instructor_dart 0.2.3

instructor_dart: ^0.2.3 copied to clipboard

• Shorten the screenshot description. pub.dev accepts up to 200 characters but scores only those under 160, so the previous release published cleanly and quietly gave up the documentation points it was meant to earn.

• Declare the diagram in pubspec.yaml so pub.dev renders it on the package page. It was already in the repository and the README, but pub.dev shows only what the screenshots: field points at.

• Shorten the pub.dev description back under the 180-character limit. The previous release grew it past that, which costs the "valid pubspec" points and truncates the text search engines show.

• Add GeminiAdapter for the Gemini API's generateContent, completing the three major providers. The schema is sent as a function declaration and forced with functionCallingConfig.mode: "ANY". Two Gemini-specific shapes are handled: contents only accepts the user and model roles, so an assistant message is sent as model, and system text goes in the top-level systemInstruction rather than being a message. The API key is sent in the x-goog-api-key header instead of the key query parameter, so it stays out of URLs and logs.

• Docs: tightened the README wording and visuals.

• Expand the package description to name what the package does in the words people search for. No code changes.

Initial release.

• Plain-Dart schema builder rendering to JSON Schema: objects, strings, integers, numbers, booleans, enums, lists, nesting, optional properties, length/range/pattern constraints.
• Local validation with JSONPath-style violation reporting.
• Instructor.extract / extractRaw with an automatic repair loop that feeds validation errors back to the model.
• OpenAIAdapter for OpenAI and OpenAI-compatible servers (Ollama, LM Studio, vLLM, OpenRouter), using forced tool calls.
• AnthropicAdapter for the Anthropic Messages API, using forced tool use.
• ExtractionException with full attempt history.