[CI] validate retained video sweep evidence / [CI] 校验保留的视频扫描证据

.github/workflows/README.md

@@ -287,11 +287,33 @@ Keep the command and required run ID on one line. This pins an eligible complete
 `run-sweep.yml` PR run, including failed or cancelled runs with usable results. The
 run may come from any PR; its commit need not be part of this one.
 
+Native video discovery requires both `video-sweep-manifest` and a bundle named
+`h3-results-<run>-<attempt>-<64-hex recipe fingerprint>`. Discovery only identifies
+candidate artifacts. Reuse authorization, automatic source selection, merge selection and
+staging all download the retained video files and validate them against the trusted
+run ID, attempt and head before admission, including mixed LLM/video runs. The same
+check is available offline:
+
+```bash
+python -m infx.results.video_artifacts --artifacts-dir artifacts \
+  --run-id "$RUN_ID" --run-attempt "$RUN_ATTEMPT" --head-sha "$HEAD_SHA"
+```
+
+The validator requires the full selected video matrix, frozen measured request
+population, native power verification and matching media/file hashes. Partial runs,
+missing cells and stale attempts fail. The generic `validate_reusable_sweep_artifacts`
+command also checks native video when its selected-matrix manifest is present.
+Executed checkout identity remains separate from the workflow's PR head. Retained
+artifact validation does not rerun media decoding or establish perceptual quality.
+Each downloaded ZIP is limited to 256 MiB compressed and 1 GiB expanded; larger
+bundles fail closed.
+
 The legacy `/reuse-sweep-run <run_id>` remains equivalent. Bare `/reuse-sweep-run`
 selects the latest successful eligible run automatically; bare `/use` is rejected.
 Both names share authorization, validation, and reactions.
 
-Source validation checks identity and artifacts, not full-matrix coverage.
+For LLM and agentic results, source validation checks identity and artifacts, not
+full-matrix coverage. Native video additionally requires its complete selected matrix.
 Acceptance does not
 certify a green full sweep. Verify coverage and pin the run ID when a full sweep
 is required by the review process.

inferencex-e2e/infx/klaud/github.py

@@ -3,9 +3,12 @@
 from __future__ import annotations
 
 import base64
+import hashlib
 import io
 import json
+import os
 import re
+import stat
 import subprocess
 import time
 import zipfile
@@ -154,35 +157,69 @@ def file_at(repository: str, head: str, path: str) -> bytes:
     return base64.b64decode(result["content"])
 
 
-def download_json(repository: str, artifact: dict, destination: Path) -> None:
-    """Write the JSON members of ``artifact`` under ``destination``, raising VerificationError.
-
-    Archives over 256 MiB, unsafe paths and duplicates are rejected. Artifact code never runs.
-    """
+def download_files(
+    repository: str,
+    artifact: dict,
+    destination: Path,
+    *,
+    token: str | None = None,
+    json_only: bool = False,
+) -> None:
+    """Read bounded artifact files without trusting ZIP paths or executing content."""
     limit = 256 * 1024 * 1024
     if artifact["expired"] or not 0 < artifact["size_in_bytes"] <= limit:
         raise VerificationError("Artifact unavailable or too large")
     archive = subprocess.check_output(
-        [
-            "gh",
-            "api",
-            f"repos/{repository}/actions/artifacts/{int(artifact['id'])}/zip",
-        ],
+        ["gh", "api", f"repos/{repository}/actions/artifacts/{int(artifact['id'])}/zip"],
+        env={**os.environ, "GH_TOKEN": token} if token is not None else None,
         timeout=60,
     )
+    if len(archive) > limit:
+        raise VerificationError("Artifact archive too large")
+    if artifact.get("digest") and artifact["digest"] != (
+        "sha256:" + hashlib.sha256(archive).hexdigest()
+    ):
+        raise VerificationError("Artifact digest mismatch")
     try:
         with zipfile.ZipFile(io.BytesIO(archive)) as source:
-            members = [item for item in source.infolist() if item.filename.endswith(".json")]
-            if not members or sum(item.file_size for item in members) > limit:
-                raise VerificationError("Invalid artifact JSON size")
+            members = [
+                item
+                for item in source.infolist()
+                if not item.is_dir() and (not json_only or item.filename.endswith(".json"))
+            ]
+            expanded_limit = limit if json_only else 4 * limit
+            if (
+                not members
+                or len(members) > 4000
+                or sum(item.file_size for item in members) > expanded_limit
+            ):
+                raise VerificationError("Invalid artifact expanded size")
+            paths = set()
             for member in members:
                 path = PurePosixPath(member.filename)
-                if path.is_absolute() or ".." in path.parts or "\\" in member.filename:
-                    raise VerificationError("Invalid artifact path")
-                target = destination.joinpath(*path.parts)
+                mode = stat.S_IFMT(member.external_attr >> 16)
+                if (
+                    path.is_absolute()
+                    or ".." in path.parts
+                    or "\\" in member.filename
+                    or not path.parts
+                    or mode not in {0, stat.S_IFREG}
+                    or path in paths
+                    or any(parent in paths for parent in path.parents)
+                    or any(path in previous.parents for previous in paths)
+                ):
+                    raise VerificationError("Invalid or duplicate artifact path")
+                paths.add(path)
+            for member in members:
+                target = destination.joinpath(*PurePosixPath(member.filename).parts)
                 if target.exists():
                     raise VerificationError("Duplicate artifact path")
                 target.parent.mkdir(parents=True, exist_ok=True)
                 target.write_bytes(source.read(member))
     except zipfile.BadZipFile as error:
         raise VerificationError("Invalid artifact archive") from error
+
+
+def download_json(repository: str, artifact: dict, destination: Path) -> None:
+    """Read bounded JSON only; never execute artifact code."""
+    download_files(repository, artifact, destination, json_only=True)

inferencex-e2e/infx/matrix/revision.py

@@ -38,12 +38,14 @@ def module_path(self) -> str:
 FINGERPRINTER = "infx.matrix.fingerprint"
 CONFIG_DIRS = ("configs", ".github/configs")
 NESTED_PROJECT = "inferencex-e2e/"
+VIDEO_SPECS = "experimental/video-generation/specs"
 SNAPSHOT_PATHS = (
     "infx",
     "utils/matrix_logic",
     *CONFIG_DIRS,
     "benchmarks/single_node/srt-slurm-recipes",
     "benchmarks/multi_node/srt-slurm-recipes",
+    VIDEO_SPECS,
 )
 INHERITED_ENV = ("PATH", "HOME", "LANG", "TMPDIR")
 _FORK_REPLY = "infx-fork-exit "
@@ -328,11 +330,12 @@ def snapshot(ref: str) -> Iterator[Revision]:
     for entry in listing.split(b"\0")[:-1]:
         metadata, path = entry.split(b"\t", 1)
         objects[os.fsdecode(path)] = metadata.split()[2]
-    if any(path.startswith(NESTED_PROJECT) for path in objects):
+    nested = any(path.startswith(NESTED_PROJECT) for path in objects)
+    if nested:
         objects = {
-            path.removeprefix(NESTED_PROJECT): oid
+            path: oid
             for path, oid in objects.items()
-            if path.startswith(NESTED_PROJECT)
+            if path.startswith((NESTED_PROJECT, VIDEO_SPECS + "/"))
         }
     blobs = io.BytesIO(
         subprocess.run(
@@ -354,7 +357,7 @@ def snapshot(ref: str) -> Iterator[Revision]:
             destination = Path(temp_dir, path)
             destination.parent.mkdir(parents=True, exist_ok=True)
             destination.write_bytes(content)
-        revision = Revision(Path(temp_dir))
+        revision = Revision(Path(temp_dir) / NESTED_PROJECT if nested else Path(temp_dir))
         inputs = [*revision.master_configs, revision.runner_config]
         if missing := [
             Path(path).relative_to(revision.root).as_posix()