Skip to content

fix: improve /model --fast description clarity#3077

Merged
tanzhenxin merged 1 commit into
QwenLM:mainfrom
wenshao:fix/model-fast-description-clarity
Apr 10, 2026
Merged

fix: improve /model --fast description clarity#3077
tanzhenxin merged 1 commit into
QwenLM:mainfrom
wenshao:fix/model-fast-description-clarity

Conversation

@wenshao

@wenshao wenshao commented Apr 10, 2026 •
edited
Loading

Copy link
Copy Markdown
Collaborator

Motivation

Users reported that the /model --fast description "Set fast model for background tasks" is unclear — they don't understand what "fast model" or "background tasks" means. Additionally, /model → Tab → Enter accidentally triggers --fast mode instead of opening the model selection dialog, breaking the expected workflow.

用户反馈 /model --fast 的描述"设置后台任务的快速模型"含义不清——不理解"快速模型"和"后台任务"具体指什么。此外，输入 /model → Tab → Enter 会误触 --fast 模式，而非打开模型选择对话框，与预期操作习惯不符。

Changes

1. Clarify description text (11 files — mostly i18n sync)

Replace vague wording with specific feature names across code, 6 i18n locales, 3 docs, and VS Code schema:

Location Before After
Completion hint Set fast model for background tasks Set a lighter model for prompt suggestions and speculative execution
Settings description Model for background tasks (suggestion generation, speculation)... Model used for generating prompt suggestions and speculative execution...
Example model qwen3.5-flash qwen3-coder-flash

2. Fix accidental --fast activation (1 file)

modelCommand.ts: '--fast'.startsWith(partialArg) matches empty string, so Tab-completing /model immediately shows --fast as the only suggestion, and Enter selects it.

Fix: partialArg && '--fast'.startsWith(partialArg) — only suggest --fast when the user starts typing (e.g. -, --f).

Test plan

  • modelCommand.test.ts — 8/8 passed
  • /model → Tab → Enter → opens model dialog (no longer triggers --fast)
  • /model → Tab → type -- → Tab → shows --fast completion
  • /model --fast → opens fast model selection dialog

🤖 Generated with Claude Code

@wenshao @claude
fix: improve /model --fast description clarity and prevent accidental…
f7bad4a 
… activation

Replace vague "background tasks" with specific "prompt suggestions and speculative
execution" in the --fast flag description across all i18n locales, docs, and VS Code
schema. Update example model name from qwen3.5-flash to qwen3-coder-flash. Also fix
completion logic to require a non-empty partial arg before suggesting --fast, preventing
Tab+Enter from accidentally entering fast model mode.

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

github-actions Bot commented Apr 10, 2026

Copy link
Copy Markdown
Contributor

📋 Review Summary

This PR improves the clarity of the /model --fast command description across all i18n locales, documentation, and VS Code schema. It replaces vague "background tasks" terminology with specific "prompt suggestions and speculative execution", updates the example model name, and fixes a completion logic bug. The changes are well-tested and consistent across all files.

🔍 General Feedback

  • Consistency: Excellent attention to updating all 6 i18n locales, documentation files, and schema files in sync
  • Scope: The PR appropriately addresses both documentation clarity and a functional bug in completion logic
  • Testing: Test file shows 8/8 tests passing; the test plan is clearly documented in the PR body
  • Positive: The completion logic fix (partialArg && check) is a subtle but important improvement preventing accidental fast model activation

🎯 Specific Feedback

🟢 Medium

  • File: packages/cli/src/ui/commands/modelCommand.ts:24 - The completion logic change from if ('--fast'.startsWith(partialArg)) to if (partialArg && '--fast'.startsWith(partialArg)) is good, but consider adding a comment explaining why the empty string case should be excluded. This prevents the "Tab+Enter accidentally enters fast model mode" issue, but the reasoning isn't obvious to future maintainers.

🔵 Low

  • File: packages/cli/src/ui/commands/modelCommand.test.ts - The existing tests don't cover the new completion logic or the --fast flag behavior. Consider adding tests for:

    • completion() with empty string (should return null)
    • completion() with --f (should suggest --fast)
    • completion() with --fast (should suggest --fast)
    • action() with --fast flag (both with and without model name)

  • File: packages/cli/src/ui/commands/modelCommand.ts:26-31 - The description text in completion could potentially be extracted to i18n keys for consistency with the rest of the file (though it is already wrapped in t()).

✅ Highlights

  • Comprehensive i18n coverage: All 6 locales (de, en, ja, pt, ru, zh) were updated consistently
  • Clear PR description: The summary and test plan are well-documented with checkboxes
  • Model name update: Updating from qwen3.5-flash to qwen3-coder-flash keeps examples current
  • Bug fix: The completion logic fix prevents accidental activation of fast model mode via Tab+Enter
  • Documentation alignment: All documentation files (settings.md, commands.md, followup-suggestions.md) are synchronized with the code changes

@tanzhenxin tanzhenxin added type/bug Something isn't working as expected and removed type/bug Something isn't working as expected labels Apr 10, 2026
tanzhenxin
tanzhenxin approved these changes Apr 10, 2026
View reviewed changes

@tanzhenxin tanzhenxin left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

LGTM — clean fix and thorough i18n coverage.

@tanzhenxin tanzhenxin merged commit 5482044 into QwenLM:main Apr 10, 2026
14 of 15 checks passed
@wenshao wenshao mentioned this pull request Apr 10, 2026
Merged
1 task
euxaristia pushed a commit to euxaristia/qwen-code that referenced this pull request Apr 10, 2026
@wenshao @claude @euxaristia
fix: improve /model --fast description clarity and prevent accidental…
28a1c08 
… activation (QwenLM#3077)

Replace vague "background tasks" with specific "prompt suggestions and speculative
execution" in the --fast flag description across all i18n locales, docs, and VS Code
schema. Update example model name from qwen3.5-flash to qwen3-coder-flash. Also fix
completion logic to require a non-empty partial arg before suggesting --fast, preventing
Tab+Enter from accidentally entering fast model mode.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@yiliang114 yiliang114 mentioned this pull request May 8, 2026
Closed
xaelistic pushed a commit to xaelistic/qwen-code that referenced this pull request Jun 7, 2026
@wenshao @claude
fix: improve /model --fast description clarity and prevent accidental…
cccafd4 
… activation (QwenLM#3077)

Replace vague "background tasks" with specific "prompt suggestions and speculative
execution" in the --fast flag description across all i18n locales, docs, and VS Code
schema. Update example model name from qwen3.5-flash to qwen3-coder-flash. Also fix
completion logic to require a non-empty partial arg before suggesting --fast, preventing
Tab+Enter from accidentally entering fast model mode.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@tanzhenxin tanzhenxin tanzhenxin approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@wenshao @tanzhenxin