Documentation
¶
Index ¶
- Constants
- Variables
- func ContainsContextLimitError(input string) bool
- func IsContinuationEnabled(model llm.Model, opts *llm.Options) bool
- type GenerateInput
- type GenerateOutput
- type Service
- func (s *Service) AttachmentUsage(convID string) int64
- func (s *Service) BuildContinuationRequest(ctx context.Context, req *llm.GenerateRequest, history *prompt.History) *llm.GenerateRequest
- func (s *Service) Generate(ctx context.Context, input *GenerateInput, output *GenerateOutput) error
- func (s *Service) Method(name string) (svc.Executable, error)
- func (s *Service) Methods() svc.Signatures
- func (s *Service) ModelFinder() llm.Finder
- func (s *Service) ModelImplements(ctx context.Context, modelName, feature string) bool
- func (s *Service) ModelMatcher() llm.Matcher
- func (s *Service) ModelToolPreviewLimit(model string) int
- func (s *Service) Name() string
- func (s *Service) ProviderAttachmentLimit(model llm.Model) int64
- func (s *Service) SetAttachmentUsage(convID string, used int64)
- func (s *Service) SetConversationClient(c apiconv.Client)
- func (s *Service) SetModelPreviewLimits(m map[string]int)
- func (s *Service) Stream(ctx context.Context, in, out interface{}) (func(), error)
- func (s *Service) ToolDefinitions() []llm.ToolDefinition
- type StreamInput
- type StreamOutput
Constants ¶
const Name = "llm/core"
Variables ¶
var ErrContextLimitExceeded = errors.New("llm/core: context limit exceeded")
ErrContextLimitExceeded signals that a provider/model rejected the request due to exceeding the maximum context window (prompt too long / too many tokens).
Functions ¶
func ContainsContextLimitError ¶ added in v0.2.9
func IsContinuationEnabled ¶ added in v0.2.18
IsContinuationEnabled is an exported wrapper for continuationEnabled so that other packages (e.g., providers) can check whether continuation-by-response-id should be considered for a given model and options.
Types ¶
type GenerateInput ¶
type GenerateInput struct {
llm.ModelSelection
SystemPrompt *prompt.Prompt
Prompt *prompt.Prompt
Binding *prompt.Binding
Message []llm.Message
// Participant identities for multi-user/agent attribution
UserID string `yaml:"userID" json:"userID"`
AgentID string `yaml:"agentID" json:"agentID"`
}
func (*GenerateInput) MatchModelIfNeeded ¶
func (i *GenerateInput) MatchModelIfNeeded(matcher llm.Matcher)
type GenerateOutput ¶
type GenerateOutput struct {
Response *llm.GenerateResponse
Content string
MessageID string
}
GenerateOutput represents output from extraction
type Service ¶
type Service struct {
// contains filtered or unexported fields
}
func (*Service) AttachmentUsage ¶ added in v0.2.1
AttachmentUsage returns cumulative attachment bytes recorded for a conversation.
func (*Service) BuildContinuationRequest ¶ added in v0.2.18
func (s *Service) BuildContinuationRequest(ctx context.Context, req *llm.GenerateRequest, history *prompt.History) *llm.GenerateRequest
BuildContinuationRequest constructs a continuation request by selecting the latest assistant response anchor (resp.id) and including only tool-call messages that map to that anchor.
func (*Service) Generate ¶
func (s *Service) Generate(ctx context.Context, input *GenerateInput, output *GenerateOutput) error
func (*Service) Method ¶
func (s *Service) Method(name string) (svc.Executable, error)
Method returns the specified method
func (*Service) Methods ¶
func (s *Service) Methods() svc.Signatures
Methods returns the service methods
func (*Service) ModelFinder ¶
func (*Service) ModelImplements ¶
ModelImplements reports whether a given model supports a feature. When modelName is empty or not found, it returns false.
func (*Service) ModelMatcher ¶
func (*Service) ModelToolPreviewLimit ¶ added in v0.2.6
ModelToolPreviewLimit returns the preview limit in bytes for a model or 0 when not configured.
func (*Service) ProviderAttachmentLimit ¶ added in v0.2.1
ProviderAttachmentLimit returns the provider-configured attachment cap for the given model. Zero means unlimited/not enforced by this provider.
func (*Service) SetAttachmentUsage ¶ added in v0.2.1
SetAttachmentUsage sets cumulative attachment bytes for a conversation.
func (*Service) SetConversationClient ¶
func (*Service) SetModelPreviewLimits ¶ added in v0.2.6
SetModelPreviewLimits sets per-model preview byte limits used by binding to trim tool results.
func (*Service) Stream ¶
Stream handles streaming LLM responses, structuring JSON output for text chunks, function calls and finish reasons.
func (*Service) ToolDefinitions ¶
func (s *Service) ToolDefinitions() []llm.ToolDefinition
ToolDefinitions returns every tool definition registered in the tool registry. The slice may be empty when no registry is configured (unit tests or mis-configuration).
type StreamInput ¶
type StreamInput struct {
*GenerateInput
StreamID string
}
type StreamOutput ¶
type StreamOutput struct {
Events []stream.Event `json:"events"`
MessageID string `json:"messageId,omitempty"`
}
StreamOutput aggregates streaming events into a slice.
Source Files
Directories