Skip to content

💄 style: add Kimi K2.6 to LobeHub-hosted card#14006

Merged
tjx666 merged 6 commits into
canaryfrom
feat/kimi-k2-6-lobehub-hosted
Apr 21, 2026
Merged

💄 style: add Kimi K2.6 to LobeHub-hosted card#14006
tjx666 merged 6 commits into
canaryfrom
feat/kimi-k2-6-lobehub-hosted

Conversation

@tjx666

@tjx666 tjx666 commented Apr 21, 2026

Copy link
Copy Markdown
Member

💻 Change Type

  • 💄 style
  • 🐛 fix
  • ♻️ refactor
  • ✅ test

🔗 Related Issue

None.

🔀 Description of Change

Add Kimi K2.6 (released 2026-04-20) to the LobeHub-hosted Moonshot model card and generalize the existing K2.5 runtime plumbing to cover the kimi-k2.x family. Applies supporting cleanups surfaced during review.

Commits in this PR:

  1. 💄 style: add Kimi K2.6 to LobeHub-hosted card — new kimi-k2.6 card (262k ctx, 32k max output, USD pricing 0.95 / 0.16 / 4). Runtime helper generalization: isKimiK25ModelisKimiThinkingToggleModel, getK25ParamsgetK2FamilyParams. Adds runtime tests covering K2.6 on both OpenAI and Anthropic payload builders.
  2. 🐛 fix(moonshot): disable built-in search for Kimi K2.6 LobeHub-hosted card — the kimi- prefix is routed through Moonshot's Anthropic endpoints, which reject the Moonshot OpenAI-format { function: { name: '$web_search' }, type: 'builtin_function' } tool the runtime appends when search is enabled. Align with the self-hosted card (which also omits search). Re-enable once the Anthropic routing channel is verified.
  3. ♻️ refactor(moonshot): clarify kimi-k2.x thinking toggle naming and docs — rename getK2FamilyParamsgetKimiThinkingToggleParams so the helper name matches the predicate name; replace hard-coded kimi-k2.5/kimi-k2.6 enumerations in JSDoc with kimi-k2.x family wording; document the prefix predicate's assumption so future kimi-k2.N additions are checked for contract compatibility.
  4. ✅ test(moonshot): rename K2.5-specific describe/title to K2 family scope — the test describe block and the non-kimi-k2.5 models exclusion case were widened to cover K2.6 but labels still claimed K2.5-only scope.
  5. 💄 style(moonshot): disable older Kimi models by default per add-model rule — keep K2.5/K2.6 as defaults; older K2-0905-preview, K2-turbo-preview, K2-thinking and K2-thinking-turbo cards remain in the bank but are no longer enabled by default.
  6. 🌐 i18n: sync locales — batch i18n sync for all languages.

🧪 How to Test

  • Tested locally — bunx vitest run packages/model-runtime/src/providers/moonshot/index.test.ts (45 tests pass)
  • Added/updated tests

📝 Additional Information

Follow-up once the Anthropic routing channel is verified to accept Moonshot's $web_search builtin_function (or is migrated to Anthropic's native web_search_20250305 server tool): re-enable abilities.search + settings.searchImpl: 'params' on the K2.5 and K2.6 LobeHub-hosted cards.

tjx666 added 6 commits April 21, 2026 10:43
- add kimi-k2.6 model card in aiModels/lobehub/chat/moonshot.ts
- rename K2.5-specific helpers to reflect the wider K2 thinking-toggle
  family (isKimiK25Model -> isKimiThinkingToggleModel, getK25Params ->
  getK2FamilyParams)
- add runtime tests covering K2.6 thinking enabled/disabled on both
  OpenAI and Anthropic payload builders
… card

The LobeHub kimi- prefix routes through Moonshot's Anthropic endpoints
(api.moonshot.cn/anthropic, api.moonshot.ai/anthropic), which reject the
Moonshot OpenAI-format `{ function: { name: '$web_search' }, type:
'builtin_function' }` tool that runtime appends when search is enabled.
Align with the self-hosted card (which also omits search) until the
Anthropic routing channel is verified per add-model skill section 2.1.
- rename getK2FamilyParams to getKimiThinkingToggleParams so helper name
  matches the predicate it pairs with (isKimiThinkingToggleModel) and
  avoids implying coverage of kimi-k2-0905-preview / kimi-k2-turbo-preview
  which use the hyphenated form
- replace hard-coded version enumeration (kimi-k2.5/kimi-k2.6) in JSDoc
  with kimi-k2.x family wording so future K2.N additions don't require
  comment updates
- document the prefix predicate's assumption so reviewers adding future
  kimi-k2.N releases know to verify thinking-toggle contract compatibility
The test describe block and the 'non-kimi-k2.5 models' exclusion case
were widened to cover K2.6 by the previous commits but their labels
still claimed K2.5-only scope. Rename them to reflect the actual
isKimiThinkingToggleModel family contract.
… rule

Follow add-model skill rule "only enable the latest two generations by
default". With K2.6 shipping, K2.5 and K2.6 are the defaults; the older
K2-0905-preview, K2-turbo-preview, K2-thinking and K2-thinking-turbo
cards remain in the bank but are no longer enabled by default.
@vercel

vercel Bot commented Apr 21, 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 21, 2026 3:26am

Request Review

@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.

Sorry @tjx666, you have reached your weekly rate limit of 500000 diff characters.

Please try again later or upgrade to continue using Sourcery

@codecov

codecov Bot commented Apr 21, 2026

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 66.81%. Comparing base (518358b) to head (d2148cd).
⚠️ Report is 1 commits behind head on canary.

Additional details and impacted files
@@            Coverage Diff            @@
##           canary   #14006     +/-   ##
=========================================
  Coverage   66.81%   66.81%             
=========================================
  Files        2100     2100             
  Lines      179130   179131      +1     
  Branches    21895    17687   -4208     
=========================================
+ Hits       119682   119685      +3     
+ Misses      59324    59322      -2     
  Partials      124      124             
Flag Coverage Δ
app 59.40% <ø> (+<0.01%) ⬆️
database 92.25% <ø> (ø)
packages/agent-runtime 79.72% <ø> (ø)
packages/context-engine 83.18% <ø> (ø)
packages/conversation-flow 92.40% <ø> (ø)
packages/file-loaders 87.02% <ø> (ø)
packages/memory-user-memory 74.74% <ø> (ø)
packages/model-bank 99.86% <ø> (ø)
packages/model-runtime 84.22% <100.00%> (+<0.01%) ⬆️
packages/prompts 69.08% <ø> (ø)
packages/python-interpreter 92.90% <ø> (ø)
packages/ssrf-safe-fetch 0.00% <ø> (ø)
packages/utils 87.95% <ø> (ø)
packages/web-crawler 88.66% <ø> (ø)

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

Components Coverage Δ
Store 66.27% <ø> (ø)
Services 51.89% <ø> (ø)
Server 66.78% <ø> (+<0.01%) ⬆️
Libs 51.32% <ø> (ø)
Utils 80.59% <ø> (ø)
🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

@tjx666 tjx666 merged commit c5db823 into canary Apr 21, 2026
31 of 32 checks passed
@tjx666 tjx666 deleted the feat/kimi-k2-6-lobehub-hosted branch April 21, 2026 03:40
@arvinxx arvinxx mentioned this pull request Apr 27, 2026
arvinxx added a commit that referenced this pull request Apr 27, 2026
# 🚀 LobeHub v2.1.53 (20260427)

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

> Introduce Heterogeneous Agent — 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** — 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** — 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** — 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** — One-click pull/push from the branch chip,
ahead/behind badge, and submodule/worktree repo detection. (#14041,
#13980, #13978)
- **Agent Signal package** — 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** — 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** — OpenCode Zen, OpenCode Go, and Azure OpenAI Router
runtime. (#13943, #14064, #13823)
- **Mobile settings overhaul** — Full settings menu and responsive
profile layout for mobile. (#14019)

---

## 🏗️ 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)

---

## 💬 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)

---

## 📱 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)

---

## 🤖 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)

---

## 🖥️ User Experience

- **Onboarding** — 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** — Agent documents promoted as primary workspace
panel; history management and compare workflow; web-crawl docs
associated with agent documents. (#13924, #13725, #13893)
- **cmdk** — 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)

---

## 🔧 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)

---

## 🔒 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)

---

## 👥 Contributors

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

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

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant