abbyswag/qwen-code
1
0
Fork 0
mirror of https://github.com/QwenLM/qwen-code.git synced 2025-12-19 09:33:53 +00:00
Code Issues Packages Projects Releases Wiki Activity
2,463 Commits 269 Branches 162 Tags
79b4821499e8562a9d921dc4a0a629bb32b69436
Commit Graph

901 Commits

Author SHA1 Message Date
pomelo-nwu
79b4821499 feat: Optimize the code 2025-10-27 11:24:38 +08:00
pomelo-nwu
b1ece177b7 feat: Optimize the code 2025-10-27 11:01:48 +08:00
pomelo-nwu
f9f6eb52dd feat: add multi websearch provider 2025-10-24 17:16:14 +08:00
tanzhenxin
eb95c131be Sync upstream Gemini-CLI v0.8.2 (#838) 2025-10-23 09:27:04 +08:00
zhutao100
9d664623f5 Fix and update the token limits handling (#754) 
* fix: make token limits regex normalize e.g. `some-model-1.1` -> `some-model` while preserve e.g. `gpt-4.1` as-is.

* feat: update token limits regex for latest models `GLM-4.6`, `deepseek-v3.2-exp`.

* feat: add exact token limit number 202752 per the model config file for `GLM-4.6`.
 2025-10-14 16:11:55 +08:00
Mingholy
40810945e0 fix: add missing trace info and cancellation events (#791) 
* fix: add missing trace info and cancellation events

* fix: re-organize tool/request cancellation logging
 2025-10-14 15:41:30 +08:00
Mingholy
e28255edb6 fix: token limits for qwen3-max (#724) 2025-10-14 15:40:20 +08:00
tanzhenxin
270dda4aa7 fix: invalid tool_calls request due to improper cancellation (#790) 2025-10-13 09:25:31 +08:00
Fan
d4fa15dd53 remove topp default value 0.0 (#785) 2025-10-09 15:41:57 +08:00
tanzhenxin
0922437bd5 chore: pump version to 0.0.14 2025-09-29 14:31:14 +08:00
tanzhenxin
9a0cb64a34 🚀 feat: DashScope cache control enhancement (#735) 2025-09-29 14:01:16 +08:00
Brando Magnani
9fce177bd8 Fix/qwen3 vl plus highres (#721) 
* feat: Add Qwen3-VL-Plus token limits (256K input, 32K output)

- Added 256K input context window limit for Qwen3-VL-Plus model
- Updated output token limit from 8K to 32K for Qwen3-VL-Plus
- Added comprehensive tests for both input and output limits

As requested by Qwen maintainers for proper model support.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* fix: enable high-res flag for qwen VL models

---------

Co-authored-by: Claude <noreply@anthropic.com>
 2025-09-26 17:20:18 +08:00
Brando Magnani
f7841338c4 feat: Add Qwen3-VL-Plus token limits (256K input, 32K output) (#720) 
- Added 256K input context window limit for Qwen3-VL-Plus model
- Updated output token limit from 8K to 32K for Qwen3-VL-Plus
- Added comprehensive tests for both input and output limits

As requested by Qwen maintainers for proper model support.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-authored-by: Claude <noreply@anthropic.com>
 2025-09-26 17:19:54 +08:00
tanzhenxin
c405434c41 Fix: TaskTool Dynamic Updates (#697) 2025-09-25 19:11:55 +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
8379bc4d81 chore: bump version to 0.0.13 (#695) 2025-09-24 13:58:18 +08:00
Mingholy
48d8587bf9 feat: add yolo mode support to auto vision model switch (#652) 
* feat: add yolo mode support to auto vision model switch

* feat: add cli args & env variables for switch behavoir

* fix: use dedicated model names and settings

* docs: add vision model instructions

* fix: failed test case

* fix: setModel failure
 2025-09-24 10:21:09 +08:00
tanzhenxin
5ecb4a2430 fix: make ripgrep lazy load, to fix vscode ide companion unable to start (#676) 2025-09-23 14:44:48 +08:00
Mingholy
9c1d7228cb fix: auth hang when select qwen-oauth (#684) 2025-09-23 14:30:22 +08:00
Mingholy
014059e8a6 fix: output token limit for qwen (#664) 2025-09-23 14:28:59 +08:00
Mingholy
3579d6555a chore: bump version to 0.0.12 (#662) 2025-09-19 20:13:31 +08:00
Mingholy
da0863b943 fix: missing tool call chunks for openai logging (#657) 2025-09-19 15:19:30 +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
tanzhenxin
50199288ec Merge branch 'main' into fix/subagent-update 2025-09-17 19:12:22 +08:00
tanzhenxin
8803b2eb76 feat: add system-reminder to help model use subagent 2025-09-17 18:56:30 +08:00
tanzhenxin
5f90472a7d fix: duplicate subagents config if qwen-code runs in home dir 2025-09-17 11:32:52 +08:00
Mingholy
d3476a2d47 fix: lint errors 2025-09-16 20:19:44 +08:00
Mingholy
f599cda7d2 fix: replace branding keywords to avoid ambiguity 2025-09-16 19:57:33 +08:00
Mingholy
9df193ca42 Merge branch 'main' into chore/sync-gemini-cli-v0.3.4 2025-09-16 19:51:32 +08:00
pomelo
0581344d48 Merge pull request #610 from QwenLM/feat/skip-loop-detection 
Add `skipLoopDetection` Configuration Option
 2025-09-16 15:31:51 +08:00
mingholy.lmh
484f8642c4 docs: improve docs to avoid ambiguity 2025-09-16 14:48:49 +08:00
mingholy.lmh
2c9e61af9e Merge branch 'main' into chore/sync-gemini-cli-v0.3.4 2025-09-16 10:23:28 +08:00
Mingholy
49d7947028 chore: bump version to 0.0.11 (#622) 2025-09-16 10:20:51 +08:00
mingholy.lmh
dbdb4db4f0 fix: lockfile and configs 2025-09-15 20:59:35 +08:00
mingholy.lmh
f19789b381 fix: lint error 2025-09-15 17:26:57 +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
tanzhenxin
386538521b feat: Add skipLoopDetection Configuration Option 2025-09-15 14:02:46 +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
DS-Controller2
67e2e270bd Fix performance issues with SharedTokenManager causing 20-minute delays (#586) 
- Optimize lock acquisition strategy with exponential backoff
- Reduce excessive I/O operations by increasing cache check interval
- Add timeout monitoring for token refresh operations
- Add timeout wrappers for file operations to prevent hanging
- Fixes issue #585 where users experienced extreme performance issues with Qwen Code
 2025-09-12 16:35:22 +08:00
Mingholy
adabd96a42 fix: clear saved creds when switching authType (#587) 2025-09-12 16:34:53 +08:00
pomelo-nwu
9ed3f887af feat: update vars 2025-09-12 16:01:38 +08:00
Mingholy
c3032db8b8 fix: relax chunk validation to avoid unnecessary retry (#584) 
* fix: relax chunk validation to avoid unnecessary retry

* fix: merge tail chunks for stable finishReason and usageMetadata
 2025-09-12 13:25:48 +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