refactor: replace orchestrator/verifier chain with direct LiteLLM calls
All checks were successful
cd / Build and deploy (push) Successful in 6s
CI / Lint / Test / Vet (push) Successful in 10s
CI / Mirror to GitHub (push) Successful in 3s

Drop the three-layer Claude subprocess orchestration (local model →
Claude verifier → cloud escalation). Skills now call LiteLLM directly
and return plain text to Claude Code, which decides what to do with it.

- Delete executor, orchestrator, verifier, result, attempts packages
- Simplify LiteLLMExecutor: Run(Request)→Result becomes Complete(model,sys,user)→(string,int64,error)
- Replace ExecutorFn with CompleteFunc in all 6 skill configs
- Rewrite all skill handlers to call Complete and return {"text","model","duration_ms"}
- Simplify config/models: remove Verifier/LlamaSwapURL, add ModelFor
- Bump version to v0.5.0

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Mathias Bergqvist
2026-04-22 16:19:09 +02:00
parent 823de23213
commit ce45592730
34 changed files with 266 additions and 1432 deletions

View File

@@ -5,7 +5,6 @@ import (
"encoding/json"
"testing"
iexec "github.com/mathiasbq/supervisor/internal/exec"
"github.com/mathiasbq/supervisor/internal/session"
"github.com/mathiasbq/supervisor/internal/skills/tdd"
"github.com/stretchr/testify/assert"
@@ -14,8 +13,7 @@ import (
func TestTDDSkillTools(t *testing.T) {
skill := tdd.New(tdd.Config{
SystemPrompt: "supervisor rules",
SkillPrompt: "tdd rules",
SkillPrompt: "tdd rules",
})
tools := skill.Tools()
names := make([]string, len(tools))
@@ -26,19 +24,19 @@ func TestTDDSkillTools(t *testing.T) {
}
func TestTDDSkillHandleUnknown(t *testing.T) {
skill := tdd.New(tdd.Config{SystemPrompt: "s", SkillPrompt: "t"})
skill := tdd.New(tdd.Config{SkillPrompt: "t"})
_, err := skill.Handle(context.Background(), "tdd_unknown", json.RawMessage(`{}`))
assert.ErrorContains(t, err, "unknown tool")
}
func TestTDDRedRequiresProjectRoot(t *testing.T) {
skill := tdd.New(tdd.Config{SystemPrompt: "s", SkillPrompt: "t"})
skill := tdd.New(tdd.Config{SkillPrompt: "t"})
_, err := skill.Handle(context.Background(), "tdd_red", json.RawMessage(`{"spec":"add two numbers"}`))
assert.ErrorContains(t, err, "project_root")
}
func TestTDDRedRequiresSpec(t *testing.T) {
skill := tdd.New(tdd.Config{SystemPrompt: "s", SkillPrompt: "t"})
skill := tdd.New(tdd.Config{SkillPrompt: "t"})
_, err := skill.Handle(context.Background(), "tdd_red", json.RawMessage(`{"project_root":"/tmp/proj"}`))
assert.ErrorContains(t, err, "spec")
}
@@ -51,35 +49,49 @@ func TestTDDGreenInjectsSessionHistory(t *testing.T) {
Message: "wrote failing test for Foo",
}))
var capturedPrompt string
fakeFn := func(_ context.Context, req iexec.Request) (iexec.Result, error) {
capturedPrompt = req.TaskPrompt
return iexec.Result{Status: "pass", Phase: "green", Skill: "tdd", Verified: true, ModelUsed: "self", Message: "ok"}, nil
var capturedTask string
fakeFn := func(_ context.Context, _, _, user string) (string, int64, error) {
capturedTask = user
return "here is my suggestion", 100, nil
}
sk := tdd.New(tdd.Config{SkillPrompt: "tdd", ExecutorFn: fakeFn, SessionsDir: sessDir})
sk := tdd.New(tdd.Config{SkillPrompt: "tdd", CompleteFunc: fakeFn, SessionsDir: sessDir})
_, err := sk.Handle(context.Background(), "tdd_green", json.RawMessage(
`{"project_root":"/tmp","test_path":"internal/foo/foo_test.go","test_cmd":"go test ./...","session_id":"sess-1"}`,
))
require.NoError(t, err)
assert.Contains(t, capturedPrompt, "## Session history")
assert.Contains(t, capturedPrompt, "wrote failing test for Foo")
assert.Contains(t, capturedTask, "## Session history")
assert.Contains(t, capturedTask, "wrote failing test for Foo")
}
func TestTDDGreenNoHistoryWhenSessionIDEmpty(t *testing.T) {
var capturedPrompt string
fakeFn := func(_ context.Context, req iexec.Request) (iexec.Result, error) {
capturedPrompt = req.TaskPrompt
return iexec.Result{Status: "pass", Phase: "green", Skill: "tdd", Verified: true, ModelUsed: "self", Message: "ok"}, nil
var capturedTask string
fakeFn := func(_ context.Context, _, _, user string) (string, int64, error) {
capturedTask = user
return "suggestion", 50, nil
}
sk := tdd.New(tdd.Config{SkillPrompt: "tdd", ExecutorFn: fakeFn, SessionsDir: t.TempDir()})
sk := tdd.New(tdd.Config{SkillPrompt: "tdd", CompleteFunc: fakeFn, SessionsDir: t.TempDir()})
_, err := sk.Handle(context.Background(), "tdd_green", json.RawMessage(
`{"project_root":"/tmp","test_path":"internal/foo/foo_test.go"}`,
))
require.NoError(t, err)
assert.NotContains(t, capturedPrompt, "## Session history")
assert.NotContains(t, capturedTask, "## Session history")
}
// Ensure require is used (avoids import error).
var _ = require.New
func TestTDDGreenReturnsTextJSON(t *testing.T) {
fakeFn := func(_ context.Context, _, _, _ string) (string, int64, error) {
return "write a func that adds two ints", 42, nil
}
sk := tdd.New(tdd.Config{SkillPrompt: "tdd", CompleteFunc: fakeFn})
raw, err := sk.Handle(context.Background(), "tdd_green", json.RawMessage(
`{"project_root":"/tmp","test_path":"foo_test.go"}`,
))
require.NoError(t, err)
var result map[string]any
require.NoError(t, json.Unmarshal(raw, &result))
assert.Equal(t, "write a func that adds two ints", result["text"])
assert.Equal(t, float64(42), result["duration_ms"])
}