fix(agent): dynamically fallback from snapcompact to text summary on high CJK/non-ASCII rates

packages/coding-agent/src/session/agent-session.ts

@@ -7645,13 +7645,24 @@ export class AgentSession {
 			// both take the summarizer path (the latter loudly).
 			const wantsSnapcompact =
 				compactionPrep.kind !== "fromHook" && effectiveSettings.strategy === "snapcompact" && !customInstructions;
-			const snapcompactReady = wantsSnapcompact && this.model.input.includes("image");
+			let snapcompactReady = wantsSnapcompact && this.model.input.includes("image");
 			if (wantsSnapcompact && !snapcompactReady) {
 				this.emitNotice(
 					"warning",
 					`snapcompact needs a vision-capable model (${this.model.id} is text-only) — using an LLM summary instead`,
 					"compaction",
 				);
+			} else if (snapcompactReady) {
+				const text = snapcompact.serializeConversation(convertToLlm(preparation.messagesToSummarize));
+				const renderScan = snapcompact.scanRenderability(text);
+				if (!renderScan.isSafe) {
+					this.emitNotice(
+						"warning",
+						`snapcompact disabled: high non-ASCII rate detected (${(renderScan.unrenderableRatio * 100).toFixed(1)}%). Falling back to an LLM summary to prevent data loss.`,
+						"compaction",
+					);
+					snapcompactReady = false;
+				}
 			}
 
 			let summary: string;

packages/snapcompact/src/snapcompact.ts

@@ -989,6 +989,47 @@ export function normalize(text: string): string {
 	return out;
 }
 
+/**
+ * Scan text to determine the proportion of graphic characters that will hit the
+ * `?` fallback during {@link normalize}. Used as a preflight check to abort
+ * snapcompact and fall back to the text summarizer when the input is heavily
+ * non-renderable (e.g., CJK).
+ */
+export function scanRenderability(text: string): { isSafe: boolean; unrenderableRatio: number } {
+	const stripped = text.includes("\u001b") ? Bun.stripANSI(text) : text;
+	const collapsed = stripped
+		.replace(COLLAPSIBLE, run => (LINE_BREAK.test(run) ? NEWLINE_GLYPH : /[^\p{Cf}]/u.test(run) ? " " : ""))
+		.replace(EDGE_RUNS, "");
+	let totalGraphics = 0;
+	let fallbackCount = 0;
+	for (const ch of collapsed) {
+		const cp = ch.codePointAt(0) as number;
+		if ((cp >= 0x20 && cp < 0x7f) || (cp >= 0xa0 && cp <= 0xff)) {
+			totalGraphics++;
+			continue;
+		}
+		if (ch === DIM_ON || ch === DIM_OFF || ch === NEWLINE_GLYPH) {
+			continue;
+		}
+		const fold = CHAR_FOLD[ch];
+		if (fold !== undefined) {
+			totalGraphics++;
+		} else if (cp >= 0x2500 && cp <= 0x257f) {
+			totalGraphics++;
+		} else {
+			const folded = foldToAscii(ch);
+			if (folded !== undefined) {
+				totalGraphics++;
+			} else if (!UNRENDERABLE.test(ch)) {
+				totalGraphics++;
+				fallbackCount++;
+			}
+		}
+	}
+	const unrenderableRatio = totalGraphics > 0 ? fallbackCount / totalGraphics : 0;
+	return { isSafe: unrenderableRatio <= 0.05, unrenderableRatio };
+}
+
 // ============================================================================
 // Stopword dimming
 // ============================================================================

packages/snapcompact/test/snapcompact.test.ts

@@ -67,6 +67,36 @@ function makePreparation(
 	};
 }
 
+describe("scanRenderability", () => {
+	it("considers pure ASCII text safe", () => {
+		const res = snapcompact.scanRenderability("function hello() { return 'world'; }");
+		expect(res.isSafe).toBe(true);
+		expect(res.unrenderableRatio).toBe(0);
+	});
+
+	it("considers Latin-1 text safe", () => {
+		const res = snapcompact.scanRenderability("café résumé naïve");
+		expect(res.isSafe).toBe(true);
+		expect(res.unrenderableRatio).toBe(0);
+	});
+
+	it("detects high unrenderable rates in CJK text and marks it unsafe", () => {
+		// Mix of ASCII and CJK: "const a = '你好世界';"
+		// Total graphics: ~15. Unrenderable: 4. Ratio > 5% (0.05).
+		const res = snapcompact.scanRenderability("const a = '你好世界';");
+		expect(res.isSafe).toBe(false);
+		expect(res.unrenderableRatio).toBeGreaterThan(0.05);
+	});
+
+	it("ignores whitespace, ANSI, and zero-width markers in ratio calculations", () => {
+		// \u001b[31m is ANSI.
+		// \u000e \u000f are DIM markers.
+		const res = snapcompact.scanRenderability("\u001b[31mhello \u000e \u000f \n\t   world\u001b[0m");
+		expect(res.isSafe).toBe(true);
+		expect(res.unrenderableRatio).toBe(0);
+	});
+});
+
 describe("computeFileLists", () => {
 	it("drops scheme:// URLs from legacy fileOps before rendering <files>", () => {
 		const fileOps = snapcompact.createFileOps();