elanous 0.2.34 → 0.2.36

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

@@ -18,6 +18,8 @@ import { GROUNDING_TOKEN_ENV, GROUNDING_URL_ENV, mintGroundingToken, revokeGroun
 import { POD_CREDENTIAL_GROK_PATH, POD_CREDENTIAL_GITHUB_PATH, POD_GITHUB_CREDENTIAL_TOKEN_ENV, POD_GITHUB_CREDENTIAL_URL_ENV, installationRepositories } from '../../nexus/api/pod-credential-api.js';
 import { coalescedInstallationCredential } from '../../auth/github-app-token.js';
 import { POD_CREDENTIAL_TOKEN_ENV, POD_CREDENTIAL_URL_ENV } from '../../grok/credential.js';
+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 { readPodRepairArtifact } from './pod-repair-commit.js';
@@ -28,12 +30,18 @@ import { controlInboxEnv } from '../../harness/control-inbox.js';
 import { finishPodFragment, writePodFragment } from '../../harness/self-send-target.js';
 import { mintRunId, normalizeRunId } from '../../harness/harness-space.js';
 import { TA_LAND_ENV } from '../../task-agent/task-hand.js';
-import { appendRunLedgerEntry, loadRunLedger, runLedgerDir, runLedgerPath } from '../../self-implement/run-ledger.js';
+import { appendRunLedgerEntry, loadRunLedger, runLedgerDir, runLedgerPath, type RunLedgerEntry } from '../../self-implement/run-ledger.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';
 import { resolvePodHostAcpReview, runPodHostAcpReview, type PodHostAcpReviewOutcome } from './pod-host-acp-review.js';
 import { REVIEW_DEFERRED_TO_HOST_ENV, REVIEW_DEFERRED_TO_HOST_MERGE_REASON } from '../../self-implement/review-deferred-to-host.js';
 import { classifyPodTerminal, applyPodTerminal, podTerminalPrBody, type PrTerminalRecord, type DraftResidueContext } from '../../self-dev/draft-residue.js';
+import { assessSiWarmReply, decideSiWarmNextStep, type SiWarmCommand, type SiWarmReply,
+  type SiWarmReturnedBytes } from './pod-si-warm-protocol.js';
+import { cleanAndReturnChildPod, type ChildPodReuseOperations } from './pod-child-reuse.js';
+import { executeSiWarmTransport, type SiWarmFixedRunner,
+  type SiWarmPodIdentity } from './pod-si-warm-transport.js';
 
 export const POD_CONTROL_INBOX_DIR = '/tmp/elanous-control.inbox';
 /** Pod Job 수명 상한(`activeDeadlineSeconds`) — 대표 2026-09-26 90분 → 180분(90분에 `DeadlineExceeded` 로 죽은 런 둘). */
@@ -56,6 +64,9 @@ export const POD_JOB_DEADLINE_SECONDS = 10_800;
 // POD-DIET (10-06 03:47~05:18 · node-b goal Pods · 89 one-minute samples · 42 Pods): per-Pod observed max median 4.6Gi ·
 // p75 6.2Gi · p90 11.7Gi — 23/42 went above the old 4Gi request, so the scheduler over-packed. 6Gi ≈ p75; limits stay.
 // Node allocatable ≈ 343Gi ≫ 25 × 6Gi. One-minute samples can miss the true peak (lower bound).
+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';
 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';
@@ -68,7 +79,7 @@ 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';
 import { acquireLockAsync } from '../../storage/file-lock.js';
-import { debug } from '../../debug/log.js';
+import { debug, redactSecretText } from '../../debug/log.js';
 import { enterJourneyNode, exitJourneyNode, passJourneyNode } from '../../self-dev/graph-journey-nodes.js';
 import { routeJourneyEdge } from '../../self-dev/graph-journey-route.js';
 import { selectLiveDetail } from '../../live/detail-switch.js';
@@ -94,7 +105,7 @@ 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, podTerminalRow, type PodExitClass } from './pod-failure-reason.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 { 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';
@@ -102,7 +113,24 @@ import { decideWarmReuse, type WarmReuseEvidenceByConsumer, type WarmReuseSwitch
 import type { WarmWorkerCommand } from './pod-warm-worker-protocol.js';
 import type { WarmPodTransportResult } from './pod-warm-worker-pod.js';
 
-export type Kubectl = (args: readonly string[], input?: string) => { status: number | null; stdout: string; stderr: string };
+export type Kubectl = (args: readonly string[], input?: string, timeoutMs?: number) => { status: number | null; stdout: string; stderr: string };
+
+/** TC's si-v1 transport supplies this receipt. No lease is considered reusable from a Job exit alone. */
+export interface SiWarmChildAttempt {
+  leaseFenced: boolean;
+  command: SiWarmCommand | null;
+  /** The consumer executes this fenced transport. A provider cannot assert its own reply verdict. */
+  transport: { pod: SiWarmPodIdentity; runner: SiWarmFixedRunner; now?: () => number };
+  payload: Uint8Array;
+  credentialBundle: Uint8Array;
+  /** Collect verified ledger/artifact bytes into the existing host stores. */
+  adopt: (command: SiWarmCommand, reply: SiWarmReply, bytes: SiWarmReturnedBytes) => Promise<void>;
+  cleanup: ChildPodReuseOperations;
+  /** The provider fences a worker even when a transport failure hides its command receipt. */
+  quarantineUnknown: (reason: string) => Promise<void>;
+}
+type OpenPrByBranch = { status: 'found'; prNumber: number; prUrl: string }
+  | { status: 'not-found' | 'failed'; reason: string };
 
 /** TC supplies the validated candidate/lease transport. UX only forwards its request command. */
 export type WarmPodRequestHook = (request: { command: WarmWorkerCommand }) => Promise<WarmPodTransportResult> | WarmPodTransportResult;
@@ -118,6 +146,13 @@ const APP_GH_AUTH_COMMAND = `bun -e '${APP_GH_AUTH_SCRIPT}'`;
 const APP_GH_EXEC = `unset GH_TOKEN GITHUB_TOKEN; GH_CONFIG_DIR="${APP_GH_CONFIG_PATH}" exec "$@"`;
 
 export interface PodSpawnOptions {
+  /** si-v1 living worker consumer. Absent means the existing one-shot Job path. */
+  siWarmAttempt?: (input: Parameters<SelfImplementJobSpawn>[0]) => Promise<SiWarmChildAttempt | null>;
+  /** POD-REUSE-SI-PROVIDER-WIRE: must apply cold-path host regate, ACP, terminal and repair checks before warm adoption. */
+  siWarmHostPostprocess?: (result: SelfImplementJobDone, attempt: SiWarmChildAttempt,
+    input: Parameters<SelfImplementJobSpawn>[0]) => Promise<SelfImplementJobDone>;
+  /** Injected test ledger; production writes to the existing run ledger. */
+  siWarmLedger?: (entry: RunLedgerEntry) => void;
   /** 이미지 판(라벨 elanous.commit) — 주입(시험·감독기가 이미 잰 값). 없으면 docker 로 잰다. */
   imageCommit?: string | null;
   /** codex 계정 이름(`~/.elanous/auth.json` 의 `openai-codex:<이름>`). 기본 team. */
@@ -169,6 +204,8 @@ export interface PodSpawnOptions {
   authorConfig?: () => UserConfig;
   /** Host fallback chain seam; a Pod has no access to the host config. */
   fallbackConfig?: () => UserConfig;
+  /** Host OpenGateway key config seam; unit tests inject isolated config without bypassing production reads. */
+  openGatewayConfig?: () => UserConfig;
   /** 원천 — 없으면 종전 `git clone --depth 50`. bundle 이면 apply 뒤 kubectl cp 로 싣는다. */
   source?: PodSource;
   /** Existing PR repair: pin the source head and export a commit bundle instead of opening a PR. */
@@ -205,6 +242,8 @@ export interface PodSpawnOptions {
   taskAgentLiveMoves?: () => Promise<ReadonlySet<string>> | ReadonlySet<string>;
   /** PR comment for host-regate failures that never reached runHostRegate (injectable for tests). */
   ghComment?: (prNumber: number, body: string) => void;
+  /** Read-only host gh lookup; injected fixtures can stand in for gh without creating or closing a PR. */
+  lookupOpenPrByBranch?: (branch: string, repoUrl: string) => Promise<OpenPrByBranch> | OpenPrByBranch;
   draftResidue?: (record: PrTerminalRecord, ctx: DraftResidueContext) => Promise<void> | void;
   /** 🔑 Pod 필수 스킬의 키(.env)를 이 런의 Secret 으로 넘긴다 — 명시 opt-in(유료 크레딧을 쓴다). */
   skillEnv?: boolean;
@@ -397,6 +436,11 @@ export async function podCodexCredentialWithPrerefresh(account: string, deps: {
       // ⑴ 잠금을 기다리는 사이 동료 런이 갱신했으면 그대로 쓴다 — 두 번째 갱신이 회전된 토큰으로 실패하는 자리.
       const first = reread();
       if (!('expiringH' in first)) { observe('refresh-skipped-already-fresh', null); return first; }
+      // The lease can transfer while an account lock is queued. Recheck inside the
+      // critical section, immediately before the only refresh-token operation.
+      let stillHolder = false;
+      try { stillHolder = await deps.isLeaseHolder(); } catch { stillHolder = false; }
+      if (!stillHolder) { observe('no-lease', null, 'lease-lost-before-refresh'); return null; }
       let refreshed: Awaited<ReturnType<typeof deps.refresh>> | null = null;
       let failReason = 'threw';
       try { refreshed = await deps.refresh(account); }
@@ -430,6 +474,7 @@ export async function podCodexCredentialWithPrerefresh(account: string, deps: {
 
 /** 기본 임대 판정 — 기존 HQ 펜스(`ledger-cli` 역할 · fail-open 없음)를 그대로 쓴다. */
 async function defaultHqLeaseHolder(): Promise<boolean> {
+  if (process.env.ELANOUS_REMOTE_CODEX_ACCESS_ONLY === '1') return false;
   const { hqFenceDecision } = await import('../../hq/hq.js');
   return hqFenceDecision('ledger-cli').run;
 }
@@ -649,20 +694,45 @@ function githubRepositoryFromUrl(repoUrl: string): string | null {
   return owner && name && ![owner, name].some((part) => part === '.' || part === '..') ? `${owner}/${name}` : null;
 }
 
-/** GROK-CHILD-GIT-GUARD — the Pod holds a GitHub write token and our repo cannot protect main (private free plan · API 403),
- *  so a child tool could `git push origin main`, force-push another run's branch or delete remote branches. A global
- *  pre-push hook lets a Pod push only its own run branches (self-impl/* · salvage/* · bench/<id>/<arm>) and refuses
- *  everything else, including deletes and the shared bench base. It stops accidental and reset-then-push overwrites;
- *  it is not a sandbox — credential isolation from child tools is the next slice. */
+/** GROK-CHILD-GIT-GUARD — the Pod holds a GitHub write token and our repo cannot protect main (private free plan · API 403).
+ *  The global hook refuses main/tags/unknown refs and most deletes. With a runId, self-impl refs use the same six-hex
+ *  run suffix as planned branch names; only that suffix and this run's disposable PR scratch create/delete pass.
+ *  A same-card PR reuse push is the one exception: per-command Git config binds its ref, old head and card;
+ *  the hook compares the Pod card and proves fast-forward ancestry before accepting it.
+ *  salvage/* and bench arm refs keep their existing broader rules. A six-hex collision remains possible, so this is
+ *  an accidental overwrite guard, not a security isolation boundary; child credential isolation is a separate slice. */
 export const POD_GIT_HOOKS_DIR = '$HOME/.elanous-git-hooks';
-export function podGitPushGuardScript(): string {
+export function podGitPushGuardScript(runId?: string): string {
+  const runKey = runId ? runSuffixKey(runId) : null;
+  const zeroSha = '0'.repeat(40);
   return [
     `mkdir -p "${POD_GIT_HOOKS_DIR}" && cat > "${POD_GIT_HOOKS_DIR}/pre-push" <<'ELANOUS_PRE_PUSH'`,
     '#!/bin/sh',
     'while read -r lref lsha rref rsha; do',
-    '  case "$lsha" in *[!0]*) ;; *) echo "[pod] git-guard: refused remote delete $rref" >&2; exit 1 ;; esac',
+    '  case "$lsha" in *[!0]*) ;; *)',
+    ...(runKey ? [
+      `    case "$rref" in refs/heads/self-impl/pr-create-r${runKey}-*) ;; *) echo "[pod] git-guard: refused remote delete $rref" >&2; exit 1 ;; esac ;;`,
+    ] : ['    echo "[pod] git-guard: refused remote delete $rref" >&2; exit 1 ;;']),
+    '  esac',
     '  case "$rref" in',
-    '    refs/heads/self-impl/*|refs/heads/salvage/*) ;;',
+    ...(runKey ? [
+      `    refs/heads/self-impl/pr-create-r${runKey}-*)`,
+      `      case "$lsha:$rsha" in ${zeroSha}:*|*:${zeroSha}) ;; *) echo "[pod] git-guard: refused scratch ref update $rref" >&2; exit 1 ;; esac ;;`,
+      `    refs/heads/self-impl/*-r${runKey}|refs/heads/self-impl/*-r${runKey}-early) ;;`,
+      '    refs/heads/self-impl/*)',
+      '      reuse_ref=$(git config --get elanous.sameCellReuseRef 2>/dev/null || true)',
+      '      reuse_head=$(git config --get elanous.sameCellReuseHead 2>/dev/null || true)',
+      '      reuse_card=$(git config --get elanous.sameCellReuseCard 2>/dev/null || true)',
+      '      if [ -z "$reuse_ref" ]; then echo "[pod] git-guard: refused push to $rref (another run)" >&2; exit 1; fi',
+      '      if [ "$rref" != "$reuse_ref" ]; then echo "[pod] git-guard: refused same-cell ref-mismatch $rref" >&2; exit 1; fi',
+      '      if [ -z "${ELANOUS_TASK_CARD_ID:-}" ] || [ "$reuse_card" != "$ELANOUS_TASK_CARD_ID" ]; then echo "[pod] git-guard: refused same-cell card-mismatch $rref" >&2; exit 1; fi',
+      '      if [ -z "$reuse_head" ] || [ "$rsha" != "$reuse_head" ]; then echo "[pod] git-guard: refused same-cell remote-head-mismatch $rref" >&2; exit 1; fi',
+      '      if ! git merge-base --is-ancestor "$rsha" "$lsha" 2>/dev/null; then echo "[pod] git-guard: refused same-cell non-fast-forward $rref" >&2; exit 1; fi',
+      '      echo "[pod] git-guard: allowed same-cell fast-forward $rref" >&2 ;;',
+    ] : [
+      ...(runId ? ['    refs/heads/self-impl/*) echo "[pod] git-guard: refused push to $rref (invalid run id)" >&2; exit 1 ;;'] : ['    refs/heads/self-impl/*) ;;']),
+    ]),
+    '    refs/heads/salvage/*) ;;',
     '    refs/heads/bench/*/base) echo "[pod] git-guard: refused push to shared bench base $rref" >&2; exit 1 ;;',
     '    refs/heads/bench/*/*) ;;',
     '    *) echo "[pod] git-guard: refused push to $rref (only this run\'s branches)" >&2; exit 1 ;;',
@@ -963,7 +1033,7 @@ export function podMemoryLimitFor(feature: string, env: NodeJS.ProcessEnv | Read
 }
 
 /** A named child provider decides the Pod provider; paid OpenRouter requires an explicit key and model. */
-export function podNamedChildProvider(named: string | undefined, credential: { grokSubscription: boolean; grokApiKey: boolean; openrouterKey?: boolean; anthropicKey?: boolean }, childModel?: string): { provider?: PodChildProvider; refuse?: string } {
+export function podNamedChildProvider(named: string | undefined, credential: { grokSubscription: boolean; grokApiKey: boolean; openrouterKey?: boolean; openGatewayKey?: boolean; anthropicKey?: boolean }, childModel?: string): { provider?: PodChildProvider; refuse?: string } {
   // 공백·빈 이름 = «미지정»(종전 기본 경로) — 유료 provider 로 흘러가지 않는다(codex 재리뷰 must-fix).
   if (!named?.trim()) return {};
   // ⭐ 목록은 한 곳(pod-child-providers.ts) — 발사 관문도 같은 상수·같은 문면으로 거부한다.
@@ -978,6 +1048,12 @@ export function podNamedChildProvider(named: string | undefined, credential: { g
     if (!childModel?.trim()) return { refuse: 'pod: openrouter 자식 모델 없음 — --child-llm-model 필요' };
     return { provider: 'openrouter' };
   }
+  if (named === 'opengateway') {
+    if (!credential.openGatewayKey) return { refuse: 'pod: Pod 에 opengateway 키 없음 — 호스트 키 캐시 또는 OPENGATEWAY_API_KEY 필요' };
+    if (!childModel?.trim()) return { refuse: 'pod: opengateway 자식 모델 없음 — --child-llm-model 필요' };
+    if (!isVerifiedOpenGatewayModel(childModel.trim())) return { refuse: `pod: opengateway model not verified: ${childModel.trim()}` };
+    return { provider: 'opengateway' };
+  }
   // BEDROCK-PROVIDER ② — 자격은 클러스터의 이름 있는 Secret 에서 온다. 있나·키가 갖춰졌나는 Pod 발사 «전»(apply 0)에 판정한다(checkBedrockPodSecret).
   if (named === 'bedrock') return { provider: 'bedrock' };
   // ZAI-POD-CHILD — glm 도 같은 결: 자격은 클러스터의 이름 있는 ZAI Secret · 있나·동시 상한은 Pod 발사 «전»(apply 0)에 판정한다(pod-zai-child.ts).
@@ -1012,7 +1088,8 @@ export function podChildLlmArgs(options: Pick<PodSpawnOptions, 'provider' | 'chi
   const provider = options.provider === 'openai-codex' && !options.childProviderExplicit ? undefined : options.provider;
   if (!provider) return [];
   const model = options.childModel?.trim() || (provider === 'grok' ? defaultGrokModel().id : provider === 'glm' ? ZAI_CODING_DEFAULT_MODEL : undefined);
-  if (provider === 'openrouter' && !model) throw new Error('pod: openrouter 자식 모델 없음 — --child-llm-model 필요');
+  if ((provider === 'openrouter' || provider === 'opengateway') && !model) throw new Error(`pod: ${provider} 자식 모델 없음 — --child-llm-model 필요`);
+  if (provider === 'opengateway' && !isVerifiedOpenGatewayModel(model!)) throw new Error(`pod: opengateway model not verified: ${model}`);
   // `self implement` registers no --child-llm-effort — passing it kills the Pod at argument parsing, so effort stays host-only.
   return ['--child-llm-provider', provider, ...(model ? ['--child-llm-model', model] : [])];
 }
@@ -1069,7 +1146,7 @@ export function podSigtermTrapScript(seqFile: string = POD_USAGE_PARTIAL_SEQ_FIL
   return `trap '{ [ -n "$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`;
 }
 
-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 }): Record<string, unknown> {
+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');
   }
@@ -1078,6 +1155,8 @@ export function podJobManifest(o: { name: string; namespace: string; image: stri
   const childModelIndex = o.args.indexOf('--child-llm-model');
   const openrouterModel = childProviderIndex >= 0 && o.args[childProviderIndex + 1] === 'openrouter' && childModelIndex >= 0
     ? o.args[childModelIndex + 1] : undefined;
+  const openGatewayModel = childProviderIndex >= 0 && o.args[childProviderIndex + 1] === 'opengateway' && childModelIndex >= 0
+    ? o.args[childModelIndex + 1] : undefined;
   // POD-ANTHROPIC-PROVIDER — anthropic 자식은 키(env · secretKeyRef)만 쓴다. codex·grok 자격 파일을 깔지 않는다.
   const anthropicChild = childProviderIndex >= 0 && o.args[childProviderIndex + 1] === 'anthropic';
   const goalPath = o.goalDoc ? `'${(o.goalDoc.startsWith('-') ? `./${o.goalDoc}` : o.goalDoc).replace(/'/g, `'\\''`)}'` : undefined;
@@ -1101,7 +1180,9 @@ export function podJobManifest(o: { name: string; namespace: string; image: stri
       'mkdir -p "$HOME/.elanous" && install -m 600 /creds/llm-fallback-config.json "$HOME/.elanous/config.json" || exit 6',
       `echo "ELANOUS_POD_FALLBACK_CHAIN source=${o.fallbackChain.source} steps=${o.fallbackChain.steps.join(',')}"`,
     ] : []),
-    openrouterModel
+    openGatewayModel
+      ? 'mkdir -p ~/.elanous && export ELANOUS_LLM_PROVIDER=opengateway'
+      : openrouterModel
       ? o.reviewerCodexAuth
         ? 'mkdir -p ~/.elanous ~/.codex && cp /creds/elanous-auth.json ~/.elanous/auth.json && cp /creds/codex-auth.json ~/.codex/auth.json && chmod 600 ~/.elanous/auth.json ~/.codex/auth.json && export ELANOUS_LLM_PROVIDER=openrouter'
         : 'mkdir -p ~/.elanous && export ELANOUS_LLM_PROVIDER=openrouter'
@@ -1120,7 +1201,7 @@ export function podJobManifest(o: { name: string; namespace: string; image: stri
     // 🔑 스킬 키(.env) — 이미지엔 없다. 이 런의 Secret 에서 각 스킬 폴더로 0600 복사(값은 로그에 안 나온다).
     ...(o.skillEnvs?.length ? [`for n in ${o.skillEnvs.join(' ')}; do [ -d ~/.claude/skills/$n ] && install -m 600 /creds/skillenv-$n ~/.claude/skills/$n/.env; done; echo "[pod] skill env: ${o.skillEnvs.join(',')}"`] : []),
     'git config --global user.name "elanous pod child" && git config --global user.email "noreply@anthropic.com" && gh auth setup-git',
-    podGitPushGuardScript(),
+    podGitPushGuardScript(o.runId),
     'curl -s -m 3 -o /dev/null http://host.orb.internal:31415/health && { echo "[pod] ISOLATION FAIL"; exit 3; }',
     // SI-POD-STAGE-MARKERS — Pod 시계 단계 표지(`ELANOUS_POD_STAGE <stage> <start|end> <epoch초>`): 호스트가 Job 로그에서 읽어
     //   pod.lifecycle stages 의 clone · mirror · run 을 채운다. 실패한 단계는 끝 표지가 없다(→ missing · 지어내지 않는다).
@@ -1132,6 +1213,9 @@ export function podJobManifest(o: { name: string; namespace: string; image: stri
     // Record that fact before the main command, without treating clone completion as install completion.
     `printf 'ELANOUS_POD_DEPS skipped %s image-prepared-no-install\\n' "$(date +%s)" || true`,
     ...(o.repairCommitOnly ? [`[ "$(git rev-parse HEAD)" = '${o.repairCommitOnly.baseHead}' ] || { echo 'ELANOUS_POD_REPAIR_FAILED source-head-mismatch'; exit 8; }`] : []),
+    // PR checkout and, when requested, the repair HEAD pin have passed before this child starts.
+    // A supervisor input may continue the repair, but cannot launch its source again.
+    ...(o.source?.kind === 'pr' ? ['export ELANOUS_POD_VERIFIED_PR_SOURCE=1'] : []),
     ...(goalPath ? [
       `mkdir -p -- "$(dirname -- ${goalPath})" && cp -- /creds/goal-doc ${goalPath} || exit 6`,
     ] : []),
@@ -1150,7 +1234,7 @@ export function podJobManifest(o: { name: string; namespace: string; image: stri
     // AUTHOR-LITE2-POD — 등급은 환경변수 `ELANOUS_AUTHOR_GRADE` 로 싣는다(옛 Pod elanous 는 모르는 환경변수를 무시하고 full 로 돈다).
     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 "$si_pid"; rc=$?; ${RUN_END}; if [ "$rc" -eq 0 ]; then elanous self repair-commit-export '${o.repairCommitOnly.pr}' '${o.repairCommitOnly.baseHead}' /tmp/si.out "$PWD" "$HOME/outbox" || rc=8; fi`
+      ? `export ${OLD_DOOR_STAMP_ENV}=self-implement; elanous self implement "$(cat /creds/feature)" --json --no-open-pr ${quoted} > /tmp/si.out 2>&1 & si_pid=$!; 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`
       : 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 ))"; ${POD_RESULT_FLATTEN}`
       : goalPath
@@ -1225,15 +1309,15 @@ if [ "$found" -eq 0 ]; then echo ELANOUS_RUN_LEDGER_NONE; fi`,
   return {
     apiVersion: 'batch/v1',
     kind: 'Job',
-    metadata: { name: o.name, namespace: o.namespace, labels: { 'elanous.substrate': 'pod', 'elanous.job': o.name, ...podRunLabels(o), ...(o.workIdentity ? podWorkLabels(o.workIdentity) : {}), ...(o.zai || o.zaiFallback ? { [ZAI_POD_EGRESS_LABEL]: 'true' } : {}) },
-      ...((o.execution || o.hostLeaseAdmitted) ? { annotations: { ...(o.execution ? { [POD_EXECUTION_KEY_ANNOTATION]: o.execution.key, [POD_ATTEMPT_ANNOTATION]: String(o.execution.attempt) } : {}), ...(o.hostLeaseAdmitted ? { [POD_HOST_LEASE_ANNOTATION]: 'true' } : {}) } } : {}) },
+    metadata: { name: o.name, namespace: o.namespace, labels: { 'elanous.substrate': 'pod', 'elanous.job': o.name, ...podRunLabels(o), ...(o.workIdentity ? podWorkLabels(o.workIdentity) : {}), ...(o.zai || o.zaiFallback ? { [ZAI_POD_EGRESS_LABEL]: 'true' } : {}), ...o.provenance?.labels },
+      ...((o.execution || o.hostLeaseAdmitted || o.provenance) ? { annotations: { ...o.provenance?.annotations, ...(o.execution ? { [POD_EXECUTION_KEY_ANNOTATION]: o.execution.key, [POD_ATTEMPT_ANNOTATION]: String(o.execution.attempt) } : {}), ...(o.hostLeaseAdmitted ? { [POD_HOST_LEASE_ANNOTATION]: 'true' } : {}) } } : {}) },
     spec: {
       backoffLimit: 0,
       ttlSecondsAfterFinished: POD_JOB_TTL_AFTER_FINISHED_SECONDS,
       activeDeadlineSeconds: o.deadlineSeconds,
       template: {
         // ⭐ Pod 라벨 — local 팔만 `elanous.egress/local-llm` 을 단다. docker/h1/policy-local-llm.yaml 이 그 라벨에만 호스트 LLM 포트 «하나»를 연다.
-        metadata: { labels: { 'elanous.job': o.name, ...podRunLabels(o), ...(o.workIdentity ? podWorkLabels(o.workIdentity) : {}), ...(o.armEnv?.ELANOUS_LLM_PROVIDER === 'local' ? { 'elanous.egress/local-llm': 'true' } : {}), ...(o.bedrock ? { [BEDROCK_POD_EGRESS_LABEL]: 'true' } : {}), ...(o.zai || o.zaiFallback ? { [ZAI_POD_EGRESS_LABEL]: 'true' } : {}) } },
+        metadata: { labels: { 'elanous.job': o.name, ...podRunLabels(o), ...(o.workIdentity ? podWorkLabels(o.workIdentity) : {}), ...(o.armEnv?.ELANOUS_LLM_PROVIDER === 'local' ? { 'elanous.egress/local-llm': 'true' } : {}), ...(o.bedrock ? { [BEDROCK_POD_EGRESS_LABEL]: 'true' } : {}), ...(o.zai || o.zaiFallback ? { [ZAI_POD_EGRESS_LABEL]: 'true' } : {}), ...o.provenance?.labels }, ...(o.provenance ? { annotations: o.provenance.annotations } : {}) },
         spec: {
           restartPolicy: 'Never',
           securityContext: { runAsUser: 1000, fsGroup: 1000 },
@@ -1260,6 +1344,8 @@ if [ "$found" -eq 0 ]; then echo ELANOUS_RUN_LEDGER_NONE; fi`,
               { name: 'ELANOUS_POD_NAMESPACE', valueFrom: { fieldRef: { fieldPath: 'metadata.namespace' } } },
               ...(o.hostId ? [{ name: 'ELANOUS_HOST_ID', value: o.hostId }] : []),
               ...(o.imageCommit ? [{ name: 'ELANOUS_IMAGE_COMMIT', value: o.imageCommit }] : []),
+              // POD-LAUNCH-PROVENANCE — the child knows who launched it, why and when (ELANOUS_POD_<key> · no secrets).
+              ...(o.provenance?.env ?? []),
               // ⭐ 런 계약(graph-run-contract.ts) — 이 칸이 «실제로» Pod 이고, 부모가 정한 계약도 Pod 다. 안의 그래프가 노드마다 대조한다.
               { name: ACTUAL_SUBSTRATE_ENV, value: 'pod' }, { name: RUN_CONTRACT_ENV, value: carryRunContract({ substrate: 'pod' }) },
               ...Object.entries(o.armEnv ?? {}).map(([name, value]) => ({ name, value })),
@@ -1291,6 +1377,93 @@ function defaultGhComment(prNumber: number, body: string): void {
   if (r.status !== 0) throw new Error((r.stderr || r.error?.message || `gh exited ${r.status}`).trim().slice(0, 200));
 }
 
+function defaultLookupOpenPrByBranch(branch: string, repoUrl: string): OpenPrByBranch {
+  const repo = /^https:\/\/github\.com\/([\w.-]+\/[\w.-]+?)(?:\.git)?\/?$/u.exec(repoUrl)?.[1];
+  if (!repo) return { status: 'failed', reason: 'repository-unrecognized' };
+  if (!branch || !/^[A-Za-z0-9._/-]+$/u.test(branch) || branch.includes('..')) return { status: 'failed', reason: 'branch-invalid' };
+  const result = spawnSync('gh', ['pr', 'list', '--repo', repo, '--state', 'open', '--head', branch,
+    '--json', 'number,url,headRefName,isCrossRepository', '--limit', '100'], { encoding: 'utf8', timeout: 10_000, maxBuffer: 1_048_576 });
+  if (result.status !== 0) return { status: 'failed', reason: result.error ? 'gh-list-unavailable' : `gh-list-rc-${result.status ?? 'null'}` };
+  let rows: unknown;
+  try { rows = JSON.parse(result.stdout); } catch { return { status: 'failed', reason: 'gh-json-invalid' }; }
+  if (!Array.isArray(rows)) return { status: 'failed', reason: 'gh-json-invalid' };
+  if (rows.some((row) => row === null || typeof row !== 'object'
+    || typeof (row as { number?: unknown }).number !== 'number'
+    || !Number.isSafeInteger((row as { number: number }).number)
+    || typeof (row as { url?: unknown }).url !== 'string'
+    || typeof (row as { headRefName?: unknown }).headRefName !== 'string'
+    || typeof (row as { isCrossRepository?: unknown }).isCrossRepository !== 'boolean'))
+    return { status: 'failed', reason: 'gh-json-invalid' };
+  if (rows.length >= 100) return { status: 'failed', reason: 'gh-result-limit-reached' };
+  const matching = rows.filter((row): row is { number: number; url: string; headRefName: string; isCrossRepository: false } => {
+    if (row === null || typeof row !== 'object') return false;
+    const candidate = row as { number?: unknown; url?: unknown; headRefName?: unknown; isCrossRepository?: unknown };
+    return candidate.headRefName === branch && candidate.isCrossRepository === false && typeof candidate.number === 'number'
+      && Number.isSafeInteger(candidate.number) && candidate.number > 0 && typeof candidate.url === 'string';
+  });
+  if (matching.length === 0) return { status: 'not-found', reason: rows.some((row) =>
+    (row as { headRefName: string }).headRefName === branch && (row as { isCrossRepository: boolean }).isCrossRepository)
+    ? 'cross-repository-only' : 'no-open-pr-for-branch' };
+  if (matching.length !== 1) return { status: 'failed', reason: 'ambiguous-open-pr-for-branch' };
+  const row = matching[0]!;
+  if (row.url.replace(/\/$/u, '').toLowerCase() !== `https://github.com/${repo}/pull/${row.number}`.toLowerCase())
+    return { status: 'failed', reason: 'pr-url-mismatch' };
+  return { status: 'found', prNumber: row.number, prUrl: row.url };
+}
+
+type PodImageObservation = { podName: string | null; podUid: string | null; podCreatedAt: string | null;
+  imageID: string | null; digest: string | null; digestUnavailable: string | null };
+
+/** Read the newest Pod owned by this Job. A stale replacement must never be named as the final Pod. */
+function readJobPodImage(kubectl: Kubectl, namespace: string, job: string, jobUid?: string): PodImageObservation {
+  const unavailable = (reason: string, podName: string | null = null, imageID: string | null = null,
+    podUid: string | null = null, podCreatedAt: string | null = null): PodImageObservation =>
+    ({ podName, podUid, podCreatedAt, imageID, digest: null, digestUnavailable: reason });
+  let result: ReturnType<Kubectl>;
+  try { result = kubectl(['-n', namespace, 'get', 'pods', '-l', `job-name=${job}`, '-o', 'json', '--request-timeout=5s']); }
+  catch { return unavailable('pod-status-threw'); }
+  if (result.status !== 0) return unavailable(`pod-status-rc-${result.status ?? 'null'}`);
+  let rows: unknown;
+  try { rows = (JSON.parse(result.stdout) as { items?: unknown }).items; }
+  catch { return unavailable('pod-status-invalid-json'); }
+  if (!Array.isArray(rows)) return unavailable('pod-status-invalid-items');
+  const owned = rows.filter((row): row is {
+    metadata: { name: string; uid?: string; creationTimestamp?: string; ownerReferences: Array<{ kind: string; name: string; uid?: string }> };
+    status?: { containerStatuses?: Array<{ name?: string; imageID?: string }> };
+  } => {
+    if (!row || typeof row !== 'object') return false;
+    const meta = (row as { metadata?: unknown }).metadata;
+    if (!meta || typeof meta !== 'object') return false;
+    const m = meta as { name?: unknown; ownerReferences?: unknown };
+    if (typeof m.name !== 'string' || !Array.isArray(m.ownerReferences)) return false;
+    return m.ownerReferences.some((owner: unknown) => !!owner && typeof owner === 'object'
+      && (owner as { kind?: unknown }).kind === 'Job' && (owner as { name?: unknown }).name === job
+      && (!jobUid || (owner as { uid?: unknown }).uid === jobUid));
+  }).sort((a, b) => {
+    const at = Date.parse(a.metadata.creationTimestamp ?? '') || 0;
+    const bt = Date.parse(b.metadata.creationTimestamp ?? '') || 0;
+    return bt - at || b.metadata.name.localeCompare(a.metadata.name);
+  });
+  const pod = owned[0];
+  if (!pod) return unavailable(rows.length ? 'no-job-owned-pod' : 'pod-not-created');
+  const podUid = typeof pod.metadata.uid === 'string' ? pod.metadata.uid : null;
+  const podCreatedAt = typeof pod.metadata.creationTimestamp === 'string' ? pod.metadata.creationTimestamp : null;
+  const child = pod.status?.containerStatuses?.find((entry) => entry.name === 'child');
+  if (!child) return unavailable('child-container-not-started', pod.metadata.name, null, podUid, podCreatedAt);
+  const imageID = typeof child.imageID === 'string' ? child.imageID : null;
+  if (!imageID?.trim()) return unavailable('image-id-missing', pod.metadata.name, imageID, podUid, podCreatedAt);
+  const digest = /(?:^|[@/])(sha256:[0-9a-f]{64})$/iu.exec(imageID.trim())?.[1]?.toLowerCase() ?? null;
+  return { podName: pod.metadata.name, podUid, podCreatedAt, imageID, digest, digestUnavailable: digest ? null : 'nonstandard-image-id' };
+}
+
+/** A repair Pod succeeds only with a verified result/bundle, even if its child gate exited 1. */
+export function repairPodExitCode(input: { state: string; repairCommitOnly: boolean; repairArtifactReady: boolean;
+  disposition?: { stage?: string; ok?: boolean } }): 0 | 1 {
+  if (input.state !== 'complete') return 1;
+  if (input.repairCommitOnly) return input.repairArtifactReady ? 0 : 1;
+  return input.disposition?.stage !== 'host-regate-failed' && input.disposition?.ok !== false ? 0 : 1;
+}
+
 export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplementJobSpawn {
   if (options.repairCommitOnly && (options.source?.kind !== 'pr' || options.source.number !== options.repairCommitOnly.pr || !/^[0-9a-f]{40}$/.test(options.repairCommitOnly.baseHead))) {
     throw new Error('repair commit-only requires a matching PR source and exact head');
@@ -1306,10 +1479,290 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
   if (hostMirror && !isAbsolute(hostMirror)) throw new Error('pod.hostMirror must be an absolute directory path');
   const hostSupervised = options.hostSupervised ?? true;
   const resultMarkerOn = options.resultMarker ?? !options.kubectl;
+  const writeWarmLedger = options.siWarmLedger
+    ?? ((entry: RunLedgerEntry) => appendRunLedgerEntry(entry, runLedgerDir(env.ELANOUS_STATE_DIR)));
   return (input) => {
     if (options.repairCommitOnly && (input.autoMerge || input.openPr || input.base !== `pr-${options.repairCommitOnly.pr}`)) {
       throw new Error('repair commit-only refuses auto merge, new PR, or a different base');
     }
+    if (options.siWarmAttempt && !options.siWarmHostPostprocess) {
+      throw new Error('si-v1 warm execution requires cold-path host postprocess parity');
+    }
+    if (options.siWarmAttempt) {
+      const done = (async (): Promise<SelfImplementJobDone> => {
+        let attempt: SiWarmChildAttempt;
+        try {
+          const acquired = await options.siWarmAttempt!(input);
+          if (!acquired) {
+            // No lease was fenced: use the existing one-shot Job path.
+            const { siWarmAttempt: _unused, siWarmHostPostprocess: _postprocess, ...coldOptions } = options;
+            return podSelfImplementSpawn(coldOptions)(input).done;
+          }
+          attempt = acquired;
+        }
+        catch (error) {
+          // A lost exec reply may conceal an already opened PR. Never start another child here.
+          const message = error instanceof Error ? error.message : String(error);
+          debug.log('pod.reuse', 'attempt-unavailable', { spaceId: input.spaceId, reason: message }, { level: 'warn' });
+          return { exitCode: 1, output: '', error: { code: 'si-warm-reconcile-only', message } };
+        }
+        let transport: Awaited<ReturnType<typeof executeSiWarmTransport>>;
+        try {
+          transport = await executeSiWarmTransport({ command: attempt.command,
+            pod: attempt.transport.pod, runner: attempt.transport.runner,
+            leaseFenced: attempt.leaseFenced, payload: attempt.payload,
+            credentialBundle: attempt.credentialBundle, now: attempt.transport.now });
+        } catch (error) {
+          const message = error instanceof Error ? error.message : String(error);
+          try { await attempt.quarantineUnknown('transport-exception'); }
+          catch (quarantineError) {
+            // Both failures must survive: the first transport error names the cause, the
+            // quarantine error names the unfinished disposition. Record the judgement.
+            const quarantineMessage = quarantineError instanceof Error ? quarantineError.message : String(quarantineError);
+            const combined = `transport:${message}; quarantine:${quarantineMessage}`;
+            try { writeWarmLedger({ runId: attempt.command?.runId ?? input.spaceId,
+              event: 'pod-reuse-quarantine-failed',
+              data: { spaceId: input.spaceId, workerId: attempt.command?.workerId ?? null,
+                leaseId: attempt.command?.leaseId ?? null, reason: combined } }); }
+            catch (ledgerError) { debug.log('pod.reuse', 'ledger-unavailable', { spaceId: input.spaceId,
+              event: 'pod-reuse-quarantine-failed', reason: ledgerError instanceof Error ? ledgerError.message : String(ledgerError) }, { level: 'warn' }); }
+            debug.log('pod.reuse', 'quarantine-failed', { spaceId: input.spaceId, reason: combined }, { level: 'error' });
+            return { exitCode: 1, output: '', error: { code: 'si-warm-worker-state-unknown', message: combined } };
+          }
+          // The quarantine is confirmed: record the settled disposal (fail-soft — the
+          // disposition survives a ledger write failure) before the reconcile-only return.
+          try { writeWarmLedger({ runId: attempt.command?.runId ?? input.spaceId,
+            event: 'pod-reuse-quarantined',
+            data: { spaceId: input.spaceId, workerId: attempt.command?.workerId ?? null,
+              leaseId: attempt.command?.leaseId ?? null, reason: 'transport-exception' } }); }
+          catch (ledgerError) { debug.log('pod.reuse', 'ledger-unavailable', { spaceId: input.spaceId,
+            event: 'pod-reuse-quarantined', reason: ledgerError instanceof Error ? ledgerError.message : String(ledgerError) }, { level: 'warn' }); }
+          return { exitCode: 1, output: '', error: { code: 'si-warm-reconcile-only', message } };
+        }
+        const validation = transport.boundary === 'exec-attempted'
+          ? assessSiWarmReply(attempt.command, transport.reply, transport.bytes,
+            attempt.payload, attempt.credentialBundle)
+          : undefined;
+        const next = decideSiWarmNextStep({ boundary: transport.boundary,
+          leaseFenced: attempt.leaseFenced, ...(validation ? { validation } : {}) });
+        debug.log('pod.reuse', 'admission-decision', { spaceId: input.spaceId, boundary: transport.boundary,
+          next: next.next, reason: transport.reason, validationReason: transport.validationReason ?? null });
+        if (next.next === 'cold-job' && transport.boundary === 'not-entered' && attempt.leaseFenced) {
+          const { siWarmAttempt: _unused, ...coldOptions } = options;
+          // The acquired lease must not silently ride along into a cold Job: dispose it first,
+          // record the disposition, and refuse to start the cold Job when disposal fails.
+          const coldLease = attempt.command ? { workerId: attempt.command.workerId,
+            podUid: attempt.command.podUid, leaseId: attempt.command.leaseId,
+            generation: attempt.command.generation, key: attempt.command.key,
+            sourceSha: attempt.command.sourceSha } : null;
+          if (coldLease) {
+            const recordColdDisposition = (event: string, action: string, residue: Record<string, unknown> = {}) => {
+              debug.log('pod.reuse', event, { spaceId: input.spaceId, workerId: coldLease.workerId,
+                leaseId: coldLease.leaseId, action, reason: transport.reason, ...residue });
+              try { writeWarmLedger({ runId: attempt.command?.runId ?? input.spaceId, event,
+                data: { spaceId: input.spaceId, workerId: coldLease.workerId, leaseId: coldLease.leaseId,
+                  action, reason: transport.reason, ...residue } }); }
+              catch (error) { debug.log('pod.reuse', 'ledger-unavailable', { spaceId: input.spaceId, event,
+                reason: error instanceof Error ? error.message : String(error) }, { level: 'warn' }); }
+            };
+            try {
+              // The acquired lease is disposed by the same eligibility standard as the
+              // entered path: process count zero, pinned-source git reset/clean/status,
+              // credential count zero, and an observable return decision — before the
+              // lease can go back into the warm pool or a cold Job starts.
+              const returned = await cleanAndReturnChildPod(coldLease, { ...attempt.cleanup,
+                observe: (event, data) => {
+                  debug.log('pod.reuse', event, { spaceId: input.spaceId, ...data },
+                    { level: event === 'return-decision'
+                      && ((data as { outcome?: string }).outcome === 'eligible'
+                        || (data as { outcome?: string }).outcome === 'returned') ? 'info' : 'warn' });
+                  attempt.cleanup.observe(event, data);
+                  // A ledger write failure is an observation failure: the settled return
+                  // or quarantine disposition must survive it (fail-soft after the decision).
+                  try { writeWarmLedger({ runId: attempt.command?.runId ?? input.spaceId,
+                    event: `pod-reuse-${event}`,
+                    data: { spaceId: input.spaceId, ...data } }); }
+                  catch (ledgerError) { debug.log('pod.reuse', 'ledger-unavailable', { spaceId: input.spaceId,
+                    runId: attempt.command?.runId ?? input.spaceId, event: `pod-reuse-${event}`,
+                    reason: ledgerError instanceof Error ? ledgerError.message : String(ledgerError) },
+                    { level: 'warn' }); }
+                } });
+              recordColdDisposition('pod-reuse-cold-fallback-dispose', returned.outcome,
+                { dispositionReason: returned.reason });
+            } catch (error) {
+              const message = error instanceof Error ? error.message : String(error);
+              try { await attempt.cleanup.quarantine(coldLease, { clean: false, reason: 'cold-fallback-dispose-failed', observedResidue: null }); }
+              catch (quarantineError) {
+                const quarantineMessage = quarantineError instanceof Error ? quarantineError.message : String(quarantineError);
+                recordColdDisposition('pod-reuse-cold-fallback-dispose-failed', 'quarantine-failed',
+                  { error: `disposal:${message}; quarantine:${quarantineMessage}` });
+                return { exitCode: 1, output: '', error: { code: 'si-warm-worker-state-unknown',
+                  message: `disposal:${message}; quarantine:${quarantineMessage}` } };
+              }
+              recordColdDisposition('pod-reuse-cold-fallback-dispose-failed', 'quarantined', { error: message });
+              return { exitCode: 1, output: '', error: { code: 'si-warm-worker-state-unknown', message } };
+            }
+          }
+          return podSelfImplementSpawn(coldOptions)(input).done;
+        }
+        const command = attempt.command;
+        const lease = command && { workerId: command.workerId, podUid: command.podUid,
+          leaseId: command.leaseId, generation: command.generation, key: command.key,
+          sourceSha: command.sourceSha };
+        const recordQuarantine = (event: string, reason: string, residue: Record<string, unknown> = {}) => {
+          debug.log('pod.reuse', event, { spaceId: input.spaceId, workerId: command?.workerId ?? null,
+            leaseId: command?.leaseId ?? null, reason, ...residue }, { level: 'warn' });
+          try { writeWarmLedger({ runId: command?.runId ?? input.spaceId, event,
+            data: { spaceId: input.spaceId, workerId: command?.workerId ?? null,
+              leaseId: command?.leaseId ?? null, reason, ...residue } }); }
+          catch (error) { debug.log('pod.reuse', 'ledger-unavailable', { spaceId: input.spaceId,
+            event, reason: error instanceof Error ? error.message : String(error) }, { level: 'warn' }); }
+        };
+        const retireLease = async (reason: string) => {
+          recordQuarantine('pod-reuse-quarantine-intent', reason);
+          if (!lease) {
+            try { await attempt.quarantineUnknown(reason); }
+            catch (error) {
+              // The unsettled quarantine is an account of its own: keep both the
+              // primary path reason and the quarantine cause in the run ledger,
+              // then let the caller surface the unknown worker state.
+              const message = error instanceof Error ? error.message : String(error);
+              recordQuarantine('pod-reuse-quarantine-failed', `${reason}; quarantine:${message}`);
+              throw error;
+            }
+            recordQuarantine('pod-reuse-quarantined', reason);
+            return;
+          }
+          // An uncertain exec may still be running. Keep it fenced and revoke its run credentials.
+          let processRemaining: number | null = null;
+          let credentialRemaining: number | null = null;
+          try { processRemaining = (await attempt.cleanup.stopChildProcesses(lease)).remaining; }
+          catch (error) { debug.log('pod.reuse', 'process-stop-failed', { spaceId: input.spaceId,
+            reason: error instanceof Error ? error.message : String(error) }, { level: 'warn' }); }
+          try { credentialRemaining = (await attempt.cleanup.removeRunCredentials(lease)).remaining; }
+          catch (error) { debug.log('pod.reuse', 'credential-revoke-failed', { spaceId: input.spaceId,
+            reason: error instanceof Error ? error.message : String(error) }, { level: 'warn' }); }
+          const observedResidue = [processRemaining, credentialRemaining]
+            .filter((value): value is number => typeof value === 'number'
+              && Number.isSafeInteger(value) && value >= 0)
+            .reduce((sum, value) => sum + value, 0);
+          try {
+            await attempt.cleanup.quarantine(lease, { clean: false, reason,
+              observedResidue: observedResidue > 0 ? observedResidue : null });
+          } catch (error) {
+            // The lease stays unfenced and the worker state unknown: record the
+            // unsettled disposal (primary reason plus the quarantine cause)
+            // before the caller reports the unknown worker state.
+            const message = error instanceof Error ? error.message : String(error);
+            recordQuarantine('pod-reuse-quarantine-failed', `${reason}; quarantine:${message}`);
+            throw error;
+          }
+          recordQuarantine('pod-reuse-quarantined', reason, { processRemaining, credentialRemaining });
+        };
+        if (next.next !== 'adopt-warm' || !transport.measured || !command
+          || !transport.reply || !transport.bytes) {
+          const reconcileDisposition = transport.verifiedBytesForReconcile
+            ? parseSelfImplementJson(new TextDecoder().decode(transport.verifiedBytesForReconcile.terminal))
+            : null;
+          const hostDisposition = reconcileDisposition ? (({ worktreePath: _podOnly, ...host }) => host)(reconcileDisposition) : null;
+          let quarantineError: string | undefined;
+          try { await retireLease(validation?.reason ?? 'response-unknown'); }
+          catch (error) { debug.log('pod.reuse', 'quarantine-failed', { spaceId: input.spaceId,
+            reason: error instanceof Error ? error.message : String(error) }, { level: 'error' });
+            quarantineError = error instanceof Error ? error.message : String(error); }
+          return { exitCode: 1, output: '',
+            ...(hostDisposition ? { disposition: hostDisposition } : {}),
+            error: { code: quarantineError
+            || (transport.quarantineWorker && !transport.quarantineRecorded)
+            ? 'si-warm-worker-state-unknown' : 'si-warm-reconcile-only',
+            message: `si-v1 exec may have run; reconcile before retry (${transport.reason})${transport.quarantineError ? `; transport quarantine: ${transport.quarantineError}` : ''}${quarantineError ? `; worker-state-unknown: ${quarantineError}` : ''}` } };
+        }
+        const terminal = new TextDecoder().decode(transport.bytes.terminal);
+        const disposition = parseSelfImplementJson(terminal);
+        if (!disposition) {
+          let quarantineError: string | undefined;
+          try { await retireLease('terminal-disposition-unreadable'); }
+          catch (error) { debug.log('pod.reuse', 'quarantine-failed', { spaceId: input.spaceId,
+            reason: error instanceof Error ? error.message : String(error) }, { level: 'error' });
+            quarantineError = error instanceof Error ? error.message : String(error); }
+          return { exitCode: 1, output: '', error: { code: quarantineError
+            ? 'si-warm-worker-state-unknown' : 'si-warm-terminal-unreadable',
+            message: quarantineError ?? 'validated si-v1 terminal was not a self-implement disposition' } };
+        }
+        try { await attempt.adopt(command, transport.reply, transport.bytes); }
+        catch (error) {
+          const message = error instanceof Error ? error.message : String(error);
+          let quarantineError: string | undefined;
+          try { await retireLease('adopt-failed'); }
+          catch (quarantineFailure) { debug.log('pod.reuse', 'quarantine-failed', { spaceId: input.spaceId,
+            reason: quarantineFailure instanceof Error ? quarantineFailure.message : String(quarantineFailure) }, { level: 'error' });
+            quarantineError = quarantineFailure instanceof Error ? quarantineFailure.message : String(quarantineFailure); }
+          debug.log('pod.reuse', 'adopt-failed', { spaceId: input.spaceId, reason: message }, { level: 'warn' });
+          return { exitCode: 1, output: '', disposition, error: { code: quarantineError
+            ? 'si-warm-worker-state-unknown' : 'si-warm-reconcile-only', message: quarantineError ?? message } };
+        }
+        let returnOutcome: 'returned' | 'quarantined' = 'quarantined';
+        let workerStateUnknown: string | undefined;
+        try {
+          const returned = await cleanAndReturnChildPod(lease!, { ...attempt.cleanup,
+            observe: (event, data) => {
+              debug.log('pod.reuse', event, { spaceId: input.spaceId, ...data },
+                { level: event === 'return-decision' && (data.outcome === 'eligible' || data.outcome === 'returned') ? 'info' : 'warn' });
+              attempt.cleanup.observe(event, data);
+              // The lease disposition is already settled by the time this callback runs; the warm
+              // ledger is an observation of it. A ledger write failure must stay an observation
+              // failure — escaping here would quarantine a lease that was already returned.
+              try { writeWarmLedger({ runId: command.runId, event: `pod-reuse-${event}`,
+                data: { spaceId: input.spaceId, ...data } }); }
+              catch (error) { debug.log('pod.reuse', 'ledger-unavailable', { spaceId: input.spaceId, runId: command.runId,
+                event: `pod-reuse-${event}`, reason: error instanceof Error ? error.message : String(error) }, { level: 'warn' }); }
+            } });
+          returnOutcome = returned.outcome;
+        } catch (error) {
+          workerStateUnknown = error instanceof Error ? error.message : String(error);
+          debug.log('pod.reuse', 'return-unavailable', { spaceId: input.spaceId,
+            reason: workerStateUnknown }, { level: 'error' });
+          // The inner return/quarantine result is unclear: quarantine the lease explicitly,
+          // and only a second quarantine failure leaves the worker state unknown.
+          try {
+            await attempt.quarantineUnknown(`return-quarantine-unavailable:${workerStateUnknown}`);
+            try { writeWarmLedger({ runId: command!.runId, event: 'pod-reuse-quarantined',
+              data: { spaceId: input.spaceId, workerId: command!.workerId, leaseId: command!.leaseId,
+                reason: `return-quarantine-unavailable:${workerStateUnknown}` } }); }
+            catch { /* ledger loss must not mask the quarantine outcome */ }
+            // The explicit quarantine settled the disposal: the caller result must
+            // account for it as quarantined instead of claiming an unknown state.
+            workerStateUnknown = undefined;
+          } catch (quarantineError) {
+            const quarantineMessage = quarantineError instanceof Error ? quarantineError.message : String(quarantineError);
+            workerStateUnknown = `return:${workerStateUnknown}; quarantine:${quarantineMessage}`;
+            try { writeWarmLedger({ runId: command!.runId, event: 'pod-reuse-quarantine-failed',
+              data: { spaceId: input.spaceId, workerId: command!.workerId, leaseId: command!.leaseId,
+                reason: workerStateUnknown } }); }
+            catch { debug.log('pod.reuse', 'ledger-unavailable', { spaceId: input.spaceId,
+              event: 'pod-reuse-quarantine-failed', reason: workerStateUnknown }, { level: 'warn' }); }
+          }
+        }
+        const log = new TextDecoder().decode(transport.bytes.log);
+        // Pod checkout paths cannot be used by the host supervisor.
+        const { worktreePath: _podOnly, ...hostDisposition } = disposition;
+        if (workerStateUnknown) return { exitCode: 1, output: log.slice(-4096), disposition: hostDisposition,
+          error: { code: 'si-warm-worker-state-unknown', message: workerStateUnknown } };
+        debug.log('pod.reuse', 'child-result', { spaceId: input.spaceId, workerId: command.workerId,
+          leaseId: command.leaseId, returnOutcome, stage: disposition.stage ?? null });
+        try {
+          return await options.siWarmHostPostprocess!({ exitCode: transport.reply.exitCode,
+            output: log.slice(-4096), disposition: hostDisposition }, attempt, input);
+        } catch (error) {
+          const message = error instanceof Error ? error.message : String(error);
+          debug.log('pod.reuse', 'host-postprocess-failed', { spaceId: input.spaceId,
+            reason: message }, { level: 'error' });
+          return { exitCode: 1, output: log.slice(-4096), disposition: hostDisposition,
+            error: { code: 'si-warm-host-postprocess-failed', message } };
+        }
+      })();
+      return { address: `self-impl:${input.spaceId}`, done };
+    }
     const name = podJobName(input.spaceId);
     let parentGoal: string | undefined;
     let parentGoalUnreadable = false;
@@ -1599,12 +2052,13 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         const jobArgs = zaiRoute === 'openrouter' ? zaiOverflowChildArgs(args, ZAI_OPENROUTER_FALLBACK_MODEL) : args;
         const grok = options.provider === 'grok';
         const openrouter = options.provider === 'openrouter' || zaiRoute === 'openrouter';
+        const openGateway = options.provider === 'opengateway';
         const anthropic = options.provider === 'anthropic';
         const bedrockChild = options.provider === 'bedrock';
         const zaiChild = zaiRoute === 'zai';
         /** 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 || anthropic || bedrockChild || zaiChild;
-        const plannedAccount = retryAccount ?? (grok ? 'grok' : openrouter ? 'openrouter' : anthropic ? 'anthropic' : bedrockChild ? 'bedrock' : zaiChild ? 'glm' : options.accountBroker?.() ?? options.account ?? 'team');
+        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');
         debug.log('self-implement.pod', 'account', { spaceId: input.spaceId, account: plannedAccount, brokered: Boolean(options.accountBroker) });
         const plannedCodexAccounts = grok || apiKeyChild || !options.accountBroker || !options.rotationAccounts ? undefined : [plannedAccount, ...options.rotationAccounts.filter((candidate) => candidate !== plannedAccount && candidate !== failedAccount)];
         if (plannedCodexAccounts && !options.rotationAccounts!.includes(plannedAccount)) throw new Error(`pod: 배분 계정 ${plannedAccount} 이 회전 계획에 없다`);
@@ -1647,6 +2101,17 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         }) : 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 openGatewayEnvKey = openGateway ? env.OPENGATEWAY_API_KEY?.trim() : undefined;
+        const openGatewayCachedKey = openGateway ? (options.readKeyCache ?? defaultReadKeyCache)('OPENGATEWAY_API_KEY')?.trim() : undefined;
+        if (openGatewayEnvKey && openGatewayCachedKey && openGatewayEnvKey !== openGatewayCachedKey)
+          throw new Error('pod: opengateway env와 키 캐시가 충돌 — Pod 발사 거부');
+        const openGatewayHostConfig = openGateway ? (options.openGatewayConfig ?? getUserConfig)() : undefined;
+        const openGatewayConfiguredKeys = openGatewayHostConfig ? configuredOpenGatewayKeys(openGatewayHostConfig.llm) : [];
+        if (openGatewayConfiguredKeys.length > 1 || openGatewayConfiguredKeys.some((key) =>
+          (openGatewayEnvKey && openGatewayEnvKey !== key) || (openGatewayCachedKey && openGatewayCachedKey !== key)))
+          throw new Error('pod: opengateway 호스트 설정과 env/키 캐시가 충돌 — Pod 발사 거부');
+        const openGatewayKey = openGatewayEnvKey || openGatewayCachedKey || openGatewayConfiguredKeys[0];
+        if (openGateway && !openGatewayKey) throw new Error('pod: Pod 에 opengateway 키 없음 — 호스트 키 캐시 또는 OPENGATEWAY_API_KEY 필요');
         // POD-ANTHROPIC-PROVIDER — 제품 자격 해석(`getAnthropicApiKey` · 키 캐시 → env)으로 읽는다. 못 읽으면 Pod 를 안 띄운다(fail-closed).
         //   ⛔ 값은 로그·오류 문면에 안 싣는다 — «있었다» 만.
         const anthropicKey = anthropic
@@ -1717,7 +2182,7 @@ 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'] : []), ...(anthropic ? ['ANTHROPIC_API_KEY'] : [])])].filter((key) => key !== 'ELANOUS_LIVE_DETAIL_UNTIL'
+        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'
           && 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
@@ -1863,7 +2328,7 @@ 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 === 'ANTHROPIC_API_KEY' && anthropic ? anthropicKey : env[k] ?? (options.readKeyCache ?? defaultReadKeyCache)(k);
+        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 normalizedFallback = normalizeFallbackChain(hostFallbackNames);
         let fallbackSteps = normalizedFallback.chain;
@@ -1932,6 +2397,10 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         //   🩸 종전엔 여기서 delete 부터 해서, 재개가 원격에서 멀쩡히 돌던 Job 을 죽였다. 실패로 끝난 Job 만 지우고 다시 만든다.
         // ☸️ 노드 레지스트리에 이 판이 있으면 그것을 pull 한다(델타 · 대표 2026-09-26) — 라벨 판정은 로컬 이미지 이름으로 한다.
         const jobImage = member?.imageRef ?? image;
+        // A pool member may pull a different image than the host's local one.
+        // The local Docker label cannot prove that member image's commit.
+        const localImageCommit = options.imageCommit !== undefined ? options.imageCommit : options.kubectl ? null : podImageFreshness({ image }).imageCommit;
+        const jobImageCommit = jobImage === image ? localImageCommit : null;
         const launchRunId = retryAccount || oomRetried || ghLoginRetried ? mintRunId() : childRunId;
         let liveChildRunId = launchRunId;
         // TA-POD-WARMBOOT-PARITY — the id the followed Job prints in its result marker (null = wait on the condition only).
@@ -2167,7 +2636,22 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
           debug.log('self-implement.pod', fit.fitted ? 'grok-deadline-fitted' : 'grok-deadline-kept', { job: name, requestedSeconds: jobDeadlineSeconds, deadlineSeconds: fit.deadlineSeconds, availableSeconds: fit.availableSeconds, relay: Boolean(credentialRelay), marginMs: POD_GROK_EXPIRY_MARGIN_MS });
           jobDeadlineSeconds = fit.deadlineSeconds;
         }
-        const job = podJobManifest({ name, namespace, fallbackChain, ...(resultMarkerLine ? { resultMarkerLine } : {}), image: jobImage, workIdentity, ...(env.ELANOUS_TASK_BOUND_PR && /^[1-9]\d*$/.test(env.ELANOUS_TASK_BOUND_PR) && Number.isSafeInteger(Number(env.ELANOUS_TASK_BOUND_PR)) ? { boundPrNumber: Number(env.ELANOUS_TASK_BOUND_PR) } : {}), ...(member?.imageRef ? { imagePullPolicy: 'IfNotPresent' as const } : {}), repoUrl, ...(options.source ? { source: options.source } : {}), ...(options.repairCommitOnly ? { repairCommitOnly: options.repairCommitOnly } : {}), ...(hostMirror ? { hostMirror } : {}), args: jobArgs, passEnv: jobPassEnv, deadlineSeconds: jobDeadlineSeconds, ...(goalDoc ? { goalDoc } : env.ELANOUS_POD_AUTHOR_ON_POD === '1' && !shard ? { authorSentence: true, ...(env.ELANOUS_POD_AUTHOR_GRADE === 'lite' || env.ELANOUS_POD_AUTHOR_GRADE === 'full' ? { authorGrade: env.ELANOUS_POD_AUTHOR_GRADE } : {}) } : {}), runId: launchRunId, ...(parentRunId ? { parentRunId } : {}), ...(jobArmEnv ? { armEnv: jobArmEnv } : {}), hostId: resolveHostId(env), skillEnvs: Object.keys(skillEnvs), memoryLimit, memoryRequest, imageCommit: options.imageCommit !== undefined ? options.imageCommit : options.kubectl ? null : podImageFreshness({ image }).imageCommit, ...(grok ? { grokCredential: 'grokAuth' in creds && creds.grokAuth ? 'subscription' as const : 'api_key' as const } : {}), ...(codexAccounts ? { codexAccounts } : {}), ...(hostRefresh ? { appCredential: true } : {}), execution: { key: executionKey, attempt: oomRetried ? 2 : 1 }, hostLeaseAdmitted: !!releaseAdmission, ...(roleCodexCredential ? { reviewerCodexAuth: true } : {}), ...(bedrockSpec ? { bedrock: bedrockSpec } : {}), ...(zaiSpec ? { zai: zaiSpec } : {}), ...(zaiFallbackSpec ? { zaiFallback: zaiFallbackSpec } : {}) });   // kubectl 주입(=시험)이면 docker 를 부르지 않는다
+        // POD-LAUNCH-PROVENANCE — fail-closed: a si-task Job without its ★ identity is never applied.
+        let provenance: PodProvenanceMetadata;
+        try {
+          let version: string | undefined;
+          try { version = packageVersion(); } catch { version = undefined; }
+          provenance = podProvenanceMetadata(siTaskPodProvenance({ env, runId: launchRunId, ...(parentRunId ? { parentRunId } : {}), workIdentity,
+            requestedAt: new Date((options.now ?? Date.now)()).toISOString(), feature: input.feature, launchHost: resolveHostId(env),
+            commit: seedSource.kind === 'commit' ? seedSource.sha : seedCommit ?? jobImageCommit, ...(version ? { version } : {}),
+            ...(memoryRequest ? { memReq: memoryRequest } : {}) }));
+        } catch (error) {
+          const message = error instanceof Error ? error.message : String(error);
+          debug.log('pod.provenance', 'si-task-refused', { job: name, reason: message }, { level: 'warn' });
+          cleanupSecret();
+          return { exitCode: 1, output: '', error: { code: 'pod-provenance', message } };
+        }
+        const job = podJobManifest({ provenance, name, namespace, fallbackChain, ...(resultMarkerLine ? { resultMarkerLine } : {}), image: jobImage, workIdentity, ...(env.ELANOUS_TASK_BOUND_PR && /^[1-9]\d*$/.test(env.ELANOUS_TASK_BOUND_PR) && Number.isSafeInteger(Number(env.ELANOUS_TASK_BOUND_PR)) ? { boundPrNumber: Number(env.ELANOUS_TASK_BOUND_PR) } : {}), ...(member?.imageRef ? { imagePullPolicy: 'IfNotPresent' as const } : {}), repoUrl, ...(options.source ? { source: options.source } : {}), ...(options.repairCommitOnly ? { repairCommitOnly: options.repairCommitOnly } : {}), ...(hostMirror ? { hostMirror } : {}), args: jobArgs, passEnv: jobPassEnv, deadlineSeconds: jobDeadlineSeconds, ...(goalDoc ? { goalDoc } : env.ELANOUS_POD_AUTHOR_ON_POD === '1' && !shard ? { authorSentence: true, ...(env.ELANOUS_POD_AUTHOR_GRADE === 'lite' || env.ELANOUS_POD_AUTHOR_GRADE === 'full' ? { authorGrade: env.ELANOUS_POD_AUTHOR_GRADE } : {}) } : {}), runId: launchRunId, ...(parentRunId ? { parentRunId } : {}), ...(jobArmEnv ? { armEnv: jobArmEnv } : {}), hostId: resolveHostId(env), skillEnvs: Object.keys(skillEnvs), memoryLimit, memoryRequest, imageCommit: jobImageCommit, ...(grok ? { grokCredential: 'grokAuth' in creds && creds.grokAuth ? 'subscription' as const : 'api_key' as const } : {}), ...(codexAccounts ? { codexAccounts } : {}), ...(hostRefresh ? { appCredential: true } : {}), execution: { key: executionKey, attempt: oomRetried ? 2 : 1 }, hostLeaseAdmitted: !!releaseAdmission, ...(roleCodexCredential ? { reviewerCodexAuth: true } : {}), ...(bedrockSpec ? { bedrock: bedrockSpec } : {}), ...(zaiSpec ? { zai: zaiSpec } : {}), ...(zaiFallbackSpec ? { zaiFallback: zaiFallbackSpec } : {}) });   // kubectl 주입(=시험)이면 docker 를 부르지 않는다
         const carriedBranch = goalDoc ? 'goal-doc' as const : env.ELANOUS_POD_AUTHOR_ON_POD === '1' && !shard ? 'author' as const : undefined;
         const carriedChildLlm = carriedBranch ? podDelegatedChildLlm(jobArgs) : undefined;
         jobApplyStartedAt = Date.now();
@@ -2175,6 +2659,15 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         zaiPendingApply.delete(name);   // apply 뒤엔 Job 라벨이 센다(성공) · 실패면 셀 것이 없다
         if (a.status !== 0) { cleanupSecret(); return { exitCode: 1, output: a.stderr, error: { code: 'pod-apply', message: a.stderr.trim() } }; }
         releaseAdmission?.applied?.(name, context, namespace);
+        const imageFacts = { job: name, childRunId: liveChildRunId, image: jobImage, imageCommit: jobImageCommit, context };
+        // POD-LAUNCH-PROVENANCE — append-only «started» row: who · why · when, on the parent's existing run ledger.
+        const startedRow = { job: name, run: launchRunId, attempt: oomRetried ? 2 : 1, provenance: provenanceRowFromAnnotations(provenance.annotations) };
+        try { appendRunLedgerEntry({ runId: ledgerRunId, event: POD_LAUNCH_STARTED_EVENT, timestamp: new Date((options.now ?? Date.now)()).toISOString(), data: startedRow }, ledgerDir); }
+        catch (error) { debug.log('pod.provenance', 'history-unavailable', { job: name, row: 'started', reason: error instanceof Error ? error.message : String(error) }, { level: 'warn' }); }
+        debug.log('pod.provenance', 'job-started', startedRow);
+        try { appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-job-image', data: imageFacts }, ledgerDir); }
+        catch (error) { debug.log('self-implement.pod', 'job-image-ledger-unavailable', { job: name, reason: error instanceof Error ? error.message : String(error) }, { level: 'warn' }); }
+        debug.log('self-implement.pod', 'job-image', imageFacts);
         // The injected observer does not acquire a production lease. The gate consumer
         // must compare the Job result and explicitly finalize before enabling replay.
         if (!oomRetried && input.warmWorkerCommand && options.warmPodRequest) {
@@ -2241,11 +2734,14 @@ 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') } : {}), ...(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, ...(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 } : {}) });
         let state: 'complete' | 'failed' | 'aborted' = 'failed';
         let failedReason = '';
         let containerReason: string | null = null;
         let containerExitCode: number | null = null;
+        // 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;
         // 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).
@@ -2253,11 +2749,34 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         // ⭐ 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;
+        let imageSnapshotRecorded = false;
+        let terminalImageRecorded = false;
+        const recordPodImage = (final: boolean): void => {
+          if (final ? terminalImageRecorded : imageSnapshotRecorded) return;
+          const observed = readJobPodImage(kubectl, namespace, name, lifecycleJobUid);
+          if (!final && !observed.podName) return;
+          const append = (isFinal: boolean): void => {
+            const data = { job: name, childRunId: liveChildRunId, attempt: oomRetried ? 2 : 1,
+              image: jobImage, imageCommit: jobImageCommit, context, ...observed, final: isFinal };
+            try {
+              appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-image-digest', data }, ledgerDir);
+              if (isFinal) terminalImageRecorded = true;
+              else imageSnapshotRecorded = true;
+            } catch (error) {
+              debug.log('self-implement.pod', 'pod-image-digest-ledger-unavailable', {
+                job: name, final: isFinal, reason: error instanceof Error ? error.message : String(error) }, { level: 'warn' });
+            }
+            debug.log('self-implement.pod', 'pod-image-digest', data);
+          };
+          if (final && !imageSnapshotRecorded && observed.podName) append(false);
+          append(final);
+        };
         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();
         for (;;) {
           if (input.signal?.aborted) {
+            recordPodImage(true);
             // METER-POD-ROLLUP-GAP — Job 삭제 «전»에 로그를 한 번 거둔다: PARTIAL 줄이 삭제와 함께 사라지면 사용량이 0 처럼 보인다.
             try {
               const captured = kubectl(['-n', namespace, 'logs', `job/${name}`, '-c', 'child', '--tail=400']);
@@ -2267,16 +2786,24 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
             state = 'aborted';
             break;
           }
+          if (!imageSnapshotRecorded) recordPodImage(false);
           const g = kubectl(['-n', namespace, 'get', 'job', name, '-o', 'jsonpath={.status.conditions[*].type}']);
           const types = g.stdout;
           if (/Complete|SuccessCriteriaMet/.test(types)) { releaseAdmission?.observed?.(); state = 'complete'; break; }
           if (/Failed|FailureTarget/.test(types)) {
             releaseAdmission?.observed?.();
             state = 'failed';
-            const reason = kubectl(['-n', namespace, 'get', 'job', name, '-o', 'jsonpath={.status.conditions[?(@.type=="Failed")].reason}']);
-            failedReason = reason.status === 0 ? reason.stdout.trim() : '';
+            // One Job read serves both: column one is the classification reason, all three the capture (no re-read a GC could empty).
+            let jobRead: { status: number | null; stdout: string } | null = null;
+            let jobReadError: unknown;
+            try { jobRead = kubectl(['-n', namespace, 'get', 'job', name, '-o', `jsonpath=${POD_TERMINATION_JOB_JSONPATH}`]); }
+            catch (error) { jobReadError = error; }
+            failedReason = jobRead?.status === 0 ? (jobRead.stdout.split('\t')[0] ?? '').trim() : '';
+            // One Pods read serves both: its first three columns are the classification layout, the rest the termination capture.
+            let podsRead: { status: number | null; stdout: string } | null = null;
             try {
-              const pods = kubectl(['-n', namespace, 'get', 'pods', '-l', `job-name=${name}`, '-o', 'jsonpath={range .items[*]}{.metadata.creationTimestamp}{"\\t"}{range .status.containerStatuses[?(@.name=="child")]}{.state.terminated.reason}{"\\t"}{.state.terminated.exitCode}{end}{"\\n"}{end}']);
+              const pods = kubectl(['-n', namespace, 'get', 'pods', '-l', `job-name=${name}`, '-o', `jsonpath=${POD_TERMINATION_PODS_JSONPATH}`]);
+              podsRead = pods;
               if (pods.status === 0 && pods.stdout) {
                 const rows = pods.stdout.trimEnd().split('\n').map((line) => line.split('\t'));
                 const latest = rows.filter(([created]) => created && !Number.isNaN(Date.parse(created)))
@@ -2289,6 +2816,14 @@ 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 });
+            if (jobReadError !== undefined) {
+              // Today's outcome stays (the throw ends the spawn as pod-error); the capture is in the ledger first.
+              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' });
+              throw jobReadError;
+            }
             break;
           }
           // TA-POD-WARMBOOT-PARITY: the condition is not there yet — the child may already be done (k3d condition lag).
@@ -2300,6 +2835,7 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
               state = seen === 0 ? 'complete' : 'failed';
               // 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 });
               debug.log('self-implement.pod', 'result-marker-early', { job: name, waitedMs: Date.now() - waitStartedAt, rc: seen });
               break;
             }
@@ -2342,6 +2878,7 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
           }
           await sleep(options.pollMs ?? 15_000);
         }
+        if (!terminalImageRecorded) recordPodImage(true);
         let logs = '';
         let logTailReason: string | undefined;
         try {
@@ -2521,23 +3058,72 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         }
         const childFailure = state === 'failed' && !oomKilled && failedReason !== 'DeadlineExceeded'
           ? lastPodChildFailure(logs) : null;
+        let childPrFailure: ReturnType<typeof podPrOpenFailure> = null;
+        if (childFailure) {
+          try {
+            const entries = loadRunLedger(liveChildRunId, ledgerDir);
+            const entry = entries?.slice().reverse().find((row) => row.event === 'pr-open-failed');
+            childPrFailure = podPrOpenFailure(entry?.data, childFailure.rawError);
+          } catch { /* child ledger is optional; terminal result remains available */ }
+          childPrFailure ??= podPrOpenFailure(null, childFailure.rawError);
+        }
+        if (childPrFailure && disposition) {
+          disposition.childEvidence = {
+            ...(disposition.childEvidence ?? {}),
+            prFailure: {
+              stage: childPrFailure.prFailureStage,
+              source: childPrFailure.prFailureSource,
+              errorTail: childPrFailure.childErrorTail,
+              ...(childPrFailure.blockingPrNumber ? { blockingPrNumber: childPrFailure.blockingPrNumber } : {}),
+              ...(childPrFailure.candidateCardId ? { candidateCardId: childPrFailure.candidateCardId } : {}),
+              ...(childPrFailure.blockingCardId ? { blockingCardId: childPrFailure.blockingCardId } : {}),
+            },
+          };
+        }
         let noResultDiagnostic: string | null = null;
-        // POD-NORESULT: the Job runs with backoffLimit 0, so any non-zero child exit is «BackoffLimitExceeded» — not a reason to skip the ledger.
-        if (state === 'failed' && containerExitCode !== null && containerExitCode !== 0 && !disposition && !oomKilled && failedReason !== 'DeadlineExceeded') {
+        // POD-NORESULT: a terminal Job without a parsed disposition is incomplete even when the Job condition says Complete.
+        const noResultCandidate = !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';
         }
-        if (childFailure) debug.log('self-implement.pod', 'child-error', { job: name, stage: childFailure.stage, error: childFailure.error }, { compact: { stringMax: 500 } });
+        // 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`.
+        let noResultLogEvidence: Record<string, unknown> | null = null;
+        if (noResultDiagnostic?.includes('stage=unknown')) {
+          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 } });
+          } 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' });
+          }
+        }
+        if (childFailure) debug.log('self-implement.pod', 'child-error', { job: name, stage: childFailure.stage, error: childFailure.error, ...(childPrFailure ?? {}) }, { compact: { stringMax: 500 } });
         if (noResultDiagnostic && !noResultDiagnostic.includes('stage=unknown')) {
           debug.log('self-implement.pod', 'no-result-ledger-diagnostic', { job: name, childRunId: liveChildRunId, diagnostic: noResultDiagnostic }, { compact: { stringMax: 500 } });
         }
+        // POD-LAUNCH-PROVENANCE — append-only «finished» row paired with its started row on job·run.
+        // Keyed on launchRunId like the started row; a reattached Job's inherited child run rides along as childRun.
+        // exitCode stays null when the container's code was not read (never filled in as 0).
+        const finishedRow = { job: name, run: launchRunId, ...(liveChildRunId !== launchRunId ? { childRun: liveChildRunId } : {}),
+          attempt: oomRetried ? 2 : 1, phase: state, exitCode: containerExitCode,
+          reason: failedReason || containerReason || (state === 'complete' ? 'complete' : 'unknown') };
+        try { appendRunLedgerEntry({ runId: ledgerRunId, event: POD_LAUNCH_FINISHED_EVENT, timestamp: new Date((options.now ?? Date.now)()).toISOString(), data: finishedRow }, ledgerDir); }
+        catch (error) { debug.log('pod.provenance', 'history-unavailable', { job: name, row: 'finished', reason: error instanceof Error ? error.message : String(error) }, { level: 'warn' }); }
+        debug.log('pod.provenance', 'job-finished', finishedRow);
         debug.log('self-implement.pod', 'job-finished', { job: name, ...(member ? { context: member.context } : {}), state, containerReason, stage: disposition?.stage ?? null, prUrl: disposition?.prUrl ?? null, childRunId: liveChildRunId, ledgerCompleteness,
+          ...(podTermination ? { podTermination } : {}),
           ...(state === 'failed' && !oomKilled && failedReason !== 'DeadlineExceeded'
             ? { ...(childFailure ? { childStage: childFailure.stage } : disposition?.stage ? { childStage: disposition.stage } : {}),
               // POD-NORESULT: a parsed result row without error text is not a missing result line (UX 10-07 01:01: 28 of 28 exit-2 Jobs printed one).
-              childError: childFailure?.error ?? (disposition?.stage ? 'result-without-error' : 'no-result-line') } : {}) },
-          state === 'failed' && !oomKilled && failedReason !== 'DeadlineExceeded' ? { compact: { stringMax: 500 } } : undefined);
+              childError: childFailure?.error ?? (disposition?.stage ? 'result-without-error' : 'no-result-line'),
+              ...(childPrFailure ?? {}) } : {}) },
+          (state === 'failed' && !oomKilled && failedReason !== 'DeadlineExceeded') ? { compact: { stringMax: 500 } } : undefined);
         // POD-LIFECYCLE-STAGES: one `pod.lifecycle stages` line — clone · mirror · run come from the Pod's own
         //   `ELANOUS_POD_STAGE` markers (SI-POD-STAGE-MARKERS), read from that Pod's full named log. ⛔ No `--tail=400` fallback:
         //   a tail can lose the real `run start` and pair a child-printed look-alike with the real `run end` (review mf) —
@@ -2606,10 +3192,11 @@ 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 record: GoalExecutionRecord = {
             runId: liveChildRunId,
             stage: (state === 'aborted' || !disposition ? 'aborted' : disposition.stage) as GoalExecutionRecord['stage'],
-            outcome: (!disposition ? noResultDiagnostic ? 'abandoned' : 'pod-no-result' : state === 'complete' && disposition.merged ? 'merged' : state === 'complete' && disposition.ok ? 'completed' : 'abandoned') as GoalExecutionRecord['outcome'],
+            outcome: (!disposition ? noResultOutcome : state === 'complete' && disposition.merged ? 'merged' : state === 'complete' && disposition.ok ? 'completed' : 'abandoned') as GoalExecutionRecord['outcome'],
             ok: state === 'complete' && (disposition?.ok ?? false),
             ...(disposition?.prNumber !== undefined ? { prNumber: disposition.prNumber } : {}),
             completedAt: new Date().toISOString(),
@@ -2619,16 +3206,41 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         }
         // The host still has the complete Pod log here. The CLI only retains a short stdout tail,
         // so preserve the parsed child facts in the parent ledger before that tail is returned.
-        if (state === 'failed' || state === 'aborted') {
+        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.
-          try { appendRunLedgerEntry({ runId: ledgerRunId, event: 'pod-child-evidence', data: { childEvidence: disposition?.childEvidence ?? null, childRunId: liveChildRunId, job: name } }, ledgerDir); }
+          const 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' }); }
         }
-        const terminalRecord = classifyPodTerminal({ childRunId: liveChildRunId, state, disposition, env,
-          prBody: options.draftResidue ? undefined : podTerminalPrBody(disposition),
-          goalText: parentGoal ?? input.feature, at: new Date().toISOString() });
-        try { await (options.draftResidue ?? applyPodTerminal)(terminalRecord, { ledgerRunId, ledgerDir }); }
+        let prLookup: OpenPrByBranch | undefined;
+        const terminalBranch = typeof disposition?.branch === 'string' ? disposition.branch.trim() : '';
+        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' }; }
+        }
+        const terminalDisposition = prLookup?.status === 'found' && disposition
+          ? { ...disposition, prNumber: prLookup.prNumber, prUrl: prLookup.prUrl } : disposition;
+        if (prLookup?.status === 'found') debug.log('self-implement.pod', 'pr-terminal-bound-by-branch', {
+          branch: terminalBranch, prNumber: prLookup.prNumber, prUrl: prLookup.prUrl, status: 'found', job: name });
+        else if (prLookup) debug.log('self-implement.pod', 'pr-terminal-branch-lookup', {
+          branch: terminalBranch, status: prLookup.status, reason: prLookup.reason, job: name });
+        const terminalRecord = { ...classifyPodTerminal({ childRunId: liveChildRunId, state, disposition: terminalDisposition, env,
+          prBody: options.draftResidue || prLookup?.status === 'found' ? undefined : podTerminalPrBody(terminalDisposition),
+          goalText: parentGoal ?? input.feature, at: new Date().toISOString() }),
+          ...(prLookup ? { prLookup: prLookup.status === 'found' ? { status: 'found', source: 'branch-lookup' }
+            : { status: prLookup.status, reason: prLookup.reason } } : {}),
+          ...(prLookup?.status === 'found' ? { prNumberSource: 'branch-lookup' } : {}) };
+        try {
+          if (options.draftResidue) await options.draftResidue(terminalRecord, { ledgerRunId, ledgerDir });
+          else if (prLookup?.status === 'found') {
+            // This lookup only repairs the host ledger's PR identity. The draft sweeper owns PR writes.
+            const alreadyRecorded = loadRunLedger(ledgerRunId, ledgerDir)?.some((entry) =>
+              entry.event === 'pr-terminal' && entry.data.childRunId === liveChildRunId);
+            if (!alreadyRecorded) appendRunLedgerEntry({ runId: ledgerRunId, event: 'pr-terminal', data: terminalRecord }, ledgerDir);
+          } else await applyPodTerminal(terminalRecord, { ledgerRunId, ledgerDir });
+        }
         catch (error) { debug.log('draft.residue', 'failed', { childRunId: liveChildRunId, prNumber: terminalRecord.prNumber,
           terminalClass: terminalRecord.terminalClass, owner: terminalRecord.owner, ownerSource: terminalRecord.ownerSource,
           step: 'apply', reason: error instanceof Error ? error.message : String(error) }); }
@@ -2648,9 +3260,15 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
         const finishedDisposition = deadlineExceeded && disposition
           ? { ...disposition, failureClassification: 'run-deadline-exceeded' as const }
           : disposition;
-        const podExitCode = state === 'complete' && disposition?.stage !== 'host-regate-failed' && disposition?.ok !== false ? 0 : 1;
+        // 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,
+          repairArtifactReady, disposition });
         // SCHED-CONTRACT: a failed child must say why outside the Pod, not «no error diagnostic».
-        const podReason = 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;
+        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;
+        const podReason = rawPodReason
+          ? redactSecretText(noResultLogEvidence ? boundedPodLogText(rawPodReason, POD_NO_RESULT_LOG_REASON_MAX_CHARS) : rawPodReason)
+          : undefined;
         if (podReason) debug.log('self-implement.pod', 'failure-reason', { job: name, reason: podReason });
         if (podExitCode === 1) {
           // HARNESS-FULL-GRAPH — 실패 쪽 두 노드: 결과 해석(result-parse) → 수확(salvage, Pod Job 이 push 한 줄로 판정).
@@ -2668,7 +3286,7 @@ export function podSelfImplementSpawn(options: PodSpawnOptions = {}): SelfImplem
                 ? { error: { code: 'pod-gh-login-failed', message: `Job ${name} GitHub 앱 로그인 실패 (container=${containerReason ?? 'unknown'}/7, attempt=${ghLoginRetried ? 2 : 1}) — 새 토큰으로 ${ghLoginRetried ? '1회 재시도했으나 다시 실패' : '재시도 불가'}` } }
               : oomKilled
                 ? { error: { code: 'pod-oom-killed', message: `Job ${name} failed (OOMKilled/${containerExitCode ?? 'unknown'}, memoryLimit=${memoryLimit})${oomRetried || (memoryGi(reattachedMemoryLimit ?? memoryLimit) ?? 0) >= (memoryGi(podMemoryLimitFor(input.feature, { ...env, ELANOUS_POD_MEMORY_TIER: 'high' }).limit) ?? Infinity) ? ` — OOM · ${oomRetried ? retryTier : 'high'} 에서도` : ''}\n${formatLastMemSample(samples.at(-1))}` } }
-                : { error: { code: 'pod-job-failed', message: `Job ${name} failed${failedReason || containerReason ? ` (${[failedReason, containerReason ? `container=${containerReason}/${containerExitCode ?? 'unknown'}` : ''].filter(Boolean).join(', ')})` : ''}${childFailure ? ` — childStage=${childFailure.stage} · childError=${childFailure.error}` : disposition?.stage ? ` — childStage=${disposition.stage} · reason=${podReason}` : ` — childError=no-result-line · reason=${podReason}`}${noResultDiagnostic ? ` · ${noResultDiagnostic}` : ''}` } }
+              : { error: { code: 'pod-job-failed', message: `Job ${name} failed${failedReason || containerReason ? ` (${[failedReason, containerReason ? `container=${containerReason}/${containerExitCode ?? 'unknown'}` : ''].filter(Boolean).join(', ')})` : ''}${childFailure ? ` — childStage=${childFailure.stage} · childError=${childFailure.error}` : disposition?.stage ? ` — childStage=${disposition.stage} · reason=${podReason}` : ` — childError=no-result-line · reason=${podReason}`}${noResultDiagnostic && containerExitCode !== null ? ` · ${noResultDiagnostic}` : ''}` } }
               : podReason && !childFailure?.error ? { error: { code: 'pod-child-failed', message: podReason } } : {}),
           ...(finishedDisposition ? { disposition: finishedDisposition } : {}),
         };
@@ -2736,7 +3354,47 @@ export function recordPodSalvage(logs: string, job: string, log: (category: stri
   return rows.map((row) => row.branch);
 }
 
-function lastPodChildFailure(logs: string): { stage: string; error: string } | null {
+type PodPrOpenFailure = {
+  childErrorTail: string;
+  prFailureStage: 'pr-open-failed';
+  prFailureSource: 'child-ledger' | 'terminal-result';
+  blockingPrNumber?: number;
+  candidateCardId?: string;
+  blockingCardId?: string;
+};
+
+/** Preserve the actionable tail independently of the bounded human error. Never infer a card from a PR number. */
+function podPrOpenFailure(ledger: Record<string, unknown> | undefined | null, terminalError: string): PodPrOpenFailure | null {
+  const ledgerError = typeof ledger?.error === 'string' ? ledger.error : '';
+  // A previous rework round can leave a pr-open-failed row behind. Only a terminal PR failure may consume it.
+  if (!/draft PR 생성 실패|PR (?:gh|guard) 실패|same-cell reuse:/u.test(terminalError)) return null;
+  // The terminal must contain the complete ledger error. A shared prefix such as "same-cell"
+  // cannot distinguish an earlier rework round from the current failed attempt.
+  const matchingLedger = ledgerError.length >= 20 && terminalError.includes(ledgerError);
+  const source = terminalError || ledgerError;
+  const sanitized = redactSecretText(source).replace(/\/home\/[^/\s]+\//gu, '~/');
+  const tail = sanitized.split(/\r\n|\n|\r/u).filter(Boolean).at(-1) ?? sanitized;
+  const terminalHasIds = /(?:blockers=|blockingPr=|candidateCardId=)/u.test(terminalError);
+  const detail = `${terminalError}\n${matchingLedger ? ledgerError : ''}`;
+  const blocker = /(?:blockers=|blockingPr=)\s*#?(\d+)(?::([A-Za-z0-9_-]{1,128}))?/u.exec(detail);
+  const prNumber = blocker ? Number(blocker[1]) : null;
+  const candidate = /candidateCardId=([A-Za-z0-9_-]{1,128})/u.exec(detail)?.[1];
+  const card = blocker?.[2];
+  return {
+    childErrorTail: tail.slice(-240),
+    prFailureStage: 'pr-open-failed',
+    prFailureSource: terminalHasIds || !matchingLedger ? 'terminal-result' : 'child-ledger',
+    ...(prNumber && Number.isSafeInteger(prNumber) ? { blockingPrNumber: prNumber } : {}),
+    ...(candidate && candidate !== 'unknown' ? { candidateCardId: candidate } : {}),
+    ...(card && card !== 'unknown' ? { blockingCardId: card } : {}),
+  };
+}
+
+function lastPodChildFailure(logs: string): { stage: string; error: string; rawError: string } | null {
+  // Keep canonical duplicate-cap attribution while preserving the raw terminal error
+  // used by PR-open failure diagnosis below.
+  const attribution = podChildFailureAttribution(logs);
+  if (!attribution) return null;
   for (const line of logs.split('\n').reverse()) {
     if (!line.trimStart().startsWith('{')) continue;
     let result: unknown;
@@ -2746,14 +3404,65 @@ function lastPodChildFailure(logs: string): { stage: string; error: string } | n
     const terminal = podTerminalRow(row);
     if (!terminal) continue;
     if (terminal.ok !== false || typeof terminal.error !== 'string') return null;
-    const lines = terminal.error.replace(/\/home\/[^/\s]+\//g, '~/').split(/\r\n|\n|\r/);
-    const first = lines[0]!.slice(0, 240);
-    const last = lines.at(-1)!.slice(0, 240);
-    return { stage: terminal.stage, error: first === last ? first : `${first}\n${last}` };
+    if (terminal.stage !== attribution.stage) return null;
+    return { ...attribution, error: redactSecretText(attribution.error), rawError: terminal.error };
   }
   return null;
 }
 
+/** POD-NORESULT-LOG-TAIL: how many container-log lines a failed Pod leaves behind for the parent. */
+export const POD_NO_RESULT_LOG_TAIL_LINES = 80;
+const POD_NO_RESULT_LOG_TAIL_LINE_CHARS = 512;
+const POD_NO_RESULT_LOG_TAIL_MAX_CHARS = 8_192;
+const POD_NO_RESULT_LOG_REASON_MAX_CHARS = 512;
+
+function boundedPodLogText(source: string, maxChars: number): string {
+  const redacted = redactSecretText(source).replace(/[\r\n\t]+/g, ' ').replace(/\s+/g, ' ').trim();
+  return redacted.length > maxChars ? `${redacted.slice(0, maxChars)}…[truncated]` : redacted;
+}
+
+/** 로그 꼬리 — 마지막 N줄만, 한 줄씩 비밀값 마스킹. */
+export function podNoResultLogTailLines(source: string, maxLines: number = POD_NO_RESULT_LOG_TAIL_LINES): string[] {
+  const lines = source.replace(/\r\n/g, '\n').split('\n');
+  while (lines.length && lines[lines.length - 1] === '') lines.pop();
+  const result: string[] = [];
+  let chars = 0;
+  for (const line of lines.slice(-Math.max(0, maxLines)).reverse()) {
+    if (chars >= POD_NO_RESULT_LOG_TAIL_MAX_CHARS) break;
+    const bounded = boundedPodLogText(line, Math.min(POD_NO_RESULT_LOG_TAIL_LINE_CHARS, POD_NO_RESULT_LOG_TAIL_MAX_CHARS - chars));
+    if (!bounded) continue;
+    result.push(bounded);
+    chars += bounded.length;
+  }
+  return result.reverse();
+}
+
+export type PodNoResultLogRead = { tail: string[] } | { unavailable: string };
+
+/**
+ * POD-NORESULT-LOG-TAIL: the terminal Job (`backoffLimit 0`) is collected right after it fails, so the
+ * container log has to be read while the Pod still exists. Never throws — an unreadable log becomes a reason.
+ */
+export function readPodNoResultLogTail(args: {
+  run: (args: readonly string[]) => { status: number | null; stdout: string; stderr: string };
+  namespace: string;
+  job: string;
+  maxLines?: number;
+}): PodNoResultLogRead {
+  const maxLines = args.maxLines ?? POD_NO_RESULT_LOG_TAIL_LINES;
+  try {
+    const result = args.run(['-n', args.namespace, 'logs', `job/${args.job}`, `--tail=${maxLines}`]);
+    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}` };
+    }
+    const tail = podNoResultLogTailLines(result.stdout, maxLines);
+    return tail.length ? { tail } : { unavailable: 'empty log output' };
+  } catch (error) {
+    return { unavailable: boundedPodLogText(error instanceof Error ? error.message : String(error), POD_NO_RESULT_LOG_REASON_MAX_CHARS) || 'unknown error' };
+  }
+}
+
 /** 사람용 런 결과 한 줄 — 수확 브랜치가 있으면 «수확할 브랜치: …» 를 붙인다. */
 export function podRunResultLine(logs: string, branches: readonly string[]): string {
   const result = logs.split('\n').filter((line) => !line.startsWith('ELANOUS_MEM ')).join('\n').slice(-4000);