Documentation
¶
Overview ¶
Package base provides the shared runtime struct and core execution methods used by both the local and temporal runtime backends. It has no dependency on any backend-specific SDK (no Temporal, no workflow/activity imports).
Index ¶
- func ApplyLLMSampling(s *types.LLMSampling, req *interfaces.LLMRequest)
- func CloneLLMUsage(u *interfaces.LLMUsage) *interfaces.LLMUsage
- func FindToolByName(tools []interfaces.Tool, toolName string) (interfaces.Tool, bool)
- func FormatRetrieverDocs(docs []interfaces.Document) string
- func MergeLLMUsage(acc, add *interfaces.LLMUsage) *interfaces.LLMUsage
- func SubAgentQuery(args map[string]any) string
- type AuthorizeResult
- type LLMResult
- type Runtime
- func (rt *Runtime) AuthorizeTool(ctx context.Context, log logger.Logger, toolName string, args map[string]any) (AuthorizeResult, error)
- func (rt *Runtime) BuildLLMRequest(messages []interfaces.Message, skipTools bool, retrieverContext string) (*interfaces.LLMRequest, []interfaces.Tool)
- func (rt *Runtime) ExecuteLLM(ctx context.Context, log logger.Logger, agentName, messageID string, ...) (*LLMResult, error)
- func (rt *Runtime) ExecuteLLMStream(ctx context.Context, log logger.Logger, agentName, messageID string, ...) (*LLMResult, error)
- func (rt *Runtime) ExecuteRetrievers(ctx context.Context, log logger.Logger, query string) (string, error)
- func (rt *Runtime) ExecuteTool(ctx context.Context, log logger.Logger, toolName string, args map[string]any) (string, error)
- func (rt *Runtime) FetchConversationMessages(ctx context.Context, log logger.Logger, conversationID string) ([]interfaces.Message, error)
- func (rt *Runtime) RequiresApproval(t interfaces.Tool) bool
- type ToolCallRequest
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
func ApplyLLMSampling ¶
func ApplyLLMSampling(s *types.LLMSampling, req *interfaces.LLMRequest)
ApplyLLMSampling copies non-zero sampling fields from s onto req. A nil sampling value is a no-op.
func CloneLLMUsage ¶
func CloneLLMUsage(u *interfaces.LLMUsage) *interfaces.LLMUsage
CloneLLMUsage returns a shallow copy of u, or nil when u is nil.
func FindToolByName ¶
func FindToolByName(tools []interfaces.Tool, toolName string) (interfaces.Tool, bool)
FindToolByName returns the first tool whose Name() matches toolName.
func FormatRetrieverDocs ¶
func FormatRetrieverDocs(docs []interfaces.Document) string
FormatRetrieverDocs formats a list of documents for injection into the LLM system prompt. Each entry is rendered as "[N] content\n(source: s, score: 0.XX)\n\n".
func MergeLLMUsage ¶
func MergeLLMUsage(acc, add *interfaces.LLMUsage) *interfaces.LLMUsage
MergeLLMUsage accumulates add into acc and returns the result. Either argument may be nil; when both are nil, nil is returned.
func SubAgentQuery ¶
SubAgentQuery extracts the query string from a sub-agent tool call's args map.
Types ¶
type AuthorizeResult ¶
AuthorizeResult is the outcome of a programmatic tool authorization check. When Allowed is false, Reason carries the denial message for logging/events.
type LLMResult ¶
type LLMResult struct {
Content string
ToolCalls []ToolCallRequest
Usage *interfaces.LLMUsage
}
LLMResult is the result of a successful LLM call. Content holds the assistant text; ToolCalls holds any tool invocations resolved against the registered tools list (NeedsApproval pre-computed from the approval policy).
type Runtime ¶
type Runtime struct {
AgentSpec runtime.AgentSpec
AgentExecution runtime.AgentExecution
Tracer interfaces.Tracer
Metrics interfaces.Metrics
// ToolExecutionMode controls whether tool calls in one LLM round are executed
// in parallel or sequentially. Defaults to parallel when empty.
ToolExecutionMode types.AgentToolExecutionMode
}
Runtime holds the execution inputs shared by all runtime backends. Local and Temporal runtimes embed this struct and call its methods directly.
func (*Runtime) AuthorizeTool ¶
func (rt *Runtime) AuthorizeTool(ctx context.Context, log logger.Logger, toolName string, args map[string]any) (AuthorizeResult, error)
AuthorizeTool checks programmatic authorization for a tool before approval/execution. Tools that do not implement interfaces.ToolAuthorizer are allowed by default.
func (*Runtime) BuildLLMRequest ¶
func (rt *Runtime) BuildLLMRequest(messages []interfaces.Message, skipTools bool, retrieverContext string) (*interfaces.LLMRequest, []interfaces.Tool)
BuildLLMRequest constructs an LLMRequest from the given messages and options. When retrieverContext is non-empty it is appended to the system prompt (prefetch/hybrid mode). Returns the request and the resolved tools slice for later use in response parsing.
func (*Runtime) ExecuteLLM ¶
func (rt *Runtime) ExecuteLLM( ctx context.Context, log logger.Logger, agentName, messageID string, messages []interfaces.Message, skipTools bool, retrieverContext string, emit func(events.AgentEvent), ) (*LLMResult, error)
ExecuteLLM calls the LLM in non-streaming mode, records metrics and traces, emits TEXT_MESSAGE_START / TEXT_MESSAGE_CONTENT / TEXT_MESSAGE_END events, and returns LLMResult. messageID and agentName are used only for event construction; emit may be nil.
func (*Runtime) ExecuteLLMStream ¶
func (rt *Runtime) ExecuteLLMStream( ctx context.Context, log logger.Logger, agentName, messageID string, messages []interfaces.Message, skipTools bool, retrieverContext string, emit func(events.AgentEvent), ) (*LLMResult, error)
ExecuteLLMStream calls the LLM in streaming mode. When the LLM client does not support streaming it falls back to Generate automatically. Delta events (text content, reasoning) are emitted via emit as chunks arrive; a final TEXT_MESSAGE_START/CONTENT/END triple is emitted for non-streaming fallback. emit may be nil.
func (*Runtime) ExecuteRetrievers ¶
func (rt *Runtime) ExecuteRetrievers(ctx context.Context, log logger.Logger, query string) (string, error)
ExecuteRetrievers runs all configured retrievers in parallel for the given query and returns a combined document context string for injection into the LLM system prompt. Partial failures are logged and skipped; all retrievers failing returns an error.
func (*Runtime) ExecuteTool ¶
func (rt *Runtime) ExecuteTool(ctx context.Context, log logger.Logger, toolName string, args map[string]any) (string, error)
ExecuteTool finds the named tool and executes it, recording tracing and metrics. Returns the string representation of the tool result.
func (*Runtime) FetchConversationMessages ¶
func (rt *Runtime) FetchConversationMessages(ctx context.Context, log logger.Logger, conversationID string) ([]interfaces.Message, error)
FetchConversationMessages loads prior messages from the conversation store. Returns an error when no conversation is configured or the store call fails.
func (*Runtime) RequiresApproval ¶
func (rt *Runtime) RequiresApproval(t interfaces.Tool) bool
RequiresApproval reports whether t requires human approval before execution. When no approval policy is configured the tool's own ApprovalRequired flag is used.
type ToolCallRequest ¶
type ToolCallRequest struct {
ToolCallID string
ToolName string
ToolDisplayName string
Args map[string]any
NeedsApproval bool
}
ToolCallRequest describes one tool call returned by the LLM. NeedsApproval is pre-computed from the tool approval policy so orchestration loops (local agent loop, temporal workflow) do not need to re-evaluate the policy.
Source Files