Files
orchestra/internal/herdr/tmux_test.go
T
kami 1fd82f863c Acknowledge a launch only when the harness accepted it
Burn-in run 2 recorded TaskLaunchAcknowledged, opened a pane, and ran nothing
for fifteen minutes. The launch instruction sat in Claude Code's input editor
as "[Pasted text #1 +66 lines]" at zero tokens and zero elapsed. Two separate
bugs produced that.

The transport was wrong for the harness. TmuxBackend.Prompt writes the whole
instruction with send-keys -l and then sends Enter, and the TUI coalesces the
fast multi-line write into a paste that absorbs the following Enter. Launch
transport is now a backend property rather than one universal prompt format:
claude on tmux submits a single line pointing at .orchestra/launch.md, every
other harness keeps the inline path it was verified on. agentctx is unchanged
and the file still holds the exact bytes Orchestra rendered, so what the agent
receives is identical either way. Under the file transport a failed write is
now a failed launch, because there the file is the instruction.

The acknowledgement was also wrong. It meant "Prompt returned nil", not "the
harness accepted the prompt". Backends may now implement ConfirmLaunch, and
the tmux one polls until the input editor clears and the agent is observably
busy, blocked on approval, or at least no longer holding the text. An editor
that still holds the prompt at the deadline is a definite failure. The worker
kills the pane, drops the session so the retry starts clean, and returns
ErrPromptNotSubmitted, which classifies as prompt_not_submitted rather than
launch_uncertain. That class already falls through to TaskReleased, so the
existing retry path takes it and no lease is held on a launch that never
happened.

The confirmation bound is tunable because how fast a terminal harness reacts
is a property of the host. It is not a sleep before the submit: the submit is
deterministic, and this waits for the harness to visibly react to it.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-27 00:46:56 +04:00

234 lines
8.0 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
package herdr
import (
"context"
"errors"
"fmt"
"os"
"os/exec"
"path/filepath"
"strings"
"testing"
"time"
)
func TestTmuxBackendStartsCapturesPromptsAndKillsClaude(t *testing.T) {
if testing.Short() {
t.Skip("requires tmux")
}
dir := t.TempDir()
harness := filepath.Join(dir, "fake-claude")
script := "#!/bin/sh\nprintf ' ready\\n'\nwhile IFS= read -r line; do printf 'GOT:%s\\n' \"$line\"; done\n"
if err := os.WriteFile(harness, []byte(script), 0o755); err != nil {
t.Fatal(err)
}
b := NewTmuxBackend(filepath.Join(t.TempDir(), "tmux.sock"), harness)
if err := b.Check(context.Background()); err != nil {
t.Fatal(err)
}
s, err := b.StartAgent(context.Background(), dir, dir, "", "claude", "tmux-backend-test")
if err != nil {
t.Fatal(err)
}
t.Cleanup(func() { _ = b.Kill(context.Background(), s) })
if s.Worktree != dir || s.Harness != "claude" || !strings.Contains(s.PaneID, ":") || !strings.Contains(s.PaneID, ".") {
t.Fatalf("unexpected session: %+v", s)
}
if err := b.Prompt(context.Background(), s.PaneID, "hello from Orchestra", 0); err != nil {
t.Fatal(err)
}
deadline := time.Now().Add(2 * time.Second)
for {
capture, err := b.PaneCapture(context.Background(), s, "recent")
if err != nil {
t.Fatal(err)
}
if strings.Contains(capture, "GOT:hello from Orchestra") {
break
}
if time.Now().After(deadline) {
t.Fatalf("prompt was not captured: %q", capture)
}
time.Sleep(20 * time.Millisecond)
}
for _, line := range []string{"/clear", "@HANDOFF.md"} {
if err := b.SendText(context.Background(), s, line); err != nil {
t.Fatal(err)
}
if err := b.SendKeys(context.Background(), s, []string{"ENTER"}); err != nil {
t.Fatal(err)
}
}
deadline = time.Now().Add(2 * time.Second)
for {
capture, err := b.PaneCapture(context.Background(), s, "recent")
if err != nil {
t.Fatal(err)
}
if strings.Contains(capture, "GOT:/clear") && strings.Contains(capture, "GOT:@HANDOFF.md") {
break
}
if time.Now().After(deadline) {
t.Fatalf("Claude rollover lines were not captured: %q", capture)
}
time.Sleep(20 * time.Millisecond)
}
if status, err := b.AgentStatus(context.Background(), s); err != nil || status != "idle" {
t.Fatalf("status=%q err=%v", status, err)
}
if err := b.ReleaseAgent(context.Background(), s, "claude"); err != nil {
t.Fatal(err)
}
if err := b.Kill(context.Background(), s); err != nil {
t.Fatal(err)
}
if _, err := b.PaneCapture(context.Background(), s, "recent"); err == nil {
t.Fatal("killed tmux session remained readable")
}
}
func TestTmuxBackendRefusesUnverifiedHarnesses(t *testing.T) {
b := NewTmuxBackend("test", "true")
if _, err := b.StartAgent(context.Background(), "", t.TempDir(), "", "codex", "task"); err == nil {
t.Fatal("tmux backend accepted Codex before its terminal behavior was implemented")
}
}
func TestTmuxSessionNameKeepsCollisionResistantSuffix(t *testing.T) {
a := tmuxSessionName(strings.Repeat("same-prefix", 10) + "-one")
b := tmuxSessionName(strings.Repeat("same-prefix", 10) + "-two")
if a == b || len(a) > 64 || len(b) > 64 {
t.Fatalf("unsafe tmux session names %q %q", a, b)
}
}
// The launch dump is Orchestra's scratch space, not the session's work. A
// worktree that starts dirty pollutes the gate, the review diff, and the
// agent's own reading of `git status`.
func TestWriteLaunchContextLeavesTheWorktreeClean(t *testing.T) {
dir := t.TempDir()
for _, args := range [][]string{{"init"}, {"config", "user.email", "t@t"}, {"config", "user.name", "t"}, {"commit", "--allow-empty", "-m", "init"}} {
if out, err := exec.Command("git", append([]string{"-C", dir}, args...)...).CombinedOutput(); err != nil {
t.Fatalf("git %v: %v: %s", args, err, out)
}
}
if err := WriteLaunchContext(dir, "the instruction"); err != nil {
t.Fatal(err)
}
b, err := os.ReadFile(filepath.Join(dir, LaunchContextFile))
if err != nil || string(b) != "the instruction" {
t.Fatalf("launch context = %q, err %v", b, err)
}
out, err := exec.Command("git", "-C", dir, "status", "--short").CombinedOutput()
if err != nil {
t.Fatal(err)
}
if strings.TrimSpace(string(out)) != "" {
t.Fatalf("worktree is dirty after a launch dump:\n%s", out)
}
}
func TestLaunchTransportIsHarnessSpecific(t *testing.T) {
b := &TmuxBackend{}
if got := b.LaunchTransport("claude"); got != LaunchFileRef {
t.Fatalf("claude transport=%q, want %q", got, LaunchFileRef)
}
for _, harness := range []string{"opencode", "codex", ""} {
if got := b.LaunchTransport(harness); got != LaunchInline {
t.Fatalf("%s transport=%q, want %q", harness, got, LaunchInline)
}
}
}
// The exact F15 signature: the TUI coalesced the launch text into a paste and
// absorbed the Enter, leaving the instruction in the input editor.
func TestPendingInputSeesAnUnsubmittedPaste(t *testing.T) {
stalled := " b141e4f6 - none | 0/1.0m ctx\n [Pasted text #1 +66 lines]\n────────────\n"
if got := pendingInput(stalled); got != "[Pasted text #1 +66 lines]" {
t.Fatalf("pendingInput=%q, want the unsubmitted paste", got)
}
if got := pendingInput("esc to interrupt\n \n"); got != "" {
t.Fatalf("pendingInput=%q, want empty for a cleared editor", got)
}
if got := pendingInput(" @.orchestra/launch.md is your complete Orchestra launch instruction."); got == "" {
t.Fatal("a one-line reference still sitting in the editor must count as pending")
}
if got := pendingInput("no editor line here"); got != "" {
t.Fatalf("pendingInput=%q, want empty when no editor line is visible", got)
}
}
// fakeTmux scripts capture-pane so confirmation can be driven without waiting
// on a real harness. clearAfter is how many captures still show the stalled
// editor before it clears.
func fakeTmux(t *testing.T, clearAfter int, failCapture bool) *TmuxBackend {
t.Helper()
dir := t.TempDir()
bin := filepath.Join(dir, "tmux")
fail := "0"
if failCapture {
fail = "1"
}
script := `#!/bin/sh
state=` + filepath.Join(dir, "count") + `
cmd=""
for a in "$@"; do
case "$a" in
capture-pane|has-session|display-message) cmd=$a; break;;
esac
done
case "$cmd" in
has-session) exit 0 ;;
display-message) printf '0\tclaude\n'; exit 0 ;;
capture-pane)
if [ "` + fail + `" = "1" ]; then echo "no server running" >&2; exit 1; fi
n=$(cat $state 2>/dev/null || echo 0); n=$((n+1)); echo $n > $state
if [ "$n" -le "` + fmt.Sprint(clearAfter) + `" ]; then
printf '\xe2\x9d\xaf [Pasted text #1 +66 lines]\n'
else
printf 'esc to interrupt\n\xe2\x9d\xaf \n'
fi
exit 0 ;;
esac
exit 0
`
if err := os.WriteFile(bin, []byte(script), 0o755); err != nil {
t.Fatal(err)
}
return &TmuxBackend{Binary: bin, LaunchConfirmTimeout: 2 * time.Second, LaunchConfirmPoll: 5 * time.Millisecond}
}
func TestConfirmLaunchAcceptsObservedActivity(t *testing.T) {
b := fakeTmux(t, 1, false)
evidence, err := b.ConfirmLaunch(context.Background(), Session{PaneID: "s:1.0"}, LaunchReference)
if err != nil {
t.Fatalf("confirm: %v", err)
}
if !strings.Contains(evidence, "busy") {
t.Fatalf("evidence=%q, want the observed activity named", evidence)
}
}
// Prompt returning nil is not proof. An editor that still holds the text at
// the deadline is a launch failure, and it must be the one class that releases
// the lease instead of holding it as uncertain.
func TestConfirmLaunchFailsWhileTheEditorStillHoldsThePrompt(t *testing.T) {
b := fakeTmux(t, 1000, false)
b.LaunchConfirmTimeout = 60 * time.Millisecond
_, err := b.ConfirmLaunch(context.Background(), Session{PaneID: "s:1.0"}, LaunchReference)
if !errors.Is(err, ErrPromptNotSubmitted) {
t.Fatalf("err=%v, want ErrPromptNotSubmitted", err)
}
if !strings.Contains(err.Error(), "Pasted text") {
t.Fatalf("err=%v, want the stalled editor content quoted", err)
}
}
// A confirmation that cannot read the pane must not become an acknowledgement.
func TestConfirmLaunchSurfacesTransportErrors(t *testing.T) {
b := fakeTmux(t, 0, true)
if _, err := b.ConfirmLaunch(context.Background(), Session{PaneID: "s:1.0"}, LaunchReference); err == nil {
t.Fatal("a failed pane capture must not confirm a launch")
}
}