@arnilo/prism 0.3.1 → 0.4.0

package/docs/providers/azure.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-provider-azure` registers an Azure OpenAI / Foundry Chat Completions provider that uses host-supplied Entra workload identity (Bearer) or Azure resource keys (`api-key`). Deployment URLs keep the configured endpoint host (custom subdomain, private endpoint, or VNet FQDN).
+`@arnilo/prism-providers/azure` registers an Azure OpenAI / Foundry Chat Completions provider that uses host-supplied Entra workload identity (Bearer) or Azure resource keys (`api-key`). Deployment URLs keep the configured endpoint host (custom subdomain, private endpoint, or VNet FQDN).
 
 ## When to use it
 
@@ -11,7 +11,7 @@ Use it for enterprise Azure OpenAI / Foundry deployments with Managed Identity o
 ## Inputs / request
 
 ```ts
-import { createAzureOpenAIProviderPackage } from "@arnilo/prism-provider-azure";
+import { createAzureOpenAIProviderPackage } from "@arnilo/prism-providers/azure";
 
 createAzureOpenAIProviderPackage({
   endpoint: "https://my-resource.openai.azure.com",
@@ -72,4 +72,4 @@ Register via `createExtensionKernel().load([createAzureOpenAIProviderPackage(...
 - [Provider packages](../provider-packages.md)
 - [Model routing](../model-routing.md)
 - [Credential storage](../credential-storage.md)
-- Package README: [`@arnilo/prism-provider-azure`](../../packages/provider-azure/README.md)
+- Package README: [`@arnilo/prism-providers` family README](../../packages/prism-providers/README.md)

package/docs/providers/bedrock.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-provider-bedrock` registers an Amazon Bedrock Runtime OpenAI-compatible Chat Completions provider. Hosts supply IAM/IRSA/assumed-role credentials; the package signs requests with SigV4 (no AWS SDK). Region and optional PrivateLink endpoint URLs are preserved.
+`@arnilo/prism-providers/bedrock` registers an Amazon Bedrock Runtime OpenAI-compatible Chat Completions provider. Hosts supply IAM/IRSA/assumed-role credentials; the package signs requests with SigV4 (no AWS SDK). Region and optional PrivateLink endpoint URLs are preserved.
 
 ## When to use it
 
@@ -11,7 +11,7 @@ Use it for enterprise Bedrock access under workload identity. Do not embed long-
 ## Inputs / request
 
 ```ts
-import { createBedrockProviderPackage } from "@arnilo/prism-provider-bedrock";
+import { createBedrockProviderPackage } from "@arnilo/prism-providers/bedrock";
 
 createBedrockProviderPackage({
   region: "eu-west-1",
@@ -71,4 +71,4 @@ Uses Bedrock’s OpenAI-compatible runtime route (not Converse eventstream). Hos
 - [OpenAI-compatible provider](openai-compatible.md)
 - [Model routing](../model-routing.md)
 - [Provider packages](../provider-packages.md)
-- Package README: [`@arnilo/prism-provider-bedrock`](../../packages/provider-bedrock/README.md)
+- Package README: [`@arnilo/prism-providers` family README](../../packages/prism-providers/README.md)

package/docs/providers/clinepass.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-provider-clinepass` provides explicit, side-effect-free setup for
+`@arnilo/prism-providers/clinepass` provides explicit, side-effect-free setup for
 the ClinePass OpenAI-compatible Chat Completions API at
 `https://api.cline.bot/api/v1`. Requests always stream. Model ids are official
 `cline-pass/…` slugs from a static featured catalog.
@@ -19,7 +19,7 @@ or caller-gated `GET /models` (no documented OpenAI models endpoint).
 ## Inputs / request
 
 ```ts
-import { createClinePassProviderPackage } from "@arnilo/prism-provider-clinepass";
+import { createClinePassProviderPackage } from "@arnilo/prism-providers/clinepass";
 
 createClinePassProviderPackage(options: ClinePassProviderPackageOptions): ProviderPackage
 ```
@@ -74,7 +74,7 @@ Completion budget is `max_completion_tokens` (not `max_tokens`).
 
 ```ts
 import { createExtensionKernel } from "@arnilo/prism";
-import { createClinePassProviderPackage } from "@arnilo/prism-provider-clinepass";
+import { createClinePassProviderPackage } from "@arnilo/prism-providers/clinepass";
 
 const kernel = createExtensionKernel();
 await kernel.load([createClinePassProviderPackage({ apiKey: "fake-cline-key" })]);

package/docs/providers/deepseek.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-provider-deepseek` provides explicit, side-effect-free setup for the
+`@arnilo/prism-providers/deepseek` provides explicit, side-effect-free setup for the
 DeepSeek Chat Completions API (`POST /chat/completions`) with official thinking
 mode, reasoning-effort mapping, tool-turn `reasoning_content` replay, and
 implicit prefix caching.
@@ -26,7 +26,7 @@ import {
   createDeepSeekProviderPackage,
   defineDeepSeekModel,
   listDeepSeekModels,
-} from "@arnilo/prism-provider-deepseek";
+} from "@arnilo/prism-providers/deepseek";
 
 createDeepSeekProviderPackage(options: DeepSeekProviderPackageOptions): ProviderPackage
 defineDeepSeekModel(config: DeepSeekModelConfig): ModelConfig
@@ -84,7 +84,7 @@ Unsupported media blocks fail before fetch. Text-only input.
 
 ```ts
 import { createExtensionKernel } from "@arnilo/prism";
-import { createDeepSeekProviderPackage, listDeepSeekModels } from "@arnilo/prism-provider-deepseek";
+import { createDeepSeekProviderPackage, listDeepSeekModels } from "@arnilo/prism-providers/deepseek";
 
 const kernel = createExtensionKernel();
 await kernel.load([createDeepSeekProviderPackage({ apiKey: "fake-deepseek-key" })]);

package/docs/providers/google.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-provider-google` is the first-party Gemini `generateContent` / `streamGenerateContent` provider for Prism (`POST /v1beta/models/{model}:streamGenerateContent?alt=sse`). Setup is side-effect-free: no network, env scan, or keychain lookup during import/setup. Uses native `fetch` + SSE — no `@google/genai` runtime dependency.
+`@arnilo/prism-providers/google` is the first-party Gemini `generateContent` / `streamGenerateContent` provider for Prism (`POST /v1beta/models/{model}:streamGenerateContent?alt=sse`). Setup is side-effect-free: no network, env scan, or keychain lookup during import/setup. Uses native `fetch` + SSE — no `@google/genai` runtime dependency.
 
 ## When to use it
 
@@ -18,7 +18,7 @@ import {
   createGoogleGenerateContentProvider,
   listGoogleModels,
   defineGoogleModel,
-} from "@arnilo/prism-provider-google";
+} from "@arnilo/prism-providers/google";
 
 createGoogleProviderPackage(options?: GoogleProviderPackageOptions): ProviderPackage
 createGoogleGenerateContentProvider(options?): AIProvider
@@ -57,7 +57,7 @@ Featured offline aliases include `gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-2
 ## Implementation example
 
 ```ts
-import { createGoogleProviderPackage, listGoogleModels } from "@arnilo/prism-provider-google";
+import { createGoogleProviderPackage, listGoogleModels } from "@arnilo/prism-providers/google";
 
 api.registerProviderPackage(createGoogleProviderPackage({ apiKey: hostKey }));
 
@@ -86,4 +86,4 @@ api.registerProviderPackage(createGoogleProviderPackage({ apiKey: hostKey, model
 - [Provider packages](../provider-packages.md): package setup + discovery contract.
 - [Thinking and reasoning](../thinking-and-reasoning.md): portable thinking helpers.
 - [Provider conformance](../provider-conformance.md): network-free assertions.
-- Package README: [`packages/provider-google/README.md`](../../packages/provider-google/README.md)
+- Package README: [`@arnilo/prism-providers` family README](../../packages/prism-providers/README.md)

package/docs/providers/kimi.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-provider-kimi` provides two distinct, side-effect-free routes:
+`@arnilo/prism-providers/kimi` provides two distinct, side-effect-free routes:
 
 1. **Kimi For Coding** (default) — Anthropic-compatible `POST /messages` on
    `https://api.kimi.com/coding` with `User-Agent: KimiCLI/1.5` (unless overridden).
@@ -33,7 +33,7 @@ import {
   createKimiProviderPackage,
   listKimiModels,
   defineKimiModel,
-} from "@arnilo/prism-provider-kimi";
+} from "@arnilo/prism-providers/kimi";
 
 createKimiProviderPackage(options: KimiProviderPackageOptions): ProviderPackage
 listKimiModels(options?: ListKimiModelsOptions): Promise<ModelConfig[]>
@@ -137,7 +137,7 @@ import { createExtensionKernel } from "@arnilo/prism";
 import {
   createKimiProviderPackage,
   listKimiModels,
-} from "@arnilo/prism-provider-kimi";
+} from "@arnilo/prism-providers/kimi";
 
 const kernel = createExtensionKernel();
 await kernel.load([

package/docs/providers/neuralwatt.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-provider-neuralwatt` provides explicit, side-effect-free setup for the
+`@arnilo/prism-providers/neuralwatt` provides explicit, side-effect-free setup for the
 NeuralWatt OpenAI-compatible Chat Completions provider using Prism's OpenAI-compatible
 route with NeuralWatt-specific reasoning/template escape hatches, SSE comment tolerance,
 and implicit prefix caching.
@@ -34,7 +34,7 @@ import {
   neuralWattEventsWithTelemetry,
   neuralWattModels,
   parseNeuralWattComment,
-} from "@arnilo/prism-provider-neuralwatt";
+} from "@arnilo/prism-providers/neuralwatt";
 
 createNeuralWattProviderPackage(options: NeuralWattProviderPackageOptions): ProviderPackage
 defineNeuralWattModel(config: NeuralWattModelConfig): ModelConfig
@@ -123,7 +123,7 @@ Example request body (OpenAI-compatible Chat Completions shape):
 
 ```ts
 import { createExtensionKernel } from "@arnilo/prism";
-import { createNeuralWattProviderPackage } from "@arnilo/prism-provider-neuralwatt";
+import { createNeuralWattProviderPackage } from "@arnilo/prism-providers/neuralwatt";
 
 const kernel = createExtensionKernel();
 await kernel.load([createNeuralWattProviderPackage({ apiKey: "fake-neuralwatt-key" })]);
@@ -132,7 +132,7 @@ await kernel.load([createNeuralWattProviderPackage({ apiKey: "fake-neuralwatt-ke
 Override the provider id and models:
 
 ```ts
-import { createNeuralWattProviderPackage, defineNeuralWattModel, neuralWattModels } from "@arnilo/prism-provider-neuralwatt";
+import { createNeuralWattProviderPackage, defineNeuralWattModel, neuralWattModels } from "@arnilo/prism-providers/neuralwatt";
 
 await kernel.load([
   createNeuralWattProviderPackage({ id: "neuralwatt", apiKey: "fake", models: neuralWattModels }),
@@ -142,7 +142,7 @@ await kernel.load([
 Explicit catalog discovery:
 
 ```ts
-import { listNeuralWattModels } from "@arnilo/prism-provider-neuralwatt";
+import { listNeuralWattModels } from "@arnilo/prism-providers/neuralwatt";
 
 const models = await listNeuralWattModels({ apiKey: "fake-neuralwatt-key", fetch });
 await kernel.load([createNeuralWattProviderPackage({ apiKey: "fake", models })]);
@@ -154,7 +154,7 @@ setup and `generate()` never call model discovery implicitly.
 Account quota:
 
 ```ts
-import { getNeuralWattQuota } from "@arnilo/prism-provider-neuralwatt";
+import { getNeuralWattQuota } from "@arnilo/prism-providers/neuralwatt";
 
 const quota = await getNeuralWattQuota({ apiKey: "fake-neuralwatt-key", fetch });
 console.log(quota.usage?.current_month?.energy_kwh, quota.balance?.balance_usd);
@@ -322,7 +322,7 @@ optional and tolerated when absent; malformed comments yield no telemetry event
 and never crash the stream.
 
 ```ts
-import { neuralWattEventsWithTelemetry } from "@arnilo/prism-provider-neuralwatt";
+import { neuralWattEventsWithTelemetry } from "@arnilo/prism-providers/neuralwatt";
 
 for await (const event of neuralWattEventsWithTelemetry(response.body)) {
   if (event.type === "neuralwatt:telemetry") {
@@ -354,7 +354,7 @@ provider. Classification is O(1) over status/headers/body and makes no extra
 provider calls.
 
 ```ts
-import { classifyNeuralWattError } from "@arnilo/prism-provider-neuralwatt";
+import { classifyNeuralWattError } from "@arnilo/prism-providers/neuralwatt";
 
 const decision = classifyNeuralWattError({ status: 429, headers: { "retry-after": "1" }, body: { error: { code: "concurrent_budget_exceeded", retry_after: 1 } } });
 // { retryable: true, code: 429, retryAfterMs: 1000, errorCode: "concurrent_budget_exceeded", strategy: undefined }

package/docs/providers/ollama.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-provider-ollama` is a side-effect-free adapter for Ollama — both
+`@arnilo/prism-providers/ollama` is a side-effect-free adapter for Ollama — both
 **Ollama Cloud** (`https://ollama.com`) and a **local** `ollama serve`
 (`http://localhost:11434`) — over the OpenAI-compatible
 `POST {base}/chat/completions` endpoint.
@@ -38,7 +38,7 @@ import {
   listOllamaModels,
   defineOllamaModel,
   ollamaBaseUrl,
-} from "@arnilo/prism-provider-ollama";
+} from "@arnilo/prism-providers/ollama";
 
 createOllamaProviderPackage(options: OllamaProviderPackageOptions): ProviderPackage
 createOllamaProvider(options?: OllamaProviderOptions): AIProvider
@@ -106,7 +106,7 @@ import { createExtensionKernel } from "@arnilo/prism";
 import {
   createOllamaProviderPackage,
   listOllamaModels,
-} from "@arnilo/prism-provider-ollama";
+} from "@arnilo/prism-providers/ollama";
 
 const kernel = createExtensionKernel();
 

package/docs/providers/openai-compatible.md

@@ -137,7 +137,7 @@ const provider = createOpenAICompatibleProvider({
 });
 ```
 
-- Cache behavior is intentionally minimal: this Chat Completions adapter sends no `prompt_cache_key`, `prompt_cache_retention`, or `cache_control` fields. Endpoints that cache implicitly do so automatically; hosts needing OpenAI `prompt_cache_key`/`prompt_cache_retention` should use the [`@arnilo/prism-provider-openai`](openai.md) Responses package. The adapter still normalizes cache usage from `prompt_tokens_details.cached_tokens` (and `prompt_cache_hit_tokens`) into `Usage.cacheReadTokens`.
+- Cache behavior is intentionally minimal: this Chat Completions adapter sends no `prompt_cache_key`, `prompt_cache_retention`, or `cache_control` fields. Endpoints that cache implicitly do so automatically; hosts needing OpenAI `prompt_cache_key`/`prompt_cache_retention` should use the [`@arnilo/prism-providers/openai`](openai.md) Responses package. The adapter still normalizes cache usage from `prompt_tokens_details.cached_tokens` (and `prompt_cache_hit_tokens`) into `Usage.cacheReadTokens`.
 
 ## Security and performance notes
 

package/docs/providers/openai.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-provider-openai` provides explicit, side-effect-free setup for the OpenAI
+`@arnilo/prism-providers/openai` provides explicit, side-effect-free setup for the OpenAI
 Responses API (`createOpenAIResponsesProvider`) and OpenAI Codex
 subscription Responses (`createOpenAICodexProvider`), plus a Codex OAuth provider
 implementing RFC 7636 PKCE browser/device-code login.
@@ -24,7 +24,7 @@ credential discovery, or real-network tests.
 ## Inputs / request
 
 ```ts
-import { createOpenAIProviderPackage } from "@arnilo/prism-provider-openai";
+import { createOpenAIProviderPackage } from "@arnilo/prism-providers/openai";
 
 createOpenAIProviderPackage(options: OpenAIProviderPackageOptions): ProviderPackage
 ```
@@ -81,7 +81,7 @@ Responses request body (Codex subscription shape, abbreviated):
 Realtime session (OpenAI session creation, abbreviated):
 
 ```ts
-import { createOpenAIRealtimeSession } from "@arnilo/prism-provider-openai";
+import { createOpenAIRealtimeSession } from "@arnilo/prism-providers/openai";
 
 const session = createOpenAIRealtimeSession({
   model: { provider: "openai", model: "gpt-realtime-2.1" },
@@ -103,7 +103,7 @@ https://auth.openai.com/authorize?response_type=code&client_id=...&code_challeng
 
 ```ts
 import { createExtensionKernel, createEnvCredentialResolver } from "@arnilo/prism";
-import { createOpenAIProviderPackage, listOpenAIModels } from "@arnilo/prism-provider-openai";
+import { createOpenAIProviderPackage, listOpenAIModels } from "@arnilo/prism-providers/openai";
 
 const apiKey = createEnvCredentialResolver({ OPENAI_API_KEY: "fake" }, { openai: "OPENAI_API_KEY" });
 const models = await listOpenAIModels({ apiKey }); // caller-gated; never runs during setup
@@ -116,7 +116,7 @@ await kernel.load([
 OAuth login (caller-supplied callbacks, mocked in tests):
 
 ```ts
-import { createOpenAICodexOAuthProvider, createPkceVerifier, computeS256Challenge } from "@arnilo/prism-provider-openai";
+import { createOpenAICodexOAuthProvider, createPkceVerifier, computeS256Challenge } from "@arnilo/prism-providers/openai";
 
 const oauth = createOpenAICodexOAuthProvider({
   redirectUri: "http://localhost:1455/auth/callback",

package/docs/providers/opencode-go.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-provider-opencode-go` provides explicit, side-effect-free setup for
+`@arnilo/prism-providers/opencode-go` provides explicit, side-effect-free setup for
 [OpenCode Go](https://opencode.ai/docs/go/) — a low-cost subscription gateway for
 open coding models. The package dual-routes by `ModelConfig.compat.route`:
 
@@ -36,7 +36,7 @@ real-network tests.
 import {
   createOpenCodeGoProviderPackage,
   listOpenCodeGoModels,
-} from "@arnilo/prism-provider-opencode-go";
+} from "@arnilo/prism-providers/opencode-go";
 
 createOpenCodeGoProviderPackage(options: OpenCodeGoProviderPackageOptions): ProviderPackage
 ```
@@ -106,7 +106,7 @@ import {
   createOpenCodeGoProviderPackage,
   listOpenCodeGoModels,
   openCodeGoModels,
-} from "@arnilo/prism-provider-opencode-go";
+} from "@arnilo/prism-providers/opencode-go";
 
 const kernel = createExtensionKernel();
 await kernel.load([createOpenCodeGoProviderPackage({ apiKey: process.env.OPENCODE_API_KEY })]);
@@ -154,7 +154,7 @@ credential-gated probe:
 
 ```sh
 PRISM_LIVE_PROVIDER_TESTS=1 OPENCODE_API_KEY=... \
-  npm run test --workspace=@arnilo/prism-provider-opencode-go
+  npm run test --workspace=@arnilo/prism-providers/opencode-go
 ```
 
 `live_json_schema_structured_output_succeeds_<model>` must pass for a model

package/docs/providers/openrouter.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-provider-openrouter` provides explicit, side-effect-free setup for the
+`@arnilo/prism-providers/openrouter` provides explicit, side-effect-free setup for the
 OpenRouter API-key provider with **app-controlled** model registration, routing
 passthrough, official `reasoning` controls, and Anthropic-style `cache_control`
 (plus sticky `session_id` routing).
@@ -29,7 +29,7 @@ import {
   createOpenRouterProviderPackage,
   defineOpenRouterModel,
   listOpenRouterModels,
-} from "@arnilo/prism-provider-openrouter";
+} from "@arnilo/prism-providers/openrouter";
 
 createOpenRouterProviderPackage(options: OpenRouterProviderPackageOptions): ProviderPackage
 defineOpenRouterModel(config: OpenRouterModelConfig): ModelConfig
@@ -83,7 +83,7 @@ import {
   createOpenRouterProviderPackage,
   defineOpenRouterModel,
   listOpenRouterModels,
-} from "@arnilo/prism-provider-openrouter";
+} from "@arnilo/prism-providers/openrouter";
 
 // App-controlled registration (default — no fetch):
 const sonnet = defineOpenRouterModel({

package/docs/providers/vertex.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-provider-vertex` registers a Vertex AI OpenAPI-compatible Chat Completions provider authenticated with host ADC / workload identity tokens. It is intentionally separate from `@arnilo/prism-provider-google` (consumer Gemini API keys).
+`@arnilo/prism-providers/vertex` registers a Vertex AI OpenAPI-compatible Chat Completions provider authenticated with host ADC / workload identity tokens. It is intentionally separate from `@arnilo/prism-providers/google` (consumer Gemini API keys).
 
 ## When to use it
 
@@ -11,7 +11,7 @@ Use it for GCP enterprise Vertex deployments with Application Default Credential
 ## Inputs / request
 
 ```ts
-import { createVertexProviderPackage } from "@arnilo/prism-provider-vertex";
+import { createVertexProviderPackage } from "@arnilo/prism-providers/vertex";
 
 createVertexProviderPackage({
   projectId: "my-gcp-project",
@@ -53,14 +53,14 @@ const provider = createVertexProvider({
 
 ## Extension and configuration notes
 
-`@arnilo/prism-provider-google` remains API-key Gemini (`generativelanguage.googleapis.com`) and must not register Vertex OAuth/ADC. Load this package explicitly for Vertex.
+`@arnilo/prism-providers/google` remains API-key Gemini (`generativelanguage.googleapis.com`) and must not register Vertex OAuth/ADC. Load this package explicitly for Vertex.
 
 ## Security and performance notes
 
 - No Google Cloud SDK dependency in the package.
 - Custom/private endpoint hosts are preserved.
 - Tokens redacted from errors; no import-time credential prefetch — the credential is resolved exactly once per request (a rotating `CredentialValueSource` is never consumed twice; the same resolved token drives the wrapper check and the inner auth header).
-- Conformance-proven (Task 6): package `setup()` performs zero fetch and zero credential resolution; an already-aborted signal fails fast; a truncated SSE stream (no `data: [DONE]`) ends in an `error` event; native Vertex cached-content lifecycle is intentionally unsupported on the OpenAI-compatible route — no cache wire fields are emitted even when the request carries Prism cache hints (use `@arnilo/prism-provider-google`'s `extra.cachedContent` on that package, or manage cache resources host-side).
+- Conformance-proven (Task 6): package `setup()` performs zero fetch and zero credential resolution; an already-aborted signal fails fast; a truncated SSE stream (no `data: [DONE]`) ends in an `error` event; native Vertex cached-content lifecycle is intentionally unsupported on the OpenAI-compatible route — no cache wire fields are emitted even when the request carries Prism cache hints (use `@arnilo/prism-providers/google`'s `extra.cachedContent` on that package, or manage cache resources host-side).
 - Pair with model-router residency allow-lists on `location`.
 
 ## Related APIs
@@ -69,4 +69,4 @@ const provider = createVertexProvider({
 - [OpenAI-compatible provider](openai-compatible.md)
 - [Provider packages](../provider-packages.md)
 - [Model routing](../model-routing.md)
-- Package README: [`@arnilo/prism-provider-vertex`](../../packages/provider-vertex/README.md)
+- Package README: [`@arnilo/prism-providers` family README](../../packages/prism-providers/README.md)

package/docs/providers/xai.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-provider-xai` provides explicit, side-effect-free setup for the
+`@arnilo/prism-providers/xai` provides explicit, side-effect-free setup for the
 xAI Grok Chat Completions API (`POST https://api.x.ai/v1/chat/completions`)
 with implicit prefix caching via a sanitized `x-grok-conv-id` header, reasoning
 replay, and host-invoked SuperGrok / X Premium OAuth.
@@ -25,7 +25,7 @@ import {
   createXaiOAuthProvider,
   createXaiProviderPackage,
   listXaiModels,
-} from "@arnilo/prism-provider-xai";
+} from "@arnilo/prism-providers/xai";
 
 createXaiProviderPackage(options: XaiProviderPackageOptions): ProviderPackage
 createXaiOAuthProvider(options?: XaiOAuthOptions): OAuthProvider
@@ -84,7 +84,7 @@ Header: `x-grok-conv-id: sess-1`.
 
 ```ts
 import { createExtensionKernel, refreshOAuthCredential } from "@arnilo/prism";
-import { createXaiOAuthProvider, createXaiProviderPackage } from "@arnilo/prism-provider-xai";
+import { createXaiOAuthProvider, createXaiProviderPackage } from "@arnilo/prism-providers/xai";
 
 const kernel = createExtensionKernel();
 await kernel.load([createXaiProviderPackage({ apiKey: "fake-xai-key" })]);

package/docs/providers/zai.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-provider-zai` provides explicit, side-effect-free setup for the Z.AI
+`@arnilo/prism-providers/zai` provides explicit, side-effect-free setup for the Z.AI
 GLM Chat Completions API (`POST /chat/completions`) with official deep-thinking,
 reasoning-effort, and tool-stream request fields.
 
@@ -25,7 +25,7 @@ import {
   createZaiProviderPackage,
   defineZaiModel,
   listZaiModels,
-} from "@arnilo/prism-provider-zai";
+} from "@arnilo/prism-providers/zai";
 
 createZaiProviderPackage(options: ZaiProviderPackageOptions): ProviderPackage
 defineZaiModel(config: ZaiModelConfig): ModelConfig
@@ -87,7 +87,7 @@ Example request body (official Chat Completions shape):
 
 ```ts
 import { createExtensionKernel } from "@arnilo/prism";
-import { createZaiProviderPackage, listZaiModels } from "@arnilo/prism-provider-zai";
+import { createZaiProviderPackage, listZaiModels } from "@arnilo/prism-providers/zai";
 
 const kernel = createExtensionKernel();
 await kernel.load([createZaiProviderPackage({ apiKey: "fake-zai-key" })]);

package/docs/public-contracts.md

@@ -10,7 +10,7 @@ Current contract groups:
 - Content/messages: `ContentBlock`, `TextContent`, `ImageContent`, `ThinkingContent`, `ToolCallDeltaContent`, `ToolCallContent`, `ToolResultContent`, `Message`
 - Providers/models/auth: `ModelConfig`, `ModelCapabilities`, `ModelLimits`, `ModelCost`, `ModelCacheCapabilities`, `PromptCacheKind`, `Usage`, `CacheRetention`, `PromptCacheMode`, `PromptCacheBreakpoint`, `PromptCacheHints`, `ProviderRequestOptions`, `ProviderRequest`, `ProviderEvent`, `AIProvider`, `ProviderPackage`, `ProviderPackageAPI`, `ProviderPackageDocs`, `AuthMethod`, `ApiKeyAuthMethod`, `OAuthAuthMethod`, `CustomAuthMethod`, `OAuthLoginCallbacks`, `OAuthCredentials`, `OAuthProvider`, `CredentialResolverSource`, `OAuthCredentialStore`, `ProviderRequestPolicy`, `ProviderRequestPolicyContext`, `ProviderRequestPolicyResult`, `SystemPromptContribution`, `SystemPromptMode`, `SystemPromptSource`, `SystemPromptConfig`
 - Agents/sessions: `AgentConfig`, `AgentDefinition`, `Agent`, `AgentSessionConfig`, `AgentSessionForkOptions`, `AgentSessionCloneOptions`, `AgentSession`, `SubscribeOptions`, `SubscriberOverflowPolicy`, `RunOptions`, `AgentEvent`
-- Tools/commands: `ToolDefinition`, `ToolRegistry`, `ToolExecutionContext`, `ToolResult`, `CommandDefinition`, `CommandExecutionContext`, `CommandResult`
+- Tools/commands: `ToolDefinition`, `ToolRegistry`, `ToolExecutionContext`, `ToolResult`, `CommandDefinition`, `CommandExecutionContext`, `CommandDrivers`, `CommandWorkflowRun`, `CommandResult`
 - Input/prompt/context/skills: `InputBuilder`, `InputBuildContext`, `AgentInput`, `DefaultInputBuilder`, `DefaultInputBuildContext`, `InputAttachment`, `PromptInstruction`, `PromptBuilder`, `PromptBuildRequest`, `ContextBlock`, `ContextProvider`, `ContextResolutionContext`, `Skill`, `SkillRegistry`
 - Extensions/middleware: `ExtensionLifecycleEventName`, `ExtensionEvent`, `Extension`, `ExtensionAPI`, `MiddlewareHookName`, `Middleware`, `MiddlewareNext`, `MiddlewareRegistry`
 - Configuration/manifests: `ConfigProvider`, `ConfigLayer`, `ConfigLoadContext`, `PrismManifest`, `ManifestContributionDeclaration`, `ManifestResourceDeclaration`, `ManifestContributionKind`

package/docs/rag.md

@@ -2,7 +2,7 @@
 
 ## What it does
 
-`@arnilo/prism-rag` is an optional package for deterministic text/Markdown chunking (with ATX heading-stack metadata), bounded embedding/vector indexing with embedder-identity drift guards, atomic scoped source replacement/deletion with content-hash skip and generation visibility, hybrid vector+lexical retrieval with reciprocal-rank fusion (one embed / one RRF / one rerank across one or many exact scopes), focused text/Markdown/HTML/PDF parsing, bounded reranking (host seam plus a TEI REST adapter), ingestion status, attributable citations, content-trust metadata, and explicit `ContextProvider` injection. It reuses `Embedder` and `VectorStore` from `@arnilo/prism-memory`; Prism core input assembly is unchanged.
+The `@arnilo/prism-memory/rag` subpath is an optional surface for deterministic text/Markdown chunking (with ATX heading-stack metadata), bounded embedding/vector indexing with embedder-identity drift guards, atomic scoped source replacement/deletion with content-hash skip and generation visibility, hybrid vector+lexical retrieval with reciprocal-rank fusion (one embed / one RRF / one rerank across one or many exact scopes), focused text/Markdown/HTML/PDF parsing, bounded reranking (host seam plus a TEI REST adapter), ingestion status, attributable citations, content-trust metadata, and explicit `ContextProvider` injection. It reuses `Embedder` and `VectorStore` from the memory root entry; Prism core input assembly is unchanged.
 
 ## When to use it
 
@@ -27,7 +27,7 @@ Document lifecycle:
 | `replaceSource({ sourceId, chunks, store, scope, ... })` | Atomically replaces one source after all bounded embedding succeeds; the store must implement scoped `getBySource()` and `transaction()`. |
 | `deleteSource({ sourceId, store, scope })` | Deletes only matching IDs under exact tenant/resource/corpus scope. |
 | `replaceDocument({ uri, loader, parser, store, scope, ... })` | Loads through a host seam, parses, chunks, and atomically replaces. `sourceId` is required unless loader supplies one. |
-| `DocumentLoader` / `Parser` | Small host-replaceable seams. Root and `@arnilo/prism-rag/loaders` / `@arnilo/prism-rag/parsers` export reference adapters. |
+| `DocumentLoader` / `Parser` | Small host-replaceable seams. `@arnilo/prism-memory/rag/loaders` and `/rag/parsers` export reference adapters. |
 | `textParser` / `markdownParser` / `htmlParser` / `pdfParser` | UTF-8 text, Markdown, script/style-stripping HTML, and uncompressed-text PDF parsers. |
 
 Index/retrieve:
@@ -84,7 +84,7 @@ Default/hard ceilings include 1,000/16,384 chunk characters, 100/4,096 overlap,
 ```ts
 import { createAgent, createMockProvider, providerDone, providerTextDelta } from "@arnilo/prism";
 import { createHashEmbedder, createMemoryVectorStore } from "@arnilo/prism-memory";
-import { chunkMarkdown, createMemoryIngestionStatusStore, createRagContextProvider, indexChunks, listIngestionStatus, retrieveContext } from "@arnilo/prism-rag";
+import { chunkMarkdown, createMemoryIngestionStatusStore, createRagContextProvider, indexChunks, listIngestionStatus, retrieveContext } from "@arnilo/prism-memory/rag";
 
 const embedder = createHashEmbedder(); // deterministic demo/test helper, not production semantic quality
 const store = createMemoryVectorStore();
@@ -118,7 +118,7 @@ console.log(found.text, await agent.createSession().run("How do approvals work?"
 Content-hash skip and hash validation:
 
 ```ts
-import { isValidContentHash } from "@arnilo/prism-rag";
+import { isValidContentHash } from "@arnilo/prism-memory/rag";
 
 const digest = "ab12..."; // host-computed SHA-256 hex of the document
 if (!isValidContentHash(digest)) throw new Error("invalid digest");
@@ -129,7 +129,7 @@ Hybrid retrieval, TEI reranking, and telemetry:
 
 ```ts
 import { createRagTelemetry } from "@arnilo/prism-observability-opentelemetry";
-import { createTeiReranker } from "@arnilo/prism-rag";
+import { createTeiReranker } from "@arnilo/prism-memory/rag";
 
 const telemetry = createRagTelemetry({ tracer, meter }); // @opentelemetry/api instruments
 const org = { tenantId: "t1", resourceId: "docs", corpusId: "org" };