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

@@ -8,7 +8,6 @@ import (
"time"
"github.com/mathiasbq/supervisor/internal/brain"
iexec "github.com/mathiasbq/supervisor/internal/exec"
"github.com/mathiasbq/supervisor/internal/session"
)
@@ -52,38 +51,32 @@ func (s *Skill) Handle(ctx context.Context, tool string, args json.RawMessage) (
task = brainCtx + "\n---\n\n" + task
}
if s.cfg.ExecutorFn == nil {
if s.cfg.CompleteFunc == nil {
return nil, fmt.Errorf("no executor configured")
}
t0 := time.Now()
result, err := s.cfg.ExecutorFn(ctx, iexec.Request{
SkillPrompt: s.cfg.SkillPrompt,
TaskPrompt: task,
Model: model,
Tools: "Read,Bash",
})
text, dur, err := s.cfg.CompleteFunc(ctx, model, s.cfg.SkillPrompt, task)
if err != nil {
return nil, err
}
if a.SessionID != "" && s.cfg.SessionsDir != "" {
msg := text
if len(msg) > 200 {
msg = msg[:200]
}
_ = session.Append(s.cfg.SessionsDir, a.SessionID, session.Entry{
SessionID: a.SessionID,
Timestamp: time.Now(),
Skill: "debug",
Phase: "debug",
ProjectRoot: a.ProjectRoot,
Attempts: session.AttemptsFrom(result.Attempts),
FinalStatus: result.Status,
ModelUsed: result.ModelUsed,
FinalStatus: "ok",
ModelUsed: model,
DurationMs: time.Since(t0).Milliseconds(),
Message: result.Message,
Message: msg,
})
}
b, err := json.Marshal(result)
if err != nil {
return nil, fmt.Errorf("marshal result: %w", err)
}
return b, nil
return json.Marshal(map[string]any{"text": text, "model": model, "duration_ms": dur})
}

View File

@@ -6,7 +6,6 @@ import (
"encoding/json"
"testing"
iexec "github.com/mathiasbq/supervisor/internal/exec"
"github.com/mathiasbq/supervisor/internal/skills/debug"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
@@ -33,29 +32,22 @@ func TestDebugRequiresError(t *testing.T) {
assert.ErrorContains(t, err, "error")
}
func TestDebugCallsExecutor(t *testing.T) {
called := false
func TestDebugCallsCompleteFunc(t *testing.T) {
var capturedTask string
fakeFn := func(_ context.Context, req iexec.Request) (iexec.Result, error) {
called = true
capturedTask = req.TaskPrompt
return iexec.Result{
Status: "pass", Phase: "debug", Skill: "debug",
RunnerOutput: "HYPOTHESIS 1 (likelihood: high): nil map access\nVERIFY: go test ./... → expected: panic line reference",
Verified: false, ModelUsed: "self", Message: "3 hypotheses for: panic nil pointer at foo.go:42",
}, nil
fakeFn := func(_ context.Context, _, _, user string) (string, int64, error) {
capturedTask = user
return "HYPOTHESIS 1 (high): nil map access. Verify: go test ./...", 90, nil
}
sk := debug.New(debug.Config{SkillPrompt: "debug rules", ExecutorFn: fakeFn, SessionsDir: t.TempDir()})
sk := debug.New(debug.Config{SkillPrompt: "debug rules", CompleteFunc: fakeFn, SessionsDir: t.TempDir()})
out, err := sk.Handle(context.Background(), "debug", json.RawMessage(
`{"project_root":"/tmp/proj","error":"panic: nil pointer dereference at foo.go:42","context":"occurs on startup"}`,
))
require.NoError(t, err)
assert.True(t, called)
assert.Contains(t, capturedTask, "panic: nil pointer dereference")
assert.Contains(t, capturedTask, "occurs on startup")
var result iexec.Result
var result map[string]any
require.NoError(t, json.Unmarshal(out, &result))
assert.Equal(t, "debug", result.Phase)
assert.Contains(t, result["text"], "nil map access")
}

View File

@@ -5,20 +5,19 @@ import (
"context"
"encoding/json"
iexec "github.com/mathiasbq/supervisor/internal/exec"
"github.com/mathiasbq/supervisor/internal/registry"
)
// ExecutorFn is the function signature for running a worker subprocess.
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)
// Config holds dependencies for the debug skill.
type Config struct {
SkillPrompt string
DefaultModel string
ExecutorFn ExecutorFn
CompleteFunc CompleteFunc
SessionsDir string
IngestBaseURL string // optional: base URL of ingestion server for brain context
IngestBaseURL string
}
// Skill implements the debug MCP tool.
@@ -40,7 +39,7 @@ func (s *Skill) Tools() []registry.ToolDef {
return []registry.ToolDef{
{
Name: "debug",
Description: "Analyse an error and return 3-5 hypotheses ordered by likelihood, each with a concrete verification step.",
Description: "Consult a local model to analyse an error and return hypotheses ordered by likelihood, each with a concrete verification step.",
InputSchema: schema(
[]string{"project_root", "error"},
map[string]any{