diff --git a/alembic/versions/0050_drop_think_enabled_setting.py b/alembic/versions/0050_drop_think_enabled_setting.py
new file mode 100644
index 0000000..9b58d0b
--- /dev/null
+++ b/alembic/versions/0050_drop_think_enabled_setting.py
@@ -0,0 +1,27 @@
+"""drop stored think_enabled rows — setting was removed
+
+Revision ID: 0050
+Revises: 0049
+Create Date: 2026-05-23
+
+The `think_enabled` user setting was retired with the chat+curator
+architecture: chat has tools=[] and curator hardcodes think=False, so
+the toggle was dead weight. Any rows already in `settings` for that
+key are now unread by the app; this migration clears them.
+"""
+from alembic import op
+
+
+revision = "0050"
+down_revision = "0049"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.execute("DELETE FROM settings WHERE key = 'think_enabled'")
+
+
+def downgrade() -> None:
+    # No-op. The setting is dead; restoring NULL rows wouldn't help.
+    pass
diff --git a/frontend/src/views/SettingsView.vue b/frontend/src/views/SettingsView.vue
index 37e23c5..b743e94 100644
--- a/frontend/src/views/SettingsView.vue
+++ b/frontend/src/views/SettingsView.vue
@@ -20,8 +20,6 @@ const savingTimezone = ref(false);
 const timezoneSaved = ref(false);
 const autoConsolidateTasks = ref(true);
 const savingAutoConsolidate = ref(false);
-const thinkEnabled = ref(false);
-const savingThinkEnabled = ref(false);
 
 async function saveAutoConsolidate() {
   savingAutoConsolidate.value = true;
@@ -36,18 +34,10 @@ async function saveAutoConsolidate() {
   }
 }
 
-async function saveThinkEnabled() {
-  savingThinkEnabled.value = true;
-  try {
-    await apiPut('/api/settings', {
-      think_enabled: thinkEnabled.value ? "true" : "false",
-    });
-  } catch {
-    toastStore.show('Failed to save setting', 'error');
-  } finally {
-    savingThinkEnabled.value = false;
-  }
-}
+// think_enabled setting removed 2026-05-23. The chat+curator architecture
+// has tools=[] on the chat model; think on a no-tools conversational pass
+// is pure latency cost. See generation_task.py:run_generation comment for
+// the full reasoning.
 
 function detectTimezone() {
   userTimezone.value = Intl.DateTimeFormat().resolvedOptions().timeZone;
@@ -826,9 +816,6 @@ onMounted(async () => {
   userTimezone.value = allSettings.user_timezone ?? "";
   // Default true if unset; explicit "false" disables auto-consolidation.
   autoConsolidateTasks.value = (allSettings.auto_consolidate_tasks ?? "true") !== "false";
-  // Default false: think mode is opt-in. Bench showed it costs 1-2 min/turn
-  // for unclear benefit; qwen3 users can re-enable if tool calls regress.
-  thinkEnabled.value = (allSettings.think_enabled ?? "false") === "true";
   chatRetentionDays.value = allSettings.chat_retention_days !== undefined
     ? Number(allSettings.chat_retention_days)
     : 90;
@@ -1569,22 +1556,6 @@ function formatUserDate(iso: string): string {
               </span>
             </p>
           </div>
-          <div class="field">
-            <label class="checkbox-label">
-              <input
-                type="checkbox"
-                v-model="thinkEnabled"
-                :disabled="savingThinkEnabled"
-                @change="saveThinkEnabled"
-              />
-              Enable model thinking
-            </label>
-            <p class="field-hint">
-              When on, the chat model runs in reasoning mode before responding.
-              Default off — bench data showed thinking adds 1–2 minutes per turn for unclear quality benefit.
-              Turn on for qwen3-family models if tool-call reliability drops without it.
-            </p>
-          </div>
         </div>
         <div class="actions">
           <button class="btn-save" @click="saveAssistant" :disabled="saving">
diff --git a/src/fabledassistant/services/generation_task.py b/src/fabledassistant/services/generation_task.py
index 9d3d3bd..51b3d97 100644
--- a/src/fabledassistant/services/generation_task.py
+++ b/src/fabledassistant/services/generation_task.py
@@ -246,15 +246,17 @@ async def run_generation(
     # Emit context event
     buf.append_event("context", {"context": context_meta})
 
-    # Think mode is per-user-setting (default off). Historically forced on for
-    # qwen3 because content-gated thinking (87fcaa6) exposed silent-generation
-    # failures on short tool-intent prompts. After moving to a model-family
-    # decoupled architecture, the bench data (May 2026) showed think costs
-    # 1-2 min/turn for unclear quality benefit; default off, opt in via
-    # the Settings UI. The generation_tool_log captures per-turn outcomes
-    # so reliability regressions surface empirically.
+    # Think mode is hardcoded off (2026-05-23). Historical context:
+    # originally forced on for qwen3's combined think+tools template;
+    # then made user-configurable when we decoupled the architecture;
+    # now removed entirely because in the chat+curator world there's no
+    # reason for the chat model to think. Chat has tools=[] — it just
+    # talks, and think on a no-tools conversational pass is pure
+    # latency cost (the May 2026 bench measured 1-2 min/turn for
+    # unclear quality benefit). The curator (services/curator.py) also
+    # already hardcodes think=False for its own reasons.
     think_requested = think
-    think = (await get_setting(user_id, "think_enabled", "false")).lower() == "true"
+    think = False
 
     t_start = time.monotonic()
     timing: dict = {