Skip to content

fix: update Nebius provider for Token Factory - #13129

Draft
demianarc wants to merge 1 commit into
continuedev:mainfrom
demianarc:codex/nebius-token-factory
Draft

fix: update Nebius provider for Token Factory#13129
demianarc wants to merge 1 commit into
continuedev:mainfrom
demianarc:codex/nebius-token-factory

Conversation

@demianarc

Copy link
Copy Markdown

Description

Fixes #13128.

Continue's existing Nebius provider still used the retired Nebius AI Studio host in both the core LLM and the OpenAI adapter. It also rewrote model names through a static alias table that had drifted from the provider catalog; notably, llama3.1-8b resolved to the 70B model.

This change:

  • switches both defaults to the documented https://api.tokenfactory.nebius.com/v1/ endpoint while preserving custom apiBase overrides
  • removes the stale alias rewrites so configured and dynamically fetched catalog IDs pass through unchanged
  • replaces the old preset list with a current starter plus Continue's existing authenticated live-catalog refresh
  • updates the provider UI, config schema, and docs to Nebius Token Factory naming and current links
  • removes the unverified pricing/trial copy and makes model-dependent tool support explicit
  • adds mocked regressions for the default endpoint, custom endpoint override, streamed Chat Completions, tool payloads, and model-ID pass-through

Chat Completions remains the default API surface; this PR does not enable or claim stateful Responses API behavior.

AI Code Review

  • Team members only: AI review runs automatically when PR is opened or marked ready for review
  • Team members can also trigger a review by commenting @continue-review

Checklist

  • I've read the contributing guide
  • The relevant docs, if any, have been updated or created
  • The relevant tests, if any, have been updated or created

Screen recording or screenshot

Not applicable: this repairs provider routing, catalog configuration, and copy without changing the form layout.

Tests

  • cd core && npx vitest run llm/llms/OpenAI-compatible.vitest.ts — 212 passed
  • cd core && npx vitest run llm/llms/OpenAI-compatible.vitest.ts -t nebius — 8 passed
  • cd packages/openai-adapters && npx vitest run src/test/main.test.ts — 17 passed
  • cd packages/openai-adapters && npm run build
  • cd core && npm run tsc:check
  • cd gui && npx tsc --project tsconfig.json --noEmit
  • focused Prettier check and git diff --check

The API behavior tests are mocked and do not require or expose a live Nebius API key.

@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.

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Nebius provider uses retired endpoint and stale model aliases

1 participant