elanous 0.2.36 → 0.2.38

package/src/task-orchestrator/surfaces/self-implement-pod.ts

@@ -21,7 +21,8 @@ import { POD_CREDENTIAL_TOKEN_ENV, POD_CREDENTIAL_URL_ENV } from '../../grok/cre
 import { isVerifiedOpenGatewayModel } from '../../llm/opengateway-models.js';
 import { configuredOpenGatewayKeys } from '../../llm/provider-credentials.js';
 import { collectPodLedgers, createPodLedgerFollower } from './pod-ledger-collect.js';
-import { collectPodArtifacts, podNoResultDiagnostic } from './pod-artifact-return.js';
+import { captureFailedPodJobs } from './pod-ledger-events.js';
+import { collectPodArtifacts, podNoResultDiagnostic, POD_SALVAGE_BUNDLE_FILE_LIMIT, POD_SALVAGE_BUNDLE_TOTAL_LIMIT } from './pod-artifact-return.js';
 import { readPodRepairArtifact } from './pod-repair-commit.js';
 import { isValidAccountName, resolveCodexAccount } from '../../oauth/codex-account.js';
 import { createCodexAccessMirror } from '../../oauth/codex-access-mirror.js';
@@ -31,6 +32,8 @@ import { finishPodFragment, writePodFragment } from '../../harness/self-send-tar
 import { mintRunId, normalizeRunId } from '../../harness/harness-space.js';
 import { TA_LAND_ENV } from '../../task-agent/task-hand.js';
 import { appendRunLedgerEntry, loadRunLedger, runLedgerDir, runLedgerPath, type RunLedgerEntry } from '../../self-implement/run-ledger.js';
+import { recordRunStop } from '../../self-implement/run-stop.js';
+import { gateFailureReceipt, gateFailureReceiptLines } from '../../self-implement/gate-failure-signature.js';
 import { runSuffixKey } from '../../self-implement/salvage-branches.js';
 import type { GoalExecutionRecord } from '../../self-implement/orchestrator.js';
 import { hostRepositoryUnavailable, runHostRegate, type HostRegateResult } from '../../self-implement/host-regate.js';
@@ -67,14 +70,14 @@ export const POD_JOB_DEADLINE_SECONDS = 10_800;
 import { POD_LAUNCH_FINISHED_EVENT, POD_LAUNCH_STARTED_EVENT, provenanceRowFromAnnotations, siTaskPodProvenance } from './pod-launch-history.js';
 import { podProvenanceMetadata, type PodProvenanceMetadata } from './pod-provenance.js';
 import { packageVersion } from '../../version/code-revision.js';
-import { podWorkLabels, type PodWorkIdentity, type PodPlacement, type PodPlacementKind, type PodPoolMember, type PodPoolScheduler } from './pod-pool.js';
+import { minihLocationFrom, podWorkLabels, type PodWorkIdentity, type PodPlacement, type PodPlacementKind, type PodPoolMember, type PodPoolScheduler } from './pod-pool.js';
 export { POD_CHILD_REQUESTS } from './pod-lease.js';
 import { measurePoolLease, recommendConcurrency, POD_CHILD_REQUESTS, POD_SI_ADMISSION_CAP_BYTES, POD_HOST_LEASE_ANNOTATION, POD_JOB_TTL_AFTER_FINISHED_SECONDS, LEASE_KUBECTL_MAX_BUFFER, memoryQuantityBytes } from './pod-lease.js';
 import { ACTUAL_SUBSTRATE_ENV, RUN_CONTRACT_ENV, carryRunContract, completionFloorFor } from '../../self-implement/graph-run-contract.js';
-import { execFile, spawnSync } from 'node:child_process';
+import { execFile, execFileSync, spawnSync } from 'node:child_process';
 import { createHash } from 'node:crypto';
-import { existsSync, mkdirSync, readFileSync, realpathSync } from 'node:fs';
-import { homedir } from 'node:os';
+import { existsSync, mkdirSync, mkdtempSync, readFileSync, realpathSync, rmSync } from 'node:fs';
+import { homedir, tmpdir } from 'node:os';
 import { isAbsolute, join, normalize, relative, resolve, sep } from 'node:path';
 import { findGitDir } from '../../git-fs/locate.js';
 import { hostLeaseBaseDir } from '../../pod-lease/host-lease.js';
@@ -84,20 +87,21 @@ import { enterJourneyNode, exitJourneyNode, passJourneyNode } from '../../self-d
 import { routeJourneyEdge } from '../../self-dev/graph-journey-route.js';
 import { selectLiveDetail } from '../../live/detail-switch.js';
 import { authStorePath } from '../../oauth/store.js';
-import { grokAuthFilePath, isGrokSubscriptionExpiring, refreshGrokSubscriptionToken, resolveGrokCredential, type GrokRefreshOutcome } from '../../grok/credential.js';
+import { grokAuthFilePath, isGrokSubscriptionExpiring, readSelectedGrokScope, refreshGrokSubscriptionToken, resolveGrokCredential, type GrokRefreshOutcome } from '../../grok/credential.js';
 import { defaultGrokModel } from '../../grok/models.js';
 import { resolveHostId } from '../../platform/host-id.js';
 import { BUDGET_SNAPSHOT_ENV, encodeBudgetSnapshot, harnessLaunchBudgetDecision, type BudgetSnapshot } from '../../execution-loop/launch-gate.js';
 import type { ReadBudgetInputsDeps } from '../../self-implement/budget-gate.js';
 import { envLiteral } from '../../platform/env-literal.js';
 import { LLM_TIER_MAP_BY_PROVIDER, lookupLlmTierSpec, type LlmTierProvider } from '../../model-tier/llm-tier-map.js';
-import { parseSelfImplementJson, type SelfImplementJobDone, type SelfImplementJobSpawn } from './self-implement.js';
+import { parseSelfImplementJson, type SelfImplementDisposition, type SelfImplementJobDone, type SelfImplementJobSpawn } from './self-implement.js';
 import { codexQuotaPolicyFromConfig } from '../../oauth/codex-account-store.js';
 import { normalizeFallbackChain, type FallbackStep } from '../../oauth/fallback-chain.js';
 import { goalTypeOf, type GoalType } from '../../../scripts/measure-pod-memory-by-goal.js';
 import { declaredGoalType, type GoalType as DeclaredGoalType } from '../../self-implement/goal-author.js';
 import { readPodMemoryAdvice, type PodMemoryAdvice } from '../../cli/pod-memory-advice.js';
 import { DEFAULT_BUDGET_GATE_MAX_USED_PERCENT, getUserConfig, roleLlmEnvName, type UserConfig } from '../../user-config.js';
+import { worktreeAddTimeoutSec } from '../../git-fs/worktree.js';
 import { podChildProviderOf, podChildProviderRefusal, type PodChildProvider } from './pod-child-providers.js';
 import { BEDROCK_POD_EGRESS_LABEL, bedrockPodEnv, checkBedrockPodSecret, type BedrockPodSpec } from './pod-bedrock-child.js';
 import { resolveBedrockRegion, validBedrockRegion } from '../../llm/bedrock.js';
@@ -105,7 +109,7 @@ import { ZAI_POD_EGRESS_LABEL, checkZaiPodSecret, countActiveZaiJobs, decideZaiP
 import { ZAI_CODING_DEFAULT_MODEL, ZAI_OPENROUTER_FALLBACK_MODEL, zaiSettingsFromConfig, type ZaiCodingPlanSettings } from '../../llm/zai-coding-plan.js';
 import { normalizePlanningFallbackReason, selectEnhanceLlm } from '../../prompt-enhance/enhance.js';
 import { inferProviderFromModel } from '../../llm.js';
-import { classifyPodExit, extractPodFailureReason, podChildFailureAttribution, podTerminalRow, POD_TERMINATION_JOB_JSONPATH, POD_TERMINATION_PODS_JSONPATH, readPodTermination, type PodExitClass, type PodTermination } from './pod-failure-reason.js';
+import { classifyPodExit, extractPodFailureReason, podChildFailureAttribution, podDeadlineResultMarker, podJobConditionReason, podTerminalRow, POD_TERMINATION_JOB_JSONPATH, POD_TERMINATION_PODS_JSONPATH, readPodTermination, type PodExitClass, type PodTermination } from './pod-failure-reason.js';
 import { kubectlTransientReason, retryKubectlTransient } from './kubectl-transient-retry.js';
 import { OLD_DOOR_STAMP_ENV } from '../../self-dev/old-door.js';
 import { resolveDefaultSourceHead, seedMirrorOnce, type MirrorSeedResult } from './pod-mirror-seed.js';
@@ -228,6 +232,8 @@ export interface PodSpawnOptions {
   /** LAUNCH-STALL: ms a launch may wait in one stage before `launch-stalled` (test seam; default harness.launchStallMinutes · 15 min). */
   launchStallMs?: number;
   kubectl?: Kubectl;
+  /** Capture SSH transport test seam; host selection and placement validation remain in the production path. */
+  failureCaptureRemote?: (host: string, args: readonly string[]) => ReturnType<Kubectl>;
   /** Host-side regate (injected for Pod tests). */
   hostRegate?: (input: { prNumber: number; headCommit: string; repoRoot: string; goalFile?: string; noMerge?: true }) => Promise<HostRegateResult>;
   /** REVIEW-ACP-POD — Pod merge-ready PR 을 호스트 Claude ACP 로 리뷰한 뒤 재게이트(opt-in · 옵션 → env `ELANOUS_POD_HOST_ACP_REVIEW` → config `llm.podHostAcpReview`). */
@@ -522,15 +528,6 @@ export function formatGrokRemaining(ms: number | null): string {
   return m >= 60 ? `${Math.floor(m / 60)}h${String(m % 60).padStart(2, '0')}m` : `${m}m`;
 }
 
-/** Latest `expires_at` among scopes that carry an access key (the token the Pod would get). */
-function grokSubscriptionExpiresAtMs(home?: string): number | null {
-  try {
-    const scopes = JSON.parse(readFileSync(grokAuthFilePath(home), 'utf8')) as Record<string, { key?: unknown; expires_at?: unknown }>;
-    const all = Object.values(scopes).flatMap((s) => (s && typeof s.key === 'string' && s.key && typeof s.expires_at === 'string' && Number.isFinite(Date.parse(s.expires_at)) ? [Date.parse(s.expires_at)] : []));
-    return all.length ? Math.max(...all) : null;
-  } catch { return null; }
-}
-
 /** POD-GROK-VALIDITY-FIT — this launch's Job deadline for a refresh-less grok subscription copy.
  *  · relay (the Pod can renew from the host) or unknown expiry → the requested deadline as is.
  *  · otherwise → min(requested, remaining − margin); below the minimum Job (time passed since the credential check)
@@ -570,38 +567,46 @@ export function podGhLoginRetryBackoffMs(job: string): number {
 export function hostGrokCredentials(opts: {
   home?: string; env?: NodeJS.ProcessEnv; apiKeyOptIn?: boolean; ghToken?: () => string;
   /** Test seams — the host refresh (read-only `grok models`) and the expiry probe. */
-  refresh?: () => void; isExpiring?: () => boolean;
+  refresh?: () => void; isExpiring?: () => boolean; grokPath?: string;
   /** Required remaining token life (default POD_GROK_MIN_VALIDITY_MS) — a caller whose Job is not fitted passes its own deadline. */
   minValidityMs?: number; now?: () => number;
 } = {}): { grokAuth?: string; grokApiKey?: string; ghToken: string } {
   let credential = resolveGrokCredential({ home: opts.home, env: opts.env });
   if (credential?.kind === 'subscription') {
+    const initialScope = readSelectedGrokScope(opts.home);
+    if (!initialScope) throw new Error('grok: 선택된 구독 scope 없음 — 발사를 거부');
     const minValidityMs = opts.minValidityMs ?? POD_GROK_MIN_VALIDITY_MS;
-    const expiring = opts.isExpiring ?? (() => isGrokSubscriptionExpiring({ home: opts.home, bufferMs: minValidityMs, ...(opts.now ? { now: opts.now } : {}) }));
-    if (expiring()) {
-      try { (opts.refresh ?? (() => { refreshGrokSubscriptionToken({ home: opts.home }); }))(); } catch { /* judged below */ }
-      if (expiring()) {
-        const at = grokSubscriptionExpiresAtMs(opts.home);
-        const remainingMs = at === null ? null : at - (opts.now ?? Date.now)();
-        try { debug.log('pod.grok-credentials', 'refused', { remainingMs, minValidityMs, expiresAt: at === null ? null : new Date(at).toISOString() }); } catch { /* fail-soft */ }
-        throw new Error(`grok: 구독 access 토큰 남은 시간 ${formatGrokRemaining(remainingMs)} < Pod 발사 기준 ${formatGrokRemaining(minValidityMs)} — 호스트 갱신(grok models)도 못 늘렸다 · 다음: 호스트에서 grok login --device-auth 후 다시`);
+    const clock = opts.now ?? Date.now;
+    const initialExpiry = initialScope.expiresAt ? Date.parse(initialScope.expiresAt) : NaN;
+    const expiring = opts.isExpiring ? opts.isExpiring()
+      : !Number.isFinite(initialExpiry) || initialExpiry - clock() < minValidityMs;
+    if (expiring) {
+      if (!initialScope.hasRefreshToken) {
+        throw new Error('grok: 선택된 구독 scope에 refresh token 없음 — 다른 계정으로 대체하지 않고 발사를 거부');
       }
-      credential = resolveGrokCredential({ home: opts.home, env: opts.env });
-      if (credential?.kind !== 'subscription') throw new Error('grok: 갱신 뒤 구독 자격을 다시 읽지 못했다');
+      try {
+        if (opts.refresh) opts.refresh();
+        else refreshGrokSubscriptionToken({ home: opts.home, requireRefreshToken: true,
+          requiredValidityMs: minValidityMs, nowMs: clock(), ...(opts.grokPath ? { grokPath: opts.grokPath } : {}) });
+      } catch { /* Final snapshot below is the launch decision. */ }
     }
-    const scopes = JSON.parse(readFileSync(grokAuthFilePath(opts.home), 'utf8')) as Record<string, unknown>;
-    const redacted: Record<string, { key: string; expires_at?: string; user_id?: string }> = {};
-    for (const [name, value] of Object.entries(scopes)) {
-      if (!value || typeof value !== 'object' || Array.isArray(value)) continue;
-      const scope = value as Record<string, unknown>;
-      if (scope.key !== credential.token) continue;
-      redacted[name] = {
-        key: scope.key,
-        ...(typeof scope.expires_at === 'string' ? { expires_at: scope.expires_at } : {}),
-        ...(typeof scope.user_id === 'string' ? { user_id: scope.user_id } : {}),
-      };
+    const selected = readSelectedGrokScope(opts.home);
+    if (!selected || selected.scopeName !== initialScope.scopeName) {
+      throw new Error('grok: 자격 확인 중 선택된 구독 scope가 사라졌거나 바뀜 — 발사를 거부');
+    }
+    const selectedExpiry = selected.expiresAt ? Date.parse(selected.expiresAt) : NaN;
+    if (!Number.isFinite(selectedExpiry) || selectedExpiry - clock() < minValidityMs) {
+      const remainingMs = Number.isFinite(selectedExpiry) ? selectedExpiry - clock() : null;
+      try { debug.log('pod.grok-credentials', 'refused', { remainingMs, minValidityMs, expiresAt: selected.expiresAt }); } catch { /* fail-soft */ }
+      throw new Error(`grok: 구독 access 토큰 남은 시간 ${formatGrokRemaining(remainingMs)} < Pod 발사 기준 ${formatGrokRemaining(minValidityMs)} — 호스트 갱신(grok models)도 못 늘렸다 · 다음: 호스트에서 grok login --device-auth 후 다시`);
     }
-    if (!Object.keys(redacted).length) throw new Error('grok: 구독 access 토큰 없음');
+    const redacted: Record<string, { key: string; expires_at?: string; user_id?: string }> = {
+      [selected.scopeName]: {
+        key: selected.key,
+        ...(selected.expiresAt ? { expires_at: selected.expiresAt } : {}),
+        ...(selected.userId ? { user_id: selected.userId } : {}),
+      },
+    };
     return { grokAuth: JSON.stringify(redacted), ghToken: (opts.ghToken ?? defaultGhToken)() };
   }
   if (credential?.kind === 'api_key' && opts.apiKeyOptIn === true) {
@@ -804,6 +809,48 @@ export function podGithubWatchdogScript(staleSeconds: number, intervalSeconds =
   ].join('\n');
 }
 
+export function podSalvageBundleScript(): string {
+  return `if [ "\${rc:-0}" -ne 0 ] && grep -Eq 'draft PR 생성 실패|PR (gh|guard) 실패|same-cell reuse:' "\${ELANOUS_POD_CHILD_OUTPUT:-/tmp/si.out}"; then
+  mkdir -p "$HOME/outbox/pod-salvage"
+  found_commits=0
+  preservation_failed=0
+  bundle_bytes=0
+  worktree_rows=$(git worktree list --porcelain) || preservation_failed=1
+  while IFS= read -r wt; do
+    [ -n "$wt" ] || continue
+    git -C "$wt" rev-parse --is-inside-work-tree >/dev/null 2>&1 || { preservation_failed=1; continue; }
+    wt_name=$(basename -- "$wt")
+    case "$wt_name" in ''|.*|*/*|*'..'*) preservation_failed=1; continue ;; esac
+    base=$(git -C "$wt" rev-parse --verify '@{u}' 2>/dev/null || git -C "$wt" rev-parse --verify origin/HEAD 2>/dev/null || git -C "$wt" rev-list --max-parents=0 HEAD | tail -n 1)
+    head=$(git -C "$wt" rev-parse HEAD) || { preservation_failed=1; continue; }
+    [ -n "$base" ] || { preservation_failed=1; continue; }
+    commitCount=$(git -C "$wt" rev-list --count "$base..$head") || { preservation_failed=1; continue; }
+    if [ "$commitCount" -eq 0 ]; then continue; fi
+    found_commits=1
+    diffStats=$(git -C "$wt" diff --numstat "$base..$head") || { preservation_failed=1; continue; }
+    diffLines=$(printf '%s\\n' "$diffStats" | awk '{added += $1; removed += $2} END {print added + removed}')
+    bundle="$HOME/outbox/pod-salvage/$wt_name.bundle"
+    branch=$(git -C "$wt" symbolic-ref --quiet --short HEAD) || { preservation_failed=1; continue; }
+    if git -C "$wt" bundle create "$bundle" "refs/heads/$branch" && [ -s "$bundle" ]; then
+      size=$(( $(wc -c < "$bundle") ))
+      if [ "$size" -gt ${POD_SALVAGE_BUNDLE_FILE_LIMIT} ] || [ $((bundle_bytes + size)) -gt ${POD_SALVAGE_BUNDLE_TOTAL_LIMIT} ]; then
+        preservation_failed=1
+        rm -f -- "$bundle"
+        printf 'ELANOUS_POD_SALVAGE_FAILED size-limit %s %s %s\\n' "$wt_name" "$size" "$head"
+      else
+        bundle_bytes=$((bundle_bytes + size))
+        printf 'ELANOUS_POD_SALVAGE_BUNDLE pod-salvage/%s.bundle %s %s %s\\n' "$wt_name" "$commitCount" "$diffLines" "$head"
+      fi
+    else
+      preservation_failed=1
+      printf 'ELANOUS_POD_SALVAGE_FAILED bundle-create %s\\n' "$wt_name"
+    fi
+  done < <(printf '%s\\n' "$worktree_rows" | awk '/^worktree / {sub(/^worktree /, ""); print}')
+  if [ "$preservation_failed" -ne 0 ]; then printf 'ELANOUS_POD_SALVAGE_FAILED incomplete\\n'
+  elif [ "$found_commits" -eq 0 ]; then printf 'ELANOUS_POD_SALVAGE_NONE no-commits\\n'; fi
+fi`;
+}
+
 export function podSalvageScript(): string {
   return [
     'if [ "${rc:-0}" -ne 0 ]; then',
@@ -1146,6 +1193,29 @@ export function podSigtermTrapScript(seqFile: string = POD_USAGE_PARTIAL_SEQ_FIL
   return `trap '{ [ -n "$si_pid" ] && kill "$si_pid" 2>/dev/null || true; [ -n "\${usage_partial_pid:-}" ] && kill "$usage_partial_pid" 2>/dev/null || true; si_seq=$(cat ${seqFile} 2>/dev/null || true); case "$si_seq" in ""|*[!0-9]*) si_seq=0;; esac; si_seq=$((10#$si_seq + 1)); { [ -f scripts/usage-rollup.ts ] && bun scripts/usage-rollup.ts --since 12h --partial --seq "$si_seq"; } & si_rollup_pid=$!; for si_i in 1 2 3 4 5 6 7 8; do kill -0 "$si_rollup_pid" 2>/dev/null || break; sleep 1; done; kill "$si_rollup_pid" 2>/dev/null || true; wait "$si_rollup_pid" 2>/dev/null || true; exit 143; }' TERM`;
 }
 
+/** Leave enough time for the Pod wrapper to print its result and push a salvage branch before Kubernetes kills the Job. */
+export function podDeadlineWatchdogScript(input: { deadlineSeconds: number; job: string; runId?: string; prNumber?: number }): string {
+  const leadSeconds = Math.max(1, Math.min(600, Math.floor(input.deadlineSeconds / 10)));
+  const waitSeconds = Math.max(1, input.deadlineSeconds - leadSeconds);
+  const job = /^[A-Za-z0-9_.:-]+$/.test(input.job) ? input.job : 'unknown-job';
+  const runId = input.runId && /^[A-Za-z0-9_.:-]+$/.test(input.runId) ? input.runId : 'unknown-run';
+  const pr = input.prNumber && Number.isSafeInteger(input.prNumber) && input.prNumber > 0 ? String(input.prNumber) : 'unknown';
+  const jsonPr = pr === 'unknown' ? 'null' : pr;
+  return `printf 'clone\\n' > /tmp/si.stage
+(sleep ${waitSeconds}; [ -f /tmp/si.finished ] && exit 0
+  stage=$(cat /tmp/si.stage 2>/dev/null || true); case "$stage" in clone|setup|run) ;; *) stage=unknown;; esac
+  branch=$(git -C repo branch --show-current 2>/dev/null || true); case "$branch" in ''|*[!A-Za-z0-9_./-]*) branch=unknown;; esac
+  [ -f /tmp/si.finished ] && exit 0
+  si_target=$(cat /tmp/si.pid 2>/dev/null || true)
+  case "$si_target" in ''|*[!0-9]*) ;; *) kill -0 "$si_target" 2>/dev/null || exit 0;; esac
+  printf 'ELANOUS_POD_DEADLINE_RESULT ${job} ${runId} stop-cause=deadline stage=%s pr=${pr} branch=%s\\n' "$stage" "$branch" | tee /tmp/si.deadline-marker
+  printf '{"stage":"deadline","ok":false,"error":"Pod deadline preemption","stopCause":"deadline","prNumber":${jsonPr},"branch":"%s"}\\n' "$branch" > /tmp/si.deadline-result
+  case "$si_target" in ''|*[!0-9]*) ;; *) kill -TERM "$si_target" 2>/dev/null || true;; esac
+) & si_deadline_watch_pid=$!`;
+}
+
+export const POD_DEADLINE_AFTER_WAIT = `if [ "$rc" -ne 0 ] && [ -f /tmp/si.deadline-result ]; then printf '\\n' >> /tmp/si.out; cat /tmp/si.deadline-result >> /tmp/si.out; rc=124; fi`;
+
 export function podJobManifest(o: { name: string; namespace: string; image: string; workIdentity?: PodWorkIdentity; boundPrNumber?: number; /** 레지스트리 이미지면 IfNotPresent(노드가 pull) · 반입 이미지면 Never. */ imagePullPolicy?: 'Never' | 'IfNotPresent'; repoUrl: string; source?: PodSource; repairCommitOnly?: { pr: number; baseHead: string }; hostMirror?: string; args: readonly string[]; passEnv: readonly string[]; deadlineSeconds: number; runId?: string; parentRunId?: string; armEnv?: Readonly<Record<string, string>>; hostId?: string; imageCommit?: string | null; skillEnvs?: readonly string[]; memoryLimit?: string; memoryRequest?: string; goalDoc?: string; /** AUTHOR-POD2 — run `harness say` on /creds/feature inside the Pod (authoring happens off the host). */ authorSentence?: boolean; authorGrade?: 'full' | 'lite'; grokCredential?: 'subscription' | 'api_key'; codexAccounts?: readonly string[]; appCredential?: boolean; /** Test seam — default POD_GH_STALE_SECONDS. */ githubStaleSeconds?: number; /** Which goal execution and attempt this Job is — a resumed host verifies it before following the Job (POD9). */ execution?: { key: string; attempt: number }; hostLeaseAdmitted?: boolean; /** POD-ROLE-LLM — OpenRouter 자식 Pod 에 리뷰어용 codex 자격을 깐다. */ reviewerCodexAuth?: boolean; /** BEDROCK-PROVIDER ② — bedrock 자식만: 이름 있는 AWS Secret 의 키(secretKeyRef) ⊕ 리전 ⊕ 이그레스 라벨. */ bedrock?: BedrockPodSpec; /** ZAI-POD-CHILD — glm(ZAI) 자식만: 이름 있는 ZAI Secret 의 키(secretKeyRef) ⊕ 이그레스·동시 상한 라벨(Pod ⊕ Job). */ zai?: ZaiPodSpec; /** Codex Job may use the same named Secret only for an explicitly admitted ZAI fallback. */ zaiFallback?: ZaiPodSpec; fallbackChain?: { steps: readonly FallbackStep[]; source: 'host' | 'default' }; /** TA-POD-WARMBOOT-PARITY — the child's final line (podResultMarkerShellLine), just before `exit $rc`. */ resultMarkerLine?: string; /** POD-LAUNCH-PROVENANCE — the shared provenance set (labels ⊕ annotations ⊕ child env) for this si-task Job. */ provenance?: PodProvenanceMetadata }): Record<string, unknown> {
   if (o.repairCommitOnly && (o.source?.kind !== 'pr' || o.source.number !== o.repairCommitOnly.pr || !/^[0-9a-f]{40}$/.test(o.repairCommitOnly.baseHead) || o.args.includes('--open-pr') || o.args.includes('--merge-by-host') || o.args.includes('--auto-merge'))) {
     throw new Error('repair commit-only requires matching PR source and no PR/merge flags');
@@ -1206,9 +1276,11 @@ export function podJobManifest(o: { name: string; namespace: string; image: stri
     // SI-POD-STAGE-MARKERS — Pod 시계 단계 표지(`ELANOUS_POD_STAGE <stage> <start|end> <epoch초>`): 호스트가 Job 로그에서 읽어
     //   pod.lifecycle stages 의 clone · mirror · run 을 채운다. 실패한 단계는 끝 표지가 없다(→ missing · 지어내지 않는다).
     //   clone 끝 = podSourceScript 전체가 끝난 뒤(갈래마다 마지막 줄이 `ELANOUS_POD_SOURCE` 또는 `cd repo` — 둘 다 소스 받기의 일부).
+    podDeadlineWatchdogScript({ deadlineSeconds: o.deadlineSeconds, job: o.name, runId: o.runId, prNumber: o.boundPrNumber }),
     siTaskPodStageShell('clone', 'start'),
     podSourceScript(o.source ?? { kind: 'default' }, o.repoUrl, undefined, { stageMarkers: true }),
     siTaskPodStageShell('clone', 'end'),
+    `printf 'setup\\n' > /tmp/si.stage`,
     // This image already contains runtime dependencies; there is no child install command.
     // Record that fact before the main command, without treating clone completion as install completion.
     `printf 'ELANOUS_POD_DEPS skipped %s image-prepared-no-install\\n' "$(date +%s)" || true`,
@@ -1232,15 +1304,19 @@ export function podJobManifest(o: { name: string; namespace: string; image: stri
     // 마지막 줄 JSON 이 «맨 끝»이어야 한다(parseSelfImplementJson) — rollup 은 그 앞에.
     // ⛔ `--author-grade` 는 Pod 안 `elanous`(이미지에 깔린 판)가 모를 수 있어 넘기지 않는다 — 10-06 «unknown option» 즉사(#24445 되돌림).
     // AUTHOR-LITE2-POD — 등급은 환경변수 `ELANOUS_AUTHOR_GRADE` 로 싣는다(옛 Pod elanous 는 모르는 환경변수를 무시하고 full 로 돈다).
+    `printf 'run\\n' > /tmp/si.stage`,
     siTaskPodStageShell('run', 'start'),
     o.repairCommitOnly
-      ? `export ${OLD_DOOR_STAMP_ENV}=self-implement; elanous self implement "$(cat /creds/feature)" --json --no-open-pr ${quoted} > /tmp/si.out 2>&1 & si_pid=$!; wait "$si_pid"; rc=$?; ${RUN_END}; if elanous self repair-commit-export '${o.repairCommitOnly.pr}' '${o.repairCommitOnly.baseHead}' /tmp/si.out "$PWD" "$HOME/outbox"; then rc=0; elif [ "$rc" -eq 0 ]; then rc=8; fi`
+      ? `export ${OLD_DOOR_STAMP_ENV}=self-implement; elanous self implement "$(cat /creds/feature)" --json --no-open-pr ${quoted} > /tmp/si.out 2>&1 & si_pid=$!; printf '%s\\n' "$si_pid" > /tmp/si.pid; wait "$si_pid"; rc=$?; touch /tmp/si.finished; ${RUN_END}; rm -f /tmp/si.pid; if elanous self repair-commit-export '${o.repairCommitOnly.pr}' '${o.repairCommitOnly.baseHead}' /tmp/si.out "$PWD" "$HOME/outbox"; then rc=0; elif [ "$rc" -eq 0 ]; then rc=8; fi; ${POD_DEADLINE_AFTER_WAIT}`
       : o.authorSentence
-      ? `echo "ELANOUS_AUTHOR_ON_POD started host=$(hostname) at=$(date -u +%Y-%m-%dT%H:%M:%SZ)"; author_t0=$(date +%s); ${o.authorGrade === 'lite' || o.authorGrade === 'full' ? `ELANOUS_AUTHOR_GRADE=${o.authorGrade} ` : ''}elanous harness say --substrate local --json${quotedAsk}${quotedChildLlm} -- "$(cat /creds/feature)" > /tmp/si.out 2>&1 & si_pid=$!; wait "$si_pid"; rc=$?; ${RUN_END}; echo "ELANOUS_AUTHOR_ON_POD finished host=$(hostname) rc=$rc seconds=$(( $(date +%s) - author_t0 ))"; ${POD_RESULT_FLATTEN}`
+      ? `echo "ELANOUS_AUTHOR_ON_POD started host=$(hostname) at=$(date -u +%Y-%m-%dT%H:%M:%SZ)"; author_t0=$(date +%s); ${o.authorGrade === 'lite' || o.authorGrade === 'full' ? `ELANOUS_AUTHOR_GRADE=${o.authorGrade} ` : ''}elanous harness say --substrate local --json${quotedAsk}${quotedChildLlm} -- "$(cat /creds/feature)" > /tmp/si.out 2>&1 & si_pid=$!; printf '%s\\n' "$si_pid" > /tmp/si.pid; wait "$si_pid"; rc=$?; touch /tmp/si.finished; ${RUN_END}; rm -f /tmp/si.pid; ${POD_DEADLINE_AFTER_WAIT}; echo "ELANOUS_AUTHOR_ON_POD finished host=$(hostname) rc=$rc seconds=$(( $(date +%s) - author_t0 ))"; ${POD_RESULT_FLATTEN}`
       : goalPath
-      ? `elanous harness ask ${goalPath} --json${quotedAsk}${quotedChildLlm} > /tmp/si.out 2>&1 & si_pid=$!; wait "$si_pid"; rc=$?; ${RUN_END}; ${POD_RESULT_FLATTEN}`
-      : `export ${OLD_DOOR_STAMP_ENV}=self-implement; elanous self implement "$(cat /creds/feature)" --json ${quoted} > /tmp/si.out 2>&1 & si_pid=$!; wait "$si_pid"; rc=$?; ${RUN_END}; ${POD_RESULT_FLATTEN}`,
+      ? `elanous harness ask ${goalPath} --json${quotedAsk}${quotedChildLlm} > /tmp/si.out 2>&1 & si_pid=$!; printf '%s\\n' "$si_pid" > /tmp/si.pid; wait "$si_pid"; rc=$?; touch /tmp/si.finished; ${RUN_END}; rm -f /tmp/si.pid; ${POD_DEADLINE_AFTER_WAIT}; ${POD_RESULT_FLATTEN}`
+      : `export ${OLD_DOOR_STAMP_ENV}=self-implement; elanous self implement "$(cat /creds/feature)" --json ${quoted} > /tmp/si.out 2>&1 & si_pid=$!; printf '%s\\n' "$si_pid" > /tmp/si.pid; wait "$si_pid"; rc=$?; touch /tmp/si.finished; ${RUN_END}; rm -f /tmp/si.pid; ${POD_DEADLINE_AFTER_WAIT}; ${POD_RESULT_FLATTEN}`,
     'cat /tmp/si.out',
+    ...(o.appCredential && !o.repairCommitOnly ? ['kill "$gh_watch_pid" 2>/dev/null || true'] : []),
+    ...(o.repairCommitOnly ? [] : [podSalvageScript()]),
+    podSalvageBundleScript(),
     '[ -f scripts/usage-rollup.ts ] && bun scripts/usage-rollup.ts --since 12h || echo "ELANOUS_USAGE_ROLLUP {\"measured\":false,\"reason\":\"no rollup script\"}"',
     // A long run's log export can pass the 5MB artifact limit; skipping it whole left no window into why a
     // 2h+ child failed (🅢 09-27). Keep the newest lines under the limit instead, and say so.
@@ -1257,23 +1333,27 @@ else
 fi`,
     `set -o pipefail
 artifact_bytes=0
+salvage_bundle_bytes=0
 if [ -d "$HOME/outbox" ]; then
   while IFS= read -r -d '' file; do
     [ -f "$file" ] && [ ! -L "$file" ] || continue
     relative=\${file#"$HOME/outbox/"}
     size=$(( $(wc -c < "$file") ))
-    if [ "$size" -gt 5242880 ] || [ $((artifact_bytes + size)) -gt 20971520 ]; then
+    salvage_bundle=0
+    case "$relative" in pod-salvage/*.bundle) salvage_bundle=1 ;; esac
+    if { [ "$salvage_bundle" -eq 0 ] && { [ "$size" -gt 5242880 ] || [ $((artifact_bytes + size)) -gt 20971520 ]; }; } || { [ "$salvage_bundle" -eq 1 ] && { [ "$size" -gt ${POD_SALVAGE_BUNDLE_FILE_LIMIT} ] || [ $((salvage_bundle_bytes + size)) -gt ${POD_SALVAGE_BUNDLE_TOTAL_LIMIT} ]; }; }; then
       printf 'ELANOUS_POD_ARTIFACT_SKIPPED %s %s\\n' "$relative" "$size"
       continue
     fi
     path_token=$(printf '%s' "$relative" | base64 | tr -d '\\n' | tr '+/' '-_' | tr -d '=')
     if encoded=$(gzip -c "$file" | base64 | tr -d '\\n'); then
-      artifact_bytes=$((artifact_bytes + size))
+      if [ "$salvage_bundle" -eq 1 ]; then salvage_bundle_bytes=$((salvage_bundle_bytes + size)); else artifact_bytes=$((artifact_bytes + size)); fi
       total=$(( (\${#encoded} + 7999) / 8000 ))
-      for ((n=1; n<=total; n++)); do
-        chunk=\${encoded:$(( (n-1)*8000 )):8000}
+      n=1
+      while IFS= read -r chunk || [ -n "$chunk" ]; do
         printf 'ELANOUS_POD_ARTIFACT %s %s/%s %s\\n' "$path_token" "$n" "$total" "$chunk"
-      done
+        n=$((n + 1))
+      done < <(printf '%s' "$encoded" | fold -w 8000)
     else
       printf 'ELANOUS_POD_ARTIFACT_SKIPPED %s %s\\n' "$relative" "$size"
     fi
@@ -1296,12 +1376,12 @@ for ledger in "\${ELANOUS_STATE_DIR:-$HOME/.elanous}"/run-ledger/*.jsonl; do
 done
 if [ "$found" -eq 0 ]; then echo ELANOUS_RUN_LEDGER_NONE; fi`,
     'kill "$mem_sampler_pid" 2>/dev/null || true',
-    ...(o.appCredential && !o.repairCommitOnly ? ['kill "$gh_watch_pid" 2>/dev/null || true'] : []),
     '[ -n "${usage_partial_pid:-}" ] && kill "$usage_partial_pid" 2>/dev/null || true',
     'wait "$mem_sampler_pid" 2>/dev/null || true',
     '[ -n "${usage_partial_pid:-}" ] && wait "$usage_partial_pid" 2>/dev/null || true',
+    'if [ "$rc" -ne 0 ] && [ -f /tmp/si.deadline-result ]; then rc=124; fi',
     'tail -n 1 /tmp/si.out',
-    ...(o.repairCommitOnly ? [] : [podSalvageScript()]),
+    'touch /tmp/si.finished; kill "$si_deadline_watch_pid" 2>/dev/null || true; [ -f /tmp/si.deadline-marker ] && cat /tmp/si.deadline-marker || true',
     // TA-POD-WARMBOOT-PARITY: the last line says «the child is done» so the host need not wait for the Job condition.
     ...(o.resultMarkerLine ? [o.resultMarkerLine] : []),
     'exit $rc',
@@ -1337,6 +1417,9 @@ if [ "$found" -eq 0 ]; then echo ELANOUS_RUN_LEDGER_NONE; fi`,
                 ? [{ name: 'ELANOUS_TASK_BOUND_PR', value: String(o.boundPrNumber) }] : []),
               ...(o.workIdentity?.slotId ? [{ name: 'ELANOUS_POD_SLOT_ID', value: o.workIdentity.slotId }] : []),
               { name: 'ELANOUS_SUBSTRATE', value: 'pod' },
+              // POD-INPLACE-WORKTREE: explicit host opt-in only; one Job runs one implementation child.
+              { name: 'ELANOUS_POD_SINGLE_CHILD', value: '1' },
+              { name: 'ELANOUS_POD_INPLACE_WORKTREE', value: process.env.ELANOUS_POD_INPLACE_WORKTREE === '1' ? '1' : '0' },
               ...Object.entries(controlInboxEnv(POD_CONTROL_INBOX_DIR)).map(([name, value]) => ({ name, value })),
               // ⭐ 런 출처(🅣 RFC run-origin §A3 · #20457/#20468 칸 이름) — Pod 는 자기 elanous_id 를 쓰지 않고 «띄운 감독기»의 hostId 를 물려받는다.
               { name: 'ELANOUS_POD_NAME', valueFrom: { fieldRef: { fieldPath: 'metadata.name' } } },
@@ -1897,13 +1980,16 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
       const acquireSlot = async (): Promise<PodPoolMember | null> => {
         if (!options.pool) return null;
         const stop = watchStall('pool-slot');
+        // MINIH-MODE (0.2.37): the location is declared by the launch env — absent/unknown keeps the configured
+        // capacities, so this launch path behaves exactly as before unless the declaration is there.
+        const minihLocation = minihLocationFrom(env.ELANOUS_MINIH_LOCATION);
         try {
           for (;;) {
             if (input.signal?.aborted) return null;
             // The reason comes back inside this call, so a concurrent launch cannot overwrite it.
             const kind = podPlacementKind(oomRetried ? retryTier : memoryTier, selectedGoalType, requestKind);
             const acquired = await options.pool.tryAcquire(unfitContexts, (reason) => { stageReason['pool-slot'] = reason; },
-              { kind, onPlacement: (placement) => { lastPlacement = placement; } });
+              { kind, ...(minihLocation ? { minihLocation } : {}), onPlacement: (placement) => { lastPlacement = placement; } });
             if (acquired) {
               debug.log('self-implement.pod', 'pool-slot', { spaceId: input.spaceId, context: acquired.context, inflight: options.pool.snapshot(), ...(lastPlacement ? { placement: lastPlacement } : {}) });
               if (lastPlacement) console.warn(`[pod] 배치: ${lastPlacement.reason}`);
@@ -1954,6 +2040,21 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
       const currentContext = member ? null : baseKubectl(['config', 'current-context']);
       let context = member?.context ?? (currentContext?.status === 0 ? currentContext.stdout.trim() : '');
       const kubectl: Kubectl = (args, stdin) => baseKubectl(['--context', context, ...args], stdin);
+      const captureKubectl = (host: string, args: readonly string[]): ReturnType<Kubectl> => {
+        if (member?.sshHost ? member.sshHost !== host : host !== resolveHostId(env))
+          return { status: 1, stdout: '', stderr: 'ledger host is not the selected pool host' };
+        if (!member?.sshHost) return baseKubectl(args);
+        if (options.failureCaptureRemote) return options.failureCaptureRemote(host, args);
+        const result = spawnSync('ssh', ['-o', 'BatchMode=yes', '-o', 'ConnectTimeout=5', '--', host, 'kubectl', ...args],
+          { encoding: 'utf8', timeout: 30_000, maxBuffer: LEASE_KUBECTL_MAX_BUFFER });
+        return { status: result.status, stdout: result.stdout ?? '', stderr: (result.stderr ?? '') + (result.error ? String(result.error) : '') };
+      };
+      const captureFailedJob = (childRunId: string): void => {
+        try {
+          captureFailedPodJobs({ runId: ledgerRunId, job: name, childRunId, ledgerPath: runLedgerPath(ledgerRunId, ledgerDir), artifactDir: join(effectiveInstanceRoot(), 'pod-artifacts'),
+            kubectl: captureKubectl, record: (event, data) => appendRunLedgerEntry({ runId: ledgerRunId, event, data }, ledgerDir), now: options.now });
+        } catch (error) { debug.log('self-implement.pod', 'failure-capture-ledger-unavailable', { job: name, reason: error instanceof Error ? error.message : String(error) }, { level: 'warn' }); }
+      };
       let recorded = false;
       let groundingMinted: string | null = null;
       try {
@@ -1995,6 +2096,44 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
           collectPodArtifacts(full.stdout, { dir: join(effectiveInstanceRoot(), 'pod-artifacts'), job: name, log: record });
         }
         catch (error) { record('self-implement.pod', 'artifact-collect-incomplete', { job: name, reason: error instanceof Error ? error.message : String(error) }); }
+        for (const line of full.stdout.split(/\r?\n/)) {
+          const bundle = /^ELANOUS_POD_SALVAGE_BUNDLE (pod-salvage\/[a-zA-Z0-9._-]+\.bundle) ([0-9]+) ([0-9]+)(?: ([0-9a-f]{40,64}))?$/.exec(line);
+          if (bundle) {
+            const bundlePath = join(effectiveInstanceRoot(), 'pod-artifacts', name, bundle[1]!);
+            if (!existsSync(bundlePath)) {
+              try { appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-salvage-bundle', data: { job: name, disposition: '보존 실패', reason: 'bundle artifact missing' } }, ledgerDir); }
+              catch (error) { record('self-implement.pod', 'salvage-bundle-ledger-incomplete', { job: name, reason: error instanceof Error ? error.message : String(error) }); }
+              record('self-implement.pod', 'salvage-bundle-collect-incomplete', { job: name, path: bundlePath, reason: 'bundle artifact missing' });
+              continue;
+            }
+            try {
+              const refs = execFileSync('git', ['bundle', 'list-heads', bundlePath], { encoding: 'utf8', stdio: ['ignore', 'pipe', 'pipe'] }).trim().split(/\r?\n/);
+              const [bundleHead, bundleRef] = refs[0]?.trim().split(/\s+/) ?? [];
+              if (!bundleHead || !bundleRef?.startsWith('refs/heads/')) throw new Error('bundle contains no branch ref');
+              const verifyDir = mkdtempSync(join(tmpdir(), 'pod-salvage-verify-'));
+              try {
+                execFileSync('git', ['clone', '--quiet', '--branch', bundleRef.slice('refs/heads/'.length), bundlePath, verifyDir], { stdio: ['ignore', 'pipe', 'pipe'] });
+                const cloneHead = execFileSync('git', ['-C', verifyDir, 'rev-parse', 'HEAD'], { encoding: 'utf8', stdio: ['ignore', 'pipe', 'pipe'] }).trim();
+                if (cloneHead !== bundleHead || (bundle[4] && cloneHead !== bundle[4])) throw new Error('bundle clone HEAD mismatch');
+              } finally { rmSync(verifyDir, { recursive: true, force: true }); }
+              appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-salvage-bundle', data: {
+                job: name, path: bundlePath,
+                commitCount: Number(bundle[2]), diffLines: Number(bundle[3]), ...(bundle[4] ? { head: bundle[4] } : {}),
+              } }, ledgerDir);
+            } catch (error) {
+              const reason = error instanceof Error ? error.message : String(error);
+              try { appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-salvage-bundle', data: { job: name, disposition: '보존 실패', reason: `bundle validation failed: ${reason}` } }, ledgerDir); }
+              catch (ledgerError) { record('self-implement.pod', 'salvage-bundle-ledger-incomplete', { job: name, reason: ledgerError instanceof Error ? ledgerError.message : String(ledgerError) }); }
+              record('self-implement.pod', 'salvage-bundle-collect-incomplete', { job: name, reason });
+            }
+          } else if (line === 'ELANOUS_POD_SALVAGE_NONE no-commits') {
+            try { appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-salvage-bundle', data: { job: name, disposition: '보존할 것 없음', commitCount: 0, diffLines: 0 } }, ledgerDir); }
+            catch (error) { record('self-implement.pod', 'salvage-bundle-ledger-incomplete', { job: name, reason: error instanceof Error ? error.message : String(error) }); }
+          } else if (line.startsWith('ELANOUS_POD_SALVAGE_FAILED ')) {
+            try { appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-salvage-bundle', data: { job: name, disposition: '보존 실패', reason: line.slice('ELANOUS_POD_SALVAGE_FAILED '.length) } }, ledgerDir); }
+            catch (error) { record('self-implement.pod', 'salvage-bundle-ledger-incomplete', { job: name, reason: error instanceof Error ? error.message : String(error) }); }
+          }
+        }
         if (options.repairCommitOnly) {
           const artifactDir = join(effectiveInstanceRoot(), 'pod-artifacts', name, 'repair');
           try {
@@ -2022,9 +2161,11 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         //   상한 안 → ZAI(이름 있는 Secret · 없으면 거부) · 넘침 → 정책대로(openrouter·balance = 기존 OpenRouter GLM · stop = 거부 · apply 0).
         let zaiRoute: 'zai' | 'openrouter' | undefined;
         let zaiSpec: ZaiPodSpec | undefined;
+        let zaiLaunchOverage: 'stop' | 'balance' | 'openrouter' | undefined;
         zaiPendingApply.delete(name);
         if (options.provider === 'glm') {
           const settings = (options.zaiSettings ?? (() => zaiSettingsFromConfig(getUserConfig().llm)))();
+          zaiLaunchOverage = settings.overage;
           const poolMembers = (options.pool as { members?: readonly PodPoolMember[] } | undefined)?.members;
           const contexts = Array.isArray(poolMembers) && poolMembers.length > 0 ? poolMembers.map((m) => m.context) : [context];
           let active: number | null = 0;
@@ -2056,6 +2197,8 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         const anthropic = options.provider === 'anthropic';
         const bedrockChild = options.provider === 'bedrock';
         const zaiChild = zaiRoute === 'zai';
+        /** ZAI 로 입장한 자식도 플랜 한도 오류 뒤 OpenRouter 로 전환할 수 있다. 실행 중 폴백 자격을 발사 전에 확보한다. */
+        const openrouterCredentialRequired = openrouter || (zaiChild && zaiLaunchOverage !== 'stop');
         /** API 키 자식 — codex 계정·자격 파일을 안 쓴다(키는 작업별 creds Secret 의 `env-<KEY>` · bedrock·glm 은 이름 있는 Secret 으로만). */
         const apiKeyChild = openrouter || openGateway || anthropic || bedrockChild || zaiChild;
         const plannedAccount = retryAccount ?? (grok ? 'grok' : openrouter ? 'openrouter' : openGateway ? 'opengateway' : anthropic ? 'anthropic' : bedrockChild ? 'bedrock' : zaiChild ? 'glm' : options.accountBroker?.() ?? options.account ?? 'team');
@@ -2099,8 +2242,8 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
           }
           return credential;
         }) : undefined;
-        const openrouterKey = openrouter ? env.OPENROUTER_API_KEY?.trim() || (options.readKeyCache ?? defaultReadKeyCache)('OPENROUTER_API_KEY')?.trim() : undefined;
-        if (openrouter && !openrouterKey) throw new Error('pod: Pod 에 openrouter 키 없음 — 호스트 키 캐시 또는 OPENROUTER_API_KEY 필요');
+        const openrouterKey = openrouterCredentialRequired ? env.OPENROUTER_API_KEY?.trim() || (options.readKeyCache ?? defaultReadKeyCache)('OPENROUTER_API_KEY')?.trim() : undefined;
+        if (openrouterCredentialRequired && !openrouterKey) throw new Error('pod: Pod 에 openrouter 키 없음 — 호스트 키 캐시 또는 OPENROUTER_API_KEY 필요');
         const openGatewayEnvKey = openGateway ? env.OPENGATEWAY_API_KEY?.trim() : undefined;
         const openGatewayCachedKey = openGateway ? (options.readKeyCache ?? defaultReadKeyCache)('OPENGATEWAY_API_KEY')?.trim() : undefined;
         if (openGatewayEnvKey && openGatewayCachedKey && openGatewayEnvKey !== openGatewayCachedKey)
@@ -2182,7 +2325,7 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
           }
         }
         // Grok 자격은 전용 Secret 키 하나로만 보낸다 — passEnv 의 API 키 중복 전달은 막는다.
-        const passKeys = [...new Set([...(options.passEnv ?? []), ...(openrouter ? ['OPENROUTER_API_KEY'] : []), ...(openGateway ? ['OPENGATEWAY_API_KEY'] : []), ...(anthropic ? ['ANTHROPIC_API_KEY'] : [])])].filter((key) => key !== 'ELANOUS_LIVE_DETAIL_UNTIL'
+        const passKeys = [...new Set([...(options.passEnv ?? []), ...(openrouterCredentialRequired ? ['OPENROUTER_API_KEY'] : []), ...(openGateway ? ['OPENGATEWAY_API_KEY'] : []), ...(anthropic ? ['ANTHROPIC_API_KEY'] : [])])].filter((key) => key !== 'ELANOUS_LIVE_DETAIL_UNTIL'
           && key !== POD_GITHUB_CREDENTIAL_TOKEN_ENV && key !== POD_GITHUB_CREDENTIAL_URL_ENV
           && (!grok || !['XAI_API_KEY', 'GROK_API_KEY', 'GROK_CODE_XAI_API_KEY'].includes(key)));
         const skillEnvs: Record<string, string> = options.skillEnv
@@ -2307,6 +2450,13 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
           if (key.startsWith('ELANOUS_PROMPT_ENHANCE_') && key !== 'ELANOUS_PROMPT_ENHANCE_MODEL' && key !== 'ELANOUS_PROMPT_ENHANCE_EFFORT') delete hostAuthorEnv[key];
         }
         let authorChoice = authorOnPod ? selectEnhanceLlm({ config: (options.authorConfig ?? getUserConfig)() }, hostAuthorEnv) : undefined;
+        // A named child model is this launch's model when planning has no explicit choice.
+        // Relay it to authoring too: the Pod's persistent grounding goal loop otherwise
+        // receives the host's default "better" model and silently spends sol for a luna child.
+        const namedChildModel = podDelegatedChildLlm(jobArgs)?.model;
+        if (authorChoice?.modelSource === 'default' && namedChildModel) {
+          authorChoice = { ...authorChoice, model: namedChildModel, modelSource: 'child' };
+        }
         let authorFallbackReason: string | undefined;
         let authorRequestedModel: string | undefined;
         let authorRequestedSource: string | undefined;
@@ -2328,8 +2478,10 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
             authorChoice = { ...authorChoice, model: childModel, modelSource: 'fallback-child' };
           } else debug.log('self-implement.pod', 'role-llm-armed', { job: name, role: 'planning', model: authorChoice.model, source: authorChoice.modelSource, account: roleCodexAccount });
         }
-        const hostKey = (k: string): string | undefined => k === 'OPENROUTER_API_KEY' && openrouter ? openrouterKey : k === 'OPENGATEWAY_API_KEY' && openGateway ? openGatewayKey : k === 'ANTHROPIC_API_KEY' && anthropic ? anthropicKey : env[k] ?? (options.readKeyCache ?? defaultReadKeyCache)(k);
-        const hostFallbackNames = (options.fallbackConfig ?? getUserConfig)().llm.fallbackChain;
+        const hostKey = (k: string): string | undefined => k === 'OPENROUTER_API_KEY' && openrouterCredentialRequired ? openrouterKey : k === 'OPENGATEWAY_API_KEY' && openGateway ? openGatewayKey : k === 'ANTHROPIC_API_KEY' && anthropic ? anthropicKey : env[k] ?? (options.readKeyCache ?? defaultReadKeyCache)(k);
+        const hostConfig = (options.fallbackConfig ?? getUserConfig)();
+        const hostFallbackNames = hostConfig.llm.fallbackChain;
+        const zaiOverage = zaiLaunchOverage ?? zaiSettingsFromConfig(hostConfig.llm).overage;
         const normalizedFallback = normalizeFallbackChain(hostFallbackNames);
         let fallbackSteps = normalizedFallback.chain;
         let zaiFallbackSpec: ZaiPodSpec | undefined;
@@ -2381,7 +2533,7 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
                 ? Object.fromEntries(codexCredentials.map((candidate, i) => [`codex-${i}.json`, JSON.stringify({ elanousAuth: candidate.elanousAuth, codexAuth: candidate.codexAuth })]))
                 : { 'elanous-auth.json': (creds as ReturnType<typeof hostCredentials>).elanousAuth, 'codex-auth.json': (creds as ReturnType<typeof hostCredentials>).codexAuth }),
             'gh-token': podGhToken, feature: input.feature,
-            'llm-fallback-config.json': JSON.stringify({ llm: { fallbackChain: fallbackChain.steps } }),
+            'llm-fallback-config.json': JSON.stringify({ llm: { fallbackChain: fallbackChain.steps, zaiCodingPlan: { overage: zaiOverage } }, harness: { worktreeAddTimeoutSec: worktreeAddTimeoutSec(hostConfig.harness?.worktreeAddTimeoutSec) ?? 1200 } }),
             ...(goalDocument !== undefined ? { 'goal-doc': goalDocument } : {}),
             ...Object.fromEntries(Object.entries(skillEnvs).map(([n, text]) => [`skillenv-${n}`, text])),
             ...(grounding ? { [`env-${GROUNDING_TOKEN_ENV}`]: grounding.token } : {}),
@@ -2448,6 +2600,7 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
           }
         }
         if (failedExisting) {
+          captureFailedJob(liveChildRunId);
           const pods = kubectl(['-n', namespace, 'get', 'pods', '-l', `job-name=${name}`, '-o', 'jsonpath={range .items[*]}{.metadata.creationTimestamp}{"\\t"}{range .status.containerStatuses[?(@.name=="child")]}{.state.terminated.reason}{"\\t"}{.state.terminated.exitCode}{end}{"\\n"}{end}']);
           const latestPod = pods.status === 0 ? pods.stdout.trimEnd().split('\n').map((line) => line.split('\t'))
             .filter(([created]) => created && !Number.isNaN(Date.parse(created)))
@@ -2723,6 +2876,7 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         }
         try {
           appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-child-run', data: { childRunId: liveChildRunId, job: name, attempt: oomRetried ? 2 : 1, ...(goalFile ? { goalFile } : {}) } }, ledgerDir);
+          appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-job-applied', data: { job: name, childRunId: liveChildRunId, jobUid: lifecycleJobUid, host: member?.sshHost ?? resolveHostId(env), context, namespace } }, ledgerDir);
           if (lastPlacement) appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-placement', data: { job: name, childRunId: liveChildRunId, attempt: oomRetried ? 2 : 1, member: lastPlacement.member, kind: lastPlacement.kind, outcome: lastPlacement.outcome, preferred: lastPlacement.preferred, reason: lastPlacement.reason } }, ledgerDir);
           appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-memory-selected', data: { job: name, childRunId: liveChildRunId, attempt: oomRetried ? 2 : 1, limit: memoryLimit, ...(appliedMemoryRequest ? { request: appliedMemoryRequest } : {}), tier: oomRetried ? retryTier : memoryTier, source: oomRetried ? 'oom-retry' : memorySource, reason: oomRetried ? 'OOMKilled' : memoryReason, declaredGoalType: selectedGoalType } }, ledgerDir);
           if (oomRetried && retryFromChildRunId) appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-oom-retry', data: { attempt: 2, from: retryFromMemoryLimit ?? selectedMemoryLimit, to: memoryLimit, tier: retryTier, reason: 'OOMKilled', job: name, childRunId: liveChildRunId, fromChildRunId: retryFromChildRunId } }, ledgerDir);
@@ -2734,7 +2888,7 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         }
         writePodFragment({ spaceId: input.spaceId, context, namespace, job: name, inboxDir: POD_CONTROL_INBOX_DIR, ...(liveChildRunId === normalizeRunId(liveChildRunId) ? { runId: liveChildRunId } : {}), ...(parentRunId && normalizeRunId(parentRunId) === parentRunId ? { parentRunId } : {}) }, env);
         recorded = true;
-        debug.log('self-implement.pod', 'job-applied', { job: name, namespace, ...(member ? { context: member.context } : {}), image: jobImage, spaceId: input.spaceId, passEnv, ...(openrouter ? { openrouterKeyPresent: passEnv.includes('OPENROUTER_API_KEY') } : {}), ...(openGateway ? { openGatewayKeyPresent: passEnv.includes('OPENGATEWAY_API_KEY') } : {}), ...(anthropic ? { anthropicKeyPresent: passEnv.includes('ANTHROPIC_API_KEY') } : {}), ...(bedrockSpec ? { bedrockSecret: bedrockSpec.secretName, bedrockSecretKeys: bedrockSpec.keys, bedrockRegionFrom: bedrockSpec.region.from } : {}), ...(zaiRoute ? { zaiRoute, ...(zaiSpec ? { zaiSecret: zaiSpec.secretName } : {}) } : {}), extraArgs: options.extraArgs ?? [], ...(options.armEnv?.ELANOUS_ARM_ID ? { armId: options.armEnv.ELANOUS_ARM_ID } : {}) });
+        debug.log('self-implement.pod', 'job-applied', { job: name, namespace, ...(member ? { context: member.context } : {}), image: jobImage, spaceId: input.spaceId, passEnv, ...(openrouterCredentialRequired ? { openrouterKeyPresent: passEnv.includes('OPENROUTER_API_KEY') } : {}), ...(openGateway ? { openGatewayKeyPresent: passEnv.includes('OPENGATEWAY_API_KEY') } : {}), ...(anthropic ? { anthropicKeyPresent: passEnv.includes('ANTHROPIC_API_KEY') } : {}), ...(bedrockSpec ? { bedrockSecret: bedrockSpec.secretName, bedrockSecretKeys: bedrockSpec.keys, bedrockRegionFrom: bedrockSpec.region.from } : {}), ...(zaiRoute ? { zaiRoute, ...(zaiSpec ? { zaiSecret: zaiSpec.secretName } : {}) } : {}), extraArgs: options.extraArgs ?? [], ...(options.armEnv?.ELANOUS_ARM_ID ? { armId: options.armEnv.ELANOUS_ARM_ID } : {}) });
         let state: 'complete' | 'failed' | 'aborted' = 'failed';
         let failedReason = '';
         let containerReason: string | null = null;
@@ -2742,10 +2896,33 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         // JOB-FAILURE-TERMINATION-CAPTURE — this Job's Kubernetes facts, read once at the failure verdict (before GC).
         //   Observation only: failedReason · containerReason · containerExitCode keep driving the classification.
         let podTermination: PodTermination | null = null;
+        const refreshPodTermination = async (): Promise<void> => {
+          if (state !== 'failed' || !podTermination || (podTermination.podLookup === 'terminated'
+            && podTermination.containerReason !== 'unknown' && podTermination.exitCode !== 'unknown'
+            && podTermination.finishedAt !== 'unknown')) return;
+          // The result marker and the Job Failed condition can precede container termination status.
+          // Re-read this launch's Pod once; keep the verdict's Job facts even if the Job has since been GC'd.
+          await sleep(1_000);
+          const retry = readPodTermination({ kubectl, namespace, job: name, path: podTermination.path,
+            jobUid: lifecycleJobUid, jobRead: null });
+          const observed = retry.podLookup === 'unavailable' ? podTermination : retry;
+          const complete = observed.podLookup === 'terminated' && observed.containerReason !== 'unknown'
+            && observed.exitCode !== 'unknown' && observed.finishedAt !== 'unknown';
+          const collectionFailureReason: PodTermination['collectionFailureReason'] | undefined = complete ? undefined
+            : retry.podLookup === 'unavailable' ? 'pod-read-unavailable-after-retry'
+            : retry.podLookup === 'absent' ? 'pod-absent-after-retry'
+            : retry.podLookup === 'running' || retry.podLookup === 'pending' ? 'pod-still-running-after-retry'
+            : retry.podLookup === 'terminated' ? 'terminated-fields-missing-after-retry'
+            : 'pod-state-unknown-after-retry';
+          podTermination = { ...podTermination, observedAt: retry.observedAt,
+            podLookup: observed.podLookup, containerReason: observed.containerReason, exitCode: observed.exitCode,
+            finishedAt: observed.finishedAt, oomKilled: observed.oomKilled, collectionAttempts: 2,
+            ...(collectionFailureReason ? { collectionFailureReason } : {}) };
+        };
         // METER-POD-ROLLUP-GAP — abort 때 Job 삭제 «전»에 거둔 로그 사본(삭제 뒤엔 PARTIAL 줄도 못 읽는다).
         let abortLogs = '';
         // ⭐ 런 «도중» 원장 증분 회수 — 호스트 슈퍼바이저가 Pod 걸음을 실시간으로 본다(🅣 요청 · 힐 루프 runtime 성형의 전제).
-        const follower = createPodLedgerFollower({ runId: liveChildRunId, dir: ledgerDir, exec: (script) => kubectl(['-n', namespace, 'exec', `job/${name}`, '-c', 'child', '--', 'sh', '-c', script]) });
+        const follower = createPodLedgerFollower({ runId: liveChildRunId, dir: ledgerDir, now, exec: (script) => kubectl(['-n', namespace, 'exec', `job/${name}`, '-c', 'child', '--', 'sh', '-c', script]) });
         // ⭐ METER-POD-ROLLUP-GAP-3 — 런 «도중» 마지막 PARTIAL 줄을 호스트가 쥔다: Pod 가 지워지면(SIGTERM 등) 종료 로그에서 PARTIAL 이 사라진다.
         let livePartialLine: string | null = null;
         let pollsSinceCapture = 0;
@@ -2774,6 +2951,10 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         const capturePolls = Math.max(1, options.usagePartialCapturePolls ?? Math.round(POD_USAGE_PARTIAL_CAPTURE_MS / Math.max(1, options.pollMs ?? 15_000)));
         const markerWait = markerToken ? await import('./pod-result-marker-wait.js') : null;
         const waitStartedAt = Date.now();
+        let consecutiveJobNotFound = 0;
+        let podVanished = false;
+        let unmeasurableSince: number | null = null;
+        let unmeasurableIncidentRecorded = false;
         for (;;) {
           if (input.signal?.aborted) {
             recordPodImage(true);
@@ -2788,6 +2969,32 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
           }
           if (!imageSnapshotRecorded) recordPodImage(false);
           const g = kubectl(['-n', namespace, 'get', 'job', name, '-o', 'jsonpath={.status.conditions[*].type}']);
+          if (g.status !== 0) {
+            // A transport/5xx error says nothing about Job existence. Only Kubernetes Job NotFound counts.
+            const jobNotFound = /\(NotFound\)/i.test(g.stderr) || /\bjobs?(?:\.batch)?\b[^\n]*\bnot found\b/i.test(g.stderr);
+            consecutiveJobNotFound = jobNotFound ? consecutiveJobNotFound + 1 : 0;
+            unmeasurableSince = null;
+            if (consecutiveJobNotFound >= 3) {
+              state = 'failed';
+              failedReason = 'JobNotFound';
+              podVanished = true;
+              const facts = { job: name, childRunId: liveChildRunId, class: 'pod-vanished', consecutiveNotFound: consecutiveJobNotFound };
+              debug.log('self-implement.pod', 'pod-vanished', facts, { level: 'error' });
+              try {
+                recordRunStop({ runId: ledgerRunId, class: 'pod-vanished', site: 'pod-job-poll',
+                  cause: `Job ${name} NotFound on ${consecutiveJobNotFound} consecutive polls`,
+                  evidenceRef: `run-ledger:${ledgerRunId}:pod-job-applied`,
+                  nextMove: 'Inspect Job deletion and child artifacts before relaunch' },
+                (entry) => appendRunLedgerEntry(entry, ledgerDir));
+              } catch (error) {
+                debug.log('self-implement.pod', 'pod-vanished-ledger-unavailable', { ...facts, reason: error instanceof Error ? error.message : String(error) }, { level: 'warn' });
+              }
+              break;
+            }
+            await sleep(options.pollMs ?? 15_000);
+            continue;
+          }
+          consecutiveJobNotFound = 0;
           const types = g.stdout;
           if (/Complete|SuccessCriteriaMet/.test(types)) { releaseAdmission?.observed?.(); state = 'complete'; break; }
           if (/Failed|FailureTarget/.test(types)) {
@@ -2798,7 +3005,8 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
             let jobReadError: unknown;
             try { jobRead = kubectl(['-n', namespace, 'get', 'job', name, '-o', `jsonpath=${POD_TERMINATION_JOB_JSONPATH}`]); }
             catch (error) { jobReadError = error; }
-            failedReason = jobRead?.status === 0 ? (jobRead.stdout.split('\t')[0] ?? '').trim() : '';
+            const observedJobReason = jobRead?.status === 0 ? podJobConditionReason(jobRead.stdout.split('\t')[0]) : 'unknown';
+            failedReason = observedJobReason === 'unknown' ? '' : observedJobReason;
             // One Pods read serves both: its first three columns are the classification layout, the rest the termination capture.
             let podsRead: { status: number | null; stdout: string } | null = null;
             try {
@@ -2817,8 +3025,11 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
             } catch { /* Pod 가 사라졌거나 조회 불가 — 종료 사유는 미상. */ }
             debug.log('self-implement.pod', 'container-terminated', { job: name, container: 'child', reason: containerReason, exitCode: containerExitCode, jobReason: failedReason || null, memoryLimit });
             podTermination = readPodTermination({ kubectl, namespace, job: name, path: 'job-failed-condition', jobRead, podsRead, jobUid: lifecycleJobUid });
+            // Keep the verdict's single Job read authoritative; collecting files may re-read a Job that GC has removed.
+            captureFailedJob(liveChildRunId);
             if (jobReadError !== undefined) {
               // Today's outcome stays (the throw ends the spawn as pod-error); the capture is in the ledger first.
+              await refreshPodTermination();
               try { appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-child-evidence', data: { childEvidence: null, childRunId: liveChildRunId, job: name, podTermination } }, ledgerDir); }
               catch (error) { debug.log('self-implement.pod', 'child-evidence-write-failed', { job: name, childRunId: liveChildRunId, reason: error instanceof Error ? error.message : String(error) }, { level: 'warn' }); }
               debug.log('self-implement.pod', 'pod-termination-captured', { job: name, podTermination, jobReadThrew: true }, { level: 'warn' });
@@ -2836,6 +3047,7 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
               // The child's own rc (the Pod's terminated state may lag like the condition) — exit-code paths read it as before.
               if (seen !== 0) containerExitCode = seen;
               if (seen !== 0) podTermination = readPodTermination({ kubectl, namespace, job: name, path: 'result-marker', jobUid: lifecycleJobUid });
+              if (seen !== 0) captureFailedJob(liveChildRunId);
               debug.log('self-implement.pod', 'result-marker-early', { job: name, waitedMs: Date.now() - waitStartedAt, rc: seen });
               break;
             }
@@ -2863,7 +3075,19 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
               debug.log('self-implement.pod', 'gh-token-refresh-failed', { job: name, reason: 'mint-verification-or-exec-failed' });
             }
           }
-          try { follower?.poll(); } catch (e) { debug.log('self-implement.pod', 'ledger-live-unavailable', { job: name, reason: e instanceof Error ? e.message : String(e) }); }
+          let measurement = { ledgerRead: false, activityMeasured: false };
+          try { measurement = follower.poll(); } catch (e) { debug.log('self-implement.pod', 'ledger-live-unavailable', { job: name, reason: e instanceof Error ? e.message : String(e) }); }
+          if (!measurement.ledgerRead && !measurement.activityMeasured) {
+            unmeasurableSince ??= now();
+            const unmeasurableMs = Math.max(0, now() - unmeasurableSince);
+            if (!unmeasurableIncidentRecorded && unmeasurableMs >= 120 * 60_000) {
+              unmeasurableIncidentRecorded = true;
+              const incident = { job: name, childRunId: liveChildRunId, unmeasurableMs, jobStatus: 'alive', ledgerRead: false, activityMeasured: false };
+              try { appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-stall-unmeasurable-incident', data: incident }, ledgerDir); }
+              catch (error) { debug.log('self-implement.pod', 'pod-stall-incident-ledger-unavailable', { job: name, reason: error instanceof Error ? error.message : String(error) }, { level: 'warn' }); }
+              debug.log('self-implement.pod', 'pod-stall-unmeasurable-incident', incident, { level: 'warn' });
+            }
+          } else unmeasurableSince = null;
           if (++pollsSinceCapture >= capturePolls) {
             pollsSinceCapture = 0;
             try {
@@ -2878,6 +3102,7 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
           }
           await sleep(options.pollMs ?? 15_000);
         }
+        await refreshPodTermination();
         if (!terminalImageRecorded) recordPodImage(true);
         let logs = '';
         let logTailReason: string | undefined;
@@ -2891,6 +3116,14 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         if (!logs && abortLogs) logs = abortLogs;
         // TA-POD-WARMBOOT-PARITY: the marker line is not child output — remove it so the last-line result parse sees the same bytes.
         if (markerWait && markerToken && logs) logs = markerWait.stripPodResultMarker(logs, markerToken);
+        const deadlineMarker = podDeadlineResultMarker(logs, name, liveChildRunId);
+        if (deadlineMarker && state !== 'aborted' && state !== 'complete') {
+          state = 'failed';
+          failedReason = 'DeadlineExceeded';
+          debug.log('self-implement.pod', 'deadline-result-marker', { job: name, childRunId: liveChildRunId, ...deadlineMarker });
+          try { appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-deadline-result', data: { job: name, childRunId: liveChildRunId, stopCause: 'deadline', ...deadlineMarker } }, ledgerDir); }
+          catch { /* A full ledger must not hide the Pod's terminal marker. */ }
+        }
         let ledgerReason = '';
         let ledgerCollected = false;
         const collection = collectFullLogs('ledger-collect-incomplete', follower.owned ? new Set([liveChildRunId]) : undefined, (event, data) => {
@@ -2950,7 +3183,9 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
           continue;
         }
         // Pod 안 경로는 호스트에서 쓸 수 없다.
-        let disposition = parsed ? { ...parsed, worktreePath: undefined } : undefined;
+        let disposition: SelfImplementDisposition | undefined = parsed ? { ...parsed, worktreePath: undefined } : deadlineMarker
+          ? { stage: 'deadline', ok: false, ...(deadlineMarker.pr ? { prNumber: deadlineMarker.pr } : {}), ...(deadlineMarker.branch ? { branch: deadlineMarker.branch } : {}) }
+          : undefined;
         if (options.repairCommitOnly && state === 'complete' && !repairArtifactReady) {
           disposition = { ...disposition, worktreePath: undefined, ok: false, stage: 'repair-artifact-missing', detail: 'Pod repair result or bundle was not collected' };
         }
@@ -3082,25 +3317,37 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         }
         let noResultDiagnostic: string | null = null;
         // POD-NORESULT: a terminal Job without a parsed disposition is incomplete even when the Job condition says Complete.
-        const noResultCandidate = !disposition && !oomKilled && failedReason !== 'DeadlineExceeded' &&
+        const noResultCandidate = !podVanished && !disposition && !oomKilled && failedReason !== 'DeadlineExceeded' &&
           (state === 'complete' || (state === 'failed' && containerExitCode !== 0));
         if (noResultCandidate) {
           try { noResultDiagnostic = podNoResultDiagnostic(readFileSync(runLedgerPath(liveChildRunId, ledgerDir), 'utf8')); }
           catch { /* ledger not returned: do not invent a stage */ }
           noResultDiagnostic ??= 'child terminal result missing; last ledger stage=unknown; round=unknown; mustFix=unknown';
         }
-        // POD-NORESULT-LOG-TAIL: the Job runs with backoffLimit 0, so the failed Pod — and its container log —
-        //   is collected right after this. When the child ledger cannot even name the stage, read the tail here,
-        //   before deletion, so the parent keeps a maskable reason instead of `childEvidence=null`.
+        // POD-FAIL-EVIDENCE-CAPTURE: failed Pods are collected/deleted immediately after terminal handling.
+        //   Preserve a bounded log tail for every non-OOM/non-deadline failure, including known child stages:
+        //   the terminal result line can be followed by the useful stderr that explains the actual exit.
         let noResultLogEvidence: Record<string, unknown> | null = null;
-        if (noResultDiagnostic?.includes('stage=unknown')) {
+        const shouldCaptureFailureLog = state === 'failed' && !oomKilled && failedReason !== 'DeadlineExceeded';
+        const missingStage = noResultDiagnostic?.includes('stage=unknown') ?? false;
+        if (shouldCaptureFailureLog || missingStage) {
           const logRead = readPodNoResultLogTail({ run: kubectl, namespace, job: name, maxLines: POD_NO_RESULT_LOG_TAIL_LINES });
           if ('tail' in logRead) {
-            noResultLogEvidence = { stderr: logRead.tail.join('\n'), logTail: logRead.tail, logTailLines: logRead.tail.length };
-            debug.log('self-implement.pod', 'no-result-log-tail', { job: name, childRunId: liveChildRunId, diagnostic: noResultDiagnostic, lines: logRead.tail.length, logTail: logRead.tail }, { compact: { stringMax: 500 } });
+            noResultLogEvidence = missingStage
+              ? { stderr: logRead.tail.join('\n'), logTail: logRead.tail, logTailLines: logRead.tail.length }
+              : { podLogTail: logRead.tail, podLogTailLines: logRead.tail.length };
+            debug.log('self-implement.pod', missingStage ? 'no-result-log-tail' : 'failed-pod-log-tail', {
+              job: name, childRunId: liveChildRunId, diagnostic: noResultDiagnostic, lines: logRead.tail.length, logTail: logRead.tail,
+            }, { compact: { stringMax: 500 } });
           } else {
-            noResultLogEvidence = { stderr: `log-unavailable: ${logRead.unavailable}` };
-            debug.log('self-implement.pod', 'no-result-log-tail', { job: name, childRunId: liveChildRunId, diagnostic: noResultDiagnostic, logUnavailable: logRead.unavailable }, { level: 'warn' });
+            const unavailable = `log-unavailable: ${logRead.unavailable}`;
+            noResultLogEvidence = missingStage
+              ? { stderr: unavailable }
+              : { podLogUnavailable: logRead.unavailable };
+            debug.log('self-implement.pod', missingStage ? 'no-result-log-tail' : 'failed-pod-log-tail', {
+              job: name, childRunId: liveChildRunId, diagnostic: noResultDiagnostic,
+              logUnavailable: missingStage ? unavailable : logRead.unavailable,
+            }, { level: 'warn' });
           }
         }
         if (childFailure) debug.log('self-implement.pod', 'child-error', { job: name, stage: childFailure.stage, error: childFailure.error, ...(childPrFailure ?? {}) }, { compact: { stringMax: 500 } });
@@ -3192,7 +3439,7 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
           appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-oom-retry-finished', data: { job: name, executionKey, fromChildRunId: retryFromChildRunId, childRunId: liveChildRunId, state } }, ledgerDir);
         }
         if (goalFile) {
-          const noResultOutcome = state === 'failed' && containerExitCode !== null && noResultDiagnostic ? 'abandoned' : 'pod-no-result';
+          const noResultOutcome = podVanished || (state === 'failed' && containerExitCode !== null && noResultDiagnostic) ? 'abandoned' : 'pod-no-result';
           const record: GoalExecutionRecord = {
             runId: liveChildRunId,
             stage: (state === 'aborted' || !disposition ? 'aborted' : disposition.stage) as GoalExecutionRecord['stage'],
@@ -3209,7 +3456,9 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         if (state === 'failed' || state === 'aborted' || noResultLogEvidence || (state === 'complete' && noResultDiagnostic !== null)) {
           // Every terminal attempt writes a marker, including one with no parseable child facts.
           // The next attempt must never inherit an earlier Pod's classification.
-          const childEvidence = noResultLogEvidence ?? disposition?.childEvidence ?? null;
+          const childEvidence = noResultLogEvidence
+            ? { ...(disposition?.childEvidence ?? {}), ...noResultLogEvidence }
+            : disposition?.childEvidence ?? null;
           try { appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-child-evidence', data: { childEvidence, childRunId: liveChildRunId, job: name, ...(podTermination ? { podTermination } : {}) } }, ledgerDir); }
           catch (error) { debug.log('self-implement.pod', 'child-evidence-write-failed', { job: name, childRunId: liveChildRunId, reason: error instanceof Error ? error.message : String(error) }, { level: 'warn' }); }
         }
@@ -3218,7 +3467,7 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         if (disposition && (state === 'failed' || state === 'aborted' || disposition.ok === false)
           && (!Number.isSafeInteger(disposition.prNumber) || (disposition.prNumber ?? 0) <= 0) && terminalBranch) {
           try { prLookup = await (options.lookupOpenPrByBranch ?? defaultLookupOpenPrByBranch)(terminalBranch, repoUrl); }
-          catch { prLookup = { status: 'failed', reason: 'pr-lookup-threw' }; }
+          catch (error) { prLookup = { status: 'failed', reason: `pr-lookup-failed: ${error instanceof Error ? error.message : String(error)}`.slice(0, 200) }; }
         }
         const terminalDisposition = prLookup?.status === 'found' && disposition
           ? { ...disposition, prNumber: prLookup.prNumber, prUrl: prLookup.prUrl } : disposition;
@@ -3262,7 +3511,7 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
           : disposition;
         // A gate environment deficit can exit the child with 1 while still yielding a
         // verified repair bundle. The host rejudges the new PR head after CAS apply.
-        const podExitCode = repairPodExitCode({ state, repairCommitOnly: !!options.repairCommitOnly,
+        const podExitCode = podVanished ? 1 : repairPodExitCode({ state, repairCommitOnly: !!options.repairCommitOnly,
           repairArtifactReady, disposition });
         // SCHED-CONTRACT: a failed child must say why outside the Pod, not «no error diagnostic».
         const rawPodReason = podExitCode === 1 ? extractPodFailureReason({ logs, logTailReason, containerReason, jobReason: failedReason || undefined, deadlineSeconds, result: disposition ? { stage: disposition.stage, prUrl: disposition.prUrl ?? null, prNumber: disposition.prNumber ?? null } : null }) : undefined;
@@ -3276,10 +3525,18 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
           const salvageOutcome = /^ELANOUS_POD_SALVAGE \S+ \S+$/m.test(logs) ? 'pushed' : logs.includes('ELANOUS_POD_SALVAGE_NONE') ? 'none' : 'unknown';
           passJourneyNode('salvage', { provenance: 'self-implement-pod', outcome: salvageOutcome, data: { job: name } });
         }
+        const repairGateReceipt = disposition?.stage === 'gate-failed' ? gateFailureReceipt(disposition.gate) : null;
+        if (repairGateReceipt) {
+          for (const line of gateFailureReceiptLines(repairGateReceipt)) console.log(line);
+          debug.log('self-implement.pod', 'gate-failure-receipt', { job: name, childRunId: liveChildRunId,
+            signature: repairGateReceipt.signature, tests: repairGateReceipt.tests });
+        }
         return {
           exitCode: podExitCode,
           output: tail,
-          ...(deadlineExceeded
+          ...(podVanished
+            ? { error: { code: 'pod-vanished', message: `Job ${name} disappeared after 3 consecutive NotFound polls` } }
+            : deadlineExceeded
             ? { error: { code: 'pod-deadline-exceeded', message: `Job ${name} 이 수명 상한 ${deadlineSeconds}초에 닿았다` } }
             : state === 'failed'
               ? containerExitCode === 7
@@ -3429,7 +3686,9 @@ export function podNoResultLogTailLines(source: string, maxLines: number = POD_N
   let chars = 0;
   for (const line of lines.slice(-Math.max(0, maxLines)).reverse()) {
     if (chars >= POD_NO_RESULT_LOG_TAIL_MAX_CHARS) break;
-    const bounded = boundedPodLogText(line, Math.min(POD_NO_RESULT_LOG_TAIL_LINE_CHARS, POD_NO_RESULT_LOG_TAIL_MAX_CHARS - chars));
+    const redacted = redactSecretText(line);
+    const limit = Math.min(POD_NO_RESULT_LOG_TAIL_LINE_CHARS, POD_NO_RESULT_LOG_TAIL_MAX_CHARS - chars);
+    const bounded = redacted.length > limit ? `${redacted.slice(0, limit)}…[truncated]` : redacted;
     if (!bounded) continue;
     result.push(bounded);
     chars += bounded.length;
@@ -3451,7 +3710,7 @@ export function readPodNoResultLogTail(args: {
 }): PodNoResultLogRead {
   const maxLines = args.maxLines ?? POD_NO_RESULT_LOG_TAIL_LINES;
   try {
-    const result = args.run(['-n', args.namespace, 'logs', `job/${args.job}`, `--tail=${maxLines}`]);
+    const result = args.run(['-n', args.namespace, 'logs', `job/${args.job}`, '-c', 'child', `--tail=${maxLines}`]);
     if (result.status !== 0) {
       const reason = boundedPodLogText(result.stderr || result.stdout || '', POD_NO_RESULT_LOG_REASON_MAX_CHARS);
       return { unavailable: reason || `kubectl logs exit ${result.status}` };