Introduces v2/agent with a minimal API: Agent, New(), Run(), and AsTool().
Agents wrap a model + system prompt + tools. AsTool() turns an agent into
a llm.Tool, enabling parent agents to delegate to sub-agents through the
normal tool-call loop — no channels, pools, or orchestration needed.
Also exports NewClient(provider.Provider) for custom provider integration.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Generic functions that use the "hidden tool" technique to force models
to return structured JSON matching a Go struct's schema, replacing the
verbose "tool as structured output" pattern.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Cover all core library logic (Client, Model, Chat, middleware, streaming,
message conversion, request building) using a configurable mock provider
that avoids real API calls. ~50 tests across 7 files.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Migrate speech-to-text transcription types and OpenAI transcriber
implementation from v1. Types are defined in provider/ to avoid
import cycles and re-exported via type aliases from the root package.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Runs on all pushes and PRs:
- Build, vet, and test both root and v2 modules (with -race)
- Verify go.mod/go.sum tidiness for both modules
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
v2 is a new Go module (v2/) with a dramatically simpler API:
- Unified Message type (no more Input marker interface)
- Define[T] for ergonomic tool creation with standard context.Context
- Chat session with automatic tool-call loop (agent loop)
- Streaming via pull-based StreamReader
- MCP one-call connect (MCPStdioServer, MCPHTTPServer, MCPSSEServer)
- Middleware support (logging, retry, timeout, usage tracking)
- Decoupled JSON Schema (map[string]any, no provider coupling)
- Sample tools: WebSearch, Browser, Exec, ReadFile, WriteFile, HTTP
- Providers: OpenAI, Anthropic, Google (all with streaming)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Introduce `MCPServer` to support connecting to MCP servers via stdio, SSE, or HTTP.
- Implement tool fetching, management, and invocation through MCP.
- Add `WithMCPServer` method to `ToolBox` for seamless tool integration.
- Extend schema package to handle raw JSON schemas for MCP tools.
- Update documentation with MCP usage guidelines and examples.
- Migrate `compress_image.go` to `internal/imageutil` for better encapsulation.
- Reorganize LLM provider implementations into distinct packages (`google`, `openai`, and `anthropic`).
- Replace `go_llm` package name with `llm`.
- Refactor internal APIs for improved clarity, including renaming `anthropic` to `anthropicImpl` and `google` to `googleImpl`.
- Add helper methods and restructure message handling for better separation of concerns.
- Update all Go dependencies to latest versions
- Migrate from github.com/google/generative-ai-go/genai to google.golang.org/genai
- Fix google.go to use the new SDK API (NewPartFromText, NewContentFromParts, etc.)
- Update schema package imports to use the new genai package
- Add CLAUDE.md with README maintenance guideline
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Introduce `Providers` struct to handle different language model providers. Implement `Parse` method to extract and validate provider/model from input string, then return a chat completion interface. Add error handling for invalid formats or unknown providers.
Previously, required fields were not handled in OpenAI and Google parameter generation. This update adds logic to include a "required" list for both, ensuring mandatory fields are accurately captured in the schema outputs.
This update introduces support for `jsonschema.Integer` types and updates the logic to handle nested items in schemas. Added a new default error log for unknown types using `slog.Error`. Also, integrated tool configuration with a `FunctionCallingConfig` when `dontRequireTool` is false.
This update introduces support for `jsonschema.Integer` types and updates the logic to handle nested items in schemas. Added a new default error log for unknown types using `slog.Error`. Also, integrated tool configuration with a `FunctionCallingConfig` when `dontRequireTool` is false.
Updated the return type of functions and related code from `string` to `any` to improve flexibility and support more diverse outputs. Adjusted function implementations, signatures, and handling of results accordingly.
Introduced `WithFunctionRemoved` and `ExecuteCallbacks` methods to enhance `ToolBox` functionality. This allows dynamic function removal and execution of custom callbacks during tool call processing. Also cleaned up logging and improved handling for required tools in `openai.go`.
Introduce `Response()` and `ToolCall()` methods to access the respective fields from the `Context` struct. This enhances encapsulation and provides a standardized way to retrieve these values.
Previously, OpenAI messages containing both `Content` and `MultiContent` could cause inconsistent behavior. This update ensures `Content` is converted into a `MultiContent` entry to maintain compatibility.
Previously, execution errors were only returned in the refusal field. This update appends errors to the result field if present, ensuring they are included in the tool's output. This change improves visibility and clarity for error reporting.
Simplified how responses and tool calls are appended to conversations. Adjusted structure in message formatting to better align with tool call requirements, ensuring consistent data representation.
Enhanced the `requestToChatHistory` method to include OpenAI schema conversion logic and integrate tools with generative AI schemas. This change improves flexibility when working with different schema types and tool definitions. Adjusted response handling to return a modified model alongside chat sessions and parts.
Replace message handling with a chat session model, aligning the logic with new API requirements. Adjust functions to properly build chat history and send messages via chat sessions, improving compatibility and extensibility.
Implemented a nil check for Toolbox to prevent potential nil pointer dereferences. Cleaned up and reorganized code for better readability and maintainability while keeping placeholder functionality intact.
Anthropic API does not support assistants sending images directly, so the role is adjusted to "user" for such messages. This ensures compatibility and prevents errors when processing image messages.
Modify `FunctionCall` struct to handle arguments as strings. Add debugging logs to facilitate error tracing and improve JSON unmarshalling in various functions.
