fix(dingtalk): 推理正文边界支持「首行即正文」并补齐卡片结构诊断 + 流式分帧重放守卫

internal/reasoningmode/corpus_feed_replay_test.go

@@ -0,0 +1,108 @@
+package reasoningmode
+
+import (
+	"bufio"
+	"encoding/json"
+	"os"
+	"testing"
+)
+
+// TestReplayProductionCorpusThroughFeed replays production reasoning answers
+// through the streaming feed the card pump actually uses, and checks two
+// properties of every frame the card receives:
+//
+//  1. a frame that already contains a structural body line must start at that
+//     body (no narration glued in front of it). A frame that shows narration
+//     above the body is exactly the "the last reasoning sentence stays on the
+//     card" defect.
+//  2. once a frame is body-only, no later frame may go back to showing
+//     narration.
+//
+// Enable with REASONING_CORPUS=<path to reasoning_corpus.jsonl>.
+func TestReplayProductionCorpusThroughFeed(t *testing.T) {
+	path := os.Getenv("REASONING_CORPUS")
+	if path == "" {
+		t.Skip("set REASONING_CORPUS to replay production answers")
+	}
+	file, err := os.Open(path)
+	if err != nil {
+		t.Fatalf("open corpus: %v", err)
+	}
+	defer file.Close()
+
+	chunkSizes := []int{11, 47, 199, 1001}
+	var rows, frames, bodyFrames int
+	type violation struct {
+		id     string
+		size   int
+		marks  bool
+		prefix int
+		bytes  int
+	}
+	var violations []violation
+
+	scanner := bufio.NewScanner(file)
+	scanner.Buffer(make([]byte, 0, 1<<20), 1<<22)
+	for scanner.Scan() {
+		var row struct {
+			ID      string `json:"id"`
+			Content string `json:"content"`
+		}
+		if err := json.Unmarshal(scanner.Bytes(), &row); err != nil {
+			t.Fatalf("decode row: %v", err)
+		}
+		rows++
+		for _, size := range chunkSizes {
+			for _, marks := range []bool{false, true} {
+				feed := NewPartialFeed("reasoning")
+				bodySeen := false
+				for start := 0; start < len(row.Content); start += size {
+					end := start + size
+					if end > len(row.Content) {
+						end = len(row.Content)
+					}
+					frame := feed.OnAnswer(row.Content[:end])
+					frames++
+					if firstStructuralLine(frame) == "" {
+						// no body in this frame yet: narration only, expected.
+						continue
+					}
+					offset, ok := BodyStartOffset(frame)
+					prefix := -1
+					if ok {
+						prefix = len([]rune(frame[:offset]))
+					}
+					if ok && prefix == 0 {
+						bodySeen = true
+						bodyFrames++
+						continue
+					}
+					// The frame carries a structural line but does not start at
+					// it: narration is still visible above the body.
+					violations = append(violations, violation{
+						id:     row.ID,
+						size:   size,
+						marks:  marks,
+						prefix: prefix,
+						bytes:  len(frame),
+					})
+					_ = bodySeen
+				}
+			}
+		}
+	}
+	if err := scanner.Err(); err != nil {
+		t.Fatalf("scan corpus: %v", err)
+	}
+	t.Logf("rows=%d frames=%d body_only_frames=%d narration_above_body_frames=%d", rows, frames, bodyFrames, len(violations))
+	for i, v := range violations {
+		if i >= 8 {
+			t.Logf("... %d more", len(violations)-i)
+			break
+		}
+		t.Logf("violation id=%s chunk=%d step_boundaries=%t body_prefix_runes=%d bytes=%d", v.id, v.size, v.marks, v.prefix, v.bytes)
+	}
+	if len(violations) > 0 {
+		t.Errorf("%d frames showed narration above the answer body", len(violations))
+	}
+}