- Corrected the file path in commands.md mapping table from
'<project>/commands/git/commit.md' to '<project>/.qwen/commands/git/commit.md'
- Removed trailing blank line in sandbox.md code block
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Update integration test environment variable name
- Ensure sandbox container naming works correctly with new variable
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
The test 'blocks write tools in plan mode' was failing because the model
would attempt to exit plan mode via exit_plan_mode tool. By cancelling
switch_mode tool calls in the permission handler, we ensure plan mode
stays active throughout the test.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Moves export-html and insight templates from cli/assets to a new
dedicated web-templates package. Updates Dockerfile and build scripts
to use consolidated bundle/prepare:package/pack workflow.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Add backupSettingsFile() utility to create .orig backup before modifying settings
- Update success message to indicate backup was created
- Sync i18n translations for all supported languages
- Update documentation to reflect the change
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Single-line layout with muted bar, accent stage text
- Inline
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>... in stage messages for cleaner code
- Simplify command intro text
- Merge coder-model and qwen3.5-plus into a single coder-model with vision capability
- Remove vlmSwitchMode CLI argument and experimental.vlmSwitchMode setting
- Remove useVisionAutoSwitch hook and inline image format checking into useGeminiStream
- Remove ModelSwitchDialog and related vision switch UI components
- Update all related tests to reflect the simplified model structure
- Set DEFAULT_QWEN_MODEL to coder-model
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Generate date-stamped filenames (insight-YYYY-MM-DD.html)
- Append timestamp for multiple runs same day (insight-YYYY-MM-DD-HHMMSS.html)
- Create insight.html alias pointing to latest report
- Use symlink when possible, fallback to copy for cross-platform compatibility
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Add share card theme selection (light/dark) with contextual export controls
- Update heatmap colors to GitHub green palette and fix time ranges
- Limit bar charts to 10 items, use full Qwen Code name
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Update totalMessages to count only user messages and slash commands
- Update heatmap to reflect only user interactions
- Update activeHours to reflect only user interactions
- Update tests to verify slash commands are counted correctly
This ensures the insight report accurately reflects actual user engagement
rather than including internal tool calls and system events.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Filter sessions to only include those with both user and assistant
records when generating facets. This prevents system-only logs from
being analyzed, ensuring more accurate session insights.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Create new model-providers.md with complete model provider configuration guide
- Add Bailian Coding Plan documentation with setup and auto-update details
- Remove modelProviders content from settings.md to avoid duplication
- Document reserved envKey BAILIAN_CODING_PLAN_API_KEY and security recommendations
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Fixes#1748 - gopls failed to start with JSON RPC parse error.
The workspaceFolders capability was incorrectly sent as an object
{ supported: true } instead of a boolean true, causing gopls to
fail with 'cannot unmarshal object into... bool'.
- Add comprehensive configuration examples for all auth types (openai, anthropic, gemini, vertex-ai)
- Add local self-hosted model examples (vLLM, Ollama, LM Studio)
- Clarify generation config layering with impermeable provider layer concept
- Add Provider Model vs Runtime Model explanation
- Document duplicate model ID limitation
- Deprecate security.auth.apiKey and security.auth.baseUrl settings
- Add notes about extra_body parameter support limitations
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
