Extract is bounded to the ranking: pull → embed → score → extract → score → summarise
The free stages run first and their score bounds the two model stages. Extract reads only the best extract.per_agent roles of each agent at extract.min_score or more, then score runs again so the gates read what it filled; summarise gets a min_score of its own. The cascade steps by position, since score is in it twice. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
1 parent
c4f2bcc0c9
commit
7db77e83a3
15 files changed
+215
-89
No files matched your search
@@ -126,7 +126,7 @@
|
||||
<h2>Runs</h2>
|
||||
<button type="button" id="pull-now" class="secondary">Pull now</button>
|
||||
</div>
|
||||
<p class="lede">Every 6 hours the pull reads every board, then extract fills in what each posting says, embed and score rank them, and summarise writes the summaries. Change the cadence below.</p>
|
||||
<p class="lede">Every 6 hours the pull reads every board, embed and score rank every role, extract fills in what the best postings say, score runs again with what it filled, and summarise writes the summaries. Change the cadence below.</p>
|
||||
|
||||
<h3>What is running</h3>
|
||||
{# The heading and the idle line are the app's: the element takes up no
|
||||
|
||||
Reference in new issue
Block a user