104 commits

Author	SHA1	Message	Date
mingholy.lmh	7311a01874	fix: sdk mcp tests	2026-02-09 11:54:20 +08:00
tanzhenxin	c71cc9ce0d	fix(integration-tests): correct MCP tool name in simple-mcp-server test ... Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-02-09 10:07:00 +08:00
tanzhenxin	21e711469d	fix(mcp): update OAuth client names and improve MCP commands ... - Rename MCP OAuth client names from 'Gemini CLI' to 'Qwen Code' - Update MCP add/remove/list commands with improved error handling - Add comprehensive tests for OAuth provider - Fix token storage test assertions - Clean up unused i18n translation keys - Update gemini-converter and window title references Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-02-08 10:46:48 +08:00
Mingholy	5c582e98c6	Merge pull request #1732 from QwenLM/mingholy/fix/sdk-release-workflow ... Add CLI source selection for SDK releases and fix subagent output handler	2026-02-06 13:01:05 +08:00
Mingholy	d90b642564	Merge pull request #1733 from QwenLM/mingholy/test/fix-acp-tests ... fix: use openai model instead of index=0 in acp integration test	2026-02-05 22:04:51 +08:00
mingholy.lmh	972103e795	fix: use openai model instead of index=0 in acp integration test ... Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-02-05 21:17:07 +08:00
mingholy.lmh	1e05359881	ci(sdk-release): add CLI source selection for SDK releases ... - Replace cli_ref input with cli_source choice (build_from_source or npm_latest) - Add support for bundling latest stable CLI from npm - Add bundle-cli-from-npm.js script for npm-based CLI bundling - Fix property naming in nonInteractiveCli.ts (outputUpdateHandler) - Improve integration tests for subagents - Skip creating issue on failure during dry-run mode Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-02-05 20:57:01 +08:00
tanzhenxin	8434b89711	Merge pull request #1682 from QwenLM/fix/vscode-ide-compaion-ui-show-bugs ... fix(vscode-ide-companion): Fix UI display issues with server-side timestamp and file path extraction	2026-02-05 20:17:30 +08:00
tanzhenxin	a31699ed73	Merge branch 'main' into mingholy/fix/acp-model-list	2026-02-05 19:01:17 +08:00
mingholy.lmh	06b37bd6bf	fix(acp): add authMethods in set_model response errors	2026-02-01 21:20:20 +08:00
tanzhenxin	831d74dbfe	feat: Preserve UTF-8 BOM when editing files (Fix #1672) ... - Add FileEncoding constants (UTF8, UTF8_BOM) - Add detectFileBOM() to detect existing file encoding - Modify writeTextFile() to support BOM option - Add defaultFileEncoding configuration option - Preserve BOM when editing existing files - Use configured encoding for new files - Add comprehensive tests (unit, integration, e2e) - Update documentation Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-02-01 10:32:20 +08:00
yiliang114	9830c70061	feat(vscode-ide-companion): 支持使用 server-side timestamp 进行消息排序 ... - 在 SessionUpdateMeta 中添加 timestamp 字段 - 为 UserMessageChunkUpdate 和 ToolCallUpdate 添加 _meta 字段 - 在 QwenAgentManager 中使用 server timestamp 而非客户端时间 - 在 QwenSessionUpdateHandler 中解析并传递 tool call timestamp - 在 useToolCalls 中改进 timestamp 解析逻辑 - 修正 App.tsx 中 timestamp 处理，使用 nullish-coalescing operator - 为 ToolCallUpdateData 和 ToolCallUpdate 类型添加 timestamp 和 _meta feat(integration-tests): add file location extraction for tool calls feat(webui): enhance ReadToolCall component with content preview and expand/collapse refactor(webui): simplify SaveMemoryToolCall component UI Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-02-01 00:22:29 +08:00
pomelo-nwu	2259943f85	feat: update export html	2026-01-29 13:27:18 +08:00
pomelo-nwu	021680cd70	feat: add html template	2026-01-28 19:56:20 +08:00
tanzhenxin	acf5824a65	fix: resolve worktree paths and load keep_worktree from config ... - Resolve worktree_dir to absolute path before using as cwd and QWEN_CODE_ROOT - Load keep_worktree option from JSON config in load_config() Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-01-28 17:25:29 +08:00
tanzhenxin	3f16948225	feat: remove npm install/build and add keep_worktree option ... - Remove npm install and npm run build from worktree initialization - Remove INITIALIZING status enum and related code - Add keep_worktree config option (default: false) - When keep_worktree is true, worktree is preserved for debugging - Renumber execution steps after removing initialize step Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-01-28 16:43:50 +08:00
tanzhenxin	0c1848896a	Revert: use text output format instead of JSON ... - Remove --output-format json from CLI commands - Change output filenames from output-{N}.json back to stdout-{N}.txt - Keep outputs in outputs/ subdirectory for clean structure Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-01-28 15:47:14 +08:00
tanzhenxin	09d4627a3d	feat: move output files to outputs/ subdirectory for cleaner structure ... - Move output-{N}.json and stderr-{N}.txt to outputs/ subdirectory - Fix typo in toy-config.json results_file path (rest-run -> test-run) - Add --output-format json to CLI commands - Update file extensions from .txt to .json for stdout captures Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-01-28 15:29:11 +08:00
tanzhenxin	f48eec9a02	feat: add git diff capture and session log collection to concurrent runner ... - Add git diff capture after each run, saved as diff.patch - Add session log collection from ~/.qwen/projects/{id}/chats/ - Store session logs in outputs/{run_id}/chats/ with original filename - Add session_id field to track chat recording UUID - Modify cwd in session logs to actual runner working directory - Remove stdout_file/stderr_file from top-level, keep only in prompt_results - Rename logs folder to openai-logs - Add File Writer task example for testing file creation Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-01-28 14:57:15 +08:00
tanzhenxin	66259aca29	feat: add git branch support for worktree creation ... Add optional branch configuration to specify which git branch to use for worktree creation. Features: - New branch config option to specify base branch (e.g., main, develop) - Each worktree creates a unique branch based on the specified branch (format: branch-run-id) - If branch is not specified, uses the repository default branch - Falls back gracefully when branch already exists Changes: - Add branch field to RunConfig dataclass - Update GitWorktreeManager.create() to accept branch parameter - Create unique branches for each worktree to avoid conflicts - Update load_config() to parse branch from config - Update config.example.json with branch option - Update README.md documentation Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-01-28 12:36:23 +08:00
tanzhenxin	47a733362e	feat: add sequential prompt execution and auto git initialization ... Enhance the concurrent runner with two key features: 1. Sequential Prompt Execution: - Run multiple prompts sequentially instead of joining them - Use --continue flag for prompts 2+ to pick up chat history - Generate separate output files per prompt (stdout-1.txt, stdout-2.txt, etc.) - Stop execution if any prompt fails - Track per-prompt results in results.json 2. Auto Git Initialization: - Automatically initialize git repo if source is not a git repository - Run git init → git add . → git commit automatically - Improves UX - users can point runner at any directory Changes: - Add PromptResult dataclass for per-prompt tracking - Modify RunRecord to include prompt_results list - Update QwenRunner.run() to execute prompts sequentially - Add GitWorktreeManager.ensure_git_repo() method - Update _build_command() to support --continue flag Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-01-28 12:27:10 +08:00
tanzhenxin	4ac3df1b63	feat: add concurrent runner for batch CLI execution ... Add a Python-based concurrent runner that executes multiple Qwen CLI tasks across different models in parallel using isolated git worktrees. Features: - Execute N tasks × M models concurrently with configurable concurrency - Create isolated git worktrees for each run under ~/.qwen/worktrees - Real-time progress display with Rich library - Capture stdout, stderr, and OpenAI API logs per run - Atomic JSON tracking of all runs with status and metadata - Automatic cleanup of worktrees after each run Structure: - runner.py: Main implementation with asyncio - requirements.txt: Python dependencies - README.md: Documentation and usage - config.example.json: Configuration template - examples/: Toy example with sample config and project Usage: python runner.py config.json Each run creates an isolated output directory: outputs/{run_id}/ ├── stdout.txt ├── stderr.txt └── logs/openai-*.json Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>	2026-01-28 12:08:56 +08:00
mingholy.lmh	b05de7a187	test: improve sdk integration tests	2026-01-27 17:10:36 +08:00
mingholy.lmh	f578ff07a2	fix: cli input stream handling and error management, improve e2e and unit tests	2026-01-23 13:56:38 +08:00
tanzhenxin	cf140b1b9d	update acp-integration.test.ts to add session/set_model command	2026-01-17 10:59:46 +08:00
mingholy.lmh	50bf65b10b	test: skip flaky & ambigous sdk e2e test case	2026-01-13 20:04:19 +08:00
顾盼	6f39ae120c	Merge pull request #1355 from QwenLM/feat/stable-acp-flag ... feat: graduate `--experimental-acp` to stable `--acp` flag	2026-01-06 17:51:43 +08:00
mingholy.lmh	8c109be48c	refactor: unified allow list of supported commands in ACP or non-interactive mode	2025-12-26 17:55:03 +08:00
LaZzyMan	fe7ff5b148	feat: stable-acp-flag	2025-12-26 17:09:16 +08:00
tanzhenxin	7233d37bd1	fix one flaky integration test	2025-12-26 09:20:24 +08:00
tanzhenxin	27e7438b75	fix one flaky integration test	2025-12-25 16:08:06 +08:00
tanzhenxin	b64d636280	anthropic provider support follow-up	2025-12-25 15:24:42 +08:00
tanzhenxin	8fd7490d8f	remove one flaky integration test	2025-12-17 09:27:25 +08:00
tanzhenxin	b9a2cc7bdf	Add chat recording toggle (CLI + settings) and disable recording in tests	2025-12-15 13:48:38 +08:00
tanzhenxin	efbf50554d	Merge branch 'main' into feat/acp-usage-metadata	2025-12-08 10:27:38 +08:00
mingholy.lmh	8b5b8d2b90	test: skip unstable e2e test	2025-12-06 18:41:19 +08:00
mingholy.lmh	22943b888d	test: clean up integration test by removing unnecessary console logs	2025-12-05 22:11:27 +08:00
mingholy.lmh	96d458fa8c	chore: rename @qwen-code/sdk-typescript to @qwen-code/sdk	2025-12-05 21:47:26 +08:00
mingholy.lmh	c218048551	fix: prevent sending control request when query is closed	2025-12-05 18:46:51 +08:00
tanzhenxin	3a7b1159ae	feat: add usage metadata in acp session/update event	2025-12-05 15:40:49 +08:00
mingholy.lmh	322ce80e2c	feat: implement SDK MCP server support and enhance control request handling ... - Added new `SdkMcpController` to manage communication between CLI MCP clients and SDK MCP servers. - Introduced `createSdkMcpServer` function for creating SDK-embedded MCP servers. - Updated configuration options to support both external and SDK MCP servers. - Enhanced timeout settings for various SDK operations, including MCP requests. - Refactored existing control request handling to accommodate new SDK MCP server functionality. - Updated tests to cover new SDK MCP server features and ensure proper integration.	2025-12-05 13:14:54 +08:00
mingholy.lmh	57b519db9a	test: skip qwen-oauth e2 case in sandbox	2025-12-04 20:39:51 +08:00
mingholy.lmh	50e3a6ee0a	fix: enhance 429 error handling and fix failed cases	2025-12-04 17:10:23 +08:00
mingholy.lmh	3056f8a63d	feat(tests): move SDK integration tests to integration-tests to share globalSetup	2025-12-04 17:10:23 +08:00
tanzhenxin	6729980b47	skip acp integration test in sandbox env (#1141)	2025-12-04 10:28:21 +08:00
tanzhenxin	2ca36d7508	skip one flaky integration test (#1137)	2025-12-03 19:40:14 +08:00
tanzhenxin	0a75d85ac9	Session-Level Conversation History Management (#1113)	2025-12-03 18:04:48 +08:00
Mingholy	c9af74816a	fix: reset authType settings (#1091) ... * fix: reset authType settings * fix: failed json-output tests * fix: sandbox exception log to stderr	2025-11-23 17:59:35 +08:00
Kdump	9e5387f159	Headless enhancement: add stream-json as input-format/output-format to support programmatically use (#926)	2025-11-21 09:26:05 +08:00
tanzhenxin	97bf48b14c	fix: skip problematic integration test (#1065)	2025-11-19 11:55:19 +08:00