feat(ai-sdk): runnable iace-audit propose CLI + live LLM wiring (P2 slice 3)

Makes the offline proposer runnable end-to-end.

- BuildProposerInput (proposer_input.go): non-test engine->hazards path. The
  PatternMatch->Hazard converter is lifted out of the GT test files into
  production scope so both the tests and the CLI share one pipeline.
- iace-audit propose <narrative.json> [<ground-truth.json>]: detect candidates ->
  GT-screen survivors (when a ground truth is given) -> judge (HeuristicJudge by
  default, LLMJudge over ollama when IACE_PROPOSE_LLM=1) -> write the human-review
  queue to audit-reports/proposals.{md,json}. Propose-only.

Smoke run on a dishwasher narrative: 32 fired -> 3 candidates -> queue with a
confident duplicate, a confident distinct, and one punted to the LLM judge; GT
wall recall-safe. Live qwen is opt-in via env; the heuristic default keeps the
tool runnable (and CI deterministic) without a model. Proposal types 2-4
(foreign-framing gates, vocab->tag, coverage blind spots) remain for slice 4.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

ai-compliance-sdk/cmd/iace-audit/main.go

@@ -34,6 +34,8 @@ func main() {
 		cmdEcho(os.Args[2:])
 	case "hierarchy":
 		cmdHierarchy(os.Args[2:])
+	case "propose":
+		cmdPropose(os.Args[2:])
 	default:
 		usage()
 		os.Exit(2)
@@ -41,7 +43,7 @@ func main() {
 }
 
 func usage() {
-	fmt.Fprintln(os.Stderr, "Usage: iace-audit <reachability|consistency|vocabulary|echo|hierarchy> [args]")
+	fmt.Fprintln(os.Stderr, "Usage: iace-audit <reachability|consistency|vocabulary|echo|hierarchy|propose> [args]")
 }
 
 func cmdReachability(_ []string) {