Skip to content

🐛 fix: default DeepSeek V4 reasoning control#14131

Merged
tjx666 merged 3 commits into
canaryfrom
fix/deepseek-v4-reasoning-default
Apr 24, 2026
Merged

🐛 fix: default DeepSeek V4 reasoning control#14131
tjx666 merged 3 commits into
canaryfrom
fix/deepseek-v4-reasoning-default

Conversation

@tjx666

@tjx666 tjx666 commented Apr 24, 2026

Copy link
Copy Markdown
Member

💻 Change Type

  • ✨ feat
  • 🐛 fix
  • ♻️ refactor
  • 💄 style
  • 👷 build
  • ⚡️ perf
  • ✅ test
  • 📝 docs
  • 🔨 chore

🔗 Related Issue

Related to #14117

🔀 Description of Change

  • Add model-level extend parameter options for enableReasoning defaults and budget emission.
  • Configure DeepSeek V4 Flash/Pro model cards to default reasoning on without sending thinking.budget_tokens.
  • Apply the same DeepSeek V4 reasoning control settings to LobeHub provider model cards.
  • Preserve explicit user disable behavior while allowing unset chat config to follow model defaults.
  • Remove default enablement from DeepSeek legacy alias model cards.

🧪 How to Test

  • Tested locally
  • Added/updated tests
  • No tests needed
bunx vitest run --silent='passed-only' 'src/services/chat/mecha/modelParamsResolver.test.ts'
bunx vitest run --silent='passed-only' 'src/store/aiInfra/slices/aiModel/selectors.test.ts'
bunx prettier --check 'packages/model-bank/src/aiModels/lobehub/chat/deepseek.ts' 'packages/model-bank/src/aiModels/deepseek.ts' 'packages/model-bank/src/types/aiModel.ts' 'src/features/ModelSwitchPanel/components/ControlsForm/ControlsForm.tsx' 'src/services/chat/mecha/modelParamsResolver.test.ts' 'src/services/chat/mecha/modelParamsResolver.ts' 'src/store/aiInfra/slices/aiModel/selectors.test.ts' 'src/store/aiInfra/slices/aiModel/selectors.ts' 'packages/const/src/settings/agent.ts'
git diff --check

Note: bun run type-check currently fails in the downstream cloud overlay with pre-existing errors in ../packages/business/model-runtime/src/router-runtime-options.ts and a missing @/server/services/routeAttemptLog module.

📸 Screenshots / Videos

Before After
N/A N/A

📝 Additional Information

DeepSeek V4 official behavior defaults thinking mode to enabled. This change lets model cards express that default without changing the global reasoning default for every provider.

@vercel

vercel Bot commented Apr 24, 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 1:08pm

Request Review

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

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

Please try again later or upgrade to continue using Sourcery

@dosubot dosubot Bot added feature:agent Assistant/Agent configuration and behavior provider:deepseek labels Apr 24, 2026
@codecov

codecov Bot commented Apr 24, 2026

Copy link
Copy Markdown

Codecov Report

❌ Patch coverage is 95.45455% with 2 lines in your changes missing coverage. Please review.
✅ Project coverage is 67.29%. Comparing base (421427f) to head (93dbacb).
⚠️ Report is 2 commits behind head on canary.

Additional details and impacted files
@@           Coverage Diff           @@
##           canary   #14131   +/-   ##
=======================================
  Coverage   67.28%   67.29%           
=======================================
  Files        2157     2157           
  Lines      185062   185092   +30     
  Branches    22662    22673   +11     
=======================================
+ Hits       124522   124552   +30     
  Misses      60415    60415           
  Partials      125      125           
Flag Coverage Δ
app 60.09% <95.45%> (+<0.01%) ⬆️
database 92.23% <ø> (ø)
packages/agent-runtime 79.82% <ø> (ø)
packages/context-engine 83.10% <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 99.89% <ø> (ø)
packages/model-runtime 84.07% <ø> (ø)
packages/prompts 70.14% <ø> (ø)
packages/python-interpreter 92.90% <ø> (ø)
packages/ssrf-safe-fetch 0.00% <ø> (ø)
packages/utils 88.41% <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 67.18% <100.00%> (+<0.01%) ⬆️
Services 52.05% <94.73%> (+0.20%) ⬆️
Server 66.40% <ø> (ø)
Libs 52.50% <ø> (ø)
Utils 80.09% <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.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: aef912035b

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Comment thread src/services/chat/mecha/modelParamsResolver.ts Outdated
@tjx666

tjx666 commented Apr 24, 2026

Copy link
Copy Markdown
Member Author

@hezhijie0327 This has been handled here.


This comment was translated by Claude.

Original Content

@hezhijie0327 这里处理了

@tjx666

tjx666 commented Apr 24, 2026

Copy link
Copy Markdown
Member Author

@codex review

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 544de5a660

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Comment thread src/features/ModelSwitchPanel/components/ControlsForm/ControlsForm.tsx Outdated
@tjx666 tjx666 force-pushed the fix/deepseek-v4-reasoning-default branch 2 times, most recently from d467953 to bcc564f Compare April 24, 2026 11:14
@tjx666

tjx666 commented Apr 24, 2026

Copy link
Copy Markdown
Member Author

@codex review

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: bcc564f806

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Comment thread src/features/ModelSwitchPanel/components/ControlsForm/ControlsForm.tsx Outdated
@tjx666 tjx666 force-pushed the fix/deepseek-v4-reasoning-default branch from bcc564f to 3e14b23 Compare April 24, 2026 11:33
@tjx666 tjx666 force-pushed the fix/deepseek-v4-reasoning-default branch from 3e14b23 to 88610a5 Compare April 24, 2026 11:41
@tjx666

tjx666 commented Apr 24, 2026

Copy link
Copy Markdown
Member Author

@codex review

@tjx666 tjx666 force-pushed the fix/deepseek-v4-reasoning-default branch from 88610a5 to 93dbacb Compare April 24, 2026 11:49

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 88610a53c9

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

@tjx666 tjx666 force-pushed the fix/deepseek-v4-reasoning-default branch from 6d46443 to dbc3741 Compare April 24, 2026 12:17
@tjx666

tjx666 commented Apr 24, 2026

Copy link
Copy Markdown
Member Author

@codex review

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: dbc374191b

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

chatConfig: LobeAgentChatConfig,
defaultValue?: boolean,
): boolean | undefined => {
if (Object.hasOwn(chatConfig, 'enableReasoning')) return chatConfig.enableReasoning;

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Treat legacy enableReasoning: false as unset

This short-circuit breaks migration for existing agents created before this change: historically DEFAULT_AGENT_CONFIG.chatConfig persisted enableReasoning: false, while DeepSeek V4 used thinking. After this commit switched V4 to enableReasoning, the hasOwn check returns false immediately and never reads legacy thinking, so prior thinking: 'enabled' preferences (or previous default-on V4 behavior when thinking was unset) are now forced to thinking.type = 'disabled' at runtime. That silently flips behavior for existing users unless they manually re-save the new switch.

Useful? React with 👍 / 👎.

@tjx666 tjx666 merged commit 9b6a603 into canary Apr 24, 2026
31 of 32 checks passed
@tjx666 tjx666 deleted the fix/deepseek-v4-reasoning-default branch April 24, 2026 12:46
@dosubot dosubot Bot mentioned this pull request Apr 25, 2026
8 tasks
@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

feature:agent Assistant/Agent configuration and behavior provider:deepseek 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