Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors
TypeScript a2aai-agentsai-gatewayanthropicclaudeclaude-codeclinecodexcopilotcursordeepseekfree-aigeminikimillm-gatewaymcpopenaiopenai-proxyqwentoken-saver
fix(docs): correct provider/strategy/MCP-tools drift (179→177, 13→14)
diegosouzapw8a26128e93ac
diff --git a/docs/architecture/ARCHITECTURE.md b/docs/architecture/ARCHITECTURE.mdindex bd814b3ee2..b80e5914e9 100644--- a/docs/architecture/ARCHITECTURE.md+++ b/docs/architecture/ARCHITECTURE.md@@ -11,7 +11,7 @@ It provides a single OpenAI-compatible endpoint (`/v1/*`) and routes traffic acrCore capabilities:-- OpenAI-compatible API surface for CLI/tools (179 providers, 31 executors)+- OpenAI-compatible API surface for CLI/tools (177 providers, 31 executors)- Request/response translation across provider formats- Model combo fallback (multi-model sequence)- Structured combo steps (`provider + model + connection`) with runtime ordering by `compositeTiers`@@ -903,7 +903,7 @@ All other providers (including custom compatible nodes) use the `DefaultExecutor## Provider Compatibility Matrix-> **Note:** The matrix below is a representative sample of the 179 registered providers in+> **Note:** The matrix below is a representative sample of the 177 registered providers in> OmniRoute v3.8.0. For the canonical and continuously-updated list, refer to> [`docs/reference/PROVIDER_REFERENCE.md`](../reference/PROVIDER_REFERENCE.md) (auto-generated) or the source of> truth at `src/shared/constants/providers.ts` (Zod-validated at load).diff --git a/docs/architecture/CODEBASE_DOCUMENTATION.md b/docs/architecture/CODEBASE_DOCUMENTATION.mdindex 1a2f70c2c5..2b0527e805 100644--- a/docs/architecture/CODEBASE_DOCUMENTATION.md+++ b/docs/architecture/CODEBASE_DOCUMENTATION.md@@ -445,7 +445,7 @@ open-sse/(shared identity helper) and `index.ts` (registry).> Note: providers not listed here are served by `default.ts` using the generic-> OpenAI-compatible executor. The full provider catalog (179+ entries) lives in+> OpenAI-compatible executor. The full provider catalog (177+ entries) lives in> `src/shared/constants/providers.ts`.### 4.3 `open-sse/translator/`diff --git a/docs/frameworks/MCP-SERVER.md b/docs/frameworks/MCP-SERVER.mdindex b03fbc98aa..1796cbdc27 100644--- a/docs/frameworks/MCP-SERVER.md+++ b/docs/frameworks/MCP-SERVER.md@@ -131,6 +131,36 @@ Defined in `open-sse/mcp-server/tools/skillTools.ts`. Backed by `src/lib/skills/| `omniroute_skills_execute` | Execute a skill with provided input and return the execution record || `omniroute_skills_executions` | List recent skill execution history |+## Related Frameworks (v3.8.0)++The MCP tool inventory above (37 tools = 30 base + 3 memory + 4 skills) is intentionally+scoped to runtime routing/cache/compression/memory/skills/proxy operations. Two adjacent+frameworks ship alongside the MCP server in v3.8.0 and are documented separately:++### Cloud Agents++Cloud Agents are out-of-process AI coding agents (codex-cloud, devin, jules) wired into+OmniRoute through the same connection model used for LLM providers. They are exposed via+their own REST surface (`/api/v1/agents/*`) and are **not** part of the MCP tool catalog+— calling a Cloud Agent does not consume an MCP scope.++- Implementation: `src/lib/cloudAgent/` (`registry.ts`, `agents/codex-cloud.ts`, `agents/devin.ts`, `agents/jules.ts`).+- Lifecycle: `createTask`, `getStatus`, `approvePlan`, `sendMessage`, `listSources`.+- Documentation: [docs/frameworks/CLOUD_AGENT.md](./CLOUD_AGENT.md).++### Guardrails++Guardrails are pre/post-execution filters (vision-bridge, pii-masker, prompt-injection)+applied inside the chat pipeline. They run before the MCP tool/route layer is reached+and emit structured violations to the audit pipeline; they are not invoked as MCP tools.++- Implementation: `src/lib/guardrails/`.+- Documentation: [docs/security/GUARDRAILS.md](../security/GUARDRAILS.md).++When debugging an MCP call that appears blocked, check both the MCP audit log+(`scope_denied:*` entries) and the guardrails audit trail — a request may be rejected by+a guardrail **before** it ever reaches the MCP scope enforcement layer.+---## REST API Endpointsdiff --git a/docs/guides/FEATURES.md b/docs/guides/FEATURES.mdindex 18e2ad5850..d95302e886 100644--- a/docs/guides/FEATURES.md+++ b/docs/guides/FEATURES.md@@ -53,7 +53,7 @@ Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI)## 🎨 Combos-Create model routing combos with 13 strategies: priority, weighted, round-robin, random, least-used, cost-optimized, strict-random, auto, fill-first, p2c, lkgp, context-optimized, and **context-relay**. Each combo chains multiple models with automatic fallback and includes quick templates and readiness checks.+Create model routing combos with 14 strategies: priority, weighted, fill-first, round-robin, p2c (power-of-two-choices), random, least-used, cost-optimized, reset-aware, strict-random, auto, lkgp (last-known-good-provider), context-optimized, and **context-relay**. Each combo chains multiple models with automatic fallback and includes quick templates and readiness checks.Recent combo improvements:diff --git a/docs/i18n/ar/llm.txt b/docs/i18n/ar/llm.txtindex 30d8e0afe8..eb130236ee 100644--- a/docs/i18n/ar/llm.txt+++ b/docs/i18n/ar/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/bg/llm.txt b/docs/i18n/bg/llm.txtindex d752b57e3e..9184a4f896 100644--- a/docs/i18n/bg/llm.txt+++ b/docs/i18n/bg/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/bn/llm.txt b/docs/i18n/bn/llm.txtindex 5390b06bf3..6ae5bc26b7 100644--- a/docs/i18n/bn/llm.txt+++ b/docs/i18n/bn/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/cs/llm.txt b/docs/i18n/cs/llm.txtindex 7c1d81ff91..4fc059a249 100644--- a/docs/i18n/cs/llm.txt+++ b/docs/i18n/cs/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/da/llm.txt b/docs/i18n/da/llm.txtindex 5b779adac3..ec2e3213c3 100644--- a/docs/i18n/da/llm.txt+++ b/docs/i18n/da/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/de/llm.txt b/docs/i18n/de/llm.txtindex db7fd0b695..649ce828ac 100644--- a/docs/i18n/de/llm.txt+++ b/docs/i18n/de/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/es/llm.txt b/docs/i18n/es/llm.txtindex d822c3352e..3535c59e7e 100644--- a/docs/i18n/es/llm.txt+++ b/docs/i18n/es/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/fa/llm.txt b/docs/i18n/fa/llm.txtindex a0da959704..79afa4005c 100644--- a/docs/i18n/fa/llm.txt+++ b/docs/i18n/fa/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/fi/llm.txt b/docs/i18n/fi/llm.txtindex d955612ef5..cd11e1e45b 100644--- a/docs/i18n/fi/llm.txt+++ b/docs/i18n/fi/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/fr/llm.txt b/docs/i18n/fr/llm.txtindex d7605da05a..d5513feb21 100644--- a/docs/i18n/fr/llm.txt+++ b/docs/i18n/fr/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/gu/llm.txt b/docs/i18n/gu/llm.txtindex b264d4bd77..a18cba9411 100644--- a/docs/i18n/gu/llm.txt+++ b/docs/i18n/gu/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/he/llm.txt b/docs/i18n/he/llm.txtindex 96aa52741c..8831054bbd 100644--- a/docs/i18n/he/llm.txt+++ b/docs/i18n/he/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/hi/llm.txt b/docs/i18n/hi/llm.txtindex 940e48983e..45b8ecd4f4 100644--- a/docs/i18n/hi/llm.txt+++ b/docs/i18n/hi/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/hu/llm.txt b/docs/i18n/hu/llm.txtindex a5174b82ba..0484dbd925 100644--- a/docs/i18n/hu/llm.txt+++ b/docs/i18n/hu/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/id/llm.txt b/docs/i18n/id/llm.txtindex a7326adc95..44eaa9952d 100644--- a/docs/i18n/id/llm.txt+++ b/docs/i18n/id/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/in/llm.txt b/docs/i18n/in/llm.txtindex 7a335876a5..66eeb8744e 100644--- a/docs/i18n/in/llm.txt+++ b/docs/i18n/in/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/it/llm.txt b/docs/i18n/it/llm.txtindex 1ec48fb907..ec64536dc2 100644--- a/docs/i18n/it/llm.txt+++ b/docs/i18n/it/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/ja/llm.txt b/docs/i18n/ja/llm.txtindex 1fd93f3d68..7d42694266 100644--- a/docs/i18n/ja/llm.txt+++ b/docs/i18n/ja/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/ko/llm.txt b/docs/i18n/ko/llm.txtindex 1a20747f59..3a6fde950b 100644--- a/docs/i18n/ko/llm.txt+++ b/docs/i18n/ko/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/mr/llm.txt b/docs/i18n/mr/llm.txtindex be205b03e8..7e49ce7878 100644--- a/docs/i18n/mr/llm.txt+++ b/docs/i18n/mr/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/ms/llm.txt b/docs/i18n/ms/llm.txtindex d2ddd056e4..f9746ea806 100644--- a/docs/i18n/ms/llm.txt+++ b/docs/i18n/ms/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/nl/llm.txt b/docs/i18n/nl/llm.txtindex 6836a11da2..4eac57ed3c 100644--- a/docs/i18n/nl/llm.txt+++ b/docs/i18n/nl/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/no/llm.txt b/docs/i18n/no/llm.txtindex 0016785cb5..f6845ae8d3 100644--- a/docs/i18n/no/llm.txt+++ b/docs/i18n/no/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/phi/llm.txt b/docs/i18n/phi/llm.txtindex 159e12a77e..f61b6eef56 100644--- a/docs/i18n/phi/llm.txt+++ b/docs/i18n/phi/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/pl/llm.txt b/docs/i18n/pl/llm.txtindex 80d86112b4..5a7bc054bf 100644--- a/docs/i18n/pl/llm.txt+++ b/docs/i18n/pl/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/pt-BR/llm.txt b/docs/i18n/pt-BR/llm.txtindex 632fc7135f..46c77c9ae2 100644--- a/docs/i18n/pt-BR/llm.txt+++ b/docs/i18n/pt-BR/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/pt/llm.txt b/docs/i18n/pt/llm.txtindex b580eb63e5..685f400c65 100644--- a/docs/i18n/pt/llm.txt+++ b/docs/i18n/pt/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/ro/llm.txt b/docs/i18n/ro/llm.txtindex 4b5e16c1ab..1c41f6beff 100644--- a/docs/i18n/ro/llm.txt+++ b/docs/i18n/ro/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/ru/llm.txt b/docs/i18n/ru/llm.txtindex a523e0186d..754574a172 100644--- a/docs/i18n/ru/llm.txt+++ b/docs/i18n/ru/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/sk/llm.txt b/docs/i18n/sk/llm.txtindex 6bf44b5000..0dc07cd167 100644--- a/docs/i18n/sk/llm.txt+++ b/docs/i18n/sk/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/sv/llm.txt b/docs/i18n/sv/llm.txtindex 07e2cebb81..debc38bd6b 100644--- a/docs/i18n/sv/llm.txt+++ b/docs/i18n/sv/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/sw/llm.txt b/docs/i18n/sw/llm.txtindex 0c8165bf65..b155a3eca9 100644--- a/docs/i18n/sw/llm.txt+++ b/docs/i18n/sw/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/ta/llm.txt b/docs/i18n/ta/llm.txtindex 62f0392dfc..e6e7d63861 100644--- a/docs/i18n/ta/llm.txt+++ b/docs/i18n/ta/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/te/llm.txt b/docs/i18n/te/llm.txtindex 90bfc5ed3f..b9d396c2c4 100644--- a/docs/i18n/te/llm.txt+++ b/docs/i18n/te/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/th/llm.txt b/docs/i18n/th/llm.txtindex 175e0a0551..e94e4315a2 100644--- a/docs/i18n/th/llm.txt+++ b/docs/i18n/th/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/tr/llm.txt b/docs/i18n/tr/llm.txtindex ba869b155c..79c79934c0 100644--- a/docs/i18n/tr/llm.txt+++ b/docs/i18n/tr/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/uk-UA/llm.txt b/docs/i18n/uk-UA/llm.txtindex 6f3fc024b0..99d1ef1648 100644--- a/docs/i18n/uk-UA/llm.txt+++ b/docs/i18n/uk-UA/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/ur/llm.txt b/docs/i18n/ur/llm.txtindex 7a90c7ce3f..3ef46a1705 100644--- a/docs/i18n/ur/llm.txt+++ b/docs/i18n/ur/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/vi/llm.txt b/docs/i18n/vi/llm.txtindex 688a0ffcf3..e334b63a7e 100644--- a/docs/i18n/vi/llm.txt+++ b/docs/i18n/vi/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/docs/i18n/zh-CN/llm.txt b/docs/i18n/zh-CN/llm.txtindex e834391ef4..2d40e8ea35 100644--- a/docs/i18n/zh-CN/llm.txt+++ b/docs/i18n/zh-CN/llm.txt@@ -45,7 +45,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -320,7 +320,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -386,7 +386,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/llm.txt b/llm.txtindex 0ef2a37fd0..313aa501e7 100644--- a/llm.txt+++ b/llm.txt@@ -41,7 +41,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo│ │ │ ├── auto-combo/ # Auto-combo engine dashboard│ │ │ ├── cache/ # Cache dashboard (semantic cache stats)│ │ │ ├── cli-tools/ # CLI tool configuration (Claude Code, Codex, Gemini CLI, etc.)-│ │ │ ├── combos/ # Model combo management (13 strategies + 4 templates)+│ │ │ ├── combos/ # Model combo management (14 strategies + 4 templates)│ │ │ ├── costs/ # Cost tracking per provider/model│ │ │ ├── endpoint/ # Unified: Endpoint Proxy, MCP, A2A, API Endpoints tabs│ │ │ ├── health/ # System health (uptime, circuit breakers, latency)@@ -316,7 +316,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo### Dashboard Pages (23 sections)- **Providers** — OAuth, API key, and free provider management with ProviderIcon SVG icons-- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 13 strategies+- **Combos** — Multi-model combo builder with 4 templates (Free Stack, High Availability, Cost Saver, Balanced) + 14 strategies- **Auto-Combo** — Auto-combo engine dashboard with scoring metrics- **Analytics** — Token consumption, cost, heatmaps, distributions- **Health** — Uptime, memory, latency percentiles, circuit breakers@@ -382,7 +382,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo3. **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 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 13 strategies including auto-combo with self-healing and context-relay for session continuity.+4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 14 strategies including auto-combo with self-healing and context-relay for session continuity.5. **SSE proxy pipeline:** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.diff --git a/scripts/i18n/sync-llm-mirrors.mjs b/scripts/i18n/sync-llm-mirrors.mjsnew file mode 100644index 0000000000..2d63d22257--- /dev/null+++ b/scripts/i18n/sync-llm-mirrors.mjs@@ -0,0 +1,89 @@+#!/usr/bin/env node+/**+ * sync-llm-mirrors.mjs — keep docs/i18n/<locale>/llm.txt in lock-step with+ * the root `llm.txt`. The mirrors are strict copies (no translation): they+ * preserve the per-locale heading + language bar block they already have at+ * the top of the file, then replace everything after the `---` separator with+ * the root body (heading stripped).+ *+ * Usage:+ * node scripts/i18n/sync-llm-mirrors.mjs+ *+ * Idempotent. Safe to run repeatedly. Used after any edit to `llm.txt` to+ * keep `npm run check:docs-sync` green.+ */++import { promises as fs } from "node:fs";+import path from "node:path";+import { fileURLToPath } from "node:url";++const __filename = fileURLToPath(import.meta.url);+const __dirname = path.dirname(__filename);+const ROOT = path.resolve(__dirname, "..", "..");+const I18N_DIR = path.join(ROOT, "docs", "i18n");+const ROOT_LLM = path.join(ROOT, "llm.txt");+const FILE_NAME = "llm.txt";++function stripTopHeading(content) {+ return content.replace(/^# .+\r?\n+/, "");+}++async function main() {+ const rootText = await fs.readFile(ROOT_LLM, "utf8");+ const rootBody = stripTopHeading(rootText).replace(/\r\n/g, "\n");++ const entries = await fs.readdir(I18N_DIR, { withFileTypes: true });+ const locales = entries+ .filter((e) => e.isDirectory())+ .map((e) => e.name)+ .sort();++ let updated = 0;+ let unchanged = 0;+ let missing = 0;++ for (const locale of locales) {+ const target = path.join(I18N_DIR, locale, FILE_NAME);+ let existing;+ try {+ existing = await fs.readFile(target, "utf8");+ } catch {+ console.warn(`[sync-llm-mirrors] skip ${locale}: ${FILE_NAME} missing`);+ missing += 1;+ continue;+ }++ // The locale header is everything up to and including the first `---`+ // separator on its own line. We keep that prefix verbatim and replace+ // the rest with the root body.+ const sepMatch = existing.match(/^---\s*$/m);+ if (!sepMatch || sepMatch.index === undefined) {+ console.warn(`[sync-llm-mirrors] skip ${locale}: missing --- separator`);+ missing += 1;+ continue;+ }++ const headerEnd = sepMatch.index + sepMatch[0].length;+ const header = existing.slice(0, headerEnd).replace(/\r\n/g, "\n");+ const trimmedHeader = header.replace(/\n+$/, "");+ const next = `${trimmedHeader}\n\n${rootBody.trimStart()}`.replace(/\r\n/g, "\n");++ const normalizedExisting = existing.replace(/\r\n/g, "\n");+ if (normalizedExisting === next) {+ unchanged += 1;+ continue;+ }+ await fs.writeFile(target, next, "utf8");+ updated += 1;+ console.log(`[sync-llm-mirrors] updated docs/i18n/${locale}/${FILE_NAME}`);+ }++ console.log(+ `[sync-llm-mirrors] done — updated=${updated} unchanged=${unchanged} missing=${missing} (${locales.length} locales)`+ );+}++main().catch((err) => {+ console.error(err);+ process.exit(1);+});diff --git a/src/i18n/messages/en.json b/src/i18n/messages/en.jsonindex 804fa96ace..b82028282b 100644--- a/src/i18n/messages/en.json+++ b/src/i18n/messages/en.json@@ -1820,7 +1820,7 @@"wizardStep2Title": "Add Models","wizardStep2Desc": "Select AI models and arrange their fallback priority order","wizardStep3Title": "Choose Strategy",- "wizardStep3Desc": "Pick how requests are distributed across your models - 13 strategies available",+ "wizardStep3Desc": "Pick how requests are distributed across your models - 14 strategies available","wizardStep4Title": "Review & Save","wizardStep4Desc": "Review your configuration and activate the combo","emailVisibilityStateOn": "On",