kami/orchestra
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Complete autonomous recovery controls

Browse Source
This commit is contained in:
kami
2026-07-30 14:57:25 +04:00
parent 8174400b1a
commit e8fadfc998
18 changed files with 364 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmd/orchestra/main.go
+52 -1
View File
@@ -1060,7 +1060,7 @@ func main() {
w.WriteHeader(http.StatusNoContent)
})
mux.HandleFunc("/v1/federation/workers/", func(w http.ResponseWriter, r *http.Request) {
if r.Method != http.MethodPost || (!strings.HasSuffix(r.URL.Path, "/heartbeat") && !strings.HasSuffix(r.URL.Path, "/renew") && !strings.HasSuffix(r.URL.Path, "/handoff") && !strings.HasSuffix(r.URL.Path, "/pickup") && !strings.HasSuffix(r.URL.Path, "/complete") && !strings.HasSuffix(r.URL.Path, "/captures")) {
if r.Method != http.MethodPost || (!strings.HasSuffix(r.URL.Path, "/heartbeat") && !strings.HasSuffix(r.URL.Path, "/renew") && !strings.HasSuffix(r.URL.Path, "/start") && !strings.HasSuffix(r.URL.Path, "/nack") && !strings.HasSuffix(r.URL.Path, "/handoff") && !strings.HasSuffix(r.URL.Path, "/pickup") && !strings.HasSuffix(r.URL.Path, "/complete") && !strings.HasSuffix(r.URL.Path, "/captures")) {
http.Error(w, "not found", 404)
return
}
@@ -1122,6 +1122,8 @@ func main() {
Branch string `json:"branch"`
Remote string `json:"remote"`
Receipt map[string]any `json:"receipt"`
FailureClass string `json:"failure_class"`
LastError string `json:"last_error"`
SessionEvidence domain.SessionEvidence `json:"session_evidence"`
}
if json.NewDecoder(r.Body).Decode(&b) != nil || b.TaskID == "" {
@@ -1149,6 +1151,55 @@ func main() {
http.Error(w, "lease version conflict", http.StatusConflict)
return
}
if strings.HasSuffix(r.URL.Path, "/start") {
// A lost response after append is an idempotent start ACK, not a
// reason to strand the running pane behind a stale version.
if t.LifecyclePhase == "started" && t.Lease != nil && t.Lease.HarnessID == parts[3] && t.Lease.Epoch == b.LeaseEpoch {
w.WriteHeader(http.StatusNoContent)
return
}
if b.ExpectedVersion != t.Version {
http.Error(w, "lease version conflict", http.StatusConflict)
return
}
p, _ := json.Marshal(map[string]any{"harness_id": parts[3], "lease_epoch": b.LeaseEpoch, "expected_version": t.Version, "lifecycle_phase": "started", "session_evidence": b.SessionEvidence})
e := domain.Event{ID: id(), Type: "TaskLaunchAcknowledged", TaskID: b.TaskID, Version: t.Version + 1, Payload: p, Surface: string(authz.System)}
if err := s.Append(e); err != nil {
http.Error(w, err.Error(), http.StatusConflict)
return
}
json.NewEncoder(w).Encode(e)
return
}
if strings.HasSuffix(r.URL.Path, "/nack") {
if b.ExpectedVersion != t.Version || b.FailureClass == "" || b.LastError == "" {
http.Error(w, "current lease version, failure_class, and last_error required", http.StatusConflict)
return
}
var typ string
var p []byte
switch b.FailureClass {
case "invalid_handoff":
typ = "TaskBlocked"
p, _ = json.Marshal(map[string]any{"blocker": b.LastError, "block_reason": string(domain.BlockReasonHandoffValidation), "harness_id": parts[3], "lease_epoch": b.LeaseEpoch, "expected_version": t.Version, "lifecycle_phase": "launch_nacked", "last_error": b.LastError, "session_evidence": b.SessionEvidence})
case "launch_uncertain":
typ = "TaskNeedsAttention"
p, _ = json.Marshal(map[string]any{"blocker": b.LastError, "block_reason": string(domain.BlockReasonLeaseFailure), "harness_id": parts[3], "lease_epoch": b.LeaseEpoch, "expected_version": t.Version, "lifecycle_phase": "launch_uncertain", "last_error": b.LastError, "session_evidence": b.SessionEvidence})
default:
typ = "TaskReleased"
p, _ = json.Marshal(map[string]any{"reason": "launch_failed", "failure_class": b.FailureClass, "harness_id": parts[3], "lease_epoch": b.LeaseEpoch, "expected_version": t.Version, "lifecycle_phase": "launch_nacked", "last_error": b.LastError, "session_evidence": b.SessionEvidence})
}
e := domain.Event{ID: id(), Type: typ, TaskID: b.TaskID, Version: t.Version + 1, Payload: p, Surface: string(authz.System)}
if err := s.Append(e); err != nil {
http.Error(w, err.Error(), http.StatusConflict)
return
}
if typ == "TaskReleased" && rt != nil {
_, _ = rt.HandleEvent(e)
}
json.NewEncoder(w).Encode(e)
return
}
if strings.HasSuffix(r.URL.Path, "/renew") {
ttl := b.TTLSeconds
if ttl == 0 {