feat(llm): add Doubao (Volcengine Ark) as an LLM provider by MackDing · Pull Request #12219 · continuedev/continue

MackDing · 2026-04-24T11:12:17Z

What

Adds Doubao (豆包 / ByteDance) via Volcengine Ark as a first-class LLM provider in Continue, following the existing pattern used for Moonshot, Deepseek, MiniMax, zAI, and SiliconFlow.

Doubao is one of the most-used LLM families in China; Volcengine Ark (火山方舟) is its official hosted platform and exposes an OpenAI-compatible /chat/completions surface at https://ark.cn-beijing.volces.com/api/v3/. Today users have to work around the gap by using the generic OpenAI provider with apiBase and model overrides — this PR makes provider: doubao just work.

Why

Demand: Doubao is ByteDance's flagship LLM and is widely deployed in mainland-China-facing projects.
No new surface area: Ark is OpenAI-compatible, so the adapter is a ~30-line OpenAI subclass. Registration is the same shape used by Moonshot / Deepseek / zAI.
Closes an implicit feature gap that existing users of China-region models have been asking about (visible in several closed Qwen/Deepseek provider-error issues where users cite Doubao as the alternative).

Changes

File	Purpose
`core/llm/llms/Doubao.ts`	New `Doubao extends OpenAI` with Ark base URL
`core/llm/llms/index.ts`	Register in `LLMClasses`
`core/llm/autodetect.ts`	Add to `PROVIDER_HANDLES_TEMPLATING` (Ark handles chat templating server-side, same as Moonshot/Deepseek)
`packages/openai-adapters/src/apis/Doubao.ts`	Adapter wrapping `OpenAIApi` with `ark.cn-beijing.volces.com/api/v3/`
`packages/openai-adapters/src/types.ts`	`DoubaoConfigSchema` in the discriminated union
`packages/openai-adapters/src/index.ts`	`constructLlmApi` → `DoubaoApi`
`packages/openai-adapters/src/apis/Doubao.test.ts`	3 new tests (routing / default base URL / preserved OpenAI-chat surface)
`core/llm/llms/OpenAI-compatible.vitest.ts`	Doubao row in the shared subclass test matrix
`docs/customize/model-providers/more/doubao.mdx`	User-facing config docs

Diff: 9 files, +222 / −0.

Design notes

No default model is set. Ark addresses models by either a date-stamped model ID (e.g. doubao-seed-1-6-251015, doubao-1-5-pro-32k-250115) or a user-provisioned endpoint ID (ep-20240xxx-xxxxx). A bare alias like doubao-1-5-pro-32k would silently 404, so the adapter intentionally requires the user to pick a valid ID. The docs link to the official Ark model list so users can copy a currently valid one.
maxStopWords = 4 matches Ark's documented limit for OpenAI-compatible chat completions.
No FIM override. Ark does not expose a public beta/completions FIM protocol today. If that changes, we can override fimStream the way Moonshot and Deepseek do.
Not registered in packages/llm-info — consistent with Moonshot and Deepseek, which also rely solely on the LLMClasses + openai-adapters registration.

Testing

packages/openai-adapters$ npm test
Test Files  15 passed | 2 skipped (17)
     Tests  148 passed | 5 skipped (150)

3 of those 148 are new Doubao tests covering:

constructLlmApi({ provider: "doubao" }) returns a DoubaoApi instance.
Default apiBase is the Ark cn-beijing v3 URL.
Inherits the OpenAI-chat surface (chatCompletionStream / chatCompletionNonStream).

TypeScript check: tsc --noEmit on packages/openai-adapters → 0 errors.

References

Volcengine Ark docs root: https://www.volcengine.com/docs/82379
Ark model list (date-stamped IDs): https://www.volcengine.com/docs/82379/1330310
Ark OpenAI-SDK compatibility notes: https://www.volcengine.com/docs/82379/1330626

Summary by cubic

Adds Doubao (ByteDance) via Volcengine Ark as a first-class LLM provider using the OpenAI-compatible /chat/completions API. Users can now set provider: doubao to use China-region Doubao models without workarounds.

New Features
- New doubao provider with default apiBase: https://ark.cn-beijing.volces.com/api/v3/.
- Registered in LLMClasses and constructLlmApi; added DoubaoConfigSchema.
- Autodetect updated so Doubao handles chat templating on the server.
- Docs added for configuration; tests cover routing and API surface.
Migration
- No default model. Set a valid Ark model ID (e.g. doubao-seed-1-6-251015) or endpoint ID (e.g. ep-...) in model.
- If you previously used provider: openai with Ark apiBase, switch to provider: doubao and keep the same model and apiKey.

^{Written for commit 27dd211. Summary will update on new commits.}

Doubao is ByteDance's widely used LLM family, served via Volcengine Ark (火山方舟). Ark exposes an OpenAI-compatible `/chat/completions` surface at https://ark.cn-beijing.volces.com/api/v3/, so the adapter is a thin OpenAI subclass that mirrors the existing Moonshot/Deepseek/zAI pattern. Registration: - core/llm/llms/Doubao.ts — new provider subclass of OpenAI. - core/llm/llms/index.ts — added to the LLMClasses registry. - core/llm/autodetect.ts — listed in PROVIDER_HANDLES_TEMPLATING so Ark's server-side chat template is trusted (consistent with Moonshot and Deepseek). - packages/openai-adapters/src/apis/Doubao.ts — OpenAI-adapter wrapper with the Ark base URL. - packages/openai-adapters/src/types.ts + index.ts — new DoubaoConfigSchema and constructLlmApi case. Notes: - No default model is set. Ark requires either a date-stamped model ID (e.g. `doubao-seed-1-6-251015`, `doubao-1-5-pro-32k-250115`) or an Ark-provisioned endpoint ID (`ep-20240xxx-xxxxx`); hard-coding a bare alias would silently 404. - Docs cover YAML + JSON config, endpoint-ID usage, and link to the Ark model list so users pick an ID that resolves today. Tests: - New packages/openai-adapters/src/apis/Doubao.test.ts covering constructLlmApi(doubao) routing, default apiBase, and preserved OpenAI-chat surface (3 tests). - OpenAI-compatible.vitest.ts subclass matrix entry for parity with Moonshot/Deepseek. - `npm test` in packages/openai-adapters: 148 passed / 5 skipped.

github-actions · 2026-04-24T11:12:27Z

All contributors have signed the CLA ✍️ ✅
_{Posted by the CLA Assistant Lite bot.}

cubic-dev-ai

2 issues found across 9 files

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="docs/customize/model-providers/more/doubao.mdx">

<violation number="1" location="docs/customize/model-providers/more/doubao.mdx:15">
P2: Configuration instructions are internally contradictory about using model aliases versus date-stamped model IDs/endpoint IDs, which can lead to invalid setup.</violation>
</file>

<file name="packages/openai-adapters/src/apis/Doubao.ts">

<violation number="1" location="packages/openai-adapters/src/apis/Doubao.ts:19">
P2: Subclass field initialization overwrites `config.apiBase` set by `OpenAIApi`, breaking custom base URL configuration.</violation>
</file>

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

cubic-dev-ai · 2026-04-24T11:16:40Z

+To use Doubao models:
+
+1. Create an API key on the [Volcengine Ark console](https://console.volcengine.com/ark/).
+2. Either deploy the model you want as an endpoint and copy its endpoint ID, or use a public model alias.


P2: Configuration instructions are internally contradictory about using model aliases versus date-stamped model IDs/endpoint IDs, which can lead to invalid setup.

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At docs/customize/model-providers/more/doubao.mdx, line 15: <comment>Configuration instructions are internally contradictory about using model aliases versus date-stamped model IDs/endpoint IDs, which can lead to invalid setup.</comment> <file context> @@ -0,0 +1,111 @@ +To use Doubao models: + +1. Create an API key on the [Volcengine Ark console](https://console.volcengine.com/ark/). +2. Either deploy the model you want as an endpoint and copy its endpoint ID, or use a public model alias. +3. Add the following configuration: + </file context>

cubic-dev-ai · 2026-04-24T11:16:40Z

+ * Reference: https://www.volcengine.com/docs/82379
+ */
+export class DoubaoApi extends OpenAIApi {
+  apiBase: string = "https://ark.cn-beijing.volces.com/api/v3/";


P2: Subclass field initialization overwrites config.apiBase set by OpenAIApi, breaking custom base URL configuration.

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At packages/openai-adapters/src/apis/Doubao.ts, line 19: <comment>Subclass field initialization overwrites `config.apiBase` set by `OpenAIApi`, breaking custom base URL configuration.</comment> <file context> @@ -0,0 +1,26 @@ + * Reference: https://www.volcengine.com/docs/82379 + */ +export class DoubaoApi extends OpenAIApi { + apiBase: string = "https://ark.cn-beijing.volces.com/api/v3/"; + constructor(config: DoubaoConfig) { + super({ </file context>

MackDing · 2026-04-24T18:33:14Z

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

MackDing · 2026-04-30T23:03:58Z

Quick follow-up: all CI on my side looks green now. If the remaining blocker is the automated review feedback or pending AI checks, I’m happy to submit a follow-up patch. If there is a maintainer-preferred direction for the Doubao provider integration, I can adjust accordingly. Thanks for taking a look.

MackDing requested a review from a team as a code owner April 24, 2026 11:12

github-project-automation Bot added this to Issues and PRs Apr 24, 2026

MackDing requested review from sestinj and removed request for a team April 24, 2026 11:12

github-project-automation Bot moved this to Todo in Issues and PRs Apr 24, 2026

dosubot Bot added the size:L This PR changes 100-499 lines, ignoring generated files. label Apr 24, 2026

cubic-dev-ai Bot reviewed Apr 24, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(llm): add Doubao (Volcengine Ark) as an LLM provider#12219

feat(llm): add Doubao (Volcengine Ark) as an LLM provider#12219
MackDing wants to merge 1 commit intocontinuedev:mainfrom
MackDing:feat-llm-provider-doubao

MackDing commented Apr 24, 2026 •

edited by cubic-dev-ai Bot

Loading

Uh oh!

github-actions Bot commented Apr 24, 2026 •

edited

Loading

Uh oh!

cubic-dev-ai Bot left a comment

Uh oh!

cubic-dev-ai Bot Apr 24, 2026 •

edited

Loading

Uh oh!

cubic-dev-ai Bot Apr 24, 2026 •

edited

Loading

Uh oh!

MackDing commented Apr 24, 2026

Uh oh!

MackDing commented Apr 30, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Conversation

MackDing commented Apr 24, 2026 • edited by cubic-dev-ai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What

Why

Changes

Design notes

Testing

References

Summary by cubic

Uh oh!

github-actions Bot commented Apr 24, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

cubic-dev-ai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

cubic-dev-ai Bot Apr 24, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

cubic-dev-ai Bot Apr 24, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

MackDing commented Apr 24, 2026

Uh oh!

MackDing commented Apr 30, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

MackDing commented Apr 24, 2026 •

edited by cubic-dev-ai Bot

Loading

github-actions Bot commented Apr 24, 2026 •

edited

Loading

cubic-dev-ai Bot Apr 24, 2026 •

edited

Loading

cubic-dev-ai Bot Apr 24, 2026 •

edited

Loading