executus/model/sink.go

package model

import (
	"context"
	"time"
)

// This file is executus's inversion of mort's llmusage / llmtrace coupling.
// The model package owns the MECHANISM (instrument every parsed model's
// Generate, attribute by serving model, emit a span when a trace is active);
// WHERE usage/traces land is a host seam. A host registers a UsageSink and/or
// a TraceSink; both are optional (nil = off), so a light host records nothing.

// --- Usage ---

// UsageSink receives one record per successful Generate through a model parsed
// by this package (ParseModelRequest / ParseModelForContext). Implement it to
// meter or bill; the token detail mirrors majordomo's Response.Usage.
type UsageSink interface {
	Record(ctx context.Context, model string, inputTokens, outputTokens, cacheReadTokens, cacheWriteTokens int)
}

var usageSink UsageSink

// SetUsageSink installs the usage sink (nil disables usage recording). Call at
// startup before model calls.
func SetUsageSink(s UsageSink) { usageSink = s }

// --- Trace ---

// Span is one traced model call. The host's TraceSink persists it however it
// likes (a DB row, a log line, an OTel span). String fields carrying structured
// data (Messages, ToolDefinitions, ...) are pre-marshalled JSON.
type Span struct {
	SpanID  string
	TraceID string
	Model   string

	SystemPrompt      string
	Messages          string
	ToolDefinitions   string
	ResponseText      string
	ResponseToolCalls string
	ToolResults       string
	Error             string

	InputTokens  int
	OutputTokens int
	DurationMs   int64

	StartedAt   time.Time
	CompletedAt time.Time
	CreatedAt   time.Time
}

// TraceSink receives a Span for each traced call (one is emitted only when a
// trace id is present on the context — see WithTraceID).
type TraceSink interface {
	WriteSpan(span Span)
}

var traceSink TraceSink

// SetTraceSink installs the trace sink (nil disables tracing).
func SetTraceSink(s TraceSink) { traceSink = s }

// TraceSinkActive reports whether a trace sink is installed.
func TraceSinkActive() bool { return traceSink != nil }

// --- Context attribution ---
//
// ParseModelForContext stamps the requested model onto the context so usage
// from a response that doesn't name its serving model can still be attributed.
// A host's tracing/usage middleware stamps a trace id and optional caller/tool
// for diagnostics. All reads are nil/empty-safe.

type (
	ctxKeyModel struct{}
	ctxKeyTrace struct{}
	ctxKeyTool  struct{}
	ctxKeyUser  struct{}
)

// WithModel attributes subsequent usage on ctx to the given model name.
func WithModel(ctx context.Context, model string) context.Context {
	return context.WithValue(ctx, ctxKeyModel{}, model)
}

func modelFromContext(ctx context.Context) string {
	if v, ok := ctx.Value(ctxKeyModel{}).(string); ok {
		return v
	}
	return ""
}

// WithTraceID marks ctx as belonging to a trace; a TraceSink (if installed)
// then receives a Span per call. An empty id (or no id) disables tracing.
func WithTraceID(ctx context.Context, id string) context.Context {
	return context.WithValue(ctx, ctxKeyTrace{}, id)
}

func traceIDFromContext(ctx context.Context) string {
	if v, ok := ctx.Value(ctxKeyTrace{}).(string); ok {
		return v
	}
	return ""
}

// WithUsageTool / WithUsageUser attach optional attribution used only in the
// "unknown model" diagnostic warning. Default "unknown".
func WithUsageTool(ctx context.Context, tool string) context.Context {
	return context.WithValue(ctx, ctxKeyTool{}, tool)
}

func toolFromContext(ctx context.Context) string {
	if v, ok := ctx.Value(ctxKeyTool{}).(string); ok && v != "" {
		return v
	}
	return "unknown"
}

func WithUsageUser(ctx context.Context, user string) context.Context {
	return context.WithValue(ctx, ctxKeyUser{}, user)
}

func userFromContext(ctx context.Context) string {
	if v, ok := ctx.Value(ctxKeyUser{}).(string); ok && v != "" {
		return v
	}
	return "unknown"
}