- 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>
- Add tool filtering in AnthropicContentGenerator (skip tools without name/description)
- Add isValid and invalidReason fields to MCPToolDisplayInfo type
- Show invalid tool warnings in ServerList, ServerDetail, ToolList, and ToolDetail steps
- Add translations for all 6 languages (en, zh, de, ja, pt, ru)
- Add tests for Anthropic converter and MCP utils
- Delete listCommand and refreshCommand from mcpCommand.ts
- Update subCommands to only include manageCommand and authCommand
- Update documentation to reference MCP management dialog instead of CLI commands
- Simplify mcp command description to focus on management dialog and OAuth auth
Note: i18n strings for deprecated commands are kept for backward compatibility
- 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>
Rename ArenaWorktreeConfig → WorktreeSetupConfig, setupArenaWorktrees →
setupWorktrees, cleanupArenaSession → cleanupSession, etc. Change default
storage path from ~/.qwen/arena/ to ~/.qwen/worktrees/ and branch prefix
from arena/ to worktrees/. Add branchPrefix and metadata options for
flexibility. Remove auto-repo-init behavior; fail fast instead.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Add AgentViewContext, AgentTabBar, and AgentChatView components for tab-based
agent switching. Add useArenaInProcess hook bridging ArenaManager events to
React state. Add agentHistoryAdapter converting AgentMessage[] to HistoryItem[].
Core support changes:
- Replace stream buffers with ROUND_TEXT events (complete round text)
- Add TOOL_OUTPUT_UPDATE events for live tool output streaming
- Add pendingApprovals/liveOutputs/shellPids state to AgentInteractive
- Fix missing ROUND_END emission for final text rounds
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Added qwen3-coder-next model to the Global/Intl Coding Plan template
- Removed thinking mode from qwen3-coder-next (both China and Global regions)
- Updated test expectations to reflect the new model count
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Added glm-4.7 and kimi-k2.5 to the Global/Intl region template
- Excluded qwen3-coder-next as it's not yet supported internationally
- Both models configured with thinking enabled
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Added three new third-party models to the Bailian Coding Plan China region template
- All models configured with thinking enabled (enable_thinking: true)
- Updated README.md with example configurations for new models
- Updated documentation to list all available Coding Plan models
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
