Files
Agent-Squad/squad/step_retry.go
T
weichen 23f161bfb3 Honor executor terminals in retries and interrupted recovery
Why: F05 - files-presence could promote failures to success, recovery
marked crashed steps completed on files alone or reran them blindly,
and retries minted a fresh ExecutionID each attempt.
Evidence: squad tests pass incl. executor result contract and recovery
tables (verify-u3b.json); (nil,nil), canceled and side-effect-possible
semantics handled; interrupted steps without a trusted terminal now
hold for reconciliation instead of auto-advancing.
Impact: retries reuse the step ExecutionID and shared deadline; no
auto-replay of unverified external actions.
Refs: feature/agent-stack-audit-remediation-b1 U3B
2026-10-21 17:20:40 +00:00

213 lines
6.5 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 squad
import (
"os"
"path/filepath"
"strings"
"unicode"
)
// MaxTransientStepInvocations is the product-layer bound: the first
// invocation plus one fresh re-invocation. SDK in-process auto_retry is
// separate and must not be confused with this.
const MaxTransientStepInvocations = 2
type FailureClass int
const (
FailureNone FailureClass = iota
FailureTransient
FailurePermanent
)
func (c FailureClass) String() string {
switch c {
case FailureTransient:
return "transient"
case FailurePermanent:
return "permanent"
default:
return "none"
}
}
type TraceSignals struct {
ProviderTransient bool
Settled bool
RetryExhausted bool
HasUsableDeliverable bool // always false: write() args in traces are not deliverables
}
type StepFailureSignals struct {
Err error
Result *ExecResult
WorkDir string
ExtraText string
TargetMissing bool
// TargetExists means this invocation wrote a non-empty file that differs
// from the pre-invoke baseline. Do not retry or overwrite it. The step
// still fails unless the backend already reported a trusted success.
TargetExists bool
}
type FailureAssessment struct {
Class FailureClass
Reason string
}
func ScanTraceText(text string) TraceSignals {
var out TraceSignals
if text == "" {
return out
}
// Line scan only. Never parse write.arguments.content into a body.
for _, line := range strings.Split(text, "\n") {
if line == "" {
continue
}
lower := strings.ToLower(line)
if strings.Contains(lower, `"type":"agent_settled"`) || strings.Contains(lower, `"type": "agent_settled"`) {
out.Settled = true
}
if strings.Contains(lower, `"type":"auto_retry_end"`) && strings.Contains(lower, `"success":false`) {
out.ProviderTransient = true
out.RetryExhausted = true
}
if strings.Contains(lower, `"type":"auto_retry_start"`) {
out.ProviderTransient = true
}
if strings.Contains(lower, `"stopreason":"error"`) {
out.ProviderTransient = true
}
if strings.Contains(lower, "connection error") {
out.ProviderTransient = true
}
if strings.Contains(lower, `"errormessage":"terminated"`) || strings.Contains(lower, `"errormessage": "terminated"`) {
out.ProviderTransient = true
}
}
return out
}
func ReadWorkDirTraces(workDir string) string {
if strings.TrimSpace(workDir) == "" {
return ""
}
p := filepath.Join(workDir, "execution.log")
b, err := os.ReadFile(p)
if err != nil {
return ""
}
const capBytes = 512 << 10
if len(b) > capBytes {
b = b[len(b)-capBytes:]
}
return string(b)
}
func AssessStepFailure(sig StepFailureSignals) FailureAssessment {
reason := combinedFailureText(sig)
lower := strings.ToLower(reason)
trace := ScanTraceText(sig.ExtraText + "\n" + ReadWorkDirTraces(sig.WorkDir))
missing := sig.TargetMissing || strings.Contains(lower, "missing target deliverable")
// F05/KTD4:explicit SideEffects=none 报告 = provably-not-dispatched。
// 缺则按 possible 对待(与旧语义一致)。这是 caller 自己传达的可重试信令。
provablyNotDispatched := sig.Result != nil && sig.Result.SideEffects == ExecSideEffectsNone
if sig.TargetExists {
return FailureAssessment{Class: FailurePermanent, Reason: "target-already-present: do not overwrite"}
}
if isPermanentReason(lower) {
return FailureAssessment{Class: FailurePermanent, Reason: "permanent: " + compactReason(reason)}
}
runnerFailed := (sig.Result != nil && sig.Result.Retryable) || isRunnerExplicitFailure(lower)
provider := trace.ProviderTransient || hasProviderTermOrConn(lower)
if runnerFailed {
return FailureAssessment{Class: FailureTransient, Reason: "runner-explicit-failure: " + compactReason(reason)}
}
if provider && missing {
kind := "provider-transient-missing-target"
if trace.Settled {
kind = "settled-failure-missing-target"
}
return FailureAssessment{Class: FailureTransient, Reason: kind + ": " + compactReason(reason)}
}
// Model settled cleanly but never wrote the target (e.g. text-only reply,
// no write tool). One product-layer re-invocation with a corrective prompt
// is worth trying; still bounded by MaxTransientStepInvocations.
if missing && trace.Settled && !provider {
return FailureAssessment{Class: FailureTransient, Reason: "settled-no-deliverable: " + compactReason(reason)}
}
// F05/U3b:SideEffects=none 失败原则上可重试(后端已声明未发生外部动作);
// 跨越该含义补一条有界重试通路,并覆盖纯获取后失败但文件已拼起的边界。
if provablyNotDispatched && !provider {
kind := "provably-not-dispatched"
if missing {
kind = "provably-not-dispatched-missing-target"
}
return FailureAssessment{Class: FailureTransient, Reason: kind + ": " + compactReason(reason)}
}
if missing {
return FailureAssessment{Class: FailurePermanent, Reason: "permanent-missing: " + compactReason(reason)}
}
return FailureAssessment{Class: FailurePermanent, Reason: "fail-closed: " + compactReason(reason)}
}
func combinedFailureText(sig StepFailureSignals) string {
var parts []string
if sig.Err != nil {
parts = append(parts, sig.Err.Error())
}
if sig.Result != nil {
if sig.Result.ErrorReason != "" {
parts = append(parts, sig.Result.ErrorReason)
}
if sig.Result.Logs != "" {
parts = append(parts, sig.Result.Logs)
}
}
return strings.Join(parts, " ")
}
func isPermanentReason(lower string) bool {
return strings.Contains(lower, "prompt_empty") ||
strings.Contains(lower, "unauthorized") ||
strings.Contains(lower, "budget_exceeded") ||
strings.Contains(lower, "治理强制终止") ||
strings.Contains(lower, "治理拦截")
}
func hasProviderTermOrConn(lower string) bool {
return strings.Contains(lower, "connection error") ||
strings.Contains(lower, "terminated") ||
strings.Contains(lower, "econnreset") ||
strings.Contains(lower, "socket hang up")
}
func isRunnerExplicitFailure(lower string) bool {
return strings.Contains(lower, "pi remote runner call failed") ||
strings.Contains(lower, "auto_retry_failed") ||
strings.Contains(lower, "auto_retry_end") ||
(hasProviderTermOrConn(lower) && !strings.Contains(lower, "missing target deliverable"))
}
func compactReason(s string) string {
s = strings.Join(strings.FieldsFunc(s, func(r rune) bool {
return r == '\n' || r == '\r'
}), " ")
s = strings.TrimSpace(s)
if s == "" {
return "unknown"
}
// Drop accidental write-argument bodies if a caller stuffed logs here.
if len(s) > 240 {
s = s[:240]
}
return strings.Map(func(r rune) rune {
if unicode.IsControl(r) && r != '\t' {
return -1
}
return r
}, s)
}