修复: 协议层与体验缺陷六件

- temperature 按模型适配,仅收 1 的模型不再 400
- 流式 error 帧不再被 choices 必填整帧丢弃
- 只读缓存写后失效
- git diff 中文截断撞 UTF-8 边界 panic
- 非视觉模型纯图片直接拒绝
- 全局快捷键补输入焦点守卫

crates/df-ai/src/openai_helpers.rs

@@ -274,6 +274,7 @@ pub(crate) fn apply_openai_sse(data: &str, usage_accum: &mut Option<TokenUsage>)
             usage: usage_accum.take(),
             error: None,
             reasoning_content: None,
+            truncated_by_max_tokens: false,
         };
     }
 
@@ -296,6 +297,7 @@ pub(crate) fn apply_openai_sse(data: &str, usage_accum: &mut Option<TokenUsage>)
                     usage: None,
                     error: Some(msg),
                     reasoning_content: None,
+                    truncated_by_max_tokens: false,
                 };
             }
             // 提取 usage（带 include_usage 时末段 chunk 携带，覆盖累积）
@@ -334,6 +336,9 @@ pub(crate) fn apply_openai_sse(data: &str, usage_accum: &mut Option<TokenUsage>)
                     choice.finish_reason.as_deref(),
                     Some("stop") | Some("tool_calls") | Some("length") | Some("content_filter")
                 );
+                // length = 输出被 max_tokens 截断:仍按正常终止收敛(finished=true),
+                // 但截断标志随 chunk 带出,消费方据此把该轮产出标记截断,不冒充完整。
+                let truncated_by_max_tokens = choice.finish_reason.as_deref() == Some("length");
 
                 let tool_calls = choice.delta.tool_calls.map(|tcs| {
                     // 缺 index 的增量缺省 0(单工具调用语义等价);但同帧多 call 且 index
@@ -379,6 +384,7 @@ pub(crate) fn apply_openai_sse(data: &str, usage_accum: &mut Option<TokenUsage>)
                     usage: usage_accum.clone(),
                     error: None,
                     reasoning_content: choice.delta.reasoning_content,
+                    truncated_by_max_tokens,
                 }
             } else {
                 // choices 为空 = usage-only chunk，不输出文本（usage 已累积），usage 一并带出
@@ -389,6 +395,7 @@ pub(crate) fn apply_openai_sse(data: &str, usage_accum: &mut Option<TokenUsage>)
                     usage: usage_accum.clone(),
                     error: None,
                     reasoning_content: None,
+                    truncated_by_max_tokens: false,
                 }
             }
         }
@@ -401,6 +408,7 @@ pub(crate) fn apply_openai_sse(data: &str, usage_accum: &mut Option<TokenUsage>)
                 usage: None,
                 error: None,
                 reasoning_content: None,
+                truncated_by_max_tokens: false,
             }
         }
     }
@@ -503,4 +511,32 @@ mod tests {
         );
         assert!(!chunk2.finished, "无终态 finish_reason 的普通 delta 不应终结");
     }
+
+    /// finish_reason=length:max_tokens 截断仍按正常终止收敛(finished=true),
+    /// 但截断标志必须随 chunk 带出(零信号会让腰斩报告冒充完整完成);
+    /// stop 等正常终态不置标志。
+    #[test]
+    fn finish_reason_length_carries_truncation_flag() {
+        let mut accum = None;
+        let chunk = apply_openai_sse(
+            r#"{"choices":[{"delta":{"content":"报告写到一半"},"finish_reason":"length"}]}"#,
+            &mut accum,
+        );
+        assert!(chunk.finished, "length 属正常终止");
+        assert!(chunk.truncated_by_max_tokens, "length 必须带截断标志");
+
+        let mut accum2 = None;
+        let chunk2 = apply_openai_sse(
+            r#"{"choices":[{"delta":{"content":"ok"},"finish_reason":"stop"}]}"#,
+            &mut accum2,
+        );
+        assert!(chunk2.finished && !chunk2.truncated_by_max_tokens, "stop 不置截断标志");
+
+        let mut accum3 = None;
+        let chunk3 = apply_openai_sse(
+            r#"{"choices":[{"delta":{"content":"x"},"finish_reason":null}]}"#,
+            &mut accum3,
+        );
+        assert!(!chunk3.truncated_by_max_tokens, "普通 delta 不置截断标志");
+    }
 }