Align prompts and strengthen validation context

internal/framework/validators/llm_context.go

@@ -0,0 +1,68 @@
+package validators
+
+import (
+	"gitea.maximumdirect.net/eric/audita/internal/core/chunking"
+	"gitea.maximumdirect.net/eric/audita/internal/core/schema"
+)
+
+// validationContext supplies adjacent source segments within the current chunk
+// and glossary definitions mentioned in the candidate or that local context.
+// These fields travel in each item so batching accounts for their size.
+func validationContext(req Request, segmentID int, corrected string) ([]schema.Segment, []schema.GlossaryEntry) {
+	var neighbors []schema.Segment
+	var source string
+	if req.WorkingTranscript != nil {
+		segments := req.WorkingTranscript.Segments
+		for i, segment := range segments {
+			if segment.ID != segmentID {
+				continue
+			}
+			source = segment.Text
+			if i > 0 {
+				neighbors = append(neighbors, segments[i-1])
+			}
+			if i+1 < len(segments) {
+				neighbors = append(neighbors, segments[i+1])
+			}
+			break
+		}
+	}
+	texts := []string{source, corrected}
+	for _, neighbor := range neighbors {
+		texts = append(texts, neighbor.Text)
+	}
+	var entries []schema.GlossaryEntry
+	if req.Glossary != nil {
+		vocabulary := NewProtectedVocabulary(req.Glossary)
+		mentioned := make(map[int]bool)
+		for _, text := range texts {
+			for identity := range vocabulary.occurrencesByIdentity(text) {
+				mentioned[identity] = true
+			}
+		}
+		for i, entry := range req.Glossary.Entries {
+			if mentioned[i] {
+				entries = append(entries, entry)
+			}
+		}
+	}
+	return neighbors, entries
+}
+
+// fitValidationContext drops optional context before treating required candidate
+// text as oversized. Glossary definitions take priority over adjacent segments.
+func fitValidationContext(item LLMValidationItem, budget int, estimator chunking.TokenEstimator) LLMValidationItem {
+	for {
+		tokens, err := estimateBatchTokens(estimator, []LLMValidationItem{item})
+		if err != nil || tokens <= budget {
+			return item
+		}
+		if len(item.NeighboringSegments) > 0 {
+			item.NeighboringSegments = item.NeighboringSegments[:len(item.NeighboringSegments)-1]
+		} else if len(item.GlossaryEntries) > 0 {
+			item.GlossaryEntries = item.GlossaryEntries[:len(item.GlossaryEntries)-1]
+		} else {
+			return item
+		}
+	}
+}