 tofarr
|
c919086e25
Fix for regression (#4075)
|
1 anno fa |
 Xingyao Wang
|
e03855cd7f
Make sure we print the observation in the same way as the LLM sees it
|
1 anno fa |
|
tofarr
|
ee284bae8f
Fix server lock up on session init (#4007)
|
1 anno fa |
|
Xingyao Wang
|
714e46f29a
[eval] save eventstream & llm completions for SWE-Bench run_infer (#3923)
|
1 anno fa |
 tobitege
|
620526b8b4
agent_controller: in PAUSED state reduce delegate logspam from delegate (#3946)
|
1 anno fa |
|
tofarr
|
ad0b549d8b
Feat Tightening up Timeouts and interrupt conditions. (#3926)
|
1 anno fa |
 niliy01
|
804674bb9f
refactor the logic in agent_controller to imporve readability (#3873)
|
1 anno fa |
 Boxuan Li
|
1e2796e168
Fix step count out-of-sync bug when child agent fails (#3680)
|
1 anno fa |
|
tobitege
|
ae153aa8ab
(enh) review of logger.py; less logging in AgentController (#3648)
|
1 anno fa |
 Raj Maheshwari
|
11d8d05b1a
[Fix] Metrics should be updated when agent reaches max iterations. (#3549)
|
1 anno fa |
|
tofarr
|
f5aa111ba6
Fix: Bump max_iterations when resuming due to throttling (#3410)
|
1 anno fa |
 Robert Brennan
|
01ae22ef57
Rename OpenDevin to OpenHands (#3472)
|
1 anno fa |
