Documentation
¶
Overview ¶
Package anthropic implements the Anthropic Messages wire protocol reused by native and compatible provider endpoints inside the models module.
Constructors:
- NewMessages — native /v1/messages. Full Claude surface: extended thinking blocks, tool_use with signature continuity, citations, fine-grained tool-result content blocks, cache_control.
Provider packages exposing an Anthropic-compatible endpoint reuse the Messages protocol through NewCompatibleMessages and select one typed Dialect. Application code continues to use the provider's own chat type.
Messages.CountInputTokens exposes the provider-specific complete-request token endpoint. NewTextCounter serves isolated text workflows.
Anthropic's Message Batches API (~50% pricing, up to 24h asynchronous) doesn't fit core/chat's synchronous request/response shape and is not exposed.
Model id constants aren't exported — anthropic-sdk-go owns them (anthropicsdk.ModelClaudeOpus5, anthropicsdk.ModelClaudeSonnet5, anthropicsdk.ModelClaudeFable5, etc.). Import the SDK directly when you need them.
Index ¶
- Constants
- func NewRedactedThinkingPart(data []byte) (corechat.Part, error)
- func NewThinkingPart(text string, signature []byte) (corechat.Part, error)
- type Dialect
- type Messages
- func (m *Messages) Call(ctx context.Context, req *corechat.Request) (*corechat.Response, error)
- func (m *Messages) CountInputTokens(ctx context.Context, req *corechat.Request) (int64, error)
- func (m *Messages) Stream(ctx context.Context, req *corechat.Request) iter.Seq2[*corechat.ResponseDelta, error]
- type MessagesConfig
- type ReasoningBlockKind
- type TextCounter
- type TextCounterConfig
Constants ¶
const ( // ResponseExtensionKey preserves the complete official Anthropic response. ResponseExtensionKey = "anthropic/response" // StreamEventExtensionKey preserves each official Anthropic stream event. StreamEventExtensionKey = "anthropic/stream_event" )
const ( // RequestExtensionKey stores provider-owned top-level Messages API fields in // a Core request for fields without a provider-neutral equivalent. RequestExtensionKey = "anthropic/request" )
Variables ¶
This section is empty.
Functions ¶
func NewRedactedThinkingPart ¶
NewRedactedThinkingPart preserves an opaque Anthropic thinking block without pretending its content is readable text.
Types ¶
type Dialect ¶
type Dialect struct {
// Provider scopes opaque reasoning state to the API that issued it. It is
// required even when the provider uses Anthropic's wire shape because signed
// thinking is not portable across vendors.
Provider string
MaxTemperature float64
RejectTopK bool
RejectTopP bool
// NativeJSONSchema reports whether this endpoint implements Anthropic's
// output_config.format JSON Schema control. Compatible providers that do not
// declare it receive the shared prompt fallback.
NativeJSONSchema bool
}
Dialect declares the protocol differences selected by an Anthropic-compatible provider adapter.
type Messages ¶ added in v0.13.0
type Messages struct {
// contains filtered or unexported fields
}
Messages implements Anthropic's Messages protocol and is also the reusable protocol base for provider packages exposing a compatible endpoint.
func NewCompatibleMessages ¶ added in v0.13.0
func NewCompatibleMessages(_ context.Context, config MessagesConfig, dialect Dialect) (*Messages, error)
NewCompatibleMessages rejects an invalid compatible binding before the first call.
func NewMessages ¶ added in v0.13.0
func NewMessages(_ context.Context, config MessagesConfig) (*Messages, error)
NewMessages rejects an invalid provider binding before the first Messages call.
func (*Messages) CountInputTokens ¶ added in v0.13.0
CountInputTokens calls the provider's Messages token-count endpoint with the same provider request projection used by Call.
type MessagesConfig ¶ added in v0.13.0
type MessagesConfig struct {
APIKey string
DefaultOptions corechat.Options
BaseURL string
HTTPClient *http.Client
Headers http.Header
}
MessagesConfig configures an Anthropic Messages adapter. Defaults are copied during construction; callers may select the model per request.
func (MessagesConfig) Validate ¶ added in v0.13.0
func (m MessagesConfig) Validate() error
type ReasoningBlockKind ¶
type ReasoningBlockKind string
ReasoningBlockKind identifies the official Anthropic reasoning block carried by a Core reasoning part.
const ( ReasoningBlockThinking ReasoningBlockKind = protocolReasoningThinking ReasoningBlockRedacted ReasoningBlockKind = protocolReasoningRedacted )
The vocabulary is closed because these kinds classify reasoning blocks the service returns. A redacted block carries no readable text but must still round trip intact for a later turn to remain valid, so it cannot be folded into the thinking kind.
func ReasoningBlockKindOf ¶
func ReasoningBlockKindOf(part corechat.Part) (ReasoningBlockKind, bool, error)
ReasoningBlockKindOf reports whether part contains Anthropic-issued reasoning replay state and, when it does, which official block variant it is.
type TextCounter ¶ added in v0.21.0
type TextCounter struct {
// contains filtered or unexported fields
}
TextCounter reports input-token counts via Anthropic's /messages/count_tokens endpoint. Implements tokenizer.TextCounter so it drops into code paths already gating on token budgets (RAG chunking, prompt-window checks, cost preflight).
Every count is a network round-trip; for high-QPS counting reach for an offline tokenizer instead.
func NewTextCounter ¶ added in v0.21.0
func NewTextCounter(_ context.Context, config TextCounterConfig) (*TextCounter, error)
NewTextCounter rejects an invalid provider/model binding before counting begins.
type TextCounterConfig ¶ added in v0.21.0
TextCounterConfig configures an Anthropic-backed token counter. Model picks the tokenizer vocabulary Anthropic counts against; a mismatch (Claude 3 model name vs Claude 4 vocab) produces wrong counts.
func (TextCounterConfig) Validate ¶ added in v0.21.0
func (t TextCounterConfig) Validate() error
Source Files