fix(auth): reduce file size

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

config/quality/file-size-baseline.json

@@ -1,9 +1,5 @@
 {
   "_rebaseline_2026_08_09_9296_adobe_media_capabilities": "PR #9296 (artickc, fix/adobe-firefly-model-capabilities) own growth: src/app/api/v1/models/catalog.ts 1590->1597 (+7). The image and video catalog serializers now expose the already-normalized Adobe Firefly discovery capability data (media_capabilities, plus the existing video modality/size fields) at their only response-emission chokepoints. The discovery parser and capability normalization remain in open-sse/services/adobeFireflyModels.ts; extracting these seven serialization fields would obscure the catalog contract. Covered by tests/unit/adobe-firefly.test.ts and tests/unit/image-upscale.test.ts.",
-  "_rebaseline_2026_08_08_v3850_base_drift_batch_9757": "Base drift on release/v3.8.50, not own growth: the 08-06..08-08 merge batches grew 12 already-frozen (or newly-landed) files without carrying their rebaselines — the dedicated rebaseline PR #9616 was closed as 'superseded' but its file-size entries never actually reached the base, and later merges (#8894 combos page, #9539 EditConnectionModal, #8895 models route, #9294/#9293 catalog, #9541 db/core, #8970 tokenHealthCheck, #8925 mcp schemas+server, #8890 accountFallback, #9467 chat.ts, #8931 openai-to-kiro, ProxyRegistryManager) kept growing them. All 12 values re-measured on THIS branch's tree (= pure tip + this PR's 1-line chat.ts fix, which adds zero lines). This PR's own source changes (chat.ts identifier restore, stream.ts format carve-out) do not grow any frozen file past these values.",
-  "_rebaseline_2026_08_08_migration_135_collision": "fix(db): resolve migration version 135 numbering collision — #9449's 135_connection_runtime_state.sql and #8908's 135_migrate_model_capability_max_token.sql both claimed version 135 (#9449 branched before #8908 merged and never got renumbered before landing on release/v3.8.50), which threw 'Migration version collision detected' the moment ANY code touched the database — a fresh install/deploy from this tip cannot even boot. Renumbered the later-landing file to 140 (next free slot) and added the matching isSchemaAlreadyApplied('140') retroactive guard, matching the established pattern already used for the prior 135/136 -> 137/138 renumber in the same file. Own growth: src/lib/db/migrationRunner.ts 1084->1094 (+10, the new case block) — irreducible, matches the existing per-case guard pattern exactly. Covered by tests/unit/migration-135-numbering-collision.test.ts (2/2), confirmed failing (reproducing the exact live crash) against the pre-fix colliding filenames, passing after.",
-  "_rebaseline_2026_08_08_9183_reasoning_cache_index_sync": "Extracted fix(responses-api): sync reasoning-cache write index with the fixed read side (from the originally-authored #9183) — chatCore.ts's write side cached every response under a hardcoded messageIndex:0, and translator/index.ts's plain-turn (non-tool-call) cache-key lookup ALSO still hardcoded messageIndex 0 at its call site (a second, previously-undiscovered instance of the same hardcoding bug, found while re-verifying this fix against the current upstream tip — the two never agreed once a conversation went past its first assistant turn, so DeepSeek/Xiaomi-mimo plain-turn reasoning replay silently missed the cache). Own growth: open-sse/handlers/chatCore.ts 5034->5042 (+8, computing messageIndex from the incoming request's message count at both the streaming and non-streaming cache-write call sites) — irreducible call-site wiring. Covered by tests/unit/reasoning-cache.test.ts (new end-to-end write/read regression test, rebaselined below) and tests/unit/translator-helper-branches.test.ts fixture updates. Other #9183 sub-fixes (output_index collision prevention, reasoning-content-alias generalization) were originally assumed already superseded by upstream's own independent fix — a live incident 2026-08-08 disproved that for the message-vs-tool-call collision case specifically (fixed separately in #9822); not re-extracted here since this PR's own scope is the narrower messageIndex sync only.",
-  "_rebaseline_2026_08_02_9259_rolling_rpm": "PR #9259 (issue #8733) own growth: open-sse/services/rateLimitManager.ts baseline 1060->1167 (+107; final source 1153). The existing withRateLimit chokepoint now composes process-local rolling RPM leases with Bottleneck admission, releases pre-dispatch leases on queue timeout/abort/connection disable, preserves caller abort reasons, and wires 429/header state into the extracted rollingRpmGate.ts. The remaining growth is irreducible lifecycle wiring at the dispatch boundary plus the real watchdog test hooks needed to verify queued-wedge recovery; moving it further would obscure lease ownership and Bottleneck cleanup. Covered by the focused rate-limit manager/sliding-window suite (33/33); distributed multi-instance coordination remains explicitly out of scope.",
   "_rebaseline_2026_07_24_8470_hyperagent_sticky_thread": "PR #8470 (artickc, fix/hyperagent-tool-loop-thread-sticky) own growth: open-sse/executors/hyperagent.ts 936->1025 (wc -l; check-file-size.mjs counts via split(\"\\n\").length so the gate sees 937->1026, +89, crosses the 1000 cap). Fixes a real bug where a reverse-conversion proxy (text-Intent/JSON to Claude Code native tool_calls) rewrites assistant messages between agentic tool-loop turns, breaking HyperAgent’s conversation-prefix fingerprint and cold-starting the thread mid tool-loop. Adds Anthropic tool_use/tool_result flattening to extractMessageText() plus a new rootUserFingerprint()/root-key lookup tier in resolveHyperAgentThreadBinding()/storeHyperAgentThreadAfterTurn() so the thread stays sticky across the tool loop. Cohesive additions inside the existing single-file executor; not extractable without splitting the executor mid-request-flow. Covered by tests/unit/executor-hyperagent.test.ts (19/19, +5 new cases for tool_result/tool_use flattening + root-key stickiness). Pre-merge review flagged a cross-conversation root-key collision risk (tracked in the PR’s own mandatory pre-merge checklist, not yet addressed) — unrelated to this file-size ratchet, tracked separately by /fix-prs.",
   "_rebaseline_2026_07_25_8494_capability_filter_fail_closed": "PR #8494 (fix/capability-filters-fail-closed, #8488) own growth: open-sse/services/combo.ts 3640->3693 (+53) adds a fail-closed guard after filterTargetsByRequestCompatibility() — when every eligible target is excluded by request-capability filtering (vision/tools/etc) instead of quota/health, the combo now returns an explicit `capability_mismatch` 400 (describeCapabilityFilterExhaustion, imported from combo/comboStructure.ts) rather than silently falling through to a generic no-targets error, plus a `compatFilterFailOpen` escape hatch (combo config OR settings) mirrored at both the main/auto and round-robin call sites for symmetry. combo/comboStructure.ts (previously under cap, un-frozen) grows 794->918 (+124) — new home for describeCapabilityFilterExhaustion + providerSupportsEmulatedToolCalling (#5240 emulated tool-calling exemption so fail-closed does not regress prompt-emulation-only combos like all-chatgpt-web). Irreducible orchestration wiring at the existing filter chokepoint (same precedent as #7301's universal-cooldown-retry generalization). Companion test tests/unit/combo-routing-engine.test.ts 3409->3449 (+40, fail-closed/fail-open coverage across both call sites) also rebaselined. Covered by tests/unit/8488-capability-filter-fail-closed.test.ts (new) + 95/95 passing across both files. Structural shrink of combo.ts tracked in #3501.",
   "_rebaseline_2026_07_25_8499_ts7_result_union_predicates": "PR #8499 (backryun, chore/ts7-types-executor-scattered) own growth: muse-spark-web.ts 1396->1405 (+9, irreducible). Under this workspace's `strictNullChecks: false`, the boolean-literal discriminant on `GraphqlResult` (`{ ok: true } | { ok: false; error: string }`) narrows the positive `.ok===true` branch but leaves `!result.ok` at the full union under TS7, making `.error` unreachable to the checker at the two call sites (warmup, mode-switch). Fixed by adding a single `isGraphqlFailure()` type-predicate helper (doc comment + 3-line body) reused at both call sites instead of duplicating the predicate inline — not extractable to a shared module without splitting a single-file executor's local narrowing helper out of its own file. Covered by the existing muse-spark-web executor test suite (no behavior change, pure narrowing fix).",
@@ -166,7 +162,6 @@
   "cap": 1000,
   "testCap": 1000,
   "testFrozen": {
-    "tests/unit/reasoning-cache.test.ts": 1035,
     "_rebaseline_2026_06_27_5193_antigravity_test": "#5193 own test growth: oauth-providers-config.test.ts 870->873 (+3: antigravity projectId assertion + 50ms tick for the now fire-and-forget onboarding, matching the no-PKCE/no-openid flow).",
     "_rebaseline_2026_07_02_5928_base_red": "web-cookie-providers-new.test.ts 845->850: #5928 (test(security) Kimi Web URL host parse, CodeQL #689) grew the file +5 lines and merged into release/v3.8.44 WITHOUT rebaselining, leaving a fast-gates base-red that blocked every subsequent PR->release. Test growth is legitimate (a security regression test); maintainer absorbs the drift here. Frozen at 850.",
     "_rebaseline_2026_07_09_6126_clinepass_dualauth": "#6126 (ClinePass dual-auth) own test growth: oauth-providers-config.test.ts 842->845 (+3: clinepass key/config/required-fields entries reusing the Cline WorkOS flow config, needed after registering clinepass in the oauth.ts PROVIDERS enum).",
@@ -355,7 +350,7 @@
     "open-sse/executors/deepseek-web.ts": 1148,
     "open-sse/executors/grok-web.ts": 1044,
     "open-sse/executors/muse-spark-web.ts": 1405,
-    "open-sse/handlers/chatCore.ts": 5042,
+    "open-sse/handlers/chatCore.ts": 5034,
     "open-sse/handlers/imageGeneration.ts": 3101,
     "open-sse/handlers/responseSanitizer.ts": 1128,
     "open-sse/handlers/search.ts": 1536,

open-sse/handlers/chatCore.ts

@@ -207,6 +207,7 @@ import { stageTrace } from "./chatCore/stageTrace.ts";
 import { attachCompressionUsageReceiptAfterAnalytics as attachCompressionUsageReceiptAfterAnalyticsFor } from "./chatCore/compressionUsageReceipt.ts";
 import { prepareUpstreamBody } from "./chatCore/upstreamBody.ts";
 import { getQuotaScopeLabelForProvider } from "../services/antigravityQuotaFamily.ts";
+
 import {
   getCallLogPipelineCaptureStreamChunks,
   getCallLogPipelineMaxSizeBytes,
@@ -366,7 +367,9 @@ import {
   isTpmExhausted,
   isRpmExhausted,
 } from "../services/geminiRateLimitTracker.ts";
+
 import { isSmallEnoughForSemanticCache } from "../utils/estimateSize.ts";
+
 /**
  * Core chat handler - shared between SSE and Worker
  * Returns { success, response, status, error } for caller to handle fallback
@@ -386,8 +389,10 @@ import { isSmallEnoughForSemanticCache } from "../utils/estimateSize.ts";
  * @param {boolean} options.isCombo - Whether this request is from a combo
  * @param {string} options.connectionId - Connection ID for settings lookup
  */
+
 // extractSystemRoleMessages extracted to chatCore/claudeSystemRole.ts (#3501); re-exported above so
 // existing importers (e.g. tests/unit/system-role-extraction.test.ts) keep resolving it from here.
+
 export async function handleChatCore({
   body,
   modelInfo,
@@ -423,6 +428,7 @@ export async function handleChatCore({
       /* fail open */
     }
   }
+
   // Per-request model-routing metadata (first extracted slice of the request-setup phase).
   const { apiFormat, customModelTargetFormat, requestedModel } = resolveChatCoreRequestSetup(
     modelInfo,
@@ -436,6 +442,7 @@ export async function handleChatCore({
   // (not Math.random) purely to satisfy CodeQL js/insecure-randomness — this id
   // is a log-correlation token, not a security secret.
   const traceId = globalThis.crypto.randomUUID().slice(0, 6);
+
   // Emit request.started event for real-time dashboard
   setImmediate(() => {
     emit("request.started", {
@@ -4326,14 +4333,9 @@ export async function handleChatCore({
     try {
       const firstChoice = translatedResponse?.choices?.[0];
       const msg = firstChoice?.message;
-      // The response being cached now will be replayed as history on the *next*
-      // turn, where the read side (translator/index.ts) keys the lookup by the
-      // message's real position in that future `messages` array — i.e. right
-      // after everything the client sent this turn.
-      const bodyMessages = (body as { messages?: unknown[] } | null | undefined)?.messages;
       cacheReasoningFromAssistantMessage(msg, provider, model, {
         requestId: skillRequestId,
-        messageIndex: Array.isArray(bodyMessages) ? bodyMessages.length : 0,
+        messageIndex: 0,
       });
     } catch {
       // Cache capture is non-critical — never block the response
@@ -4758,15 +4760,12 @@ export async function handleChatCore({
     // with tool_calls so it can be replayed on subsequent turns (DeepSeek V4, Kimi K2, etc.)
     if (normalizedStreamStatus === 200 && streamResponseBody) {
       try {
-        const streamBody = streamResponseBody as Record<string, unknown>;
-        const choices = streamBody.choices as { message?: Record<string, unknown> }[] | undefined;
+        const body = streamResponseBody as Record<string, unknown>;
+        const choices = body.choices as { message?: Record<string, unknown> }[] | undefined;
         const msg = choices?.[0]?.message;
-        // See the non-streaming capture above: messageIndex must match the
-        // position this message will occupy in the *next* turn's history.
-        const bodyMessages = (body as { messages?: unknown[] } | null | undefined)?.messages;
         cacheReasoningFromAssistantMessage(msg, provider, model, {
           requestId: skillRequestId,
-          messageIndex: Array.isArray(bodyMessages) ? bodyMessages.length : 0,
+          messageIndex: 0,
         });
       } catch {
         // Cache capture is non-critical — never block the stream
@@ -5026,6 +5025,7 @@ export async function handleChatCore({
     }),
   };
 }
+
 export function isTokenExpiringSoon(expiresAt, bufferMs = 5 * 60 * 1000) {
   if (!expiresAt) return false;
   const expiresAtMs = new Date(expiresAt).getTime();

open-sse/translator/index.ts

@@ -570,7 +570,7 @@ export function translateRequest(
 
       const cacheKey = hasToolCalls
         ? msg.tool_calls[0]?.id
-        : getAssistantMessageCacheKey(result, messageIndex);
+        : getAssistantMessageCacheKey(result, 0);
       if (cacheKey) {
         const cached = lookupReasoning(cacheKey);
         if (cached) {

src/sse/services/auth.ts

@@ -83,7 +83,6 @@ import { getResource404Bypass } from "./requestResourceHealth";
 import * as log from "../utils/logger";
 import { fisherYatesShuffle, getNextFromDeckSync } from "@/shared/utils/shuffleDeck";
 import { readHeaderValue, type AuthRequestHeaders } from "./headerReader.ts";
-
 type JsonRecord = Record<string, unknown>;
 interface RecoverableConnectionState {
   connectionId: string;
@@ -94,7 +93,6 @@ interface RecoverableConnectionState {
   lastErrorType?: string | null;
   lastErrorSource?: string | null;
 }
-
 interface CredentialSelectionOptions {
   allowSuppressedConnections?: boolean;
   allowRateLimitedConnections?: boolean;
@@ -104,14 +102,12 @@ interface CredentialSelectionOptions {
   sessionKey?: string | null;
   sessionAffinityTtlMs?: number | null;
 }
-
 interface CooldownInspectionState {
   connection: ProviderConnectionView;
   connectionCooldownMs: number | null;
   codexScopeCooldownMs: number | null;
   retryableModelCooldownMs: number | null;
 }
-
 const MIN_QUOTA_THRESHOLD_PERCENT = 1;
 const MAX_QUOTA_THRESHOLD_PERCENT = 100;
 const NON_RETRYABLE_MODEL_LOCKOUT_REASONS = new Set(["not_found", "not_found_local"]);
@@ -119,25 +115,20 @@ const NON_RETRYABLE_MODEL_LOCKOUT_REASONS = new Set(["not_found", "not_found_loc
 // this base. Real upstream Retry-After hints still win — they flow through
 // `exactCooldownMs` (usedUpstreamRetryHint), not this base. (#5222)
 const ANTIGRAVITY_FAMILY_INFERRED_BASE_COOLDOWN_MS = 30_000;
-
 function asRecord(value: unknown): JsonRecord {
   return value && typeof value === "object" && !Array.isArray(value) ? (value as JsonRecord) : {};
 }
-
 function toStringOrNull(value: unknown): string | null {
   return typeof value === "string" && value.trim().length > 0 ? value : null;
 }
-
 function toNullableNumber(value: unknown): number | null {
   if (value === null || value === undefined) return null;
   const parsed = toNumber(value, Number.NaN);
   return Number.isFinite(parsed) ? parsed : null;
 }
-
 function toBooleanOrDefault(value: unknown, fallback: boolean): boolean {
   return typeof value === "boolean" ? value : fallback;
 }
-
 function normalizeSessionKey(value: unknown, prefix: string): string | null {
   if (typeof value !== "string" || value.trim().length === 0) return null;
   const trimmed = value.trim();
@@ -146,7 +137,6 @@ function normalizeSessionKey(value: unknown, prefix: string): string | null {
   }
   return `${prefix}:sha256:${createHash("sha256").update(trimmed).digest("hex")}`;
 }
-
 function extractTextForSessionHash(value: unknown): string | null {
   if (typeof value === "string") return value;
   if (Array.isArray(value)) {
@@ -164,7 +154,6 @@ function extractTextForSessionHash(value: unknown): string | null {
   if (value && typeof value === "object") return JSON.stringify(value);
   return null;
 }
-
 function getFirstInputText(body: unknown): string | null {
   const record = asRecord(body);
   if (record.input !== undefined) {
@@ -189,7 +178,6 @@ function getFirstInputText(body: unknown): string | null {
 
   return null;
 }
-
 export function extractSessionAffinityKey(
   body: unknown,
   headers?: Headers | { get?: (name: string) => string | null } | null
@@ -216,7 +204,6 @@ export function extractSessionAffinityKey(
   if (!inputText || inputText.trim().length === 0) return null;
   return `input:sha256:${createHash("sha256").update(inputText.slice(0, 4096)).digest("hex")}`;
 }
-
 function getCodexLimitPolicy(providerSpecificData: JsonRecord): {
   use5h: boolean;
   useWeekly: boolean;
@@ -227,13 +214,11 @@ function getCodexLimitPolicy(providerSpecificData: JsonRecord): {
     useWeekly: toBooleanOrDefault(policy.useWeekly, true),
   };
 }
-
 interface QuotaLimitPolicy {
   enabled: boolean;
   thresholdPercent: number;
   windows: string[];
 }
-
 interface QuotaCacheView {
   quotas?: Record<
     string,
@@ -243,7 +228,6 @@ interface QuotaCacheView {
     }
   >;
 }
-
 function normalizeQuotaThreshold(
   value: unknown,
   fallback = DEFAULT_QUOTA_THRESHOLD_PERCENT
@@ -251,17 +235,14 @@ function normalizeQuotaThreshold(
   const parsed = toNumber(value, fallback);
   return Math.min(MAX_QUOTA_THRESHOLD_PERCENT, Math.max(MIN_QUOTA_THRESHOLD_PERCENT, parsed));
 }
-
 function normalizeWindowName(windowName: unknown): string | null {
   if (typeof windowName !== "string") return null;
   const normalized = windowName.trim().toLowerCase();
   return normalized.length > 0 ? normalized : null;
 }
-
 function uniqueWindows(windows: string[]): string[] {
   return [...new Set(windows)];
 }
-
 function normalizeCodexWindowName(windowName: unknown): string | null {
   if (typeof windowName !== "string") return null;
   const normalized = windowName.trim().toLowerCase();
@@ -273,7 +254,6 @@ function normalizeCodexWindowName(windowName: unknown): string | null {
   }
   return toCodexBaseQuotaWindowName(normalized);
 }
-
 function applyCodexWindowPolicy(rawWindows: string[], providerSpecificData: JsonRecord): string[] {
   const codexPolicy = getCodexLimitPolicy(providerSpecificData);
   const normalizedRaw = rawWindows.map(normalizeCodexWindowName).filter(Boolean) as string[];
@@ -291,7 +271,6 @@ function applyCodexWindowPolicy(rawWindows: string[], providerSpecificData: Json
 
   return uniqueWindows(windows);
 }
-
 function getCodexScopeRateLimitedUntil(
   providerSpecificData: JsonRecord,
   model: string | null
@@ -302,7 +281,6 @@ function getCodexScopeRateLimitedUntil(
   const value = scopeMap[scope];
   return typeof value === "string" && value.trim().length > 0 ? value : null;
 }
-
 function isCodexScopeUnavailable(
   connection: ProviderConnectionView,
   model: string | null
@@ -311,7 +289,6 @@ function isCodexScopeUnavailable(
   if (!until) return false;
   return new Date(until).getTime() > Date.now();
 }
-
 function getEarliestCodexScopeRateLimitedUntil(
   connections: ProviderConnectionView[],
   model: string | null
@@ -332,11 +309,9 @@ function getEarliestCodexScopeRateLimitedUntil(
 
   return earliest;
 }
-
 function normalizeStatus(value: string | null): string {
   return (value || "").trim().toLowerCase();
 }
-
 function isTerminalConnectionStatus(connection: ProviderConnectionView): boolean {
   const status = normalizeStatus(connection.testStatus);
   return status === "credits_exhausted" || status === "banned" || status === "expired";
@@ -354,7 +329,6 @@ function isRecoverableCookieAuth401(
     resolveProviderId(provider) in WEB_COOKIE_PROVIDERS
   );
 }
-
 function resolveTerminalConnectionStatus(
   status: number,
   result: { permanent?: boolean; creditsExhausted?: boolean },
@@ -381,7 +355,6 @@ function resolveTerminalConnectionStatus(
   }
   return null;
 }
-
 export function resolveQuotaLimitPolicy(
   provider: string,
   providerSpecificData: JsonRecord
@@ -407,7 +380,6 @@ export function resolveQuotaLimitPolicy(
     windows,
   };
 }
-
 export function evaluateQuotaLimitPolicy(
   provider: string,
   connection: ProviderConnectionView,
@@ -440,7 +412,6 @@ export function evaluateQuotaLimitPolicy(
     resetAt: getEarliestFutureDate(resetCandidates),
   };
 }
-
 function parseFutureDateMs(value: string | null): number | null {
   if (!value) return null;
   // Tolerate numeric-epoch strings (e.g. "1781696905131.0") as well as ISO
@@ -449,7 +420,6 @@ function parseFutureDateMs(value: string | null): number | null {
   if (!Number.isFinite(ms) || ms <= Date.now()) return null;
   return ms;
 }
-
 function getEarliestFutureDate(candidates: Array<string | null>): string | null {
   return (
     candidates
@@ -461,31 +431,26 @@ function getEarliestFutureDate(candidates: Array<string | null>): string | null
       .sort((a, b) => (a.ms as number) - (b.ms as number))[0]?.raw || null
   );
 }
-
 function getCachedQuotaResetAt(connectionId: string): string | null {
   const entry = getQuotaCache(connectionId);
   if (!entry?.quotas) return null;
   return getEarliestFutureDate(Object.values(entry.quotas).map((quota) => quota.resetAt));
 }
-
 function isRetryableModelLockoutReason(reason: unknown): boolean {
   return typeof reason === "string" && reason.length > 0
     ? !NON_RETRYABLE_MODEL_LOCKOUT_REASONS.has(reason)
     : false;
 }
-
 function pushClampedPercentage(percentages: number[], value: number): void {
   if (Number.isFinite(value)) {
     percentages.push(Math.max(0, Math.min(100, value)));
   }
 }
-
 function isResetAtInPast(resetAt: string | null): boolean {
   if (!resetAt) return false;
   const resetMs = new Date(resetAt).getTime();
   return Number.isFinite(resetMs) && resetMs <= Date.now();
 }
-
 function collectPolicyQuotaHeadroomPercentages(
   provider: string,
   connection: ProviderConnectionView,
@@ -508,7 +473,6 @@ function collectPolicyQuotaHeadroomPercentages(
 
   return percentages;
 }
-
 function collectCachedQuotaHeadroomPercentages(
   provider: string,
   connection: ProviderConnectionView,
@@ -528,7 +492,6 @@ function collectCachedQuotaHeadroomPercentages(
 
   return percentages;
 }
-
 function getConnectionQuotaHeadroomPercent(
   provider: string,
   connection: ProviderConnectionView,
@@ -548,7 +511,6 @@ function getConnectionQuotaHeadroomPercent(
 
   return percentages.length > 0 ? Math.min(...percentages) : null;
 }
-
 function getConnectionErrorPenalty(connection: ProviderConnectionView): number {
   const errorType = normalizeStatus(connection.lastErrorType);
   const errorSource = normalizeStatus(connection.lastErrorSource);
@@ -572,7 +534,6 @@ function getConnectionErrorPenalty(connection: ProviderConnectionView): number {
 
   return penalty;
 }
-
 function getConnectionRecencyPenalty(connection: ProviderConnectionView): number {
   if (!connection.lastUsedAt) return 0;
   const ageMs = Date.now() - new Date(connection.lastUsedAt).getTime();
@@ -582,7 +543,6 @@ function getConnectionRecencyPenalty(connection: ProviderConnectionView): number
   if (ageMs < 5 * 60_000) return 1;
   return 0;
 }
-
 function getP2CConnectionScore(
   provider: string,
   connection: ProviderConnectionView,
@@ -628,7 +588,6 @@ function getP2CConnectionScore(
 
   return { score, quotaHeadroomPercent };
 }
-
 function compareP2CConnections(
   provider: string,
   a: ProviderConnectionView,
@@ -662,12 +621,10 @@ function compareP2CConnections(
  * exclude it (#3061), otherwise it gets re-selected forever.
  */
 const SYNTHETIC_NOAUTH_CONNECTION_ID = "noauth";
-
 type AnonymousFallbackProviderDefinition = {
   anonymousFallback?: boolean;
   noAuth?: boolean;
 };
-
 function buildSyntheticNoAuthCredentials(providerSpecificData: JsonRecord = {}): {
   apiKey: null;
   accessToken: null;
@@ -756,7 +713,6 @@ async function loadNoAuthProviderSpecificData(providerId: string): Promise<JsonR
     return {};
   }
 }
-
 function providerCanUseSyntheticNoAuthFallback(providerId: string): boolean {
   const providerDef = getProviderById(providerId) as
     AnonymousFallbackProviderDefinition | undefined;
@@ -772,7 +728,6 @@ function providerCanUseSyntheticNoAuthFallback(providerId: string): boolean {
     webCookieProviderDef?.noAuth === true
   );
 }
-
 async function maybeSyntheticNoAuthFallback(
   providerId: string,
   excludedConnectionIds: Set<string>,
@@ -790,7 +745,6 @@ async function maybeSyntheticNoAuthFallback(
   const providerSpecificData = await loadNoAuthProviderSpecificData(providerId);
   return buildSyntheticNoAuthCredentials(providerSpecificData);
 }
-
 function normalizeExcludedConnectionIds(
   excludeConnectionId: string | null,
   extraExcludedConnectionIds: string[] | null | undefined
@@ -811,7 +765,6 @@ function normalizeExcludedConnectionIds(
 
   return normalized;
 }
-
 function formatConnectionPrefixesForLog(ids: Iterable<string>, max = 6): string {
   const prefixes = Array.from(ids)
     .filter((id) => typeof id === "string" && id.length > 0)
@@ -819,7 +772,6 @@ function formatConnectionPrefixesForLog(ids: Iterable<string>, max = 6): string
     .map((id) => `${id.slice(0, 8)}...`);
   return prefixes.length > 0 ? prefixes.join(",") : "none";
 }
-
 function buildQuotaPreflightRateLimitedResult(
   provider: string,
   blockedByPreflight: Array<{
@@ -850,12 +802,10 @@ function buildQuotaPreflightRateLimitedResult(
     lastErrorCode: 429,
   };
 }
-
 function quotaPreflightUnavailableUntil(resetAt?: string | null): string {
   const resetMs = parseFutureDateMs(resetAt ?? null);
   return new Date(resetMs ?? Date.now() + 5 * 60 * 1000).toISOString();
 }
-
 async function markQuotaPreflightAccountUnavailable(
   provider: string,
   connectionId: string,
@@ -884,14 +834,12 @@ async function markQuotaPreflightAccountUnavailable(
 // Provider-scoped mutexes prevent race conditions during account selection without
 // serializing unrelated providers behind a single global lock.
 const selectionMutexes = new Map<string, Promise<void>>();
-
 function getSelectionMutexKey(provider: string, options: CredentialSelectionOptions): string {
   return [
     resolveProviderId(provider) || provider,
     options.forcedConnectionId ? `forced:${options.forcedConnectionId}` : "pool",
   ].join(":");
 }
-
 function createSelectionLock(key: string) {
   const currentMutex = selectionMutexes.get(key) ?? Promise.resolve();
   let resolveMutex: (() => void) | undefined;
@@ -923,7 +871,6 @@ export { fisherYatesShuffle, getNextFromDeckSync as getNextFromDeck };
 // Re-export readHeaderValue and AuthRequestHeaders from headerReader.ts for
 // backwards compat with existing imports (e.g. googApiKeyAuth.ts).
 export { readHeaderValue, type AuthRequestHeaders } from "./headerReader.ts";
-
 const PROVIDER_SEARCH_PAIRS: string[][] = [
   ["nvidia", "nvidia_nim"],
   ["kimi-coding", "kimi-coding-apikey"],
@@ -1703,7 +1650,6 @@ export async function getProviderCredentials(
     selectionLock.release();
   }
 }
-
 export async function getProviderCredentialsWithQuotaPreflight(
   provider: string,
   excludeConnectionId: string | null = null,
@@ -2005,16 +1951,17 @@ export async function markAccountUnavailable(
     const disableCooling = connProviderSpecificData.disableCooling === true;
 
     const isPerModelQuotaProvider = hasPerModelQuota(provider, model, connectionPassthroughModels);
+    const isNvidiaModelGone = provider === "nvidia" && status === 410;
     const modelLockoutOptions = { maxCooldownMs: effectiveProviderProfile?.maxCooldownMs };
     if (
       isPerModelQuotaProvider &&
       provider &&
       provider !== "codex" &&
       model &&
-      (status === 404 || status === 429 || status >= 500)
+      (status === 404 || isNvidiaModelGone || status === 429 || status >= 500)
     ) {
       const reason =
-        status === 404
+        status === 404 || isNvidiaModelGone
           ? "not_found"
           : status === 429 && fallbackResult.reason === RateLimitReason.QUOTA_EXHAUSTED
             ? "quota_exhausted"
@@ -2046,7 +1993,10 @@ export async function markAccountUnavailable(
         ? "model"
         : getQuotaScopeLabelForProvider(provider, model);
       const antigravityFamilyInferredBaseCooldownMs =
-        !usesExactAntigravityLock && provider === "antigravity" && quotaScope === "family" && status === 429
+        !usesExactAntigravityLock &&
+        provider === "antigravity" &&
+        quotaScope === "family" &&
+        status === 429
           ? ANTIGRAVITY_FAMILY_INFERRED_BASE_COOLDOWN_MS
           : null;
       const lockout = recordModelLockoutFailure(
@@ -2055,7 +2005,7 @@ export async function markAccountUnavailable(
         model,
         reason,
         status,
-        status === 404
+        status === 404 || isNvidiaModelGone
           ? (effectiveProviderProfile?.baseCooldownMs ?? COOLDOWN_MS.notFoundLocal)
           : (antigravityFamilyInferredBaseCooldownMs ??
               fallbackResult.baseCooldownMs ??
@@ -2352,7 +2302,6 @@ export interface RecoveredStateExpectation {
   lastErrorAt: string | null;
   rateLimitedUntil: string | null;
 }
-
 export async function clearRecoveredProviderState(
   credentials: Partial<RecoverableConnectionState> | null,
   expectedState?: RecoveredStateExpectation
@@ -2373,12 +2322,10 @@ export async function clearRecoveredProviderState(
   await clearAccountError(credentials.connectionId, credentials);
   return { applied: true };
 }
-
 type AuthRequestLike = {
   headers?: AuthRequestHeaders | null;
   url?: string | null;
 };
-
 function readNonEmptyUrlToken(request: AuthRequestLike): string | null {
   if (typeof request?.url !== "string" || request.url.trim().length === 0) return null;
 

stryker.conf.json

@@ -247,6 +247,7 @@
       "tests/unit/no-memory-header.test.ts",
       "tests/unit/noauth-autocombo-lockout-7623.test.ts",
       "tests/unit/non-streaming-sse-terminal-typescan-4459.test.ts",
+      "tests/unit/nvidia-410-model-scope.test.ts",
       "tests/unit/nvidia-passthrough-models-6773.test.ts",
       "tests/unit/nvidia-quota-phase1.test.ts",
       "tests/unit/oauth-providers-config.test.ts",

tests/unit/nvidia-410-model-scope.test.ts

@@ -0,0 +1,196 @@
+import test from "node:test";
+import assert from "node:assert/strict";
+import fs from "node:fs";
+import os from "node:os";
+import path from "node:path";
+
+const TEST_DATA_DIR = fs.mkdtempSync(path.join(os.tmpdir(), "omniroute-nvidia-410-model-scope-"));
+
+process.env.DATA_DIR = TEST_DATA_DIR;
+process.env.API_KEY_SECRET = process.env.API_KEY_SECRET || "nvidia-410-model-scope-test-secret";
+
+const core = await import("../../src/lib/db/core.ts");
+const providersDb = await import("../../src/lib/db/providers.ts");
+const auth = await import("../../src/sse/services/auth.ts");
+const fallback = await import("../../open-sse/services/accountFallback.ts");
+
+const DEAD_MODEL = "deepseek-ai/deepseek-v4-pro";
+const HEALTHY_MODEL = "z-ai/glm-5.2";
+
+const GONE_BODY = JSON.stringify({
+  type: "about:blank",
+  title: "Gone",
+  status: 410,
+  detail:
+    "The model 'deepseek-ai/deepseek-v4-pro' has reached its end of life " +
+    "and is no longer available.",
+});
+
+async function resetStorage() {
+  core.resetDbInstance();
+  fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
+  fs.mkdirSync(TEST_DATA_DIR, { recursive: true });
+}
+
+async function seedNvidiaConnection() {
+  return providersDb.createProviderConnection({
+    provider: "nvidia",
+    authType: "apikey",
+    name: "nvidia-410-model-scope",
+    apiKey: "sk-nvidia-410-model-scope",
+    isActive: true,
+    testStatus: "active",
+    providerSpecificData: {},
+  });
+}
+
+test.beforeEach(async () => {
+  await resetStorage();
+});
+
+test.after(async () => {
+  core.resetDbInstance();
+  fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
+});
+
+test("NVIDIA 410 Gone stays model-scoped and leaves the connection usable", async () => {
+  const connection = await seedNvidiaConnection();
+
+  assert.equal(
+    fallback.hasPerModelQuota("nvidia", DEAD_MODEL),
+    true,
+    "NVIDIA must use per-model failure scoping"
+  );
+
+  const result = await auth.markAccountUnavailable(
+    connection.id,
+    410,
+    GONE_BODY,
+    "nvidia",
+    DEAD_MODEL
+  );
+
+  assert.equal(result.shouldFallback, true);
+
+  const after = await providersDb.getProviderConnectionById(connection.id);
+
+  assert.equal(
+    after?.rateLimitedUntil ?? null,
+    null,
+    "410 for one retired NVIDIA model must not apply a connection-wide cooldown"
+  );
+
+  assert.equal(
+    after?.testStatus,
+    "active",
+    "410 for one retired NVIDIA model must leave the NVIDIA connection active"
+  );
+
+  assert.equal(
+    fallback.isModelLocked("nvidia", connection.id, DEAD_MODEL),
+    true,
+    "the retired model itself should be locked"
+  );
+
+  assert.equal(
+    fallback.isModelLocked("nvidia", connection.id, HEALTHY_MODEL),
+    false,
+    "a healthy sibling NVIDIA model must remain unlocked"
+  );
+
+  const healthyCredentials = await auth.getProviderCredentials("nvidia", null, null, HEALTHY_MODEL);
+
+  assert.equal(
+    healthyCredentials?.connectionId,
+    connection.id,
+    "the same NVIDIA connection must remain selectable for healthy sibling models"
+  );
+});
+
+test("non-per-model provider keeps 410 connection-scoped", async () => {
+  assert.equal(
+    fallback.hasPerModelQuota("openai", DEAD_MODEL),
+    false,
+    "plain OpenAI API-key connections are not per-model quota providers"
+  );
+
+  const connection = await providersDb.createProviderConnection({
+    provider: "openai",
+    authType: "apikey",
+    name: "openai-410-connection-scope",
+    apiKey: "sk-openai-410-connection-scope",
+    isActive: true,
+    testStatus: "active",
+    providerSpecificData: {},
+  });
+
+  const result = await auth.markAccountUnavailable(
+    connection.id,
+    410,
+    "Gone",
+    "openai",
+    DEAD_MODEL
+  );
+
+  assert.equal(result.shouldFallback, true);
+
+  const after = await providersDb.getProviderConnectionById(connection.id);
+
+  assert.ok(
+    after?.rateLimitedUntil,
+    "non-per-model providers should retain the existing connection-level 410 behavior"
+  );
+
+  assert.equal(
+    after?.testStatus,
+    "unavailable",
+    "410 model scoping must not be applied globally to every provider"
+  );
+});
+
+test("other per-model providers retain existing 410 connection scope", async () => {
+  assert.equal(
+    fallback.hasPerModelQuota("gemini", DEAD_MODEL),
+    true,
+    "Gemini provides a non-NVIDIA per-model control case"
+  );
+
+  const connection = await providersDb.createProviderConnection({
+    provider: "gemini",
+    authType: "apikey",
+    name: "gemini-410-control",
+    apiKey: "sk-gemini-410-control",
+    isActive: true,
+    testStatus: "active",
+    providerSpecificData: {},
+  });
+
+  const result = await auth.markAccountUnavailable(
+    connection.id,
+    410,
+    "Gone",
+    "gemini",
+    DEAD_MODEL
+  );
+
+  assert.equal(result.shouldFallback, true);
+
+  const after = await providersDb.getProviderConnectionById(connection.id);
+
+  assert.ok(
+    after?.rateLimitedUntil,
+    "410 must remain connection-scoped for per-model providers without an explicit 410 contract"
+  );
+
+  assert.equal(
+    after?.testStatus,
+    "unavailable",
+    "the NVIDIA-specific 410 fix must not change other provider semantics"
+  );
+
+  assert.equal(
+    fallback.isModelLocked("gemini", connection.id, DEAD_MODEL),
+    false,
+    "a generic per-model provider must not inherit NVIDIA's 410 model lock"
+  );
+});

tests/unit/reasoning-cache.test.ts

@@ -865,12 +865,11 @@ describe("Reasoning Replay Cache — Translator Replay", () => {
         }),
       },
     });
-    // The non-tool-call cache key is built as `getAssistantMessageCacheKey(result, messageIndex)`
-    // where messageIndex is the assistant message's real position in the `messages`
-    // array (index 1 here: user, assistant, user) — matching what the write side
-    // (chatCore.ts) now caches under once the response is generated.
+    // NOTE: the non-tool-call cache key is built as `getAssistantMessageCacheKey(result, 0)`
+    // — the message index is hardcoded to 0 in the translator, so the key is always
+    // `request:<id>:message:0` regardless of the assistant message's actual position.
     cacheReasoning(
-      "request:req-plain-1:message:1",
+      "request:req-plain-1:message:0",
       "deepseek",
       "deepseek-v4-pro",
       "Real cached plain-turn reasoning"
@@ -900,60 +899,6 @@ describe("Reasoning Replay Cache — Translator Replay", () => {
     );
     assert.equal(getReasoningCacheServiceStats().replays, 1);
   });
-
-  it("write side (chatCore's messageIndex) and read side (translateRequest) agree on the same key end-to-end", () => {
-    // Regression for a mismatch where chatCore.ts always cached under
-    // `messageIndex: 0` (the position of the response within *its own* choices
-    // array) while translateRequest's read side looked up the message's real
-    // position in the *next* turn's full history — the two never agreed once a
-    // conversation went past its first assistant turn, so replay silently
-    // fell back to the placeholder in real multi-turn usage.
-    clearReasoningCacheAll();
-    clearModelsDevCapabilities();
-    saveModelsDevCapabilities({
-      deepseek: {
-        "deepseek-v4-pro": buildCapability({
-          interleaved_field: "reasoning_content",
-          reasoning: true,
-          tool_call: true,
-        }),
-      },
-    });
-
-    // Turn 1: the incoming request has a single user message (length 1), so
-    // the assistant response chatCore is about to cache will occupy index 1
-    // once it's appended to history for turn 2 — mirroring
-    // `messageIndex: bodyMessages.length` in chatCore.ts.
-    const turn1RequestBody = { messages: [{ role: "user", content: "hi" }] };
-    cacheReasoningFromAssistantMessage(
-      { role: "assistant", content: "Hello! How can I help?", reasoning_content: "real reasoning" },
-      "deepseek",
-      "deepseek-v4-pro",
-      { requestId: "req-e2e-1", messageIndex: turn1RequestBody.messages.length }
-    );
-
-    // Turn 2: client replays the full history including the cached assistant
-    // turn, now genuinely at index 1.
-    const translated = translateRequest(
-      FORMATS.OPENAI,
-      FORMATS.OPENAI,
-      "deepseek-v4-pro",
-      {
-        request_id: "req-e2e-1",
-        messages: [
-          { role: "user", content: "hi" },
-          { role: "assistant", content: "Hello! How can I help?" },
-          { role: "user", content: "tell me more" },
-        ],
-      },
-      false,
-      null,
-      "deepseek"
-    );
-
-    assert.equal(translated.messages[1].reasoning_content, "real reasoning");
-    assert.equal(getReasoningCacheServiceStats().replays, 1);
-  });
 });
 
 describe("Reasoning Replay Cache — API Route", () => {

tests/unit/translator-helper-branches.test.ts

@@ -632,7 +632,7 @@ test("translateRequest replays cached reasoning-only messages when interleaved f
     },
   });
   cacheReasoningByKey(
-    "request:req_reasoning_only:message:1",
+    "request:req_reasoning_only:message:0",
     "deepseek",
     "deepseek-v4-flash",
     "cached reasoning only"
@@ -690,131 +690,138 @@ test("translateRequest does not replay reasoning-only messages for non-DeepSeek
   clearReasoningCacheAll();
 });
 
-test("translateRequest uses Kimi Coding's empty thinking marker instead of cached replay", () => {
-  clearReasoningCacheAll();
-  cacheReasoningByKey(
-    "toolu_kimi_claude",
-    "kimi-coding",
-    "kimi-for-coding",
-    "cached thinking for Kimi tool call"
-  );
+  test("translateRequest uses Kimi Coding's empty thinking marker instead of cached replay", () => {
+    clearReasoningCacheAll();
+    cacheReasoningByKey(
+      "toolu_kimi_claude",
+      "kimi-coding",
+      "kimi-for-coding",
+      "cached thinking for Kimi tool call"
+    );
 
-  // Claude-format request: assistant has tool_use in content[] but NO thinking block
-  // This simulates the scenario that causes infinite loops
-  const result = translateRequest(
-    FORMATS.OPENAI,
-    FORMATS.CLAUDE,
-    "kimi-for-coding",
-    {
-      reasoning_effort: "high",
-      messages: [
-        { role: "user", content: "read the file" },
-        {
-          role: "assistant",
-          content: [
-            {
-              type: "tool_use",
-              id: "toolu_kimi_claude",
-              name: "read_file",
-              input: { path: "test.ts" },
-            },
-          ],
-        },
-        { role: "tool", tool_call_id: "toolu_kimi_claude", content: "file data" },
-      ],
-    },
-    false,
-    null,
-    "kimi-coding"
-  );
+    // Claude-format request: assistant has tool_use in content[] but NO thinking block
+    // This simulates the scenario that causes infinite loops
+    const result = translateRequest(
+      FORMATS.OPENAI,
+      FORMATS.CLAUDE,
+      "kimi-for-coding",
+      {
+        reasoning_effort: "high",
+        messages: [
+          { role: "user", content: "read the file" },
+          {
+            role: "assistant",
+            content: [
+              {
+                type: "tool_use",
+                id: "toolu_kimi_claude",
+                name: "read_file",
+                input: { path: "test.ts" },
+              },
+            ],
+          },
+          { role: "tool", tool_call_id: "toolu_kimi_claude", content: "file data" },
+        ],
+      },
+      false,
+      null,
+      "kimi-coding"
+    );
 
-  const assistantMsg = result.messages.find((m) => m.role === "assistant");
-  assert.ok(assistantMsg, "assistant message should exist");
-  assert.ok(Array.isArray(assistantMsg.content), "content should be array");
+    const assistantMsg = result.messages.find((m) => m.role === "assistant");
+    assert.ok(assistantMsg, "assistant message should exist");
+    assert.ok(Array.isArray(assistantMsg.content), "content should be array");
 
-  // Kimi Code CLI 0.26 sends an explicit empty thinking marker before tool_use.
-  const thinkingBlock = assistantMsg.content.find((b) => b?.type === "thinking");
-  assert.ok(thinkingBlock, "thinking block should be injected");
-  assert.equal(thinkingBlock.thinking, "");
+    // Kimi Code CLI 0.26 sends an explicit empty thinking marker before tool_use.
+    const thinkingBlock = assistantMsg.content.find((b) => b?.type === "thinking");
+    assert.ok(thinkingBlock, "thinking block should be injected");
+    assert.equal(thinkingBlock.thinking, "");
 
-  // Thinking block should appear before tool_use
-  const thinkingIdx = assistantMsg.content.indexOf(thinkingBlock);
-  const toolUseIdx = assistantMsg.content.findIndex((b) => b?.type === "tool_use");
-  assert.ok(thinkingIdx < toolUseIdx, "thinking block should be before tool_use");
+    // Thinking block should appear before tool_use
+    const thinkingIdx = assistantMsg.content.indexOf(thinkingBlock);
+    const toolUseIdx = assistantMsg.content.findIndex((b) => b?.type === "tool_use");
+    assert.ok(thinkingIdx < toolUseIdx, "thinking block should be before tool_use");
 
-  assert.equal(getReasoningCacheServiceStats().replays, 0);
-  clearReasoningCacheAll();
-});
+    assert.equal(getReasoningCacheServiceStats().replays, 0);
+    clearReasoningCacheAll();
+  });
 
-test("translateRequest uses an empty Kimi Coding thinking marker on cache miss", () => {
-  clearReasoningCacheAll();
+  test("translateRequest uses an empty Kimi Coding thinking marker on cache miss", () => {
+    clearReasoningCacheAll();
 
-  const result = translateRequest(
-    FORMATS.OPENAI,
-    FORMATS.CLAUDE,
-    "kimi-for-coding",
-    {
-      reasoning_effort: "high",
-      messages: [
-        { role: "user", content: "do it" },
-        {
-          role: "assistant",
-          content: [{ type: "tool_use", id: "toolu_miss", name: "bash", input: { command: "ls" } }],
-        },
-        { role: "tool", tool_call_id: "toolu_miss", content: "output" },
-      ],
-    },
-    false,
-    null,
-    "kimi-coding"
-  );
+    const result = translateRequest(
+      FORMATS.OPENAI,
+      FORMATS.CLAUDE,
+      "kimi-for-coding",
+      {
+        reasoning_effort: "high",
+        messages: [
+          { role: "user", content: "do it" },
+          {
+            role: "assistant",
+            content: [
+              { type: "tool_use", id: "toolu_miss", name: "bash", input: { command: "ls" } },
+            ],
+          },
+          { role: "tool", tool_call_id: "toolu_miss", content: "output" },
+        ],
+      },
+      false,
+      null,
+      "kimi-coding"
+    );
 
-  const assistantMsg = result.messages.find((m) => m.role === "assistant");
-  assert.ok(assistantMsg, "assistant message should exist");
+    const assistantMsg = result.messages.find((m) => m.role === "assistant");
+    assert.ok(assistantMsg, "assistant message should exist");
 
-  const thinkingBlock =
-    Array.isArray(assistantMsg.content) && assistantMsg.content.find((b) => b?.type === "thinking");
-  assert.ok(thinkingBlock, "thinking block should be injected on cache miss");
-  assert.equal(thinkingBlock.thinking, "");
+    const thinkingBlock =
+      Array.isArray(assistantMsg.content) &&
+      assistantMsg.content.find((b) => b?.type === "thinking");
+    assert.ok(thinkingBlock, "thinking block should be injected on cache miss");
+    assert.equal(thinkingBlock.thinking, "");
 
-  clearReasoningCacheAll();
-});
+    clearReasoningCacheAll();
+  });
 
-test("translateRequest does NOT inject duplicate thinking for Claude-format messages with existing thinking block", () => {
-  clearReasoningCacheAll();
+  test("translateRequest does NOT inject duplicate thinking for Claude-format messages with existing thinking block", () => {
+    clearReasoningCacheAll();
 
-  const result = translateRequest(
-    FORMATS.OPENAI,
-    FORMATS.CLAUDE,
-    "kimi-for-coding",
-    {
-      messages: [
-        { role: "user", content: "hi" },
-        {
-          role: "assistant",
-          content: [
-            { type: "thinking", thinking: "I already have this" },
-            { type: "tool_use", id: "toolu_existing", name: "read", input: {} },
-          ],
-        },
-        { role: "tool", tool_call_id: "toolu_existing", content: "data" },
-      ],
-    },
-    false,
-    null,
-    "kimi-coding"
-  );
+    const result = translateRequest(
+      FORMATS.OPENAI,
+      FORMATS.CLAUDE,
+      "kimi-for-coding",
+      {
+        messages: [
+          { role: "user", content: "hi" },
+          {
+            role: "assistant",
+            content: [
+              { type: "thinking", thinking: "I already have this" },
+              { type: "tool_use", id: "toolu_existing", name: "read", input: {} },
+            ],
+          },
+          { role: "tool", tool_call_id: "toolu_existing", content: "data" },
+        ],
+      },
+      false,
+      null,
+      "kimi-coding"
+    );
 
-  const assistantMsg = result.messages.find((m) => m.role === "assistant");
-  const thinkingBlocks =
-    Array.isArray(assistantMsg.content) &&
-    assistantMsg.content.filter((b) => b?.type === "thinking");
-  assert.equal(thinkingBlocks?.length, 1, "should have exactly one thinking block (no duplicate)");
-  assert.equal(
-    thinkingBlocks[0].thinking,
-    "I already have this",
-    "original thinking should be preserved"
-  );
+    const assistantMsg = result.messages.find((m) => m.role === "assistant");
+    const thinkingBlocks =
+      Array.isArray(assistantMsg.content) &&
+      assistantMsg.content.filter((b) => b?.type === "thinking");
+    assert.equal(
+      thinkingBlocks?.length,
+      1,
+      "should have exactly one thinking block (no duplicate)"
+    );
+    assert.equal(
+      thinkingBlocks[0].thinking,
+      "I already have this",
+      "original thinking should be preserved"
+    );
 
-  clearReasoningCacheAll();
-});
+    clearReasoningCacheAll();
+  });