@oh-my-pi/pi-coding-agent 15.10.1 → 15.10.2

package/src/web/search/providers/codex.ts

@@ -114,8 +114,34 @@ interface CodexResponse {
 	usage?: CodexUsage;
 }
 
+/**
+ * Known Codex "image placeholder" answers — short prose the assistant emits in
+ * place of a real answer when it produced a screenshot instead of text. These
+ * carry no information, so callers treat them as non-answers and advance the
+ * chain to a provider that returns text. Extend by adding the normalized
+ * literal below; no regex tuning required.
+ */
+const IMAGE_PLACEHOLDER_ANSWERS: ReadonlySet<string> = new Set([
+	"see attached image",
+	"attached image",
+	"see the attached image",
+	"see image",
+	"see image above",
+	"image above",
+	"see image below",
+	"image below",
+]);
+
 function isImagePlaceholderAnswer(text: string): boolean {
-	return text.trim().toLowerCase() === "(see attached image)";
+	// Strip surrounding brackets/quotes and trailing punctuation, lowercase,
+	// then match against the known-placeholder set.
+	const normalized = text
+		.trim()
+		.replace(/^[[("'`*_]+/, "")
+		.replace(/[\])"'`*_.!?]+$/, "")
+		.trim()
+		.toLowerCase();
+	return IMAGE_PLACEHOLDER_ANSWERS.has(normalized);
 }
 
 function addSource(sources: SearchSource[], source: SearchSource): void {
@@ -423,15 +449,18 @@ async function callCodexSearch(
 
 	const finalAnswer = answerParts.join("\n\n").trim();
 	const streamedAnswer = streamedAnswerParts.join("").trim();
-	if (isImagePlaceholderAnswer(finalAnswer) && streamedAnswer.length === 0) {
+	// Throw to advance the chain whenever Codex emitted nothing but image
+	// placeholder prose — including the case where the streamed delta itself
+	// is the placeholder (the model occasionally streams the same text it
+	// publishes as the final output_text).
+	const finalIsPlaceholder = finalAnswer.length > 0 && isImagePlaceholderAnswer(finalAnswer);
+	const streamedIsPlaceholder = streamedAnswer.length > 0 && isImagePlaceholderAnswer(streamedAnswer);
+	const hasFinalText = finalAnswer.length > 0 && !finalIsPlaceholder;
+	const hasStreamedText = streamedAnswer.length > 0 && !streamedIsPlaceholder;
+	if (!hasFinalText && !hasStreamedText && sources.length === 0) {
 		throw new SearchProviderError("codex", "Codex returned image-only response", 502);
 	}
-	const answer =
-		finalAnswer.length > 0 && !isImagePlaceholderAnswer(finalAnswer)
-			? finalAnswer
-			: streamedAnswer.length > 0
-				? streamedAnswer
-				: finalAnswer;
+	const answer = hasFinalText ? finalAnswer : hasStreamedText ? streamedAnswer : "";
 
 	// Fallback: when Codex omits url_citation annotations, scrape markdown links
 	// and bare URLs from the synthesized answer so callers still receive sources.