run: critic parity — fuller RecordStep + cause-carrying Kill (distinct status)
executus CI / test (pull_request) Successful in 46s
Adversarial Review (Gadfly) / review (pull_request) Successful in 22m30s

Completes the run-critic seam so a host adapter (mort's agentcritic) has full
fidelity, closing the two limitations gadfly surfaced on mort #1334.

- RecordStep(iter int, resp *llm.Response): the completed step's model response
  is now passed to the critic (was index-only), so a host that records a trace
  (mort's ProgressRecorder) can show what the agent actually produced, not just
  an iteration count. The executor forwards s.Response; the battery ignores it
  (its Progress is count-based).
- CriticHandle.KillCause() error + ErrCriticKill: the executor now distinguishes
  an explicit critic KILL from a natural backstop expiry. runCtx uses a
  cause-carrying cancel (WithCancelCause + a MaxRuntime timer cancelling with
  DeadlineExceeded); the deadline-watch cancels with ErrCriticKill when
  KillCause()!=nil, else DeadlineExceeded. statusFor reads context.Cause →
  killed / timeout / cancelled are now distinct (were all "cancelled"). The
  battery sets killCause from Decision.KillReason on a Kill.

Tests: statusFor "killed" case (cause=ErrCriticKill, err=Canceled); fake handle
+ battery RecordStep/KillCause signatures. Core stays battery-free.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-27 16:35:13 -04:00
parent 1a1d5e417b
commit 390e6cf905
7 changed files with 98 additions and 36 deletions
+14 -7
View File
@@ -148,20 +148,27 @@ func TestExecutorNilModelNoPanic(t *testing.T) {
}
}
// TestStatusFor maps run errors to RunStats.Status (gadfly F3).
// TestStatusFor maps run errors + cancellation cause to RunStats.Status (gadfly F3).
func TestStatusFor(t *testing.T) {
bg := context.Background()
// A context cancelled with the critic-kill cause: ctx.Err() is Canceled, but
// context.Cause carries ErrCriticKill → "killed".
killCtx, killCancel := context.WithCancelCause(context.Background())
killCancel(fmt.Errorf("%w: hung", ErrCriticKill))
cases := []struct {
ctx context.Context
err error
want string
}{
{nil, "ok"},
{context.DeadlineExceeded, "timeout"},
{context.Canceled, "cancelled"},
{fmt.Errorf("wrapped: %w", context.DeadlineExceeded), "timeout"},
{errors.New("boom"), "error"},
{bg, nil, "ok"},
{bg, context.DeadlineExceeded, "timeout"},
{bg, context.Canceled, "cancelled"},
{bg, fmt.Errorf("wrapped: %w", context.DeadlineExceeded), "timeout"},
{bg, errors.New("boom"), "error"},
{killCtx, context.Canceled, "killed"},
}
for _, c := range cases {
if got := statusFor(c.err); got != c.want {
if got := statusFor(c.ctx, c.err); got != c.want {
t.Errorf("statusFor(%v) = %q, want %q", c.err, got, c.want)
}
}