Remove unconditional stateful-turn truncation
This commit is contained in:
@@ -4,6 +4,19 @@ This file records strategy changes that materially affect dataset decisions or
|
||||
training-data semantics. Generated audit manifests are not treated as stable API
|
||||
contracts.
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Strategy correction
|
||||
|
||||
- Removed the unconditional cutoff before the first state-changing turn for
|
||||
failed and unverified trajectories. A write or edit is not evidence of an
|
||||
error by itself, and this cap discarded normal implementation, recovery, and
|
||||
verification work.
|
||||
- The semantic boundary now remains the earliest unrecovered major or critical
|
||||
assistant behavior selected by the boundary stage. The isolated prefix-quality
|
||||
stage remains the safety gate. The first stateful turn is retained as telemetry
|
||||
for paired evaluation against the former policy.
|
||||
|
||||
## 2.0.0 - 2026-08-07
|
||||
|
||||
### Strategy
|
||||
|
||||
Reference in New Issue
Block a user