Skip to content

docs: add app.nz model provider page#12914

Open
lee101 wants to merge 1 commit into
continuedev:mainfrom
lee101:add-appnz-docs
Open

docs: add app.nz model provider page#12914
lee101 wants to merge 1 commit into
continuedev:mainfrom
lee101:add-appnz-docs

Conversation

@lee101

@lee101 lee101 commented Jun 28, 2026

Copy link
Copy Markdown

Description

Adds documentation for app.nz, a hosted OpenAI-compatible (and Anthropic-compatible) LLM gateway with an automatic model router.

Changes

  • New page docs/customize/model-providers/more/appnz.mdx covering setup with provider: openai, apiBase: https://app.nz/v1, model: app/auto, and the app/auto-code / app/auto-reasoning / app/auto-fast / app/auto-cheap / app/auto-vision routing variants, plus provider/model direct addressing.
  • Registered the page in the docs.json "More Providers" sidebar.
  • Added an app.nz row to the providers overview table in overview.mdx.

The page mirrors the frontmatter and structure of existing more/*.mdx provider pages (e.g. ClawRouter, Morph).


Summary by cubic

Add documentation for app.nz, an OpenAI-compatible LLM gateway with automatic model routing. The new page covers setup using provider: openai, apiBase: https://app.nz/v1, and model: app/auto (plus auto-* variants and provider/model direct addressing), and is linked in the “More Providers” sidebar and the providers overview.

Written for commit 8c0964e. Summary will update on new commits.

Review in cubic

Add docs/customize/model-providers/more/appnz.mdx covering the app.nz
OpenAI-compatible gateway (provider: openai, apiBase https://app.nz/v1,
model app/auto plus auto-* routing variants). Register the page in the
docs.json "More Providers" sidebar and the providers overview table.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@lee101 lee101 requested a review from a team as a code owner June 28, 2026 09:43
@lee101 lee101 requested review from sestinj and removed request for a team June 28, 2026 09:43
@dosubot dosubot Bot added the size:L This PR changes 100-499 lines, ignoring generated files. label Jun 28, 2026
@github-actions

Copy link
Copy Markdown
Contributor


Thank you for your submission, we really appreciate it. Like many open-source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution. You can sign the CLA by just posting a Pull Request Comment same as the below format.


I have read the CLA Document and I hereby sign the CLA


You can retrigger this bot by commenting recheck in this Pull Request. Posted by the CLA Assistant Lite bot.

@cubic-dev-ai cubic-dev-ai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No issues found across 3 files

Re-trigger cubic

@chatgpt-codex-connector

Copy link
Copy Markdown

💡 Codex Review

on("models/fetch", async (msg) => {

P1 Badge Restore the license-key core handler

The VS Code command continue.enterEnterpriseLicenseKey is still contributed and calls core.invoke("mdm/setLicenseKey", ...), and IntelliJ's AddLicenseKey flow still sends the same message, but this hunk removes the only mdm/setLicenseKey handler and registers models/fetch instead. In those IDE flows, entering an enterprise license key now results in an unhandled core request rather than validating and saving the key, so enterprise license setup is unusable unless the handler is restored or the commands are removed/updated.



P2 Badge Avoid rerunning non-idempotent stream setup on retry

When a 529/overloaded error happens after the user message has already been inserted, this retry loop calls runStream() again from the top. For normal chat, streamResponseThunk recomputes inputIndex from the current history and calls submitEditorAndInitAtIndex, so each retry appends another copy of the same user input before resending, corrupting the conversation and prompt. The retry should wrap only the LLM request or reuse the original input/index instead of rerunning the whole setup closure.


const target = redirectTo.startsWith("http")
? redirectTo
: `/docs${redirectTo}`;

P2 Badge Redirect old docs URLs to the app route

For internal redirects such as /customization -> /customize/overview from docs/docs.json, this builds /docs/customize/overview and passes it directly to window.location.replace. The new standalone docs app is a root catch-all route (and GitHub Pages also needs the /continue base path), so these legacy URLs navigate to a non-existent /docs/... path instead of the destination page. Use the same route/base-path resolution as normal docs links, or redirect to redirectTo directly with the deploy base path applied.

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size:L This PR changes 100-499 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant