COMMITS
/ examples/coding_agent_rl/generate.py June 23, 2026
J
feat(coding_agent_rl): select claude_code/codex harness+adapter pair via SWE_AGENT (#2125)
jingshenghang committed
J
fix(agent) SWE coding-agent RL stability bugs (abort handling, session cleanup) (#2124)
jingshenghang committed
June 17, 2026
June 4, 2026
Z
Revert "rename rollout_ids to group_ids" (#2013)
Zilin Zhu committed
May 30, 2026
Z
rename rollout_ids to group_ids (#1984)
Zilin Zhu committed
May 29, 2026
Z
[agent] extract Adapter class (#1981)
Zilin Zhu committed
Z
[agent] Add openai and anthropic adapters (#1979)
Zilin Zhu committed
May 27, 2026
J
[coding_agent_rl] middleware: shutdown_session drains in-flight handl… (#1954)
jingshenghang committed
Z
Extract more util code from coding_agent_rl example (#1960)
Zilin Zhu committed
Z
Move coding_agent_rl's helper function to sandbox.py (#1958)
Zilin Zhu committed
Z
Minor refactor for coding agent rl logic and remove SWE_LIST_TRAJECTORY (#1957)
Zilin Zhu committed
Z
Add slime/agent/ and move sandbox impl inside (#1956)
Zilin Zhu committed
May 26, 2026
J
[examples] add coding_agent_rl: agent-in-sandbox RL minimal demo (#1923)
jingshenghang committed