mirror of
https://github.com/harvard-edge/cs249r_book.git
synced 2026-11-14 18:24:37 -06:00
Vijay Janapa Reddi
f1ffe5b6fa
interviews/ held StaffML and nothing else, so the directory now carries the product's name. Three names inside it repeated that prefix, and now line up with vault/, vault-cli/, and paper/: interviews/staffml/ -> staffml/app/ interviews/staffml-vault-worker/ -> staffml/vault-worker/ interviews/staffml-vault-types/ -> staffml/vault-types/ Every repository path moved with it: workflow paths: triggers and variable fallbacks, pre-commit hooks, .gitignore, contributor tooling, vault-cli path joins, the app's tsconfig mapping to the shared types, and the docs. Left alone on purpose: - the published /interviews/ redirect to /staffml/ and the gh-pages subsite lists that protect it; those are URLs, not repository paths - package and worker names (staffml-vault-worker, @staffml/vault-types) and the vitest job name, which branch protection may key on - question YAMLs and generated track JSON, which are content-addressed. Three questions carry an older corruption, "recall @interviews/vault/ questions/...", that predates this change - the applied D1 migration 0001 and the vault CHANGELOG, which are history codegen-hashes.txt is re-recorded; the three pinned artifacts changed only in path strings. vault-cli: 97 passed, codegen --check clean. interviewer.py's __main__ loader was one parent short and pointed at a corpus.json that never existed; it now resolves staffml/app/src/data/ corpus.json. tools/validate_playbook.py and generate_interview_flashcard.py still expect per-track directories that no longer exist; they point at the new root but remain dead. The GitHub repository variables STAFFML_ROOT, VAULT_DIR, and VAULT_CLI_DIR still name the old paths and must change when this reaches origin.
124 lines
4.0 KiB
Python
124 lines
4.0 KiB
Python
"""Tests for the canonical hashing layer.
|
|
|
|
Key invariants:
|
|
- Same semantic content hashes identically regardless of YAML key order.
|
|
- Whitelist fields drive the hash; metadata doesn't.
|
|
- Merkle construction stable across re-ordering of leaves.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from vault_cli.hashing import CANON_VERSION, content_hash, release_hash
|
|
|
|
|
|
def _base_question() -> dict:
|
|
return {
|
|
"id": "global-0000",
|
|
"title": "Example",
|
|
"topic": "kv-cache-management",
|
|
"chain": {"id": "global-chain-000", "position": 1},
|
|
"status": "published",
|
|
"scenario": "Explain KV-cache.",
|
|
"details": {"realistic_solution": "Paged attention."},
|
|
"tags": ["a", "b"],
|
|
"provenance": "human",
|
|
}
|
|
|
|
|
|
def test_content_hash_stable_across_key_reorder() -> None:
|
|
"""Soumith M-NEW-4 / R3-F-4: top-level AND nested-dict hashing must be
|
|
key-order-invariant.
|
|
|
|
The prior version of this test only reordered top-level keys and collapsed
|
|
``details`` to a single-key dict, so it didn't actually exercise the
|
|
nested-dict claim. Extended to also reorder ``details`` and ``chain``.
|
|
"""
|
|
q1 = _base_question()
|
|
# Reorder top-level keys AND nested dicts.
|
|
q2 = {k: q1[k] for k in reversed(list(q1.keys()))}
|
|
q2["details"] = {
|
|
"napkin_math": "X", # add a second nested key so the order matters
|
|
"common_mistake": "Y",
|
|
"realistic_solution": q1["details"]["realistic_solution"],
|
|
}
|
|
q2["chain"] = {"position": q1["chain"]["position"], "id": q1["chain"]["id"]}
|
|
# Mirror on q1 to keep the semantic payload identical.
|
|
q1 = dict(q1)
|
|
q1["details"] = dict(q2["details"])
|
|
# Now q1 and q2 share the same semantic fields; only key insertion order differs.
|
|
assert content_hash(q1) == content_hash(q2)
|
|
|
|
|
|
def test_content_hash_nested_dict_order_invariance() -> None:
|
|
"""Explicit nested-order test with a 3-key ``details`` — must hash identical
|
|
regardless of ``details`` key insertion order.
|
|
"""
|
|
base = _base_question()
|
|
base["details"] = {
|
|
"realistic_solution": "ANS",
|
|
"common_mistake": "WRONG",
|
|
"napkin_math": "2 + 2 = 4",
|
|
}
|
|
reordered = dict(base)
|
|
reordered["details"] = {
|
|
"napkin_math": "2 + 2 = 4",
|
|
"realistic_solution": "ANS",
|
|
"common_mistake": "WRONG",
|
|
}
|
|
assert content_hash(base) == content_hash(reordered)
|
|
|
|
|
|
def test_content_hash_excludes_metadata() -> None:
|
|
"""Hash must NOT change when last_modified or file_path changes."""
|
|
q1 = _base_question()
|
|
q2 = dict(q1)
|
|
q2["last_modified"] = "2050-01-01T00:00:00Z"
|
|
q2["file_path"] = "/tmp/foo.yaml"
|
|
q2["authors"] = ["someone"]
|
|
assert content_hash(q1) == content_hash(q2)
|
|
|
|
|
|
def test_content_hash_changes_with_semantic_edit() -> None:
|
|
"""Hash MUST change when scenario changes."""
|
|
q1 = _base_question()
|
|
q2 = dict(q1)
|
|
q2["scenario"] = "An edited scenario."
|
|
assert content_hash(q1) != content_hash(q2)
|
|
|
|
|
|
def test_release_hash_includes_canon_and_policy_leaves() -> None:
|
|
"""Chip N-H5: release_hash must bind canon version and policy."""
|
|
leaves = [("a", "1" * 64), ("b", "2" * 64)]
|
|
base = release_hash(
|
|
per_question=leaves,
|
|
taxonomy_hash="t" * 64,
|
|
chains_hash="c" * 64,
|
|
zones_hash="z" * 64,
|
|
policy_hash="p" * 64,
|
|
)
|
|
# Different policy_hash → different release_hash
|
|
different_policy = release_hash(
|
|
per_question=leaves,
|
|
taxonomy_hash="t" * 64,
|
|
chains_hash="c" * 64,
|
|
zones_hash="z" * 64,
|
|
policy_hash="P" * 64,
|
|
)
|
|
assert base != different_policy
|
|
|
|
# Different canon_version → different release_hash
|
|
different_canon = release_hash(
|
|
per_question=leaves,
|
|
taxonomy_hash="t" * 64,
|
|
chains_hash="c" * 64,
|
|
zones_hash="z" * 64,
|
|
policy_hash="p" * 64,
|
|
canon_version=999,
|
|
)
|
|
assert base != different_canon
|
|
|
|
|
|
def test_canon_version_is_pinned() -> None:
|
|
assert isinstance(CANON_VERSION, int)
|
|
assert CANON_VERSION >= 1
|