mirrors/pikasTech-unidesk
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: 收敛受控 CLI 调用与诊断

Browse Source
This commit is contained in:
Codex
2026-07-12 17:08:00 +02:00
parent 00c60a17cd
commit 2a80e08a40
13 changed files with 168 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/src/platform-infra-observability/diagnose-code-agent-script.ts
+32 -7
View File
@@ -2023,10 +2023,10 @@ def root_cause_candidates(http_summary, agentrun, read_model, lag_summary, error
status_conflict = terminal_status_conflicts(agentrun.get("terminalStatus"), read_model_turn_status)
if status_conflict:
candidates.append({
"code": "otel_business_trace_terminal_conflict",
"label": "OTel terminal conflict",
"code": "projection_authority_terminal_conflict",
"label": "projection/authority terminal conflict",
"confidence": 0.86,
"summary": "Scoped AgentRun terminal status conflicts with HWLAB read-model turn status for the requested business trace; prefer the HWLAB read-model status for Workbench RCA and inspect OTel correlation leakage.",
"summary": "HWLAB projection conflicts with the scoped AgentRun durable authority; preserve the AgentRun terminal outcome and inspect projection correlation or lag.",
"evidence": {
"agentrunTerminalStatus": agentrun.get("terminalStatus"),
"hwlabReadModelTurnStatus": read_model_turn_status,
@@ -2502,16 +2502,16 @@ if http_summary.get("actorForbidden"):
read_model_turn_status = read_model.get("turnStatus")
agentrun_read_model_status_conflict = terminal_status_conflicts(terminal_status, read_model_turn_status)
if agentrun_read_model_status_conflict:
facts.append("OTel AgentRun terminal status conflicts with HWLAB read model")
if terminal_status in ("failed", "error", "timeout", "blocked", "cancelled") and not agentrun_read_model_status_conflict:
facts.append("HWLAB projection conflicts with AgentRun durable authority")
if terminal_status in ("failed", "error", "timeout", "blocked", "cancelled"):
failure_kind = agentrun.get("failureKind")
if failure_kind:
facts.append(f"AgentRun terminal failed ({failure_kind})")
else:
facts.append("AgentRun terminal failed")
if terminal_status == "completed" and not agentrun_read_model_status_conflict:
if terminal_status == "completed":
facts.append("AgentRun completed")
if (terminal_status in (None, "") or agentrun_read_model_status_conflict) and read_model_turn_status in ("completed", "failed", "error", "timeout", "blocked", "cancelled", "canceled"):
if terminal_status in (None, "") and read_model_turn_status in ("completed", "failed", "error", "timeout", "blocked", "cancelled", "canceled"):
facts.append("HWLAB read model terminal " + str(read_model_turn_status))
if lag.get("status") in ("confirmed", "suspected"):
facts.append("projection/read-model stale")
@@ -2552,6 +2552,30 @@ evidence = {
"idleWarningSpanCount": len(idle_warning_spans),
"idleWarningSpanTail": [tiny_span(item) for item in idle_warning_spans[-3:]],
}
projection_warning = lag.get("status") in ("confirmed", "suspected") or agentrun_read_model_status_conflict
effective_status = terminal_status if terminal_status not in (None, "") else read_model_turn_status
typed_outcome = "unknown"
if effective_status not in (None, ""):
typed_outcome = str(effective_status)
if projection_warning:
typed_outcome = typed_outcome + "-with-projection-warning"
outcome = {
"typed": typed_outcome,
"effectiveStatus": effective_status,
"authority": {
"kind": "agentrun-durable-command",
"status": terminal_status,
"source": agentrun.get("terminalSource"),
},
"projection": {
"kind": "hwlab-read-model",
"status": read_model_turn_status,
"lag": lag.get("status"),
"warning": projection_warning,
"blocking": False,
},
"mutation": False,
}
payload = {
"ok": trace_rc == 0 and len(spans) > 0,
"mapping": mapping,
@@ -2594,6 +2618,7 @@ payload = {
"actorForbidden": http_summary.get("actorForbidden"),
},
"projectionLag": lag,
"outcome": outcome,
"summary": summary,
"rootCauseCandidates": candidates,
"spanNameCounts": flat["spanNameCounts"][:12],