first extension execution path

src/guide_board/execution.py

@@ -9,6 +9,7 @@ from typing import Any
 
 from guide_board.io import write_json
 from guide_board.planning import build_run_plan
+from guide_board.runners import run_step
 from guide_board.schema import assert_valid
 
 
@@ -23,7 +24,10 @@ def run_assessment(
     run_dir = output_dir or root / "runs" / run_id
     created_at = _now()
 
-    evidence = [_evidence_for_step(run_id, plan, step) for step in plan["ordered_steps"]]
+    evidence = [
+        _evidence_for_step(root, run_dir, run_id, plan, step)
+        for step in plan["ordered_steps"]
+    ]
     for item in evidence:
         assert_valid(item, "evidence-item")
 
@@ -53,19 +57,16 @@ def run_assessment(
     }
 
 
-def _evidence_for_step(run_id: str, plan: dict[str, Any], step: dict[str, Any]) -> dict[str, Any]:
+def _evidence_for_step(
+    root: Path,
+    run_dir: Path,
+    run_id: str,
+    plan: dict[str, Any],
+    step: dict[str, Any],
+) -> dict[str, Any]:
     now = _now()
     runner_ref = step.get("runner_ref")
-    if runner_ref is None:
-        result = "manual" if step["kind"] == "check_group" else "skipped"
-        observations = [
-            "No runner is configured for this step in the baseline core."
-        ]
-    else:
-        result = "blocked"
-        observations = [
-            f"Runner {runner_ref!r} is declared but not implemented by the baseline core."
-        ]
+    runner_result = run_step(root, run_dir, run_id, plan, step)
 
     return {
         "id": f"evidence:{step['id']}",
@@ -73,14 +74,15 @@ def _evidence_for_step(run_id: str, plan: dict[str, Any], step: dict[str, Any])
         "extension_id": step["extension_id"],
         "check_id": step["id"],
         "subject_ref": plan["target_profile_snapshot"]["id"],
-        "result": result,
-        "observations": observations,
+        "result": runner_result["result"],
+        "observations": runner_result["observations"],
         "facts": {
             "step_kind": step["kind"],
             "runner_ref": runner_ref,
+            **runner_result["facts"],
         },
         "requirement_refs": _requirement_refs(plan, step),
-        "artifact_refs": [],
+        "artifact_refs": runner_result["artifact_refs"],
         "started_at": now,
         "completed_at": now,
     }
@@ -95,25 +97,38 @@ def _requirement_refs(plan: dict[str, Any], step: dict[str, Any]) -> list[str]:
 def _findings_for_evidence(run_id: str, evidence: list[dict[str, Any]]) -> list[dict[str, Any]]:
     findings: list[dict[str, Any]] = []
     for item in evidence:
-        if item["result"] != "blocked":
+        if item["result"] not in {"blocked", "fail", "infrastructure_error"}:
             continue
+        classification = {
+            "blocked": "runner_not_implemented",
+            "fail": "check_failed",
+            "infrastructure_error": "infrastructure_error",
+        }[item["result"]]
         findings.append(
             {
                 "id": f"finding:{item['check_id']}",
                 "run_id": run_id,
-                "status": "blocked",
-                "severity": "info",
-                "classification": "runner_not_implemented",
+                "status": item["result"],
+                "severity": "info" if item["result"] == "blocked" else "medium",
+                "classification": classification,
                 "requirement_refs": item["requirement_refs"],
                 "evidence_refs": [item["id"]],
-                "expected": True,
+                "expected": item["result"] == "blocked",
                 "waiver_ref": None,
-                "remediation": "Implement or configure the declared extension runner.",
+                "remediation": _remediation_for_result(item["result"]),
             }
         )
     return findings
 
 
+def _remediation_for_result(result: str) -> str:
+    if result == "blocked":
+        return "Implement or configure the declared extension runner."
+    if result == "infrastructure_error":
+        return "Fix the target, network, credentials, or harness runtime and rerun the assessment."
+    return "Review the failed check and target implementation."
+
+
 def _assessment_package(
     run_id: str,
     plan: dict[str, Any],
@@ -198,6 +213,8 @@ def _markdown_report(run_metadata: dict[str, Any], package: dict[str, Any]) -> s
 def _run_status(evidence: list[dict[str, Any]]) -> str:
     if any(item["result"] == "fail" for item in evidence):
         return "failed"
+    if any(item["result"] == "infrastructure_error" for item in evidence):
+        return "infrastructure_error"
     if any(item["result"] == "blocked" for item in evidence):
         return "blocked"
     return "completed"