Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Add InProcessBackend to run subagents in-process rather than via subprocess,
enabling faster initialization and better resource management for agent
collaboration arenas.
Key changes:
- Add InProcessBackend with sandboxed in-process agent execution
- Refactor agent runtime into headless vs interactive modes
- Add AsyncMessageQueue utility for agent message passing
- Update ArenaManager with backend selection (in-process vs subprocess)
- Refactor subagent types/exports; consolidate in subagents/types
- Remove deprecated agent-hooks.ts (functionality merged into runtime)
- Update task tool to support new agent lifecycle
Breaking: Subagent type exports restructured; import from subagents/types
- Rename SubAgentScope → AgentHeadless and runNonInteractive → execute
- Move agents-collab/ into agents/ with new runtime/ subdirectory
- Split subagent.ts into agent-core.ts and agent-headless.ts
- Update all event types, emitters, and statistics classes
BREAKING CHANGE: SubAgentScope renamed to AgentHeadless;
runNonInteractive() renamed to execute()
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Replace SESSION_WARNING with SESSION_UPDATE supporting info/warning types
- Emit setup progress messages from ArenaManager during agent initialization
- Record all arena UI events to session JSONL for chat history replay
- Clean up unused agent event types (stream, tool calls, stats)
- Update arena select/stop dialogs to record their output
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Introduces a new Arena system for running multiple AI agents in parallel
terminal sessions with support for iTerm and Tmux backends.
Core:
- Add ArenaManager and ArenaAgentClient for orchestrating multi-agent sessions
- Add terminal backends (ITermBackend, TmuxBackend) with feature detection
- Add git worktree service for isolated agent workspaces
- Add arena event system for real-time status updates
CLI:
- Add /arena command with start, stop, status, and select subcommands
- Add Arena dialogs (Select, Start, Status, Stop)
- Add ArenaCards component for displaying parallel agent outputs
- Consolidate message components into StatusMessages and ConversationMessages
- Add MultiSelect component for agent selection
Config:
- Add arena-related settings to schema and config
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Fix AuthDialog to show correct description for coding-plan-intl mode
- Update i18n keys from 'Coding Plan (Bailian, Global/Intl)' to 'Bailian Coding Plan (Global/Intl)'
- Sync translations across all locales (en, zh, de, ja, pt, ru)
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Add support for Coding Plan international region with separate base URL:
- Add CodingPlanRegion enum (CHINA, GLOBAL) for region management
- Add CODING_PLAN_INTL_MODELS template with intl base URL
- Add version storage for both regions (codingPlan.version/versionIntl)
- Update AuthDialog to show both region options
- Update useCodingPlanUpdates to handle region-specific updates
- Add i18n translations for all supported languages
- Fix and update unit tests
Users can now choose between:
- Coding Plan (Bailian, China) - https://coding.dashscope.aliyuncs.com/v1
- Coding Plan (Bailian, Global/Intl) - https://coding-intl.dashscope.aliyuncs.com/v1
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Add news banner announcing Qwen3.5-Plus availability
- Include OAuth sign-in option and Alibaba Cloud ModelStudio link for API key access
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Add comprehensive quick setup section with 3-step guide for settings.json
- Include multiple practical examples (Coding Plan, multi-provider, thinking mode)
- Update README with settings.json quick reference table
- Enhance auth.md with one-file setup recommendation
- Clarify field descriptions and priority order for API key configuration
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Allow SANDBOX_SET_UID_GID to control user identity in integration tests
- Fix project naming from gemini-cli to qwen-code
- Use random UUID in tests to avoid conflicts
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Add --session-id flag to CLI for specifying custom session ID
- Add sessionId option to SDK QueryOptions
- Implement UUID validation for session IDs
- Pass session ID from SDK to CLI via --session-id argument
- Add integration tests for session-id functionality
- Update unit tests for ProcessTransport
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Move AbortController creation inside while(true) loop to create a new
instance per round. This prevents listeners from accumulating across
multiple rounds which was causing maxListener warnings.
Key changes:
- Create roundAbortController at the start of each loop iteration
- Track current round's controller with currentRoundAbortController
- External abort signal propagates to current round's controller in real-time
- Cleanup external listener and clear reference in finally block
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Replace hardcoded Colors.* with theme.* in AuthDialog and ApiKeyInput
- Fix selectedIndex reset when going back from API-KEY sub-view to main view
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Consolidate Escape key behavior to improve UX and prevent conflicts:
- Move Escape handling from useGeminiStream to AppContainer
- Input with content: double-press to clear, then single-press to cancel
- Empty input: single-press immediately cancels ongoing request
- Preserve embeddedShellFocused check to allow shell's own escape handling
- Update tests to use cancelOngoingRequest directly instead of simulating keypress
Fixes inconsistent escape behavior between input clearing and request cancellation.
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Use fixed 60s delay matching DashScope per-minute quota window
- Increase max retries from 3 to 10 to align with Claude Code behavior
- Remove unused isTPMThrottlingError, isGLMRateLimitError, isRateLimitThrottlingError functions
- Simplify getRateLimitRetryInfo to only extract reason, delay is now caller's responsibility
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Add Ajv2020 validator to support draft-2020-12 schemas used by playwright-mcp
- Auto-select validator based on $schema field
- Gracefully skip validation when schema compilation fails
- Add comprehensive tests for JSON Schema version support
Reference: gemini-cli implementation pattern
