feat(providers): add CodeBuddy international (codebuddy-intl, cbai) provider (#15173) (#15799)

Thanks @Junior-HJ! This adds CodeBuddy international (codebuddy-intl / cbai), splitting the CN and intl modules over shared executor, OAuth, usage and token-refresh helpers. Your commits are kept intact. Maintainer fix-up commits on top: restored the 'N AI providers' wording that the count bump had turned into bare numbers in 67 llm.txt files, README alt texts and SVGs; synced the total to 372, since the tip had meanwhile added typesafe without regenerating the reference; typed the two `any` casts in codebuddyDeviceAuth.ts; and regenerated the executor-map and translate-path goldens. The translate-path golden had been generated on win32. Protected surfaces (AGENTS.md, llm.txt) carry the count change only, approved by the owner. Validated: typecheck:core, open-sse typecheck, file-size, t11 any-budget, ESLint, check:docs-all, provider consistency/assets/order/provenance, and 195/195 focused tests across 13 files.

AGENTS.md

@@ -47,7 +47,7 @@ Repository map and Reference Documentation sections below.
 
 ## Project at a Glance
 
-**OmniRoute** — unified AI proxy/router. One endpoint, 370 LLM providers, auto-fallback.
+**OmniRoute** — unified AI proxy/router. One endpoint, 372 LLM providers, auto-fallback.
 
 | Layer         | Location                | Purpose                                                                                                                                                                   |
 | ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

README.md

@@ -7,7 +7,7 @@
 
 # 🚀 OmniRoute — The Free AI Gateway
 
-<img src="./docs/diagrams/readme-hero.svg" width="100%" alt="OmniRoute — Never stop coding. Every AI tool → 370 providers — 150+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini with auto-fallback. RTK + Caveman stacked compression saves 15–95% tokens (~89% avg) — never hit limits. 370 AI providers · 150+ free tiers · ~1.62B free tokens/mo · 19 routing strategies · $0 to start."/>
+<img src="./docs/diagrams/readme-hero.svg" width="100%" alt="OmniRoute — Never stop coding. Every AI tool → 372 providers — 150+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini with auto-fallback. RTK + Caveman stacked compression saves 15–95% tokens (~89% avg) — never hit limits. 372 AI providers · 150+ free tiers · ~1.62B free tokens/mo · 19 routing strategies · $0 to start."/>
 
 </div>
 
@@ -237,7 +237,7 @@ curl http://localhost:20128/v1/chat/completions \
 
 </div>
 
-<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint and 370 providers. Automatic fallback keeps routing while another healthy target is available. Six pillars: resilient fallback across 370 providers · up to 95% token savings on eligible workloads · $0 to start with 150+ free tiers and 54 recurring/keyless free-forever providers · 36 CLI/agent integrations through one config · OpenAI, Claude, Gemini and Responses API compatibility at /v1 · production controls including circuit breakers, TLS stealth, MCP 110 tools, A2A, memory, guardrails, evals and 39,000+ static test declarations across 5,100+ tracked test files."/>
+<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint and 372 providers. Automatic fallback keeps routing while another healthy target is available. Six pillars: resilient fallback across 372 providers · up to 95% token savings on eligible workloads · $0 to start with 150+ free tiers and 54 recurring/keyless free-forever providers · 36 CLI/agent integrations through one config · OpenAI, Claude, Gemini and Responses API compatibility at /v1 · production controls including circuit breakers, TLS stealth, MCP 110 tools, A2A, memory, guardrails, evals and 39,000+ static test declarations across 5,100+ tracked test files."/>
 
 <br/>
 <br/>
@@ -492,7 +492,7 @@ All **19** strategies — mix & match per combo step:
 
 </div>
 
-<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — a dated feature snapshot vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 370 providers, 150+ free tiers built in, 19 routing strategies, 12-engine token compression, built-in MCP server with 110 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA and 42 i18n UI locales. OmniRoute is MIT-licensed and self-hostable. Competitor capabilities and counts may change; see the linked methodology."/>
+<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — a dated feature snapshot vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 372 providers, 150+ free tiers built in, 19 routing strategies, 12-engine token compression, built-in MCP server with 110 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA and 42 i18n UI locales. OmniRoute is MIT-licensed and self-hostable. Competitor capabilities and counts may change; see the linked methodology."/>
 
 <sub>📊 Full methodology &amp; per-feature detail vs 9router, OpenRouter, CLIProxyAPI &amp; LiteLLM → [`docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md`](docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md)</sub>
 

changelog.d/features/15173-codebuddy-intl-provider.md

@@ -0,0 +1,4 @@
+# CodeBuddy International (codebuddy-intl) Provider
+
+Added the CodeBuddy International (`codebuddy.ai`) provider under the `cbai` alias (#15173).
+Parametrizes the shared CodeBuddy device-auth flow, executor, token refresh, and quota fetcher by realm.

config/quality/eslint-suppressions.json

@@ -548,14 +548,6 @@
       "count": 3
     }
   },
-  "open-sse/services/usage/codebuddy-cn.ts": {
-    "@typescript-eslint/no-explicit-any": {
-      "count": 2
-    },
-    "@typescript-eslint/no-unused-vars": {
-      "count": 1
-    }
-  },
   "open-sse/services/usage/github.ts": {
     "@typescript-eslint/no-unused-vars": {
       "count": 1
@@ -1462,11 +1454,6 @@
       "count": 1
     }
   },
-  "src/lib/oauth/providers/codebuddy-cn.ts": {
-    "@typescript-eslint/no-unused-vars": {
-      "count": 1
-    }
-  },
   "src/lib/oauth/providers/codex.ts": {
     "@typescript-eslint/no-unused-vars": {
       "count": 1

docs/architecture/ARCHITECTURE.md

@@ -17,13 +17,13 @@ It provides a single OpenAI-compatible endpoint (`/v1/*`) and routes traffic acr
 
 Core capabilities:
 
-- OpenAI-compatible API surface for CLI/tools (355 providers, 108 executors)
+- OpenAI-compatible API surface for CLI/tools (372 providers, 148 executors)
 - Request/response translation across provider formats
 - Model combo fallback (multi-model sequence)
 - Structured combo steps (`provider + model + connection`) with runtime ordering by `compositeTiers`
 - Account-level fallback (multi-account per provider)
 - Quota preflight and quota-aware P2C account selection in the main chat path
-- OAuth + API-key provider connection management (22 OAuth provider modules)
+- OAuth + API-key provider connection management (27 OAuth provider modules)
 - Embedding generation via `/v1/embeddings` (18 providers)
 - Image generation via `/v1/images/generations` (10+ providers, 20+ models)
 - Audio transcription via `/v1/audio/transcriptions` (18 providers)
@@ -321,10 +321,11 @@ Domain layer modules:
 - Eval runner: `src/lib/evals/evalRunner.ts`
 - Domain state persistence: `src/lib/db/domainState.ts` — SQLite CRUD for fallback chains, budgets, cost history, lockout state, circuit breakers
 
-OAuth provider modules (22 individual files under `src/lib/oauth/providers/`):
+OAuth provider modules (27 individual files under `src/lib/oauth/providers/`):
 
 - Registry index: `src/lib/oauth/providers/index.ts`
-- Individual providers: `agy.ts`, `antigravity.ts`, `claude.ts`, `cline.ts`, `codebuddy-cn.ts`, `codex.ts`, `cursor.ts`, `devin-desktop.ts`, `ghe-copilot.ts`, `github.ts`, `gitlab-duo.ts`, `grok-cli-oauth.ts`, `grok-cli.ts`, `kilocode.ts`, `kimi-coding.ts`, `kiro.ts`, `openference.ts`, `qoder.ts`, `trae.ts`, `xai-oauth.ts`, `zed-hosted.ts`, `zed.ts`
+- Individual providers: `agy.ts`, `antigravity.ts`, `claude.ts`, `cline.ts`, `codebuddy-cn.ts`, `codebuddy-intl.ts`, `codex.ts`, `cursor.ts`, `devin-desktop.ts`, `ghe-copilot.ts`, `github.ts`, `gitlab-duo.ts`, `grok-cli-oauth.ts`, `grok-cli.ts`, `kilocode.ts`, `kimi-coding.ts`, `kiro.ts`, `muse-code.ts`, `openference.ts`, `qoder.ts`, `trae.ts`, `workbuddy.ts`, `xai-oauth.ts`, `zed-hosted.ts`, `zed.ts`
+- Shared helpers: `codebuddyDeviceAuth.ts` (CodeBuddy CN/intl device flow), `museCodeDeviceResponse.ts`
 - Thin wrapper: `src/lib/oauth/providers.ts` — re-exports from individual modules
 
 ## 5) Embedded Services (v3.8.4)

docs/architecture/CODEBASE_DOCUMENTATION.md

@@ -479,7 +479,7 @@ open-sse/
 
 ### 4.2 `open-sse/executors/`
 
-108 provider executors, each extending `BaseExecutor` (`base.ts`):
+148 provider executors, each extending `BaseExecutor` (`base.ts`):
 
 `antigravity`, `azure-openai`, `blackbox-web`, `cliproxyapi`,
 `chatgpt-web-codex`, `cloudflare-ai`, `codex`, `commandCode`, `cursor`, `default`, `devin-cli`,

docs/diagrams/cli-terminal.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 350" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Animated terminal demoing the OmniRoute CLI: omniroute providers list (370 providers registered, anthropic, codex, glm, kimi shown active), omniroute combo list (always-on priority, cost-saver, fusion-panel, context-relay) and omniroute health (healthy, 18412 requests in 24h, p95 412ms, circuit breakers 24 closed, 1 half-open, 0 open), cycling over 86 top-level commands: providers, oauth, keys, combo, nodes, models, cache, compression, cost, usage, quota, health, resilience, telemetry, logs, audit, mcp, a2a, cloud, memory, skills, eval, doctor, repl, tunnel, backup, sync, webhooks, policy, pricing, translator, simulate and more.">
+<svg viewBox="0 0 1200 350" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Animated terminal demoing the OmniRoute CLI: omniroute providers list (372 providers registered, anthropic, codex, glm, kimi shown active), omniroute combo list (always-on priority, cost-saver, fusion-panel, context-relay) and omniroute health (healthy, 18412 requests in 24h, p95 412ms, circuit breakers 24 closed, 1 half-open, 0 open), cycling over 86 top-level commands: providers, oauth, keys, combo, nodes, models, cache, compression, cost, usage, quota, health, resilience, telemetry, logs, audit, mcp, a2a, cloud, memory, skills, eval, doctor, repl, tunnel, backup, sync, webhooks, policy, pricing, translator, simulate and more.">
 <desc>Compact animated terminal cycling three real OmniRoute CLI commands with a typewriter effect and a scrolling subcommand ticker; the first frame shows the completed providers-list screen.</desc>
 <defs><clipPath id="tickerClip"><rect x="12" y="304" width="1176" height="40"/></clipPath><clipPath id="tw0"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;31;61;92;122;153;184;214;245;245" keyTimes="0;0.012;0.018;0.024;0.030;0.036;0.042;0.048;0.054;1" dur="18s" repeatCount="indefinite"/></rect></clipPath><clipPath id="tw1"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;26;51;76;102;128;153;178;204;204" keyTimes="0;0.348;0.351;0.357;0.363;0.369;0.375;0.381;0.387;1" dur="18s" repeatCount="indefinite"/></rect></clipPath><clipPath id="tw2"><rect x="64" y="46" height="26" width="0"><animate attributeName="width" calcMode="discrete" values="0;20;41;61;82;102;122;143;163;163" keyTimes="0;0.678;0.684;0.690;0.696;0.702;0.708;0.714;0.720;1" dur="18s" repeatCount="indefinite"/></rect></clipPath></defs>
 <rect width="1200" height="350" fill="#0d1117"/>

docs/diagrams/comparison-table.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 780" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Comparison table: OmniRoute versus 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute is the only one with the full set: 370 providers, 150+ free providers built-in, 20 routing strategies, 12-engine token compression, a built-in MCP server with 110 tools, A2A protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, desktop/Termux/PWA, 43 UI locales and 100% MIT self-hosted. 9router has free providers, RTK compression and translation but no MCP, A2A, memory, guardrails, cloud agents or stealth. OpenRouter is a hosted SaaS with 400+ models, guardrails and a hosted MCP but is not self-hosted and lacks A2A, memory, cloud agents and stealth. CLIProxyAPI is a light OAuth proxy with two routing strategies. LiteLLM has 100+ providers, A2A and extensive guardrails but no memory, compression, free tier, stealth or cloud agents.">
+<svg viewBox="0 0 1200 780" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="Comparison table: OmniRoute versus 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute is the only one with the full set: 372 providers, 150+ free providers built-in, 20 routing strategies, 12-engine token compression, a built-in MCP server with 110 tools, A2A protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, desktop/Termux/PWA, 43 UI locales and 100% MIT self-hosted. 9router has free providers, RTK compression and translation but no MCP, A2A, memory, guardrails, cloud agents or stealth. OpenRouter is a hosted SaaS with 400+ models, guardrails and a hosted MCP but is not self-hosted and lacks A2A, memory, cloud agents and stealth. CLIProxyAPI is a light OAuth proxy with two routing strategies. LiteLLM has 100+ providers, A2A and extensive guardrails but no memory, compression, free tier, stealth or cloud agents.">
   <desc>Static-header comparison table where each capability row fades in top to bottom; the OmniRoute column is highlighted and shows a check or a leading value in every row, while competitors show a mix of checks, partials and crosses.</desc>
   <defs>
     <pattern id="gC" width="32" height="32" patternUnits="userSpaceOnUse"><path d="M 32 0 L 0 0 0 32" fill="none" stroke="#ffffff" stroke-opacity="0.05" stroke-width="1"/></pattern>

docs/diagrams/promise-pillars.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 540" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="The OmniRoute promise: one endpoint and 370 providers. Six pillars. Resilient fallback: automatic routing continues while another healthy target is available. Save up to 95 percent of eligible tokens: RTK plus Caveman stacked compression averages about 89 percent on tool-heavy sessions. Zero dollars to start: 150+ providers with a free tier and 54 recurring or keyless free-forever providers. Every tool works: 36 CLI and agent integration records, including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity, through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation at /v1. Production controls: circuit breakers, TLS stealth, MCP with 110 tools, A2A, memory, guardrails, evals, and 39,000+ static test declarations across 5,100+ tracked test files.">
+<svg viewBox="0 0 1200 540" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="The OmniRoute promise: one endpoint and 372 providers. Six pillars. Resilient fallback: automatic routing continues while another healthy target is available. Save up to 95 percent of eligible tokens: RTK plus Caveman stacked compression averages about 89 percent on tool-heavy sessions. Zero dollars to start: 150+ providers with a free tier and 54 recurring or keyless free-forever providers. Every tool works: 36 CLI and agent integration records, including Claude Code, Codex, Cursor, Cline, Copilot and Antigravity, through one config. One endpoint: OpenAI, Claude, Gemini and Responses API translation at /v1. Production controls: circuit breakers, TLS stealth, MCP with 110 tools, A2A, memory, guardrails, evals, and 39,000+ static test declarations across 5,100+ tracked test files.">
   <desc>Animated promise card: six pillar tiles fade in in reading order, then a soft colored border highlight sweeps from tile to tile in a continuous cycle.</desc>
   <defs>
     <pattern id="gridPaperP" width="32" height="32" patternUnits="userSpaceOnUse">
@@ -21,7 +21,7 @@
     <line x1="150" y1="53" x2="1160" y2="53" stroke="#232b38" stroke-width="1.5"/>
   </g>
   <g>
-    <text x="40" y="100" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="23" font-weight="600" fill="#c9d1d9">One endpoint. <tspan fill="#a78bfa" font-weight="800">370 providers.</tspan> Never stop building — OmniRoute picks <tspan fill="#7ee787" font-weight="700">the cheapest one that works</tspan>.</text>
+    <text x="40" y="100" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="23" font-weight="600" fill="#c9d1d9">One endpoint. <tspan fill="#a78bfa" font-weight="800">372 providers.</tspan> Never stop building — OmniRoute picks <tspan fill="#7ee787" font-weight="700">the cheapest one that works</tspan>.</text>
   </g>
 
   <g font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif">
@@ -38,7 +38,7 @@
         <line x1="3.9" y1="3.9" x2="18.1" y2="18.1"/>
       </g>
       <text x="102" y="170" font-size="18" font-weight="800" fill="#74b9ff">Never hit limits</text>
-      <text x="66" y="204" font-size="13.5" fill="#a1a1aa">Auto-fallback across 370 providers in</text>
+      <text x="66" y="204" font-size="13.5" fill="#a1a1aa">Auto-fallback across 372 providers in</text>
       <text x="66" y="226" font-size="13.5" fill="#a1a1aa">milliseconds. Quota out? The next provider</text>
       <text x="66" y="248" font-size="13.5" fill="#a1a1aa">takes over while a healthy target remains.</text>
     </g>

docs/diagrams/readme-hero.svg

@@ -1,4 +1,4 @@
-<svg viewBox="0 0 1200 548" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="OmniRoute hero: Never stop coding. Every AI tool to 370 providers — 150+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot and Antigravity into free Claude, GPT and Gemini with auto-fallback. RTK + Caveman stacked compression saves 15 to 95 percent of tokens — about 89 percent average on tool-heavy sessions — so you never hit limits. Stats: 370 AI providers, 150+ free tiers, about 1.62B free tokens per month, 15 to 95 percent token savings, 20 routing strategies, zero dollars to start.">
+<svg viewBox="0 0 1200 548" xmlns="http://www.w3.org/2000/svg" role="img" aria-label="OmniRoute hero: Never stop coding. Every AI tool to 372 providers — 150+ free — through one endpoint. Claude Code, Codex, Cursor, Cline, Copilot and Antigravity into free Claude, GPT and Gemini with auto-fallback. RTK + Caveman stacked compression saves 15 to 95 percent of tokens — about 89 percent average on tool-heavy sessions — so you never hit limits. Stats: 372 AI providers, 150+ free tiers, about 1.62B free tokens per month, 15 to 95 percent token savings, 20 routing strategies, zero dollars to start.">
   <desc>Animated hero card: a pulse travels the divider line and a compression bar demo repeatedly shrinks a prompt by up to 95 percent; all headline content is static and readable on the first frame.</desc>
   <defs>
     <pattern id="gridPaperH" width="32" height="32" patternUnits="userSpaceOnUse">
@@ -28,7 +28,7 @@
   <text x="48" y="138" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="60" font-weight="800" fill="#e9edf3">Never stop coding<tspan fill="#a855f7">.</tspan></text>
 
   <!-- subheadline -->
-  <text x="48" y="184" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="25" font-weight="600" fill="#c9d1d9">Every AI tool → <tspan fill="#a78bfa" font-weight="800">370 providers</tspan> — <tspan fill="#7ee787" font-weight="800">150+ free</tspan> — through one endpoint.</text>
+  <text x="48" y="184" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="25" font-weight="600" fill="#c9d1d9">Every AI tool → <tspan fill="#a78bfa" font-weight="800">372 providers</tspan> — <tspan fill="#7ee787" font-weight="800">150+ free</tspan> — through one endpoint.</text>
 
   <!-- plug line -->
   <text x="48" y="222" font-family="Inter, 'Segoe UI', Arial, Helvetica, system-ui, sans-serif" font-size="16.5" fill="#a1a1aa">Claude Code · Codex · Cursor · Cline · Copilot · Antigravity&#160;&#160;→&#160;&#160;<tspan fill="#7ee787" font-weight="700">FREE</tspan> Claude / GPT / Gemini · auto-fallback</text>

docs/i18n/am/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/ar/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/az/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/bg/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/bn/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/bs/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/cs/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/da/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/de/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/el/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/es/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/et/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/fa/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/fi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/fr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/ga/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/gu/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/ha/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/he/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/hi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/hr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/hu/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/hy/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/id/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/ig/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/it/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/ja/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/ka/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/km/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/kn/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/ko/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/lt/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/lv/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/ml/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/mr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/ms/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/mt/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/my/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/ne/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/nl/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/no/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/or/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/pa/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/phi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/pl/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/pt-BR/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/pt/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/ro/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/ru/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/si/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/sk/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/sl/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/sr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/sv/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/sw/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/ta/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/te/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/th/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/tr/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/uk-UA/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/ur/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/uz/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/vi/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/yo/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/zh-CN/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/i18n/zh-TW/llm.txt

@@ -4,7 +4,7 @@
 
 ---
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -281,7 +281,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

docs/reference/PROVIDER_REFERENCE.md

@@ -1,16 +1,16 @@
 ---
 title: "Provider Reference"
 version: 3.8.52
-lastUpdated: 2026-10-08
+lastUpdated: 2026-10-10
 ---
 
 # Provider Reference
 
 > **Auto-generated** from `src/shared/constants/providers.ts` — do not edit by hand.
 > Regenerate with: `npm run gen:provider-reference`
-> **Last generated:** 2026-10-08
+> **Last generated:** 2026-10-10
 
-Total providers: **370**. See category breakdown below.
+Total providers: **372**. See category breakdown below.
 
 ## Categories
 
@@ -49,7 +49,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `veoaifree-web` | `veo-free` | Veo AI Free | No-auth, video | [link](https://veoaifree.com) | No auth required. Rate limited to 6 requests/hour per IP. | — |
 | `zcode` | `zc` | ZCode (GLM Coding Plan) | No-auth | [link](https://zcode.z.ai) | No API key stored by OmniRoute. The local ZCode app-server uses the existing builtin:zai-coding-plan login. | — |
 
-## OAuth Providers (26)
+## OAuth Providers (27)
 
 | ID | Alias | Name | Tags | Website | Notes |
 |----|-------|------|------|---------|-------|
@@ -60,6 +60,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `cline` | `cl` | Cline | OAuth | — | Sign in with your Cline account (OAuth), or paste a direct API key from app.cline.bot → Settings → API Keys. Multiple API keys are supported and rotated automatically — add each as a separate connection. |
 | `clinepass` | `cp` | ClinePass | OAuth | [link](https://cline.bot/cline-pass) | ClinePass is Cline's $9.99/mo subscription bundling 10 open coding models. Sign in with your Cline account (same login as the Cline CLI/IDE), or paste a direct ClinePass API key (app.cline.bot → Settings → API Keys). A ClinePass subscription unlocks the cline-pass/* models. Reuses the Cline WorkOS OAuth flow. |
 | `codebuddy-cn` | `cbcn` | CodeBuddy CN | OAuth | [link](https://copilot.tencent.com) | Tencent CodeBuddy CN (copilot.tencent.com). Sign in via the official CLI device-code flow, or paste a direct API key (sent as Authorization: Bearer). Catalog: GLM / Kimi / MiniMax / DeepSeek / Hunyuan. |
+| `codebuddy-intl` | `cbai` | CodeBuddy Intl | OAuth | [link](https://www.codebuddy.ai) | CodeBuddy International (codebuddy.ai). Sign in via the device-code flow, or paste a direct API key (sent as Authorization: Bearer). Catalog: GLM / Kimi / MiniMax / DeepSeek / Hunyuan. |
 | `codex` | `cx` | OpenAI Codex | OAuth | — | — |
 | `cursor` | `cu` | Cursor IDE | OAuth | — | — |
 | `devin-cli` | `dv` | Devin CLI | OAuth | [link](https://cli.devin.ai) | Requires the Devin CLI binary. Run `devin auth login` to authenticate, or provide your WINDSURF_API_KEY. Install: https://cli.devin.ai |
@@ -73,7 +74,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `kiro` | `kr` | Kiro AI | OAuth | — | Free tier: 50 credits/month (~25K–100K tokens). ⚠️ Kiro ToS prohibits third-party proxy/harness use. |
 | `muse-code` | `mc` | Muse Code (Meta) | OAuth | [link](https://ai.developer.meta.com/docs/muse-code/auth) | Sign in with the Muse Code device flow (same as `muse login` / CLIProxyAPI `-meta-login`) to use a Muse subscription, or paste a META_API_KEY. Device login keeps the durable dca token and mints the inference key; a 401 remints that key. Wire format is OpenAI Responses (POST /responses). |
 | `openference` | `of` | Openference | OAuth | [link](https://openference.com) | Sign in with your Openference account to route requests through api.openference.com. Includes free-tier access to Qwen3.8 27b and Llama 3.2 3B — see openference.com/pricing for current plan terms. |
-| `qoder` | `if` | Qoder | OAuth | — | — |
+| `qoder` | `if` | Qoder | OAuth | — | PAT (pt-): requires local qodercli; plain chat only, no caller tools, buffered streaming and a 45-second chat limit. HTTP keys use DashScope; browser OAuth requires administrator configuration. |
 | `trae` | `tr` | Trae | OAuth | [link](https://trae.ai) | Trae is an AI-native IDE by ByteDance (SOLO remote agent). Authorize via trae.ai in the popup, or sign in at solo.trae.ai and paste the Cloud-IDE-JWT (sent as 'Authorization: Cloud-IDE-JWT <token>', ~14-day lifetime) as the access token; web_id/biz_user_id/user_unique_id/scope/tenant/region propagate via providerSpecificData. No headless refresh for pasted tokens — re-paste on expiry. |
 | `workbuddy` | `wb` | WorkBuddy | OAuth | [link](https://www.workbuddy.ai) | Tencent WorkBuddy (www.workbuddy.ai). Authorize the CLI device flow in the popup; OmniRoute then polls for the token and attaches the required X-Product: SaaS header. The model roster is served by the authenticated catalogue, so it is discovered live rather than listed here. WorkBuddy only accepts streaming requests, which OmniRoute accumulates back into a JSON response for non-streaming callers. |
 | `xai-oauth` | `xao` | xAI OAuth (Grok) | OAuth | [link](https://x.ai) | Sign in with xAI to use api.x.ai models such as Grok 4.5. This is separate from Grok Build JWT sessions, which use cli-chat-proxy.grok.com and grok-build model aliases. |
@@ -122,7 +123,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `zai-web` | `zw` | Z.ai Web | Web cookie | [link](https://chat.z.ai) | Copy the "token" value from chat.z.ai → DevTools → Application → Local Storage. Do not copy cookies; OmniRoute handles the per-request CAPTCHA through its browser transport. | — |
 | `zenmux-free` | `zmf` | ZenMux Free (Web) | Web cookie | [link](https://zenmux.ai) | Login at zenmux.ai, then export all cookies using EditThisCookie or Cookie-Editor and paste the full Cookie header string here. Refresh every ~30 days. | — |
 
-## API Key Providers (paid / paid-with-free-credits) (248)
+## API Key Providers (paid / paid-with-free-credits) (249)
 
 | ID | Alias | Name | Tags | Website | Notes |
 |----|-------|------|------|---------|-------|
@@ -342,6 +343,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 | `tokenreply` | `tokenreply` | TokenReply | API key, aggregator | [link](https://www.tokenreply.com) | Free-tagged models have model- and campaign-specific daily limits; no fixed global free quota is published. |
 | `tokenrouter` | `trk` | TokenRouter | API key | [link](https://tokenrouter.com) | Use your TokenRouter API key in Authorization: Bearer <key>. Fully OpenAI-compatible. API base URL: https://api.tokenrouter.com/v1. |
 | `topaz` | `topaz` | Topaz | API key, image | [link](https://topazlabs.com) | — |
+| `typesafe` | `typesafe` | TypeSafe AI | API key | [link](https://docs.typesafe.ai) | Bearer API key for api.typesafe.ai. OmniRoute uses it for System One evaluation (Jev) — not chat completions. Store the key here; the jev combo strategy reads it at request time. |
 | `typhoon` | `typhoon` | Typhoon | API key | [link](https://docs.opentyphoon.ai) | Free API key with a 5 req/s and 200 req/m rate limit. |
 | `uc-direct` | `ucd` | UC Direct (uncensored.com) | API key | [link](https://uncensored.com) | Use your uncensored.com Developer API key (uai_sk_live_...). OmniRoute sends it as the X-api-key header to the OpenAI-compatible https://api.uncensored.com/api/v1 endpoint. The key never expires. This is the metered/credits surface; the un-metered subscription chat is the separate 'uc' provider. |
 | `udio` | `udio` | Udio | API key | [link](https://udio.com) | Paste session cookie from udio.com (Supabase auth) |
@@ -458,7 +460,7 @@ Use the dashboard at `/dashboard/providers` to enable, configure, and test each
 
 - Catalog: [`src/shared/constants/providers.ts`](../../src/shared/constants/providers.ts)
 - Registry (per-model details): [`open-sse/config/providerRegistry.ts`](../../open-sse/config/providerRegistry.ts)
-- Executors: [`open-sse/executors/`](../../open-sse/executors/) (146 implementations)
+- Executors: [`open-sse/executors/`](../../open-sse/executors/) (148 implementations)
 - Translators: [`open-sse/translator/`](../../open-sse/translator/)
 
 ## See Also

llm.txt

@@ -1,6 +1,6 @@
 # OmniRoute
 
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 370 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
+> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 372 AI providers — all through a single OpenAI-compatible endpoint. Includes a built-in MCP Server (110 tools), A2A v0.3 protocol, Memory/Skills systems, Cloud Agents (codex, cursor, devin, jules), Guardrails framework, and an Electron desktop app.
 
 ## Overview
 
@@ -277,7 +277,7 @@ OmniRoute solves the problem of managing multiple AI provider subscriptions, quo
 ## Key Features (v3.8.50)
 
 ### Core Proxy
-- **370 AI providers** with automatic format translation
+- **372 AI providers** with automatic format translation
 - **Provider categories**: Free (90+ free tiers), OAuth, API Key, Self-Hosted, Custom (OpenAI/Anthropic-compatible)
 - **19 routing strategies**: priority, weighted, round-robin, fill-first, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline
 - **4-tier fallback**: Subscription → API Key → Cheap → Free

open-sse/config/providerHeaderProfiles.ts

@@ -191,6 +191,9 @@ export const QODER_DEFAULT_USER_AGENT = "Qoder-Cli";
 // getCodeBuddyCnUserAgent(), which may replace both numbers with a newer npm publish.
 export const CODEBUDDY_CN_USER_AGENT = "CLI/2.108.1 CodeBuddy/2.108.1";
 
+// CodeBuddy International (codebuddy.ai) - single source of truth for intl profile.
+export const CODEBUDDY_INTL_USER_AGENT = "IDE/2.108.1 CodeBuddy/2.108.1";
+
 const QWEN_DOTTED_TRIPLE_PATTERN = /^\d+\.\d+\.\d+$/;
 const NPM_QWEN_CODE_LATEST_URL = "https://registry.npmjs.org/@qwen-code/qwen-code/latest";
 const NPM_CODEBUDDY_LATEST_URL = "https://registry.npmjs.org/@tencent-ai/codebuddy-code/latest";

open-sse/config/providers/index.ts

@@ -226,6 +226,7 @@ import { tokenrouterProvider } from "./registry/tokenrouter/index.ts";
 import { token_kioskProvider } from "./registry/token-kiosk/index.ts";
 import { grok_cliProvider } from "./registry/grok-cli/index.ts";
 import { codebuddy_cnProvider } from "./registry/codebuddy-cn/index.ts";
+import { codebuddy_intlProvider } from "./registry/codebuddy-intl/index.ts";
 import { pioneerProvider } from "./registry/pioneer/index.ts";
 import { zenmux_freeProvider } from "./registry/zenmux-free/index.ts";
 import { tinycmsProvider } from "./registry/tinycms/index.ts";
@@ -515,6 +516,7 @@ export const REGISTRY: Record<string, RegistryEntry> = {
   "token-kiosk": token_kioskProvider,
   "grok-cli": grok_cliProvider,
   "codebuddy-cn": codebuddy_cnProvider,
+  "codebuddy-intl": codebuddy_intlProvider,
   pioneer: pioneerProvider,
   "zenmux-free": zenmux_freeProvider,
   "tinycms-web": tinycmsProvider,

open-sse/config/providers/registry/codebuddy-cn/index.ts

@@ -9,7 +9,7 @@ import type { RegistryEntry } from "../../shared.ts";
  * `reasoning_effort` (not vendor-native thinking shapes). Streaming is forced
  * by the executor because non-stream requests are rejected with code 11101.
  *
- * Short alias "cbcn" reserves "cbai" for a future CodeBuddy intl variant.
+ * Short alias "cbcn" (paired with "cbai" for the CodeBuddy intl variant).
  * Per-model context windows/vision are advertised in the catalog below.
  */
 export const codebuddy_cnProvider: RegistryEntry = {

open-sse/config/providers/registry/codebuddy-intl/index.ts

@@ -0,0 +1,199 @@
+import { CODEBUDDY_INTL_USER_AGENT } from "../../../providerHeaderProfiles.ts";
+import type { RegistryEntry } from "../../shared.ts";
+
+/**
+ * CodeBuddy International (codebuddy.ai).
+ *
+ * Unified OpenAI-compatible gateway behind the CodeBuddy International service.
+ * Carries live-probed models (GLM, Kimi, MiniMax, DeepSeek, Hunyuan, GPT, Gemini)
+ * and reasons via OpenAI-style `reasoning_effort` (not vendor-native thinking shapes).
+ * Streaming is forced by the executor because non-stream requests are rejected
+ * with code 11101. The intl gateway publishes no model-catalog endpoint, so
+ * this list is curated from live-gateway probes.
+ *
+ * Short alias "cbai" matches the reserved alias convention.
+ */
+export const codebuddy_intlProvider: RegistryEntry = {
+  id: "codebuddy-intl",
+  alias: "cbai",
+  format: "openai",
+  executor: "codebuddy-intl",
+  baseUrl: "https://www.codebuddy.ai/v2/chat/completions",
+  authType: "oauth",
+  authHeader: "bearer",
+  headers: {
+    "User-Agent": CODEBUDDY_INTL_USER_AGENT,
+    "X-Product": "SaaS",
+    "X-IDE-Type": "IDE",
+    "X-IDE-Name": "IDE",
+    "x-requested-with": "XMLHttpRequest",
+    "x-codebuddy-request": "1",
+  },
+  models: [
+    {
+      id: "hy4-preview",
+      name: "Hy4-Preview",
+      contextLength: 256000,
+      maxOutputTokens: 64000,
+      supportsReasoning: true,
+      supportsVision: true,
+    },
+    {
+      id: "hy3",
+      name: "Hy3",
+      contextLength: 192000,
+      maxOutputTokens: 64000,
+      supportsReasoning: true,
+      supportsVision: true,
+    },
+    {
+      id: "gpt-6-astra",
+      name: "GPT 6.0 Astra",
+      contextLength: 1000000,
+      maxOutputTokens: 64000,
+      supportsReasoning: true,
+    },
+    {
+      id: "gpt-6-luna",
+      name: "GPT-6-Luna",
+      contextLength: 1000000,
+      maxOutputTokens: 64000,
+      supportsReasoning: true,
+    },
+    {
+      id: "gpt-6-sol",
+      name: "GPT-6-Sol",
+      contextLength: 1000000,
+      maxOutputTokens: 64000,
+      supportsReasoning: true,
+    },
+    {
+      id: "gpt-5.6-sol",
+      name: "GPT-5.6-Sol",
+      contextLength: 512000,
+      maxOutputTokens: 64000,
+      supportsReasoning: true,
+    },
+    {
+      id: "gpt-5.6-terra",
+      name: "GPT-5.6-Terra",
+      contextLength: 256000,
+      maxOutputTokens: 64000,
+      supportsReasoning: true,
+    },
+    {
+      id: "gpt-5.6-luna",
+      name: "GPT-5.6-Luna",
+      contextLength: 256000,
+      maxOutputTokens: 64000,
+      supportsReasoning: true,
+    },
+    {
+      id: "gpt-5.5",
+      name: "GPT-5.5",
+      contextLength: 256000,
+      maxOutputTokens: 64000,
+      supportsReasoning: true,
+    },
+    {
+      id: "gpt-5.4",
+      name: "GPT-5.4",
+      contextLength: 256000,
+      maxOutputTokens: 64000,
+      supportsReasoning: true,
+    },
+    {
+      id: "gpt-5.3-codex",
+      name: "GPT-5.3-Codex",
+      contextLength: 256000,
+      maxOutputTokens: 64000,
+      supportsReasoning: true,
+    },
+    {
+      id: "gemini-3.5-flash",
+      name: "Gemini-3.5-Flash",
+      contextLength: 1000000,
+      maxOutputTokens: 64000,
+      supportsReasoning: true,
+      supportsVision: true,
+    },
+    {
+      id: "glm-5v-turbo",
+      name: "GLM-5v-Turbo",
+      contextLength: 200000,
+      maxOutputTokens: 38000,
+      supportsReasoning: true,
+      supportsVision: true,
+    },
+    {
+      id: "glm-5.3",
+      name: "GLM-5.3",
+      contextLength: 1000000,
+      maxOutputTokens: 48000,
+      supportsReasoning: true,
+    },
+    {
+      id: "glm-5.3-flash",
+      name: "GLM-5.3-Flash",
+      contextLength: 1000000,
+      maxOutputTokens: 48000,
+      supportsReasoning: true,
+    },
+    {
+      id: "glm-5.2",
+      name: "GLM-5.2",
+      contextLength: 1000000,
+      maxOutputTokens: 48000,
+      supportsReasoning: true,
+    },
+    {
+      id: "glm-5.1",
+      name: "GLM-5.1",
+      contextLength: 200000,
+      maxOutputTokens: 48000,
+      supportsReasoning: true,
+    },
+    {
+      id: "minimax-m3",
+      name: "MiniMax-M3",
+      contextLength: 512000,
+      maxOutputTokens: 48000,
+      supportsReasoning: true,
+      supportsVision: true,
+    },
+    {
+      id: "kimi-k3",
+      name: "Kimi-K3",
+      contextLength: 256000,
+      maxOutputTokens: 32000,
+      supportsReasoning: true,
+      supportsVision: true,
+    },
+    {
+      id: "kimi-k2.7",
+      name: "Kimi-K2.7-Code",
+      contextLength: 256000,
+      maxOutputTokens: 32000,
+      supportsReasoning: true,
+      supportsVision: true,
+    },
+    {
+      id: "kimi-k2.6",
+      name: "Kimi-K2.6",
+      contextLength: 256000,
+      maxOutputTokens: 32000,
+      supportsReasoning: true,
+      supportsVision: true,
+    },
+    {
+      id: "deepseek-v4.1-flash",
+      name: "DeepSeek-V4.1-Flash",
+      contextLength: 1000000,
+      maxOutputTokens: 50000,
+      supportsReasoning: true,
+      supportsVision: true,
+    },
+  ],
+};
+
+export default codebuddy_intlProvider;

open-sse/executors/codebuddy-cn.ts

@@ -1,208 +1,14 @@
-import { DefaultExecutor } from "./default.ts";
-import type { ExecuteInput, ExecutorExecuteResult, ProviderCredentials } from "./base.ts";
-
-const SENSITIVE_CONTENT_REJECTION =
-  "抱歉，系统检测到您当前输入的信息存在敏感内容，我无法响应您的请求，请检查后重新输入";
-const LARGE_TOOL_METADATA_BYTES = 64 * 1024;
-
-function responseFromResult(result: ExecutorExecuteResult): Response {
-  return result instanceof Response ? result : result.response;
-}
-
-function credentialsFromResult(
-  result: ExecutorExecuteResult,
-  fallback: ProviderCredentials
-): ProviderCredentials {
-  if (result instanceof Response || !result.headers) return fallback;
-
-  const authorization = Object.entries(result.headers).find(
-    ([name]) => name.toLowerCase() === "authorization"
-  )?.[1];
-  if (!authorization?.startsWith("Bearer ")) return fallback;
-
-  return {
-    ...fallback,
-    accessToken: authorization.slice("Bearer ".length),
-    expiresAt: undefined,
-  };
-}
-
-function compactToolDescriptions(body: unknown): unknown | null {
-  if (!body || typeof body !== "object" || Array.isArray(body)) return null;
-
-  const request = body as Record<string, unknown>;
-  if (!Array.isArray(request.tools) || request.tools.length === 0) return null;
-
-  const originalTools = request.tools;
-  try {
-    const serializedTools = JSON.stringify(originalTools);
-    if (new TextEncoder().encode(serializedTools).byteLength < LARGE_TOOL_METADATA_BYTES) {
-      return null;
-    }
-  } catch {
-    return null;
-  }
-
-  let tools: unknown[] | null = null;
-  originalTools.forEach((tool, index) => {
-    if (!tool || typeof tool !== "object" || Array.isArray(tool)) return;
-
-    const declaration = tool as Record<string, unknown>;
-    if (
-      declaration.type !== "function" ||
-      !declaration.function ||
-      typeof declaration.function !== "object" ||
-      Array.isArray(declaration.function)
-    ) {
-      return;
-    }
-
-    const toolFunction = declaration.function as Record<string, unknown>;
-    if (!Object.prototype.hasOwnProperty.call(toolFunction, "description")) return;
-
-    const compactFunction = { ...toolFunction };
-    delete compactFunction.description;
-    tools ??= originalTools.slice();
-    tools[index] = { ...declaration, function: compactFunction };
-  });
-
-  return tools ? { ...request, tools } : null;
-}
-
-async function isSensitiveContentRejection(response: Response): Promise<boolean> {
-  if (response.status !== 400) return false;
-  const responseText = await response
-    .clone()
-    .text()
-    .catch(() => "");
-  return responseText.includes(SENSITIVE_CONTENT_REJECTION);
-}
+import { CodeBuddyBaseExecutor } from "./codebuddy/shared.ts";
 
 /**
  * CodeBuddyCnExecutor — talks to https://copilot.tencent.com/v2/chat/completions
  *
- * CodeBuddy CN is an OpenAI-compatible Tencent gateway but it rejects non-stream
- * chat requests (HTTP 400, code 11101 "Non-stream chat request is currently not
- * supported"). The same-format (openai→openai) translator path leaves body.stream
- * as the client sent it, so we force it true here — OmniRoute still re-aggregates
- * the SSE into a JSON response for non-streaming clients.
- *
- * Reasoning params are opt-in: reasoning_summary:"auto" is only added when the
- * client explicitly sets reasoning_effort. Plain requests are left untouched.
- * When the caller explicitly asks for "none"/"off" we drop the field entirely
- * (the gateway has no "none" value). Forcing reasoning on plain requests trips
- * CodeBuddy's content filter and returns an error.
- *
- * Agent system prompt replacement: Tencent's content filter flags CLI agent system
- * prompts ("You are Claude Code, Anthropic's official CLI…") as prompt injection /
- * sensitive content and rejects the whole request. Detect agent system prompts
- * (length catch-all + identity-marker regex) and replace them with a neutral one,
- * while leaving legitimate user system prompts untouched. Content may be a string
- * or typed blocks ([{type:"text",text}]) depending on the incoming client format,
- * so flatten before matching and preserve the original shape on replacement.
+ * CodeBuddy CN is an OpenAI-compatible Tencent gateway. Inherits all shared
+ * CodeBuddy gateway behavior (forced stream, reasoning_summary, agent-prompt
+ * sanitization, tool compaction).
  */
-export class CodeBuddyCnExecutor extends DefaultExecutor {
-  constructor() {
-    super("codebuddy-cn");
-  }
-
-  async execute(input: ExecuteInput): Promise<ExecutorExecuteResult> {
-    const result = await super.execute(input);
-    if (!(await isSensitiveContentRejection(responseFromResult(result)))) {
-      return result;
-    }
-
-    const compactBody = compactToolDescriptions(input.body);
-    if (!compactBody) return result;
-
-    input.log?.debug?.(
-      "CODEBUDDY_CN",
-      "Upstream rejected an oversized tool request as sensitive content; retrying with compact tool descriptions"
-    );
-    return super.execute({
-      ...input,
-      body: compactBody,
-      credentials: credentialsFromResult(result, input.credentials),
-    });
-  }
-
-  transformRequest(
-    model: string,
-    body: unknown,
-    stream: boolean,
-    credentials: ProviderCredentials
-  ): unknown {
-    const transformed = super.transformRequest(model, body, stream, credentials);
-    if (!transformed || typeof transformed !== "object" || Array.isArray(transformed)) {
-      return transformed;
-    }
-    const out = transformed as Record<string, unknown>;
-    out.stream = true;
-
-    const eff = out.reasoning_effort;
-    if (eff === "none" || eff === "off") {
-      delete out.reasoning_effort;
-    } else if (eff) {
-      out.reasoning_summary = "auto";
-    }
-
-    // --- Agent system prompt replacement ---
-    // Tencent's content filter flags CLI agent system prompts as sensitive content.
-    // Detect and replace them with a neutral prompt.
-    const NEUTRAL_PROMPT = "You are a helpful AI assistant that helps with software engineering tasks.";
-    const AGENT_PATTERN = /you are claude code|claude.?code.+official.+cli|anthropic.+official.+cli|anxthxropic.+official.+cli|you are (?:cursor|windsurf|cline|aider|continue|copilot|cody)|you are an? (?:ai )?(?:coding |code )?agent|cc_entrypoint\s*=\s*(?:cli|vscode|jetbrains|gui)|claude.?code.+issues|give feedback.+claude.?code|you are .{0,30}(?:powerful )?ai agent|orchestration capabilities|OhMyOpenCode|<agent-identity>|<Role>|<Behavior_Instructions>/i;
-    const flatten = (content: unknown): string =>
-      typeof content === "string"
-        ? content
-        : Array.isArray(content)
-          ? (content as Array<Record<string, unknown>>)
-              .map((b) => (b && typeof b.text === "string" ? b.text : ""))
-              .join("\n")
-          : "";
-
-    // Handle top-level `system` field (Anthropic format after translation)
-    if (out.system) {
-      const text = flatten(out.system);
-      if (text && (text.length > 2000 || AGENT_PATTERN.test(text))) {
-        out.system = NEUTRAL_PROMPT;
-      }
-    }
-
-    // Handle messages array with role: "system"
-    if (Array.isArray(out.messages)) {
-      out.messages = (out.messages as Array<Record<string, unknown>>).map((message) => {
-        if (!message || message.role !== "system") return message;
-        const text = flatten(message.content);
-        if (!text) return message;
-        if (text.length > 2000 || AGENT_PATTERN.test(text)) {
-          return typeof message.content === "string"
-            ? { ...message, content: NEUTRAL_PROMPT }
-            : { ...message, content: [{ type: "text", text: NEUTRAL_PROMPT }] };
-        }
-        return message;
-      });
-    }
-
-    // --- Strip oversized tool descriptions (>64KB) ---
-    // Large tool descriptions can also trigger the content filter.
-    if (Array.isArray(out.tools) && out.tools.length > 0) {
-      try {
-        const s = JSON.stringify(out.tools);
-        if (new TextEncoder().encode(s).byteLength >= 65536) {
-          out.tools = (out.tools as Array<Record<string, unknown>>).map((tool) => {
-            if (!tool || typeof tool !== "object" || Array.isArray(tool)) return tool;
-            if (tool.type !== "function" || !tool.function || typeof tool.function !== "object" || Array.isArray(tool.function)) return tool;
-            if (!Object.prototype.hasOwnProperty.call(tool.function, "description")) return tool;
-            const cf = { ...(tool.function as Record<string, unknown>) };
-            delete cf.description;
-            return { ...tool, function: cf };
-          });
-        }
-      } catch {}
-    }
-
-    return out;
+export class CodeBuddyCnExecutor extends CodeBuddyBaseExecutor {
+  constructor(providerId: string = "codebuddy-cn") {
+    super(providerId);
   }
 }
-
-export default CodeBuddyCnExecutor;

open-sse/executors/codebuddy-intl.ts

@@ -0,0 +1,38 @@
+import { CodeBuddyBaseExecutor, NEUTRAL_PROMPT } from "./codebuddy/shared.ts";
+import type { ProviderCredentials } from "./base.ts";
+
+/**
+ * CodeBuddyIntlExecutor — talks to https://www.codebuddy.ai/v2/chat/completions
+ *
+ * CodeBuddy International gateway strictly requires the first message in the
+ * request to be a system prompt (rejects with 400 "first message is not system
+ * prompt" otherwise). Inherits all shared CodeBuddy gateway behavior and
+ * prepends a neutral system prompt when callers/probes send none.
+ */
+export class CodeBuddyIntlExecutor extends CodeBuddyBaseExecutor {
+  constructor(providerId: string = "codebuddy-intl") {
+    super(providerId);
+  }
+
+  transformRequest(
+    model: string,
+    body: unknown,
+    stream: boolean,
+    credentials: ProviderCredentials
+  ): unknown {
+    const transformed = super.transformRequest(model, body, stream, credentials);
+    if (!transformed || typeof transformed !== "object" || Array.isArray(transformed)) {
+      return transformed;
+    }
+    const out = transformed as Record<string, unknown>;
+
+    if (Array.isArray(out.messages)) {
+      const first = out.messages[0] as Record<string, unknown> | undefined;
+      if (!first || first.role !== "system") {
+        out.messages = [{ role: "system", content: NEUTRAL_PROMPT }, ...out.messages];
+      }
+    }
+
+    return out;
+  }
+}

open-sse/executors/codebuddy/shared.ts

@@ -0,0 +1,199 @@
+import { DefaultExecutor } from "../default.ts";
+import type { ExecuteInput, ExecutorExecuteResult, ProviderCredentials } from "../base.ts";
+
+export const SENSITIVE_CONTENT_REJECTION =
+  "抱歉，系统检测到您当前输入的信息存在敏感内容，我无法响应您的请求，请检查后重新输入";
+export const LARGE_TOOL_METADATA_BYTES = 64 * 1024;
+export const NEUTRAL_PROMPT =
+  "You are a helpful AI assistant that helps with software engineering tasks.";
+export const AGENT_PATTERN =
+  /you are claude code|claude.?code.+official.+cli|anthropic.+official.+cli|anxthxropic.+official.+cli|you are (?:cursor|windsurf|cline|aider|continue|copilot|cody)|you are an? (?:ai )?(?:coding |code )?agent|cc_entrypoint\s*=\s*(?:cli|vscode|jetbrains|gui)|claude.?code.+issues|give feedback.+claude.?code|you are .{0,30}(?:powerful )?ai agent|orchestration capabilities|OhMyOpenCode|<agent-identity>|<Role>|<Behavior_Instructions>/i;
+
+export function responseFromResult(result: ExecutorExecuteResult): Response {
+  return result instanceof Response ? result : result.response;
+}
+
+export function credentialsFromResult(
+  result: ExecutorExecuteResult,
+  fallback: ProviderCredentials
+): ProviderCredentials {
+  if (result instanceof Response || !result.headers) return fallback;
+
+  const authorization = Object.entries(result.headers).find(
+    ([name]) => name.toLowerCase() === "authorization"
+  )?.[1];
+  if (!authorization?.startsWith("Bearer ")) return fallback;
+
+  return {
+    ...fallback,
+    accessToken: authorization.slice("Bearer ".length),
+    expiresAt: undefined,
+  };
+}
+
+export function compactToolDescriptions(body: unknown): unknown | null {
+  if (!body || typeof body !== "object" || Array.isArray(body)) return null;
+
+  const request = body as Record<string, unknown>;
+  if (!Array.isArray(request.tools) || request.tools.length === 0) return null;
+
+  const originalTools = request.tools;
+  try {
+    const serializedTools = JSON.stringify(originalTools);
+    if (new TextEncoder().encode(serializedTools).byteLength < LARGE_TOOL_METADATA_BYTES) {
+      return null;
+    }
+  } catch {
+    return null;
+  }
+
+  let tools: unknown[] | null = null;
+  originalTools.forEach((tool, index) => {
+    if (!tool || typeof tool !== "object" || Array.isArray(tool)) return;
+
+    const declaration = tool as Record<string, unknown>;
+    if (
+      declaration.type !== "function" ||
+      !declaration.function ||
+      typeof declaration.function !== "object" ||
+      Array.isArray(declaration.function)
+    ) {
+      return;
+    }
+
+    const toolFunction = declaration.function as Record<string, unknown>;
+    if (!Object.prototype.hasOwnProperty.call(toolFunction, "description")) return;
+
+    const compactFunction = { ...toolFunction };
+    delete compactFunction.description;
+    tools ??= originalTools.slice();
+    tools[index] = { ...declaration, function: compactFunction };
+  });
+
+  return tools ? { ...request, tools } : null;
+}
+
+export async function isSensitiveContentRejection(response: Response): Promise<boolean> {
+  if (response.status !== 400) return false;
+  const responseText = await response
+    .clone()
+    .text()
+    .catch(() => "");
+  return responseText.includes(SENSITIVE_CONTENT_REJECTION);
+}
+
+export function flattenContent(content: unknown): string {
+  if (typeof content === "string") return content;
+  if (Array.isArray(content)) {
+    return (content as Array<Record<string, unknown>>)
+      .map((b) => (b && typeof b.text === "string" ? b.text : ""))
+      .join("\n");
+  }
+  return "";
+}
+
+/**
+ * Shared base executor for CodeBuddy gateways (Tencent CN and International).
+ *
+ * Both speak OpenAI-compatible SSE over their respective gateways. Shared behavior:
+ *  - forces stream: true (non-stream rejected with code 11101)
+ *  - handles reasoning_effort (strips none/off, adds reasoning_summary:"auto")
+ *  - sanitizes agent system prompts to avoid Tencent's content filter
+ *  - proactively strips oversized tool descriptions (>64KB)
+ *  - retries sensitive-content 400 rejections once with compact tool descriptions
+ */
+export class CodeBuddyBaseExecutor extends DefaultExecutor {
+  constructor(providerId: string) {
+    super(providerId);
+  }
+
+  async execute(input: ExecuteInput): Promise<ExecutorExecuteResult> {
+    const result = await super.execute(input);
+    if (!(await isSensitiveContentRejection(responseFromResult(result)))) {
+      return result;
+    }
+
+    const compactBody = compactToolDescriptions(input.body);
+    if (!compactBody) return result;
+
+    const logTag = (this.provider || "codebuddy").toUpperCase().replace(/-/g, "_");
+    input.log?.debug?.(
+      logTag,
+      "Upstream rejected an oversized tool request as sensitive content; retrying with compact tool descriptions"
+    );
+    return super.execute({
+      ...input,
+      body: compactBody,
+      credentials: credentialsFromResult(result, input.credentials),
+    });
+  }
+
+  transformRequest(
+    model: string,
+    body: unknown,
+    stream: boolean,
+    credentials: ProviderCredentials
+  ): unknown {
+    const transformed = super.transformRequest(model, body, stream, credentials);
+    if (!transformed || typeof transformed !== "object" || Array.isArray(transformed)) {
+      return transformed;
+    }
+    const out = transformed as Record<string, unknown>;
+    out.stream = true;
+
+    const eff = out.reasoning_effort;
+    if (eff === "none" || eff === "off") {
+      delete out.reasoning_effort;
+    } else if (eff) {
+      out.reasoning_summary = "auto";
+    }
+
+    // --- Agent system prompt replacement ---
+    if (out.system) {
+      const text = flattenContent(out.system);
+      if (text && (text.length > 2000 || AGENT_PATTERN.test(text))) {
+        out.system = NEUTRAL_PROMPT;
+      }
+    }
+
+    if (Array.isArray(out.messages)) {
+      out.messages = (out.messages as Array<Record<string, unknown>>).map((message) => {
+        if (!message || message.role !== "system") return message;
+        const text = flattenContent(message.content);
+        if (!text) return message;
+        if (text.length > 2000 || AGENT_PATTERN.test(text)) {
+          return typeof message.content === "string"
+            ? { ...message, content: NEUTRAL_PROMPT }
+            : { ...message, content: [{ type: "text", text: NEUTRAL_PROMPT }] };
+        }
+        return message;
+      });
+    }
+
+    // --- Strip oversized tool descriptions (>64KB) ---
+    if (Array.isArray(out.tools) && out.tools.length > 0) {
+      try {
+        const s = JSON.stringify(out.tools);
+        if (new TextEncoder().encode(s).byteLength >= 65536) {
+          out.tools = (out.tools as Array<Record<string, unknown>>).map((tool) => {
+            if (!tool || typeof tool !== "object" || Array.isArray(tool)) return tool;
+            if (
+              tool.type !== "function" ||
+              !tool.function ||
+              typeof tool.function !== "object" ||
+              Array.isArray(tool.function)
+            ) {
+              return tool;
+            }
+            if (!Object.prototype.hasOwnProperty.call(tool.function, "description")) return tool;
+            const cf = { ...(tool.function as Record<string, unknown>) };
+            delete cf.description;
+            return { ...tool, function: cf };
+          });
+        }
+      } catch {}
+    }
+
+    return out;
+  }
+}

open-sse/executors/index.ts

@@ -168,6 +168,8 @@ const lazyExecutors: Record<string, () => Promise<BaseExecutor>> = {
   gc: () => import("./grok-cli.ts").then((m) => new m.GrokCliExecutor()), // Alias
   "codebuddy-cn": () => import("./codebuddy-cn.ts").then((m) => new m.CodeBuddyCnExecutor()),
   cbcn: () => import("./codebuddy-cn.ts").then((m) => new m.CodeBuddyCnExecutor()), // Alias for codebuddy-cn
+  "codebuddy-intl": () => import("./codebuddy-intl.ts").then((m) => new m.CodeBuddyIntlExecutor()),
+  cbai: () => import("./codebuddy-intl.ts").then((m) => new m.CodeBuddyIntlExecutor()), // Alias for codebuddy-intl
   "zenmux-free": () => import("./zenmux-free.ts").then((m) => new m.ZenmuxFreeExecutor()),
   "cloudflare-playground": () =>
     import("./cloudflare-playground.ts").then((m) => new m.CloudflarePlaygroundExecutor()),

open-sse/services/tokenRefresh.ts

@@ -40,6 +40,7 @@ import {
   refreshWithRetry,
 } from "./tokenRefresh/circuitBreaker.ts";
 import { refreshCodebuddyCnToken } from "./tokenRefresh/providers/codebuddyCn.ts";
+import { refreshCodebuddyIntlToken } from "./tokenRefresh/providers/codebuddyIntl.ts";
 import { refreshWorkbuddyToken } from "./tokenRefresh/providers/workbuddy.ts";
 import { refreshClineToken } from "./tokenRefresh/providers/cline.ts";
 import { refreshKimiCodingToken } from "./tokenRefresh/providers/kimiCoding.ts";
@@ -472,6 +473,9 @@ async function _getAccessTokenInternal(provider, credentials, log, proxyConfig:
     case "codebuddy-cn":
       return await refreshCodebuddyCnToken(credentials.refreshToken, log, proxyConfig);
 
+    case "codebuddy-intl":
+      return await refreshCodebuddyIntlToken(credentials.refreshToken, log, proxyConfig);
+
     case "workbuddy":
       return await refreshWorkbuddyToken(credentials.refreshToken, log, proxyConfig);
 
@@ -506,6 +510,7 @@ export function supportsTokenRefresh(provider) {
     // testStatus="expired" / errorCode="no_refresh_token".
     "gitlab-duo",
     "codebuddy-cn",
+    "codebuddy-intl",
     "workbuddy",
     "cursor",
   ]);

open-sse/services/tokenRefresh/providers/codebuddyCn.ts

@@ -1,71 +1,12 @@
 // @ts-nocheck
-// Extracted from open-sse/services/tokenRefresh.ts — see ../shared.ts for
-// provenance notes (ported idea from KooshaPari's PR #7338, redone on tip).
-import { runWithProxyContext } from "../../../utils/proxyFetch.ts";
 import type { RefreshLogger } from "../shared.ts";
+import { refreshCodebuddyToken } from "./codebuddyShared.ts";
 
-/**
- * CodeBuddy CN (Tencent) token refresh — POST /v2/plugin/auth/token/refresh with
- * the refresh token carried in the X-Refresh-Token header (not a form body),
- * matching the official CodeBuddy CLI. Response: { code: 0, data: <token> }.
- */
 export async function refreshCodebuddyCnToken(
   refreshToken: string,
   log: RefreshLogger,
   proxyConfig: unknown = null
 ) {
-  if (!refreshToken) return null;
   const { CODEBUDDY_CN_CONFIG } = await import("@/lib/oauth/constants/oauth");
-  const oauth = CODEBUDDY_CN_CONFIG;
-  try {
-    const response = await runWithProxyContext(proxyConfig, () =>
-      fetch(oauth.refreshUrl, {
-        method: "POST",
-        headers: {
-          "Content-Type": "application/json",
-          Accept: "application/json",
-          "User-Agent": oauth.userAgent,
-          "X-Requested-With": "XMLHttpRequest",
-          "X-Domain": "copilot.tencent.com",
-          "X-Refresh-Token": refreshToken,
-          "X-Auth-Refresh-Source": "plugin",
-          "X-Product": "SaaS",
-        },
-        body: "{}",
-      })
-    );
-
-    if (!response.ok) {
-      const errorText = await response.text();
-      log?.error?.("TOKEN_REFRESH", "Failed to refresh CodeBuddy CN token", {
-        status: response.status,
-        error: errorText,
-      });
-      return null;
-    }
-
-    const data = await response.json();
-    if (data?.code !== 0 || !data?.data?.accessToken) {
-      log?.error?.("TOKEN_REFRESH", "CodeBuddy CN token refresh returned no token", {
-        code: data?.code,
-        msg: data?.msg,
-      });
-      return null;
-    }
-
-    log?.info?.("TOKEN_REFRESH", "Successfully refreshed CodeBuddy CN token", {
-      hasNewAccessToken: !!data.data.accessToken,
-      hasNewRefreshToken: !!data.data.refreshToken,
-      expiresIn: data.data.expiresIn,
-    });
-
-    return {
-      accessToken: data.data.accessToken,
-      refreshToken: data.data.refreshToken || refreshToken,
-      expiresIn: data.data.expiresIn,
-    };
-  } catch (error) {
-    log?.error?.("TOKEN_REFRESH", `Network error refreshing CodeBuddy CN token: ${error?.message}`);
-    return null;
-  }
+  return refreshCodebuddyToken(CODEBUDDY_CN_CONFIG, refreshToken, log, proxyConfig, "CodeBuddy CN");
 }

open-sse/services/tokenRefresh/providers/codebuddyIntl.ts

@@ -0,0 +1,18 @@
+// @ts-nocheck
+import type { RefreshLogger } from "../shared.ts";
+import { refreshCodebuddyToken } from "./codebuddyShared.ts";
+
+export async function refreshCodebuddyIntlToken(
+  refreshToken: string,
+  log: RefreshLogger,
+  proxyConfig: unknown = null
+) {
+  const { CODEBUDDY_INTL_CONFIG } = await import("@/lib/oauth/constants/oauth");
+  return refreshCodebuddyToken(
+    CODEBUDDY_INTL_CONFIG,
+    refreshToken,
+    log,
+    proxyConfig,
+    "CodeBuddy Intl"
+  );
+}

open-sse/services/tokenRefresh/providers/codebuddyShared.ts

@@ -0,0 +1,75 @@
+// @ts-nocheck
+// Extracted from open-sse/services/tokenRefresh.ts — see ../shared.ts for
+// provenance notes (ported idea from KooshaPari's PR #7338, redone on tip).
+import { runWithProxyContext } from "../../../utils/proxyFetch.ts";
+import type { RefreshLogger } from "../shared.ts";
+
+/**
+ * Shared CodeBuddy token refresh — POST /v2/plugin/auth/token/refresh with
+ * the refresh token carried in the X-Refresh-Token header (not a form body),
+ * matching the official CodeBuddy CLI. Response: { code: 0, data: <token> }.
+ */
+export async function refreshCodebuddyToken(
+  oauthConfig: { refreshUrl: string; userAgent: string; domain?: string },
+  refreshToken: string,
+  log: RefreshLogger,
+  proxyConfig: unknown = null,
+  realmLabel: string = "CodeBuddy"
+) {
+  if (!refreshToken) return null;
+  const domain = oauthConfig.domain || "copilot.tencent.com";
+  try {
+    const response = await runWithProxyContext(proxyConfig, () =>
+      fetch(oauthConfig.refreshUrl, {
+        method: "POST",
+        headers: {
+          "Content-Type": "application/json",
+          Accept: "application/json",
+          "User-Agent": oauthConfig.userAgent,
+          "X-Requested-With": "XMLHttpRequest",
+          "X-Domain": domain,
+          "X-Refresh-Token": refreshToken,
+          "X-Auth-Refresh-Source": "plugin",
+          "X-Product": "SaaS",
+        },
+        body: "{}",
+      })
+    );
+
+    if (!response.ok) {
+      const errorText = await response.text();
+      log?.error?.("TOKEN_REFRESH", `Failed to refresh ${realmLabel} token`, {
+        status: response.status,
+        error: errorText,
+      });
+      return null;
+    }
+
+    const data = await response.json();
+    if (data?.code !== 0 || !data?.data?.accessToken) {
+      log?.error?.("TOKEN_REFRESH", `${realmLabel} token refresh returned no token`, {
+        code: data?.code,
+        msg: data?.msg,
+      });
+      return null;
+    }
+
+    log?.info?.("TOKEN_REFRESH", `Successfully refreshed ${realmLabel} token`, {
+      hasNewAccessToken: !!data.data.accessToken,
+      hasNewRefreshToken: !!data.data.refreshToken,
+      expiresIn: data.data.expiresIn,
+    });
+
+    return {
+      accessToken: data.data.accessToken,
+      refreshToken: data.data.refreshToken || refreshToken,
+      expiresIn: data.data.expiresIn,
+    };
+  } catch (error) {
+    log?.error?.(
+      "TOKEN_REFRESH",
+      `Network error refreshing ${realmLabel} token: ${error?.message}`
+    );
+    return null;
+  }
+}

open-sse/services/usage.ts

@@ -55,6 +55,7 @@ import { getLlmgatewayUsage } from "./usage/llmgateway.ts";
 import { getLyceumUsage } from "./usage/lyceum.ts";
 import { getOllamaCloudUsage } from "./opencodeOllamaUsage.ts";
 import { getCodeBuddyCnUsage } from "./usage/codebuddy-cn.ts";
+import { getCodeBuddyIntlUsage } from "./usage/codebuddy-intl.ts";
 import { getPromptQlUsage } from "./usage/promptql.ts";
 import { getHyperAgentUsage } from "./usage/hyperagent.ts";
 import { getGitHubUsage, formatGitHubQuotaSnapshot, inferGitHubPlanName } from "./usage/github.ts";
@@ -236,6 +237,9 @@ export async function getUsageForProvider(
       return await getGrokCliUsage(accessToken);
     case "codebuddy-cn":
       return await getCodeBuddyCnUsage(accessToken, apiKey, providerSpecificData);
+    case "codebuddy-intl":
+    case "cbai":
+      return await getCodeBuddyIntlUsage(accessToken, apiKey, providerSpecificData);
     case "promptql":
     case "pql":
       // DDN lux JWTs carry projectId only in JWT aud; connection.projectId may be set by sync.

open-sse/services/usage/codebuddy-cn.ts

@@ -1,201 +1,19 @@
-/**
- * CodeBuddy CN usage handler — scoped to the "codebuddy-cn" provider.
- *
- * Quota lives behind a Tencent billing endpoint (POST, payload wrapped twice
- * under data.Response.Data). It mixes two credit types that must NOT be merged:
- *
- *  - Refill / base ("基础体验包"): recurring allowance whose cycle resets long
- *    before the resource itself expires (CycleEndTime << DeductionEndTime).
- *    Live numbers in the *Cycle* fields; resetAt = next refresh.
- *  - Bonus ("活动赠送包"): one-shot credits that run a single cycle and expire
- *    (CycleEndTime ≈ DeductionEndTime). Numbers in the plain Capacity fields.
- *
- * One quota row per package — cadence label (Monthly/Weekly/Daily) for refill
- * packs, "Bonus Pack N" for bonus packs (soonest-expiring first).
- */
-
 import { CODEBUDDY_CN_USER_AGENT } from "../../config/providerHeaderProfiles.ts";
+import { fetchCodeBuddyQuotaFromEndpoint, type CodeBuddyUsageResult } from "./codebuddyShared.ts";
 
-const USAGE_URL = "https://copilot.tencent.com/v2/billing/meter/get-user-resource";
-
-interface TencentAccount {
-  PackageName?: string;
-  SubProductName?: string;
-  CycleStartTime?: string | number;
-  CycleEndTime?: string | number;
-  DeductionEndTime?: string | number;
-  CycleCapacitySize?: number | string;
-  CycleCapacitySizePrecise?: string | number;
-  CycleCapacityUsed?: number | string;
-  CycleCapacityUsedPrecise?: string | number;
-  CapacitySize?: number | string;
-  CapacitySizePrecise?: string | number;
-  CapacityUsed?: number | string;
-  CapacityUsedPrecise?: string | number;
-}
-
-function parseResetTime(value: unknown): string | null {
-  if (!value) return null;
-  try {
-    if (value instanceof Date) return value.toISOString();
-    if (typeof value === "number") {
-      const ts = value < 1e12 ? value * 1000 : value;
-      const d = new Date(ts);
-      return d.getTime() > 0 ? d.toISOString() : null;
-    }
-    if (typeof value === "string") {
-      if (/^\d+$/.test(value)) {
-        const n = Number(value);
-        const d = new Date(n < 1e12 ? n * 1000 : n);
-        return d.getTime() > 0 ? d.toISOString() : null;
-      }
-      const d = new Date(value);
-      return Number.isNaN(d.getTime()) || d.getTime() <= 0 ? null : d.toISOString();
-    }
-    return null;
-  } catch {
-    return null;
-  }
-}
-
-// Prefer the *Precise string fields (exact), fall back to the numeric ones.
-function num(precise: unknown, plain: unknown): number {
-  const n = Number(precise ?? plain);
-  return Number.isFinite(n) ? n : 0;
-}
-
-// Label a refill pack by its cycle length (Monthly is the common CodeBuddy case).
-function refillCadence(acc: TencentAccount): "Monthly" | "Weekly" | "Daily" {
-  const start = parseResetTime(acc.CycleStartTime);
-  const end = parseResetTime(acc.CycleEndTime);
-  if (start && end) {
-    const days = (new Date(end).getTime() - new Date(start).getTime()) / 86400000;
-    if (days <= 1.5) return "Daily";
-    if (days <= 10) return "Weekly";
-  }
-  return "Monthly";
-}
-
-function cycleEndMs(acc: TencentAccount): number {
-  const r = parseResetTime(acc.CycleEndTime);
-  return r ? new Date(r).getTime() : Number.POSITIVE_INFINITY;
-}
-
-function deductionEndMs(acc: TencentAccount): number {
-  const v = acc.DeductionEndTime;
-  if (typeof v === "number") return v < 1e12 ? v * 1000 : v;
-  if (typeof v === "string" && /^\d+$/.test(v)) {
-    const n = Number(v);
-    return n < 1e12 ? n * 1000 : n;
-  }
-  const r = parseResetTime(v);
-  return r ? new Date(r).getTime() : Number.POSITIVE_INFINITY;
-}
-
-// Refill packs roll into a new cycle before the resource expires; bonus packs
-// end at expiry. >2d gap between cycle end and validity end = refill.
-const REFILL_GAP_MS = 2 * 24 * 60 * 60 * 1000;
-function isRefill(acc: TencentAccount): boolean {
-  const ce = cycleEndMs(acc);
-  const de = deductionEndMs(acc);
-  return Number.isFinite(ce) && Number.isFinite(de) && de - ce > REFILL_GAP_MS;
-}
-
-interface CodeBuddyUsageResult {
-  plan?: string;
-  quotas?: Record<
-    string,
-    {
-      used: number;
-      total: number;
-      resetAt: string | null;
-      unlimited: boolean;
-    }
-  >;
-  message?: string;
-}
+export const CN_USAGE_URL = "https://copilot.tencent.com/v2/billing/meter/get-user-resource";
 
 export async function getCodeBuddyCnUsage(
   accessToken?: string,
   apiKey?: string,
   _providerSpecificData?: unknown
 ): Promise<CodeBuddyUsageResult> {
-  const token = accessToken || apiKey;
-  if (!token) {
-    return { message: "CodeBuddy CN credential not available." };
-  }
-
-  try {
-    const response = await fetch(USAGE_URL, {
-      method: "POST",
-      headers: {
-        Authorization: `Bearer ${token}`,
-        "Content-Type": "application/json",
-        Accept: "application/json",
-        "User-Agent": CODEBUDDY_CN_USER_AGENT,
-        "X-Product": "SaaS",
-        "X-IDE-Type": "CLI",
-        "X-IDE-Name": "CLI",
-        "x-requested-with": "XMLHttpRequest",
-        "x-codebuddy-request": "1",
-      },
-      body: "{}",
-    });
-
-    if (response.status === 401 || response.status === 403) {
-      return { message: "CodeBuddy CN credential invalid or expired." };
-    }
-    if (!response.ok) {
-      return { message: `CodeBuddy CN quota API error (${response.status}).` };
-    }
-
-    const json: any = await response.json();
-    if (json?.code !== 0) {
-      return { message: `CodeBuddy CN quota error: ${json?.msg || "unknown"}` };
-    }
-
-    const data = json?.data?.Response?.Data || {};
-    const accountsRaw: TencentAccount[] = Array.isArray(data.Accounts) ? data.Accounts : [];
-    if (accountsRaw.length === 0) {
-      return { message: "CodeBuddy CN connected. No credit package found." };
-    }
-
-    const byExpiry = (a: TencentAccount, b: TencentAccount) => cycleEndMs(a) - cycleEndMs(b);
-    const refills = accountsRaw.filter(isRefill).sort(byExpiry);
-    const bonuses = accountsRaw.filter((a) => !isRefill(a)).sort(byExpiry);
-
-    const quotas: NonNullable<CodeBuddyUsageResult["quotas"]> = {};
-    const seenRefill: Record<string, number> = {};
-    refills.forEach((acc) => {
-      const base = refillCadence(acc);
-      seenRefill[base] = (seenRefill[base] || 0) + 1;
-      const name = seenRefill[base] > 1 ? `${base} ${seenRefill[base]}` : base;
-      quotas[name] = {
-        used: num(acc.CycleCapacityUsedPrecise, acc.CycleCapacityUsed),
-        total: num(acc.CycleCapacitySizePrecise, acc.CycleCapacitySize),
-        resetAt: parseResetTime(acc.CycleEndTime),
-        unlimited: false,
-      };
-    });
-    bonuses.forEach((acc, i) => {
-      quotas[`Bonus Pack ${i + 1}`] = {
-        used: num(acc.CapacityUsedPrecise, acc.CapacityUsed),
-        total: num(acc.CapacitySizePrecise, acc.CapacitySize),
-        resetAt: parseResetTime(acc.CycleEndTime),
-        unlimited: false,
-      };
-    });
-
-    const basePkg = refills[0] || accountsRaw[0] || {};
-    const plan = basePkg.PackageName || basePkg.SubProductName || "CodeBuddy CN";
-
-    return { plan, quotas };
-  } catch (error: any) {
-    // Hard Rule #12: no raw err.message in any HTTP/SSE/executor response. Usage
-    // handler returns a controlled string for the dashboard; do not include the
-    // raw exception text in case it carries a path/stack snippet.
-    return { message: "CodeBuddy CN error: failed to fetch quota." };
-  }
+  return fetchCodeBuddyQuotaFromEndpoint(accessToken, apiKey, {
+    url: CN_USAGE_URL,
+    userAgent: CODEBUDDY_CN_USER_AGENT,
+    ideType: "CLI",
+    label: "CodeBuddy CN",
+  });
 }
 
 export default getCodeBuddyCnUsage;

open-sse/services/usage/codebuddy-intl.ts

@@ -0,0 +1,19 @@
+import { CODEBUDDY_INTL_USER_AGENT } from "../../config/providerHeaderProfiles.ts";
+import { fetchCodeBuddyQuotaFromEndpoint, type CodeBuddyUsageResult } from "./codebuddyShared.ts";
+
+export const INTL_USAGE_URL = "https://www.codebuddy.ai/v2/billing/meter/get-user-resource";
+
+export async function getCodeBuddyIntlUsage(
+  accessToken?: string,
+  apiKey?: string,
+  _providerSpecificData?: unknown
+): Promise<CodeBuddyUsageResult> {
+  return fetchCodeBuddyQuotaFromEndpoint(accessToken, apiKey, {
+    url: INTL_USAGE_URL,
+    userAgent: CODEBUDDY_INTL_USER_AGENT,
+    ideType: "IDE",
+    label: "CodeBuddy Intl",
+  });
+}
+
+export default getCodeBuddyIntlUsage;

open-sse/services/usage/codebuddyShared.ts

@@ -0,0 +1,190 @@
+export interface TencentAccount {
+  PackageName?: string;
+  SubProductName?: string;
+  CycleStartTime?: string | number;
+  CycleEndTime?: string | number;
+  DeductionEndTime?: string | number;
+  CycleCapacitySize?: number | string;
+  CycleCapacitySizePrecise?: string | number;
+  CycleCapacityUsed?: number | string;
+  CycleCapacityUsedPrecise?: string | number;
+  CapacitySize?: number | string;
+  CapacitySizePrecise?: string | number;
+  CapacityUsed?: number | string;
+  CapacityUsedPrecise?: string | number;
+}
+
+export function parseResetTime(value: unknown): string | null {
+  if (!value) return null;
+  try {
+    if (value instanceof Date) return value.toISOString();
+    if (typeof value === "number") {
+      const ts = value < 1e12 ? value * 1000 : value;
+      const d = new Date(ts);
+      return d.getTime() > 0 ? d.toISOString() : null;
+    }
+    if (typeof value === "string") {
+      if (/^\d+$/.test(value)) {
+        const n = Number(value);
+        const d = new Date(n < 1e12 ? n * 1000 : n);
+        return d.getTime() > 0 ? d.toISOString() : null;
+      }
+      const d = new Date(value);
+      return Number.isNaN(d.getTime()) || d.getTime() <= 0 ? null : d.toISOString();
+    }
+    return null;
+  } catch {
+    return null;
+  }
+}
+
+export function num(precise: unknown, plain: unknown): number {
+  const n = Number(precise ?? plain);
+  return Number.isFinite(n) ? n : 0;
+}
+
+export function refillCadence(acc: TencentAccount): "Monthly" | "Weekly" | "Daily" {
+  const start = parseResetTime(acc.CycleStartTime);
+  const end = parseResetTime(acc.CycleEndTime);
+  if (start && end) {
+    const days = (new Date(end).getTime() - new Date(start).getTime()) / 86400000;
+    if (days <= 1.5) return "Daily";
+    if (days <= 10) return "Weekly";
+  }
+  return "Monthly";
+}
+
+export function cycleEndMs(acc: TencentAccount): number {
+  const r = parseResetTime(acc.CycleEndTime);
+  return r ? new Date(r).getTime() : Number.POSITIVE_INFINITY;
+}
+
+export function deductionEndMs(acc: TencentAccount): number {
+  const v = acc.DeductionEndTime;
+  if (typeof v === "number") return v < 1e12 ? v * 1000 : v;
+  if (typeof v === "string" && /^\d+$/.test(v)) {
+    const n = Number(v);
+    return n < 1e12 ? n * 1000 : n;
+  }
+  const r = parseResetTime(v);
+  return r ? new Date(r).getTime() : Number.POSITIVE_INFINITY;
+}
+
+export const REFILL_GAP_MS = 2 * 24 * 60 * 60 * 1000;
+export function isRefill(acc: TencentAccount): boolean {
+  const ce = cycleEndMs(acc);
+  const de = deductionEndMs(acc);
+  return Number.isFinite(ce) && Number.isFinite(de) && de - ce > REFILL_GAP_MS;
+}
+
+export interface CodeBuddyUsageResult {
+  plan?: string;
+  quotas?: Record<
+    string,
+    {
+      used: number;
+      total: number;
+      resetAt: string | null;
+      unlimited: boolean;
+    }
+  >;
+  message?: string;
+}
+
+export interface CodeBuddyQuotaOptions {
+  url: string;
+  userAgent: string;
+  ideType: string;
+  label: string;
+}
+
+export async function fetchCodeBuddyQuotaFromEndpoint(
+  accessToken: string | undefined,
+  apiKey: string | undefined,
+  options: CodeBuddyQuotaOptions
+): Promise<CodeBuddyUsageResult> {
+  const token = accessToken || apiKey;
+  const { url, userAgent, ideType, label } = options;
+  if (!token) {
+    return { message: `${label} credential not available.` };
+  }
+
+  try {
+    const response = await fetch(url, {
+      method: "POST",
+      headers: {
+        Authorization: `Bearer ${token}`,
+        "Content-Type": "application/json",
+        Accept: "application/json",
+        "User-Agent": userAgent,
+        "X-Product": "SaaS",
+        "X-IDE-Type": ideType,
+        "X-IDE-Name": ideType,
+        "x-requested-with": "XMLHttpRequest",
+        "x-codebuddy-request": "1",
+      },
+      body: "{}",
+    });
+
+    if (response.status === 401 || response.status === 403) {
+      return { message: `${label} credential invalid or expired.` };
+    }
+    if (!response.ok) {
+      return { message: `${label} quota API error (${response.status}).` };
+    }
+
+    const json = (await response.json()) as {
+      code?: number;
+      msg?: string;
+      data?: {
+        Response?: {
+          Data?: {
+            Accounts?: TencentAccount[];
+          };
+        };
+      };
+    };
+    if (json?.code !== 0) {
+      return { message: `${label} quota error: ${json?.msg || "unknown"}` };
+    }
+
+    const data = json?.data?.Response?.Data || {};
+    const accountsRaw: TencentAccount[] = Array.isArray(data.Accounts) ? data.Accounts : [];
+    if (accountsRaw.length === 0) {
+      return { message: `${label} connected. No credit package found.` };
+    }
+
+    const byExpiry = (a: TencentAccount, b: TencentAccount) => cycleEndMs(a) - cycleEndMs(b);
+    const refills = accountsRaw.filter(isRefill).sort(byExpiry);
+    const bonuses = accountsRaw.filter((a) => !isRefill(a)).sort(byExpiry);
+
+    const quotas: NonNullable<CodeBuddyUsageResult["quotas"]> = {};
+    const seenRefill: Record<string, number> = {};
+    refills.forEach((acc) => {
+      const base = refillCadence(acc);
+      seenRefill[base] = (seenRefill[base] || 0) + 1;
+      const name = seenRefill[base] > 1 ? `${base} ${seenRefill[base]}` : base;
+      quotas[name] = {
+        used: num(acc.CycleCapacityUsedPrecise, acc.CycleCapacityUsed),
+        total: num(acc.CycleCapacitySizePrecise, acc.CycleCapacitySize),
+        resetAt: parseResetTime(acc.CycleEndTime),
+        unlimited: false,
+      };
+    });
+    bonuses.forEach((acc, i) => {
+      quotas[`Bonus Pack ${i + 1}`] = {
+        used: num(acc.CapacityUsedPrecise, acc.CapacityUsed),
+        total: num(acc.CapacitySizePrecise, acc.CapacitySize),
+        resetAt: parseResetTime(acc.CycleEndTime),
+        unlimited: false,
+      };
+    });
+
+    const basePkg = refills[0] || accountsRaw[0] || {};
+    const plan = basePkg.PackageName || basePkg.SubProductName || label;
+
+    return { plan, quotas };
+  } catch (_error: unknown) {
+    return { message: `${label} error: failed to fetch quota.` };
+  }
+}

open-sse/services/usage/fetcherProviders.ts

@@ -61,6 +61,8 @@ export const USAGE_FETCHER_PROVIDERS = [
   "vertex",
   "vertex-partner",
   "codebuddy-cn",
+  "codebuddy-intl",
+  "cbai",
   "openrouter",
   // LLM Gateway DevPass allowance (GET /v1/key → monthly + weekly premium)
   "llmgateway",

open-sse/services/usage/supportedProviders.ts

@@ -52,6 +52,8 @@ export const USAGE_SUPPORTED_PROVIDERS: readonly string[] = [
   "vertex",
   "vertex-partner",
   "codebuddy-cn",
+  "codebuddy-intl",
+  "cbai",
   // PromptQL playground credits (getCreditSummary → USD micros)
   "promptql",
   "pql",

package.json

@@ -1,7 +1,7 @@
 {
   "name": "omniroute",
   "version": "3.8.52",
-  "description": "Unified AI router with 370 providers, RTK+Caveman compression, auto fallback, MCP/A2A, desktop, PWA, and OpenAI-compatible APIs.",
+  "description": "Unified AI router with 372 providers, RTK+Caveman compression, auto fallback, MCP/A2A, desktop, PWA, and OpenAI-compatible APIs.",
   "type": "module",
   "bin": {
     "omniroute": "bin/omniroute.mjs",

public/images/tier-flow-dark.svg

@@ -1,6 +1,6 @@
-<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 800 420" font-family="system-ui, -apple-system, Segoe UI, Arial, Helvetica, sans-serif" role="img" aria-label="OmniRoute 4-tier fallback: your IDE or CLI calls one local endpoint and the OmniRoute Smart Router fails over across 370 providers in 4 tiers — Tier 1 Subscription, Tier 2 API, Tier 3 Cheap, Tier 4 Free.">
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 800 420" font-family="system-ui, -apple-system, Segoe UI, Arial, Helvetica, sans-serif" role="img" aria-label="OmniRoute 4-tier fallback: your IDE or CLI calls one local endpoint and the OmniRoute Smart Router fails over across 372 providers in 4 tiers — Tier 1 Subscription, Tier 2 API, Tier 3 Cheap, Tier 4 Free.">
   <title>OmniRoute 4-tier fallback</title>
-  <desc>OmniRoute 4-tier fallback: your IDE or CLI calls one local endpoint and the OmniRoute Smart Router fails over across 370 providers in 4 tiers — Tier 1 Subscription, Tier 2 API, Tier 3 Cheap, Tier 4 Free.</desc>
+  <desc>OmniRoute 4-tier fallback: your IDE or CLI calls one local endpoint and the OmniRoute Smart Router fails over across 372 providers in 4 tiers — Tier 1 Subscription, Tier 2 API, Tier 3 Cheap, Tier 4 Free.</desc>
   <defs>
     <marker id="arrow-dark" markerWidth="10" markerHeight="10" refX="9" refY="3" orient="auto">
       <path d="M0,0 L0,6 L9,3 z" fill="#9ca3af"/>
@@ -15,7 +15,7 @@
 
   <!-- Title -->
   <text x="400" y="32" text-anchor="middle" font-size="18" font-weight="700" fill="#f9fafb">OmniRoute 4-tier fallback</text>
-  <text x="400" y="52" text-anchor="middle" font-size="12" fill="#6b7280">Never stop building — automatic zero-config failover across 370 providers</text>
+  <text x="400" y="52" text-anchor="middle" font-size="12" fill="#6b7280">Never stop building — automatic zero-config failover across 372 providers</text>
 
   <!-- Client box -->
   <rect x="275" y="70" width="250" height="52" rx="8" fill="#1f2937" stroke="#374151" stroke-width="1.5"/>

public/images/tier-flow-light.svg

@@ -1,6 +1,6 @@
-<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 800 420" font-family="system-ui, -apple-system, Segoe UI, Arial, Helvetica, sans-serif" role="img" aria-label="OmniRoute 4-tier fallback: your IDE or CLI calls one local endpoint and the OmniRoute Smart Router fails over across 370 providers in 4 tiers — Tier 1 Subscription, Tier 2 API, Tier 3 Cheap, Tier 4 Free.">
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 800 420" font-family="system-ui, -apple-system, Segoe UI, Arial, Helvetica, sans-serif" role="img" aria-label="OmniRoute 4-tier fallback: your IDE or CLI calls one local endpoint and the OmniRoute Smart Router fails over across 372 providers in 4 tiers — Tier 1 Subscription, Tier 2 API, Tier 3 Cheap, Tier 4 Free.">
   <title>OmniRoute 4-tier fallback</title>
-  <desc>OmniRoute 4-tier fallback: your IDE or CLI calls one local endpoint and the OmniRoute Smart Router fails over across 370 providers in 4 tiers — Tier 1 Subscription, Tier 2 API, Tier 3 Cheap, Tier 4 Free.</desc>
+  <desc>OmniRoute 4-tier fallback: your IDE or CLI calls one local endpoint and the OmniRoute Smart Router fails over across 372 providers in 4 tiers — Tier 1 Subscription, Tier 2 API, Tier 3 Cheap, Tier 4 Free.</desc>
   <defs>
     <marker id="arrow-light" markerWidth="10" markerHeight="10" refX="9" refY="3" orient="auto">
       <path d="M0,0 L0,6 L9,3 z" fill="#6b7280"/>
@@ -15,7 +15,7 @@
 
   <!-- Title -->
   <text x="400" y="32" text-anchor="middle" font-size="18" font-weight="700" fill="#111827">OmniRoute 4-tier fallback</text>
-  <text x="400" y="52" text-anchor="middle" font-size="12" fill="#6b7280">Never stop building — automatic zero-config failover across 370 providers</text>
+  <text x="400" y="52" text-anchor="middle" font-size="12" fill="#6b7280">Never stop building — automatic zero-config failover across 372 providers</text>
 
   <!-- Client box -->
   <rect x="275" y="70" width="250" height="52" rx="8" fill="#ffffff" stroke="#d1d5db" stroke-width="1.5"/>

src/app/api/oauth/[provider]/[action]/route.ts

@@ -68,6 +68,7 @@ const NO_PKCE_DEVICE_CODE_PROVIDERS = new Set([
   "kimi-coding",
   "kilocode",
   "codebuddy-cn",
+  "codebuddy-intl",
   "workbuddy",
   "grok-cli",
   "ghe-copilot",