@gajae-code/ai 0.11.10 → 0.12.0

package/CHANGELOG.md

@@ -2,7 +2,34 @@
 
 ## [Unreleased]
 
-## [0.11.10] - 2026-07-25
+## [0.12.0] - 2026-07-28
+
+### Added
+
+- Added first-class support for **BizRouter**, an OpenAI-compatible Korean enterprise LLM gateway. Registers the `bizrouter` provider descriptor, `/login` entry (API-key paste validated against `https://api.bizrouter.ai/v1/models`), `BIZROUTER_API_KEY` environment resolution, and bundled `models.json` seed models. Models are discovered dynamically from `GET /v1/models` (base URL `https://api.bizrouter.ai/v1`).
+### Fixed
+
+- Anthropic subscription OAuth requests now use the current Claude Code compatibility attribution (`2.1.219`, `sdk-cli`) instead of the stale `2.1.63` CLI fingerprint that Anthropic can misclassify as extra usage.
+- Connection failures now name the transport code and the target URL. Bun reports DNS and socket failures as a bare `Error` whose message is a standalone hint ("Was there a typo in the url or port?", "Unable to connect. Is the computer able to access the url?") and keeps the actionable facts on `code` and `path`, but only `message` reached the assistant message. A provider outage, a local DNS failure, and a mistyped custom base URL therefore all rendered as the same context-free sentence with no host in it. Such failures now read `... (transport=FailedToOpenSocket url=https://chatgpt.com/backend-api/codex/responses)`; the URL is reduced to origin and path so a key carried in the query string is not surfaced.
+
+### Documentation
+
+- `docs/environment-variables.md` now names the Anthropic Foundry gateway variables that are actually read: `CLAUDE_CODE_USE_FOUNDRY`, `CLAUDE_CODE_CLIENT_CERT`, and `CLAUDE_CODE_CLIENT_KEY`. The page advertised `ANTHROPIC_MODEL_CODE_*` spellings that no code path reads, so an operator following it could not enable Foundry mode at all, and the mTLS client material was silently ignored.
+
+## [0.11.11] - 2026-07-26
+
+### Fixed
+
+- The Kimi usage endpoint base (`KIMI_CODE_BASE_URL`) is now resolved from trusted environment sources only. That base becomes the URL the usage request sends `Authorization: Bearer <accessToken>` to, so reading it through the merged view that includes the caller's `cwd/.env` let a repository collect the user's Kimi access token. An explicit caller-supplied base URL still takes precedence, and shell / user-level configuration is unchanged.
+- The Gemini CLI compatibility version used in the outbound `User-Agent` is refreshed from `0.50.0` to `0.52.0`, matching the current upstream release. The repository ships `check-spoofed-versions` for exactly this, but that check is not wired into CI, so the value had drifted two minor releases behind.
+- The OpenAI and Azure endpoint decisions are now resolved from trusted environment sources only: `OPENAI_BASE_URL` (streaming responses, completions, and the model manager) and `AZURE_OPENAI_BASE_URL`. `Bun.env` is `process.env` and the env module merges the caller's `cwd/.env` into it, so a repository could previously plant a `.env` that redirected authenticated requests; the two provider paths already reached for `$inheritedEnv` but re-admitted the project `.env` through a fallback. Resolution now goes through the non-project resolver (launching shell plus GJC/user-owned `.env` files); shell and user-level configuration is unchanged.
+- The OpenAI and Azure endpoint decisions are now resolved from trusted environment sources only: `OPENAI_BASE_URL` (streaming responses, completions, and the model manager), `AZURE_OPENAI_BASE_URL`, and `AZURE_OPENAI_RESOURCE_NAME` (the alternate constructor for the same Azure host). `Bun.env` is `process.env` and the env module merges the caller's `cwd/.env` into it, so a repository could previously plant a `.env` that redirected authenticated requests; the two provider paths already reached for `$inheritedEnv` but re-admitted the project `.env` through a fallback. Resolution now goes through the non-project resolver (launching shell plus GJC/user-owned `.env` files); shell and user-level configuration is unchanged.
+- Google credential material is now resolved from trusted environment sources only: the `GOOGLE_APPLICATION_CREDENTIALS` service-account / authorized-user file path used by the ADC loader, and `GOOGLE_CLOUD_API_KEY` used as the Vertex API key. Both were read through the merged view that includes the caller's `cwd/.env`, so a repository could ship a key file and point the agent at it, making it authenticate to Google as an identity the repository chose. `stream.ts` already resolved the same ADC variable through the non-project resolver; the two now agree. An explicit caller-supplied API key still takes precedence.
+- The Grok usage token fallback (`GROK_CLI_OAUTH_TOKEN`) is now resolved from trusted environment sources only. It authenticates the billing/usage call, and reading it through the merged view that includes the caller's `cwd/.env` let a repository decide which account that call ran against. Stored credentials keep precedence, and shell / user-level configuration is unchanged.
+- Anthropic `ping` keepalives no longer reset stream progress, so responses that stop producing content now reach the idle timeout instead of hanging indefinitely.
+- The Anthropic endpoint decision is now resolved from trusted environment sources only: `ANTHROPIC_BASE_URL`, `FOUNDRY_BASE_URL`, `ZCODE_PLAN_ANTHROPIC_BASE_URL`, and the `CLAUDE_CODE_USE_FOUNDRY` mode switch. `Bun.env` is `process.env` and the env module merges the caller's `cwd/.env` into it, so a repository could previously plant a `.env` that redirected authenticated Anthropic requests — the resolved base URL becomes `${baseUrl}/v1/messages` while the headers carry the API key or OAuth token. Resolution now goes through the non-project resolver (launching shell plus GJC/user-owned `.env` files); shell and user-level configuration is unchanged.
+- The documented `GJC_OPENAI_STREAM_IDLE_TIMEOUT_MS` environment variable now takes effect: the stream-watchdog idle-timeout helpers resolve it GJC-first before the legacy `PI_OPENAI_STREAM_IDLE_TIMEOUT_MS` / `PI_STREAM_IDLE_TIMEOUT_MS` aliases (previously only the `PI_`-prefixed names were read, so setting the documented GJC name was a silent no-op).
+- The documented OpenAI-code provider knobs now take effect: `GJC_OPENAI_CODE_DEBUG`, `GJC_OPENAI_CODE_WEBSOCKET`, `GJC_OPENAI_CODE_WEBSOCKET_IDLE_TIMEOUT_MS`, `GJC_OPENAI_CODE_WEBSOCKET_RETRY_BUDGET`, and `GJC_OPENAI_CODE_WEBSOCKET_RETRY_DELAY_MS` are resolved GJC-first ahead of the legacy `PI_CODEX_*` names. The Codex → OpenAI-code rename had updated the documentation but not the reads, so every documented name was a silent no-op.
 
 ## [0.11.9] - 2026-07-24
 ### Fixed

package/README.md

@@ -70,6 +70,7 @@ Unified LLM API with automatic model discovery, provider configuration, token an
 - **Xiaomi MiMo** (requires `XIAOMI_API_KEY`)
 - **ZenMux** (requires `ZENMUX_API_KEY`)
 - **OpenGateway by Sionic AI** (requires `OPENGATEWAY_API_KEY`)
+- **BizRouter** (requires `BIZROUTER_API_KEY`)
 - **Qwen Portal** (supports `QWEN_OAUTH_TOKEN` or `QWEN_PORTAL_API_KEY`)
 - **Cloudflare AI Gateway** (requires `CLOUDFLARE_AI_GATEWAY_API_KEY` and provider-specific gateway base URL)
 - **Ollama** (local OpenAI-compatible runtime; optional `OLLAMA_API_KEY`)
@@ -956,6 +957,7 @@ In Node.js environments, you can set environment variables to avoid passing API
 | Xiaomi MiMo    | `XIAOMI_API_KEY`                                                             |
 | ZenMux         | `ZENMUX_API_KEY`                                                             |
 | OpenGateway    | `OPENGATEWAY_API_KEY`                                                        |
+| BizRouter      | `BIZROUTER_API_KEY`                                                          |
 | vLLM           | `VLLM_API_KEY`                                                               |
 | Cloudflare AI Gateway | `CLOUDFLARE_AI_GATEWAY_API_KEY`                                      |
 | GitHub Copilot | `COPILOT_GITHUB_TOKEN` or `GH_TOKEN` or `GITHUB_TOKEN`                      |
@@ -980,6 +982,7 @@ Provider endpoint defaults for the current OpenAI-compatible integrations:
 - ZenMux (OpenAI): `https://zenmux.ai/api/v1`
 - ZenMux (Anthropic models): `https://zenmux.ai/api/anthropic`
 - OpenGateway by Sionic AI: `https://apis.opengateway.ai/v1`
+- BizRouter: `https://api.bizrouter.ai/v1`
 - vLLM: `http://127.0.0.1:8000/v1`
 - Ollama: local OpenAI-compatible runtime (`http://127.0.0.1:11434/v1`)
 - Ollama Cloud: native Ollama API host (`https://ollama.com/api`, configured here as base URL `https://ollama.com`)

package/dist/types/provider-models/openai-compat.d.ts

@@ -27,6 +27,8 @@ export interface OpenAIModelManagerConfig {
     apiKey?: string;
     baseUrl?: string;
 }
+/** Test seam: the model-manager base URL as resolved from trusted env. */
+export declare function resolveOpenAIModelManagerBaseUrlForTest(config?: OpenAIModelManagerConfig): string;
 export declare function openaiModelManagerOptions(config?: OpenAIModelManagerConfig): ModelManagerOptions<"openai-responses">;
 export interface GroqModelManagerConfig {
     apiKey?: string;
@@ -121,6 +123,11 @@ export interface OpenGatewayModelManagerConfig {
  * the OpenAI-compatible `/v1/models` endpoint.
  */
 export declare function opengatewayModelManagerOptions(config?: OpenGatewayModelManagerConfig): ModelManagerOptions<"openai-completions">;
+export interface BizRouterModelManagerConfig {
+    apiKey?: string;
+    baseUrl?: string;
+}
+export declare function bizrouterModelManagerOptions(config?: BizRouterModelManagerConfig): ModelManagerOptions<"openai-completions">;
 export interface KiloModelManagerConfig {
     apiKey?: string;
     baseUrl?: string;

package/dist/types/providers/anthropic.d.ts

@@ -50,7 +50,8 @@ export declare function isAnthropicThinkingBlockMutationError(error: unknown): b
  * than only the latest one.
  */
 export declare function isAnthropicThinkingSignatureInvalidError(error: unknown): boolean;
-export declare const claudeCodeVersion = "2.1.63";
+export declare const claudeCodeVersion = "2.1.219";
+export declare const claudeCodeEntrypoint = "sdk-cli";
 export declare const claudeToolPrefix: string;
 export declare const claudeCodeSystemInstruction = "You are a Claude agent, built on Anthropic's Claude Agent SDK.";
 export declare function mapStainlessOs(platform: string): "MacOS" | "Windows" | "Linux" | "FreeBSD" | `Other::${string}`;

package/dist/types/providers/azure-openai-responses.d.ts

@@ -1,4 +1,4 @@
-import type { ServiceTier, StreamFunction, StreamOptions, ToolChoice } from "../types";
+import type { Model, ServiceTier, StreamFunction, StreamOptions, ToolChoice } from "../types";
 export interface AzureOpenAIResponsesOptions extends StreamOptions {
     reasoning?: "minimal" | "low" | "medium" | "high" | "xhigh" | "max";
     reasoningSummary?: "auto" | "detailed" | "concise" | null;
@@ -13,3 +13,8 @@ export interface AzureOpenAIResponsesOptions extends StreamOptions {
  * Generate function for Azure OpenAI Responses API
  */
 export declare const streamAzureOpenAIResponses: StreamFunction<"azure-openai-responses">;
+/** Test seam: the Azure endpoint config as resolved from trusted env. */
+export declare function resolveAzureConfigForTest(model: Model<"azure-openai-responses">, options?: AzureOpenAIResponsesOptions): {
+    baseUrl: string;
+    apiVersion: string;
+};

package/dist/types/providers/google-auth.d.ts

@@ -12,6 +12,8 @@
  * (default 60s). Concurrent callers waiting on a refresh share the same in-flight promise.
  */
 import type { FetchImpl } from "../types";
+/** Test seam: the ADC credentials file path as resolved from trusted env. */
+export declare function resolveAdcCredentialsPathForTest(): string | undefined;
 /**
  * Returns a Bearer access token suitable for the `Authorization` header on Vertex AI calls.
  * The token is cached in module scope and refreshed `GOOGLE_VERTEX_REFRESH_SKEW_MS` ms before it expires.

package/dist/types/providers/google-gemini-headers.d.ts

@@ -5,7 +5,7 @@
  */
 export declare const GEMINI_CLI_VERSION_ENV = "GJC_AI_GEMINI_CLI_VERSION";
 export declare const LEGACY_GEMINI_CLI_VERSION_ENV = "PI_AI_GEMINI_CLI_VERSION";
-export declare const DEFAULT_GEMINI_CLI_VERSION = "0.50.0";
+export declare const DEFAULT_GEMINI_CLI_VERSION = "0.52.0";
 export declare function getGeminiCliUserAgent(modelId?: string): string;
 export declare const getGeminiCliHeaders: (modelId?: string) => {
     "User-Agent": string;

package/dist/types/providers/google-vertex.d.ts

@@ -5,3 +5,5 @@ export interface GoogleVertexOptions extends GoogleSharedStreamOptions {
     location?: string;
 }
 export declare const streamGoogleVertex: StreamFunction<"google-vertex">;
+/** Test seam: the Vertex API key as resolved from options plus trusted env. */
+export declare function resolveVertexApiKeyForTest(options?: GoogleVertexOptions): string | undefined;

package/dist/types/providers/openai-codex-responses.d.ts

@@ -10,6 +10,10 @@ export interface OpenAICodexResponsesOptions extends StreamOptions {
     preferWebsockets?: boolean;
     serviceTier?: ServiceTier;
 }
+/** Maps a canonical tool name to the name Codex accepts on the wire. */
+export declare function codexToolWireName(name: string): string;
+/** Maps a Codex wire tool name back to the canonical harness tool name. */
+export declare function codexToolCanonicalName(wireName: string): string;
 type CodexTransport = "sse" | "websocket";
 export interface OpenAICodexWebSocketDebugStats {
     fullContextRequests: number;

package/dist/types/providers/openai-completions.d.ts

@@ -1,6 +1,8 @@
 import type { ChatCompletionMessageParam } from "openai/resources/chat/completions";
 import { type AssistantMessage, type Context, type Model, type ServiceTier, type StreamFunction, type StreamOptions, type ToolChoice } from "../types";
 import { type ResolvedOpenAICompat } from "./openai-completions-compat";
+/** Test seam: the provider base URL as resolved from trusted env. */
+export declare function resolveOpenAICompletionsBaseUrlForTest(baseUrl: string | undefined, authCredentialType: "api_key" | "oauth" | undefined): string;
 /**
  * Identify "real progress" stream chunks vs. keepalives, role-only preambles,
  * and empty `{choices:[]}` no-ops emitted by some OpenAI-compatible endpoints.

package/dist/types/providers/openai-responses.d.ts

@@ -13,6 +13,8 @@ export interface OpenAIResponsesOptions extends StreamOptions {
      */
     strictResponsesPairing?: boolean;
 }
+/** Test seam: the provider base URL as resolved from trusted env. */
+export declare function resolveOpenAIProviderBaseUrlForTest(baseUrl: string | undefined, authCredentialType: "api_key" | "oauth" | undefined): string;
 /**
  * Generate function for OpenAI Responses API
  */

package/dist/types/types.d.ts

@@ -51,7 +51,7 @@ export interface ThinkingConfig {
     /** Provider-specific transport used to encode the selected effort. */
     mode: ThinkingControlMode;
 }
-export type KnownProvider = "alibaba-token-plan" | "amazon-bedrock" | "azure-openai" | "anthropic" | "google" | "google-gemini-cli" | "google-antigravity" | "google-vertex" | "openai" | "openai-codex" | "kimi-code" | "minimax-code" | "minimax-code-cn" | "github-copilot" | "fireworks" | "firepass" | "fugu" | "gitlab-duo" | "cursor" | "deepseek" | "deepinfra" | "xai" | "groq" | "cerebras" | "openrouter" | "kilo" | "vercel-ai-gateway" | "zai" | "glm-zcode" | "mistral" | "minimax" | "opencode-go" | "opencode-zen" | "opengateway" | "synthetic" | "cloudflare-ai-gateway" | "huggingface" | "litellm" | "moonshot" | "nvidia" | "nanogpt" | "ollama" | "ollama-cloud" | "qianfan" | "qwen-portal" | "together" | "venice" | "vllm" | "xiaomi" | "xiaomi-token-plan-sgp" | "xiaomi-token-plan-ams" | "xiaomi-token-plan-cn" | "zenmux" | "lm-studio";
+export type KnownProvider = "alibaba-token-plan" | "amazon-bedrock" | "azure-openai" | "anthropic" | "google" | "google-gemini-cli" | "google-antigravity" | "google-vertex" | "openai" | "openai-codex" | "kimi-code" | "minimax-code" | "minimax-code-cn" | "github-copilot" | "fireworks" | "firepass" | "fugu" | "gitlab-duo" | "cursor" | "deepseek" | "deepinfra" | "xai" | "groq" | "cerebras" | "openrouter" | "kilo" | "vercel-ai-gateway" | "zai" | "glm-zcode" | "mistral" | "minimax" | "opencode-go" | "opencode-zen" | "opengateway" | "bizrouter" | "synthetic" | "cloudflare-ai-gateway" | "huggingface" | "litellm" | "moonshot" | "nvidia" | "nanogpt" | "ollama" | "ollama-cloud" | "qianfan" | "qwen-portal" | "together" | "venice" | "vllm" | "xiaomi" | "xiaomi-token-plan-sgp" | "xiaomi-token-plan-ams" | "xiaomi-token-plan-cn" | "zenmux" | "lm-studio";
 export type Provider = KnownProvider | string;
 import type { Effort } from "./model-thinking";
 /** Token budgets for each thinking level (token-based providers only) */

package/dist/types/usage/grok-cli.d.ts

@@ -1,10 +1,12 @@
-import type { CredentialRankingStrategy, UsageProvider } from "../usage";
+import type { CredentialRankingStrategy, UsageFetchParams, UsageProvider } from "../usage";
 interface BillingUsage {
     monthlyLimit: number;
     used: number;
     billingPeriodEnd: string;
 }
 export declare function parseGrokCliBillingUsage(payload: unknown): BillingUsage;
+/** Test seam: the usage access token as resolved from a credential plus trusted env. */
+export declare function resolveGrokAccessTokenForTest(params: UsageFetchParams): string | undefined;
 export declare const grokCliUsageProvider: UsageProvider;
 export declare const grokCliRankingStrategy: CredentialRankingStrategy;
 export {};

package/dist/types/usage/kimi.d.ts

@@ -1,2 +1,4 @@
 import type { UsageProvider } from "../usage";
+/** Test seam: the usage base URL as resolved from a caller value plus trusted env. */
+export declare function normalizeKimiUsageBaseUrlForTest(baseUrl?: string): string;
 export declare const kimiUsageProvider: UsageProvider;

package/dist/types/utils/anthropic-auth.d.ts

@@ -4,6 +4,14 @@ export interface AnthropicAuthConfig {
     baseUrl: string;
     isOAuth: boolean;
 }
+/**
+ * Resolve the Anthropic base URL from the environment.
+ *
+ * Trusted sources only: the result becomes the request URL that carries the
+ * Anthropic API key / OAuth token, so whatever can set it can redirect
+ * authenticated traffic. `$env` merges the caller's `cwd/.env`, so reading it
+ * there would let repository content choose where credentials are sent.
+ */
 export declare function resolveAnthropicBaseUrlFromEnv(): string | undefined;
 /**
  * Checks if a token is an OAuth token by looking for sk-ant-oat prefix.

package/dist/types/utils/foundry.d.ts

@@ -1 +1,11 @@
+/**
+ * Whether Anthropic requests run in Foundry gateway mode.
+ *
+ * Resolved from trusted environment sources only. Enabling Foundry switches the
+ * request base URL and injects TLS client material, so whatever can set this
+ * redirects authenticated traffic. `$env` merges the caller's `cwd/.env`, so
+ * reading it there would let repository content flip the mode; resolve it the
+ * same way the credentials themselves are (launching shell plus GJC/user-owned
+ * `.env` files, never the project `.env`).
+ */
 export declare function isFoundryEnabled(): boolean;

package/dist/types/utils/http-inspector.d.ts

@@ -18,6 +18,19 @@ export declare function isModelUnavailableError(message: string, error: unknown)
 /** Actionable guidance for selecting an available model/provider. */
 export declare function formatModelUnavailableGuidance(dump: RawHttpRequestDump | undefined): string;
 export declare function appendRawHttpRequestDumpFor400(message: string, error: unknown, dump: RawHttpRequestDump | undefined): Promise<string>;
+/**
+ * Name the failed connection when the request never produced an HTTP status.
+ *
+ * Bun raises DNS and socket failures as a bare `Error` whose message is a
+ * standalone hint ("Was there a typo in the url or port?", "Unable to connect.
+ * Is the computer able to access the url?") while the actionable facts live on
+ * `code` and `path`. Those properties are dropped when only `message` reaches
+ * the assistant message, so a provider outage, a local DNS failure, and a
+ * mistyped custom base URL all render as the same context-free sentence.
+ * Appending the code and the target URL tells the user which host failed and
+ * whether the fault is theirs.
+ */
+export declare function appendTransportFailureContext(message: string, error: unknown, rawRequestDump: RawHttpRequestDump | undefined): string;
 export declare function finalizeErrorMessage(error: unknown, rawRequestDump: RawHttpRequestDump | undefined, capturedErrorResponse?: CapturedHttpErrorResponse): Promise<string>;
 export declare function withHttpStatus(error: unknown, status: number): Error;
 /**

package/dist/types/utils/idle-iterator.d.ts

@@ -2,7 +2,7 @@ export declare function getProviderFirstEventTimeoutFallbackMs(provider: string)
 /**
  * Returns the idle timeout used for provider streaming transports.
  *
- * `PI_OPENAI_STREAM_IDLE_TIMEOUT_MS` is accepted as a backward-compatible alias.
+ * `GJC_OPENAI_STREAM_IDLE_TIMEOUT_MS` is honored first; `PI_OPENAI_STREAM_IDLE_TIMEOUT_MS` is a backward-compatible alias.
  * Set `PI_STREAM_IDLE_TIMEOUT_MS=0` to disable the watchdog.
  *
  * Providers that legitimately stream much slower than the global default can pass
@@ -13,7 +13,7 @@ export declare function getStreamIdleTimeoutMs(fallbackMs?: number): number | un
 /**
  * Returns the idle timeout used for OpenAI-family streaming transports.
  *
- * Set `PI_OPENAI_STREAM_IDLE_TIMEOUT_MS=0` to disable the watchdog.
+ * Honors `GJC_OPENAI_STREAM_IDLE_TIMEOUT_MS` first (`PI_OPENAI_STREAM_IDLE_TIMEOUT_MS` is the legacy alias). Set `=0` to disable.
  */
 export declare function getOpenAIStreamIdleTimeoutMs(): number | undefined;
 /**

package/dist/types/utils/oauth/bizrouter.d.ts

@@ -0,0 +1 @@
+export declare const loginBizRouter: (options: import("./types").OAuthController) => Promise<string>;

package/dist/types/utils/oauth/types.d.ts

@@ -7,7 +7,7 @@ export type OAuthCredentials = {
     email?: string;
     accountId?: string;
 };
-export type OAuthProvider = "alibaba-token-plan" | "anthropic" | "cerebras" | "cloudflare-ai-gateway" | "cursor" | "deepseek" | "deepinfra" | "fireworks" | "firepass" | "fugu" | "github-copilot" | "google-gemini-cli" | "google-antigravity" | "gitlab-duo" | "huggingface" | "kimi-code" | "kilo" | "kagi" | "litellm" | "lm-studio" | "minimax-code" | "minimax-code-cn" | "moonshot" | "nvidia" | "nanogpt" | "ollama" | "ollama-cloud" | "openai-codex" | "openai-codex-device" | "opencode-go" | "opencode-zen" | "opengateway" | "parallel" | "perplexity" | "qianfan" | "qwen-portal" | "synthetic" | "tavily" | "together" | "venice" | "vercel-ai-gateway" | "vllm" | "xai" | "glm-zcode" | "xiaomi" | "xiaomi-token-plan-sgp" | "xiaomi-token-plan-ams" | "xiaomi-token-plan-cn" | "zenmux" | "zai";
+export type OAuthProvider = "alibaba-token-plan" | "anthropic" | "bizrouter" | "cerebras" | "cloudflare-ai-gateway" | "cursor" | "deepseek" | "deepinfra" | "fireworks" | "firepass" | "fugu" | "github-copilot" | "google-gemini-cli" | "google-antigravity" | "gitlab-duo" | "huggingface" | "kimi-code" | "kilo" | "kagi" | "litellm" | "lm-studio" | "minimax-code" | "minimax-code-cn" | "moonshot" | "nvidia" | "nanogpt" | "ollama" | "ollama-cloud" | "openai-codex" | "openai-codex-device" | "opencode-go" | "opencode-zen" | "opengateway" | "parallel" | "perplexity" | "qianfan" | "qwen-portal" | "synthetic" | "tavily" | "together" | "venice" | "vercel-ai-gateway" | "vllm" | "xai" | "glm-zcode" | "xiaomi" | "xiaomi-token-plan-sgp" | "xiaomi-token-plan-ams" | "xiaomi-token-plan-cn" | "zenmux" | "zai";
 export type OAuthProviderId = OAuthProvider | (string & {});
 export type OAuthPrompt = {
     message: string;

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@gajae-code/ai",
-	"version": "0.11.10",
+	"version": "0.12.0",
 	"description": "Unified LLM API with automatic model discovery and provider configuration",
 	"homepage": "https://gajae-code.com",
 	"author": "Yeachan-Heo and Gajae Code Contributors",
@@ -40,7 +40,7 @@
 	"dependencies": {
 		"@anthropic-ai/sdk": "^0.94.0",
 		"@bufbuild/protobuf": "^2.12.0",
-		"@gajae-code/utils": "0.11.10",
+		"@gajae-code/utils": "0.12.0",
 		"openai": "^6.36.0",
 		"partial-json": "^0.1.7",
 		"zod": "4.4.3"

package/src/auth-storage.ts

@@ -1998,6 +1998,12 @@ export class AuthStorage {
 				await saveApiKeyCredential(apiKey);
 				return;
 			}
+			case "bizrouter": {
+				const { loginBizRouter } = await import("./utils/oauth/bizrouter");
+				const apiKey = await loginBizRouter(ctrl);
+				await saveApiKeyCredential(apiKey);
+				return;
+			}
 			case "opengateway": {
 				const { loginOpenGateway } = await import("./utils/oauth/opengateway");
 				const apiKey = await loginOpenGateway(ctrl);

package/src/cli.ts

@@ -119,6 +119,7 @@ Providers:
   cursor            Cursor (Anthropic, GPT, etc.)
   zenmux            ZenMux
   opengateway       OpenGateway by Sionic AI
+  bizrouter         BizRouter
   ollama-cloud      Ollama Cloud
 
 Examples:

package/src/models.json

@@ -4030,6 +4030,78 @@
 			}
 		}
 	},
+	"bizrouter": {
+		"anthropic/claude-sonnet-4.5": {
+			"id": "anthropic/claude-sonnet-4.5",
+			"name": "Anthropic Sonnet 4.5",
+			"api": "openai-completions",
+			"provider": "bizrouter",
+			"baseUrl": "https://api.bizrouter.ai/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 3,
+				"output": 15,
+				"cacheRead": 0.3,
+				"cacheWrite": 3.75
+			},
+			"contextWindow": 200000,
+			"maxTokens": 64000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			}
+		},
+		"google/gemini-2.5-pro": {
+			"id": "google/gemini-2.5-pro",
+			"name": "Gemini 2.5 Pro",
+			"api": "openai-completions",
+			"provider": "bizrouter",
+			"baseUrl": "https://api.bizrouter.ai/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 1.25,
+				"output": 10,
+				"cacheRead": 0.31,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1048576,
+			"maxTokens": 65536,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "high"
+			}
+		},
+		"openai/gpt-4o": {
+			"id": "openai/gpt-4o",
+			"name": "GPT-4o",
+			"api": "openai-completions",
+			"provider": "bizrouter",
+			"baseUrl": "https://api.bizrouter.ai/v1",
+			"reasoning": false,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 2.5,
+				"output": 10,
+				"cacheRead": 1.25,
+				"cacheWrite": 0
+			},
+			"contextWindow": 128000,
+			"maxTokens": 16384
+		}
+	},
 	"cerebras": {
 		"gemma-4-31b": {
 			"id": "gemma-4-31b",

package/src/provider-models/descriptors.ts

@@ -11,6 +11,7 @@ import { ollamaCloudModelManagerOptions } from "./ollama";
 import {
 	alibabaTokenPlanModelManagerOptions,
 	anthropicModelManagerOptions,
+	bizrouterModelManagerOptions,
 	cerebrasModelManagerOptions,
 	cloudflareAiGatewayModelManagerOptions,
 	deepinfraModelManagerOptions,
@@ -319,6 +320,12 @@ export const PROVIDER_DESCRIPTORS: readonly ProviderDescriptor[] = [
 		config => opengatewayModelManagerOptions(config),
 		catalog("OpenGateway by Sionic AI", ["OPENGATEWAY_API_KEY"]),
 	),
+	catalogDescriptor(
+		"bizrouter",
+		"anthropic/claude-sonnet-4.5",
+		config => bizrouterModelManagerOptions(config),
+		catalog("BizRouter", ["BIZROUTER_API_KEY"]),
+	),
 	catalogDescriptor("zai", "glm-5.2", config => zaiModelManagerOptions(config), catalog("zAI", ["ZAI_API_KEY"])),
 	catalogDescriptor(
 		"glm-zcode",

package/src/provider-models/openai-compat.ts

@@ -1,4 +1,4 @@
-import { $env, $inheritedEnv } from "@gajae-code/utils";
+import { $credentialEnv } from "@gajae-code/utils";
 import type { ModelManagerOptions } from "../model-manager";
 import { Effort } from "../model-thinking";
 import { getBundledModels } from "../models";
@@ -553,13 +553,19 @@ export interface OpenAIModelManagerConfig {
 	baseUrl?: string;
 }
 
+/** Base URL for the OpenAI model manager, from trusted env only (`$env` merges the caller's `cwd/.env`). */
+function resolveOpenAIModelManagerBaseUrl(config?: OpenAIModelManagerConfig): string {
+	return config?.baseUrl?.trim() || $credentialEnv("OPENAI_BASE_URL") || OPENAI_DEFAULT_BASE_URL;
+}
+
+/** Test seam: the model-manager base URL as resolved from trusted env. */
+export function resolveOpenAIModelManagerBaseUrlForTest(config?: OpenAIModelManagerConfig): string {
+	return resolveOpenAIModelManagerBaseUrl(config);
+}
+
 export function openaiModelManagerOptions(config?: OpenAIModelManagerConfig): ModelManagerOptions<"openai-responses"> {
 	const apiKey = config?.apiKey;
-	const baseUrl =
-		config?.baseUrl?.trim() ||
-		$inheritedEnv("OPENAI_BASE_URL") ||
-		$env.OPENAI_BASE_URL?.trim() ||
-		OPENAI_DEFAULT_BASE_URL;
+	const baseUrl = resolveOpenAIModelManagerBaseUrl(config);
 	const references = createBundledReferenceMap<"openai-responses">("openai");
 	return {
 		providerId: "openai",
@@ -1119,6 +1125,61 @@ export function opengatewayModelManagerOptions(
 	return createSimpleOpenAICompletionsOptions("opengateway", "https://apis.opengateway.ai/v1", config);
 }
 
+// ---------------------------------------------------------------------------
+// 10.5.2 BizRouter
+// ---------------------------------------------------------------------------
+
+const BIZROUTER_BASE_URL = "https://api.bizrouter.ai/v1";
+
+function toBizRouterPrice(value: unknown, fallback: number): number {
+	const parsed = toNumber(value);
+	return parsed === undefined || parsed < 0 ? fallback : parsed;
+}
+
+export interface BizRouterModelManagerConfig {
+	apiKey?: string;
+	baseUrl?: string;
+}
+
+export function bizrouterModelManagerOptions(
+	config?: BizRouterModelManagerConfig,
+): ModelManagerOptions<"openai-completions"> {
+	const apiKey = config?.apiKey;
+	const baseUrl = config?.baseUrl ?? BIZROUTER_BASE_URL;
+	const references = createBundledReferenceMap<"openai-completions">("bizrouter");
+	return {
+		providerId: "bizrouter",
+		...(apiKey && {
+			fetchDynamicModels: () =>
+				fetchOpenAICompatibleModels({
+					api: "openai-completions",
+					provider: "bizrouter",
+					baseUrl,
+					apiKey,
+					mapModel: (entry, defaults) => {
+						const mapped = mapWithBundledReference(entry, defaults, references.get(defaults.id));
+						return {
+							...mapped,
+							name: toModelName(entry.display_name, mapped.name),
+							contextWindow: toPositiveNumber(entry.context_length, mapped.contextWindow),
+							maxTokens: toPositiveNumber(entry.max_output_tokens, mapped.maxTokens),
+							input: toInputCapabilities(entry.input_modalities),
+							cost: {
+								input: toBizRouterPrice(entry.input_price_per_1m_usd, mapped.cost.input),
+								output: toBizRouterPrice(entry.output_price_per_1m_usd, mapped.cost.output),
+								cacheRead: mapped.cost.cacheRead,
+								cacheWrite: mapped.cost.cacheWrite,
+							},
+							api: "openai-completions",
+							provider: "bizrouter",
+							baseUrl,
+						};
+					},
+				}),
+		}),
+	};
+}
+
 // ---------------------------------------------------------------------------
 // 10.6 Kilo Gateway
 // ---------------------------------------------------------------------------

package/src/providers/anthropic.ts

@@ -11,6 +11,7 @@ import type {
 	RawMessageStreamEvent,
 } from "@anthropic-ai/sdk/resources/messages";
 import {
+	$credentialEnv,
 	$env,
 	extractHttpStatusFromError,
 	isEnoent,
@@ -490,7 +491,8 @@ function getCacheControl(
 }
 
 // Stealth mode: Mimic Anthropic Code headers and tool prefixing.
-export const claudeCodeVersion = "2.1.63";
+export const claudeCodeVersion = "2.1.219";
+export const claudeCodeEntrypoint = "sdk-cli";
 export const claudeToolPrefix: string = "proxy_";
 export const claudeCodeSystemInstruction = "You are a Claude agent, built on Anthropic's Claude Agent SDK.";
 
@@ -566,7 +568,7 @@ function createClaudeBillingHeader(payload: unknown): string {
 	const buildHash = Array.from(randomBytes, byte => byte.toString(16).padStart(2, "0"))
 		.join("")
 		.slice(0, 3);
-	return `${CLAUDE_BILLING_HEADER_PREFIX} cc_version=${claudeCodeVersion}.${buildHash}; cc_entrypoint=cli; cch=${cch};`;
+	return `${CLAUDE_BILLING_HEADER_PREFIX} cc_version=${claudeCodeVersion}.${buildHash}; cc_entrypoint=${claudeCodeEntrypoint}; cch=${cch};`;
 }
 
 const CLAUDE_CLOAKING_USER_ID_REGEX =
@@ -816,10 +818,12 @@ function resolveAnthropicBaseUrl(model: Model<"anthropic-messages">, apiKey?: st
 	// calls api.z.ai directly (no zcode.z.ai gateway, no captcha). Pin the base so dynamic
 	// discovery / stale bundled catalogs / model cache can't redirect it elsewhere.
 	if (model.provider === "glm-zcode") {
-		return normalizeAnthropicBaseUrl(process.env.ZCODE_PLAN_ANTHROPIC_BASE_URL) ?? "https://api.z.ai/api/anthropic";
+		return (
+			normalizeAnthropicBaseUrl($credentialEnv("ZCODE_PLAN_ANTHROPIC_BASE_URL")) ?? "https://api.z.ai/api/anthropic"
+		);
 	}
 	if (model.provider === "anthropic" && isFoundryEnabled()) {
-		const foundryBaseUrl = normalizeAnthropicBaseUrl($env.FOUNDRY_BASE_URL);
+		const foundryBaseUrl = normalizeAnthropicBaseUrl($credentialEnv("FOUNDRY_BASE_URL"));
 		if (foundryBaseUrl) {
 			return foundryBaseUrl;
 		}
@@ -1182,6 +1186,40 @@ function shouldIgnoreAnthropicPreambleEvent(eventType: unknown): boolean {
 	return !ANTHROPIC_PRE_MESSAGE_START_EVENT_TYPES.has(eventType);
 }
 
+function createAnthropicStreamProgressPredicate(): (event: unknown) => boolean {
+	let outputTokens = -1;
+
+	return event => {
+		if (!isRecord(event) || typeof event.type !== "string") return false;
+		if (
+			event.type === "message_start" ||
+			event.type === "content_block_start" ||
+			event.type === "content_block_stop" ||
+			event.type === "message_stop"
+		) {
+			return true;
+		}
+		if (event.type === "content_block_delta") {
+			if (!isRecord(event.delta)) return false;
+			const delta = event.delta;
+			return (
+				(typeof delta.text === "string" && delta.text.length > 0) ||
+				(typeof delta.thinking === "string" && delta.thinking.length > 0) ||
+				(typeof delta.partial_json === "string" && delta.partial_json.length > 0) ||
+				(typeof delta.signature === "string" && delta.signature.length > 0)
+			);
+		}
+		if (event.type === "message_delta") {
+			if (isRecord(event.delta) && event.delta.stop_reason != null) return true;
+			if (!isRecord(event.usage) || typeof event.usage.output_tokens !== "number") return false;
+			if (event.usage.output_tokens <= outputTokens) return false;
+			outputTokens = event.usage.output_tokens;
+			return true;
+		}
+		return false;
+	};
+}
+
 function isTransientStreamEnvelopeError(error: unknown): boolean {
 	if (!(error instanceof Error)) return false;
 	return (
@@ -1457,6 +1495,7 @@ export const streamAnthropic: StreamFunction<"anthropic-messages"> = (
 					let sawEvent = false;
 					let sawMessageStart = false;
 					let sawTerminalEnvelope = false;
+					const isProgressEvent = createAnthropicStreamProgressPredicate();
 
 					for await (const event of iterateWithIdleTimeout(anthropicStream, {
 						idleTimeoutMs,
@@ -1466,6 +1505,7 @@ export const streamAnthropic: StreamFunction<"anthropic-messages"> = (
 						onIdle: () => activeAbortTracker.abortLocally(idleTimeoutAbortError),
 						onFirstItemTimeout: () => activeAbortTracker.abortLocally(firstEventTimeoutAbortError),
 						abortSignal: options?.signal,
+						isProgressItem: isProgressEvent,
 					})) {
 						sawEvent = true;
 						if (sawProviderSafetyStop) {