Xingyao Wang 5114230e53 Some SWE-Bench infer fixes and improvements (#2065) ...

* reset workspace base properly

* support running without hint

* support running without hint

* bump swe-bench eval docker to v1.2 for latest agentskills

* only give hint when use hint text is trie

* add swe-agent instructions for validation

* update dockerfile

* pin the python interpreter for execute_cli

* avoid initialize plugins twice

* default to use hint

* save results to swe_bench_lite

* unset gh token and increase max iter to 50

* remove printing of use hint status

* refractor ssh login into one function

* ok drop to 30 turns bc it is so expensive :(

* remove reproduce comments to avoid stuck

2024-05-26 10:02:11 +00:00

..

agent_skills

fix the openai_api_key detected by agentskills (#2052)

2024-05-25 22:09:07 +08:00

jupyter

Some SWE-Bench infer fixes and improvements (#2065)

2024-05-26 10:02:11 +00:00

swe_agent_commands

Refactored Logs (#1939)

2024-05-22 03:06:13 +08:00

__init__.py

Implement agentskills for OpenDevin to helpfully improve edit AND including more useful tools/skills (#1941)

2024-05-23 16:04:09 +00:00

mixin.py

Some SWE-Bench infer fixes and improvements (#2065)

2024-05-26 10:02:11 +00:00

requirement.py

Migrate to new folder structure in preparation for refactor (#1531)

2024-05-02 17:01:54 +00:00