ai_sdk_anthropic

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

• Migrated language generation and streaming to V4 lifecycle, metadata, structured warnings, nested usage, and unified tool contracts.
• Mapped cache reads and cache writes into the nested input-token usage breakdown for both generated and streamed responses.
• Cancelling an abort signal now cancels the in-flight Dio request.

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

• Errors: non-2xx API responses now throw a typed AiApiCallError (carrying Anthropic's error message / type and the statusCode) instead of a raw DioException, on both the generate and stream paths.
• Version aligned with the rest of the monorepo (1.2.0).

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

New Features

• AnthropicThinkingOptions — typed options for Claude's extended thinking (reasoning) API.
  • budgetTokens — maximum tokens to allocate for the thinking block.
  • enabled — whether thinking is active (default true).
  • speed: 'fast' — convenience shorthand that disables the thinking block for lower-latency responses.
  • Use via providerOptions: {'anthropic': AnthropicThinkingOptions(budgetTokens: 5000).toMap()}.
• AnthropicLanguageModelOptions — top-level wrapper for Anthropic provider options; currently wraps AnthropicThinkingOptions.

First stable release. Depends on ai_sdk_dart 1.0.0.

• anthropic('claude-sonnet-4-5') factory — create language model instances.
• Full SSE streaming with thinking content block → ReasoningPart mapping.
• tool_use content block → ToolCallPart mapping.
• Tool choice mapping (Anthropic wire format).
• Tool input examples forwarding via description enrichment.
• Usage extraction from both message_start and message_delta events.
• Source, file content, and raw finish reason forwarding.
• Configurable baseUrl.

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.