prizmkit 1.1.139 → 1.1.141

package/bundled/dev-pipeline/tests/test_generate_bugfix_prompt.py

@@ -500,66 +500,43 @@ class TestBugfixCheckpointGeneration:
         test_step = checkpoint["steps"][4]
         assert test_step["depends_on"] == "S04"
         assert test_step["required_artifacts"] == [
-            ".prizmkit/test/evidence/*/manifest.json",
-            ".prizmkit/test/evidence/*/verdict.json",
-            ".prizmkit/test/evidence/*/validation.json",
+            ".prizmkit/bugfix/B-001/test-report.md",
+            ".prizmkit/bugfix/B-001/test-result.json",
         ]
         assert checkpoint["steps"][5]["depends_on"] == "S05"
 
-    def test_bugfix_repair_routing_preserves_review_and_test_boundaries(self):
+    def test_bugfix_result_routing_stops_test_non_pass(self):
         review = route_bugfix_repair("REVIEW_NEEDS_FIXES", repair_round=0)
-        test_infra = route_bugfix_repair(
-            "TEST_FAIL", "test-infrastructure", repair_round=1,
-        )
-        production = route_bugfix_repair("TEST_FAIL", "public-interface", repair_round=2)
+        needs_fixes = route_bugfix_repair("TEST_NEEDS_FIXES", repair_round=1)
+        blocked = route_bugfix_repair("TEST_BLOCKED", repair_round=1)
 
         assert review["route"] == [
             "prizmkit-implement", "prizmkit-code-review", "prizmkit-test",
         ]
-        assert test_infra["route"] == ["prizmkit-implement", "prizmkit-test"]
-        assert production["route"] == [
-            "prizmkit-implement", "prizmkit-code-review", "prizmkit-test",
-        ]
-        assert production["repair_round"] == 3
-
-    def test_bugfix_repair_routing_blocks_unsafe_blocked_and_exhausted_results(self):
-        unknown = route_bugfix_repair("TEST_FAIL", "unknown", repair_round=1)
-        blocked = route_bugfix_repair("TEST_BLOCKED", "production", repair_round=1)
-        exhausted = route_bugfix_repair("TEST_FAIL", "production", repair_round=3)
-
-        assert unknown["blocked"] is True
-        assert unknown["route"] == []
+        assert review["repair_round"] == 1
+        assert needs_fixes["blocked"] is True
+        assert needs_fixes["route"] == []
+        assert needs_fixes["blocked_reason"] == "test_needs_fixes"
         assert blocked["blocked"] is True
         assert blocked["resumable"] is False
         assert blocked["next_stage"] is None
         assert blocked["terminal_status"] == "WORKFLOW_BLOCKED"
         assert blocked["blocked_reason"] == "test_blocked"
-        assert blocked["route"] == []
-        assert "cannot safely edit production" in blocked["reason"]
-        assert exhausted["blocked"] is True
-        assert exhausted["repair_round"] == 3
 
-    def test_bugfix_checkpoint_metadata_preserves_artifact_and_evidence_handoff(self):
+    def test_bugfix_checkpoint_metadata_has_no_evidence_handoff(self):
         metadata = bugfix_checkpoint_metadata(
             ".prizmkit/bugfix/B-001",
-            evidence={
-                "manifest_path": ".prizmkit/test/evidence/id/manifest.json",
-                "verdict_path": ".prizmkit/test/evidence/id/verdict.json",
-                "validation_path": ".prizmkit/test/evidence/id/validation.json",
-            },
             stage="test",
-            status="TEST_FAIL",
-            stage_result="TEST_FAIL",
-            repair_scope="test-infrastructure",
-            repair_round=2,
+            status="TEST_NEEDS_FIXES",
+            stage_result="TEST_NEEDS_FIXES",
+            repair_round=0,
+            next_stage=None,
+            resume_from=None,
         )
 
         assert metadata["artifact_dir"] == ".prizmkit/bugfix/B-001"
-        assert metadata["authoritative_evidence_paths"]["validation"].endswith(
-            "/validation.json"
-        )
-        assert metadata["repair_round"] == 2
-        assert metadata["resume_from"] == "prizmkit-implement"
+        assert metadata["stage_result"] == "TEST_NEEDS_FIXES"
+        assert "authoritative_evidence_paths" not in metadata
 
     def test_manual_bugfix_uses_automatic_verification_and_keeps_commit_gate(self):
         sections = assemble_bugfix_sections(

package/bundled/dev-pipeline/tests/test_generate_refactor_prompt.py

@@ -59,12 +59,12 @@ class TestRefactorCheckpointMerge:
         existing["refactor_state"] = refactor_checkpoint_metadata(
             ".prizmkit/refactor/R-008",
             stage="test",
-            status="TEST_FAIL",
-            stage_result="TEST_FAIL",
+            status="TEST_NEEDS_FIXES",
+            stage_result="TEST_NEEDS_FIXES",
             repair_scope="public-interface",
             repair_round=2,
-            next_stage="prizmkit-implement",
-            resume_from="prizmkit-implement",
+            next_stage=None,
+            resume_from=None,
         )
         existing["steps"][0]["status"] = "skipped"
 
@@ -215,7 +215,7 @@ def test_template_source_is_clean_for_headless_prompt_contract():
     assert "/prizmkit-test scope=this-change artifact_dir=.prizmkit/refactor/{{REFACTOR_ID}}/" in content
     assert "local_commit_authorized=true" in content
     assert "push_authorized" not in content
-    assert "Behavior-preservation checks remain supporting evidence" in content
+    assert "Behavior-preservation context remains supporting input" in content
 
 
 # ---------------------------------------------------------------------------
@@ -349,35 +349,32 @@ class TestRefactorCheckpointGeneration:
             "completion-summary",
         ]
         assert checkpoint["steps"][4]["depends_on"] == "S04"
+        assert checkpoint["steps"][4]["required_artifacts"] == [
+            ".prizmkit/refactor/R-001/test-report.md",
+            ".prizmkit/refactor/R-001/test-result.json",
+        ]
         assert checkpoint["steps"][5]["depends_on"] == "S05"
 
-    def test_refactor_repair_routing_preserves_behavior_review_and_test(self):
-        test_infra = route_refactor_repair(
-            "TEST_FAIL", "test-infrastructure", repair_round=1,
-        )
-        production = route_refactor_repair("TEST_FAIL", "public-interface", repair_round=1)
-        blocked = route_refactor_repair("TEST_BLOCKED", "production", repair_round=1)
+    def test_refactor_result_routing_stops_test_non_pass(self):
+        review = route_refactor_repair("REVIEW_NEEDS_FIXES", repair_round=0)
+        needs_fixes = route_refactor_repair("TEST_NEEDS_FIXES", repair_round=1)
+        blocked = route_refactor_repair("TEST_BLOCKED", repair_round=1)
 
-        assert test_infra["route"] == ["prizmkit-implement", "prizmkit-test"]
-        assert production["route"] == [
+        assert review["route"] == [
             "prizmkit-implement", "prizmkit-code-review", "prizmkit-test",
         ]
-        unknown = route_refactor_repair("TEST_FAIL", "contract", repair_round=1)
-        exhausted = route_refactor_repair("TEST_FAIL", "production", repair_round=3)
-        assert unknown["blocked"] is True
-        assert unknown["route"] == []
-        assert exhausted["blocked"] is True
-        assert exhausted["repair_round"] == 3
+        assert needs_fixes["blocked"] is True
+        assert needs_fixes["route"] == []
+        assert needs_fixes["blocked_reason"] == "test_needs_fixes"
         assert blocked["blocked"] is True
         assert blocked["route"] == []
         assert blocked["next_stage"] is None
         assert blocked["terminal_status"] == "WORKFLOW_BLOCKED"
         assert blocked["blocked_reason"] == "test_blocked"
 
-    def test_refactor_checkpoint_metadata_preserves_artifact_and_evidence_handoff(self):
+    def test_refactor_checkpoint_metadata_has_no_evidence_handoff(self):
         metadata = refactor_checkpoint_metadata(
             ".prizmkit/refactor/R-001",
-            evidence={"manifest_path": "manifest.json"},
             stage="test",
             status="TEST_PASS",
             stage_result="TEST_PASS",
@@ -386,7 +383,7 @@ class TestRefactorCheckpointGeneration:
         )
 
         assert metadata["artifact_dir"] == ".prizmkit/refactor/R-001"
-        assert metadata["authoritative_evidence_paths"]["manifest"] == "manifest.json"
+        assert "authoritative_evidence_paths" not in metadata
         assert metadata["next_stage"] == "prizmkit-retrospective"
         assert metadata["resume_from"] == "prizmkit-retrospective"
 
@@ -397,7 +394,7 @@ class TestRefactorCheckpointGeneration:
             "/prizmkit-test scope=this-change artifact_dir=.prizmkit/refactor/R-001/"
         ) < prompt.index("### Headless Commit Authorization")
         assert "prizmkit-workflow" not in prompt
-        assert "Behavior-preservation checks collected during planning and implementation remain supporting evidence" in prompt
+        assert "Existing behavior-preservation context is input to testing" in prompt
         assert '"local_commit_authorized": true' in prompt
         assert "push_authorized" not in prompt
         assert "Remote publication is controlled by the runtime" in prompt

package/bundled/dev-pipeline/tests/test_python_runner_parity.py

@@ -92,12 +92,6 @@ def _item_id_from_next_result(kind, result):
 
 
 def _write_semantic_completion_checkpoint(project_root, artifact_dir, workflow_type="feature-pipeline"):
-    validator = (
-        project_root / ".claude" / "command-assets" / "prizmkit-test"
-        / "scripts" / "validate_test_evidence.py"
-    )
-    validator.parent.mkdir(parents=True, exist_ok=True)
-    validator.write_text("import sys\nsys.exit(0)\n", encoding="utf-8")
     contracts = {
         "feature-pipeline": (
             "feature_state",
@@ -123,25 +117,6 @@ def _write_semantic_completion_checkpoint(project_root, artifact_dir, workflow_t
         ),
     }
     state_key, skills = contracts[workflow_type]
-    evidence_id = "semantic-evidence"
-    evidence_dir = project_root / ".prizmkit" / "test" / "evidence" / evidence_id
-    evidence_dir.mkdir(parents=True, exist_ok=True)
-    evidence = {
-        "manifest": evidence_dir / "manifest.json",
-        "verdict": evidence_dir / "verdict.json",
-        "validation": evidence_dir / "validation.json",
-    }
-    evidence["manifest"].write_text(
-        json.dumps({"evidence_id": evidence_id, "final_verdict": "TEST_PASS"}),
-        encoding="utf-8",
-    )
-    evidence["verdict"].write_text(json.dumps({"verdict": "TEST_PASS"}), encoding="utf-8")
-    evidence["validation"].write_text(
-        json.dumps({"verdict": "TEST_PASS", "result": "passed"}), encoding="utf-8"
-    )
-    relative_evidence = {
-        key: str(path.relative_to(project_root)) for key, path in evidence.items()
-    }
     steps = []
     previous = None
     for index, skill in enumerate(skills, start=1):
@@ -157,10 +132,38 @@ def _write_semantic_completion_checkpoint(project_root, artifact_dir, workflow_t
             step["stage_result"] = "REVIEW_PASS"
         if skill == "prizmkit-test":
             step["stage_result"] = "TEST_PASS"
-            step["authoritative_evidence_paths"] = relative_evidence
+            relative_artifact = artifact_dir.relative_to(project_root)
+            step["required_artifacts"] = [
+                str(relative_artifact / "test-report.md"),
+                str(relative_artifact / "test-result.json"),
+            ]
         steps.append(step)
         previous = step["id"]
     artifact_dir.mkdir(parents=True, exist_ok=True)
+    (artifact_dir / "test-report.md").write_text(
+        "# Test Report\n\n## Final Result\n\n- Result: TEST_PASS\n",
+        encoding="utf-8",
+    )
+    (artifact_dir / "test-result.json").write_text(
+        json.dumps({
+            "schema_version": 1,
+            "result": "TEST_PASS",
+            "report": "test-report.md",
+            "main_review_rounds": 1,
+            "independent_review": {
+                "status": "downgraded",
+                "responses": 0,
+                "downgrade_reason": "read-only continuation capability unavailable",
+                "final_state_rechecked": False,
+            },
+            "repair_rounds": 0,
+            "production_changed": False,
+            "review_required": False,
+            "review_scope": None,
+            "unresolved_items": [],
+        }),
+        encoding="utf-8",
+    )
     checkpoint = artifact_dir / "workflow-checkpoint.json"
     checkpoint.write_text(
         json.dumps({
@@ -169,7 +172,6 @@ def _write_semantic_completion_checkpoint(project_root, artifact_dir, workflow_t
             "steps": steps,
             state_key: {
                 "repair_round": 0,
-                "authoritative_evidence_paths": relative_evidence,
                 "terminal_status": "WORKFLOW_COMPLETED",
             },
         }),
@@ -3877,11 +3879,6 @@ def test_family_status_persists_identical_semantic_blocked_snapshot_without_retr
         "stage_result": "TEST_BLOCKED",
         "repair_scope": "production",
         "repair_round": 2,
-        "authoritative_evidence_paths": {
-            "manifest": ".prizmkit/test/evidence/id/manifest.json",
-            "verdict": ".prizmkit/test/evidence/id/verdict.json",
-            "validation": ".prizmkit/test/evidence/id/validation.json",
-        },
         "blocked_reason": "test_blocked",
         "terminal_status": "WORKFLOW_BLOCKED",
     }

package/bundled/skills/_metadata.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.1.139",
+  "version": "1.1.141",
   "skills": {
     "prizmkit": {
       "description": "Framework introduction and navigation for the formal single-requirement lifecycle, project initialization, Prizm docs, and independent deployment.",
@@ -9,7 +9,7 @@
       "hasScripts": false
     },
     "prizmkit-workflow": {
-      "description": "Composite L1 workflow for one explicitly requested formal requirement: plan → implement → code-review → test → retrospective → committer, with stable artifact identity and deterministic repair routing.",
+      "description": "Composite workflow for one explicitly requested formal requirement: plan → implement → code-review → test → retrospective → committer, with stable artifact identity and deterministic repair routing.",
       "tier": "foundation",
       "category": "prizmkit-skill",
       "hasAssets": false,
@@ -44,7 +44,7 @@
       "hasScripts": true
     },
     "prizmkit-committer": {
-      "description": "Final formal-requirement commit gate: verifies all prior stages, confirms interactive commits or performs authorized L4-headless local commits, and never pushes automatically.",
+      "description": "Final formal-requirement commit gate: verifies all prior stages, confirms interactive commits or performs authorized headless pipeline commits, and never pushes automatically.",
       "tier": "1",
       "category": "prizmkit-skill",
       "hasAssets": false,
@@ -72,11 +72,11 @@
       "hasScripts": false
     },
     "prizmkit-test": {
-      "description": "Mandatory post-review auditable test evidence with TEST_PASS/TEST_FAIL/TEST_BLOCKED verdicts, repair-scope routing, current-workspace execution evidence, replay, and deterministic validation.",
+      "description": "AI-led project-native testing for the affected business module and Regression Ring, with bounded failure repair, mandatory Main-Agent review, optional strict independent Test Reviewer, and TEST_PASS/TEST_NEEDS_FIXES/TEST_BLOCKED results.",
       "tier": "1",
       "category": "prizmkit-skill",
-      "hasAssets": true,
-      "hasScripts": true
+      "hasAssets": false,
+      "hasScripts": false
     },
     "feature-workflow": {
       "description": "Thin feature scenario router. Clarifies whether the request needs direct single-requirement guidance, app planning, feature planning, or command construction from an existing feature list.",

package/bundled/skills/prizmkit/SKILL.md

@@ -72,7 +72,7 @@ Typos, pure formatting, small documentation edits, and other explicitly low-risk
 | `prizmkit-plan` | Clarify the requirement and create/review `spec.md` and `plan.md`. | `PLAN_READY` → `prizmkit-implement` |
 | `prizmkit-implement` | Execute the plan tasks and record completion. | `IMPLEMENTED` → `prizmkit-code-review` |
 | `prizmkit-code-review` | Main Agent reviews, repairs, verifies, and loops until convergence. | `REVIEW_PASS` → `prizmkit-test` |
-| `prizmkit-test` | Validate the final reviewed workspace with project-native evidence. | `TEST_PASS` → `prizmkit-retrospective` |
+| `prizmkit-test` | Validate the final reviewed workspace with project-native tests and a consistent terminal report/result pair. | `TEST_PASS` → `prizmkit-retrospective` |
 | `prizmkit-retrospective` | Synchronize durable project documentation or record no documentation change. | `RETRO_COMPLETE` → `prizmkit-committer` |
 | `prizmkit-committer` | Verify gates, request commit confirmation, and create the local commit. | `COMMITTED` |
 
@@ -108,19 +108,14 @@ REVIEW_NEEDS_FIXES
   → prizmkit-implement
   → prizmkit-code-review
 
-TEST_FAIL affecting only tests, fixtures, or test-runner configuration
-  → prizmkit-implement
-  → prizmkit-test
-
-TEST_FAIL affecting production code, runtime configuration, schema,
-dependencies, or public interfaces
-  → prizmkit-implement
-  → prizmkit-code-review
-  → prizmkit-test
+TEST_NEEDS_FIXES
+  → preserve test-report.md and test-result.json
+  → stop with the known correction or delta-review requirement
+  → caller owns any later review/retest route
 
 TEST_BLOCKED
-  → pause without speculative code changes
-  → resume from prizmkit-test when the environment is available
+  → preserve the blocker without speculative code changes
+  → caller owns recovery after truth, input, safety, environment, or reliability is restored
 ```
 
 Automatic outer repair is limited to three rounds. The workflow stops with a resumable blocked result when the limit is reached or a gate cannot be safely completed.
@@ -141,7 +136,7 @@ An active requirement may use:
 
 This runtime state records the current stage, terminal status, repair scope, repair round, and resume entry. The skill set does not prescribe whether the target project commits, ignores, or shares this file.
 
-Read `${SKILL_DIR}/references/workflow-state-protocol.md` for the state protocol. If the state file is missing or stale, use `spec.md`, `plan.md`, review evidence, and test evidence to reconstruct the safest recoverable stage and report that reconstruction.
+Read `${SKILL_DIR}/references/workflow-state-protocol.md` for the state protocol. If the state file is missing or stale, use `spec.md`, `plan.md`, the review report, `test-report.md`, and `test-result.json` to reconstruct the safest recoverable stage and report that reconstruction.
 
 ## Quick Start
 

package/bundled/skills/prizmkit/references/workflow-state-protocol.md

@@ -1,6 +1,6 @@
 # PrizmKit Workflow State Protocol
 
-`workflow-state.json` is lifecycle runtime metadata for one formal requirement. It preserves stage handoff, repair routing, orchestrator ownership, and resume information without replacing authoritative artifacts or any host-owned execution checkpoint.
+`workflow-state.json` is lifecycle metadata for one formal requirement. It preserves stage handoff, orchestrator ownership, and resume information without replacing skill-owned artifacts or any host-owned execution checkpoint.
 
 ## Location and Identity
 
@@ -8,7 +8,7 @@
 .prizmkit/state/workflows/<requirement-slug>.json
 ```
 
-The state file is created only when a lifecycle runs. The active `artifact_dir` is the generic requirement artifact root and must be preserved exactly across every stage:
+The active `artifact_dir` is preserved exactly across every stage:
 
 ```text
 .prizmkit/specs/<requirement-slug>/
@@ -16,7 +16,7 @@ The state file is created only when a lifecycle runs. The active `artifact_dir`
 .prizmkit/refactor/<refactor-id>/
 ```
 
-Never select a different most-recent plan when resuming or handing off. Any execution checkpoint maintained by an external host remains separate from this lifecycle state. Never merge, substitute, or infer one schema from the other. The target project controls whether generated `.prizmkit/` files are committed, ignored, or shared.
+Never select another recent plan when resuming. Any external execution checkpoint remains separate from this state. Never merge, substitute, or infer one schema from the other.
 
 ## Authority
 
@@ -26,16 +26,16 @@ The state file is an index, not the authority for stage completion:
 |---|---|
 | Requirement goals and acceptance criteria | `{artifact_dir}/spec.md` |
 | Implementation tasks and completion | `{artifact_dir}/plan.md` plus current workspace |
-| Review findings and verdict | `{artifact_dir}/review-report.md` final result |
-| Test execution, verdict, and repair scope | Validated evidence package and authoritative `verdict.json` |
-| Test report presentation | `{artifact_dir}/test-report.md` as a derived view only |
-| Retrospective completion and result | `{artifact_dir}/retrospective-result.json` |
+| Review findings and result | `{artifact_dir}/review-report.md` |
+| Test semantics and native execution | `{artifact_dir}/test-report.md` |
+| Terminal testing result | `{artifact_dir}/test-result.json` |
+| Retrospective completion | `{artifact_dir}/retrospective-result.json` |
 | Durable architecture knowledge | `.prizmkit/prizm-docs/` |
 | Local commit | Git history and confirmed or authorized commit identity |
 | Current stage, orchestrator, and resume entry | Workflow state |
-| External orchestration progress | The external host's own checkpoint, never this state |
+| External orchestration progress | External host checkpoint |
 
-Every consumer compares workflow state with authoritative artifacts and the current workspace. Missing or stale state is reconstructed from those sources and is never accepted as success by itself.
+Every consumer compares workflow state with the skill-owned artifacts and current workspace. Missing or stale state is reconstructed from those sources and is never accepted as success by itself.
 
 ## Schema
 
@@ -59,88 +59,71 @@ Every consumer compares workflow state with authoritative artifacts and the curr
 
 | Field | Meaning |
 |---|---|
-| `schema_version` | State schema version. Current value is `1`. |
-| `artifact_dir` | The single generic requirement artifact root reused by every stage. |
-| `orchestrator` | `prizmkit-workflow`, another semantic coordinator identifier, or `null` for direct stage use. |
-| `stage` | The stage that most recently wrote state. |
-| `status` | Lifecycle progression status, distinct from the domain `stage_result`. |
+| `schema_version` | State schema version. |
+| `artifact_dir` | Generic requirement artifact root reused by every stage. |
+| `orchestrator` | Semantic coordinator identifier, or null for direct stage use. |
+| `stage` | Stage that most recently wrote state. |
+| `status` | Lifecycle progression status, distinct from `stage_result`. |
 | `stage_result` | Domain result such as `PASS`, `NEEDS_FIXES`, `TEST_*`, `DOCS_UPDATED`, or `NO_DOC_CHANGE`. |
 | `completed_stages` | Ordered stages completed for this requirement. |
-| `repair_scope` | `null`, `test-infrastructure`, `production`, `runtime`, `schema`, `dependency`, `public-interface`, or `unknown`. |
-| `repair_round` | Outer cross-stage repair round, from `0` through `3`. |
-| `next_stage` | Next semantic stage, or `null` after commit. |
-| `resume_from` | Exact atomic skill that can resume, or `null` after commit. |
+| `repair_scope` | Optional caller-owned routing scope. The test skill reports high-risk repairs through `test-result.json` instead of scheduling another stage. |
+| `repair_round` | Optional outer cross-stage repair round, from 0 through 3. It is not a test-internal repair counter. |
+| `next_stage` | Next semantic stage, or null when stopped. |
+| `resume_from` | Exact atomic skill that can resume, or null when none is selected. |
 
-## Lifecycle and Verdict Mappings
-
-The mandatory formal lifecycle is:
+## Lifecycle and Result Mappings
 
 ```text
 PLAN_READY
-  → IMPLEMENTED
-  → REVIEW_PASS
-  → TEST_PASS
-  → RETRO_COMPLETE
-  → COMMIT_PENDING
-  → COMMITTED
+→ IMPLEMENTED
+→ REVIEW_PASS
+→ TEST_PASS
+→ RETRO_COMPLETE
+→ COMMIT_PENDING
+→ COMMITTED
 ```
 
-No formal stage is silently optional. Domain evidence maps as follows:
+No formal stage is silently optional. Domain artifacts map as follows:
 
 ```text
-review-report final PASS        → status=REVIEW_PASS, stage_result=PASS
-review-report final NEEDS_FIXES → status=REVIEW_NEEDS_FIXES, stage_result=NEEDS_FIXES
-validated verdict TEST_PASS     → status=TEST_PASS, stage_result=TEST_PASS
-validated verdict TEST_FAIL     → status=TEST_FAIL, stage_result=TEST_FAIL
-validated verdict TEST_BLOCKED  → status=TEST_BLOCKED, stage_result=TEST_BLOCKED
-retrospective result DOCS_UPDATED  → status=RETRO_COMPLETE, stage_result=DOCS_UPDATED
-retrospective result NO_DOC_CHANGE → status=RETRO_COMPLETE, stage_result=NO_DOC_CHANGE
+review-report PASS               → status=REVIEW_PASS, stage_result=PASS
+review-report NEEDS_FIXES        → status=REVIEW_NEEDS_FIXES, stage_result=NEEDS_FIXES
+test-result TEST_PASS            → status=TEST_PASS, stage_result=TEST_PASS
+test-result TEST_NEEDS_FIXES     → status=TEST_NEEDS_FIXES, stage_result=TEST_NEEDS_FIXES
+test-result TEST_BLOCKED         → status=TEST_BLOCKED, stage_result=TEST_BLOCKED
+retrospective DOCS_UPDATED       → status=RETRO_COMPLETE, stage_result=DOCS_UPDATED
+retrospective NO_DOC_CHANGE      → status=RETRO_COMPLETE, stage_result=NO_DOC_CHANGE
 ```
 
-`RETRO_COMPLETE` is the stable completion status. `DOCS_UPDATED` and `NO_DOC_CHANGE` are mutually exclusive retrospective results, not substitute statuses. A derived Markdown test report never establishes a `TEST_*` status without validated authoritative evidence.
-
-## Repair Routing
-
-```text
-REVIEW_NEEDS_FIXES
-  → implement
-  → code-review
-  → test
+`TEST_PASS` requires both `test-report.md` and a consistent `test-result.json`. No manifest, attestation, evidence package, or test-internal checkpoint is part of this contract.
 
-TEST_FAIL with repair_scope=test-infrastructure
-  → implement
-  → test
+## Non-Pass Results and Routing Boundary
 
-TEST_FAIL with repair_scope=production|runtime|schema|dependency|public-interface
-  → implement
-  → code-review
-  → test
+`prizmkit-test` performs its own bounded failure repair and review loops before returning. The test skill never invokes another lifecycle stage.
 
-TEST_FAIL with repair_scope=unknown
-  → conservative production route only when safe
-  → otherwise WORKFLOW_BLOCKED
+```text
+TEST_NEEDS_FIXES
+→ known correction or required delta review remains
+→ caller decides whether and how to arrange another stage
 
 TEST_BLOCKED
-  → never make speculative production edits
-  → interactive execution stops with a prizmkit-test resume entry
-  → a trusted headless host may perform bounded environment recovery, then records WORKFLOW_BLOCKED if unresolved
-
-RETRO_BLOCKED
-  → WORKFLOW_BLOCKED
-WORKFLOW_BLOCKED
-  → resume only after the recorded blocker is resolved
+→ truth, input, safe environment, or reliable execution prevents a verdict
+→ never make speculative production edits
+→ caller or external host owns recovery policy
 ```
 
-The outer workflow permits at most three automatic repair rounds. These are cross-stage rounds (`repair_round` `0` through `3`). The code-review internal loop permits at most ten completed review rounds and is separate; review-internal repairs do not increment the outer counter.
+A test result is not an AI CLI session classification. `TEST_NEEDS_FIXES` and `TEST_BLOCKED` must not be rewritten as crash or infrastructure failure merely because they stop lifecycle progression.
+
+Any outer repair or continuation policy is independently owned by the caller and cannot alter the test report. The Main-Agent test review limit of ten rounds, independent Test Reviewer limit of five responses, and execution-failure repair limit of three rounds are internal to one test invocation and do not update outer counters.
 
 ## Orchestrator Ownership and Handoff
 
-1. An atomic stage performs only its own stage, writes the truthful terminal result and `next_stage`, and returns control.
-2. When `orchestrator` is non-null, only that orchestrator invokes the next skill. The atomic stage must not auto-invoke it again.
-3. Direct stage use may report one deterministic next invocation but does not claim the next stage ran.
+1. An atomic stage performs only its own stage, writes its truthful result and artifact paths, and returns control.
+2. When `orchestrator` is non-null, only that orchestrator invokes the next skill.
+3. Direct stage use may report a possible next invocation but does not claim it ran.
 4. Every handoff preserves the same `artifact_dir`.
-5. External automation invokes atomic stages directly and does not invoke `prizmkit-workflow` as a nested coordinator.
-6. Workflow state never replaces or absorbs an external host's checkpoint.
+5. External automation invokes atomic stages directly and does not nest the composite workflow.
+6. Workflow state never replaces or absorbs an external host checkpoint.
 
 ## Commit Authorization
 
@@ -148,34 +131,32 @@ Interactive execution:
 
 ```text
 committer previews intended files and message
-→ waits for explicit confirmation from the current user
+→ waits for explicit current-user confirmation
 → creates the local commit
 ```
 
 Trusted headless execution:
 
 ```text
-a trusted host explicitly authorizes the current local task commit
-→ host injects mode=<host-defined-headless-mode>, owner=<trusted-host-identifier>,
-  local_commit_authorized=true
+trusted host explicitly authorizes the current local task commit
 → committer verifies gates and commits automatically
-→ no question or wait is permitted
+→ remote publication remains separate
 ```
 
-A self-declared or otherwise untrusted headless context does not authorize a commit. Remote publication remains a separate host-runtime decision.
+A self-declared or untrusted headless context does not authorize a commit.
 
 ## Recovery
 
 When state is missing, stale, or inconsistent:
 
-1. Read `spec.md` and `plan.md` from `artifact_dir` only when they are not already available in current context.
-2. Inspect task markers and the current workspace.
-3. Read the latest review report and final result when needed to establish review authority.
-4. Validate authoritative test evidence and `repair_scope`.
+1. Reuse current context, then read `spec.md` and `plan.md` only when needed.
+2. Inspect task markers and current workspace.
+3. Read the current review report when needed to establish review authority.
+4. Validate that `test-report.md` and terminal `test-result.json` exist, agree, and reflect the claimed result.
 5. Validate `retrospective-result.json` when retrospective is claimed complete.
 6. Verify the commit when commit is claimed complete.
-7. When an external host is active, let that host validate its own checkpoint independently; never merge the schemas.
+7. Let an active external host validate its own checkpoint independently.
 8. Reconstruct the latest safe predecessor and report the reconstruction.
 9. Continue only from the first incomplete or invalid stage.
 
-Stale state never bypasses review, testing, retrospective, commit authorization, or external host checkpoint enforcement.
+Stale state never bypasses review, testing, retrospective, commit authorization, or external checkpoint enforcement.

package/bundled/skills/prizmkit-code-review/SKILL.md

@@ -15,7 +15,7 @@ description: "Review the complete current change for a formal PrizmKit requireme
 - Do not launch any additional review work through a general-purpose execution unit or relabel it as a finder, verifier, audit, compatibility review, verification, or gap sweep.
 - The independent Reviewer cannot mutate, execute arbitrary commands, or create downstream execution units; prompt instructions never substitute for these structural guarantees.
 - The Main Agent may directly read, search, edit, and run targeted verification in the active workspace.
-- Review repairs occur before the full `/prizmkit-test` stage so final test evidence represents the final reviewed workspace.
+- Review repairs occur before the full `/prizmkit-test` stage so project-native tests run against the final reviewed workspace.
 - `{artifact_dir}/review-report.md` is the only persisted review artifact for this execution.
 
 ## Atomic Stage Boundary
@@ -26,7 +26,7 @@ description: "Review the complete current change for a formal PrizmKit requireme
 
 - After `/prizmkit-implement` reports `IMPLEMENTED`.
 - After implementation repairs that changed production code, runtime configuration, schema, dependencies, or public interfaces.
-- When workflow state routes a formal requirement back to review after `TEST_FAIL`.
+- When a caller routes a high-risk production repair reported by `prizmkit-test` back for delta review.
 - When the user asks for a complete review or commit readiness decision.
 
 ## When NOT to Use
@@ -43,7 +43,7 @@ description: "Review the complete current change for a formal PrizmKit requireme
 | `artifact_dir` | No | Directory containing `spec.md` and `plan.md`. Reuse the caller's directory or workflow-state value. |
 | `review_scope` | No | `full` for the initial review; `delta` for a production-affecting repair after a prior review pass. |
 
-Every invocation must reuse the same `artifact_dir`. If workflow state is missing, reconstruct it from `spec.md`, `plan.md`, `review-report.md`, the current diff, and any test evidence, and report the reconstruction.
+Every invocation must reuse the same `artifact_dir`. If workflow state is missing, reconstruct it from `spec.md`, `plan.md`, `review-report.md`, the current diff, and any current test report/result pair, and report the reconstruction.
 
 ## Phase 0: Initialize Report and Reuse Current Context