diff --git a/packages/ai/CHANGELOG.md b/packages/ai/CHANGELOG.md
index e4d9ced06..bb1087258 100644
--- a/packages/ai/CHANGELOG.md
+++ b/packages/ai/CHANGELOG.md
@@ -8,6 +8,7 @@
 
 ### Fixed
 
+- Fixed OpenAI Responses streaming to tolerate null message content from OpenAI-compatible servers before tool calls ([#5819](https://github.com/earendil-works/pi/issues/5819)).
 - Fixed Z.AI GLM-5.2 thinking requests to send `reasoning_effort` with the provider's `high`/`max` effort mapping ([#5770](https://github.com/earendil-works/pi/issues/5770)).
 - Fixed Google and `google-vertex` Gemini model metadata to map `latest` aliases to the current models, add Gemini 3.5 Flash for Vertex, correct Gemini 2.5 Flash Vertex cache pricing, and remove shut-down Vertex preview models ([#5761](https://github.com/earendil-works/pi/issues/5761)).
 - Fixed Moonshot AI China model metadata to include Kimi K2.7 Code, and omitted unsupported thinking-off payloads for Kimi K2.7 Code models ([#5760](https://github.com/earendil-works/pi/issues/5760)).
diff --git a/packages/ai/src/providers/openai-responses-shared.ts b/packages/ai/src/providers/openai-responses-shared.ts
index c006c284b..6fd59a443 100644
--- a/packages/ai/src/providers/openai-responses-shared.ts
+++ b/packages/ai/src/providers/openai-responses-shared.ts
@@ -456,7 +456,8 @@ export async function processResponsesStream<TApi extends Api>(
 				});
 				currentBlock = null;
 			} else if (item.type === "message" && currentBlock?.type === "text") {
-				currentBlock.text = item.content.map((c) => (c.type === "output_text" ? c.text : c.refusal)).join("");
+				currentBlock.text =
+					item.content?.map((c) => (c.type === "output_text" ? c.text : c.refusal)).join("") || "";
 				currentBlock.textSignature = encodeTextSignatureV1(item.id, item.phase ?? undefined);
 				stream.push({
 					type: "text_end",