@juspay/neurolink 12.47.3 → 12.47.5

package/dist/utils/errorClassifier.d.ts

@@ -1,7 +1,10 @@
 /**
- * Shared provider-error classification. Every provider's
- * `formatProviderError(error)` delegates here instead of hand-rolling its
+ * Shared provider-error classification. Migrated providers'
+ * `formatProviderError(error)` delegate here instead of hand-rolling their
  * own TimeoutError-check → .includes()-chain → `new XError(...)` ladder.
+ * Not yet migrated (they do not call it): Google AI Studio, SageMaker, the
+ * media and embedding providers (Ideogram, Recraft, Stability, Replicate,
+ * Jina, Voyage) and the System One decision provider.
  *
  * `classifyProviderError` picks the Error subclass + message; it does NOT
  * stamp statusCode/isRetryable/retryAfterMs onto the result — that
@@ -21,10 +24,13 @@ export declare function classifyProviderError(error: unknown, rules: ProviderErr
 /**
  * Generic fallback rule table covering the five categories every
  * OpenAI-compatible provider already hand-rolled near-identically:
- * auth (401), rate limit (429), model-not-found (404), network/connection
- * errors, and 5xx server errors. Providers with a provider-specific auth
- * message (naming the exact env var) prepend one override rule and spread
- * this table after it — see errorClassifier usage in any migrated
+ * auth (401), rate limit (429), model-not-found, network/connection
+ * errors, and 5xx server errors. Model-not-found is a 404 whose text names
+ * the model or deployment as missing, or the old "model not found" message
+ * text at any status; any other 404 stays a plain `ProviderError` carrying
+ * the status and the vendor's message. Providers with a provider-specific
+ * auth message (naming the exact env var) prepend one override rule and
+ * spread this table after it — see errorClassifier usage in any migrated
  * provider's formatProviderError for the pattern.
  */
 export declare const DEFAULT_ERROR_RULES: ProviderErrorRule[];

package/dist/utils/errorClassifier.js

@@ -1,7 +1,10 @@
 /**
- * Shared provider-error classification. Every provider's
- * `formatProviderError(error)` delegates here instead of hand-rolling its
+ * Shared provider-error classification. Migrated providers'
+ * `formatProviderError(error)` delegate here instead of hand-rolling their
  * own TimeoutError-check → .includes()-chain → `new XError(...)` ladder.
+ * Not yet migrated (they do not call it): Google AI Studio, SageMaker, the
+ * media and embedding providers (Ideogram, Recraft, Stability, Replicate,
+ * Jina, Voyage) and the System One decision provider.
  *
  * `classifyProviderError` picks the Error subclass + message; it does NOT
  * stamp statusCode/isRetryable/retryAfterMs onto the result — that
@@ -113,13 +116,20 @@ export function classifyProviderError(error, rules, provider, modelName) {
     const message = typeof rule.message === "function" ? rule.message(ctx) : rule.message;
     return new rule.errorClass(message, provider);
 }
+// A 404 alone is a route answer (a wrong base URL gives the same reply): it only
+// means "missing model" when the text names a model or deployment as absent.
+// The gap is bounded rather than "no dot" because real model ids contain dots.
+const MODEL_404_TEXT = /model[_ ]?not[_ ]?found|unknown model|no such model|invalid model|unsupported model|\b(?:model|deployment)\b.{0,120}\b(?:does not exist|not found|unavailable|not (?:available|supported))\b|\b(?:does not exist|not found)\b.{0,120}\b(?:model|deployment)\b|unable to access.{0,60}\bmodel\b/i;
 /**
  * Generic fallback rule table covering the five categories every
  * OpenAI-compatible provider already hand-rolled near-identically:
- * auth (401), rate limit (429), model-not-found (404), network/connection
- * errors, and 5xx server errors. Providers with a provider-specific auth
- * message (naming the exact env var) prepend one override rule and spread
- * this table after it — see errorClassifier usage in any migrated
+ * auth (401), rate limit (429), model-not-found, network/connection
+ * errors, and 5xx server errors. Model-not-found is a 404 whose text names
+ * the model or deployment as missing, or the old "model not found" message
+ * text at any status; any other 404 stays a plain `ProviderError` carrying
+ * the status and the vendor's message. Providers with a provider-specific
+ * auth message (naming the exact env var) prepend one override rule and
+ * spread this table after it — see errorClassifier usage in any migrated
  * provider's formatProviderError for the pattern.
  */
 export const DEFAULT_ERROR_RULES = [
@@ -135,13 +145,18 @@ export const DEFAULT_ERROR_RULES = [
         message: (ctx) => `${ctx.provider} rate limit exceeded. Please try again later.`,
     },
     {
-        match: (ctx) => ctx.statusCode === 404 ||
-            /model_not_found|model not found/i.test(ctx.message),
+        match: (ctx) => /model_not_found|model not found/i.test(ctx.message) ||
+            (ctx.statusCode === 404 && MODEL_404_TEXT.test(ctx.message)),
         errorClass: InvalidModelError,
         message: (ctx) => ctx.modelName
             ? `${ctx.provider} model '${ctx.modelName}' not found.`
             : `${ctx.provider} model not found.`,
     },
+    {
+        match: (ctx) => ctx.statusCode === 404,
+        errorClass: ProviderError,
+        message: (ctx) => `${ctx.provider} returned HTTP 404: ${ctx.message}`,
+    },
     {
         // Message regex covers providers/SDKs that surface a code as text
         // (e.g. AWS SDK wrapping "ECONNRESET" into its own message). errorCode

package/dist/utils/messageBuilder.js

@@ -2566,7 +2566,14 @@ mediaOptions = {}) {
                 });
                 try {
                     const extracted = await parser.getText();
-                    const pdfText = (extracted?.text ?? "").trim();
+                    // pdf-parse appends a "-- n of N --" marker after every page, so
+                    // extracted.text is never empty; a scan is detected from the
+                    // per-page text instead.
+                    const pageTexts = extracted?.pages?.map((page) => page.text) ?? [
+                        extracted?.text ?? "",
+                    ];
+                    const hasTextLayer = pageTexts.some((text) => text.trim().length > 0);
+                    const pdfText = hasTextLayer ? (extracted?.text ?? "").trim() : "";
                     if (pdfText.length > 0) {
                         content.push({
                             type: "text",
@@ -2574,6 +2581,13 @@ mediaOptions = {}) {
                         });
                         logger.info(`[PDF→Text] ✅ Extracted text for non-vision provider ${provider}: ${name} (${pdfText.length} chars)`);
                     }
+                    else if (providerCanSeeImages) {
+                        content.push({
+                            type: "text",
+                            text: `\n[Attached PDF: ${name} — no extractable text layer (likely a scanned document); page images are attached below.]`,
+                        });
+                        logger.warn(`[PDF→Text] ${name} has no text layer; page images follow`);
+                    }
                     else {
                         content.push({
                             type: "text",

package/dist/utils/modelChoices.d.ts

@@ -15,6 +15,13 @@ import type { CatalogProviderName, ModelChoice } from "../types/index.js";
  *
  * AUTO is also excluded — it never had an entry here either (matches
  * pre-existing behavior: `getDefaultModel(AUTO)` returns `undefined`).
+ *
+ * This table is not what a call with no model uses. The runtime order is the
+ * explicit model, then the provider's environment variable, then the default in
+ * the dynamic model configuration, then the registry default
+ * (`providerRegistry.ts`); the OpenAI row mirrors that registry default. Only
+ * an `OpenAIProvider` constructed directly with none of those falls back to
+ * `gpt-5.4` (`openAI/client.ts`).
  */
 export declare const DEFAULT_MODELS: Record<Exclude<AIProviderName, CatalogProviderName | AIProviderName.AUTO>, string>;
 /**
@@ -56,6 +63,9 @@ export declare function getAllProviderChoices(): string[];
 /**
  * Get the default model for a provider
  *
+ * Reads `DEFAULT_MODELS`, which mirrors the registry default rather than the
+ * runtime resolution order (see the note on that table).
+ *
  * @param provider - The AI provider
  * @returns Default model string for the provider
  */

package/dist/utils/modelChoices.js

@@ -43,14 +43,19 @@ function catalogTopModels(entry) {
  */
 const TOP_MODELS_CONFIG = {
     [AIProviderName.OPENAI]: [
+        {
+            model: OpenAIModels.GPT_5_4,
+            description: "Recommended - Direct OpenAI GPT-5.4 model",
+        },
+        { model: OpenAIModels.GPT_5_4_MINI, description: "Cost-effective, fast" },
         {
             model: OpenAIModels.GPT_4O,
-            description: "Recommended - Latest multimodal model",
+            description: "Previous generation multimodal model",
         },
         { model: OpenAIModels.GPT_4O_MINI, description: "Cost-effective, fast" },
         {
             model: OpenAIModels.GPT_5_2,
-            description: "Latest flagship with deep reasoning",
+            description: "Previous flagship with deep reasoning",
         },
         { model: OpenAIModels.O3, description: "Advanced reasoning model" },
         { model: OpenAIModels.GPT_4_TURBO, description: "Previous generation" },
@@ -422,9 +427,16 @@ const TOP_MODELS_CONFIG = {
  *
  * AUTO is also excluded — it never had an entry here either (matches
  * pre-existing behavior: `getDefaultModel(AUTO)` returns `undefined`).
+ *
+ * This table is not what a call with no model uses. The runtime order is the
+ * explicit model, then the provider's environment variable, then the default in
+ * the dynamic model configuration, then the registry default
+ * (`providerRegistry.ts`); the OpenAI row mirrors that registry default. Only
+ * an `OpenAIProvider` constructed directly with none of those falls back to
+ * `gpt-5.4` (`openAI/client.ts`).
  */
 export const DEFAULT_MODELS = {
-    [AIProviderName.OPENAI]: OpenAIModels.GPT_4O,
+    [AIProviderName.OPENAI]: OpenAIModels.GPT_4O_MINI,
     [AIProviderName.ANTHROPIC]: AnthropicModels.CLAUDE_SONNET_4_5,
     [AIProviderName.GOOGLE_AI]: GoogleAIModels.GEMINI_2_5_FLASH,
     [AIProviderName.VERTEX]: VertexModels.GEMINI_2_5_FLASH,
@@ -572,6 +584,9 @@ export function getAllProviderChoices() {
 /**
  * Get the default model for a provider
  *
+ * Reads `DEFAULT_MODELS`, which mirrors the registry default rather than the
+ * runtime resolution order (see the note on that table).
+ *
  * @param provider - The AI provider
  * @returns Default model string for the provider
  */

package/dist/utils/providerHealth.js

@@ -305,10 +305,17 @@ export class ProviderHealthChecker {
             }
             return;
         }
+        // A descriptor with no apiKey variable at all (LM Studio, llama.cpp) would
+        // otherwise read process.env[""] below and report a missing key named by
+        // nothing; hasProviderEnvVars already treats these as usable with defaults.
+        const providerDescriptor = ProviderFactory.getDescriptor(providerName);
         // Providers that don't use API keys directly
         if (providerName === AIProviderName.OLLAMA ||
             providerName === AIProviderName.BEDROCK ||
-            providerName === AIProviderName.LITELLM) {
+            providerName === AIProviderName.LITELLM ||
+            providerDescriptor?.localRuntime === true ||
+            (providerDescriptor?.envVars.optional === true &&
+                !providerDescriptor.envVars.apiKey)) {
             healthStatus.hasApiKey = true;
             return;
         }
@@ -996,8 +1003,10 @@ export class ProviderHealthChecker {
                 ];
             case AIProviderName.OPENAI:
                 return [
-                    OpenAIModels.GPT_4O,
+                    OpenAIModels.GPT_5_4,
+                    OpenAIModels.GPT_5_4_MINI,
                     OpenAIModels.GPT_4O_MINI,
+                    OpenAIModels.GPT_4O,
                     OpenAIModels.GPT_3_5_TURBO,
                 ];
             case AIProviderName.GOOGLE_AI:
@@ -1541,8 +1550,18 @@ export class ProviderHealthChecker {
                 return provider;
             }
         }
-        // Fallback to first healthy provider
-        const firstHealthyProvider = healthStatuses.find((h) => h.isHealthy);
+        // Fallback to first healthy provider. A local runtime that nothing probes
+        // (LM Studio, llama.cpp) is "healthy" only in that it needs no
+        // configuration, which says nothing about whether it is running, so it
+        // must not outrank a provider the caller actually configured.
+        const firstHealthyProvider = healthStatuses.find((h) => {
+            if (!h.isHealthy) {
+                return false;
+            }
+            const descriptor = ProviderFactory.getDescriptor(h.provider);
+            return !(descriptor?.localRuntime === true &&
+                descriptor.healthCheck === "env-only");
+        });
         if (firstHealthyProvider) {
             logger.info(`Using fallback healthy provider: ${firstHealthyProvider.provider}`);
             return firstHealthyProvider.provider;

package/dist/utils/providerRetry.d.ts

@@ -86,6 +86,10 @@ export declare function getErrorStatusCode(error: unknown): number | undefined;
  * @param operation  - The async operation to execute (should already use `maxRetries: 0`)
  * @param span       - The OTel span to annotate with retry events and attributes
  * @param label      - A human-readable label for log messages (e.g. "generateText", "streamText")
+ * @param sleep      - Wait between attempts; receives the delay and the caller's abort signal
+ * @param abortSignal - The caller's cancellation. An abort during the wait ends the call with the
+ *                     signal's reason instead of waiting out the delay and running the operation
+ *                     again, and an already-aborted signal is checked before every attempt.
  * @returns The result of the operation
  */
-export declare function withProviderRetry<T>(operation: () => Promise<T>, span: Span | undefined, label: string, sleep?: (delayMs: number) => Promise<void>): Promise<T>;
+export declare function withProviderRetry<T>(operation: () => Promise<T>, span: Span | undefined, label: string, sleep?: (delayMs: number, abortSignal?: AbortSignal) => Promise<void>, abortSignal?: AbortSignal): Promise<T>;

package/dist/utils/providerRetry.js

@@ -33,7 +33,21 @@ export const NO_HINT_FLOOR_MS = 10_000;
  * get a prompt rate-limit error rather than a silent multi-minute stall.
  */
 export const MAX_RETRY_AFTER_MS = 60_000;
-const sleepWithTimeout = (delayMs) => new Promise((resolve) => setTimeout(resolve, delayMs));
+const sleepWithTimeout = (delayMs, abortSignal) => new Promise((resolve, reject) => {
+    if (abortSignal?.aborted) {
+        reject(abortSignal.reason);
+        return;
+    }
+    const onAbort = () => {
+        clearTimeout(timer);
+        reject(abortSignal?.reason);
+    };
+    const timer = setTimeout(() => {
+        abortSignal?.removeEventListener("abort", onAbort);
+        resolve();
+    }, delayMs);
+    abortSignal?.addEventListener("abort", onAbort, { once: true });
+});
 /**
  * Check whether an error thrown by the AI SDK is retryable.
  *
@@ -244,10 +258,15 @@ function getRetryAfterMs(error) {
  * @param operation  - The async operation to execute (should already use `maxRetries: 0`)
  * @param span       - The OTel span to annotate with retry events and attributes
  * @param label      - A human-readable label for log messages (e.g. "generateText", "streamText")
+ * @param sleep      - Wait between attempts; receives the delay and the caller's abort signal
+ * @param abortSignal - The caller's cancellation. An abort during the wait ends the call with the
+ *                     signal's reason instead of waiting out the delay and running the operation
+ *                     again, and an already-aborted signal is checked before every attempt.
  * @returns The result of the operation
  */
-export async function withProviderRetry(operation, span, label, sleep = sleepWithTimeout) {
+export async function withProviderRetry(operation, span, label, sleep = sleepWithTimeout, abortSignal) {
     for (let attempt = 0; attempt <= MAX_PROVIDER_RETRIES; attempt++) {
+        abortSignal?.throwIfAborted();
         try {
             const result = await operation();
             // Record how many attempts it took on the span
@@ -314,7 +333,10 @@ export async function withProviderRetry(operation, span, label, sleep = sleepWit
                 statusCode,
                 error: errorMessage,
             });
-            await sleep(delay);
+            await sleep(delay, abortSignal);
+            // A custom sleep may ignore the signal, and a signal can abort in the
+            // same tick the timer fires.
+            abortSignal?.throwIfAborted();
         }
     }
     // This should never be reached due to the throw inside the loop,

package/dist/utils/providerUtils.js

@@ -52,16 +52,8 @@ export async function getBestProvider(requestedProvider) {
             // Fall through to cloud providers
         }
     }
-    /**
-     * Provider priority order rationale:
-     * - LiteLLM and Ollama are prioritized first for local/self-hosted deployments,
-     *   avoiding unnecessary dependence on external providers during fallback scenarios.
-     * - Vertex (Google Cloud AI) follows for enterprise-grade reliability.
-     * - Google AI follows as second cloud priority for comprehensive Google AI ecosystem support.
-     * - OpenAI maintains high priority due to its consistent reliability and broad model support.
-     * - Other providers are ordered based on a combination of reliability, feature set, and historical performance.
-     * Please update this comment if the order is changed in the future, and document the rationale for maintainability.
-     */
+    // Order comes from ProviderDescriptor.autoSelectPriority (lower = tried
+    // first); see providerDescriptors.ts and the catalog JSON.
     const providers = PROVIDER_DESCRIPTORS.filter((d) => d.autoSelectPriority !== undefined)
         .sort((a, b) => (a.autoSelectPriority ?? 0) - (b.autoSelectPriority ?? 0))
         .map((d) => d.name);

package/docs-site/static/search-index.json

@@ -2732,7 +2732,7 @@
 {"objectID":"67869c44bf604306f5e7d4f118c84d1357aba914cd78f1c63e338a61afd446cd","title":"ModelMapping Fields","url":"/docs/features/claude-proxy-config-reference#modelmapping-fields","content":"| Field      | Type     | Default       | Required | Description                                      |\n| ---------- | -------- | ------------- | -------- | ------------------------------------------------ |\n| from     | string | \"\"          | Yes      | Incoming model name (what Claude Code requests). |\n| to       | string | \"\"          | Yes      | Target model name at the destination provider.   |\n| provider | string | \"anthropic\" | No       | Target provider to route to.                     |","hierarchy":{"lvl0":"Features","lvl1":"Claude Proxy Configuration Reference","lvl2":"ModelMapping Fields","lvl3":""}},
 {"objectID":"52dc93bd2fb61c11e711465bcce7ab2445d21dd11f8601a791c1800577cd68bc","title":"FallbackEntry Fields","url":"/docs/features/claude-proxy-config-reference#fallbackentry-fields","content":"| Field      | Type     | Default | Required | Description                                  |\n| ---------- | -------- | ------- | -------- | -------------------------------------------- |\n| provider | string | \"\"    | Yes      | Provider name (e.g., google-ai, openai). |\n| model    | string | \"\"    | Yes      | Model to use at that provider.               |","hierarchy":{"lvl0":"Features","lvl1":"Claude Proxy Configuration Reference","lvl2":"FallbackEntry Fields","lvl3":""}},
 {"objectID":"d9b034b736d0076ac98c315f8227b06382eafb161166a630a350add28c818ee6","title":"Cloaking Fields","url":"/docs/features/claude-proxy-config-reference#cloaking-fields","content":"| Field                            | Type                            | Default                       | Description                                                                                                  |\n| -------------------------------- | ------------------------------- | ----------------------------- | ------------------------------------------------------------------------------------------------------------ |\n| mode                           | \"auto\" \\| \"always\" \\| \"never\" | \"auto\"                      | auto applies cloaking only to OAuth accounts. always applies to all. never disables all plugins.       |\n| plugins.headerScrubber         | boolean                       | false                       | Strip proxy-revealing headers (x-forwarded-for, via, sec-ch-\\*, etc.).                                       |\n| plugins.sessionIdentity        | boolean                       | false                       | Generate consistent userid/sessionid per account with 1-hour TTL.                                          |\n| plugins.systemPromptInjector   | boolean                       | false                       | Inject Claude Code session context (IDE metadata, timestamps) into system prompt. OAuth accounts only.       |\n| plugins.wordObfuscator.enabled | boolean                       | false                       | Insert zero-width characters into sensitive words to defeat string matching.                                 |\n| plugins.wordObfuscator.words   | string[]                      | [\"proxy\", \"neurolink\", ...] | Words to obfuscate. Defaults include: proxy, neurolink, load balancer, round-robin, failover, multi-account. |\n| plugins.tlsFingerprint.enabled | boolean                       | false                       | TLS fingerprint mimicry. Currently a stub/placeholder (no-op).                                               |","hierarchy":{"lvl0":"Features","lvl1":"Claude Proxy Configuration Reference","lvl2":"Cloaking Fields","lvl3":""}},
-{"objectID":"f1d10e310dd6cdd2e1ec76e8fb228e48f343eec841772b564c22357e7ea8f64f","title":"Validation Rules","url":"/docs/features/claude-proxy-config-reference#validation-rules","content":"The config loader validates the following:\naccounts must be present and be a non-array object.\nEach provider key in accounts must map to an array.\nEach account must have a non-empty string apiKey.\nIf version is present, it must be a number.\nrouting.account-allowlist must be an array of non-empty strings when present.\nrouting.quota-routing must be a boolean when present.\nrouting.auto-fallback must be a boolean when present.\nrouting.max-inflight-per-account must be an integer from 1 through 20 when present.\nrouting.session-soft-limit must be a number in (0, 1] when present.\nrouting.session-reset-tolerance-ms must be a positive integer when present.\nrouting.use-overage must be auto, always, or never (case-insensitive)\n  when present.\nrouting.account-ranking must be expiry-first or headroom-first when\n  present.\nrouting.prefer-primary must be a boolean when present.\nrouting.session-affinity must be a boolean when present.\nrouting.session-affinity-idle-ttl-ms must be an integer from 60000 through\n  86400000 when present.\nrouting.spill-inflight must be an integer from 0 through 100 when present.\nFor those five routing policy keys, an explicit null counts as present\n  and is rejected, whichever spelling (kebab-case or camelCase) carries it.\nPlaintext API keys (not using ${ENV_VAR} references) trigger a warning.\n\nAn absent default config is optional. An existing config that cannot be read or\nvalidated fails proxy startup; it is never ignored in favor of unrestricted\nrouting. A value that fails any check above rejects the whole config, never\njust that key: at startup the proxy does not start, and on a hot reload the\nlast-known-good generation stays active.","hierarchy":{"lvl0":"Features","lvl1":"Claude Proxy Configuration Reference","lvl2":"Validation Rules","lvl3":""}},
+{"objectID":"f1d10e310dd6cdd2e1ec76e8fb228e48f343eec841772b564c22357e7ea8f64f","title":"Validation Rules","url":"/docs/features/claude-proxy-config-reference#validation-rules","content":"The config loader validates the following:\naccounts must be present and be a non-array object.\nEach provider key in accounts must map to an array.\nEach account must have a non-empty string apiKey.\nIf version is present, it must be a number.\nrouting.account-allowlist must be an array of non-empty strings when present. An explicit null counts as present and is rejected, whichever spelling carries it, including when the other spelling holds an array.\nrouting.quota-routing must be a boolean when present.\nrouting.auto-fallback must be a boolean when present.\nrouting.max-inflight-per-account must be an integer from 1 through 20 when present.\nrouting.session-soft-limit must be a number in (0, 1] when present.\nrouting.session-reset-tolerance-ms must be a positive integer when present.\nrouting.use-overage must be auto, always, or never (case-insensitive)\n  when present.\nrouting.account-ranking must be expiry-first or headroom-first when\n  present.\nrouting.prefer-primary must be a boolean when present.\nrouting.session-affinity must be a boolean when present.\nrouting.session-affinity-idle-ttl-ms must be an integer from 60000 through\n  86400000 when present.\nrouting.spill-inflight must be an integer from 0 through 100 when present.\nFor those five routing policy keys, an explicit null counts as present\n  and is rejected, whichever spelling (kebab-case or camelCase) carries it.\nPlaintext API keys (not using ${ENV_VAR} references) trigger a warning.\n\nAn absent default config is optional. An existing config that cannot be read or\nvalidated fails proxy startup; it is never ignored in favor of unrestricted\nrouting. A value that fails any check above rejects the whole config, never\njust that key: at startup the proxy does not start, and on a hot reload the\nlast-known-good generation stays active.","hierarchy":{"lvl0":"Features","lvl1":"Claude Proxy Configuration Reference","lvl2":"Validation Rules","lvl3":""}},
 {"objectID":"c8450374b1fc8e0a0f5fb47d3bef0cab242c75e17bfebe6e943ef17b22c10227","title":"Account Routing Policies","url":"/docs/features/claude-proxy-config-reference#account-routing-policies","content":"The five keys above (account-ranking, prefer-primary, session-affinity,\nsession-affinity-idle-ttl-ms, spill-inflight) all default to today's exact\nbehavior — expiry-first ranking, no affinity, no primary preference, no\nspill — and are validated and hot-reloaded through the same runtime config\nsnapshot as every other routing key.\n\nstrategy: round-robin ignores all five keys. They apply only under\nfill-first with more than one enabled account.\n\nNEUROLINK_PROXY_QUOTA_ROUTING=off disables quota-based ranking, but\nsession-affinity, prefer-primary and spill-inflight still apply.\nTurning off quota routing removes the expiry/headroom ordering step, so\naccount-ranking has no effect; it does not disable sticky sessions, the\nprimary preference or spill, which then work on the configured account\norder.\n\nPrecedence. After unusable accounts are removed, the order a request\ntries is:\nthe session's bound account, when session-affinity is on and that\n   account is usable and not session-saturated;\nthe configured primary-account, when prefer-primary is on and it is\n   usable and not session-saturated;\nthe remaining accounts in account-ranking order.\n\nSpill only changes which account is tried first, and only for requests\nwithout an active session-affinity binding — it never re-orders or moves a\nrequest that is already bound to an account. Its target must be usable and\nnot session-saturated, like every step above; when no account under the\nthreshold qualifies, nothing spills.\n\nBinding. A served request binds its session to the Anthropic account\nthat served it. The existing binding is kept only when that request never\ntried the bound account and the bound account is still usable and not\nsession-saturated — a request that overflowed the bound account's\nmax-inflight-per-account cap onto another account keeps the session on its\nwarm prompt cache.","hierarchy":{"lvl0":"Features","lvl1":"Claude Proxy Configuration Reference","lvl2":"Account Routing Policies","lvl3":""}},
 {"objectID":"2b5d2865be217ed908e64f9d07acbe019108e95f210f6c14f031cf8cb99ece6f","title":"3. Environment Variables","url":"/docs/features/claude-proxy-config-reference#3-environment-variables","content":"| Variable                                     | Purpose                                                                                                                                                                                                                                                                                                                | Used By                                          |\n| -------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------ |\n| ANTHROPIC_API_KEY                          | Anthropic API key. Used as a fallback credential when no OAuth accounts are found.                                                                                                                                                                                                                                     | Proxy routes, Anthropic provider                 |\n| ANTHROPIC_OAUTH_TOKEN                      | OAuth access token for Anthropic (alternative to stored tokens).                                                                                                                                                                                                                                                       | Anthropic provider, providerConfig               |\n| CLAUDE_OAUTH_TOKEN                         | Alias for ANTHROPIC_OAUTH_TOKEN. Checked as a fallback.","hierarchy":{"lvl0":"Features","lvl1":"Claude Proxy Configuration Reference","lvl2":"3. Environment Variables","lvl3":""}},
 {"objectID":"3f1a3fc9d7711064037deec5635e85b2dc713d3d9c019df22c659f47215812b8","title":"Proxy Env File Resolution Order","url":"/docs/features/claude-proxy-config-reference#proxy-env-file-resolution-order","content":"When the proxy starts, it loads env vars from a .env file using this priority:\n--env-file <path> CLI flag — explicit path, required to exist.\nNEUROLINK_ENV_FILE=<path> environment variable — explicit path, required to exist.\n~/.neurolink/.env — loaded automatically if the file exists (created by neurolink proxy telemetry setup).\nNothing — proxy starts without extra env vars; telemetry remains disabled unless env vars are already set in the shell, and the proxy emits a startup log explaining how to enable it unless output is suppressed.\n\nThe --env-file flag is baked into the launchd plist by proxy install, so the service always loads from the same file across reboots. The three runtime routing variables above and routing interpolation are reread transactionally; other env settings remain startup-only.\n\nPriority for Anthropic credentials (checked in order by the proxy routes):\nTokenStore compound keys -- anthropic:<label> entries in ~/.neurolink/tokens.json.\nLegacy credentials file -- ~/.neurolink/anthropic-credentials.json (only if no compound keys exist).\nANTHROPIC_API_KEY env var -- Only if no Anthropic TokenStore entries or legacy credential are present.\n\nrouting.account-allowlist filters these sources before loading or refresh. Legacy and environment fallbacks are never activated merely because existing TokenStore accounts are disabled, cooling, or unavailable.","hierarchy":{"lvl0":"Features","lvl1":"Claude Proxy Configuration Reference","lvl2":"Proxy Env File Resolution Order","lvl3":""}},
@@ -4727,7 +4727,7 @@
 {"objectID":"8b922e3ee9644559addad4738b5f0c6360fe12ae2d1d0c98d678ddaac03eede9","title":"Troubleshooting","url":"/docs/features/workflow-engine#troubleshooting","content":"| Problem                           | Solution                                                                           |\n| --------------------------------- | ---------------------------------------------------------------------------------- |\n| Workflow not found in registry    | Register it with registerWorkflow() before calling generate() with workflow: |\n| All models failed                 | Check API keys, increase timeout, verify provider availability                   |\n| Judge returns neutral scores (50) | Judge response parsing failed; check judge model supports JSON output              |\n| Slow execution                    | Reduce model count, use faster models, increase parallelism                      |\n| High costs                        | Use consensus-3-fast, chain/adaptive workflows, or set costThreshold           |\n| Low consensus in multi-judge      | Normal for subjective queries; increase judge count or align criteria              |","hierarchy":{"lvl0":"Features","lvl1":"Workflow Engine Guide","lvl2":"Troubleshooting","lvl3":""}},
 {"objectID":"e9de380e8339140c2951bda58d6eaaffb28f182c85fbfda7d7679ea6f5af270e","title":"Core Exports","url":"/docs/features/workflow-engine#core-exports","content":"Execution:\nrunWorkflow(config, options) -- Execute a complete workflow\nrunWorkflowWithStreaming(config, options) -- Execute with progressive streaming\nexecuteEnsemble(options) -- Low-level parallel model execution\nexecuteModelGroups(groups, prompt, config) -- Low-level layer-based execution\nscoreEnsemble(options) -- Low-level judge scoring\nconditionResponse(options) -- Low-level response conditioning\n\nConfiguration:\ncreateWorkflowConfig(partial) -- Create config with defaults\nvalidateWorkflow(config) -- Validate workflow configuration\nvalidateForExecution(config) -- Validate for execution readiness\n\nRegistry:\nregisterWorkflow(config, options) -- Register a workflow\nunregisterWorkflow(workflowId) -- Remove a workflow\ngetWorkflow(workflowId) -- Retrieve by ID\nlistWorkflows(options) -- List with filtering\ngetRegistryStats() -- Registry statistics\nclearRegistry() -- Remove all workflows\n\nPre-built Workflows:\nCONSENSUS_3_WORKFLOW -- 3-model ensemble with judge\nCONSENSUS_3_FAST_WORKFLOW -- Fast/cheap 3-model ensemble\nBALANCED_ADAPTIVE_WORKFLOW -- 2-tier balanced adaptive\nQUALITY_MAX_WORKFLOW -- 3-tier quality-maximizing adaptive\nSPEED_FIRST_WORKFLOW -- Speed-optimized adaptive\nAGGRESSIVE_FALLBACK_WORKFLOW -- Fast + parallel premium fallback\nFAST_FALLBACK_WORKFLOW -- Sequential 3-tier fallback\nMULTI_JUDGE_3_WORKFLOW -- 3 models, 2 judges\nMULTI_JUDGE_5_WORKFLOW -- 5 models, 3 judges\n\nFactory Functions:\ncreateConsensus3WithPrompt(systemPrompt) -- Consensus-3 with custom prompt\ncreateAdaptiveWorkflow(tiers, strategy) -- Custom adaptive workflow\ncreateMultiJudgeWorkflow(modelCount, judgeCount) -- Custom multi-judge\n\nMetrics:\ncalculateModelMetrics(responses) -- Per-model metrics\ncalculateConfidence(scores) -- Confidence calculation\ncalculateConsensus(scores) -- Consensus calculation\ngenerateSummaryStats(results) -- Summary statistics\ncompareWorkflows(stats1, stats2) -- Workflow comparison\nformatMetricsForLogging(result) -- Formatted logging output\n\nTypes:\nWorkflowConfig,","hierarchy":{"lvl0":"Features","lvl1":"Workflow Engine Guide","lvl2":"Core Exports","lvl3":""}},
 {"objectID":"fb91715f0910d539aa3342bb53890eb88ef04121ad496d9c8c982c55d6a645d5","title":"See Also","url":"/docs/features/workflow-engine#see-also","content":"Provider Orchestration Guide -- Multi-provider configuration\nObservability Guide -- Tracing workflow executions with Langfuse\nStructured Output Guide -- JSON schema output (note: incompatible with Gemini tools)","hierarchy":{"lvl0":"Features","lvl1":"Workflow Engine Guide","lvl2":"See Also","lvl3":""}},
-{"objectID":"fcc71bbb437aec3313f917118186ae468e33d960b134ccbe3a8151a55970c6a9","title":"🔧 Environment Variables Configuration Guide","url":"/docs/getting-started/environment-variables","content":"🔧 Environment Variables Configuration Guide\n\nThis guide provides comprehensive setup instructions for all AI providers supported by NeuroLink. The CLI automatically loads environment variables from .env files, making configuration seamless.\n\n🚀 Quick Setup\n\nAutomatic .env Loading ✨ NEW!\n\nNeuroLink CLI automatically loads environment variables from .env files in your project directory:\n\nManual Export (Also Supported)\n\n🏗️ Enterprise Configuration Management\n\n✨ NEW: Automatic Backup System\n\nInterface Configuration\n\nPerformance & Optimization\n\n🆕 AI Enhancement Features\n\nBasic Enhancement Configuration\n\nDescription: Configures the AI model used for response quality evaluation when --enable-evaluation flag is used. Uses Google AI's fast Gemini 2.5 Flash model for quick quality assessment.\n\nSupported Models:\ngemini-2.5-flash (default) - Fast evaluation processing\ngemini-2.5-pro - More detailed evaluation (slower)\n\nUsage:\n\n🌐 Universal Evaluation System (Advanced)\n\nPrimary Configuration\n\nNEUROLINK_EVALUATION_PROVIDER: Primary AI provider for evaluation\nOptions: google-ai, openai, anthropic, vertex, bedrock, azure, ollama, huggingface, mistral\nDefault: google-ai\nUsage: Determines which AI provider performs the quality evaluation\n\nNEUROLINK_EVALUATION_MODE: Performance vs quality trade-off\nOptions: fast (cost-effective), balanced (optimal), quality (highest accuracy)\nDefault: fast\nUsage: Selects appropriate model for the provider (e.g., gemini-2.5-flash vs gemini-2.5-pro)\n\nFallback Configuration\n\nNEUROLINK_EVALUATION_FALLBACK_ENABLED: Enable intelligent fallback system\nOptions: true, false\nDefault: true\nUsage: When enabled, automatically tries backup providers if primary fails\n\nNEUROLINK_EVALUATION_FALLBACK_PROVIDERS: Backup provider order\nFormat: Comma-separated provider names\nDefault: openai,anthropic,vertex,bedrock\nUsage: Defines the order of providers to try if primary fails\n\nPerformance Tuning\n\nPerformance Variables:\nTIMEOUT: Maximum time to wait for evaluation (prevents hanging)\nMAX_TOKENS: Limits evaluation response length (controls cost)\nTEMPERATURE: Lower values = more consistent scoring\nRETRY_ATTEMPTS: Number of retry attempts for transient failures\n\nCost Optimization\n\nNEUROLINK_EVALUATION_PREFER_CHEAP: Cost optimization preference\nOptions: true, false\nDefault: true\nUsage: When enabled, prioritizes cheaper providers and models\n\nNEUROLINK_EVALUATION_MAX_COST_PER_EVAL: Cost limit per evaluation\nFormat: Decimal number (USD)\nDefault: 0.01 ($0.01)\nUsage: Prevents expensive evaluations, switches to cheaper providers if needed\n\nComplete Universal Evaluation Example\n\nTesting Universal Evaluation\n\n🏢 Enterprise Proxy Configuration\n\nProxy Environment Variables\n\n| Variable      | Description                     | Example                            |\n| ------------- | ------------------------------- | ---------------------------------- |\n| HTTPS_PROXY | Proxy server for HTTPS requests | http://proxy.company.com:8080    |\n| HTTP_PROXY  | Proxy server for HTTP requests  | http://proxy.company.com:8080    |\n| NO_PROXY    | Domains to bypass proxy         | localhost,127.0.0.1,.company.com |\n\nAuthenticated Proxy\n\nAll NeuroLink providers automatically use proxy settings when configured.\n\nFor detailed proxy setup → See Enterprise & Proxy Setup Guide\n\n🤖 Provider Configuration\nOpenAI\n\nRequired Variables\n\nOptional Variables\n\nHow to Get OpenAI API Key\nVisit OpenAI Platform\nSign up or log in to your account\nNavigate to API Keys section\nClick Create new secret key\nCopy the key (starts with sk-proj- or sk-)\nAdd billing information if required\n\nSupported Models\ngpt-4o (default) - Latest GPT-4 Optimized\ngpt-4o-mini - Faster, cost-effective option\ngpt-4-turbo - High-performance model\ngpt-3.5-turbo - Legacy cost-effective option\nAmazon Bedrock\n\nRequired Variables\n\nModel Configuration (⚠️ Critical)\n\nOptional Variables\n\nHow to Get AWS Credentials\nSign up for AWS Account\nNavigate to IAM Console\nCreate new user with programmatic access\nAttach policy: AmazonBedrockFullAccess\nDownload access key and secret key\nImportant: Request model access in Bedrock console\n\nBedrock Model Access Setup\nGo to AWS Bedrock Console\nNavigate to Model access\nClick Request model access\nSelect desired models (Claude, Titan, etc.)\nSubmit request and wait for approval\n\nSupported Models\nAnthropic Claude:\narn:aws:bedrock:<region>:<account_id>:inference-profile/us.anthropic.claude-3-7-sonnet-20250219-v1:0\narn:aws:bedrock:<region>:<account_id>:inference-profile/us.anthropic.claude-3-5-sonnet-20241022-v2:0\nAmazon Titan:\namazon.titan-text-express-v1\namazon.titan-text-lite-v1\nGoogle Vertex AI\n\nGoogle Vertex AI supports three authentication methods. Choose the one that fits your deployment:\n\nMethod 1: Service Account File (Recommended)\n\nMethod 2: Service Account JSON String\n\nMethod 3: Individual Environment Variables\n\nOptional Variables\n\nHow to Set Up Google Vertex AI\nCreate Google Cloud Project\nEnable Vertex AI API\nCreate Service Account:\nGo to IAM & Admin > Service Ac","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"","lvl3":""}},
+{"objectID":"fcc71bbb437aec3313f917118186ae468e33d960b134ccbe3a8151a55970c6a9","title":"🔧 Environment Variables Configuration Guide","url":"/docs/getting-started/environment-variables","content":"🔧 Environment Variables Configuration Guide\n\nThis guide provides comprehensive setup instructions for all AI providers supported by NeuroLink. The CLI automatically loads environment variables from .env files, making configuration seamless.\n\n🚀 Quick Setup\n\nAutomatic .env Loading ✨ NEW!\n\nNeuroLink CLI automatically loads environment variables from .env files in your project directory:\n\nManual Export (Also Supported)\n\n🏗️ Enterprise Configuration Management\n\n✨ NEW: Automatic Backup System\n\nInterface Configuration\n\nPerformance & Optimization\n\n🆕 AI Enhancement Features\n\nBasic Enhancement Configuration\n\nDescription: Configures the AI model used for response quality evaluation when --enable-evaluation flag is used. Uses Google AI's fast Gemini 2.5 Flash model for quick quality assessment.\n\nSupported Models:\ngemini-2.5-flash (default) - Fast evaluation processing\ngemini-2.5-pro - More detailed evaluation (slower)\n\nUsage:\n\n🌐 Universal Evaluation System (Advanced)\n\nPrimary Configuration\n\nNEUROLINK_EVALUATION_PROVIDER: Primary AI provider for evaluation\nOptions: google-ai, openai, anthropic, vertex, bedrock, azure, ollama, huggingface, mistral\nDefault: google-ai\nUsage: Determines which AI provider performs the quality evaluation\n\nNEUROLINK_EVALUATION_MODE: Performance vs quality trade-off\nOptions: fast (cost-effective), balanced (optimal), quality (highest accuracy)\nDefault: fast\nUsage: Selects appropriate model for the provider (e.g., gemini-2.5-flash vs gemini-2.5-pro)\n\nFallback Configuration\n\nNEUROLINK_EVALUATION_FALLBACK_ENABLED: Enable intelligent fallback system\nOptions: true, false\nDefault: true\nUsage: When enabled, automatically tries backup providers if primary fails\n\nNEUROLINK_EVALUATION_FALLBACK_PROVIDERS: Backup provider order\nFormat: Comma-separated provider names\nDefault: openai,anthropic,vertex,bedrock\nUsage: Defines the order of providers to try if primary fails\n\nPerformance Tuning\n\nPerformance Variables:\nTIMEOUT: Maximum time to wait for evaluation (prevents hanging)\nMAX_TOKENS: Limits evaluation response length (controls cost)\nTEMPERATURE: Lower values = more consistent scoring\nRETRY_ATTEMPTS: Number of retry attempts for transient failures\n\nCost Optimization\n\nNEUROLINK_EVALUATION_PREFER_CHEAP: Cost optimization preference\nOptions: true, false\nDefault: true\nUsage: When enabled, prioritizes cheaper providers and models\n\nNEUROLINK_EVALUATION_MAX_COST_PER_EVAL: Cost limit per evaluation\nFormat: Decimal number (USD)\nDefault: 0.01 ($0.01)\nUsage: Prevents expensive evaluations, switches to cheaper providers if needed\n\nComplete Universal Evaluation Example\n\nTesting Universal Evaluation\n\n🏢 Enterprise Proxy Configuration\n\nProxy Environment Variables\n\n| Variable      | Description                     | Example                            |\n| ------------- | ------------------------------- | ---------------------------------- |\n| HTTPS_PROXY | Proxy server for HTTPS requests | http://proxy.company.com:8080    |\n| HTTP_PROXY  | Proxy server for HTTP requests  | http://proxy.company.com:8080    |\n| NO_PROXY    | Domains to bypass proxy         | localhost,127.0.0.1,.company.com |\n\nAuthenticated Proxy\n\nAll NeuroLink providers automatically use proxy settings when configured.\n\nFor detailed proxy setup → See Enterprise & Proxy Setup Guide\n\n🤖 Provider Configuration\nOpenAI\n\nRequired Variables\n\nOptional Variables\n\nHow to Get OpenAI API Key\nVisit OpenAI Platform\nSign up or log in to your account\nNavigate to API Keys section\nClick Create new secret key\nCopy the key (starts with sk-proj- or sk-)\nAdd billing information if required\n\nSupported Models\ngpt-5.4 - GPT-5.4 model\ngpt-5.4-mini - Faster, cost-effective GPT-5.4 option\ngpt-4o-mini (default) - Cost-effective, fast\ngpt-4o - Previous generation multimodal model\ngpt-4-turbo - High-performance model\ngpt-3.5-turbo - Legacy cost-effective option\n\nWith no model set, NeuroLink uses the explicit model option, then OPENAI_MODEL, then the default in the model configuration (MODEL_CONFIG_URL, otherwise the repository's config/models.json), then the registry default gpt-4o-mini. Constructing OpenAIProvider directly with none of these falls back to gpt-5.4.\nAmazon Bedrock\n\nRequired Variables\n\nModel Configuration (⚠️ Critical)\n\nOptional Variables\n\nHow to Get AWS Credentials\nSign up for AWS Account\nNavigate to IAM Console\nCreate new user with programmatic access\nAttach policy: AmazonBedrockFullAccess\nDownload access key and secret key\nImportant: Request model access in Bedrock console\n\nBedrock Model Access Setup\nGo to AWS Bedrock Console\nNavigate to Model access\nClick Request model access\nSelect desired models (Claude, Titan, etc.)\nSubmit request and wait for approval\n\nSupported Models\nAnthropic Claude:\narn:aws:bedrock:<region>:<account_id>:inference-profile/us.anthropic.claude-3-7-sonnet-20250219-v1:0\narn:aws:bedrock:<region>:<account_id>:inference-profile/us.anthropic.claude-3-5-sonnet-20241022-v2:0\nAmazon Titan:\namazon.titan-text-express-v1\namazon.titan-text-lite-v1\nGoogle V","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"","lvl3":""}},
 {"objectID":"c81a81fd6221fc873edf4a381a6af70939b66519ee4d4ce31acce9afec8fb5f1","title":"🔧 Environment Variables Configuration Guide","url":"/docs/getting-started/environment-variables#-environment-variables-configuration-guide","content":"This guide provides comprehensive setup instructions for all AI providers supported by NeuroLink. The CLI automatically loads environment variables from .env files, making configuration seamless.","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"🔧 Environment Variables Configuration Guide","lvl3":""}},
 {"objectID":"a78ad3583ac3d28848100b6a1e832a69a5d8d6dd5538da571bcf5d184ef34789","title":"Automatic .env Loading ✨ NEW!","url":"/docs/getting-started/environment-variables#automatic-env-loading-new","content":"NeuroLink CLI automatically loads environment variables from .env files in your project directory:\n\n`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"Automatic .env Loading ✨ NEW!","lvl3":""}},
 {"objectID":"7f0086c723d683ab77c7a74bfeaf8a61a34e60fc87f62f7c8abceeb385bebab3","title":"Create .env file (automatically loaded)","url":"/docs/getting-started/environment-variables#create-env-file-automatically-loaded","content":"echo 'OPENAIAPIKEY=\"sk-your-key\"' > .env\necho 'AWSACCESSKEY_ID=\"your-key\"' >> .env","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"Create .env file (automatically loaded)","lvl3":""}},
@@ -4771,7 +4771,7 @@
 {"objectID":"d5cabd5bf6ae965d7bf7274d74934ba63f7d8b3567bc4b54317270dade223d44","title":"Authenticated Proxy","url":"/docs/getting-started/environment-variables#authenticated-proxy","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"Authenticated Proxy","lvl3":""}},
 {"objectID":"bf0792704fa31e90694a52e8e293682873f558d49131eba9f2e9a4d2f40498ec","title":"Proxy with username/password authentication","url":"/docs/getting-started/environment-variables#proxy-with-usernamepassword-authentication","content":"HTTPS_PROXY=\"http://username:password@proxy.company.com:8080\"\nHTTP_PROXY=\"http://username:password@proxy.company.com:8080\"\n`\n\nAll NeuroLink providers automatically use proxy settings when configured.\n\nFor detailed proxy setup → See Enterprise & Proxy Setup Guide","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"Proxy with username/password authentication","lvl3":""}},
 {"objectID":"010e6483ced7a9b1fba1740513766a58d6e77b2da14e91d6d3669cfb10eaecc8","title":"How to Get OpenAI API Key","url":"/docs/getting-started/environment-variables#how-to-get-openai-api-key","content":"Visit OpenAI Platform\nSign up or log in to your account\nNavigate to API Keys section\nClick Create new secret key\nCopy the key (starts with sk-proj- or sk-)\nAdd billing information if required","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"How to Get OpenAI API Key","lvl3":""}},
-{"objectID":"dc3d270e290e8328b30e8814d306c2f91955a36a56e2204eba0e8ab3ac284bf1","title":"Supported Models","url":"/docs/getting-started/environment-variables#supported-models","content":"gpt-4o (default) - Latest GPT-4 Optimized\ngpt-4o-mini - Faster, cost-effective option\ngpt-4-turbo - High-performance model\ngpt-3.5-turbo - Legacy cost-effective option","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"Supported Models","lvl3":""}},
+{"objectID":"dc3d270e290e8328b30e8814d306c2f91955a36a56e2204eba0e8ab3ac284bf1","title":"Supported Models","url":"/docs/getting-started/environment-variables#supported-models","content":"gpt-5.4 - GPT-5.4 model\ngpt-5.4-mini - Faster, cost-effective GPT-5.4 option\ngpt-4o-mini (default) - Cost-effective, fast\ngpt-4o - Previous generation multimodal model\ngpt-4-turbo - High-performance model\ngpt-3.5-turbo - Legacy cost-effective option\n\nWith no model set, NeuroLink uses the explicit model option, then OPENAI_MODEL, then the default in the model configuration (MODEL_CONFIG_URL, otherwise the repository's config/models.json), then the registry default gpt-4o-mini. Constructing OpenAIProvider directly with none of these falls back to gpt-5.4.","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"Supported Models","lvl3":""}},
 {"objectID":"d73a5c2adb25974a196bb6ecad05bc436d23500f98110dc47bd16408df6000a0","title":"Model Configuration (⚠️ Critical)","url":"/docs/getting-started/environment-variables#model-configuration-critical","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"Model Configuration (⚠️ Critical)","lvl3":""}},
 {"objectID":"122f80d8fffd22fa876007b951e16c9a6406ea21c25e0a4c6bdffa6fb4eb4fe3","title":"Use full inference profile ARN for Anthropic models","url":"/docs/getting-started/environment-variables#use-full-inference-profile-arn-for-anthropic-models","content":"BEDROCK_MODEL=\"arn:aws:bedrock:us-east-2::inference-profile/us.anthropic.claude-3-7-sonnet-20250219-v1:0\"","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"Use full inference profile ARN for Anthropic models","lvl3":""}},
 {"objectID":"760493b55dfa9f12d29701bdea240a7f20e48c40af9ae3cc5038c87ea0a60844","title":"OR use simple model names for non-Anthropic models","url":"/docs/getting-started/environment-variables#or-use-simple-model-names-for-non-anthropic-models","content":"BEDROCK_MODEL=\"amazon.titan-text-express-v1\"\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"🔧 Environment Variables Configuration Guide","lvl2":"OR use simple model names for non-Anthropic models","lvl3":""}},
@@ -4938,7 +4938,9 @@
 {"objectID":"cc96a04c9f262c3c1f6f8b8e7c82407cc63406705250afd22947a3567e151721","title":"Other providers (setup guides in the Provider Guides index)","url":"/docs/getting-started/provider-setup#other-providers-setup-guides-in-the-provider-guides-index","content":"Onboarded via the zero-quirk OpenAI-wire-compatible catalog (Tier 2) — each has its own setup guide under providers/:\nGroq - LPU-accelerated inference; default openai/gpt-oss-120b\nCerebras - Wafer-scale inference; default gpt-oss-120b\nSambaNova - default Meta-Llama-3.3-70B-Instruct\nTogether AI - default meta-llama/Llama-3.3-70B-Instruct-Turbo\nFireworks AI - default accounts/fireworks/models/kimi-k3\nPerplexity - search-augmented models; default sonar\nCloudflare Workers AI - edge inference\nxAI - Grok models; default grok-4.6\nBaseten - default zai-org/GLM-5.3-Flash (BASETEN_API_KEY)\nGMI Cloud - default MiniMaxAI/MiniMax-M3 (GMICLOUD_API_KEY)\nInception Labs - diffusion LLMs; default mercury-2 (INCEPTION_LABS_API_KEY)\nio.net Intelligence - decentralized GPU inference; default meta-llama/Llama-3.3-70B-Instruct (IO_INTELLIGENCE_API_KEY)\nMancer - default deepseek-v4-flash (MANCER_API_KEY); no tool calling\nUpstage - Solar models; default solar-pro4 (UPSTAGE_API_KEY)\nAPI Route - OpenAI-compatible passthrough; default claude-sonnet-4-6 (API_ROUTE_API_KEY)\nDeepInfra - default deepseek-ai/DeepSeek-V4-Flash-0731 (DEEPINFRA_API_KEY); docs- and roster-verified, not yet live-verified\nFeatherless AI - default unsloth/Llama-3.3-70B-Instruct (FEATHERLESS_AI_API_KEY); docs- and roster-verified, not yet live-verified\nChutes - default moonshotai/Kimi-K2.6-TEE (CHUTES_API_KEY); docs- and roster-verified, not yet live-verified\nOVHcloud AI Endpoints - default gpt-oss-120b (OVH_AI_ENDPOINTS_ACCESS_TOKEN); docs- and roster-verified, not yet live-verified\nSarvam AI - default sarvam-105b (SARVAM_API_KEY); docs- and roster-verified, not yet live-verified\nSynthetic - default syn:large:text (SYNTHETIC_API_KEY); docs- and roster-verified, not yet live-verified\nAmbient - default ambient/large (AMBIENT_API_KEY); docs- and roster-verified, not yet live-verified\nInference.net - default glm-5.2 (INFERENCE_API_KEY); docs- and roster-verified, not yet live-verified\nEmpirioLabs AI - default glm-5-3","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Other providers (setup guides in the Provider Guides index)","lvl3":""}},
 {"objectID":"d17be3311722218280d0e76731e7344c620c18f5073e07abbc826f3922db976a","title":"💰 Model Availability & Cost Considerations","url":"/docs/getting-started/provider-setup#-model-availability-cost-considerations","content":"Important Notes:\nModel Availability: Specific models may not be available in all regions or require special access\nCost Variations: Pricing differs significantly between providers and models (e.g., Claude 3.5 Sonnet vs GPT-4o)\nRate Limits: Each provider has different rate limits and quota restrictions\nLocal vs Cloud: Ollama (local) has no per-request cost but requires hardware resources\nEnterprise Tiers: AWS Bedrock, Google Vertex AI, and Azure typically offer enterprise pricing\n\nBest Practices:\nUse new NeuroLink() with automatic provider selection for cost-optimized routing\nMonitor usage through built-in analytics to track costs\nConsider local models (Ollama) for development and testing\nCheck provider documentation for current pricing and availability","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"💰 Model Availability & Cost Considerations","lvl3":""}},
 {"objectID":"3a1bd0ccb708d37a59e2db3650f689f77fba69e91ec88142c7c9b85f1c18057d","title":"🏢 Enterprise Proxy Support","url":"/docs/getting-started/provider-setup#-enterprise-proxy-support","content":"Providers support corporate proxy environments automatically. Simply set environment variables:\n\nNo code changes required - NeuroLink automatically detects and uses proxy settings.\n\nFor detailed proxy setup → See Enterprise & Proxy Setup Guide","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"🏢 Enterprise Proxy Support","lvl3":""}},
-{"objectID":"1b0159447e4aee3ffd31efe28600cf755e4cc49d50f354e1a59d9574199213d2","title":"Supported Models","url":"/docs/getting-started/provider-setup#supported-models","content":"gpt-4o (default) - Latest multimodal model\ngpt-4o-mini - Cost-effective variant\ngpt-4-turbo - High-performance model","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Supported Models","lvl3":""}},
+{"objectID":"4e800f7c6d1d49fcbf1a5a8613f3449ee6fc0585728904b2f4b2d36dea4ce9ea","title":"Optional Configuration","url":"/docs/getting-started/provider-setup#optional-configuration","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Optional Configuration","lvl3":""}},
+{"objectID":"f455604e5b971c306f68461570edeca70b81f3a7b6cd9edd89d7e158bdfaddf9","title":"Optional: override the default model (default: gpt-4o-mini)","url":"/docs/getting-started/provider-setup#optional-override-the-default-model-default-gpt-4o-mini","content":"`","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Optional: override the default model (default: gpt-4o-mini)","lvl3":""}},
+{"objectID":"1b0159447e4aee3ffd31efe28600cf755e4cc49d50f354e1a59d9574199213d2","title":"Supported Models","url":"/docs/getting-started/provider-setup#supported-models","content":"gpt-5.4 - GPT-5.4 model\ngpt-5.4-mini - Cost-effective GPT-5.4 variant\ngpt-4o-mini (default) - Cost-effective variant\ngpt-4o - Previous generation multimodal model\ngpt-4-turbo - High-performance model\n\nSee the environment variables guide for the order in which the model is chosen when none is set.","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Supported Models","lvl3":""}},
 {"objectID":"27581667470b332f3c1c5159d4345a675be587f71dfb0d0b5d2a342adf1d2d44","title":"Timeout Configuration","url":"/docs/getting-started/provider-setup#timeout-configuration","content":"Default Timeout: 30 seconds\nSupported Formats: Milliseconds (30000), human-readable ('30s', '1m', '5m')\nEnvironment Variable: OPENAI_TIMEOUT='45s' (optional)","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"Timeout Configuration","lvl3":""}},
 {"objectID":"9c310a3f365a46c6628ae6910d2bb72ec8560e43353e044f6c9b73e5ce8d1798","title":"🚨 Critical Setup Requirements","url":"/docs/getting-started/provider-setup#-critical-setup-requirements","content":"⚠️ IMPORTANT: Anthropic Models Require Inference Profile ARN\n\nFor Anthropic Claude models in Bedrock, you MUST use the full inference profile ARN, not simple model names:\n\n`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"🚨 Critical Setup Requirements","lvl3":""}},
 {"objectID":"8f68b311be31716cccb17765bab6b712bc3ca441695a69967f7cc3c9cdf8929b","title":"export BEDROCK_MODEL=\"anthropic.claude-3-sonnet-20240229-v1:0\"","url":"/docs/getting-started/provider-setup#export-bedrock_modelanthropicclaude-3-sonnet-20240229-v10","content":"`","hierarchy":{"lvl0":"Getting Started","lvl1":"⚙️ Provider Configuration Guide","lvl2":"export BEDROCK_MODEL=\"anthropic.claude-3-sonnet-20240229-v1:0\"","lvl3":""}},
@@ -6789,7 +6791,7 @@
 {"objectID":"6102cd238f922f95762068dd3d2b3950e839a87ac388ee96bb805db79c47d00e","title":"Use specific model","url":"/docs/getting-started/providers/openai#use-specific-model","content":"pnpm run cli -- generate \"Write a haiku about AI\" \\\n  --provider openai \\\n  --model \"gpt-4o\"","hierarchy":{"lvl0":"Getting Started","lvl1":"OpenAI Provider Guide","lvl2":"Use specific model","lvl3":""}},
 {"objectID":"b56485bde526a3210810b768ba819d40dffdff5e3cf66309d26c5f53b89e30c1","title":"Interactive loop mode","url":"/docs/getting-started/providers/openai#interactive-loop-mode","content":"pnpm run cli -- loop \\\n  --provider openai \\\n  --model \"gpt-4o-mini\"\n`","hierarchy":{"lvl0":"Getting Started","lvl1":"OpenAI Provider Guide","lvl2":"Interactive loop mode","lvl3":""}},
 {"objectID":"dc674c0134ff9c1c707403e195849d7738176f984fe0c8226f05877f4951e0cd","title":"Available Models (from OpenAIModels enum)","url":"/docs/getting-started/providers/openai#available-models-from-openaimodels-enum","content":"| Enum Key              | Model ID              | Series       | Context Window | Notes                    |\n| --------------------- | --------------------- | ------------ | -------------- | ------------------------ |\n| GPT_6_ASTRA         | gpt-6-astra         | GPT-6        | 1.05M          | New (September 2026) |\n| GPT_6_SOL           | gpt-6-sol           | GPT-6        | 1.05M          | New (September 2026) |\n| GPT_6_LUNA          | gpt-6-luna          | GPT-6        | 1.05M          | New (September 2026) |\n| GPT_5_4             | gpt-5.4             | GPT-5.4      | 1.05M          | New (March 2026)     |\n| GPT_5_4_MINI        | gpt-5.4-mini        | GPT-5.4      | 400K           | New (March 2026)     |\n| GPT_5_4_NANO        | gpt-5.4-nano        | GPT-5.4      | 400K           | New (March 2026)     |\n| GPT_5_3_CODEX       | gpt-5.3-codex       | GPT-5.3      | 400K           |                          |\n| GPT_5_2             | gpt-5.2             | GPT-5.2      | 400K           |                          |\n| GPT_5_2_CHAT_LATEST | gpt-5.2-chat-latest | GPT-5.2      | 128K           |                          |\n| GPT_5_2_PRO         | gpt-5.2-pro         | GPT-5.2      | 400K           |                          |\n| GPT_5_2_CODEX       | gpt-5.2-codex       | GPT-5.2      | 400K           |                          |\n| GPT_5_1             | gpt-5.1             | GPT-5.1      | 400K           |                          |\n| GPT_5_1_CHAT_LATEST | gpt-5.1-chat-latest | GPT-5.1      | 128K           |                          |\n| GPT_5_1_CODEX       | gpt-5.1-codex       | GPT-5.1      | 400K           |                          |\n| GPT_5_1_CODEX_MAX   | gpt-5.1-codex-max   | GPT-5.1      | 400K           |                          |\n| GPT_5_1_CODEX_MINI  | gpt-5.1-codex-mini  | GPT-5.1      | 400K           |                          |\n| GPT_5               | gpt-5               | GPT-5        | 400K           |                          |\n| GPT_5_MINI","hierarchy":{"lvl0":"Getting Started","lvl1":"OpenAI Provider Guide","lvl2":"Available Models (from OpenAIModels enum)","lvl3":""}},
-{"objectID":"daaa71958d244b14e0a92247a5ea7890e487f466f9647915a9b274196dcf2cd3","title":"Default Model","url":"/docs/getting-started/providers/openai#default-model","content":"The default model when no model is specified is gpt-4o-mini (set via OpenAIModels.GPT_4O_MINI in the provider registry). This can be overridden with the OPENAI_MODEL environment variable.\n\nNote: When using NeuroLink SDK/CLI, the default is gpt-4o-mini. When instantiating OpenAIProvider directly without setting OPENAI_MODEL, the internal fallback is gpt-4o.","hierarchy":{"lvl0":"Getting Started","lvl1":"OpenAI Provider Guide","lvl2":"Default Model","lvl3":""}},
+{"objectID":"daaa71958d244b14e0a92247a5ea7890e487f466f9647915a9b274196dcf2cd3","title":"Default Model","url":"/docs/getting-started/providers/openai#default-model","content":"The default model when no model is specified is gpt-4o-mini (set via OpenAIModels.GPT_4O_MINI in the provider registry). This can be overridden with the OPENAI_MODEL environment variable.\n\nNote: When using NeuroLink SDK/CLI, the default is gpt-4o-mini. When instantiating OpenAIProvider directly without setting OPENAI_MODEL, the internal fallback is gpt-5.4.","hierarchy":{"lvl0":"Getting Started","lvl1":"OpenAI Provider Guide","lvl2":"Default Model","lvl3":""}},
 {"objectID":"a722c79038b2a55ddfff8bbe51cc124c6b52334826423cf1b4db83de4e7b9aef","title":"Multimodal Capabilities","url":"/docs/getting-started/providers/openai#multimodal-capabilities","content":"Models listed in VISION_CAPABILITIES for the openai provider support image analysis. This includes the GPT-5 family, GPT-4.1 family, GPT-4o family, and o-series models.","hierarchy":{"lvl0":"Getting Started","lvl1":"OpenAI Provider Guide","lvl2":"Multimodal Capabilities","lvl3":""}},
 {"objectID":"c331cb5e1ae253efea1792e057d6a4178c61191fe30972b6974856225af3cb12","title":"Image Analysis","url":"/docs/getting-started/providers/openai#image-analysis","content":"`bash","hierarchy":{"lvl0":"Getting Started","lvl1":"OpenAI Provider Guide","lvl2":"Image Analysis","lvl3":""}},
 {"objectID":"38a79b6cfe051e6742d94758c2df3c0646cae963aab6b4e141db528eb2890eed","title":"From file path (CLI)","url":"/docs/getting-started/providers/openai#from-file-path-cli","content":"pnpm run cli -- generate \"Describe this image\" \\\n  --provider openai \\\n  --model gpt-4o \\\n  --image ./photo.jpg\n\n\nThe provider supports up to **10 images per request** (defined in IMAGE_LIMITS in src/lib/adapters/providerImageAdapter.ts`).","hierarchy":{"lvl0":"Getting Started","lvl1":"OpenAI Provider Guide","lvl2":"From file path (CLI)","lvl3":""}},
@@ -9758,7 +9760,7 @@
 {"objectID":"72e3f0653f5610f5b565dde0eeb5fae0f9c2aa2e077546cf977d08fb5ba16d7a","title":"Environment Variables","url":"/docs/rag/CLI-COVERAGE#environment-variables","content":"The following environment variables can be used to configure default behavior:","hierarchy":{"lvl0":"Rag","lvl1":"RAG Processing - CLI Reference","lvl2":"Environment Variables","lvl3":""}},
 {"objectID":"08692e093a4e83ac5f475c624ccb93198b7787555cb016a315235c899937aa7e","title":"Provider & Authentication","url":"/docs/rag/CLI-COVERAGE#provider-authentication","content":"| Variable                  | Description                              | Default  |\n| ------------------------- | ---------------------------------------- | -------- |\n| NEUROLINK_PROVIDER      | Default AI provider                      | vertex |\n| AI_PROVIDER             | Alternative env var for default provider | vertex |\n| GOOGLE_CLOUD_PROJECT_ID | Google Cloud project ID (for Vertex AI)  | -        |\n| GOOGLE_API_KEY          | Google AI Studio API key                 | -        |\n| OPENAI_API_KEY          | OpenAI API key                           | -        |\n| ANTHROPIC_API_KEY       | Anthropic API key                        | -        |","hierarchy":{"lvl0":"Rag","lvl1":"RAG Processing - CLI Reference","lvl2":"Provider & Authentication","lvl3":""}},
 {"objectID":"07f864c105b32f6b1fc50e0cb08e2125ef5503b8fba263eb75f440ededc69f8b","title":"Embedding Models (for index and query commands)","url":"/docs/rag/CLI-COVERAGE#embedding-models-for-index-and-query-commands","content":"| Variable                       | Description                    | Default                        |\n| ------------------------------ | ------------------------------ | ------------------------------ |\n| NEUROLINK_EMBEDDING_MODEL    | Global default embedding model | Provider-specific default      |\n| VERTEX_EMBEDDING_MODEL       | Vertex AI embedding model      | text-embedding-004           |\n| GOOGLE_EMBEDDING_MODEL       | Google AI embedding model      | text-embedding-004           |\n| OPENAI_EMBEDDING_MODEL       | OpenAI embedding model         | text-embedding-3-small       |\n| AZURE_OPENAI_EMBEDDING_MODEL | Azure OpenAI embedding model   | text-embedding-3-small       |\n| BEDROCK_EMBEDDING_MODEL      | AWS Bedrock embedding model    | amazon.titan-embed-text-v2:0 |","hierarchy":{"lvl0":"Rag","lvl1":"RAG Processing - CLI Reference","lvl2":"Embedding Models (for index and query commands)","lvl3":""}},
-{"objectID":"50663c177a070a66d4944fcf5d84f98d78f14bd15f71691772f0dc73015bf0f1","title":"Generation Models (for chunk --extract and other text generation)","url":"/docs/rag/CLI-COVERAGE#generation-models-for-chunk---extract-and-other-text-generation","content":"| Variable             | Description                    | Default            |\n| -------------------- | ------------------------------ | ------------------ |\n| VERTEX_MODEL       | Default model for Vertex AI    | gemini-2.5-flash |\n| OPENAI_MODEL       | Default model for OpenAI       | gpt-4o           |\n| AZURE_OPENAI_MODEL | Default model for Azure OpenAI | Deployment-based   |\n| BEDROCK_MODEL      | Default model for AWS Bedrock  | Provider-specific  |","hierarchy":{"lvl0":"Rag","lvl1":"RAG Processing - CLI Reference","lvl2":"Generation Models (for chunk --extract and other text generation)","lvl3":""}},
+{"objectID":"50663c177a070a66d4944fcf5d84f98d78f14bd15f71691772f0dc73015bf0f1","title":"Generation Models (for chunk --extract and other text generation)","url":"/docs/rag/CLI-COVERAGE#generation-models-for-chunk---extract-and-other-text-generation","content":"| Variable             | Description                    | Default            |\n| -------------------- | ------------------------------ | ------------------ |\n| VERTEX_MODEL       | Default model for Vertex AI    | gemini-2.5-flash |\n| OPENAI_MODEL       | Default model for OpenAI       | gpt-4o-mini      |\n| AZURE_OPENAI_MODEL | Default model for Azure OpenAI | Deployment-based   |\n| BEDROCK_MODEL      | Default model for AWS Bedrock  | Provider-specific  |","hierarchy":{"lvl0":"Rag","lvl1":"RAG Processing - CLI Reference","lvl2":"Generation Models (for chunk --extract and other text generation)","lvl3":""}},
 {"objectID":"6c018c3875b57f47baf2f47fba0097a6ce95bc6057d3455ad0d76888b62885bb","title":"Embedding Model Resolution Order","url":"/docs/rag/CLI-COVERAGE#embedding-model-resolution-order","content":"For index and query commands, the embedding model is resolved in this order:\nCLI --model flag (if it's an embedding model)\nNEUROLINK_EMBEDDING_MODEL (global embedding model)\nProvider-specific embedding env vars (e.g., VERTEX_EMBEDDING_MODEL)\nProvider's default model env var (if it's an embedding model, e.g., if VERTEX_MODEL=text-embedding-004)\nProvider-specific default embedding model (e.g., text-embedding-004 for Vertex)\nFallback: OpenAI text-embedding-3-small\n\nNote: The RAG CLI is smart about model selection. Even if you have VERTEX_MODEL=gemini-2.5-flash set for text generation, the index and query commands will automatically use the appropriate embedding model for your provider.\nIf you explicitly specify a model with --model, ensure it's an embedding model that supports the embed() operation.","hierarchy":{"lvl0":"Rag","lvl1":"RAG Processing - CLI Reference","lvl2":"Embedding Model Resolution Order","lvl3":""}},
 {"objectID":"89a49e923879e964391df538667a2f5c4215cb7d3fc33a55f5b27872411f621e","title":"Common Errors","url":"/docs/rag/CLI-COVERAGE#common-errors","content":"File not found:\n\nEnsure the file path is correct and the file exists.\n\nNo indexed documents:\n\nYou must index a document before querying. Run neurolink rag index <file> first.\n\nIndex not found:\n\nThe specified index name doesn't exist. Check available indices or use the default.","hierarchy":{"lvl0":"Rag","lvl1":"RAG Processing - CLI Reference","lvl2":"Common Errors","lvl3":""}},
 {"objectID":"e2ed24b27e4284131ff513d59ed982787d2eef74c8dcbe04f9c5f8b4e7f74687","title":"Notes","url":"/docs/rag/CLI-COVERAGE#notes","content":"In-memory storage: Currently, indexed documents are stored in memory and will be lost when the process exits. For persistence, use the SDK API with a vector database.\nAuto-detection: When --strategy is not specified, the chunking strategy is automatically detected based on file extension.\nGraph RAG: Building a Graph RAG index (--graph) requires additional processing time but enables context-aware traversal during queries.","hierarchy":{"lvl0":"Rag","lvl1":"RAG Processing - CLI Reference","lvl2":"Notes","lvl3":""}},

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@juspay/neurolink",
-  "version": "12.47.3",
+  "version": "12.47.5",
   "packageManager": "pnpm@10.15.1",
   "description": "The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002/call) for routing, tool selection and context budgeting. MCP-native (4 transports), voice TTS/STT/realtime, RAG, agents, memory, compaction, 9 observability exporters. OpenAI · Anthropic · Gemini · Bedrock · Azure · Ollama · TypeSafe Jev and more.",
   "author": {
@@ -261,6 +261,7 @@
     "test:multimodal:sdk": "pnpm exec tsx test/continuous-test-suite-multimodal-sdk.ts",
     "test:video-frames": "pnpm exec tsx test/continuous-test-suite-video-frames.ts",
     "test:video-no-ffprobe": "pnpm exec tsx test/continuous-test-suite-video-no-ffprobe.ts",
+    "test:model-default-resolution": "pnpm exec tsx test/continuous-test-suite-model-default-resolution.ts",
     "test:video-native": "pnpm exec tsx test/continuous-test-suite-video-native.ts",
     "test:mcp-result-cache": "pnpm exec tsx test/continuous-test-suite-mcp-result-cache.ts",
     "test:mcp-breaker-resolved-errors": "pnpm exec tsx test/continuous-test-suite-mcp-breaker-resolved-errors.ts",