feat(pierre): sanity check

internal/gitadapters/bitbucket/resource.go

@@ -1,6 +1,10 @@
 package bitbucket
 
 import (
+	"context"
+	"fmt"
+	"io"
+	"net/http"
 	"strings"
 
 	"git.schreifuchs.ch/schreifuchs/pierre-bot/internal/gitadapters/baseadapter"
@@ -18,3 +22,43 @@ func NewBitbucket(baseURL string, bearerToken string) *BitbucketAdapter {
 		Rest: baseadapter.NewRest(baseURL, bearerToken),
 	}
 }
+
+// GetFileContent returns the raw file content at the given ref (commit SHA) or HEAD if ref is empty.
+func (b *BitbucketAdapter) GetFileContent(ctx context.Context, projectKey, repositorySlug, path, ref string) (string, error) {
+	// Use the Rest helper to build the base URL, then add the "at" query param if needed.
+	r, err := b.CreateRequest(ctx, http.MethodGet, nil,
+		"/projects/", projectKey, "repos", repositorySlug, "raw", path)
+	if err != nil {
+		return "", err
+	}
+	if ref != "" {
+		q := r.URL.Query()
+		q.Set("at", ref)
+		r.URL.RawQuery = q.Encode()
+	}
+
+	resp, err := http.DefaultClient.Do(r)
+	if err != nil {
+		return "", err
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != http.StatusOK {
+		sb := &strings.Builder{}
+		io.Copy(sb, resp.Body)
+		return "", fmt.Errorf("error fetching file %s status %d, body %s", path, resp.StatusCode, sb.String())
+	}
+	content, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return "", err
+	}
+	return string(content), nil
+}
+
+// GetPRHeadSHA fetches the PR and returns the SHA of the source (to) branch.
+func (b *BitbucketAdapter) GetPRHeadSHA(ctx context.Context, projectKey, repositorySlug string, pullRequestID int) (string, error) {
+	pr, err := b.GetPR(ctx, projectKey, repositorySlug, pullRequestID)
+	if err != nil {
+		return "", err
+	}
+	return pr.ToRef.LatestCommit, nil
+}

internal/gitadapters/gitea/adapter.go

@@ -3,6 +3,7 @@ package gitea
 import (
 	"bytes"
 	"context"
+	"fmt"
 	"io"
 
 	"code.gitea.io/sdk/gitea"
@@ -47,3 +48,28 @@ func (g *Adapter) AddComment(ctx context.Context, owner, repo string, prID int,
 	_, _, err := g.client.CreatePullReview(owner, repo, int64(prID), opts)
 	return err
 }
+
+// GetFileContent returns the file content at a given path and ref (commit SHA).
+func (g *Adapter) GetFileContent(ctx context.Context, owner, repo, path, ref string) (string, error) {
+	g.client.SetContext(ctx)
+	// The SDK's GetFile returns the raw bytes of the file.
+	data, _, err := g.client.GetFile(owner, repo, ref, path)
+	if err != nil {
+		return "", err
+	}
+	return string(data), nil
+}
+
+// GetPRHeadSHA fetches the pull request and returns the head commit SHA.
+func (g *Adapter) GetPRHeadSHA(ctx context.Context, owner, repo string, prID int) (string, error) {
+	g.client.SetContext(ctx)
+	// GetPullRequest returns the detailed PR information.
+	pr, _, err := g.client.GetPullRequest(owner, repo, int64(prID))
+	if err != nil {
+		return "", err
+	}
+	if pr == nil || pr.Head == nil {
+		return "", fmt.Errorf("pull request %d has no head information", prID)
+	}
+	return pr.Head.Sha, nil
+}

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()