pub.dev · #1971 most downloaded on pub.dev

genkit

1.0.028K downloads/mogenkit-ai/genkit-dart ↗New releases in your daily digest, changelog included.

Genkit Dart package, a Generative AI library for pure Dart client/server and Flutter apps.

Last release today
07 Oct 2026
Ships fairly regularly
a new release about every 2 weeks
Nearly every release is documented
notes for 24 of 24 stable releases
Nothing withdrawn
no release was ever pulled
1 years old
49 releases · first in 2025

Release timeline

49 releases since 2025

20252026

One column per month.

Releases

1.0.07 Oct 2026Breaking

This release has a lot of breaking changes. Most of them are small renames and tightened types that came out of a full review of the public API before…

Genkit Dart is now 1.0. The core genkit package, schemantic, and the main plugins are stable and covered by semantic versioning. Some packages stay on 0.x because their underlying platforms or APIs are still changing:

Package	Version
`genkit`, `schemantic`, `schemantic_builder`	1.0.0
`genkit_google_genai`, `genkit_vertexai`, `genkit_anthropic`, `genkit_openai`	1.0.0
`genkit_middleware`, `genkit_mcp`, `genkit_shelf`	1.0.0
`genkit_firebase_ai`, `genkit_google_cloud`	0.3.0
`genkit_chrome`, `genkit_otel`, `genkit_vertex_auth`	0.2.0
`genkit_a2ui`	0.4.0

This release has a lot of breaking changes. Most of them are small renames and tightened types that came out of a full review of the public API before freezing it. The ones you are most likely to hit are GenkitRouter (if you used genkit_shelf), prompts, and GenerateResult.

Highlights

Stable vs. experimental imports

The stable API is now clearly separated from experimental features. Stable libraries are covered by semver:

import 'package:genkit/genkit.dart';
import 'package:genkit/client.dart';
import 'package:genkit/lite.dart';
import 'package:genkit/plugin.dart';
import 'package:genkit/telemetry.dart';
import 'package:genkit/io.dart';       // new: HTTP serving (dart:io)

Experimental features have their own imports. They can change or be removed in any minor release:

import 'package:genkit/experimental.dart';        // agents, sessions, snapshots, live/bidi models
import 'package:genkit/experimental_client.dart'; // browser-safe agent client
import 'package:genkit/experimental_io.dart';     // FileSessionStore, GenkitRouter.addAgent
import 'package:genkit_middleware/agents.dart';   // agents() sub-agent delegation middleware

These libraries are annotated @experimental, so the analyzer warns (experimental_member_use) as soon as you import one. If you've accepted the instability, you can silence the warning:

# analysis_options.yaml
analyzer:
  errors:
    experimental_member_use: ignore

What moved:

Agent and session data types (AgentOutput, AgentInput, SessionSnapshot, TurnEnd, Artifact, JsonPatchOperation, and about 15 more) are no longer exported from the stable libraries. Import experimental.dart or experimental_client.dart. (#480)
genkit_middleware no longer re-exports agents(), AgentsPlugin, AgentsOptions and related types. Import package:genkit_middleware/agents.dart directly. (#482)
Bidi streaming: calling Action.streamBidi() now triggers the experimental warning. BidiActionStream and BidiActionFn are exported from experimental.dart. (#483)
Dev UI reflection protocol types are no longer exported. (#481)

Serving over HTTP: `GenkitRouter`

HTTP serving now lives in core (package:genkit/io.dart) and runs on plain dart:io. genkit_shelf is now a thin adapter on top of it. startFlowServer and FlowWithContextProvider are gone. (#533)

import 'package:genkit/io.dart';

final genkit = GenkitRouter()
  ..addAction(helloFlow)                                 // POST /hello
  ..addAction(secureFlow, contextProvider: bearerAuth)   // per-action auth
  ..addAction(googleAI().model('gemini-flash-latest'));  // models and tools can be served too

await genkit.serve(port: 8080, cors: const CorsOptions());

Context providers get a framework-neutral RequestData instead of a shelf Request. Header names are lowercased:

Future<Map<String, dynamic>> bearerAuth(RequestData request) async {
  final user = await verifyToken(request.headers['authorization']);
  if (user == null) {
    throw GenkitException('Unauthorized', status: StatusCode.unauthenticated); // 401
  }
  return {'userId': user.id}; // becomes ctx.context
}

You can also mount it inside your own server, or serve a single action:

// your own dart:io server
await for (final request in server) {
  if (await genkit.handleHttpRequest(request, basePath: '/api')) continue;
  // ...your routes
}

// single action
final handleHello = ioHandler(helloFlow, contextProvider: bearerAuth);

// shelf
final app = Router()
  ..post('/hello', shelfHandler(helloFlow))
  ..mount('/api/', genkit.asShelfHandler());

Agents (experimental) mount with one call. You no longer need hand-written /getSnapshot and /abort routes:

import 'package:genkit/experimental_io.dart';

final api = GenkitRouter()
  ..addAgent(weatherAgent)                               // turn + /getSnapshot + /abort
  ..addAgent(bankingAgent, contextProvider: bearerAuth);

Migrating from startFlowServer:

// before
await startFlowServer(
  flows: [helloFlow, FlowWithContextProvider(flow: secureFlow, context: bearerAuth)],
  cors: {'origin': '*'},
);

// after
final genkit = GenkitRouter()
  ..addAction(helloFlow)
  ..addAction(secureFlow, contextProvider: bearerAuth);
await genkit.serve(cors: const CorsOptions());

Wire format change: streamed responses now use Content-Type: text/event-stream, and a failed stream ends with a data: {"error": ...} frame instead of error: {...}. This matches the Go and Python servers. Clients from genkit 0.17 and earlier only understand the old frame. If you have shipped apps (for example Flutter apps) that use an old client, turn on the legacy frame:

final genkit = GenkitRouter(sendLegacyErrorFrame: true);

See #533 for the full design and migration guide.

Constrained generation middleware

Some models don't support constrained (schema-enforced) output natively. For those, you can opt into simulateConstrainedGeneration(). It moves the output schema into the prompt as instructions, so structured output still works. It's built in, so you don't need to register a plugin. (#453, #519)

final response = await ai.generate(
  model: someModel,
  prompt: 'Describe a cat',
  outputSchema: Cat.$schema,
  use: [simulateConstrainedGeneration()],
);

// Lite API
await lite.generate(
  model: model,
  outputSchema: Cat.$schema,
  use: [SimulateConstrainedGenerationMiddleware()],
);

Nothing is rewritten unless you add the middleware. If a model doesn't support constrained output (for example Chrome's built-in model), add the middleware or use the provider's own config option, such as Chrome's responseConstraint.

Typed prompts

Prompts now have an Output type parameter, so they return typed structured output just like generate. ExecutablePrompt is renamed to Prompt. Call options are now named parameters, the same ones generate takes. (#527, #622)

final joke = ai.definePrompt(
  name: 'joke',
  inputSchema: JokeInput.$schema,
  outputSchema: Joke.$schema,
  prompt: 'Tell a joke about {{topic}}',
); // Prompt<JokeInput, Joke>

final Joke? j = (await joke(JokeInput(topic: 'cats'), config: {'temperature': 0.2})).output;

// typed lookup
final p = await ai.prompt<JokeInput, Joke>('joke');

// .prompt file with a schema but no Dart type
final s = await ai.prompt('summarize', outputParserSchema: Summary.$schema);

The Lite API's generate / generateStream also infer a typed output from outputSchema now. (#499)

Middleware

ai.defineGenerateMiddleware registers middleware from app code, with no plugin needed. The top-level defineMiddleware used by plugin authors is renamed to generateMiddleware. (#571)

final logging = ai.defineGenerateMiddleware<LoggingOptions>(
  name: 'logging',
  configSchema: LoggingOptions.$schema,
  create: (config, ctx) => LoggingMiddleware(config),
);

await ai.generate(prompt: 'hi', use: [logging(LoggingOptions(level: 'debug'))]);

retry() works out of the box. RetryPlugin is removed; delete it from plugins:. Delays are now Durations, and retryModel is now noRetryModel. (#531, #549)
```
use: [retry(maxRetries: 3, initialDelay: const Duration(milliseconds: 500))]
```
The middleware tool hook returns ToolResult. GenerateMiddleware.tool now returns Future<ToolResult>, and ToolInterruptException is removed. Return .interrupt(data) instead of throwing. (#503)

Breaking changes

Core (`genkit`)

Generate results

GenerateResponseHelper is renamed to GenerateResult. rawResponse is now modelResponse, rawChunk is now modelChunk, and jsonOutput is removed (use output). (#534)
GenerateResult and GenerateResponseChunk are now read-only views. They no longer extend the wire types and have no setters or toJson(). To forward chunks to a flow, use onChunk: (c) => ctx.sendChunk(c.modelChunk). (#547)
Usage counts and indexes (inputTokens, outputTokens, Candidate.index, ...) are now int instead of double. (#546)

Prompts

ExecutablePrompt<Input> is now Prompt<Input, Output>. Type parameter order is now payload types first, config last, everywhere: generate<Output, CustomOptions>, definePrompt<Input, Output, CustomOptions>, defineAgent<Input, State, CustomOptions>. (#527)
Prompt.call / stream / render take named parameters. PromptGenerateOptions is removed. (#622)
ExecutablePrompt.ref is now a PromptRef class instead of a record. PromptConfig is no longer exported. (#528, #529)

Renames

Before	After	PR
`StatusCodes.NOT_FOUND`	`StatusCode.notFound` (use `.wireName` for `'NOT_FOUND'`)	#542
`EvalStatusEnum.PASS`	`EvalStatus.pass`	#545
`GenkitException(underlyingException:)`	`GenkitException(cause:)`. `statusCode` is removed (use `status.value` or `status.httpStatus`)	#548
`ToolFnArgs`	`ToolFnArg`	#537
`remoteModel(modelInfo:)`, `modelMetadata(modelInfo:)`	`info:`	#537
`RemoteAction.dispose()`	`close()`	#537
`Tool(toolOutputSchema:)`	`Tool(outputSchema:)`	#530
`ai.embedMany(documents:)`	`ai.embed(documents:)`	#535
`cacheTtlMillis: 60000`	`cacheTtl: const Duration(minutes: 1)` (also in `genkit_mcp`)	#539
`defineMiddleware(...)`	`generateMiddleware(...)`	#571

Types and class shapes

toolChoice is now a ToolChoice open enum instead of String, for example toolChoice: .required. (#493)
Open-enum values (Role, FinishReason, ToolChoice, ...) are now const, so you can use them as switch cases. (#544)
ActionFnArg, GenerateTurnState and GenerateMiddlewareContext are now final classes instead of record typedefs. Code that built them with record literals needs to use the constructors. (#484, #485, #486)
Core classes now have class modifiers. Actions (Model, Flow, Tool, ...) are base. Handle types are final. Registry is final, and its plumbing methods are now @internal. (#487, #529)
The Model, Embedder, Evaluator and Flow constructors now take non-null input, so plugin authors no longer need req!. Evaluator drops its unused type parameter. (#536, #528)
ActionStream.setResult / setError and the ActionMetadata.key setter are now @internal. BidiModel.customOptions and Embedder.customOptions are now final. (#488, #489, #528)
GenerateMiddlewareDef is now a final, callable class. Build one with generateMiddleware or ai.defineGenerateMiddleware. (#571)

Removed

ToolFnArgs.interrupt(). Return .interrupt(data) from the tool instead. (#497)
ToolInterruptException. (#503)
RetryPlugin. (#531)
Formatter, FormatterHandlerResult, MessageParser and ChunkParser exports. (#491)
createResourceMatcher from genkit.dart. It's now exported from plugin.dart. (#529)
The old, empty package:genkit/io.dart. The name is reused for the new HTTP serving library. (#498, #533)

Added exports

Types that appeared in public signatures but couldn't be named are now exported: ActionStream, Evaluator, ActionFn, StreamingCallback, Registry, and others. (#490)

Dotprompt 2.0

.prompt files now use spec-compliant Picoschema:

tags(array): string is now an array of strings. It used to be a string with the description "array".
(*): string now maps to additionalProperties.
The old description form email(the email): string logs a warning at load time and fails at render time. Use email: string, the email instead.

(#573)

`genkit_shelf`

startFlowServer and FlowWithContextProvider are removed. Use GenkitRouter with shelfHandler / asShelfHandler(). Context providers take RequestData. See Serving over HTTP. (#533)

`genkit_middleware`

The agents middleware is no longer exported from the main library. Import package:genkit_middleware/agents.dart. (#482)

`genkit_google_genai` / `genkit_vertexai`

GoogleAiModels is removed. Name models by string: googleAI.gemini('gemini-flash-latest'), googleAI.geminiTts('gemini-3.8-flash-tts'). Catalog enums are no longer exported. (#524)
Exported option types now have a provider prefix, which avoids import clashes with other plugins. ThinkingConfig is now GeminiThinkingConfig. The same applies to GeminiSafetySettings, GeminiFunctionCallingConfig, GeminiGoogleSearch, GeminiFileSearch, and the speech/voice config types. TextEmbedderOptions is now GoogleGenAiEmbedderOptions. (#572)

`genkit_anthropic`

ThinkingConfig is now AnthropicThinkingConfig. (#572)
toolChoice: required now maps to Anthropic's any. (#492)

`genkit_openai`

OpenAIModels, OpenAIEmbedders, XaiModels and DeepSeekModels are removed. Use openAI.model('gpt-5.5'), xAI.model(...), deepSeek.model(...) and openAI.embedder(...). modelInfoFor and related functions are still exported. OpenAIModelKind is now a class. (#525)
Implementation helpers (GenkitConverter, getModelType, the capability-set constants) are no longer exported. (#502)

`schemantic`

Generated code now emits plain JSON Schema maps instead of json_schema_builder calls. $Schema and the SchemaValidation re-export are removed. Regenerate your .g.dart files with schemantic_builder 1.0.0. (#522)

New features

Core (`genkit`)

Interrupt tool class for human-in-the-loop patterns. Tool and the related types are now exported from the Lite API. (#399)

`genkit_openai`

Text-to-speech with tts-1, tts-1-hd and gpt-4o-mini-tts through openAI.speechModel(). (#405)
Speech-to-text with whisper-1, gpt-4o-transcribe and gpt-4o-mini-transcribe through openAI.transcriptionModel(), including Whisper translation. (#406)
reasoningEffort and verbosity options, plus reasoning output. (#430)

`genkit_anthropic`

Stable/beta API selection (apiVersion, betas) and native structured output through output_config.format. Structured output now works together with extended thinking and with your own tools. (#402)
Every Claude model, including ones not yet in the curated catalog, now claims native structured output. (#518)
You can pass a custom http.Client. (#226)

`genkit_google_genai` / `genkit_vertexai`

gemini-embedding-* embedders are discovered automatically and can embed media. (#394)
The curated model catalog is expanded to match the JS/Go plugins, and TTS models get the correct capability profile. (#513, #523, #524)

Bug fixes

Core (`genkit`)

A partial streamed chunk that doesn't match the output schema yet no longer fails the generation. (#500)
Reflection health checks for a different runtime id are now rejected. (#477)
The v1 reflection server reports the real package version. (#506)
defineSchema names in .prompt files are resolved at render time. (#570)
Detached agent turns keep running after a remote detach. (#567)
The remote client keeps the server's error status and message instead of a generic HTTP-derived error. (#568)
Logging now goes through package:logging instead of print(). (#508)

`genkit_middleware`

Fixed a filesystem sandbox escape through symlinks. (#566)
ToolApprovalPlugin(approvedTools:) is honored when toolApproval() is called without a list. (#538)

Plugins

google_genai, openai, firebase_ai: now honor the portable toolChoice option. (#494, #495, #496)
google_genai: Gemini finish reasons now map to Genkit's vocabulary. (#425)
google_genai, vertexai: injected HTTP clients are no longer closed by the plugin, and late cancellation is honored. (#454)
google_genai, vertexai: list() falls back to the curated catalog when model discovery fails. (#512)
openai: fixed xAI recursive tool schemas, and xAI model discovery no longer lists models that can't be served. (#476)
firebase_ai: stopped pre-registering the retired gemini-2.5-pro. (#509)

Docs

READMEs now explain how to install the Genkit Dart agent skill. (#521)
example/ programs added for genkit_chrome, genkit_firebase_ai and genkit_google_cloud. (#505)
Fixed stale package descriptions. The Preview label is removed from the root README. (#504, #632)

Full Changelog: genkit-v0.17.0...genkit-v1.0.0

From the same repository

genkit-ai/genkit-dart

Additional notes2 sources agree

Breaking Changes

take prompt call options as named parameters (#622)
add ai.defineGenerateMiddleware; rename top-level defineMiddleware to generateMiddleware (#571)
upgrade to dotprompt 2.0 for spec-compliant Picoschema (#573)
introduce GenkitRouter and update shelf adapter (#533)
rename GenkitException.underlyingException to cause; drop statusCode (#548)
add an Output type parameter to prompts; rename ExecutablePrompt to Prompt (#527)
use Duration for retry delays; rename retryModel to noRetryModel (#549)
rename EvalStatusEnum to EvalStatus with lowerCamelCase values (#545)
type usage counts and indexes as int (#546)
make GenerateResult and GenerateResponseChunk read-only views (#547)
non-null input for Model/Embedder/Evaluator/Flow constructors (#536)
rename GenerateResponseHelper to GenerateResult and drop redundant members (#534)
rename StatusCodes to StatusCode with lowerCamelCase values (#542)
use Duration for cache TTLs (#539)
remove embedMany in favor of embed (#535)
align naming of ToolFnArg, ModelInfo params and RemoteAction.close (#537)
seal Registry and hide internal plumbing (#529)
register retry middleware by default and remove RetryPlugin (#531)
rename Tool(toolOutputSchema:) to outputSchema (#530)
replace ExecutablePrompt.ref record with PromptRef; tidy Embedder/Evaluator (#528)
generate plain JSON schema maps instead of json_schema_builder calls (#522)
make constrained generation simulation an opt-in middleware (#519)
middleware tool hook returns ToolResult; remove ToolInterruptException (#503)
remove the empty package:genkit/io.dart library (#498)
remove the deprecated ToolFnArgs.interrupt() (#497)
type toolChoice as an open enum instead of String (#493)
stop exporting the Formatter types (#491)
export every type that appears in a public signature (#490)
stop exposing public setters on action metadata (#489)
make ActionStream's completion setters @internal (#488)
add class modifiers to the core public classes (#487)
replace the GenerateMiddlewareContext record typedef with a final class (#486)
replace the GenerateTurnState record typedef with a final class (#485)
replace the ActionFnArg record typedef with a final class (#484)
annotate the bidirectional-streaming API as @experimental (#483)
stop exporting Dev UI protocol types (#481)
move agent/session schema types out of the stable libraries (#480)
simulate constrained generation when a model lacks native support (#453)

Features

make open-enum values const so they work as switch cases (#544)
discover gemini-embedding-* embedders and embed media (#394)
infer a typed Output in the lite generate API (#499)
add Interrupt tool and export tools in Lite API (#399)
add OpenTelemetry GenAI instrumentation package (#446)

Fixes

keep the server error status and message in the remote client (#568)
resolve defineSchema names in .prompt files at render time (#570)
keep detached agent turns running after a remote detach (#567)
report the real package version from the v1 reflection server (#506)
don't fail a generation when a partial chunk misses the output schema (#500)
reject reflection health checks for a different runtime id (#477)

Other Changes

mark manifestOutputSchema @internal; document Tool.toolOutputSchema (#551)
mark DynamicActionProvider reflection helpers @internal (#550)
replace custom API golden script with package:api_summary (#532)
add Genkit Dart agent skill install instructions to READMEs (#521)
add public API surface snapshot test (#479)

genkit

Release timeline

Releases

Highlights

Stable vs. experimental imports

Serving over HTTP: GenkitRouter

Constrained generation middleware

Typed prompts

Middleware

Breaking changes

Core (genkit)

Generate results

Prompts

Renames

Types and class shapes

Removed

Added exports

Dotprompt 2.0

genkit_shelf

genkit_middleware

genkit_google_genai / genkit_vertexai

genkit_anthropic

genkit_openai

schemantic

New features

Core (genkit)

genkit_openai

genkit_anthropic

genkit_google_genai / genkit_vertexai

Bug fixes

Core (genkit)

genkit_middleware

Plugins

Docs

From the same repository

Breaking Changes

Features

Fixes

Other Changes

Breaking Changes

Breaking Changes

Fixes

Breaking Changes

Features

Fixes

Other Changes

Highlights

Breaking Changes

generate resolves instead of throwing (#397, #413)

Agent snapshot lifecycle: aborting status and resumable terminal snapshots (#411, #413)

Agent and bidi APIs moved behind experimental imports (#450, #461)

agent.send() now runs over the streaming transport (#457)

DAP feature gaps closed (#432)

Telemetry

Agents and middleware

Plugins

genkit_openai

genkit_anthropic

genkit_google_genai

genkit_mcp

genkit

Other changes

New Contributors

Breaking Changes

Features

Fixes

Bug Fixes

Breaking Changes

New Contributors

Features

Breaking Changes

Features

Fixes

Breaking Changes

Features

Fixes

What's Changed

Fixes

Agents

What agents give you

Serving over HTTP: `GenkitRouter`

Core (`genkit`)

`genkit_shelf`

`genkit_middleware`

`genkit_google_genai` / `genkit_vertexai`

`genkit_anthropic`

`genkit_openai`

`schemantic`

Core (`genkit`)

`genkit_openai`

`genkit_anthropic`

`genkit_google_genai` / `genkit_vertexai`

Core (`genkit`)

`genkit_middleware`

`generate` resolves instead of throwing (#397, #413)

Agent snapshot lifecycle: `aborting` status and resumable terminal snapshots (#411, #413)

`agent.send()` now runs over the streaming transport (#457)