executor: fix sandbox git fetch + inject prior failure history

Fix: use file:// prefix in git fetch during sandbox teardown to force
pack-protocol transfer. The local optimization uses hard links which
fail across devices and with mixed-owner object stores.

Feature: before running a task, query prior failed/timed-out executions
and prepend their error messages to the agent's --append-system-prompt.
This tells the agent what went wrong in previous attempts so it doesn't
repeat the same mistakes.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

1 files changed, 106 insertions, 0 deletions

diff --git a/internal/executor/executor_test.go b/internal/executor/executor_test.go
index 028e5cf..e6b8f0b 100644
--- a/internal/executor/executor_test.go
+++ b/internal/executor/executor_test.go
@@ -22,11 +22,13 @@ type mockRunner struct {
 	delay    time.Duration
 	err      error
 	exitCode int
+	onRun    func(*task.Task, *storage.Execution) error
 }
 
 func (m *mockRunner) Run(ctx context.Context, t *task.Task, e *storage.Execution) error {
 	m.mu.Lock()
 	m.calls++
+	cb := m.onRun
 	m.mu.Unlock()
 
 	if m.delay > 0 {
@@ -36,6 +38,9 @@ func (m *mockRunner) Run(ctx context.Context, t *task.Task, e *storage.Execution
 			return ctx.Err()
 		}
 	}
+	if cb != nil {
+		return cb(t, e)
+	}
 	if m.err != nil {
 		e.ExitCode = m.exitCode
 		return m.err
@@ -355,6 +360,107 @@ func TestPool_ConcurrentExecution(t *testing.T) {
 	}
 }
 
+func TestWithFailureHistory_NoFailures_ReturnsUnchanged(t *testing.T) {
+	tk := makeTask("no-fail")
+	result := withFailureHistory(tk, nil, nil)
+	if result != tk {
+		t.Error("expected same pointer when no prior executions")
+	}
+}
+
+func TestWithFailureHistory_WithError_ReturnsUnchanged(t *testing.T) {
+	tk := makeTask("err-case")
+	result := withFailureHistory(tk, nil, fmt.Errorf("db error"))
+	if result != tk {
+		t.Error("expected same pointer when ListExecutions errors")
+	}
+}
+
+func TestWithFailureHistory_InjectsFailedHistory(t *testing.T) {
+	tk := makeTask("with-fail")
+	tk.Agent.Instructions = "do the work"
+
+	execs := []*storage.Execution{
+		{ID: "e1", Status: "FAILED", ErrorMsg: "sandbox: uncommitted changes", StartTime: time.Now()},
+		{ID: "e2", Status: "COMPLETED", ErrorMsg: "", StartTime: time.Now()}, // not a failure, should be ignored
+	}
+	result := withFailureHistory(tk, execs, nil)
+
+	if result == tk {
+		t.Fatal("expected a new task copy, got same pointer")
+	}
+	if !strings.Contains(result.Agent.SystemPromptAppend, "Prior Attempt History") {
+		t.Errorf("expected history header in SystemPromptAppend, got: %q", result.Agent.SystemPromptAppend)
+	}
+	if !strings.Contains(result.Agent.SystemPromptAppend, "sandbox: uncommitted changes") {
+		t.Errorf("expected error message in SystemPromptAppend, got: %q", result.Agent.SystemPromptAppend)
+	}
+	// COMPLETED execution should not appear
+	if strings.Contains(result.Agent.SystemPromptAppend, "e2") {
+		t.Errorf("COMPLETED execution should not appear in history")
+	}
+	// Original instructions unchanged
+	if result.Agent.Instructions != "do the work" {
+		t.Errorf("instructions should be unchanged, got: %q", result.Agent.Instructions)
+	}
+}
+
+func TestWithFailureHistory_PreservesExistingSystemPrompt(t *testing.T) {
+	tk := makeTask("with-prompt")
+	tk.Agent.SystemPromptAppend = "existing prompt"
+
+	execs := []*storage.Execution{
+		{ID: "e1", Status: "FAILED", ErrorMsg: "some error", StartTime: time.Now()},
+	}
+	result := withFailureHistory(tk, execs, nil)
+
+	if !strings.Contains(result.Agent.SystemPromptAppend, "Prior Attempt History") {
+		t.Error("expected history prepended")
+	}
+	if !strings.Contains(result.Agent.SystemPromptAppend, "existing prompt") {
+		t.Error("expected existing prompt preserved")
+	}
+	// History must come BEFORE the existing prompt
+	histIdx := strings.Index(result.Agent.SystemPromptAppend, "Prior Attempt History")
+	existIdx := strings.Index(result.Agent.SystemPromptAppend, "existing prompt")
+	if histIdx > existIdx {
+		t.Error("history should be prepended before existing system prompt")
+	}
+}
+
+func TestPool_FailureHistoryInjectedOnRetry(t *testing.T) {
+	store := testStore(t)
+
+	var capturedPrompt string
+	runner := &mockRunner{}
+	runner.onRun = func(t *task.Task, _ *storage.Execution) error {
+		capturedPrompt = t.Agent.SystemPromptAppend
+		return nil
+	}
+	runners := map[string]Runner{"claude": runner}
+	logger := slog.New(slog.NewTextHandler(os.Stderr, &slog.HandlerOptions{Level: slog.LevelError}))
+	pool := NewPool(2, runners, store, logger)
+
+	tk := makeTask("retry-hist")
+	store.CreateTask(tk)
+
+	// Simulate a prior failed execution.
+	store.CreateExecution(&storage.Execution{
+		ID: "prior-exec", TaskID: tk.ID,
+		StartTime: time.Now(), EndTime: time.Now(),
+		Status: "FAILED", ErrorMsg: "prior failure reason",
+	})
+
+	if err := pool.Submit(context.Background(), tk); err != nil {
+		t.Fatalf("submit: %v", err)
+	}
+	<-pool.Results()
+
+	if !strings.Contains(capturedPrompt, "prior failure reason") {
+		t.Errorf("expected prior failure in system prompt, got: %q", capturedPrompt)
+	}
+}
+
 func TestPool_UnsupportedAgent(t *testing.T) {
 	store := testStore(t)
 	runners := map[string]Runner{"claude": &mockRunner{}}