💄 style: Add new MiniMax-M3 model#15403
Merged
Merged
Conversation
|
@sxjeru is attempting to deploy a commit to the LobeHub OSS Team on Vercel. A member of the Team first needs to authorize it. |
Contributor
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Adds support for the new MiniMax-M3 model, including provider-side payload handling, a non-streaming-to-streaming response transformer, pricing in the model bank, and corresponding tests. Also removes two MiMo-V2 entries from xiaomimimo.ts and turns off the previous default-enabled flags on older MiniMax models.
Changes:
- Introduce
MiniMax-M3model card, pricing tiers, and vision keyword classification. - Branch
buildMiniMaxOpenAIPayloadon M3 to switch parameter ranges, output token field, and thinking config; addhandleTransformResponseToStreamto convert MiniMax's non-streaming response into chunked stream events. - Add tests for the new payload behavior and pricing tiers; remove MiMo-V2-Pro and MiMo-V2-Omni entries.
Reviewed changes
Copilot reviewed 6 out of 6 changed files in this pull request and generated 5 comments.
Show a summary per file
| File | Description |
|---|---|
| packages/model-runtime/src/utils/modelParse.ts | Adds -m3 to MiniMax vision keywords so M3 is classified as a vision model. |
| packages/model-runtime/src/providers/minimax/index.ts | Adds M3-specific payload mapping (thinking, ranges, max_completion_tokens) and a response-to-stream transformer. |
| packages/model-runtime/src/providers/minimax/index.test.ts | Adds tests covering M3 payload mapping, multimodal pass-through, and non-M3 fallback. |
| packages/model-runtime/src/core/usageConverters/utils/computeChatCost.test.ts | Adds tiered-pricing tests for MiniMax-M3. |
| packages/model-bank/src/aiModels/minimax.ts | Registers MiniMax-M3 model card and disables previous enabled: true defaults on M2.7 and Hailuo 02. |
| packages/model-bank/src/aiModels/xiaomimimo.ts | Removes MiMo-V2-Pro and MiMo-V2-Omni entries. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+257
to
+277
| if (data.usage) { | ||
| controller.enqueue({ | ||
| choices: [], | ||
| created: data.created, | ||
| id: data.id, | ||
| model: data.model, | ||
| object: 'chat.completion.chunk', | ||
| usage: data.usage, | ||
| }); | ||
| } | ||
|
|
||
| controller.enqueue({ | ||
| choices: choices.map((choice: any) => ({ | ||
| delta: { | ||
| content: null, | ||
| role: choice.message.role, | ||
| }, | ||
| finish_reason: choice.finish_reason, | ||
| index: choice.index, | ||
| logprobs: choice.logprobs, | ||
| })), |
Comment on lines
+172
to
+180
| const finalThinking = isM3 | ||
| ? thinking?.type === 'disabled' | ||
| ? { thinking: { type: 'disabled' } } | ||
| : thinking?.type === 'enabled' || thinking?.type === 'adaptive' | ||
| ? { thinking: { type: 'adaptive' } } | ||
| : {} | ||
| : thinking | ||
| ? { thinking } | ||
| : {}; |
| baseURL: DEFAULT_MINIMAX_BASE_URL, | ||
| chatCompletion: { | ||
| handlePayload: buildMiniMaxOpenAIPayload, | ||
| handleTransformResponseToStream: (data) => { |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 86be247ea5
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".
|
|
||
| export const buildMiniMaxOpenAIPayload = (payload: ChatStreamPayload) => { | ||
| const { enabledSearch, max_tokens, messages, temperature, top_p, ...params } = payload; | ||
| const { enabledSearch, max_tokens, messages, temperature, thinking, top_p, ...params } = payload; |
There was a problem hiding this comment.
Avoid forwarding unsupported n for MiniMax-M3
When a caller sets n > 1 (the payload type allows it, and the new M3 test passes n: 2), this rest spread keeps n in the request for MiniMax-M3. MiniMax's OpenAI-compatible docs state that M3 only supports n value 1 (https://platform.minimax.io/docs/api-reference/text-openai-api), so these requests will be rejected upstream instead of using the newly added model; drop n for M3 or clamp it to 1 before spreading the remaining params.
Useful? React with 👍 / 👎.
Member
|
@arvinxx @tjx666 — could you review this PR? Summary: Adds new MiniMax-M3 model definitions and updates the MiniMax provider runtime in Files changed:
Note: PR #15380 ("feat: support MiniMax M3 Anthropic video runtime") was recently merged — worth checking for overlap or conflicts. |
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## canary #15403 +/- ##
==========================================
- Coverage 71.17% 71.08% -0.09%
==========================================
Files 3200 3210 +10
Lines 320173 320680 +507
Branches 34056 29241 -4815
==========================================
+ Hits 227870 227959 +89
- Misses 92128 92545 +417
- Partials 175 176 +1
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
tjx666
reviewed
Jun 2, 2026
|
|
||
| export const buildMiniMaxOpenAIPayload = (payload: ChatStreamPayload) => { | ||
| const { enabledSearch, max_tokens, messages, temperature, top_p, ...params } = payload; | ||
| const { enabledSearch, max_tokens, messages, temperature, thinking, top_p, ...params } = payload; |
Member
There was a problem hiding this comment.
MiniMax-M3 only supports n = 1 in the OpenAI-compatible API, but this rest spread forwards any caller-provided n unchanged (the new test even passes n: 2). That will make those requests fail upstream. Please drop n for M3 or normalize it to 1 before spreading the remaining params.
Reference: https://platform.minimax.io/docs/api-reference/text-openai-api
Contributor
Author
There was a problem hiding this comment.
LobeHub 应该没有使用 n 参数的先例？
tjx666
reviewed
Jun 2, 2026
tjx666
reviewed
Jun 2, 2026
Member
|
❤️ Great PR @sxjeru ❤️ The growth of project is inseparable from user feedback and contribution, thanks for your contribution! If you are interesting with the lobehub developer community, please join our discord and then dm @arvinxx or @canisminor1990. They will invite you to our private developer channel. We are talking about the lobe-chat development or sharing ai newsletter around the world. |
Merged
arvinxx
added a commit
that referenced
this pull request
Jun 4, 2026
# 🚀 LobeHub Release (20260604) **Release Date:** June 4, 2026 **Since v2.2.1:** 88 merged PRs · 11 contributors > This week brings Execution Devices out of the lab — run agents and Claude Code on any configured local or remote machine — alongside Claude Opus 4.8, token-usage analytics, and Page sharing. --- ## ✨ Highlights - **Execution Devices** — Pick where an agent runs. Desktop and CLI devices auto-register with a stable machine ID, route through the gateway by channel, and surface a device switcher in the chat input. Run remote Claude Code on a configured device, with a recent-directory picker you can drag to reorder. (#15300, #15315, #15322, #15343, #15351, #15371) - **Claude Opus 4.8** — Day-one support for Anthropic's latest model. (#15314) - **Token-usage analytics** — A new token-usage mode on the activity heatmap, backed by a denormalized topic usage/cost rollup so totals stay accurate without recomputing from messages. (#15365, #15417, #15425) - **Page sharing** — Share a Page through a dedicated document share flow, plus new Workspace and Agent share tables. (#15309, #15439) - **Self-iteration agents** — Agent Signal's execAgent migration lands a server-runtime bridge, async memory writer, and a registered self-iteration tool package, with a CLI trigger command for testing. (#15360, #15364, #15392) - **Knowledge search** — BM25 search now extends to file-backed documents, and the portal ships an editable CodeMirror viewer for local files with document highlighting. (#15247, #15298) --- ## 🏗️ Core Agent & Architecture ### Agent Signal & Runtime - **execAgent migration** — Server-runtime bridge, completion projection, async memory writer, and removal of the legacy `executeSelfIteration` path. (#15392) - Registered the self-iteration builtin tool package and restored the three mode-specific self-iteration agent slugs. (#15202, #15364) - Added a CLI trigger command with a golden-snapshot fixture for Agent Signal. (#15360) - **Skill priority** — Agent Builder now emits a skill-priority instruction with matching server runtime. (#15409) - Retry empty LLM completions instead of silently finishing the turn. (#15355) - Classify topic/agent/session foreign-key violations as `ConversationParentMissing` for clearer recovery. (#15408) - Persist canonical nested usage/performance on assistant messages, and re-link orphan tool messages at the raw bucket write boundary. (#15359, #15438) - Guard `createAgent` against LLM double-encoded array fields. (#15381) --- ## 🖥️ Execution Devices & Gateway - Auto-register desktop and CLI devices with a stable machine ID, and add the `@lobechat/device-identity` package. (#15300, #15321) - New Devices settings page behind the Execution Device Switcher lab, with a device switcher shown for all agents in the chat input. (#15315, #15371) - `connectionId` + channel routing across the gateway client and device list; preset the local device on the first LLM request for the 本机 target. (#15322, #15435) - Run remote Claude Code on a configured device, with drag-to-reorder recent-directory management and client renders for device tool results. (#15343, #15351, #15437) - Preserve content and state across gateway tool calls, and prevent duplicate streaming from stale reconnects. (#15114, #15354) --- ## 🖥️ CLI & Desktop - Preserve content/state for connect local file and shell tools; render the `runCommand` tool result card. (#15441, #15442) - New `lh topic view` command; CLI now auto-registers its device on login, matching desktop. (#15340, #15377) - Resolve CLI tools from the shell `PATH`, and clarify local command session handling. (#15368, #15389) - Relocate visual-ref helpers to `@lobechat/const` to fix a renderer crash; upload `.blockmap` files to S3 for differential updates. (#15326, #15369) - Fix a market OAuth expiry that triggered the wrong re-login modal, and kill dev child processes on parent shutdown. (#15246, #15290) --- ## 🗂️ Pages, Library & Knowledge - Document share flow with business slot stubs, plus Workspace and Agent share tables. (#15309, #15439) - Export Agent profiles as Markdown, preserving an empty agent prompt on export. (#15312, #15316) - Editable CodeMirror viewer for local files with document highlighting; BM25 search extended to file-backed documents. (#15247, #15298) - Default new Agent-doc files to `.md` and preserve IME composition; refresh folder data on slug switch and dedupe breadcrumb fetches. (#15335, #15427) --- ## 💬 Chat & User Experience - Group-by-status mode for the Topic sidebar; dropped the legacy session→agentId compatibility path from Topic queries. (#15366, #15378) - Restore editor focus after the file picker closes, and close the skill dropdown before navigating to settings. (#15391, #15394) - Strip markdown tokens from fallback Topic titles; keep an open ActionBar popup when hovering another message. (#15303, #15372) - Stabilize home starter loading and stop transliterating model names in the home starter; show artifact source while streaming. (#15310, #15324, #15386) - Group the sidebar spacer with recents and agents. (#15373) --- ## 📊 Analytics, Tasks & Notifications - Token-usage mode on the activity heatmap, backed by a denormalized topic usage/cost rollup. (#15365, #15417, #15425) - Push: new `PushChannel`, receipt cron, and `pushToken` tRPC API. (#15233) - Tasks now support file and image attachments. (#15141) --- ## 🧩 Models & Providers - Support Claude Opus 4.8 and configurable model routing with starters. (#15314, #15384) - MiniMax M3: new model entry and an Anthropic video runtime. (#15380, #15403) - Add `intern-s2-preview` with `thinking_mode`, and `step-3.7-flash` support. (#15308, #15317) - Block disabling the official provider; fix default provider setup in business mode. (#15379, #15382) --- ## 🎨 UI & Modals - Migrate modals to `@lobehub/ui/base-ui` (LOBE-9711 + eval batch), including the create-custom-model and feedback/changelog modals. (#15401, #15416) - Restructure confirmModal title and content across deletion flows; polish the service-model form and migrate its Switch to base-ui. (#15426, #15440) - Wrap the BlueBubbles bridge config into a connection card; update `@lobehub/ui` to v5.15.5. (#15325, #15342) --- ## 🔒 Reliability - Replace hardcoded `session_context` values with template variables in credentials. (#15352) - Point `CHANGELOG_URL` to `/changelog`. (#15428) --- ## 👥 Contributors Huge thanks to **11 contributors** who shipped **88 merged PRs** this cycle. @hezhijie0327 · @qybaihe · @sxjeru · @arvinxx · @Innei · @tjx666 · @lijian · @sudongyuer · @cy948 · @rivertwilight · @AmAzing129 Plus @lobehubbot and renovate[bot] for maintenance. --- **Full Changelog**: v2.2.1...release/weekly-20260604
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
💻 Change Type
🔗 Related Issue
🔀 Description of Change
https://www.minimaxi.com/models/text/m3
已测试验证可用。
可以一并合并下述 pr：
🧪 How to Test
📸 Screenshots / Videos
📝 Additional Information