Add Quick mode (nova-lite/Bedrock) as 3rd tier for timeline tool

Timeline now offers Quick/Standard/Deep: nova_lite routes to Amazon
Bedrock nova-lite via LiteLLM (1 credit, ~2s faster), azure_mini stays
gpt-4o-mini (1 credit), azure_full stays gpt-4o (2 credits, Pro only).
ToolModels tier rules: free→nova_lite only, plus→quick/standard,
pro→all three.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-05-25 10:26:07 +02:00
parent 1d1bbeb69f
commit f00d3d68e5
6 changed files with 24 additions and 16 deletions
+5 -4
View File
@@ -24,11 +24,12 @@ require_once __DIR__ . '/includes/layout.php';
</div>
<div class="control-row" id="timelineEngineControl">
<span class="control-label" data-i18n="timelineEngine">Engine</span>
<label><input type="radio" name="timelineEngine" value="azure_mini" checked id="timelineEngineAzureMini"> <span data-i18n="timelineEngineAzureMini">Azure gpt-4o-mini</span> &#9733; <small class="control-hint">(fast)</small></label>
<label><input type="radio" name="timelineEngine" value="azure_full" id="timelineEngineAzureFull"> <span data-i18n="timelineEngineAzureFull">Azure gpt-4o</span> <small class="control-hint">(best)</small></label>
<span class="control-label" data-i18n="timelineEngine">Mode</span>
<label><input type="radio" name="timelineEngine" value="nova_lite" id="timelineEngineNovaLite"> <span>Quick</span> <small class="control-hint">(nova-lite · 1 credit · fastest)</small></label>
<label><input type="radio" name="timelineEngine" value="azure_mini" checked id="timelineEngineAzureMini"> <span data-i18n="timelineEngineAzureMini">Standard</span> &#9733; <small class="control-hint">(gpt-4o-mini · 1 credit)</small></label>
<label><input type="radio" name="timelineEngine" value="azure_full" id="timelineEngineAzureFull"> <span data-i18n="timelineEngineAzureFull">Deep</span> <small class="control-hint">(gpt-4o · 2 credits · Pro)</small></label>
</div>
<p class="upload-hint" data-i18n="timelineEngineHint">Azure engines use your BNL Azure credits. GPU runs the local LiteLLM proxy on cuttlefish.</p>
<p class="upload-hint" data-i18n="timelineEngineHint">Quick uses Amazon Bedrock nova-lite (fast, cheap). Standard and Deep use Azure OpenAI.</p>
<details class="advanced-panel" id="timelineAdvanced">
<summary class="advanced-toggle" data-i18n="timelineAdvancedToggle">Advanced settings</summary>