feat: reasoning level select (Off/Light/Moderate/High/Max)

Replace free-form reasoning_budget_tokens number input with a 5-level
select in both the edit form (local_llm.py) and add-model form
(local_llm.html). Values: 0 / 1024 / 4096 / 8192 / 32768 tokens.
Edit form pre-selects the stored value.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

cortex/routers/local_llm.py

@@ -211,6 +211,11 @@ def _render(username: str, success: str = "", error: str = "") -> str:
         cur_tools           = m.get("tools", True)
         cur_tags            = ", ".join(m.get("tags") or [])
         cur_reasoning_budget = m.get("reasoning_budget_tokens") or 0
+        _rb_levels = [(0, "Off — Non-think"), (1024, "Light"), (4096, "Moderate"), (8192, "High"), (32768, "Max")]
+        reasoning_opts = "".join(
+            f'<option value="{v}" {"selected" if cur_reasoning_budget == v else ""}>{lbl}</option>'
+            for v, lbl in _rb_levels
+        )
 
         model_rows += f'''
         <div class="model-row" id="model-{m["id"]}">
@@ -258,9 +263,11 @@ def _render(username: str, success: str = "", error: str = "") -> str:
                        title="Per-model tool loop cap. 0 = use the global default (orchestrator_max_rounds).">
               </div>
               <div class="field" style="flex:0 0 auto">
-                <label title="OpenRouter reasoning budget in tokens. 0 = no reasoning override (model default). Injects reasoning.budget_tokens into the API call.">Reasoning tokens</label>
+                <label title="Reasoning depth via OpenRouter's reasoning.budget_tokens. Off = Non-think. Light ~1k, Moderate ~4k, High ~8k, Max ~32k tokens.">Reasoning</label>
-                <input type="number" name="reasoning_budget_tokens" value="{cur_reasoning_budget}" min="0"
+                <select name="reasoning_budget_tokens"
-                       title="OpenRouter reasoning budget in tokens. 0 = disabled. E.g. 2048 for light thinking, 8192 for deep reasoning.">
+                        title="Reasoning depth via OpenRouter's reasoning.budget_tokens. Off = Non-think. Light ~1k, Moderate ~4k, High ~8k, Max ~32k tokens.">
+                  {reasoning_opts}
+                </select>
               </div>
               <div class="field" style="flex:0 0 auto">
                 <label title="Whether this model supports tool calling. If not supported, requests skip the tool loop entirely.">Tool calling</label>

cortex/static/local_llm.html

@@ -503,6 +503,17 @@
             <input type="number" name="max_rounds" value="0" min="0"
                    title="Per-model tool loop cap. 0 = use the global default (orchestrator_max_rounds).">
           </div>
+          <div class="field" style="flex:0 0 auto">
+            <label title="Reasoning depth via OpenRouter's reasoning.budget_tokens. Off = Non-think. Light ~1k, Moderate ~4k, High ~8k, Max ~32k tokens.">Reasoning</label>
+            <select name="reasoning_budget_tokens"
+                    title="Reasoning depth via OpenRouter's reasoning.budget_tokens. Off = Non-think. Light ~1k, Moderate ~4k, High ~8k, Max ~32k tokens.">
+              <option value="0" selected>Off — Non-think</option>
+              <option value="1024">Light</option>
+              <option value="4096">Moderate</option>
+              <option value="8192">High</option>
+              <option value="32768">Max</option>
+            </select>
+          </div>
           <div class="field" style="flex:0 0 auto">
             <label title="Whether this model supports tool calling. If not supported, requests skip the tool loop entirely.">Tool calling</label>
             <select name="tools"