@warlock.js/ai-bedrock 4.1.1

package/esm/utils/to-bedrock-tools.mjs

@@ -0,0 +1,41 @@
+import { extractJsonSchema } from "@warlock.js/ai";
+
+//#region ../../@warlock.js/ai-bedrock/src/utils/to-bedrock-tools.ts
+/**
+* Convert vendor-neutral `ToolConfig[]` into Bedrock Converse's
+* `ToolConfiguration`. Each tool becomes a `toolSpec` with a JSON
+* `inputSchema`. Bedrock requires the schema root to be an object —
+* a non-object extraction degrades to a parameterless object schema
+* so registration never fails.
+*
+* Returns `undefined` when there are no tools so the caller can omit
+* `toolConfig` from the request entirely (Bedrock rejects an empty
+* `tools` array).
+*
+* @example
+* const toolConfig = toBedrockToolConfig([weatherTool]);
+* await client.send(new ConverseCommand({ modelId, messages, toolConfig }));
+*/
+function toBedrockToolConfig(tools) {
+	if (!tools || tools.length === 0) return;
+	return { tools: tools.map((tool) => ({ toolSpec: {
+		name: tool.name,
+		description: tool.description,
+		inputSchema: { json: toJsonSchema(tool.input) }
+	} })) };
+}
+/**
+* Resolve a tool's input schema to a JSON-Schema object. Bedrock's
+* `ToolInputSchema.json` requires an object root; anything else (or a
+* failed extraction) degrades to a parameterless object so the tool
+* still registers.
+*/
+function toJsonSchema(input) {
+	const schema = extractJsonSchema(input);
+	if (schema && schema.type === "object") return schema;
+	return { type: "object" };
+}
+
+//#endregion
+export { toBedrockToolConfig };
+//# sourceMappingURL=to-bedrock-tools.mjs.map

package/esm/utils/to-bedrock-tools.mjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"to-bedrock-tools.mjs","names":[],"sources":["../../../../../../@warlock.js/ai-bedrock/src/utils/to-bedrock-tools.ts"],"sourcesContent":["import { extractJsonSchema, type ToolConfig } from \"@warlock.js/ai\";\nimport type { Tool, ToolConfiguration, ToolInputSchema } from \"@aws-sdk/client-bedrock-runtime\";\n\n/**\n * Convert vendor-neutral `ToolConfig[]` into Bedrock Converse's\n * `ToolConfiguration`. Each tool becomes a `toolSpec` with a JSON\n * `inputSchema`. Bedrock requires the schema root to be an object —\n * a non-object extraction degrades to a parameterless object schema\n * so registration never fails.\n *\n * Returns `undefined` when there are no tools so the caller can omit\n * `toolConfig` from the request entirely (Bedrock rejects an empty\n * `tools` array).\n *\n * @example\n * const toolConfig = toBedrockToolConfig([weatherTool]);\n * await client.send(new ConverseCommand({ modelId, messages, toolConfig }));\n */\nexport function toBedrockToolConfig(\n  tools: ToolConfig<unknown, unknown>[] | undefined,\n): ToolConfiguration | undefined {\n  if (!tools || tools.length === 0) {\n    return undefined;\n  }\n\n  return {\n    tools: tools.map(\n      (tool): Tool => ({\n        toolSpec: {\n          name: tool.name,\n          description: tool.description,\n          inputSchema: { json: toJsonSchema(tool.input) } as ToolInputSchema,\n        },\n      }),\n    ),\n  };\n}\n\n/**\n * Resolve a tool's input schema to a JSON-Schema object. Bedrock's\n * `ToolInputSchema.json` requires an object root; anything else (or a\n * failed extraction) degrades to a parameterless object so the tool\n * still registers.\n */\nfunction toJsonSchema(input: ToolConfig<unknown, unknown>[\"input\"]): Record<string, unknown> {\n  const schema = extractJsonSchema(input);\n\n  if (schema && schema.type === \"object\") {\n    return schema;\n  }\n\n  return { type: \"object\" };\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;AAkBA,SAAgB,oBACd,OAC+B;CAC/B,IAAI,CAAC,SAAS,MAAM,WAAW,GAC7B;CAGF,OAAO,EACL,OAAO,MAAM,KACV,UAAgB,EACf,UAAU;EACR,MAAM,KAAK;EACX,aAAa,KAAK;EAClB,aAAa,EAAE,MAAM,aAAa,KAAK,KAAK,EAAE;CAChD,EACF,EACF,EACF;AACF;;;;;;;AAQA,SAAS,aAAa,OAAuE;CAC3F,MAAM,SAAS,kBAAkB,KAAK;CAEtC,IAAI,UAAU,OAAO,SAAS,UAC5B,OAAO;CAGT,OAAO,EAAE,MAAM,SAAS;AAC1B"}

package/esm/utils/wrap-bedrock-error.mjs

@@ -0,0 +1,121 @@
+import { AIError, ContextLengthExceededError, InvalidRequestError, ProviderAuthError, ProviderError, ProviderRateLimitError, ProviderTimeoutError, QuotaExceededError } from "@warlock.js/ai";
+
+//#region ../../@warlock.js/ai-bedrock/src/utils/wrap-bedrock-error.ts
+const TIMEOUT_NAMES = new Set([
+	"ModelTimeoutException",
+	"TimeoutError",
+	"RequestTimeout",
+	"RequestTimeoutException"
+]);
+/**
+* Wrap any thrown value caught inside the Bedrock adapter into the
+* appropriate `@warlock.js/ai` `AIError` subclass.
+*
+* **Dispatch strategy.** AWS errors carry no provider machine `code`;
+* the stable identifier is the Smithy exception `name`. Dispatch keys
+* on `name`, falls back to `$metadata.httpStatusCode` when the name is
+* missing (flattened/proxied errors). `ValidationException` is split:
+* the "input is too long / exceeds context window" phrasing maps to
+* `ContextLengthExceededError`, everything else to
+* `InvalidRequestError`.
+*
+* `AIError` instances pass through unchanged so `catch/throw wrap(e)`
+* pipelines never double-wrap.
+*
+* @example
+* try {
+*   return await this.client.send(new ConverseCommand(...));
+* } catch (thrown) {
+*   throw wrapBedrockError(thrown);
+* }
+*/
+function wrapBedrockError(thrown) {
+	if (thrown instanceof AIError) return thrown;
+	const shape = toShape(thrown);
+	const context = buildContext(shape);
+	const message = shape.message ?? (thrown instanceof Error ? thrown.message : String(thrown));
+	if (isTimeout(shape)) return new ProviderTimeoutError(message, {
+		cause: thrown,
+		context
+	});
+	if (shape.name === "AccessDeniedException" || shape.httpStatusCode === 403) return new ProviderAuthError(message, {
+		cause: thrown,
+		context
+	});
+	if (shape.httpStatusCode === 401) return new ProviderAuthError(message, {
+		cause: thrown,
+		context
+	});
+	if (shape.name === "ServiceQuotaExceededException") return new QuotaExceededError(message, {
+		cause: thrown,
+		context
+	});
+	if (shape.name === "ThrottlingException" || shape.httpStatusCode === 429) return new ProviderRateLimitError(message, {
+		cause: thrown,
+		context
+	});
+	if (shape.name === "ValidationException") {
+		if (/too long|context window|maximum context|exceeds the maximum/i.test(message)) return new ContextLengthExceededError(message, {
+			cause: thrown,
+			context
+		});
+		return new InvalidRequestError(message, {
+			cause: thrown,
+			context
+		});
+	}
+	if (shape.name === "ResourceNotFoundException" || shape.name === "ConflictException" || isClientStatus(shape.httpStatusCode)) return new InvalidRequestError(message, {
+		cause: thrown,
+		context
+	});
+	return new ProviderError(message, {
+		cause: thrown,
+		context
+	});
+}
+/**
+* Read the raw error shape without depending on `instanceof`. AWS
+* exceptions expose `$metadata`; plain/proxied errors may carry
+* `status` / `code` instead.
+*/
+function toShape(thrown) {
+	if (typeof thrown !== "object" || thrown === null) return {};
+	const raw = thrown;
+	const metadata = raw.$metadata;
+	return {
+		name: typeof raw.name === "string" ? raw.name : void 0,
+		message: typeof raw.message === "string" ? raw.message : void 0,
+		httpStatusCode: metadata && typeof metadata.httpStatusCode === "number" ? metadata.httpStatusCode : typeof raw.status === "number" ? raw.status : void 0,
+		requestId: metadata && typeof metadata.requestId === "string" ? metadata.requestId : void 0,
+		code: typeof raw.code === "string" ? raw.code : void 0
+	};
+}
+/**
+* Decide whether the error is a timeout. Bedrock surfaces
+* `ModelTimeoutException`; the AWS transport layer surfaces
+* `TimeoutError` / `ETIMEDOUT` / `ECONNABORTED`.
+*/
+function isTimeout(shape) {
+	if (shape.name && TIMEOUT_NAMES.has(shape.name)) return true;
+	return shape.code === "ETIMEDOUT" || shape.code === "ECONNABORTED";
+}
+/** True for HTTP 4xx — a client-side request problem, not a server fault. */
+function isClientStatus(status) {
+	return typeof status === "number" && status >= 400 && status < 500;
+}
+/**
+* Attach the raw diagnostic fields to `error.context`. The Smithy
+* exception `name` is the closest thing Bedrock has to a stable error
+* code, so it lands on `context.code`.
+*/
+function buildContext(shape) {
+	const context = {};
+	if (shape.httpStatusCode !== void 0) context.status = shape.httpStatusCode;
+	if (shape.name) context.code = shape.name;
+	if (shape.requestId) context.requestId = shape.requestId;
+	return context;
+}
+
+//#endregion
+export { wrapBedrockError };
+//# sourceMappingURL=wrap-bedrock-error.mjs.map

package/esm/utils/wrap-bedrock-error.mjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"wrap-bedrock-error.mjs","names":[],"sources":["../../../../../../@warlock.js/ai-bedrock/src/utils/wrap-bedrock-error.ts"],"sourcesContent":["import {\n  AIError,\n  ContextLengthExceededError,\n  InvalidRequestError,\n  ProviderAuthError,\n  ProviderError,\n  ProviderRateLimitError,\n  ProviderTimeoutError,\n  QuotaExceededError,\n} from \"@warlock.js/ai\";\n\n/**\n * Raw-error fields the wrapper reads off an AWS SDK exception. Every\n * Bedrock error is a Smithy `__BaseException` with a stable `name`\n * (`\"ThrottlingException\"`, `\"ValidationException\"`, …) and a\n * `$metadata` carrying `httpStatusCode` + `requestId`. We duck-type\n * because retries and proxies sometimes flatten the prototype chain.\n */\ntype BedrockErrorShape = {\n  name?: string;\n  message?: string;\n  httpStatusCode?: number;\n  requestId?: string;\n  code?: string;\n};\n\nconst TIMEOUT_NAMES = new Set([\n  \"ModelTimeoutException\",\n  \"TimeoutError\",\n  \"RequestTimeout\",\n  \"RequestTimeoutException\",\n]);\n\n/**\n * Wrap any thrown value caught inside the Bedrock adapter into the\n * appropriate `@warlock.js/ai` `AIError` subclass.\n *\n * **Dispatch strategy.** AWS errors carry no provider machine `code`;\n * the stable identifier is the Smithy exception `name`. Dispatch keys\n * on `name`, falls back to `$metadata.httpStatusCode` when the name is\n * missing (flattened/proxied errors). `ValidationException` is split:\n * the \"input is too long / exceeds context window\" phrasing maps to\n * `ContextLengthExceededError`, everything else to\n * `InvalidRequestError`.\n *\n * `AIError` instances pass through unchanged so `catch/throw wrap(e)`\n * pipelines never double-wrap.\n *\n * @example\n * try {\n *   return await this.client.send(new ConverseCommand(...));\n * } catch (thrown) {\n *   throw wrapBedrockError(thrown);\n * }\n */\nexport function wrapBedrockError(thrown: unknown): AIError {\n  if (thrown instanceof AIError) {\n    return thrown;\n  }\n\n  const shape = toShape(thrown);\n  const context = buildContext(shape);\n  const message = shape.message ?? (thrown instanceof Error ? thrown.message : String(thrown));\n\n  if (isTimeout(shape)) {\n    return new ProviderTimeoutError(message, { cause: thrown, context });\n  }\n\n  if (shape.name === \"AccessDeniedException\" || shape.httpStatusCode === 403) {\n    return new ProviderAuthError(message, { cause: thrown, context });\n  }\n\n  if (shape.httpStatusCode === 401) {\n    return new ProviderAuthError(message, { cause: thrown, context });\n  }\n\n  if (shape.name === \"ServiceQuotaExceededException\") {\n    return new QuotaExceededError(message, { cause: thrown, context });\n  }\n\n  if (shape.name === \"ThrottlingException\" || shape.httpStatusCode === 429) {\n    return new ProviderRateLimitError(message, { cause: thrown, context });\n  }\n\n  if (shape.name === \"ValidationException\") {\n    if (/too long|context window|maximum context|exceeds the maximum/i.test(message)) {\n      return new ContextLengthExceededError(message, { cause: thrown, context });\n    }\n\n    return new InvalidRequestError(message, { cause: thrown, context });\n  }\n\n  if (\n    shape.name === \"ResourceNotFoundException\" ||\n    shape.name === \"ConflictException\" ||\n    isClientStatus(shape.httpStatusCode)\n  ) {\n    return new InvalidRequestError(message, { cause: thrown, context });\n  }\n\n  return new ProviderError(message, { cause: thrown, context });\n}\n\n/**\n * Read the raw error shape without depending on `instanceof`. AWS\n * exceptions expose `$metadata`; plain/proxied errors may carry\n * `status` / `code` instead.\n */\nfunction toShape(thrown: unknown): BedrockErrorShape {\n  if (typeof thrown !== \"object\" || thrown === null) {\n    return {};\n  }\n\n  const raw = thrown as Record<string, unknown>;\n  const metadata = raw.$metadata as { httpStatusCode?: number; requestId?: string } | undefined;\n\n  return {\n    name: typeof raw.name === \"string\" ? raw.name : undefined,\n    message: typeof raw.message === \"string\" ? raw.message : undefined,\n    httpStatusCode:\n      metadata && typeof metadata.httpStatusCode === \"number\"\n        ? metadata.httpStatusCode\n        : typeof raw.status === \"number\"\n          ? (raw.status as number)\n          : undefined,\n    requestId: metadata && typeof metadata.requestId === \"string\" ? metadata.requestId : undefined,\n    code: typeof raw.code === \"string\" ? raw.code : undefined,\n  };\n}\n\n/**\n * Decide whether the error is a timeout. Bedrock surfaces\n * `ModelTimeoutException`; the AWS transport layer surfaces\n * `TimeoutError` / `ETIMEDOUT` / `ECONNABORTED`.\n */\nfunction isTimeout(shape: BedrockErrorShape): boolean {\n  if (shape.name && TIMEOUT_NAMES.has(shape.name)) {\n    return true;\n  }\n\n  return shape.code === \"ETIMEDOUT\" || shape.code === \"ECONNABORTED\";\n}\n\n/** True for HTTP 4xx — a client-side request problem, not a server fault. */\nfunction isClientStatus(status: number | undefined): boolean {\n  return typeof status === \"number\" && status >= 400 && status < 500;\n}\n\n/**\n * Attach the raw diagnostic fields to `error.context`. The Smithy\n * exception `name` is the closest thing Bedrock has to a stable error\n * code, so it lands on `context.code`.\n */\nfunction buildContext(shape: BedrockErrorShape): Record<string, unknown> {\n  const context: Record<string, unknown> = {};\n\n  if (shape.httpStatusCode !== undefined) {\n    context.status = shape.httpStatusCode;\n  }\n\n  if (shape.name) {\n    context.code = shape.name;\n  }\n\n  if (shape.requestId) {\n    context.requestId = shape.requestId;\n  }\n\n  return context;\n}\n"],"mappings":";;;AA0BA,MAAM,gBAAgB,IAAI,IAAI;CAC5B;CACA;CACA;CACA;AACF,CAAC;;;;;;;;;;;;;;;;;;;;;;;AAwBD,SAAgB,iBAAiB,QAA0B;CACzD,IAAI,kBAAkB,SACpB,OAAO;CAGT,MAAM,QAAQ,QAAQ,MAAM;CAC5B,MAAM,UAAU,aAAa,KAAK;CAClC,MAAM,UAAU,MAAM,YAAY,kBAAkB,QAAQ,OAAO,UAAU,OAAO,MAAM;CAE1F,IAAI,UAAU,KAAK,GACjB,OAAO,IAAI,qBAAqB,SAAS;EAAE,OAAO;EAAQ;CAAQ,CAAC;CAGrE,IAAI,MAAM,SAAS,2BAA2B,MAAM,mBAAmB,KACrE,OAAO,IAAI,kBAAkB,SAAS;EAAE,OAAO;EAAQ;CAAQ,CAAC;CAGlE,IAAI,MAAM,mBAAmB,KAC3B,OAAO,IAAI,kBAAkB,SAAS;EAAE,OAAO;EAAQ;CAAQ,CAAC;CAGlE,IAAI,MAAM,SAAS,iCACjB,OAAO,IAAI,mBAAmB,SAAS;EAAE,OAAO;EAAQ;CAAQ,CAAC;CAGnE,IAAI,MAAM,SAAS,yBAAyB,MAAM,mBAAmB,KACnE,OAAO,IAAI,uBAAuB,SAAS;EAAE,OAAO;EAAQ;CAAQ,CAAC;CAGvE,IAAI,MAAM,SAAS,uBAAuB;EACxC,IAAI,+DAA+D,KAAK,OAAO,GAC7E,OAAO,IAAI,2BAA2B,SAAS;GAAE,OAAO;GAAQ;EAAQ,CAAC;EAG3E,OAAO,IAAI,oBAAoB,SAAS;GAAE,OAAO;GAAQ;EAAQ,CAAC;CACpE;CAEA,IACE,MAAM,SAAS,+BACf,MAAM,SAAS,uBACf,eAAe,MAAM,cAAc,GAEnC,OAAO,IAAI,oBAAoB,SAAS;EAAE,OAAO;EAAQ;CAAQ,CAAC;CAGpE,OAAO,IAAI,cAAc,SAAS;EAAE,OAAO;EAAQ;CAAQ,CAAC;AAC9D;;;;;;AAOA,SAAS,QAAQ,QAAoC;CACnD,IAAI,OAAO,WAAW,YAAY,WAAW,MAC3C,OAAO,CAAC;CAGV,MAAM,MAAM;CACZ,MAAM,WAAW,IAAI;CAErB,OAAO;EACL,MAAM,OAAO,IAAI,SAAS,WAAW,IAAI,OAAO;EAChD,SAAS,OAAO,IAAI,YAAY,WAAW,IAAI,UAAU;EACzD,gBACE,YAAY,OAAO,SAAS,mBAAmB,WAC3C,SAAS,iBACT,OAAO,IAAI,WAAW,WACnB,IAAI,SACL;EACR,WAAW,YAAY,OAAO,SAAS,cAAc,WAAW,SAAS,YAAY;EACrF,MAAM,OAAO,IAAI,SAAS,WAAW,IAAI,OAAO;CAClD;AACF;;;;;;AAOA,SAAS,UAAU,OAAmC;CACpD,IAAI,MAAM,QAAQ,cAAc,IAAI,MAAM,IAAI,GAC5C,OAAO;CAGT,OAAO,MAAM,SAAS,eAAe,MAAM,SAAS;AACtD;;AAGA,SAAS,eAAe,QAAqC;CAC3D,OAAO,OAAO,WAAW,YAAY,UAAU,OAAO,SAAS;AACjE;;;;;;AAOA,SAAS,aAAa,OAAmD;CACvE,MAAM,UAAmC,CAAC;CAE1C,IAAI,MAAM,mBAAmB,QAC3B,QAAQ,SAAS,MAAM;CAGzB,IAAI,MAAM,MACR,QAAQ,OAAO,MAAM;CAGvB,IAAI,MAAM,WACR,QAAQ,YAAY,MAAM;CAG5B,OAAO;AACT"}

package/llms-full.txt

@@ -0,0 +1,153 @@
+# Warlock AI Bedrock — full skills
+
+> Package: `@warlock.js/ai-bedrock`
+
+> Generated artifact. Concatenates every SKILL.md and reference file under `@warlock.js/ai-bedrock/skills/`. Re-run `node scripts/generate-llms.mjs` after any change.
+
+## setup-bedrock  `@warlock.js/ai-bedrock/setup-bedrock/SKILL.md`
+
+---
+name: setup-bedrock
+description: 'Wire @warlock.js/ai-bedrock — new BedrockSDK({region, credentials?, provider?}) for AWS Bedrock Converse API + Titan embeddings. AWS credential chain (no apiKey). Triggers: `BedrockSDK`, `bedrock.model`, `bedrock.embedder`, `bedrock.count`, `BedrockRuntimeClient`; "how do I use AWS Bedrock", "wire Claude/Nova/Llama on Bedrock", "Titan embeddings", "Bedrock Converse API"; typical import `import { BedrockSDK } from "@warlock.js/ai-bedrock"`. Skip: agent wiring — `@warlock.js/ai/run-ai-agent/SKILL.md`; provider choice — `@warlock.js/ai/pick-ai-provider/SKILL.md`; embeddings concepts — `@warlock.js/ai/embed-text/SKILL.md`; competing libs `@aws-sdk/client-bedrock-runtime`, `@ai-sdk/amazon-bedrock`; sibling adapters `@warlock.js/ai-openai`, `@warlock.js/ai-anthropic`, `@warlock.js/ai-google`, `@warlock.js/ai-ollama`.'
+---
+
+# `@warlock.js/ai-bedrock`
+
+Provider adapter that turns AWS Bedrock's **Converse API** into a vendor-neutral `ModelContract`, plus an Amazon **Titan** embedder. One wire mapping covers every Bedrock family.
+
+## Construction
+
+```ts
+import { BedrockSDK } from "@warlock.js/ai-bedrock";
+
+// Ambient AWS credential chain (env vars / SSO / IAM role):
+const bedrock = new BedrockSDK({ region: "us-east-1" });
+
+// Explicit static credentials:
+const bedrock2 = new BedrockSDK({
+  region: "us-east-1",
+  credentials: { accessKeyId: "AKIA...", secretAccessKey: "..." },
+  provider: "bedrock-eu",
+});
+```
+
+Bedrock authenticates via the **AWS credential chain, not an API key** — there is no `apiKey`. `region` is required; `credentials` is optional (omit to use the standard provider chain). The whole config object is forwarded to `BedrockRuntimeClient`, so any AWS client option (`endpoint`, `requestHandler`, retry config) is accepted. `provider` defaults to `"bedrock"`.
+
+## Producing a model
+
+`name` is the Bedrock **model id or inference-profile id**:
+
+```ts
+bedrock.model({ name: "anthropic.claude-sonnet-4-5-20250929-v1:0" })
+bedrock.model({ name: "us.amazon.nova-pro-v1:0", temperature: 0.2 })
+bedrock.model({ name: "meta.llama3-1-8b-instruct-v1:0", maxTokens: 1024 })
+```
+
+Uses the model-agnostic **Converse / ConverseStream** API — one wire mapping covers every Bedrock family (Claude, Nova, Llama, Mistral, Cohere) instead of per-family `InvokeModel` body shapes.
+
+## Capabilities — what's auto-set
+
+| Flag | Default |
+| --- | --- |
+| `structuredOutput` | `true` (via Converse `outputConfig.textFormat`) |
+| `vision` | Inferred from model id substring. `true` for Claude 3/3.5/3.7/4, Nova Lite/Pro/Premier, Llama 3.2-11B/90B, Llama 4. |
+
+Explicit config always wins.
+
+## System prompt
+
+Converse has no `"system"` role in `messages`. The adapter hoists every neutral `role: "system"` message into the separate `system: SystemContentBlock[]` request field. Transparent to the agent.
+
+## Tool calls
+
+- Outgoing: neutral tools → `toolConfig.tools[].toolSpec` with a JSON `inputSchema`. No tools → `toolConfig` omitted entirely (Bedrock rejects an empty `tools` array).
+- Assistant tool calls in history → `assistant` message with optional leading `{ text }` + one `{ toolUse }` block per call.
+- Tool results (`role: "tool"`) → a `user` turn with one `{ toolResult: { toolUseId, content: [{ text }] } }` block.
+- Response `toolUse` blocks → neutral `toolCalls`; `stopReason: "tool_use"` → `finishReason: "tool_calls"`.
+
+## Structured output
+
+Object-root `responseSchema` + `structuredOutput`-capable → `outputConfig.textFormat = { type: "json_schema", structure: { jsonSchema: { name, schema } } }` — note Bedrock wants the schema as a **stringified JSON document**.
+
+## Multipart messages (vision)
+
+- `{ type: "text" }` → `{ text }`
+- `{ type: "image", source: { base64, mediaType } }` → `{ image: { format, source: { bytes } } }` (base64 decoded; media type → `jpeg`/`png`/`gif`/`webp`)
+- `{ type: "image", source: { url } }` → **throws `InvalidRequestError`**. Bedrock's `ImageSource` only accepts raw bytes or an S3 location. Resolve images to base64 first.
+
+## Streaming
+
+`model.stream()` drains `ConverseStreamCommand`'s `response.stream`:
+
+- `contentBlockDelta.delta.text` → `{ type: "delta", content }`
+- `toolUse`: `contentBlockStart` opens an accumulator, `contentBlockDelta.delta.toolUse.input` fragments append, `contentBlockStop` emits one consolidated `{ type: "tool-call", ... }`
+- terminal `{ type: "done", finishReason, usage }` — usage from `metadata.usage` (a `TokenUsage`)
+
+## Finish-reason mapping
+
+`end_turn` / `stop_sequence` → `stop` · `max_tokens` → `length` · `tool_use` → `tool_calls` · `content_filtered` / `guardrail_intervened` / unknown / null → `error`.
+
+## Embeddings — Amazon Titan only
+
+```ts
+const embedder = bedrock.embedder({ name: "amazon.titan-embed-text-v2:0" });
+const { vector } = await embedder.embed("Hello world");
+const { vectors } = await embedder.embedMany(["a", "b"]);   // N sequential calls
+```
+
+Targets the **Titan Text Embeddings** family via `InvokeModel`. **Titan has no batch endpoint** — `embedMany` issues one request per input sequentially and aggregates token usage. Cohere-on-Bedrock batch embeddings use an incompatible body shape and are out of scope — use the OpenAI adapter when batch throughput matters.
+
+Pass `dimensions` to forward Titan v2's truncation hint (256 / 512 / 1024).
+
+## Errors
+
+Raw AWS SDK exceptions are wrapped into the typed `@warlock.js/ai` `AIError` hierarchy. Dispatch keys on the Smithy exception `name`:
+
+- `AccessDeniedException` / 401 / 403 → `ProviderAuthError`
+- `ThrottlingException` / 429 → `ProviderRateLimitError`
+- `ServiceQuotaExceededException` → `QuotaExceededError`
+- `ValidationException` with "too long / context window" → `ContextLengthExceededError`, else `InvalidRequestError`
+- `ModelTimeoutException` / `ETIMEDOUT` → `ProviderTimeoutError`
+- 5xx / `ModelError` / `ServiceUnavailable` → `ProviderError`
+
+## Token counting
+
+```ts
+await bedrock.count("some text")  // approximate heuristic, offline
+```
+
+Per-model tokenizers differ across Bedrock families.
+
+## Pricing — per-model registry
+
+`pricing` is an optional **registry keyed by Bedrock model id** — one entry per model, all rates in **USD per 1,000,000 tokens** (`ModelPricing`: `input`, `output`, optional `cachedInput` / `cachedOutput`). Set it on the SDK so every model it produces inherits the rates:
+
+```ts
+const bedrock = new BedrockSDK({
+  region: "us-east-1",
+  pricing: {
+    // USD per 1M tokens. Key = exact Bedrock model id / inference-profile id.
+    "anthropic.claude-sonnet-4-5-20250929-v1:0": { input: 3, output: 15 },
+    "us.amazon.nova-pro-v1:0":                    { input: 0.8, output: 3.2 },
+  },
+});
+
+const { usage } = await ai.agent({ model: bedrock.model({ name: "us.amazon.nova-pro-v1:0" }) }).execute("hi");
+usage.cost;  // per-channel USD breakdown of THIS run, computed from tokens × pricing[model]
+```
+
+Resolution at `model()` time: per-model `pricing` (`bedrock.model({ name, pricing })`) > SDK registry > `undefined` (no cost computed). When the same model id appears under a cross-region inference profile, list each id you actually invoke (`us.`, `eu.`, `apac.` prefixes are distinct keys). Bedrock meters cache-read tokens via Converse `usage` — those surface as `usage.cachedTokens`, so set `cachedInput` to have them priced at the discounted rate. See [`@warlock.js/ai/pick-ai-provider/SKILL.md`](@warlock.js/ai/pick-ai-provider/SKILL.md).
+
+## When NOT to use this skill
+
+- Direct `@aws-sdk/client-bedrock-runtime` calls without going through `@warlock.js/ai` agents.
+- OpenAI / Anthropic-direct / Gemini / Ollama models — those have their own adapter packages.
+- Batch embeddings throughput — Titan is single-input upstream; use the OpenAI / Google / Ollama adapter (those batch natively).
+
+## See also
+
+- [`@warlock.js/ai/run-ai-agent/SKILL.md`](@warlock.js/ai/run-ai-agent/SKILL.md)
+- [`@warlock.js/ai/pick-ai-provider/SKILL.md`](@warlock.js/ai/pick-ai-provider/SKILL.md)
+- [`@warlock.js/ai/embed-text/SKILL.md`](@warlock.js/ai/embed-text/SKILL.md)
+
+

package/llms.txt

@@ -0,0 +1,9 @@
+# Warlock AI Bedrock
+
+> Package: `@warlock.js/ai-bedrock`
+
+> AWS Bedrock adapter for @warlock.js/ai
+
+## Skills
+
+- [setup-bedrock](@warlock.js/ai-bedrock/setup-bedrock/SKILL.md): Wire @warlock.js/ai-bedrock — new BedrockSDK({region, credentials?, provider?}) for AWS Bedrock Converse API + Titan embeddings. AWS credential chain (no apiKey). Triggers: `BedrockSDK`, `bedrock.model`, `bedrock.embedder`, `bedrock.count`, `BedrockRuntimeClient`; "how do I use AWS Bedrock", "wire Claude/Nova/Llama on Bedrock", "Titan embeddings", "Bedrock Converse API"; typical import `import { BedrockSDK } from "@warlock.js/ai-bedrock"`. Skip: agent wiring — `@warlock.js/ai/run-ai-agent/SKILL.md`; provider choice — `@warlock.js/ai/pick-ai-provider/SKILL.md`; embeddings concepts — `@warlock.js/ai/embed-text/SKILL.md`; competing libs `@aws-sdk/client-bedrock-runtime`, `@ai-sdk/amazon-bedrock`; sibling adapters `@warlock.js/ai-openai`, `@warlock.js/ai-anthropic`, `@warlock.js/ai-google`, `@warlock.js/ai-ollama`.

package/package.json

@@ -0,0 +1,39 @@
+{
+  "name": "@warlock.js/ai-bedrock",
+  "description": "AWS Bedrock adapter for @warlock.js/ai",
+  "keywords": [
+    "warlock",
+    "ai",
+    "bedrock",
+    "aws"
+  ],
+  "author": "Hasan Zohdy",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/warlockjs/ai-bedrock"
+  },
+  "dependencies": {
+    "@aws-sdk/client-bedrock-runtime": "^3.1048.0",
+    "@warlock.js/logger": "*"
+  },
+  "peerDependencies": {
+    "@warlock.js/ai": "*"
+  },
+  "version": "4.1.1",
+  "main": "./cjs/index.cjs",
+  "module": "./esm/index.mjs",
+  "types": "./esm/index.d.mts",
+  "exports": {
+    ".": {
+      "import": {
+        "types": "./esm/index.d.mts",
+        "default": "./esm/index.mjs"
+      },
+      "require": {
+        "types": "./esm/index.d.mts",
+        "default": "./cjs/index.cjs"
+      }
+    }
+  }
+}

package/skills/README.md

@@ -0,0 +1,9 @@
+# `@warlock.js/ai-bedrock` — skills index
+
+Per-task skills. All cross-references use the form `@warlock.js/<pkg>/<skill>/SKILL.md`.
+
+## Skills
+
+### [`setup-bedrock/`](./setup-bedrock/SKILL.md)
+
+Wire @warlock.js/ai-bedrock — new BedrockSDK({region, credentials?, provider?}) for AWS Bedrock Converse API + Titan embeddings. AWS credential chain (no apiKey). Load when wiring a Bedrock-hosted model (Claude / Nova / Llama / Mistral / Cohere) into a @warlock.js agent.

package/skills/setup-bedrock/SKILL.md

@@ -0,0 +1,143 @@
+---
+name: setup-bedrock
+description: 'Wire @warlock.js/ai-bedrock — new BedrockSDK({region, credentials?, provider?}) for AWS Bedrock Converse API + Titan embeddings. AWS credential chain (no apiKey). Triggers: `BedrockSDK`, `bedrock.model`, `bedrock.embedder`, `bedrock.count`, `BedrockRuntimeClient`; "how do I use AWS Bedrock", "wire Claude/Nova/Llama on Bedrock", "Titan embeddings", "Bedrock Converse API"; typical import `import { BedrockSDK } from "@warlock.js/ai-bedrock"`. Skip: agent wiring — `@warlock.js/ai/run-ai-agent/SKILL.md`; provider choice — `@warlock.js/ai/pick-ai-provider/SKILL.md`; embeddings concepts — `@warlock.js/ai/embed-text/SKILL.md`; competing libs `@aws-sdk/client-bedrock-runtime`, `@ai-sdk/amazon-bedrock`; sibling adapters `@warlock.js/ai-openai`, `@warlock.js/ai-anthropic`, `@warlock.js/ai-google`, `@warlock.js/ai-ollama`.'
+---
+
+# `@warlock.js/ai-bedrock`
+
+Provider adapter that turns AWS Bedrock's **Converse API** into a vendor-neutral `ModelContract`, plus an Amazon **Titan** embedder. One wire mapping covers every Bedrock family.
+
+## Construction
+
+```ts
+import { BedrockSDK } from "@warlock.js/ai-bedrock";
+
+// Ambient AWS credential chain (env vars / SSO / IAM role):
+const bedrock = new BedrockSDK({ region: "us-east-1" });
+
+// Explicit static credentials:
+const bedrock2 = new BedrockSDK({
+  region: "us-east-1",
+  credentials: { accessKeyId: "AKIA...", secretAccessKey: "..." },
+  provider: "bedrock-eu",
+});
+```
+
+Bedrock authenticates via the **AWS credential chain, not an API key** — there is no `apiKey`. `region` is required; `credentials` is optional (omit to use the standard provider chain). The whole config object is forwarded to `BedrockRuntimeClient`, so any AWS client option (`endpoint`, `requestHandler`, retry config) is accepted. `provider` defaults to `"bedrock"`.
+
+## Producing a model
+
+`name` is the Bedrock **model id or inference-profile id**:
+
+```ts
+bedrock.model({ name: "anthropic.claude-sonnet-4-5-20250929-v1:0" })
+bedrock.model({ name: "us.amazon.nova-pro-v1:0", temperature: 0.2 })
+bedrock.model({ name: "meta.llama3-1-8b-instruct-v1:0", maxTokens: 1024 })
+```
+
+Uses the model-agnostic **Converse / ConverseStream** API — one wire mapping covers every Bedrock family (Claude, Nova, Llama, Mistral, Cohere) instead of per-family `InvokeModel` body shapes.
+
+## Capabilities — what's auto-set
+
+| Flag | Default |
+| --- | --- |
+| `structuredOutput` | `true` (via Converse `outputConfig.textFormat`) |
+| `vision` | Inferred from model id substring. `true` for Claude 3/3.5/3.7/4, Nova Lite/Pro/Premier, Llama 3.2-11B/90B, Llama 4. |
+
+Explicit config always wins.
+
+## System prompt
+
+Converse has no `"system"` role in `messages`. The adapter hoists every neutral `role: "system"` message into the separate `system: SystemContentBlock[]` request field. Transparent to the agent.
+
+## Tool calls
+
+- Outgoing: neutral tools → `toolConfig.tools[].toolSpec` with a JSON `inputSchema`. No tools → `toolConfig` omitted entirely (Bedrock rejects an empty `tools` array).
+- Assistant tool calls in history → `assistant` message with optional leading `{ text }` + one `{ toolUse }` block per call.
+- Tool results (`role: "tool"`) → a `user` turn with one `{ toolResult: { toolUseId, content: [{ text }] } }` block.
+- Response `toolUse` blocks → neutral `toolCalls`; `stopReason: "tool_use"` → `finishReason: "tool_calls"`.
+
+## Structured output
+
+Object-root `responseSchema` + `structuredOutput`-capable → `outputConfig.textFormat = { type: "json_schema", structure: { jsonSchema: { name, schema } } }` — note Bedrock wants the schema as a **stringified JSON document**.
+
+## Multipart messages (vision)
+
+- `{ type: "text" }` → `{ text }`
+- `{ type: "image", source: { base64, mediaType } }` → `{ image: { format, source: { bytes } } }` (base64 decoded; media type → `jpeg`/`png`/`gif`/`webp`)
+- `{ type: "image", source: { url } }` → **throws `InvalidRequestError`**. Bedrock's `ImageSource` only accepts raw bytes or an S3 location. Resolve images to base64 first.
+
+## Streaming
+
+`model.stream()` drains `ConverseStreamCommand`'s `response.stream`:
+
+- `contentBlockDelta.delta.text` → `{ type: "delta", content }`
+- `toolUse`: `contentBlockStart` opens an accumulator, `contentBlockDelta.delta.toolUse.input` fragments append, `contentBlockStop` emits one consolidated `{ type: "tool-call", ... }`
+- terminal `{ type: "done", finishReason, usage }` — usage from `metadata.usage` (a `TokenUsage`)
+
+## Finish-reason mapping
+
+`end_turn` / `stop_sequence` → `stop` · `max_tokens` → `length` · `tool_use` → `tool_calls` · `content_filtered` / `guardrail_intervened` / unknown / null → `error`.
+
+## Embeddings — Amazon Titan only
+
+```ts
+const embedder = bedrock.embedder({ name: "amazon.titan-embed-text-v2:0" });
+const { vector } = await embedder.embed("Hello world");
+const { vectors } = await embedder.embedMany(["a", "b"]);   // N sequential calls
+```
+
+Targets the **Titan Text Embeddings** family via `InvokeModel`. **Titan has no batch endpoint** — `embedMany` issues one request per input sequentially and aggregates token usage. Cohere-on-Bedrock batch embeddings use an incompatible body shape and are out of scope — use the OpenAI adapter when batch throughput matters.
+
+Pass `dimensions` to forward Titan v2's truncation hint (256 / 512 / 1024).
+
+## Errors
+
+Raw AWS SDK exceptions are wrapped into the typed `@warlock.js/ai` `AIError` hierarchy. Dispatch keys on the Smithy exception `name`:
+
+- `AccessDeniedException` / 401 / 403 → `ProviderAuthError`
+- `ThrottlingException` / 429 → `ProviderRateLimitError`
+- `ServiceQuotaExceededException` → `QuotaExceededError`
+- `ValidationException` with "too long / context window" → `ContextLengthExceededError`, else `InvalidRequestError`
+- `ModelTimeoutException` / `ETIMEDOUT` → `ProviderTimeoutError`
+- 5xx / `ModelError` / `ServiceUnavailable` → `ProviderError`
+
+## Token counting
+
+```ts
+await bedrock.count("some text")  // approximate heuristic, offline
+```
+
+Per-model tokenizers differ across Bedrock families.
+
+## Pricing — per-model registry
+
+`pricing` is an optional **registry keyed by Bedrock model id** — one entry per model, all rates in **USD per 1,000,000 tokens** (`ModelPricing`: `input`, `output`, optional `cachedInput` / `cachedOutput`). Set it on the SDK so every model it produces inherits the rates:
+
+```ts
+const bedrock = new BedrockSDK({
+  region: "us-east-1",
+  pricing: {
+    // USD per 1M tokens. Key = exact Bedrock model id / inference-profile id.
+    "anthropic.claude-sonnet-4-5-20250929-v1:0": { input: 3, output: 15 },
+    "us.amazon.nova-pro-v1:0":                    { input: 0.8, output: 3.2 },
+  },
+});
+
+const { usage } = await ai.agent({ model: bedrock.model({ name: "us.amazon.nova-pro-v1:0" }) }).execute("hi");
+usage.cost;  // per-channel USD breakdown of THIS run, computed from tokens × pricing[model]
+```
+
+Resolution at `model()` time: per-model `pricing` (`bedrock.model({ name, pricing })`) > SDK registry > `undefined` (no cost computed). When the same model id appears under a cross-region inference profile, list each id you actually invoke (`us.`, `eu.`, `apac.` prefixes are distinct keys). Bedrock meters cache-read tokens via Converse `usage` — those surface as `usage.cachedTokens`, so set `cachedInput` to have them priced at the discounted rate. See [`@warlock.js/ai/pick-ai-provider/SKILL.md`](@warlock.js/ai/pick-ai-provider/SKILL.md).
+
+## When NOT to use this skill
+
+- Direct `@aws-sdk/client-bedrock-runtime` calls without going through `@warlock.js/ai` agents.
+- OpenAI / Anthropic-direct / Gemini / Ollama models — those have their own adapter packages.
+- Batch embeddings throughput — Titan is single-input upstream; use the OpenAI / Google / Ollama adapter (those batch natively).
+
+## See also
+
+- [`@warlock.js/ai/run-ai-agent/SKILL.md`](@warlock.js/ai/run-ai-agent/SKILL.md)
+- [`@warlock.js/ai/pick-ai-provider/SKILL.md`](@warlock.js/ai/pick-ai-provider/SKILL.md)
+- [`@warlock.js/ai/embed-text/SKILL.md`](@warlock.js/ai/embed-text/SKILL.md)