Yichen Jiang
|
5234a40f9c
refactor(llm): classify auxiliary request purpose
|
2 сар өмнө |
Jinhua Zhu
|
66e5f8eecd
feat(llm): mark compaction requests with x-deepseek-harness-compact header
|
2 сар өмнө |
Tianyi Cui
|
21721bf3b1
Merge branch 'master' into fix/compaction-kv-cache-reuse
|
2 сар өмнө |
Turtle
|
a0268d2509
fix(compact-basic): replay conversation prefix so summarization reuses KV cache
|
2 сар өмнө |
Yichen Jiang
|
b6f6c58435
Merge remote-tracking branch 'origin/master' into worktree/routed-model-compaction-policy
|
2 сар өмнө |
Yichen Jiang
|
cfa180c127
Resolve compaction policy per routed model
|
2 сар өмнө |
Tianyi Cui
|
3b0b0cefeb
feat: implement bounded LLM request recovery
|
2 сар өмнө |
Tianyi Cui
|
7be78c7d4c
Merge latest origin/master into compact-post-step-overflow-recovery
|
2 сар өмнө |
Tianyi Cui
|
f943bc8d4c
Merge latest origin/master into token-meter-service
|
2 сар өмнө |
Hypatia May
|
12484104c8
feat(compact): recover context overflow (PR3 phase 2)
|
2 сар өмнө |
Hypatia May
|
f038780ff6
feat(llm): add replay token metering (PR2 round 1)
|
2 сар өмнө |