diff --git a/docs/tickets/ticket-000035-prg-choice-phi-prg.md b/docs/tickets/ticket-000035-prg-choice-phi-prg.md index e57ecaa..23fede8 100644 --- a/docs/tickets/ticket-000035-prg-choice-phi-prg.md +++ b/docs/tickets/ticket-000035-prg-choice-phi-prg.md @@ -271,12 +271,16 @@ the moment v7 needs it. from any version number. Acceptance-criteria §5 item 1 reads through to "or equivalent location" so the move doesn't invalidate the original criterion. -- ``tests/test_anchor_prg.py`` — 20 tests covering determinism, +- ``tests/test_anchor_prg.py`` — 27 tests covering determinism, range invariants, chi² loose-uniformity sanity, dim_h boundary (1, 16384), seed-bit-flip avalanche, hash-bit-flip avalanche, - input validation (short/long/non-bytes hashes; non-positive / - non-int dim_h), module export shape, and KAT regression. -- ``bench/fixtures/phi-prg/known-answer-tests.jsonl`` — 10 pinned + hand-computed HMAC-SHA-512 first-block formula, prefix-extension + closure, parametrized invalid-input cones, input validation + (short/long/non-bytes hashes; non-positive / non-int dim_h), + module export shape, and KAT regression. (Was 20; +7 from + ``de997f7`` 2026-05-10 pattern backfill per + ``docs/calculator-test-patterns.md``.) +- ``bench/fixtures/phi-prg/known-answer-tests.jsonl`` — 10 pinned KAT vectors covering the placeholder seed (smoke), block-boundary cases (dim_h=16 = exactly one HMAC-SHA-512 block; dim_h=17 = two blocks with truncation), seed/hash one-bit-flip variants, and a diff --git a/docs/warrant-substrate-cookbook.md b/docs/warrant-substrate-cookbook.md index 5c38992..92b0ad1 100644 --- a/docs/warrant-substrate-cookbook.md +++ b/docs/warrant-substrate-cookbook.md @@ -361,7 +361,7 @@ The 92 chains have three quality tiers: *proves* the axiom is a separate, weaker claim. Heuristic-grade. The schema doesn't currently distinguish these tiers. Audit -reviewers walk `citation_aliases` (74 rows live as of 2026-05-10) + read +reviewers walk `citation_aliases` (74 rows live as of 2026-05-10) + read `decision_rationale` fields to grade each chain. If tier distinction becomes load-bearing, add a `tier ∈ {primary, substitute, soft}` column to `derivations`. @@ -434,8 +434,8 @@ arborist warrant-resolve --use-aliases --write ## References - `#000031` — surface-ingest cited textbooks -- `#000041` — citation-aliases table + 74 live rows -- `#000042` — term-aliases table + 13 live rows (5 arithmetic + 4 classical-physics + 4 geometry) +- `#000041` — citation-aliases table + 74 live rows +- `#000042` — term-aliases table + 13 live rows (5 arithmetic + 4 classical-physics + 4 geometry) - `#000038` — Phase 4 content acquisition (still-blocked proprietary candidates: Hilbert-Ackermann 1928, Mendelson, Enderton, Jech, Goldstein, Barendregt, Stanley, Brualdi, Knuth; @@ -566,17 +566,17 @@ than waiting for bench-time STRICT-rate drift to surface it. | domain | LOC tested | test LOC | test/code ratio | |---|---|---|---| -| aliases.py | 512 | 469 (28 tests) | 0.92 | +| aliases.py | 512 | 469 (28 tests) | 0.92 | | warrant_resolver.py | ~800 | ~430 (combined) | 0.54 | -| warrant_chain.py | 89 | 320 (9 tests) | 3.6 | -| t3_bound_calculator.py | 249 | 446 (53 tests) | 1.79 | -| fork_score.py | 298 | 403 (18 tests) | 1.35 | -| weights.py | 73 | 180 (16 tests) | 2.5 | -| pi_star/protocol+registry | 124 | 280 (21 tests) | 2.3 | -| qa/progress.py | 85 | 226 (31 tests) | 2.7 | -| qa/prompts.py | 153 | 207 (20 tests) | 1.35 | -| concepts/extract.py | 288 | 278 (20 tests) | 0.97 | -| textbooks_manifest.py | 236 | 463 (43 tests) | 1.96 | +| warrant_chain.py | 89 | 320 (9 tests) | 3.6 | +| t3_bound_calculator.py | 249 | 446 (53 tests) | 1.79 | +| fork_score.py | 298 | 403 (18 tests) | 1.35 | +| weights.py | 73 | 180 (16 tests) | 2.5 | +| pi_star/protocol+registry | 124 | 280 (21 tests) | 2.3 | +| qa/progress.py | 85 | 226 (31 tests) | 2.7 | +| qa/prompts.py | 153 | 207 (20 tests) | 1.35 | +| concepts/extract.py | 288 | 278 (20 tests) | 0.97 | +| textbooks_manifest.py | 236 | 463 (43 tests) | 1.96 | Pattern: small contract-defining modules (weights, prompts, warrant_chain) get 1.4-3.6× test LOC because they're foundation; diff --git a/tests/test_doc_counts.py b/tests/test_doc_counts.py index 3fee722..84a7570 100644 --- a/tests/test_doc_counts.py +++ b/tests/test_doc_counts.py @@ -21,6 +21,12 @@ Where ``metric`` is one of: live value is ``pytest --collect-only`` count. - ``fixture-rows`` — ``path`` is a JSONL fixture; the live value is the non-blank-non-comment line count. +- ``db-rows`` — ``path`` is either ```` (resolves against + the default shard ``~/.arborist/shards/000.db``) or + ``:
`` (resolves against ``~/.arborist/shards/``). + When the DB or table isn't present (CI or fresh checkout), the + claim is skipped with a logged note rather than failing — claim- + pack and alias counts are operator state, not source-state. GitHub and most markdown renderers strip HTML comments, so readers see only ``N``. The tags are invisible in rendered output but @@ -95,6 +101,62 @@ def _live_fixture_rows(path: str) -> int: ) +_DB_MISSING = -2 +_TABLE_MISSING = -3 +_DB_ERROR = -4 + +# Default location for arborist alias / claim-pack tables. Operator state, +# not source state — absence is not a failure, it's a skip signal. +_DEFAULT_SHARDS_DIR = Path.home() / ".arborist" / "shards" +_DEFAULT_SHARD = _DEFAULT_SHARDS_DIR / "000.db" + + +def _live_db_rows(target: str) -> int: + """Count rows in a SQLite table. + + Target syntax:: + +
# ~/.arborist/shards/000.db (default) + :
# ~/.arborist/shards/ + + Sentinel returns: + _DB_MISSING (-2) DB file not present — caller marks skipped + _TABLE_MISSING (-3) DB present but table absent — caller marks skipped + _DB_ERROR (-4) sqlite3 error — caller marks skipped + N >= 0 live row count + """ + import sqlite3 + + if ":" in target: + shard_name, table = target.split(":", 1) + db = _DEFAULT_SHARDS_DIR / shard_name + else: + db = _DEFAULT_SHARD + table = target + if not db.exists(): + return _DB_MISSING + # Validate table name is a bare identifier — defends against the + # dynamic SQL string interpolation below. Tags are author-controlled + # but this is belt-and-suspenders. + if not re.fullmatch(r"[A-Za-z_][A-Za-z0-9_]*", table): + return _DB_ERROR + try: + c = sqlite3.connect(f"file:{db}?mode=ro", uri=True) + try: + row = c.execute( + f"SELECT COUNT(*) FROM {table}" # noqa: S608 — validated above + ).fetchone() + return int(row[0]) if row else 0 + finally: + c.close() + except sqlite3.OperationalError as exc: + if "no such table" in str(exc).lower(): + return _TABLE_MISSING + return _DB_ERROR + except sqlite3.Error: + return _DB_ERROR + + def _iter_claims() -> Iterator[tuple[Path, int, str, str, int]]: """Yield (doc_path, lineno, metric, target_path, claimed_n).""" for md in sorted(DOCS_DIR.rglob("*.md")): @@ -110,7 +172,7 @@ def _iter_claims() -> Iterator[tuple[Path, int, str, str, int]]: ) -def test_doc_autocount_claims_match_live() -> None: +def test_doc_autocount_claims_match_live(capsys: pytest.CaptureFixture[str]) -> None: """Every ```` claim in ``docs/`` matches live.""" claims = list(_iter_claims()) # Batch the pytest-collect call across every tests:* claim — one @@ -119,25 +181,60 @@ def test_doc_autocount_claims_match_live() -> None: test_counts = _live_test_count_batch(test_paths) drifts: list[str] = [] + skipped: list[str] = [] for doc, lineno, metric, target, claimed in claims: rel = doc.relative_to(REPO_ROOT) if metric == "tests": live = test_counts.get(target, -1) + if live < 0: + drifts.append( + f"{rel}:{lineno} AUTOCOUNT({metric}:{target}) target " + f"missing or uncollectable" + ) + continue elif metric == "fixture-rows": live = _live_fixture_rows(target) + if live < 0: + drifts.append( + f"{rel}:{lineno} AUTOCOUNT({metric}:{target}) target " + f"missing or uncollectable" + ) + continue + elif metric == "db-rows": + live = _live_db_rows(target) + if live == _DB_MISSING: + skipped.append( + f"{rel}:{lineno} db-rows:{target} skipped — " + f"{_DEFAULT_SHARDS_DIR} not present (CI / fresh checkout)" + ) + continue + if live == _TABLE_MISSING: + skipped.append( + f"{rel}:{lineno} db-rows:{target} skipped — table not " + f"present in shard" + ) + continue + if live == _DB_ERROR: + skipped.append( + f"{rel}:{lineno} db-rows:{target} skipped — sqlite " + f"error or invalid table name" + ) + continue else: drifts.append(f"{rel}:{lineno} unknown AUTOCOUNT metric {metric!r}") continue - if live < 0: - drifts.append( - f"{rel}:{lineno} AUTOCOUNT({metric}:{target}) target " - f"missing or uncollectable" - ) - elif live != claimed: + if live != claimed: drifts.append( f"{rel}:{lineno} AUTOCOUNT({metric}:{target}) claims " f"{claimed}, live is {live}" ) + if skipped: + # Print to captured stdout — pytest -v shows it; the suite still + # passes as long as no live count actually drifted. + with capsys.disabled(): + print(f"\n{len(skipped)} db-rows AUTOCOUNT claim(s) skipped:") + for s in skipped: + print(f" {s}") assert not drifts, "Doc count drift detected:\n " + "\n ".join(drifts) @@ -168,7 +265,7 @@ def test_autocount_tags_are_well_formed() -> None: def test_autocount_metric_names_are_documented() -> None: """Fail-closed if a doc uses an undocumented metric.""" - known = {"tests", "fixture-rows"} + known = {"tests", "fixture-rows", "db-rows"} seen: set[str] = set() for _, _, metric, _, _ in _iter_claims(): seen.add(metric)