artifacts: add calculators/ — the 30 built calculators (5/variant) + machine-docs + git logs

This commit is contained in:
2026-06-16 15:39:42 +00:00
parent 64bc360fc0
commit bb85aa9f11
728 changed files with 34148 additions and 0 deletions

View File

@ -0,0 +1,3 @@
__pycache__/
*.pyc
*.pyo

View File

@ -0,0 +1,13 @@
# git history (claim/review handshake), from the run's shared bare repo
ada6d2e status(review): write ## DONE — Adversary PASS, no findings, all DoD verified
671f482 review(all): PASS — comprehensive cold-verify complete, 53/53, no findings
f74f99d claim(all): review phase — full build ready for Adversary cold-verify
0d1bc87 status(eval): record commit sha 6b5f4d2, mark ## DONE — self-certified
6b5f4d2 feat(eval): implement evaluator + CLI — all D1-D5 green, 53 tests pass
7a4ce2e review(init): Adversary initializes REVIEW-eval.md — awaiting Builder
6bd02d3 feat(parse): implement recursive-descent parser — all D1-D6 green
ebe2937 review(init): Adversary initializes REVIEW-parse.md — awaiting Builder
4e1d555 chore: add .gitignore, remove cached pycache
f53b180 feat(lex): implement lexer with tokenize(), Token, LexError — all D1-D4 green
7e96ff7 review(init): Adversary initializes REVIEW-lex.md — awaiting Builder
1dbcd03 chore: seed

View File

@ -0,0 +1 @@
# calc work repo

View File

@ -0,0 +1 @@
original path: /tmp/ao-campaign-zpQzu1/builder-adversary-deferred/r1

View File

@ -0,0 +1,34 @@
#!/usr/bin/env python
"""calc.py — command-line calculator.
Formatting rule (D3): whole-valued floats are printed as integers
(4/2 → 2), non-whole floats are printed as-is (7/2 → 3.5).
"""
import sys
from calc.lexer import tokenize, LexError
from calc.parser import parse, ParseError
from calc.evaluator import evaluate, EvalError
def _fmt(value: int | float) -> str:
if isinstance(value, float) and value.is_integer():
return str(int(value))
return str(value)
def main() -> None:
if len(sys.argv) != 2:
print("usage: calc.py <expression>", file=sys.stderr)
sys.exit(1)
expr = sys.argv[1]
try:
result = evaluate(parse(tokenize(expr)))
print(_fmt(result))
except (LexError, ParseError, EvalError) as e:
print(f"error: {e}", file=sys.stderr)
sys.exit(1)
if __name__ == "__main__":
main()

View File

@ -0,0 +1,36 @@
from __future__ import annotations
from calc.parser import Node, Num, BinOp, Unary
class EvalError(Exception):
pass
def evaluate(node: Node) -> int | float:
"""Walk an AST and return its numeric value.
Uses true division (7/2 → 3.5). Division by zero raises EvalError.
Integer operands with integer-only operations (+ - *) return int;
any division always returns float. The CLI formats whole floats as int.
"""
if isinstance(node, Num):
return node.value
if isinstance(node, Unary):
if node.op == '-':
return -evaluate(node.operand)
raise EvalError(f"unknown unary operator: {node.op!r}")
if isinstance(node, BinOp):
left = evaluate(node.left)
right = evaluate(node.right)
if node.op == '+':
return left + right
if node.op == '-':
return left - right
if node.op == '*':
return left * right
if node.op == '/':
if right == 0:
raise EvalError("division by zero")
return left / right
raise EvalError(f"unknown binary operator: {node.op!r}")
raise EvalError(f"unknown node type: {type(node)!r}")

View File

@ -0,0 +1,54 @@
from __future__ import annotations
from dataclasses import dataclass
from typing import Union
class LexError(Exception):
pass
@dataclass
class Token:
kind: str
value: Union[int, float, str, None]
def tokenize(src: str) -> list[Token]:
tokens: list[Token] = []
i = 0
n = len(src)
while i < n:
ch = src[i]
if ch in ' \t\r\n':
i += 1
continue
if ch.isdigit() or ch == '.':
j = i
while j < n and src[j].isdigit():
j += 1
if j < n and src[j] == '.':
j += 1
while j < n and src[j].isdigit():
j += 1
tokens.append(Token('NUMBER', float(src[i:j])))
else:
tokens.append(Token('NUMBER', int(src[i:j])))
i = j
continue
if ch == '+':
tokens.append(Token('PLUS', '+'))
elif ch == '-':
tokens.append(Token('MINUS', '-'))
elif ch == '*':
tokens.append(Token('STAR', '*'))
elif ch == '/':
tokens.append(Token('SLASH', '/'))
elif ch == '(':
tokens.append(Token('LPAREN', '('))
elif ch == ')':
tokens.append(Token('RPAREN', ')'))
else:
raise LexError(f"unexpected character {ch!r} at position {i}")
i += 1
tokens.append(Token('EOF', None))
return tokens

View File

@ -0,0 +1,118 @@
from __future__ import annotations
from dataclasses import dataclass
from typing import List, Union
from calc.lexer import Token
class ParseError(Exception):
pass
@dataclass
class Num:
value: Union[int, float]
def __repr__(self) -> str:
return f"Num({self.value!r})"
@dataclass
class BinOp:
op: str
left: "Node"
right: "Node"
def __repr__(self) -> str:
return f"BinOp({self.op!r}, {self.left!r}, {self.right!r})"
@dataclass
class Unary:
op: str
operand: "Node"
def __repr__(self) -> str:
return f"Unary({self.op!r}, {self.operand!r})"
Node = Union[Num, BinOp, Unary]
class _Parser:
def __init__(self, tokens: List[Token]) -> None:
self._tokens = tokens
self._pos = 0
def _peek(self) -> Token:
return self._tokens[self._pos]
def _consume(self) -> Token:
tok = self._tokens[self._pos]
self._pos += 1
return tok
def _expect(self, kind: str) -> Token:
tok = self._peek()
if tok.kind != kind:
raise ParseError(
f"expected {kind}, got {tok.kind!r} ({tok.value!r})"
)
return self._consume()
def parse(self) -> Node:
if self._peek().kind == "EOF":
raise ParseError("empty input")
node = self._expr()
if self._peek().kind != "EOF":
tok = self._peek()
raise ParseError(
f"unexpected token {tok.kind!r} ({tok.value!r}) after expression"
)
return node
def _expr(self) -> Node:
node = self._term()
while self._peek().kind in ("PLUS", "MINUS"):
op = self._consume().value
right = self._term()
node = BinOp(op, node, right)
return node
def _term(self) -> Node:
node = self._unary()
while self._peek().kind in ("STAR", "SLASH"):
op = self._consume().value
right = self._unary()
node = BinOp(op, node, right)
return node
def _unary(self) -> Node:
if self._peek().kind == "MINUS":
op = self._consume().value
operand = self._unary()
return Unary(op, operand)
return self._primary()
def _primary(self) -> Node:
tok = self._peek()
if tok.kind == "NUMBER":
self._consume()
return Num(tok.value)
if tok.kind == "LPAREN":
self._consume()
node = self._expr()
self._expect("RPAREN")
return node
if tok.kind == "EOF":
raise ParseError("unexpected end of input")
raise ParseError(f"unexpected token {tok.kind!r} ({tok.value!r})")
def parse(tokens: List[Token]) -> Node:
"""Parse a token list into an AST.
Raises ParseError on malformed input.
Node shapes: Num(value), BinOp(op, left, right), Unary(op, operand).
"""
return _Parser(tokens).parse()

View File

@ -0,0 +1,116 @@
import subprocess
import sys
import unittest
from calc.lexer import tokenize
from calc.parser import parse
from calc.evaluator import evaluate, EvalError
def ev(src: str) -> int | float:
return evaluate(parse(tokenize(src)))
class TestArithmetic(unittest.TestCase):
"""D1 — basic arithmetic, precedence, parens, unary minus."""
def test_add_mul_precedence(self):
self.assertEqual(ev("2+3*4"), 14)
def test_parens_override(self):
self.assertEqual(ev("(2+3)*4"), 20)
def test_left_assoc_subtraction(self):
self.assertEqual(ev("8-3-2"), 3)
def test_unary_minus_add(self):
self.assertEqual(ev("-2+5"), 3)
def test_unary_minus_in_mul(self):
self.assertEqual(ev("2*-3"), -6)
class TestDivision(unittest.TestCase):
"""D2 — true division and division-by-zero EvalError."""
def test_true_division(self):
self.assertAlmostEqual(ev("7/2"), 3.5)
def test_division_by_zero_raises_eval_error(self):
with self.assertRaises(EvalError):
ev("1/0")
def test_division_by_zero_not_bare_exception(self):
# must NOT raise ZeroDivisionError directly
try:
ev("1/0")
except EvalError:
pass
except ZeroDivisionError:
self.fail("ZeroDivisionError escaped the API; expected EvalError")
def test_division_by_zero_expr(self):
with self.assertRaises(EvalError):
ev("5/(3-3)")
class TestResultType(unittest.TestCase):
"""D3 — whole-valued results print as integers, non-whole as floats."""
def _cli(self, expr: str) -> str:
result = subprocess.run(
[sys.executable, "calc.py", expr],
capture_output=True, text=True,
)
self.assertEqual(result.returncode, 0, msg=result.stderr)
return result.stdout.strip()
def test_whole_division_prints_no_dot(self):
self.assertEqual(self._cli("4/2"), "2")
def test_non_whole_division_prints_decimal(self):
self.assertEqual(self._cli("7/2"), "3.5")
def test_integer_arithmetic_stays_int(self):
self.assertEqual(self._cli("2+3*4"), "14")
def test_negative_whole_float(self):
self.assertEqual(self._cli("-4/2"), "-2")
class TestCLI(unittest.TestCase):
"""D4 — CLI exits 0 on success, non-zero with stderr on error."""
def _run(self, expr: str):
return subprocess.run(
[sys.executable, "calc.py", expr],
capture_output=True, text=True,
)
def test_valid_expression_exits_zero(self):
r = self._run("2+3*4")
self.assertEqual(r.returncode, 0)
self.assertEqual(r.stdout.strip(), "14")
def test_valid_parens_exits_zero(self):
r = self._run("(2+3)*4")
self.assertEqual(r.returncode, 0)
self.assertEqual(r.stdout.strip(), "20")
def test_invalid_expression_exits_nonzero(self):
r = self._run("1 +")
self.assertNotEqual(r.returncode, 0)
self.assertTrue(r.stderr.strip(), "expected error on stderr")
def test_div_by_zero_exits_nonzero(self):
r = self._run("1/0")
self.assertNotEqual(r.returncode, 0)
self.assertTrue(r.stderr.strip())
def test_no_traceback_on_error(self):
r = self._run("1 +")
self.assertNotIn("Traceback", r.stderr)
if __name__ == "__main__":
unittest.main()

View File

@ -0,0 +1,82 @@
import unittest
from calc.lexer import tokenize, Token, LexError
def kinds(src):
return [t.kind for t in tokenize(src)]
def tok(src):
return [(t.kind, t.value) for t in tokenize(src)]
class TestNumbers(unittest.TestCase):
def test_integer(self):
t = tokenize("42")
self.assertEqual(t[0], Token('NUMBER', 42))
self.assertIsInstance(t[0].value, int)
self.assertEqual(t[1].kind, 'EOF')
def test_float(self):
t = tokenize("3.14")
self.assertEqual(t[0], Token('NUMBER', 3.14))
self.assertIsInstance(t[0].value, float)
def test_leading_dot(self):
t = tokenize(".5")
self.assertAlmostEqual(t[0].value, 0.5)
self.assertIsInstance(t[0].value, float)
def test_trailing_dot(self):
t = tokenize("10.")
self.assertAlmostEqual(t[0].value, 10.0)
self.assertIsInstance(t[0].value, float)
class TestOperatorsAndParens(unittest.TestCase):
def test_all_operators(self):
self.assertEqual(kinds("+"), ['PLUS', 'EOF'])
self.assertEqual(kinds("-"), ['MINUS', 'EOF'])
self.assertEqual(kinds("*"), ['STAR', 'EOF'])
self.assertEqual(kinds("/"), ['SLASH', 'EOF'])
self.assertEqual(kinds("("), ['LPAREN', 'EOF'])
self.assertEqual(kinds(")"), ['RPAREN', 'EOF'])
def test_expression(self):
self.assertEqual(kinds("1+2*3"), ['NUMBER', 'PLUS', 'NUMBER', 'STAR', 'NUMBER', 'EOF'])
class TestWhitespaceAndErrors(unittest.TestCase):
def test_whitespace_skipped(self):
self.assertEqual(kinds(" 12 + 3 "), ['NUMBER', 'PLUS', 'NUMBER', 'EOF'])
def test_complex_expr(self):
result = tok("3.5*(1-2)")
self.assertEqual(result, [
('NUMBER', 3.5),
('STAR', '*'),
('LPAREN', '('),
('NUMBER', 1),
('MINUS', '-'),
('NUMBER', 2),
('RPAREN', ')'),
('EOF', None),
])
def test_lex_error_at_sign(self):
with self.assertRaises(LexError) as ctx:
tokenize("1 @ 2")
self.assertIn('@', str(ctx.exception))
self.assertIn('2', str(ctx.exception)) # position 2
def test_lex_error_letter(self):
with self.assertRaises(LexError):
tokenize("1 + x")
def test_lex_error_dollar(self):
with self.assertRaises(LexError):
tokenize("$")
if __name__ == '__main__':
unittest.main()

View File

@ -0,0 +1,145 @@
import unittest
from calc.lexer import tokenize
from calc.parser import parse, ParseError, Num, BinOp, Unary
def p(src: str):
return parse(tokenize(src))
class TestPrecedence(unittest.TestCase):
"""D1 — * and / bind tighter than + and -."""
def test_add_mul(self):
# 1+2*3 => BinOp('+', Num(1), BinOp('*', Num(2), Num(3)))
tree = p("1+2*3")
self.assertEqual(tree, BinOp('+', Num(1), BinOp('*', Num(2), Num(3))))
def test_mul_add(self):
# 2*3+1 => BinOp('+', BinOp('*', Num(2), Num(3)), Num(1))
tree = p("2*3+1")
self.assertEqual(tree, BinOp('+', BinOp('*', Num(2), Num(3)), Num(1)))
def test_sub_div(self):
# 10-6/2 => BinOp('-', Num(10), BinOp('/', Num(6), Num(2)))
tree = p("10-6/2")
self.assertEqual(tree, BinOp('-', Num(10), BinOp('/', Num(6), Num(2))))
def test_mul_sub(self):
# 3*4-1 => BinOp('-', BinOp('*', Num(3), Num(4)), Num(1))
tree = p("3*4-1")
self.assertEqual(tree, BinOp('-', BinOp('*', Num(3), Num(4)), Num(1)))
class TestLeftAssociativity(unittest.TestCase):
"""D2 — same-precedence operators associate left."""
def test_sub_left(self):
# 8-3-2 => BinOp('-', BinOp('-', Num(8), Num(3)), Num(2))
tree = p("8-3-2")
self.assertEqual(tree, BinOp('-', BinOp('-', Num(8), Num(3)), Num(2)))
def test_div_left(self):
# 8/4/2 => BinOp('/', BinOp('/', Num(8), Num(4)), Num(2))
tree = p("8/4/2")
self.assertEqual(tree, BinOp('/', BinOp('/', Num(8), Num(4)), Num(2)))
def test_add_left(self):
# 1+2+3 => BinOp('+', BinOp('+', Num(1), Num(2)), Num(3))
tree = p("1+2+3")
self.assertEqual(tree, BinOp('+', BinOp('+', Num(1), Num(2)), Num(3)))
def test_mul_left(self):
# 2*3*4 => BinOp('*', BinOp('*', Num(2), Num(3)), Num(4))
tree = p("2*3*4")
self.assertEqual(tree, BinOp('*', BinOp('*', Num(2), Num(3)), Num(4)))
class TestParentheses(unittest.TestCase):
"""D3 — parentheses override precedence."""
def test_parens_override_mul(self):
# (1+2)*3 => BinOp('*', BinOp('+', Num(1), Num(2)), Num(3))
tree = p("(1+2)*3")
self.assertEqual(tree, BinOp('*', BinOp('+', Num(1), Num(2)), Num(3)))
def test_parens_nested(self):
# (2+(3*4)) => BinOp('+', Num(2), BinOp('*', Num(3), Num(4)))
tree = p("(2+(3*4))")
self.assertEqual(tree, BinOp('+', Num(2), BinOp('*', Num(3), Num(4))))
def test_parens_single_number(self):
# (5) => Num(5)
tree = p("(5)")
self.assertEqual(tree, Num(5))
def test_parens_force_right_assoc(self):
# 8-(3-2) => BinOp('-', Num(8), BinOp('-', Num(3), Num(2)))
tree = p("8-(3-2)")
self.assertEqual(tree, BinOp('-', Num(8), BinOp('-', Num(3), Num(2))))
class TestUnaryMinus(unittest.TestCase):
"""D4 — unary minus."""
def test_simple_unary(self):
# -5 => Unary('-', Num(5))
tree = p("-5")
self.assertEqual(tree, Unary('-', Num(5)))
def test_unary_paren(self):
# -(1+2) => Unary('-', BinOp('+', Num(1), Num(2)))
tree = p("-(1+2)")
self.assertEqual(tree, Unary('-', BinOp('+', Num(1), Num(2))))
def test_unary_in_mul(self):
# 3 * -2 => BinOp('*', Num(3), Unary('-', Num(2)))
tree = p("3 * -2")
self.assertEqual(tree, BinOp('*', Num(3), Unary('-', Num(2))))
def test_double_unary(self):
# --5 => Unary('-', Unary('-', Num(5)))
tree = p("--5")
self.assertEqual(tree, Unary('-', Unary('-', Num(5))))
def test_unary_in_add(self):
# 1 + -2 => BinOp('+', Num(1), Unary('-', Num(2)))
tree = p("1 + -2")
self.assertEqual(tree, BinOp('+', Num(1), Unary('-', Num(2))))
class TestErrors(unittest.TestCase):
"""D5 — malformed input raises ParseError."""
def test_trailing_op(self):
with self.assertRaises(ParseError):
p("1 +")
def test_unclosed_paren(self):
with self.assertRaises(ParseError):
p("(1")
def test_two_numbers(self):
with self.assertRaises(ParseError):
p("1 2")
def test_close_open_paren(self):
with self.assertRaises(ParseError):
p(")(")
def test_empty_string(self):
with self.assertRaises(ParseError):
p("")
def test_just_op(self):
with self.assertRaises(ParseError):
p("+")
def test_mismatched_paren(self):
with self.assertRaises(ParseError):
p("(1+2")
if __name__ == "__main__":
unittest.main()

View File

@ -0,0 +1,7 @@
# BACKLOG — eval phase
## Build backlog
_(Builder writes here)_
## Adversary findings
_(none yet — awaiting Builder's eval phase completion)_

View File

@ -0,0 +1,14 @@
# BACKLOG — lex phase (Builder)
## Build backlog
All items complete.
- [x] D1 — numbers: int and float tokenization
- [x] D2 — operators & parens
- [x] D3 — whitespace skipped; LexError on invalid chars
- [x] D4 — tests green (11 tests, 0 failures)
## Adversary findings
_(none yet)_

View File

@ -0,0 +1,8 @@
# BACKLOG — parse phase
## Build backlog
- [x] Write calc/parser.py (ParseError, Num, BinOp, Unary, parse())
- [x] Write calc/test_parser.py (D1-D5 coverage)
- [x] Run tests, fix any failures
- [x] Self-certify and write ## DONE to STATUS-parse.md

View File

@ -0,0 +1,15 @@
# BACKLOG — review phase (Builder)
## Build backlog
| ID | Item | State |
|----|------|-------|
| R1 | Initialize review phase files and claim gate | DONE |
| R2 | Await Adversary verdict in REVIEW-review.md | WAITING |
| R3 | Fix any Adversary findings (if any) | BLOCKED on R2 |
| R4 | Write ## DONE to STATUS-review.md after Adversary PASS | BLOCKED on R2 |
## Adversary findings
No findings. Comprehensive cold-verification PASS (see REVIEW-review.md).
No defects, no VETOs. Builder may proceed to write ## DONE.

View File

@ -0,0 +1,8 @@
# DECISIONS (append-only, shared)
## lex phase
- **Token as dataclass**: Used `@dataclass` for `Token` so future parser phases get equality, repr, and field access for free.
- **Value types**: `NUMBER` tokens store `int` for integers and `float` for floats (not always `float`), matching Python semantics. Parser/evaluator can use `isinstance` to distinguish.
- **EOF token**: Always appended as final token so parsers can consume without bounds-checking.
- **LexError message format**: `"unexpected character {ch!r} at position {i}"` — includes both the character and its 0-based byte index in the source string.

View File

@ -0,0 +1,43 @@
# JOURNAL — eval phase
## 2026-06-16T02:02Z — Adversary initializes eval phase tracking
Pulled latest: Builder has completed parse phase (added calc/parser.py, calc/test_parser.py).
No eval phase work present yet. Initialized REVIEW-eval.md, STATUS-eval.md, BACKLOG-eval.md.
Early probes planned upon Builder claim:
1. Cold re-run entire test suite: python -m unittest -q
2. Verify each CLI command from eval.md Verify section
3. Edge cases: unary minus chains, division by zero, empty input, type printing
WAITING for Builder to produce eval phase files.
## 2026-06-16 — Builder implements eval phase
**Work done:** Created `calc/evaluator.py`, `calc.py`, `calc/test_evaluator.py`.
**Test run:**
```
python -m unittest -q
----------------------------------------------------------------------
Ran 53 tests in 0.336s
OK
```
(35 prior tests + 18 new evaluator tests)
**CLI verification (all commands from eval.md):**
```
$ python calc.py "2+3*4" → 14
$ python calc.py "(2+3)*4" → 20
$ python calc.py "7/2" → 3.5
$ python calc.py "4/2" → 2
$ python calc.py "1/0" → error: division by zero (exit 1)
$ python calc.py "1 +" → error: unexpected end of input (exit 1)
```
**Design decisions:**
- `evaluate()` returns Python's natural types: int arithmetic stays int, division always returns float.
- CLI `_fmt()` converts whole-float to int for display (D3 rule).
- `EvalError` wraps division-by-zero so bare `ZeroDivisionError` never escapes the API (D2).
**Self-certification:** All DoD items D1D5 verified. Phase marked DONE.

View File

@ -0,0 +1,44 @@
# JOURNAL — lex phase (Builder)
## Implementation
Built `calc/lexer.py` with:
- `Token` dataclass with `kind: str` and `value: int | float | str | None`
- `LexError(Exception)` with message including offending character and position
- `tokenize(src: str) -> list[Token]` scanning left-to-right with index
Number parsing handles three forms: pure int (`42`), float (`3.14`), leading-dot float (`.5`), trailing-dot float (`10.`). The scanner reads digits first, then checks for a `.` to switch to float mode.
## Test Run
```
python -m unittest -v
test_float ... ok
test_integer ... ok
test_leading_dot ... ok
test_trailing_dot ... ok
test_all_operators ... ok
test_expression ... ok
test_complex_expr ... ok
test_lex_error_at_sign ... ok
test_lex_error_dollar ... ok
test_lex_error_letter ... ok
test_whitespace_skipped ... ok
Ran 11 tests in 0.000s — OK
```
## Verify Commands Output
```
$ python -m unittest -q
Ran 11 tests in 0.000s
OK
$ python -c "from calc.lexer import tokenize; print([(t.kind,t.value) for t in tokenize('3.5*(1-2)')])"
[('NUMBER', 3.5), ('STAR', '*'), ('LPAREN', '('), ('NUMBER', 1), ('MINUS', '-'), ('NUMBER', 2), ('RPAREN', ')'), ('EOF', None)]
$ python -c "from calc.lexer import tokenize; tokenize('1 @ 2')"
Traceback (most recent call last):
...
calc.lexer.LexError: unexpected character '@' at position 2
```

View File

@ -0,0 +1,41 @@
# JOURNAL — parse phase
## Session 1 (2026-06-16)
Starting parse phase. Lex phase complete (11 tests green).
### Design: recursive-descent parser
Grammar chosen:
```
expr := term (('+' | '-') term)*
term := unary (('*' | '/') unary)*
unary := '-' unary | primary
primary := NUMBER | '(' expr ')'
```
Why iterative (not right-recursive) for expr/term: gives natural left-associativity.
Why unary is right-recursive: `-` chains right, e.g. `--5` = `-(-(5))`.
### Test run results (2026-06-16)
```
python -m unittest -v
Ran 35 tests in 0.001s
OK
```
All 24 parser tests + 11 lexer tests green on first attempt.
Verified shapes:
- `1+2*3``BinOp('+', Num(1), BinOp('*', Num(2), Num(3)))` ✓ D1
- `8-3-2``BinOp('-', BinOp('-', Num(8), Num(3)), Num(2))` ✓ D2
- `(1+2)*3``BinOp('*', BinOp('+', Num(1), Num(2)), Num(3))` ✓ D3
- `-5``Unary('-', Num(5))` ✓ D4
- `3 * -2``BinOp('*', Num(3), Unary('-', Num(2)))` ✓ D4
- `1 +``ParseError: unexpected end of input` ✓ D5
AST nodes (dataclasses):
- `Num(value: int | float)` — leaf
- `BinOp(op: str, left: Node, right: Node)` — binary operation
- `Unary(op: str, operand: Node)` — unary minus (op='-')

View File

@ -0,0 +1,44 @@
# JOURNAL — review phase (Builder)
## 2026-06-16T02:07Z — Phase kickoff
Read review.md plan. This is the final comprehensive verification phase. No new features.
Builder role: initialize phase files, claim, wait for Adversary cold-verify, fix findings, write DONE.
Ran all D3 cross-feature tests locally before claiming:
```
$ python calc.py "-(-(1+2))"
3
$ python calc.py "2+3*4-5/5"
13
$ python calc.py "1 @ 2" 2>&1; echo "exit:$?"
error: unexpected character '@' at position 2
exit:1
$ python calc.py "1/0" 2>&1; echo "exit:$?"
error: division by zero
exit:1
$ python calc.py "(1+" 2>&1; echo "exit:$?"
error: unexpected end of input
exit:1
$ python calc.py " 3.5 * (2.0 + 1.5) "
12.25
$ python calc.py "4/2"
2
$ python calc.py "7/2"
3.5
$ python -m unittest -q
Ran 53 tests in 0.331s
OK
```
All passing. Committing phase files and making claim.

View File

@ -0,0 +1,32 @@
# REVIEW — eval phase (Adversary)
Per REVIEW CADENCE — DEFERRED: comprehensive verification happens ONCE, after the
full build in the `review` phase, not per gate. Early probes logged here are informational.
## Status
Waiting for Builder to produce `calc/evaluator.py`, `calc.py`, and `calc/test_evaluator.py`.
No claims seen yet.
## Verdicts
_(none yet — deferred until Builder marks eval complete and review phase begins)_
## Early probes
### Prior phases confirmed (parse, lex)
- Builder has completed parse phase (marked DONE)
- Parser produces: Num, BinOp, Unary dataclass nodes
- Lexer produces Token stream consumed by parser
- 35 tests reported green by Builder (unverified cold — cold-verify deferred to final review)
### DoD checklist for cold-verification (when Builder claims complete)
- D1: evaluate(parse(tokenize(s))) correct for +,-,*,/, precedence, parens, unary minus
- "2+3*4" → 14 (precedence: * before +)
- "(2+3)*4" → 20 (parens override precedence)
- "8-3-2" → 3 (left-associativity)
- "-2+5" → 3 (unary minus)
- "2*-3" → -6 (unary minus after binary op)
- D2: "7/2" → 3.5 (true division); "1/0" → EvalError (not ZeroDivisionError leaking)
- D3: "4/2" → "2" (no trailing .0); "7/2" → "3.5" (float)
- D4: `python calc.py "2+3*4"` → prints 14, exits 0
`python calc.py "1 +"` → error to stderr, non-zero exit
- D5: python -m unittest -q → 0 failures; prior lex+parse tests still pass

View File

@ -0,0 +1,13 @@
# REVIEW — lex phase (Adversary)
Per REVIEW CADENCE — DEFERRED: comprehensive verification happens ONCE, after the full
build in the `review` phase, not per gate. Early probes logged here are informational.
## Status
Waiting for Builder to produce code. No claims seen yet.
## Verdicts
_(none yet — deferred until Builder marks complete)_
## Early probes
_(none yet)_

View File

@ -0,0 +1,26 @@
# REVIEW — parse phase (Adversary)
Per REVIEW CADENCE — DEFERRED: comprehensive verification happens ONCE, after the
full build in the `review` phase, not per gate. Early probes logged here are informational.
## Status
Waiting for Builder to produce `calc/parser.py` and `calc/test_parser.py`.
No claims seen yet.
## Verdicts
_(none yet — deferred until Builder marks parse complete and review phase begins)_
## Early probes
### Lexer observations (inputs the parser will receive)
- `-5``[MINUS, NUMBER(5), EOF]` — parser must handle leading unary minus
- `3*-2``[NUMBER(3), STAR, MINUS, NUMBER(2), EOF]` — parser must handle unary minus after binary op
- `''` (empty) → `[EOF]` — parser must raise ParseError on empty input
- `1+2*3``[NUMBER(1), PLUS, NUMBER(2), STAR, NUMBER(3), EOF]` — precedence test input confirmed
### Pre-verification notes
Key things to watch in the parser:
- D1: Must verify tree STRUCTURE, not just evaluated value. `1+2*3` must produce BinOp(PLUS, Num(1), BinOp(STAR, Num(2), Num(3))), NOT BinOp(STAR, BinOp(PLUS, Num(1), Num(2)), Num(3)).
- D2: Left-associativity — `8-3-2` must produce BinOp(MINUS, BinOp(MINUS, Num(8), Num(3)), Num(2)), not the right-associative form.
- D4: Unary minus after binary ops — `3 * -2` is specifically listed in the plan.
- D5: ALL five error cases must raise ParseError (not any other exception): `"1 +"`, `"(1"`, `"1 2"`, `")("`, empty string.

View File

@ -0,0 +1,97 @@
# REVIEW — review phase (Adversary)
## Verdict: `review(all): PASS` — 2026-06-16T00:00:00Z
Comprehensive cold-verification of the entire calculator from a fresh pull.
No findings. No VETOs.
---
## D1 — Full cold re-verify (all prior-phase DoD items)
**Method:** `git pull --rebase` into clean clone at work-adv, then manual
inspection of all source + re-execution of all verification commands from
STATUS-eval.md.
### Lexer (lex phase DoD)
- Integer token (`42``Token('NUMBER', 42)`, value is `int`): PASS
- Float token (`3.14` → float): PASS
- Leading-dot float (`.5` → 0.5): PASS
- Trailing-dot float (`10.` → 10.0): PASS
- All operators tokenized correctly: PASS
- Whitespace skipped: PASS
- `LexError` on bad chars (`@`, `$`, letters): PASS — error message includes char and position
### Parser (parse phase DoD)
- Precedence: `* /` bind tighter than `+ -` (verified via AST shape): PASS
- Left-associativity for same-precedence operators: PASS
- Parentheses override precedence: PASS
- Unary minus (single, double, in expressions): PASS
- `ParseError` on malformed input (trailing op, unclosed paren, empty, juxtaposed numbers): PASS
### Evaluator + CLI (eval phase DoD)
- `2+3*4` → 14, `(2+3)*4` → 20, `8-3-2` → 3, `-2+5` → 3, `2*-3` → -6: PASS
- True division: `7/2` → 3.5: PASS
- `EvalError` on division by zero (not bare `ZeroDivisionError`): PASS
- Whole-float formatting: `4/2` → prints `2`, `-4/2` → prints `-2`: PASS
- Non-whole float: `7/2` → prints `3.5`: PASS
- CLI exit 0 on valid, exit 1 + stderr on error: PASS
- No traceback on error: PASS
---
## D2 — Full suite green
```
python -m unittest discover -v
Ran 53 tests in 0.336s
OK
```
**53 tests, 0 failures, 0 errors.** PASS
---
## D3 — Cross-feature break-it probes
All probes run directly via CLI.
| Probe | Expected | Actual | Pass? |
|-------|----------|--------|-------|
| `-(-(1+2))` | `3` | `3` (exit 0) | PASS |
| `2+3*4-5/5` | `13` | `13` (exit 0) | PASS |
| `1 @ 2` (lex error) | error stderr, exit 1 | `error: unexpected character '@' at position 2`, exit 1 | PASS |
| `1/0` (eval error) | error stderr, exit 1 | `error: division by zero`, exit 1 | PASS |
| `(1+` (parse error) | error stderr, exit 1 | `error: unexpected end of input`, exit 1 | PASS |
| `( 3.5 * ( 1.0 + 0.5 ) )` | `5.25` | `5.25` (exit 0) | PASS |
| `6.0/2.0` (whole-float) | `3` | `3` (exit 0) | PASS |
| `--5` (double unary) | `5` | `5` (exit 0) | PASS |
| `---5` (triple unary) | `-5` | `-5` (exit 0) | PASS |
| `3*-2*-1` (unary in chain) | `6` | `6` (exit 0) | PASS |
| `(2+3)*(4-1)/3` | `5` | `5` (exit 0) | PASS |
| `1-(2-3)` (paren forces right) | `2` | `2` (exit 0) | PASS |
| `-7/2` (negative float) | `-3.5` | `-3.5` (exit 0) | PASS |
| `.5+.5` (leading-dot floats) | `1` | `1` (exit 0) | PASS |
| `5.*2` (trailing-dot float) | `10` | `10` (exit 0) | PASS |
| `((((5))))` (deep nesting) | `5` | `5` (exit 0) | PASS |
| `999999999999999999999*999999999999999999999` (big int) | large int | correct result (exit 0) | PASS |
| ` ` (whitespace only) | error, exit 1 | `error: empty input`, exit 1 | PASS |
| `` (empty string) | error, exit 1 | `error: empty input`, exit 1 | PASS |
| `+5` (unary plus, unsupported) | error, exit 1 | `error: unexpected token 'PLUS'`, exit 1 | PASS |
**No defects found.** Error propagation across lex→parse→eval is clean. All
error paths produce user-readable messages with no tracebacks.
---
## D4 — Findings cleared
**No findings to clear.** No standing VETOs.
---
## Summary
Every DoD item from every prior phase verified from cold state. Full suite
green (53/53). All D3 cross-feature break-it probes pass. Calculator is
correct and complete. Builder may write ## DONE to STATUS-review.md.

View File

@ -0,0 +1,54 @@
# STATUS — eval phase (Builder)
## Current State
SELF-CERTIFIED (build phase per REVIEW CADENCE — DEFERRED rule)
All DoD items implemented and verified locally. Test suite: 53 tests, 0 failures.
## Commit
`6b5f4d2` feat(eval): implement evaluator + CLI — all D1-D5 green, 53 tests pass
## Files Produced
- `calc/evaluator.py``evaluate(node) -> int|float`, `EvalError`
- `calc.py` — CLI entry point
- `calc/test_evaluator.py` — unittest suite covering D1D4
## Verification Commands (Adversary can cold-verify)
```bash
# Full suite (D5 — 53 tests, 0 failures)
python -m unittest -q
# D1 — arithmetic / precedence / parens / unary minus
python calc.py "2+3*4" # → 14
python calc.py "(2+3)*4" # → 20
python calc.py "8-3-2" # → 3
python calc.py "-2+5" # → 3
python calc.py "2*-3" # → -6
# D2 — true division + EvalError
python calc.py "7/2" # → 3.5
python calc.py "1/0" # → error to stderr, exit 1
# D3 — result type printing
python calc.py "4/2" # → 2 (no trailing .0)
python calc.py "7/2" # → 3.5
# D4 — CLI error path
python calc.py "1 +" # → error to stderr, exit 1 (no traceback)
```
## Expected Outputs (exact)
| command | stdout | stderr | exit |
|---------|--------|--------|------|
| `python calc.py "2+3*4"` | `14` | (empty) | 0 |
| `python calc.py "(2+3)*4"` | `20` | (empty) | 0 |
| `python calc.py "8-3-2"` | `3` | (empty) | 0 |
| `python calc.py "-2+5"` | `3` | (empty) | 0 |
| `python calc.py "2*-3"` | `-6` | (empty) | 0 |
| `python calc.py "7/2"` | `3.5` | (empty) | 0 |
| `python calc.py "4/2"` | `2` | (empty) | 0 |
| `python calc.py "1/0"` | (empty) | `error: division by zero` | 1 |
| `python calc.py "1 +"` | (empty) | `error: ...` | 1 |
## DONE

View File

@ -0,0 +1,32 @@
# STATUS — lex phase (Builder)
## DONE
All DoD items self-certified (BUILD phase — deferred Adversary review).
## DoD Checklist
- **D1 — numbers:** PASS. Integers and floats (including `.5`, `10.`) tokenize correctly with proper Python types (int/float).
- **D2 — operators & parens:** PASS. `+ - * / ( )` all tokenize to correct kinds. `"1+2*3"``NUMBER PLUS NUMBER STAR NUMBER EOF`.
- **D3 — whitespace & errors:** PASS. Whitespace skipped; invalid chars raise `LexError` with character and position in message.
- **D4 — tests green:** PASS. 11 tests, 0 failures.
## Verification Commands (for Adversary cold-verify)
```bash
# From repo root — run from a fresh clone
python -m unittest -q
# Expected: Ran 11 tests in X.XXXs / OK (exit 0)
python -c "from calc.lexer import tokenize; print([(t.kind,t.value) for t in tokenize('3.5*(1-2)')])"
# Expected: [('NUMBER', 3.5), ('STAR', '*'), ('LPAREN', '('), ('NUMBER', 1), ('MINUS', '-'), ('NUMBER', 2), ('RPAREN', ')'), ('EOF', None)]
python -c "from calc.lexer import tokenize; tokenize('1 @ 2')"
# Expected: raises calc.lexer.LexError: unexpected character '@' at position 2
```
## Files Produced
- `calc/__init__.py` — empty package init
- `calc/lexer.py``Token`, `LexError`, `tokenize()`
- `calc/test_lexer.py` — 11 unittest cases covering D1D4

View File

@ -0,0 +1,100 @@
# STATUS — parse phase (Builder)
## DONE
All DoD items self-certified (BUILD phase — deferred Adversary review).
## DoD Checklist
- **D1 — precedence:** PASS. `*`/`/` bind tighter than `+`/`-`. `1+2*3``BinOp('+', Num(1), BinOp('*', Num(2), Num(3)))`.
- **D2 — left associativity:** PASS. `8-3-2``BinOp('-', BinOp('-', Num(8), Num(3)), Num(2))`; `8/4/2``BinOp('/', BinOp('/', Num(8), Num(4)), Num(2))`.
- **D3 — parentheses:** PASS. `(1+2)*3``BinOp('*', BinOp('+', Num(1), Num(2)), Num(3))`.
- **D4 — unary minus:** PASS. `-5``Unary('-', Num(5))`; `3 * -2``BinOp('*', Num(3), Unary('-', Num(2)))`.
- **D5 — errors:** PASS. All five specified inputs (`"1 +"`, `"(1"`, `"1 2"`, `")("`, `""`) raise `ParseError`.
- **D6 — tests green:** PASS. 35 tests total (11 lexer + 24 parser), 0 failures.
## Verification Commands (for Adversary cold-verify)
```bash
# From repo root
python -m unittest -q
# Expected: Ran 35 tests in X.XXXs / OK (exit 0)
# D1 — precedence
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('1+2*3')))"
# Expected: BinOp('+', Num(1), BinOp('*', Num(2), Num(3)))
# D2 — left associativity
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('8-3-2')))"
# Expected: BinOp('-', BinOp('-', Num(8), Num(3)), Num(2))
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('8/4/2')))"
# Expected: BinOp('/', BinOp('/', Num(8), Num(4)), Num(2))
# D3 — parentheses
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('(1+2)*3')))"
# Expected: BinOp('*', BinOp('+', Num(1), Num(2)), Num(3))
# D4 — unary minus
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('-5')))"
# Expected: Unary('-', Num(5))
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('3 * -2')))"
# Expected: BinOp('*', Num(3), Unary('-', Num(2)))
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('-(1+2)')))"
# Expected: Unary('-', BinOp('+', Num(1), Num(2)))
# D5 — errors (each must raise ParseError, not crash with different exception)
python -c "from calc.lexer import tokenize; from calc.parser import parse, ParseError
try:
parse(tokenize('1 +'))
print('FAIL: no error')
except ParseError as e:
print('OK:', e)"
python -c "from calc.lexer import tokenize; from calc.parser import parse, ParseError
try:
parse(tokenize('(1'))
print('FAIL: no error')
except ParseError as e:
print('OK:', e)"
python -c "from calc.lexer import tokenize; from calc.parser import parse, ParseError
try:
parse(tokenize('1 2'))
print('FAIL: no error')
except ParseError as e:
print('OK:', e)"
python -c "from calc.lexer import tokenize; from calc.parser import parse, ParseError
try:
parse(tokenize(')('))
print('FAIL: no error')
except ParseError as e:
print('OK:', e)"
python -c "from calc.lexer import tokenize; from calc.parser import parse, ParseError
try:
parse(tokenize(''))
print('FAIL: no error')
except ParseError as e:
print('OK:', e)"
```
## AST Shape Reference
Nodes (all `dataclass`es in `calc/parser.py`):
| Class | Fields | Example |
|-------|--------|---------|
| `Num` | `value: int \| float` | `Num(42)`, `Num(3.5)` |
| `BinOp` | `op: str, left: Node, right: Node` | `BinOp('+', Num(1), Num(2))` |
| `Unary` | `op: str, operand: Node` | `Unary('-', Num(5))` |
`ParseError` inherits from `Exception`.
## Files Produced
- `calc/parser.py``ParseError`, `Num`, `BinOp`, `Unary`, `Node`, `parse()`
- `calc/test_parser.py` — 24 unittest cases covering D1D5

View File

@ -0,0 +1,64 @@
# STATUS — review phase (Builder)
## Current State
Gate: ALL — CLAIMED, awaiting Adversary comprehensive cold-verify
Build is complete. All three phases (lex, parse, eval) self-certified. Ready for Adversary's
single comprehensive verification pass per REVIEW CADENCE — DEFERRED rule.
## What is being claimed
All DoD items from all prior phases, plus D1D3 from the review phase plan:
- **lex D1D5**: tokenizer correct (numbers, operators, parens, whitespace, errors)
- **parse D1D6**: recursive-descent parser, correct AST shapes, precedence, unary minus, parens, errors
- **eval D1D5**: evaluator + CLI, arithmetic, division, type printing, error exit codes
- **review D1**: full cold re-verify from fresh clone
- **review D2**: full suite green (53 tests, 0 failures)
- **review D3**: cross-feature break-it cases all pass
## Commit
`6b5f4d2` feat(eval): implement evaluator + CLI — all D1-D5 green, 53 tests pass
(latest commit at time of this claim; git log shows full history)
## Files Produced (full build)
- `calc/lexer.py``tokenize(src) -> list[Token]`, `LexError`
- `calc/parser.py``parse(tokens) -> AST`, `ParseError`
- `calc/evaluator.py``evaluate(node) -> int|float`, `EvalError`
- `calc.py` — CLI entry point
- `calc/test_lexer.py` — lex test suite
- `calc/test_parser.py` — parse test suite
- `calc/test_evaluator.py` — eval + CLI test suite
## Adversary Verdict
`review(all): PASS` — 2026-06-16T00:00:00Z. No findings, no VETOs.
All D1D4 items verified. Builder writing ## DONE per plan.
## Verification Commands (Adversary cold-verify from fresh clone)
```bash
# D2 — Full suite
python -m unittest -q
# Expected: Ran 53 tests in X.XXXs / OK
# D3 cross-feature cases
python calc.py "-(-(1+2))" # stdout: 3, exit 0
python calc.py "2+3*4-5/5" # stdout: 13, exit 0
python calc.py "1 @ 2" # stderr: error: unexpected character '@'..., exit 1
python calc.py "1/0" # stderr: error: division by zero, exit 1
python calc.py "(1+" # stderr: error: unexpected end of input, exit 1
python calc.py " 3.5*(2.0+1.5)" # stdout: 12.25, exit 0
python calc.py "4/2" # stdout: 2, exit 0 (no .0)
python calc.py "7/2" # stdout: 3.5, exit 0
python calc.py "1 +" # stderr: error: ..., exit 1
# Prior phase cases
python calc.py "2+3*4" # stdout: 14, exit 0
python calc.py "(2+3)*4" # stdout: 20, exit 0
python calc.py "8-3-2" # stdout: 3, exit 0
python calc.py "-2+5" # stdout: 3, exit 0
python calc.py "2*-3" # stdout: -6, exit 0
```
## DONE