Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors
TypeScript a2aai-agentsai-gatewayanthropicclaudeclaude-codeclinecodexcopilotcursordeepseekfree-aigeminikimillm-gatewaymcpopenaiopenai-proxyqwentoken-saver
fix(combo): fall back across targets on all 400 responses (#1713)
Randi42952ee42f5d
diff --git a/open-sse/services/accountFallback.ts b/open-sse/services/accountFallback.tsindex 19c8be2e43..c1b02de5d9 100644--- a/open-sse/services/accountFallback.ts+++ b/open-sse/services/accountFallback.ts@@ -1016,7 +1016,8 @@ export function checkFallbackError(};}- // Generic 400 — same request will likely fail on all accounts; don't fallback.+ // Generic 400 is not account-fallback-worthy. Combo routing may still try a+ // different provider/model because combo fallback is target-level orchestration.return { shouldFallback: false, cooldownMs: 0, reason: RateLimitReason.UNKNOWN };}diff --git a/open-sse/services/combo.ts b/open-sse/services/combo.tsindex a85848b11a..a1b1477618 100644--- a/open-sse/services/combo.ts+++ b/open-sse/services/combo.ts@@ -20,7 +20,6 @@ import { fisherYatesShuffle, getNextFromDeck } from "../../src/shared/utils/shufimport { parseModel } from "./model.ts";import { applyComboAgentMiddleware, injectModelTag } from "./comboAgentMiddleware.ts";import { classifyWithConfig, DEFAULT_INTENT_CONFIG } from "./intentClassifier.ts";-import { CONTEXT_OVERFLOW_REGEX } from "./errorClassifier.ts";import { selectProvider as selectAutoProvider } from "./autoCombo/engine.ts";import { selectWithStrategy } from "./autoCombo/routerStrategy.ts";import { getTaskFitness } from "./autoCombo/taskFitness.ts";@@ -41,16 +40,6 @@ import {getComboStepWeight,normalizeComboStep,} from "../../src/lib/combos/steps.ts";--function isProviderBreakerOpenResponse(- result: Response,- errorBody?: { error?: { code?: string | null } } | null-) {- return (- result.headers.get("x-omniroute-provider-breaker") === "open" ||- errorBody?.error?.code === "provider_circuit_open"- );-}import {getConnectionRoutingTags,matchesRoutingTags,@@ -60,51 +49,6 @@ import {// Status codes that should mark round-robin target semaphores as cooling down.const TRANSIENT_FOR_SEMAPHORE = [429, 502, 503, 504];-const COMBO_BAD_REQUEST_FALLBACK_PATTERNS = [- /\bprohibited_content\b/i,- /request blocked by .*api/i,- /provided message roles? is not valid/i,- /unsupported .*message role/i,- /no such tool available/i,- /unsupported content part type/i,- /tool(?:_call|_use)? .* not (?:available|found)/i,- /third-party apps/i,- CONTEXT_OVERFLOW_REGEX,- // Model not supported/found — permanent model-level error, try next combo target- /no provider supported/i,- /model not found/i,- /model not available/i,- /unsupported model/i,- /model.*has no provider/i,- // Function calling format error — model doesn't support this capability- /function\.?arguments.*(must be|should be|\u5fc5\u987b).*(json|JSON)/i,- /tool.*arguments.*invalid/i,- /function.*parameter.*(invalid|format)/i,- // Input length range error — model-specific context limit- /range of input length/i,- /input length should be/i,- // Transient 400 errors from upstream — should fallback to next combo target- /\u670d\u52a1\u9047\u5230\u4e86\u4e00\u70b9\u5c0f\u72b6\u51b5/i, // ModelScope/Qwen transient error- /\u62b1\u6b49.*?\u654f\u611f\u5185\u5bb9.*?\u8bf7\u68c0\u67e5/i, // ModelScope/Qwen content moderation with context- /\u5185\u5bb9.*?\u654f\u611f.*?(?:\u65e0\u6cd5|\u8fc7\u6ee4)/i, // Content sensitivity block- /\u65e0\u6cd5\u54cd\u5e94.*?\u8bf7\u6c42/i, // "unable to respond to request"- /\u7a0d\u540e\u91cd\u8bd5/i, // "retry later" in Chinese- /temporary.*error/i,- /transient.*error/i,- /service.*unavailable/i,- /please.*try.*again/i,- // Rate limit errors — some providers return 400 instead of 429- /\brate.?-?limit.?(?:exceeded|reached|hit)/i,- /too many requests/i,- /\u8bf7\u6c42\u8fc7\u4e8e\u9891\u7e41/i, // Chinese rate limit message- // Tool call function name errors — model-specific, try next combo target- /\bfunction'?s? name (?:can't|can not|is|has) (?:blank|empty|missing)/i,- /function.*name.*(?:blank|empty|missing)/i,- /tool_call.*name.*(?:blank|empty|missing)/i,- // Anthropic thinking block signature errors — stale/expired signatures cannot be retried (#1696)- /invalid.*signature.*thinking/i,-];-// Patterns that signal all accounts for a provider are rate-limited / exhausted.// Used to detect 503 responses from handleNoCredentials so combo can fallback.const ALL_ACCOUNTS_RATE_LIMITED_PATTERNS = [/unavailable/i, /service temporarily unavailable/i];@@ -748,12 +692,6 @@ function extractPromptForIntent(body) {return "";}-export function shouldFallbackComboBadRequest(status, errorText) {- if (status !== 400 || !errorText) return false;- const message = String(errorText);- return COMBO_BAD_REQUEST_FALLBACK_PATTERNS.some((pattern) => pattern.test(message));-}-function mapIntentToTaskType(intent) {switch (intent) {case "code":@@ -1703,7 +1641,6 @@ export async function handleComboChat({}}- const providerBreakerOpen = isProviderBreakerOpenResponse(result, errorBody);const isStreamReadinessTimeout =result.status === 504 && isStreamReadinessTimeoutErrorBody(errorBody);@@ -1722,15 +1659,11 @@ export async function handleComboChat({return result;}- if (providerBreakerOpen) {- lastError = errorText || String(result.status);- if (!lastStatus) lastStatus = result.status;- if (i > 0) fallbackCount++;- log.info("COMBO", `Skipping ${modelStr}: provider circuit breaker OPEN for ${provider}`);- break;- }-- const { shouldFallback, cooldownMs } = checkFallbackError(+ // Combo fallback is target-level orchestration: a non-ok target response is+ // treated as local to that target and the combo continues to the next target.+ // Error classification is retained only for retry/cooldown pacing; it must+ // not decide whether fallback happens, including for generic 400 responses.+ const { cooldownMs } = checkFallbackError(result.status,errorText,0,@@ -1739,27 +1672,6 @@ export async function handleComboChat({result.headers,profile);- const comboBadRequestFallback = shouldFallbackComboBadRequest(result.status, errorText);-- if (!shouldFallback && !comboBadRequestFallback) {- log.warn("COMBO", `Model ${modelStr} failed (no fallback)`, { status: result.status });- recordComboRequest(combo.name, modelStr, {- success: false,- latencyMs: Date.now() - startTime,- fallbackCount,- strategy,- target: toRecordedTarget(target),- });- recordedAttempts++;- return result;- }-- if (comboBadRequestFallback) {- log.info(- "COMBO",- `Treating provider-scoped 400 from ${modelStr} as model-local failure; trying next combo target`- );- }// Check if this is a transient error worth retrying on same modelconst isTransient =@@ -2068,20 +1980,14 @@ async function handleRoundRobinCombo({}}- if (isProviderBreakerOpenResponse(result, errorBody as Record<string, unknown> | null)) {- lastError = errorText || String(result.status);- if (!lastStatus) lastStatus = result.status;- if (offset > 0) fallbackCount++;- log.info(- "COMBO-RR",- `Skipping ${modelStr}: provider circuit breaker OPEN for ${provider}`- );- break;- }const isStreamReadinessTimeout =result.status === 504 && isStreamReadinessTimeoutErrorBody(errorBody);- const { shouldFallback, cooldownMs } = checkFallbackError(+ // Round-robin uses the same target-level fallback rule as other combo+ // strategies: non-ok target responses fall through to the next target.+ // Classification stays here only to support cooldown/semaphore pacing,+ // not to decide whether fallback is allowed.+ const { cooldownMs } = checkFallbackError(result.status,errorText,0,@@ -2090,7 +1996,6 @@ async function handleRoundRobinCombo({result.headers,profile);- const comboBadRequestFallback = shouldFallbackComboBadRequest(result.status, errorText);const isAllAccountsRateLimited = isAllAccountsRateLimitedResponse(result.status,@@ -2105,27 +2010,9 @@ async function handleRoundRobinCombo({}if (isAllAccountsRateLimited) {- log.info(- "COMBO",- `All accounts rate-limited for ${modelStr}, falling back to next model`- );- } else if (!shouldFallback && !comboBadRequestFallback) {- log.warn("COMBO-RR", `${modelStr} failed (no fallback)`, { status: result.status });- recordComboRequest(combo.name, modelStr, {- success: false,- latencyMs: Date.now() - startTime,- fallbackCount,- strategy: "round-robin",- target: toRecordedTarget(target),- });- recordedAttempts++;- return result;- }-- if (comboBadRequestFallback) {log.info("COMBO-RR",- `Treating provider-scoped 400 from ${modelStr} as model-local failure; trying next model`+ `All accounts rate-limited for ${modelStr}, falling back to next model`);}diff --git a/tests/integration/chatcore-compression-integration.test.ts b/tests/integration/chatcore-compression-integration.test.tsindex 2ab34d8fa0..65db274628 100644--- a/tests/integration/chatcore-compression-integration.test.ts+++ b/tests/integration/chatcore-compression-integration.test.ts@@ -49,6 +49,7 @@ test("chatCore integration: compressContext called proactively when context exce// Use the same pattern as test 3 which successfully tests compressionconst body = {model,+ stream: false,messages: [{ role: "system", content: "You are helpful." },{ role: "user", content: "x".repeat(50000) },@@ -62,11 +63,12 @@ test("chatCore integration: compressContext called proactively when context exce};// Create provider connection- const connectionId = await providersDb.createProviderConnection({+ const connection = await providersDb.createProviderConnection({provider,apiKey: "test-key",isActive: true,});+ const connectionId = connection.id;// Mock fetch to capture the requestlet capturedBody: any = null;@@ -125,6 +127,7 @@ test("chatCore integration: compressContext NOT called when context is below 85%const smallMessage = "Hello, how are you?";const body = {model,+ stream: false,messages: [{ role: "system", content: "You are helpful." },{ role: "user", content: smallMessage },@@ -138,11 +141,12 @@ test("chatCore integration: compressContext NOT called when context is below 85%);// Create provider connection- const connectionId = await providersDb.createProviderConnection({+ const connection = await providersDb.createProviderConnection({provider,apiKey: "test-key",isActive: true,});+ const connectionId = connection.id;// Mock fetch to capture the requestlet capturedBody: any = null;@@ -195,6 +199,7 @@ test("chatCore integration: compression preserves message structure", async () =const body = {model,+ stream: false,messages: [{ role: "system", content: "You are helpful." },{ role: "user", content: "x".repeat(50000) },@@ -206,11 +211,12 @@ test("chatCore integration: compression preserves message structure", async () =};// Create provider connection- const connectionId = await providersDb.createProviderConnection({+ const connection = await providersDb.createProviderConnection({provider,apiKey: "test-key",isActive: true,});+ const connectionId = connection.id;// Mock fetch to capture the requestlet capturedBody: any = null;@@ -267,6 +273,7 @@ test("chatCore integration: compression handles tool messages", async () => {const longToolOutput = "x".repeat(10000);const body = {model,+ stream: false,messages: [{ role: "system", content: "You are helpful." },{ role: "user", content: "Run the tool" },@@ -277,11 +284,12 @@ test("chatCore integration: compression handles tool messages", async () => {};// Create provider connection- const connectionId = await providersDb.createProviderConnection({+ const connection = await providersDb.createProviderConnection({provider,apiKey: "test-key",isActive: true,});+ const connectionId = connection.id;// Mock fetch to capture the requestlet capturedBody: any = null;@@ -333,11 +341,12 @@ test("chatCore integration: combo requests run proactive compression before Kiroconst provider = "kiro";const model = "claude-sonnet-4.5";- const connectionId = await providersDb.createProviderConnection({+ const connection = await providersDb.createProviderConnection({provider,apiKey: "test-key",isActive: true,});+ const connectionId = connection.id;await combosDb.createCombo({name: "test-kiro-compression-combo",diff --git a/tests/integration/resilience-http-e2e.test.ts b/tests/integration/resilience-http-e2e.test.tsindex 8942d7c32f..e0b10cc0da 100644--- a/tests/integration/resilience-http-e2e.test.ts+++ b/tests/integration/resilience-http-e2e.test.ts@@ -620,7 +620,8 @@ test("wait-for-cooldown honors upstream Retry-After when enabled", async () => {assert.equal(result.response.status, 200, JSON.stringify(result.json));assert.equal(result.json.choices[0].message.content, "wait-for-cooldown via upstream hint");- assert.equal(relay.getState(TOKENS.p3).hits, 2);+ const hits = relay.getState(TOKENS.p3).hits;+ assert.ok(hits >= 2, `expected at least one retry after cooldown, got ${hits} hits`);assert.ok(elapsed >= 800, `expected upstream wait >= 800ms, got ${elapsed}ms`);});@@ -655,7 +656,8 @@ test("connection cooldown can ignore upstream Retry-After and use the configuredassert.equal(result.response.status, 200, JSON.stringify(result.json));assert.equal(result.json.choices[0].message.content, "ignored upstream retry hint");- assert.equal(relay.getState(TOKENS.p4).hits, 2);+ const hits = relay.getState(TOKENS.p4).hits;+ assert.ok(hits >= 2, `expected at least one retry after cooldown, got ${hits} hits`);assert.ok(elapsed < 5_000,`expected ignored upstream hint to avoid a 30s wait, got ${elapsed}ms`diff --git a/tests/unit/combo-context-relay.test.ts b/tests/unit/combo-context-relay.test.tsindex b3aa09f78d..61420af029 100644--- a/tests/unit/combo-context-relay.test.ts+++ b/tests/unit/combo-context-relay.test.ts@@ -177,14 +177,13 @@ test("handleComboChat context-relay skips unavailable models and falls through tassert.deepEqual(calls, ["openai/gpt-4o-mini"]);});-test("handleComboChat context-relay skips targets that report an open provider circuit breaker", async () => {+test("handleComboChat context-relay treats provider circuit breaker responses as ordinary target failures", async () => {const combo = {name: "relay-breaker",strategy: "context-relay",models: ["codex/gpt-5.4", "openai/gpt-4o-mini"],config: { maxRetries: 0 },};- const log = createLog();const calls = [];const result = await handleComboChat({@@ -200,16 +199,13 @@ test("handleComboChat context-relay skips targets that report an open provider creturn okResponse();},isModelAvailable: async () => true,- log,+ log: createLog(),settings: null,allCombos: null,});assert.equal(result.ok, true);assert.deepEqual(calls, ["codex/gpt-5.4", "openai/gpt-4o-mini"]);- assert.ok(- log.entries.some((entry) => String(entry.msg).includes("provider circuit breaker OPEN"))- );});test("handleComboChat context-relay persists a handoff when codex quota reaches the warning threshold", async () => {diff --git a/tests/unit/combo-routing-engine.test.ts b/tests/unit/combo-routing-engine.test.tsindex 29fab4fd29..53f34b233f 100644--- a/tests/unit/combo-routing-engine.test.ts+++ b/tests/unit/combo-routing-engine.test.ts@@ -14,7 +14,6 @@ const {validateComboDAG,resolveNestedComboModels,handleComboChat,- shouldFallbackComboBadRequest,} = await import("../../open-sse/services/combo.ts");const { normalizeComboStep } = await import("../../src/lib/combos/steps.ts");const { registerStrategy } = await import("../../open-sse/services/autoCombo/routerStrategy.ts");@@ -246,9 +245,7 @@ test("handleComboChat priority strategy defaults to first model and records succisModelAvailable: async () => true,log: createLog(),settings: null,- relayOptions: null as any,allCombos: null,- relayOptions: null,});const metrics = getComboMetrics("priority-default");@@ -324,7 +321,6 @@ test("handleComboChat priority strategy honors composite tier order before fallbsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -359,7 +355,6 @@ test("handleComboChat weighted strategy selects by weight and falls back in descsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -395,7 +390,6 @@ test("handleComboChat weighted strategy falls back to uniform random when all wesettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -429,7 +423,6 @@ test("handleComboChat random strategy uses shuffled model order", async () => {settings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(calls.length, 1);@@ -474,7 +467,6 @@ test("handleComboChat least-used strategy prefers the model with fewer recordedsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(calls[0], "model-c");@@ -498,7 +490,6 @@ test("handleComboChat skips unavailable models and falls through to the next actsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -527,7 +518,6 @@ test("handleComboChat falls through empty successful responses and records failusettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});const metrics = getComboMetrics("quality-fallback");@@ -580,7 +570,6 @@ test("handleComboChat records per-target metrics separately when the same modelsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});const firstStep = normalizeComboStep(combo.models[0], {@@ -619,7 +608,6 @@ test("handleComboChat preserves the first failure status but surfaces the last esettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});const payload = (await result.json()) as any;@@ -650,7 +638,6 @@ test("handleComboChat round-robin rotates sequentially across requests", async (settings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -710,7 +697,6 @@ test("handleComboChat round-robin starts from composite tier default ordering",settings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -750,70 +736,6 @@ test("combo helpers short-circuit safely for missing combos, cycles, and excessi);});-test("shouldFallbackComboBadRequest only flags known provider-scoped 400 patterns", () => {- assert.equal(shouldFallbackComboBadRequest(400, "prohibited_content"), true);- assert.equal(shouldFallbackComboBadRequest(400, "unsupported message role"), true);- assert.equal(shouldFallbackComboBadRequest(400, "tool_call weather_lookup not found"), true);- assert.equal(shouldFallbackComboBadRequest(429, "prohibited_content"), false);- assert.equal(shouldFallbackComboBadRequest(400, null), false);- assert.equal(shouldFallbackComboBadRequest(400, "generic bad request"), false);- // Chinese transient errors (ModelScope/Qwen)- assert.equal(- shouldFallbackComboBadRequest(400, "[400]: 抱歉,服务遇到了一点小状况,请您稍后重试。"),- true- );- assert.equal(shouldFallbackComboBadRequest(400, "服务遇到了一点小状况"), true);- assert.equal(shouldFallbackComboBadRequest(400, "请稍后重试"), true);- // Model not supported errors- assert.equal(- shouldFallbackComboBadRequest(- 400,- "Model id : XiaomiMiMo/MiMo-V2-Flash , has no provider supported"- ),- true- );- assert.equal(shouldFallbackComboBadRequest(400, "no provider supported"), true);- assert.equal(shouldFallbackComboBadRequest(400, "model not found"), true);- assert.equal(shouldFallbackComboBadRequest(400, "model not available"), true);- // Function calling format errors- assert.equal(- shouldFallbackComboBadRequest(400, "function.arguments parameter must be in JSON format"),- true- );- assert.equal(- shouldFallbackComboBadRequest(- 400,- '[400]: <400> InternalError.Algo.InvalidParameter: The "function.arguments" parameter of the code model must be in JSON format.'- ),- true- );- assert.equal(shouldFallbackComboBadRequest(400, "tool arguments invalid format"), true);- // Input length range errors- assert.equal(- shouldFallbackComboBadRequest(400, "Range of input length should be [1, 98304]"),- true- );- assert.equal(shouldFallbackComboBadRequest(400, "input length should be"), true);- // Content moderation errors (should fallback to next model)- assert.equal(- shouldFallbackComboBadRequest(400, "抱歉,您的内容包含敏感内容,请检查后重试"),- true- );- assert.equal(shouldFallbackComboBadRequest(400, "内容存在敏感信息,无法响应"), true);- assert.equal(shouldFallbackComboBadRequest(400, "无法响应该请求"), true);- // Generic "please check" should NOT match (was too broad before)- assert.equal(shouldFallbackComboBadRequest(400, "请检查您的参数"), false);- // Anthropic thinking block signature errors (#1696)- assert.equal(- shouldFallbackComboBadRequest(- 400,- "[400]: messages.31.content.0: Invalid `signature` in `thinking` block"- ),- true- );- assert.equal(shouldFallbackComboBadRequest(400, "Invalid signature in thinking block"), true);-});-test("handleComboChat accepts binary and Responses-style 200 bodies but falls through malformed success payloads", async () => {const binaryResult = await handleComboChat({body: {},@@ -833,7 +755,6 @@ test("handleComboChat accepts binary and Responses-style 200 bodies but falls thsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(binaryResult.ok, true);@@ -856,7 +777,6 @@ test("handleComboChat accepts binary and Responses-style 200 bodies but falls thsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(responsesResult.ok, true);@@ -888,7 +808,6 @@ test("handleComboChat accepts binary and Responses-style 200 bodies but falls thsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(malformedResult.ok, true);@@ -914,7 +833,6 @@ test("handleComboChat accepts text-mode SSE payloads as valid non-streaming passsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -952,7 +870,6 @@ test("handleComboChat falls through invalid JSON and embedded 200 error bodies bsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -988,7 +905,6 @@ test("handleComboChat returns the earliest retry-after when all priority targets},relayOptions: null as any,allCombos: null,- relayOptions: null,});const payload = (await result.json()) as any;@@ -1019,7 +935,6 @@ test("handleComboChat returns 404 model_not_found when a combo has no executable},relayOptions: null as any,allCombos: null,- relayOptions: null,});const payload = (await result.json()) as any;@@ -1052,7 +967,6 @@ test("handleComboChat round-robin returns 404 when no models are configured", as},relayOptions: null as any,allCombos: null,- relayOptions: null,});const payload = (await result.json()) as any;@@ -1099,7 +1013,6 @@ test("handleComboChat round-robin falls through semaphore timeouts and malformed},relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -1143,7 +1056,6 @@ test("handleComboChat round-robin surfaces retry-after metadata after exhausting},relayOptions: null as any,allCombos: null,- relayOptions: null,});const payload = (await result.json()) as any;@@ -1153,13 +1065,47 @@ test("handleComboChat round-robin surfaces retry-after metadata after exhaustingassert.ok(Number(result.headers.get("Retry-After")) >= 1);});-test("handleComboChat round-robin keeps generic 400 errors terminal", async () => {+test("handleComboChat falls through generic 400s when a later priority target succeeds", async () => {const calls: any[] = [];const result = await handleComboChat({body: {},combo: {- name: "rr-terminal-400",+ name: "priority-generic-400-recover",+ strategy: "priority",+ models: ["provider-a/model-a", "provider-b/model-b"],+ config: { maxRetries: 0, retryDelayMs: 1 },+ },+ handleSingleModel: async (_body: any, modelStr: any) => {+ calls.push(modelStr);+ if (modelStr === "provider-a/model-a") {+ return new Response(JSON.stringify({ error: { message: "Instructions are required" } }), {+ status: 400,+ headers: { "content-type": "application/json" },+ });+ }+ return okResponse({ choices: [{ message: { content: "recovered" } }] });+ },+ isModelAvailable: async () => true,+ log: createLog(),+ settings: null,+ relayOptions: null as any,+ allCombos: null,+ });++ const payload = (await result.json()) as any;+ assert.equal(result.status, 200);+ assert.equal(payload.choices[0].message.content, "recovered");+ assert.deepEqual(calls, ["provider-a/model-a", "provider-b/model-b"]);+});++test("handleComboChat round-robin falls through generic 400s when a later model succeeds", async () => {+ const calls: any[] = [];++ const result = await handleComboChat({+ body: {},+ combo: {+ name: "rr-generic-400-recover",strategy: "round-robin",models: ["model-a", "model-b"],},@@ -1185,15 +1131,13 @@ test("handleComboChat round-robin keeps generic 400 errors terminal", async () =},relayOptions: null as any,allCombos: null,- relayOptions: null,});- assert.equal(result.status, 400);- assert.deepEqual(calls, ["model-a"]);- assert.match((await result.json()).error.message, /generic bad request/);+ assert.equal(result.status, 200);+ assert.deepEqual(calls, ["model-a", "model-b"]);});-test("handleComboChat round-robin falls through provider-scoped 400s and returns the final error payload when no target recovers", async () => {+test("handleComboChat round-robin falls through 400s and returns the final error payload when no target recovers", async () => {const calls: any[] = [];const result = await handleComboChat({@@ -1228,7 +1172,6 @@ test("handleComboChat round-robin falls through provider-scoped 400s and returns},relayOptions: null as any,allCombos: null,- relayOptions: null,});const payload = (await result.json()) as any;@@ -1258,7 +1201,6 @@ test("handleComboChat strict-random uses the shared deck without repeating withisettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -1293,7 +1235,6 @@ test("handleComboChat cost-optimized orders models by the cheapest configured insettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -1371,7 +1312,6 @@ test("handleComboChat context-optimized orders models by the largest synced contsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -1394,7 +1334,6 @@ test("handleComboChat returns a 503 when every model is unavailable before execusettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});const payload = (await result.json()) as any;@@ -1402,15 +1341,15 @@ test("handleComboChat returns a 503 when every model is unavailable before execuassert.equal(payload.error.code, "ALL_ACCOUNTS_INACTIVE");});-test("handleComboChat falls through targets that return provider circuit breaker open responses", async () => {+test("handleComboChat treats provider circuit breaker responses as ordinary target failures", async () => {const calls = [];- const log = createLog();const result = await handleComboChat({body: {},combo: {name: "provider-breaker-open",strategy: "priority",models: ["openai/model-a", "openai/model-b"],+ config: { maxRetries: 0 },},handleSingleModel: async (_body, modelStr) => {calls.push(modelStr);@@ -1420,18 +1359,14 @@ test("handleComboChat falls through targets that return provider circuit breakerreturn okResponse();},isModelAvailable: async () => true,- log,+ log: createLog(),settings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);assert.deepEqual(calls, ["openai/model-a", "openai/model-b"]);- assert.ok(- log.entries.some((entry) => String(entry.msg).includes("provider circuit breaker OPEN"))- );});test("handleComboChat auto strategy honors LKGP after filtering to tool-capable models", async () => {@@ -1459,7 +1394,6 @@ test("handleComboChat auto strategy honors LKGP after filtering to tool-capablesettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -1487,7 +1421,6 @@ test("handleComboChat standalone lkgp strategy prioritizes the last known good psettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -1513,7 +1446,6 @@ test("handleComboChat standalone lkgp strategy falls back to original order whensettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -1535,7 +1467,6 @@ test("handleComboChat standalone lkgp strategy updates LKGP after a successful csettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});const persistedProvider = await settingsDb.getLKGP(@@ -1581,7 +1512,6 @@ test("handleComboChat auto strategy falls back to the full pool when tool filter},relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -1616,7 +1546,6 @@ test("handleComboChat auto strategy falls back to rules when a custom router strsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -1651,7 +1580,6 @@ test("handleComboChat auto strategy reads strategyName from combo.config.auto ansettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -1700,7 +1628,6 @@ test("handleComboChat context cache protection pins the model and tags tool-callsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});const payload = (await result.json()) as any;@@ -1732,7 +1659,6 @@ test("handleComboChat context cache protection sanitizes streamed text tags fromsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});const text = await result.text();@@ -1762,7 +1688,6 @@ test("handleComboChat context cache protection injects a hidden tag for tool-calsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});const text = await result.text();@@ -1786,7 +1711,6 @@ test("handleComboChat context cache protection flushes cleanly when a stream endsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});const text = await result.text();@@ -1823,9 +1747,8 @@ test("handleComboChat round-robin resolves nested combos and returns inactive whassert.equal(payload.error.code, "ALL_ACCOUNTS_INACTIVE");});-test("handleComboChat round-robin skips targets that return provider circuit breaker open responses", async () => {+test("handleComboChat round-robin treats provider circuit breaker responses as ordinary target failures", async () => {const calls = [];- const log = createLog();const result = await handleComboChat({body: {},combo: {@@ -1842,18 +1765,14 @@ test("handleComboChat round-robin skips targets that return provider circuit brereturn okResponse();},isModelAvailable: async () => true,- log,+ log: createLog(),settings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);assert.deepEqual(calls, ["openai/model-a", "openai/model-b"]);- assert.ok(- log.entries.some((entry) => String(entry.msg).includes("provider circuit breaker OPEN"))- );});test("handleComboChat round-robin retries a transient failure on the same model before succeeding", async () => {@@ -1879,14 +1798,13 @@ test("handleComboChat round-robin retries a transient failure on the same modelsettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);assert.deepEqual(calls, ["model-a", "model-a"]);});-test("handleComboChat round-robin recovers from provider-scoped 400s when a later model succeeds", async () => {+test("handleComboChat round-robin recovers from 400s when a later model succeeds", async () => {const calls: any[] = [];const result = await handleComboChat({@@ -1915,7 +1833,6 @@ test("handleComboChat round-robin recovers from provider-scoped 400s when a latesettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});assert.equal(result.ok, true);@@ -1953,7 +1870,6 @@ test("handleComboChat falls back to next model when first model returns all-accosettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});const payload = (await result.json()) as any;@@ -1994,7 +1910,6 @@ test("handleComboChat round-robin falls back when all-accounts-rate-limited 503settings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});const payload = (await result.json()) as any;@@ -2028,7 +1943,6 @@ test("handleComboChat aborts combo when 503 response does NOT contain the unavaisettings: null,relayOptions: null as any,allCombos: null,- relayOptions: null,});const payload = (await result.json()) as any;diff --git a/tests/unit/t23-t24-fallback-resilience.test.ts b/tests/unit/t23-t24-fallback-resilience.test.tsindex d72a0b275f..3fe1dde59b 100644--- a/tests/unit/t23-t24-fallback-resilience.test.ts+++ b/tests/unit/t23-t24-fallback-resilience.test.ts@@ -2,8 +2,7 @@ import test from "node:test";import assert from "node:assert/strict";const { checkFallbackError } = await import("../../open-sse/services/accountFallback.ts");-const { handleComboChat, shouldFallbackComboBadRequest } =- await import("../../open-sse/services/combo.ts");+const { handleComboChat } = await import("../../open-sse/services/combo.ts");const { resetAllCircuitBreakers } = await import("../../src/shared/utils/circuitBreaker.ts");test.beforeEach(() => {@@ -141,8 +140,13 @@ test("T24: all inactive accounts return 503 service_unavailable (not 406)", asynassert.equal(body.error?.code, "ALL_ACCOUNTS_INACTIVE");});-test("combo falls through provider-scoped 400s and reaches the next model", async () => {- const log = createLog();+test("combo falls through 400s and reaches the next model", async () => {+ const calls = [];+ const sequence = [+ { status: 429, message: "No capacity available for model gemini-3.1-pro-preview" },+ { status: 400, message: "bad request" },+ { status: 200 },+ ];const result = await handleComboChat({body: {},@@ -154,29 +158,29 @@ test("combo falls through provider-scoped 400s and reaches the next model", asyn{ model: "aio/gemini-3.1-pro-preview-thinking-high", weight: 0 },{ model: "openrouter/google/gemini-3.1-pro-preview", weight: 0 },],+ config: { maxRetries: 0 },+ },+ handleSingleModel: async (_body, modelStr) => {+ calls.push(modelStr);+ const step = sequence[calls.length - 1] || { status: 200 };+ if (step.status === 200) {+ return new Response(JSON.stringify({ ok: true }), { status: 200 });+ }+ return new Response(JSON.stringify({ error: { message: step.message } }), {+ status: step.status,+ headers: { "content-type": "application/json" },+ });},- handleSingleModel: createStatusSequenceHandler([- { status: 429, message: "No capacity available for model gemini-3.1-pro-preview" },- { status: 400, message: "request blocked by Gemini API: PROHIBITED_CONTENT" },- { status: 200 },- ]),isModelAvailable: () => true,- log,+ log: createLog(),settings: null,allCombos: null,});assert.equal(result.ok, true);- const badRequestLog = log.entries.find((entry) => entry.msg.includes("provider-scoped 400"));- assert.ok(badRequestLog);-});--test("combo bad-request fallback helper keeps generic 400s terminal", () => {- assert.equal(shouldFallbackComboBadRequest(400, "request blocked by Gemini API"), true);- assert.equal(- shouldFallbackComboBadRequest(400, "One or more of the provided message roles is not valid"),- true- );- assert.equal(shouldFallbackComboBadRequest(400, "bad request"), false);- assert.equal(shouldFallbackComboBadRequest(422, "request blocked by Gemini API"), false);+ assert.deepEqual(calls, [+ "free/gemini-3.1-pro-preview",+ "aio/gemini-3.1-pro-preview-thinking-high",+ "openrouter/google/gemini-3.1-pro-preview",+ ]);});