Scale fit across each agent's run, and lower the starter prefer weights
With fit as (cos + 1) / 2 the real run spanned about 0.55 to 0.79, so a prefer gate at weight 0.2 moved a score more than the whole spread of fit. fit is now the cosine min-max scaled across the roles an agent scores in that run: the closest is 1, the farthest 0, a single role 1, and a role a require gate rules out stays out of the range. The starter agents' prefer weights drop to 0.05, enough to break a tie. A regression test pins the case: two close cosines that the old mapping let a 0.05 gate reorder. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
59a301c351
commit
8b246c3035
5 files changed
+132
-31
No files matched your search
@@ -14,7 +14,7 @@
|
||||
<label>Name <input type="text" id="a-name" required></label>
|
||||
<label>Intent <span class="hint">a CV paragraph, or what this search is for</span>
|
||||
<textarea id="a-intent" rows="5"></textarea></label>
|
||||
<label>Gates <span class="hint">JSON: [{"field": "place", "values": ["Berlin"], "mode": "require"}, {"field": "remote", "values": ["remote"], "mode": "prefer", "weight": 0.2}]</span>
|
||||
<label>Gates <span class="hint">JSON: [{"field": "place", "values": ["Berlin"], "mode": "require"}, {"field": "remote", "values": ["remote"], "mode": "prefer", "weight": 0.05}]</span>
|
||||
<textarea id="a-gates" rows="5" spellcheck="false">[]</textarea></label>
|
||||
<fieldset class="weights">
|
||||
<legend>Weights</legend>
|
||||
|
||||
Reference in new issue
Block a user