abbyswag/qwen-code
1
0
Fork 0
mirror of https://github.com/QwenLM/qwen-code.git synced 2025-12-21 17:27:54 +00:00
Code Issues Packages Projects Releases Wiki Activity
2,792 Commits 273 Branches 166 Tags
44794121a838c7ea65584914caaab1e630de4616
Commit Graph

230 Commits

Author SHA1 Message Date
kefuxin
b6a3ab11e0 fix: improve Gemini compatibility by adding configurable schema converter 
This commit addresses issue #1186 by introducing a configurable schema compliance
mechanism for tool definitions sent to LLMs.

Key changes:
1.  **New Configuration**: Added `model.generationConfig.schemaCompliance` setting (defaults to 'auto', optional 'openapi_30').
2.  **Schema Converter**: Implemented `toOpenAPI30` converter in `packages/core` to strictly downgrade modern JSON Schema to OpenAPI 3.0.3 (required for Gemini API), handling:
    -   Nullable types (`["string", "null"]` -> `nullable: true`)
    -   Numeric exclusive limits
    -   Const to Enum conversion
    -   Removal of tuples and invalid keywords (``, `dependencies`, etc.)
3.  **Tests**: Added comprehensive unit tests for the schema converter and updated pipeline tests.

Fixes #1186
 2025-12-11 14:23:27 +08:00
xuewenjie
e5e1e6a3da Merge branch 'main' of github.com:QwenLM/qwen-code into fix/windows-shell-output-garbled 2025-12-08 11:35:47 +08:00
xuewenjie
2c1a836f18 fix: prefer UTF-8 encoding for shell output on Windows when detected 2025-12-05 16:49:26 +08:00
tanzhenxin
3e2a2255ee DeepSeek V3.2 Thinking Mode Integration (#1134) 2025-12-05 15:08:35 +08:00
tanzhenxin
0a75d85ac9 Session-Level Conversation History Management (#1113) 2025-12-03 18:04:48 +08:00
Zijun Yang
a7abd8d09f fix(shell-utils): resolve command detection on Ubuntu by using shell for builtins (#1123) 2025-12-02 11:49:40 +08:00
tanzhenxin
442a9aed58 Replace spawn with execFile for memory-safe command execution (#1068) 2025-11-20 15:04:00 +08:00
tanzhenxin
71646490f1 Fix: Improve ripgrep binary detection and cross-platform compatibility (#1060) 2025-11-18 19:38:30 +08:00
yyyanghj
0eeffc6875 feat: add support for Trae editor (#1037) 2025-11-17 10:58:33 +08:00
tanzhenxin
0752a31e1e 🎯 PR: Improve Edit Tool Reliability with Fuzzy Matching Pipeline (#1025) 2025-11-13 19:01:09 +08:00
tanzhenxin
06141cda8d Refactor: Standardize Tool Naming and Configuration System (#1004) 2025-11-12 19:46:05 +08:00
tanzhenxin
c3d427730e 🎯 Feature: Customizable Model Training and Tool Output Management (#981) 2025-11-07 17:28:16 +08:00
tanzhenxin
d17c37af7d Feat: Simplify and Improve Search Tools (glob, grep, ripgrep) (#969) 2025-11-06 16:25:06 +08:00
pomelo-nwu
d4ab328671 feat: support for custom OpenAI logging directory configuration 2025-11-05 18:49:04 +08:00
tanzhenxin
ea4a7a2368 fix: compression tool (#935) 2025-10-31 18:09:08 +08:00
tanzhenxin
817218f1cf feat: Refactor and Enhance Ripgrep Tool (#930) 2025-10-31 10:53:13 +08:00
tanzhenxin
f8be8a61c8 🐛 Bug Fixes Release v0.1.1 (#898) 2025-10-29 12:25:50 +08:00
tanzhenxin
be633a80cc 📦 Release qwen-code CLI as a Standalone Bundled Package (#866) 2025-10-24 17:08:59 +08:00
tanzhenxin
eb95c131be Sync upstream Gemini-CLI v0.8.2 (#838) 2025-10-23 09:27:04 +08:00
tanzhenxin
673854b446 fix: Remove unreliable editCorrector that injects extra escape characters (#713) 2025-09-25 16:46:58 +08:00
tanzhenxin
4e7a7e2656 feat: Implement Plan Mode for Safe Code Planning (#658) 2025-09-24 14:26:17 +08:00
Mingholy
5f68a8b6b3 fix: switch system prompt to avoid malformed tool_calls (#650) 
* fix: switch system prompt to avoid malformed tool_calls

* fix: circular dependency issue and configurable tool-call style

* fix: regExp issue
 2025-09-18 21:10:03 +08:00
Mingholy
761833c915 Vision model support for Qwen-OAuth (#525) 
* refactor: openaiContentGenerator

* refactor: optimize stream handling

* refactor: re-organize refactored files

* fix: unit test cases

* feat: `/model` command for switching to vision model

* fix: lint error

* feat: add image tokenizer to fit vlm context window

* fix: lint and type errors

* feat: add `visionModelPreview` to control default visibility of vision models

* fix: remove deprecated files

* fix: align supported image formats with bailian doc
 2025-09-18 13:32:00 +08:00
Mingholy
56808ac210 fix: reset is_background (#644) 2025-09-18 13:27:09 +08:00
Peter Stewart
724c24933c Enable tool call type coersion (#477) 
* feat: enable tool call type coercion

* fix: tests for type coercion

---------

Co-authored-by: Mingholy <mingholy.lmh@gmail.com>
 2025-09-18 13:04:27 +08:00
mingholy.lmh
62d858f344 fix: failed unit tests 2025-09-15 14:38:02 +08:00
mingholy.lmh
e9b423b43a fi: import type errors 2025-09-15 14:26:01 +08:00
mingholy.lmh
acb93b1e1b fix: type errors 2025-09-15 14:11:31 +08:00
mingholy.lmh
1976837eda Merge branch 'main' into chore/sync-gemini-cli-v0.3.4 2025-09-15 13:42:42 +08:00
mingholy.lmh
1993156721 fix: change .geminiignore to .qwenignore 2025-09-14 19:38:40 +08:00
pomelo
38d9ee64ca Merge pull request #563 from zhutao100/pr-readManyFilesLineLimit 
Make the ReadManyFiles tool share the "DEFAULT_MAX_LINES_TEXT_FILE" limit across files.
 2025-09-11 17:32:58 +08:00
tanzhenxin
81e83ac855 Merge branch 'main' into feat/subagents 2025-09-11 17:00:50 +08:00
pomelo
b1a1ce530e feat: Add Welcome Back Dialog, Project Summary, and Enhanced Quit Options (#553) 2025-09-11 16:59:26 +08:00
mingholy.lmh
14ea33063f Merge tag 'v0.3.0' into chore/sync-gemini-cli-v0.3.0 2025-09-11 16:26:56 +08:00
tanzhenxin
e341e9ae37 fix: tests fail on Windows 2025-09-10 16:24:59 +08:00
tanzhenxin
ecf032c76e chore: update copyright for newly added files 2025-09-09 16:06:43 +08:00
Tao Zhu
ac0a0e061e Make the ReadManyFiles tool share the "DEFAULT_MAX_LINES_TEXT_FILE=2000" limit across files. 
The current implementation can return 2000 x N lines when reading N files, such a length can be either extremely slow or infeasible for LLMs to process.
 2025-09-08 22:47:45 -07:00
tanzhenxin
5d8874205d feat: subagent phase 2 implementation 2025-09-03 19:17:29 +08:00
tanzhenxin
c49e4f6e8a feat: Implement subagents phase 1 with file-based configuration system 
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
 2025-09-02 14:02:30 +08:00
tanzhenxin
2572faf726 # 🚀 Sync Gemini CLI v0.2.1 - Major Feature Update (#483) 2025-09-01 14:48:55 +08:00
Abhi
bfdddcbd99 feat(commands): Enable @file processing in TOML commands (#6716) 2025-08-28 03:22:21 +00:00
Bryant Chandler
99a28e6b6a fix: Enable disableFuzzySearch config option propagation (#7002) 
Co-authored-by: Jacob Richman <jacob314@gmail.com>
 2025-08-27 15:27:41 +00:00
tanzhenxin
600c58bbcb 🔧 Miscellaneous Improvements and Refactoring (#466) 2025-08-27 17:32:57 +08:00
Andrew Garrett
52dae2c583 feat(cli): Add --allowed-tools flag to bypass tool confirmation (#2417) (#6453) 2025-08-26 16:17:43 +00:00
koalazf.99
5cd3349773 rename GEMINI_DIR to QWEN_DIR 2025-08-26 20:14:10 +08:00
Tommaso Sciortino
7e31577813 Standardize exit codes (#7055) 2025-08-26 04:44:45 +00:00
Pascal Birchler
0f031a7f89 Explict imports & exports with type modifier (#3774) 2025-08-25 22:04:53 +00:00
Pascal Birchler
ee4feea006 chore: consistently import node modules with prefix (#3013) 
Co-authored-by: N. Taylor Mullen <ntaylormullen@google.com>
 2025-08-25 20:11:27 +00:00
Pascal Birchler
49cce8a15d chore(test): install and configure vitest eslint plugin (#3228) 
Co-authored-by: N. Taylor Mullen <ntaylormullen@google.com>
 2025-08-25 14:21:47 +00:00
Billy Biggs
a8cac96cc9 Support JSON schema formats using ajv-formats (#6949) 2025-08-24 16:37:09 +00:00