Documentation
¶
Overview ¶
Package anthropic implements models.Provider for Anthropic / Claude.
ADK Go ships only the Gemini and Apigee model backends, so this package adapts the official Anthropic Go SDK (github.com/anthropics/anthropic-sdk-go) to the ADK's model.LLM interface. genai-shaped requests are translated to Anthropic's Messages API; streaming responses are accumulated back into genai-shaped events the ADK runner expects.
Conversation history is preserved automatically by the ADK runner (the in-memory session service replays prior events on each turn); this provider is stateless aside from the API client.
Index ¶
Constants ¶
const ( EnvVertexProject = "ANTHROPIC_VERTEX_PROJECT_ID" EnvVertexRegion = "CLOUD_ML_REGION" )
Env vars consulted by the Vertex constructor when project / region are not supplied explicitly via config. Names match Anthropic SDK conventions; the GCP-standard fallbacks let the same env that drives Vertex Gemini also drive Vertex Anthropic.
const DefaultMaxTokens = 16_384
DefaultMaxTokens caps a single response when the caller hasn't set one. 16K is a comfortable middle ground: plenty for most turns, well under the streaming SDK's HTTP timeouts.
const DefaultModel = "claude-opus-4-7"
DefaultModel is used when LLMRequest.Model is empty. We follow the claude-api skill's guidance and default to the most capable Opus.
const DefaultSmallModelID = "claude-haiku-4-5"
DefaultSmallModelID is the Anthropic cheap-tier model used by default for agentic subtasks when the operator hasn't pinned one with --agentic-small-model. Same value for the first-party and Vertex backends; the Vertex publication name resolves at call time.
const DefaultVertexRegion = "us-east5"
Default Vertex region for Claude. Most current Anthropic Vertex deployments live in us-east5; override per call site as needed.
const EnvAPIKey = "ANTHROPIC_API_KEY" // #nosec G101 -- env var name, not a credential
EnvAPIKey is the environment variable consulted when no key is supplied via config.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type BuiltinTools ¶
type BuiltinTools struct {
WebSearch bool // Server-side web search; per-search billing on top of tokens.
}
BuiltinTools toggles Anthropic's server-side built-in tools surfaced by core-agent. Each enabled flag becomes one entry on the request's Tools slice alongside any user-defined function declarations.
Defaults: everything OFF. Anthropic's server-side tools are billed per use on top of token cost (web_search is per-search), so we apply the same "active surface = opt in" rule that keeps Gemini's CodeExecution off by default. The library caller decides explicitly whether the cost and external-action posture are acceptable.
To turn one on:
provider, _ := anthropic.New(key, anthropic.WithWebSearch(true))
To replace the whole set:
provider, _ := anthropic.New(key, anthropic.WithBuiltinTools(anthropic.BuiltinTools{
WebSearch: true,
}))
Other Anthropic server-side tools (web_fetch, code_execution, text_editor, bash, memory) aren't surfaced today. Add them under the same struct when a concrete consumer needs one.
func DefaultBuiltinTools ¶
func DefaultBuiltinTools() BuiltinTools
DefaultBuiltinTools returns the on-by-default baseline applied to every Provider unless overridden via WithBuiltinTools or one of the per-tool helpers. Currently empty — see BuiltinTools doc for why.
type Option ¶
type Option func(*Provider)
Option configures a Provider at construction.
func WithBuiltinTools ¶
func WithBuiltinTools(b BuiltinTools) Option
WithBuiltinTools replaces the Provider's whole BuiltinTools set.
func WithCacheSystem ¶
WithCacheSystem enables prompt caching on the last system block by default. Off by default — turn it on once you've confirmed the system prompt is stable across turns (otherwise the cache write premium is paid for nothing).
func WithWebSearch ¶
WithWebSearch toggles Anthropic's server-side web_search tool. Off by default — opt in when you've decided the per-search cost and external-call posture are acceptable.
type Provider ¶
type Provider struct {
// contains filtered or unexported fields
}
Provider is the Anthropic implementation of models.Provider. The same struct serves both the first-party API and Vertex AI backends — only the embedded client differs. name carries which one this is so telemetry and Resolve() see the right identity.
func New ¶
New constructs a Provider with the given API key (first-party api.anthropic.com). Pass options to tune behavior. Empty key falls back to the ANTHROPIC_API_KEY env var.
func NewVertex ¶
NewVertex constructs a Provider that talks to Claude via Google Vertex AI. project and region are required. Authentication uses Application Default Credentials (run `gcloud auth application-default login`, or set GOOGLE_APPLICATION_CREDENTIALS, or rely on workload identity in production).
We deliberately load credentials via google.FindDefaultCredentials ourselves and pass them to vertex.WithCredentials — vertex.WithGoogleAuth panics on missing creds, which we don't want at startup.
func (*Provider) DefaultSmallModel ¶
DefaultSmallModel satisfies models.SmallModelDefaulter so core-agent can route subtask digesting to a cheap-tier Claude model without requiring the operator to set --agentic-small-model.
func (*Provider) Model ¶
Model returns a model.LLM for the given model ID. modelID may be empty, in which case DefaultModel is used.
Note: Vertex AI sometimes serves Claude under date-suffixed model IDs (e.g. "claude-opus-4-5@20251101"). When using "anthropic-vertex", pass the exact ID Vertex expects via cfg.Model.Name; the SDK plugs it into the Vertex URL path verbatim.
Source Files