Files
orchestra/internal/integration/reconcile_escalation_test.go
T
kami 7f12c7fc37 v3 workflow: intent, phases, review, submission, enforcement, burn-in
The v3 stack, previously an uncommitted working tree, plus this session's two
units and the burn-in instrument. This commit is the burn-in build identity:
coordinator and worker must both report this revision before a task is created.

Workflow (earlier sessions, uncommitted until now): human decision events and
reduction, source cursors and reconcile-before-launch, turn-boundary
reconciliation, internal/agentctx as the single renderer, ace-fca phases with
sealed artifacts, the trajectory gate, bounded grilling, independent review,
task pr enforcement, and human review reflection.

Capability restrictions at the agent boundary: an authz.Agent surface at
GatedWrite may ask and may not act. It also fixes two bugs the unit exposed --
gated surfaces could not reach the two endpoints written for them, and
RequestHumanDecision would block an unowned task while rejecting a question
from the session that did own it.

Turn-boundary reconcile-failure escalation: a streak of consecutive failures
asks the session to hand off, fenced on the lease epoch, with reconcile_failure
as a real handoff reason. The worker was dropping the coordinator's verdict on
the floor; it now acts on it.

Burn-in: herdr.WriteLaunchContext dumps the exact agentctx.Build result to
<worktree>/.orchestra/launch.md at every launch, local and federated. BURNIN.md
is the runbook. deploy/build.sh stamps both binaries from one commit.

go build, go vet and go test ./... pass, 20 packages.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-26 18:31:20 +04:00

101 lines
3.6 KiB
Go

package integration
import (
"context"
"errors"
"testing"
"time"
"orchestra/internal/domain"
"orchestra/internal/human"
"orchestra/internal/orchestrator"
"orchestra/internal/router"
)
// The escape path, end to end. A source that stays down does not freeze a live
// session and does not let it run forever on intent Orchestra cannot refresh:
// the session is handed off, and the task then waits for the source rather
// than resuming from an older authority.
func TestReconcileFailureStreakHandsTheTaskToASuccessor(t *testing.T) {
s, reg, _ := setup(t)
task := ingest(t, s, "381")
src := &tracingSource{tr: &trace{}}
rec := &human.Reconciler{Store: s, Sources: map[string]human.Source{"gitea": src}}
s.PreLease = func(id string) error { return rec.Reconcile(context.Background(), id) }
h := &harness{occupancy: .5}
c := &orchestrator.Coordinator{Store: s, Worktrees: worktrees{}, Adapters: adapters{h}, StatePath: t.TempDir() + "/sessions.json", Hard: .8}
c.ReconcileFailureHandoff = 3
c.ReconcileHumanInput = rec.Reconcile
rt := router.Router{Store: s, Registry: reg, Reachability: alwaysReachable{}, OnLease: func(e domain.Event) error {
return c.Start(context.Background(), e)
}}
if leased, err := rt.AssignPending(); err != nil || len(leased) != 1 {
t.Fatalf("leased=%d err=%v", len(leased), err)
}
// The source goes down while the session is running.
src.err = errors.New("gitea unreachable")
for turn := 1; turn <= 2; turn++ {
verdict, err := c.TurnDecision(context.Background(), task.ID)
if err != nil {
t.Fatal(err)
}
if verdict != orchestrator.TurnContinue {
t.Fatalf("turn %d verdict = %q, want continue", turn, verdict)
}
}
verdict, err := c.TurnDecision(context.Background(), task.ID)
if err != nil {
t.Fatal(err)
}
if verdict != orchestrator.TurnPrepareHandoff {
t.Fatalf("third verdict = %q, want prepare_handoff", verdict)
}
// The agent writes its handoff and the session releases. (The release
// mechanics are proven in internal/orchestrator; what matters here is what
// happens to the task afterwards.)
ref, err := s.PutArtifact([]byte("handoff: next, keep going from the anchor"))
if err != nil {
t.Fatal(err)
}
leased, _ := s.Task(task.ID)
if err := s.Append(domain.Event{ID: domain.NewID(), Type: "TaskReleased", TaskID: task.ID, Version: leased.Version + 1, Surface: "system", Payload: mustJSON(map[string]any{
"handoff_ref": ref,
"reason": "reconcile_failure",
"anchor_sha": "0123456789012345678901234567890123456789",
"harness_id": leased.Lease.HarnessID,
"lease_epoch": leased.Lease.Epoch,
"expected_version": leased.Version,
})}); err != nil {
t.Fatal(err)
}
// Fail closed: while the source is still down, no successor starts.
if got, err := rt.AssignPending(); len(got) != 0 {
t.Fatalf("a successor was leased with the source still down: %v (err=%v)", got, err)
}
if got, _ := s.Task(task.ID); got.State != domain.StateQueued {
t.Fatalf("state = %s, want queued", got.State)
}
// The source recovers, carrying the correction the outage was hiding.
src.err = nil
src.inputs = []human.Input{{Provider: "gitea", ExternalID: "918", Author: "kami", Body: "no, use b", At: time.Now().UTC()}}
src.next = "918"
if got, err := rt.AssignPending(); err != nil || len(got) != 1 {
t.Fatalf("successor leased=%d err=%v", len(got), err)
}
intent, err := s.EffectiveIntent(task.ID)
if err != nil {
t.Fatal(err)
}
if len(intent.Decisions) != 1 || intent.Decisions[0].Value != "no, use b" {
t.Fatalf("successor authority = %+v", intent.Decisions)
}
if intent.Task.HandoffRef != ref {
t.Fatalf("handoff ref = %q, want %q", intent.Task.HandoffRef, ref)
}
}