/v1/responses`) para Codex | ### 🎵 APIs Multi-Modal @@ -603,18 +605,20 @@ Quando minimizado, o OmniRoute fica na bandeja do sistema com ações rápidas: ### 🛡️ Resiliência e Segurança -| Funcionalidade | O que Faz | -| ---------------------------------- | --------------------------------------------------------------------------- | -| 🔌 **Circuit Breaker** | Auto-abertura/fechamento por provedor com limites configuráveis | -| 🛡️ **Anti-Thundering Herd** | Mutex + semáforo rate-limit para provedores com API key | -| 🧠 **Cache Semântico** | Cache de duas camadas (assinatura + semântico) reduz custo e latência | -| ⚡ **Idempotência de Requisição** | Janela de dedup de 5s para requisições duplicadas | -| 🔒 **Spoofing de Fingerprint TLS** | Bypass de detecção de bot via TLS com wreq-js | -| 🌐 **Filtragem de IP** | Allowlist/blocklist para controle de acesso à API | -| 📊 **Rate Limits Editáveis** | RPM, gap mínimo e concorrência máxima configuráveis | -| 🛡 **Proteção de Endpoint API** | Gateway de Auth + bloqueio de provedores para o endpoint `/models` | -| 🔒 **Visibilidade de Proxy** | Badges coloridos: 🟢 global, 🟡 provedor, 🔵 por-conexão com exibição de IP | -| 🌐 **Proxy em 3 Níveis** | Configure proxies em nível global, por provedor ou por conexão | +| Funcionalidade | O que Faz | +| ----------------------------------- | ----------------------------------------------------------------------------- | +| 🔌 **Circuit Breaker** | Auto-abertura/fechamento por provedor com limites configuráveis | +| 🛡️ **Anti-Thundering Herd** | Mutex + semáforo rate-limit para provedores com API key | +| 🧠 **Cache Semântico** | Cache de duas camadas (assinatura + semântico) reduz custo e latência | +| ⚡ **Idempotência de Requisição** | Janela de dedup de 5s para requisições duplicadas | +| 🔒 **Spoofing de Fingerprint TLS** | Bypass de detecção de bot via TLS com wreq-js | +| 🌐 **Filtragem de IP** | Allowlist/blocklist para controle de acesso à API | +| 📊 **Rate Limits Editáveis** | RPM, gap mínimo e concorrência máxima configuráveis | +| 💾 **Persistência de Rate Limits** | Limites aprendidos persistem via SQLite com debounce de 60s + 24h de validade | +| 🔄 **Resiliência de Token Refresh** | Circuit breaker por provedor (5 falhas→30min) + timeout de 30s por tentativa | +| 🛡 **Proteção de Endpoint API** | Gateway de Auth + bloqueio de provedores para o endpoint `/models` | +| 🔒 **Visibilidade de Proxy** | Badges coloridos: 🟢 global, 🟡 provedor, 🔵 por-conexão com exibição de IP | +| 🌐 **Proxy em 3 Níveis** | Configure proxies em nível global, por provedor ou por conexão | ### 📊 Observabilidade e Analytics diff --git a/docs/FEATURES.md b/docs/FEATURES.md index eff467bf51..66d352e3cb 100644 --- a/docs/FEATURES.md +++ b/docs/FEATURES.md @@ -48,7 +48,7 @@ Four modes for debugging API translations: **Playground** (format converter), ** ## ⚙️ Settings -General settings, system storage, backup management (export/import database), appearance (dark/light mode), security (includes API endpoint protection and custom provider blocking), routing, resilience, and advanced configuration. +General settings, system storage, backup management (export/import database), appearance (dark/light mode), security (includes API endpoint protection and custom provider blocking), routing (model aliases, background task degradation), resilience (rate limit persistence), and advanced configuration. ![Settings Dashboard](screenshots/06-settings.png) diff --git a/open-sse/config/providerRegistry.ts b/open-sse/config/providerRegistry.ts index f929e7c4c8..08c8eef6dd 100644 --- a/open-sse/config/providerRegistry.ts +++ b/open-sse/config/providerRegistry.ts @@ -111,7 +111,10 @@ export const REGISTRY: Record = { clientSecretDefault: "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", }, models: [ - { id: "gemini-3-pro-preview", name: "Gemini 3 Pro Preview" }, + { id: "gemini-3.1-pro", name: "Gemini 3.1 Pro" }, + { id: "gemini-3.1-flash", name: "Gemini 3.1 Flash" }, + { id: "gemini-3-pro-preview", name: "Gemini 3.0 Pro Preview" }, + { id: "gemini-3-flash-preview", name: "Gemini 3.0 Flash Preview" }, { id: "gemini-2.5-pro", name: "Gemini 2.5 Pro" }, { id: "gemini-2.5-flash", name: "Gemini 2.5 Flash" }, { id: "gemini-2.5-flash-lite", name: "Gemini 2.5 Flash Lite" }, @@ -137,8 +140,10 @@ export const REGISTRY: Record = { clientSecretDefault: "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", }, models: [ - { id: "gemini-3-flash-preview", name: "Gemini 3 Flash Preview" }, - { id: "gemini-3-pro-preview", name: "Gemini 3 Pro Preview" }, + { id: "gemini-3.1-pro", name: "Gemini 3.1 Pro" }, + { id: "gemini-3.1-flash", name: "Gemini 3.1 Flash" }, + { id: "gemini-3-flash-preview", name: "Gemini 3.0 Flash Preview" }, + { id: "gemini-3-pro-preview", name: "Gemini 3.0 Pro Preview" }, { id: "gemini-2.5-pro", name: "Gemini 2.5 Pro" }, { id: "gemini-2.5-flash", name: "Gemini 2.5 Flash" }, { id: "gemini-2.5-flash-lite", name: "Gemini 2.5 Flash Lite" }, @@ -268,7 +273,8 @@ export const REGISTRY: Record = { { id: "claude-sonnet-4-6", name: "Claude Sonnet 4.6" }, { id: "gemini-3.1-pro-high", name: "Gemini 3.1 Pro High" }, { id: "gemini-3.1-pro-low", name: "Gemini 3.1 Pro Low" }, - { id: "gemini-3-flash", name: "Gemini 3 Flash" }, + { id: "gemini-3.1-flash", name: "Gemini 3.1 Flash" }, + { id: "gemini-3-flash", name: "Gemini 3.0 Flash" }, { id: "gpt-oss-120b-medium", name: "GPT OSS 120B Medium" }, ], }, diff --git a/open-sse/services/backgroundTaskDetector.ts b/open-sse/services/backgroundTaskDetector.ts new file mode 100644 index 0000000000..328ed8497b --- /dev/null +++ b/open-sse/services/backgroundTaskDetector.ts @@ -0,0 +1,187 @@ +/** + * Background Task Detector — Feature 3 + * + * Detects when CLI tools send "background" requests (title generation, + * summarization, short descriptions) and provides model degradation + * recommendations to save premium model quota. + * + * Detection heuristics: + * - System prompt patterns indicating background/utility tasks + * - Very short conversations with summary-like system prompts + * - X-Request-Priority header + */ + +// ── Configuration ─────────────────────────────────────────────────────────── + +interface DegradationConfig { + enabled: boolean; + degradationMap: Record; // original → cheaper model + detectionPatterns: string[]; // regex patterns for system prompt matching + stats: { + detected: number; + tokensSaved: number; + }; +} + +const DEFAULT_DETECTION_PATTERNS = [ + "generate a title", + "generate title", + "create a title", + "create a short", + "summarize this", + "summarize the", + "write a brief", + "write a summary", + "one-line summary", + "one line summary", + "short description", + "brief description", + "conversation title", + "chat title", + "name this conversation", + "name this chat", + "title for this", + "suggest a title", + "label this", +]; + +const DEFAULT_DEGRADATION_MAP: Record = { + // Premium → Cheap alternatives + "claude-opus-4-6": "gemini-2.5-flash", + "claude-opus-4-6-thinking": "gemini-2.5-flash", + "claude-opus-4-5-20251101": "gemini-2.5-flash", + "claude-sonnet-4-5-20250929": "gemini-2.5-flash", + "claude-sonnet-4-20250514": "gemini-2.5-flash", + "claude-sonnet-4": "gemini-2.5-flash", + "gemini-3.1-pro": "gemini-3.1-flash", + "gemini-3.1-pro-high": "gemini-3.1-flash", + "gemini-3-pro-preview": "gemini-3-flash-preview", + "gemini-2.5-pro": "gemini-2.5-flash", + "gpt-4o": "gpt-4o-mini", + "gpt-5": "gpt-5-mini", + "gpt-5.1": "gpt-5-mini", + "gpt-5.1-codex": "gpt-5.1-codex-mini", +}; + +// ── State ─────────────────────────────────────────────────────────────────── + +let _config: DegradationConfig = { + enabled: false, // Disabled by default — user must opt in + degradationMap: { ...DEFAULT_DEGRADATION_MAP }, + detectionPatterns: [...DEFAULT_DETECTION_PATTERNS], + stats: { detected: 0, tokensSaved: 0 }, +}; + +// ── Config Management ─────────────────────────────────────────────────────── + +/** + * Set the background degradation config (called from settings API or startup). + */ +export function setBackgroundDegradationConfig(config: Partial): void { + _config = { + ..._config, + ...config, + stats: _config.stats, // preserve stats across config changes + }; +} + +/** + * Get current background degradation config. + */ +export function getBackgroundDegradationConfig(): DegradationConfig { + return { + ..._config, + degradationMap: { ..._config.degradationMap }, + detectionPatterns: [..._config.detectionPatterns], + stats: { ..._config.stats }, + }; +} + +/** + * Reset stats counters. + */ +export function resetStats(): void { + _config.stats = { detected: 0, tokensSaved: 0 }; +} + +// ── Detection ─────────────────────────────────────────────────────────────── + +/** + * Check if a request is a background/utility task. + * + * @param {object} body - Request body + * @param {object} [headers] - Request headers (optional) + * @returns {boolean} True if the request looks like a background task + */ +export function isBackgroundTask( + body: any, + headers: Record | null = null +): boolean { + if (!body || typeof body !== "object") return false; + + // 1. Check explicit header + if (headers) { + const priority = + headers["x-request-priority"] || headers["X-Request-Priority"] || headers["x-initiator"]; + if (priority === "background" || priority === "Background") return true; + } + + // 2. Check system prompt for background task patterns + const messages = body.messages || body.input || []; + if (!Array.isArray(messages) || messages.length === 0) return false; + + // Find system message + const systemMsg = messages.find((m: any) => m.role === "system" || m.role === "developer"); + if (!systemMsg) return false; + + const systemContent = + typeof systemMsg.content === "string" ? systemMsg.content.toLowerCase() : ""; + + if (!systemContent) return false; + + // Check against detection patterns + const matched = _config.detectionPatterns.some((pattern) => + systemContent.includes(pattern.toLowerCase()) + ); + + if (!matched) return false; + + // 3. Additional heuristic: background tasks typically have very few messages + // (system + 1-2 user messages) + const userMessages = messages.filter((m: any) => m.role === "user"); + if (userMessages.length > 3) return false; // Too many turns for a background task + + return true; +} + +/** + * Get the degraded (cheaper) model for a given model. + * + * @param {string} originalModel - The original model ID + * @returns {string} The cheaper model or original if no mapping exists + */ +export function getDegradedModel(originalModel: string): string { + if (!originalModel) return originalModel; + + const degraded = _config.degradationMap[originalModel]; + if (degraded) { + _config.stats.detected++; + return degraded; + } + + return originalModel; +} + +/** + * Get default degradation map (for UI reset). + */ +export function getDefaultDegradationMap(): Record { + return { ...DEFAULT_DEGRADATION_MAP }; +} + +/** + * Get default detection patterns (for UI reset). + */ +export function getDefaultDetectionPatterns(): string[] { + return [...DEFAULT_DETECTION_PATTERNS]; +} diff --git a/open-sse/services/modelDeprecation.ts b/open-sse/services/modelDeprecation.ts new file mode 100644 index 0000000000..738bc33183 --- /dev/null +++ b/open-sse/services/modelDeprecation.ts @@ -0,0 +1,125 @@ +/** + * Model Deprecation Auto-Forward — Feature 2 + * + * Maps deprecated model IDs to their replacements so user configs + * don't break when providers rename or retire models. + * + * Supports both built-in aliases (static) and custom aliases (persisted via Settings API). + */ + +// ── Built-in Deprecation Aliases ──────────────────────────────────────────── +// These are known renames/retirements across providers. +// Format: deprecated ID → current ID +const BUILT_IN_ALIASES: Record = { + // Gemini legacy → current + "gemini-pro": "gemini-2.5-pro", + "gemini-pro-vision": "gemini-2.5-pro", + "gemini-1.5-pro": "gemini-2.5-pro", + "gemini-1.5-flash": "gemini-2.5-flash", + "gemini-1.0-pro": "gemini-2.5-pro", + "gemini-2.0-flash": "gemini-2.5-flash", + + // Claude legacy → current + "claude-3-opus-20240229": "claude-opus-4-20250514", + "claude-3-sonnet-20240229": "claude-sonnet-4-20250514", + "claude-3-haiku-20240307": "claude-3-5-sonnet-20241022", + "claude-3-5-sonnet-latest": "claude-sonnet-4-20250514", + "claude-3-5-haiku-latest": "claude-3-5-sonnet-20241022", + + // OpenAI legacy → current + "gpt-4-turbo-preview": "gpt-4-turbo", + "gpt-4-0125-preview": "gpt-4-turbo", + "gpt-4-1106-preview": "gpt-4-turbo", + "gpt-3.5-turbo-0125": "gpt-3.5-turbo", +}; + +// ── Custom Aliases (persisted via Settings API) ───────────────────────────── +let _customAliases: Record = {}; + +/** + * Set custom aliases (called from settings API or startup). + */ +export function setCustomAliases(aliases: Record): void { + _customAliases = { ...aliases }; +} + +/** + * Get current custom aliases. + */ +export function getCustomAliases(): Record { + return { ..._customAliases }; +} + +/** + * Get the full alias map (built-in + custom). + * Custom aliases take precedence over built-in. + */ +export function getAllAliases(): Record { + return { ...BUILT_IN_ALIASES, ..._customAliases }; +} + +/** + * Resolve a model alias to its current ID. + * Custom aliases override built-in ones. + * + * @param {string} modelId - The model ID to resolve + * @returns {string} The resolved model ID, or the original if not deprecated + */ +export function resolveModelAlias(modelId: string): string { + if (!modelId) return modelId; + + // Check custom aliases first (higher priority) + if (_customAliases[modelId]) return _customAliases[modelId]; + + // Then check built-in + if (BUILT_IN_ALIASES[modelId]) return BUILT_IN_ALIASES[modelId]; + + return modelId; +} + +/** + * Get a deprecation notice if the model is deprecated. + * + * @param {string} modelId - The model ID to check + * @returns {string | null} Deprecation message or null if not deprecated + */ +export function getDeprecationNotice(modelId: string): string | null { + if (!modelId) return null; + + const resolved = resolveModelAlias(modelId); + if (resolved === modelId) return null; + + return `Model "${modelId}" is deprecated. Forwarding to "${resolved}".`; +} + +/** + * Check if a model is deprecated. + */ +export function isDeprecated(modelId: string): boolean { + return getDeprecationNotice(modelId) !== null; +} + +/** + * Add a custom alias. + */ +export function addCustomAlias(from: string, to: string): void { + _customAliases[from] = to; +} + +/** + * Remove a custom alias. + */ +export function removeCustomAlias(from: string): boolean { + if (_customAliases[from]) { + delete _customAliases[from]; + return true; + } + return false; +} + +/** + * Get the built-in aliases (read-only reference). + */ +export function getBuiltInAliases(): Record { + return { ...BUILT_IN_ALIASES }; +} diff --git a/open-sse/services/rateLimitManager.ts b/open-sse/services/rateLimitManager.ts index 401d9673cd..3d38a1c65e 100644 --- a/open-sse/services/rateLimitManager.ts +++ b/open-sse/services/rateLimitManager.ts @@ -19,6 +19,11 @@ const limiters = new Map(); // Store connections that have rate limit protection enabled const enabledConnections = new Set(); +// Store learned limits for persistence (debounced) +const learnedLimits: Record = {}; +let persistTimer: ReturnType | null = null; +const PERSIST_DEBOUNCE_MS = 60_000; // Debounce persistence to every 60s max + // Track initialization let initialized = false; @@ -82,6 +87,9 @@ export async function initializeRateLimits() { `🛡️ [RATE-LIMIT] Loaded ${explicitCount} explicit + ${autoCount} auto-enabled (API key) protection(s)` ); } + + // Load persisted learned limits + await loadPersistedLimits(); } catch (err) { console.error("[RATE-LIMIT] Failed to load settings:", err.message); } @@ -314,6 +322,9 @@ export function updateFromHeaders(provider, connectionId, headers, status, model } limiter.updateSettings(updates); + + // Persist learned limits (debounced) + recordLearnedLimit(provider, connectionId, { limit, remaining, minTime: updates.minTime }); } } @@ -360,6 +371,82 @@ export function getAllRateLimitStatus() { return result; } +/** + * Get all learned limits (for dashboard display). + */ +export function getLearnedLimits() { + return { ...learnedLimits }; +} + +// ─── Persistence ──────────────────────────────────────────────────────────── + +/** + * Record a learned limit for debounced persistence. + */ +function recordLearnedLimit(provider: string, connectionId: string, limits: any) { + const key = `${provider}:${connectionId}`; + learnedLimits[key] = { + ...limits, + provider, + connectionId, + lastUpdated: Date.now(), + }; + + // Debounce: save at most once per PERSIST_DEBOUNCE_MS + if (!persistTimer) { + persistTimer = setTimeout(async () => { + persistTimer = null; + try { + const { updateSettings } = await import("@/lib/db/settings"); + await updateSettings({ learnedRateLimits: JSON.stringify(learnedLimits) }); + console.log( + `💾 [RATE-LIMIT] Persisted learned limits for ${Object.keys(learnedLimits).length} provider(s)` + ); + } catch (err) { + console.error("[RATE-LIMIT] Failed to persist learned limits:", err.message); + } + }, PERSIST_DEBOUNCE_MS); + } +} + +/** + * Load persisted learned limits on startup. + */ +async function loadPersistedLimits() { + try { + const { getSettings } = await import("@/lib/db/settings"); + const settings = await getSettings(); + const raw = settings?.learnedRateLimits; + if (!raw) return; + + const parsed = JSON.parse(raw); + let count = 0; + + for (const [key, data] of Object.entries(parsed)) { + // Skip stale entries (older than 24h) + if (data.lastUpdated && Date.now() - data.lastUpdated > 24 * 60 * 60 * 1000) continue; + + learnedLimits[key] = data; + + // Apply to limiter if it exists and has rate limit enabled + if (data.connectionId && enabledConnections.has(data.connectionId)) { + const limiter = limiters.get(key); + if (limiter && data.limit) { + const minTime = data.minTime || Math.max(0, Math.floor(60000 / data.limit) - 10); + limiter.updateSettings({ minTime }); + count++; + } + } + } + + if (count > 0) { + console.log(`📥 [RATE-LIMIT] Restored ${count} learned rate limit(s) from persistence`); + } + } catch (err) { + console.error("[RATE-LIMIT] Failed to load persisted limits:", err.message); + } +} + /** * Update rate limiter based on API response body (JSON error responses). * Providers embed retry info in JSON payloads in different formats. diff --git a/open-sse/services/thinkingBudget.ts b/open-sse/services/thinkingBudget.ts index 6ea4656a77..97fb3a25c0 100644 --- a/open-sse/services/thinkingBudget.ts +++ b/open-sse/services/thinkingBudget.ts @@ -21,6 +21,15 @@ export const EFFORT_BUDGETS = { high: 131072, }; +// thinkingLevel string → budget token mapping +// Used when clients send string-based thinking levels (e.g., VS Code Copilot) +export const THINKING_LEVEL_MAP = { + none: 0, + low: 1024, + medium: 10240, + high: 131072, +}; + // Default config (passthrough = backward compatible) export const DEFAULT_THINKING_CONFIG = { mode: ThinkingMode.PASSTHROUGH, @@ -45,10 +54,81 @@ export function getThinkingBudgetConfig() { return { ..._config }; } +/** + * Normalize thinkingLevel string fields into numeric budget. + * Handles: body.thinkingLevel, body.thinking_level, + * and Gemini's generationConfig.thinkingConfig.thinkingLevel + * + * @param {object} body - Request body + * @returns {object} Body with string thinkingLevel converted to numeric budget + */ +export function normalizeThinkingLevel(body) { + if (!body || typeof body !== "object") return body; + const result = { ...body }; + + // Handle top-level thinkingLevel or thinking_level string fields + const levelStr = result.thinkingLevel || result.thinking_level; + if (typeof levelStr === "string" && THINKING_LEVEL_MAP[levelStr] !== undefined) { + const budget = THINKING_LEVEL_MAP[levelStr]; + // Convert to Claude thinking format as canonical representation + result.thinking = { + type: budget > 0 ? "enabled" : "disabled", + budget_tokens: budget, + }; + delete result.thinkingLevel; + delete result.thinking_level; + } + + // Handle Gemini's generationConfig.thinkingConfig.thinkingLevel + const geminiLevel = + result.generationConfig?.thinkingConfig?.thinkingLevel || + result.generationConfig?.thinking_config?.thinkingLevel; + if (typeof geminiLevel === "string" && THINKING_LEVEL_MAP[geminiLevel] !== undefined) { + const budget = THINKING_LEVEL_MAP[geminiLevel]; + result.generationConfig = { + ...result.generationConfig, + thinking_config: { thinking_budget: budget }, + }; + // Clean up camelCase variant if it was the source + if (result.generationConfig.thinkingConfig) { + delete result.generationConfig.thinkingConfig; + } + } + + return result; +} + +/** + * Ensure models with -thinking suffix have thinking config injected. + * Prevents 400 errors from Claude API when thinking params are missing. + * + * @param {object} body - Request body + * @returns {object} Body with thinking config auto-injected if needed + */ +export function ensureThinkingConfig(body) { + if (!body || typeof body !== "object") return body; + const model = body.model || ""; + + // Only auto-inject for models with -thinking suffix + if (!model.endsWith("-thinking")) return body; + + // If thinking config already present, don't override + if (body.thinking) return body; + + const result = { ...body }; + result.thinking = { + type: "enabled", + budget_tokens: EFFORT_BUDGETS.medium, // 10240 default + }; + return result; +} + /** * Apply thinking budget control to a request body. * Called before format-specific translation. * + * Pipeline: normalizeThinkingLevel → ensureThinkingConfig → mode processing + * * @param {object} body - Request body (any format) * @param {object} [config] - Override config (defaults to stored config) * @returns {object} Modified body @@ -57,21 +137,27 @@ export function applyThinkingBudget(body, config = null) { const cfg = config || _config; if (!body || typeof body !== "object") return body; + // Pre-processing: convert string thinkingLevel to numeric budget + let processed = normalizeThinkingLevel(body); + + // Pre-processing: auto-inject thinking config for -thinking suffix models + processed = ensureThinkingConfig(processed); + switch (cfg.mode) { case ThinkingMode.AUTO: - return stripThinkingConfig(body); + return stripThinkingConfig(processed); case ThinkingMode.PASSTHROUGH: - return body; // No changes + return processed; case ThinkingMode.CUSTOM: - return setCustomBudget(body, cfg.customBudget); + return setCustomBudget(processed, cfg.customBudget); case ThinkingMode.ADAPTIVE: - return applyAdaptiveBudget(body, cfg); + return applyAdaptiveBudget(processed, cfg); default: - return body; + return processed; } } @@ -151,9 +237,10 @@ function applyAdaptiveBudget(body, cfg) { for (let i = messages.length - 1; i >= 0; i--) { const msg = messages[i]; if (msg.role === "user") { - lastMsgLength = typeof msg.content === "string" - ? msg.content.length - : JSON.stringify(msg.content || "").length; + lastMsgLength = + typeof msg.content === "string" + ? msg.content.length + : JSON.stringify(msg.content || "").length; break; } } @@ -173,7 +260,7 @@ function applyAdaptiveBudget(body, cfg) { /** * Check if model name suggests thinking capability */ -function hasThinkingCapableModel(body) { +export function hasThinkingCapableModel(body) { const model = body.model || ""; return ( model.includes("claude") || @@ -181,6 +268,7 @@ function hasThinkingCapableModel(body) { model.includes("o3") || model.includes("o4") || model.includes("gemini") || + model.endsWith("-thinking") || model.includes("thinking") ); } diff --git a/open-sse/services/tokenRefresh.ts b/open-sse/services/tokenRefresh.ts index 6dd0fd8d64..34d85c45ab 100644 --- a/open-sse/services/tokenRefresh.ts +++ b/open-sse/services/tokenRefresh.ts @@ -323,9 +323,13 @@ export async function refreshQwenToken(refreshToken, log) { } if (errorCode === "invalid_request") { - log?.error?.("TOKEN_REFRESH", "Qwen refresh token is invalid or expired. Re-authentication required.", { - status: response.status, - }); + log?.error?.( + "TOKEN_REFRESH", + "Qwen refresh token is invalid or expired. Re-authentication required.", + { + status: response.status, + } + ); return { error: "invalid_request" }; } @@ -720,8 +724,11 @@ export function supportsTokenRefresh(provider) { * Callers should stop retrying and request re-authentication. */ export function isUnrecoverableRefreshError(result) { - return result && typeof result === "object" && - (result.error === "refresh_token_reused" || result.error === "invalid_request"); + return ( + result && + typeof result === "object" && + (result.error === "refresh_token_reused" || result.error === "invalid_request") + ); } /** @@ -841,12 +848,103 @@ export async function getAllAccessTokens(userInfo, log) { /** * Refresh token with retry and exponential backoff * Retries on failure with increasing delay: 1s, 2s, 3s... + * + * Includes: + * - Per-provider circuit breaker (5 consecutive failures → 30min pause) + * - 30s timeout per refresh attempt to prevent hanging connections + * * @param {function} refreshFn - Async function that returns token or null * @param {number} maxRetries - Max retry attempts (default 3) * @param {object} log - Logger instance (optional) + * @param {string} provider - Provider ID for circuit breaker tracking (optional) * @returns {Promise} Token result or null if all retries fail */ -export async function refreshWithRetry(refreshFn, maxRetries = 3, log = null) { + +// ─── Circuit Breaker State ────────────────────────────────────────────────── +const _circuitBreaker: Record = {}; +const CIRCUIT_BREAKER_THRESHOLD = 5; // consecutive failures before tripping +const CIRCUIT_BREAKER_COOLDOWN = 30 * 60 * 1000; // 30 minutes +const REFRESH_TIMEOUT_MS = 30_000; // 30s max per refresh attempt + +/** + * Check if a provider is circuit-breaker blocked. + */ +export function isProviderBlocked(provider: string): boolean { + const state = _circuitBreaker[provider]; + if (!state) return false; + if (state.blockedUntil > Date.now()) return true; + // Cooldown expired — reset + delete _circuitBreaker[provider]; + return false; +} + +/** + * Get circuit breaker status for all providers (for diagnostics). + */ +export function getCircuitBreakerStatus(): Record { + const result: Record = {}; + for (const [provider, state] of Object.entries(_circuitBreaker)) { + result[provider] = { + failures: state.failures, + blocked: state.blockedUntil > Date.now(), + blockedUntil: + state.blockedUntil > Date.now() ? new Date(state.blockedUntil).toISOString() : null, + remainingMs: Math.max(0, state.blockedUntil - Date.now()), + }; + } + return result; +} + +/** + * Record a successful refresh — resets circuit breaker for provider. + */ +function recordSuccess(provider: string) { + if (_circuitBreaker[provider]) { + delete _circuitBreaker[provider]; + } +} + +/** + * Record a failed refresh — increments circuit breaker counter. + */ +function recordFailure(provider: string, log: any = null) { + if (!_circuitBreaker[provider]) { + _circuitBreaker[provider] = { failures: 0, blockedUntil: 0 }; + } + _circuitBreaker[provider].failures++; + + if (_circuitBreaker[provider].failures >= CIRCUIT_BREAKER_THRESHOLD) { + _circuitBreaker[provider].blockedUntil = Date.now() + CIRCUIT_BREAKER_COOLDOWN; + log?.error?.( + "TOKEN_REFRESH", + `🔴 Circuit breaker tripped for ${provider}: ${CIRCUIT_BREAKER_THRESHOLD} consecutive failures. ` + + `Blocked for ${CIRCUIT_BREAKER_COOLDOWN / 60000}min. Provider needs re-authentication.` + ); + } +} + +/** + * Execute a function with a timeout. + */ +async function withTimeout(fn: () => Promise, timeoutMs: number): Promise { + return Promise.race([ + fn(), + new Promise((resolve) => setTimeout(() => resolve(null), timeoutMs)), + ]); +} + +export async function refreshWithRetry( + refreshFn, + maxRetries = 3, + log = null, + provider = "unknown" +) { + // Circuit breaker check + if (isProviderBlocked(provider)) { + log?.warn?.("TOKEN_REFRESH", `⚡ Circuit breaker active for ${provider}, skipping refresh`); + return null; + } + for (let attempt = 0; attempt < maxRetries; attempt++) { if (attempt > 0) { const delay = attempt * 1000; @@ -855,13 +953,18 @@ export async function refreshWithRetry(refreshFn, maxRetries = 3, log = null) { } try { - const result = await refreshFn(); - if (result) return result; + const result = await withTimeout(refreshFn, REFRESH_TIMEOUT_MS); + if (result) { + recordSuccess(provider); + return result; + } } catch (error) { log?.warn?.("TOKEN_REFRESH", `Attempt ${attempt + 1}/${maxRetries} failed: ${error.message}`); } } - log?.error?.("TOKEN_REFRESH", `All ${maxRetries} retry attempts failed`); + // All retries exhausted — record failure for circuit breaker + recordFailure(provider, log); + log?.error?.("TOKEN_REFRESH", `All ${maxRetries} retry attempts failed for ${provider}`); return null; } diff --git a/package.json b/package.json index 480964d87d..0bc756d055 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "omniroute", - "version": "1.7.2", + "version": "1.7.3", "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": { diff --git a/src/app/(dashboard)/dashboard/settings/components/BackgroundDegradationTab.tsx b/src/app/(dashboard)/dashboard/settings/components/BackgroundDegradationTab.tsx new file mode 100644 index 0000000000..d42926584f --- /dev/null +++ b/src/app/(dashboard)/dashboard/settings/components/BackgroundDegradationTab.tsx @@ -0,0 +1,261 @@ +"use client"; + +import { useState, useEffect } from "react"; +import { Card } from "@/shared/components"; +import { useTranslations } from "next-intl"; + +export default function BackgroundDegradationTab() { + const [config, setConfig] = useState({ + enabled: false, + degradationMap: {}, + detectionPatterns: [], + stats: { detected: 0, tokensSaved: 0 }, + }); + const [loading, setLoading] = useState(true); + const [saving, setSaving] = useState(false); + const [status, setStatus] = useState(""); + const [newFrom, setNewFrom] = useState(""); + const [newTo, setNewTo] = useState(""); + const [newPattern, setNewPattern] = useState(""); + const t = useTranslations("settings"); + + useEffect(() => { + fetch("/api/settings/background-degradation") + .then((res) => res.json()) + .then((data) => { + setConfig(data); + setLoading(false); + }) + .catch(() => setLoading(false)); + }, []); + + const save = async (updates) => { + const newConfig = { ...config, ...updates }; + setConfig(newConfig); + setSaving(true); + setStatus(""); + try { + const { stats, ...persistable } = newConfig; + const res = await fetch("/api/settings/background-degradation", { + method: "PUT", + headers: { "Content-Type": "application/json" }, + body: JSON.stringify(persistable), + }); + if (res.ok) { + const data = await res.json(); + setConfig(data); + setStatus("saved"); + setTimeout(() => setStatus(""), 2000); + } else { + setStatus("error"); + } + } catch { + setStatus("error"); + } finally { + setSaving(false); + } + }; + + const addMapping = () => { + if (!newFrom.trim() || !newTo.trim()) return; + const map = { ...config.degradationMap, [newFrom.trim()]: newTo.trim() }; + save({ degradationMap: map }); + setNewFrom(""); + setNewTo(""); + }; + + const removeMapping = (key) => { + const map = { ...config.degradationMap }; + delete map[key]; + save({ degradationMap: map }); + }; + + const addPattern = () => { + if (!newPattern.trim()) return; + const patterns = [...config.detectionPatterns, newPattern.trim()]; + save({ detectionPatterns: patterns }); + setNewPattern(""); + }; + + const removePattern = (idx) => { + const patterns = config.detectionPatterns.filter((_, i) => i !== idx); + save({ detectionPatterns: patterns }); + }; + + const mapEntries = Object.entries(config.degradationMap || {}) as [string, string][]; + + return ( + +
+
+ +
+
+

+ {t("backgroundDegradationTitle") || "Background Task Degradation"} +

+

+ {t("backgroundDegradationDesc") || + "Auto-redirect background requests (titles, summaries) to cheaper models"} +

+
+ {status === "saved" && ( + + check_circle{" "} + {t("saved") || "Saved"} + + )} +
+ + {/* Toggle */} +
+
+

+ {t("enableDegradation") || "Enable Background Degradation"} +

+

+ {t("enableDegradationHint") || + "Automatically use cheaper models for background utility tasks"} +

+
+ +
+ + {/* Stats */} + {config.stats && config.stats.detected > 0 && ( +
+
+ analytics + + {t("tasksDetected") || "Tasks detected"}: + + + {config.stats.detected} + +
+
+ )} + + {config.enabled && ( + <> + {/* Degradation Map */} +
+

+ {t("degradationMap") || "Model Degradation Map"} +

+ + {/* Add new mapping */} +
+ setNewFrom(e.target.value)} + className="flex-1 px-3 py-2 rounded-lg text-sm bg-surface border border-border/50 focus:border-sky-500/50 focus:outline-none" + /> + → + setNewTo(e.target.value)} + className="flex-1 px-3 py-2 rounded-lg text-sm bg-surface border border-border/50 focus:border-sky-500/50 focus:outline-none" + /> + +
+ + {/* Existing mappings */} + {mapEntries.length > 0 && ( +
+ {mapEntries.map(([from, to]) => ( +
+ {from} + + arrow_forward + + {to} + +
+ ))} +
+ )} +
+ + {/* Detection Patterns */} +
+ + + chevron_right + + {t("detectionPatterns") || "Detection Patterns"} ( + {config.detectionPatterns?.length || 0}) + + + {/* Add new pattern */} +
+ setNewPattern(e.target.value)} + className="flex-1 px-3 py-2 rounded-lg text-sm bg-surface border border-border/50 focus:border-sky-500/50 focus:outline-none" + /> + +
+ + {/* Existing patterns */} +
+ {(config.detectionPatterns || []).map((pattern, idx) => ( + + {pattern} + + + ))} +
+
+ + )} + + ); +} diff --git a/src/app/(dashboard)/dashboard/settings/components/ModelAliasesTab.tsx b/src/app/(dashboard)/dashboard/settings/components/ModelAliasesTab.tsx new file mode 100644 index 0000000000..092c7a0c02 --- /dev/null +++ b/src/app/(dashboard)/dashboard/settings/components/ModelAliasesTab.tsx @@ -0,0 +1,179 @@ +"use client"; + +import { useState, useEffect } from "react"; +import { Card } from "@/shared/components"; +import { useTranslations } from "next-intl"; + +export default function ModelAliasesTab() { + const [builtIn, setBuiltIn] = useState({}); + const [custom, setCustom] = useState({}); + const [loading, setLoading] = useState(true); + const [saving, setSaving] = useState(false); + const [status, setStatus] = useState(""); + const [newFrom, setNewFrom] = useState(""); + const [newTo, setNewTo] = useState(""); + const t = useTranslations("settings"); + + useEffect(() => { + fetch("/api/settings/model-aliases") + .then((res) => res.json()) + .then((data) => { + setBuiltIn(data.builtIn || {}); + setCustom(data.custom || {}); + setLoading(false); + }) + .catch(() => setLoading(false)); + }, []); + + const addAlias = async () => { + if (!newFrom.trim() || !newTo.trim()) return; + setSaving(true); + try { + const res = await fetch("/api/settings/model-aliases", { + method: "POST", + headers: { "Content-Type": "application/json" }, + body: JSON.stringify({ from: newFrom.trim(), to: newTo.trim() }), + }); + if (res.ok) { + const data = await res.json(); + setCustom(data.custom); + setNewFrom(""); + setNewTo(""); + setStatus("saved"); + setTimeout(() => setStatus(""), 2000); + } + } catch { + setStatus("error"); + } finally { + setSaving(false); + } + }; + + const removeAlias = async (from) => { + setSaving(true); + try { + const res = await fetch("/api/settings/model-aliases", { + method: "DELETE", + headers: { "Content-Type": "application/json" }, + body: JSON.stringify({ from }), + }); + if (res.ok) { + const data = await res.json(); + setCustom(data.custom); + setStatus("saved"); + setTimeout(() => setStatus(""), 2000); + } + } catch { + setStatus("error"); + } finally { + setSaving(false); + } + }; + + const builtInEntries = Object.entries(builtIn); + const customEntries = Object.entries(custom); + + return ( + +
+
+ +
+
+

{t("modelAliasesTitle") || "Model Aliases"}

+

+ {t("modelAliasesDesc") || "Auto-forward deprecated model IDs to their replacements"} +

+
+ {status === "saved" && ( + + check_circle{" "} + {t("saved") || "Saved"} + + )} +
+ + {/* Add custom alias */} +
+

+ {t("addCustomAlias") || "Add Custom Alias"} +

+
+ setNewFrom(e.target.value)} + className="flex-1 px-3 py-2 rounded-lg text-sm bg-surface border border-border/50 focus:border-amber-500/50 focus:outline-none" + /> + → + setNewTo(e.target.value)} + className="flex-1 px-3 py-2 rounded-lg text-sm bg-surface border border-border/50 focus:border-amber-500/50 focus:outline-none" + /> + +
+
+ + {/* Custom aliases */} + {customEntries.length > 0 && ( +
+

+ {t("customAliases") || "Custom Aliases"} +

+
+ {customEntries.map(([from, to]) => ( +
+ {from} + + arrow_forward + + {to} + +
+ ))} +
+
+ )} + + {/* Built-in aliases (collapsed by default) */} +
+ + + chevron_right + + {t("builtInAliases") || "Built-in Aliases"} ({builtInEntries.length}) + +
+ {builtInEntries.map(([from, to]) => ( +
+ {from} + + arrow_forward + + {to} + lock +
+ ))} +
+
+ + ); +} diff --git a/src/app/(dashboard)/dashboard/settings/page.tsx b/src/app/(dashboard)/dashboard/settings/page.tsx index 3d40e7b023..d307eb3801 100644 --- a/src/app/(dashboard)/dashboard/settings/page.tsx +++ b/src/app/(dashboard)/dashboard/settings/page.tsx @@ -13,6 +13,8 @@ import ProxyTab from "./components/ProxyTab"; import AppearanceTab from "./components/AppearanceTab"; import ThinkingBudgetTab from "./components/ThinkingBudgetTab"; import SystemPromptTab from "./components/SystemPromptTab"; +import ModelAliasesTab from "./components/ModelAliasesTab"; +import BackgroundDegradationTab from "./components/BackgroundDegradationTab"; import CacheStatsCard from "./components/CacheStatsCard"; import ResilienceTab from "./components/ResilienceTab"; @@ -94,6 +96,8 @@ export default function SettingsPage() {
+ +
)} diff --git a/src/app/api/settings/background-degradation/route.ts b/src/app/api/settings/background-degradation/route.ts new file mode 100644 index 0000000000..49b4da2c40 --- /dev/null +++ b/src/app/api/settings/background-degradation/route.ts @@ -0,0 +1,60 @@ +import { NextResponse } from "next/server"; +import { + getBackgroundDegradationConfig, + setBackgroundDegradationConfig, + resetStats, +} from "@omniroute/open-sse/services/backgroundTaskDetector.ts"; +import { updateSettings } from "@/lib/db/settings"; + +/** + * GET /api/settings/background-degradation + * Returns the current background degradation configuration. + */ +export async function GET() { + try { + return NextResponse.json(getBackgroundDegradationConfig()); + } catch (error) { + console.error("[API ERROR] /api/settings/background-degradation GET:", error); + return NextResponse.json({ error: "Failed to get config" }, { status: 500 }); + } +} + +/** + * PUT /api/settings/background-degradation + * Update the background degradation configuration. + * Body: { enabled?: boolean, degradationMap?: {...}, detectionPatterns?: [...] } + */ +export async function PUT(request) { + try { + const config = await request.json(); + setBackgroundDegradationConfig(config); + + // Persist to database (excluding stats) + const { stats, ...persistable } = getBackgroundDegradationConfig(); + await updateSettings({ backgroundDegradation: JSON.stringify(persistable) }); + + return NextResponse.json({ success: true, ...getBackgroundDegradationConfig() }); + } catch (error) { + console.error("[API ERROR] /api/settings/background-degradation PUT:", error); + return NextResponse.json({ error: "Failed to update config" }, { status: 500 }); + } +} + +/** + * POST /api/settings/background-degradation + * Reset stats counters. + * Body: { action: "reset-stats" } + */ +export async function POST(request) { + try { + const { action } = await request.json(); + if (action === "reset-stats") { + resetStats(); + return NextResponse.json({ success: true, stats: getBackgroundDegradationConfig().stats }); + } + return NextResponse.json({ error: "Unknown action" }, { status: 400 }); + } catch (error) { + console.error("[API ERROR] /api/settings/background-degradation POST:", error); + return NextResponse.json({ error: "Failed to execute action" }, { status: 500 }); + } +} diff --git a/src/app/api/settings/model-aliases/route.ts b/src/app/api/settings/model-aliases/route.ts new file mode 100644 index 0000000000..9d307db110 --- /dev/null +++ b/src/app/api/settings/model-aliases/route.ts @@ -0,0 +1,90 @@ +import { NextResponse } from "next/server"; +import { + getAllAliases, + getCustomAliases, + getBuiltInAliases, + setCustomAliases, + addCustomAlias, + removeCustomAlias, +} from "@omniroute/open-sse/services/modelDeprecation.ts"; +import { getSettings, updateSettings } from "@/lib/db/settings"; + +/** + * GET /api/settings/model-aliases + * Returns the full alias map, separated into built-in and custom. + */ +export async function GET() { + try { + return NextResponse.json({ + builtIn: getBuiltInAliases(), + custom: getCustomAliases(), + all: getAllAliases(), + }); + } catch (error) { + console.error("[API ERROR] /api/settings/model-aliases GET:", error); + return NextResponse.json({ error: "Failed to get model aliases" }, { status: 500 }); + } +} + +/** + * PUT /api/settings/model-aliases + * Update the custom aliases map. + * Body: { aliases: { "old-model": "new-model", ... } } + */ +export async function PUT(request) { + try { + const { aliases } = await request.json(); + if (!aliases || typeof aliases !== "object") { + return NextResponse.json({ error: "Missing or invalid 'aliases' object" }, { status: 400 }); + } + setCustomAliases(aliases); + await updateSettings({ modelAliases: JSON.stringify(aliases) }); + return NextResponse.json({ success: true, custom: getCustomAliases() }); + } catch (error) { + console.error("[API ERROR] /api/settings/model-aliases PUT:", error); + return NextResponse.json({ error: "Failed to update model aliases" }, { status: 500 }); + } +} + +/** + * POST /api/settings/model-aliases + * Add a single custom alias. + * Body: { from: "old-model", to: "new-model" } + */ +export async function POST(request) { + try { + const { from, to } = await request.json(); + if (!from || !to) { + return NextResponse.json({ error: "Missing 'from' or 'to'" }, { status: 400 }); + } + addCustomAlias(from, to); + await updateSettings({ modelAliases: JSON.stringify(getCustomAliases()) }); + return NextResponse.json({ success: true, custom: getCustomAliases() }); + } catch (error) { + console.error("[API ERROR] /api/settings/model-aliases POST:", error); + return NextResponse.json({ error: "Failed to add alias" }, { status: 500 }); + } +} + +/** + * DELETE /api/settings/model-aliases + * Remove a custom alias. + * Body: { from: "old-model" } + */ +export async function DELETE(request) { + try { + const { from } = await request.json(); + if (!from) { + return NextResponse.json({ error: "Missing 'from'" }, { status: 400 }); + } + const removed = removeCustomAlias(from); + if (!removed) { + return NextResponse.json({ error: "Alias not found" }, { status: 404 }); + } + await updateSettings({ modelAliases: JSON.stringify(getCustomAliases()) }); + return NextResponse.json({ success: true, custom: getCustomAliases() }); + } catch (error) { + console.error("[API ERROR] /api/settings/model-aliases DELETE:", error); + return NextResponse.json({ error: "Failed to remove alias" }, { status: 500 }); + } +} diff --git a/tests/unit/background-task-detector.test.mjs b/tests/unit/background-task-detector.test.mjs new file mode 100644 index 0000000000..b483b1556e --- /dev/null +++ b/tests/unit/background-task-detector.test.mjs @@ -0,0 +1,130 @@ +import test from "node:test"; +import assert from "node:assert/strict"; + +const { + isBackgroundTask, + getDegradedModel, + setBackgroundDegradationConfig, + getBackgroundDegradationConfig, + getDefaultDegradationMap, + getDefaultDetectionPatterns, + resetStats, +} = await import("../../open-sse/services/backgroundTaskDetector.ts"); + +// ─── isBackgroundTask ─────────────────────────────────────────────────────── + +test("isBackgroundTask: returns true for title generation pattern", () => { + setBackgroundDegradationConfig({ enabled: true }); + const body = { + model: "claude-sonnet-4", + messages: [ + { role: "system", content: "Generate a title for this conversation" }, + { role: "user", content: "How to deploy a Next.js app" }, + ], + }; + assert.equal(isBackgroundTask(body), true); +}); + +test("isBackgroundTask: returns true for summarize pattern", () => { + const body = { + model: "claude-sonnet-4", + messages: [ + { role: "system", content: "Summarize this conversation briefly" }, + { role: "user", content: "We discussed deployment techniques" }, + ], + }; + assert.equal(isBackgroundTask(body), true); +}); + +test("isBackgroundTask: returns false for normal chat", () => { + const body = { + model: "claude-sonnet-4", + messages: [ + { role: "system", content: "You are a helpful coding assistant" }, + { role: "user", content: "Help me write a function" }, + ], + }; + assert.equal(isBackgroundTask(body), false); +}); + +test("isBackgroundTask: returns false for many-turn conversations", () => { + const messages = [ + { role: "system", content: "Generate a title" }, + ...Array.from({ length: 10 }, (_, i) => ({ + role: i % 2 === 0 ? "user" : "assistant", + content: `Message ${i}`, + })), + ]; + const body = { model: "claude-sonnet-4", messages }; + assert.equal(isBackgroundTask(body), false); // Too many turns +}); + +test("isBackgroundTask: detects X-Request-Priority header", () => { + const body = { + model: "claude-sonnet-4", + messages: [{ role: "user", content: "hello" }], + }; + const headers = { "x-request-priority": "background" }; + assert.equal(isBackgroundTask(body, headers), true); +}); + +test("isBackgroundTask: returns false for null/undefined body", () => { + assert.equal(isBackgroundTask(null), false); + assert.equal(isBackgroundTask(undefined), false); +}); + +test("isBackgroundTask: returns false for empty messages", () => { + assert.equal(isBackgroundTask({ messages: [] }), false); +}); + +// ─── getDegradedModel ─────────────────────────────────────────────────────── + +test("getDegradedModel: returns cheaper model from map", () => { + resetStats(); + assert.equal(getDegradedModel("claude-opus-4-6"), "gemini-2.5-flash"); + assert.equal(getDegradedModel("gemini-2.5-pro"), "gemini-2.5-flash"); + assert.equal(getDegradedModel("gpt-4o"), "gpt-4o-mini"); +}); + +test("getDegradedModel: returns original if no mapping exists", () => { + assert.equal(getDegradedModel("some-unknown-model"), "some-unknown-model"); +}); + +test("getDegradedModel: handles null/empty", () => { + assert.equal(getDegradedModel(""), ""); + assert.equal(getDegradedModel(null), null); +}); + +test("getDegradedModel: increments stats counter", () => { + resetStats(); + getDegradedModel("claude-opus-4-6"); // known mapping + const config = getBackgroundDegradationConfig(); + assert.equal(config.stats.detected, 1); +}); + +// ─── Config Management ────────────────────────────────────────────────────── + +test("getBackgroundDegradationConfig: returns config copy", () => { + const config = getBackgroundDegradationConfig(); + assert.ok(typeof config.enabled === "boolean"); + assert.ok(typeof config.degradationMap === "object"); + assert.ok(Array.isArray(config.detectionPatterns)); +}); + +test("setBackgroundDegradationConfig: updates config", () => { + setBackgroundDegradationConfig({ enabled: true }); + assert.equal(getBackgroundDegradationConfig().enabled, true); + setBackgroundDegradationConfig({ enabled: false }); // reset +}); + +test("getDefaultDegradationMap: returns non-empty map", () => { + const map = getDefaultDegradationMap(); + assert.ok(Object.keys(map).length > 0); + assert.ok(map["claude-opus-4-6"]); +}); + +test("getDefaultDetectionPatterns: returns non-empty array", () => { + const patterns = getDefaultDetectionPatterns(); + assert.ok(patterns.length > 0); + assert.ok(patterns.includes("generate a title")); +}); diff --git a/tests/unit/model-deprecation.test.mjs b/tests/unit/model-deprecation.test.mjs new file mode 100644 index 0000000000..da67af3e58 --- /dev/null +++ b/tests/unit/model-deprecation.test.mjs @@ -0,0 +1,105 @@ +import test from "node:test"; +import assert from "node:assert/strict"; + +const { + resolveModelAlias, + getDeprecationNotice, + isDeprecated, + setCustomAliases, + getCustomAliases, + addCustomAlias, + removeCustomAlias, + getAllAliases, + getBuiltInAliases, +} = await import("../../open-sse/services/modelDeprecation.ts"); + +// ─── resolveModelAlias ────────────────────────────────────────────────────── + +test("resolveModelAlias: returns original for non-deprecated model", () => { + assert.equal(resolveModelAlias("claude-opus-4-6"), "claude-opus-4-6"); +}); + +test("resolveModelAlias: resolves deprecated Gemini model", () => { + assert.equal(resolveModelAlias("gemini-pro"), "gemini-2.5-pro"); + assert.equal(resolveModelAlias("gemini-1.5-pro"), "gemini-2.5-pro"); + assert.equal(resolveModelAlias("gemini-1.5-flash"), "gemini-2.5-flash"); +}); + +test("resolveModelAlias: resolves deprecated Claude model", () => { + assert.equal(resolveModelAlias("claude-3-opus-20240229"), "claude-opus-4-20250514"); + assert.equal(resolveModelAlias("claude-3-5-sonnet-latest"), "claude-sonnet-4-20250514"); +}); + +test("resolveModelAlias: resolves deprecated OpenAI model", () => { + assert.equal(resolveModelAlias("gpt-4-turbo-preview"), "gpt-4-turbo"); + assert.equal(resolveModelAlias("gpt-3.5-turbo-0125"), "gpt-3.5-turbo"); +}); + +test("resolveModelAlias: handles null/empty", () => { + assert.equal(resolveModelAlias(""), ""); + assert.equal(resolveModelAlias(null), null); + assert.equal(resolveModelAlias(undefined), undefined); +}); + +// ─── getDeprecationNotice ─────────────────────────────────────────────────── + +test("getDeprecationNotice: returns message for deprecated model", () => { + const notice = getDeprecationNotice("gemini-pro"); + assert.ok(notice); + assert.ok(notice.includes("deprecated")); + assert.ok(notice.includes("gemini-2.5-pro")); +}); + +test("getDeprecationNotice: returns null for non-deprecated model", () => { + assert.equal(getDeprecationNotice("claude-opus-4-6"), null); +}); + +test("getDeprecationNotice: returns null for empty/null", () => { + assert.equal(getDeprecationNotice(""), null); + assert.equal(getDeprecationNotice(null), null); +}); + +// ─── isDeprecated ─────────────────────────────────────────────────────────── + +test("isDeprecated: true for deprecated model", () => { + assert.equal(isDeprecated("gemini-pro"), true); +}); + +test("isDeprecated: false for current model", () => { + assert.equal(isDeprecated("claude-opus-4-6"), false); +}); + +// ─── Custom Aliases ───────────────────────────────────────────────────────── + +test("custom aliases override built-in", () => { + setCustomAliases({ "gemini-pro": "gemini-3.1-pro" }); + assert.equal(resolveModelAlias("gemini-pro"), "gemini-3.1-pro"); // custom wins + setCustomAliases({}); // reset +}); + +test("addCustomAlias and removeCustomAlias", () => { + addCustomAlias("my-old-model", "my-new-model"); + assert.equal(resolveModelAlias("my-old-model"), "my-new-model"); + + const removed = removeCustomAlias("my-old-model"); + assert.equal(removed, true); + assert.equal(resolveModelAlias("my-old-model"), "my-old-model"); +}); + +test("removeCustomAlias: returns false for non-existent", () => { + assert.equal(removeCustomAlias("nonexistent"), false); +}); + +test("getAllAliases: includes both built-in and custom", () => { + addCustomAlias("test-from", "test-to"); + const all = getAllAliases(); + assert.ok(all["gemini-pro"]); // built-in + assert.equal(all["test-from"], "test-to"); // custom + removeCustomAlias("test-from"); // cleanup +}); + +test("getBuiltInAliases: returns built-in aliases", () => { + const builtIn = getBuiltInAliases(); + assert.ok(builtIn["gemini-pro"]); + assert.ok(builtIn["claude-3-opus-20240229"]); +}); diff --git a/tests/unit/thinking-budget.test.mjs b/tests/unit/thinking-budget.test.mjs index a1873bf4df..79b2ed2980 100644 --- a/tests/unit/thinking-budget.test.mjs +++ b/tests/unit/thinking-budget.test.mjs @@ -8,6 +8,10 @@ const { ThinkingMode, EFFORT_BUDGETS, DEFAULT_THINKING_CONFIG, + THINKING_LEVEL_MAP, + normalizeThinkingLevel, + ensureThinkingConfig, + hasThinkingCapableModel, } = await import("../../open-sse/services/thinkingBudget.ts"); // ─── Config Management ────────────────────────────────────────────────────── @@ -159,3 +163,124 @@ test("EFFORT_BUDGETS has expected keys", () => { assert.ok(EFFORT_BUDGETS.medium > EFFORT_BUDGETS.low); assert.ok(EFFORT_BUDGETS.high > EFFORT_BUDGETS.medium); }); + +// ─── thinkingLevel String Conversion (Feature 4) ──────────────────────────── + +test("THINKING_LEVEL_MAP has all expected levels", () => { + assert.equal(THINKING_LEVEL_MAP.none, 0); + assert.equal(THINKING_LEVEL_MAP.low, 1024); + assert.equal(THINKING_LEVEL_MAP.medium, 10240); + assert.equal(THINKING_LEVEL_MAP.high, 131072); +}); + +test("normalizeThinkingLevel: converts thinkingLevel 'high' to budget", () => { + const body = { + model: "claude-sonnet-4", + thinkingLevel: "high", + messages: [{ role: "user", content: "hello" }], + }; + const result = normalizeThinkingLevel(body); + assert.equal(result.thinking.type, "enabled"); + assert.equal(result.thinking.budget_tokens, 131072); + assert.equal(result.thinkingLevel, undefined); +}); + +test("normalizeThinkingLevel: converts thinking_level 'low' to budget", () => { + const body = { + model: "claude-sonnet-4", + thinking_level: "low", + messages: [{ role: "user", content: "hello" }], + }; + const result = normalizeThinkingLevel(body); + assert.equal(result.thinking.type, "enabled"); + assert.equal(result.thinking.budget_tokens, 1024); + assert.equal(result.thinking_level, undefined); +}); + +test("normalizeThinkingLevel: converts 'none' to disabled", () => { + const body = { model: "claude-sonnet-4", thinkingLevel: "none" }; + const result = normalizeThinkingLevel(body); + assert.equal(result.thinking.type, "disabled"); + assert.equal(result.thinking.budget_tokens, 0); +}); + +test("normalizeThinkingLevel: converts Gemini thinkingConfig.thinkingLevel", () => { + const body = { + model: "gemini-2.5-pro", + generationConfig: { + thinkingConfig: { thinkingLevel: "high" }, + }, + }; + const result = normalizeThinkingLevel(body); + assert.equal(result.generationConfig.thinking_config.thinking_budget, 131072); + assert.equal(result.generationConfig.thinkingConfig, undefined); +}); + +test("normalizeThinkingLevel: ignores unknown string values", () => { + const body = { model: "claude-sonnet-4", thinkingLevel: "ultra" }; + const result = normalizeThinkingLevel(body); + assert.equal(result.thinking, undefined); // not converted + assert.equal(result.thinkingLevel, "ultra"); // preserved +}); + +// ─── -thinking Suffix Auto-Injection (Feature 5) ──────────────────────────── + +test("ensureThinkingConfig: auto-injects for -thinking suffix model", () => { + const body = { + model: "claude-opus-4-6-thinking", + messages: [{ role: "user", content: "hello" }], + }; + const result = ensureThinkingConfig(body); + assert.equal(result.thinking.type, "enabled"); + assert.equal(result.thinking.budget_tokens, EFFORT_BUDGETS.medium); +}); + +test("ensureThinkingConfig: does NOT override existing thinking config", () => { + const body = { + model: "claude-opus-4-6-thinking", + thinking: { type: "enabled", budget_tokens: 50000 }, + messages: [{ role: "user", content: "hello" }], + }; + const result = ensureThinkingConfig(body); + assert.equal(result.thinking.budget_tokens, 50000); // preserved +}); + +test("ensureThinkingConfig: does nothing for non-thinking models", () => { + const body = { + model: "claude-sonnet-4", + messages: [{ role: "user", content: "hello" }], + }; + const result = ensureThinkingConfig(body); + assert.equal(result.thinking, undefined); +}); + +test("hasThinkingCapableModel: matches -thinking suffix", () => { + assert.ok(hasThinkingCapableModel({ model: "claude-opus-4-6-thinking" })); + assert.ok(hasThinkingCapableModel({ model: "kimi-k2-thinking" })); + assert.ok(hasThinkingCapableModel({ model: "custom-model-thinking" })); +}); + +test("applyThinkingBudget: thinkingLevel 'high' + PASSTHROUGH = converts and passes through", () => { + setThinkingBudgetConfig({ mode: ThinkingMode.PASSTHROUGH }); + const body = { + model: "claude-sonnet-4", + thinkingLevel: "high", + messages: [{ role: "user", content: "hello" }], + }; + const result = applyThinkingBudget(body); + assert.equal(result.thinking.budget_tokens, 131072); + assert.equal(result.thinkingLevel, undefined); + setThinkingBudgetConfig(DEFAULT_THINKING_CONFIG); +}); + +test("applyThinkingBudget: -thinking model without config + PASSTHROUGH = auto-inject", () => { + setThinkingBudgetConfig({ mode: ThinkingMode.PASSTHROUGH }); + const body = { + model: "claude-opus-4-6-thinking", + messages: [{ role: "user", content: "hello" }], + }; + const result = applyThinkingBudget(body); + assert.equal(result.thinking.type, "enabled"); + assert.equal(result.thinking.budget_tokens, EFFORT_BUDGETS.medium); + setThinkingBudgetConfig(DEFAULT_THINKING_CONFIG); +});