Accept the full re-judge after a CV or prompt edit

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
WolfandClaude Opus 5.5 committed 2026-10-04 10:13:10 +02:00
1 parent 9d30582599
commit 5f1d225d21
1 file changed
+1 -1
+1 -1
View File
@@ -86,7 +86,7 @@ Without the Where lines, about four in five model reads go to roles outside DK,
The form wording for the sizes becomes "at most N, each scoring at least X", in place of "the best N down to a score of X".
**Cost.** Every model read happens once per role (judge once per role and CV), so a larger cut costs mostly a one-off catch-up. With a cut of about 650 roles, that catch-up is about 16 minutes of extract and about an hour of judge on the live backend (`claude_code`, the subscription, so no per-token bill). After it, each pull reads only the roles new to the cut. The recurring cost is a re-judge: changing the CV, a prompt, or the like or dislike text changes every judgement's input, so the whole cut is judged again, about an hour for 650 roles. A changed posting text re-judges that role only.
**Cost.** Every model read happens once per role (judge once per role and CV), so a larger cut costs mostly a one-off catch-up. With a cut of about 650 roles, that catch-up is about 16 minutes of extract and about an hour of judge on the live backend (`claude_code`, the subscription, so no per-token bill). After it, each pull reads only the roles new to the cut. The recurring cost is a re-judge: changing the CV, a prompt, or the like or dislike text changes every judgement's input, so the whole cut is judged again, about an hour for 650 roles. A changed posting text re-judges that role only. Accepted: the re-judge takes a while but is correct, since the old judgements were made against the old text.
**Decided: extract and judge stay two calls.** Extract needs no CV and its location and remote answers feed the rescore before judge reads anything. Judge works per agent and role, with the CV in the system prompt.