diff --git a/frontend/src/lib/components/copilot/chat/AIChatModelSettings.svelte b/frontend/src/lib/components/copilot/chat/AIChatModelSettings.svelte
index 8fcc610e3a..7122a9fd0e 100644
--- a/frontend/src/lib/components/copilot/chat/AIChatModelSettings.svelte
+++ b/frontend/src/lib/components/copilot/chat/AIChatModelSettings.svelte
@@ -247,16 +247,20 @@
 				}))
 			}
 		],
-		reasoning: {
-			provider: providerModel.provider as AIProvider,
-			model: providerModel.model,
-			value: providerModel.reasoning,
-			offToken: REASONING_OFF,
-			// The copilot fills an unset effort in before it calls the provider, so unset
-			// really does run at the default level and the button may name it.
-			sendsDefaultWhenUnset: true,
-			onSelect: selectReasoning
-		},
+		// Silent where the registry has no rules for the provider: claiming the model cannot
+		// think would be a guess, and the row saying so is the only thing that would render.
+		reasoning: getReasoningCapability(providerModel.provider, providerModel.model).known
+			? {
+					provider: providerModel.provider as AIProvider,
+					model: providerModel.model,
+					value: providerModel.reasoning,
+					offToken: REASONING_OFF,
+					// The copilot fills an unset effort in before it calls the provider, so unset
+					// really does run at the default level and the button may name it.
+					sendsDefaultWhenUnset: true,
+					onSelect: selectReasoning
+				}
+			: undefined,
 		// A reading preference rather than a model parameter: it applies to every chat in
 		// this browser, including thinking already in the transcript. No close(): flipping
 		// it should not dismiss the menu.
diff --git a/frontend/src/lib/components/copilot/chatModelSettings.ts b/frontend/src/lib/components/copilot/chatModelSettings.ts
index ac7c202fd7..0dda8d0e2f 100644
--- a/frontend/src/lib/components/copilot/chatModelSettings.ts
+++ b/frontend/src/lib/components/copilot/chatModelSettings.ts
@@ -84,13 +84,18 @@ export const REASONING_PROVIDER_DEFAULT = 'default'
  * level. Dropped rather than carried because a model that cannot think at that level either
  * rejects the request or quietly runs at another one, and the button would name a level the
  * run never used. Off survives only onto a model that can truly disable.
+ *
+ * A model the registry has no rules for keeps whatever it had: dropping on `supported:
+ * false` would discard a real setting on the strength of never having heard of the
+ * provider, and nothing would draw a control to put it back.
  */
 export function carriedReasoning(
 	current: string | undefined,
 	offToken: string | undefined,
-	capability: { levels: string[]; canDisable: boolean }
+	capability: { levels: string[]; canDisable: boolean; known: boolean }
 ): string | undefined {
 	if (current === undefined || current === '') return undefined
+	if (!capability.known) return current
 	if (offToken !== undefined && current === offToken) {
 		return capability.canDisable ? current : undefined
 	}
diff --git a/frontend/src/lib/components/flows/conversations/flowChatViewHost.svelte.ts b/frontend/src/lib/components/flows/conversations/flowChatViewHost.svelte.ts
index 2600fa06be..7b1ca6c46a 100644
--- a/frontend/src/lib/components/flows/conversations/flowChatViewHost.svelte.ts
+++ b/frontend/src/lib/components/flows/conversations/flowChatViewHost.svelte.ts
@@ -16,6 +16,7 @@ import type { AttachedTextFile } from '$lib/components/copilot/chat/textFileUtil
 import { HelpersService } from '$lib/gen'
 import { sendUserToast } from '$lib/toast'
 import { randomUUID } from '$lib/utils/uuid'
+import { turnFailed } from './turnTranscript'
 import {
 	attachmentsToMessageInputs,
 	MessageInputsStore,
@@ -134,27 +135,6 @@ function toDisplayMessage(
 	}
 }
 
-/**
- * Whether the turn a user message started ended without an answer.
- *
- * Read from the turn's last row and no other. A tool that fails mid-turn is handed back to
- * the agent, which routinely recovers and answers, so an unsuccessful tool row says nothing
- * about the turn — and this drives the Retry button, which in the copilot means "the request
- * never went through" rather than "something inside it went wrong". Offering it for a turn
- * that answered would invite running the whole flow a second time, side effects and all.
- */
-function turnFailed(messages: ChatMessage[], userIndex: number): boolean {
-	let last: ChatMessage | undefined
-	for (let i = userIndex + 1; i < messages.length; i++) {
-		const message = messages[i]
-		if (message.message_type === 'user') break
-		// Still going, so the turn has no outcome to report yet.
-		if (message.streaming || message.loading) return false
-		last = message
-	}
-	return last?.success === false
-}
-
 /**
  * Renders a flow run's conversation through the AI session chat components. The
  * turn itself is a flow job, so everything the copilot's own loop owns — context
diff --git a/frontend/src/lib/components/flows/conversations/turnTranscript.test.ts b/frontend/src/lib/components/flows/conversations/turnTranscript.test.ts
index 1def903a85..c8dfdb2325 100644
--- a/frontend/src/lib/components/flows/conversations/turnTranscript.test.ts
+++ b/frontend/src/lib/components/flows/conversations/turnTranscript.test.ts
@@ -1,5 +1,12 @@
 import { describe, expect, it } from 'vitest'
-import { appendRevealed, applyStreamEvent, emptyTurnState, type TurnStep } from './turnTranscript'
+import {
+	appendRevealed,
+	applyStreamEvent,
+	emptyTurnState,
+	turnFailed,
+	type TurnStep
+} from './turnTranscript'
+import type { ChatMessage } from './FlowChatManager.svelte'
 import type { StreamEvent } from '$lib/components/chat/utils'
 
 function start(): TurnStep {
@@ -75,3 +82,55 @@ describe('turn transcript', () => {
 		expect(step.rows[0].streaming).toBe(true)
 	})
 })
+
+/**
+ * Gates the Retry button, which on a flow re-runs the whole thing — side effects included —
+ * so it has to mean "this turn produced no answer", not "something inside it went wrong".
+ */
+describe('turnFailed', () => {
+	const row = (over: Partial<ChatMessage>): ChatMessage =>
+		({ id: 'x', message_type: 'assistant', content: '', ...over }) as ChatMessage
+
+	it('is false when a tool failed but the agent went on to answer', () => {
+		const messages = [
+			row({ message_type: 'user' }),
+			row({ message_type: 'tool', success: false }),
+			row({ message_type: 'assistant', success: true })
+		]
+		expect(turnFailed(messages, 0)).toBe(false)
+	})
+
+	it('is true when the turn ends on a failure', () => {
+		const messages = [
+			row({ message_type: 'user' }),
+			row({ message_type: 'tool', success: true }),
+			row({ message_type: 'assistant', success: false })
+		]
+		expect(turnFailed(messages, 0)).toBe(true)
+	})
+
+	it('reports nothing while the turn is still running', () => {
+		const messages = [
+			row({ message_type: 'user' }),
+			row({ message_type: 'tool', success: false }),
+			row({ message_type: 'assistant', streaming: true })
+		]
+		expect(turnFailed(messages, 0)).toBe(false)
+	})
+
+	// The window stops at the next user message, so a later turn's failure is not this one's.
+	it('does not read past the next user message', () => {
+		const messages = [
+			row({ message_type: 'user' }),
+			row({ message_type: 'assistant', success: true }),
+			row({ message_type: 'user' }),
+			row({ message_type: 'assistant', success: false })
+		]
+		expect(turnFailed(messages, 0)).toBe(false)
+		expect(turnFailed(messages, 2)).toBe(true)
+	})
+
+	it('is false for a turn that has produced nothing yet', () => {
+		expect(turnFailed([row({ message_type: 'user' })], 0)).toBe(false)
+	})
+})
diff --git a/frontend/src/lib/components/flows/conversations/turnTranscript.ts b/frontend/src/lib/components/flows/conversations/turnTranscript.ts
index 547672fbf1..52b2a2bf35 100644
--- a/frontend/src/lib/components/flows/conversations/turnTranscript.ts
+++ b/frontend/src/lib/components/flows/conversations/turnTranscript.ts
@@ -161,3 +161,24 @@ export function applyStreamEvent(
 			return step
 	}
 }
+
+/**
+ * Whether the turn a user message started ended without an answer.
+ *
+ * Read from the turn's last row and no other. A tool that fails mid-turn is handed back to
+ * the agent, which routinely recovers and answers, so an unsuccessful tool row says nothing
+ * about the turn — and this drives the Retry button, which in the copilot means "the request
+ * never went through" rather than "something inside it went wrong". Offering it for a turn
+ * that answered would invite running the whole flow a second time, side effects and all.
+ */
+export function turnFailed(messages: ChatMessage[], userIndex: number): boolean {
+	let last: ChatMessage | undefined
+	for (let i = userIndex + 1; i < messages.length; i++) {
+		const message = messages[i]
+		if (message.message_type === 'user') break
+		// Still going, so the turn has no outcome to report yet.
+		if (message.streaming || message.loading) return false
+		last = message
+	}
+	return last?.success === false
+}