prizmkit 1.1.121 → 1.1.122

package/bundled/VERSION.json

@@ -1,5 +1,5 @@
 {
-  "frameworkVersion": "1.1.121",
-  "bundledAt": "2026-07-11T06:00:42.680Z",
-  "bundledFrom": "c2f98e2"
+  "frameworkVersion": "1.1.122",
+  "bundledAt": "2026-07-11T17:19:34.691Z",
+  "bundledFrom": "fbcb3f4"
 }

package/bundled/dev-pipeline/prizmkit_runtime/cli.py

@@ -142,6 +142,7 @@ def build_parser() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(
         prog="prizmkit-runtime",
         description=DESCRIPTION,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
     )
     parser.add_argument(
         "--project-root",

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

@@ -30,10 +30,11 @@ if str(PIPELINE_ROOT) not in sys.path:
     sys.path.insert(0, str(PIPELINE_ROOT))
 
 
-def run_cli(*args):
+def run_cli(*args, env=None):
     return subprocess.run(
         [PYTHON_310_PLUS, str(CLI_PATH), *args],
         cwd=REPO_ROOT,
+        env=env,
         text=True,
         stdout=subprocess.PIPE,
         stderr=subprocess.PIPE,
@@ -72,6 +73,14 @@ def test_cli_help_exposes_python_runtime_command_groups():
     assert "Traceback" not in result.stderr
 
 
+def test_cli_help_preserves_runtime_identity_at_narrow_terminal_width():
+    result = run_cli("--help", env={**os.environ, "COLUMNS": "24"})
+
+    assert result.returncode == 0
+    assert "canonical Python runtime CLI" in result.stdout
+    assert "without shell wrappers" in result.stdout
+
+
 def test_module_entrypoint_help_exposes_same_cli():
     env = {**os.environ, "PYTHONPATH": str(PIPELINE_ROOT)}
     result = subprocess.run(

package/bundled/skills/_metadata.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.1.121",
+  "version": "1.1.122",
   "skills": {
     "prizmkit": {
       "description": "Full-lifecycle dev toolkit. Covers spec-driven development, Prizm context docs, code quality, debugging, deployment, and knowledge management.",

package/bundled/skills/prizmkit-test/SKILL.md

@@ -145,8 +145,9 @@ Differentially prove each added/changed necessary behavior test:
 
 - Prefer baseline failure plus current success in an isolated/uncontaminated environment.
 - If baseline is inapplicable, use a minimal controlled mutation tied to the same risk.
-- Bind proof to runner receipts, baseline commit, current/isolation tree hashes, mutation apply/restore hashes, and complete cleanup.
-- Completely remove mutations and verify the original project tree is unchanged.
+- Bind proof to runner receipts, baseline commit, a stable source-snapshot hash, mutation apply/restore hashes, and complete cleanup. The source snapshot excludes runtime-managed `.prizmkit/state/`, evidence output under `.prizmkit/test/evidence/`, `.claude/worktrees/`, Git metadata, and Python bytecode caches because those paths change while the tested code remains identical.
+- Keep source identity separate from evidence integrity: the stable snapshot detects behavior-bearing project drift, while `manifest.json` hashes every evidence file and detects report/output tampering.
+- Completely remove mutations and verify the stable source snapshot is unchanged. Never rebind completed proof to the mutable live project tree.
 - Classify each proof as `PROVEN`, structured `NOT_APPLICABLE`, or `UNPROVEN`.
 
 Necessary `UNPROVEN` behavior, required flakiness, unavailable infrastructure after bounded recovery, failed cleanup, unreliable execution, or budget truncation yields `TEST_BLOCKED`.
@@ -170,7 +171,7 @@ Create `.prizmkit/test/evidence/<evidence-id>/` from the package template with:
 - `contracts/` snapshots
 - derived `test-report.md`
 
-Hash baseline, diff, source, tests, contracts, lockfiles, environment, plan, and every evidence file. Set `environment_claim=mocked-code-level-only` and `compatibility=legacy-test-report-interface-not-supported`.
+Hash baseline, diff, the stable source snapshot, inventoried source/tests/contracts/lockfiles, environment, plan, and every evidence file. Runtime state, evidence output, linked Agent worktrees, Git metadata, and bytecode caches are outside source identity; evidence files remain independently content-addressed through `manifest.json`. Set `environment_claim=mocked-code-level-only` and `compatibility=legacy-test-report-interface-not-supported`.
 
 ### 9. EVIDENCE_VALIDATE
 

package/bundled/skills/prizmkit-test/references/evidence-protocol.md

@@ -10,7 +10,14 @@ Write packages under `.prizmkit/test/evidence/<evidence-id>/`. Compute `evidence
 - `working_diff_sha256`
 - `scope_sha256`
 
-Store those values as `evidence_id_inputs` in `manifest.json`. Record separate aggregate hashes for source, tests, contracts, lockfiles, full environment values, and plan inputs. Hash every evidence file except `manifest.json` in the manifest; do not create a self-referential manifest hash.
+Store those values as `evidence_id_inputs` in `manifest.json`. Record separate aggregate hashes for inventoried source, tests, contracts, lockfiles, full environment values, and plan inputs. Hash every evidence file except `manifest.json` in the manifest; do not create a self-referential manifest hash.
+
+Use two separate integrity domains:
+
+- **Stable source snapshot:** hash behavior-bearing project files while excluding runtime-managed `.prizmkit/state/`, evidence output under `.prizmkit/test/evidence/`, linked `.claude/worktrees/`, Git metadata, and Python bytecode caches. Builder and validator use the same deterministic exclusion policy, and isolated current execution is copied from that same snapshot scope.
+- **Evidence package:** hash each evidence record through `manifest.json`; any report, receipt, raw output, request, or proof mutation remains detectable even though evidence output is outside source identity.
+
+Runtime-only churn must not invalidate a source proof. Drift in an inventoried source, test, contract, or lockfile must still fail live inventory validation. Never replace a completed proof's stable snapshot identity with a later hash of the mutable parent workspace.
 
 Hashes and validator receipts provide byte-level binding and drift detection, not cryptographic non-repudiation. A caller with the same OS permissions can replace the runner, requests, project tree, or package before validation. Preserve runner/request hashes and use replay to improve auditability without claiming resistance to a malicious same-privilege producer.
 
@@ -126,7 +133,7 @@ For each added or changed necessary behavior test, prove the test:
 2. If baseline execution is inapplicable (for example, the public behavior did not exist), apply a minimal controlled mutation tied to the same matrix risk, observe failure, restore it completely, and observe current success.
 3. Record `PROVEN`, justified `NOT_APPLICABLE`, or `UNPROVEN`.
 
-Record baseline/current/mutation runner receipt IDs, request hash, baseline commit, current and isolation tree hashes, mutation apply/restore hashes, expected failure signal match, and original-tree cleanup result. Necessary `UNPROVEN` behavior prevents `TEST_PASS`.
+Record baseline/current/mutation runner receipt IDs, request hash, baseline commit, stable source-snapshot and isolation hashes, mutation apply/restore hashes, expected failure signal match, and source-snapshot cleanup result. Necessary `UNPROVEN` behavior prevents `TEST_PASS`.
 
 ### EVIDENCE_PACKAGE
 
@@ -157,7 +164,7 @@ python3 ${SKILL_DIR}/scripts/validate_test_evidence.py \
 
 When feasible, replay recorded requests through `build_test_evidence.py execute --replay-receipt ...`. Replay performs a new real execution and emits a new linked receipt; it does not pretend the attestation establishes what historically ran.
 
-The validator checks all shipped JSON schemas, evidence-directory identity, live target-project inventories and aggregate hashes, changed-file/module-root/exclusion/Regression Ring cross-links, patch/diff binding, stage output ownership and predecessor hashes, generated-test snapshot existence, planned test/inventory/execution linkage, module/matrix completeness, successful selected runner receipts with request/raw-output binding, proof-linked isolated failures/current successes, controlled-mutation apply/restoration hashes, cleanup, structured N/A and obvious signal conflicts, production/unknown external-target safety, strict verdict semantics, and honest mocked-versus-real claims. `TEST_PASS` requires deterministic validator success.
+The validator checks all shipped JSON schemas, evidence-directory identity, live target-project inventories and aggregate hashes, stable source-snapshot identity with runtime paths excluded, changed-file/module-root/exclusion/Regression Ring cross-links, patch/diff binding, stage output ownership and predecessor hashes, generated-test snapshot existence, planned test/inventory/execution linkage, module/matrix completeness, successful selected runner receipts with request/raw-output binding, proof-linked isolated failures/current successes, controlled-mutation apply/restoration hashes, cleanup, structured N/A and obvious signal conflicts, production/unknown external-target safety, strict verdict semantics, and honest mocked-versus-real claims. `TEST_PASS` requires deterministic validator success.
 
 ## Resume and Invalidation
 

package/bundled/skills/prizmkit-test/references/evidence-request-protocol.md

@@ -41,11 +41,11 @@ Record:
 
 - behavior ID and model-selected `baseline` or `controlled-mutation` method;
 - the nested execution request;
-- actual baseline commit and current project-tree hash;
+- actual baseline commit and the stable source-snapshot hash produced with the builder's runtime exclusions;
 - mutation patch path when applicable;
 - concrete expected failure signals.
 
-The builder creates isolated copies, executes the failing and current sides, records receipts, binds the differential request hash, and verifies that the original project tree is unchanged. A proof is `PROVEN` only when the intended failure signal appears, the failing side exits nonzero, current exits zero, and cleanup/tree checks pass.
+The builder creates isolated copies from the same stable source-snapshot scope, executes the failing and current sides, records receipts, binds the differential request hash, and verifies that behavior-bearing project content is unchanged. Runtime state, evidence output, linked Agent worktrees, Git metadata, and Python bytecode caches do not participate in source identity. A proof is `PROVEN` only when the intended failure signal appears, the failing side exits nonzero, current exits zero, and cleanup/snapshot checks pass.
 
 ## Structured N/A
 

package/bundled/skills/prizmkit-test/scripts/build_test_evidence.py

@@ -36,6 +36,12 @@ STAGES = [
 ]
 CATEGORIES = ("source", "tests", "contracts", "lockfiles")
 BLOCKED_EXTERNAL_CLASSES = {"production", "unknown"}
+SNAPSHOT_VOLATILE_ROOTS = (
+    ".prizmkit/state",
+    ".prizmkit/test/evidence",
+    ".claude/worktrees",
+)
+SNAPSHOT_VOLATILE_NAMES = {".git", "__pycache__"}
 
 
 class RequestError(Exception):
@@ -176,14 +182,23 @@ def validate_execution_request(request: Any) -> dict[str, Any]:
     return request
 
 
+def is_volatile_snapshot_path(root: Path, candidate: Path, excluded: list[Path] | None = None) -> bool:
+    try:
+        relative = candidate.relative_to(root)
+    except ValueError:
+        return True
+    if any(part in SNAPSHOT_VOLATILE_NAMES for part in relative.parts):
+        return True
+    if any(relative == Path(prefix) or Path(prefix) in relative.parents for prefix in SNAPSHOT_VOLATILE_ROOTS):
+        return True
+    resolved = candidate.resolve()
+    return any(resolved == item.resolve() or item.resolve() in resolved.parents for item in (excluded or []))
+
+
 def tree_sha256(root: Path, excluded: list[Path] | None = None) -> str:
-    excluded_resolved = [path.resolve() for path in (excluded or [])]
     entries: list[dict[str, str]] = []
     for candidate in sorted(root.rglob("*")):
-        if not candidate.is_file() or ".git" in candidate.parts or "__pycache__" in candidate.parts:
-            continue
-        resolved = candidate.resolve()
-        if any(resolved == item or item in resolved.parents for item in excluded_resolved):
+        if not candidate.is_file() or is_volatile_snapshot_path(root, candidate, excluded):
             continue
         entries.append({"path": candidate.relative_to(root).as_posix(), "sha256": file_sha256(candidate)})
     return canonical_sha256(entries)
@@ -454,13 +469,14 @@ def execute_request(
 
 
 def copy_project_tree(project_root: Path, destination: Path, evidence_dir: Path) -> None:
-    ignored_path = evidence_dir.resolve().relative_to(project_root.resolve())
-
     def ignore(directory: str, names: list[str]) -> set[str]:
-        ignored = {".git", "__pycache__"} & set(names)
         directory_relative = Path(directory).resolve().relative_to(project_root.resolve())
-        if ignored_path.parent == directory_relative and ignored_path.name in names:
-            ignored.add(ignored_path.name)
+        ignored: set[str] = set()
+        for name in names:
+            relative = directory_relative / name
+            candidate = project_root / relative
+            if is_volatile_snapshot_path(project_root, candidate, [evidence_dir]):
+                ignored.add(name)
         return ignored
 
     shutil.copytree(project_root, destination, ignore=ignore)

package/bundled/skills/prizmkit-test/scripts/validate_test_evidence.py

@@ -51,6 +51,12 @@ LIGHTWEIGHT_RECORDS = {"lightweight-verification.json"}
 SHA256_RE = re.compile(r"^[a-f0-9]{64}$")
 UUID_RE = re.compile(r"^[a-f0-9-]{36}$")
 BLOCKED_EXTERNAL_CLASSES = {"production", "unknown"}
+SNAPSHOT_VOLATILE_ROOTS = (
+    ".prizmkit/state",
+    ".prizmkit/test/evidence",
+    ".claude/worktrees",
+)
+SNAPSHOT_VOLATILE_NAMES = {".git", "__pycache__"}
 RISK_CONFLICT_PATTERNS = {
     "permission": re.compile(r"auth|tenant|role|permission|access|acl|rbac", re.I),
     "concurrency": re.compile(r"lock|shared[ _-]?state|worker|queue|concurr|parallel|race", re.I),
@@ -1019,14 +1025,24 @@ def validate_matrix_risks(
                     errors.append(f"TEST_PASS has unresolved behavior risk: {behavior_id}/{risk_name}")
 
 
-def tree_sha256(root: Path, evidence_root: Path) -> str:
+def is_volatile_snapshot_path(root: Path, candidate: Path, evidence_root: Path) -> bool:
+    try:
+        relative = candidate.relative_to(root)
+    except ValueError:
+        return True
+    if any(part in SNAPSHOT_VOLATILE_NAMES for part in relative.parts):
+        return True
+    if any(relative == Path(prefix) or Path(prefix) in relative.parents for prefix in SNAPSHOT_VOLATILE_ROOTS):
+        return True
+    resolved = candidate.resolve()
     excluded = evidence_root.resolve()
+    return resolved == excluded or excluded in resolved.parents
+
+
+def tree_sha256(root: Path, evidence_root: Path) -> str:
     entries: list[dict[str, str]] = []
     for candidate in sorted(root.rglob("*")):
-        if not candidate.is_file() or ".git" in candidate.parts or "__pycache__" in candidate.parts:
-            continue
-        resolved = candidate.resolve()
-        if resolved == excluded or excluded in resolved.parents:
+        if not candidate.is_file() or is_volatile_snapshot_path(root, candidate, evidence_root):
             continue
         entries.append({"path": candidate.relative_to(root).as_posix(), "sha256": file_sha256(candidate)})
     return canonical_sha256(entries)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prizmkit",
-  "version": "1.1.121",
+  "version": "1.1.122",
   "description": "Create a new PrizmKit-powered project with clean initialization — no framework dev files, just what you need.",
   "type": "module",
   "bin": {