chore: update llm.txt to v2.0.13 state

- Complete rewrite of llm.txt with current project structure - Added ACP agents, CLI fingerprint, sidebar reorganization - Added 30 languages, MCP/A2A servers, anti-ban features - Updated project structure tree with all dashboard pages
2026-07-26 09:52:11 +03:00 · 2026-03-07 12:36:24 -03:00
parent c9a15772b0
commit 8909ae041e
1 changed files with 104 additions and 11 deletions
--- a/llm.txt
+++ b/llm.txt
@@ -8,6 +8,8 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo

 **Key value:** One endpoint (`http://localhost:20128/v1`), unlimited models, zero downtime, minimal cost.

+**Current version:** 2.0.13
+
 ## Tech Stack

 - **Runtime:** Node.js >= 18
@@ -19,6 +21,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 - **Background jobs:** Custom token health check scheduler
 - **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
 - **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting
+- **i18n:** next-intl with 30 languages
 - **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)

 ## Project Structure
@@ -27,9 +30,27 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 /
 ├── src/                          # Main application source
 │   ├── app/                      # Next.js App Router pages and API routes
-│   │   ├── (dashboard)/          # Dashboard UI pages (providers, combos, analytics, logs, etc.)
+│   │   ├── (dashboard)/          # Dashboard UI pages
+│   │   │   └── dashboard/
+│   │   │       ├── agents/       # ACP Agents dashboard (CLI agent detection + custom agents)
+│   │   │       ├── analytics/    # Usage analytics and charts
+│   │   │       ├── api-manager/  # API key management
+│   │   │       ├── cli-tools/    # CLI tool configuration (Claude, Codex, Gemini, etc.)
+│   │   │       ├── combos/       # Model combo management
+│   │   │       ├── costs/        # Cost tracking
+│   │   │       ├── endpoint/     # Endpoint info and cloud proxy
+│   │   │       ├── health/       # System health monitoring
+│   │   │       ├── limits/       # Rate limits dashboard
+│   │   │       ├── logs/         # Request logs viewer
+│   │   │       ├── media/        # Image/video/music generation
+│   │   │       ├── playground/   # Model playground (Monaco editor, streaming)
+│   │   │       ├── providers/    # Provider management (OAuth + API key + free)
+│   │   │       ├── settings/     # Settings tabs (General, Appearance, Security, Routing, Resilience, Advanced)
+│   │   │       ├── translator/   # Format translator + debug tools
+│   │   │       └── usage/        # Usage history
 │   │   ├── api/                  # REST API endpoints
 │   │   │   ├── v1/               # OpenAI-compatible API (chat, models, embeddings, images, audio)
+│   │   │   ├── acp/              # ACP agent management API
 │   │   │   ├── oauth/            # OAuth flows per provider (authorize, exchange, callback)
 │   │   │   ├── providers/        # Provider CRUD and batch testing
 │   │   │   ├── models/           # Dashboard model listing and aliases
@@ -37,7 +58,10 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   │   └── ...               # Other endpoints (usage, logs, health, settings, etc.)
 │   │   └── login/                # Login page
 │   ├── domain/                   # Domain types and business logic interfaces
+│   ├── i18n/                     # Internationalization
+│   │   └── messages/             # 30 language JSON files (ar, bg, da, de, en, es, fi, fr, he, hu, id, in, it, ja, ko, ms, nl, no, phi, pl, pt, pt-BR, ro, ru, sk, sv, th, uk-UA, vi, zh-CN)
 │   ├── lib/                      # Core libraries
+│   │   ├── acp/                  # ACP agent registry and manager (14 built-in agents + custom)
 │   │   ├── db/                   # SQLite database layer (providers, combos, prompts, logs)
 │   │   ├── oauth/                # OAuth providers, services, and utilities
 │   │   │   ├── providers/        # Provider-specific OAuth configs (GitHub, Google, Claude, etc.)
@@ -47,28 +71,88 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 │   │   ├── tokenHealthCheck.ts   # Background OAuth token refresh scheduler
 │   │   └── localDb.ts            # Unified database access layer
 │   ├── shared/                   # Shared utilities, components, and constants
-│   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, etc.)
+│   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, Sidebar, etc.)
 │   │   ├── constants/            # Provider definitions, model lists, pricing
+│   │   ├── validation/           # Zod schemas (settings, providers, etc.)
 │   │   └── utils/                # Helpers (auth, CORS, error codes, machine ID)
 │   ├── sse/                      # SSE proxy pipeline
 │   │   ├── services/             # Auth resolution, format translation, response handling
 │   │   └── middleware/           # Rate limiting, circuit breaker, caching, idempotency
-│   ├── store/                    # Zustand client-side stores
+│   ├── store/                    # Zustand client-side stores (theme, providers, etc.)
 │   ├── types/                    # TypeScript type definitions
 │   ├── proxy.ts                  # Main proxy request handler
 │   └── server-init.ts            # Server initialization (DB, health checks)
 ├── open-sse/                     # Standalone SSE server (npm workspace)
-│   ├── config/                   # Model registries (embedding, image, audio, rerank, moderation)
+│   ├── config/                   # Model registries (embedding, image, audio, rerank, moderation, CLI fingerprints)
 │   ├── handlers/                 # Request handlers per API type
-│   └── translators/              # Format translators (OpenAI ↔ Claude ↔ Gemini ↔ Responses)
+│   ├── mcp-server/               # Built-in MCP server (16 tools, audit logging, scope auth)
+│   └── translators/              # Format translators (OpenAI ↔ Claude ↔ Gemini ↔ Responses ↔ Ollama)
 ├── tests/                        # Test suites
 │   ├── unit/                     # Unit tests (32+ test files)
 │   └── integration/              # Integration tests
-├── docs/                         # Documentation and screenshots
+├── docs/                         # Documentation (with 29-language i18n subdirectories)
+│   ├── i18n/                     # Translated docs (ar, bg, da, de, es, fi, fr, he, hu, id, in, it, ja, ko, ms, nl, no, phi, pl, pt, pt-BR, ro, ru, sk, sv, th, uk-UA, vi, zh-CN)
+│   ├── screenshots/              # Dashboard screenshots
+│   ├── a2a-server.md             # A2A agent protocol documentation
+│   ├── auto-combo.md             # Auto-combo engine (6-factor scoring)
+│   └── mcp-server.md             # MCP server (16 tools)
+├── electron/                     # Electron desktop app
 ├── bin/                          # CLI entry points (omniroute, reset-password)
 └── .env.example                  # Environment variable template
 ```

+## Key Features (v2.0.13)
+
+### Core Proxy
+- **36+ AI providers** with automatic format translation
+- **6 routing strategies**: priority, weighted, round-robin, random, least-used, cost-optimized
+- **4-tier fallback**: Subscription → API Key → Cheap → Free
+- **Semantic caching** with cache hit/miss headers
+- **Idempotency** with configurable dedup window
+- **Circuit breaker** per provider with configurable thresholds
+
+### Anti-Ban Protection
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint to reduce bot detection
+- **CLI Fingerprint Matching** — Per-provider request signature matching (headers/body ordering) to match native CLI tools. Proxy IP is preserved.
+
+### Dashboard Pages
+- **Providers** — OAuth, API key, and free provider management
+- **Combos** — Multi-model fallback chain builder with templates
+- **Analytics** — Token consumption, cost, heatmaps, distributions
+- **Health** — Uptime, memory, latency percentiles, circuit breakers
+- **Logs** — Real-time request log viewer with filtering
+- **Costs** — Cost tracking per provider/model
+- **Limits** — Rate limit monitoring
+- **CLI Tools** — One-click configuration for 10+ AI CLI tools
+- **CLI Agents** — Grid of 14 built-in agents with install detection + custom agent registration
+- **Playground** — Test any model with Monaco editor, streaming responses
+- **Media** — Image/video/music generation (DALL-E, FLUX, AnimateDiff, etc.)
+- **Translator** — Format debugging: playground, chat tester, test bench, live monitor
+- **Settings** — General, Appearance (7 color themes), Security (TLS/CLI fingerprint, IP filter), Routing, Resilience, Advanced
+- **Endpoint** — Unified API endpoint info + cloud proxy
+
+### Sidebar Organization
+- **Main**: Home, Endpoints, API Manager, Providers, Combos, Costs, Analytics, Limits
+- **CLI**: Tools, Agents
+- **Debug**: Translator, Playground, Media
+- **System**: Health, Logs, Settings
+- **Help**: Docs, Issues
+
+### Protocol Support
+- **OpenAI-compatible** — `/v1/chat/completions`, `/v1/models`, `/v1/embeddings`, `/v1/images/generations`, `/v1/audio/transcriptions`
+- **Anthropic** — `/v1/messages`, `/v1/messages/count_tokens`
+- **OpenAI Responses** — `/v1/responses`
+- **Gemini** — `/v1beta/models`, `/v1beta/models/{...path}`
+- **Ollama** — `/v1/api/chat`, `/api/tags`
+- **MCP** — 16-tool MCP server with scope-based auth
+- **A2A** — Agent-to-Agent protocol (smart-routing, quota-management skills)
+- **ACP** — Agent detection, custom agent registry
+
+### Internationalization
+- 30 languages for UI (sidebar, settings, agents, and all dashboard pages)
+- 30 READMEs (root README.md + 29 translated README.*.md)
+- 29 translated doc sets in docs/i18n/
+
 ## Key Architectural Decisions

 1. **OpenAI-compatible API surface:** All incoming requests follow the OpenAI API format (`/v1/chat/completions`, `/v1/models`, etc.). This makes OmniRoute a drop-in replacement for any tool that supports custom OpenAI endpoints.
@@ -77,13 +161,15 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo

 3. **Connection-based provider model:** Providers are stored as "connections" in SQLite. Each connection has an `id`, `provider`, `authType` (oauth/apikey/free), `isActive` flag, and credentials. Multiple connections per provider are supported for multi-account rotation.

-4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 6 strategies: fill-first, round-robin, power-of-two-choices, random, least-used, cost-optimized.
+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 6 strategies.

 5. **SSE proxy pipeline (`src/sse/`):** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.

 6. **SQLite for persistence:** All state (providers, combos, logs, settings) is stored in a single SQLite database file at `data/omniroute.db`. This keeps the app self-contained and zero-config.

-7. **OAuth with PKCE:** OAuth flows use PKCE for security. A local callback server (`src/lib/oauth/utils/server.ts`) handles the redirect. Token refresh is handled by a background job (`tokenHealthCheck.ts`).
+7. **OAuth with PKCE:** OAuth flows use PKCE for security. A local callback server handles the redirect. Token refresh is handled by a background job (`tokenHealthCheck.ts`).
+
+8. **ACP Agent Registry:** 14 built-in CLI agents with dynamic detection and a 60-second cache. Custom agents can be added via dashboard or API, stored in settings DB.

 ## Main Flows

@@ -94,9 +180,10 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 4. For combos: iterate through models in fallback order
 5. Auth resolution: get credentials for the target provider
 6. Format translation: OpenAI → provider native format
-7. Upstream request with circuit breaker and rate limiting
-8. Response translation: provider → OpenAI format
-9. SSE streaming back to client
+7. CLI fingerprint matching (if enabled for provider)
+8. Upstream request with circuit breaker and rate limiting
+9. Response translation: provider → OpenAI format
+10. SSE streaming back to client

 ### OAuth Flow
 1. Dashboard initiates `/api/oauth/[provider]/authorize`
@@ -125,6 +212,12 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo

 7. **The proxy pipeline is in `src/sse/`**, not in `src/app/api/v1/`. The API routes in `src/app/api/v1/` delegate to the SSE server running on a separate Express instance.

+8. **Sidebar sections:** Main nav, CLI (Tools + Agents), Debug (Translator + Playground + Media), System (Health + Logs + Settings), Help (Docs + Issues).
+
+9. **ACP agents** are in `src/lib/acp/registry.ts` (14 built-in) with a 60s detection cache. Custom agents stored via `src/shared/validation/settingsSchemas.ts`.
+
+10. **CLI fingerprint configs** are in `open-sse/config/cliFingerprints.ts`. They match native CLI request patterns per provider.
+
 ## Links

 - Repository: https://github.com/diegosouzapw/OmniRoute