daveadmin/dobetternorge-tools
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(tools): converge two-tier Quick/Pro selector onto .no fork

Browse Source 
Port the dobetterlegal-tools two-tier quality stack to dobetternorge.no:
QUALITY_TIERS registry + resolveTier (ToolModels), dbnToolsResolveToolRun
(bootstrap), tier read+charge in the 6 analytical endpoints, Quick/Pro
UI + payload.tier on the 6 tool pages/JS, and the bounded
corpusContextForSummarize RAG fix (per-passage trim + total budget +
reranker_enabled). Back-compat: requests without `tier` keep legacy
engine behavior.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
davegilligan
2026-06-15 12:23:46 +02:00
parent b217f18118
commit a8b1bb87a6
21 changed files with 339 additions and 103 deletions
Download Patch File Download Diff File Expand all files Collapse all files
advocate.php
+5 -5
View File
@@ -50,12 +50,12 @@ require_once __DIR__ . '/includes/layout.php';
<small id="advInputCount" class="adv-char-count">0 / 4,000</small>
</div>
<div class="control-row" id="advEngineControl">
<span class="control-label">Engine</span>
<label><input type="radio" name="advEngine" value="azure_mini" checked> &#x2601;&#xFE0F; Claude Haiku 4.5 <small class="control-hint">(fast · ~2-4 min)</small></label>
<label><input type="radio" name="advEngine" value="claude_sonnet"> &#x2601;&#xFE0F; Claude Sonnet 4.6 &#9733;&#9733; <small class="control-hint">(thorough · ~3-5 min)</small></label>
<div class="control-row" id="advTierControl">
<span class="control-label">Quality</span>
<label><input type="radio" name="advTier" value="quick" checked> Quick &#9733; <small class="control-hint">(Claude Haiku · fast · 3 credits)</small></label>
<label><input type="radio" name="advTier" value="pro"> Pro <small class="control-hint">(Claude Sonnet · best · 6 credits)</small></label>
</div>
<p class="upload-hint">Both engines run on AWS Bedrock via Claude. Most of the time is spent on multiple question-answering passes — 6–10 sub-questions each requiring a full retrieval and answer cycle. Haiku is faster and handles most cases well. Sonnet produces a more thorough brief with deeper ECHR precedent analysis and stronger multi-party argumentation.</p>
<p class="upload-hint">Most of the time is spent on multiple question-answering passes — 6–10 sub-questions each requiring a full retrieval and answer cycle. Quick uses Claude Haiku 4.5 — faster and handles most cases well (3 credits). Pro uses Claude Sonnet 4.6 — a more thorough brief with deeper ECHR precedent analysis and stronger multi-party argumentation (6 credits).</p>
<div class="dr-slice-section">
<p class="control-label">Corpus slices</p>