zuplo 7.9.13 → 7.9.15

package/docs/ai-gateway/bedrock-runtime.mdx

@@ -234,7 +234,7 @@ model ID, the same as every other provider. Cross-region inference profiles are
 priced too: the `us.`, `eu.`, `apac.`, `au.`, `jp.`, `us-gov.`, and `global.`
 IDs are catalog rows in their own right, each at its own rate. A
 foundation-model or inference-profile ARN, such as
-`arn:aws:bedrock:eu-central-1:123456789012:inference-profile/eu.anthropic.claude-opus-4-8`,
+`arn:aws:bedrock:eu-central-1:123456789012:inference-profile/eu.anthropic.claude-opus-5-5`,
 is priced as the ID it contains. Every model you can call has a catalog price,
 so each request counts toward token, request, and spending
 [budgets](./usage-limits.mdx).

package/docs/ai-gateway/custom-policies.mdx

@@ -144,7 +144,7 @@ terms. By the end, one app on your gateway rejects a prompt containing
      -H "Authorization: Bearer YOUR_APP_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
-       "model": "openai/gpt-5-mini",
+       "model": "openai/gpt-6-luna",
        "messages": [{"role": "user", "content": "Tell me about acme-secret-project"}]
      }'
    ```

package/docs/ai-gateway/fallback.mdx

@@ -38,7 +38,7 @@ models are referenced like any model, as `providerName/model`.
    - **Fallback**: the model attempted after a retryable error or timeout, for
      example `anthropic/claude-haiku-4-5`.
    - **Quota fallback**: the model used once a usage limit is exceeded, for
-     example `openai/gpt-4o-mini`.
+     example `openai/gpt-6-luna`.
    - **Fallback timeout (seconds)**: how long the primary call can run before
      the gateway fails over. The default is `60`; values from `1` to `300` are
      accepted.

package/docs/ai-gateway/integrations/ai-sdk.mdx

@@ -71,7 +71,7 @@ const openai = createOpenAI({
 });
 
 const { text } = await generateText({
-  model: openai.chat("openai/gpt-5-mini"),
+  model: openai.chat("openai/gpt-6-luna"),
   prompt: "Write a one-sentence bedtime story about a unicorn.",
 });
 ```
@@ -93,7 +93,7 @@ const anthropic = createAnthropic({
 });
 
 const { text } = await generateText({
-  model: anthropic("anthropic/claude-sonnet-4-5-20250929"),
+  model: anthropic("anthropic/claude-sonnet-5"),
   prompt: "Write a one-sentence bedtime story about a unicorn.",
 });
 ```
@@ -118,7 +118,7 @@ const gateway = createOpenAICompatible({
 });
 
 const { text } = await generateText({
-  model: gateway("google/gemini-2.5-flash"),
+  model: gateway("google/gemini-3.5-flash"),
   prompt: "Write a one-sentence bedtime story about a unicorn.",
 });
 ```
@@ -160,7 +160,7 @@ const xai = createXai({
 });
 
 const { text } = await generateText({
-  model: xai.chat("xai/grok-4"),
+  model: xai.chat("xai/grok-4.3"),
   prompt: "Write a one-sentence bedtime story about a unicorn.",
 });
 ```
@@ -314,7 +314,7 @@ const openai = createOpenAI({
 });
 
 const { text } = await generateText({
-  model: openai.chat("openrouter/anthropic/claude-sonnet-4.5"),
+  model: openai.chat("openrouter/anthropic/claude-sonnet-5"),
   prompt: "Write a one-sentence bedtime story about a unicorn.",
 });
 ```

package/docs/ai-gateway/integrations/claude-code.mdx

@@ -76,10 +76,9 @@ use the app's API key and API URL instead.
   "env": {
     "ANTHROPIC_AUTH_TOKEN": "<your-personal-api-key>",
     "ANTHROPIC_BASE_URL": "https://my-gateway-main-2e18f50.zuplo.app/u/741d375d631b429293481d6d0458bb64",
-    "ANTHROPIC_MODEL": "anthropic/claude-sonnet-5",
-    "ANTHROPIC_SMALL_FAST_MODEL": "anthropic/claude-haiku-4-5",
-    "ANTHROPIC_DEFAULT_OPUS_MODEL": "anthropic/claude-opus-5",
-    "ANTHROPIC_DEFAULT_SONNET_MODEL": "anthropic/claude-sonnet-5",
+    "ANTHROPIC_MODEL": "anthropic/claude-sonnet-5-5",
+    "ANTHROPIC_DEFAULT_OPUS_MODEL": "anthropic/claude-opus-5-5",
+    "ANTHROPIC_DEFAULT_SONNET_MODEL": "anthropic/claude-sonnet-5-5",
     "ANTHROPIC_DEFAULT_HAIKU_MODEL": "anthropic/claude-haiku-4-5",
     "ANTHROPIC_DEFAULT_FABLE_MODEL": "anthropic/claude-fable-5-1"
   },
@@ -152,10 +151,9 @@ In the **JSON** editor:
   "env": {
     "ANTHROPIC_BASE_URL": "https://my-gateway-main-2e18f50.zuplo.app/config_fe0a04972d2848e0a94ae4b8bcd1497e",
     "ANTHROPIC_CUSTOM_HEADERS": "zp-gateway-api-key: <your-ai-gateway-app-api-key>",
-    "ANTHROPIC_MODEL": "anthropic/claude-sonnet-5",
-    "ANTHROPIC_SMALL_FAST_MODEL": "anthropic/claude-haiku-4-5",
-    "ANTHROPIC_DEFAULT_OPUS_MODEL": "anthropic/claude-opus-5",
-    "ANTHROPIC_DEFAULT_SONNET_MODEL": "anthropic/claude-sonnet-5",
+    "ANTHROPIC_MODEL": "anthropic/claude-sonnet-5-5",
+    "ANTHROPIC_DEFAULT_OPUS_MODEL": "anthropic/claude-opus-5-5",
+    "ANTHROPIC_DEFAULT_SONNET_MODEL": "anthropic/claude-sonnet-5-5",
     "ANTHROPIC_DEFAULT_HAIKU_MODEL": "anthropic/claude-haiku-4-5",
     "ANTHROPIC_DEFAULT_FABLE_MODEL": "anthropic/claude-fable-5-1"
   },

package/docs/ai-gateway/integrations/codex.mdx

@@ -40,8 +40,9 @@ The rest of this guide calls these your **gateway URL** and **gateway key**.
 
 The examples assume your provider is named `openai`. Replace that prefix with
 the name of **your** provider before copying anything. A provider named
-`my-openai` routes `my-openai/gpt-5`. The model part must be an ID that provider
-serves. Check [your provider's page](../managing-providers.mdx) in the Portal.
+`my-openai` routes `my-openai/gpt-6.1-sol`. The model part must be an ID that
+provider serves. Check [your provider's page](../managing-providers.mdx) in the
+Portal.
 
 :::
 
@@ -60,7 +61,7 @@ instead.
 
 ```toml
 model_provider = "zuplo"
-model = "openai/gpt-5"
+model = "openai/gpt-6.1-sol"
 
 [model_providers.zuplo]
 name = "Zuplo AI Gateway"
@@ -80,7 +81,7 @@ subscription logins.
 
 ```toml
 model_provider = "zuplo"
-model = "openai/gpt-5.6-sol"
+model = "openai/gpt-6.1-sol"
 
 [model_providers.zuplo]
 name = "Zuplo AI Gateway"
@@ -138,7 +139,7 @@ do. A placeholder value works if nothing else uses it.
 Set `model` in `config.toml`, or pass it on the command line:
 
 ```bash
-codex --config model_provider="zuplo" --model "openai/gpt-5.6-sol"
+codex --config model_provider="zuplo" --model "openai/gpt-6.1-sol"
 ```
 
 Do not use the `/model` picker. It sends model names without the provider

package/docs/ai-gateway/integrations/goose.mdx

@@ -57,7 +57,7 @@ configuration approaches depending on which version you choose.
    `v1/chat/completions` as the value
 
 7. Enter the model you want to use with goose, as `providerName/model`—for
-   example `openai/gpt-5-mini`.
+   example `openai/gpt-6-luna`.
 
 </Stepper>
 
@@ -98,8 +98,8 @@ Gateway by following these steps:
 8. Set the **API Key** to your gateway key
 
 9. Set the list of **Available Models** to the models the Model Filtering policy
-   allows, named as `providerName/model` (for example `openai/gpt-5-mini`,
-   `openai/gpt-5`, `openai/gpt-5-nano`)
+   allows, named as `providerName/model` (for example `openai/gpt-6-luna` and
+   `openai/gpt-6.1-sol`)
 
 10. Click on **Create Provider**
 

package/docs/ai-gateway/integrations/langchain.mdx

@@ -57,7 +57,7 @@ def init_chat_model():
         exit(1)
 
     return ChatOpenAI(
-        api_key=api_key, model="openai/gpt-5-mini", base_url=base_url
+        api_key=api_key, model="openai/gpt-6-luna", base_url=base_url
     )
 ```
 

package/docs/ai-gateway/integrations/openai.mdx

@@ -59,7 +59,7 @@ const client = new OpenAI({
 });
 
 const response = await client.chat.completions.create({
-  model: "openai/gpt-5-mini",
+  model: "openai/gpt-6-luna",
   messages: [
     {
       role: "user",
@@ -83,7 +83,7 @@ The AI Gateway supports all major OpenAI API endpoints through the
   interactions
 - **Embeddings** (`/v1/embeddings`) - For generating vector embeddings
 - **Responses** (`/v1/responses`) - For OpenAI models that support the responses
-  endpoint (such as GPT-5 and other compatible models)
+  endpoint (such as GPT-6.1 Sol and other compatible models)
 
 ## Using the Responses Endpoint
 
@@ -100,7 +100,7 @@ const client = new OpenAI({
 });
 
 const response = await client.responses.create({
-  model: "openai/gpt-5",
+  model: "openai/gpt-6.1-sol",
   input: "Write a one-sentence bedtime story about a unicorn.",
 });
 

package/docs/ai-gateway/managing-providers.mdx

@@ -45,7 +45,7 @@ To add a new AI provider to your Zuplo AI Gateway, follow these steps:
    provider you selected (a second OpenAI configuration becomes `openai-2`). You
    can replace it with your own name, but only now—the name is permanent after
    creation. Apps reference this provider's models as `providerName/model`—for
-   example, a provider named `openai` serves `openai/gpt-5-mini`.
+   example, a provider named `openai` serves `openai/gpt-6-luna`.
 
 1. Enter the API Key for the selected provider. For instructions on how to
    create an API key for each provider see the

package/docs/ai-gateway/openrouter.mdx

@@ -27,13 +27,13 @@ type:
 
 ## Model references include the vendor prefix
 
-Every OpenRouter model ID is vendor-qualified — `anthropic/claude-sonnet-4.5`,
-`openai/gpt-5`, `meta-llama/llama-3.3-70b-instruct`. A gateway model reference
-prefixes your provider name onto that, so it has **two** slashes:
+Every OpenRouter model ID is vendor-qualified — `anthropic/claude-sonnet-5`,
+`openai/gpt-6-sol`, `meta-llama/llama-3.3-70b-instruct`. A gateway model
+reference prefixes your provider name onto that, so it has **two** slashes:
 
 ```text
-openrouter/anthropic/claude-sonnet-4.5
-openrouter/openai/gpt-5
+openrouter/anthropic/claude-sonnet-5
+openrouter/openai/gpt-6-sol
 openrouter/meta-llama/llama-3.3-70b-instruct
 ```
 
@@ -101,7 +101,7 @@ account and project **Admins**—see
 
 3. Give the provider a **Provider Name**. This is the first segment of every
    model reference, so a provider named `openrouter` serves
-   `openrouter/openai/gpt-5`. The name is permanent after creation.
+   `openrouter/openai/gpt-6-sol`. The name is permanent after creation.
 
 4. Paste your **API Key**. There is no endpoint or region to enter — OpenRouter
    is a single global host.
@@ -123,14 +123,15 @@ OpenRouter lets you append a routing preference to any model ID:
 
 These work through the gateway and are forwarded to OpenRouter unchanged. They
 don't appear in the model picker, because they aren't separate models — the
-gateway resolves `openrouter/openai/gpt-5:nitro` against the `openai/gpt-5`
-catalog entry and sends the suffix upstream.
+gateway resolves `openrouter/openai/gpt-6-sol:nitro` against the
+`openai/gpt-6-sol` catalog entry and sends the suffix upstream.
 
 Two consequences worth knowing:
 
 - **A model-filtering allow list matches literally.** Allowing
-  `openrouter/openai/gpt-5` does not allow `openrouter/openai/gpt-5:nitro`. Add
-  the suffixed reference explicitly if you want it.
+  `openrouter/openai/gpt-6-sol` does not allow
+  `openrouter/openai/gpt-6-sol:nitro`. Add the suffixed reference explicitly if
+  you want it.
 - **Other suffixes aren't supported.** OpenRouter's `:free` variants are
   separate models, and the gateway's OpenRouter catalog doesn't include them, so
   a request for one is rejected like any model outside your selections.
@@ -149,7 +150,7 @@ const client = new OpenAI({
 });
 
 const completion = await client.chat.completions.create({
-  model: "openrouter/openai/gpt-5",
+  model: "openrouter/openai/gpt-6-sol",
   messages: [{ role: "user", content: "Hello!" }],
 });
 ```
@@ -161,7 +162,7 @@ preferences per request:
 
 ```ts
 const completion = await client.chat.completions.create({
-  model: "openrouter/openai/gpt-5",
+  model: "openrouter/openai/gpt-6-sol",
   messages: [{ role: "user", content: "Hello!" }],
   // @ts-expect-error -- an OpenRouter extension, not part of the OpenAI types
   provider: { sort: "throughput" },
@@ -205,7 +206,7 @@ const client = new Anthropic({
 });
 
 const message = await client.messages.create({
-  model: "openrouter/anthropic/claude-sonnet-4.5",
+  model: "openrouter/anthropic/claude-sonnet-5",
   max_tokens: 1024,
   messages: [{ role: "user", content: "Hello!" }],
 });

package/docs/ai-gateway/overview.mdx

@@ -89,7 +89,7 @@ providers include OpenAI, Anthropic, Google, Mistral, xAI, Microsoft Azure
 System One model ([Jev](./jev.mdx)), and OpenAI-compatible custom providers. See
 [AI Providers](./providers.mdx) for the full list of providers and supported
 capabilities. Apps reference models as `providerName/model`—for example
-`openai/gpt-5-mini`—so a single app can use models from several providers.
+`openai/gpt-6-luna`—so a single app can use models from several providers.
 
 ### Source-Controlled Gateway
 
@@ -97,7 +97,9 @@ A new AI Gateway project deploys without a Git repository, so you can configure
 providers, pools, and apps right away. Connect a
 [Git repository](./source-control.mdx) when you want to write custom policies or
 review gateway changes in Git. After you connect, the default branch is what
-production runs.
+production runs, and new template routes and policies reach the gateway only
+when you
+[add them to the repository](./source-control.mdx#keep-the-gateway-up-to-date).
 
 ### Per-App Policy Chains
 

package/docs/ai-gateway/providers.mdx

@@ -90,7 +90,7 @@ segment on its API URL, and you enter that URL as an origin root—without the
 [Custom Providers](./custom-providers.mdx#requirements) for the exact contract.
 
 Apps reference a provider's models as `providerName/model`—for example
-`openai/gpt-5-mini` or `anthropic/claude-sonnet-4-6`—where `providerName` is the
+`openai/gpt-6-luna` or `anthropic/claude-sonnet-5`—where `providerName` is the
 name you give the provider configuration. See the
 [Universal API](./universal-api.mdx).
 
@@ -199,7 +199,7 @@ Three things are specific to it:
 
 - **Model references have two slashes.** Every OpenRouter model ID is
   vendor-qualified, so a provider named `openrouter` serves
-  `openrouter/anthropic/claude-sonnet-4.5` and `openrouter/openai/gpt-5`. This
+  `openrouter/anthropic/claude-sonnet-5` and `openrouter/openai/gpt-6-sol`. This
   is the same shape Vertex AI uses.
 - **Claude models are on the Messages API.** Models whose ID begins `anthropic/`
   serve the native Anthropic Messages API (`/v1/messages`) and a translated

package/docs/ai-gateway/source-control.mdx

@@ -36,8 +36,20 @@ it. The first push rebuilds production from that source. After that, with
 GitHub, pushes to your default branch deploy to production.
 
 Until you connect a repository, production runs the gateway template Zuplo
-deploys at project creation. Connecting a repository doesn't replace that
-production URL; the first source deploy reuses it.
+deploys at project creation, and Zuplo redeploys it daily from the latest
+template, so new routes and policies reach the gateway automatically. Connecting
+a repository doesn't replace that production URL; the first source deploy reuses
+it.
+
+:::caution{title="Connected gateways stop receiving template updates"}
+
+Connecting a repository copies the current template into it. After that,
+production runs only what's in your repository, and Zuplo doesn't change it.
+Routes and policies that Zuplo later adds to the template, such as the `/u/`
+route that serves the [User App](./user-apps.mdx), don't reach the gateway until
+you add them. See [Keep the gateway up to date](#keep-the-gateway-up-to-date).
+
+:::
 
 To work with the source locally, clone the repository:
 
@@ -98,9 +110,56 @@ deployment.
 
 :::
 
+## Keep the gateway up to date
+
+When Zuplo adds routes or policies to the AI Gateway template, a connected
+gateway doesn't get them until you add them to `config/ai.oas.json` and
+`config/policies.json`. The [`zuplo source upgrade`](../cli/source-upgrade.mdx)
+command adds the missing definitions for you. Run it from a local clone of the
+repository:
+
+1. Install the latest `zuplo` package. If `package.json` or the lockfile change,
+   commit them; applying an upgrade requires a clean working tree.
+
+   ```bash
+   npm install zuplo@latest
+   ```
+
+2. Preview the upgrade. The CLI prints each missing route and policy and a diff,
+   without changing any files:
+
+   ```bash
+   npx zuplo source upgrade --type ai-gateway
+   ```
+
+3. Apply the upgrade. The CLI asks you to confirm before it writes the files:
+
+   ```bash
+   npx zuplo source upgrade --type ai-gateway --apply
+   ```
+
+4. Review and test the changes, then commit and push them:
+
+   ```bash
+   git add --all
+   git commit -m "Upgrade AI Gateway template"
+   git push
+   ```
+
+   The push deploys like any other repository change—see
+   [How deployments work](#how-deployments-work).
+
+The command only adds what's missing. It doesn't change your existing routes,
+policies, or custom policy code. If an addition conflicts with your
+configuration or can't be verified, the CLI changes nothing and prints the
+definitions so you can add them by hand. Review authentication and policy order
+before you add a route manually.
+
 ## Next steps
 
 - [Policy Chains](./policy-chains.mdx): how apps select policies from
   `config/policies.json`
 - [Custom Policies](./custom-policies.mdx): add your own policy to the
   repository
+- [`zuplo source upgrade`](../cli/source-upgrade.mdx): every option and the
+  recovery steps for an interrupted upgrade

package/docs/ai-gateway/universal-api.mdx

@@ -40,7 +40,7 @@ const client = new OpenAI({
 });
 
 const response = await client.chat.completions.create({
-  model: "openai/gpt-5-mini",
+  model: "openai/gpt-6-luna",
   messages: [
     {
       role: "user",

package/docs/ai-gateway/user-apps.mdx

@@ -18,8 +18,11 @@ engineer using Claude Code or Codex is a person, and calls the User App with a
 personal key.
 
 Each AI Gateway project has one User App, created for you. A new project gets it
-right away; an existing project gets it on its next production deployment. It
-has:
+right away; an existing project gets it on its next production deployment. A
+project connected to source control also needs the User App route in its
+repository—see
+[Keep the gateway up to date](./source-control.mdx#keep-the-gateway-up-to-date).
+It has:
 
 - **A URL** under `/u/`, such as
   `https://my-gateway-main-2e18f50.zuplo.app/u/741d375d631b429293481d6d0458bb64`.

package/docs/articles/accounts/audit-logs.mdx

@@ -142,26 +142,20 @@ exceed 30 days. The start date must be before the end date.
   "data": [
     {
       "action": "project.update",
-      "metadata": {
-        /* action-specific metadata */
-      },
+      "metadata": {/* action-specific metadata */},
       "actor": {
         "sub": "auth0|123456",
         "email": "user@example.com",
         "type": "user",
         "connection": "auth0",
         "actingAs": null,
-        "metadata": {
-          /* additional actor metadata */
-        }
+        "metadata": {/* additional actor metadata */}
       },
       "resources": [
         {
           "type": "project",
           "id": "proj_123",
-          "metadata": {
-            /* resource-specific metadata */
-          }
+          "metadata": {/* resource-specific metadata */}
         }
       ],
       "context": {