@effect/ai-anthropic

0.27.0

Patch Changes

• Updated dependencies [fffdee0]:
  • effect@3.22.0
  • @effect/ai@0.37.0
  • @effect/experimental@0.61.0
  • @effect/platform@0.97.0

0.26.1

Patch Changes

• #6288 cfa2bbf Thanks @davidgoli! - populate cachedInputTokens in streaming responses from cache_read_input_tokens

• Updated dependencies [307d54a, d95868a, 95c7d2e, d24511f, 99d5575]:

  • effect@3.21.5
  • @effect/platform@0.96.3

0.26.0

Patch Changes

• Updated dependencies [02ae8fb, e2126bc, f7e836e]:
  • @effect/ai@0.36.0
  • effect@3.21.3

0.25.0

Patch Changes

• Updated dependencies [f7bb09b, bd7552a, ad1a7eb, 0d32048, 0d32048]:
  • effect@3.21.0
  • @effect/ai@0.35.0
  • @effect/experimental@0.60.0
  • @effect/platform@0.96.0

0.24.0

Patch Changes

• Updated dependencies [fc82e81, 82996bc, 4d97a61, f6b0960, 8798a84]:
  • effect@3.20.0
  • @effect/ai@0.34.0
  • @effect/experimental@0.59.0
  • @effect/platform@0.95.0

0.23.0

Patch Changes

• Updated dependencies [77eeb86, ff7053f, 287c32c]:
  • effect@3.19.13
  • @effect/platform@0.94.0
  • @effect/ai@0.33.0
  • @effect/experimental@0.58.0

0.22.0

Patch Changes

• Updated dependencies [3c15d5f, 3863fa8, 2a03c76, 24a1685]:
  • effect@3.19.0
  • @effect/platform@0.93.0
  • @effect/ai@0.32.0
  • @effect/experimental@0.57.0

0.21.1

Patch Changes

• #5644 7de0bfc Thanks @IMax153! - Ensure that model accepts a string in Anthropic request schemas

0.21.0

Minor Changes

• #5621 4c3bdfb Thanks @IMax153! - Remove Either / EitherEncoded from tool call results.

  Specifically, the encoding of tool call results as an Either / EitherEncoded has been removed and is replaced by encoding the tool call success / failure directly into the result property.

  To allow type-safe discrimination between a tool call result which was a success vs. one that was a failure, an isFailure property has also been added to the "tool-result" part. If isFailure is true, then the tool call handler result was an error.

  1
  import * as AnthropicClient from "@effect/ai-anthropic/AnthropicClient"
  2
  import * as AnthropicLanguageModel from "@effect/ai-anthropic/AnthropicLanguageModel"
  3
  import * as LanguageModel from "@effect/ai/LanguageModel"
  4
  import * as Tool from "@effect/ai/Tool"
  5
  import * as Toolkit from "@effect/ai/Toolkit"
  6
  import * as NodeHttpClient from "@effect/platform-node/NodeHttpClient"
  7
  import { Config, Effect, Layer, Schema, Stream } from "effect"
  8
  
  9
  const Claude = AnthropicLanguageModel.model("claude-4-sonnet-20250514")
  10
  
  11
  const MyTool = Tool.make("MyTool", {
  12
    description: "An example of a tool with success and failure types",
  13
    failureMode: "return", // Return errors in the response
  14
    parameters: { bar: Schema.Number },
  15
    success: Schema.Number,
  16
    failure: Schema.Struct({ reason: Schema.Literal("reason-1", "reason-2") })
  17
  })
  18
  
  19
  const MyToolkit = Toolkit.make(MyTool)
  20
  
  21
  const MyToolkitLayer = MyToolkit.toLayer({
  22
    MyTool: () => Effect.succeed(42)
  23
  })
  24
  
  25
  const program = LanguageModel.streamText({
  26
    prompt: "Tell me about the meaning of life",
  27
    toolkit: MyToolkit
  28
  }).pipe(
  29
    Stream.runForEach((part) => {
  30
      if (part.type === "tool-result" && part.name === "MyTool") {
  31
        // The `isFailure` property can be used to discriminate whether the result
  32
        // of a tool call is a success or a failure
  33
        if (part.isFailure) {
  34
          part.result
  35
          //   ^? { readonly reason: "reason-1" | "reason-2"; }
  36
        } else {
  37
          part.result
  38
          //   ^? number
  39
        }
  40
      }
  41
      return Effect.void
  42
    }),
  43
    Effect.provide(Claude)
  44
  )
  45
  
  46
  const Anthropic = AnthropicClient.layerConfig({
  47
    apiKey: Config.redacted("ANTHROPIC_API_KEY")
  48
  }).pipe(Layer.provide(NodeHttpClient.layerUndici))
  49
  
  50
  program.pipe(Effect.provide([Anthropic, MyToolkitLayer]), Effect.runPromise)

Patch Changes

• Updated dependencies [4c3bdfb]:
  • @effect/ai@0.31.0

0.20.0

Minor Changes

• #5614 c63e658 Thanks @IMax153! - Previously, tool call handler errors were always raised as an expected error in the Effect E channel at the point of execution of the tool call handler (i.e. when a generate* method is invoked on a LanguageModel).

  With this PR, the end user now has control over whether tool call handler errors should be raised as an Effect error, or returned by the SDK to allow, for example, sending that error information to another application.

  Tool Call Specification

  The Tool.make and Tool.providerDefined constructors now take an extra optional parameter called failureMode, which can be set to either "error" or "return".

  1
  import { Tool } from "@effect/ai"
  2
  import { Schema } from "effect"
  3
  
  4
  const MyTool = Tool.make("MyTool", {
  5
    description: "My special tool",
  6
    failureMode: "return" // "error" (default) or "return"
  7
    parameters: {
  8
      myParam: Schema.String
  9
    },
  10
    success: Schema.Struct({
  11
      mySuccess: Schema.String
  12
    }),
  13
    failure: Schema.Struct({
  14
      myFailure: Schema.String
  15
    })
  16
  })

  The semantics of failureMode are as follows:

  • If set to "error" (the default), errors that occur during tool call handler execution will be returned in the error channel of the calling effect
  • If set to "return", errors that occur during tool call handler execution will be captured and returned as part of the tool call result

  Response - Tool Result Parts

  The result field of a "tool-result" part of a large language model provider response is now represented as an Either.

  • If the result is a Left, the result will be the failure specified in the tool call specification
  • If the result is a Right, the result will be the success specified in the tool call specification

  This is only relevant if the end user sets failureMode to "return". If set to "error" (the default), then the result property will always be a Right with the successful result of the tool call handler.

  Similarly the encodedResult field of a "tool-result" part will be represented as an EitherEncoded, where:

  • { _tag: "Left", left: <failure> } represents a tool call handler failure
  • { _tag: "Right", right: <success> } represents a tool call handler success

  Prompt - Tool Result Parts

  The result field of a "tool-result" part of a prompt will now only accept an EitherEncoded as specified above.

Patch Changes

• #5615 1d2e92d Thanks @janglad! - Remove accidental commit of debug console.dir

• Updated dependencies [6ae2f5d, c63e658]:

  • effect@3.18.4
  • @effect/ai@0.30.0

0.19.2

Patch Changes

• #5608 215ed46 Thanks @IMax153! - Fix incorrect detection of either result

• Updated dependencies [8ba4757]:

  • effect@3.18.2

0.19.1

Patch Changes

• #5599 d7eba97 Thanks @IMax153! - Fix provider defined tool results in prompt input

0.19.0

Patch Changes

• Updated dependencies [1c6ab74, 70fe803, c296e32, a098ddf, f8b93ac]:
  • effect@3.18.0
  • @effect/ai@0.29.0
  • @effect/platform@0.92.0
  • @effect/experimental@0.56.0

0.18.2

Patch Changes

• #5571 122aa53 Thanks @IMax153! - Ensure that AI provider clients filter response status for stream requests

0.18.1

Patch Changes

• #5554 800ab2e Thanks @IMax153! - Improve the information available to the user following a model response error

• Updated dependencies [800ab2e, 800ab2e, 800ab2e, 800ab2e, 800ab2e, 800ab2e]:

  • @effect/ai@0.28.2

0.18.0

Patch Changes

• Updated dependencies [d4d86a8]:
  • @effect/platform@0.91.0
  • @effect/ai@0.28.0
  • @effect/experimental@0.55.0

0.17.1

Patch Changes

• #5521 fa49bc8 Thanks @IMax153! - Fix provider metadata and parse tool call parameters safely

• Updated dependencies [fa49bc8]:

  • @effect/ai@0.27.1

0.17.0

Minor Changes

• #5469 42b914a Thanks @IMax153! - Refactor the Effect AI SDK and associated provider packages

  This pull request contains a complete refactor of the base Effect AI SDK package as well as the associated provider integration packages to improve flexibility and enhance ergonomics. Major changes are outlined below.

  Modules

  All modules in the base Effect AI SDK have had the leading Ai prefix dropped from their name (except for the AiError module).

  For example, the AiLanguageModel module is now the LanguageModel module.

  In addition, the AiInput module has been renamed to the Prompt module.

  Prompts

  The Prompt module has been completely redesigned with flexibility in mind.

  The Prompt module now supports building a prompt using either the constructors exposed from the Prompt module, or using raw prompt content parts / messages, which should be familiar to those coming from other AI SDKs.

  In addition, the system option has been removed from all LanguageModel methods and must now be provided as part of the prompt.

  Prompt Constructors

  1
  import { LanguageModel, Prompt } from "@effect/ai"
  2
  
  3
  const textPart = Prompt.makePart("text", {
  4
    text: "What is machine learning?"
  5
  })
  6
  
  7
  const userMessage = Prompt.makeMessage("user", {
  8
    content: [textPart]
  9
  })
  10
  
  11
  const systemMessage = Prompt.makeMessage("system", {
  12
    content: "You are an expert in machine learning"
  13
  })
  14
  
  15
  const program = LanguageModel.generateText({
  16
    prompt: Prompt.fromMessages([systemMessage, userMessage])
  17
  })

  Raw Prompt Input

  1
  import { LanguageModel } from "@effect/ai"
  2
  
  3
  const program = LanguageModel.generateText({
  4
    prompt: [
  5
      { role: "system", content: "You are an expert in machine learning" },
  6
      {
  7
        role: "user",
  8
        content: [{ type: "text", text: "What is machine learning?" }]
  9
      }
  10
    ]
  11
  })

  NOTE: Providing a plain string as a prompt is still supported, and will be converted internally into a user message with a single text content part.

  Provider-Specific Options

  To support specification of provider-specific options when interacting with large language model providers, support has been added for adding provider-specific options to the parts of a Prompt.

  1
  import { LanguageModel } from "@effect/ai"
  2
  import { AnthropicLanguageModel } from "@effect/ai-anthropic"
  3
  
  4
  const Claude = AnthropicLanguageModel.model("claude-sonnet-4-20250514")
  5
  
  6
  const program = LanguageModel.generateText({
  7
    prompt: [
  8
      {
  9
        role: "user",
  10
        content: [{ type: "text", text: "What is machine learning?" }],
  11
        options: {
  12
          anthropic: { cacheControl: { type: "ephemeral", ttl: "1h" } }
  13
        }
  14
      }
  15
    ]
  16
  }).pipe(Effect.provide(Claude))

  Responses

  The Response module has also been completely redesigned to support a wider variety of response parts, particularly when streaming.

  Streaming Responses

  When streaming text via the LanguageModel.streamText method, you will now receive a stream of content parts instead of a stream of responses, which should make it much simpler to filter down the stream to the parts you are interested in.

  In addition, additional content parts will be present in the stream to allow you to track, for example, when a text content part starts / ends.

  Tool Calls / Tool Call Results

  The decoded parts of a Response (as returned by the methods of LanguageModel) are now fully type-safe on tool calls / tool call results. Filtering the content parts of a response to tool calls will narrow the type of the tool call params based on the tool name. Similarly, filtering the response to tool call results will narrow the type of the tool call result based on the tool name.

  1
  import { LanguageModel, Tool, Toolkit } from "@effect/ai"
  2
  import { Effect, Schema } from "effect"
  3
  
  4
  const DadJokeTool = Tool.make("DadJokeTool", {
  5
    parameters: { topic: Schema.String },
  6
    success: Schema.Struct({ joke: Schema.String })
  7
  })
  8
  
  9
  const FooTool = Tool.make("FooTool", {
  10
    parameters: { foo: Schema.Number },
  11
    success: Schema.Struct({ bar: Schema.Boolean })
  12
  })
  13
  
  14
  const MyToolkit = Toolkit.make(DadJokeTool, FooTool)
  15
  
  16
  const program = Effect.gen(function* () {
  17
    const response = yield* LanguageModel.generateText({
  18
      prompt: "Tell me a dad joke",
  19
      toolkit: MyToolkit
  20
    })
  21
  
  22
    for (const toolCall of response.toolCalls) {
  23
      if (toolCall.name === "DadJokeTool") {
  24
        //         ^? "DadJokeTool" | "FooTool"
  25
        toolCall.params
  26
        //       ^? { readonly topic: string }
  27
      }
  28
    }
  29
  
  30
    for (const toolResult of response.toolResults) {
  31
      if (toolResult.name === "DadJokeTool") {
  32
        //           ^? "DadJokeTool" | "FooTool"
  33
        toolResult.result
  34
        //         ^? { readonly joke: string }
  35
      }
  36
    }
  37
  })

  Provider Metadata

  As with provider-specific options, provider-specific metadata is now returned as part of the response from the large language model provider.

  1
  import { LanguageModel } from "@effect/ai"
  2
  import { AnthropicLanguageModel } from "@effect/ai-anthropic"
  3
  import { Effect } from "effect"
  4
  
  5
  const Claude = AnthropicLanguageModel.model("claude-4-sonnet-20250514")
  6
  
  7
  const program = Effect.gen(function* () {
  8
    const response = yield* LanguageModel.generateText({
  9
      prompt: "What is the meaning of life?"
  10
    })
  11
  
  12
    for (const part of response.content) {
  13
      // When metadata **is not** defined for a content part, accessing the
  14
      // provider's key on the part's metadata will return an untyped record
  15
      if (part.type === "text") {
  16
        const metadata = part.metadata.anthropic
  17
        //    ^? { readonly [x: string]: unknown } | undefined
  18
      }
  19
      // When metadata **is** defined for a content part, accessing the
  20
      // provider's key on the part's metadata will return typed metadata
  21
      if (part.type === "reasoning") {
  22
        const metadata = part.metadata.anthropic
  23
        //    ^? AnthropicReasoningInfo | undefined
  24
      }
  25
    }
  26
  }).pipe(Effect.provide(Claude))

  Tool Calls

  The Tool module has been enhanced to support provider-defined tools (e.g. web search, computer use, etc.). Large language model providers which support calling their own tools now have a separate module present in their provider integration packages which contain definitions for their tools.

  These provider-defined tools can be included alongside user-defined tools in existing Toolkits. Provider-defined tools that require a user-space handler will be raise a type error in the associated Toolkit layer if no such handler is defined.

  1
  import { LanguageModel, Tool, Toolkit } from "@effect/ai"
  2
  import { AnthropicTool } from "@effect/ai-anthropic"
  3
  import { Schema } from "effect"
  4
  
  5
  const DadJokeTool = Tool.make("DadJokeTool", {
  6
    parameters: { topic: Schema.String },
  7
    success: Schema.Struct({ joke: Schema.String })
  8
  })
  9
  
  10
  const MyToolkit = Toolkit.make(
  11
    DadJokeTool,
  12
    AnthropicTool.WebSearch_20250305({ max_uses: 1 })
  13
  )
  14
  
  15
  const program = LanguageModel.generateText({
  16
    prompt: "Search the web for a dad joke",
  17
    toolkit: MyToolkit
  18
  })

  AiError

  The AiError type has been refactored into a union of different error types which can be raised by the Effect AI SDK. The goal of defining separate error types is to allow providing the end-user with more granular information about the error that occurred.

  For now, the following errors have been defined. More error types may be added over time based upon necessity / use case.

  1
  type AiError =
  2
    | HttpRequestError,
  3
    | HttpResponseError,
  4
    | MalformedInput,
  5
    | MalformedOutput,
  6
    | UnknownError

Patch Changes

• Updated dependencies [42b914a]:
  • @effect/ai@0.27.0

0.16.2

Patch Changes

• #5476 18ec398 Thanks @richburdon! - fix total token count

0.16.1

Patch Changes

• #5474 5f5ae17 Thanks @IMax153! - Ensure that the finish part is emitted when streaming text from Anthropic

0.16.0

Patch Changes

• Updated dependencies []:
  • @effect/ai@0.26.0
  • @effect/experimental@0.54.6

0.15.1

Patch Changes

• 4bcf799 Thanks @dmaretskyi! - Fix tools with no parameters not being called

0.15.0

Patch Changes

• Updated dependencies [5a0f4f1]:
  • effect@3.17.1
  • @effect/ai@0.25.0
  • @effect/experimental@0.54.0

0.14.0

Patch Changes

• Updated dependencies [7813640]:
  • @effect/platform@0.90.0
  • @effect/ai@0.24.0
  • @effect/experimental@0.54.0

0.13.0

Patch Changes

• Updated dependencies [40c3c87, ed2c74a, 073a1b8, f382e99, e8c7ba5, 7e10415, e9bdece, 8d95eb0]:
  • effect@3.17.0
  • @effect/ai@0.23.0
  • @effect/experimental@0.53.0
  • @effect/platform@0.89.0

0.12.2

Patch Changes

• Updated dependencies [f5dfabf, 17a5ea8, d25f22b]:
  • effect@3.16.14
  • @effect/platform@0.88.1
  • @effect/experimental@0.52.1
  • @effect/ai@0.22.1

0.12.1

Patch Changes

• #5209 3deaa66 Thanks @tim-smart! - fix ai layerConfig regression, to allow for conditional Config variables

0.12.0

Patch Changes

• Updated dependencies [27206d7, dbabf5e]:
  • @effect/platform@0.88.0
  • @effect/ai@0.22.0
  • @effect/experimental@0.52.0

0.11.19

Patch Changes

• Updated dependencies [c1c05a8, 81fe4a2]:
  • effect@3.16.13
  • @effect/ai@0.21.17
  • @effect/experimental@0.51.14
  • @effect/platform@0.87.13

0.11.18

Patch Changes

• #5186 e5692ab Thanks @IMax153! - Do not use Config.Wrap for AI provider layerConfig

• Updated dependencies [32ba77a, d5e25b2]:

  • @effect/platform@0.87.12
  • @effect/ai@0.21.16
  • @effect/experimental@0.51.13

0.11.17

Patch Changes

• Updated dependencies [001392b, 7bfb099]:
  • @effect/platform@0.87.11
  • @effect/ai@0.21.15
  • @effect/experimental@0.51.12

0.11.16

Patch Changes

• Updated dependencies [678318d, 678318d]:
  • @effect/platform@0.87.10
  • @effect/ai@0.21.14
  • @effect/experimental@0.51.11

0.11.15

Patch Changes

• Updated dependencies [54514a2]:
  • @effect/platform@0.87.9
  • @effect/ai@0.21.13
  • @effect/experimental@0.51.10

0.11.14

Patch Changes

• Updated dependencies [4ce4f82]:
  • @effect/platform@0.87.8
  • @effect/experimental@0.51.9
  • @effect/ai@0.21.12

0.11.13

Patch Changes

• #5029 d92d12a Thanks @IMax153! - Cleanup AiLanguageModel construction and finish basic support for gemini

• Updated dependencies [d92d12a, 25ca0cf, d92d12a]:

  • @effect/ai@0.21.11

0.11.12

Patch Changes

• Updated dependencies [a9b617f, 7e26e86]:
  • @effect/platform@0.87.7
  • @effect/ai@0.21.10
  • @effect/experimental@0.51.8

0.11.11

Patch Changes

• Updated dependencies [030ac21, 905da99, aaae9b1]:
  • @effect/ai@0.21.9
  • effect@3.16.12
  • @effect/experimental@0.51.7
  • @effect/platform@0.87.6

0.11.10

Patch Changes

• Updated dependencies [96c1292]:
  • @effect/experimental@0.51.6
  • @effect/ai@0.21.8

0.11.9

Patch Changes

• Updated dependencies [2fd8676]:
  • @effect/platform@0.87.5
  • @effect/ai@0.21.7
  • @effect/experimental@0.51.5

0.11.8

Patch Changes

• Updated dependencies [e82a4fd]:
  • @effect/platform@0.87.4
  • @effect/ai@0.21.6
  • @effect/experimental@0.51.4

0.11.7

Patch Changes

• Updated dependencies [1b6e396]:
  • @effect/platform@0.87.3
  • @effect/ai@0.21.5
  • @effect/experimental@0.51.3

0.11.6

Patch Changes

• Updated dependencies [4fea68c, b927954, 99590a6, 6c3e24c]:
  • @effect/platform@0.87.2
  • effect@3.16.11
  • @effect/ai@0.21.4
  • @effect/experimental@0.51.2

0.11.5

Patch Changes

• #5121 8e3c565 Thanks @IMax153! - Fix several issues in the generated OpenAPI models for the Anthropic AI provider package.

  The OpenAPI specification that Anthropic maintains for its API is apparently incorrect. Some properties which are marked as nullable but required are sometimes not returned by the API. This fixes the schemas associated with some of those properties, though others may exist / be found that require manual adjustment.

0.11.4

Patch Changes

• #5020 530aa65 Thanks @IMax153! - add Amazon Bedrock AI provider package

0.11.3

Patch Changes

• Updated dependencies [faad30e]:
  • effect@3.16.10
  • @effect/ai@0.21.3
  • @effect/experimental@0.51.1
  • @effect/platform@0.87.1

0.11.2

Patch Changes

• Updated dependencies []:
  • @effect/ai@0.21.2
  • @effect/experimental@0.51.0

0.11.1

Patch Changes

• Updated dependencies [f667373]:
  • @effect/ai@0.21.1
  • @effect/experimental@0.51.0

0.11.0

Patch Changes

• Updated dependencies [b5bac9a]:
  • @effect/platform@0.87.0
  • @effect/ai@0.21.0
  • @effect/experimental@0.51.0

0.10.0

Patch Changes

• Updated dependencies [5137c70, c23d25c, 5137c70, 5137c70]:
  • effect@3.16.9
  • @effect/platform@0.86.0
  • @effect/ai@0.20.0
  • @effect/experimental@0.50.0

0.9.5

Patch Changes

• Updated dependencies [a8d99b2]:
  • @effect/ai@0.19.4
  • @effect/experimental@0.49.2

0.9.4

Patch Changes

• Updated dependencies [914a191]:
  • @effect/platform@0.85.2
  • @effect/ai@0.19.3
  • @effect/experimental@0.49.2

0.9.3

Patch Changes

• #5051 0945c0d Thanks @IMax153! - Fix the generated Anthropic OpenAPI schemas

0.9.2

Patch Changes

• Updated dependencies []:
  • @effect/ai@0.19.2
  • @effect/experimental@0.49.1

0.9.1

Patch Changes

• Updated dependencies [8cb98d5, db2dd3c]:
  • effect@3.16.8
  • @effect/ai@0.19.1
  • @effect/experimental@0.49.1
  • @effect/platform@0.85.1

0.9.0

Patch Changes

• Updated dependencies [93687dd, 93687dd, 93687dd]:
  • @effect/platform@0.85.0
  • @effect/ai@0.19.0
  • @effect/experimental@0.49.0

0.8.16

Patch Changes

• Updated dependencies [daed158]:
  • @effect/ai@0.18.16

0.8.15

Patch Changes

• Updated dependencies [c315989]:
  • @effect/ai@0.18.15

0.8.14

Patch Changes

• Updated dependencies [1bb0d8a, cbac1ac, dd4d380]:
  • effect@3.16.7
  • @effect/ai@0.18.14
  • @effect/experimental@0.48.12
  • @effect/platform@0.84.11

0.8.13

Patch Changes

• Updated dependencies [a5f7595, a02470c, aa3a819, bf369b2, f891d45]:
  • effect@3.16.6
  • @effect/ai@0.18.13
  • @effect/platform@0.84.10
  • @effect/experimental@0.48.11

0.8.12

Patch Changes

• Updated dependencies [bf418ef]:
  • effect@3.16.5
  • @effect/ai@0.18.12
  • @effect/experimental@0.48.10
  • @effect/platform@0.84.9

0.8.11

Patch Changes

• Updated dependencies [2dc5f93]:
  • @effect/ai@0.18.11
  • @effect/experimental@0.48.9

0.8.10

Patch Changes

• Updated dependencies [8b9db77]:
  • @effect/platform@0.84.8
  • @effect/experimental@0.48.9
  • @effect/ai@0.18.10

0.8.9

Patch Changes

• Updated dependencies [74ab9a0, 770008e]:
  • effect@3.16.4
  • @effect/ai@0.18.9
  • @effect/experimental@0.48.8
  • @effect/platform@0.84.7

0.8.8

Patch Changes

• Updated dependencies [a2d57c9]:
  • @effect/experimental@0.48.7
  • @effect/ai@0.18.8

0.8.7

Patch Changes

• Updated dependencies [ceea77a]:
  • @effect/platform@0.84.6
  • @effect/ai@0.18.7
  • @effect/experimental@0.48.6

0.8.6

Patch Changes

• Updated dependencies [85f54ed, ec52c6a]:
  • @effect/ai@0.18.6
  • @effect/platform@0.84.5
  • @effect/experimental@0.48.5

0.8.5

Patch Changes

• Updated dependencies [4ddb28d]:
  • @effect/ai@0.18.5

0.8.4

Patch Changes

• Updated dependencies [87722fc, 36217ee]:
  • effect@3.16.3
  • @effect/ai@0.18.4
  • @effect/experimental@0.48.4
  • @effect/platform@0.84.4

0.8.3

Patch Changes

• Updated dependencies [52c88c4, ab7684f]:
  • @effect/ai@0.18.3
  • @effect/platform@0.84.3
  • @effect/experimental@0.48.3

0.8.2

Patch Changes

• Updated dependencies [0ddf148]:
  • effect@3.16.2
  • @effect/ai@0.18.2
  • @effect/experimental@0.48.2
  • @effect/platform@0.84.2

0.8.1

Patch Changes

• Updated dependencies [71174d0, d615e6e]:
  • @effect/platform@0.84.1
  • effect@3.16.1
  • @effect/ai@0.18.1
  • @effect/experimental@0.48.1

0.8.0

Minor Changes

• #4891 0552674 Thanks @IMax153! - Make AiModel a plain Layer and remove AiPlan in favor of ExecutionPlan

  This release substantially simplifies and improves the ergonomics of using AiModel for various providers. With these changes, an AiModel now returns a plain Layer which can be used to provide services to a program that interacts with large language models.

  Before

  1
  import { AiLanguageModel } from "@effect/ai"
  2
  import { OpenAiClient, OpenAiLanguageModel } from "@effect/ai-openai"
  3
  import { NodeHttpClient } from "@effect/platform-node"
  4
  import { Config, Console, Effect, Layer } from "effect"
  5
  
  6
  // Produces an `AiModel<AiLanguageModel, OpenAiClient>`
  7
  const Gpt4o = OpenAiLanguageModel.model("gpt-4o")
  8
  
  9
  // Generate a dad joke
  10
  const getDadJoke = AiLanguageModel.generateText({
  11
    prompt: "Tell me a dad joke"
  12
  })
  13
  
  14
  const program = Effect.gen(function* () {
  15
    // Build the `AiModel` into a `Provider`
  16
    const gpt4o = yield* Gpt4o
  17
    // Use the built `AiModel` to run the program
  18
    const response = yield* gpt4o.use(getDadJoke)
  19
    // Log the response
  20
    yield* Console.log(response.text)
  21
  })
  22
  
  23
  const OpenAi = OpenAiClient.layerConfig({
  24
    apiKey: Config.redacted("OPENAI_API_KEY")
  25
  }).pipe(Layer.provide(NodeHttpClient.layerUndici))
  26
  
  27
  program.pipe(Effect.provide(OpenAi), Effect.runPromise)

  After

  1
  import { AiLanguageModel } from "@effect/ai"
  2
  import { OpenAiClient, OpenAiLanguageModel } from "@effect/ai-openai"
  3
  import { NodeHttpClient } from "@effect/platform-node"
  4
  import { Config, Console, Effect, Layer } from "effect"
  5
  
  6
  // Produces a `Layer<AiLanguageModel, never, OpenAiClient>`
  7
  const Gpt4o = OpenAiLanguageModel.model("gpt-4o")
  8
  
  9
  const program = Effect.gen(function*() {
  10
    // Generate a dad joke
  11
    const response = yield* AiLanguageModel.generateText({
  12
      prompt: "Tell me a dad joke"
  13
    })
  14
    // Log the response
  15
    yield* Console.log(response.text)
  16
  ).pipe(Effect.provide(Gpt4o))
  17
  
  18
  const OpenAi = OpenAiClient.layerConfig({
  19
    apiKey: Config.redacted("OPENAI_API_KEY")
  20
  }).pipe(Layer.provide(NodeHttpClient.layerUndici))
  21
  
  22
  program.pipe(
  23
    Effect.provide(OpenAi),
  24
    Effect.runPromise
  25
  )

  In addition, AiModel can be yield*’ed to produce a layer with no requirements.

  This shifts the requirements of building the layer into the calling effect, which is particularly useful for creating AI-powered services.

  1
  import { AiLanguageModel } from "@effect/ai"
  2
  import { OpenAiLanguageModel } from "@effect/ai-openai"
  3
  import { Effect } from "effect"
  4
  
  5
  class DadJokes extends Effect.Service<DadJokes>()("DadJokes", {
  6
    effect: Effect.gen(function* () {
  7
      // Yielding the model will return a layer with no requirements
  8
      //
  9
      //      ┌─── Layer<AiLanguageModel>
  10
      //      ▼
  11
      const model = yield* OpenAiLanguageModel.model("gpt-4o")
  12
  
  13
      const getDadJoke = AiLanguageModel.generateText({
  14
        prompt: "Generate a dad joke"
  15
      }).pipe(Effect.provide(model))
  16
  
  17
      return { getDadJoke } as const
  18
    })
  19
  }) {}
  20
  
  21
  // The requirements are lifted into the service constructor
  22
  //
  23
  //          ┌─── Layer<DadJokes, never, OpenAiClient>
  24
  //          ▼
  25
  DadJokes.Default

Patch Changes

• Updated dependencies [ee0bd5d, 5189800, 58bfeaa, 194d748, 0552674, 918c9ea, 9198e6f, 2a370bf, 58ccb91, fd47834]:
  • effect@3.16.0
  • @effect/ai@0.18.0
  • @effect/experimental@0.48.0
  • @effect/platform@0.84.0

0.7.0

Patch Changes

• Updated dependencies [5522520, cc5bb2b]:
  • @effect/platform@0.83.0
  • effect@3.15.5
  • @effect/ai@0.17.0
  • @effect/experimental@0.47.0

0.6.9

Patch Changes

• Updated dependencies [0617b9d]:
  • @effect/platform@0.82.8
  • @effect/ai@0.16.9
  • @effect/experimental@0.46.8

0.6.8

Patch Changes

• Updated dependencies [f570554, 78047e8, c20b95a, 94ada43]:
  • effect@3.15.4
  • @effect/platform@0.82.7
  • @effect/ai@0.16.8
  • @effect/experimental@0.46.7

0.6.7

Patch Changes

• Updated dependencies [618903b]:
  • @effect/platform@0.82.6
  • @effect/ai@0.16.7
  • @effect/experimental@0.46.6

0.6.6

Patch Changes

• Updated dependencies [7764a07, 4577f54, 30a0d9c]:
  • @effect/platform@0.82.5
  • effect@3.15.3
  • @effect/ai@0.16.6
  • @effect/experimental@0.46.5

0.6.5

Patch Changes

• #4899 0a8c0e7 Thanks @alex-dixon! - fix: anthropic tag name

• Updated dependencies [d45e8a8, d13b68e]:

  • @effect/platform@0.82.4
  • @effect/ai@0.16.5
  • @effect/experimental@0.46.4

0.6.4

Patch Changes

• Updated dependencies [b8722b8, a328f4b]:
  • effect@3.15.2
  • @effect/platform@0.82.3
  • @effect/ai@0.16.4
  • @effect/experimental@0.46.3

0.6.3

Patch Changes

• Updated dependencies [739a3d4]:
  • @effect/platform@0.82.2
  • @effect/ai@0.16.3
  • @effect/experimental@0.46.2

0.6.2

Patch Changes

• Updated dependencies [787ce70, 1269641, 1269641]:
  • effect@3.15.1
  • @effect/ai@0.16.2
  • @effect/experimental@0.46.1
  • @effect/platform@0.82.1

0.6.1

Patch Changes

• Updated dependencies [cb3c30f]:
  • @effect/ai@0.16.1
  • @effect/experimental@0.46.0

0.6.0

Patch Changes

• Updated dependencies [c654595, d9f5dea, 49aa723, 74c14d0, e4f49b6, 6f02224, 1dcfd41, b21ab16, fcf1822, 0061dd1, 8421e6e, a9b3fb7, fa10f56]:
  • effect@3.15.0
  • @effect/platform@0.82.0
  • @effect/ai@0.16.0
  • @effect/experimental@0.46.0

0.5.0

Minor Changes

• #4766 a4d42c5 Thanks @IMax153! - Refactor @effect/ai-anthropic to align with changes to @effect/ai

Patch Changes

• Updated dependencies [a4d42c5]:
  • @effect/ai@0.15.0
  • @effect/experimental@0.45.1

0.4.1

Patch Changes

• Updated dependencies [24a9ebb]:
  • effect@3.14.22
  • @effect/ai@0.14.1
  • @effect/experimental@0.45.1
  • @effect/platform@0.81.1

0.4.0

Patch Changes

• Updated dependencies [672920f]:
  • @effect/platform@0.81.0
  • @effect/ai@0.14.0
  • @effect/experimental@0.45.0

0.3.22

Patch Changes

• Updated dependencies [2f3b7d4]:
  • effect@3.14.21
  • @effect/ai@0.13.21
  • @effect/experimental@0.44.21
  • @effect/platform@0.80.21

0.3.21

Patch Changes

• Updated dependencies [17e2f30]:
  • effect@3.14.20
  • @effect/ai@0.13.20
  • @effect/experimental@0.44.20
  • @effect/platform@0.80.20

0.3.20

Patch Changes

• Updated dependencies [056a910, e25e7bb, 3273d57]:
  • effect@3.14.19
  • @effect/platform@0.80.19
  • @effect/ai@0.13.19
  • @effect/experimental@0.44.19

0.3.19

Patch Changes

• Updated dependencies [b1164d4]:
  • effect@3.14.18
  • @effect/ai@0.13.18
  • @effect/experimental@0.44.18
  • @effect/platform@0.80.18

0.3.18

Patch Changes

• Updated dependencies [0b54681, 41a59d5]:
  • effect@3.14.17
  • @effect/ai@0.13.17
  • @effect/experimental@0.44.17
  • @effect/platform@0.80.17

0.3.17

Patch Changes

• Updated dependencies [ee14444, f1c8583]:
  • effect@3.14.16
  • @effect/platform@0.80.16
  • @effect/ai@0.13.16
  • @effect/experimental@0.44.16

0.3.16

Patch Changes

• Updated dependencies [239cc99, 8b6c947, c50a63b]:
  • effect@3.14.15
  • @effect/ai@0.13.15
  • @effect/experimental@0.44.15
  • @effect/platform@0.80.15

0.3.15

Patch Changes

• Updated dependencies [6ed8d15]:
  • effect@3.14.14
  • @effect/ai@0.13.14
  • @effect/experimental@0.44.14
  • @effect/platform@0.80.14

0.3.14

Patch Changes

• Updated dependencies [ee77788, 5fce6ba, 570e45f]:
  • effect@3.14.13
  • @effect/ai@0.13.13
  • @effect/experimental@0.44.13
  • @effect/platform@0.80.13

0.3.13

Patch Changes

• Updated dependencies [c2ad9ee, 9c68654]:
  • effect@3.14.12
  • @effect/ai@0.13.12
  • @effect/experimental@0.44.12
  • @effect/platform@0.80.12

0.3.12

Patch Changes

• Updated dependencies [e536127]:
  • effect@3.14.11
  • @effect/ai@0.13.11
  • @effect/experimental@0.44.11
  • @effect/platform@0.80.11

0.3.11

Patch Changes

• Updated dependencies [bc7efa3]:
  • effect@3.14.10
  • @effect/ai@0.13.10
  • @effect/experimental@0.44.10
  • @effect/platform@0.80.10

0.3.10

Patch Changes

• Updated dependencies [d78249f]:
  • effect@3.14.9
  • @effect/ai@0.13.9
  • @effect/experimental@0.44.9
  • @effect/platform@0.80.9

0.3.9

Patch Changes

• #4726 b8b0703 Thanks @dearlordylord! - AnthropicClient.layerConfig has the same ROut as AnthropicClient.layer - specifically, AiModels.AiModels was missing

0.3.8

Patch Changes

• Updated dependencies [b3a2d32]:
  • effect@3.14.8
  • @effect/ai@0.13.8
  • @effect/experimental@0.44.8
  • @effect/platform@0.80.8

0.3.7

Patch Changes

• Updated dependencies [b542a4b]:
  • effect@3.14.7
  • @effect/ai@0.13.7
  • @effect/experimental@0.44.7
  • @effect/platform@0.80.7

0.3.6

Patch Changes

• Updated dependencies [47618c1, 6077882]:
  • effect@3.14.6
  • @effect/ai@0.13.6
  • @effect/experimental@0.44.6
  • @effect/platform@0.80.6

0.3.5

Patch Changes

• Updated dependencies [40dbfef, 85fba81, 5a5ebdd]:
  • effect@3.14.5
  • @effect/platform@0.80.5
  • @effect/ai@0.13.5
  • @effect/experimental@0.44.5

0.3.4

Patch Changes

• Updated dependencies [e4ba2c6]:
  • effect@3.14.4
  • @effect/ai@0.13.4
  • @effect/experimental@0.44.4
  • @effect/platform@0.80.4

0.3.3

Patch Changes

• Updated dependencies [37aa8e1, 34f03d6]:
  • effect@3.14.3
  • @effect/ai@0.13.3
  • @effect/experimental@0.44.3
  • @effect/platform@0.80.3

0.3.2

Patch Changes

• Updated dependencies [f87991b, f87991b, 0a3e3e1]:
  • effect@3.14.2
  • @effect/ai@0.13.2
  • @effect/experimental@0.44.2
  • @effect/platform@0.80.2

0.3.1

Patch Changes

• Updated dependencies [4a274fe]:
  • effect@3.14.1
  • @effect/ai@0.13.1
  • @effect/experimental@0.44.1
  • @effect/platform@0.80.1

0.3.0

Patch Changes

• Updated dependencies [1f47e4e, 26dd75f, aba2d1d, 3131f8f, aba2d1d, 04dff2d, aba2d1d, c7fac0c, aba2d1d, ffaa3f3, ab957c1, 35db9ce, aba2d1d, cf77ea9, 26dd75f, baaab60]:
  • effect@3.14.0
  • @effect/experimental@0.44.0
  • @effect/platform@0.80.0
  • @effect/ai@0.13.0

0.2.4

Patch Changes

• #4592 5662363 Thanks @tim-smart! - update generated ai clients

• Updated dependencies [5662363, 5f1fd15, 8bb1460]:

  • @effect/platform@0.79.4
  • @effect/ai@0.12.4
  • @effect/experimental@0.43.4

0.2.3

Patch Changes

• Updated dependencies [0c4803f, 6f65ac4]:
  • effect@3.13.12
  • @effect/ai@0.12.3
  • @effect/experimental@0.43.3
  • @effect/platform@0.79.3

0.2.2

Patch Changes

• Updated dependencies [fad8cca, 4296293, 9c241ab, 082b0c1, be12983, de88127]:
  • effect@3.13.11
  • @effect/ai@0.12.2
  • @effect/experimental@0.43.2
  • @effect/platform@0.79.2

0.2.1

Patch Changes

• Updated dependencies [527c964]:
  • effect@3.13.10
  • @effect/ai@0.12.1
  • @effect/experimental@0.43.1
  • @effect/platform@0.79.1

0.2.0

Patch Changes

• Updated dependencies [88fe129, d630249, 2976e52]:
  • @effect/platform@0.79.0
  • effect@3.13.9
  • @effect/experimental@0.43.0
  • @effect/ai@0.12.0

0.1.1

Patch Changes

• Updated dependencies [c65d336, 22d2ebb]:
  • effect@3.13.8
  • @effect/ai@0.11.1
  • @effect/experimental@0.42.1
  • @effect/platform@0.78.1

0.1.0

Patch Changes

• Updated dependencies [c5bcf53]:
  • @effect/platform@0.78.0
  • @effect/ai@0.11.0
  • @effect/experimental@0.42.0

0.0.7

Patch Changes

• Updated dependencies [840cc73, 9bf8a74, 87ba23c, f910880, 0d01480, a95108a]:
  • @effect/platform@0.77.7
  • effect@3.13.7
  • @effect/ai@0.10.7
  • @effect/experimental@0.41.7

0.0.6

Patch Changes

• Updated dependencies [3154ce4]:
  • effect@3.13.6
  • @effect/ai@0.10.6
  • @effect/experimental@0.41.6
  • @effect/platform@0.77.6

0.0.5

Patch Changes

• Updated dependencies [3d6d323, 367bb35, 6cf11c3, a0acec8, 975c20e]:
  • @effect/ai@0.10.5
  • effect@3.13.5
  • @effect/experimental@0.41.5
  • @effect/platform@0.77.5

0.0.4

Patch Changes

• Updated dependencies [e0746f9, 17d9e89]:
  • @effect/platform@0.77.4
  • effect@3.13.4
  • @effect/ai@0.10.4
  • @effect/experimental@0.41.4

0.0.3

Patch Changes

• #4504 a67a8a1 Thanks @IMax153! - Introduce AiModel and AiPlan for describing retry / fallback logic between models and providers

  For example, the following program builds an AiPlan which will attempt to use OpenAi’s chat completions API, and if after three attempts the operation is still failing, the plan will fallback to utilizing Anthropic’s messages API to resolve the request.

  1
  import { AiPlan, Completions } from "@effect/ai"
  2
  import { AnthropicClient, AnthropicCompletions } from "@effect/ai-anthropic"
  3
  import { OpenAiClient, OpenAiCompletions } from "@effect/ai-openai"
  4
  import { NodeHttpClient, NodeRuntime } from "@effect/platform-node"
  5
  import { Config, Console, Effect, Layer } from "effect"
  6
  
  7
  // Create Anthropic client
  8
  const Anthropic = AnthropicClient.layerConfig({
  9
    apiKey: Config.redacted("ANTHROPIC_API_KEY")
  10
  }).pipe(Layer.provide(NodeHttpClient.layerUndici))
  11
  
  12
  // Create OpenAi client
  13
  const OpenAi = OpenAiClient.layerConfig({
  14
    apiKey: Config.redacted("OPENAI_API_KEY")
  15
  }).pipe(Layer.provide(NodeHttpClient.layerUndici))
  16
  
  17
  // Create a plan of request execution
  18
  const Plan = AiPlan.fromModel(OpenAiCompletions.model("gpt-4o-mini"), {
  19
    attempts: 3
  20
  }).pipe(
  21
    AiPlan.withFallback({
  22
      model: AnthropicCompletions.model("claude-3-5-haiku-latest")
  23
    })
  24
  )
  25
  
  26
  const program = Effect.gen(function* () {
  27
    // Build the plan of execution
  28
    const plan = yield* Plan
  29
  
  30
    // Create a program which uses the services provided by the plan
  31
    const getDadJoke = Effect.gen(function* () {
  32
      const completions = yield* Completions.Completions
  33
      const response = yield* completions.create("Tell me a dad joke")
  34
      yield* Console.log(response.text)
  35
    })
  36
  
  37
    // Provide the plan to whichever programs need it
  38
    yield* plan.provide(getDadJoke)
  39
  })
  40
  
  41
  program.pipe(Effect.provide([Anthropic, OpenAi]), NodeRuntime.runMain)

• Updated dependencies [cc5588d, 623c8cd, 00b4eb1, f2aee98, fb798eb, 2251b15, 2e15c1e, a4979db, b74255a, d7f6a5c, 9dd8979, 477b488, 10932cb, 9f6c784, 2c639ec, 886aaa8, a67a8a1]:

  • effect@3.13.3
  • @effect/ai@0.10.3
  • @effect/experimental@0.41.3
  • @effect/platform@0.77.3

0.0.2

Patch Changes

• Updated dependencies [31be72a, 3e7ce97, 31be72a]:
  • effect@3.13.2
  • @effect/platform@0.77.2
  • @effect/ai@0.10.2
  • @effect/experimental@0.41.2

0.0.1

Patch Changes

• #4446 9375c28 Thanks @IMax153! - Add Anthropic AI provider integration

• Updated dependencies [b56a211, 9375c28]:

  • effect@3.13.1
  • @effect/ai@0.10.1
  • @effect/experimental@0.41.1
  • @effect/platform@0.77.1