feat(role): add versioned role configs + escalation ladder + scheduler (Phase 5)

Two parts:

Part A (fixes a gap from Phase 1): Groq/OpenRouter/OpenAI were documented in
docs/api-keys-setup.md as usable once configured, but nothing actually
constructed runners for them. internal/cli/cloudrunners.go consolidates
anthropic/google/groq/openrouter/openai NativeRunner construction into one
table-driven registerCloudRunners() helper, replacing the two hand-written
per-provider blocks in serve.go/run.go. Groq/OpenRouter/OpenAI reuse
openaicompat (no new adapter code) at SandboxKind: "docker".

Part B: the token-husbanding harness's core routing mechanism.

- internal/role: RoleConfig/Tier/Rung -- a role's system prompt and a
  multi-tier (provider, model) escalation ladder, versioned via config_json.
- storage: new role_configs table (draft/active/retired, UNIQUE(role,
  version)) with transactional activate-retires-prior-active semantics;
  new executions.escalation_rung column.
- task.AgentConfig.Role string -- purely additive; every existing task shape
  (Agent.Role == "") is unaffected, proven by TestPool_Execute_NonRoleTask_Unaffected
  plus the full pre-existing suite passing unchanged.
- executor.Pool.execute(): role-typed tasks with no Agent.Type yet resolve
  tier 0 of their active ladder (round-robin across multi-candidate tiers,
  skipping rate-limited providers, falling back to soonest-clearing) before
  the existing pickAgent/Classifier path runs; SystemPrompt applies to
  Agent.SystemPromptAppend. Already-resolved role tasks (scheduler resubmits)
  get their escalation_rung re-derived read-only via findTierIndex.
- internal/scheduler: polls role-typed FAILED tasks, retries at the same
  rung under MaxRetries or escalates to the next tier's first candidate when
  budget.Accountant.Allow() permits (emitting event.KindEscalated), else
  leaves the task FAILED with a final:true KindEscalated event. An
  in-memory per-execution-ID "handled" set keeps the poll loop convergent.
  Started by `serve` only, config knob [scheduler].poll_interval_seconds.
- internal/api: POST/GET /api/roles/{role}/versions, POST
  /api/roles/{role}/activate -- unauthenticated, matching the existing
  projects/tasks REST endpoints' auth posture (only chatbot MCP, agent MCP,
  and WebSocket are api_token-gated in this codebase today).

Documented as stored-but-not-yet-enforced (CLAUDE.md Design Debt, matching
how task.Priority/RetryConfig are already documented): RoleConfig.Tools/
SandboxKind don't affect dispatch yet; DefaultBudgetUSD is read narrowly as
the scheduler's escalation cost estimate, not enforced at initial dispatch;
scheduler escalation always targets Candidates[0] (no round-robin, unlike
initial-dispatch tier-0 resolution); the scheduler's dedupe is per-process
and resets on restart (idempotent, harmless).

go build/vet/test -race -count=1 all pass, 21 packages.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs

1 files changed, 78 insertions, 0 deletions

diff --git a/internal/cli/cloudrunners_test.go b/internal/cli/cloudrunners_test.go
new file mode 100644
index 0000000..7943347
--- /dev/null
+++ b/internal/cli/cloudrunners_test.go
@@ -0,0 +1,78 @@
+package cli
+
+import (
+	"log/slog"
+	"os"
+	"testing"
+
+	"github.com/thepeterstone/claudomator/internal/config"
+	"github.com/thepeterstone/claudomator/internal/executor"
+)
+
+// TestRegisterCloudRunners_RegistersAllFiveConfiguredProviders confirms
+// registerCloudRunners (used identically by both `serve` and `run`) wires up
+// a NativeRunner for every cloud provider that has a non-empty API key —
+// including groq/openrouter/openai, which docs/api-keys-setup.md documented
+// as "works once configured" before this phase actually configured them.
+func TestRegisterCloudRunners_RegistersAllFiveConfiguredProviders(t *testing.T) {
+	cfg := &config.Config{
+		SandboxImage: "test-image:latest",
+		Providers: map[string]config.ProviderConfig{
+			"anthropic":  {APIKey: "ak", DefaultModel: "claude-sonnet-5"},
+			"google":     {APIKey: "gk", DefaultModel: "gemini-2.5-flash"},
+			"groq":       {APIKey: "grk", Endpoint: "https://api.groq.com/openai/v1", DefaultModel: "llama-3.3-70b-versatile"},
+			"openrouter": {APIKey: "ork", Endpoint: "https://openrouter.ai/api/v1", DefaultModel: "meta-llama/llama-3.3-70b-instruct:free"},
+			"openai":     {APIKey: "oak", Endpoint: "https://api.openai.com/v1", DefaultModel: "gpt-4o-mini"},
+		},
+	}
+	runners := map[string]executor.Runner{}
+	logger := slog.New(slog.NewTextHandler(os.Stderr, &slog.HandlerOptions{Level: slog.LevelError}))
+	registerCloudRunners(runners, cfg, logger, t.TempDir())
+
+	for _, name := range []string{"anthropic", "google", "groq", "openrouter", "openai"} {
+		r, ok := runners[name]
+		if !ok {
+			t.Errorf("expected a %q runner to be registered", name)
+			continue
+		}
+		nr, ok := r.(*executor.NativeRunner)
+		if !ok {
+			t.Errorf("%q runner should be a *executor.NativeRunner", name)
+			continue
+		}
+		if nr.Provider == nil {
+			t.Errorf("%q runner has a nil Provider", name)
+		}
+		if nr.SandboxKind != "docker" {
+			t.Errorf("%q runner should use SandboxKind \"docker\", got %q", name, nr.SandboxKind)
+		}
+	}
+}
+
+// TestRegisterCloudRunners_SkipsProvidersWithoutAPIKeyOrDisabled confirms
+// providers are skipped when unconfigured (no api_key) or explicitly
+// disabled via [runners], matching the anthropic/google-only behavior this
+// generalizes.
+func TestRegisterCloudRunners_SkipsProvidersWithoutAPIKeyOrDisabled(t *testing.T) {
+	f := false
+	cfg := &config.Config{
+		Providers: map[string]config.ProviderConfig{
+			"groq":       {APIKey: "", DefaultModel: "x"}, // no key
+			"openrouter": {APIKey: "ork", DefaultModel: "x"},
+		},
+		Runners: config.RunnersConfig{OpenRouter: &f}, // explicitly disabled
+	}
+	runners := map[string]executor.Runner{}
+	logger := slog.New(slog.NewTextHandler(os.Stderr, &slog.HandlerOptions{Level: slog.LevelError}))
+	registerCloudRunners(runners, cfg, logger, t.TempDir())
+
+	if _, ok := runners["groq"]; ok {
+		t.Error("groq should not be registered without an api_key")
+	}
+	if _, ok := runners["openrouter"]; ok {
+		t.Error("openrouter should not be registered when explicitly disabled")
+	}
+	if _, ok := runners["openai"]; ok {
+		t.Error("openai should not be registered when absent from cfg.Providers")
+	}
+}