Documentation
¶
Overview ¶
Package delegation runs an explicit bounded local-first task policy. It can escalate once after a known complete durable answer fails declared checks; it never retries uncertain calls, intercepts an agent session, or picks models.
Index ¶
- Variables
- func NewOutcomeRunID() (string, error)
- func OutcomeRecord(request Request, result Result, runID string) outcomes.Run
- func RecordOutcome(ctx context.Context, broker inference.Broker, request Request, result *Result, ...)
- func RequestDigest(request Request) string
- func ShadowPartition(request Request, tier Tier, runtimeID string) (string, error)
- func SpecForTier(request Request, tierID string, allowPaid bool) (inference.Spec, error)
- func Validate(request Request, allowPaid bool) error
- type Attempt
- type OutcomeTracking
- type Policy
- type Request
- type Result
- type Router
- type Runner
- type RunnerFactory
- type ShadowObserver
- type Tier
Constants ¶
This section is empty.
Variables ¶
var ( ErrQualityFailed = errors.New("delegated task did not satisfy every declared quality check") ErrStopped = errors.New("delegated task stopped without escalating; inspect its recorded outcome") )
Functions ¶
func NewOutcomeRunID ¶ added in v0.9.0
func OutcomeRecord ¶ added in v0.9.0
func RecordOutcome ¶ added in v0.9.0
func RequestDigest ¶ added in v0.13.0
RequestDigest returns the canonical identity used by Router results. Callers must Validate the request before using the digest as an approval binding. Outcome tracking is excluded, matching the existing generation identity.
func ShadowPartition ¶ added in v0.14.0
ShadowPartition binds every approved non-question part of the task. Bindings must declare business variables embedded in the question; a partition alone is not a proof that two free-form questions have equivalent answers.
func SpecForTier ¶ added in v0.13.0
SpecForTier validates the entire approved request and returns the exact derived spec for a declared tier. It uses the Router's unchanged task and revision identities; it performs no inference or provider discovery.
Types ¶
type Attempt ¶
type Attempt struct {
BudgetDiagnostic *inference.BudgetDiagnostic `json:"budget_diagnostic,omitempty"`
TierID string `json:"tier_id"`
Result inference.Result `json:"result"` // Response.Text is always stripped.
Checks []evaluation.CheckResult `json:"checks"`
QualityPassed bool `json:"quality_passed"`
OutputSHA256 string `json:"output_sha256,omitempty"`
ErrorCategory string `json:"error_category,omitempty"`
}
type OutcomeTracking ¶ added in v0.4.0
type OutcomeTracking struct {
Status string `json:"status"` // recorded or failed
RunID string `json:"run_id"`
Task outcomes.Task `json:"task"`
Receipt *outcomes.Receipt `json:"receipt,omitempty"`
Record *outcomes.Run `json:"record,omitempty"`
}
OutcomeTracking is separate from answer quality. Registration failure never changes a checked answer or authorizes another model call. Record is returned on failure so the exact metadata can be reconciled without regenerating text.
type Request ¶
type Request struct {
TrackOutcome bool `json:"track_outcome,omitempty"` // Opt-in shared accounting; excluded from generation identity.
Spec inference.Spec `json:"spec"`
Policy Policy `json:"policy"`
Checks []evaluation.Check `json:"checks"`
SemanticShadow *semantic.Config `json:"semantic_shadow,omitempty"` // Advisory observation; excluded from generation identity.
}
Request.Spec supplies approved task, revision, prompt and context only. Every model and resource setting comes from the explicit tier templates.
type Result ¶
type Result struct {
SemanticShadow *semantic.Observation `json:"semantic_shadow,omitempty"`
BudgetDiagnostic *inference.BudgetDiagnostic `json:"budget_diagnostic,omitempty"`
OutcomeTracking *OutcomeTracking `json:"outcome_tracking,omitempty"`
RequestSHA256 string `json:"request_sha256"`
Attempts []Attempt `json:"attempts"`
SelectedTier string `json:"selected_tier,omitempty"`
Response *inference.Response `json:"response,omitempty"` // Only a passing answer is exposed.
Status string `json:"status"` // completed, quality_failed, stopped
}
type Router ¶
type Router struct {
Factory RunnerFactory
AllowPaid bool // Caller permission, never read from request JSON or environment.
Shadow *ShadowObserver
}
func (Router) Run ¶
Run executes at most two explicitly configured tiers. A second tier is reached only after error-free, known complete and durable output fails the declared checks. Every provider/accounting error stops the whole policy. Repeated calls retain the same request/tier identity and the Runner's reuse behavior; the Router never changes a revision to force another generation.
type RunnerFactory ¶
type ShadowObserver ¶ added in v0.14.0
type ShadowObserver struct {
Broker inference.Broker
Index semantic.Index
EmbedderFactory func(context.Context, semantic.Config) (semantic.Embedder, error)
Resources admission.Source // nil lets a Go caller provide its own admission.
// contains filtered or unexported fields
}
ShadowObserver is optional, local-only opportunity measurement. One observer admits one bounded observation at a time and retains no waiting task history. Failures never change a generated answer, its accounting, or its claims.
Source Files