@ai-ecoverse/slicc-agent 6.18.4 → 6.18.5

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/README.md +1 -1
  2. package/dist/providers.js +1 -1
  3. package/dist/providers.js.map +1 -1
  4. package/package.json +3 -3
package/README.md CHANGED
@@ -138,7 +138,7 @@ const owner = await startAgent({
138
138
 
139
139
  `runAgentWorker(self, options)` is the same with its parts replaceable (model, providers, kernel attach, the account store, storage).
140
140
 
141
- **Providers.** `sliccProviders()` registers Bedrock, Adobe and every pi-ai provider that takes a plain API key: Anthropic, OpenAI, Mistral, Groq, DeepSeek, Together, Hugging Face, Xiaomi and its three token plans, Cerebras, OpenRouter, Fireworks, Baseten, Moonshot AI and its China platform, xAI, Meta, Vercel AI Gateway, MiniMax and MiniMax CN, Z.AI and Z.AI Coding CN, NVIDIA, Kimi For Coding, Ant Ling, OpenCode Zen and Go, and the three Qwen token plans (`KEY_PROVIDERS` in `src/providers.ts`, each with its id, pi-ai factory, pi-ai env name, a description, a key URL and whether it answers browsers). Three more take a key and non-secret fields (`auth: 'fields'`), each checked in `connect` and mapped to pi-ai's env: Azure (`endpoint`, required: a resource name becomes `AZURE_OPENAI_RESOURCE_NAME`, an `https:` URL without a port or user name `AZURE_OPENAI_BASE_URL`; `deployments`, optional `model=deployment` pairs, `AZURE_OPENAI_DEPLOYMENT_NAME_MAP`), Cloudflare Workers AI (`account`, 32 hex characters, `CLOUDFLARE_ACCOUNT_ID`) and Cloudflare AI Gateway (`account` and `gateway`, `CLOUDFLARE_GATEWAY_ID`). Bedrock's `region` is on the same mechanism. A bad value rejects `connect` with a sentence, a required field left out keeps its stored value or rejects with “{label} can’t be empty.”, and a stored value that no longer passes is left out of the env. A fields provider whose required fields are missing or no longer pass shows as not connected, gives pi-ai no credential and offers no models, even with its key already in the vault (spectrum puts the key before `connect` checks the fields). Bedrock's region is any AWS region name (`eusc-de-east-1` and `us-gov-west-1` included), and stored values are trimmed. OpenCode Zen and OpenCode Go need seven's vault 1.12.2 or later, whose built-in table has their `/inference` endpoints; their descriptions say so. Azure's `endpoint` field says `customBase: true`: when its value is a full URL, spectrum registers it with the vault (the page's `endpoints`) before `connect`, since the agent never registers model endpoints for pi-ai providers; a resource name needs nothing, as `*.openai.azure.com` is built into the vault. The worker routes requests to an Azure account's base URL as Azure's. Google and Google Vertex wait for slicc-bios to stop removing `@google/genai`; the sign-ins come later. A provider's preferred model is pi-coding-agent 1.3.0's `defaultModelPerProvider` (Bedrock keeps `us.anthropic.claude-sonnet-5-5`), and the first model when that one is missing. Providers that don't answer a browser from `https://seven.sliccy.ai` with the headers pi-ai and the AWS SDK send say `needs: 'cors-free-transport'`; the direct ones are Bedrock, Adobe, Anthropic, OpenAI, Azure, Mistral, Groq, DeepSeek, Together, Hugging Face, Baseten, both Moonshot AI platforms, xAI, Meta and the four Xiaomi providers. Chrome accepts `Authorization` under a bare `Access-Control-Allow-Headers: *` (as xAI, Meta and Adobe's proxy answer), checked in Chrome 156. The worker's transport fetch drops the Stainless SDKs' `x-stainless-*` telemetry headers from every request it sends, which is what Baseten's and Moonshot AI's preflights refuse.
141
+ **Providers.** `sliccProviders()` registers Bedrock, Adobe and every pi-ai provider that takes a plain API key: Anthropic, OpenAI, Mistral, Groq, DeepSeek, Together, Hugging Face, Xiaomi and its three token plans, Cerebras, OpenRouter, Fireworks, Baseten, Moonshot AI and its China platform, xAI, Meta, Vercel AI Gateway, MiniMax and MiniMax CN, Z.AI and Z.AI Coding CN, NVIDIA, Kimi For Coding, Ant Ling, OpenCode Zen and Go, and the three Qwen token plans (`KEY_PROVIDERS` in `src/providers.ts`, each with its id, pi-ai factory, pi-ai env name, a description, a key URL and whether it answers browsers). Three more take a key and non-secret fields (`auth: 'fields'`), each checked in `connect` and mapped to pi-ai's env: Azure (`endpoint`, required: a resource name becomes `AZURE_OPENAI_RESOURCE_NAME`, an `https:` URL without a port or user name `AZURE_OPENAI_BASE_URL`; `deployments`, optional `model=deployment` pairs, `AZURE_OPENAI_DEPLOYMENT_NAME_MAP`), Cloudflare Workers AI (`account`, 32 hex characters, `CLOUDFLARE_ACCOUNT_ID`) and Cloudflare AI Gateway (`account` and `gateway`, `CLOUDFLARE_GATEWAY_ID`). Bedrock's `region` is on the same mechanism. A bad value rejects `connect` with a sentence, a required field left out keeps its stored value or rejects with “{label} can’t be empty.”, and a stored value that no longer passes is left out of the env. A fields provider whose required fields are missing or no longer pass shows as not connected, gives pi-ai no credential and offers no models, even with its key already in the vault (spectrum puts the key before `connect` checks the fields). Bedrock's region is any AWS region name (`eusc-de-east-1` and `us-gov-west-1` included), and stored values are trimmed. OpenCode Zen and OpenCode Go need seven's vault 1.12.2 or later, whose built-in table has their `/inference` endpoints; their descriptions say so. Azure's `endpoint` field says `customBase: true`: when its value is a full URL, spectrum registers it with the vault (the page's `endpoints`) before `connect`, since the agent never registers model endpoints for pi-ai providers; a resource name needs nothing, as `*.openai.azure.com` is built into the vault. The worker routes requests to an Azure account's base URL as Azure's. Google and Google Vertex wait for slicc-bios to stop removing `@google/genai`; the sign-ins come later. A provider's preferred model is pi-coding-agent 1.3.0's `defaultModelPerProvider` (Bedrock keeps `us.anthropic.claude-sonnet-5-5`), and the first model when that one is missing. Providers that don't answer a browser from `https://seven.sliccy.ai` with the headers pi-ai and the AWS SDK send say `needs: 'cors-free-transport'`; the direct ones are Bedrock, Adobe, Anthropic, OpenAI, Azure, Mistral, Groq, DeepSeek, Together, Hugging Face, Baseten, both Moonshot AI platforms, xAI, Meta, Z.AI Coding CN and the four Xiaomi providers. Chrome accepts `Authorization` under a bare `Access-Control-Allow-Headers: *` (as xAI, Meta and Adobe's proxy answer), checked in Chrome 156. The worker's transport fetch drops the Stainless SDKs' `x-stainless-*` telemetry headers from every request it sends, which is what Baseten's and Moonshot AI's preflights refuse.
142
142
 
143
143
  **Reachability, nightly.** `npm run reach` (`scripts/reach.mjs`, through `verdict.mjs`) checks every listing from `https://seven.sliccy.ai`. It captures the request pi-ai builds for each of the provider's APIs (with a dummy key and dummy fields, and the fetch faked; Bedrock's from the AWS SDK's own request, caught at its Node HTTP handler, which carries the same headers as in a browser: `amz-sdk-invocation-id`, `amz-sdk-request`, `authorization`, `content-type`, `x-amz-user-agent`). Then it sends that request's preflight and, when the preflight passes, the request itself with dummy credentials, whose answer must carry `Access-Control-Allow-Origin` too. Besides each chat API it probes what the provider's models need beyond a turn: the requests its model discovery sends under its base URL (Adobe's `/v1/config`), one classifier call per classifier API (Adobe's `/v1/ai/run`, OpenAI's `/v1/decisions`, OpenRouter's and Cloudflare's), and Adobe's `/v1/usage`. It prints `reach: <id> direct|cors-free|unknown|unprobed` per provider (`unknown` when the network gave no answer; `unprobed` when it captured no request at all, which counts as a disagreement, so a provider can't silently drop out of the check) and one `reach: PASS` line. A provider that stays `unknown` three runs in a row counts as a disagreement too: the workflow keeps the streaks in the Actions cache (`REACH_HISTORY`), and the line says how many runs in a row. A direct provider that passes only because Chrome lets `Authorization` through under a bare `Access-Control-Allow-Headers: *` reads `direct (wildcard auth)` (today Adobe, xAI and Meta); the PASS line, the run's summary and the issue body list them, without failing, so we know at once which break if Chrome ever enforces the Fetch spec. `.github/workflows/reach.yml` runs it every night on `ubuntu-latest`, never on pull requests, and opens or updates the issue titled “Provider reachability disagrees with the listings” when a provider's verdict isn't its `needs`, and closes it with a comment once every provider's verdict matches its listing again (a run with an `unknown` provider leaves it open); a run without the PASS line fails.
144
144
 
package/dist/providers.js CHANGED
@@ -355,7 +355,7 @@ const KEY_PROVIDERS = [
355
355
  env: "ZAI_CODING_CN_API_KEY",
356
356
  description: "GLM models on Zhipu\u2019s coding plan in China.",
357
357
  keyUrl: "https://open.bigmodel.cn/usercenter/apikeys",
358
- cors: false
358
+ cors: true
359
359
  },
360
360
  {
361
361
  id: "nvidia",
package/dist/providers.js.map CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "version": 3,
3
3
  "sources": ["../src/providers.ts"],
4
- "sourcesContent": ["import type { Provider } from '@earendil-works/pi-ai';\nimport { antLingProvider } from '@earendil-works/pi-ai/providers/ant-ling';\nimport { anthropicProvider } from '@earendil-works/pi-ai/providers/anthropic';\nimport { azureProvider } from '@earendil-works/pi-ai/providers/azure';\nimport { basetenProvider } from '@earendil-works/pi-ai/providers/baseten';\nimport { cerebrasProvider } from '@earendil-works/pi-ai/providers/cerebras';\nimport { cloudflareAIGatewayProvider } from '@earendil-works/pi-ai/providers/cloudflare-ai-gateway';\nimport { cloudflareWorkersAIProvider } from '@earendil-works/pi-ai/providers/cloudflare-workers-ai';\nimport { deepseekProvider } from '@earendil-works/pi-ai/providers/deepseek';\nimport { fireworksProvider } from '@earendil-works/pi-ai/providers/fireworks';\nimport { groqProvider } from '@earendil-works/pi-ai/providers/groq';\nimport { huggingfaceProvider } from '@earendil-works/pi-ai/providers/huggingface';\nimport { kimiCodingProvider } from '@earendil-works/pi-ai/providers/kimi-coding';\nimport { metaProvider } from '@earendil-works/pi-ai/providers/meta';\nimport { minimaxProvider } from '@earendil-works/pi-ai/providers/minimax';\nimport { minimaxCnProvider } from '@earendil-works/pi-ai/providers/minimax-cn';\nimport { mistralProvider } from '@earendil-works/pi-ai/providers/mistral';\nimport { moonshotaiProvider } from '@earendil-works/pi-ai/providers/moonshotai';\nimport { moonshotaiCnProvider } from '@earendil-works/pi-ai/providers/moonshotai-cn';\nimport { nvidiaProvider } from '@earendil-works/pi-ai/providers/nvidia';\nimport { openaiProvider } from '@earendil-works/pi-ai/providers/openai';\nimport { opencodeProvider } from '@earendil-works/pi-ai/providers/opencode';\nimport { opencodeGoProvider } from '@earendil-works/pi-ai/providers/opencode-go';\nimport { openrouterProvider } from '@earendil-works/pi-ai/providers/openrouter';\nimport { qwenTokenPlanProvider } from '@earendil-works/pi-ai/providers/qwen-token-plan';\nimport { qwenTokenPlanCnProvider } from '@earendil-works/pi-ai/providers/qwen-token-plan-cn';\nimport { qwenTokenPlanIndividualProvider } from '@earendil-works/pi-ai/providers/qwen-token-plan-individual';\nimport { togetherProvider } from '@earendil-works/pi-ai/providers/together';\nimport { vercelAIGatewayProvider } from '@earendil-works/pi-ai/providers/vercel-ai-gateway';\nimport { xaiProvider } from '@earendil-works/pi-ai/providers/xai';\nimport { xiaomiProvider } from '@earendil-works/pi-ai/providers/xiaomi';\nimport { xiaomiTokenPlanAmsProvider } from '@earendil-works/pi-ai/providers/xiaomi-token-plan-ams';\nimport { xiaomiTokenPlanCnProvider } from '@earendil-works/pi-ai/providers/xiaomi-token-plan-cn';\nimport { xiaomiTokenPlanSgpProvider } from '@earendil-works/pi-ai/providers/xiaomi-token-plan-sgp';\nimport { zaiProvider } from '@earendil-works/pi-ai/providers/zai';\nimport { zaiCodingCnProvider } from '@earendil-works/pi-ai/providers/zai-coding-cn';\nimport { CODEX } from './sign-ins.ts';\n\nexport interface FieldOption {\n value: string;\n label: string;\n}\n\nexport interface FieldInput {\n name: string;\n label: string;\n required?: boolean;\n placeholder?: string;\n help?: string;\n customBase?: true;\n vaultSetting?: string;\n options?: readonly FieldOption[];\n value?: string;\n}\n\nexport interface FieldSpec extends FieldInput {\n env(value: string): Record<string, string> | string;\n}\n\nexport interface KeyProvider {\n id: string;\n make: () => Provider;\n env: string;\n description: string;\n keyUrl: string;\n cors: boolean;\n signIn?: true;\n fields?: readonly FieldSpec[];\n}\n\nconst RESOURCE = /^[a-z0-9][a-z0-9-]{0,62}$/i;\nconst DEPLOYMENTS = /^[^=,\\s]+\\s*=\\s*[^=,\\s]+(\\s*,\\s*[^=,\\s]+\\s*=\\s*[^=,\\s]+)*$/;\n\nexport function httpsBase(value: string): URL | undefined {\n const url = URL.parse(value);\n if (url?.protocol !== 'https:' || url.username || url.password) return undefined;\n return url.port === '' || url.port === '443' ? url : undefined;\n}\n\nfunction azureEndpoint(value: string): Record<string, string> | string {\n if (RESOURCE.test(value)) return { AZURE_OPENAI_RESOURCE_NAME: value };\n const url = httpsBase(value);\n if (!url)\n return 'Enter your Azure resource name, or its endpoint as an https:// address without a port or a user name.';\n return { AZURE_OPENAI_BASE_URL: url.href.replace(/\\/+$/, '') };\n}\n\nexport const AZURE = 'azure';\n\nexport function azureBase(env: Readonly<Record<string, string>>): string | undefined {\n if (env.AZURE_OPENAI_BASE_URL) return env.AZURE_OPENAI_BASE_URL;\n const name = env.AZURE_OPENAI_RESOURCE_NAME;\n return name ? `https://${name}.openai.azure.com/openai/v1` : undefined;\n}\n\nconst REGION = /^[a-z]{2,}(-[a-z]+)+-\\d{1,2}$/;\nconst ACCOUNT = /^[0-9a-f]{32}$/i;\nconst GATEWAY = /^[A-Za-z0-9_-]{1,64}$/;\n\nconst checked =\n (pattern: RegExp, env: string, problem: string) =>\n (value: string): Record<string, string> | string =>\n pattern.test(value) ? { [env]: value } : problem;\n\nconst BEDROCK_REGIONS: readonly (readonly [string, string])[] = [\n ['ap-northeast-1', 'Asia Pacific (Tokyo)'],\n ['ap-northeast-2', 'Asia Pacific (Seoul)'],\n ['ap-northeast-3', 'Asia Pacific (Osaka)'],\n ['ap-south-1', 'Asia Pacific (Mumbai)'],\n ['ap-south-2', 'Asia Pacific (Hyderabad)'],\n ['ap-southeast-1', 'Asia Pacific (Singapore)'],\n ['ap-southeast-2', 'Asia Pacific (Sydney)'],\n ['ca-central-1', 'Canada (Central)'],\n ['eu-central-1', 'Europe (Frankfurt)'],\n ['eu-central-2', 'Europe (Zurich)'],\n ['eu-north-1', 'Europe (Stockholm)'],\n ['eu-south-1', 'Europe (Milan)'],\n ['eu-south-2', 'Europe (Spain)'],\n ['eu-west-1', 'Europe (Ireland)'],\n ['eu-west-2', 'Europe (London)'],\n ['eu-west-3', 'Europe (Paris)'],\n ['sa-east-1', 'South America (S\u00E3o Paulo)'],\n ['us-east-1', 'US East (N. Virginia)'],\n ['us-gov-east-1', 'AWS GovCloud (US-East)'],\n ['us-gov-west-1', 'AWS GovCloud (US-West)'],\n ['us-west-2', 'US West (Oregon)'],\n];\n\nexport const DEFAULT_REGION = 'us-west-2';\n\nexport const REGION_FIELD: FieldSpec = {\n name: 'region',\n label: 'Region',\n help: 'The AWS region your Bedrock models run in.',\n options: BEDROCK_REGIONS.map(([value, label]) => ({ value, label: `${label}, ${value}` })),\n value: DEFAULT_REGION,\n env: checked(REGION, 'AWS_REGION', 'Enter an AWS region such as us-west-2.'),\n};\n\nconst ACCOUNT_FIELD: FieldSpec = {\n name: 'account',\n label: 'Account ID',\n required: true,\n placeholder: '0123456789abcdef0123456789abcdef',\n help: 'The 32-character ID on your Cloudflare dashboard\u2019s account overview.',\n vaultSetting: 'CLOUDFLARE_ACCOUNT_ID',\n env: checked(\n ACCOUNT,\n 'CLOUDFLARE_ACCOUNT_ID',\n 'A Cloudflare account ID is 32 characters of 0\u20139 and a\u2013f.'\n ),\n};\n\nexport const KEY_PROVIDERS: readonly KeyProvider[] = [\n {\n id: 'azure',\n make: azureProvider,\n env: 'AZURE_OPENAI_API_KEY',\n description: 'OpenAI models deployed in your own Azure OpenAI or AI Foundry resource.',\n keyUrl: 'https://portal.azure.com',\n cors: true,\n fields: [\n {\n name: 'endpoint',\n label: 'Endpoint',\n required: true,\n placeholder: 'my-resource or https://my-resource.openai.azure.com',\n help: 'Your resource\u2019s name, or its endpoint address from Keys and Endpoint.',\n customBase: true,\n vaultSetting: 'AZURE_OPENAI_RESOURCE_NAME',\n env: azureEndpoint,\n },\n {\n name: 'deployments',\n label: 'Deployments',\n placeholder: 'gpt-5.4=my-gpt',\n help: 'Only for deployments named differently from their model, as model=deployment, separated by commas.',\n env: (value) =>\n DEPLOYMENTS.test(value)\n ? { AZURE_OPENAI_DEPLOYMENT_NAME_MAP: value }\n : 'Write each deployment as model=deployment, separated by commas.',\n },\n ],\n },\n {\n id: 'cloudflare-workers-ai',\n make: cloudflareWorkersAIProvider,\n env: 'CLOUDFLARE_API_KEY',\n description: 'Open models on Cloudflare Workers AI, in your Cloudflare account.',\n keyUrl: 'https://dash.cloudflare.com/profile/api-tokens',\n cors: false,\n fields: [ACCOUNT_FIELD],\n },\n {\n id: 'cloudflare-ai-gateway',\n make: cloudflareAIGatewayProvider,\n env: 'CLOUDFLARE_API_KEY',\n description: 'Models from many labs through your Cloudflare AI Gateway.',\n keyUrl: 'https://dash.cloudflare.com/profile/api-tokens',\n cors: false,\n fields: [\n ACCOUNT_FIELD,\n {\n name: 'gateway',\n label: 'Gateway ID',\n required: true,\n placeholder: 'my-gateway',\n help: 'The name of your gateway under AI \u203A AI Gateway.',\n vaultSetting: 'CLOUDFLARE_GATEWAY_ID',\n env: checked(\n GATEWAY,\n 'CLOUDFLARE_GATEWAY_ID',\n 'A gateway ID is letters, digits, - and _, up to 64 characters.'\n ),\n },\n ],\n },\n {\n id: 'anthropic',\n make: anthropicProvider,\n env: 'ANTHROPIC_API_KEY',\n description: 'Claude models, with an API key from the Claude Console.',\n keyUrl: 'https://console.anthropic.com/settings/keys',\n cors: true,\n },\n {\n id: 'openai',\n make: openaiProvider,\n env: 'OPENAI_API_KEY',\n description: 'GPT models, with an API key from the OpenAI platform.',\n keyUrl: 'https://platform.openai.com/api-keys',\n cors: true,\n },\n {\n id: 'mistral',\n make: mistralProvider,\n env: 'MISTRAL_API_KEY',\n description: 'Mistral and Devstral models from La Plateforme.',\n keyUrl: 'https://console.mistral.ai/api-keys',\n cors: true,\n },\n {\n id: 'groq',\n make: groqProvider,\n env: 'GROQ_API_KEY',\n description: 'Open models on Groq\u2019s fast inference.',\n keyUrl: 'https://console.groq.com/keys',\n cors: true,\n },\n {\n id: 'deepseek',\n make: deepseekProvider,\n env: 'DEEPSEEK_API_KEY',\n description: 'DeepSeek\u2019s own models.',\n keyUrl: 'https://platform.deepseek.com/api_keys',\n cors: true,\n },\n {\n id: 'together',\n make: togetherProvider,\n env: 'TOGETHER_API_KEY',\n description: 'Open models hosted by Together AI.',\n keyUrl: 'https://api.together.ai/settings/api-keys',\n cors: true,\n },\n {\n id: 'huggingface',\n make: huggingfaceProvider,\n env: 'HF_TOKEN',\n description: 'Open models through Hugging Face\u2019s inference router.',\n keyUrl: 'https://huggingface.co/settings/tokens',\n cors: true,\n },\n {\n id: 'xiaomi',\n make: xiaomiProvider,\n env: 'XIAOMI_API_KEY',\n description: 'Xiaomi\u2019s MiMo models.',\n keyUrl: 'https://platform.xiaomimimo.com/#/console/api-keys',\n cors: true,\n },\n {\n id: 'xiaomi-token-plan-ams',\n make: xiaomiTokenPlanAmsProvider,\n env: 'XIAOMI_TOKEN_PLAN_AMS_API_KEY',\n description: 'MiMo models on a Xiaomi token plan, served from Amsterdam.',\n keyUrl: 'https://platform.xiaomimimo.com/#/console/api-keys',\n cors: true,\n },\n {\n id: 'xiaomi-token-plan-cn',\n make: xiaomiTokenPlanCnProvider,\n env: 'XIAOMI_TOKEN_PLAN_CN_API_KEY',\n description: 'MiMo models on a Xiaomi token plan, served from China.',\n keyUrl: 'https://platform.xiaomimimo.com/#/console/api-keys',\n cors: true,\n },\n {\n id: 'xiaomi-token-plan-sgp',\n make: xiaomiTokenPlanSgpProvider,\n env: 'XIAOMI_TOKEN_PLAN_SGP_API_KEY',\n description: 'MiMo models on a Xiaomi token plan, served from Singapore.',\n keyUrl: 'https://platform.xiaomimimo.com/#/console/api-keys',\n cors: true,\n },\n {\n id: 'cerebras',\n make: cerebrasProvider,\n env: 'CEREBRAS_API_KEY',\n description: 'Open models on Cerebras inference.',\n keyUrl: 'https://cloud.cerebras.ai',\n cors: false,\n },\n {\n id: 'openrouter',\n make: openrouterProvider,\n env: 'OPENROUTER_API_KEY',\n description: 'Hundreds of models from many labs through one key.',\n keyUrl: 'https://openrouter.ai/settings/keys',\n cors: false,\n },\n {\n id: 'fireworks',\n make: fireworksProvider,\n env: 'FIREWORKS_API_KEY',\n description: 'Open models hosted by Fireworks AI.',\n keyUrl: 'https://app.fireworks.ai/settings/users/api-keys',\n cors: false,\n },\n {\n id: 'baseten',\n make: basetenProvider,\n env: 'BASETEN_API_KEY',\n description: 'Open models hosted by Baseten.',\n keyUrl: 'https://app.baseten.co/settings/api_keys',\n cors: true,\n },\n {\n id: 'moonshotai',\n make: moonshotaiProvider,\n env: 'MOONSHOT_API_KEY',\n description: 'Kimi models from Moonshot AI.',\n keyUrl: 'https://platform.moonshot.ai/console/api-keys',\n cors: true,\n },\n {\n id: 'moonshotai-cn',\n make: moonshotaiCnProvider,\n env: 'MOONSHOT_API_KEY',\n description: 'Kimi models from Moonshot AI\u2019s China platform.',\n keyUrl: 'https://platform.moonshot.cn/console/api-keys',\n cors: true,\n },\n {\n id: 'xai',\n make: xaiProvider,\n env: 'XAI_API_KEY',\n description: 'Grok models from xAI.',\n keyUrl: 'https://console.x.ai',\n cors: true,\n signIn: true,\n },\n {\n id: 'meta',\n make: metaProvider,\n env: 'META_API_KEY',\n description: 'Meta\u2019s Muse models.',\n keyUrl: 'https://developer.meta.ai',\n cors: true,\n },\n {\n id: 'vercel-ai-gateway',\n make: vercelAIGatewayProvider,\n env: 'AI_GATEWAY_API_KEY',\n description: 'Models from many labs through Vercel\u2019s AI Gateway.',\n keyUrl: 'https://vercel.com/docs/ai-gateway/authentication',\n cors: false,\n },\n {\n id: 'minimax',\n make: minimaxProvider,\n env: 'MINIMAX_API_KEY',\n description: 'MiniMax\u2019s models.',\n keyUrl: 'https://platform.minimax.io/user-center/basic-information/interface-key',\n cors: false,\n },\n {\n id: 'minimax-cn',\n make: minimaxCnProvider,\n env: 'MINIMAX_CN_API_KEY',\n description: 'MiniMax\u2019s models from its China platform.',\n keyUrl: 'https://platform.minimaxi.com/user-center/basic-information/interface-key',\n cors: false,\n },\n {\n id: 'zai',\n make: zaiProvider,\n env: 'ZAI_API_KEY',\n description: 'GLM models on Z.AI\u2019s coding plan.',\n keyUrl: 'https://z.ai/manage-apikey/apikey-list',\n cors: false,\n },\n {\n id: 'zai-coding-cn',\n make: zaiCodingCnProvider,\n env: 'ZAI_CODING_CN_API_KEY',\n description: 'GLM models on Zhipu\u2019s coding plan in China.',\n keyUrl: 'https://open.bigmodel.cn/usercenter/apikeys',\n cors: false,\n },\n {\n id: 'nvidia',\n make: nvidiaProvider,\n env: 'NVIDIA_API_KEY',\n description: 'Open models on NVIDIA\u2019s API catalog.',\n keyUrl: 'https://build.nvidia.com/settings/api-keys',\n cors: false,\n },\n {\n id: 'kimi-coding',\n make: kimiCodingProvider,\n env: 'KIMI_API_KEY',\n description: 'Kimi models on the Kimi Code subscription.',\n keyUrl: 'https://www.kimi.com/code/console',\n cors: false,\n signIn: true,\n },\n {\n id: 'ant-ling',\n make: antLingProvider,\n env: 'ANT_LING_API_KEY',\n description: 'Ling and Ring models from Ant Group.',\n keyUrl: 'https://www.ant-ling.com',\n cors: false,\n },\n {\n id: 'opencode',\n make: opencodeProvider,\n env: 'OPENCODE_API_KEY',\n description:\n 'Models curated for coding agents by OpenCode Zen. Needs seven\u2019s vault 1.12.2 or later.',\n keyUrl: 'https://opencode.ai/auth',\n cors: false,\n },\n {\n id: 'opencode-go',\n make: opencodeGoProvider,\n env: 'OPENCODE_API_KEY',\n description:\n 'Open models on the OpenCode Go subscription. Needs seven\u2019s vault 1.12.2 or later.',\n keyUrl: 'https://opencode.ai/auth',\n cors: false,\n },\n {\n id: 'qwen-token-plan',\n make: qwenTokenPlanProvider,\n env: 'QWEN_TOKEN_PLAN_API_KEY',\n description: 'Qwen models on an Alibaba Cloud token plan.',\n keyUrl: 'https://modelstudio.console.alibabacloud.com',\n cors: false,\n },\n {\n id: 'qwen-token-plan-cn',\n make: qwenTokenPlanCnProvider,\n env: 'QWEN_TOKEN_PLAN_CN_API_KEY',\n description: 'Qwen models on an Alibaba Cloud token plan in China.',\n keyUrl: 'https://bailian.console.aliyun.com',\n cors: false,\n },\n {\n id: 'qwen-token-plan-individual',\n make: qwenTokenPlanIndividualProvider,\n env: 'QWEN_TOKEN_PLAN_API_KEY',\n description: 'Qwen models on an individual Alibaba Cloud token plan.',\n keyUrl: 'https://modelstudio.console.alibabacloud.com',\n cors: false,\n },\n];\n\nexport type ProviderAuth = 'api-key' | 'oauth' | 'fields' | 'local';\n\nexport interface Listing {\n description: string;\n keyUrl?: string;\n auth: ProviderAuth;\n corsFree: boolean;\n vaultName: string;\n fields?: readonly FieldSpec[];\n}\n\nconst upper = (text: string) => text.toUpperCase().replace(/[^A-Z0-9]/g, '_');\n\nfunction vaultNames(entries: readonly KeyProvider[]): Map<string, string> {\n const uses = Map.groupBy(entries, (entry) => entry.env);\n return new Map(\n entries.map((entry) => [\n entry.id,\n (uses.get(entry.env) as KeyProvider[]).length > 1 ? `${upper(entry.id)}_API_KEY` : entry.env,\n ])\n );\n}\n\nconst named = vaultNames(KEY_PROVIDERS);\n\nexport const LISTINGS: ReadonlyMap<string, Listing> = new Map<string, Listing>([\n [\n 'amazon-bedrock',\n {\n description: 'Claude and other models on AWS, with a Bedrock API key.',\n keyUrl: 'https://console.aws.amazon.com/bedrock/home#/api-keys',\n auth: 'fields',\n corsFree: false,\n vaultName: 'AWS_BEARER_TOKEN_BEDROCK',\n fields: [REGION_FIELD],\n },\n ],\n [\n 'adobe',\n {\n description: 'Models through Adobe\u2019s LLM proxy, with your Adobe ID.',\n auth: 'oauth',\n corsFree: false,\n vaultName: 'ADOBE_IMS_TOKEN',\n },\n ],\n ...KEY_PROVIDERS.map((entry): [string, Listing] => [\n entry.id,\n {\n description: entry.description,\n keyUrl: entry.keyUrl,\n auth: entry.signIn ? 'oauth' : entry.fields ? 'fields' : 'api-key',\n corsFree: !entry.cors,\n vaultName: named.get(entry.id) as string,\n ...(entry.fields ? { fields: entry.fields } : {}),\n },\n ]),\n [\n CODEX,\n {\n description: 'GPT models on your ChatGPT Plus or Pro plan, with your ChatGPT account.',\n auth: 'oauth',\n corsFree: true,\n vaultName: 'OPENAI_CODEX_TOKEN',\n },\n ],\n]);\n\nexport const ADDED_FIRST: readonly string[] = ['amazon-bedrock', 'adobe'];\n"],
4
+ "sourcesContent": ["import type { Provider } from '@earendil-works/pi-ai';\nimport { antLingProvider } from '@earendil-works/pi-ai/providers/ant-ling';\nimport { anthropicProvider } from '@earendil-works/pi-ai/providers/anthropic';\nimport { azureProvider } from '@earendil-works/pi-ai/providers/azure';\nimport { basetenProvider } from '@earendil-works/pi-ai/providers/baseten';\nimport { cerebrasProvider } from '@earendil-works/pi-ai/providers/cerebras';\nimport { cloudflareAIGatewayProvider } from '@earendil-works/pi-ai/providers/cloudflare-ai-gateway';\nimport { cloudflareWorkersAIProvider } from '@earendil-works/pi-ai/providers/cloudflare-workers-ai';\nimport { deepseekProvider } from '@earendil-works/pi-ai/providers/deepseek';\nimport { fireworksProvider } from '@earendil-works/pi-ai/providers/fireworks';\nimport { groqProvider } from '@earendil-works/pi-ai/providers/groq';\nimport { huggingfaceProvider } from '@earendil-works/pi-ai/providers/huggingface';\nimport { kimiCodingProvider } from '@earendil-works/pi-ai/providers/kimi-coding';\nimport { metaProvider } from '@earendil-works/pi-ai/providers/meta';\nimport { minimaxProvider } from '@earendil-works/pi-ai/providers/minimax';\nimport { minimaxCnProvider } from '@earendil-works/pi-ai/providers/minimax-cn';\nimport { mistralProvider } from '@earendil-works/pi-ai/providers/mistral';\nimport { moonshotaiProvider } from '@earendil-works/pi-ai/providers/moonshotai';\nimport { moonshotaiCnProvider } from '@earendil-works/pi-ai/providers/moonshotai-cn';\nimport { nvidiaProvider } from '@earendil-works/pi-ai/providers/nvidia';\nimport { openaiProvider } from '@earendil-works/pi-ai/providers/openai';\nimport { opencodeProvider } from '@earendil-works/pi-ai/providers/opencode';\nimport { opencodeGoProvider } from '@earendil-works/pi-ai/providers/opencode-go';\nimport { openrouterProvider } from '@earendil-works/pi-ai/providers/openrouter';\nimport { qwenTokenPlanProvider } from '@earendil-works/pi-ai/providers/qwen-token-plan';\nimport { qwenTokenPlanCnProvider } from '@earendil-works/pi-ai/providers/qwen-token-plan-cn';\nimport { qwenTokenPlanIndividualProvider } from '@earendil-works/pi-ai/providers/qwen-token-plan-individual';\nimport { togetherProvider } from '@earendil-works/pi-ai/providers/together';\nimport { vercelAIGatewayProvider } from '@earendil-works/pi-ai/providers/vercel-ai-gateway';\nimport { xaiProvider } from '@earendil-works/pi-ai/providers/xai';\nimport { xiaomiProvider } from '@earendil-works/pi-ai/providers/xiaomi';\nimport { xiaomiTokenPlanAmsProvider } from '@earendil-works/pi-ai/providers/xiaomi-token-plan-ams';\nimport { xiaomiTokenPlanCnProvider } from '@earendil-works/pi-ai/providers/xiaomi-token-plan-cn';\nimport { xiaomiTokenPlanSgpProvider } from '@earendil-works/pi-ai/providers/xiaomi-token-plan-sgp';\nimport { zaiProvider } from '@earendil-works/pi-ai/providers/zai';\nimport { zaiCodingCnProvider } from '@earendil-works/pi-ai/providers/zai-coding-cn';\nimport { CODEX } from './sign-ins.ts';\n\nexport interface FieldOption {\n value: string;\n label: string;\n}\n\nexport interface FieldInput {\n name: string;\n label: string;\n required?: boolean;\n placeholder?: string;\n help?: string;\n customBase?: true;\n vaultSetting?: string;\n options?: readonly FieldOption[];\n value?: string;\n}\n\nexport interface FieldSpec extends FieldInput {\n env(value: string): Record<string, string> | string;\n}\n\nexport interface KeyProvider {\n id: string;\n make: () => Provider;\n env: string;\n description: string;\n keyUrl: string;\n cors: boolean;\n signIn?: true;\n fields?: readonly FieldSpec[];\n}\n\nconst RESOURCE = /^[a-z0-9][a-z0-9-]{0,62}$/i;\nconst DEPLOYMENTS = /^[^=,\\s]+\\s*=\\s*[^=,\\s]+(\\s*,\\s*[^=,\\s]+\\s*=\\s*[^=,\\s]+)*$/;\n\nexport function httpsBase(value: string): URL | undefined {\n const url = URL.parse(value);\n if (url?.protocol !== 'https:' || url.username || url.password) return undefined;\n return url.port === '' || url.port === '443' ? url : undefined;\n}\n\nfunction azureEndpoint(value: string): Record<string, string> | string {\n if (RESOURCE.test(value)) return { AZURE_OPENAI_RESOURCE_NAME: value };\n const url = httpsBase(value);\n if (!url)\n return 'Enter your Azure resource name, or its endpoint as an https:// address without a port or a user name.';\n return { AZURE_OPENAI_BASE_URL: url.href.replace(/\\/+$/, '') };\n}\n\nexport const AZURE = 'azure';\n\nexport function azureBase(env: Readonly<Record<string, string>>): string | undefined {\n if (env.AZURE_OPENAI_BASE_URL) return env.AZURE_OPENAI_BASE_URL;\n const name = env.AZURE_OPENAI_RESOURCE_NAME;\n return name ? `https://${name}.openai.azure.com/openai/v1` : undefined;\n}\n\nconst REGION = /^[a-z]{2,}(-[a-z]+)+-\\d{1,2}$/;\nconst ACCOUNT = /^[0-9a-f]{32}$/i;\nconst GATEWAY = /^[A-Za-z0-9_-]{1,64}$/;\n\nconst checked =\n (pattern: RegExp, env: string, problem: string) =>\n (value: string): Record<string, string> | string =>\n pattern.test(value) ? { [env]: value } : problem;\n\nconst BEDROCK_REGIONS: readonly (readonly [string, string])[] = [\n ['ap-northeast-1', 'Asia Pacific (Tokyo)'],\n ['ap-northeast-2', 'Asia Pacific (Seoul)'],\n ['ap-northeast-3', 'Asia Pacific (Osaka)'],\n ['ap-south-1', 'Asia Pacific (Mumbai)'],\n ['ap-south-2', 'Asia Pacific (Hyderabad)'],\n ['ap-southeast-1', 'Asia Pacific (Singapore)'],\n ['ap-southeast-2', 'Asia Pacific (Sydney)'],\n ['ca-central-1', 'Canada (Central)'],\n ['eu-central-1', 'Europe (Frankfurt)'],\n ['eu-central-2', 'Europe (Zurich)'],\n ['eu-north-1', 'Europe (Stockholm)'],\n ['eu-south-1', 'Europe (Milan)'],\n ['eu-south-2', 'Europe (Spain)'],\n ['eu-west-1', 'Europe (Ireland)'],\n ['eu-west-2', 'Europe (London)'],\n ['eu-west-3', 'Europe (Paris)'],\n ['sa-east-1', 'South America (S\u00E3o Paulo)'],\n ['us-east-1', 'US East (N. Virginia)'],\n ['us-gov-east-1', 'AWS GovCloud (US-East)'],\n ['us-gov-west-1', 'AWS GovCloud (US-West)'],\n ['us-west-2', 'US West (Oregon)'],\n];\n\nexport const DEFAULT_REGION = 'us-west-2';\n\nexport const REGION_FIELD: FieldSpec = {\n name: 'region',\n label: 'Region',\n help: 'The AWS region your Bedrock models run in.',\n options: BEDROCK_REGIONS.map(([value, label]) => ({ value, label: `${label}, ${value}` })),\n value: DEFAULT_REGION,\n env: checked(REGION, 'AWS_REGION', 'Enter an AWS region such as us-west-2.'),\n};\n\nconst ACCOUNT_FIELD: FieldSpec = {\n name: 'account',\n label: 'Account ID',\n required: true,\n placeholder: '0123456789abcdef0123456789abcdef',\n help: 'The 32-character ID on your Cloudflare dashboard\u2019s account overview.',\n vaultSetting: 'CLOUDFLARE_ACCOUNT_ID',\n env: checked(\n ACCOUNT,\n 'CLOUDFLARE_ACCOUNT_ID',\n 'A Cloudflare account ID is 32 characters of 0\u20139 and a\u2013f.'\n ),\n};\n\nexport const KEY_PROVIDERS: readonly KeyProvider[] = [\n {\n id: 'azure',\n make: azureProvider,\n env: 'AZURE_OPENAI_API_KEY',\n description: 'OpenAI models deployed in your own Azure OpenAI or AI Foundry resource.',\n keyUrl: 'https://portal.azure.com',\n cors: true,\n fields: [\n {\n name: 'endpoint',\n label: 'Endpoint',\n required: true,\n placeholder: 'my-resource or https://my-resource.openai.azure.com',\n help: 'Your resource\u2019s name, or its endpoint address from Keys and Endpoint.',\n customBase: true,\n vaultSetting: 'AZURE_OPENAI_RESOURCE_NAME',\n env: azureEndpoint,\n },\n {\n name: 'deployments',\n label: 'Deployments',\n placeholder: 'gpt-5.4=my-gpt',\n help: 'Only for deployments named differently from their model, as model=deployment, separated by commas.',\n env: (value) =>\n DEPLOYMENTS.test(value)\n ? { AZURE_OPENAI_DEPLOYMENT_NAME_MAP: value }\n : 'Write each deployment as model=deployment, separated by commas.',\n },\n ],\n },\n {\n id: 'cloudflare-workers-ai',\n make: cloudflareWorkersAIProvider,\n env: 'CLOUDFLARE_API_KEY',\n description: 'Open models on Cloudflare Workers AI, in your Cloudflare account.',\n keyUrl: 'https://dash.cloudflare.com/profile/api-tokens',\n cors: false,\n fields: [ACCOUNT_FIELD],\n },\n {\n id: 'cloudflare-ai-gateway',\n make: cloudflareAIGatewayProvider,\n env: 'CLOUDFLARE_API_KEY',\n description: 'Models from many labs through your Cloudflare AI Gateway.',\n keyUrl: 'https://dash.cloudflare.com/profile/api-tokens',\n cors: false,\n fields: [\n ACCOUNT_FIELD,\n {\n name: 'gateway',\n label: 'Gateway ID',\n required: true,\n placeholder: 'my-gateway',\n help: 'The name of your gateway under AI \u203A AI Gateway.',\n vaultSetting: 'CLOUDFLARE_GATEWAY_ID',\n env: checked(\n GATEWAY,\n 'CLOUDFLARE_GATEWAY_ID',\n 'A gateway ID is letters, digits, - and _, up to 64 characters.'\n ),\n },\n ],\n },\n {\n id: 'anthropic',\n make: anthropicProvider,\n env: 'ANTHROPIC_API_KEY',\n description: 'Claude models, with an API key from the Claude Console.',\n keyUrl: 'https://console.anthropic.com/settings/keys',\n cors: true,\n },\n {\n id: 'openai',\n make: openaiProvider,\n env: 'OPENAI_API_KEY',\n description: 'GPT models, with an API key from the OpenAI platform.',\n keyUrl: 'https://platform.openai.com/api-keys',\n cors: true,\n },\n {\n id: 'mistral',\n make: mistralProvider,\n env: 'MISTRAL_API_KEY',\n description: 'Mistral and Devstral models from La Plateforme.',\n keyUrl: 'https://console.mistral.ai/api-keys',\n cors: true,\n },\n {\n id: 'groq',\n make: groqProvider,\n env: 'GROQ_API_KEY',\n description: 'Open models on Groq\u2019s fast inference.',\n keyUrl: 'https://console.groq.com/keys',\n cors: true,\n },\n {\n id: 'deepseek',\n make: deepseekProvider,\n env: 'DEEPSEEK_API_KEY',\n description: 'DeepSeek\u2019s own models.',\n keyUrl: 'https://platform.deepseek.com/api_keys',\n cors: true,\n },\n {\n id: 'together',\n make: togetherProvider,\n env: 'TOGETHER_API_KEY',\n description: 'Open models hosted by Together AI.',\n keyUrl: 'https://api.together.ai/settings/api-keys',\n cors: true,\n },\n {\n id: 'huggingface',\n make: huggingfaceProvider,\n env: 'HF_TOKEN',\n description: 'Open models through Hugging Face\u2019s inference router.',\n keyUrl: 'https://huggingface.co/settings/tokens',\n cors: true,\n },\n {\n id: 'xiaomi',\n make: xiaomiProvider,\n env: 'XIAOMI_API_KEY',\n description: 'Xiaomi\u2019s MiMo models.',\n keyUrl: 'https://platform.xiaomimimo.com/#/console/api-keys',\n cors: true,\n },\n {\n id: 'xiaomi-token-plan-ams',\n make: xiaomiTokenPlanAmsProvider,\n env: 'XIAOMI_TOKEN_PLAN_AMS_API_KEY',\n description: 'MiMo models on a Xiaomi token plan, served from Amsterdam.',\n keyUrl: 'https://platform.xiaomimimo.com/#/console/api-keys',\n cors: true,\n },\n {\n id: 'xiaomi-token-plan-cn',\n make: xiaomiTokenPlanCnProvider,\n env: 'XIAOMI_TOKEN_PLAN_CN_API_KEY',\n description: 'MiMo models on a Xiaomi token plan, served from China.',\n keyUrl: 'https://platform.xiaomimimo.com/#/console/api-keys',\n cors: true,\n },\n {\n id: 'xiaomi-token-plan-sgp',\n make: xiaomiTokenPlanSgpProvider,\n env: 'XIAOMI_TOKEN_PLAN_SGP_API_KEY',\n description: 'MiMo models on a Xiaomi token plan, served from Singapore.',\n keyUrl: 'https://platform.xiaomimimo.com/#/console/api-keys',\n cors: true,\n },\n {\n id: 'cerebras',\n make: cerebrasProvider,\n env: 'CEREBRAS_API_KEY',\n description: 'Open models on Cerebras inference.',\n keyUrl: 'https://cloud.cerebras.ai',\n cors: false,\n },\n {\n id: 'openrouter',\n make: openrouterProvider,\n env: 'OPENROUTER_API_KEY',\n description: 'Hundreds of models from many labs through one key.',\n keyUrl: 'https://openrouter.ai/settings/keys',\n cors: false,\n },\n {\n id: 'fireworks',\n make: fireworksProvider,\n env: 'FIREWORKS_API_KEY',\n description: 'Open models hosted by Fireworks AI.',\n keyUrl: 'https://app.fireworks.ai/settings/users/api-keys',\n cors: false,\n },\n {\n id: 'baseten',\n make: basetenProvider,\n env: 'BASETEN_API_KEY',\n description: 'Open models hosted by Baseten.',\n keyUrl: 'https://app.baseten.co/settings/api_keys',\n cors: true,\n },\n {\n id: 'moonshotai',\n make: moonshotaiProvider,\n env: 'MOONSHOT_API_KEY',\n description: 'Kimi models from Moonshot AI.',\n keyUrl: 'https://platform.moonshot.ai/console/api-keys',\n cors: true,\n },\n {\n id: 'moonshotai-cn',\n make: moonshotaiCnProvider,\n env: 'MOONSHOT_API_KEY',\n description: 'Kimi models from Moonshot AI\u2019s China platform.',\n keyUrl: 'https://platform.moonshot.cn/console/api-keys',\n cors: true,\n },\n {\n id: 'xai',\n make: xaiProvider,\n env: 'XAI_API_KEY',\n description: 'Grok models from xAI.',\n keyUrl: 'https://console.x.ai',\n cors: true,\n signIn: true,\n },\n {\n id: 'meta',\n make: metaProvider,\n env: 'META_API_KEY',\n description: 'Meta\u2019s Muse models.',\n keyUrl: 'https://developer.meta.ai',\n cors: true,\n },\n {\n id: 'vercel-ai-gateway',\n make: vercelAIGatewayProvider,\n env: 'AI_GATEWAY_API_KEY',\n description: 'Models from many labs through Vercel\u2019s AI Gateway.',\n keyUrl: 'https://vercel.com/docs/ai-gateway/authentication',\n cors: false,\n },\n {\n id: 'minimax',\n make: minimaxProvider,\n env: 'MINIMAX_API_KEY',\n description: 'MiniMax\u2019s models.',\n keyUrl: 'https://platform.minimax.io/user-center/basic-information/interface-key',\n cors: false,\n },\n {\n id: 'minimax-cn',\n make: minimaxCnProvider,\n env: 'MINIMAX_CN_API_KEY',\n description: 'MiniMax\u2019s models from its China platform.',\n keyUrl: 'https://platform.minimaxi.com/user-center/basic-information/interface-key',\n cors: false,\n },\n {\n id: 'zai',\n make: zaiProvider,\n env: 'ZAI_API_KEY',\n description: 'GLM models on Z.AI\u2019s coding plan.',\n keyUrl: 'https://z.ai/manage-apikey/apikey-list',\n cors: false,\n },\n {\n id: 'zai-coding-cn',\n make: zaiCodingCnProvider,\n env: 'ZAI_CODING_CN_API_KEY',\n description: 'GLM models on Zhipu\u2019s coding plan in China.',\n keyUrl: 'https://open.bigmodel.cn/usercenter/apikeys',\n cors: true,\n },\n {\n id: 'nvidia',\n make: nvidiaProvider,\n env: 'NVIDIA_API_KEY',\n description: 'Open models on NVIDIA\u2019s API catalog.',\n keyUrl: 'https://build.nvidia.com/settings/api-keys',\n cors: false,\n },\n {\n id: 'kimi-coding',\n make: kimiCodingProvider,\n env: 'KIMI_API_KEY',\n description: 'Kimi models on the Kimi Code subscription.',\n keyUrl: 'https://www.kimi.com/code/console',\n cors: false,\n signIn: true,\n },\n {\n id: 'ant-ling',\n make: antLingProvider,\n env: 'ANT_LING_API_KEY',\n description: 'Ling and Ring models from Ant Group.',\n keyUrl: 'https://www.ant-ling.com',\n cors: false,\n },\n {\n id: 'opencode',\n make: opencodeProvider,\n env: 'OPENCODE_API_KEY',\n description:\n 'Models curated for coding agents by OpenCode Zen. Needs seven\u2019s vault 1.12.2 or later.',\n keyUrl: 'https://opencode.ai/auth',\n cors: false,\n },\n {\n id: 'opencode-go',\n make: opencodeGoProvider,\n env: 'OPENCODE_API_KEY',\n description:\n 'Open models on the OpenCode Go subscription. Needs seven\u2019s vault 1.12.2 or later.',\n keyUrl: 'https://opencode.ai/auth',\n cors: false,\n },\n {\n id: 'qwen-token-plan',\n make: qwenTokenPlanProvider,\n env: 'QWEN_TOKEN_PLAN_API_KEY',\n description: 'Qwen models on an Alibaba Cloud token plan.',\n keyUrl: 'https://modelstudio.console.alibabacloud.com',\n cors: false,\n },\n {\n id: 'qwen-token-plan-cn',\n make: qwenTokenPlanCnProvider,\n env: 'QWEN_TOKEN_PLAN_CN_API_KEY',\n description: 'Qwen models on an Alibaba Cloud token plan in China.',\n keyUrl: 'https://bailian.console.aliyun.com',\n cors: false,\n },\n {\n id: 'qwen-token-plan-individual',\n make: qwenTokenPlanIndividualProvider,\n env: 'QWEN_TOKEN_PLAN_API_KEY',\n description: 'Qwen models on an individual Alibaba Cloud token plan.',\n keyUrl: 'https://modelstudio.console.alibabacloud.com',\n cors: false,\n },\n];\n\nexport type ProviderAuth = 'api-key' | 'oauth' | 'fields' | 'local';\n\nexport interface Listing {\n description: string;\n keyUrl?: string;\n auth: ProviderAuth;\n corsFree: boolean;\n vaultName: string;\n fields?: readonly FieldSpec[];\n}\n\nconst upper = (text: string) => text.toUpperCase().replace(/[^A-Z0-9]/g, '_');\n\nfunction vaultNames(entries: readonly KeyProvider[]): Map<string, string> {\n const uses = Map.groupBy(entries, (entry) => entry.env);\n return new Map(\n entries.map((entry) => [\n entry.id,\n (uses.get(entry.env) as KeyProvider[]).length > 1 ? `${upper(entry.id)}_API_KEY` : entry.env,\n ])\n );\n}\n\nconst named = vaultNames(KEY_PROVIDERS);\n\nexport const LISTINGS: ReadonlyMap<string, Listing> = new Map<string, Listing>([\n [\n 'amazon-bedrock',\n {\n description: 'Claude and other models on AWS, with a Bedrock API key.',\n keyUrl: 'https://console.aws.amazon.com/bedrock/home#/api-keys',\n auth: 'fields',\n corsFree: false,\n vaultName: 'AWS_BEARER_TOKEN_BEDROCK',\n fields: [REGION_FIELD],\n },\n ],\n [\n 'adobe',\n {\n description: 'Models through Adobe\u2019s LLM proxy, with your Adobe ID.',\n auth: 'oauth',\n corsFree: false,\n vaultName: 'ADOBE_IMS_TOKEN',\n },\n ],\n ...KEY_PROVIDERS.map((entry): [string, Listing] => [\n entry.id,\n {\n description: entry.description,\n keyUrl: entry.keyUrl,\n auth: entry.signIn ? 'oauth' : entry.fields ? 'fields' : 'api-key',\n corsFree: !entry.cors,\n vaultName: named.get(entry.id) as string,\n ...(entry.fields ? { fields: entry.fields } : {}),\n },\n ]),\n [\n CODEX,\n {\n description: 'GPT models on your ChatGPT Plus or Pro plan, with your ChatGPT account.',\n auth: 'oauth',\n corsFree: true,\n vaultName: 'OPENAI_CODEX_TOKEN',\n },\n ],\n]);\n\nexport const ADDED_FIRST: readonly string[] = ['amazon-bedrock', 'adobe'];\n"],
5
5
  "mappings": "AACA,SAAS,uBAAuB;AAChC,SAAS,yBAAyB;AAClC,SAAS,qBAAqB;AAC9B,SAAS,uBAAuB;AAChC,SAAS,wBAAwB;AACjC,SAAS,mCAAmC;AAC5C,SAAS,mCAAmC;AAC5C,SAAS,wBAAwB;AACjC,SAAS,yBAAyB;AAClC,SAAS,oBAAoB;AAC7B,SAAS,2BAA2B;AACpC,SAAS,0BAA0B;AACnC,SAAS,oBAAoB;AAC7B,SAAS,uBAAuB;AAChC,SAAS,yBAAyB;AAClC,SAAS,uBAAuB;AAChC,SAAS,0BAA0B;AACnC,SAAS,4BAA4B;AACrC,SAAS,sBAAsB;AAC/B,SAAS,sBAAsB;AAC/B,SAAS,wBAAwB;AACjC,SAAS,0BAA0B;AACnC,SAAS,0BAA0B;AACnC,SAAS,6BAA6B;AACtC,SAAS,+BAA+B;AACxC,SAAS,uCAAuC;AAChD,SAAS,wBAAwB;AACjC,SAAS,+BAA+B;AACxC,SAAS,mBAAmB;AAC5B,SAAS,sBAAsB;AAC/B,SAAS,kCAAkC;AAC3C,SAAS,iCAAiC;AAC1C,SAAS,kCAAkC;AAC3C,SAAS,mBAAmB;AAC5B,SAAS,2BAA2B;AACpC,SAAS,aAAa;AAkCtB,MAAM,WAAW;AACjB,MAAM,cAAc;AAEb,SAAS,UAAU,OAAgC;AACxD,QAAM,MAAM,IAAI,MAAM,KAAK;AAC3B,MAAI,KAAK,aAAa,YAAY,IAAI,YAAY,IAAI,SAAU,QAAO;AACvE,SAAO,IAAI,SAAS,MAAM,IAAI,SAAS,QAAQ,MAAM;AACvD;AAEA,SAAS,cAAc,OAAgD;AACrE,MAAI,SAAS,KAAK,KAAK,EAAG,QAAO,EAAE,4BAA4B,MAAM;AACrE,QAAM,MAAM,UAAU,KAAK;AAC3B,MAAI,CAAC;AACH,WAAO;AACT,SAAO,EAAE,uBAAuB,IAAI,KAAK,QAAQ,QAAQ,EAAE,EAAE;AAC/D;AAEO,MAAM,QAAQ;AAEd,SAAS,UAAU,KAA2D;AACnF,MAAI,IAAI,sBAAuB,QAAO,IAAI;AAC1C,QAAM,OAAO,IAAI;AACjB,SAAO,OAAO,WAAW,IAAI,gCAAgC;AAC/D;AAEA,MAAM,SAAS;AACf,MAAM,UAAU;AAChB,MAAM,UAAU;AAEhB,MAAM,UACJ,CAAC,SAAiB,KAAa,YAC/B,CAAC,UACC,QAAQ,KAAK,KAAK,IAAI,EAAE,CAAC,GAAG,GAAG,MAAM,IAAI;AAE7C,MAAM,kBAA0D;AAAA,EAC9D,CAAC,kBAAkB,sBAAsB;AAAA,EACzC,CAAC,kBAAkB,sBAAsB;AAAA,EACzC,CAAC,kBAAkB,sBAAsB;AAAA,EACzC,CAAC,cAAc,uBAAuB;AAAA,EACtC,CAAC,cAAc,0BAA0B;AAAA,EACzC,CAAC,kBAAkB,0BAA0B;AAAA,EAC7C,CAAC,kBAAkB,uBAAuB;AAAA,EAC1C,CAAC,gBAAgB,kBAAkB;AAAA,EACnC,CAAC,gBAAgB,oBAAoB;AAAA,EACrC,CAAC,gBAAgB,iBAAiB;AAAA,EAClC,CAAC,cAAc,oBAAoB;AAAA,EACnC,CAAC,cAAc,gBAAgB;AAAA,EAC/B,CAAC,cAAc,gBAAgB;AAAA,EAC/B,CAAC,aAAa,kBAAkB;AAAA,EAChC,CAAC,aAAa,iBAAiB;AAAA,EAC/B,CAAC,aAAa,gBAAgB;AAAA,EAC9B,CAAC,aAAa,8BAA2B;AAAA,EACzC,CAAC,aAAa,uBAAuB;AAAA,EACrC,CAAC,iBAAiB,wBAAwB;AAAA,EAC1C,CAAC,iBAAiB,wBAAwB;AAAA,EAC1C,CAAC,aAAa,kBAAkB;AAClC;AAEO,MAAM,iBAAiB;AAEvB,MAAM,eAA0B;AAAA,EACrC,MAAM;AAAA,EACN,OAAO;AAAA,EACP,MAAM;AAAA,EACN,SAAS,gBAAgB,IAAI,CAAC,CAAC,OAAO,KAAK,OAAO,EAAE,OAAO,OAAO,GAAG,KAAK,KAAK,KAAK,GAAG,EAAE;AAAA,EACzF,OAAO;AAAA,EACP,KAAK,QAAQ,QAAQ,cAAc,wCAAwC;AAC7E;AAEA,MAAM,gBAA2B;AAAA,EAC/B,MAAM;AAAA,EACN,OAAO;AAAA,EACP,UAAU;AAAA,EACV,aAAa;AAAA,EACb,MAAM;AAAA,EACN,cAAc;AAAA,EACd,KAAK;AAAA,IACH;AAAA,IACA;AAAA,IACA;AAAA,EACF;AACF;AAEO,MAAM,gBAAwC;AAAA,EACnD;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,IACN,QAAQ;AAAA,MACN;AAAA,QACE,MAAM;AAAA,QACN,OAAO;AAAA,QACP,UAAU;AAAA,QACV,aAAa;AAAA,QACb,MAAM;AAAA,QACN,YAAY;AAAA,QACZ,cAAc;AAAA,QACd,KAAK;AAAA,MACP;AAAA,MACA;AAAA,QACE,MAAM;AAAA,QACN,OAAO;AAAA,QACP,aAAa;AAAA,QACb,MAAM;AAAA,QACN,KAAK,CAAC,UACJ,YAAY,KAAK,KAAK,IAClB,EAAE,kCAAkC,MAAM,IAC1C;AAAA,MACR;AAAA,IACF;AAAA,EACF;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,IACN,QAAQ,CAAC,aAAa;AAAA,EACxB;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,IACN,QAAQ;AAAA,MACN;AAAA,MACA;AAAA,QACE,MAAM;AAAA,QACN,OAAO;AAAA,QACP,UAAU;AAAA,QACV,aAAa;AAAA,QACb,MAAM;AAAA,QACN,cAAc;AAAA,QACd,KAAK;AAAA,UACH;AAAA,UACA;AAAA,UACA;AAAA,QACF;AAAA,MACF;AAAA,IACF;AAAA,EACF;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,IACN,QAAQ;AAAA,EACV;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,IACN,QAAQ;AAAA,EACV;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aACE;AAAA,IACF,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aACE;AAAA,IACF,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AAAA,EACA;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,KAAK;AAAA,IACL,aAAa;AAAA,IACb,QAAQ;AAAA,IACR,MAAM;AAAA,EACR;AACF;AAaA,MAAM,QAAQ,CAAC,SAAiB,KAAK,YAAY,EAAE,QAAQ,cAAc,GAAG;AAE5E,SAAS,WAAW,SAAsD;AACxE,QAAM,OAAO,IAAI,QAAQ,SAAS,CAAC,UAAU,MAAM,GAAG;AACtD,SAAO,IAAI;AAAA,IACT,QAAQ,IAAI,CAAC,UAAU;AAAA,MACrB,MAAM;AAAA,MACL,KAAK,IAAI,MAAM,GAAG,EAAoB,SAAS,IAAI,GAAG,MAAM,MAAM,EAAE,CAAC,aAAa,MAAM;AAAA,IAC3F,CAAC;AAAA,EACH;AACF;AAEA,MAAM,QAAQ,WAAW,aAAa;AAE/B,MAAM,WAAyC,IAAI,IAAqB;AAAA,EAC7E;AAAA,IACE;AAAA,IACA;AAAA,MACE,aAAa;AAAA,MACb,QAAQ;AAAA,MACR,MAAM;AAAA,MACN,UAAU;AAAA,MACV,WAAW;AAAA,MACX,QAAQ,CAAC,YAAY;AAAA,IACvB;AAAA,EACF;AAAA,EACA;AAAA,IACE;AAAA,IACA;AAAA,MACE,aAAa;AAAA,MACb,MAAM;AAAA,MACN,UAAU;AAAA,MACV,WAAW;AAAA,IACb;AAAA,EACF;AAAA,EACA,GAAG,cAAc,IAAI,CAAC,UAA6B;AAAA,IACjD,MAAM;AAAA,IACN;AAAA,MACE,aAAa,MAAM;AAAA,MACnB,QAAQ,MAAM;AAAA,MACd,MAAM,MAAM,SAAS,UAAU,MAAM,SAAS,WAAW;AAAA,MACzD,UAAU,CAAC,MAAM;AAAA,MACjB,WAAW,MAAM,IAAI,MAAM,EAAE;AAAA,MAC7B,GAAI,MAAM,SAAS,EAAE,QAAQ,MAAM,OAAO,IAAI,CAAC;AAAA,IACjD;AAAA,EACF,CAAC;AAAA,EACD;AAAA,IACE;AAAA,IACA;AAAA,MACE,aAAa;AAAA,MACb,MAAM;AAAA,MACN,UAAU;AAAA,MACV,WAAW;AAAA,IACb;AAAA,EACF;AACF,CAAC;AAEM,MAAM,cAAiC,CAAC,kBAAkB,OAAO;",
6
6
  "names": []
7
7
  }
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@ai-ecoverse/slicc-agent",
3
- "version": "6.18.4",
3
+ "version": "6.18.5",
4
4
  "description": "SLICC's agent core on pi durable: an agent worker, session storage, remoting and pi extensions",
5
5
  "type": "module",
6
6
  "license": "Apache-2.0",
@@ -68,7 +68,7 @@
68
68
  "@ai-ecoverse/slicc-kernel": "1.138.1",
69
69
  "@ai-ecoverse/slicc-scrub": "1.0.0",
70
70
  "@ai-ecoverse/slicc-shared-web": "1.29.1",
71
- "@ai-ecoverse/slicc-spectrum": "1.103.2",
71
+ "@ai-ecoverse/slicc-spectrum": "1.103.3",
72
72
  "@ai-ecoverse/wasi-fnox": "1.39.0-6",
73
73
  "@ai-ecoverse/wasm-bash": "5.3.0-22",
74
74
  "@ai-ecoverse/wasm-coreutils": "9.12.0-12",
@@ -77,7 +77,7 @@
77
77
  "@types/node": "24.19.2",
78
78
  "esbuild": "0.28.2",
79
79
  "fake-indexeddb": "6.2.5",
80
- "lefthook": "2.2.1",
80
+ "lefthook": "2.2.2",
81
81
  "monocart-coverage-reports": "2.13.2",
82
82
  "playwright-core": "1.64.0",
83
83
  "semantic-release": "25.0.9",