feat(config): replace single-model config with chain-based routing
Implements escalation chains per skill with three-layer priority: 1. Caller override (model param) — no escalation 2. Per-skill chain from models.yaml 3. default_chain fallback New APIs: - Verifier() — fixed verifier for output validation - LlamaSwapURL() — base URL for warm-state probing - ChainFor(skill, override) — ordered model list for escalation Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -7,9 +7,15 @@ import (
|
||||
"gopkg.in/yaml.v3"
|
||||
)
|
||||
|
||||
type skillChain struct {
|
||||
Chain []string `yaml:"chain"`
|
||||
}
|
||||
|
||||
type modelsFile struct {
|
||||
Default string `yaml:"default"`
|
||||
Skills map[string]string `yaml:"skills"`
|
||||
Verifier string `yaml:"verifier"`
|
||||
LlamaSwapURL string `yaml:"llama_swap_url"`
|
||||
DefaultChain []string `yaml:"default_chain"`
|
||||
Skills map[string]skillChain `yaml:"skills"`
|
||||
}
|
||||
|
||||
type Models struct {
|
||||
@@ -28,16 +34,23 @@ func LoadModels(path string) (Models, error) {
|
||||
return Models{data: f}, nil
|
||||
}
|
||||
|
||||
// Resolve returns the model for a skill, respecting three-layer priority:
|
||||
// 1. override (from MCP call) — highest
|
||||
// 2. per-skill default from models.yaml
|
||||
// 3. global default
|
||||
func (m Models) Resolve(skill, override string) string {
|
||||
// Verifier returns the model name to use for all local-tier output verification.
|
||||
func (m Models) Verifier() string { return m.data.Verifier }
|
||||
|
||||
// LlamaSwapURL returns the llama-swap base URL for warm-state probing.
|
||||
func (m Models) LlamaSwapURL() string { return m.data.LlamaSwapURL }
|
||||
|
||||
// ChainFor returns the ordered list of model names for a skill.
|
||||
// If override is non-empty, returns a single-entry chain (no escalation).
|
||||
// Falls back to default_chain when the skill has no explicit entry.
|
||||
func (m Models) ChainFor(skill, override string) []string {
|
||||
if override != "" {
|
||||
return override
|
||||
return []string{override}
|
||||
}
|
||||
if model, ok := m.data.Skills[skill]; ok {
|
||||
return model
|
||||
if sc, ok := m.data.Skills[skill]; ok && len(sc.Chain) > 0 {
|
||||
return sc.Chain
|
||||
}
|
||||
return m.data.Default
|
||||
out := make([]string, len(m.data.DefaultChain))
|
||||
copy(out, m.data.DefaultChain)
|
||||
return out
|
||||
}
|
||||
|
||||
@@ -10,35 +10,71 @@ import (
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
func TestModelsResolve(t *testing.T) {
|
||||
yaml := `
|
||||
default: ollama/default-model
|
||||
const testYAML = `
|
||||
verifier: claude-sonnet-4-6
|
||||
llama_swap_url: http://koala:8080
|
||||
|
||||
default_chain:
|
||||
- ollama/qwen3-coder-30b-tuned
|
||||
- claude-sonnet-4-6
|
||||
|
||||
skills:
|
||||
tdd: ollama/qwen3-coder-30b-tuned
|
||||
review: ollama/devstral-tuned
|
||||
review:
|
||||
chain:
|
||||
- ollama/devstral-tuned
|
||||
- ollama/gemma4
|
||||
- claude-sonnet-4-6
|
||||
spec:
|
||||
chain:
|
||||
- ollama/phi4
|
||||
- claude-opus-4-6
|
||||
`
|
||||
|
||||
func writeModels(t *testing.T, content string) string {
|
||||
t.Helper()
|
||||
f := filepath.Join(t.TempDir(), "models.yaml")
|
||||
require.NoError(t, os.WriteFile(f, []byte(yaml), 0644))
|
||||
|
||||
m, err := config.LoadModels(f)
|
||||
require.NoError(t, err)
|
||||
|
||||
assert.Equal(t, "ollama/qwen3-coder-30b-tuned", m.Resolve("tdd", ""))
|
||||
assert.Equal(t, "ollama/devstral-tuned", m.Resolve("review", ""))
|
||||
assert.Equal(t, "ollama/default-model", m.Resolve("unknown", ""))
|
||||
require.NoError(t, os.WriteFile(f, []byte(content), 0644))
|
||||
return f
|
||||
}
|
||||
|
||||
func TestModelsOverride(t *testing.T) {
|
||||
yaml := `
|
||||
default: ollama/default-model
|
||||
skills:
|
||||
tdd: ollama/qwen3-coder-30b-tuned
|
||||
`
|
||||
f := filepath.Join(t.TempDir(), "models.yaml")
|
||||
require.NoError(t, os.WriteFile(f, []byte(yaml), 0644))
|
||||
func TestModelsVerifier(t *testing.T) {
|
||||
m, err := config.LoadModels(writeModels(t, testYAML))
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, "claude-sonnet-4-6", m.Verifier())
|
||||
}
|
||||
|
||||
m, err := config.LoadModels(f)
|
||||
func TestModelsLlamaSwapURL(t *testing.T) {
|
||||
m, err := config.LoadModels(writeModels(t, testYAML))
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, "http://koala:8080", m.LlamaSwapURL())
|
||||
}
|
||||
|
||||
func TestModelsChainForSkillOverride(t *testing.T) {
|
||||
m, err := config.LoadModels(writeModels(t, testYAML))
|
||||
require.NoError(t, err)
|
||||
|
||||
assert.Equal(t, "anthropic/claude-sonnet-4-6", m.Resolve("tdd", "anthropic/claude-sonnet-4-6"))
|
||||
chain := m.ChainFor("review", "")
|
||||
require.Len(t, chain, 3)
|
||||
assert.Equal(t, "ollama/devstral-tuned", chain[0])
|
||||
assert.Equal(t, "ollama/gemma4", chain[1])
|
||||
assert.Equal(t, "claude-sonnet-4-6", chain[2])
|
||||
}
|
||||
|
||||
func TestModelsChainForDefaultFallback(t *testing.T) {
|
||||
m, err := config.LoadModels(writeModels(t, testYAML))
|
||||
require.NoError(t, err)
|
||||
|
||||
chain := m.ChainFor("trainer", "") // not in skills map
|
||||
require.Len(t, chain, 2)
|
||||
assert.Equal(t, "ollama/qwen3-coder-30b-tuned", chain[0])
|
||||
assert.Equal(t, "claude-sonnet-4-6", chain[1])
|
||||
}
|
||||
|
||||
func TestModelsChainForCallerOverride(t *testing.T) {
|
||||
m, err := config.LoadModels(writeModels(t, testYAML))
|
||||
require.NoError(t, err)
|
||||
|
||||
chain := m.ChainFor("review", "claude-opus-4-6")
|
||||
require.Len(t, chain, 1)
|
||||
assert.Equal(t, "claude-opus-4-6", chain[0])
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user