From 9833725f315df6ed7bea18b9b57452db2d60d465 Mon Sep 17 00:00:00 2001
From: jordan <jordan.washburn@gmail.com>
Date: Sat, 7 Feb 2026 08:40:36 -0700
Subject: [PATCH] fix: preserve work on build retry, clear stale audit data

Two critical fixes for build retry behavior:

1. pod_git_operations.go: Normalize remote URL before comparison
   - Clone stores URL with token (https://token:x@host/...)
   - Subsequent retry compares against URL without token
   - Without normalization, URLs never match, so workspace is always
     cleared and re-cloned, losing all code from previous attempt

2. build_audit.go: Clear stale result data when task transitions to running
   - When a failed task is retried, UpdateStatus only updated status/worker_id
   - Result and completed_at from previous failure remained, causing
     API to return stale failure data even while retry was running
   - Now clears result, completed_at and resets started_at when
     status is set to "running"

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---
 internal/adapter/postgres/build_audit.go | 25 +++++++++++++++++++-----
 internal/worker/pod_git_operations.go    | 11 +++++++++--
 2 files changed, 29 insertions(+), 7 deletions(-)

diff --git a/internal/adapter/postgres/build_audit.go b/internal/adapter/postgres/build_audit.go
index 2f974af..df4dcc5 100644
--- a/internal/adapter/postgres/build_audit.go
+++ b/internal/adapter/postgres/build_audit.go
@@ -84,12 +84,27 @@ func (r *BuildAuditRepository) Update(ctx context.Context, taskID string, result
 }
 
 // UpdateStatus updates the status and worker assignment when a task is claimed.
+// When status is "running" (task claimed for execution/retry), this also clears
+// any stale result and completed_at from previous failed attempts.
 func (r *BuildAuditRepository) UpdateStatus(ctx context.Context, taskID string, status domain.BuildStatus, workerID string) error {
-	res, err := r.db.ExecContext(ctx, `
-		UPDATE build_audit
-		SET status = $2, worker_id = $3
-		WHERE task_id = $1
-	`, taskID, status, nullString(workerID))
+	// When a task transitions to running (claimed for execution or retry),
+	// clear stale result data from any previous failed attempts.
+	var query string
+	if status == domain.BuildStatusRunning {
+		query = `
+			UPDATE build_audit
+			SET status = $2, worker_id = $3, result = NULL, completed_at = NULL, started_at = NOW()
+			WHERE task_id = $1
+		`
+	} else {
+		query = `
+			UPDATE build_audit
+			SET status = $2, worker_id = $3
+			WHERE task_id = $1
+		`
+	}
+
+	res, err := r.db.ExecContext(ctx, query, taskID, status, nullString(workerID))
 	if err != nil {
 		return fmt.Errorf("update build audit status: %w", err)
 	}
diff --git a/internal/worker/pod_git_operations.go b/internal/worker/pod_git_operations.go
index fc26167..ef50a29 100644
--- a/internal/worker/pod_git_operations.go
+++ b/internal/worker/pod_git_operations.go
@@ -94,10 +94,17 @@ func (g *PodGitOperations) CloneRepo(ctx context.Context, podName, workDir, clon
 		// Verify the remote URL matches the expected clone URL
 		currentRemote, err := g.runGitInPodOutput(ctx, podName, workDir, "config", "--get", "remote.origin.url")
 		currentRemote = strings.TrimSpace(currentRemote)
+
+		// Strip token from currentRemote for comparison, since clone stores the authenticated URL
+		// Format: https://token:TOKEN@host/path -> https://host/path
+		normalizedRemote := currentRemote
+		if idx := strings.Index(currentRemote, "@"); idx != -1 && strings.HasPrefix(currentRemote, "https://") {
+			normalizedRemote = "https://" + currentRemote[idx+1:]
+		}
 		expectedURL := cloneURL
 
-		// Normalize URLs for comparison (both should be HTTPS)
-		if err == nil && currentRemote == expectedURL {
+		// Normalize URLs for comparison (both should be HTTPS without credentials)
+		if err == nil && normalizedRemote == expectedURL {
 			log.Info("workspace is already a git repo with correct remote, pulling latest",
 				logging.FieldPodName, podName,
 				"workDir", workDir,