prizmkit 1.1.130 → 1.1.131

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

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 import json
 
-from prizmkit_runtime.checkpoint_state import load_checkpoint_state, read_checkpoint_cursor
+from prizmkit_runtime.checkpoint_state import load_checkpoint_state, read_checkpoint_cursor, validate_checkpoint_data
 from update_checkpoint import update_checkpoint
 
 
@@ -138,7 +138,7 @@ def test_update_checkpoint_rejects_ambiguous_skill_without_mutation(tmp_path):
 
 def test_update_checkpoint_exact_id_updates_one_duplicate_skill_step(tmp_path):
     path = _write(tmp_path / "workflow-checkpoint.json", _checkpoint([
-        _step("S01", "prizmkit-committer", "Commit First", "pending"),
+        _step("S01", "prizmkit-committer", "Commit First", "completed"),
         _step("S02", "prizmkit-committer", "Commit Second", "pending", "S01"),
     ]))
 
@@ -147,7 +147,7 @@ def test_update_checkpoint_exact_id_updates_one_duplicate_skill_step(tmp_path):
 
     assert result["ok"] is True
     assert result["step_id"] == "S02"
-    assert data["steps"][0]["status"] == "pending"
+    assert data["steps"][0]["status"] == "completed"
     assert data["steps"][1]["status"] == "completed"
 
 
@@ -162,3 +162,362 @@ def test_update_checkpoint_invalid_checkpoint_fails_without_mutation(tmp_path):
     assert result["ok"] is False
     assert "invalid_status" in result["error"]
     assert path.read_text(encoding="utf-8") == before
+
+
+
+def _family_checkpoint(workflow_type, skills, *, semantic=None):
+    steps = []
+    previous = None
+    for index, skill in enumerate(skills, start=1):
+        step = _step(f"S{index:02d}", skill, skill, "completed", previous)
+        if skill == "prizmkit-code-review":
+            step["stage_result"] = "REVIEW_PASS"
+        if skill == "prizmkit-test":
+            step["stage_result"] = "TEST_PASS"
+        steps.append(step)
+        previous = step["id"]
+    payload = {"version": 1, "workflow_type": workflow_type, "steps": steps}
+    state_key = {
+        "feature-pipeline": "feature_state",
+        "bugfix-pipeline": "bugfix_state",
+        "refactor-pipeline": "refactor_state",
+    }[workflow_type]
+    payload[state_key] = semantic or {}
+    return payload
+
+
+def _write_test_evidence(root, verdict="TEST_PASS", validation_result="passed", evidence_id="evidence-1"):
+    evidence = root / ".prizmkit" / "test" / "evidence" / evidence_id
+    evidence.mkdir(parents=True)
+    manifest = evidence / "manifest.json"
+    verdict_path = evidence / "verdict.json"
+    validation = evidence / "validation.json"
+    manifest.write_text(json.dumps({"evidence_id": evidence_id, "final_verdict": verdict}), encoding="utf-8")
+    verdict_path.write_text(json.dumps({"verdict": verdict}), encoding="utf-8")
+    validation.write_text(json.dumps({"verdict": verdict, "result": validation_result}), encoding="utf-8")
+    return {
+        "manifest": str(manifest.relative_to(root)),
+        "verdict": str(verdict_path.relative_to(root)),
+        "validation": str(validation.relative_to(root)),
+    }
+
+
+def test_semantic_completion_requires_family_sequence_verdicts_and_structured_evidence(tmp_path, monkeypatch):
+    monkeypatch.setattr(
+        "prizmkit_runtime.checkpoint_state._resolve_evidence_validator",
+        lambda _root: tmp_path / "validator.py",
+    )
+    monkeypatch.setattr(
+        "prizmkit_runtime.checkpoint_state._evidence_validator_passes",
+        lambda *_args: True,
+    )
+    paths = _write_test_evidence(tmp_path)
+    skills = [
+        "prizmkit-implement", "prizmkit-code-review", "prizmkit-test",
+        "prizmkit-retrospective", "prizmkit-committer", "completion-summary",
+    ]
+    payload = _family_checkpoint(
+        "feature-pipeline",
+        skills,
+        semantic={
+            "repair_round": 0,
+            "authoritative_evidence_paths": paths,
+            "terminal_status": "WORKFLOW_COMPLETED",
+        },
+    )
+    payload["steps"][2]["authoritative_evidence_paths"] = paths
+    checkpoint = tmp_path / ".prizmkit" / "specs" / "feature" / "workflow-checkpoint.json"
+    checkpoint.parent.mkdir(parents=True)
+    _write(checkpoint, payload)
+
+    state = load_checkpoint_state(checkpoint, project_root=tmp_path)
+
+    assert state.valid is True
+    assert state.all_completed is True
+    assert state.semantic_complete is True
+    assert state.semantic.evidence_valid is True
+    assert state.semantic.terminal_status == "WORKFLOW_COMPLETED"
+
+
+def test_completed_steps_without_stage_verdicts_are_not_semantic_completion(tmp_path):
+    skills = [
+        "prizmkit-implement", "prizmkit-code-review", "prizmkit-test",
+        "prizmkit-retrospective", "prizmkit-committer", "completion-summary",
+    ]
+    payload = _family_checkpoint("feature-pipeline", skills)
+    payload["steps"][1].pop("stage_result")
+    payload["steps"][2].pop("stage_result")
+    payload["feature_state"]["terminal_status"] = "WORKFLOW_COMPLETED"
+
+    state = validate_checkpoint_data(payload, project_root=tmp_path)
+
+    assert state.valid is True
+    assert state.all_completed is True
+    assert state.semantic_complete is False
+    assert state.semantic.error_code == "incomplete_semantic_evidence"
+
+
+def test_family_sequence_mismatch_cannot_complete(tmp_path):
+    paths = _write_test_evidence(tmp_path)
+    skills = [
+        "prizmkit-implement", "prizmkit-test", "prizmkit-code-review",
+        "prizmkit-retrospective", "prizmkit-committer", "completion-summary",
+    ]
+    payload = _family_checkpoint(
+        "feature-pipeline",
+        skills,
+        semantic={"authoritative_evidence_paths": paths, "terminal_status": "WORKFLOW_COMPLETED"},
+    )
+    payload["steps"][1]["authoritative_evidence_paths"] = paths
+
+    state = validate_checkpoint_data(payload, project_root=tmp_path)
+
+    assert state.semantic_complete is False
+    assert state.semantic.sequence_valid is False
+    assert state.semantic.error_code == "invalid_stage_sequence"
+
+
+def test_stale_or_mismatched_test_evidence_cannot_complete(tmp_path):
+    paths = _write_test_evidence(tmp_path, verdict="TEST_FAIL")
+    skills = [
+        "prizmkit-implement", "prizmkit-code-review", "prizmkit-test",
+        "prizmkit-retrospective", "prizmkit-committer", "completion-summary",
+    ]
+    payload = _family_checkpoint(
+        "feature-pipeline",
+        skills,
+        semantic={"authoritative_evidence_paths": paths, "terminal_status": "WORKFLOW_COMPLETED"},
+    )
+    payload["steps"][2]["authoritative_evidence_paths"] = paths
+
+    state = validate_checkpoint_data(payload, project_root=tmp_path)
+
+    assert state.semantic_complete is False
+    assert state.semantic.evidence_valid is False
+    assert state.semantic.error_code == "incomplete_semantic_evidence"
+
+
+def test_blocked_terminal_is_semantic_and_requires_reason(tmp_path):
+    payload = _family_checkpoint(
+        "feature-pipeline",
+        [
+            "prizmkit-implement", "prizmkit-code-review", "prizmkit-test",
+            "prizmkit-retrospective", "prizmkit-committer", "completion-summary",
+        ],
+        semantic={
+            "repair_scope": "production",
+            "repair_round": 3,
+            "blocked_reason": "repair_round_limit",
+            "terminal_status": "WORKFLOW_BLOCKED",
+        },
+    )
+    payload["steps"][2]["stage_result"] = "TEST_FAIL"
+
+    state = validate_checkpoint_data(payload, project_root=tmp_path)
+
+    assert state.semantic_blocked is True
+    assert state.semantic_complete is False
+    assert state.semantic.blocked_reason == "repair_round_limit"
+    assert state.cursor_signature == "blocked:repair_round_limit"
+
+
+def test_step_progress_must_be_a_terminal_prefix(tmp_path):
+    payload = _checkpoint([
+        _step("S01", "plan", "Plan", "pending"),
+        _step("S02", "implement", "Implement", "completed", "S01"),
+    ])
+
+    state = validate_checkpoint_data(payload)
+
+    assert state.valid is False
+    assert state.error_code == "invalid_step_progress"
+
+
+
+def test_update_checkpoint_rejects_out_of_order_transition(tmp_path):
+    path = _write(tmp_path / "workflow-checkpoint.json", _checkpoint([
+        _step("S01", "plan", "Plan", "pending"),
+        _step("S02", "implement", "Implement", "pending", "S01"),
+    ]))
+
+    result = update_checkpoint(str(path), "S02", "in_progress")
+
+    assert result["ok"] is False
+    assert "before all predecessors" in result["error"]
+
+
+def test_update_checkpoint_blocks_unknown_repair_scope_without_mutating_retry_budget(tmp_path):
+    payload = _family_checkpoint(
+        "feature-pipeline",
+        [
+            "prizmkit-implement", "prizmkit-code-review", "prizmkit-test",
+            "prizmkit-retrospective", "prizmkit-committer", "completion-summary",
+        ],
+    )
+    payload["steps"][1]["status"] = "in_progress"
+    for step in payload["steps"][2:]:
+        step["status"] = "pending"
+        step.pop("stage_result", None)
+    path = _write(tmp_path / "workflow-checkpoint.json", payload)
+
+    result = update_checkpoint(
+        str(path),
+        "prizmkit-code-review",
+        "failed",
+        semantic_update={"stage_result": "REVIEW_NEEDS_FIXES", "repair_round": 0},
+    )
+    data = json.loads(path.read_text(encoding="utf-8"))
+
+    assert result["ok"] is True
+    assert data["feature_state"]["terminal_status"] == "WORKFLOW_BLOCKED"
+    assert data["feature_state"]["blocked_reason"] == "unsafe_repair_scope"
+    assert "retry_count" not in data["feature_state"]
+
+
+def test_update_checkpoint_enforces_three_outer_repair_rounds(tmp_path):
+    payload = _family_checkpoint(
+        "feature-pipeline",
+        [
+            "prizmkit-implement", "prizmkit-code-review", "prizmkit-test",
+            "prizmkit-retrospective", "prizmkit-committer", "completion-summary",
+        ],
+        semantic={"repair_scope": "production", "repair_round": 3},
+    )
+    payload["steps"][1]["status"] = "in_progress"
+    for step in payload["steps"][2:]:
+        step["status"] = "pending"
+        step.pop("stage_result", None)
+    path = _write(tmp_path / "workflow-checkpoint.json", payload)
+
+    result = update_checkpoint(
+        str(path),
+        "prizmkit-code-review",
+        "failed",
+        semantic_update={"stage_result": "REVIEW_NEEDS_FIXES", "repair_scope": "production"},
+    )
+    data = json.loads(path.read_text(encoding="utf-8"))
+
+    assert result["ok"] is True
+    assert data["feature_state"]["repair_round"] == 3
+    assert data["feature_state"]["terminal_status"] == "WORKFLOW_BLOCKED"
+    assert data["feature_state"]["blocked_reason"] == "repair_round_limit"
+
+
+
+def test_declared_final_artifact_must_exist_for_semantic_completion(tmp_path, monkeypatch):
+    monkeypatch.setattr(
+        "prizmkit_runtime.checkpoint_state._resolve_evidence_validator",
+        lambda _root: tmp_path / "validator.py",
+    )
+    monkeypatch.setattr(
+        "prizmkit_runtime.checkpoint_state._evidence_validator_passes",
+        lambda *_args: True,
+    )
+    paths = _write_test_evidence(tmp_path)
+    skills = [
+        "prizmkit-implement", "prizmkit-code-review", "prizmkit-test",
+        "prizmkit-retrospective", "prizmkit-committer", "completion-summary",
+    ]
+    payload = _family_checkpoint(
+        "feature-pipeline",
+        skills,
+        semantic={"authoritative_evidence_paths": paths, "terminal_status": "WORKFLOW_COMPLETED"},
+    )
+    payload["steps"][2]["authoritative_evidence_paths"] = paths
+    payload["steps"][-1]["required_artifacts"] = [".prizmkit/specs/feature/completion-summary.json"]
+    checkpoint = tmp_path / ".prizmkit" / "specs" / "feature" / "workflow-checkpoint.json"
+    checkpoint.parent.mkdir(parents=True)
+    _write(checkpoint, payload)
+
+    missing = load_checkpoint_state(checkpoint, project_root=tmp_path)
+    (checkpoint.parent / "completion-summary.json").write_text("{}", encoding="utf-8")
+    present = load_checkpoint_state(checkpoint, project_root=tmp_path)
+
+    assert missing.semantic_complete is False
+    assert missing.semantic.artifacts_valid is False
+    assert present.semantic_complete is True
+    assert present.semantic.artifacts_valid is True
+
+
+
+def test_update_checkpoint_rejects_test_pass_when_validator_replay_fails(tmp_path, monkeypatch):
+    paths = _write_test_evidence(tmp_path)
+    payload = _family_checkpoint(
+        "feature-pipeline",
+        [
+            "prizmkit-implement", "prizmkit-code-review", "prizmkit-test",
+            "prizmkit-retrospective", "prizmkit-committer", "completion-summary",
+        ],
+    )
+    payload["steps"][2]["status"] = "in_progress"
+    for step in payload["steps"][3:]:
+        step["status"] = "pending"
+        step.pop("stage_result", None)
+    checkpoint = tmp_path / "workflow-checkpoint.json"
+    _write(checkpoint, payload)
+    monkeypatch.setattr(
+        "prizmkit_runtime.checkpoint_state._resolve_evidence_validator",
+        lambda _root: tmp_path / "validator.py",
+    )
+    monkeypatch.setattr(
+        "prizmkit_runtime.checkpoint_state._evidence_validator_passes",
+        lambda *_args: False,
+    )
+
+    result = update_checkpoint(
+        str(checkpoint),
+        "prizmkit-test",
+        "completed",
+        semantic_update={
+            "stage_result": "TEST_PASS",
+            "authoritative_evidence_paths": paths,
+        },
+    )
+
+    assert result["ok"] is False
+    assert "validator-attested" in result["error"]
+
+
+
+def test_update_checkpoint_rejects_test_before_review_pass(tmp_path):
+    payload = _family_checkpoint(
+        "feature-pipeline",
+        [
+            "prizmkit-implement", "prizmkit-code-review", "prizmkit-test",
+            "prizmkit-retrospective", "prizmkit-committer", "completion-summary",
+        ],
+    )
+    payload["steps"][1]["status"] = "skipped"
+    payload["steps"][1].pop("stage_result", None)
+    payload["steps"][2]["status"] = "pending"
+    for step in payload["steps"][3:]:
+        step["status"] = "pending"
+        step.pop("stage_result", None)
+    checkpoint = _write(tmp_path / "workflow-checkpoint.json", payload)
+
+    result = update_checkpoint(str(checkpoint), "prizmkit-test", "in_progress")
+
+    assert result["ok"] is False
+    assert "REVIEW_PASS" in result["error"]
+
+
+def test_update_checkpoint_rejects_finalization_before_test_pass(tmp_path):
+    payload = _family_checkpoint(
+        "feature-pipeline",
+        [
+            "prizmkit-implement", "prizmkit-code-review", "prizmkit-test",
+            "prizmkit-retrospective", "prizmkit-committer", "completion-summary",
+        ],
+    )
+    payload["steps"][2]["status"] = "skipped"
+    payload["steps"][2].pop("stage_result", None)
+    payload["steps"][3]["status"] = "pending"
+    for step in payload["steps"][4:]:
+        step["status"] = "pending"
+        step.pop("stage_result", None)
+    checkpoint = _write(tmp_path / "workflow-checkpoint.json", payload)
+
+    result = update_checkpoint(str(checkpoint), "prizmkit-retrospective", "in_progress")
+
+    assert result["ok"] is False
+    assert "TEST_PASS" in result["error"]