fix(vertex): discover and route partner models correctly

README.md

@@ -17,9 +17,9 @@
 
 </div>
 
-> Stacking free tiers by hand is painful — dozens of SDKs, dozens of rate limits, and no idea how much you actually have. OmniRoute catalogs **444 free-tier entries across 34 recurring pool keys** and computes the token headline from the **16 pools with a published positive monthly budget plus five per-model Groq caps**, deduplicated by shared pool. Quotas that only open after a regional identity check (today: ModelScope) are shown apart, +~6M behind regional identity verification, and never summed into the headline. The result stays visible on the dashboard (`/dashboard/free-tiers`).
+> Stacking free tiers by hand is painful — dozens of SDKs, dozens of rate limits, and no idea how much you actually have. OmniRoute catalogs **450 free-tier entries across 34 recurring pool keys** and computes the token headline from the **16 pools with a published positive monthly budget plus five per-model Groq caps**, deduplicated by shared pool. Quotas that only open after a regional identity check (today: ModelScope) are shown apart, +~6M behind regional identity verification, and never summed into the headline. The result stays visible on the dashboard (`/dashboard/free-tiers`).
 
-<img src="./docs/diagrams/free-tier-budget.svg" width="100%" alt="OmniRoute free-tier budget card: ~1.47B free tokens per month steady, up to ~2.10B in the first month with signup credits, from 34 documented recurring pool keys covering 444 cataloged free-tier entries behind one endpoint. Honest pool-deduped math — each shared pool counted once, including 16 recurring pools with a published positive monthly token budget plus five per-model Groq caps; 13 providers are marked avoid in the terms-risk catalog so you decide. Budget bar includes Mistral 1B, Nara 210M, LLM7 150M, Groq 30M (five per-model caps) and smaller pools, plus first-month signup credits and permanently-free no-token-cap providers surfaced separately so they never inflate the headline. Live used/remaining on /dashboard/free-tiers."/>
+<img src="./docs/diagrams/free-tier-budget.svg" width="100%" alt="OmniRoute free-tier budget card: ~1.47B free tokens per month steady, up to ~2.10B in the first month with signup credits, from 34 documented recurring pool keys covering 450 cataloged free-tier entries behind one endpoint. Honest pool-deduped math — each shared pool counted once, including 16 recurring pools with a published positive monthly token budget plus five per-model Groq caps; 13 providers are marked avoid in the terms-risk catalog so you decide. Budget bar includes Mistral 1B, Nara 210M, LLM7 150M, Groq 30M (five per-model caps) and smaller pools, plus first-month signup credits and permanently-free no-token-cap providers surfaced separately so they never inflate the headline. Live used/remaining on /dashboard/free-tiers."/>
 
 > Animated summary of the live `/dashboard/free-tiers` page. Full methodology (pool dedupe, credit tiers, provider terms): **[docs/reference/FREE_TIERS.md](docs/reference/FREE_TIERS.md)**.
 >
@@ -648,7 +648,7 @@ of your shell history. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
 
 </div>
 
-> **352 registered providers** across the canonical chat, media, search, local, cloud-agent and system collections, including **152 carrying `hasFree: true` discovery metadata**. The chat model registry covers **229 providers / 2,554 distinct provider-model pairs / 1,283 raw model IDs**; the separate free-budget catalog has **444 per-model rows**, **34 recurring pools** and **52 recurring/keyless free-forever providers**. These are different denominators by design; definitions and pool-deduped calculations live in the [Provider Reference](docs/reference/PROVIDER_REFERENCE.md) and [Free Tiers](docs/reference/FREE_TIERS.md).
+> **352 registered providers** across the canonical chat, media, search, local, cloud-agent and system collections, including **152 carrying `hasFree: true` discovery metadata**. The chat model registry covers **229 providers / 2,554 distinct provider-model pairs / 1,283 raw model IDs**; the separate free-budget catalog has **450 per-model rows**, **34 recurring pools** and **52 recurring/keyless free-forever providers**. These are different denominators by design; definitions and pool-deduped calculations live in the [Provider Reference](docs/reference/PROVIDER_REFERENCE.md) and [Free Tiers](docs/reference/FREE_TIERS.md).
 
 <div align="center">
 
@@ -1307,7 +1307,7 @@ Métricas canônicas em 2026-08-24: **1.029 vídeos únicos** · **11.132.922 vi
   <tr><td nowrap><b><a href="docs/architecture/RESILIENCE_GUIDE.md">Resilience Guide</a></b></td><td>Circuit breakers, cooldowns, queue, anti-thundering herd, TLS spoofing</td></tr>
   <tr><td nowrap><b><a href="docs/routing/AUTO-COMBO.md">Auto-Combo Engine</a></b></td><td>16-factor scoring, mode packs, self-healing</td></tr>
   <tr><td nowrap><b><a href="docs/ops/PROXY_GUIDE.md">Proxy Guide</a></b></td><td>3-level proxy system, 1proxy marketplace, registry CRUD</td></tr>
-  <tr><td nowrap><b><a href="docs/reference/FREE_TIERS.md">Free Tiers</a></b></td><td>Consolidated directory: 34 documented recurring pools / 444 cataloged free-tier entries</td></tr>
+  <tr><td nowrap><b><a href="docs/reference/FREE_TIERS.md">Free Tiers</a></b></td><td>Consolidated directory: 34 documented recurring pools / 450 cataloged free-tier entries</td></tr>
   <tr><td nowrap><b><a href="docs/guides/FEATURES.md">Features Gallery</a></b></td><td>Visual dashboard tour with screenshots</td></tr>
   <tr><td nowrap><b><a href="docs/architecture/CODEBASE_DOCUMENTATION.md">Codebase Documentation</a></b></td><td>Beginner-friendly codebase walkthrough</td></tr>
 </table>

changelog.d/fixes/vertex-express-xai-models.md

@@ -0,0 +1 @@
+- **fix(vertex):** prefer live model discovery for OAuth, Service Account, and service-account-bound authorization-key credentials while falling back cleanly to the Gemini-only Express catalog for standard API keys. Model Garden resources now route by publisher protocol: Claude and Mistral use their native `rawPredict` APIs, and Grok plus current or future open MaaS publishers use Vertex's OpenAI-compatible endpoint with normalized request IDs such as `xai/grok-4.6`.

docs/getting-started/FREE-TIERS-GUIDE.md

@@ -1,6 +1,6 @@
 # Free Tiers Guide: Understand and Combine Free AI Access
 
-> **TL;DR**: OmniRoute registers 352 provider IDs, with **152 provider-catalog entries marked `hasFree`**. The stricter audited free-model catalog covers **34 recurring pool keys / 444 entries** (437 active + 7 discontinued). Connect several suitable providers for broader fallback capacity; every quota, approval rule, privacy policy, and paid-overage condition still applies.
+> **TL;DR**: OmniRoute registers 352 provider IDs, with **152 provider-catalog entries marked `hasFree`**. The stricter audited free-model catalog covers **34 recurring pool keys / 450 entries** (443 active + 7 discontinued). Connect several suitable providers for broader fallback capacity; every quota, approval rule, privacy policy, and paid-overage condition still applies.
 
 ---
 
@@ -163,7 +163,7 @@ The live, pool-deduplicated catalog currently reports:
 | ---------------------------------------------------- | -----------------------------------------------: | -------------------------------------------------------------------------------------------------------------------------- |
 | Recurring quantified grant                           |                          **~1.47B tokens/month** | Shared pools counted once; excludes uncapped providers from the sum                                                        |
 | First month with signup grants                       |                                **~2.10B tokens** | Recurring total plus one-time and recurring credits                                                                        |
-| Audited free-model inventory                         | **34 recurring pool keys / 444 catalog entries** | 437 active + 7 discontinued; distinct from the 352-provider catalog                                                        |
+| Audited free-model inventory                         | **34 recurring pool keys / 450 catalog entries** | 443 active + 7 discontinued; distinct from the 352-provider catalog                                                        |
 | Recurring/keyless free-forever providers represented |                                           **52** | Unique providers across recurring daily/monthly/credit/uncapped and keyless catalog types, eligibility-gated rows excluded |
 | Provider catalog entries marked `hasFree`            |                                    **152 / 352** | Broader provider metadata; not all have a quantifiable recurring quota                                                     |
 

next.config.mjs

@@ -349,6 +349,10 @@ const nextConfig = {
     "keytar",
     "wreq-js",
     "zod",
+    // jsdom relies on Node class relationships that Turbopack's server-chunk transform can break
+    // (observed as "Class extends value undefined" during Vertex metadata sync). Keep the native
+    // package boundary; standalone file tracing still copies the runtime dependency.
+    "jsdom",
     "@ngrok/ngrok",
     "@huggingface/transformers",
     // The ESM entry imports tiktoken_bg.wasm as a module. Turbopack can compile

open-sse/config/freeModelCatalog.data.ts

@@ -443,11 +443,17 @@ export const FREE_MODEL_BUDGETS: FreeModelBudget[] = [
   { provider: "vertex", modelId: "gemini-3.1-pro-preview", displayName: "Gemini 3.1 Pro Preview (Vertex)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
   { provider: "vertex", modelId: "gemini-3.1-flash-lite", displayName: "Gemini 3.1 Flash Lite (Vertex)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
   { provider: "vertex", modelId: "gemini-3-flash-preview", displayName: "Gemini 3 Flash Preview (Vertex)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
-  { provider: "vertex", modelId: "gemma-4-31b-it", displayName: "Gemma 4 31B (Vertex)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
-  { provider: "vertex", modelId: "DeepSeek-V4-Flash", displayName: "DeepSeek V4 Flash (Vertex Partner)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
-  { provider: "vertex", modelId: "DeepSeek-V4-Pro", displayName: "DeepSeek V4 Pro (Vertex Partner)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
-  { provider: "vertex", modelId: "Qwen3.6-35B-A3B", displayName: "Qwen3.6 35B A3B (Vertex Partner)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
-  { provider: "vertex", modelId: "GLM-5.1-FP8", displayName: "GLM-5.1 (Vertex Partner)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
+  { provider: "vertex", modelId: "gemini-3.7-flash", displayName: "Gemini 3.7 Flash (Vertex)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
+  { provider: "vertex", modelId: "gemini-3.6-flash", displayName: "Gemini 3.6 Flash (Vertex)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
+  { provider: "vertex", modelId: "gemini-3.5-flash", displayName: "Gemini 3.5 Flash (Vertex)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
+  { provider: "vertex", modelId: "gemini-3.5-flash-lite", displayName: "Gemini 3.5 Flash-Lite (Vertex)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
+  { provider: "vertex", modelId: "gemini-2.5-pro", displayName: "Gemini 2.5 Pro (Vertex)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
+  { provider: "vertex", modelId: "gemini-2.5-flash", displayName: "Gemini 2.5 Flash (Vertex)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
+  { provider: "vertex", modelId: "gemini-2.5-flash-lite", displayName: "Gemini 2.5 Flash-Lite (Vertex)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
+  { provider: "vertex", modelId: "deepseek-ai/deepseek-v3.2-maas", displayName: "DeepSeek V3.2 (Vertex MaaS)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
+  { provider: "vertex", modelId: "deepseek-ai/deepseek-v3.1-maas", displayName: "DeepSeek V3.1 (Vertex MaaS)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
+  { provider: "vertex", modelId: "qwen/qwen3-next-80b-a3b-instruct-maas", displayName: "Qwen3 Next 80B Instruct (Vertex MaaS)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
+  { provider: "vertex", modelId: "zai-org/glm-5-maas", displayName: "GLM 5 (Vertex MaaS)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
   { provider: "vertex", modelId: "claude-opus-4-7", displayName: "Claude Opus 4.7 (Vertex)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
   { provider: "vertex", modelId: "claude-sonnet-4-6", displayName: "Claude Sonnet 4.6 (Vertex)", monthlyTokens: 0, creditTokens: 300000000, freeType: "one-time-initial", poolKey: "vertex", tos: "caution" },
   { provider: "requesty", modelId: "openai/gpt-oss-120b", displayName: "GPT-OSS 120B (Requesty free)", monthlyTokens: 0, creditTokens: 0, freeType: "recurring-uncapped", poolKey: "requesty-free", tos: "ok" },