fix: revert verbose conversation budget help to one concise line
This commit is contained in:
parent
6f63b8f538
commit
a7fb45515f
1 changed files with 1 additions and 3 deletions
|
|
@ -344,10 +344,8 @@
|
|||
</div>
|
||||
</div>
|
||||
<div>
|
||||
<strong>Conversation input budget — read-only server configuration</strong>
|
||||
<strong>Conversation input budget</strong>
|
||||
<p id="assistant-conversation-budget" role="status">Loading server budget metadata...</p>
|
||||
<p id="assistant-conversation-help" class="assistant-muted">Set by CLINICAL_ASSISTANT_CONVERSATION_CHARS, or the server default when unset; legacy saved settings are ignored. Counts all prior user/assistant text plus the new question using JavaScript string length (UTF-16 code units), not provider tokens. Over-budget requests stop before inference; no automatic clipping or summarization.</p>
|
||||
<p class="assistant-muted">Output limits: 2,600 tokens per text answer (5,000 on completion retry); image prompts clip at 5,000 UTF-16 code units.</p>
|
||||
</div>
|
||||
<section aria-labelledby="assistant-text-prompts-heading">
|
||||
<h4 id="assistant-text-prompts-heading">Clinical Assistant TEXT — system behavior</h4>
|
||||
|
|
|
|||
Loading…
Reference in a new issue