fix(model): 解析 stop_reason + max_tokens 截断重试/非空兜底 — 不再静默空回复

- model.go: Response.StopReason; anthropic wire加stop_reason; openai finish_reason映射(两协议统一,原值透传)
- truncation.go(新,159行): effectiveMaxTokens/retryMaxTokens(×2封顶32768)/isTruncatedEmpty(空正文+无tool_use+stop_reason∈{max_tokens,length})/withEmptyBodyHint/callWithTruncationRetry/callStreamWithTruncationRetry/dropThinking/emitTextSegment
- anthropic.go Chat/ChatStream 走重试+兜底; anthropic_encode.go(新)拆编码(anthropic.go 529→357合规); anthropic_stream message_delta落StopReason
- agent/loop: 把模型层StopReason带到llm.call span的model_stop_reason属性(修掉trace硬编码stop的误导); loop.Result.StopReason语义未动
- 触发仅当截断空正文; tool_use空正文永不触发(native_toolcall_test仍过); 至多1次重试; 兜底回'（思考过长，未能生成回复）'绝不用thinking
- 新增7测试(非流式/流式重试+兜底+tool_use不触发+封顶+openai映射), build/vet/test绿+3平台交叉编译

internal/runtime/model/anthropic_stream.go

@@ -28,11 +28,14 @@ type anthropicStartBlock struct {
 }
 
 // anthropicDelta is the incremental payload inside a content_block_delta event.
+// The message_delta event reuses the same field name for its terminal
+// stop_reason (end_turn / max_tokens / tool_use), so it is decoded here too.
 type anthropicDelta struct {
 	Type        string `json:"type"` // text_delta | input_json_delta | thinking_delta
 	Text        string `json:"text,omitempty"`
 	PartialJSON string `json:"partial_json,omitempty"`
 	Thinking    string `json:"thinking,omitempty"`
+	StopReason  string `json:"stop_reason,omitempty"`
 }
 
 // anthropicStreamError is the payload of an error event.
@@ -201,6 +204,9 @@ func applyAnthropicEvent(
 			}
 		}
 	case "message_delta":
+		if evt.Delta != nil {
+			agg.StopReason = evt.Delta.StopReason
+		}
 		if evt.Usage != nil {
 			agg.CompletionTokens = evt.Usage.OutputTokens
 		}