vrr/qwen-code
2
0
Fork 0
mirror of https://github.com/QwenLM/qwen-code.git synced 2026-04-28 03:30:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

Merge pull request #2897 from QwenLM/feat/thinking-cross-turn-retention-idle-cleanup

Browse source 
feat(core): thinking block cross-turn retention with idle cleanup
This commit is contained in:
tanzhenxin 2026-04-08 15:26:53 +08:00 • committed by GitHub
commit 3c23952ef7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 434 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

1
docs/users/configuration/settings.md
View file

@ -206,6 +206,7 @@ The `extra_body` field allows you to add custom parameters to the request body s
| `context.fileFiltering.respectQwenIgnore` | boolean | Respect .qwenignore files when searching. | `true` |
| `context.fileFiltering.enableRecursiveFileSearch` | boolean | Whether to enable searching recursively for filenames under the current tree when completing `@` prefixes in the prompt. | `true` |
| `context.fileFiltering.enableFuzzySearch` | boolean | When `true`, enables fuzzy search capabilities when searching for files. Set to `false` to improve performance on projects with a large number of files. | `true` |
| `context.gapThresholdMinutes` | number | Minutes of inactivity after which retained thinking blocks are cleared to free context tokens. Aligns with typical provider prompt-cache TTL. Set higher if your provider has a longer cache TTL. | `5` |
#### Troubleshooting File Search Performance