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

@@ -4,17 +4,15 @@ import (
"context"
"encoding/json"
iexec "github.com/mathiasbq/supervisor/internal/exec"
"github.com/mathiasbq/supervisor/internal/registry"
)
// ExecutorFn allows injecting a test double for the executor.
type ExecutorFn func(ctx context.Context, req iexec.Request) (iexec.Result, error)
// CompleteFunc is the function used to call a local model.
type CompleteFunc func(ctx context.Context, model, system, user string) (string, int64, error)
type Config struct {
SystemPrompt string
SkillPrompt string
ExecutorFn ExecutorFn // nil = no executor (tests that don't reach execute())
CompleteFunc CompleteFunc // nil = no executor (tests that don't reach execute())
DefaultModel string
SessionsDir string // optional: path to brain/sessions/ for history injection
IngestBaseURL string // optional: base URL of ingestion server for brain context
@@ -44,7 +42,7 @@ func (s *Skill) Tools() []registry.ToolDef {
return []registry.ToolDef{
{
Name: "tdd_red",
Description: "Write a failing test for the described behavior. Verifies the test fails before returning.",
Description: "Consult a local model for help writing a failing test for the described behavior.",
InputSchema: schema(
[]string{"project_root", "spec"},
map[string]any{
@@ -57,7 +55,7 @@ func (s *Skill) Tools() []registry.ToolDef {
},
{
Name: "tdd_green",
Description: "Write minimal implementation to make the test at test_path pass.",
Description: "Consult a local model for implementation ideas to make the test at test_path pass.",
InputSchema: schema(
[]string{"project_root", "test_path"},
map[string]any{
@@ -71,7 +69,7 @@ func (s *Skill) Tools() []registry.ToolDef {
},
{
Name: "tdd_refactor",
Description: "Refactor the implementation at impl_path while keeping tests green.",
Description: "Consult a local model for refactoring suggestions for impl_path while keeping tests green.",
InputSchema: schema(
[]string{"project_root", "test_path", "impl_path"},
map[string]any{