completion-kit 0.5.9 → 0.5.11

data/app/views/completion_kit/api_reference/_body.html.erb

@@ -2,6 +2,12 @@
   token = local_assigns.fetch(:token, "YOUR_TOKEN")
   real_token = local_assigns.fetch(:real_token, nil)
   published_prompts = local_assigns.fetch(:published_prompts, [])
+  recent_runs = local_assigns.fetch(:recent_runs, [])
+  datasets = local_assigns.fetch(:datasets, [])
+  metrics = local_assigns.fetch(:metrics, [])
+  metric_groups = local_assigns.fetch(:metric_groups, [])
+  tags = local_assigns.fetch(:tags, [])
+  provider_credentials = local_assigns.fetch(:provider_credentials, [])
 %>
 <div class="ck-api-tabs">
   <input type="radio" name="ck-api-tab" id="ck-tab-mcp" class="ck-api-tabs__radio" checked>
@@ -86,28 +92,11 @@
         <p class="ck-api-method"><span class="ck-chip ck-chip--soft">GET</span> /api/v1/prompts/:id</p>
         <p class="ck-meta-copy">Get a single prompt by ID.</p>
       </div>
-      <% if published_prompts.any? %>
-        <div class="ck-api-endpoint" style="padding-top: 1rem;">
-          <p class="ck-kicker" style="margin-bottom: 0.5rem;">Your published prompts</p>
-          <% published_prompts.each do |p| %>
-            <div class="ck-api-prompt-card">
-              <div class="ck-api-prompt-card__top">
-                <div>
-                  <strong class="ck-api-prompt-card__name"><%= p.name %></strong>
-                  <% if p.description.present? %>
-                    <p class="ck-api-prompt-card__desc"><%= p.description %></p>
-                  <% end %>
-                </div>
-                <span class="ck-chip" style="text-transform: none; flex-shrink: 0;"><%= p.llm_model %></span>
-              </div>
-              <div class="ck-api-prompt-card__url">
-                <code class="ck-endpoint__url" id="prompt_ep_<%= p.id %>"><%= base_url %>/api/v1/prompts/<%= p.slug %></code>
-                <button type="button" class="ck-icon-btn" title="Copy endpoint" aria-label="Copy endpoint URL" onclick="navigator.clipboard.writeText(document.getElementById('prompt_ep_<%= p.id %>').textContent)"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16" fill="currentColor" width="14" height="14" aria-hidden="true"><path d="M0 6.75C0 5.784.784 5 1.75 5h1.5a.75.75 0 0 1 0 1.5h-1.5a.25.25 0 0 0-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 0 0 .25-.25v-1.5a.75.75 0 0 1 1.5 0v1.5A1.75 1.75 0 0 1 9.25 16h-7.5A1.75 1.75 0 0 1 0 14.25Z"/><path d="M5 1.75C5 .784 5.784 0 6.75 0h7.5C15.216 0 16 .784 16 1.75v7.5A1.75 1.75 0 0 1 14.25 11h-7.5A1.75 1.75 0 0 1 5 9.25Zm1.75-.25a.25.25 0 0 0-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 0 0 .25-.25v-7.5a.25.25 0 0 0-.25-.25Z"/></svg></button>
-              </div>
-            </div>
-          <% end %>
-        </div>
-      <% end %>
+      <%= render "completion_kit/api_reference/resource_list", title: "Your published prompts",
+            items: published_prompts.map { |p|
+              { name: p.name, subtitle: p.description, meta: p.llm_model,
+                url: "#{base_url}/api/v1/prompts/#{p.slug}", dom_id: "prompt_ep_#{p.id}" }
+            } %>
       <div class="ck-api-endpoint">
         <p class="ck-api-method"><span class="ck-chip ck-chip--soft">PATCH</span> /api/v1/prompts/:id</p>
         <p class="ck-meta-copy">Update a prompt. Accepts same params as create.</p>
@@ -132,7 +121,7 @@
       <div class="ck-api-endpoint">
         <p class="ck-api-method"><span class="ck-chip ck-chip--soft">POST</span> /api/v1/runs</p>
         <p class="ck-meta-copy">Create a new run.</p>
-        <p class="ck-api-params"><strong>Required:</strong>&ensp;<code>prompt_id</code>&emsp;<strong>Optional:</strong>&ensp;<code>name</code>, <code>dataset_id</code>, <code>metric_ids</code>, <code>judge_model</code></p>
+        <p class="ck-api-params"><strong>Optional:</strong>&ensp;<code>name</code>, <code>prompt_id</code>, <code>dataset_id</code>, <code>metric_ids</code>, <code>judge_model</code>, <code>output_column</code> (judge-only: omit <code>prompt_id</code> and grade a dataset column instead, default <code>actual_output</code>)</p>
         <%= render "completion_kit/api_reference/example", base_url: base_url, token: token, real_token: real_token, cmd: "curl -X POST #{base_url}/api/v1/runs \\\n  -H \"Authorization: Bearer #{token}\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"prompt_id\": 1, \"dataset_id\": 1, \"metric_ids\": [1, 2]}'" %>
       </div>
       <div class="ck-api-endpoint">
@@ -140,6 +129,11 @@
         <p class="ck-meta-copy">Get a run with status, progress, response count, and average score.</p>
         <%= render "completion_kit/api_reference/example", base_url: base_url, token: token, real_token: real_token, cmd: "curl #{base_url}/api/v1/runs/1 \\\n  -H \"Authorization: Bearer #{token}\"" %>
       </div>
+      <%= render "completion_kit/api_reference/resource_list", title: "Your recent runs",
+            items: recent_runs.map { |r|
+              { name: r.name, meta: r.status.to_s.titleize,
+                url: "#{base_url}/api/v1/runs/#{r.id}", dom_id: "run_ep_#{r.id}" }
+            } %>
       <div class="ck-api-endpoint">
         <p class="ck-api-method"><span class="ck-chip ck-chip--soft">POST</span> /api/v1/runs/:id/generate</p>
         <p class="ck-meta-copy">Start generating responses. Returns 202 Accepted. Poll the run to check progress.</p>
@@ -167,6 +161,11 @@
         <p class="ck-api-method"><span class="ck-chip ck-chip--soft">GET</span> /api/v1/runs/:run_id/responses/:id</p>
         <p class="ck-meta-copy">Get a single response with its review scores and feedback.</p>
       </div>
+      <%= render "completion_kit/api_reference/resource_list", title: "Your responses",
+            items: recent_runs.first(1).map { |r|
+              { name: "#{r.name} — responses",
+                url: "#{base_url}/api/v1/runs/#{r.id}/responses", dom_id: "responses_ep_#{r.id}" }
+            } %>
     </div>
 
     <div class="ck-api-tabs__panel">
@@ -186,6 +185,11 @@
         <p class="ck-api-method"><span class="ck-chip ck-chip--soft">GET</span>&ensp;<span class="ck-chip ck-chip--soft">PATCH</span>&ensp;<span class="ck-chip" style="color: var(--ck-danger);">DELETE</span> /api/v1/datasets/:id</p>
         <p class="ck-meta-copy">Get, update, or delete a dataset.</p>
       </div>
+      <%= render "completion_kit/api_reference/resource_list", title: "Your datasets",
+            items: datasets.map { |d|
+              { name: d.name, meta: pluralize([d.csv_data.to_s.lines.count - 1, 0].max, "row"),
+                url: "#{base_url}/api/v1/datasets/#{d.id}", dom_id: "dataset_ep_#{d.id}" }
+            } %>
     </div>
 
     <div class="ck-api-tabs__panel">
@@ -205,6 +209,11 @@
         <p class="ck-api-method"><span class="ck-chip ck-chip--soft">GET</span>&ensp;<span class="ck-chip ck-chip--soft">PATCH</span>&ensp;<span class="ck-chip" style="color: var(--ck-danger);">DELETE</span> /api/v1/metrics/:id</p>
         <p class="ck-meta-copy">Get, update, or delete a metric.</p>
       </div>
+      <%= render "completion_kit/api_reference/resource_list", title: "Your metrics",
+            items: metrics.map { |m|
+              { name: m.name, subtitle: m.instruction.presence&.truncate(100),
+                url: "#{base_url}/api/v1/metrics/#{m.id}", dom_id: "metric_ep_#{m.id}" }
+            } %>
     </div>
 
     <div class="ck-api-tabs__panel">
@@ -223,6 +232,11 @@
         <p class="ck-api-method"><span class="ck-chip ck-chip--soft">GET</span>&ensp;<span class="ck-chip ck-chip--soft">PATCH</span>&ensp;<span class="ck-chip" style="color: var(--ck-danger);">DELETE</span> /api/v1/metric_groups/:id</p>
         <p class="ck-meta-copy">Get, update, or delete a metric group. PATCH with <code>metric_ids</code> replaces all metric associations.</p>
       </div>
+      <%= render "completion_kit/api_reference/resource_list", title: "Your metric groups",
+            items: metric_groups.map { |g|
+              { name: g.name, subtitle: g.description.presence, meta: pluralize(g.metric_ids.size, "metric"),
+                url: "#{base_url}/api/v1/metric_groups/#{g.id}", dom_id: "metric_group_ep_#{g.id}" }
+            } %>
     </div>
 
     <div class="ck-api-tabs__panel">
@@ -243,6 +257,11 @@
         <p class="ck-api-method"><span class="ck-chip ck-chip--soft">GET</span>&ensp;<span class="ck-chip ck-chip--soft">PATCH</span>&ensp;<span class="ck-chip" style="color: var(--ck-danger);">DELETE</span> /api/v1/tags/:id</p>
         <p class="ck-meta-copy">Get, update, or delete a tag. PATCH accepts <code>name</code>. DELETE returns 204 No Content and removes all taggings for this tag.</p>
       </div>
+      <%= render "completion_kit/api_reference/resource_list", title: "Your tags",
+            items: tags.map { |t|
+              { name: t.name, meta: t.color,
+                url: "#{base_url}/api/v1/tags/#{t.id}", dom_id: "tag_ep_#{t.id}" }
+            } %>
       <div class="ck-api-endpoint" style="padding-top: 1rem;">
         <p class="ck-kicker" style="margin-bottom: 0.5rem;">Tagging resources</p>
         <p class="ck-meta-copy">Metrics, prompts, runs, and datasets accept a <code>tag_names</code> array on their create and update endpoints. Passing a name that does not yet exist silently creates the tag. On PATCH, the list replaces all existing tags for that record (omit the field to leave tags unchanged).</p>
@@ -277,6 +296,11 @@
         <p class="ck-api-method"><span class="ck-chip ck-chip--soft">GET</span>&ensp;<span class="ck-chip ck-chip--soft">PATCH</span>&ensp;<span class="ck-chip" style="color: var(--ck-danger);">DELETE</span> /api/v1/provider_credentials/:id</p>
         <p class="ck-meta-copy">Get, update, or delete a provider credential.</p>
       </div>
+      <%= render "completion_kit/api_reference/resource_list", title: "Your providers",
+            items: provider_credentials.map { |pc|
+              { name: ck_provider_label(pc.provider), meta: pluralize(pc.model_count, "model"),
+                url: "#{base_url}/api/v1/provider_credentials/#{pc.id}", dom_id: "provider_ep_#{pc.id}" }
+            } %>
     </div>
 
   </div>

data/app/views/completion_kit/api_reference/_resource_card.html.erb

@@ -0,0 +1,24 @@
+<%
+  name = local_assigns.fetch(:name)
+  url = local_assigns.fetch(:url)
+  dom_id = local_assigns.fetch(:dom_id)
+  subtitle = local_assigns[:subtitle]
+  meta = local_assigns[:meta]
+%>
+<div class="ck-api-prompt-card">
+  <div class="ck-api-prompt-card__top">
+    <div>
+      <strong class="ck-api-prompt-card__name"><%= name %></strong>
+      <% if subtitle.present? %>
+        <p class="ck-api-prompt-card__desc"><%= subtitle %></p>
+      <% end %>
+    </div>
+    <% if meta.present? %>
+      <span class="ck-chip" style="text-transform: none; flex-shrink: 0;"><%= meta %></span>
+    <% end %>
+  </div>
+  <div class="ck-api-prompt-card__url">
+    <code class="ck-endpoint__url" id="<%= dom_id %>"><%= url %></code>
+    <button type="button" class="ck-icon-btn" title="Copy endpoint" aria-label="Copy endpoint URL" onclick="navigator.clipboard.writeText(document.getElementById('<%= dom_id %>').textContent)"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16" fill="currentColor" width="14" height="14" aria-hidden="true"><path d="M0 6.75C0 5.784.784 5 1.75 5h1.5a.75.75 0 0 1 0 1.5h-1.5a.25.25 0 0 0-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 0 0 .25-.25v-1.5a.75.75 0 0 1 1.5 0v1.5A1.75 1.75 0 0 1 9.25 16h-7.5A1.75 1.75 0 0 1 0 14.25Z"/><path d="M5 1.75C5 .784 5.784 0 6.75 0h7.5C15.216 0 16 .784 16 1.75v7.5A1.75 1.75 0 0 1 14.25 11h-7.5A1.75 1.75 0 0 1 5 9.25Zm1.75-.25a.25.25 0 0 0-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 0 0 .25-.25v-7.5a.25.25 0 0 0-.25-.25Z"/></svg></button>
+  </div>
+</div>

data/app/views/completion_kit/api_reference/_resource_list.html.erb

@@ -0,0 +1,10 @@
+<%# title: heading text; items: array of hashes for _resource_card (name:, url:, dom_id:, subtitle?:, meta?:) %>
+<% items = Array(local_assigns.fetch(:items, [])) %>
+<% if items.any? %>
+  <div class="ck-api-endpoint" style="padding-top: 1rem;">
+    <p class="ck-kicker" style="margin-bottom: 0.5rem;"><%= local_assigns.fetch(:title) %></p>
+    <% items.each do |item| %>
+      <%= render "completion_kit/api_reference/resource_card", item %>
+    <% end %>
+  </div>
+<% end %>

data/app/views/completion_kit/api_reference/index.html.erb

@@ -20,4 +20,10 @@
       base_url: @base_url,
       token: ck_masked_token(@token),
       real_token: @token,
-      published_prompts: @published_prompts %>
+      published_prompts: @published_prompts,
+      recent_runs: @recent_runs,
+      datasets: @datasets,
+      metrics: @metrics,
+      metric_groups: @metric_groups,
+      tags: @tags,
+      provider_credentials: @provider_credentials %>

data/app/views/completion_kit/datasets/show.html.erb

@@ -8,6 +8,7 @@
     <h1 class="ck-title"><%= @dataset.name %></h1>
   </div>
   <div class="ck-actions">
+    <%= link_to "Download CSV", dataset_path(@dataset, format: :csv), class: ck_button_classes(:light, variant: :outline) %>
     <%= link_to "Edit", edit_dataset_path(@dataset), class: ck_button_classes(:light, variant: :outline) %>
   </div>
 </section>
@@ -67,23 +68,6 @@
 <% if @runs.any? %>
   <section class="ck-card--spaced">
     <p class="ck-kicker">Runs</p>
-
-    <table class="ck-results-table ck-runs-table" style="margin-top: 0.5rem;">
-      <thead>
-        <tr>
-          <th>Run</th>
-          <th>Responses</th>
-          <th>Metrics</th>
-          <th>Avg score</th>
-          <th>When</th>
-          <th></th>
-        </tr>
-      </thead>
-      <tbody>
-        <% @runs.each do |run| %>
-          <%= render "completion_kit/runs/row", run: run %>
-        <% end %>
-      </tbody>
-    </table>
+    <%= render "completion_kit/runs/table", runs: @runs %>
   </section>
 <% end %>

data/app/views/completion_kit/prompts/show.html.erb

@@ -17,6 +17,11 @@
       <code class="ck-endpoint__url" id="prompt_endpoint"><%= request.base_url %><%= api_v1_prompt_path(@prompt.slug) %></code>
       <button type="button" class="ck-icon-btn" title="Copy endpoint" onclick="navigator.clipboard.writeText(document.getElementById('prompt_endpoint').textContent)"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16" fill="currentColor" width="14" height="14"><path d="M0 6.75C0 5.784.784 5 1.75 5h1.5a.75.75 0 0 1 0 1.5h-1.5a.25.25 0 0 0-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 0 0 .25-.25v-1.5a.75.75 0 0 1 1.5 0v1.5A1.75 1.75 0 0 1 9.25 16h-7.5A1.75 1.75 0 0 1 0 14.25Z"/><path d="M5 1.75C5 .784 5.784 0 6.75 0h7.5C15.216 0 16 .784 16 1.75v7.5A1.75 1.75 0 0 1 14.25 11h-7.5A1.75 1.75 0 0 1 5 9.25Zm1.75-.25a.25.25 0 0 0-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 0 0 .25-.25v-7.5a.25.25 0 0 0-.25-.25Z"/></svg></button>
     </div>
+    <% if @prompt.tags.any? %>
+      <div class="tag-marks-row">
+        <%= render "completion_kit/tags/marks", tags: @prompt.tags %>
+      </div>
+    <% end %>
   </div>
 
   <div class="ck-actions">
@@ -26,13 +31,7 @@
   </div>
 </section>
 
-<% if @prompt.tags.any? %>
-  <div class="tag-marks-row tag-marks-row--header">
-    <%= render "completion_kit/tags/marks", tags: @prompt.tags %>
-  </div>
-<% end %>
-
-<section>
+<section class="ck-card--spaced">
   <div class="ck-prompt-preview__header">
     <p class="ck-kicker">Prompt</p>
     <% judged_run = @runs.select { |r| r.prompt_id == @prompt.id && r.status == "completed" }.find { |r| r.responses.joins(:reviews).exists? } %>
@@ -45,7 +44,7 @@
       <p class="ck-hint"><%= link_to "Run a test with judging configured", new_run_path(prompt_id: @prompt.id), class: "ck-link" %> to get AI-suggested improvements.</p>
     <% end %>
   </div>
-  <pre class="ck-code ck-code--dark"><%= @prompt.template %></pre>
+  <pre class="ck-code ck-code--dark ck-code--prompt"><%= @prompt.template %></pre>
 </section>
 
 <% versions = @prompt.family_versions.includes(runs: { responses: :reviews }).to_a %>
@@ -140,24 +139,7 @@
 <% if @runs.any? %>
   <section class="ck-card--spaced">
     <p class="ck-kicker">Runs</p>
-
-    <table class="ck-results-table ck-runs-table" style="margin-top: 0.5rem;">
-      <thead>
-        <tr>
-          <th>Run</th>
-          <th>Responses</th>
-          <th>Metrics</th>
-          <th>Avg score</th>
-          <th>When</th>
-          <th></th>
-        </tr>
-      </thead>
-      <tbody>
-        <% @runs.each do |run| %>
-          <%= render "completion_kit/runs/row", run: run %>
-        <% end %>
-      </tbody>
-    </table>
+    <%= render "completion_kit/runs/table", runs: @runs %>
   </section>
 <% end %>
 

data/app/views/completion_kit/responses/show.html.erb

@@ -1,6 +1,10 @@
 <ol class="ck-breadcrumb">
-  <li><%= link_to "Prompts", prompts_path %></li>
-  <li><%= link_to @run.prompt.name, prompt_path(@run.prompt) %></li>
+  <% if @run.prompt %>
+    <li><%= link_to "Prompts", prompts_path %></li>
+    <li><%= link_to @run.prompt.name, prompt_path(@run.prompt) %></li>
+  <% else %>
+    <li><%= link_to "Runs", runs_path %></li>
+  <% end %>
   <li><%= link_to @run.name, run_path(@run) %></li>
   <li>Response #<%= @response_number %></li>
 </ol>
@@ -30,20 +34,29 @@
     <span class="ck-run-config__key">Run</span>
     <%= link_to @run.name, run_path(@run), class: "ck-link" %>
   </div>
-  <div class="ck-run-config__row">
-    <span class="ck-run-config__key">Prompt</span>
-    <%= link_to @run.prompt.display_name, prompt_path(@run.prompt), class: "ck-link" %>
-  </div>
+  <% if @run.prompt %>
+    <div class="ck-run-config__row">
+      <span class="ck-run-config__key">Prompt</span>
+      <%= link_to @run.prompt.display_name, prompt_path(@run.prompt), class: "ck-link" %>
+    </div>
+  <% else %>
+    <div class="ck-run-config__row">
+      <span class="ck-run-config__key">Output</span>
+      <span>Dataset column <code><%= @run.output_column.presence || "actual_output" %></code></span>
+    </div>
+  <% end %>
   <% if @run.dataset %>
     <div class="ck-run-config__row">
       <span class="ck-run-config__key">Dataset</span>
       <%= link_to @run.dataset.name, dataset_path(@run.dataset), class: "ck-link" %>
     </div>
   <% end %>
-  <div class="ck-run-config__row">
-    <span class="ck-run-config__key">Model</span>
-    <span style="text-transform: none;"><%= @run.prompt.llm_model %></span>
-  </div>
+  <% if @run.prompt %>
+    <div class="ck-run-config__row">
+      <span class="ck-run-config__key">Model</span>
+      <span style="text-transform: none;"><%= @run.prompt.llm_model %></span>
+    </div>
+  <% end %>
   <% if @run.judge_model.present? %>
     <div class="ck-run-config__row">
       <span class="ck-run-config__key">Judge</span>
@@ -60,7 +73,9 @@
 <section class="ck-card--spaced">
   <div class="ck-prompt-preview__header">
     <p class="ck-kicker">Response</p>
-    <span class="ck-chip ck-chip--soft" style="text-transform: none;"><%= @run.prompt.llm_model %></span>
+    <% if @run.prompt %>
+      <span class="ck-chip ck-chip--soft" style="text-transform: none;"><%= @run.prompt.llm_model %></span>
+    <% end %>
   </div>
   <pre class="ck-code"><%= @response.response_text %></pre>
 </section>

data/app/views/completion_kit/runs/_form.html.erb

@@ -17,6 +17,17 @@
     </div>
 
     <div class="ck-field">
+      <label class="ck-checkbox-label">
+        <%= check_box_tag "run[judge_only]", "1", run.persisted? && run.judge_only?, id: "run_judge_only", class: "ck-checkbox" %>
+        <span class="ck-checkbox-label__box" aria-hidden="true"></span>
+        <span class="ck-checkbox-label__body">
+          <span class="ck-checkbox-label__text">Judge-only run</span>
+          <span class="ck-checkbox-label__hint">Grade an existing column on the dataset instead of running a prompt. Roughly half the LLM calls per row.</span>
+        </span>
+      </label>
+    </div>
+
+    <div class="ck-field" id="prompt-field">
       <%= form.label :prompt_id, "Prompt", class: "ck-label" %>
       <%= form.select :prompt_id,
             @prompts.map { |p|
@@ -43,6 +54,12 @@
       </div>
     </div>
 
+    <div class="ck-field" id="output-column-field" hidden>
+      <%= form.label :output_column, "Output column", class: "ck-label" %>
+      <%= form.text_field :output_column, value: run.output_column.presence || "actual_output", class: "ck-input", id: "run_output_column", placeholder: "actual_output" %>
+      <p class="ck-field-hint">Name of the dataset column whose value will be graded as the response. Defaults to <code>actual_output</code>.</p>
+    </div>
+
     <div class="ck-field" id="dataset-field">
       <%= form.label :dataset_id, "Dataset", class: "ck-label" %>
       <% if @datasets.empty? %>
@@ -93,10 +110,10 @@
 
     <div class="ck-field" id="metrics-field">
       <label class="ck-label">Metrics</label>
-      <p class="ck-field-hint" id="metrics-hint"></p>
       <% if @all_metrics.empty? %>
         <p class="ck-field-hint" style="color: var(--ck-warning);">No metrics yet.&ensp;<%= link_to "Create a metric", new_metric_path, class: "ck-link" %></p>
       <% else %>
+        <p class="ck-field-hint" id="metrics-hint"></p>
         <% if @metric_groups.any? %>
           <div class="ck-metric-groups">
             <span class="ck-metric-groups__label">Groups</span>
@@ -157,6 +174,15 @@
 function updateRunForm() {
   var promptEl = document.getElementById('run_prompt_id');
   var judgeEl = document.getElementById('run_judge_model');
+  var judgeOnlyEl = document.getElementById('run_judge_only');
+  var judgeOnly = !!(judgeOnlyEl && judgeOnlyEl.checked);
+  var promptField = document.getElementById('prompt-field');
+  var outputColumnField = document.getElementById('output-column-field');
+  var outputColumnEl = document.getElementById('run_output_column');
+  if (promptField) promptField.hidden = judgeOnly;
+  if (outputColumnField) outputColumnField.hidden = !judgeOnly;
+  if (judgeOnly && promptEl) promptEl.value = '';
+
   var prompt = promptEl ? promptEl.value : '';
   var judge = judgeEl ? judgeEl.value : '';
   var metrics = document.querySelectorAll('input[name="run[metric_ids][]"]:checked');
@@ -222,11 +248,28 @@ function updateRunForm() {
     }
   }
 
-  var valid = prompt !== '';
+  var valid;
+  if (judgeOnly) {
+    valid = !!dataset;
+    if (dataset && datasetEl && outputColumnEl) {
+      var headersJudge = (datasetEl.options[datasetEl.selectedIndex] && datasetEl.options[datasetEl.selectedIndex].dataset.headers ? datasetEl.options[datasetEl.selectedIndex].dataset.headers.split(/,\s*/) : []).filter(Boolean);
+      var col = (outputColumnEl.value || 'actual_output').trim();
+      if (col === '' || headersJudge.indexOf(col) === -1) {
+        valid = false;
+        if (datasetField) datasetField.className = 'ck-field ck-field--error';
+        if (datasetHint) datasetHint.textContent = "Dataset has no \"" + col + "\" column — pick a different output column or dataset.";
+      }
+    } else if (!dataset) {
+      if (datasetField) datasetField.className = 'ck-field ck-field--info';
+      if (datasetHint) datasetHint.textContent = 'Judge-only runs need a dataset that supplies the output column.';
+    }
+  } else {
+    valid = prompt !== '';
+    if (hasVars && !dataset) valid = false;
+    if (missingVars.length > 0) valid = false;
+  }
   if (judge && metrics.length === 0) valid = false;
   if (!judge && metrics.length > 0) valid = false;
-  if (hasVars && !dataset) valid = false;
-  if (missingVars.length > 0) valid = false;
   if (submitBtn) submitBtn.disabled = !valid;
 
   ckUpdateMetricGroupsState();
@@ -260,9 +303,13 @@ function ckUpdateMetricGroupsState() {
 var judgeEl = document.getElementById('run_judge_model');
 var promptEl = document.getElementById('run_prompt_id');
 var datasetEl = document.getElementById('run_dataset_id');
+var judgeOnlyEl = document.getElementById('run_judge_only');
+var outputColumnEl = document.getElementById('run_output_column');
 if (judgeEl) judgeEl.addEventListener('change', updateRunForm);
 if (promptEl) promptEl.addEventListener('change', updateRunForm);
 if (datasetEl) datasetEl.addEventListener('change', updateRunForm);
+if (judgeOnlyEl) judgeOnlyEl.addEventListener('change', updateRunForm);
+if (outputColumnEl) outputColumnEl.addEventListener('input', updateRunForm);
 document.querySelectorAll('input[name="run[metric_ids][]"]').forEach(function(cb) {
   cb.addEventListener('change', updateRunForm);
 });

data/app/views/completion_kit/runs/_row.html.erb

@@ -6,8 +6,12 @@
         <strong><%= run.name %></strong>
       </span>
       <div class="ck-runs-table__config">
-        <%= link_to run.prompt.name, prompt_path(run.prompt), class: "ck-runs-table__config-link", onclick: "event.stopPropagation();" %>
-        <span class="ck-runs-table__version">v<%= run.prompt.version_number %></span>
+        <% if run.prompt %>
+          <%= link_to run.prompt.name, prompt_path(run.prompt), class: "ck-runs-table__config-link", onclick: "event.stopPropagation();" %>
+          <span class="ck-runs-table__version">v<%= run.prompt.version_number %></span>
+        <% else %>
+          <span class="ck-runs-table__version">Judge-only</span>
+        <% end %>
         <% if run.dataset %>
           <span class="ck-runs-table__sep">·</span>
           <%= link_to run.dataset.name, dataset_path(run.dataset), class: "ck-runs-table__config-link", onclick: "event.stopPropagation();" %>

data/app/views/completion_kit/runs/_status_header.html.erb

@@ -19,7 +19,11 @@
         <span class="ck-status-badge__label"><%= run.status.upcase %></span>
       </span>
       <h1 class="ck-title"><%= run.name %></h1>
-      <p class="ck-meta-copy"><%= link_to run.prompt.display_name, prompt_path(run.prompt), class: "ck-link" %>&ensp;<span class="ck-chip" style="text-transform: none;"><%= run.prompt.llm_model %></span></p>
+      <% if run.prompt %>
+        <p class="ck-meta-copy"><%= link_to run.prompt.display_name, prompt_path(run.prompt), class: "ck-link" %>&ensp;<span class="ck-chip" style="text-transform: none;"><%= run.prompt.llm_model %></span></p>
+      <% else %>
+        <p class="ck-meta-copy">Judge-only run — grading column <code><%= run.output_column.presence || "actual_output" %></code><% if run.dataset %> on <%= link_to run.dataset.name, dataset_path(run.dataset), class: "ck-link" %><% end %></p>
+      <% end %>
     </div>
     <%= render "completion_kit/runs/actions", run: run %>
   </section>

data/app/views/completion_kit/runs/_table.html.erb

@@ -0,0 +1,19 @@
+<%# Renders a runs table. Locals: runs: enumerable of CompletionKit::Run. %>
+<% runs = local_assigns.fetch(:runs) %>
+<table class="ck-results-table ck-runs-table" style="margin-top: 0.5rem;">
+  <thead>
+    <tr>
+      <th>Run</th>
+      <th>Responses</th>
+      <th>Metrics</th>
+      <th>Avg score</th>
+      <th>When</th>
+      <th></th>
+    </tr>
+  </thead>
+  <tbody>
+    <% runs.each do |run| %>
+      <%= render "completion_kit/runs/row", run: run %>
+    <% end %>
+  </tbody>
+</table>

data/app/views/completion_kit/runs/edit.html.erb

@@ -1,6 +1,10 @@
 <ol class="ck-breadcrumb">
-  <li><%= link_to "Prompts", prompts_path %></li>
-  <li><%= link_to @run.prompt.name, prompt_path(@run.prompt) %></li>
+  <% if @run.prompt %>
+    <li><%= link_to "Prompts", prompts_path %></li>
+    <li><%= link_to @run.prompt.name, prompt_path(@run.prompt) %></li>
+  <% else %>
+    <li><%= link_to "Runs", runs_path %></li>
+  <% end %>
   <li><%= link_to @run.name, run_path(@run) %></li>
   <li>Edit</li>
 </ol>

data/app/views/completion_kit/runs/index.html.erb

@@ -14,23 +14,7 @@
       base_path: runs_path %>
 
 <% if @runs.any? %>
-  <table class="ck-results-table ck-runs-table">
-    <thead>
-      <tr>
-        <th>Run</th>
-        <th>Responses</th>
-        <th>Metrics</th>
-        <th>Avg score</th>
-        <th>When</th>
-        <th></th>
-      </tr>
-    </thead>
-    <tbody>
-      <% @runs.each do |run| %>
-        <%= render "row", run: run %>
-      <% end %>
-    </tbody>
-  </table>
+  <%= render "completion_kit/runs/table", runs: @runs %>
 <% elsif @selected_tags.any? %>
   <div class="ck-empty">
     <p>No runs match these tags. <%= link_to "Clear filters", runs_path, class: "ck-link" %>.</p>

data/app/views/completion_kit/runs/show.html.erb

@@ -59,24 +59,33 @@
   </div>
 </div>
 
-<div class="ck-prompt-preview">
-  <div class="ck-prompt-preview__header">
-    <p class="ck-kicker">Prompt</p>
-    <% latest_suggestion = @run.suggestions.order(created_at: :desc).first %>
-    <% if latest_suggestion %>
-      <%= link_to "View suggestion", suggestion_path(latest_suggestion, from: "run"), class: ck_button_classes(:light, variant: :outline) + " ck-button--sm" %>
-    <% elsif @run.status == "completed" && @run.responses.joins(:reviews).exists? %>
-      <%= button_to suggest_run_path(@run), method: :post, class: ck_button_classes(:light, variant: :outline) + " ck-button--sm", form_class: "inline-block" do %>
-        <%= heroicon_tag "sparkles", variant: :outline, class: "ck-magic-icon", "aria-hidden": "true" %>
-        Suggest improvements
+<% if @run.prompt %>
+  <div class="ck-prompt-preview">
+    <div class="ck-prompt-preview__header">
+      <p class="ck-kicker">Prompt</p>
+      <% latest_suggestion = @run.suggestions.order(created_at: :desc).first %>
+      <% if latest_suggestion %>
+        <%= link_to "View suggestion", suggestion_path(latest_suggestion, from: "run"), class: ck_button_classes(:light, variant: :outline) + " ck-button--sm" %>
+      <% elsif @run.status == "completed" && @run.responses.joins(:reviews).exists? %>
+        <%= button_to suggest_run_path(@run), method: :post, class: ck_button_classes(:light, variant: :outline) + " ck-button--sm", form_class: "inline-block" do %>
+          <%= heroicon_tag "sparkles", variant: :outline, class: "ck-magic-icon", "aria-hidden": "true" %>
+          Suggest improvements
+        <% end %>
       <% end %>
+    </div>
+    <p class="ck-prompt-preview__text" id="prompt_text"><%= @run.prompt.template %></p>
+    <% if @run.prompt.template.length > 200 %>
+      <button type="button" class="ck-disclosure-toggle" id="prompt_toggle" aria-expanded="false" aria-controls="prompt_text" onclick="var t=document.getElementById('prompt_text');var l=this;var expanded=t.classList.toggle('ck-prompt-preview__text--expanded');l.firstChild.textContent=expanded?'Show less':'Show more';l.setAttribute('aria-expanded',expanded?'true':'false')"><span>Show more</span></button>
     <% end %>
   </div>
-  <p class="ck-prompt-preview__text" id="prompt_text"><%= @run.prompt.template %></p>
-  <% if @run.prompt.template.length > 200 %>
-    <button type="button" class="ck-disclosure-toggle" id="prompt_toggle" aria-expanded="false" aria-controls="prompt_text" onclick="var t=document.getElementById('prompt_text');var l=this;var expanded=t.classList.toggle('ck-prompt-preview__text--expanded');l.firstChild.textContent=expanded?'Show less':'Show more';l.setAttribute('aria-expanded',expanded?'true':'false')"><span>Show more</span></button>
-  <% end %>
-</div>
+<% else %>
+  <div class="ck-prompt-preview">
+    <div class="ck-prompt-preview__header">
+      <p class="ck-kicker">Output source</p>
+    </div>
+    <p class="ck-prompt-preview__text">Dataset column <code><%= @run.output_column.presence || "actual_output" %></code> — no prompt generated these outputs.</p>
+  </div>
+<% end %>
 
 <% if @run.dataset %>
   <dialog id="dataset-preview-<%= @run.id %>" class="ck-modal" onclick="if(event.target===this)this.close()">

data/app/views/layouts/completion_kit/application.html.erb

@@ -6,7 +6,7 @@
   <%= csrf_meta_tags %>
   <%= csp_meta_tag %>
 
-  <%= favicon_link_tag "completion_kit/logo.svg", type: "image/svg+xml" %>
+  <%= favicon_link_tag "completion_kit/favicon.ico" %>
   <%= stylesheet_link_tag "completion_kit/application", media: "all" %>
   <%= javascript_include_tag "turbo", type: "module" %>
   <%= javascript_include_tag "completion_kit/application", defer: true %>
@@ -15,7 +15,7 @@
 <body class="ck-app">
   <header class="ck-topbar">
     <div class="ck-wrap ck-topbar__inner">
-      <%= link_to (main_app.respond_to?(:root_path) ? main_app.root_path : prompts_path), class: "ck-brand" do %><%= image_tag "completion_kit/logo.svg", alt: "CompletionKit", style: "height: 52px; width: auto; margin-bottom: 10px;" %> CompletionKit<% end %>
+      <%= link_to (main_app.respond_to?(:root_path) ? main_app.root_path : prompts_path), class: "ck-brand" do %><%= image_tag "completion_kit/logo.png", alt: "CompletionKit", style: "height: 64px; width: auto;" %><span class="ck-brand__name">Completion<span class="ck-brand__kit">Kit</span></span><% end %>
 
       <nav class="ck-nav">
         <% active = ->(path) { request.path.start_with?(path) ? ck_button_classes(:dark) : ck_button_classes(:light, variant: :outline) } %>

data/db/migrate/20260513000001_create_completion_kit_mcp_sessions.rb

@@ -0,0 +1,12 @@
+class CreateCompletionKitMcpSessions < ActiveRecord::Migration[8.1]
+  def change
+    create_table :completion_kit_mcp_sessions do |t|
+      t.string :session_id, null: false
+      t.datetime :expires_at, null: false
+      t.timestamps
+    end
+
+    add_index :completion_kit_mcp_sessions, :session_id, unique: true
+    add_index :completion_kit_mcp_sessions, :expires_at
+  end
+end