ai_sdk_provider

AI SDK Dart 2.0 is a coordinated major release across all 13 packages.

Highlights

• V4 is now the only language-model provider contract.
• Generation and streaming gain scoped timeouts, provider-backed cancellation, stable runtime context and telemetry APIs, structured output improvements, and safer streamed tool execution.
• Provider usage reports nested input/output token details, including cache reads and writes where available.
• Flutter UI gains polished tool approval, source citation, reasoning, streaming, error, and long-history experiences.
• MCP transports and lifecycle handling are substantially hardened.

Breaking changes

Upgrade every ai_sdk package together. The obsolete V3 language-model contract, experimental API names, video surface, and old provider call fields were removed without compatibility shims.

Read the 2.0 migration guide before upgrading.

Packages

All 13 packages are published on pub.dev.

What's Changed

• fix(openai): surface reasoning/thinking deltas on streaming + non-streaming paths (fixes #3) by @codenameakshay in #7
• chore: add SessionStart hook to provision Flutter via FVM on the web by @codenameakshay in #5
• feat(usage): map provider cache tokens into inputTokenDetails by @codenameakshay in #9
• Prepare the next release with V4 providers and hardened UX by @codenameakshay in #10
• Prepare the coordinated 2.0.0 release by @codenameakshay in #11

Full Changelog: 1.2.0...2.0.0

• Breaking: replaced the language-model V3 seam with LanguageModelV4 and removed the obsolete V3 language-model paths.
• Added unified typed tools, response formats, reasoning controls, abort signals, supported URLs, structured warnings, request/response metadata, nested token usage, and the complete V4 stream lifecycle.

Coordinated 1.2.0 release across all 13 packages — now live on pub.dev. A v6 hardening pass that makes the AI SDK Dart port more complete, honest, and tested.

Highlights

🚨 Typed provider API errors (new)

Non-2xx provider responses now throw a typed AiApiCallError carrying the provider's message, type, code, statusCode, raw body, and an isRetryable flag — consistently across every provider. The AiSdkError hierarchy moved into ai_sdk_provider (re-exported by ai_sdk_dart, so the public surface is unchanged).

🧩 Shared ai_sdk_openai_compatible base (new package)

A shared OpenAI Chat Completions implementation now powers OpenAI / Azure / Groq / Mistral. All 8 providers support tool use + multimodal image input; Cohere & Ollama gained them natively.

🔌 MCP

Real Server-Sent-Events streaming transport (SseClientTransport) plus a plain request/response HttpClientTransport; web-safe — dart:io is isolated behind conditional imports, so the client runs on Flutter web.

📱 Flutter UI hub

19 prebuilt, themeable Material widgets plus hardened controllers (ObjectStreamController.submit, ChatController.isStreaming, streaming-error surfacing). A restrained Material 3 redesign — bubbleless assistant transcript, an AiMotion motion/haptics vocabulary, and a first-class reduced-motion path. Fixed a PressableScale crash-on-dispose under reduced motion.

✅ Correctness

onAbort now interrupts an in-flight streamText; stopWhen can extend the tool loop past maxSteps. Removed the unusable generateVideo / VideoModelV1 (no backing provider). OpenAI image generation no longer sends response_format to gpt-image-1.

🧪 Quality

1,057 tests (924 Dart + 133 Flutter), 99.9% line coverage (11 of 12 packages at 100%), enforced by a CI coverage gate.

Packages (all published at 1.2.0)

ai_sdk_provider · ai_sdk_dart · ai_sdk_openai_compatible · ai_sdk_openai · ai_sdk_anthropic · ai_sdk_google · ai_sdk_azure · ai_sdk_cohere · ai_sdk_groq · ai_sdk_mistral · ai_sdk_ollama · ai_sdk_mcp · ai_sdk_flutter_ui

See each package's CHANGELOG.md for full details.

Full Changelog: 1.1.0...1.2.0

Error hierarchy

• The full AiSdkError hierarchy now lives here (relocated from ai_sdk_dart) so that every provider package — which depends on ai_sdk_provider, not ai_sdk_dart — can throw the same typed errors. ai_sdk_dart re-exports the hierarchy, so its public surface is unchanged.
• AiApiCallError is enriched with statusCode, url, responseBody, responseHeaders, type, code, isRetryable, and cause, plus an AiApiCallError.fromResponse(...) factory that tolerantly parses each provider's error-body shape (OpenAI/Groq/Mistral, Anthropic, Google, Cohere, Ollama). The original positional-message constructor stays const and backward-compatible.

Removed

• VideoModelV1 and its VideoModelV1CallOptions / VideoModelV1GenerateResult types. No provider ever implemented video generation, so the interface was dead surface area. The matching generateVideo entry point was removed from ai_sdk_dart in the same release.

What's Changed

• Development environment setup: fix dependency conflict + add AGENTS.md by @codenameakshay in #1
• feat: update v1.1.0 by @codenameakshay in #2

New Contributors

• @codenameakshay made their first contribution in #1

Full Changelog: 1.0.0+1...1.1.0

• LanguageModelV3CallOptions.outputSchema — new optional Map<String, dynamic>? field. When non-null, providers that support native structured output (e.g. OpenAI response_format: json_schema) should use it to request schema-validated responses directly from the model API.

First stable release. Defines the provider interface contract for all AI SDK Dart providers.

• LanguageModelV3 — doGenerate / doStream interface.
• EmbeddingModelV2<VALUE> — doEmbed interface.
• ImageModelV3 — doGenerate interface.
• SpeechModelV1 — doGenerate interface.
• TranscriptionModelV1 — doGenerate interface.
• RerankModelV1 — doRerank interface.
• Full LanguageModelV3StreamPart sealed class hierarchy (text, tool call, reasoning, source, file, finish, error parts).
• LanguageModelV3CallOptions with all v6 call-time options.
• LanguageModelV3GenerateResult and LanguageModelV3StreamResult.
• Shared types: JsonValue, ProviderMetadata, content parts, finish reasons, tool definitions, usage.

Full Changelog: https://github.com/codenameakshay/ai_sdk_dart/commits/1.0.0+1

• Improved pubspec descriptions for better pub.dev discoverability.
• Added example/example.md with usage examples and links to runnable apps.