refactor: replace orchestrator/verifier chain with direct LiteLLM calls

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>

cmd/supervisor/main.go

@@ -37,12 +37,6 @@ func main() {
 		os.Exit(1)
 	}
 
-	systemPrompt, err := os.ReadFile(cfg.ConfigDir + "/CLAUDE.md")
-	if err != nil {
-		logger.Error("read supervisor CLAUDE.md", "path", cfg.ConfigDir+"/CLAUDE.md", "err", err)
-		os.Exit(1)
-	}
-
 	protocolsPrompt, err := os.ReadFile(cfg.ConfigDir + "/protocols.md")
 	if err != nil {
 		logger.Error("read protocols.md", "path", cfg.ConfigDir+"/protocols.md", "err", err)
@@ -95,40 +89,7 @@ func main() {
 		os.Exit(1)
 	}
 
-	claudeExec := iexec.New(iexec.Config{
-		SystemPrompt:   string(systemPrompt),
-		LiteLLMBaseURL: cfg.LiteLLMBaseURL,
-		LiteLLMAPIKey:  cfg.LiteLLMAPIKey,
-	})
-	litellmExec := iexec.NewLiteLLM(cfg.LiteLLMBaseURL, cfg.LiteLLMAPIKey, 0)
-	verifier := iexec.NewVerifier("", models.Verifier(), 0)
-
-	buildOrch := func(skill string) func(ctx context.Context, req iexec.Request) (iexec.Result, error) {
-		return func(ctx context.Context, req iexec.Request) (iexec.Result, error) {
-			rawChain := models.ChainFor(skill, req.Model)
-			chain := make([]iexec.ChainEntry, len(rawChain))
-			for i, m := range rawChain {
-				chain[i] = iexec.EntryFor(m)
-			}
-			attempts := make([]iexec.AttemptRecord, 0, len(chain))
-			orch := iexec.NewOrchestrator(chain, litellmExec.Run, claudeExec.Run, verifier, models.LlamaSwapURL(), &attempts)
-			result, err := orch.Run(ctx, req)
-			result.Attempts = attempts // attach orchestration metadata before returning
-			// Log per-attempt verdicts so pass rates are visible in pod logs.
-			for i, a := range attempts {
-				logger.Info("chain attempt",
-					"skill", skill,
-					"attempt", i+1,
-					"model", a.Model,
-					"tier", a.Tier,
-					"verdict", a.Verdict,
-					"duration_ms", a.DurationMs,
-					"warm", a.WarmStart,
-				)
-			}
-			return result, err
-		}
-	}
+	litellm := iexec.NewLiteLLM(cfg.LiteLLMBaseURL, cfg.LiteLLMAPIKey, 0)
 
 	tierFn := func(ctx context.Context) tier.Info {
 		return tier.Detect(ctx, "https://api.anthropic.com", cfg.LiteLLMBaseURL)
@@ -136,10 +97,9 @@ func main() {
 
 	reg := registry.New()
 	reg.Register(tdd.New(tdd.Config{
-		SystemPrompt:  string(systemPrompt),
 		SkillPrompt:   prependProtocols(tddPrompt),
-		DefaultModel:  models.ChainFor("tdd", "")[0],
-		ExecutorFn:    buildOrch("tdd"),
+		DefaultModel:  models.ModelFor("tdd", ""),
+		CompleteFunc:  litellm.Complete,
 		SessionsDir:   cfg.SessionsDir,
 		IngestBaseURL: cfg.IngestBaseURL,
 	}))
@@ -154,36 +114,36 @@ func main() {
 	}))
 	reg.Register(retrospective.New(retrospective.Config{
 		SkillPrompt:  prependProtocols(retroPrompt),
-		DefaultModel: models.ChainFor("retrospective", "")[0],
+		DefaultModel: models.ModelFor("retrospective", ""),
 		SessionsDir:  cfg.SessionsDir,
-		ExecutorFn:   buildOrch("retrospective"),
+		CompleteFunc: litellm.Complete,
 	}))
 	reg.Register(review.New(review.Config{
 		SkillPrompt:   prependProtocols(reviewPrompt),
-		DefaultModel:  models.ChainFor("review", "")[0],
-		ExecutorFn:    buildOrch("review"),
+		DefaultModel:  models.ModelFor("review", ""),
+		CompleteFunc:  litellm.Complete,
 		SessionsDir:   cfg.SessionsDir,
 		IngestBaseURL: cfg.IngestBaseURL,
 	}))
 	reg.Register(skilldebug.New(skilldebug.Config{
 		SkillPrompt:   prependProtocols(debugPrompt),
-		DefaultModel:  models.ChainFor("debug", "")[0],
-		ExecutorFn:    buildOrch("debug"),
+		DefaultModel:  models.ModelFor("debug", ""),
+		CompleteFunc:  litellm.Complete,
 		SessionsDir:   cfg.SessionsDir,
 		IngestBaseURL: cfg.IngestBaseURL,
 	}))
 	reg.Register(spec.New(spec.Config{
 		SkillPrompt:   prependProtocols(specPrompt),
-		DefaultModel:  models.ChainFor("spec", "")[0],
-		ExecutorFn:    buildOrch("spec"),
+		DefaultModel:  models.ModelFor("spec", ""),
+		CompleteFunc:  litellm.Complete,
 		SessionsDir:   cfg.SessionsDir,
 		IngestBaseURL: cfg.IngestBaseURL,
 	}))
 	reg.Register(trainer.New(trainer.Config{
 		ReaderPrompt: prependProtocols(trainerReaderPrompt),
 		WriterPrompt: prependProtocols(trainerWriterPrompt),
-		DefaultModel: models.ChainFor("trainer", "")[0],
-		ExecutorFn:   buildOrch("trainer"),
+		DefaultModel: models.ModelFor("trainer", ""),
+		CompleteFunc: litellm.Complete,
 		SessionsDir:  cfg.SessionsDir,
 		BrainDir:     cfg.BrainDir,
 	}))
@@ -193,7 +153,7 @@ func main() {
 	mux.Handle("/mcp", srv)
 
 	addr := ":" + cfg.Port
-	logger.Info("supervisor starting", "addr", addr, "version", "v0.4.0")
+	logger.Info("supervisor starting", "addr", addr, "version", "v0.5.0")
 	if err := http.ListenAndServe(addr, mux); err != nil {
 		logger.Error("server stopped", "err", err)
 		os.Exit(1)