@linxiraos/pi-ai 1.1.8 → 1.1.9

package/CHANGELOG.md

@@ -2,10 +2,9 @@
 
 ## [Unreleased]
 
-## [1.1.8] - 2026-09-04
+## [1.1.9] - 2026-09-05
 
-- OMP sync v18.1.2–v18.1.5: Copilot auth standardization, transport-error-safe retries after tool calls, and prefix-binding control state.
-- Fixed the Z.ai OAuth key name to the Zeta brand (`zeta`) — the merge had reintroduced upstream's `oh-my-pi` fixture rows.
+- Z.ai OAuth key name sends zeta (merge restored the upstream oh-my-pi literal in tests); xAI/OpenAI-compatible requests send the zeta User-Agent again.
 
 ## [1.1.6] - 2026-08-30
 
@@ -43,20 +42,3 @@
 
 - Reset the version to 1.0.0 and republished under the `@linxiraos/*` scope, breaking from the `@linxiraos` version lineage.
 - Fixed Gemini thought summaries occasionally leaking a raw `` ```thinking `` / `` ``````thinking `` fence delimiter into the reasoning block, so it no longer shows up as fence spam in the thinking display or persisted transcripts ([#8719](https://github.com/can1357/oh-my-pi/issues/8719)).
-- Fixed the OpenCode Go login prompting for an "OpenCode Zen API key": the shared login flow now names the provider you selected, so connecting OpenCode Go asks for an OpenCode Go key (the `opencode.ai/auth` console is still shared, as documented upstream) ([#8738](https://github.com/can1357/oh-my-pi/issues/8738)).
-- Fixed Anthropic-compatible endpoints with strict prompt validation (e.g. Z.AI GLM `api.z.ai/api/anthropic`, which rejects the whole request with `400 code 1213 "The prompt parameter was not received normally"`) failing sessions once a tool returned empty output on a vision-capable model: empty successful `tool_result` blocks now encode as `content: ""` instead of `content: []`, which both the official API and strict compatible endpoints accept.
-- Fixed `retry.usageReservePct` (Reserve Margin) ignoring Claude Fable/Mythos weekly tier usage until it hit 100%, so a Fable model kept serving turns past the configured reserve; reserve health now honors the mapped tier row while credential-wide hard blocks still require confirmed exhaustion ([#8773](https://github.com/can1357/oh-my-pi/issues/8773)).
-- Fixed `cursor-agent` streams stalling with "Provider stream stalled while waiting for the next event" when Cursor asked the client to approve a hosted WebFetch / web search (reproduced on `cursor-grok-4.6-xhigh` after "I'll fetch the page…"). Those `interaction_query` frames — including the newer WebFetch field 9 this proto did not name — were dropped, so the server waited forever and the idle watchdog aborted a live connection. Permission queries are now answered; hosted search/fetch is approved, unnamed permission fields get an `approved` reply on the same field number, and prompts this client cannot serve are rejected so the turn can continue.
-
-### Fixed
-
-- Fixed thinking effort selections being ignored for local Qwen 3.8+ models on llama.cpp and vLLM: the Qwen chat-completions dialects only toggled `enable_thinking`, so the chat template always reasoned at its `xhigh` default no matter which level was selected. The encoder now routes the requested effort onto the template's `reasoning_effort` kwarg (`chat_template_kwargs` for both Qwen dialects, plus the top-level field newer llama.cpp builds map natively).
-- Fixed OpenAI Completions, Amazon Bedrock, and Cursor providers ignoring `onPayload` replacement payloads. The hook now transforms the actual request body sent upstream on these providers, matching the Anthropic/Gemini/OpenAI Responses replacement contract. `devin-agent` still does not fire the hook (its payload is a protobuf object).
-- Fixed Codex requests failing outright when the signed-in ChatGPT account is not entitled to the requested model; the exact model denial is now classified as an account-policy error so credential rotation can reach an entitled sibling account
-- Fixed Perplexity email-OTP login after its verification response renamed the encrypted session token from `token` to `challenge_token`.
-- Cloud Code Assist Gemini 3.6/3.7 Flash requests at `minimal` now send `thinkingLevel: LOW` on the aliased `-low` SKU instead of `MINIMAL`, which the API rejects with HTTP 400.
-- Answer Cursor `interaction_query` permission gates (hosted web search, Exa, unnamed field-9 WebFetch) so the Run RPC continues instead of sitting silent until the 300s idle watchdog.
-- Fixed provider tool calls arriving with flattened array argument paths (e.g. Gemini's `questions[0].id`) being stripped and rejected by argument validation; well-formed flattened paths are now rebuilt into the nested arrays the tool schema expects ([#8886](https://github.com/can1357/oh-my-pi/issues/8886)).
-- Fixed opencode-go (Console Go) rejecting Responses turns with `400 No tool output found for tool call …` (naming a random call of the batch on each retry) when a model streamed a trailing text/thinking block after its tool calls: `buildResponsesInput` emitted that block as an assistant `message` item wedged between the `function_call` batch and its `function_call_output` items. Such interleaved messages are now hoisted ahead of their call batch (canonical `message(s) → calls → outputs`), which the strict gateway validator accepts; content is unchanged ([#8789](https://github.com/can1357/oh-my-pi/issues/8789)).
-- Fixed the OpenAI-wire transport sleeping on a LiteLLM concurrency-admission 429 (`rate_limit_type: max_parallel_requests`, `Retry-After: 60`) and retrying it up to 6 times (~300s) before session recovery saw the error. Because a 60s hint equals the transport's `maxDelayMs` cap, `fetchWithRetry` kept sleeping and retrying; the request now surfaces on the first attempt so `TurnRecovery`'s concurrency backoff/model fallback runs promptly. Genuine RPM/quota 429s (no such marker) still honor `Retry-After` ([#8854](https://github.com/can1357/oh-my-pi/issues/8854)).
-- Fixed OAuth login (Codex `localhost:1455`, and any `localhost` callback flow) failing on hosts with IPv6 disabled at the kernel (`ipv6.disable=1`). The `::1` companion listener added in #8081 fails there with Bun's generic "Is port X in use?" message (oven-sh/bun#7187), which the in-use check misread as a real collision — tearing down the healthy IPv4 listener and surfacing a bogus "port 1455 is in use" error. The dual-bind path now detects the missing IPv6 loopback up front and serves IPv4 alone ([#8814](https://github.com/can1357/oh-my-pi/issues/8814)).

package/README.md

@@ -10,38 +10,38 @@ Unified LLM API with automatic model discovery, provider configuration, token an
 - [Installation](#installation)
 - [Quick Start](#quick-start)
 - [Tools](#tools)
-  - [Defining Tools](#defining-tools)
-  - [Handling Tool Calls](#handling-tool-calls)
-  - [Streaming Tool Calls with Partial JSON](#streaming-tool-calls-with-partial-json)
-  - [Validating Tool Arguments](#validating-tool-arguments)
-  - [Complete Event Reference](#complete-event-reference)
+   - [Defining Tools](#defining-tools)
+   - [Handling Tool Calls](#handling-tool-calls)
+   - [Streaming Tool Calls with Partial JSON](#streaming-tool-calls-with-partial-json)
+   - [Validating Tool Arguments](#validating-tool-arguments)
+   - [Complete Event Reference](#complete-event-reference)
 - [Image Input](#image-input)
 - [Thinking/Reasoning](#thinkingreasoning)
-  - [Unified Interface](#unified-interface-streamsimplecompletesimple)
-  - [Provider-Specific Options](#provider-specific-options-streamcomplete)
-  - [Streaming Thinking Content](#streaming-thinking-content)
+   - [Unified Interface](#unified-interface-streamsimplecompletesimple)
+   - [Provider-Specific Options](#provider-specific-options-streamcomplete)
+   - [Streaming Thinking Content](#streaming-thinking-content)
 - [Stop Reasons](#stop-reasons)
 - [Error Handling](#error-handling)
-  - [Aborting Requests](#aborting-requests)
-  - [Continuing After Abort](#continuing-after-abort)
+   - [Aborting Requests](#aborting-requests)
+   - [Continuing After Abort](#continuing-after-abort)
 - [APIs, Models, and Providers](#apis-models-and-providers)
-  - [Providers and Models](#providers-and-models)
-  - [Querying Providers and Models](#querying-providers-and-models)
-  - [Custom Models](#custom-models)
-  - [OpenAI Compatibility Settings](#openai-compatibility-settings)
-  - [Type Safety](#type-safety)
+   - [Providers and Models](#providers-and-models)
+   - [Querying Providers and Models](#querying-providers-and-models)
+   - [Custom Models](#custom-models)
+   - [OpenAI Compatibility Settings](#openai-compatibility-settings)
+   - [Type Safety](#type-safety)
 - [Cross-Provider Handoffs](#cross-provider-handoffs)
 - [Context Serialization](#context-serialization)
 - [Browser Usage](#browser-usage)
-  - [Environment Variables](#environment-variables-nodejs-only)
-  - [Checking Environment Variables](#checking-environment-variables)
+   - [Environment Variables](#environment-variables-nodejs-only)
+   - [Checking Environment Variables](#checking-environment-variables)
 - [OAuth Providers](#oauth-providers)
-  - [Vertex AI (ADC)](#vertex-ai-adc)
-  - [CLI Login](#cli-login)
-  - [Programmatic OAuth](#programmatic-oauth)
-  - [Login Flow Example](#login-flow-example)
-  - [Using OAuth Tokens](#using-oauth-tokens)
-  - [Provider Notes](#provider-notes)
+   - [Vertex AI (ADC)](#vertex-ai-adc)
+   - [CLI Login](#cli-login)
+   - [Programmatic OAuth](#programmatic-oauth)
+   - [Login Flow Example](#login-flow-example)
+   - [Using OAuth Tokens](#using-oauth-tokens)
+   - [Provider Notes](#provider-notes)
 - [License](#license)
 
 ## Supported Providers
@@ -172,7 +172,7 @@ const finalMessage = await s.result();
 context.messages.push(finalMessage);
 
 // Handle tool calls if any
-const toolCalls = finalMessage.content.filter((b) => b.type === "toolCall");
+const toolCalls = finalMessage.content.filter(b => b.type === "toolCall");
 for (const call of toolCalls) {
 	// Execute the tool
 	const result =
@@ -464,7 +464,7 @@ const response = await completeSimple(
 	},
 	{
 		reasoning: "medium", // 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' (xhigh maps to high on non-OpenAI providers)
-	}
+	},
 );
 
 // Access thinking and text blocks
@@ -583,7 +583,7 @@ const s = stream(
 	},
 	{
 		signal,
-	}
+	},
 );
 
 for await (const event of s) {
@@ -643,7 +643,7 @@ Example:
 const response = await complete(model, context, {
 	apiKey: "sk-live",
 	headers: { "X-Debug-Trace": "true" },
-	onPayload: (payload) => {
+	onPayload: payload => {
 		console.log("request payload", payload);
 	},
 });
@@ -918,7 +918,7 @@ const response = await complete(
 	},
 	{
 		apiKey: "your-api-key",
-	}
+	},
 );
 ```
 
@@ -928,40 +928,40 @@ const response = await complete(
 
 In Node.js environments, you can set environment variables to avoid passing API keys:
 
-| Provider       | Environment Variable(s)                                                      |
-| -------------- | ---------------------------------------------------------------------------- |
-| OpenAI         | `OPENAI_API_KEY`                                                             |
-| Anthropic      | `ANTHROPIC_API_KEY` or `ANTHROPIC_OAUTH_TOKEN` (or `ANTHROPIC_FOUNDRY_API_KEY` when `CLAUDE_CODE_USE_FOUNDRY=true`) |
-| Google         | `GEMINI_API_KEY`                                                             |
-| Vertex AI      | `GOOGLE_CLOUD_PROJECT` (or `GCLOUD_PROJECT`) + `GOOGLE_CLOUD_LOCATION` + ADC |
-| Mistral        | `MISTRAL_API_KEY`                                                            |
-| Groq           | `GROQ_API_KEY`                                                               |
-| Cerebras       | `CEREBRAS_API_KEY`                                                           |
-| Together       | `TOGETHER_API_KEY`                                                           |
-| Qianfan        | `QIANFAN_API_KEY`                                                            |
-| Hugging Face   | `HUGGINGFACE_HUB_TOKEN` or `HF_TOKEN`                                        |
-| Synthetic      | `SYNTHETIC_API_KEY`                                                          |
-| NVIDIA         | `NVIDIA_API_KEY`                                                             |
-| NanoGPT        | `NANO_GPT_API_KEY`                                                          |
-| Novita         | `NOVITA_API_KEY`                                                           |
-| DeepInfra      | `DEEPINFRA_API_KEY`                                                          |
-| Venice         | `VENICE_API_KEY`                                                             |
-| Moonshot       | `MOONSHOT_API_KEY`                                                           |
-| xAI            | `XAI_API_KEY`                                                                |
-| OpenRouter     | `OPENROUTER_API_KEY`                                                         |
-| LiteLLM        | `LITELLM_API_KEY`                                                            |
-| Ollama         | `OLLAMA_API_KEY` (optional for local deployments)                            |
-| Ollama Cloud   | `OLLAMA_CLOUD_API_KEY`                                                     |
-| Qwen Portal    | `QWEN_OAUTH_TOKEN` or `QWEN_PORTAL_API_KEY`                                  |
-| QwenCloud Token Plan | `ALIBABA_TOKEN_PLAN_API_KEY` or `BAILIAN_TOKEN_PLAN_API_KEY`                   |
-| zAI            | `ZAI_API_KEY`                                                                |
-| Umans AI Coding Plan | `UMANS_AI_CODING_PLAN_API_KEY`                                           |
-| MiniMax Code   | `MINIMAX_CODE_API_KEY` (international) or `MINIMAX_CODE_CN_API_KEY` (China) |
-| Xiaomi MiMo    | `XIAOMI_API_KEY`                                                             |
-| ZenMux         | `ZENMUX_API_KEY`                                                             |
-| vLLM           | `VLLM_API_KEY`                                                               |
-| Cloudflare AI Gateway | `CLOUDFLARE_AI_GATEWAY_API_KEY` + `CLOUDFLARE_ACCOUNT_ID` + `CLOUDFLARE_GATEWAY_ID` |
-| GitHub Copilot | `COPILOT_GITHUB_TOKEN` or `GH_TOKEN` or `GITHUB_TOKEN`                      |
+| Provider              | Environment Variable(s)                                                                                             |
+| --------------------- | ------------------------------------------------------------------------------------------------------------------- |
+| OpenAI                | `OPENAI_API_KEY`                                                                                                    |
+| Anthropic             | `ANTHROPIC_API_KEY` or `ANTHROPIC_OAUTH_TOKEN` (or `ANTHROPIC_FOUNDRY_API_KEY` when `CLAUDE_CODE_USE_FOUNDRY=true`) |
+| Google                | `GEMINI_API_KEY`                                                                                                    |
+| Vertex AI             | `GOOGLE_CLOUD_PROJECT` (or `GCLOUD_PROJECT`) + `GOOGLE_CLOUD_LOCATION` + ADC                                        |
+| Mistral               | `MISTRAL_API_KEY`                                                                                                   |
+| Groq                  | `GROQ_API_KEY`                                                                                                      |
+| Cerebras              | `CEREBRAS_API_KEY`                                                                                                  |
+| Together              | `TOGETHER_API_KEY`                                                                                                  |
+| Qianfan               | `QIANFAN_API_KEY`                                                                                                   |
+| Hugging Face          | `HUGGINGFACE_HUB_TOKEN` or `HF_TOKEN`                                                                               |
+| Synthetic             | `SYNTHETIC_API_KEY`                                                                                                 |
+| NVIDIA                | `NVIDIA_API_KEY`                                                                                                    |
+| NanoGPT               | `NANO_GPT_API_KEY`                                                                                                  |
+| Novita                | `NOVITA_API_KEY`                                                                                                    |
+| DeepInfra             | `DEEPINFRA_API_KEY`                                                                                                 |
+| Venice                | `VENICE_API_KEY`                                                                                                    |
+| Moonshot              | `MOONSHOT_API_KEY`                                                                                                  |
+| xAI                   | `XAI_API_KEY`                                                                                                       |
+| OpenRouter            | `OPENROUTER_API_KEY`                                                                                                |
+| LiteLLM               | `LITELLM_API_KEY`                                                                                                   |
+| Ollama                | `OLLAMA_API_KEY` (optional for local deployments)                                                                   |
+| Ollama Cloud          | `OLLAMA_CLOUD_API_KEY`                                                                                              |
+| Qwen Portal           | `QWEN_OAUTH_TOKEN` or `QWEN_PORTAL_API_KEY`                                                                         |
+| QwenCloud Token Plan  | `ALIBABA_TOKEN_PLAN_API_KEY` or `BAILIAN_TOKEN_PLAN_API_KEY`                                                        |
+| zAI                   | `ZAI_API_KEY`                                                                                                       |
+| Umans AI Coding Plan  | `UMANS_AI_CODING_PLAN_API_KEY`                                                                                      |
+| MiniMax Code          | `MINIMAX_CODE_API_KEY` (international) or `MINIMAX_CODE_CN_API_KEY` (China)                                         |
+| Xiaomi MiMo           | `XIAOMI_API_KEY`                                                                                                    |
+| ZenMux                | `ZENMUX_API_KEY`                                                                                                    |
+| vLLM                  | `VLLM_API_KEY`                                                                                                      |
+| Cloudflare AI Gateway | `CLOUDFLARE_AI_GATEWAY_API_KEY` + `CLOUDFLARE_ACCOUNT_ID` + `CLOUDFLARE_GATEWAY_ID`                                 |
+| GitHub Copilot        | `COPILOT_GITHUB_TOKEN` or `GH_TOKEN` or `GITHUB_TOKEN`                                                              |
 
 `/login cloudflare-ai-gateway` collects and stores the gateway token, account ID, and gateway ID. For environment configuration, set all three Cloudflare values above. OMP derives provider endpoints from the account and gateway IDs.
 
@@ -997,7 +997,7 @@ Provider endpoint defaults for the current OpenAI-compatible integrations:
 - LiteLLM: `http://localhost:4000/v1`
 - Cloudflare AI Gateway: native Anthropic, OpenAI, and Workers AI routes under `https://gateway.ai.cloudflare.com/v1/<account>/<gateway>`
 - Qwen Portal: `https://portal.qwen.ai/v1`
-When set, the library automatically uses these keys:
+  When set, the library automatically uses these keys:
 
 ```typescript
 // Uses OPENAI_API_KEY from environment
@@ -1143,10 +1143,10 @@ const credentials = await loginGitHubCopilot({
 		console.log(`Open: ${url}`);
 		if (instructions) console.log(instructions);
 	},
-	onPrompt: async (prompt) => {
+	onPrompt: async prompt => {
 		return await getUserInput(prompt.message);
 	},
-	onProgress: (message) => console.log(message),
+	onProgress: message => console.log(message),
 });
 
 // Store credentials yourself
@@ -1180,7 +1180,7 @@ const response = await complete(
 	{
 		messages: [{ role: "user", content: "Hello!" }],
 	},
-	{ apiKey: result.apiKey }
+	{ apiKey: result.apiKey },
 );
 ```
 

package/package.json

@@ -1,138 +1,133 @@
 {
-	"type": "module",
-	"name": "@linxiraos/pi-ai",
-	"version": "1.1.8",
-	"description": "Unified LLM API with automatic model discovery and provider configuration",
-	"homepage": "https://linxira-os.github.io/zeta/",
-	"author": "Can Boluk",
-	"contributors": [
-		"Mario Zechner"
-	],
-	"license": "MIT",
-	"repository": {
-		"type": "git",
-		"url": "git+https://github.com/Linxira-OS/linxira-zeta.git",
-		"directory": "packages/ai"
-	},
-	"bugs": {
-		"url": "https://github.com/Linxira-OS/linxira-zeta/issues"
-	},
-	"keywords": [
-		"ai",
-		"llm",
-		"openai",
-		"anthropic",
-		"gemini",
-		"unified",
-		"api"
-	],
-	"main": "./src/index.ts",
-	"types": "./dist/types/index.d.ts",
-	"scripts": {
-		"check": "biome check . && bun run check:types",
-		"check:types": "tsgo -p tsconfig.json --noEmit",
-		"lint": "biome lint .",
-		"test": "bun test --parallel",
-		"fix": "biome check --write --unsafe .",
-		"fmt": "biome format --write ."
-	},
-	"dependencies": {
-		"@linxiraos/pi-omptype": "1.1.8",
-		"@linxiraos/pi-catalog": "1.1.8",
-		"@linxiraos/pi-utils": "1.1.8",
-		"@linxiraos/pi-wire": "1.1.8"
-	},
-	"devDependencies": {
-		"@types/bun": "^1.3.14"
-	},
-	"engines": {
-		"bun": ">=1.3.14"
-	},
-	"files": [
-		"src",
-		"README.md",
-		"CHANGELOG.md",
-		"LICENSE",
-		"THIRD-PARTY-NOTICES.txt",
-		"dist/types"
-	],
-	"exports": {
-		".": {
-			"types": "./dist/types/index.d.ts",
-			"import": "./src/index.ts"
-		},
-		"./error": {
-			"types": "./dist/types/error/index.d.ts",
-			"import": "./src/error/index.ts"
-		},
-		"./*": {
-			"types": "./dist/types/*.d.ts",
-			"import": "./src/*.ts"
-		},
-		"./auth-broker": {
-			"types": "./dist/types/auth-broker/index.d.ts",
-			"import": "./src/auth-broker/index.ts"
-		},
-		"./auth-broker/*": {
-			"types": "./dist/types/auth-broker/*.d.ts",
-			"import": "./src/auth-broker/*.ts"
-		},
-		"./auth-gateway": {
-			"types": "./dist/types/auth-gateway/index.d.ts",
-			"import": "./src/auth-gateway/index.ts"
-		},
-		"./auth-gateway/*": {
-			"types": "./dist/types/auth-gateway/*.d.ts",
-			"import": "./src/auth-gateway/*.ts"
-		},
-		"./providers/*": {
-			"types": "./dist/types/providers/*.d.ts",
-			"import": "./src/providers/*.ts"
-		},
-		"./providers/openai-codex/*": {
-			"types": "./dist/types/providers/openai-codex/*.d.ts",
-			"import": "./src/providers/openai-codex/*.ts"
-		},
-		"./usage/*": {
-			"types": "./dist/types/usage/*.d.ts",
-			"import": "./src/usage/*.ts"
-		},
-		"./utils/harmony-leak": {
-			"types": "./dist/types/utils/harmony-leak.d.ts",
-			"import": "./src/utils/harmony-leak.ts"
-		},
-		"./dialect": {
-			"types": "./dist/types/dialect/index.d.ts",
-			"import": "./src/dialect/index.ts"
-		},
-		"./utils/*": {
-			"types": "./dist/types/utils/*.d.ts",
-			"import": "./src/utils/*.ts"
-		},
-		"./oauth": {
-			"types": "./dist/types/registry/oauth/index.d.ts",
-			"import": "./src/registry/oauth/index.ts"
-		},
-		"./oauth/*": {
-			"types": "./dist/types/registry/oauth/*.d.ts",
-			"import": "./src/registry/oauth/*.ts"
-		},
-		"./registry": {
-			"types": "./dist/types/registry/index.d.ts",
-			"import": "./src/registry/index.ts"
-		},
-		"./registry/oauth": {
-			"types": "./dist/types/registry/oauth/index.d.ts",
-			"import": "./src/registry/oauth/index.ts"
-		},
-		"./utils/schema": {
-			"types": "./dist/types/utils/schema/index.d.ts",
-			"import": "./src/utils/schema/index.ts"
-		},
-		"./utils/schema/*": {
-			"types": "./dist/types/utils/schema/*.d.ts",
-			"import": "./src/utils/schema/*.ts"
-		},
-		"./*.js": "./src/*.ts"
-	}
+  "engines": {
+    "bun": ">=1.3.14"
+  },
+  "devDependencies": {
+    "@types/bun": "^1.3.14"
+  },
+  "dependencies": {
+    "@linxiraos/pi-wire": "1.1.9",
+    "@linxiraos/pi-utils": "1.1.9",
+    "@linxiraos/pi-catalog": "1.1.9",
+    "@linxiraos/pi-omptype": "1.1.9",
+    "@linxiraos/pi-natives": "1.1.9"
+  },
+  "scripts": {
+    "test": "bun test --parallel",
+    "check:types": "tsgo -p tsconfig.json --noEmit",
+    "check": "tsgo -p tsconfig.json --noEmit"
+  },
+  "exports": {
+    "./*.js": "./src/*.ts",
+    "./utils/schema/*": {
+      "import": "./src/utils/schema/*.ts",
+      "types": "./src/utils/schema/*.ts"
+    },
+    "./utils/schema": {
+      "import": "./src/utils/schema/index.ts",
+      "types": "./src/utils/schema/index.ts"
+    },
+    "./registry/oauth": {
+      "import": "./src/registry/oauth/index.ts",
+      "types": "./src/registry/oauth/index.ts"
+    },
+    "./registry": {
+      "import": "./src/registry/index.ts",
+      "types": "./src/registry/index.ts"
+    },
+    "./oauth/*": {
+      "import": "./src/registry/oauth/*.ts",
+      "types": "./src/registry/oauth/*.ts"
+    },
+    "./oauth": {
+      "import": "./src/registry/oauth/index.ts",
+      "types": "./src/registry/oauth/index.ts"
+    },
+    "./utils/*": {
+      "import": "./src/utils/*.ts",
+      "types": "./src/utils/*.ts"
+    },
+    "./dialect": {
+      "import": "./src/dialect/index.ts",
+      "types": "./src/dialect/index.ts"
+    },
+    "./utils/harmony-leak": {
+      "import": "./src/utils/harmony-leak.ts",
+      "types": "./src/utils/harmony-leak.ts"
+    },
+    "./usage/*": {
+      "import": "./src/usage/*.ts",
+      "types": "./src/usage/*.ts"
+    },
+    "./providers/openai-codex/*": {
+      "import": "./src/providers/openai-codex/*.ts",
+      "types": "./src/providers/openai-codex/*.ts"
+    },
+    "./providers/*": {
+      "import": "./src/providers/*.ts",
+      "types": "./src/providers/*.ts"
+    },
+    "./auth-gateway/*": {
+      "import": "./src/auth-gateway/*.ts",
+      "types": "./src/auth-gateway/*.ts"
+    },
+    "./auth-gateway": {
+      "import": "./src/auth-gateway/index.ts",
+      "types": "./src/auth-gateway/index.ts"
+    },
+    "./auth-broker/*": {
+      "import": "./src/auth-broker/*.ts",
+      "types": "./src/auth-broker/*.ts"
+    },
+    "./auth-broker": {
+      "import": "./src/auth-broker/index.ts",
+      "types": "./src/auth-broker/index.ts"
+    },
+    "./*": {
+      "import": "./src/*.ts",
+      "types": "./src/*.ts"
+    },
+    "./error": {
+      "import": "./src/error/index.ts",
+      "types": "./src/error/index.ts"
+    },
+    ".": {
+      "import": "./src/index.ts",
+      "types": "./src/index.ts"
+    }
+  },
+  "types": "./src/index.ts",
+  "main": "./src/index.ts",
+  "type": "module",
+  "files": [
+    "src",
+    "README.md",
+    "CHANGELOG.md"
+  ],
+  "repository": {
+    "directory": "packages/ai",
+    "url": "git+https://github.com/Linxira-OS/linxira-zeta.git",
+    "type": "git"
+  },
+  "contributors": [
+    "Mario Zechner"
+  ],
+  "author": "Can Boluk",
+  "license": "MIT",
+  "bugs": {
+    "url": "https://github.com/Linxira-OS/linxira-zeta/issues"
+  },
+  "homepage": "https://linxira-os.github.io/zeta/",
+  "keywords": [
+    "ai",
+    "llm",
+    "openai",
+    "anthropic",
+    "gemini",
+    "unified",
+    "api"
+  ],
+  "description": "Unified LLM API with automatic model discovery and provider configuration",
+  "version": "1.1.9",
+  "name": "@linxiraos/pi-ai"
 }

package/src/auth-storage.ts

@@ -9,7 +9,7 @@
  */
 import { createHash } from "node:crypto";
 import { planRequirementFor } from "@linxiraos/pi-catalog/compat/behavior";
-import { $env, $envExact, extractRetryHint, getAgentDbPath, logger } from "@linxiraos/pi-utils";
+import { $env, $envExact, extractRetryHint, getAgentDbPath, logger, untilAborted } from "@linxiraos/pi-utils";
 import {
 	isSqliteCorruptionError,
 	resolveCredentialIdentityKey,
@@ -622,7 +622,7 @@ export type AuthStorageOptions = {
 	 * so the TUI can show where a token came from (broker URL or local SQLite path).
 	 *
 	 * Examples:
-	 * - `"local ~/.omp/agent/agent.db"`
+	 * - `"local ~/.zeta/agent/agent.db"`
 	 * - `"broker http://omp.internal:8765"`
 	 */
 	sourceLabel?: string;
@@ -3025,17 +3025,18 @@ export class AuthStorage {
 	): Promise<OAuthLoginIdentity | undefined> {
 		// Only paste-code providers (fixed non-loopback redirect, e.g. GitLab Duo
 		// Agent's vscode:// URI) get a default manual-code prompt. For loopback OAuth
-		// providers the `OAuthCallbackFlow` would otherwise race this readline prompt
-		// against the HTTP callback and, when the callback wins, leave the prompt
-		// outstanding — a dirty/blocked terminal. Synthesizing the default only for
-		// paste-code providers is the authoritative gate (it covers every caller, not
+		// providers an eager paste prompt adds noise to a flow that normally completes
+		// through HTTP. Synthesizing the default only for paste-code providers is the
+		// authoritative gate (it covers every caller, not
 		// just the CLI); an explicit caller-supplied `onManualCodeInput` is still
 		// honored for any provider as an escape hatch.
 		const manualCodeInput = PASTE_CODE_LOGIN_PROVIDERS.has(provider)
-			? () =>
-					ctrl.onPrompt({
-						message: "Paste the authorization code (or full redirect URL):",
-					})
+			? (signal?: AbortSignal) =>
+					untilAborted(signal, () =>
+						ctrl.onPrompt({
+							message: "Paste the authorization code (or full redirect URL):",
+						}),
+					)
 			: undefined;
 		// Built-in registry first, then runtime-registered extension providers.
 		const def = getProviderDefinition(provider) ?? getOAuthProvider(provider);

package/src/error/rate-limit.ts

@@ -24,6 +24,12 @@ const SERVER_ERROR_BACKOFF_MS = 20 * 1000; // 20s
 const ACCOUNT_RATE_LIMIT_PATTERN =
 	/\baccount(?:'s)?\b[^\n]{0,80}\brate.?limit\b|\brate.?limit\b[^\n]{0,80}\baccount\b/i;
 const INSUFFICIENT_BALANCE_PATTERN = /insufficient.?balance/i;
+// Prepaid-credit exhaustion phrased around the credit balance rather than a
+// quota: Anthropic "This request would exceed your available credits given
+// your current in-flight requests" (402), OpenRouter "Insufficient credits",
+// "credits exhausted". Account-local, so rotate to a sibling credential.
+const CREDITS_EXHAUSTED_PATTERN =
+	/\b(?:exceed\w*|insufficient|not enough)\b[^\n]{0,40}\bcredits?\b|\bcredits?\b[^\n]{0,40}\b(?:exhausted|depleted)\b/i;
 const SPEND_LIMIT_PATTERN = /spend.?limit/i;
 const SUBSCRIPTION_CAP_PATTERN =
 	/\b(?:subscription|plan|membership)\b[^\n]{0,80}\b(?:rate.?limits?|quota|cap)\b|\b(?:rate.?limits?|quota|cap)\b[^\n]{0,80}\b(?:subscription|plan|membership)\b/i;
@@ -247,7 +253,8 @@ export function parseRateLimitReason(errorMessage: string): RateLimitReason {
 		lower.includes("out of credits") ||
 		lower.includes("spending-limit") ||
 		lower.includes("spending limit") ||
-		INSUFFICIENT_BALANCE_PATTERN.test(errorMessage)
+		INSUFFICIENT_BALANCE_PATTERN.test(errorMessage) ||
+		CREDITS_EXHAUSTED_PATTERN.test(errorMessage)
 	) {
 		return "QUOTA_EXHAUSTED";
 	}
@@ -390,6 +397,7 @@ export function matchesUsageLimitText(errorMessage: string): boolean {
 	if (isDashScopeTokenLimitText(errorMessage)) return false;
 	return (
 		USAGE_LIMIT_PATTERN.test(errorMessage) ||
+		CREDITS_EXHAUSTED_PATTERN.test(errorMessage) ||
 		(CN_QUOTA_EXHAUSTED_PATTERN.test(errorMessage) && !CN_TRANSIENT_CAP_PATTERN.test(errorMessage)) ||
 		SPEND_LIMIT_PATTERN.test(errorMessage) ||
 		ACCOUNT_RATE_LIMIT_PATTERN.test(errorMessage) ||