Skip to content

✨ feat(deepseek): add V4 Flash/Pro cards + reasoning_effort slider#14114

Merged
tjx666 merged 7 commits into
canaryfrom
feat/deepseek-v4
Apr 24, 2026
Merged

✨ feat(deepseek): add V4 Flash/Pro cards + reasoning_effort slider#14114
tjx666 merged 7 commits into
canaryfrom
feat/deepseek-v4

Conversation

@tjx666

@tjx666 tjx666 commented Apr 24, 2026

Copy link
Copy Markdown
Member

πŸ’» Change Type

  • ✨ feat
  • πŸ› fix

πŸ”— Related Issue

N/A β€” model rollout follow-up for DeepSeek V4.

πŸ”€ Description of Change

Adds support for DeepSeek V4 (Flash + Pro) across the model bank, runtime, and UI.

Model cards (packages/model-bank)

  • New deepseek-v4-flash and deepseek-v4-pro entries in both self-hosted (CNY) and LobeHub-hosted (USD) banks.
  • 1M context / 384K max output, function call, reasoning, and thinking extendParam.
  • Per official docs, deepseek-chat and deepseek-reasoner are now compatibility aliases for v4-flash's non-thinking / thinking modes and are slated for deprecation. Marked legacy: true, disabled by default, and repriced to match v4-flash's actual endpoint rates.
  • planCardModels and checkModel now point to deepseek-v4-flash.
  • modelParse keyword list recognizes v4 for automatic ability inference.

Runtime (packages/model-runtime)

  • Extends the existing reasoning_content fallback from deepseek-reasoner only to cover all deepseek-v4-* models unless thinking.type === 'disabled'. Per official docs, follow-up turns with tool calls in thinking mode return HTTP 400 without this payback β€” this patch prevents the regression for V4.

Reasoning effort UI

  • New deepseekV4ReasoningEffort extend param (2 levels: high / max, default high) wired through ExtendParamsType + zod schema + agent chatConfig + resolver mapping to reasoning_effort.
  • New DeepseekV4ReasoningEffortSlider registered in ControlsForm and ExtendParamsSelect with i18n hint.
  • Only high / max are meaningfully distinct per official docs (low/medium β†’ high, xhigh β†’ max), so the slider exposes just the two effective levels.

Reference: https://api-docs.deepseek.com/quick_start/pricing Β· https://api-docs.deepseek.com/guides/thinking_mode

πŸ§ͺ How to Test

  • Tested locally
  • Added/updated tests
  • No tests needed
  1. Select DeepSeek V4 Flash or DeepSeek V4 Pro from the model list.
  2. Confirm the Model Config panel shows both Thinking (OFF/Auto/ON) and Reasoning Effort (high/max) sliders.
  3. Run a simple conversation; then run a tool-call workflow (e.g. artifacts snake game) to exercise multi-turn + thinking + tool calls β€” should not see HTTP 400 on the 2nd turn.
  4. Toggle thinking off, send a message β€” confirm reasoning_content is not forced and the API accepts it.

πŸ“Έ Screenshots / Videos

N/A β€” attach before/after of the Model Config panel when reviewing.

πŸ“ Additional Information

Breaking changes for downstream users

  • Existing conversations using deepseek-chat / deepseek-reasoner continue to work. The model IDs stay resolvable; they are hidden from the default model picker via enabled: false + legacy: true.
  • Their pricing in the model bank was updated to match v4-flash rates since the upstream endpoint now bills at v4-flash rates for these aliases.

Runtime behavior

  • shouldForceAssistantReasoningContent now also triggers for deepseek-v4-* unless the caller explicitly disables thinking. API silently ignores reasoning_content outside thinking mode, so this is a conservative expansion.

tjx666 added 3 commits April 24, 2026 12:26
Adds `deepseek-v4-flash` and `deepseek-v4-pro` to both the self-hosted
(CNY) and LobeHub-hosted (USD) DeepSeek model banks, with 1M context,
384K max output, and `thinking` extendParam for mode toggling.

Marks the V3.2 aliases `deepseek-chat` and `deepseek-reasoner` as
legacy and disables them by default β€” per official docs they are now
compatibility aliases for v4-flash's non-thinking/thinking modes and
are billed at v4-flash rates, so their pricing is updated accordingly.

Also flips `checkModel` + LobeHub `planCardModels` to v4-flash and
teaches the deepseek model-parser to infer abilities from `v4` keyword.

Ref: https://api-docs.deepseek.com/quick_start/pricing
…thinking mode

DeepSeek V4 defaults to thinking=enabled. Per official docs, follow-up
turns with tool calls MUST pass back `reasoning_content` on assistant
messages or the API returns HTTP 400.

Extends the existing `deepseek-reasoner` fallback to cover `deepseek-v4-*`
models unless the caller explicitly disables thinking.

Ref: https://api-docs.deepseek.com/guides/thinking_mode#tool-calls
Adds a new `deepseekV4ReasoningEffort` extend param (values `high` / `max`,
default `high`) wired through the full stack: type union + zod schema,
agent chatConfig field, resolver mapping to `reasoning_effort`, a 2-level
slider component, ControlsForm + ExtendParamsSelect registration, i18n
hint, and enabled on both deepseek-v4-flash and deepseek-v4-pro cards.

Only `high` and `max` are meaningfully distinct per official docs β€”
`low/medium` are silently mapped to `high`, `xhigh` to `max` β€” so the
slider exposes just the two effective levels instead of mimicking the
4-level OpenAI effort scale.

Ref: https://api-docs.deepseek.com/guides/thinking_mode#thinking-mode-toggle-and-effort-control

@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

@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 5:41am

Request Review

@dosubot dosubot Bot added size:L This PR changes 100-499 lines, ignoring generated files. feature:agent Assistant/Agent configuration and behavior provider:deepseek labels Apr 24, 2026

@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.

πŸ’‘ Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: f25f8e6b65

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 πŸ‘.

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

description:
'Compatibility alias for DeepSeek V4 Flash non-thinking mode. Slated for deprecation β€” use deepseek-v4-flash instead.',
displayName: 'DeepSeek V3.2 (Legacy alias)',
enabled: false,

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 Keep legacy DeepSeek aliases enabled

Setting these compatibility aliases to enabled: false makes them disappear from enabledAiModels, which is what capability selectors use (src/store/aiInfra/slices/aiModel/selectors.ts:44-50). As a result, existing agents still pinned to deepseek-chat/deepseek-reasoner are treated as lacking function-call support, and the Tools action is disabled (src/features/ChatInput/ActionBar/Tools/index.tsx:26-33), breaking tool-call workflows despite the stated backward-compatibility goal.

Useful? React with πŸ‘Β / πŸ‘Ž.

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

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

Good catch, taken. Kept enabled: true on both aliases and retained only the legacy: true marker + displayName suffix so tool-call capability continues to resolve for existing agents via enabledAiModels. Fixed in afe7eed.

…xisting agents

The previous commit disabled `deepseek-chat` and `deepseek-reasoner`
via `enabled: false`, which filters them out of `enabledAiModels` and
breaks capability selectors. Agents still pinned to these IDs were
treated as lacking function-call support, disabling the Tools action
in ChatInput.

Keep `legacy: true` so future UI surfaces can surface deprecation
without breaking backward compatibility.

Ref: #14114 (comment)
@codecov

codecov Bot commented Apr 24, 2026

Copy link
Copy Markdown

Codecov Report

❌ Patch coverage is 97.29730% with 1 line in your changes missing coverage. Please review.
βœ… Project coverage is 67.33%. Comparing base (1958a59) to head (365e3d1).
⚠️ Report is 1 commits behind head on canary.

Additional details and impacted files
@@            Coverage Diff            @@
##           canary   #14114     +/-   ##
=========================================
  Coverage   67.33%   67.33%             
=========================================
  Files        2155     2156      +1     
  Lines      184805   184836     +31     
  Branches    22647    18308   -4339     
=========================================
+ Hits       124431   124463     +32     
+ Misses      60249    60248      -1     
  Partials      125      125             
Flag Coverage Ξ”
app 60.14% <96.29%> (+<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% <100.00%> (ΓΈ)
packages/model-runtime 84.07% <100.00%> (+<0.01%) ⬆️
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 51.84% <100.00%> (+0.05%) ⬆️
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 13:12
…h reality

The `deepseek-chat` and `deepseek-reasoner` aliases hit v4-flash on the
backend, but our model bank still advertised V3.2-era capacity (64K–128K
context, 8K–64K output), artificially capping what the UI allowed users
on these IDs to send and receive.

- Bump `contextWindowTokens` to 1,000,000 and `maxOutput` to 384,000 to
  match the actual endpoint capability.
- Rename displayName from "DeepSeek V3.2 (Legacy alias)" to
  "DeepSeek V4 Flash Non-thinking (legacy alias)" / "DeepSeek V4 Flash
  Thinking (legacy alias)" so the model picker names the real backing
  model.

No `settings.extendParams` added β€” aliases pin a fixed thinking mode
upstream, so exposing thinking / effort sliders would be misleading.
Rename legacy alias displayName to retain the original "DeepSeek V3.2"
prefix users recognize, followed by a routing hint:

  "DeepSeek V3.2 (routes to V4 Flash)"
  "DeepSeek V3.2 Thinking (routes to V4 Flash)"

This way existing agents still show the name they were created with,
while the suffix makes the actual backing model explicit.
@tjx666 tjx666 merged commit 0b57c9d into canary Apr 24, 2026
33 of 34 checks passed
@tjx666 tjx666 deleted the feat/deepseek-v4 branch April 24, 2026 05:37
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

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