From 06a5a1a7aa31acfefeedf0d25422a7646c9994a6 Mon Sep 17 00:00:00 2001
From: Grass Zhang <grassX1998@outlook.com>
Date: Sun, 1 Feb 2026 11:30:44 +0000
Subject: [PATCH] fix: handle array content format in OpenAI messages

The OpenAI Chat Completions API allows message content to be either a
plain string or an array of content parts (e.g.
[{type: "text", text: "..."}]). When an upstream client sends array
content, the previous code passed it directly to template literals,
resulting in "[object Object]" being sent to Claude CLI.

Add extractContent() helper that normalises both string and array
formats into a single string, and update the OpenAIChatMessage type to
reflect the actual API spec.
---
 src/adapter/openai-to-cli.ts | 39 ++++++++++++++++++++++++++++++++----
 src/types/openai.ts          | 12 ++++++++++-
 2 files changed, 46 insertions(+), 5 deletions(-)

diff --git a/src/adapter/openai-to-cli.ts b/src/adapter/openai-to-cli.ts
index c8ecaa1..41af8a3 100644
--- a/src/adapter/openai-to-cli.ts
+++ b/src/adapter/openai-to-cli.ts
@@ -2,7 +2,10 @@
  * Converts OpenAI chat request format to Claude CLI input
  */
 
-import type { OpenAIChatRequest } from "../types/openai.js";
+import type {
+  OpenAIChatRequest,
+  OpenAIContentPart,
+} from "../types/openai.js";
 
 export type ClaudeModel = "opus" | "sonnet" | "haiku";
 
@@ -46,6 +49,32 @@ export function extractModel(model: string): ClaudeModel {
   return "opus";
 }
 
+/**
+ * Extract text from message content.
+ *
+ * OpenAI API allows content to be either a plain string or an array of
+ * content parts (e.g. [{type: "text", text: "..."}]). This function
+ * normalises both forms into a single string.
+ */
+export function extractContent(
+  content: string | OpenAIContentPart[],
+): string {
+  if (typeof content === "string") return content;
+
+  if (Array.isArray(content)) {
+    return content
+      .map((part) => {
+        if (typeof part === "string") return part;
+        if (part && typeof part === "object") return part.text ?? "";
+        return "";
+      })
+      .filter(Boolean)
+      .join("\n");
+  }
+
+  return String(content ?? "");
+}
+
 /**
  * Convert OpenAI messages array to a single prompt string for Claude CLI
  *
@@ -56,20 +85,22 @@ export function messagesToPrompt(messages: OpenAIChatRequest["messages"]): strin
   const parts: string[] = [];
 
   for (const msg of messages) {
+    const text = extractContent(msg.content);
+
     switch (msg.role) {
       case "system":
         // System messages become context instructions
-        parts.push(`<system>\n${msg.content}\n</system>\n`);
+        parts.push(`<system>\n${text}\n</system>\n`);
         break;
 
       case "user":
         // User messages are the main prompt
-        parts.push(msg.content);
+        parts.push(text);
         break;
 
       case "assistant":
         // Previous assistant responses for context
-        parts.push(`<previous_response>\n${msg.content}\n</previous_response>\n`);
+        parts.push(`<previous_response>\n${text}\n</previous_response>\n`);
         break;
     }
   }
diff --git a/src/types/openai.ts b/src/types/openai.ts
index c116658..706ef62 100644
--- a/src/types/openai.ts
+++ b/src/types/openai.ts
@@ -3,9 +3,19 @@
  * Used for Clawdbot integration
  */
 
+/**
+ * A single content part in a multi-part message.
+ * See: https://platform.openai.com/docs/api-reference/chat/create#chat-create-messages
+ */
+export interface OpenAIContentPart {
+  type: "text" | "image_url";
+  text?: string;
+  image_url?: { url: string; detail?: string };
+}
+
 export interface OpenAIChatMessage {
   role: "system" | "user" | "assistant";
-  content: string;
+  content: string | OpenAIContentPart[];
 }
 
 export interface OpenAIChatRequest {