feat(02-02): three-tier orchestrator with confidence routing and research stub

- Orchestrator.Analyze: tier1 → confidence check → tier2 escalation if < threshold
- CatalogStatus mapped from confidence: >= threshold → StatusIndexed, else StatusNeedsResearch
- Both tiers fail gracefully: returns zero-value IntakeResult + StatusNeedsResearch, err nil
- ResearchClient interface + NoOpResearchClient stub for Phase 7 SearXNG
- 5 TestOrchestrator* tests all passing (TDD green)
This commit is contained in:
Mikkel Georgsen 2026-04-10 05:47:41 +00:00
parent 3eed2e9c63
commit 799acd26ef
3 changed files with 222 additions and 0 deletions

View file

@ -0,0 +1,72 @@
package ai
import (
"context"
"log"
"git.georgsen.dk/hwlab/internal/inventory"
)
// Orchestrator manages the three-tier AI pipeline.
// Tier1 is local oMLX (fast, low cost). Tier2 is OpenRouter (slower, better).
// Tier3 (Lab Advisor) is out of scope for Phase 2.
type Orchestrator struct {
tier1 AIClient
tier2 AIClient
threshold float64 // confidence threshold for escalation; default 0.75
}
// NewOrchestrator creates an Orchestrator. Both tier1 and tier2 must be non-nil.
func NewOrchestrator(tier1, tier2 AIClient, threshold float64) *Orchestrator {
if threshold <= 0 {
threshold = 0.75
}
return &Orchestrator{tier1: tier1, tier2: tier2, threshold: threshold}
}
// Analyze runs tier1 and escalates to tier2 if confidence is below threshold.
// Never returns an error from individual tier failures — tier errors cause escalation.
// Returns a non-nil IntakeResult in all cases (may be zero-value on total failure).
// The returned CatalogStatus is either StatusIndexed or StatusNeedsResearch.
func (o *Orchestrator) Analyze(ctx context.Context, req IntakeRequest) (*IntakeResult, inventory.CatalogStatus, error) {
result, err := o.tier1.AnalyzePhotos(ctx, req)
if err != nil {
log.Printf("orchestrator: tier1 error (escalating to tier2): %v", err)
result = nil
}
// Escalate if tier1 result is missing, nil, or low confidence
if result == nil || result.Confidence < o.threshold {
log.Printf("orchestrator: tier1 confidence=%.2f < threshold=%.2f — escalating to tier2",
confidenceOf(result), o.threshold)
result2, err2 := o.tier2.AnalyzePhotos(ctx, req)
if err2 != nil {
log.Printf("orchestrator: tier2 error: %v", err2)
} else if result2 != nil {
result = result2
}
}
// Map confidence to CatalogStatus
if result == nil {
return &IntakeResult{
AINotes: "all AI tiers failed",
Confidence: 0.0,
ConfidenceNote: "no result from any tier",
}, inventory.StatusNeedsResearch, nil
}
status := inventory.StatusIndexed
if result.Confidence < o.threshold {
status = inventory.StatusNeedsResearch
}
return result, status, nil
}
// confidenceOf returns 0.0 for nil results, otherwise result.Confidence.
func confidenceOf(r *IntakeResult) float64 {
if r == nil {
return 0.0
}
return r.Confidence
}

View file

@ -0,0 +1,126 @@
package ai
import (
"context"
"errors"
"testing"
"git.georgsen.dk/hwlab/internal/inventory"
)
func testReq() IntakeRequest {
return IntakeRequest{PhotosBase64: []string{"data:image/jpeg;base64,/9j/"}, JobID: "test-job"}
}
// TestOrchestratorHighConfidence: tier1 returns confidence 0.95; tier2 never called; status == StatusIndexed
func TestOrchestratorHighConfidence(t *testing.T) {
tier1 := &MockAIClient{FixedResult: HighConfidenceResult()}
tier2 := &MockAIClient{}
o := NewOrchestrator(tier1, tier2, 0.75)
result, status, err := o.Analyze(context.Background(), testReq())
if err != nil {
t.Fatalf("expected no error, got: %v", err)
}
if result == nil {
t.Fatal("expected non-nil result")
}
if status != inventory.StatusIndexed {
t.Errorf("expected StatusIndexed, got %q", status)
}
if len(tier2.Calls) != 0 {
t.Errorf("expected tier2 never called, got %d calls", len(tier2.Calls))
}
if len(tier1.Calls) != 1 {
t.Errorf("expected tier1 called once, got %d calls", len(tier1.Calls))
}
}
// TestOrchestratorLowConfidenceEscalates: tier1 returns confidence 0.40; tier2 called once; tier2 returns 0.85; status == StatusIndexed
func TestOrchestratorLowConfidenceEscalates(t *testing.T) {
tier1 := &MockAIClient{FixedResult: LowConfidenceResult()}
tier2 := &MockAIClient{FixedResult: HighConfidenceResult()}
o := NewOrchestrator(tier1, tier2, 0.75)
result, status, err := o.Analyze(context.Background(), testReq())
if err != nil {
t.Fatalf("expected no error, got: %v", err)
}
if result == nil {
t.Fatal("expected non-nil result")
}
if status != inventory.StatusIndexed {
t.Errorf("expected StatusIndexed after tier2 escalation, got %q", status)
}
if len(tier2.Calls) != 1 {
t.Errorf("expected tier2 called once, got %d calls", len(tier2.Calls))
}
if result.Confidence < 0.75 {
t.Errorf("expected tier2 result confidence >= 0.75, got %.2f", result.Confidence)
}
}
// TestOrchestratorBothTiersFail: both tiers error; result is non-nil, status == StatusNeedsResearch, err == nil
func TestOrchestratorBothTiersFail(t *testing.T) {
tier1 := &MockAIClient{FixedError: errors.New("tier1 connection refused")}
tier2 := &MockAIClient{FixedError: errors.New("tier2 connection refused")}
o := NewOrchestrator(tier1, tier2, 0.75)
result, status, err := o.Analyze(context.Background(), testReq())
if err != nil {
t.Fatalf("orchestrator must not propagate tier errors, got: %v", err)
}
if result == nil {
t.Fatal("orchestrator must return non-nil result even on total failure")
}
if status != inventory.StatusNeedsResearch {
t.Errorf("expected StatusNeedsResearch on total failure, got %q", status)
}
}
// TestOrchestratorTier1NilResult: tier1 returns nil result with nil error; orchestrator escalates to tier2
func TestOrchestratorTier1NilResult(t *testing.T) {
tier1 := &MockAIClient{FixedResult: nil, FixedError: nil}
tier2 := &MockAIClient{FixedResult: HighConfidenceResult()}
o := NewOrchestrator(tier1, tier2, 0.75)
result, status, err := o.Analyze(context.Background(), testReq())
if err != nil {
t.Fatalf("expected no error, got: %v", err)
}
if result == nil {
t.Fatal("expected non-nil result from tier2 escalation")
}
if len(tier2.Calls) != 1 {
t.Errorf("expected tier2 called once after tier1 nil result, got %d calls", len(tier2.Calls))
}
if status != inventory.StatusIndexed {
t.Errorf("expected StatusIndexed from tier2, got %q", status)
}
}
// TestOrchestratorNeedsResearch: tier1 returns 0.40; tier2 also returns 0.40; final status == StatusNeedsResearch
func TestOrchestratorNeedsResearch(t *testing.T) {
tier1 := &MockAIClient{FixedResult: LowConfidenceResult()}
tier2 := &MockAIClient{FixedResult: LowConfidenceResult()}
o := NewOrchestrator(tier1, tier2, 0.75)
result, status, err := o.Analyze(context.Background(), testReq())
if err != nil {
t.Fatalf("expected no error, got: %v", err)
}
if result == nil {
t.Fatal("expected non-nil result")
}
if status != inventory.StatusNeedsResearch {
t.Errorf("expected StatusNeedsResearch when both tiers return low confidence, got %q", status)
}
if len(tier2.Calls) != 1 {
t.Errorf("expected tier2 called once, got %d calls", len(tier2.Calls))
}
}

24
internal/ai/research.go Normal file
View file

@ -0,0 +1,24 @@
package ai
import "context"
// SearchResult is a single result from a SearXNG research query.
type SearchResult struct {
Title string
URL string
Snippet string
}
// ResearchClient abstracts the SearXNG search backend.
// Phase 7 will provide a real implementation.
type ResearchClient interface {
Search(ctx context.Context, query string) ([]SearchResult, error)
}
// NoOpResearchClient is a Phase 2 stub that returns empty results.
// Replace with SearXNG HTTP client in Phase 7.
type NoOpResearchClient struct{}
func (n *NoOpResearchClient) Search(_ context.Context, _ string) ([]SearchResult, error) {
return nil, nil
}