feat(pierre): sanity check

internal/pierre/judge.go

@@ -88,6 +88,10 @@ If project guidelines are provided, treat them as hard rules that must be respec
 // It tries to split on file boundaries ("diff --git") first, then on hunk boundaries (@@),
 // and finally on a hard byte limit.
 func splitDiffIntoChunks(diff []byte, maxSize int) []string {
+	// Preserve the file header for each chunk when a single file's diff is split across multiple chunks.
+	// The header is the portion before the first hunk marker "@@" (including the "diff --git" line).
+	// When we need to split by hunks, we prepend this header to every resulting sub‑chunk.
+
 	if len(diff) <= maxSize {
 		return []string{string(diff)}
 	}
@@ -107,22 +111,31 @@ func splitDiffIntoChunks(diff []byte, maxSize int) []string {
 			current.Reset()
 		}
 		if len(seg) > maxSize {
-			// Split further by hunks
-			hunks := strings.Split(seg, "\n@@ ")
-			for j, h := range hunks {
-				var hseg string
-				if j == 0 {
-					// First hunk segment already contains the preceding content (including any needed newline)
-					hseg = h
-				} else {
-					// Subsequent hunks need the leading newline and "@@ " marker restored
-					hseg = "\n@@ " + h
+			// Determine if there is a hunk marker. If not, fall back to simple size‑based chunking.
+			headerEnd := strings.Index(seg, "\n@@ ")
+			if headerEnd == -1 {
+				// No hunk marker – split purely by size.
+				remaining := seg
+				for len(remaining) > maxSize {
+					chunks = append(chunks, remaining[:maxSize])
+					remaining = remaining[maxSize:]
 				}
+				current.WriteString(remaining)
+				continue
+			}
+			// Preserve the header up to the first hunk.
+			header := seg[:headerEnd+1] // include newline before "@@"
+			// Split the rest of the segment into hunks (excluding the header part).
+			hunks := strings.Split(strings.TrimPrefix(seg, header), "\n@@ ")
+			for _, h := range hunks {
+				// Reconstruct each hunk with its header and "@@ " prefix.
+				hseg := header + "@@ " + h
 				if current.Len()+len(hseg) > maxSize && current.Len() > 0 {
 					chunks = append(chunks, current.String())
 					current.Reset()
 				}
 				if len(hseg) > maxSize {
+					// If a single hunk exceeds maxSize, split it further.
 					for len(hseg) > maxSize {
 						chunks = append(chunks, hseg[:maxSize])
 						hseg = hseg[maxSize:]

internal/pierre/judge_test.go

@@ -37,6 +37,15 @@ func (g *mockGit) AddComment(ctx context.Context, owner, repo string, prID int,
 	return nil
 }
 
+func (g *mockGit) GetFileContent(ctx context.Context, owner, repo, path, ref string) (string, error) {
+	// For tests, return a simple placeholder content.
+	return "package main\n\nfunc placeholder() {}", nil
+}
+
+func (g *mockGit) GetPRHeadSHA(ctx context.Context, owner, repo string, prID int) (string, error) {
+	return "dummysha", nil
+}
+
 func TestSplitDiffIntoChunks(t *testing.T) {
 	cases := []struct {
 		name           string

internal/pierre/resource.go

@@ -33,6 +33,8 @@ func New(chat ChatAdapter, git GitAdapter, maxChunkSize int, guidelines []string
 type GitAdapter interface {
 	GetDiff(ctx context.Context, owner, repo string, prID int) (io.ReadCloser, error)
 	AddComment(ctx context.Context, owner, repo string, prID int, comment Comment) error
+	GetFileContent(ctx context.Context, owner, repo, path, ref string) (string, error)
+	GetPRHeadSHA(ctx context.Context, owner, repo string, prID int) (string, error)
 }
 
 type ChatAdapter interface {

internal/pierre/review.go

@@ -4,6 +4,8 @@ import (
 	"context"
 	"fmt"
 	"log"
+
+	"git.schreifuchs.ch/schreifuchs/pierre-bot/internal/chatter"
 )
 
 func (s *Service) MakeReview(ctx context.Context, organisation string, repo string, prID int) error {
@@ -20,6 +22,46 @@ func (s *Service) MakeReview(ctx context.Context, organisation string, repo stri
 		return fmt.Errorf("error judging PR: %w", err)
 	}
 
+	// ---------- Sanity‑check step (always enabled) ----------
+	headSHA, err := s.git.GetPRHeadSHA(ctx, organisation, repo, prID)
+	if err != nil {
+		log.Printf("warning: could not fetch PR head SHA (%v); skipping sanity check", err)
+	} else {
+		filtered := []Comment{}
+		for _, c := range comments {
+			// Retrieve full file content at the PR head
+			fileContent, fErr := s.git.GetFileContent(ctx, organisation, repo, c.File, headSHA)
+			if fErr != nil {
+				log.Printf("failed to fetch file %s: %v – keeping original comment", c.File, fErr)
+				filtered = append(filtered, c)
+				continue
+			}
+
+			// Build a simple sanity‑check prompt
+			systemPrompt := `You are a senior software architect. Given the full source code of a file and a review comment that refers to it, decide whether the comment is useful. Return JSON with fields "useful" (bool) and "reason" (short explanation, ≤2 sentences).`
+			userPrompt := fmt.Sprintf("File content:\n%s\n\nComment:\n%s", fileContent, c.Message)
+
+			type sanityResult struct {
+				Useful bool   `json:"useful"`
+				Reason string `json:"reason"`
+			}
+			var res sanityResult
+			if err := s.chat.GenerateStructured(ctx, []chatter.Message{{Role: chatter.RoleSystem, Content: systemPrompt}, {Role: chatter.RoleUser, Content: userPrompt}}, &res); err != nil {
+				log.Printf("sanity check error for %s:%d: %v – keeping comment", c.File, c.Line, err)
+				filtered = append(filtered, c)
+				continue
+			}
+			if res.Useful {
+				// Optionally annotate the comment with the reason for debugging
+				c.Message = fmt.Sprintf("%s (Reason: %s)", c.Message, res.Reason)
+				filtered = append(filtered, c)
+			} else {
+				log.Printf("comment on %s:%d discarded: %s", c.File, c.Line, res.Reason)
+			}
+		}
+		comments = filtered
+	}
+
 	fmt.Printf("Analysis complete. Found %d issues.\n---\n", len(comments))
 
 	model := s.chat.GetProviderName()