From 525346188be62e68d64bc9b06c491a18e81ad41b Mon Sep 17 00:00:00 2001
From: Jason <farion1231@gmail.com>
Date: Tue, 7 Jul 2026 12:57:11 +0800
Subject: [PATCH] fix(proxy): close media fallback gaps for Volcano GLM 5.2
 image 400s

Fixes #5025. The rectifier's media fallback missed Volcano Coding Plan's
GLM 5.2 on both paths:

- Preventive: known_text_only_model had glm-5.1 but not glm-5.2, so image
  blocks were forwarded verbatim. Added glm-5.2 as an exact tail match
  (not a prefix, to avoid stripping images from a future glm-5.2v
  multimodal variant following Zhipu's 4v/5v naming).
- Reactive: the upstream error "Model only support text input" never
  mentions image/media, so the mentions_image gate rejected it before
  hints ran; and the existing "only supports text" hint misses the
  gateway's missing third-person "s". Added a self-evident phrase list
  ("only support text" / "only supports text") that asserts a modality
  rejection on its own and bypasses the image-mention gate.

Includes regression tests using the verbatim #5025 error body and the
glm-5.2[1M] mapped-model form, plus a glm-5.2v negative assertion.
---
 src-tauri/src/proxy/media_sanitizer.rs | 43 +++++++++++++++++++++++++-
 1 file changed, 42 insertions(+), 1 deletion(-)

diff --git a/src-tauri/src/proxy/media_sanitizer.rs b/src-tauri/src/proxy/media_sanitizer.rs
index 95b2aa305..880b18fa4 100644
--- a/src-tauri/src/proxy/media_sanitizer.rs
+++ b/src-tauri/src/proxy/media_sanitizer.rs
@@ -63,6 +63,19 @@ pub fn is_unsupported_image_error(error: &ProxyError) -> bool {
 
     let message = extract_error_text(body);
     let message = message.to_ascii_lowercase();
+
+    // 自证性表述：这类短语本身就断言了"仅接受文本"，属于模态拒绝，无需再要求
+    // 错误提到 image/media 等字样——火山方舟等网关的报错是
+    // "Model only support text input"，全程不出现 image（issue #5025）。
+    // 国产网关的英文常缺三单 s，因此带 s / 不带 s 两种形式都要列。
+    const TEXT_ONLY_SELF_EVIDENT_HINTS: &[&str] = &["only support text", "only supports text"];
+    if TEXT_ONLY_SELF_EVIDENT_HINTS
+        .iter()
+        .any(|hint| message.contains(hint))
+    {
+        return true;
+    }
+
     let mentions_image = message.contains("image")
         || message.contains("vision")
         || message.contains("multimodal")
@@ -83,7 +96,6 @@ pub fn is_unsupported_image_error(error: &ProxyError) -> bool {
         "doesn't support",
         "do not support",
         "don't support",
-        "only supports text",
         "text only",
         "text-only",
         "invalid content type",
@@ -250,6 +262,9 @@ fn known_text_only_model(model: &str) -> bool {
         "deepseek-v4-flash",
         "deepseek-v4-pro",
         "glm-5.1",
+        // 精确匹配而非 TAIL_PREFIXES：智谱视觉版沿用 4v/5v 命名（glm-5.2v），
+        // 前缀匹配会误剥未来多模态变体的图片。
+        "glm-5.2",
         "kat-coder",
         "kat-coder-pro",
         "kat-coder-pro v1",
@@ -727,6 +742,32 @@ mod tests {
         assert!(is_unsupported_image_error(&error));
     }
 
+    #[test]
+    fn detects_text_only_errors_without_image_mention() {
+        // 火山方舟真实报错（issue #5025）：不含 image/media 等字样，且英文缺
+        // 三单 s——旧逻辑的 mentions_image 门与 "only supports text" 提示都拦不住。
+        let error = ProxyError::UpstreamError {
+            status: 400,
+            body: Some(
+                r#"{"error":{"message":"Model only support text input Request id: 021783"}}"#
+                    .to_string(),
+            ),
+        };
+
+        assert!(is_unsupported_image_error(&error));
+    }
+
+    #[test]
+    fn glm_52_is_classified_text_only() {
+        // issue #5025：火山 Coding Plan 的 GLM 5.2 是纯文本端点，
+        // 映射链 glm-5.2[1M] 归一化后尾部为 glm-5.2。
+        assert!(known_text_only_model("glm-5.2"));
+        assert!(known_text_only_model("GLM-5.2[1M]"));
+        assert!(known_text_only_model("zai-org/GLM-5.2"));
+        // 未来视觉版（智谱 4v/5v 命名惯例）不能被误判为纯文本。
+        assert!(!known_text_only_model("glm-5.2v"));
+    }
+
     #[test]
     fn ignores_non_image_errors() {
         let error = ProxyError::UpstreamError {