@bitkyc08/opencodex 2.79.0 → 2.81.0

package/src/server/responses/adapter-dispatch.ts

@@ -1,5 +1,5 @@
 import { classifyAnthropic429 } from "../../oauth/anthropic-rate-limit-policy";
-import { rotateAnthropicAccountOnResponse } from "../../oauth/anthropic-account-refusal";
+import { rotateAnthropicAccountOnResponseForInstance } from "../../oauth/anthropic-account-refusal";
 import { authorizeResendForRecovery } from "../../lib/request-resend-gate";
 import { ambiguousResendAllowanceFor, selfContainedResponsesBody } from "./reset-replay";
 import { transientSendCapFor } from "./request-send-budget";
@@ -65,7 +65,7 @@ import { bindRouteReasoningReplayScope } from "./core-replay";
 import {
   AnthropicAccountCooldownError,
   ANTHROPIC_POOL_MAX_FAILOVERS_PER_REQUEST,
-  getAnthropicPoolAccessSnapshot,
+  anthropicRoutingFor,
   formatAnthropicProviderForLog,
 } from "../../oauth/anthropic-routing";
 import {
@@ -106,6 +106,7 @@ import { isCanonicalOpenAiForwardProvider } from "../../providers/openai-tiers";
 import { mapCodexAuthContextErrorToResponse } from "./codex-auth-error";
 import { chargeWorkflowSends } from "../../lib/workflow-budget";
 import { isAntigravityValidationRefusal } from "./antigravity-validation-refusal";
+import { unboundPoolSpendRefusalResponse } from "../workflow-refusal";
 
 /** One responsibility of the Responses request pipeline; state owners are explicit. */
 export async function prepareAdapterExchange(
@@ -139,6 +140,8 @@ export async function prepareAdapterExchange(
     | "replayOAuthCredentialSnapshot"
     | "invalidateSameTargetRequest"
     | "resolveSelectionAdapter"
+    | "anthropicInstance"
+    | "currentAnthropicRouteDecision"
     | "anthropicRouteDecision"
     | "anthropicPoolAccountId"
     | "anthropicPoolFailovers"
@@ -157,7 +160,8 @@ export async function prepareAdapterExchange(
     | "noteAdapterPhysicalSend"
     | "noteAdapterRecoveryWithheld"
     | "remainingTransientSendBudget"
-    | "noteTransientSends"
+    | "adapterSendBudget"
+    | "transientSendReporter"
     | "recoverySendAllowance"
     | "recoveryClassFor"
     | "sendBudgetExhausted"
@@ -175,6 +179,8 @@ export async function prepareAdapterExchange(
     refreshResolvedOAuthSelection,
     invalidateSameTargetRequest,
     resolveSelectionAdapter,
+    anthropicInstance,
+    currentAnthropicRouteDecision,
     anthropicSessionKey,
     commitResolvedOAuthSelection,
     applyFailoverSnapshot,
@@ -194,7 +200,7 @@ export async function prepareAdapterExchange(
     noteAdapterPhysicalSend,
     noteAdapterRecoveryWithheld,
     remainingTransientSendBudget,
-    noteTransientSends,
+    transientSendReporter,
     recoverySendAllowance,
     recoveryClassFor,
     sendBudgetExhausted,
@@ -333,6 +339,8 @@ export async function prepareAdapterExchange(
   try {
     if (transportState.activeAdapter.fetchResponse) {
       transportState.noteRoutedAttemptSend(inputTokenEstimate);
+      const producer = adapterDispatchBudget?.beginSpendProducer?.();
+      try {
       upstreamResponse = await withProviderRequestSlot(route.providerName, route.provider, route.modelId, upstream.signal, pacingSlot =>
         transportState.activeAdapter.fetchResponse!(builtInitialRequest, {
           kiroPreferAccountFailover: route.providerName === "kiro" && isGenericOAuthFailoverEnabled(config, "kiro"),
@@ -352,6 +360,7 @@ export async function prepareAdapterExchange(
               ? createCodexAuthDispatchGuard(admissionState.authCtx, options.codexAuthPolicy ?? config, route.modelId, options.admission, options.visionDescribeTerminal === true) : undefined,
           }),
         }));
+      } finally { producer?.close(); }
     } else {
       // #1851 scope guard: transient-5xx retry on this generic adapter path is opt-in for
       // direct Google AI Studio only (Vertex/Antigravity use fetchResponse above). Other
@@ -361,13 +370,14 @@ export async function prepareAdapterExchange(
       // legacy direct-Google exception is preserved exactly; every other adapter still keeps
       // reset-only semantics so combo failover hops on the first 5xx.
       const transientPolicy = transientRetryPolicyFor(route.provider);
+      const resetPolicy = resetReplayPolicyFor(route.provider);
       const compactPrepaid = options.compactionRecoveryAttempted ? sendBudgetState.pendingHopPermit : undefined;
       if (compactPrepaid) sendBudgetState.pendingHopPermit = undefined;
       let compactPrepaidUsed = false;
       // Combo and emergency compaction admission already book this target's first send.
       // Its configured initial ceiling is target-local; the shared remainder below still
       // accounts for earlier targets without deducting their sends from this target twice.
-      const initialSendCap = transientPolicy || resetReplayPolicyFor(route.provider)
+      const initialSendCap = transientPolicy || resetPolicy
         ? transientSendCapFor(transientPolicy?.attempts,
           (options.comboAttempt || compactPrepaid) ? 0 : sendBudgetState.sendsUsed)
         : 1;
@@ -376,6 +386,11 @@ export async function prepareAdapterExchange(
         : fetchWithResetRetry;
       upstreamResponse = await fetchWithRetryPolicy(
         recovery => {
+          // Unconfigured generic sends may omit the counting reporter. Capture policy
+          // independently so a later recovery still belongs to this request's start.
+          sendBudgetState.adapterSendBudget?.startRequest?.({
+            poolId: logCtx.spendPoolId ?? route.providerName, identityId: logCtx.accountLogLabel,
+          });
           if (compactPrepaid && !compactPrepaidUsed) {
             if (!compactPrepaid.use()) throw new SendBudgetExhaustedError(safeHostLabel(builtInitialRequest.url));
             compactPrepaidUsed = true;
@@ -398,12 +413,18 @@ export async function prepareAdapterExchange(
           abortSignal: upstream.signal,
           label: safeHostLabel(builtInitialRequest.url),
           claimAmbiguousResend: claimPreHeaderResend,
-          ...(transientPolicy || resetReplayPolicyFor(route.provider) || compactPrepaid
+          ...(sendBudgetState.adapterSendBudget?.spendEnforced || options.comboDispatchPermit || transientPolicy || resetPolicy || compactPrepaid
             ? {
               // A pending compaction permit already booked this leg's first physical send.
-              attempts: Math.min(initialSendCap,
-                remainingTransientSendBudget(initialSendCap) + (compactPrepaid ? 1 : 0)),
-              onSendsConsumed: noteTransientSends,
+              ...(transientPolicy || resetPolicy || compactPrepaid
+                ? {
+                  attempts: Math.min(initialSendCap,
+                    remainingTransientSendBudget(initialSendCap) + (compactPrepaid ? 1 : 0)),
+                }
+                : {}),
+              // Keep the exact combo or compaction receipt on the helper callback. The reporter
+              // also settles the request and workflow counters for reset-only retries.
+              onSendsConsumed: transientSendReporter(compactPrepaid ?? options.comboDispatchPermit),
             }
             : {}),
         },
@@ -437,7 +458,8 @@ export async function prepareAdapterExchange(
     // blaming the provider makes the caller send the whole turn again -- the amplification this
     // budget exists to stop. The passthrough path has answered 429 here since #4546.
     if (err instanceof SendBudgetExhaustedError) {
-      return formatErrorResponse(429, SEND_BUDGET_EXHAUSTED_CODE, err.message);
+      return unboundPoolSpendRefusalResponse(logCtx)
+        ?? formatErrorResponse(429, SEND_BUDGET_EXHAUSTED_CODE, err.message);
     }
     const msg = describeUpstreamConnectFailure(err, connectMs);
     return formatErrorResponse(502, "upstream_error", msg);
@@ -541,6 +563,8 @@ export async function prepareAdapterExchange(
         try {
           if (transportState.activeAdapter.fetchResponse) {
             transportState.noteRoutedAttemptSend(retryEstimate, recovery);
+            const producer = adapterDispatchBudget?.beginSpendProducer?.();
+            try {
             return await withProviderRequestSlot(route.providerName, route.provider, route.modelId, upstream.signal, pacingSlot => {
               // The dispatch boundary is HERE, not before the pacing wait: that wait can reject for
               // an abort, a saturated queue, an expired slot or a removed provider, and none of
@@ -570,6 +594,7 @@ export async function prepareAdapterExchange(
                 }),
               });
             });
+            } finally { producer?.close(); }
           }
           // #2643 review: this leg used to call fetchWithHeaderTimeout directly, so an
           // opted-in provider's transient-5xx policy applied to the initial send and to
@@ -581,7 +606,7 @@ export async function prepareAdapterExchange(
           const refetchWithPolicy = (route.provider.adapter === "google" || refetchTransientPolicy)
             ? fetchWithTransientRetry
             : fetchWithResetRetry;
-          const helperCountsSends = refetchTransientPolicy !== null || resetReplayPolicyFor(route.provider) !== null;
+          const helperCountsSends = sendBudgetState.adapterSendBudget?.spendEnforced === true || refetchTransientPolicy !== null || resetReplayPolicyFor(route.provider) !== null;
           const prepaid = sendBudgetState.pendingHopPermit;
           const configuredTotal = refetchTransientPolicy?.attempts;
           const refetchCap = transientSendCapFor(configuredTotal,
@@ -601,6 +626,9 @@ export async function prepareAdapterExchange(
           try {
             return await refetchWithPolicy(
               recoveryKind => {
+                sendBudgetState.adapterSendBudget?.startRequest?.({
+                  poolId: logCtx.spendPoolId ?? route.providerName, identityId: logCtx.accountLogLabel,
+                });
                 if (refetchAllowance?.permit && !refetchAllowance.permit.use()) {
                   throw new SendBudgetExhaustedError(safeHostLabel(retryRequest.url));
                 }
@@ -629,7 +657,7 @@ export async function prepareAdapterExchange(
                 ...(refetchAllowance
                   ? {
                     attempts: refetchAllowance.attempts,
-                    onSendsConsumed: noteTransientSends,
+                    onSendsConsumed: transientSendReporter(refetchAllowance.permit),
                   }
                   : {}),
               },
@@ -673,7 +701,8 @@ export async function prepareAdapterExchange(
         // Same rule on the recovery leg: the ladder refused to send again, so the answer names
         // this proxy rather than the provider it never reached.
         if (err instanceof SendBudgetExhaustedError) {
-          return { failed: formatErrorResponse(429, SEND_BUDGET_EXHAUSTED_CODE, err.message) };
+          return { failed: unboundPoolSpendRefusalResponse(logCtx)
+            ?? formatErrorResponse(429, SEND_BUDGET_EXHAUSTED_CODE, err.message) };
         }
         const msg = describeUpstreamConnectFailure(err, connectMs);
         return { failed: formatErrorResponse(502, "upstream_error", msg) };
@@ -1048,23 +1077,24 @@ export async function prepareAdapterExchange(
       // before output, within the shared request and account rotation limits.
       while (
         (upstreamResponse.status === 429 || upstreamResponse.status === 403)
+        && anthropicInstance
         && transportState.anthropicPoolAccountId
       ) {
-        const nextAccountId = await rotateAnthropicAccountOnResponse(upstreamResponse, {
+        const nextAccountId = await rotateAnthropicAccountOnResponseForInstance(anthropicInstance, upstreamResponse, {
           config, accountId: transportState.anthropicPoolAccountId, sessionKey: anthropicSessionKey,
-          model: route.modelId, requestKey: transportState, decision: transportState.anthropicRouteDecision, signal: upstream.signal,
+          model: route.modelId, requestKey: transportState, decision: transportState.anthropicRouteDecision, currentDecision: currentAnthropicRouteDecision, signal: upstream.signal,
           canRetry: !sendBudgetExhausted() && transportState.anthropicPoolFailovers < ANTHROPIC_POOL_MAX_FAILOVERS_PER_REQUEST,
         });
         if (!nextAccountId) break;
         try {
-          const admitted = await commitResolvedOAuthSelection(await getAnthropicPoolAccessSnapshot(nextAccountId));
+          const admitted = await commitResolvedOAuthSelection(await anthropicRoutingFor(anthropicInstance).getAnthropicPoolAccessSnapshot(nextAccountId));
           if (!admitted) throw new Error("OAuth selection changed during recovery");
           try { void upstreamResponse.body?.cancel().catch(() => {}); } catch { /* already consumed/closed */ }
           transportState.anthropicPoolAccountId = admitted.accountId;
           transportState.anthropicPoolFailovers += 1;
           route.provider = { ...route.provider, apiKey: admitted.accessToken };
           invalidateSameTargetRequest();
-          logCtx.provider = formatAnthropicProviderForLog("anthropic", admitted.accountId, config);
+          logCtx.provider = formatAnthropicProviderForLog(anthropicInstance, admitted.accountId, config);
           transportState.activeAdapter = resolveSelectionAdapter(
             resolveWireProtocolOverride(route.providerName, route.modelId, route.provider, inboundWire, route.staticPolicy),
             config.cacheRetention,

package/src/server/responses/antigravity-validation-refusal.ts

@@ -1,19 +1,33 @@
-import { ANTIGRAVITY_VALIDATION_REQUIRED_PREFIX } from "../../adapters/google-errors";
+import { ANTIGRAVITY_VALIDATION_REQUIRED_PREFIX, safeAntigravityHttpErrorMessage } from "../../adapters/google-errors";
 import { readBoundedResponseBody } from "../../lib/bounded-body";
 
+/** Match only the normalized Antigravity validation-refusal marker. */
+export function hasAntigravityValidationRefusalMarker(text: string): boolean {
+  return text.startsWith(`${ANTIGRAVITY_VALIDATION_REQUIRED_PREFIX}: `);
+}
+
 /** Inspect only the Google adapter's normalized, already bounded 403 response. */
 export async function isAntigravityValidationRefusal(response: Response, signal?: AbortSignal): Promise<boolean> {
+  return inspectValidationRefusal(response, signal, false);
+}
+
+/** Sidecar dispatch retains the raw Google envelope; normalize only a complete bounded body. */
+export async function isAntigravityRawValidationRefusal(response: Response, signal?: AbortSignal): Promise<boolean> {
+  return inspectValidationRefusal(response, signal, true);
+}
+
+async function inspectValidationRefusal(response: Response, signal: AbortSignal | undefined, raw: boolean): Promise<boolean> {
   if (response.status !== 403 || signal?.aborted) return false;
   try {
     const body = await readBoundedResponseBody(response.clone(), {
-      maxBytes: 1024,
-      totalTimeoutMs: 1000,
-      firstByteTimeoutMs: 1000,
-      inactivityTimeoutMs: 1000,
+      maxBytes: raw ? 4096 : 1024,
+      totalTimeoutMs: raw ? 2000 : 1000,
+      firstByteTimeoutMs: raw ? 2000 : 1000,
+      inactivityTimeoutMs: raw ? 2000 : 1000,
       signal,
     });
     return !signal?.aborted && body.displaySafe && !body.truncated && !body.timedOut && !body.oversized
-      && body.text.startsWith(`${ANTIGRAVITY_VALIDATION_REQUIRED_PREFIX}: `);
+      && hasAntigravityValidationRefusalMarker(raw ? safeAntigravityHttpErrorMessage(403, body.text) : body.text);
   } catch {
     return false;
   }

package/src/server/responses/combo-requested-effort.ts

@@ -0,0 +1,14 @@
+/** Restore the caller label while retaining JEV's forced effort and later child transitions. */
+export function comboRequestedEffortLabel(
+  originalRequestedEffort: string | undefined,
+  childRequestedEffort: string | undefined,
+  forcedEffort?: string | null,
+): string | undefined {
+  if (originalRequestedEffort === undefined) return childRequestedEffort;
+  const transitionIndex = childRequestedEffort?.indexOf("->") ?? -1;
+  const laterTransitions = transitionIndex >= 0 ? childRequestedEffort!.slice(transitionIndex) : "";
+  const forcedTransition = forcedEffort != null && forcedEffort !== originalRequestedEffort
+    ? `->${forcedEffort}`
+    : "";
+  return `${originalRequestedEffort}${forcedTransition}${laterTransitions}`;
+}

package/src/server/responses/compact.ts

@@ -1,3 +1,6 @@
+import { createPhysicalSendReporter } from "../../lib/request-execution-budget";
+import { createInferenceSendBudget } from "../inference/context";
+import { unboundPoolSpendRefusalResponse } from "../workflow-refusal";
 import { capturePoolQuotaWriter } from "../../codex/account-store";
 import { previewXaiOauthWireModel } from "./core-normalize";
 import {
@@ -722,6 +725,7 @@ export async function handleResponsesCompact(
   logCtx.provider = route.codexAccountNamespace
     ? `${route.providerName}-${route.codexAccountNamespace}`
     : route.providerName;
+  logCtx.spendPoolId = route.providerName;
   logCtx.providerAdapter = route.provider.adapter;
   // #4940, and the same refusal the ordinary Responses path makes in request-prepare.ts. Compact has
   // to repeat it rather than inherit it: the native branch below dispatches straight to
@@ -804,7 +808,7 @@ export async function handleResponsesCompact(
   // failure that hands off, continues here. The routed turn used to call handleResponses with
   // no budget at all, so `handleResponsesInner` minted a fresh four after the native attempt
   // had already spent some of the first one.
-  const sendBudget: RequestExecutionBudget = options.sendBudget ?? createRequestExecutionBudget();
+  const sendBudget: RequestExecutionBudget = options.sendBudget ?? createInferenceSendBudget(req, logCtx);
   // A manual override onto another backend must not mint ciphertext the conversation model cannot replay.
   const manualOverrideCrossesProvider = options.compactionRoutingOverride
     ? !compactionRoutingKeepsProviderIdentity(config, options.compactionRoutingOverride, route)
@@ -1022,12 +1026,21 @@ export async function handleResponsesCompact(
     // `kind === "pool"` and a main-pool credential left it false -- so 401 then 429 really did
     // reach five. The single sends spend the base allowance first and then the one shared
     // final-recovery reserve, which is the same rule the Responses path follows.
-    const sendSingleCompactAttempt = (
+    const sendSingleCompactAttempt = async (
       doFetch: () => Promise<Response>,
     ): Promise<Response> => {
       if (sendBudget.remainingBaseSends(TRANSIENT_RETRY_MAX_ATTEMPTS) > 0) {
-        sendBudget.used += 1;
-        return doFetch();
+        const report = createPhysicalSendReporter(sendBudget, () => ({ poolId: logCtx.spendPoolId ?? route.providerName,
+          identityId: logCtx.accountLogLabel }));
+        let started = false;
+        try {
+          if (report.beforeSend?.() === false) throw new SendBudgetExhaustedError(safeHostLabel(compactUrl));
+          started = true;
+          return await doFetch();
+        } finally {
+          try { if (started) report(1); }
+          finally { report.close?.(); }
+        }
       }
       const decision = sendBudget.reserveDispatch({
         sendClass: "auth-recovery",
@@ -1076,7 +1089,8 @@ export async function handleResponsesCompact(
           // Draws the shared remainder instead of a fresh three. Compact is a native endpoint
           // of the same logical turn, so its sends belong to the same cap.
           attempts: sendBudget.remainingBaseSends(TRANSIENT_RETRY_MAX_ATTEMPTS),
-          onSendsConsumed: (used: number) => { sendBudget.used += Math.max(0, used); },
+          onSendsConsumed: createPhysicalSendReporter(sendBudget, () => ({ poolId: logCtx.spendPoolId ?? route.providerName,
+            identityId: logCtx.accountLogLabel })),
         });
     };
 
@@ -1084,9 +1098,12 @@ export async function handleResponsesCompact(
     // actually happens, so every recorder call names the context that produced it.
     let outcomeCtx = authCtx;
     const localDispatchRefusal = (error: unknown): Response | undefined => {
-      const response = mapCodexAuthContextErrorToResponse(unwrapUpstreamRetryEvidenceError(error), {
-        now: Date.now(), accountSelector: route.codexAccountNamespace,
-      });
+      const cause = unwrapUpstreamRetryEvidenceError(error);
+      const response = cause instanceof SendBudgetExhaustedError
+        ? unboundPoolSpendRefusalResponse(logCtx) ?? formatErrorResponse(429, "request_send_budget_exhausted", cause.message)
+        : mapCodexAuthContextErrorToResponse(cause, {
+          now: Date.now(), accountSelector: route.codexAccountNamespace,
+        });
       if (response) {
         releaseUpstreamHostAdmission(compactHostAdmissionLease);
         compactHostAdmissionLease = null;

package/src/server/responses/compaction-recovery.ts

@@ -47,7 +47,7 @@ function settlePhysicalSends(log: RequestLogContext, budget: RequestExecutionBud
   // An external report may settle a prepaid booking without changing used. Its explicit
   // receipt outranks the numeric delta, or the same source send would be charged twice.
   const unreported = Math.max(0, sent - Math.max(reported, Math.max(0, budget.used - beforeUsed)));
-  if (unreported > 0) budget.used += unreported;
+  if (unreported > 0 && !budget.spendEnforced) budget.used += unreported;
   return sent;
 }
 

package/src/server/responses/core-combo-native.ts

@@ -18,7 +18,7 @@ import type { OcxConfig } from "../../types";
 import type { RouteResult } from "../../router";
 import type { DataPlaneAdmission } from "../auth-cors";
 import type { AdmissionLease } from "../../lib/admission";
-import type { RequestExecutionBudget } from "../../lib/request-execution-budget";
+import type { RequestExecutionBudget, SingleUseDispatchPermit } from "../../lib/request-execution-budget";
 import type { TransientSendBudget } from "../../lib/upstream-retry";
 import type { ResponsesTerminalStatus } from "../../bridge";
 import type { NativeChatFinishLog } from "../chat-native";
@@ -62,6 +62,7 @@ export interface NativeComboChildRun {
   childLog: RequestLogContext;
   attemptHandle: InferenceAttempt;
   sendBudget: RequestExecutionBudget;
+  comboDispatchPermit?: SingleUseDispatchPermit;
   turnAdmissionLease?: AdmissionLease;
   onFirstOutput: () => void;
   /** Reports to the combo's child callbacks; it never writes the parent's final row itself. */
@@ -272,6 +273,7 @@ export interface ComboChildCallbacks {
 export async function dispatchNativeComboChild(input: {
   source: ComboProtocolSource;
   plan: NativeComboChildPlan;
+  comboDispatchPermit?: SingleUseDispatchPermit;
   logCtx: RequestLogContext;
   childLog: RequestLogContext;
   attempt: PersistedUsageAttempt;
@@ -317,6 +319,7 @@ export async function dispatchNativeComboChild(input: {
     childLog,
     attemptHandle,
     sendBudget: plan.sendBudget,
+    comboDispatchPermit: input.comboDispatchPermit,
     ...(input.turnAdmissionLease ? { turnAdmissionLease: input.turnAdmissionLease } : {}),
     onFirstOutput: () => {
       outputSeen = true;

package/src/server/responses/core-combo.ts

@@ -52,11 +52,10 @@ import { routeConcreteModel, comboRouteDecisionTrace } from "../../router";
 import { memoryModelRouteReason } from "./memory-models";
 import { poolAccountProviderLabel } from "../../providers/label";
 import { getAccountSet } from "../../oauth/store";
+import { configuredAnthropicInstance } from "../../providers/anthropic-instance";
 import {
+  anthropicRoutingFor,
   formatAnthropicProviderForLog,
-  getAnthropicAccountHealthSnapshot,
-  getAnthropicPoolRetryAfterSeconds,
-  getEligibleAnthropicAccounts,
 } from "../../oauth/anthropic-routing";
 import { codexAccountLogLabel } from "../../codex/account-label";
 import { codexQuotaScopeForModel, getCodexQuotaHealthSnapshot } from "../../codex/routing";
@@ -106,6 +105,7 @@ import { mandatoryResponsesReasoningReplayUnavailable } from "./core-replay";
 import { settleOperatorReplacement } from "../../lib/upstream-retry";
 import { createComboProtocolLanes, dispatchNativeComboChild } from "./core-combo-native";
 import { createJevModelInvoker } from "./jev-model-invoke";
+import { comboRequestedEffortLabel } from "./combo-requested-effort";
 import { clientWireOf } from "../inference/client-wire";
 
 /**
@@ -117,10 +117,11 @@ export const COMBO_TARGET_BASE_SENDS = CODEX_TEXT_GUARDED_BUDGET_POLICY.baseSend
 
 function cooledPoolAccountLabel(config: OcxConfig, providerName: string, modelId: string, label: string | undefined): string | undefined {
   if (!label) return undefined;
-  if (providerName === "anthropic") {
-    const matches = getAccountSet("anthropic")?.accounts.filter(account =>
-      formatAnthropicProviderForLog("anthropic", account.id) === label) ?? [];
-    return matches.length === 1 && getAnthropicAccountHealthSnapshot(matches[0]!.id) ? label : undefined;
+  const instance = configuredAnthropicInstance(config, providerName);
+  if (instance && config.providers[providerName]?.authMode === "oauth") {
+    const matches = getAccountSet(instance)?.accounts.filter(account =>
+      formatAnthropicProviderForLog(instance, account.id) === label) ?? [];
+    return matches.length === 1 && anthropicRoutingFor(instance).getAnthropicAccountHealthSnapshot(matches[0]!.id) ? label : undefined;
   }
   const provider = config.providers[providerName];
   if (!provider || !isCanonicalOpenAiForwardProvider(provider)) return undefined;
@@ -151,12 +152,13 @@ export function isAnthropicPoolLocalRefusal(
   failedAccount: string | undefined,
   now = Date.now(),
 ): boolean {
-  return providerName === "anthropic"
+  const instance = configuredAnthropicInstance(config, providerName);
+  return instance !== undefined
     && config.providers[providerName]?.authMode === "oauth"
     && status === 429
     && failedAccount === undefined
-    && getEligibleAnthropicAccounts(now).length === 0
-    && getAnthropicPoolRetryAfterSeconds(now) !== null;
+    && anthropicRoutingFor(instance).getEligibleAnthropicAccounts(now).length === 0
+    && anthropicRoutingFor(instance).getAnthropicPoolRetryAfterSeconds(now) !== null;
 }
 
 /**
@@ -656,13 +658,9 @@ export async function executeComboResponses(
     && isDeclaredReasoningEffort(originalRequestedEffortValue)
     ? originalRequestedEffortValue
     : undefined;
-  const restoreOriginalRequestedEffort = (childLog: RequestLogContext): void => {
+  const restoreOriginalRequestedEffort = (childLog: RequestLogContext, forcedEffort?: string | null): void => {
     if (originalRequestedEffort === undefined) return;
-    const normalizedRequestedEffort = childLog.requestedEffort;
-    const transitionIndex = normalizedRequestedEffort?.indexOf("->") ?? -1;
-    childLog.requestedEffort = transitionIndex >= 0
-      ? `${originalRequestedEffort}${normalizedRequestedEffort!.slice(transitionIndex)}`
-      : originalRequestedEffort;
+    childLog.requestedEffort = comboRequestedEffortLabel(originalRequestedEffort, childLog.requestedEffort, forcedEffort);
     recordAttemptRequestedEffort(childLog);
   };
 
@@ -716,6 +714,9 @@ export async function executeComboResponses(
   while (pick) {
     if (options.abortSignal?.aborted) return clientCancelledResponse();
     const firstComboTarget = comboTargetsDispatched === 0;
+    const targetRoute = routeConcreteModel(config, `${pick.target.provider}/${pick.target.model}`);
+    // The inherited spend tracker observes this parent log, before the child has its own label.
+    logCtx.spendPoolId = targetRoute.providerName;
     // The first target seeds the ledger's target identity and charges nothing; every later one
     // is a real transition, refused once the declared hops, the alternate-target ledger or the
     // request total are spent. `countedExternally` is required: the child charges its own
@@ -747,7 +748,6 @@ export async function executeComboResponses(
       ...(logCtx.conversationId ? { conversationId: logCtx.conversationId } : {}),
       ...(logCtx.surface ? { surface: logCtx.surface } : {}),
     };
-    const targetRoute = routeConcreteModel(config, `${pick.target.provider}/${pick.target.model}`);
     const targetReasoningEfforts = supportedLadderFor({
       provider: targetRoute.provider,
       modelId: targetRoute.modelId,
@@ -864,6 +864,7 @@ export async function executeComboResponses(
       response = nativeChild ? await dispatchNativeComboChild({
         source: options.protocolSource!,
         plan: nativeChild,
+        comboDispatchPermit: hopDecision?.allowed ? hopDecision.permit : undefined,
         logCtx,
         childLog,
         attempt,
@@ -889,6 +890,7 @@ export async function executeComboResponses(
         // parent arrived with.
         sendBudget: targetSendBudget,
         comboAttempt: true,
+        comboDispatchPermit: hopDecision?.allowed ? hopDecision.permit : undefined,
         comboReplaySnapshot,
         deferCodexResetDerivedCooldown,
         // Attempt-relative TTFT is recorded HERE (not via childLog.firstOutputMs — a later
@@ -907,7 +909,8 @@ export async function executeComboResponses(
         onNativePassthroughCancel: callbackGate.onCancel,
         onResponseComplete: callbackGate.onResponseComplete,
       });
-      restoreOriginalRequestedEffort(childLog);
+      // Native Chat rebuilds its own body and does not apply the initial JEV effort.
+      restoreOriginalRequestedEffort(childLog, nativeChild ? undefined : initialJevDecision?.effort);
     } catch (error) {
       callbackGate.discard();
       if (options.abortSignal?.aborted) {

package/src/server/responses/core-normalize.ts

@@ -210,6 +210,7 @@ export async function applyFinalRouteRequestNormalization(args: {
   if (preserveAnthropicResponseModel) parsed._responseModelId = responseModelId;
   logCtx.model = virtualModel?.selectedModelId ?? route.modelId;
   logCtx.provider = route.providerName;
+  logCtx.spendPoolId = route.providerName;
   logCtx.providerAdapter = route.provider.adapter;
   logCtx.routeDecision = route.routeDecision;
   logCtx.policyEligibility = route.policyEligibility;

package/src/server/responses/core-options.ts

@@ -71,7 +71,7 @@ export interface HandleResponsesOptions {
   compactionRecoveryKind?: "compaction-v1" | "compaction-v2";
   onCompactionRecoveryRoute?: (route: RouteResult) => void;
   onCompactionRecoveryAdapterEvent?: (event: AdapterEvent) => void;
-  /** Physical-send reports already delivered to the shared used setter, including booking settlement. */
+  /** Physical-send reports already delivered to the shared ledger, including exact booking settlement. */
   onCompactionRecoverySendsReported?: (count: number) => void;
   /** Private holder for the Kiro serving-account lease. */
   accountLoad?: { lease: AccountLease | null; cancelled: boolean };
@@ -158,6 +158,8 @@ export interface HandleResponsesOptions {
   callerDirectAuth?: CallerDirectAuth | null;
   /** Internal recursion guard; callers outside this module must not set it. */
   comboAttempt?: boolean;
+  /** Exact externally booked combo hop, used for its child's spend preflight and send reports. */
+  comboDispatchPermit?: SingleUseDispatchPermit;
   /** Internal handoff: this combo was selected by shadow-call interception. */
   shadowCallIntercepted?: boolean;
   /** Internal handoff: the memory phase this turn belongs to, so combo children keep its routing. */

package/src/server/responses/core-replay.ts

@@ -37,6 +37,11 @@ export function adapterNeedsForcedContinuation(name: string): boolean {
   return name === "kiro" || name === "cursor";
 }
 
+/** Adapters opting into restricted store:false replay for pending client function calls. */
+export function adapterNeedsToolCallContinuation(name: string): boolean {
+  return name === "qoder";
+}
+
 
 export type ContinuationOwnerRead =
   | { kind: "missing" }

package/src/server/responses/passthrough-delivery.ts

@@ -364,6 +364,7 @@ export async function deliverPassthroughResponse(
     | "subagentFallbackAccountId"
     | "clientRequestedStream"
     | "translatorBudget"
+    | "inboundWire"
   >,
   transportState: Pick<ResponsesTransport, "requestBindings">,
   sidecarState: Pick<ResponsesSidecarAuth, "openAiSidecar">,
@@ -428,7 +429,8 @@ export async function deliverPassthroughResponse(
     normalizeFunctionCompletionJson,
   } = nativeExchange;
   const { commitReasoningReplayServingRoute, recordTerminalOutcomes } = responseEffects;
-  const { parsed, route, subagentQuotaFailureModel, clientRequestedStream, translatorBudget } = requestState;
+  const { parsed, route, subagentQuotaFailureModel, clientRequestedStream, translatorBudget, inboundWire } = requestState;
+  const enforceDeclaredToolNames = inboundWire !== "chat" && inboundWire !== "anthropic";
   const { openAiSidecar } = sidecarState;
   const { requestBindings } = transportState;
 
@@ -637,6 +639,7 @@ export async function deliverPassthroughResponse(
         route.provider.webSearchBridge?.backend,
         config,
         openAiSidecar,
+        route.providerName,
       );
       const webSearchBridgePlan = planPassthroughWebSearchBridge(parsed, route.provider, {
         providerName: route.providerName,
@@ -836,6 +839,7 @@ export async function deliverPassthroughResponse(
             providerExecutedCallTypes,
             declaredBareWireToolNames,
             recoverableBareCustomWireToolNames,
+            enforceDeclaredToolNames,
           )
           : undefined,
         grokUpstreamEchoEnabled
@@ -1293,7 +1297,7 @@ export async function deliverPassthroughResponse(
       if (grokUpstreamEchoEnabled) {
         clientJson = stripGrokUpstreamEnvelopeEchoFromResponsesJson(clientJson);
       }
-      // #1700: same fail-closed policy as the SSE relay above. Both the plain JSON answer and
+      // #1700: same inbound-wire refusal policy as the SSE relay above. Both the plain JSON answer and
       // the reframed-SSE branch below are built from this body, so one check covers them. This
       // runs BEFORE the continuation cache write below: a refused turn must not become state a
       // later `previous_response_id` replay can expand from.
@@ -1312,7 +1316,7 @@ export async function deliverPassthroughResponse(
             return undefined;
           }
         })();
-        if (undeclared !== undefined) {
+        if (enforceDeclaredToolNames && undeclared !== undefined) {
           return formatErrorResponse(502, "upstream_error", undeclaredToolCallMessage(undeclared));
         }
         clientJson = normalizeDefaultNamespaceInJson(