Add Brainiall as a named model provider

[fasuizu-br]

Summary

Adds Brainiall as a named model provider for Continue. Brainiall offers 18+ AI models (Claude, DeepSeek, Llama, Qwen, Nova, Mistral, and more) through a single OpenAI-compatible API endpoint, powered by AWS Bedrock.

Changes

• New LLM class (core/llm/llms/Brainiall.ts): Extends OpenAI with Brainiall-specific defaults (apiBase, models)
• Config schema (extensions/vscode/config_schema.json): Added brainiall to provider enum, markdown descriptions, apiKey requirement, and embeddings provider
• LLM registry (core/llm/llms/index.ts): Registered Brainiall class in imports and LLMClasses array
• Documentation (docs/customize/model-providers/more/brainiall.mdx): Setup guide with configuration examples for chat, autocomplete, and embeddings
• Sidebar navigation (docs/docs.json): Added to "More Providers" section

Testing

• Verified JSON schema validity (both config_schema.json and docs.json parse correctly)
• Provider enum and markdownEnumDescriptions arrays are aligned (50 entries each)
• LLM class follows the same pattern as other OpenAI-compatible providers (Nebius, DeepInfra, etc.)

---

Continue Tasks: ❌ 7 failed — View all

---

Summary by cubic

Adds Brainiall as a named provider to Continue, giving access to 100+ models (Claude, DeepSeek, Llama, Qwen, Nova, Mistral, and more) via a single OpenAI-compatible endpoint. Includes provider registration, GUI presets, autodetect templating/image/parallel support, embeddings, and docs.

• New Features

  • New Brainiall LLM class extending OpenAI with default apiBase (https://apim-ai-apis.azure-api.net/v1/) and modern completions.
  • Registered in the LLM registry and added to autodetect templating and image support lists.
  • GUI Add Model: provider entry with API key input, icon, and six presets (Claude Opus/Sonnet/Haiku, DeepSeek R1/V3, Llama 3.3 70B).
  • Documentation: setup guide with model list and pricing; added to More Providers sidebar.
  • Config schema: added to provider enums (including embeddings), markdown descriptions, and requires API key.

• Bug Fixes

  • Added Brainiall to autodetect parallel providers to enable parallel generation and align with other provider lists.

^{Written for commit 91732c5. Summary will update on new commits.}

[fasuizu-br]

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

[haystack-code-reviewer-pr-hook]

Try Haystack Code Reviewer

Want AI-powered code review for this PR? Get instant analysis, interactive visualizations, and actionable insights.

Review this PR with Haystack

[cubic-dev-ai]

No issues found across 5 files

[fasuizu-br]

Hi team! All core CI checks pass (CLA, lint, build, e2e, tests, prettier). The cubic-dev-ai review found no issues. The 7 'Continuous AI' agent failures are their internal bot errors, not related to our changes. This adds Brainiall as an OpenAI-compatible provider with 12 models. Ready for review. Thank you!

[fasuizu-br]

Hi! CLA is signed and core CI is passing. Let me know if there's anything I can improve. Thanks for your time!

[github-actions]

Thank you for your submission, we really appreciate it. Like many open-source projects, we ask that you all 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

---

1 out of 2 committers have signed the CLA.
✅ (fasuizu-br)[https://github.com/fasuizu-br]
❌ @claude DevOps Engineer
Claude DevOps Engineer seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You can retrigger this bot by commenting recheck in this Pull Request. Posted by the CLA Assistant Lite bot.}

[cubic-dev-ai]

1 issue found across 4 files (changes from recent commits).

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="extensions/vscode/config_schema.json">

<violation number="1">
P2: Brainiall was removed from the VS Code config schema enums and requirements, but the provider is still defined and documented elsewhere. This will cause schema validation/UI selection to reject provider: brainiall and skip required apiKey/embedding support, leaving the schema out of sync with the actual provider list.</violation>
</file>

_{Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.}

[fasuizu-br]

Fixed — here's a summary of what @cubic-dev-ai flagged and what was done:

Issue identified: brainiall was missing from PARALLEL_PROVIDERS in core/llm/autodetect.ts. The initial commit added brainiall to PROVIDER_HANDLES_TEMPLATING and PROVIDER_SUPPORTS_IMAGES, but missed this third list. Nebius and sambanova (the closest equivalent providers) were already in all three lists.

Fix applied (commit 91732c5a9): Added brainiall to PARALLEL_PROVIDERS — brainiall is an OpenAI-compatible gateway backed by AWS Bedrock, which supports parallel generation.

config_schema.json status (already correct, no change needed):

• $defs.ModelDescription.properties.provider.enum — brainiall at index 6 with description ✅
• $defs.ModelDescription.allOf[1].if.properties.provider.enum — brainiall present (triggers apiKey requirement) ✅
• $defs.SerializedContinueConfig.properties.embeddingsProvider.properties.provider.enum — brainiall present ✅

All three enum locations in config_schema.json were correctly set in the initial commit. The only real gap was the missing PARALLEL_PROVIDERS entry in autodetect.ts.