✨ feat(editor): implement AI input auto-completion by arvinxx · Pull Request #13458 · lobehub/lobehub

arvinxx · 2026-04-01T02:04:15Z

💻 Change Type

✨ feat

🔗 Related Issue

Fixes LOBE-6586
close #10486

🔀 Description of Change

Implements GitHub Copilot-style ghost text auto-completion in the chat input, powered by @lobehub/editor's ReactAutoCompletePlugin.

System Agent Config:

New inputCompletion: SystemAgentItem in UserSystemAgentConfig
Default: enabled: false, mini model
Settings UI in Service Model page with enable toggle

Prompt Chain (V2 — benchmarked optimal):

Concise system prompt with few-shot examples
Supports conversation context for contextually relevant completions
max_tokens: 100 to keep completions short

Editor Integration:

Conditionally mounts ReactAutoCompletePlugin when enabled
600ms delay before triggering completion
Uses plugin's built-in abortSignal for cancellation
Calls chatService.fetchPresetTaskResult to get completions

Data Flow:

getMessages callback wired through ChatInput store → StoreUpdater → Provider
Conversation page provides dbMessages as context; Home page has no context

Benchmark Results (84 runs, 21 scenarios × 4 models):

Default model: gpt-5.4-mini — 21/21 PASS, ~3.9s latency, best quality stability
Speed option: groq/llama-4-scout — ~3.2s latency, $0.00004/call
Full results: LOBE-6596

🧪 How to Test

Go to Settings → Service Model → Enable "Input Auto-Completion Agent"
Navigate to any chat conversation
Type a partial message (e.g., "How do I implement ") and wait ~1 second
Ghost text should appear in gray after the cursor
Press Tab to accept, or continue typing to dismiss

Tested locally
Added/updated tests
No tests needed

📝 Additional Information

Feature is disabled by default — users must opt-in via settings
Prompt was selected through systematic benchmarking (V2 few-shot beat V1 XML-tags and V3 structured across all models)
10+ models tested; rejected models documented with reasons in benchmark sub-issue LOBE-6596

vercel · 2026-04-01T02:04:21Z

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

Project	Deployment	Actions	Updated (UTC)
lobehub	Ready	Preview, Comment	Apr 2, 2026 5:58pm

sourcery-ai

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

Please try again later or upgrade to continue using Sourcery

lobehubbot · 2026-04-01T02:05:20Z

@canisminor1990 @ONLY-yours - This PR implements AI input auto-completion via the editor's ReactAutoCompletePlugin. It touches the ChatInput editor integration (primary) and settings/system agent config (secondary). Please coordinate on review.

codecov · 2026-04-01T02:08:12Z

Codecov Report

❌ Patch coverage is 24.24242% with 25 lines in your changes missing coverage. Please review.
✅ Project coverage is 66.42%. Comparing base (dd7819b) to head (6dae86f).
⚠️ Report is 3 commits behind head on canary.

Additional details and impacted files

@@            Coverage Diff             @@
##           canary   #13458      +/-   ##
==========================================
- Coverage   66.43%   66.42%   -0.01%     
==========================================
  Files        1976     1977       +1     
  Lines      163601   163634      +33     
  Branches    18709    16511    -2198     
==========================================
+ Hits       108695   108701       +6     
- Misses      54784    54811      +27     
  Partials      122      122

Flag	Coverage Δ
app	`58.08% <85.71%> (-0.01%)`	⬇️
database	`92.57% <ø> (ø)`
packages/agent-runtime	`88.98% <ø> (ø)`
packages/context-engine	`86.51% <ø> (ø)`
packages/conversation-flow	`92.36% <ø> (ø)`
packages/file-loaders	`87.02% <ø> (ø)`
packages/memory-user-memory	`66.68% <ø> (ø)`
packages/model-bank	`99.85% <ø> (ø)`
packages/model-runtime	`84.68% <ø> (ø)`
packages/prompts	`65.80% <7.69%> (-0.69%)`	⬇️
packages/python-interpreter	`92.90% <ø> (ø)`
packages/ssrf-safe-fetch	`0.00% <ø> (ø)`
packages/utils	`90.41% <ø> (ø)`
packages/web-crawler	`88.82% <ø> (ø)`

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

Components	Coverage Δ
Store	`66.55% <100.00%> (+<0.01%)`	⬆️
Services	`49.05% <ø> (ø)`
Server	`65.94% <ø> (-0.01%)`	⬇️
Libs	`51.03% <ø> (ø)`
Utils	`91.01% <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

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: f0263d598a

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".

src/features/Conversation/ChatInput/index.tsx

Adds GitHub Copilot-style ghost text completion to the chat input, powered by a configurable system agent (disabled by default). Key changes: - Add `inputCompletion` system agent config (type, default, selector, i18n) - Create `chainInputCompletion` prompt chain (V2 few-shot, benchmarked) - Mount `ReactAutoCompletePlugin` in InputEditor when enabled - Wire `getMessages` through ChatInput store for conversation context - Add settings UI in Service Model page with enable toggle Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Filter getMessages to use displayMessages (active visible thread) instead of dbMessages (raw DB records including tool messages and inactive branches). Also limit to last 10 user/assistant turns to keep payload small and relevant. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Autocomplete needs the full result before displaying ghost text, so streaming adds unnecessary overhead. Setting stream: false reduces latency by avoiding SSE chunking. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

fetchPresetTaskResult uses fetchSSE internally which cannot handle non-streaming JSON responses, causing the editor to freeze after receiving the completion result. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Autocomplete waits for the full result before displaying ghost text. fetchSSE handles non-streaming responses via its fallback path (response.clone().text()), avoiding SSE chunking overhead. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Call getChatCompletion directly instead of fetchPresetTaskResult to avoid triggering agentDocument.getDocuments on every autocomplete request. Input completion only needs a simple LLM call with the prompt chain, not the full context engineering pipeline. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Use the standard contextEngineering pipeline. The agentDocument overhead will be addressed separately. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

@chriszf

# 🚀 release: 20260407 This release includes **148 commits**. Key updates are below. - **Response API tool execution is more capable and reliable** — Added hosted builtin tools + client-side function tools and improved tool-call streaming/completion behavior. [#13406](#13406) [#13414](#13414) [#13506](#13506) [#13555](#13555) - **Input and composition UX upgraded** — Added AI input auto-completion and multiple chat-input stability fixes. [#13458](#13458) [#13551](#13551) [#13481](#13481) - **Model/provider compatibility improved** — Better Gemini/Google tool schema handling and additional model updates. [#13429](#13429) [#13465](#13465) [#13613](#13613) - **Desktop and CLI reliability improved** — Gateway WebSocket support and desktop runtime upgrades. [#13608](#13608) [#13550](#13550) [#13557](#13557) - **Security hardening continued** — Fixed auth and sanitization risks and upgraded vulnerable dependencies. [#13535](#13535) [#13529](#13529) [#13479](#13479) ### Models & Providers - Added/updated support for `glm-5v-turbo`, GLM-5.1 updates, and qwen3.5-omni series. [#13487](#13487) [#13405](#13405) [#13422](#13422) - Added additional ImageGen providers/models (Wanxiang 2.7 and Keling from Qwen). [#13478](#13478) - Improved Gemini/Google tool schema and compatibility handling across runtime paths. [#13429](#13429) [#13465](#13465) [#13613](#13613) ### Response API & Runtime - Added hosted builtin tools in Response API and client-side function tool execution support. [#13406](#13406) [#13414](#13414) - Improved stream tool-call argument handling and `response.completed` output correctness. [#13506](#13506) [#13555](#13555) - Improved runtime error/context handling for intervention and provider edge cases. [#13420](#13420) [#13607](#13607) ### Desktop App - Bumped desktop dependencies and runtime integrations (`agent-browser`, `electron`). [#13550](#13550) [#13557](#13557) - Simplified desktop release channel setup by removing nightly release flow. [#13480](#13480) ### CLI - Added OpenClaw migration command. [#13566](#13566) - Added local device binding support for `lh agent run`. [#13277](#13277) - Added WebSocket gateway support and reconnect reliability improvements. [#13608](#13608) [#13418](#13418) ### Security - Removed risky `apiKey` fallback behavior in webapi auth path to prevent bypass risk. [#13535](#13535) - Sanitized HTML artifact rendering and iframe sandboxing to reduce XSS-to-RCE risk. [#13529](#13529) - Upgraded nodemailer to v8 to address SMTP command injection advisory. [#13479](#13479) ### Bug Fixes - Fixed image generation model default switch issues. [#13587](#13587) - Fixed subtopic re-fork message scope behavior and agent panel reset edge cases. [#13606](#13606) [#13556](#13556) - Fixed chat-input freeze on paste and mention plugin behavior. [#13551](#13551) [#13415](#13415) - Fixed auth/social sign-in and settings UX edge cases. [#13368](#13368) [#13392](#13392) [#13338](#13338) ### Credits Huge thanks to these contributors: @chriszf @hardy-one @Innei @lijian @neko @OctopusNote @rdmclin2 @rivertwilight @RylanCai @suyua9 @sxjeru @Tsuki @wangyk @WindSpiritSR @yizhuo @YuTengjing @hezhijie0327 @arvinxx

sourcery-ai bot reviewed Apr 1, 2026

View reviewed changes

vercel bot had a problem deploying to Preview April 1, 2026 02:08 Failure

chatgpt-codex-connector bot reviewed Apr 1, 2026

View reviewed changes

src/features/Conversation/ChatInput/index.tsx Outdated Show resolved Hide resolved

vercel bot had a problem deploying to Preview April 1, 2026 02:19 Failure

arvinxx force-pushed the feat/lobe-6586-input-auto-completion branch 4 times, most recently from 6965591 to dad86ae Compare April 1, 2026 07:22

vercel bot deployed to Preview April 1, 2026 07:38 View deployment

vercel bot deployed to Preview April 1, 2026 08:13 View deployment

arvinxx force-pushed the feat/lobe-6586-input-auto-completion branch from b317537 to e2ae00f Compare April 1, 2026 08:16

vercel bot deployed to Preview April 1, 2026 08:33 View deployment

vercel bot deployed to Preview April 1, 2026 10:44 View deployment

arvinxx force-pushed the feat/lobe-6586-input-auto-completion branch from 9e2cebe to e2ae00f Compare April 1, 2026 10:50

vercel bot deployed to Preview April 1, 2026 13:15 View deployment

arvinxx force-pushed the feat/lobe-6586-input-auto-completion branch from d50e988 to aff5013 Compare April 2, 2026 02:41

vercel bot deployed to Preview April 2, 2026 02:52 View deployment

vercel bot deployed to Preview April 2, 2026 04:15 View deployment

vercel bot had a problem deploying to Preview April 2, 2026 08:06 Failure

vercel bot had a problem deploying to Preview April 2, 2026 08:57 Failure

vercel bot had a problem deploying to Preview April 2, 2026 09:51 Failure

arvinxx force-pushed the feat/lobe-6586-input-auto-completion branch 2 times, most recently from 3146e2e to a27edf1 Compare April 2, 2026 16:53

vercel bot had a problem deploying to Preview April 2, 2026 17:18 Failure

arvinxx and others added 3 commits April 3, 2026 01:47

✅ test: update systemAgent snapshot for inputCompletion

28f4e3f

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

arvinxx and others added 6 commits April 3, 2026 01:47

✨ feat: enable input completion by default

dd17cfd

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

🐛 fix: revert stream:false for input completion

035a3c3

fetchPresetTaskResult uses fetchSSE internally which cannot handle non-streaming JSON responses, causing the editor to freeze after receiving the completion result. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

♻️ refactor: revert to fetchPresetTaskResult for input completion

6dae86f

Use the standard contextEngineering pipeline. The agentDocument overhead will be addressed separately. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

arvinxx force-pushed the feat/lobe-6586-input-auto-completion branch from a27edf1 to 6dae86f Compare April 2, 2026 17:47

vercel bot deployed to Preview April 2, 2026 17:58 View deployment

arvinxx merged commit 251e12c into canary Apr 2, 2026
34 checks passed

arvinxx deleted the feat/lobe-6586-input-auto-completion branch April 2, 2026 18:00

nekomeowww mentioned this pull request Apr 7, 2026

🚀 release: 20260407 #13626

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

✨ feat(editor): implement AI input auto-completion#13458

✨ feat(editor): implement AI input auto-completion#13458
arvinxx merged 9 commits intocanaryfrom
feat/lobe-6586-input-auto-completion

arvinxx commented Apr 1, 2026 •

edited

Loading

Uh oh!

vercel bot commented Apr 1, 2026 •

edited

Loading

Uh oh!

sourcery-ai bot left a comment

Uh oh!

lobehubbot commented Apr 1, 2026

Uh oh!

codecov bot commented Apr 1, 2026 •

edited

Loading

Uh oh!

chatgpt-codex-connector bot left a comment

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

arvinxx commented Apr 1, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

💻 Change Type

🔗 Related Issue

🔀 Description of Change

🧪 How to Test

📝 Additional Information

Uh oh!

vercel bot commented Apr 1, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

sourcery-ai bot left a comment

Choose a reason for hiding this comment

Uh oh!

lobehubbot commented Apr 1, 2026

Uh oh!

codecov bot commented Apr 1, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

arvinxx commented Apr 1, 2026 •

edited

Loading

vercel bot commented Apr 1, 2026 •

edited

Loading

codecov bot commented Apr 1, 2026 •

edited

Loading