gensokyo-dev
aa51e43439
Use compact MCP input advertisements by default while preserving explicit full, canonical validation, output contracts and complete Evidence. Require an explicit selected catalog for runtime identity and honor both profiles in CLI status. Real ripgrep/Zellij SDK tasks, independent ELF oracle, actual client trials, profile parity workflows and CI are recorded in experiments/analysis-efficiency/mcp-input-catalog.md. SDK token estimates improve; actual Codex token savings and general latency/memory gains are not established. Refs #5861 BREAKING CHANGE: MCP input advertisements default to compact. Set REA_MCP_INPUT_SCHEMA_PROFILE=full for complete advertised guidance and nested constraints.
55 lines
2.4 KiB
Python
55 lines
2.4 KiB
Python
"""Independent ELF64 little-endian / zlib oracle for the pinned Alpine corpus."""
|
|
import argparse
|
|
import hashlib
|
|
import json
|
|
from pathlib import Path
|
|
import struct
|
|
import zlib
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(description=__doc__)
|
|
parser.add_argument("artifact", type=Path)
|
|
parser.add_argument("output", type=Path)
|
|
args = parser.parse_args()
|
|
assert args.artifact.stat().st_size <= 256 * 1024 ** 2
|
|
binary = args.artifact.read_bytes()
|
|
assert binary[:6] == b"\x7fELF\x02\x01"
|
|
table = struct.unpack_from("<Q", binary, 40)[0]
|
|
stride, count, strings_index = struct.unpack_from("<HHH", binary, 58)
|
|
assert stride == 64 and 0 < count < 65535 and strings_index < count
|
|
sections = [struct.unpack_from("<IIQQQQIIQQ", binary, table + index * stride)
|
|
for index in range(count)]
|
|
string_row = sections[strings_index]
|
|
names = binary[string_row[4]:string_row[4] + string_row[5]]
|
|
matches = [row for row in sections
|
|
if names[row[0]:names.index(b"\0", row[0])] == b".dep-v0"]
|
|
assert len(matches) == 1
|
|
row = matches[0]
|
|
assert row[5] <= 1024 ** 2
|
|
compressed = binary[row[4]:row[4] + row[5]]
|
|
decoder = zlib.decompressobj()
|
|
decoded = decoder.decompress(compressed, 8 * 1024 ** 2 + 1)
|
|
assert len(decoded) <= 8 * 1024 ** 2 and decoder.eof
|
|
assert not decoder.unconsumed_tail and not decoder.unused_data
|
|
raw = json.loads(decoded)
|
|
packages = [{"name": item["name"], "version": item["version"],
|
|
"source": item.get("source"), "kind": item.get("kind"),
|
|
"dependencies": item.get("dependencies", []), "root": item.get("root", False)}
|
|
for item in raw["packages"]]
|
|
result = {
|
|
"artifact_sha256": hashlib.sha256(binary).hexdigest(),
|
|
"section_sha256": hashlib.sha256(compressed).hexdigest(),
|
|
"json_sha256": hashlib.sha256(decoded).hexdigest(),
|
|
"packages": packages,
|
|
"edges": [{"from_index": index, "to_index": destination}
|
|
for index, item in enumerate(packages) for destination in item["dependencies"]],
|
|
"serde_rows": [{"index": index, **{key: item[key] for key in ["name", "version", "kind"]}}
|
|
for index, item in enumerate(packages) if item["name"] == "serde"],
|
|
}
|
|
args.output.write_text(json.dumps(result, indent=2) + "\n")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|