Skip to content

✨ feat: add MiMo-V2.5 and MiMo-V2.5-Pro model cards#14089

Merged
tjx666 merged 4 commits into
canaryfrom
feat/add-mimo-v2-5
Apr 24, 2026
Merged

✨ feat: add MiMo-V2.5 and MiMo-V2.5-Pro model cards#14089
tjx666 merged 4 commits into
canaryfrom
feat/add-mimo-v2-5

Conversation

@tjx666

@tjx666 tjx666 commented Apr 23, 2026

Copy link
Copy Markdown
Member

πŸ’» Change Type

  • ✨ feat
  • πŸ› fix

πŸ”— Related Issue

N/A

πŸ”€ Description of Change

Add Xiaomi MiMo-V2.5 series (released 2026-04-22) to the model bank,
and fix a stale keyword match in the dynamic model-list detector.

New model cards (both self-hosted and LobeHub-hosted):

  • mimo-v2.5-pro: 1T total / 42B active, 1M context, text agentic
    flagship. Priced at USD 1 / 3 (CNY 7 / 21). Flat pricing replaces
    V2 Pro's 256k-tiered scheme per Xiaomi's 2026-04-23 Token Plan
    announcement.
  • mimo-v2.5: native omni-modal Agent foundation (image / video /
    audio / text), 1M context. Priced at USD 0.4 / 2 (CNY 2.8 / 14).

Previous-generation V2 Pro / Omni / Flash remain enabled: true per
the "latest two generations" rule.

Runtime: no API schema changes β€” thinking: { type } request
shape, reasoning_content response parsing, OpenAI-compatible tools,
and keyword-based routing all continue to work unchanged. New model
IDs are auto-picked up by the existing mimo keyword match.

LobeHub-hosted cards disable built-in search (search: false,
no searchImpl) to match the current router-proxy compatibility β€”
the proxy channel still rejects provider-specific chat.completions
search payloads.

modelParse fix: visionKeywords: ['omni'] could not infer
vision for dynamically-fetched mimo-v2.5 (natively omni-modal).
Added a regex matcher re:^mimo-v2\.5$ so non-pro v2.5 is covered
while mimo-v2.5-pro (text-only) remains excluded.

πŸ§ͺ How to Test

  • Tested locally (modelParse tests: 62 passed)
  • Added/updated tests (new v2.5 cases in modelParse.test.ts)
  • No tests needed

πŸ“ Additional Information

Cache-read pricing is inferred from the V2-Pro / V2-Omni 20% ratio
(Xiaomi did not publish official cache numbers for V2.5 yet); should
be reconciled with billing before GA.

@vercel

vercel Bot commented Apr 23, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
lobehub Ready Ready Preview, Comment Apr 24, 2026 3:56am

Request Review

@dosubot dosubot Bot added the size:L This PR changes 100-499 lines, ignoring generated files. label Apr 23, 2026

@sourcery-ai sourcery-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.

We've reviewed this pull request using the Sourcery rules engine

@codecov

codecov Bot commented Apr 23, 2026

Copy link
Copy Markdown

Codecov Report

βœ… All modified and coverable lines are covered by tests.
βœ… Project coverage is 67.33%. Comparing base (a18569c) to head (4c5858c).
⚠️ Report is 1 commits behind head on canary.

Additional details and impacted files
@@            Coverage Diff             @@
##           canary   #14089      +/-   ##
==========================================
- Coverage   67.33%   67.33%   -0.01%     
==========================================
  Files        2155     2155              
  Lines      184805   184805              
  Branches    22646    19085    -3561     
==========================================
- Hits       124433   124431       -2     
- Misses      60247    60249       +2     
  Partials      125      125              
Flag Coverage Ξ”
app 60.13% <ΓΈ> (-0.01%) ⬇️
database 92.23% <ΓΈ> (ΓΈ)
packages/agent-runtime 79.82% <ΓΈ> (ΓΈ)
packages/context-engine 83.10% <ΓΈ> (ΓΈ)
packages/conversation-flow 92.40% <ΓΈ> (ΓΈ)
packages/file-loaders 87.02% <ΓΈ> (ΓΈ)
packages/memory-user-memory 74.74% <ΓΈ> (ΓΈ)
packages/model-bank 99.89% <ΓΈ> (ΓΈ)
packages/model-runtime 84.07% <100.00%> (ΓΈ)
packages/prompts 70.14% <ΓΈ> (ΓΈ)
packages/python-interpreter 92.90% <ΓΈ> (ΓΈ)
packages/ssrf-safe-fetch 0.00% <ΓΈ> (ΓΈ)
packages/utils 88.41% <ΓΈ> (ΓΈ)
packages/web-crawler 88.66% <ΓΈ> (ΓΈ)

Flags with carried forward coverage won't be shown. Click here to find out more.

Components Coverage Ξ”
Store 67.17% <ΓΈ> (ΓΈ)
Services 51.79% <ΓΈ> (ΓΈ)
Server 66.60% <ΓΈ> (-0.01%) ⬇️
Libs 52.50% <ΓΈ> (ΓΈ)
Utils 80.09% <ΓΈ> (ΓΈ)
πŸš€ New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • πŸ“¦ JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

tjx666 added 2 commits April 24, 2026 10:27
Add Xiaomi MiMo-V2.5 series released on 2026-04-22:

- mimo-v2.5-pro: 1T / 42B active, 1M context, text agentic flagship
  (USD 1 / 3, CNY 7 / 21), flat pricing replaces V2 Pro's context-tiered scheme
- mimo-v2.5: native omni-modal Agent (image, video, audio, text),
  1M context (USD 0.4 / 2, CNY 2.8 / 14)

Both self-hosted and LobeHub-hosted cards are added. LobeHub-hosted
cards disable built-in search to match current router-proxy compatibility.
visionKeywords only matched the literal 'omni' substring, so users
fetching the model list dynamically from Xiaomi's API would not get
vision inferred for mimo-v2.5 (natively omni-modal). Add a regex
matcher scoped to the non-pro v2.5 id so mimo-v2.5-pro (text-only)
stays excluded.
V2.5 API pricing still uses 256K/1M context tiers on the per-token
API endpoint, matching V2-Pro's scheme. The flat-rate removal from
the April 2026 announcement only applies to the Token Plan Credits
subscription, not to per-token API billing.

Fix mimo-v2.5-pro and mimo-v2.5 cards in both self-hosted and
LobeHub-hosted banks to use tiered pricing per
platform.xiaomimimo.com/docs/pricing:

- mimo-v2.5-pro: CNY 7/14, 1.4/2.8, 21/42 | USD 1/2, 0.2/0.4, 3/6
- mimo-v2.5:     CNY 2.8/5.6, 0.56/1.12, 14/28 | USD 0.4/0.8, 0.08/0.16, 2/4
Add a short header comment on the LobeHub-hosted Xiaomi MiMo card
pointing to the authoritative /docs/pricing URL (SPA β€” fetch via
devtools MCP, not WebFetch) and flagging that Token Plan / Credits
subscription billing is separate from per-token API billing. The
latter keeps 0-256K / 256K-1M context tiers even when the former
drops its multiplier.
@tjx666 tjx666 merged commit 1958a59 into canary Apr 24, 2026
30 of 32 checks passed
@tjx666 tjx666 deleted the feat/add-mimo-v2-5 branch April 24, 2026 03:51
arvinxx added a commit that referenced this pull request Apr 27, 2026
# πŸš€ LobeHub v2.1.53 (20260427)

**Release Date:** April 27, 2026
**Since v2.1.52:** 194 merged PRs Β· 17 contributors

> Introduce Heterogeneous Agent β€” Claude Code and Codex run as
first-class desktop runtimes, paired with a new Agent Signal package,
sharper desktop UX, and a wave of flagship model additions.

---

## ✨ Highlights

- **Introduce Heterogeneous Agent** β€” Claude Code and Codex run as
first-class desktop agents: subagent rendering, partial-message
streaming, multi-turn resume, terminal error surfacing, rich tool
inspectors, and runtime polish. (#14162, #13754, #14067, #14001, #13970,
#13942)
- **Screen capture & Quick Chat tray** β€” New desktop screen capture
overlay (macOS permission-gated) with Quick Chat tray and upload
pipeline improvements; chat input auto-focuses on overlay mount.
(#13818, #14097, #14105)
- **Desktop topic & tab UX** β€” Dedicated topic popup window with
cross-window sync, Cmd+W/Cmd+T tab shortcuts, TabBar polish, recent
working directories expanded to 20, and human approval notifications.
(#13957, #13983, #13972, #14036, #14092)
- **Git workflow built-in** β€” One-click pull/push from the branch chip,
ahead/behind badge, and submodule/worktree repo detection. (#14041,
#13980, #13978)
- **Agent Signal package** β€” New `@lobechat/agent-signal` runtime for
dynamic memory feedback signals, with OTel metrics and self-iteration in
Lab. (#14157, #14170, #14159, #14169, #14187)
- **New models** β€” Claude Opus 4.7 with `xhigh` effort tier, GPT-5.5,
DeepSeek V4 Flash/Pro with reasoning slider, Kimi K2.6, MiMo-V2.5/Pro,
gpt-image-2, Qwen3.6 Flash/Plus, and Pixverse-c1. (#13903, #14147,
#14114, #14004, #14089, #14039, #13923)
- **New providers** β€” OpenCode Zen, OpenCode Go, and Azure OpenAI Router
runtime. (#13943, #14064, #13823)
- **Mobile settings overhaul** β€” Full settings menu and responsive
profile layout for mobile. (#14019)

---

## πŸ—οΈ Heterogeneous Agent

- Claude Code runtime, working-directory awareness, and sidebar polish.
(#13970)
- CC subagent rendering with persistent streamed text; parallel-tool
orphan fix. (#14001, #13968, #14024)
- Per-step usage persisted to each step assistant message. (#13964)
- Per-phase workflow expand defaults; full-expand toggle with
three-level expansion. (#14171, #13906)
- Hetero-mode actions bar; tool inspector polish. (#13963, #14034,
#14030)
- Codex desktop integration with rich tool rendering and devtools
preview. (#14067, #14100)
- Codex terminal error surfacing and CLI output tracing. (#14166)
- Tighten `isCanUseVision` default and add aggregator fallback. (#14172)
- Persist `ccSessionId` in topic metadata for CC multi-turn resume.
(#13902)
- CC account card, topic filter, and integration polish. (#13955,
#13942, #13950)
- Token-level deltas streamed via `--include-partial-messages`. (#13929)

---

## 🧠 Agent Signal & Self-Iteration

- New `@lobechat/agent-signal` package with dynamic feedback signals.
(#14157)
- AgentSignalRuntime wired through agent-tracing and observability-otel
metrics. (#14170, #14159)
- Self-iteration feature flag added to Lab; front-side flag check.
(#14169, #14186)
- Signal policy for receiving memory feedback dynamically. (#14187)

---

## πŸ’¬ Conversation

- Queue follow-up sends during running CC turns. (#14179)
- Persist per-topic chat scroll position; pin user message + fold long
messages. (#14191, #14056)
- Inline resend when editing last user message. (#14080)
- Disable first-block markdown streaming to prevent flicker. (#14193,
#13904)
- Prevent Markdown stream replay when vlist remounts streaming items.
(#14086)
- Stop repinning after manual scroll; unify scroll-to-user + spacer
hooks. (#14099, #14132)

---

## πŸ“± Platforms & Integrations

### Desktop / Electron

- Screen capture overlay, Quick Chat tray, and upload pipeline
improvements. (#13818)
- macOS permission gate for screen capture; auto-focus chat panel input.
(#14097, #14105)
- Dedicated topic popup window with cross-window sync. (#13957)
- TabBar polish: `+` button for new topic, dark theme blend, close icon
by default. (#13972, #14203, #13973)
- Recent working directories expanded from 5 to 20; submodule/worktree
repo detection. (#14036, #13978)
- Cmd+W / Cmd+T tab shortcuts and global shortcut consolidation.
(#13983, #13880)
- Linux icon configuration; human approval desktop notifications.
(#14042, #14092)

### Git Workflow

- One-click pull/push from branch chip; ahead/behind badge with
refactored GitCtr. (#14041, #13980)

### Mobile

- Full settings menu and responsive profile layout. (#14019)
- Agent route added to mobile router; mobile agent topic route
registered. (#14103, #14158)
- Session list skeleton row layout corrected. (#14040)

### Bot / Messaging

- DM strategy support; bot emoji and markdown render optimization.
(#14201, #14091, #14140)
- Slack webhook fix; bot platform setup guide reference. (#14052,
#14121)

---

## πŸ€– Models & Providers

### New models

- **Claude Opus 4.7** with `xhigh` effort tier; strip temperature/top_p.
(#13903, #13909)
- **GPT-5.5**. (#14147)
- **DeepSeek V4** Flash/Pro cards with reasoning slider; cache-hit and
Pro discount pricing. (#14114, #14209, #14196, #14131)
- **Kimi K2.6** model with LobeHub-hosted card. (#14004, #14006)
- **MiMo-V2.5 / V2.5-Pro**. (#14089)
- **gpt-image-2**, **Qwen3.6 Flash/Plus**, **Pixverse-c1**. (#14039,
#13923)

### New providers

- **OpenCode Zen** and **OpenCode Go** with env-var support. (#13943,
#14064)
- **Azure OpenAI Router** runtime support. (#13823)
- Model alias mapping for image and video runtimes. (#13896)
- Seedance video models migrated to Dreamina. (#14144)

### Runtime reliability

- Sanitize invalid tool_call arguments to unbreak strict providers.
(#14033)
- Tolerate null `function.name` in streaming tool_call deltas. (#14139)
- Preserve Gemini 3 `thoughtSignature` in `call_tools_batch`
normalization. (#14032)
- Downgrade `image_url` parts when target model lacks vision. (#14029)
- Preserve Cloudflare provider error context. (#14136)
- Use `safety_identifier` for OpenAI Responses API. (#14148)
- Unwrap underlying PG error in `formatErrorEventData`. (#14038)

---

## πŸ–₯️ User Experience

- **Onboarding** β€” Preset agent naming suggestions, structured hunk ops
for `updateDocument`, persona analytics snapshot, footer promotion
pipeline, wrap-up button. (#13931, #13989, #13930, #13853, #13934)
- **Document workflow** β€” Agent documents promoted as primary workspace
panel; history management and compare workflow; web-crawl docs
associated with agent documents. (#13924, #13725, #13893)
- **cmdk** β€” Agent identity surfaced on topic search results;
topic/message search scoped to current agent. (#14204, #13960)
- **Floating chat panel** and workspace improvements. (#13887)
- **Topic completion status** with dropdown action and filter. (#14005)

---

## πŸ”§ Tooling

- Redis-backed feature flag provider for runtime config. (#14098)
- Vite upgraded to 8.0.0 with Rolldown strict execution order. (#12720,
#14058)
- `@lobechat/model-bank` automated npm release with provenance. (#14015,
#14017, #14018)
- Skill activation fallback when `activateTools` cannot find identifier.
(#14010)
- Cron tool: timezone and existing jobs injected into system prompt;
clarified `lobe-gtd` and `lobe-cron` descriptions. (#14012, #14013)

---

## πŸ”’ Security & Reliability

- **Security:** uuid bumped to v14 (advisory). (#14083)
- **Security:** validate avatar URL and scope old-avatar deletion to
owner. (#13982)
- **Security:** clear OIDC sessions on better-auth signout; return 401
(not 500) for expired OIDC JWT. (#13916, #14014)
- **Reliability:** scope pending-approval check to current assistant
turn. (#14182)
- **Reliability:** sanitize heterogeneous-agent attachment cache
filenames. (#13937)
- **Reliability:** reduce subagent task status error noise. (#14026)

---

## πŸ‘₯ Contributors

Huge thanks to **17 contributors** who shipped **194 merged PRs** this
week.

@hardy Β· @shaun0927 Β· @hezhijie0327 Β· @sxjeru Β· @arvinxx Β· @Innei Β·
@tjx666 Β· @lijian Β· @neko Β· @rdmclin2 Β· @AmAzing129 Β· @sudongyuer Β·
@CanisMinor Β· @rivertwilight

Plus @lobehubbot and renovate[bot] for maintenance.

---

**Full Changelog**:
v2.1.52...v2.1.53
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