# v0.4.30 (2026-05-11)

## Features
- MCP stdio→SSE bridge: expose local stdio MCP plugins over SSE (api/mcp/[plugin]/sse, /message)
- Dynamic Linux cert resolution + NSS DB injection (Debian/Arch/Fedora/openSUSE, Chrome/Chromium/Firefox incl. snap) (#1010)
- Cowork tool: expanded settings UI & API
- GitBook docs (DocsContent, DocsLayout)
## Fixes
- OAuth callback postMessage scoped to expected origins (CWE-1385) (#998)
- Re-enable TLS verification on DNS-bypass fetch (CWE-295) (#998)
- Normalize `developer` role → `system` for OpenAI-format providers (Deepseek, Groq, …) (#1011, closes #773)
- Respect `PORT` env in internal model-test fetch (#1014)
- Dropdown text readability in dark theme on usage page (#997)
## Improvements
- Refactor Claude CLI spoof headers into shared constant
- Tool deduper utility in open-sse handlers

open-sse/services/model.js

@@ -86,6 +86,50 @@ const ALIAS_TO_PROVIDER_ID = {
   // TTS
   polly: "aws-polly",
   "aws-polly": "aws-polly",
+  // Free-tier providers (synced from OmniRoute)
+  agentrouter: "agentrouter",
+  aimlapi: "aimlapi",
+  aiml: "aimlapi",
+  novita: "novita",
+  modal: "modal",
+  mdl: "modal",
+  reka: "reka",
+  nlpcloud: "nlpcloud",
+  nlpc: "nlpcloud",
+  bazaarlink: "bazaarlink",
+  bzl: "bazaarlink",
+  completions: "completions",
+  cpl: "completions",
+  enally: "enally",
+  enly: "enally",
+  freetheai: "freetheai",
+  fta: "freetheai",
+  llm7: "llm7",
+  lepton: "lepton",
+  kluster: "kluster",
+  ai21: "ai21",
+  "inference-net": "inference-net",
+  inet: "inference-net",
+  predibase: "predibase",
+  bytez: "bytez",
+  morph: "morph",
+  longcat: "longcat",
+  lc: "longcat",
+  puter: "puter",
+  pu: "puter",
+  uncloseai: "uncloseai",
+  unc: "uncloseai",
+  scaleway: "scaleway",
+  scw: "scaleway",
+  deepinfra: "deepinfra",
+  sambanova: "sambanova",
+  samba: "sambanova",
+  nscale: "nscale",
+  baseten: "baseten",
+  publicai: "publicai",
+  "nous-research": "nous-research",
+  nous: "nous-research",
+  glhf: "glhf",
 };
 
 /**