mirror of
https://github.com/getcompanion-ai/co-mono.git
synced 2026-04-15 07:04:45 +00:00
feat(ai): Add Amazon Bedrock provider (#494)
Adds support for Amazon Bedrock with Claude models including: - Full streaming support via Converse API - Reasoning/thinking support for Claude models - Cross-region inference model ID handling - Multiple AWS credential sources (profile, IAM keys, API keys) - Image support in messages and tool results - Unicode surrogate sanitization Also adds 'Adding a New Provider' documentation to AGENTS.md and README. Co-authored-by: nickchan2 <nickchan2@users.noreply.github.com>
This commit is contained in:
Mario Zechner
parent
4f216d318f
commit
fd268479a4
31 changed files with 3550 additions and 2593 deletions
40
AGENTS.md
40
AGENTS.md
|
|
@ -75,6 +75,46 @@ Use these sections under `## [Unreleased]`:
|
|||
- **Internal changes (from issues)**: `Fixed foo bar ([#123](https://github.com/badlogic/pi-mono/issues/123))`
|
||||
- **External contributions**: `Added feature X ([#456](https://github.com/badlogic/pi-mono/pull/456) by [@username](https://github.com/username))`
|
||||
|
||||
## Adding a New LLM Provider (packages/ai)
|
||||
|
||||
Adding a new provider requires changes across multiple files:
|
||||
|
||||
### 1. Core Types (`packages/ai/src/types.ts`)
|
||||
- Add API identifier to `Api` type union (e.g., `"bedrock-converse-stream"`)
|
||||
- Create options interface extending `StreamOptions`
|
||||
- Add mapping to `ApiOptionsMap`
|
||||
- Add provider name to `KnownProvider` type union
|
||||
|
||||
### 2. Provider Implementation (`packages/ai/src/providers/`)
|
||||
Create provider file exporting:
|
||||
- `stream<Provider>()` function returning `AssistantMessageEventStream`
|
||||
- Message/tool conversion functions
|
||||
- Response parsing emitting standardized events (`text`, `tool_call`, `thinking`, `usage`, `stop`)
|
||||
|
||||
### 3. Stream Integration (`packages/ai/src/stream.ts`)
|
||||
- Import provider's stream function and options type
|
||||
- Add credential detection in `getEnvApiKey()`
|
||||
- Add case in `mapOptionsForApi()` for `SimpleStreamOptions` mapping
|
||||
- Add provider to `streamFunctions` map
|
||||
|
||||
### 4. Model Generation (`packages/ai/scripts/generate-models.ts`)
|
||||
- Add logic to fetch/parse models from provider source
|
||||
- Map to standardized `Model` interface
|
||||
|
||||
### 5. Tests (`packages/ai/test/`)
|
||||
Add provider to: `stream.test.ts`, `tokens.test.ts`, `abort.test.ts`, `empty.test.ts`, `context-overflow.test.ts`, `image-limits.test.ts`, `unicode-surrogate.test.ts`, `tool-call-without-result.test.ts`, `image-tool-result.test.ts`, `total-tokens.test.ts`
|
||||
|
||||
For non-standard auth, create utility (e.g., `bedrock-utils.ts`) with credential detection.
|
||||
|
||||
### 6. Coding Agent (`packages/coding-agent/`)
|
||||
- `src/core/model-resolver.ts`: Add default model ID to `DEFAULT_MODELS`
|
||||
- `src/cli/args.ts`: Add env var documentation
|
||||
- `README.md`: Add provider setup instructions
|
||||
|
||||
### 7. Documentation
|
||||
- `packages/ai/README.md`: Add to providers table, document options/auth, add env vars
|
||||
- `packages/ai/CHANGELOG.md`: Add entry under `## [Unreleased]`
|
||||
|
||||
## Releasing
|
||||
|
||||
**Lockstep versioning**: All packages always share the same version number. Every release updates all packages together.
|
||||
|
|
|
|||
4051
package-lock.json
generated
4051
package-lock.json
generated
File diff suppressed because it is too large
Load diff
18
packages/agent/test/bedrock-utils.ts
Normal file
18
packages/agent/test/bedrock-utils.ts
Normal file
|
|
@ -0,0 +1,18 @@
|
|||
/**
|
||||
* Utility functions for Amazon Bedrock tests
|
||||
*/
|
||||
|
||||
/**
|
||||
* Check if any valid AWS credentials are configured for Bedrock.
|
||||
* Returns true if any of the following are set:
|
||||
* - AWS_PROFILE (named profile from ~/.aws/credentials)
|
||||
* - AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY (IAM keys)
|
||||
* - AWS_BEARER_TOKEN_BEDROCK (Bedrock API key)
|
||||
*/
|
||||
export function hasBedrockCredentials(): boolean {
|
||||
return !!(
|
||||
process.env.AWS_PROFILE ||
|
||||
(process.env.AWS_ACCESS_KEY_ID && process.env.AWS_SECRET_ACCESS_KEY) ||
|
||||
process.env.AWS_BEARER_TOKEN_BEDROCK
|
||||
);
|
||||
}
|
||||
|
|
@ -2,6 +2,7 @@ import type { AssistantMessage, Model, ToolResultMessage, UserMessage } from "@m
|
|||
import { getModel } from "@mariozechner/pi-ai";
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { Agent } from "../src/index.js";
|
||||
import { hasBedrockCredentials } from "./bedrock-utils.js";
|
||||
import { calculateTool } from "./utils/calculate.js";
|
||||
|
||||
async function basicPrompt(model: Model<any>) {
|
||||
|
|
@ -324,6 +325,30 @@ describe("Agent E2E Tests", () => {
|
|||
await multiTurnConversation(model);
|
||||
});
|
||||
});
|
||||
|
||||
describe.skipIf(!hasBedrockCredentials())("Amazon Bedrock Provider (claude-sonnet-4-5)", () => {
|
||||
const model = getModel("amazon-bedrock", "global.anthropic.claude-sonnet-4-5-20250929-v1:0");
|
||||
|
||||
it("should handle basic text prompt", async () => {
|
||||
await basicPrompt(model);
|
||||
});
|
||||
|
||||
it("should execute tools correctly", async () => {
|
||||
await toolExecution(model);
|
||||
});
|
||||
|
||||
it("should handle abort during execution", async () => {
|
||||
await abortExecution(model);
|
||||
});
|
||||
|
||||
it("should emit state updates during streaming", async () => {
|
||||
await stateUpdates(model);
|
||||
});
|
||||
|
||||
it("should maintain context across multiple turns", async () => {
|
||||
await multiTurnConversation(model);
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe("Agent.continue()", () => {
|
||||
|
|
|
|||
|
|
@ -4,6 +4,7 @@
|
|||
|
||||
### Added
|
||||
|
||||
- Add Amazon Bedrock provider ([#494](https://github.com/badlogic/pi-mono/pull/494) by [@unexge](https://github.com/unexge))
|
||||
- Added `serviceTier` option for OpenAI Responses requests ([#672](https://github.com/badlogic/pi-mono/pull/672) by [@markusylisiurunen](https://github.com/markusylisiurunen))
|
||||
- **Anthropic caching on OpenRouter**: Interactions with Anthropic models via OpenRouter now set a 5-minute cache point using Anthropic-style `cache_control` breakpoints on the last assistant or user message. ([#584](https://github.com/badlogic/pi-mono/pull/584) by [@nathyong](https://github.com/nathyong))
|
||||
|
||||
|
|
|
|||
|
|
@ -59,6 +59,7 @@ Unified LLM API with automatic model discovery, provider configuration, token an
|
|||
- **GitHub Copilot** (requires OAuth, see below)
|
||||
- **Google Gemini CLI** (requires OAuth, see below)
|
||||
- **Antigravity** (requires OAuth, see below)
|
||||
- **Amazon Bedrock**
|
||||
- **Any OpenAI-compatible API**: Ollama, vLLM, LM Studio, etc.
|
||||
|
||||
## Installation
|
||||
|
|
@ -1026,6 +1027,90 @@ const response = await complete(model, {
|
|||
|
||||
**Google Gemini CLI / Antigravity**: These use Google Cloud OAuth. The `apiKey` returned by `getOAuthApiKey()` is a JSON string containing both the token and project ID, which the library handles automatically.
|
||||
|
||||
## Development
|
||||
|
||||
### Adding a New Provider
|
||||
|
||||
Adding a new LLM provider requires changes across multiple files. This checklist covers all necessary steps:
|
||||
|
||||
#### 1. Core Types (`src/types.ts`)
|
||||
|
||||
- Add the API identifier to the `Api` type union (e.g., `"bedrock-converse-stream"`)
|
||||
- Create an options interface extending `StreamOptions` (e.g., `BedrockOptions`)
|
||||
- Add the mapping to `ApiOptionsMap`
|
||||
- Add the provider name to `KnownProvider` type union (e.g., `"amazon-bedrock"`)
|
||||
|
||||
#### 2. Provider Implementation (`src/providers/`)
|
||||
|
||||
Create a new provider file (e.g., `amazon-bedrock.ts`) that exports:
|
||||
|
||||
- `stream<Provider>()` function returning `AssistantMessageEventStream`
|
||||
- Provider-specific options interface
|
||||
- Message conversion functions to transform `Context` to provider format
|
||||
- Tool conversion if the provider supports tools
|
||||
- Response parsing to emit standardized events (`text`, `tool_call`, `thinking`, `usage`, `stop`)
|
||||
|
||||
#### 3. Stream Integration (`src/stream.ts`)
|
||||
|
||||
- Import the provider's stream function and options type
|
||||
- Add credential detection in `getEnvApiKey()` for the new provider
|
||||
- Add a case in `mapOptionsForApi()` to map `SimpleStreamOptions` to provider options
|
||||
- Add the provider's stream function to the `streamFunctions` map
|
||||
|
||||
#### 4. Model Generation (`scripts/generate-models.ts`)
|
||||
|
||||
- Add logic to fetch and parse models from the provider's source (e.g., models.dev API)
|
||||
- Map provider model data to the standardized `Model` interface
|
||||
- Handle provider-specific quirks (pricing format, capability flags, model ID transformations)
|
||||
|
||||
#### 5. Tests (`test/`)
|
||||
|
||||
Create or update test files to cover the new provider:
|
||||
|
||||
- `stream.test.ts` - Basic streaming and tool use
|
||||
- `tokens.test.ts` - Token usage reporting
|
||||
- `abort.test.ts` - Request cancellation
|
||||
- `empty.test.ts` - Empty message handling
|
||||
- `context-overflow.test.ts` - Context limit errors
|
||||
- `image-limits.test.ts` - Image support (if applicable)
|
||||
- `unicode-surrogate.test.ts` - Unicode handling
|
||||
- `tool-call-without-result.test.ts` - Orphaned tool calls
|
||||
- `image-tool-result.test.ts` - Images in tool results
|
||||
- `total-tokens.test.ts` - Token counting accuracy
|
||||
|
||||
For providers with non-standard auth (AWS, Google Vertex), create a utility like `bedrock-utils.ts` with credential detection helpers.
|
||||
|
||||
#### 6. Coding Agent Integration (`../coding-agent/`)
|
||||
|
||||
Update `src/core/model-resolver.ts`:
|
||||
|
||||
- Add a default model ID for the provider in `DEFAULT_MODELS`
|
||||
|
||||
Update `src/cli/args.ts`:
|
||||
|
||||
- Add environment variable documentation in the help text
|
||||
|
||||
Update `README.md`:
|
||||
|
||||
- Add the provider to the providers section with setup instructions
|
||||
|
||||
#### 7. Documentation
|
||||
|
||||
Update `packages/ai/README.md`:
|
||||
|
||||
- Add to the Supported Providers table
|
||||
- Document any provider-specific options or authentication requirements
|
||||
- Add environment variable to the Environment Variables section
|
||||
|
||||
#### 8. Changelog
|
||||
|
||||
Add an entry to `packages/ai/CHANGELOG.md` under `## [Unreleased]`:
|
||||
|
||||
```markdown
|
||||
### Added
|
||||
- Added support for [Provider Name] provider ([#PR](link) by [@author](link))
|
||||
```
|
||||
|
||||
## License
|
||||
|
||||
MIT
|
||||
|
|
|
|||
|
|
@ -23,6 +23,7 @@
|
|||
},
|
||||
"dependencies": {
|
||||
"@anthropic-ai/sdk": "0.71.2",
|
||||
"@aws-sdk/client-bedrock-runtime": "^3.966.0",
|
||||
"@google/genai": "1.34.0",
|
||||
"@mistralai/mistralai": "1.10.0",
|
||||
"@sinclair/typebox": "^0.34.41",
|
||||
|
|
@ -39,6 +40,7 @@
|
|||
"openai",
|
||||
"anthropic",
|
||||
"gemini",
|
||||
"bedrock",
|
||||
"unified",
|
||||
"api"
|
||||
],
|
||||
|
|
|
|||
|
|
@ -105,6 +105,75 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
|
|||
|
||||
const models: Model<any>[] = [];
|
||||
|
||||
// Process Amazon Bedrock models
|
||||
if (data["amazon-bedrock"]?.models) {
|
||||
for (const [modelId, model] of Object.entries(data["amazon-bedrock"].models)) {
|
||||
const m = model as ModelsDevModel;
|
||||
if (m.tool_call !== true) continue;
|
||||
|
||||
let id = modelId;
|
||||
|
||||
if (id.startsWith("ai21.jamba")) {
|
||||
// These models doesn't support tool use in streaming mode
|
||||
continue;
|
||||
}
|
||||
|
||||
if (id.startsWith("amazon.titan-text-express") ||
|
||||
id.startsWith("mistral.mistral-7b-instruct-v0")) {
|
||||
// These models doesn't support system messages
|
||||
continue;
|
||||
}
|
||||
|
||||
// Some Amazon Bedrock models require cross-region inference profiles to work.
|
||||
// To use cross-region inference, we need to add a region prefix to the models.
|
||||
// See https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html#inference-profiles-support-system
|
||||
// TODO: Remove Claude models once https://github.com/anomalyco/models.dev/pull/607 is merged, and follow-up with other models.
|
||||
|
||||
// Models with global cross-region inference profiles
|
||||
if (id.startsWith("anthropic.claude-haiku-4-5") ||
|
||||
id.startsWith("anthropic.claude-sonnet-4") ||
|
||||
id.startsWith("anthropic.claude-opus-4-5") ||
|
||||
id.startsWith("amazon.nova-2-lite") ||
|
||||
id.startsWith("cohere.embed-v4") ||
|
||||
id.startsWith("twelvelabs.pegasus-1-2")) {
|
||||
id = "global." + id;
|
||||
}
|
||||
|
||||
// Models with US cross-region inference profiles
|
||||
if (id.startsWith("amazon.nova-lite") ||
|
||||
id.startsWith("amazon.nova-micro") ||
|
||||
id.startsWith("amazon.nova-premier") ||
|
||||
id.startsWith("amazon.nova-pro") ||
|
||||
id.startsWith("anthropic.claude-3-7-sonnet") ||
|
||||
id.startsWith("anthropic.claude-opus-4-1") ||
|
||||
id.startsWith("anthropic.claude-opus-4-20250514") ||
|
||||
id.startsWith("deepseek.r1") ||
|
||||
id.startsWith("meta.llama3-2") ||
|
||||
id.startsWith("meta.llama3-3") ||
|
||||
id.startsWith("meta.llama4")) {
|
||||
id = "us." + id;
|
||||
}
|
||||
|
||||
models.push({
|
||||
id,
|
||||
name: m.name || id,
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: m.reasoning === true,
|
||||
input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
|
||||
cost: {
|
||||
input: m.cost?.input || 0,
|
||||
output: m.cost?.output || 0,
|
||||
cacheRead: m.cost?.cache_read || 0,
|
||||
cacheWrite: m.cost?.cache_write || 0,
|
||||
},
|
||||
contextWindow: m.limit?.context || 4096,
|
||||
maxTokens: m.limit?.output || 4096,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// Process Anthropic models
|
||||
if (data.anthropic?.models) {
|
||||
for (const [modelId, model] of Object.entries(data.anthropic.models)) {
|
||||
|
|
|
|||
|
|
@ -4,6 +4,892 @@
|
|||
import type { Model } from "./types.js";
|
||||
|
||||
export const MODELS = {
|
||||
"amazon-bedrock": {
|
||||
"anthropic.claude-3-5-haiku-20241022-v1:0": {
|
||||
id: "anthropic.claude-3-5-haiku-20241022-v1:0",
|
||||
name: "Claude Haiku 3.5",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.8,
|
||||
output: 4,
|
||||
cacheRead: 0.08,
|
||||
cacheWrite: 1,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
|
||||
id: "anthropic.claude-3-5-sonnet-20240620-v1:0",
|
||||
name: "Claude Sonnet 3.5",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 3,
|
||||
output: 15,
|
||||
cacheRead: 0.3,
|
||||
cacheWrite: 3.75,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"anthropic.claude-3-5-sonnet-20241022-v2:0": {
|
||||
id: "anthropic.claude-3-5-sonnet-20241022-v2:0",
|
||||
name: "Claude Sonnet 3.5 v2",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 3,
|
||||
output: 15,
|
||||
cacheRead: 0.3,
|
||||
cacheWrite: 3.75,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"anthropic.claude-3-haiku-20240307-v1:0": {
|
||||
id: "anthropic.claude-3-haiku-20240307-v1:0",
|
||||
name: "Claude Haiku 3",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.25,
|
||||
output: 1.25,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"anthropic.claude-3-opus-20240229-v1:0": {
|
||||
id: "anthropic.claude-3-opus-20240229-v1:0",
|
||||
name: "Claude Opus 3",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 15,
|
||||
output: 75,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"anthropic.claude-3-sonnet-20240229-v1:0": {
|
||||
id: "anthropic.claude-3-sonnet-20240229-v1:0",
|
||||
name: "Claude Sonnet 3",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 3,
|
||||
output: 15,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"cohere.command-r-plus-v1:0": {
|
||||
id: "cohere.command-r-plus-v1:0",
|
||||
name: "Command R+",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 3,
|
||||
output: 15,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"cohere.command-r-v1:0": {
|
||||
id: "cohere.command-r-v1:0",
|
||||
name: "Command R",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.5,
|
||||
output: 1.5,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"deepseek.v3-v1:0": {
|
||||
id: "deepseek.v3-v1:0",
|
||||
name: "DeepSeek-V3.1",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.58,
|
||||
output: 1.68,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 163840,
|
||||
maxTokens: 81920,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"global.amazon.nova-2-lite-v1:0": {
|
||||
id: "global.amazon.nova-2-lite-v1:0",
|
||||
name: "Nova 2 Lite",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.33,
|
||||
output: 2.75,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"global.anthropic.claude-haiku-4-5-20251001-v1:0": {
|
||||
id: "global.anthropic.claude-haiku-4-5-20251001-v1:0",
|
||||
name: "Claude Haiku 4.5",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 1,
|
||||
output: 5,
|
||||
cacheRead: 0.1,
|
||||
cacheWrite: 1.25,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 64000,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"global.anthropic.claude-opus-4-5-20251101-v1:0": {
|
||||
id: "global.anthropic.claude-opus-4-5-20251101-v1:0",
|
||||
name: "Claude Opus 4.5",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 5,
|
||||
output: 25,
|
||||
cacheRead: 0.5,
|
||||
cacheWrite: 6.25,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 64000,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"global.anthropic.claude-sonnet-4-20250514-v1:0": {
|
||||
id: "global.anthropic.claude-sonnet-4-20250514-v1:0",
|
||||
name: "Claude Sonnet 4",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 3,
|
||||
output: 15,
|
||||
cacheRead: 0.3,
|
||||
cacheWrite: 3.75,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 64000,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"global.anthropic.claude-sonnet-4-5-20250929-v1:0": {
|
||||
id: "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
|
||||
name: "Claude Sonnet 4.5",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 3,
|
||||
output: 15,
|
||||
cacheRead: 0.3,
|
||||
cacheWrite: 3.75,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 64000,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"google.gemma-3-27b-it": {
|
||||
id: "google.gemma-3-27b-it",
|
||||
name: "Google Gemma 3 27B Instruct",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.12,
|
||||
output: 0.2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 202752,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"google.gemma-3-4b-it": {
|
||||
id: "google.gemma-3-4b-it",
|
||||
name: "Gemma 3 4B IT",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.04,
|
||||
output: 0.08,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"meta.llama3-1-70b-instruct-v1:0": {
|
||||
id: "meta.llama3-1-70b-instruct-v1:0",
|
||||
name: "Llama 3.1 70B Instruct",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.72,
|
||||
output: 0.72,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"meta.llama3-1-8b-instruct-v1:0": {
|
||||
id: "meta.llama3-1-8b-instruct-v1:0",
|
||||
name: "Llama 3.1 8B Instruct",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.22,
|
||||
output: 0.22,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"minimax.minimax-m2": {
|
||||
id: "minimax.minimax-m2",
|
||||
name: "MiniMax M2",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 1.2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 204608,
|
||||
maxTokens: 128000,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"mistral.ministral-3-14b-instruct": {
|
||||
id: "mistral.ministral-3-14b-instruct",
|
||||
name: "Ministral 14B 3.0",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.2,
|
||||
output: 0.2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"mistral.ministral-3-8b-instruct": {
|
||||
id: "mistral.ministral-3-8b-instruct",
|
||||
name: "Ministral 3 8B",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.15,
|
||||
output: 0.15,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"mistral.mistral-large-2402-v1:0": {
|
||||
id: "mistral.mistral-large-2402-v1:0",
|
||||
name: "Mistral Large (24.02)",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.5,
|
||||
output: 1.5,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"mistral.voxtral-mini-3b-2507": {
|
||||
id: "mistral.voxtral-mini-3b-2507",
|
||||
name: "Voxtral Mini 3B 2507",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.04,
|
||||
output: 0.04,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"mistral.voxtral-small-24b-2507": {
|
||||
id: "mistral.voxtral-small-24b-2507",
|
||||
name: "Voxtral Small 24B 2507",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.15,
|
||||
output: 0.35,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 32000,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"moonshot.kimi-k2-thinking": {
|
||||
id: "moonshot.kimi-k2-thinking",
|
||||
name: "Kimi K2 Thinking",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.6,
|
||||
output: 2.5,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 256000,
|
||||
maxTokens: 256000,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"nvidia.nemotron-nano-12b-v2": {
|
||||
id: "nvidia.nemotron-nano-12b-v2",
|
||||
name: "NVIDIA Nemotron Nano 12B v2 VL BF16",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.2,
|
||||
output: 0.6,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"nvidia.nemotron-nano-9b-v2": {
|
||||
id: "nvidia.nemotron-nano-9b-v2",
|
||||
name: "NVIDIA Nemotron Nano 9B v2",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.06,
|
||||
output: 0.23,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"openai.gpt-oss-120b-1:0": {
|
||||
id: "openai.gpt-oss-120b-1:0",
|
||||
name: "gpt-oss-120b",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.15,
|
||||
output: 0.6,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"openai.gpt-oss-20b-1:0": {
|
||||
id: "openai.gpt-oss-20b-1:0",
|
||||
name: "gpt-oss-20b",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.07,
|
||||
output: 0.3,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"openai.gpt-oss-safeguard-120b": {
|
||||
id: "openai.gpt-oss-safeguard-120b",
|
||||
name: "GPT OSS Safeguard 120B",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.15,
|
||||
output: 0.6,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"openai.gpt-oss-safeguard-20b": {
|
||||
id: "openai.gpt-oss-safeguard-20b",
|
||||
name: "GPT OSS Safeguard 20B",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.07,
|
||||
output: 0.2,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"qwen.qwen3-235b-a22b-2507-v1:0": {
|
||||
id: "qwen.qwen3-235b-a22b-2507-v1:0",
|
||||
name: "Qwen3 235B A22B 2507",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.22,
|
||||
output: 0.88,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"qwen.qwen3-32b-v1:0": {
|
||||
id: "qwen.qwen3-32b-v1:0",
|
||||
name: "Qwen3 32B (dense)",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.15,
|
||||
output: 0.6,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 16384,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"qwen.qwen3-coder-30b-a3b-v1:0": {
|
||||
id: "qwen.qwen3-coder-30b-a3b-v1:0",
|
||||
name: "Qwen3 Coder 30B A3B Instruct",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.15,
|
||||
output: 0.6,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
maxTokens: 131072,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"qwen.qwen3-coder-480b-a35b-v1:0": {
|
||||
id: "qwen.qwen3-coder-480b-a35b-v1:0",
|
||||
name: "Qwen3 Coder 480B A35B Instruct",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.22,
|
||||
output: 1.8,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131072,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"qwen.qwen3-next-80b-a3b": {
|
||||
id: "qwen.qwen3-next-80b-a3b",
|
||||
name: "Qwen/Qwen3-Next-80B-A3B-Instruct",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.14,
|
||||
output: 1.4,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262000,
|
||||
maxTokens: 262000,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"qwen.qwen3-vl-235b-a22b": {
|
||||
id: "qwen.qwen3-vl-235b-a22b",
|
||||
name: "Qwen/Qwen3-VL-235B-A22B-Instruct",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.3,
|
||||
output: 1.5,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262000,
|
||||
maxTokens: 262000,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.amazon.nova-lite-v1:0": {
|
||||
id: "us.amazon.nova-lite-v1:0",
|
||||
name: "Nova Lite",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.06,
|
||||
output: 0.24,
|
||||
cacheRead: 0.015,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 300000,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.amazon.nova-micro-v1:0": {
|
||||
id: "us.amazon.nova-micro-v1:0",
|
||||
name: "Nova Micro",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.035,
|
||||
output: 0.14,
|
||||
cacheRead: 0.00875,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.amazon.nova-premier-v1:0": {
|
||||
id: "us.amazon.nova-premier-v1:0",
|
||||
name: "Nova Premier",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 2.5,
|
||||
output: 12.5,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1000000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.amazon.nova-pro-v1:0": {
|
||||
id: "us.amazon.nova-pro-v1:0",
|
||||
name: "Nova Pro",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.8,
|
||||
output: 3.2,
|
||||
cacheRead: 0.2,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 300000,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.anthropic.claude-3-7-sonnet-20250219-v1:0": {
|
||||
id: "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
|
||||
name: "Claude Sonnet 3.7",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 3,
|
||||
output: 15,
|
||||
cacheRead: 0.3,
|
||||
cacheWrite: 3.75,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 8192,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.anthropic.claude-opus-4-1-20250805-v1:0": {
|
||||
id: "us.anthropic.claude-opus-4-1-20250805-v1:0",
|
||||
name: "Claude Opus 4.1",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 15,
|
||||
output: 75,
|
||||
cacheRead: 1.5,
|
||||
cacheWrite: 18.75,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 32000,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.anthropic.claude-opus-4-20250514-v1:0": {
|
||||
id: "us.anthropic.claude-opus-4-20250514-v1:0",
|
||||
name: "Claude Opus 4",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 15,
|
||||
output: 75,
|
||||
cacheRead: 1.5,
|
||||
cacheWrite: 18.75,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 32000,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.deepseek.r1-v1:0": {
|
||||
id: "us.deepseek.r1-v1:0",
|
||||
name: "DeepSeek-R1",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 1.35,
|
||||
output: 5.4,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.meta.llama3-2-11b-instruct-v1:0": {
|
||||
id: "us.meta.llama3-2-11b-instruct-v1:0",
|
||||
name: "Llama 3.2 11B Instruct",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.16,
|
||||
output: 0.16,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.meta.llama3-2-1b-instruct-v1:0": {
|
||||
id: "us.meta.llama3-2-1b-instruct-v1:0",
|
||||
name: "Llama 3.2 1B Instruct",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.1,
|
||||
output: 0.1,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.meta.llama3-2-3b-instruct-v1:0": {
|
||||
id: "us.meta.llama3-2-3b-instruct-v1:0",
|
||||
name: "Llama 3.2 3B Instruct",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.15,
|
||||
output: 0.15,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 131000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.meta.llama3-2-90b-instruct-v1:0": {
|
||||
id: "us.meta.llama3-2-90b-instruct-v1:0",
|
||||
name: "Llama 3.2 90B Instruct",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.72,
|
||||
output: 0.72,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.meta.llama3-3-70b-instruct-v1:0": {
|
||||
id: "us.meta.llama3-3-70b-instruct-v1:0",
|
||||
name: "Llama 3.3 70B Instruct",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.72,
|
||||
output: 0.72,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.meta.llama4-maverick-17b-instruct-v1:0": {
|
||||
id: "us.meta.llama4-maverick-17b-instruct-v1:0",
|
||||
name: "Llama 4 Maverick 17B Instruct",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.24,
|
||||
output: 0.97,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1000000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
"us.meta.llama4-scout-17b-instruct-v1:0": {
|
||||
id: "us.meta.llama4-scout-17b-instruct-v1:0",
|
||||
name: "Llama 4 Scout 17B Instruct",
|
||||
api: "bedrock-converse-stream",
|
||||
provider: "amazon-bedrock",
|
||||
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
|
||||
reasoning: false,
|
||||
input: ["text", "image"],
|
||||
cost: {
|
||||
input: 0.17,
|
||||
output: 0.66,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 3500000,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"bedrock-converse-stream">,
|
||||
},
|
||||
"anthropic": {
|
||||
"claude-3-5-haiku-20241022": {
|
||||
id: "claude-3-5-haiku-20241022",
|
||||
|
|
@ -3660,7 +4546,7 @@ export const MODELS = {
|
|||
cacheWrite: 6.25,
|
||||
},
|
||||
contextWindow: 200000,
|
||||
maxTokens: 32000,
|
||||
maxTokens: 64000,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"anthropic/claude-sonnet-4": {
|
||||
id: "anthropic/claude-sonnet-4",
|
||||
|
|
@ -3977,13 +4863,13 @@ export const MODELS = {
|
|||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0.39999999999999997,
|
||||
output: 1.75,
|
||||
input: 0.44999999999999996,
|
||||
output: 2.1500000000000004,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 163840,
|
||||
maxTokens: 65536,
|
||||
contextWindow: 131072,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"openai-completions">,
|
||||
"deepseek/deepseek-r1-distill-llama-70b": {
|
||||
id: "deepseek/deepseek-r1-distill-llama-70b",
|
||||
|
|
|
|||
511
packages/ai/src/providers/amazon-bedrock.ts
Normal file
511
packages/ai/src/providers/amazon-bedrock.ts
Normal file
|
|
@ -0,0 +1,511 @@
|
|||
import {
|
||||
BedrockRuntimeClient,
|
||||
StopReason as BedrockStopReason,
|
||||
type Tool as BedrockTool,
|
||||
type ContentBlock,
|
||||
type ContentBlockDeltaEvent,
|
||||
type ContentBlockStartEvent,
|
||||
type ContentBlockStopEvent,
|
||||
ConversationRole,
|
||||
ConverseStreamCommand,
|
||||
type ConverseStreamMetadataEvent,
|
||||
ImageFormat,
|
||||
type Message,
|
||||
type ToolChoice,
|
||||
type ToolConfiguration,
|
||||
ToolResultStatus,
|
||||
} from "@aws-sdk/client-bedrock-runtime";
|
||||
|
||||
import { calculateCost } from "../models.js";
|
||||
import type {
|
||||
Api,
|
||||
AssistantMessage,
|
||||
Context,
|
||||
Model,
|
||||
StopReason,
|
||||
StreamFunction,
|
||||
StreamOptions,
|
||||
TextContent,
|
||||
ThinkingBudgets,
|
||||
ThinkingContent,
|
||||
ThinkingLevel,
|
||||
Tool,
|
||||
ToolCall,
|
||||
ToolResultMessage,
|
||||
} from "../types.js";
|
||||
import { AssistantMessageEventStream } from "../utils/event-stream.js";
|
||||
import { parseStreamingJson } from "../utils/json-parse.js";
|
||||
import { sanitizeSurrogates } from "../utils/sanitize-unicode.js";
|
||||
|
||||
export interface BedrockOptions extends StreamOptions {
|
||||
region?: string;
|
||||
profile?: string;
|
||||
toolChoice?: "auto" | "any" | "none" | { type: "tool"; name: string };
|
||||
/* See https://docs.aws.amazon.com/bedrock/latest/userguide/inference-reasoning.html for supported models. */
|
||||
reasoning?: ThinkingLevel;
|
||||
/* Custom token budgets per thinking level. Overrides default budgets. */
|
||||
thinkingBudgets?: ThinkingBudgets;
|
||||
/* Only supported by Claude 4.x models, see https://docs.aws.amazon.com/bedrock/latest/userguide/claude-messages-extended-thinking.html#claude-messages-extended-thinking-tool-use-interleaved */
|
||||
interleavedThinking?: boolean;
|
||||
}
|
||||
|
||||
type Block = (TextContent | ThinkingContent | ToolCall) & { index?: number; partialJson?: string };
|
||||
|
||||
export const streamBedrock: StreamFunction<"bedrock-converse-stream"> = (
|
||||
model: Model<"bedrock-converse-stream">,
|
||||
context: Context,
|
||||
options: BedrockOptions,
|
||||
): AssistantMessageEventStream => {
|
||||
const stream = new AssistantMessageEventStream();
|
||||
|
||||
(async () => {
|
||||
const output: AssistantMessage = {
|
||||
role: "assistant",
|
||||
content: [],
|
||||
api: "bedrock-converse-stream" as Api,
|
||||
provider: model.provider,
|
||||
model: model.id,
|
||||
usage: {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
totalTokens: 0,
|
||||
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },
|
||||
},
|
||||
stopReason: "stop",
|
||||
timestamp: Date.now(),
|
||||
};
|
||||
|
||||
const blocks = output.content as Block[];
|
||||
|
||||
try {
|
||||
const client = new BedrockRuntimeClient({
|
||||
region: options.region || process.env.AWS_REGION || process.env.AWS_DEFAULT_REGION || "us-east-1",
|
||||
profile: options.profile,
|
||||
});
|
||||
|
||||
const command = new ConverseStreamCommand({
|
||||
modelId: model.id,
|
||||
messages: convertMessages(context),
|
||||
system: context.systemPrompt ? [{ text: sanitizeSurrogates(context.systemPrompt) }] : undefined,
|
||||
inferenceConfig: { maxTokens: options.maxTokens, temperature: options.temperature },
|
||||
toolConfig: convertToolConfig(context.tools, options.toolChoice),
|
||||
additionalModelRequestFields: buildAdditionalModelRequestFields(model, options),
|
||||
});
|
||||
|
||||
const response = await client.send(command, { abortSignal: options.signal });
|
||||
|
||||
for await (const item of response.stream!) {
|
||||
if (item.messageStart) {
|
||||
if (item.messageStart.role !== ConversationRole.ASSISTANT) {
|
||||
throw new Error("Unexpected assistant message start but got user message start instead");
|
||||
}
|
||||
stream.push({ type: "start", partial: output });
|
||||
} else if (item.contentBlockStart) {
|
||||
handleContentBlockStart(item.contentBlockStart, blocks, output, stream);
|
||||
} else if (item.contentBlockDelta) {
|
||||
handleContentBlockDelta(item.contentBlockDelta, blocks, output, stream);
|
||||
} else if (item.contentBlockStop) {
|
||||
handleContentBlockStop(item.contentBlockStop, blocks, output, stream);
|
||||
} else if (item.messageStop) {
|
||||
output.stopReason = mapStopReason(item.messageStop.stopReason);
|
||||
} else if (item.metadata) {
|
||||
handleMetadata(item.metadata, model, output);
|
||||
} else if (item.internalServerException) {
|
||||
throw new Error(`Internal server error: ${item.internalServerException.message}`);
|
||||
} else if (item.modelStreamErrorException) {
|
||||
throw new Error(`Model stream error: ${item.modelStreamErrorException.message}`);
|
||||
} else if (item.validationException) {
|
||||
throw new Error(`Validation error: ${item.validationException.message}`);
|
||||
} else if (item.throttlingException) {
|
||||
throw new Error(`Throttling error: ${item.throttlingException.message}`);
|
||||
} else if (item.serviceUnavailableException) {
|
||||
throw new Error(`Service unavailable: ${item.serviceUnavailableException.message}`);
|
||||
}
|
||||
}
|
||||
|
||||
if (options.signal?.aborted) {
|
||||
throw new Error("Request was aborted");
|
||||
}
|
||||
|
||||
if (output.stopReason === "error" || output.stopReason === "aborted") {
|
||||
throw new Error("An unknown error occurred");
|
||||
}
|
||||
|
||||
stream.push({ type: "done", reason: output.stopReason, message: output });
|
||||
stream.end();
|
||||
} catch (error) {
|
||||
for (const block of output.content) {
|
||||
delete (block as Block).index;
|
||||
delete (block as Block).partialJson;
|
||||
}
|
||||
output.stopReason = options.signal?.aborted ? "aborted" : "error";
|
||||
output.errorMessage = error instanceof Error ? error.message : JSON.stringify(error);
|
||||
stream.push({ type: "error", reason: output.stopReason, error: output });
|
||||
stream.end();
|
||||
}
|
||||
})();
|
||||
|
||||
return stream;
|
||||
};
|
||||
|
||||
function handleContentBlockStart(
|
||||
event: ContentBlockStartEvent,
|
||||
blocks: Block[],
|
||||
output: AssistantMessage,
|
||||
stream: AssistantMessageEventStream,
|
||||
): void {
|
||||
const index = event.contentBlockIndex!;
|
||||
const start = event.start;
|
||||
|
||||
if (start?.toolUse) {
|
||||
const block: Block = {
|
||||
type: "toolCall",
|
||||
id: start.toolUse.toolUseId || "",
|
||||
name: start.toolUse.name || "",
|
||||
arguments: {},
|
||||
partialJson: "",
|
||||
index,
|
||||
};
|
||||
output.content.push(block);
|
||||
stream.push({ type: "toolcall_start", contentIndex: blocks.length - 1, partial: output });
|
||||
}
|
||||
}
|
||||
|
||||
function handleContentBlockDelta(
|
||||
event: ContentBlockDeltaEvent,
|
||||
blocks: Block[],
|
||||
output: AssistantMessage,
|
||||
stream: AssistantMessageEventStream,
|
||||
): void {
|
||||
const contentBlockIndex = event.contentBlockIndex!;
|
||||
const delta = event.delta;
|
||||
let index = blocks.findIndex((b) => b.index === contentBlockIndex);
|
||||
let block = blocks[index];
|
||||
|
||||
if (delta?.text !== undefined) {
|
||||
// If no text block exists yet, create one, as `handleContentBlockStart` is not sent for text blocks
|
||||
if (!block) {
|
||||
const newBlock: Block = { type: "text", text: "", index: contentBlockIndex };
|
||||
output.content.push(newBlock);
|
||||
index = blocks.length - 1;
|
||||
block = blocks[index];
|
||||
stream.push({ type: "text_start", contentIndex: index, partial: output });
|
||||
}
|
||||
if (block.type === "text") {
|
||||
block.text += delta.text;
|
||||
stream.push({ type: "text_delta", contentIndex: index, delta: delta.text, partial: output });
|
||||
}
|
||||
} else if (delta?.toolUse && block?.type === "toolCall") {
|
||||
block.partialJson = (block.partialJson || "") + (delta.toolUse.input || "");
|
||||
block.arguments = parseStreamingJson(block.partialJson);
|
||||
stream.push({ type: "toolcall_delta", contentIndex: index, delta: delta.toolUse.input || "", partial: output });
|
||||
} else if (delta?.reasoningContent) {
|
||||
let thinkingBlock = block;
|
||||
let thinkingIndex = index;
|
||||
|
||||
if (!thinkingBlock) {
|
||||
const newBlock: Block = { type: "thinking", thinking: "", thinkingSignature: "", index: contentBlockIndex };
|
||||
output.content.push(newBlock);
|
||||
thinkingIndex = blocks.length - 1;
|
||||
thinkingBlock = blocks[thinkingIndex];
|
||||
stream.push({ type: "thinking_start", contentIndex: thinkingIndex, partial: output });
|
||||
}
|
||||
|
||||
if (thinkingBlock?.type === "thinking") {
|
||||
if (delta.reasoningContent.text) {
|
||||
thinkingBlock.thinking += delta.reasoningContent.text;
|
||||
stream.push({
|
||||
type: "thinking_delta",
|
||||
contentIndex: thinkingIndex,
|
||||
delta: delta.reasoningContent.text,
|
||||
partial: output,
|
||||
});
|
||||
}
|
||||
if (delta.reasoningContent.signature) {
|
||||
thinkingBlock.thinkingSignature =
|
||||
(thinkingBlock.thinkingSignature || "") + delta.reasoningContent.signature;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
function handleMetadata(
|
||||
event: ConverseStreamMetadataEvent,
|
||||
model: Model<"bedrock-converse-stream">,
|
||||
output: AssistantMessage,
|
||||
): void {
|
||||
if (event.usage) {
|
||||
output.usage.input = event.usage.inputTokens || 0;
|
||||
output.usage.output = event.usage.outputTokens || 0;
|
||||
output.usage.cacheRead = event.usage.cacheReadInputTokens || 0;
|
||||
output.usage.cacheWrite = event.usage.cacheWriteInputTokens || 0;
|
||||
output.usage.totalTokens = event.usage.totalTokens || output.usage.input + output.usage.output;
|
||||
calculateCost(model, output.usage);
|
||||
}
|
||||
}
|
||||
|
||||
function handleContentBlockStop(
|
||||
event: ContentBlockStopEvent,
|
||||
blocks: Block[],
|
||||
output: AssistantMessage,
|
||||
stream: AssistantMessageEventStream,
|
||||
): void {
|
||||
const index = blocks.findIndex((b) => b.index === event.contentBlockIndex);
|
||||
const block = blocks[index];
|
||||
if (!block) return;
|
||||
delete (block as Block).index;
|
||||
|
||||
switch (block.type) {
|
||||
case "text":
|
||||
stream.push({ type: "text_end", contentIndex: index, content: block.text, partial: output });
|
||||
break;
|
||||
case "thinking":
|
||||
stream.push({ type: "thinking_end", contentIndex: index, content: block.thinking, partial: output });
|
||||
break;
|
||||
case "toolCall":
|
||||
block.arguments = parseStreamingJson(block.partialJson);
|
||||
delete (block as Block).partialJson;
|
||||
stream.push({ type: "toolcall_end", contentIndex: index, toolCall: block, partial: output });
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
function convertMessages(context: Context): Message[] {
|
||||
const result: Message[] = [];
|
||||
const messages = context.messages;
|
||||
|
||||
for (let i = 0; i < messages.length; i++) {
|
||||
const m = messages[i];
|
||||
|
||||
switch (m.role) {
|
||||
case "user":
|
||||
result.push({
|
||||
role: ConversationRole.USER,
|
||||
content:
|
||||
typeof m.content === "string"
|
||||
? [{ text: sanitizeSurrogates(m.content) }]
|
||||
: m.content.map((c) => {
|
||||
switch (c.type) {
|
||||
case "text":
|
||||
return { text: sanitizeSurrogates(c.text) };
|
||||
case "image":
|
||||
return { image: createImageBlock(c.mimeType, c.data) };
|
||||
default:
|
||||
throw new Error("Unknown user content type");
|
||||
}
|
||||
}),
|
||||
});
|
||||
break;
|
||||
case "assistant": {
|
||||
// Skip assistant messages with empty content (e.g., from aborted requests)
|
||||
// Bedrock rejects messages with empty content arrays
|
||||
if (m.content.length === 0) {
|
||||
continue;
|
||||
}
|
||||
const contentBlocks: ContentBlock[] = [];
|
||||
for (const c of m.content) {
|
||||
switch (c.type) {
|
||||
case "text":
|
||||
// Skip empty text blocks
|
||||
if (c.text.trim().length === 0) continue;
|
||||
contentBlocks.push({ text: sanitizeSurrogates(c.text) });
|
||||
break;
|
||||
case "toolCall":
|
||||
contentBlocks.push({
|
||||
toolUse: { toolUseId: c.id, name: c.name, input: c.arguments },
|
||||
});
|
||||
break;
|
||||
case "thinking":
|
||||
// Skip empty thinking blocks
|
||||
if (c.thinking.trim().length === 0) continue;
|
||||
contentBlocks.push({
|
||||
reasoningContent: {
|
||||
reasoningText: { text: sanitizeSurrogates(c.thinking), signature: c.thinkingSignature },
|
||||
},
|
||||
});
|
||||
break;
|
||||
default:
|
||||
throw new Error("Unknown assistant content type");
|
||||
}
|
||||
}
|
||||
// Skip if all content blocks were filtered out
|
||||
if (contentBlocks.length === 0) {
|
||||
continue;
|
||||
}
|
||||
result.push({
|
||||
role: ConversationRole.ASSISTANT,
|
||||
content: contentBlocks,
|
||||
});
|
||||
break;
|
||||
}
|
||||
case "toolResult": {
|
||||
// Collect all consecutive toolResult messages into a single user message
|
||||
// Bedrock requires all tool results to be in one message
|
||||
const toolResults: ContentBlock.ToolResultMember[] = [];
|
||||
|
||||
// Add current tool result
|
||||
for (const c of m.content) {
|
||||
toolResults.push({
|
||||
toolResult: {
|
||||
toolUseId: m.toolCallId,
|
||||
content: [
|
||||
c.type === "image"
|
||||
? { image: createImageBlock(c.mimeType, c.data) }
|
||||
: { text: sanitizeSurrogates(c.text) },
|
||||
],
|
||||
status: m.isError ? ToolResultStatus.ERROR : ToolResultStatus.SUCCESS,
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
// Look ahead for consecutive toolResult messages
|
||||
let j = i + 1;
|
||||
while (j < messages.length && messages[j].role === "toolResult") {
|
||||
const nextMsg = messages[j] as ToolResultMessage;
|
||||
for (const c of nextMsg.content) {
|
||||
toolResults.push({
|
||||
toolResult: {
|
||||
toolUseId: nextMsg.toolCallId,
|
||||
content: [
|
||||
c.type === "image"
|
||||
? { image: createImageBlock(c.mimeType, c.data) }
|
||||
: { text: sanitizeSurrogates(c.text) },
|
||||
],
|
||||
status: nextMsg.isError ? ToolResultStatus.ERROR : ToolResultStatus.SUCCESS,
|
||||
},
|
||||
});
|
||||
}
|
||||
j++;
|
||||
}
|
||||
|
||||
// Skip the messages we've already processed
|
||||
i = j - 1;
|
||||
|
||||
result.push({
|
||||
role: ConversationRole.USER,
|
||||
content: toolResults,
|
||||
});
|
||||
break;
|
||||
}
|
||||
default:
|
||||
throw new Error("Unknown message role");
|
||||
}
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
function convertToolConfig(
|
||||
tools: Tool[] | undefined,
|
||||
toolChoice: BedrockOptions["toolChoice"],
|
||||
): ToolConfiguration | undefined {
|
||||
if (!tools?.length || toolChoice === "none") return undefined;
|
||||
|
||||
const bedrockTools: BedrockTool[] = tools.map((tool) => ({
|
||||
toolSpec: {
|
||||
name: tool.name,
|
||||
description: tool.description,
|
||||
inputSchema: { json: tool.parameters },
|
||||
},
|
||||
}));
|
||||
|
||||
let bedrockToolChoice: ToolChoice | undefined;
|
||||
switch (toolChoice) {
|
||||
case "auto":
|
||||
bedrockToolChoice = { auto: {} };
|
||||
break;
|
||||
case "any":
|
||||
bedrockToolChoice = { any: {} };
|
||||
break;
|
||||
default:
|
||||
if (toolChoice?.type === "tool") {
|
||||
bedrockToolChoice = { tool: { name: toolChoice.name } };
|
||||
}
|
||||
}
|
||||
|
||||
return { tools: bedrockTools, toolChoice: bedrockToolChoice };
|
||||
}
|
||||
|
||||
function mapStopReason(reason: string | undefined): StopReason {
|
||||
switch (reason) {
|
||||
case BedrockStopReason.END_TURN:
|
||||
case BedrockStopReason.STOP_SEQUENCE:
|
||||
return "stop";
|
||||
case BedrockStopReason.MAX_TOKENS:
|
||||
case BedrockStopReason.MODEL_CONTEXT_WINDOW_EXCEEDED:
|
||||
return "length";
|
||||
case BedrockStopReason.TOOL_USE:
|
||||
return "toolUse";
|
||||
default:
|
||||
return "error";
|
||||
}
|
||||
}
|
||||
|
||||
function buildAdditionalModelRequestFields(
|
||||
model: Model<"bedrock-converse-stream">,
|
||||
options: BedrockOptions,
|
||||
): Record<string, any> | undefined {
|
||||
if (!options.reasoning || !model.reasoning) {
|
||||
return undefined;
|
||||
}
|
||||
|
||||
if (model.id.includes("anthropic.claude")) {
|
||||
const defaultBudgets: Record<ThinkingLevel, number> = {
|
||||
minimal: 1024,
|
||||
low: 2048,
|
||||
medium: 8192,
|
||||
high: 16384,
|
||||
xhigh: 16384, // Claude doesn't support xhigh, clamp to high
|
||||
};
|
||||
|
||||
// Custom budgets override defaults (xhigh not in ThinkingBudgets, use high)
|
||||
const level = options.reasoning === "xhigh" ? "high" : options.reasoning;
|
||||
const budget = options.thinkingBudgets?.[level] ?? defaultBudgets[options.reasoning];
|
||||
|
||||
const result: Record<string, any> = {
|
||||
thinking: {
|
||||
type: "enabled",
|
||||
budget_tokens: budget,
|
||||
},
|
||||
};
|
||||
|
||||
if (options.interleavedThinking) {
|
||||
result.anthropic_beta = ["interleaved-thinking-2025-05-14"];
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
return undefined;
|
||||
}
|
||||
|
||||
function createImageBlock(mimeType: string, data: string) {
|
||||
let format: ImageFormat;
|
||||
switch (mimeType) {
|
||||
case "image/jpeg":
|
||||
case "image/jpg":
|
||||
format = ImageFormat.JPEG;
|
||||
break;
|
||||
case "image/png":
|
||||
format = ImageFormat.PNG;
|
||||
break;
|
||||
case "image/gif":
|
||||
format = ImageFormat.GIF;
|
||||
break;
|
||||
case "image/webp":
|
||||
format = ImageFormat.WEBP;
|
||||
break;
|
||||
default:
|
||||
throw new Error(`Unknown image type: ${mimeType}`);
|
||||
}
|
||||
|
||||
const binaryString = atob(data);
|
||||
const bytes = new Uint8Array(binaryString.length);
|
||||
for (let i = 0; i < binaryString.length; i++) {
|
||||
bytes[i] = binaryString.charCodeAt(i);
|
||||
}
|
||||
|
||||
return { source: { bytes }, format };
|
||||
}
|
||||
|
|
@ -287,7 +287,7 @@ export const streamAnthropic: StreamFunction<"anthropic-messages"> = (
|
|||
}
|
||||
|
||||
if (output.stopReason === "aborted" || output.stopReason === "error") {
|
||||
throw new Error("An unkown error ocurred");
|
||||
throw new Error("An unknown error occurred");
|
||||
}
|
||||
|
||||
stream.push({ type: "done", reason: output.stopReason, message: output });
|
||||
|
|
|
|||
|
|
@ -2,6 +2,7 @@ import { existsSync } from "node:fs";
|
|||
import { homedir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import { supportsXhigh } from "./models.js";
|
||||
import { type BedrockOptions, streamBedrock } from "./providers/amazon-bedrock.js";
|
||||
import { type AnthropicOptions, streamAnthropic } from "./providers/anthropic.js";
|
||||
import { type GoogleOptions, streamGoogle } from "./providers/google.js";
|
||||
import {
|
||||
|
|
@ -74,6 +75,20 @@ export function getEnvApiKey(provider: any): string | undefined {
|
|||
}
|
||||
}
|
||||
|
||||
if (provider === "amazon-bedrock") {
|
||||
// Amazon Bedrock supports multiple credential sources:
|
||||
// 1. AWS_PROFILE - named profile from ~/.aws/credentials
|
||||
// 2. AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY - standard IAM keys
|
||||
// 3. AWS_BEARER_TOKEN_BEDROCK - Bedrock API keys (bearer token)
|
||||
if (
|
||||
process.env.AWS_PROFILE ||
|
||||
(process.env.AWS_ACCESS_KEY_ID && process.env.AWS_SECRET_ACCESS_KEY) ||
|
||||
process.env.AWS_BEARER_TOKEN_BEDROCK
|
||||
) {
|
||||
return "<authenticated>";
|
||||
}
|
||||
}
|
||||
|
||||
const envMap: Record<string, string> = {
|
||||
openai: "OPENAI_API_KEY",
|
||||
google: "GEMINI_API_KEY",
|
||||
|
|
@ -98,6 +113,9 @@ export function stream<TApi extends Api>(
|
|||
// Vertex AI uses Application Default Credentials, not API keys
|
||||
if (model.api === "google-vertex") {
|
||||
return streamGoogleVertex(model as Model<"google-vertex">, context, options as GoogleVertexOptions);
|
||||
} else if (model.api === "bedrock-converse-stream") {
|
||||
// Bedrock doesn't have any API keys instead it sources credentials from standard AWS env variables or from given AWS profile.
|
||||
return streamBedrock(model as Model<"bedrock-converse-stream">, context, (options || {}) as BedrockOptions);
|
||||
}
|
||||
|
||||
const apiKey = options?.apiKey || getEnvApiKey(model.provider);
|
||||
|
|
@ -156,6 +174,10 @@ export function streamSimple<TApi extends Api>(
|
|||
if (model.api === "google-vertex") {
|
||||
const providerOptions = mapOptionsForApi(model, options, undefined);
|
||||
return stream(model, context, providerOptions);
|
||||
} else if (model.api === "bedrock-converse-stream") {
|
||||
// Bedrock doesn't have any API keys instead it sources credentials from standard AWS env variables or from given AWS profile.
|
||||
const providerOptions = mapOptionsForApi(model, options, undefined);
|
||||
return stream(model, context, providerOptions);
|
||||
}
|
||||
|
||||
const apiKey = options?.apiKey || getEnvApiKey(model.provider);
|
||||
|
|
@ -228,6 +250,13 @@ function mapOptionsForApi<TApi extends Api>(
|
|||
} satisfies AnthropicOptions;
|
||||
}
|
||||
|
||||
case "bedrock-converse-stream":
|
||||
return {
|
||||
...base,
|
||||
reasoning: options?.reasoning,
|
||||
thinkingBudgets: options?.thinkingBudgets,
|
||||
} satisfies BedrockOptions;
|
||||
|
||||
case "openai-completions":
|
||||
return {
|
||||
...base,
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
import type { BedrockOptions } from "./providers/amazon-bedrock.js";
|
||||
import type { AnthropicOptions } from "./providers/anthropic.js";
|
||||
import type { GoogleOptions } from "./providers/google.js";
|
||||
import type { GoogleGeminiCliOptions } from "./providers/google-gemini-cli.js";
|
||||
|
|
@ -14,12 +15,14 @@ export type Api =
|
|||
| "openai-responses"
|
||||
| "openai-codex-responses"
|
||||
| "anthropic-messages"
|
||||
| "bedrock-converse-stream"
|
||||
| "google-generative-ai"
|
||||
| "google-gemini-cli"
|
||||
| "google-vertex";
|
||||
|
||||
export interface ApiOptionsMap {
|
||||
"anthropic-messages": AnthropicOptions;
|
||||
"bedrock-converse-stream": BedrockOptions;
|
||||
"openai-completions": OpenAICompletionsOptions;
|
||||
"openai-responses": OpenAIResponsesOptions;
|
||||
"openai-codex-responses": OpenAICodexResponsesOptions;
|
||||
|
|
@ -40,6 +43,7 @@ const _exhaustive: _CheckExhaustive = true;
|
|||
export type OptionsForApi<TApi extends Api> = ApiOptionsMap[TApi];
|
||||
|
||||
export type KnownProvider =
|
||||
| "amazon-bedrock"
|
||||
| "anthropic"
|
||||
| "google"
|
||||
| "google-gemini-cli"
|
||||
|
|
|
|||
|
|
@ -24,6 +24,7 @@ import type { AssistantMessage } from "../types.js";
|
|||
*/
|
||||
const OVERFLOW_PATTERNS = [
|
||||
/prompt is too long/i, // Anthropic
|
||||
/input is too long for requested model/i, // Amazon Bedrock
|
||||
/exceeds the context window/i, // OpenAI (Completions & Responses API)
|
||||
/input token count.*exceeds the maximum/i, // Google (Gemini)
|
||||
/maximum prompt length is \d+/i, // xAI (Grok)
|
||||
|
|
|
|||
|
|
@ -2,6 +2,7 @@ import { describe, expect, it } from "vitest";
|
|||
import { getModel } from "../src/models.js";
|
||||
import { complete, stream } from "../src/stream.js";
|
||||
import type { Api, Context, Model, OptionsForApi } from "../src/types.js";
|
||||
import { hasBedrockCredentials } from "./bedrock-utils.js";
|
||||
import { resolveApiKey } from "./oauth.js";
|
||||
|
||||
// Resolve OAuth tokens at module level (async, runs before tests)
|
||||
|
|
@ -66,6 +67,35 @@ async function testImmediateAbort<TApi extends Api>(llm: Model<TApi>, options: O
|
|||
expect(response.stopReason).toBe("aborted");
|
||||
}
|
||||
|
||||
async function testAbortThenNewMessage<TApi extends Api>(llm: Model<TApi>, options: OptionsForApi<TApi> = {}) {
|
||||
// First request: abort immediately before any response content arrives
|
||||
const controller = new AbortController();
|
||||
controller.abort();
|
||||
|
||||
const context: Context = {
|
||||
messages: [{ role: "user", content: "Hello, how are you?", timestamp: Date.now() }],
|
||||
};
|
||||
|
||||
const abortedResponse = await complete(llm, context, { ...options, signal: controller.signal });
|
||||
expect(abortedResponse.stopReason).toBe("aborted");
|
||||
// The aborted message has empty content since we aborted before anything arrived
|
||||
expect(abortedResponse.content.length).toBe(0);
|
||||
|
||||
// Add the aborted assistant message to context (this is what happens in the real coding agent)
|
||||
context.messages.push(abortedResponse);
|
||||
|
||||
// Second request: send a new message - this should work even with the aborted message in context
|
||||
context.messages.push({
|
||||
role: "user",
|
||||
content: "What is 2 + 2?",
|
||||
timestamp: Date.now(),
|
||||
});
|
||||
|
||||
const followUp = await complete(llm, context, options);
|
||||
expect(followUp.stopReason).toBe("stop");
|
||||
expect(followUp.content.length).toBeGreaterThan(0);
|
||||
}
|
||||
|
||||
describe("AI Providers Abort Tests", () => {
|
||||
describe.skipIf(!process.env.GEMINI_API_KEY)("Google Provider Abort", () => {
|
||||
const llm = getModel("google", "gemini-2.5-flash");
|
||||
|
|
@ -154,4 +184,20 @@ describe("AI Providers Abort Tests", () => {
|
|||
await testImmediateAbort(llm, { apiKey: openaiCodexToken });
|
||||
});
|
||||
});
|
||||
|
||||
describe.skipIf(!hasBedrockCredentials())("Amazon Bedrock Provider Abort", () => {
|
||||
const llm = getModel("amazon-bedrock", "global.anthropic.claude-sonnet-4-5-20250929-v1:0");
|
||||
|
||||
it("should abort mid-stream", { retry: 3 }, async () => {
|
||||
await testAbortSignal(llm, { reasoning: "medium" });
|
||||
});
|
||||
|
||||
it("should handle immediate abort", { retry: 3 }, async () => {
|
||||
await testImmediateAbort(llm);
|
||||
});
|
||||
|
||||
it("should handle abort then new message", { retry: 3 }, async () => {
|
||||
await testAbortThenNewMessage(llm);
|
||||
});
|
||||
});
|
||||
});
|
||||
|
|
|
|||
66
packages/ai/test/bedrock-models.test.ts
Normal file
66
packages/ai/test/bedrock-models.test.ts
Normal file
|
|
@ -0,0 +1,66 @@
|
|||
/**
|
||||
* A test suite to ensure all configured Amazon Bedrock models are usable.
|
||||
*
|
||||
* This is here to make sure we got correct model identifiers from models.dev and other sources.
|
||||
* Because Amazon Bedrock requires cross-region inference in some models,
|
||||
* plain model identifiers are not always usable and it requires tweaking of model identifiers to use cross-region inference.
|
||||
* See https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html#inference-profiles-support-system for more details.
|
||||
*
|
||||
* This test suite is not enabled by default unless AWS credentials and `BEDROCK_EXTENSIVE_MODEL_TEST` environment variables are set.
|
||||
* This test suite takes ~2 minutes to run. Because not all models are available in all regions,
|
||||
* it's recommended to use `us-west-2` region for best coverage for running this test suite.
|
||||
*
|
||||
* You can run this test suite with:
|
||||
* ```bash
|
||||
* $ AWS_REGION=us-west-2 BEDROCK_EXTENSIVE_MODEL_TEST=1 AWS_PROFILE=... npm test -- ./test/bedrock-models.test.ts
|
||||
* ```
|
||||
*/
|
||||
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { getModels } from "../src/models.js";
|
||||
import { complete } from "../src/stream.js";
|
||||
import type { Context } from "../src/types.js";
|
||||
import { hasBedrockCredentials } from "./bedrock-utils.js";
|
||||
|
||||
describe("Amazon Bedrock Models", () => {
|
||||
const models = getModels("amazon-bedrock");
|
||||
|
||||
it("should get all available Bedrock models", () => {
|
||||
expect(models.length).toBeGreaterThan(0);
|
||||
console.log(`Found ${models.length} Bedrock models`);
|
||||
});
|
||||
|
||||
if (hasBedrockCredentials() && process.env.BEDROCK_EXTENSIVE_MODEL_TEST) {
|
||||
for (const model of models) {
|
||||
it(`should make a simple request with ${model.id}`, { timeout: 10_000 }, async () => {
|
||||
const context: Context = {
|
||||
systemPrompt: "You are a helpful assistant. Be extremely concise.",
|
||||
messages: [
|
||||
{
|
||||
role: "user",
|
||||
content: "Reply with exactly: 'OK'",
|
||||
timestamp: Date.now(),
|
||||
},
|
||||
],
|
||||
};
|
||||
|
||||
const response = await complete(model, context);
|
||||
|
||||
expect(response.role).toBe("assistant");
|
||||
expect(response.content).toBeTruthy();
|
||||
expect(response.content.length).toBeGreaterThan(0);
|
||||
expect(response.usage.input + response.usage.cacheRead).toBeGreaterThan(0);
|
||||
expect(response.usage.output).toBeGreaterThan(0);
|
||||
expect(response.errorMessage).toBeFalsy();
|
||||
|
||||
const textContent = response.content
|
||||
.filter((b) => b.type === "text")
|
||||
.map((b) => (b.type === "text" ? b.text : ""))
|
||||
.join("")
|
||||
.trim();
|
||||
expect(textContent).toBeTruthy();
|
||||
console.log(`${model.id}: ${textContent.substring(0, 100)}`);
|
||||
});
|
||||
}
|
||||
}
|
||||
});
|
||||
18
packages/ai/test/bedrock-utils.ts
Normal file
18
packages/ai/test/bedrock-utils.ts
Normal file
|
|
@ -0,0 +1,18 @@
|
|||
/**
|
||||
* Utility functions for Amazon Bedrock tests
|
||||
*/
|
||||
|
||||
/**
|
||||
* Check if any valid AWS credentials are configured for Bedrock.
|
||||
* Returns true if any of the following are set:
|
||||
* - AWS_PROFILE (named profile from ~/.aws/credentials)
|
||||
* - AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY (IAM keys)
|
||||
* - AWS_BEARER_TOKEN_BEDROCK (Bedrock API key)
|
||||
*/
|
||||
export function hasBedrockCredentials(): boolean {
|
||||
return !!(
|
||||
process.env.AWS_PROFILE ||
|
||||
(process.env.AWS_ACCESS_KEY_ID && process.env.AWS_SECRET_ACCESS_KEY) ||
|
||||
process.env.AWS_BEARER_TOKEN_BEDROCK
|
||||
);
|
||||
}
|
||||
|
|
@ -18,6 +18,7 @@ import { getModel } from "../src/models.js";
|
|||
import { complete } from "../src/stream.js";
|
||||
import type { AssistantMessage, Context, Model, Usage } from "../src/types.js";
|
||||
import { isContextOverflow } from "../src/utils/overflow.js";
|
||||
import { hasBedrockCredentials } from "./bedrock-utils.js";
|
||||
import { resolveApiKey } from "./oauth.js";
|
||||
|
||||
// Resolve OAuth tokens at module level (async, runs before tests)
|
||||
|
|
@ -284,6 +285,22 @@ describe("Context overflow error handling", () => {
|
|||
);
|
||||
});
|
||||
|
||||
// =============================================================================
|
||||
// Amazon Bedrock
|
||||
// Expected pattern: "Input is too long for requested model"
|
||||
// =============================================================================
|
||||
|
||||
describe.skipIf(!hasBedrockCredentials())("Amazon Bedrock", () => {
|
||||
it("claude-sonnet-4-5 - should detect overflow via isContextOverflow", async () => {
|
||||
const model = getModel("amazon-bedrock", "global.anthropic.claude-sonnet-4-5-20250929-v1:0");
|
||||
const result = await testContextOverflow(model, "");
|
||||
logResult(result);
|
||||
|
||||
expect(result.stopReason).toBe("error");
|
||||
expect(isContextOverflow(result.response, model.contextWindow)).toBe(true);
|
||||
}, 120000);
|
||||
});
|
||||
|
||||
// =============================================================================
|
||||
// xAI
|
||||
// Expected pattern: "maximum prompt length is X but the request contains Y"
|
||||
|
|
|
|||
|
|
@ -2,6 +2,7 @@ import { describe, expect, it } from "vitest";
|
|||
import { getModel } from "../src/models.js";
|
||||
import { complete } from "../src/stream.js";
|
||||
import type { Api, AssistantMessage, Context, Model, OptionsForApi, UserMessage } from "../src/types.js";
|
||||
import { hasBedrockCredentials } from "./bedrock-utils.js";
|
||||
import { resolveApiKey } from "./oauth.js";
|
||||
|
||||
// Resolve OAuth tokens at module level (async, runs before tests)
|
||||
|
|
@ -321,6 +322,26 @@ describe("AI Providers Empty Message Tests", () => {
|
|||
});
|
||||
});
|
||||
|
||||
describe.skipIf(!hasBedrockCredentials())("Amazon Bedrock Provider Empty Messages", () => {
|
||||
const llm = getModel("amazon-bedrock", "global.anthropic.claude-sonnet-4-5-20250929-v1:0");
|
||||
|
||||
it("should handle empty content array", { retry: 3, timeout: 30000 }, async () => {
|
||||
await testEmptyMessage(llm);
|
||||
});
|
||||
|
||||
it("should handle empty string content", { retry: 3, timeout: 30000 }, async () => {
|
||||
await testEmptyStringMessage(llm);
|
||||
});
|
||||
|
||||
it("should handle whitespace-only content", { retry: 3, timeout: 30000 }, async () => {
|
||||
await testWhitespaceOnlyMessage(llm);
|
||||
});
|
||||
|
||||
it("should handle empty assistant message in conversation", { retry: 3, timeout: 30000 }, async () => {
|
||||
await testEmptyAssistantMessage(llm);
|
||||
});
|
||||
});
|
||||
|
||||
// =========================================================================
|
||||
// OAuth-based providers (credentials from ~/.pi/agent/oauth.json)
|
||||
// =========================================================================
|
||||
|
|
|
|||
|
|
@ -75,6 +75,7 @@ import { afterAll, beforeAll, describe, expect, it } from "vitest";
|
|||
import { getModel } from "../src/models.js";
|
||||
import { complete } from "../src/stream.js";
|
||||
import type { Api, Context, ImageContent, Model, OptionsForApi, UserMessage } from "../src/types.js";
|
||||
import { hasBedrockCredentials } from "./bedrock-utils.js";
|
||||
|
||||
const __filename = fileURLToPath(import.meta.url);
|
||||
const __dirname = dirname(__filename);
|
||||
|
|
@ -840,6 +841,79 @@ describe("Image Limits E2E Tests", () => {
|
|||
});
|
||||
});
|
||||
|
||||
// -------------------------------------------------------------------------
|
||||
// Amazon Bedrock (claude-sonnet-4-5)
|
||||
// Limits: 100 images (Anthropic), 5MB per image, 8000px max dimension
|
||||
// -------------------------------------------------------------------------
|
||||
describe.skipIf(!hasBedrockCredentials())("Amazon Bedrock (claude-sonnet-4-5)", () => {
|
||||
const model = getModel("amazon-bedrock", "global.anthropic.claude-sonnet-4-5-20250929-v1:0");
|
||||
|
||||
it("should accept a small number of images (5)", async () => {
|
||||
const result = await testImageCount(model, 5, smallImage);
|
||||
expect(result.success, result.error).toBe(true);
|
||||
});
|
||||
|
||||
it("should find maximum image count limit", { timeout: 600000 }, async () => {
|
||||
// Anthropic limit: 100 images
|
||||
const { limit, lastError } = await findLimit((count) => testImageCount(model, count, smallImage), 20, 120, 20);
|
||||
console.log(`\n Bedrock max images: ~${limit} (last error: ${lastError})`);
|
||||
expect(limit).toBeGreaterThanOrEqual(80);
|
||||
expect(limit).toBeLessThanOrEqual(100);
|
||||
});
|
||||
|
||||
it("should find maximum image size limit", { timeout: 600000 }, async () => {
|
||||
const MB = 1024 * 1024;
|
||||
// Anthropic limit: 5MB per image
|
||||
const sizes = [1, 2, 3, 4, 5, 6];
|
||||
|
||||
let lastSuccess = 0;
|
||||
let lastError: string | undefined;
|
||||
|
||||
for (const sizeMB of sizes) {
|
||||
console.log(` Testing size: ${sizeMB}MB...`);
|
||||
const imageBase64 = generateImageWithSize(sizeMB * MB, `size-${sizeMB}mb.png`);
|
||||
const result = await testImageSize(model, imageBase64);
|
||||
if (result.success) {
|
||||
lastSuccess = sizeMB;
|
||||
console.log(` SUCCESS`);
|
||||
} else {
|
||||
lastError = result.error;
|
||||
console.log(` FAILED: ${result.error?.substring(0, 100)}`);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
console.log(`\n Bedrock max image size: ~${lastSuccess}MB (last error: ${lastError})`);
|
||||
expect(lastSuccess).toBeGreaterThanOrEqual(1);
|
||||
});
|
||||
|
||||
it("should find maximum image dimension limit", { timeout: 600000 }, async () => {
|
||||
// Anthropic limit: 8000px
|
||||
const dimensions = [1000, 2000, 4000, 6000, 8000, 10000];
|
||||
|
||||
let lastSuccess = 0;
|
||||
let lastError: string | undefined;
|
||||
|
||||
for (const dim of dimensions) {
|
||||
console.log(` Testing dimension: ${dim}x${dim}...`);
|
||||
const imageBase64 = generateImage(dim, dim, `dim-${dim}.png`);
|
||||
const result = await testImageDimensions(model, imageBase64);
|
||||
if (result.success) {
|
||||
lastSuccess = dim;
|
||||
console.log(` SUCCESS`);
|
||||
} else {
|
||||
lastError = result.error;
|
||||
console.log(` FAILED: ${result.error?.substring(0, 100)}`);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
console.log(`\n Bedrock max dimension: ~${lastSuccess}px (last error: ${lastError})`);
|
||||
expect(lastSuccess).toBeGreaterThanOrEqual(6000);
|
||||
expect(lastSuccess).toBeLessThanOrEqual(8000);
|
||||
});
|
||||
});
|
||||
|
||||
// =========================================================================
|
||||
// MAX SIZE IMAGES TEST
|
||||
// =========================================================================
|
||||
|
|
@ -898,6 +972,38 @@ describe("Image Limits E2E Tests", () => {
|
|||
},
|
||||
);
|
||||
|
||||
// Amazon Bedrock (Claude) - 5MB per image limit, same as Anthropic direct
|
||||
// Using 3MB to stay under 5MB limit
|
||||
it.skipIf(!hasBedrockCredentials())(
|
||||
"Bedrock: max ~3MB images before rejection",
|
||||
{ timeout: 900000 },
|
||||
async () => {
|
||||
const model = getModel("amazon-bedrock", "global.anthropic.claude-sonnet-4-5-20250929-v1:0");
|
||||
const image3mb = getImageAtSize(3);
|
||||
// Similar to Anthropic, test progressively
|
||||
const counts = [1, 2, 4, 6, 8, 10, 12];
|
||||
|
||||
let lastSuccess = 0;
|
||||
let lastError: string | undefined;
|
||||
|
||||
for (const count of counts) {
|
||||
console.log(` Testing ${count} x ~3MB images...`);
|
||||
const result = await testImageCount(model, count, image3mb);
|
||||
if (result.success) {
|
||||
lastSuccess = count;
|
||||
console.log(` SUCCESS`);
|
||||
} else {
|
||||
lastError = result.error;
|
||||
console.log(` FAILED: ${result.error?.substring(0, 150)}`);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
console.log(`\n Bedrock max ~3MB images: ${lastSuccess} (last error: ${lastError})`);
|
||||
expect(lastSuccess).toBeGreaterThanOrEqual(1);
|
||||
},
|
||||
);
|
||||
|
||||
// OpenAI - 20MB per image documented, we found ≥25MB works
|
||||
// Test with 15MB images to stay safely under limit
|
||||
it.skipIf(!process.env.OPENAI_API_KEY)(
|
||||
|
|
|
|||
|
|
@ -5,6 +5,7 @@ import { describe, expect, it } from "vitest";
|
|||
import type { Api, Context, Model, Tool, ToolResultMessage } from "../src/index.js";
|
||||
import { complete, getModel } from "../src/index.js";
|
||||
import type { OptionsForApi } from "../src/types.js";
|
||||
import { hasBedrockCredentials } from "./bedrock-utils.js";
|
||||
import { resolveApiKey } from "./oauth.js";
|
||||
|
||||
// Resolve OAuth tokens at module level (async, runs before tests)
|
||||
|
|
@ -273,6 +274,18 @@ describe("Tool Results with Images", () => {
|
|||
});
|
||||
});
|
||||
|
||||
describe.skipIf(!hasBedrockCredentials())("Amazon Bedrock Provider (claude-sonnet-4-5)", () => {
|
||||
const llm = getModel("amazon-bedrock", "global.anthropic.claude-sonnet-4-5-20250929-v1:0");
|
||||
|
||||
it("should handle tool result with only image", { retry: 3, timeout: 30000 }, async () => {
|
||||
await handleToolWithImageResult(llm);
|
||||
});
|
||||
|
||||
it("should handle tool result with text and image", { retry: 3, timeout: 30000 }, async () => {
|
||||
await handleToolWithTextAndImageResult(llm);
|
||||
});
|
||||
});
|
||||
|
||||
// =========================================================================
|
||||
// OAuth-based providers (credentials from ~/.pi/agent/oauth.json)
|
||||
// =========================================================================
|
||||
|
|
|
|||
|
|
@ -8,6 +8,7 @@ import { getModel } from "../src/models.js";
|
|||
import { complete, stream } from "../src/stream.js";
|
||||
import type { Api, Context, ImageContent, Model, OptionsForApi, Tool, ToolResultMessage } from "../src/types.js";
|
||||
import { StringEnum } from "../src/utils/typebox-helpers.js";
|
||||
import { hasBedrockCredentials } from "./bedrock-utils.js";
|
||||
import { resolveApiKey } from "./oauth.js";
|
||||
|
||||
const __filename = fileURLToPath(import.meta.url);
|
||||
|
|
@ -356,7 +357,7 @@ describe("Generate E2E Tests", () => {
|
|||
await handleStreaming(llm);
|
||||
});
|
||||
|
||||
it("should handle ", { retry: 3 }, async () => {
|
||||
it("should handle thinking", { retry: 3 }, async () => {
|
||||
await handleThinking(llm, { thinking: { enabled: true, budgetTokens: 1024 } });
|
||||
});
|
||||
|
||||
|
|
@ -907,6 +908,34 @@ describe("Generate E2E Tests", () => {
|
|||
});
|
||||
});
|
||||
|
||||
describe.skipIf(!hasBedrockCredentials())("Amazon Bedrock Provider (claude-sonnet-4-5)", () => {
|
||||
const llm = getModel("amazon-bedrock", "global.anthropic.claude-sonnet-4-5-20250929-v1:0");
|
||||
|
||||
it("should complete basic text generation", { retry: 3 }, async () => {
|
||||
await basicTextGeneration(llm);
|
||||
});
|
||||
|
||||
it("should handle tool calling", { retry: 3 }, async () => {
|
||||
await handleToolCall(llm);
|
||||
});
|
||||
|
||||
it("should handle streaming", { retry: 3 }, async () => {
|
||||
await handleStreaming(llm);
|
||||
});
|
||||
|
||||
it("should handle thinking", { retry: 3 }, async () => {
|
||||
await handleThinking(llm, { reasoning: "medium" });
|
||||
});
|
||||
|
||||
it("should handle multi-turn with thinking and tools", { retry: 3 }, async () => {
|
||||
await multiTurn(llm, { reasoning: "high" });
|
||||
});
|
||||
|
||||
it("should handle image input", { retry: 3 }, async () => {
|
||||
await handleImage(llm);
|
||||
});
|
||||
});
|
||||
|
||||
// Check if ollama is installed and local LLM tests are enabled
|
||||
let ollamaInstalled = false;
|
||||
if (!process.env.PI_NO_LOCAL_LLM) {
|
||||
|
|
|
|||
|
|
@ -2,6 +2,7 @@ import { describe, expect, it } from "vitest";
|
|||
import { getModel } from "../src/models.js";
|
||||
import { stream } from "../src/stream.js";
|
||||
import type { Api, Context, Model, OptionsForApi } from "../src/types.js";
|
||||
import { hasBedrockCredentials } from "./bedrock-utils.js";
|
||||
import { resolveApiKey } from "./oauth.js";
|
||||
|
||||
// Resolve OAuth tokens at module level (async, runs before tests)
|
||||
|
|
@ -44,7 +45,7 @@ async function testTokensOnAbort<TApi extends Api>(llm: Model<TApi>, options: Op
|
|||
|
||||
expect(msg.stopReason).toBe("aborted");
|
||||
|
||||
// OpenAI providers, OpenAI Codex, Gemini CLI, zai, and the GPT-OSS model on Antigravity only send usage in the final chunk,
|
||||
// OpenAI providers, OpenAI Codex, Gemini CLI, zai, Amazon Bedrock, and the GPT-OSS model on Antigravity only send usage in the final chunk,
|
||||
// so when aborted they have no token stats Anthropic and Google send usage information early in the stream
|
||||
if (
|
||||
llm.api === "openai-completions" ||
|
||||
|
|
@ -52,6 +53,7 @@ async function testTokensOnAbort<TApi extends Api>(llm: Model<TApi>, options: Op
|
|||
llm.api === "openai-codex-responses" ||
|
||||
llm.provider === "google-gemini-cli" ||
|
||||
llm.provider === "zai" ||
|
||||
llm.provider === "amazon-bedrock" ||
|
||||
(llm.provider === "google-antigravity" && llm.id.includes("gpt-oss"))
|
||||
) {
|
||||
expect(msg.usage.input).toBe(0);
|
||||
|
|
@ -230,4 +232,12 @@ describe("Token Statistics on Abort", () => {
|
|||
},
|
||||
);
|
||||
});
|
||||
|
||||
describe.skipIf(!hasBedrockCredentials())("Amazon Bedrock Provider", () => {
|
||||
const llm = getModel("amazon-bedrock", "global.anthropic.claude-sonnet-4-5-20250929-v1:0");
|
||||
|
||||
it("should include token stats when aborted mid-stream", { retry: 3, timeout: 30000 }, async () => {
|
||||
await testTokensOnAbort(llm);
|
||||
});
|
||||
});
|
||||
});
|
||||
|
|
|
|||
|
|
@ -3,6 +3,7 @@ import { describe, expect, it } from "vitest";
|
|||
import { getModel } from "../src/models.js";
|
||||
import { complete } from "../src/stream.js";
|
||||
import type { Api, Context, Model, OptionsForApi, Tool } from "../src/types.js";
|
||||
import { hasBedrockCredentials } from "./bedrock-utils.js";
|
||||
import { resolveApiKey } from "./oauth.js";
|
||||
|
||||
// Resolve OAuth tokens at module level (async, runs before tests)
|
||||
|
|
@ -170,6 +171,14 @@ describe("Tool Call Without Result Tests", () => {
|
|||
});
|
||||
});
|
||||
|
||||
describe.skipIf(!hasBedrockCredentials())("Amazon Bedrock Provider", () => {
|
||||
const model = getModel("amazon-bedrock", "global.anthropic.claude-sonnet-4-5-20250929-v1:0");
|
||||
|
||||
it("should filter out tool calls without corresponding tool results", { retry: 3, timeout: 30000 }, async () => {
|
||||
await testToolCallWithoutResult(model);
|
||||
});
|
||||
});
|
||||
|
||||
// =========================================================================
|
||||
// OAuth-based providers (credentials from ~/.pi/agent/oauth.json)
|
||||
// =========================================================================
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@ import { describe, expect, it } from "vitest";
|
|||
import { getModel } from "../src/models.js";
|
||||
import { complete } from "../src/stream.js";
|
||||
import type { Api, Context, Model, OptionsForApi, Usage } from "../src/types.js";
|
||||
import { hasBedrockCredentials } from "./bedrock-utils.js";
|
||||
import { resolveApiKey } from "./oauth.js";
|
||||
|
||||
// Resolve OAuth tokens at module level (async, runs before tests)
|
||||
|
|
@ -535,6 +536,25 @@ describe("totalTokens field", () => {
|
|||
);
|
||||
});
|
||||
|
||||
describe.skipIf(!hasBedrockCredentials())("Amazon Bedrock", () => {
|
||||
it(
|
||||
"claude-sonnet-4-5 - should return totalTokens equal to sum of components",
|
||||
{ retry: 3, timeout: 60000 },
|
||||
async () => {
|
||||
const llm = getModel("amazon-bedrock", "global.anthropic.claude-sonnet-4-5-20250929-v1:0");
|
||||
|
||||
console.log(`\nAmazon Bedrock / ${llm.id}:`);
|
||||
const { first, second } = await testTotalTokensWithCache(llm);
|
||||
|
||||
logUsage("First request", first);
|
||||
logUsage("Second request", second);
|
||||
|
||||
assertTotalTokensEqualsComponents(first);
|
||||
assertTotalTokensEqualsComponents(second);
|
||||
},
|
||||
);
|
||||
});
|
||||
|
||||
// =========================================================================
|
||||
// OpenAI Codex (OAuth)
|
||||
// =========================================================================
|
||||
|
|
|
|||
|
|
@ -3,6 +3,7 @@ import { describe, expect, it } from "vitest";
|
|||
import { getModel } from "../src/models.js";
|
||||
import { complete } from "../src/stream.js";
|
||||
import type { Api, Context, Model, OptionsForApi, ToolResultMessage } from "../src/types.js";
|
||||
import { hasBedrockCredentials } from "./bedrock-utils.js";
|
||||
import { resolveApiKey } from "./oauth.js";
|
||||
|
||||
// Empty schema for test tools - must be proper OBJECT type for Cloud Code Assist
|
||||
|
|
@ -617,6 +618,22 @@ describe("AI Providers Unicode Surrogate Pair Tests", () => {
|
|||
});
|
||||
});
|
||||
|
||||
describe.skipIf(!hasBedrockCredentials())("Amazon Bedrock Provider Unicode Handling", () => {
|
||||
const llm = getModel("amazon-bedrock", "global.anthropic.claude-sonnet-4-5-20250929-v1:0");
|
||||
|
||||
it("should handle emoji in tool results", { retry: 3, timeout: 30000 }, async () => {
|
||||
await testEmojiInToolResults(llm);
|
||||
});
|
||||
|
||||
it("should handle real-world LinkedIn comment data with emoji", { retry: 3, timeout: 30000 }, async () => {
|
||||
await testRealWorldLinkedInData(llm);
|
||||
});
|
||||
|
||||
it("should handle unpaired high surrogate (0xD83D) in tool results", { retry: 3, timeout: 30000 }, async () => {
|
||||
await testUnpairedHighSurrogate(llm);
|
||||
});
|
||||
});
|
||||
|
||||
describe("OpenAI Codex Provider Unicode Handling", () => {
|
||||
it.skipIf(!openaiCodexToken)(
|
||||
"gpt-5.2-codex - should handle emoji in tool results",
|
||||
|
|
|
|||
|
|
@ -211,6 +211,29 @@ Credentials stored in `~/.pi/agent/auth.json`. Use `/logout` to clear.
|
|||
- **Token expired / refresh failed:** Run `/login` again for the provider to refresh credentials.
|
||||
- **Usage limits (429):** Wait for the reset window; pi will surface a friendly message with the approximate retry time.
|
||||
|
||||
**Amazon Bedrock:**
|
||||
|
||||
Amazon Bedrock supports multiple authentication methods:
|
||||
|
||||
```bash
|
||||
# Option 1: AWS Profile (from ~/.aws/credentials)
|
||||
export AWS_PROFILE=your-profile-name
|
||||
|
||||
# Option 2: IAM Access Keys
|
||||
export AWS_ACCESS_KEY_ID=AKIA...
|
||||
export AWS_SECRET_ACCESS_KEY=...
|
||||
|
||||
# Option 3: Bedrock API Key (bearer token)
|
||||
export AWS_BEARER_TOKEN_BEDROCK=...
|
||||
|
||||
# Optional: Set region (defaults to us-east-1)
|
||||
export AWS_REGION=us-east-1
|
||||
|
||||
pi --provider amazon-bedrock --model global.anthropic.claude-sonnet-4-5-20250929-v1:0
|
||||
```
|
||||
|
||||
See [Supported foundation models in Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html).
|
||||
|
||||
### Quick Start
|
||||
|
||||
```bash
|
||||
|
|
|
|||
|
|
@ -243,6 +243,11 @@ ${chalk.bold("Environment Variables:")}
|
|||
XAI_API_KEY - xAI Grok API key
|
||||
OPENROUTER_API_KEY - OpenRouter API key
|
||||
ZAI_API_KEY - ZAI API key
|
||||
AWS_PROFILE - AWS profile for Amazon Bedrock
|
||||
AWS_ACCESS_KEY_ID - AWS access key for Amazon Bedrock
|
||||
AWS_SECRET_ACCESS_KEY - AWS secret key for Amazon Bedrock
|
||||
AWS_BEARER_TOKEN_BEDROCK - Bedrock API key (bearer token)
|
||||
AWS_REGION - AWS region for Amazon Bedrock (e.g., us-east-1)
|
||||
${ENV_AGENT_DIR.padEnd(23)} - Session storage directory (default: ~/${CONFIG_DIR_NAME}/agent)
|
||||
|
||||
${chalk.bold("Available Tools (default: read, bash, edit, write):")}
|
||||
|
|
|
|||
|
|
@ -25,7 +25,7 @@ function formatTokenCount(count: number): string {
|
|||
* List available models, optionally filtered by search pattern
|
||||
*/
|
||||
export async function listModels(modelRegistry: ModelRegistry, searchPattern?: string): Promise<void> {
|
||||
const models = await modelRegistry.getAvailable();
|
||||
const models = modelRegistry.getAvailable();
|
||||
|
||||
if (models.length === 0) {
|
||||
console.log("No models available. Set API keys in environment variables.");
|
||||
|
|
|
|||
|
|
@ -37,6 +37,7 @@ const ModelDefinitionSchema = Type.Object({
|
|||
Type.Literal("openai-codex-responses"),
|
||||
Type.Literal("anthropic-messages"),
|
||||
Type.Literal("google-generative-ai"),
|
||||
Type.Literal("bedrock-converse-stream"),
|
||||
]),
|
||||
),
|
||||
reasoning: Type.Boolean(),
|
||||
|
|
@ -63,6 +64,7 @@ const ProviderConfigSchema = Type.Object({
|
|||
Type.Literal("openai-codex-responses"),
|
||||
Type.Literal("anthropic-messages"),
|
||||
Type.Literal("google-generative-ai"),
|
||||
Type.Literal("bedrock-converse-stream"),
|
||||
]),
|
||||
),
|
||||
headers: Type.Optional(Type.Record(Type.String(), Type.String())),
|
||||
|
|
|
|||
|
|
@ -11,6 +11,7 @@ import type { ModelRegistry } from "./model-registry.js";
|
|||
|
||||
/** Default model IDs for each known provider */
|
||||
export const defaultModelPerProvider: Record<KnownProvider, string> = {
|
||||
"amazon-bedrock": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
|
||||
anthropic: "claude-sonnet-4-5",
|
||||
openai: "gpt-5.1-codex",
|
||||
"openai-codex": "gpt-5.2-codex",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue