harness: Issue 검증 증빙을 checkout 밖에 보관

2026-10-08 01:06:16 +00:00
parent e7bcfef532
commit 6ae993887c
8 changed files with 590 additions and 56 deletions
@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 """Create and validate bounded, fail-closed evidence manifests."""
 from __future__ import annotations
-import argparse, datetime as dt, hashlib, json, math, os, platform, re, shutil, subprocess, sys, tempfile, time
+import argparse, datetime as dt, grp, hashlib, json, math, os, platform, pwd, re, shutil, stat, subprocess, sys, tempfile, time
 from pathlib import Path

 HEX40 = re.compile(r"^[0-9a-f]{40}$")
@@ -16,7 +16,7 @@ SECRET_PATTERNS = [
    re.compile(r"\b(?:password|passwd|secret|token)\s*[:=]", re.I),
    re.compile(r"(?:^|\s)--?(?:password|passwd|secret|token)(?:\s+|=)\S+", re.I),
 ]
-SAFE_CHILD_ENV = ("PATH", "HOME", "TMPDIR", "TMP", "TEMP", "LANG", "LC_ALL", "VIRTUAL_ENV", "UV_CACHE_DIR")
+SAFE_CHILD_ENV = ("PATH", "HOME", "TMPDIR", "TMP", "TEMP", "LANG", "LC_ALL", "VIRTUAL_ENV", "UV_CACHE_DIR", "PYTHONDONTWRITEBYTECODE")
 SHELL_NAMES = {"sh", "bash", "dash", "zsh", "ksh", "fish", "cmd", "cmd.exe", "powershell", "powershell.exe", "pwsh", "pwsh.exe"}


@@ -43,7 +43,100 @@ def inside(root, value, *, allow_absolute=False):
    return candidate, candidate.relative_to(root.resolve()).as_posix()


+def safe_entry(path, *, directory=False, mode=None, owned=True, writable_mask=0o022):
+    info = path.lstat()
+    if stat.S_ISLNK(info.st_mode) or not (stat.S_ISDIR(info.st_mode) if directory else stat.S_ISREG(info.st_mode)):
+        raise ValueError("unsafe path entry")
+    if owned and info.st_uid != os.getuid():
+        raise ValueError("path ownership mismatch")
+    actual = stat.S_IMODE(info.st_mode)
+    if mode is not None and actual != mode:
+        raise ValueError("path permission mismatch")
+    if directory and actual & writable_mask:
+        raise ValueError("writable directory boundary")
+
+
+def safe_repositories(path):
+    safe_entry(path, directory=True, writable_mask=0o002)
+    info=path.lstat()
+    if info.st_mode & 0o020:
+        try:
+            group=grp.getgrgid(info.st_gid)
+            members=set(group.gr_mem) | {entry.pw_name for entry in pwd.getpwall() if entry.pw_gid==info.st_gid}
+            member_uids={pwd.getpwnam(name).pw_uid for name in members}
+        except KeyError:
+            raise ValueError("unverifiable repositories group")
+        if member_uids!={os.getuid()}:
+            raise ValueError("repositories group is not exclusive to executing role")
+
+
+def lexical_absolute(value):
+    path = Path(value)
+    if not path.is_absolute() or any(x in ("", ".", "..") for x in str(value).split("/")[1:]):
+        raise ValueError("canonical absolute path required")
+    for ancestor in reversed((path, *path.parents)):
+        if ancestor.is_symlink():
+            raise ValueError("symlink path boundary")
+    return path
+
+
+def artifact_context(args):
+    contract = lexical_absolute(args.contract_path)
+    if contract.name != "repository-cache.md" or contract.parent.name != "operations" or contract.parent.parent.name != "harness":
+        raise ValueError("invalid canonical contract path")
+    harness_root = contract.parents[2]
+    # Read-only harness code parents are not private runtime directories.
+    # Their type/symlink gates and the trusted NFS root follow the contract.
+    safe_entry(harness_root, directory=True, owned=False, writable_mask=0o002)
+    for directory in (contract.parent.parent, contract.parent):
+        safe_entry(directory, directory=True, owned=False, writable_mask=0)
+    safe_entry(contract, owned=False)
+    repo = lexical_absolute(args.repo_root)
+    artifact = lexical_absolute(args.artifact_root)
+    relative = repo.relative_to(harness_root).parts
+    if len(relative) != 6 or relative[0] != "repositories" or relative[3] != "worktrees" or relative[5] != "checkout":
+        raise ValueError("repository is not canonical Issue checkout")
+    owner, repository, issue_name = relative[1], relative[2], relative[4]
+    identifier = re.compile(r"[A-Za-z0-9][A-Za-z0-9_.-]{0,254}")
+    if not identifier.fullmatch(owner) or not identifier.fullmatch(repository) or not re.fullmatch(r"issue-[1-9][0-9]*", issue_name):
+        raise ValueError("invalid Issue identity")
+    if artifact.parent != repo.parent / "verification" or not re.fullmatch(r"[A-Za-z0-9][A-Za-z0-9_.-]{0,127}", artifact.name):
+        raise ValueError("artifact root is not canonical verification run")
+    safe_repositories(harness_root / "repositories")
+    for directory in (repo.parents[3], repo.parents[2], repo.parents[1], repo.parent, artifact.parent, artifact):
+        safe_entry(directory, directory=True, mode=0o700)
+    safe_entry(repo, directory=True)
+    identity = {"owner": owner, "repository": repository, "issue": int(issue_name[6:]), "run_id": artifact.name}
+    return repo, artifact, identity
+
+
+def artifact_file(root, value, *, must_exist=True):
+    if not isinstance(value, str) or not value or any(ord(c) < 32 or ord(c) == 127 for c in value) or "\\" in value:
+        raise ValueError("invalid artifact path")
+    if Path(value).is_absolute() or any(part in ("", ".", "..") for part in value.split("/")):
+        raise ValueError("artifact path must be run-relative")
+    path = root / value
+    for parent in reversed(path.parents):
+        if parent == root or parent.is_relative_to(root):
+            safe_entry(parent, directory=True, mode=0o700)
+    if must_exist:
+        safe_entry(path, mode=0o600)
+    elif path.exists() or path.is_symlink():
+        raise ValueError("completed artifact already exists")
+    return path, value
+
+
 def utc_now(): return dt.datetime.now(dt.timezone.utc).isoformat().replace("+00:00", "Z")
+def source_file(root, value):
+    if not isinstance(value, str) or not value or Path(value).is_absolute() or "\\" in value or any(ord(c) < 32 or ord(c) == 127 for c in value):
+        raise ValueError("invalid source path")
+    if any(part in ("", ".", "..", ".git") for part in value.split("/")):
+        raise ValueError("source path traversal or metadata path")
+    lexical_absolute(str(root) + "/" + value)
+    path, rel = inside(root, value)
+    safe_entry(path)
+    return path, rel
+
 def canonical(obj): return json.dumps(obj, sort_keys=True, separators=(",", ":"), ensure_ascii=False) + "\n"
 def text_bytes(b): return b.decode("utf-8", "replace")

@@ -88,8 +181,9 @@ def run_bounded(argv, root, env, max_bytes):
            proc.kill(); proc.wait()


-def status_paths(root):
-    raw = git(root, "status", "--porcelain=v1", "-z").stdout
+def status_paths(root, *, include_ignored=True):
+    flags=("--ignored=matching", "--untracked-files=all") if include_ignored else ()
+    raw = git(root, "status", "--porcelain=v1", "-z", *flags).stdout
    out=[]
    for entry in raw.split(b"\0"):
        if not entry: continue
@@ -100,8 +194,8 @@ def status_paths(root):
    return out


-def check_clean(root, allowed):
-    bad = [p for p in status_paths(root) if p not in allowed]
+def check_clean(root, allowed, *, include_ignored=True):
+    bad = [p for p in status_paths(root, include_ignored=include_ignored) if p not in allowed]
    if bad: raise ValueError("source tree is not clean: " + ", ".join(bad))


@@ -151,7 +245,8 @@ def atomic_write(path, data):
    try:
        with os.fdopen(fd,"w",encoding="utf-8",newline="") as f:
            f.write(data); f.flush(); os.fsync(f.fileno())
-        os.replace(tmp,path)
+        os.link(tmp,path)
+        os.unlink(tmp)
        dir_fd = os.open(path.parent, os.O_RDONLY)
        try: os.fsync(dir_fd)
        finally: os.close(dir_fd)
@@ -161,7 +256,7 @@ def atomic_write(path, data):


 def run(args):
-    root=Path(args.repo_root).resolve(); plan_path,plan_rel=inside(root,args.plan); out,out_rel=inside(root,args.output)
+    root,artifact,identity=artifact_context(args); plan_path,plan_rel=artifact_file(artifact,args.plan); out,out_rel=artifact_file(artifact,args.output,must_exist=False)
    if plan_path.suffix.lower()!=".json": raise ValueError("plan must be a JSON file")
    if not out.parent.is_dir(): raise ValueError("output parent must already exist")
    plan_bytes=plan_path.read_bytes(); plan_sha256=hashlib.sha256(plan_bytes).hexdigest()
@@ -169,18 +264,17 @@ def run(args):
    for _,argv,_,_,_ in commandspec:
        violation=scan_sensitive("\n".join(argv),secrets,forbidden)
        if violation: raise ValueError("sensitive command rejected before execution: "+violation)
-    check_clean(root,{plan_rel,out_rel})
+    check_clean(root,set())
    source=git(root,"rev-parse","HEAD").stdout.decode().strip()
    if not HEX40.fullmatch(source): raise ValueError("source revision is not full SHA")
    files=[]
    for item in plan.get("hash_paths",[]):
-        path,rel=inside(root,item)
+        path,rel=source_file(root,item)
        if not path.is_file() or path.is_symlink(): raise ValueError(f"hash path is not a regular file: {item}")
        oid,sha=tracked_blob(root,source,rel)
        if hashlib.sha256(path.read_bytes()).hexdigest()!=sha: raise ValueError(f"source hash mismatch: {rel}")
        files.append({"path":rel,"sha256":sha,"blob_oid":oid})
-    bound_paths={record["path"] for record in files}
-    if plan_rel==out_rel or plan_rel in bound_paths or out_rel in bound_paths: raise ValueError("plan/output paths must not overlap bound source paths")
+    if plan_rel==out_rel: raise ValueError("plan/output paths must not overlap")
    child_env={name:os.environ[name] for name in child_names if name in os.environ}
    result_commands=[]; claim_map={}
    for i,(spec,argv,expected,maxb,claim_ids) in enumerate(commandspec):
@@ -198,7 +292,7 @@ def run(args):
                f"/commands/{i}/started_at_utc",
                f"/commands/{i}/finished_at_utc",
            ]
-    env={k:None for k in env_keys}
+    env: dict[str, str | None]={k:None for k in env_keys}
    if "os" in env: env["os"]=platform.system()
    if "kernel" in env: env["kernel"]=platform.release()
    if "architecture" in env: env["architecture"]=platform.machine()
@@ -208,14 +302,18 @@ def run(args):
        env["uv"]=text_bytes((p.stdout+p.stderr).strip()) if p and p.returncode==0 else None
    # Commands are evidence producers, not trusted source mutators. Recheck the
    # tree and every bound blob before persisting their claims.
-    check_clean(root,{plan_rel,out_rel})
+    if artifact_context(args)!=(root,artifact,identity): raise ValueError("artifact boundary changed during verification")
+    artifact_file(artifact,args.plan)
+    artifact_file(artifact,args.output,must_exist=False)
+    check_clean(root,set())
    if git(root,"rev-parse","HEAD").stdout.decode().strip()!=source: raise ValueError("HEAD changed during verification")
    if not plan_path.is_file() or hashlib.sha256(plan_path.read_bytes()).hexdigest()!=plan_sha256: raise ValueError("plan changed during verification")
    for record in files:
-        if hashlib.sha256((root/record["path"]).read_bytes()).hexdigest()!=record["sha256"]:
+        path,_=source_file(root,record["path"])
+        if hashlib.sha256(path.read_bytes()).hexdigest()!=record["sha256"]:
            raise ValueError(f"source changed during verification: {record['path']}")
    success=all(c["exit_code"]==c["expected_exit_code"] for c in result_commands)
-    manifest={"schema":"evidence-manifest/v1","source_revision":source,"source_tree_clean":True,"excluded_paths":[plan_rel,out_rel],"plan":{"path":plan_rel,"sha256":plan_sha256},"generated_at":utc_now(),"environment":env,"commands":result_commands,"files":files,"claims":claim_map,"redaction":{"checked":True,"violations":[]},"limitations":plan.get("limitations",[]),"result":"success" if success else "failure"}
+    manifest={"schema":"evidence-manifest/v2","source_revision":source,"source_tree_clean":True,"artifact":identity,"plan":{"path":plan_rel,"sha256":plan_sha256},"generated_at":utc_now(),"environment":env,"commands":result_commands,"files":files,"claims":claim_map,"redaction":{"checked":True,"violations":[]},"limitations":plan.get("limitations",[]),"result":"success" if success else "failure"}
    atomic_write(out,canonical(manifest))
    return 0 if success else 1

@@ -232,25 +330,40 @@ def pointer(obj,ptr):


 def validate(args):
-    root=Path(args.repo_root).resolve(); mp,mp_rel=inside(root,args.manifest); raw=mp.read_text(encoding="utf-8"); obj=json.loads(raw)
+    legacy = args.op == "validate-legacy"
+    identity = None
+    if legacy:
+        root=Path(args.repo_root).resolve(); artifact=root; mp,mp_rel=inside(root,args.manifest)
+    else:
+        root,artifact,identity=artifact_context(args); mp,mp_rel=artifact_file(artifact,args.manifest)
+    raw=mp.read_text(encoding="utf-8"); obj=json.loads(raw)
    if canonical(obj)!=raw: raise ValueError("manifest is not canonical JSON")
-    required={"schema","source_revision","source_tree_clean","excluded_paths","plan","generated_at","commands","files","claims","redaction","environment","limitations","result"}
-    if set(obj)!=required or obj["schema"]!="evidence-manifest/v1" or obj["result"] not in ("success","failure"): raise ValueError("invalid manifest structure")
-    if obj["source_tree_clean"] is not True or not isinstance(obj["excluded_paths"],list): raise ValueError("source tree was not clean")
+    required={"schema","source_revision","source_tree_clean","plan","generated_at","commands","files","claims","redaction","environment","limitations","result"} | ({"excluded_paths"} if legacy else {"artifact"})
+    if set(obj)!=required or obj["schema"]!=("evidence-manifest/v1" if legacy else "evidence-manifest/v2") or obj["result"] not in ("success","failure"): raise ValueError("invalid manifest structure")
+    if obj["source_tree_clean"] is not True: raise ValueError("source tree was not clean")
    if not isinstance(obj["generated_at"],str) or not ISO.fullmatch(obj["generated_at"]): raise ValueError("invalid generated timestamp")
-    if len(obj["excluded_paths"])!=2 or len(set(obj["excluded_paths"]))!=2 or any(not isinstance(x,str) for x in obj["excluded_paths"]) or obj["excluded_paths"][1]!=mp_rel: raise ValueError("invalid excluded paths")
-    for excluded in obj["excluded_paths"]: inside(root,excluded)
-    if not isinstance(obj["plan"],dict) or set(obj["plan"])!={"path","sha256"} or obj["plan"]["path"]!=obj["excluded_paths"][0] or not isinstance(obj["plan"]["sha256"],str) or not HEX64.fullmatch(obj["plan"]["sha256"]): raise ValueError("invalid plan binding")
-    plan_path,plan_rel=inside(root,obj["plan"]["path"])
+    if legacy:
+        if not isinstance(obj["excluded_paths"],list) or len(obj["excluded_paths"])!=2 or len(set(obj["excluded_paths"]))!=2 or any(not isinstance(x,str) for x in obj["excluded_paths"]) or obj["excluded_paths"][1]!=mp_rel: raise ValueError("invalid excluded paths")
+        for excluded in obj["excluded_paths"]: inside(root,excluded)
+    elif not isinstance(obj["artifact"],dict) or obj["artifact"] != identity or type(obj["artifact"].get("issue")) is not int:
+        raise ValueError("artifact identity mismatch")
+    if not isinstance(obj["plan"],dict) or set(obj["plan"])!={"path","sha256"} or not isinstance(obj["plan"]["sha256"],str) or not HEX64.fullmatch(obj["plan"]["sha256"]): raise ValueError("invalid plan binding")
+    if legacy:
+        if obj["plan"]["path"]!=obj["excluded_paths"][0]: raise ValueError("invalid plan binding")
+        plan_path,plan_rel=inside(root,obj["plan"]["path"])
+    else:
+        plan_path,plan_rel=artifact_file(artifact,obj["plan"]["path"])
+        if plan_rel==mp_rel: raise ValueError("plan and manifest overlap")
    if plan_path.suffix.lower()!=".json" or not plan_path.is_file() or plan_path.is_symlink(): raise ValueError("bound plan is unavailable")
    plan_bytes=plan_path.read_bytes()
    if hashlib.sha256(plan_bytes).hexdigest()!=obj["plan"]["sha256"]: raise ValueError("plan hash mismatch")
    plan=json.loads(plan_bytes.decode("utf-8")); plan_secrets,plan_forbidden,requested_env,_,planned_commands=plan_checks(plan,root)
-    check_clean(root,set(obj["excluded_paths"]))
+    check_clean(root,set(obj["excluded_paths"]) if legacy else set(),include_ignored=not legacy)
    src=obj["source_revision"]
    if not isinstance(src,str) or not HEX40.fullmatch(src): raise ValueError("invalid source revision")
    if git(root,"cat-file","-e",src,check=False).returncode: raise ValueError("missing source revision")
    head=git(root,"rev-parse","HEAD").stdout.decode().strip()
+    if not legacy and src!=head: raise ValueError("source revision is not current HEAD")
    if git(root,"merge-base","--is-ancestor",src,head,check=False).returncode: raise ValueError("source is not ancestor")
    if not isinstance(obj["environment"],dict) or not obj["environment"] or any(not isinstance(k,str) or k not in SAFE_ENV or not (isinstance(v,str) or v is None) for k,v in obj["environment"].items()): raise ValueError("invalid environment")
    if set(obj["environment"])!=set(requested_env): raise ValueError("environment does not match plan")
@@ -262,16 +375,17 @@ def validate(args):
        for k,v in obj["claims"].items()
    ): raise ValueError("invalid claims")
    if not isinstance(obj["files"],list) or not obj["files"]: raise ValueError("files must be nonempty")
-    planned_paths=[inside(root,item)[1] for item in plan.get("hash_paths",[])]
+    path_reader=inside if legacy else source_file
+    planned_paths=[path_reader(root,item)[1] for item in plan.get("hash_paths",[])]
    if [f.get("path") if isinstance(f,dict) else None for f in obj["files"]]!=planned_paths: raise ValueError("file records do not match plan")
    claim_seen=set()
    for f in obj["files"]:
        if not isinstance(f,dict) or set(f)!={"path","sha256","blob_oid"}: raise ValueError("invalid file record")
-        _,rel=inside(root,f["path"]); path=root/rel
+        path,rel=path_reader(root,f["path"])
        if not HEX64.fullmatch(f["sha256"]) or not HEX40.fullmatch(f["blob_oid"]): raise ValueError("invalid file identity")
        oid,sha=tracked_blob(root,src,rel)
        if oid!=f["blob_oid"] or sha!=f["sha256"] or hashlib.sha256(path.read_bytes()).hexdigest()!=sha: raise ValueError("file hash mismatch")
-    if any(f["path"] in set(obj["excluded_paths"]) for f in obj["files"]): raise ValueError("evidence paths overlap bound source paths")
+    if legacy and any(f["path"] in set(obj["excluded_paths"]) for f in obj["files"]): raise ValueError("evidence paths overlap bound source paths")
    if not isinstance(obj["commands"],list) or not obj["commands"] or len(obj["commands"])!=len(planned_commands): raise ValueError("commands do not match plan")
    command_ids=set()
    for i,c in enumerate(obj["commands"]):
@@ -311,8 +425,14 @@ def validate(args):

 def main():
    p=argparse.ArgumentParser(); sub=p.add_subparsers(dest="op",required=True)
-    r=sub.add_parser("run"); r.add_argument("--repo-root",required=True); r.add_argument("--plan",required=True); r.add_argument("--output",required=True)
-    v=sub.add_parser("validate"); v.add_argument("--repo-root",required=True); v.add_argument("--manifest",required=True)
+    r=sub.add_parser("run"); r.add_argument("--plan",required=True); r.add_argument("--output",required=True)
+    v=sub.add_parser("validate"); v.add_argument("--manifest",required=True)
+    for parser in (r,v):
+        parser.add_argument("--contract-path",required=True)
+        parser.add_argument("--repo-root",required=True)
+        parser.add_argument("--artifact-root",required=True)
+    old=sub.add_parser("validate-legacy",help="read-only archived v1 compatibility; not a new publication gate")
+    old.add_argument("--repo-root",required=True); old.add_argument("--manifest",required=True)
    a=p.parse_args()
    try: return run(a) if a.op=="run" else validate(a)
    except (OSError, ValueError, TypeError, KeyError, AttributeError, UnicodeError, json.JSONDecodeError, re.error, subprocess.SubprocessError) as e: return die(e)