Tim bb71c18080 feat: merge selectively (#888) ...

* chore: avoid incorporate changes
best as sota
merge hypothesis
fix: max_retrieve_num after decision
chore: select last experiments and feedbacks
* add the set_current_selection before the exp_gen when merging
add trace.NEW_ROOT
fix: no scen_prob_multiplier
fix: use regex with timeout
chore: hypothesis_rank with selected_idx
chore: define is_parent in proposal
chore: rename collect_all_ancestors to get_parent_exps
---------

Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
Co-authored-by: Young <afe.young@gmail.com>
Co-authored-by: Xu <v-xuminrui@microsoft.com>
Co-authored-by: Xu Yang <xuyang1@microsoft.com>

2025-06-04 14:46:47 +08:00

..

app

feat: add RD-Agent-Quant scenario (#838)

2025-05-29 16:16:51 +08:00

components

feat: log reaching max time limit before breaking CoSTEER evolution (#921)

2025-06-03 12:51:56 +08:00

core

feat: merge selectively (#888)

2025-06-04 14:46:47 +08:00

log

fix loop_num calc logic (#911)

2025-05-29 16:40:57 +08:00

oai

fix: default cost to NaN when calculation fails in LiteLLM backend (#912)

2025-05-29 22:58:29 +08:00

scenarios

feat: merge selectively (#888)

2025-06-04 14:46:47 +08:00

utils

feat: merge selectively (#888)

2025-06-04 14:46:47 +08:00