byre/internal/agents/review.go

package agents

import (
	"context"
	"encoding/json"
	"errors"
	"fmt"
	"log/slog"
	"net/http"
	"os"
	"path/filepath"
	"strings"
	"time"

	"g.fc.run/misc/byre/internal/api"
	"g.fc.run/misc/byre/internal/git"
	"g.fc.run/misc/byre/internal/mcp"
	"g.fc.run/misc/byre/internal/store"
)

const maxReviewFiles = 200

var reviewModels = map[api.AgentSessionVendor]string{api.Claude: "claude-opus-5-5", api.Codex: "gpt-6.1-sol"}

var severities = []string{"critical", "high", "medium", "low", "info"}

const reviewGuidance = `You are a reviewer running inside byre. Another agent is doing a task; you review the change it just made, and a human may read your review in byre's web UI.
- Your working directory is a detached checkout of the snapshot under review. Read, build and run whatever you need there, but don't edit, commit or push: the checkout is discarded when you finish, and the task's own worktree belongs to its agent.
- Report with byre's submit_review tool, exactly once, then end your turn with one line. A review that isn't submitted is lost.
- Start the review with ` + "`change`" + `: what the change does, in a few sentences, for someone who hasn't read it.
- Each finding says what is wrong, where (path and line), why it matters and what to do about it. Leave out praise and nits. No findings is a fine result.
- With no findings, the summary is exactly "No significant findings." and nothing else. With findings, the summary is a bulleted Markdown list, one line per finding, and nothing else.
- Show rather than quote. Give a finding's file and lines and byre shows that part of the diff, so don't paste code. When a picture would explain something better than prose, such as a data flow, call graph, state machine or schema the change alters, draw it in a ` + "```mermaid" + ` block. When the change alters something you can see, you can run it (on any free port on 127.0.0.1) and attach screenshots taken with the Playwright tools. Most reviews need neither; leave out a diagram or screenshot that adds nothing to the text.`

func reviewSchema() json.RawMessage {
	images := map[string]any{
		"type":        "array",
		"description": "Screenshots, only when they show something the text can't.",
		"items": map[string]any{
			"type": "object",
			"properties": map[string]any{
				"path":    map[string]any{"type": "string", "description": "A PNG, JPEG, GIF or WebP file of at most 5 MiB you saved: absolute, or relative to your working directory. byre keeps a copy."},
				"caption": map[string]any{"type": "string", "description": "One line saying what it shows."},
			},
			"required": []any{"path"},
		},
	}
	b, err := json.Marshal(map[string]any{
		"type": "object",
		"properties": map[string]any{
			"change":  map[string]any{"type": "string", "description": "What the change does, in a few sentences of Markdown, for someone who hasn't read it."},
			"summary": map[string]any{"type": "string", "description": "Exactly \"No significant findings.\" when findings is empty; otherwise a bulleted Markdown list with one line per finding, and nothing else."},
			"findings": map[string]any{
				"type": "array",
				"items": map[string]any{
					"type": "object",
					"properties": map[string]any{
						"severity": map[string]any{"type": "string", "enum": severities},
						"category": map[string]any{"type": "string", "description": "A short label, such as correctness, security or tests."},
						"title":    map[string]any{"type": "string", "description": "One line."},
						"detail":   map[string]any{"type": "string", "description": "What is wrong, why it matters and what to do, in Markdown."},
						"path":     map[string]any{"type": "string", "description": "Repo-relative path of the file, if the finding is about one."},
						"line":     map[string]any{"type": "integer", "description": "Line in the file as of this snapshot; byre shows the diff around it."},
						"end_line": map[string]any{"type": "integer", "description": "Last line, when the finding covers a range."},
						"images":   images,
					},
					"required": []any{"severity", "title", "detail"},
				},
			},
			"images": images,
		},
		"required": []any{"change", "summary", "findings"},
	})
	if err != nil {
		panic(err)
	}
	return b
}

func (m *Manager) afterSnapshot(snap *api.Snapshot) {
	if snap == nil {
		return
	}
	ctx := context.Background()
	m.reviewMu.Lock()
	defer m.reviewMu.Unlock()

	task, err := m.store.GetTask(ctx, snap.TaskId)
	if err != nil {
		slog.Error("load task to review", "task", snap.TaskId, "err", err)
		return
	}
	if task.Status != api.TaskStatusActive {
		return
	}
	err = m.startReviewer(ctx, task, *snap)
	if err != nil {
		slog.Error("start review", "task", task.Id, "snapshot", snap.N, "err", err)
	}
}

func (m *Manager) reviewDir(projectID, reviewID string) string {
	return filepath.Join(m.worktreeRoot, projectID, "review-"+reviewID)
}

func (m *Manager) reviewMediaDir(projectID, reviewID string) string {
	return m.reviewDir(projectID, reviewID) + "-media"
}

func playwrightMCP(outputDir string) mcp.Stdio {
	return mcp.Stdio{
		Name:    "playwright",
		Command: "npx",
		Args:    []string{"--yes", "@playwright/mcp@0.0.83", "--headless", "--isolated", "--browser", "chrome", "--file-paths", "absolute", "--output-dir", outputDir},
	}
}

func (m *Manager) implementerVendor(ctx context.Context, taskID string) api.AgentSessionVendor {
	sessions, err := m.store.ListSessions(ctx, taskID)
	if err != nil || len(sessions) == 0 {
		return api.Claude
	}
	return sessions[len(sessions)-1].Vendor
}

func reviewVendor(implementer api.AgentSessionVendor) api.AgentSessionVendor {
	if implementer == api.Codex {
		return api.Claude
	}
	return api.Codex
}

func (m *Manager) startReviewer(ctx context.Context, task api.Task, snap api.Snapshot) error {
	project, err := m.store.GetProject(ctx, task.ProjectId)
	if err != nil {
		return err
	}
	vendor := reviewVendor(m.implementerVendor(ctx, task.Id))
	model := reviewModels[vendor]
	prompt, err := m.reviewPrompt(ctx, task, project, snap)
	if err != nil {
		return err
	}
	if prompt == "" {
		now := time.Now().UTC()
		err = m.store.CreateReview(ctx, api.Review{
			Id:         store.NewID(),
			TaskId:     task.Id,
			SnapshotN:  snap.N,
			State:      api.ReviewStateSkipped,
			CreatedAt:  now,
			FinishedAt: &now,
		})
		if err != nil {
			return err
		}
		slog.Info("review skipped, snapshot has no diff", "task", task.Id, "snapshot", snap.N)
		return nil
	}

	reviewID := store.NewID()
	dir := m.reviewDir(project.Id, reviewID)
	err = git.AddDetachedWorktree(project.RepoPath, dir, snap.CommitSha)
	if err != nil {
		return err
	}
	err = os.MkdirAll(m.reviewMediaDir(project.Id, reviewID), 0o755)
	if err != nil {
		m.removeReviewDir(project, reviewID)
		return err
	}

	id := newUUID()
	sess := api.AgentSession{
		Id:              id,
		TaskId:          task.Id,
		Vendor:          vendor,
		Model:           model,
		VendorSessionId: initialVendorSessionID(vendor, id),
		State:           api.AgentSessionStateIdle,
		Role:            api.Reviewer,
		CreatedBy:       task.CreatedBy,
		CreatedAt:       time.Now().UTC(),
	}
	err = m.store.CreateSession(ctx, sess, project.Id)
	if err != nil {
		m.removeReviewDir(project, reviewID)
		return err
	}
	err = m.store.CreateReview(ctx, api.Review{
		Id:             reviewID,
		TaskId:         task.Id,
		SnapshotN:      snap.N,
		AgentSessionId: sess.Id,
		Vendor:         string(vendor),
		Model:          model,
		State:          api.ReviewStateRunning,
		CreatedAt:      time.Now().UTC(),
	})
	if err != nil {
		m.endReviewer(ctx, sess.Id, project, reviewID)
		return err
	}

	_, err = m.turn(ctx, sess, task, "byre", prompt, nil)
	if err != nil {
		m.endReviewer(ctx, sess.Id, project, reviewID)
		m.failReview(ctx, reviewID, "the reviewer didn't start: "+err.Error())
		return err
	}
	slog.Info("review started", "review", reviewID, "task", task.Id, "snapshot", snap.N, "vendor", vendor, "model", model)
	return nil
}

func (m *Manager) reviewPrompt(ctx context.Context, task api.Task, project api.Project, snap api.Snapshot) (string, error) {
	previous := ""
	if snap.N > 1 {
		prev, err := m.store.GetSnapshot(ctx, task.Id, snap.N-1)
		if err != nil {
			return "", err
		}
		previous = prev.CommitSha
	}
	changes, err := git.Compare(project.RepoPath, project.DefaultBranch, snap.CommitSha, snap.TreeSha, previous)
	if err != nil {
		return "", err
	}
	previous = changes.Base
	if len(changes.Files) == 0 {
		return "", nil
	}
	whole, err := git.Compare(project.RepoPath, project.DefaultBranch, snap.CommitSha, snap.TreeSha, "")
	if err != nil {
		return "", err
	}
	brief, err := m.store.FirstTaskMessage(ctx, task.Id)
	if err != nil {
		return "", err
	}

	b := &strings.Builder{}
	fmt.Fprintf(b, "Review the change the agent working on the byre task %q just made: look for bugs, security problems, missing or wrong tests, and anything that doesn't do what the task asked.\n\n", task.Title)
	fmt.Fprintf(b, "It is snapshot %d of the task, commit %s, checked out in your working directory. The change is `git diff %s %s`; %d files changed:\n",
		snap.N, snap.CommitSha, previous, snap.CommitSha, len(changes.Files))
	for i, f := range changes.Files {
		if i == maxReviewFiles {
			fmt.Fprintf(b, "- … and %d more\n", len(changes.Files)-maxReviewFiles)
			break
		}
		fmt.Fprintf(b, "- %s %s (+%d −%d)\n", f.Status, f.Path, f.Additions, f.Deletions)
	}
	fmt.Fprintf(b, "\nFor context, all of the task's work so far is `git diff %s %s` (from the merge-base with %s, %d files).\n", whole.Base, snap.CommitSha, project.DefaultBranch, len(whole.Files))
	if brief != "" {
		fmt.Fprintf(b, "\nThe task's brief, the first message its agent got:\n\n%s\n", quote(clip(brief, 4000)))
	}
	b.WriteString("\nWhen you're done, call submit_review once with your review, then end your turn.")
	return b.String(), nil
}

func quote(s string) string {
	lines := strings.Split(strings.TrimSpace(s), "\n")
	for i, l := range lines {
		lines[i] = "> " + l
	}
	return strings.Join(lines, "\n")
}

func (m *Manager) submitReviewTool(l *live) mcp.Tool {
	return mcp.Tool{
		Name:        "submit_review",
		Description: "Submit your review. Call it exactly once, when you're done; its arguments are the review the human reads.",
		InputSchema: reviewSchema(),
		Handler: func(ctx context.Context, args json.RawMessage) (string, error) {
			return m.submitReview(ctx, l, args)
		},
	}
}

func (m *Manager) submitReview(ctx context.Context, l *live, raw json.RawMessage) (string, error) {
	result := map[string]any{}
	err := json.Unmarshal(raw, &result)
	if err != nil {
		return "", fmt.Errorf("submit_review takes a JSON object: %w", err)
	}
	if c, ok := result["change"].(string); !ok || strings.TrimSpace(c) == "" {
		return "", errors.New("submit_review rejected, nothing was recorded: change must say what the change does")
	}
	if _, ok := result["summary"].(string); !ok {
		return "", errors.New("submit_review rejected, nothing was recorded: summary must be a string")
	}
	findings, ok := result["findings"].([]any)
	if !ok {
		return "", errors.New("submit_review rejected, nothing was recorded: findings must be a list")
	}

	holders := []map[string]any{result}
	for _, f := range findings {
		fm, ok := f.(map[string]any)
		if !ok {
			return "", errors.New("submit_review rejected, nothing was recorded: each finding must be an object")
		}
		holders = append(holders, fm)
	}
	pending := []reviewImage{}
	for _, holder := range holders {
		imgs, err := m.readReviewImages(l, holder["images"])
		if err != nil {
			return "", fmt.Errorf("submit_review rejected, nothing was recorded: %w", err)
		}
		pending = append(pending, imgs...)
	}
	for _, img := range pending {
		b, err := m.store.CreateBlob(ctx, img.contentType, img.data, agentActor)
		if err != nil {
			return "", err
		}
		img.entry["blob"] = b.Id
		delete(img.entry, "path")
	}

	err = m.store.FinishReview(ctx, l.reviewID, api.ReviewStateDone, result, "")
	if errors.Is(err, store.ErrNotFound) {
		return "", errors.New("this review was already submitted or has ended")
	}
	if err != nil {
		return "", err
	}
	return "Review recorded. End your turn now with one line.", nil
}

type reviewImage struct {
	entry       map[string]any
	contentType string
	data        []byte
}

func (m *Manager) readReviewImages(l *live, raw any) ([]reviewImage, error) {
	if raw == nil {
		return nil, nil
	}
	list, ok := raw.([]any)
	if !ok {
		return nil, errors.New("images must be a list")
	}
	out := []reviewImage{}
	for _, item := range list {
		entry, ok := item.(map[string]any)
		if !ok {
			return nil, errors.New("each image must be an object with a path")
		}
		p, ok := entry["path"].(string)
		if !ok || p == "" {
			return nil, errors.New("each image needs a path")
		}
		if !filepath.IsAbs(p) {
			p = filepath.Join(l.dir, p)
		}
		info, err := os.Stat(p)
		if err != nil {
			return nil, fmt.Errorf("image %s: %w", p, err)
		}
		if !info.Mode().IsRegular() {
			return nil, fmt.Errorf("image %s is not a file", p)
		}
		if info.Size() > store.MaxBlobBytes {
			return nil, fmt.Errorf("image %s is %d bytes; images are limited to %d MiB", p, info.Size(), store.MaxBlobBytes>>20)
		}
		data, err := os.ReadFile(p)
		if err != nil {
			return nil, fmt.Errorf("image %s: %w", p, err)
		}
		contentType := http.DetectContentType(data)
		if !store.ImageTypes[contentType] {
			return nil, fmt.Errorf("image %s is %s; use PNG, JPEG, GIF or WebP", p, contentType)
		}
		out = append(out, reviewImage{entry: entry, contentType: contentType, data: data})
	}
	return out, nil
}

func (m *Manager) reviewTurnEnded(ctx context.Context, l *live, res endResult) error {
	m.mu.Lock()
	interrupted := l.interrupted
	m.mu.Unlock()

	err := m.emit(ctx, l, agentActor, "turn.ended", res.payload)
	if err != nil {
		return err
	}
	if res.window > 0 {
		err = m.updateContext(ctx, l, l.contextUsed, res.window)
		if err != nil {
			return err
		}
	}

	reason := fmt.Sprintf("the reviewer ended its turn without calling submit_review: %s", clip(strings.TrimSpace(res.result), 500))
	switch {
	case interrupted:
		reason = "the reviewer was interrupted"
	case res.isError:
		reason = fmt.Sprintf("the reviewer's turn ended with an error (%s): %s", res.subtype, clip(res.result, 500))
	}
	go m.finishReviewer(l, reason)
	return nil
}

func (m *Manager) finishReviewer(l *live, reason string) {
	ctx := context.Background()
	project, err := m.store.GetProject(ctx, l.projectID)
	if err != nil {
		slog.Error("load project to end reviewer", "review", l.reviewID, "err", err)
		return
	}
	m.endReviewer(ctx, l.id, project, l.reviewID)
	m.failReview(ctx, l.reviewID, reason)
}

func (m *Manager) endReviewer(ctx context.Context, sessionID string, project api.Project, reviewID string) {
	sess, err := m.store.GetSession(ctx, sessionID)
	if err != nil {
		slog.Error("load reviewer session", "session", sessionID, "err", err)
	}
	if err == nil && sess.State != api.AgentSessionStateCompleted {
		err = m.retire(ctx, sess, "byre")
		if err != nil {
			slog.Error("retire reviewer session", "session", sessionID, "err", err)
		}
	}
	m.removeReviewDir(project, reviewID)
}

func (m *Manager) removeReviewDir(project api.Project, reviewID string) {
	err := git.RemoveDetachedWorktree(project.RepoPath, m.reviewDir(project.Id, reviewID))
	if err != nil {
		slog.Error("remove review worktree", "review", reviewID, "err", err)
	}
	err = os.RemoveAll(m.reviewMediaDir(project.Id, reviewID))
	if err != nil {
		slog.Error("remove review media", "review", reviewID, "err", err)
	}
}

func (m *Manager) failReview(ctx context.Context, reviewID, reason string) {
	err := m.store.FinishReview(ctx, reviewID, api.ReviewStateFailed, nil, reason)
	if errors.Is(err, store.ErrNotFound) {
		return
	}
	if err != nil {
		slog.Error("record failed review", "review", reviewID, "err", err)
		return
	}
	slog.Info("review failed", "review", reviewID, "reason", reason)
}

func (m *Manager) cancelReviews(ctx context.Context, task api.Task, project api.Project) {
	m.reviewMu.Lock()
	defer m.reviewMu.Unlock()
	reviews, err := m.store.ListReviews(ctx, task.Id)
	if err != nil {
		slog.Error("list reviews to cancel", "task", task.Id, "err", err)
		return
	}
	for _, r := range reviews {
		if r.State != api.ReviewStateRunning {
			continue
		}
		m.endReviewer(ctx, r.AgentSessionId, project, r.Id)
		m.failReview(ctx, r.Id, "the task was closed")
	}
}

func (m *Manager) recoverReviews(ctx context.Context) error {
	running, err := m.store.RunningReviews(ctx)
	if err != nil {
		return err
	}
	for _, r := range running {
		sess, err := m.store.GetSession(ctx, r.AgentSessionId)
		if err != nil {
			return err
		}
		if sess.State == api.AgentSessionStateRunning {
			continue
		}
		task, err := m.store.GetTask(ctx, r.TaskId)
		if err != nil {
			return err
		}
		project, err := m.store.GetProject(ctx, task.ProjectId)
		if err != nil {
			return err
		}
		m.endReviewer(ctx, r.AgentSessionId, project, r.Id)
		m.failReview(ctx, r.Id, "byre restarted before the reviewer finished")
	}
	return nil
}

func reviewLine(r api.Review) string {
	if r.State == api.ReviewStateFailed {
		return fmt.Sprintf("review of snapshot %d failed: %s", r.SnapshotN, clip(r.Error, 300))
	}
	if r.State == api.ReviewStateSkipped {
		return fmt.Sprintf("review of snapshot %d skipped: no changes", r.SnapshotN)
	}
	res := map[string]any{}
	if r.Result != nil {
		res = *r.Result
	}
	b := &strings.Builder{}
	fmt.Fprintf(b, "review of snapshot %d: %s", r.SnapshotN, clip(strings.TrimSpace(fmt.Sprint(res["summary"])), 600))
	if c, ok := res["change"].(string); ok && c != "" {
		fmt.Fprintf(b, "\n  change: %s", clip(strings.TrimSpace(c), 600))
	}
	findings, _ := res["findings"].([]any)
	for _, f := range findings {
		fm, _ := f.(map[string]any)
		where := ""
		if p, ok := fm["path"].(string); ok && p != "" {
			where = " (" + p
			if line, ok := fm["line"].(float64); ok && line > 0 {
				where += fmt.Sprintf(":%d", int(line))
			}
			where += ")"
		}
		fmt.Fprintf(b, "\n  - [%v] %v%s: %s", fm["severity"], fm["title"], where, clip(strings.TrimSpace(fmt.Sprint(fm["detail"])), 300))
	}
	return b.String()
}