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/anthropic_helpers.rs

@@ -137,7 +137,7 @@ pub(crate) fn apply_anthropic_event(data: &str, usage_accum: &mut Option<TokenUs
     let v: serde_json::Value = match serde_json::from_str(data) {
         Ok(v) => v,
         Err(_) => {
-            return StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: None, error: None, reasoning_content: None }
+            return StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: None, error: None, reasoning_content: None, truncated_by_max_tokens: false }
         }
     };
     let ty = v.get("type").and_then(|t| t.as_str()).unwrap_or("");
@@ -169,7 +169,7 @@ pub(crate) fn apply_anthropic_event(data: &str, usage_accum: &mut Option<TokenUs
                     reasoning_tokens: 0,
                 });
             }
-            StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: usage_accum.clone(), error: None, reasoning_content: None }
+            StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: usage_accum.clone(), error: None, reasoning_content: None, truncated_by_max_tokens: false }
         }
         // 消息增量：output_tokens 是累计值（非增量），直接覆盖 completion + 重算 total
         "message_delta" => {
@@ -179,9 +179,12 @@ pub(crate) fn apply_anthropic_event(data: &str, usage_accum: &mut Option<TokenUs
                 acc.completion_tokens = out as u32;
                 acc.total_tokens = acc.prompt_tokens.saturating_add(acc.completion_tokens);
             }
+            // stop_reason=max_tokens(message_delta 帧携带):输出被 max_tokens 截断。
+            // 终态 finished 在后续 message_stop 帧,截断标志挂本帧,消费方跨帧 OR 累积。
+            let truncated_by_max_tokens = v.get("delta").and_then(|d| d.get("stop_reason")).and_then(|s| s.as_str()) == Some("max_tokens");
             // 加固:usage 挂到本帧(而非仅 message_stop 带出),中途断连/端点不发 message_stop
             // 时仍能拿到真实 usage,对称 openai_helpers 的修复。
-            StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: usage_accum.clone(), error: None, reasoning_content: None }
+            StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: usage_accum.clone(), error: None, reasoning_content: None, truncated_by_max_tokens }
         }
         // 文本增量
         "content_block_delta" => {
@@ -190,16 +193,16 @@ pub(crate) fn apply_anthropic_event(data: &str, usage_accum: &mut Option<TokenUs
                 // 不混入正文 delta。本侧请求未启用 thinking，此分支只为不丢端点侧自行产出的思考。
                 if delta.get("type").and_then(|t| t.as_str()) == Some("thinking_delta") {
                     let text = delta.get("thinking").and_then(|t| t.as_str()).unwrap_or("").to_string();
-                    return StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: None, error: None, reasoning_content: Some(text) };
+                    return StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: None, error: None, reasoning_content: Some(text), truncated_by_max_tokens: false };
                 }
                 // signature_delta：thinking 块签名字段，仅回传校验用。DevFlow 从不把 thinking 回传
                 // anthropic 历史（丢弃 signature 后伪造回传必 400），签名无处消费，安静忽略。
                 if delta.get("type").and_then(|t| t.as_str()) == Some("signature_delta") {
-                    return StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: None, error: None, reasoning_content: None };
+                    return StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: None, error: None, reasoning_content: None, truncated_by_max_tokens: false };
                 }
                 if delta.get("type").and_then(|t| t.as_str()) == Some("text_delta") {
                     let text = delta.get("text").and_then(|t| t.as_str()).unwrap_or("").to_string();
-                    return StreamChunk { delta: text, finished: false, tool_calls: None, usage: None, error: None, reasoning_content: None };
+                    return StreamChunk { delta: text, finished: false, tool_calls: None, usage: None, error: None, reasoning_content: None, truncated_by_max_tokens: false };
                 }
                 // 工具入参增量
                 if delta.get("type").and_then(|t| t.as_str()) == Some("input_json_delta") {
@@ -217,10 +220,11 @@ pub(crate) fn apply_anthropic_event(data: &str, usage_accum: &mut Option<TokenUs
                         usage: None,
                         error: None,
                         reasoning_content: None,
+                        truncated_by_max_tokens: false,
                     };
                 }
             }
-            StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: None, error: None, reasoning_content: None }
+            StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: None, error: None, reasoning_content: None, truncated_by_max_tokens: false }
         }
         // 工具块开始：带 id + name
         "content_block_start" => {
@@ -253,10 +257,11 @@ pub(crate) fn apply_anthropic_event(data: &str, usage_accum: &mut Option<TokenUs
                         usage: None,
                         error: None,
                         reasoning_content: None,
+                        truncated_by_max_tokens: false,
                     };
                 }
             }
-            StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: None, error: None, reasoning_content: None }
+            StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: None, error: None, reasoning_content: None, truncated_by_max_tokens: false }
         }
         // 消息结束：带出累积 usage
         "message_stop" => StreamChunk {
@@ -266,15 +271,16 @@ pub(crate) fn apply_anthropic_event(data: &str, usage_accum: &mut Option<TokenUs
             usage: usage_accum.take(),
             error: None,
             reasoning_content: None,
+            truncated_by_max_tokens: false,
         },
         // 错误事件：流中途出错。不走 finished 完成路径（避免残缺响应被当正常完成入库），
         // 改由 stream_llm 识别 error 非空 → 发 AiError + 丢弃残缺（与 OpenAI 路径 Err 一致）。
         "error" => {
             let msg = v.get("error").and_then(|e| e.get("message")).and_then(|m| m.as_str()).unwrap_or("stream error").to_string();
             error!(%msg, "Anthropic 流式错误事件");
-            StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: None, error: Some(msg), reasoning_content: None }
+            StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: None, error: Some(msg), reasoning_content: None, truncated_by_max_tokens: false }
         }
         // content_block_stop / ping 等不产出 chunk
-        _ => StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: None, error: None, reasoning_content: None },
+        _ => StreamChunk { delta: String::new(), finished: false, tool_calls: None, usage: None, error: None, reasoning_content: None, truncated_by_max_tokens: false },
     }
 }