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, 73 insertions, 0 deletions

diff --git a/internal/role/role_test.go b/internal/role/role_test.go
new file mode 100644
index 0000000..6d2294e
--- /dev/null
+++ b/internal/role/role_test.go
@@ -0,0 +1,73 @@
+package role
+
+import (
+	"encoding/json"
+	"reflect"
+	"testing"
+)
+
+func TestRoleConfig_JSONRoundTrip(t *testing.T) {
+	rc := RoleConfig{
+		Role:             "coder",
+		SystemPrompt:     "You are a careful coding agent.",
+		Tools:            []string{"Bash", "Read", "Edit"},
+		SandboxKind:      "docker",
+		DefaultBudgetUSD: 1.5,
+		EscalationLadder: []Tier{
+			{
+				Candidates: []Rung{
+					{Provider: "local", Model: "llama3.1:8b"},
+				},
+				SelectionMode: "single",
+				MaxRetries:    2,
+			},
+			{
+				Candidates: []Rung{
+					{Provider: "groq", Model: "llama-3.3-70b-versatile"},
+					{Provider: "openrouter", Model: "meta-llama/llama-3.3-70b-instruct:free"},
+				},
+				SelectionMode: "round_robin",
+				MaxRetries:    1,
+			},
+			{
+				Candidates: []Rung{
+					{Provider: "anthropic", Model: "claude-sonnet-5"},
+				},
+				MaxRetries: 0,
+			},
+		},
+	}
+
+	b, err := json.Marshal(rc)
+	if err != nil {
+		t.Fatalf("Marshal: %v", err)
+	}
+
+	var got RoleConfig
+	if err := json.Unmarshal(b, &got); err != nil {
+		t.Fatalf("Unmarshal: %v", err)
+	}
+
+	if !reflect.DeepEqual(rc, got) {
+		t.Errorf("round trip mismatch:\n  want: %+v\n  got:  %+v", rc, got)
+	}
+}
+
+func TestTier_EffectiveSelectionMode(t *testing.T) {
+	cases := []struct {
+		name string
+		tier Tier
+		want string
+	}{
+		{"empty defaults to round_robin", Tier{}, "round_robin"},
+		{"explicit single", Tier{SelectionMode: "single"}, "single"},
+		{"explicit round_robin", Tier{SelectionMode: "round_robin"}, "round_robin"},
+	}
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			if got := c.tier.EffectiveSelectionMode(); got != c.want {
+				t.Errorf("got %q, want %q", got, c.want)
+			}
+		})
+	}
+}