fix(testing): align plan example and show run progress

Author: kvinwang

docs/testing/test-case-authoring-spec.md

@@ -70,23 +70,33 @@ The index is authoritative for discovery and order. A minimal example is:
   "schema_version": "1.0",
   "id": "dstack-v0-6-0-release",
   "title": "dstack v0.6.0 Release Test Plan",
-  "guide": "README.md",
+  "guide": {"path": "README.md", "anchor": "release-test-guide"},
   "chapters": [
     {
       "id": "chapter-gateway",
       "title": "Gateway",
       "order": 1,
+      "path": "01-gateway",
       "sections": [
         {
           "id": "section-gateway-proxy-protocol",
           "title": "Proxy Protocol",
           "order": 1,
+          "path": "01-gateway/01-proxy-protocol",
           "cases": [
             {
               "id": "tc-gw-pp-001",
               "title": "Forward a Proxy v1 client address over TLS termination",
               "order": 1,
-              "path": "01-gateway/01-proxy-protocol/tc-gw-pp-001"
+              "priority": "P0",
+              "path": "01-gateway/01-proxy-protocol/tc-gw-pp-001",
+              "spec": {
+                "path": "01-gateway/01-proxy-protocol/tc-gw-pp-001/case.md",
+                "anchor": "tc-gw-pp-001"
+              },
+              "requirements": ["req-gw-pp-001"],
+              "risks": ["risk-gw-spoofing-001"],
+              "tags": ["gateway", "proxy-protocol"]
             }
           ]
         }

tools/dstack-test/dstack-test

@@ -591,23 +591,34 @@ def main(argv: list[str] | None = None) -> int:
         )
     elif args.subcommand == "run-plan":
         values = []
-        for case in plan.cases:
+        total = len(plan.cases)
+        for index, case in enumerate(plan.cases, 1):
+            print(f"[{index}/{total}] starting {case.id}", file=sys.stderr, flush=True)
             try:
-                values.append(
-                    run_case(
-                        plan,
-                        case,
-                        args.run_id,
-                        args.agent,
-                        args.model,
-                        args.workdir.resolve(),
-                        prompt_text(args),
-                        args.agent_arg,
-                        args.overwrite,
-                    )
+                case_value = run_case(
+                    plan,
+                    case,
+                    args.run_id,
+                    args.agent,
+                    args.model,
+                    args.workdir.resolve(),
+                    prompt_text(args),
+                    args.agent_arg,
+                    args.overwrite,
+                )
+                values.append(case_value)
+                print(
+                    f"[{index}/{total}] finished {case.id}: {case_value['status']}",
+                    file=sys.stderr,
+                    flush=True,
                 )
             except DstackTestError as error:
                 values.append({"case": case.id, "runner_error": str(error)})
+                print(
+                    f"[{index}/{total}] runner error for {case.id}: {error}",
+                    file=sys.stderr,
+                    flush=True,
+                )
         run = finalize_run(plan, args.run_id, context_value(args.context))
         value = {"cases": values, "run": run}
     elif args.subcommand == "finalize":