diff --git a/internal/tui/provider_wizard.go b/internal/tui/provider_wizard.go
index 6c2789af7..8f4ee8bb3 100644
--- a/internal/tui/provider_wizard.go
+++ b/internal/tui/provider_wizard.go
@@ -1959,12 +1959,49 @@ func (wizard *providerWizardState) filteredModels() []providerWizardModel {
 	return models
 }
 
+// A model Description is only a good row label when it reads like a display
+// NAME — "Grok 4.3" for x-ai/grok-4.3 — which is what the field is for, and why
+// the row prefers it over an ugly raw ID.
+//
+// Providers do not all honour that. Aggregators commonly return a prose blurb
+// instead ("Fast DeepSeek model for efficient chat, coding help, and agent
+// loops"), which fails as a label twice over: it overflows the row, and because
+// such blurbs are written per model FAMILY rather than per model, several
+// DIFFERENT models collapse to byte-identical rows. A picker then offers two
+// visually identical entries with the distinguishing ID visible only in the
+// detail line of whichever one is highlighted.
+//
+// providerWizardGenericModelDescription cannot catch these: it rejects
+// descriptions that are vague ("live model", "catalog default"), whereas these
+// are specific — just shared and sentence-shaped. So the test is shape, not
+// wording: a name is short and few-worded; anything longer is prose, and the ID
+// (unique by construction) makes the better label.
+const (
+	providerWizardMaxModelNameChars = 28
+	providerWizardMaxModelNameWords = 4
+)
+
+func providerWizardDescriptionIsDisplayName(description string) bool {
+	trimmed := strings.TrimSpace(description)
+	if trimmed == "" || providerWizardGenericModelDescription(trimmed) {
+		return false
+	}
+	if len(trimmed) > providerWizardMaxModelNameChars {
+		return false
+	}
+	return len(strings.Fields(trimmed)) <= providerWizardMaxModelNameWords
+}
+
 func (model providerWizardModel) displayLabel() string {
-	description := strings.TrimSpace(model.Description)
-	if description != "" && !providerWizardGenericModelDescription(description) {
-		return description
+	if providerWizardDescriptionIsDisplayName(model.Description) {
+		return strings.TrimSpace(model.Description)
+	}
+	if id := strings.TrimSpace(model.ID); id != "" {
+		return id
 	}
-	return model.ID
+	// ID-less sentinel rows built in currentModel ("model name required",
+	// "no matching models") would otherwise render blank.
+	return strings.TrimSpace(model.Description)
 }
 
 func (model providerWizardModel) secondaryText() string {
diff --git a/internal/tui/provider_wizard_test.go b/internal/tui/provider_wizard_test.go
index bbb32fc17..4d095849e 100644
--- a/internal/tui/provider_wizard_test.go
+++ b/internal/tui/provider_wizard_test.go
@@ -1787,3 +1787,37 @@ func providerWizardIDs(descriptors []providercatalog.Descriptor) []string {
 	}
 	return ids
 }
+
+// A provider that returns prose blurbs instead of display names must not
+// collapse distinct models into identical rows. Reproduces the reported picker
+// where two "Open-weight GPT model..." and two "Kimi multimodal agent model..."
+// rows were indistinguishable, with the ID visible only for the highlighted one.
+func TestProviderWizardModelRowsStayDistinctWithProseDescriptions(t *testing.T) {
+	wizard := &providerWizardState{
+		step:        providerWizardStepModel,
+		modelSource: "models.dev",
+		models: []providerWizardModel{
+			{ID: "gpt-oss-120b", Description: "Open-weight GPT model for self-hosted reasoning and instruction-following workloads"},
+			{ID: "gpt-oss-20b", Description: "Open-weight GPT model for self-hosted reasoning and instruction-following workloads"},
+			{ID: "kimi-k2-thinking", Description: "Kimi multimodal agent model for visual understanding, coding, and planning"},
+			{ID: "kimi-k2-instruct", Description: "Kimi multimodal agent model for visual understanding, coding, and planning"},
+			{ID: "x-ai/grok-4.3", Description: "Grok 4.3"},
+		},
+	}
+	view := plainRender(t, strings.Join(wizard.renderModelStep(96), "\n"))
+
+	// every prose-described model is identified by its unique ID
+	for _, id := range []string{"gpt-oss-120b", "gpt-oss-20b", "kimi-k2-thinking", "kimi-k2-instruct"} {
+		if !strings.Contains(view, id) {
+			t.Errorf("model %q is not identifiable in the list:\n%s", id, view)
+		}
+	}
+	// a genuine display name is still preferred over the raw id
+	if !strings.Contains(view, "Grok 4.3") {
+		t.Errorf("friendly display name was lost:\n%s", view)
+	}
+	// the prose blurb must not be a row label
+	if strings.Contains(view, "❯ Open-weight GPT model") {
+		t.Errorf("prose blurb still used as a row label:\n%s", view)
+	}
+}
diff --git a/internal/tui/sidebar.go b/internal/tui/sidebar.go
index 966debe35..13b87a14b 100644
--- a/internal/tui/sidebar.go
+++ b/internal/tui/sidebar.go
@@ -94,12 +94,26 @@ func (m model) sidebarAvailable() bool {
 	if widthTier(m.width) < tierMedium {
 		return false
 	}
-	// Full-screen overlays (setup, wizards, pickers, the empty-state suggestion
-	// list) take over the chat column and render at full width; suppress the
-	// second column while any is active so their geometry and mouse hit-testing
-	// stay full-width as before.
+	// Full-screen overlays (setup, wizards, pickers) take over the chat column and
+	// render at full width; suppress the second column while any is active so
+	// their geometry and mouse hit-testing stay full-width as before.
+	//
+	// The `/` command palette is deliberately NOT in this list. It is not a
+	// full-screen overlay: suggestionOverlay draws it via centerRenderedBlock at
+	// minInt(width, suggestionPaletteMaxWidth) — a centred box capped at 76 cells
+	// — floating over the chat column rather than replacing it. Suppressing the
+	// sidebar for it collapsed the whole layout on every keystroke of `/`: the
+	// plan panel dropped out of the sidebar and re-rendered inline at the bottom
+	// and the transcript re-wrapped to full width, which is at its most jarring
+	// mid-run with a live plan on screen. Since the sidebar already requires the
+	// medium tier (>= 80 cells) the palette is always strictly narrower than the
+	// chat column here, so the two never contend for the same cells.
+	//
+	// Mouse hit-testing is unaffected: sidebarLineAtMouse carries its own
+	// suggestionsActive() guard, so clicks still go to the palette and not to the
+	// sidebar rows underneath it.
 	if m.setup.visible || m.helpOverlay || m.leaderHelpOverlay || m.providerWizard != nil || m.mcpAddWizard != nil ||
-		m.mcpManager != nil || m.picker != nil || m.suggestionsActive() {
+		m.mcpManager != nil || m.picker != nil {
 		return false
 	}
 	// Home/welcome screen: stay single-column until there's real conversation, so
diff --git a/internal/tui/sidebar_test.go b/internal/tui/sidebar_test.go
index 45ffdac6a..2c0d15cc7 100644
--- a/internal/tui/sidebar_test.go
+++ b/internal/tui/sidebar_test.go
@@ -631,3 +631,58 @@ func TestTwoColumnTranscriptViewWidth(t *testing.T) {
 func stripSidebar(lines []string) string {
 	return ansiPattern.ReplaceAllString(strings.Join(lines, "\n"), "")
 }
+
+// The `/` command palette must NOT collapse the sidebar. It is a centred box
+// capped at suggestionPaletteMaxWidth floating over the chat column, not a
+// full-screen overlay — suppressing the second column for it dropped the plan
+// out of the sidebar and re-rendered it inline at the bottom on every `/`,
+// which is at its most disruptive mid-run with a live plan on screen. The
+// genuinely full-width overlays must still suppress it.
+func TestSidebarSurvivesCommandPalette(t *testing.T) {
+	base := func() model {
+		m := runningPlanModel(t, 3)
+		m.altScreen = true
+		m.height = 40
+		m.headerPrinted = true
+		m.transcript = append(m.transcript, transcriptRow{kind: rowToolCall, tool: "read_file", detail: "main.go"})
+		return m
+	}
+
+	m := base()
+	if !m.sidebarActive() {
+		t.Fatal("precondition: sidebar should be active for a wide alt-screen model with a plan")
+	}
+
+	// `/` palette open: sidebar stays, so the plan keeps its home and the layout
+	// does not reflow.
+	m.suggestions = []commandSuggestion{{Name: "/model", Desc: "Pick a model."}, {Name: "/plan", Desc: "Show planning mode status."}}
+	if !m.suggestionsActive() {
+		t.Fatal("precondition: suggestions should be active")
+	}
+	if !m.sidebarActive() {
+		t.Error("command palette must not collapse the sidebar")
+	}
+	if got := m.renderPinnedPlanPanel(m.chatColumnWidth(), 10); got != "" {
+		t.Errorf("plan must stay in the sidebar, not fall back to the pinned panel:\n%s", got)
+	}
+	// The palette never contends for the sidebar's cells: the two-column path
+	// renders it at width = chatColumnWidth, so it is centred inside the chat
+	// column and cannot overlap the sidebar.
+	chatW := m.chatColumnWidth()
+	for _, line := range strings.Split(plainRender(t, m.suggestionOverlay(chatW)), "\n") {
+		if w := lipgloss.Width(line); w > chatW {
+			t.Errorf("palette line is %d wide, wider than the chat column %d — it would overlap the sidebar", w, chatW)
+		}
+	}
+	// Clicks still belong to the palette, not the sidebar rows beneath it.
+	if _, ok := m.sidebarLineAtMouse(tea.MouseClickMsg{Button: tea.MouseLeft}); ok {
+		t.Error("sidebar must not take mouse hits while the palette is open")
+	}
+
+	// A genuinely full-width overlay still suppresses the sidebar.
+	full := base()
+	full.picker = &commandPicker{}
+	if full.sidebarActive() {
+		t.Error("a full-screen picker must still collapse the sidebar")
+	}
+}