nezumi/9router
1
0
Fork 0
mirror of https://github.com/Nezumi-2711/9router.git synced 2026-09-22 13:38:31 +00:00
Code Issues Packages Projects Releases Wiki Activity
911 Commits 3 Branches 0 Tags
71cd5b2f23f3b174b573c1bb2f75d46c656eac0c
Commit Graph
4 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
KunN-21andCursor 19281b5524 feat(rtk): add JS-native git-log filter (#2423) 
Compress git log output via dedicated RTK filter: keep commit headers,
Author/Date, subject; drop body padding, decoration, embedded diff lines.
Wire into autodetect (git-log prioritized before git-diff) and registry.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-07 12:02:56 +07:00
KunN-21andCursor 97a6708651 feat(caveman): add targeted upstream-aligned style rules (#2424) 
Add four shared Caveman prompt fragments (no invented abbreviations,
preserve user language, no self-reference, no decoration) across all six
levels, and remove ULTRA contradictions around abbreviations/arrow
shorthand. Adds regression tests for the prompt rules.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-07 11:55:45 +07:00
KunN-21andCursor cb0135b695 fix: prevent non-SSE stream pipe crash and cross-IdP account overwrites (#2244) 
- streamingHandler: when upstream returns non-SSE/JSON (e.g. Cloudflare
  5xx HTML), read body, sanitize <title>, notify streamController and
  return a clean JSON error instead of crashing the pipe.
- connectionsRepo: dedup OAuth connections on (email + username) so
  cross-IdP accounts sharing an email no longer overwrite each other;
  workspace providers keep workspace-id matching.
- kimchi: bump User-Agent to 0.1.50, add svg asset + browser-login
  service, and 21 unit tests.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-03 11:11:07 +07:00
KunN-21andCursor 7afaecd617 fix(kimchi): strip reasoning_content echo to bound multi-turn input tokens 
Clients echo full message history each turn including reasoning_content,
which the Kimchi OpenAI gateway counts as input tokens. Multi-turn convos
balloon to 100k+ tokens and the model returns empty content.

KimchiExecutor.transformRequest now strips reasoning_content from assistant
messages when it exceeds an 8-char threshold, preserving the 1-char
placeholder injectReasoningContent sets and keeping content intact.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-03 10:58:31 +07:00