[aw] Pin Daily Go Function Namer experiment to concrete Claude models (#37325)

Author: Copilot

.github/workflows/daily-function-namer.lock.yml

@@ -20,9 +20,9 @@ engine:
 
 experiments:
   model_size:
-    variants: [agent, small-agent]
-    description: "Tests whether a small-agent model identifies function rename candidates with equivalent quality at lower token cost."
-    hypothesis: "H0: no change in issue creation rate or run success rate. H1: small-agent reduces effective token usage >=30% with equivalent run success rate (>=0.90)."
+    variants: [claude-sonnet-4-6, claude-haiku-4-5-20251001]
+    description: "Tests whether Claude Haiku identifies function rename candidates with equivalent quality at lower token cost versus Claude Sonnet."
+    hypothesis: "H0: no change in issue creation rate or run success rate. H1: Claude Haiku reduces effective token usage >=30% with equivalent run success rate (>=0.90)."
     metric: effective_tokens_total
     secondary_metrics: [run_success_rate, run_duration_ms]
     guardrail_metrics:

.github/workflows/daily-function-namer.md

@@ -8,6 +8,7 @@ import (
 	"strings"
 	"testing"
 
+	"github.com/github/gh-aw/pkg/parser"
 	"github.com/github/gh-aw/pkg/stringutil"
 )
 
@@ -241,6 +242,45 @@ func TestDailyFunctionNamerColdStartHandling(t *testing.T) {
 	}
 }
 
+func TestDailyFunctionNamerUsesConcreteClaudeModelsForExperiment(t *testing.T) {
+	repoRoot, err := findRepoRoot()
+	if err != nil {
+		t.Fatalf("Failed to find repo root: %v", err)
+	}
+
+	workflowFile := filepath.Join(repoRoot, ".github", "workflows", "daily-function-namer.md")
+	content, err := os.ReadFile(workflowFile)
+	if err != nil {
+		t.Fatalf("Failed to read workflow file: %v", err)
+	}
+
+	parsed, err := parser.ExtractFrontmatterFromContent(string(content))
+	if err != nil {
+		t.Fatalf("Failed to parse workflow frontmatter: %v", err)
+	}
+
+	experiments, ok := parsed.Frontmatter["experiments"].(map[string]any)
+	if !ok {
+		t.Fatal("Expected daily-function-namer workflow to define experiments")
+	}
+	modelSize, ok := experiments["model_size"].(map[string]any)
+	if !ok {
+		t.Fatal("Expected daily-function-namer workflow to define experiments.model_size")
+	}
+	variants, ok := modelSize["variants"].([]any)
+	if !ok {
+		t.Fatal("Expected daily-function-namer workflow to define experiments.model_size.variants")
+	}
+	if len(variants) != 2 || variants[0] != "claude-sonnet-4-6" || variants[1] != "claude-haiku-4-5-20251001" {
+		t.Fatalf("Expected concrete Claude variants [claude-sonnet-4-6, claude-haiku-4-5-20251001], got %#v", variants)
+	}
+	for _, variant := range variants {
+		if variant == "agent" || variant == "small-agent" {
+			t.Fatalf("Expected concrete model variants, found alias %q", variant)
+		}
+	}
+}
+
 // ============================================================================
 // Playwright Prompt Tests
 // ============================================================================