fix(coding-agent): show length stop errors

closes #4290

packages/coding-agent/CHANGELOG.md

@@ -4,6 +4,7 @@
 
 ### Fixed
 
+- Fixed assistant messages stopped by output length to show a visible incomplete-response error ([#4290](https://github.com/earendil-works/pi/issues/4290)).
 - Fixed `--no-session --session-id` so ephemeral CLI runs can use deterministic session IDs for provider cache affinity ([#6070](https://github.com/earendil-works/pi/issues/6070)).
 - Fixed disk BMP image files to be detected, converted to PNG, and attached through `read` and CLI `@file` inputs ([#6047](https://github.com/earendil-works/pi/issues/6047)).
 - Fixed auto-retry for provider stream errors that explicitly tell callers to retry the request ([#6019](https://github.com/earendil-works/pi/issues/6019)).

packages/coding-agent/src/modes/interactive/components/assistant-message.ts

@@ -121,21 +121,30 @@ export class AssistantMessageComponent extends Container {
 			}
 		}
 
-		// Check if aborted - show after partial content
-		// But only if there are no tool calls (tool execution components will show the error)
+		// Check if incomplete/failed - show after partial content.
+		// For aborted/error tool calls, tool execution components show the error.
+		// Length stops can happen before a tool call is complete, so surface them here too.
 		const hasToolCalls = message.content.some((c) => c.type === "toolCall");
 		this.hasToolCalls = hasToolCalls;
-		if (!hasToolCalls) {
+		if (message.stopReason === "length") {
+			this.contentContainer.addChild(new Spacer(1));
+			this.contentContainer.addChild(
+				new Text(
+					theme.fg(
+						"error",
+						"Error: Model stopped because it reached the maximum output token limit. The response may be incomplete.",
+					),
+					1,
+					0,
+				),
+			);
+		} else if (!hasToolCalls) {
 			if (message.stopReason === "aborted") {
 				const abortMessage =
 					message.errorMessage && message.errorMessage !== "Request was aborted"
 						? message.errorMessage
 						: "Operation aborted";
-				if (hasVisibleContent) {
-					this.contentContainer.addChild(new Spacer(1));
-				} else {
-					this.contentContainer.addChild(new Spacer(1));
-				}
+				this.contentContainer.addChild(new Spacer(1));
 				this.contentContainer.addChild(new Text(theme.fg("error", abortMessage), 1, 0));
 			} else if (message.stopReason === "error") {
 				const errorMsg = message.errorMessage || "Unknown error";

packages/coding-agent/test/assistant-message.test.ts

@@ -7,7 +7,10 @@ const OSC133_ZONE_START = "\x1b]133;A\x07";
 const OSC133_ZONE_END = "\x1b]133;B\x07";
 const OSC133_ZONE_FINAL = "\x1b]133;C\x07";
 
-function createAssistantMessage(content: AssistantMessage["content"]): AssistantMessage {
+function createAssistantMessage(
+	content: AssistantMessage["content"],
+	overrides: Partial<Pick<AssistantMessage, "stopReason">> = {},
+): AssistantMessage {
 	return {
 		role: "assistant",
 		content,
@@ -22,7 +25,7 @@ function createAssistantMessage(content: AssistantMessage["content"]): Assistant
 			totalTokens: 0,
 			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },
 		},
-		stopReason: "stop",
+		stopReason: overrides.stopReason ?? "stop",
 		timestamp: Date.now(),
 	};
 }
@@ -54,4 +57,18 @@ describe("AssistantMessageComponent", () => {
 		expect(rendered.includes(OSC133_ZONE_END)).toBe(false);
 		expect(rendered.includes(OSC133_ZONE_FINAL)).toBe(false);
 	});
+
+	test("renders length stops as visible errors", () => {
+		initTheme("dark");
+
+		const component = new AssistantMessageComponent(
+			createAssistantMessage([{ type: "thinking", thinking: "private reasoning" }], { stopReason: "length" }),
+			true,
+		);
+		const rendered = component.render(80).join("\n");
+
+		expect(rendered).toContain("Thinking...");
+		expect(rendered).toContain("maximum output token limit");
+		expect(rendered).toContain("response may be incomplete");
+	});
 });