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 +1,2 @@
__pycache__/
*.pyc

View File

@ -0,0 +1,16 @@
# git history (claim/review handshake), from the run's shared bare repo
b30af2d status: eval phase DONE — all D1-D5 PASS, no Adversary findings
6ee8abb review(D1,D2,D3,D4,D5): PASS — all eval gates verified, no defects found
732a9df claim(D1,D2,D3,D4,D5): evaluator + CLI + tests complete
6d4fbb6 feat(eval): evaluator + CLI + tests
eb590b3 review(eval): Adversary initialized REVIEW-eval.md for eval phase
8e9b6c3 status: parse phase DONE — all D1-D6 PASS, no Adversary findings
4ef7254 review(D1,D2,D3,D4,D5,D6): PASS — all gates verified, no defects found
deb7758 claim(D1,D2,D3,D4,D5,D6): parser implementation + tests green
3ce93b6 review(init): Adversary initialized REVIEW-parse.md for parse phase
d9dd96f fix(AF-1): bare dot raises LexError instead of leaking ValueError
163d7ae review(D1,D2,D3,D4): PASS — all gates verified; AF-1 bare-dot ValueError (non-blocking)
0777cb8 status: update SHA in STATUS-lex.md
328d25f claim(D1,D2,D3,D4): lexer implementation + tests green
b1b03af review(init): Adversary initialized REVIEW-lex.md and JOURNAL-lex.md
f47b649 chore: seed

View File

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

View File

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

View File

@ -0,0 +1,23 @@
#!/usr/bin/env python3
import sys
from calc.lexer import tokenize, LexError
from calc.parser import parse, ParseError
from calc.evaluator import evaluate, EvalError
def main():
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)))
except (LexError, ParseError, EvalError) as e:
print(f"error: {e}", file=sys.stderr)
sys.exit(1)
print(result)
if __name__ == "__main__":
main()

View File

@ -0,0 +1,34 @@
from calc.parser import Num, BinOp, Unary, Node
class EvalError(Exception):
pass
def evaluate(node: Node) -> "int | float":
if isinstance(node, Num):
return node.value
if isinstance(node, Unary):
v = evaluate(node.operand)
if node.op == '-':
return -v
raise EvalError(f"unknown unary op {node.op!r}")
if isinstance(node, BinOp):
l = evaluate(node.left)
r = evaluate(node.right)
if node.op == '+':
result = l + r
elif node.op == '-':
result = l - r
elif node.op == '*':
result = l * r
elif node.op == '/':
if r == 0:
raise EvalError("division by zero")
result = l / r
else:
raise EvalError(f"unknown binary op {node.op!r}")
if isinstance(result, float) and result == int(result):
return int(result)
return result
raise EvalError(f"unknown node type {type(node)!r}")

View File

@ -0,0 +1,62 @@
from dataclasses import dataclass
from typing import Union
class LexError(Exception):
pass
@dataclass
class Token:
kind: str
value: Union[int, float, str, None]
def __repr__(self):
return f"{self.kind}({self.value!r})"
_SINGLE = {
'+': 'PLUS',
'-': 'MINUS',
'*': 'STAR',
'/': 'SLASH',
'(': 'LPAREN',
')': 'RPAREN',
}
def tokenize(src: str) -> list:
tokens = []
i = 0
while i < len(src):
ch = src[i]
if ch in ' \t':
i += 1
continue
if ch in _SINGLE:
tokens.append(Token(_SINGLE[ch], ch))
i += 1
continue
if ch.isdigit() or ch == '.':
j = i
has_dot = False
while j < len(src) and (src[j].isdigit() or (src[j] == '.' and not has_dot)):
if src[j] == '.':
has_dot = True
j += 1
raw = src[i:j]
try:
value = float(raw) if has_dot else int(raw)
except ValueError:
raise LexError(f"unexpected character '.' at position {i}")
tokens.append(Token('NUMBER', value))
i = j
continue
raise LexError(f"unexpected character {ch!r} at position {i}")
tokens.append(Token('EOF', None))
return tokens

View File

@ -0,0 +1,114 @@
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):
return f"Num(value={self.value!r})"
@dataclass
class BinOp:
op: str
left: "Node"
right: "Node"
def __repr__(self):
return f"BinOp(op={self.op!r}, left={self.left!r}, right={self.right!r})"
@dataclass
class Unary:
op: str
operand: "Node"
def __repr__(self):
return f"Unary(op={self.op!r}, operand={self.operand!r})"
Node = Union[Num, BinOp, Unary]
class _Parser:
def __init__(self, tokens: List[Token]):
self._tokens = tokens
self._pos = 0
def _peek(self) -> Token:
return self._tokens[self._pos]
def _consume(self, kind: str) -> Token:
tok = self._peek()
if tok.kind != kind:
raise ParseError(
f"expected {kind}, got {tok.kind!r} ({tok.value!r})"
)
self._pos += 1
return tok
def _advance(self) -> Token:
tok = self._tokens[self._pos]
self._pos += 1
return tok
def parse(self) -> Node:
if self._peek().kind == "EOF":
raise ParseError("empty expression")
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._advance().value
right = self._term()
node = BinOp(op=op, left=node, right=right)
return node
def _term(self) -> Node:
node = self._unary()
while self._peek().kind in ("STAR", "SLASH"):
op = self._advance().value
right = self._unary()
node = BinOp(op=op, left=node, right=right)
return node
def _unary(self) -> Node:
if self._peek().kind == "MINUS":
op = self._advance().value
operand = self._unary()
return Unary(op=op, operand=operand)
return self._primary()
def _primary(self) -> Node:
tok = self._peek()
if tok.kind == "NUMBER":
self._advance()
return Num(value=tok.value)
if tok.kind == "LPAREN":
self._advance()
node = self._expr()
self._consume("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."""
return _Parser(tokens).parse()

View File

@ -0,0 +1,63 @@
import unittest
from calc.lexer import tokenize
from calc.parser import parse
from calc.evaluator import evaluate, EvalError
def calc(s):
return evaluate(parse(tokenize(s)))
class TestArithmetic(unittest.TestCase):
def test_add_mul_precedence(self):
self.assertEqual(calc("2+3*4"), 14)
def test_parens(self):
self.assertEqual(calc("(2+3)*4"), 20)
def test_left_assoc_sub(self):
self.assertEqual(calc("8-3-2"), 3)
def test_unary_minus(self):
self.assertEqual(calc("-2+5"), 3)
def test_unary_before_mul(self):
self.assertEqual(calc("2*-3"), -6)
class TestDivision(unittest.TestCase):
def test_true_division(self):
self.assertEqual(calc("7/2"), 3.5)
def test_div_by_zero(self):
with self.assertRaises(EvalError):
calc("1/0")
def test_no_bare_zero_division_error(self):
try:
calc("1/0")
except EvalError:
pass
except ZeroDivisionError:
self.fail("ZeroDivisionError escaped the API")
class TestResultType(unittest.TestCase):
def test_whole_division_is_int(self):
result = calc("4/2")
self.assertEqual(result, 2)
self.assertIsInstance(result, int)
def test_fractional_division_is_float(self):
result = calc("7/2")
self.assertEqual(result, 3.5)
self.assertIsInstance(result, float)
def test_integer_arithmetic_stays_int(self):
result = calc("2+3")
self.assertIsInstance(result, int)
if __name__ == "__main__":
unittest.main()

View File

@ -0,0 +1,91 @@
import unittest
from calc.lexer import tokenize, Token, LexError
def kinds(src):
return [t.kind for t in tokenize(src)]
def values(src):
return [(t.kind, t.value) for t in tokenize(src)]
class TestNumbers(unittest.TestCase):
def test_integer(self):
toks = tokenize("42")
self.assertEqual(len(toks), 2)
self.assertEqual(toks[0].kind, 'NUMBER')
self.assertEqual(toks[0].value, 42)
self.assertIsInstance(toks[0].value, int)
self.assertEqual(toks[1].kind, 'EOF')
def test_float_standard(self):
toks = tokenize("3.14")
self.assertEqual(toks[0].kind, 'NUMBER')
self.assertAlmostEqual(toks[0].value, 3.14)
self.assertIsInstance(toks[0].value, float)
def test_float_leading_dot(self):
toks = tokenize(".5")
self.assertEqual(toks[0].kind, 'NUMBER')
self.assertAlmostEqual(toks[0].value, 0.5)
self.assertIsInstance(toks[0].value, float)
def test_float_trailing_dot(self):
toks = tokenize("10.")
self.assertEqual(toks[0].kind, 'NUMBER')
self.assertAlmostEqual(toks[0].value, 10.0)
self.assertIsInstance(toks[0].value, float)
class TestOperatorsAndParens(unittest.TestCase):
def test_all_operators(self):
self.assertEqual(kinds("+-*/()"), ['PLUS', 'MINUS', 'STAR', 'SLASH', 'LPAREN', 'RPAREN', 'EOF'])
def test_expression(self):
self.assertEqual(kinds("1+2*3"), ['NUMBER', 'PLUS', 'NUMBER', 'STAR', 'NUMBER', 'EOF'])
def test_operator_values(self):
toks = tokenize("+")
self.assertEqual(toks[0].value, '+')
def test_parens_values(self):
toks = tokenize("()")
self.assertEqual(toks[0].kind, 'LPAREN')
self.assertEqual(toks[0].value, '(')
self.assertEqual(toks[1].kind, 'RPAREN')
self.assertEqual(toks[1].value, ')')
class TestWhitespaceAndErrors(unittest.TestCase):
def test_spaces_skipped(self):
self.assertEqual(kinds(" 12 + 3 "), ['NUMBER', 'PLUS', 'NUMBER', 'EOF'])
def test_tabs_skipped(self):
self.assertEqual(kinds("1\t+\t2"), ['NUMBER', 'PLUS', 'NUMBER', 'EOF'])
def test_complex_expression(self):
self.assertEqual(kinds("3.5*(1-2)"), ['NUMBER', 'STAR', 'LPAREN', 'NUMBER', 'MINUS', 'NUMBER', 'RPAREN', 'EOF'])
def test_at_sign_raises(self):
with self.assertRaises(LexError) as ctx:
tokenize("1 @ 2")
self.assertIn('@', str(ctx.exception))
def test_dollar_raises(self):
with self.assertRaises(LexError):
tokenize("$5")
def test_letter_raises(self):
with self.assertRaises(LexError):
tokenize("x")
def test_error_position_in_message(self):
with self.assertRaises(LexError) as ctx:
tokenize("1 @ 2")
msg = str(ctx.exception)
self.assertIn('2', msg) # position 2
if __name__ == '__main__':
unittest.main()

View File

@ -0,0 +1,159 @@
import unittest
from calc.lexer import tokenize
from calc.parser import BinOp, Num, ParseError, Unary, parse
def p(src):
return parse(tokenize(src))
class TestPrecedence(unittest.TestCase):
"""D1 — * and / bind tighter than + and -"""
def test_add_mul(self):
# 1+2*3 → 1+(2*3)
tree = p("1+2*3")
self.assertEqual(
tree,
BinOp("+", Num(1), BinOp("*", Num(2), Num(3))),
)
def test_mul_add(self):
# 3*2+1 → (3*2)+1
tree = p("3*2+1")
self.assertEqual(
tree,
BinOp("+", BinOp("*", Num(3), Num(2)), Num(1)),
)
def test_sub_div(self):
# 10-4/2 → 10-(4/2)
tree = p("10-4/2")
self.assertEqual(
tree,
BinOp("-", Num(10), BinOp("/", Num(4), Num(2))),
)
class TestLeftAssociativity(unittest.TestCase):
"""D2 — same-precedence operators associate left"""
def test_sub_left(self):
# 8-3-2 → (8-3)-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 → (8/4)/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 → (1+2)+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 → (2*3)*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_force_add_first(self):
# (1+2)*3 → mul at root, add under left
tree = p("(1+2)*3")
self.assertEqual(
tree,
BinOp("*", BinOp("+", Num(1), Num(2)), Num(3)),
)
def test_nested_parens(self):
# ((4)) → Num(4)
tree = p("((4))")
self.assertEqual(tree, Num(4))
def test_parens_right(self):
# 2*(3+4) → mul at root, add under right
tree = p("2*(3+4)")
self.assertEqual(
tree,
BinOp("*", Num(2), BinOp("+", Num(3), Num(4))),
)
class TestUnaryMinus(unittest.TestCase):
"""D4 — leading and nested unary minus"""
def test_simple(self):
tree = p("-5")
self.assertEqual(tree, Unary("-", Num(5)))
def test_unary_paren(self):
# -(1+2) → Unary at root
tree = p("-(1+2)")
self.assertEqual(tree, Unary("-", BinOp("+", Num(1), Num(2))))
def test_mul_unary(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))))
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(self):
with self.assertRaises(ParseError):
p(")(")
def test_empty(self):
with self.assertRaises(ParseError):
p("")
def test_just_op(self):
with self.assertRaises(ParseError):
p("+")
def test_mismatched_parens(self):
with self.assertRaises(ParseError):
p("(1+2")
if __name__ == "__main__":
unittest.main()

View File

@ -0,0 +1,7 @@
# BACKLOG — phase `eval`
## Build backlog
(Builder's section — read-only for Adversary)
## Adversary findings
(None yet — phase not started)

View File

@ -0,0 +1,14 @@
# BACKLOG — phase lex
## Build backlog
- [x] Create calc/__init__.py
- [ ] Create calc/lexer.py (Token, LexError, tokenize)
- [ ] Create calc/test_lexer.py (unittest covering D1-D3)
- [ ] Run tests green
- [ ] Claim D1
- [ ] Claim D2
- [ ] Claim D3
- [ ] Claim D4
## Adversary findings
<!-- Adversary writes here -->

View File

@ -0,0 +1,10 @@
# BACKLOG — phase `parse`
## Build backlog
- [x] Write calc/parser.py (AST nodes + recursive descent parser)
- [x] Write calc/test_parser.py (unittest suite covering D1-D5)
- [ ] Claim D1-D6 after tests green
## Adversary findings
(Adversary writes here)

View File

@ -0,0 +1,17 @@
# JOURNAL — phase `lex`
## Builder — Wake 1 — 2026-06-15
- Implemented calc/lexer.py: Token dataclass, LexError, tokenize().
- Implemented calc/test_lexer.py: 15 tests covering D1-D3.
- Ran `python -m unittest -q`: 15 tests, 0 failures.
- Verified:
- `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')"` → raises `LexError: unexpected character '@' at position 2`
- Claiming D1, D2, D3, D4.
## Adversary — Wake 1 — 2026-06-15
- Initialized adversary tracking files.
- No Builder claims yet; machine-docs/ empty, only seed commit exists.
- Entering idle loop, will check every 10 min for Builder progress.

View File

@ -0,0 +1,45 @@
# JOURNAL — phase `parse`
## 2026-06-15 — Initial implementation
Plan: recursive-descent parser with two precedence levels.
- `expr` → additive level (+ -)
- `term` → multiplicative level (* /)
- `unary` → handle leading -
- `primary` → NUMBER or parenthesized expr
Grammar:
```
expr ::= term (('+' | '-') term)*
term ::= unary (('*' | '/') unary)*
unary ::= '-' unary | primary
primary ::= NUMBER | '(' expr ')'
```
Left-associativity achieved naturally by the while loop in `expr` and `term`.
## Test run output
```
Ran 36 tests in 0.001s
OK
```
## AST shape verification
```
1+2*3: BinOp(op='+', left=Num(value=1), right=BinOp(op='*', left=Num(value=2), right=Num(value=3)))
8-3-2: BinOp(op='-', left=BinOp(op='-', left=Num(value=8), right=Num(value=3)), right=Num(value=2))
8/4/2: BinOp(op='/', left=BinOp(op='/', left=Num(value=8), right=Num(value=4)), right=Num(value=2))
(1+2)*3: BinOp(op='*', left=BinOp(op='+', left=Num(value=1), right=Num(value=2)), right=Num(value=3))
-5: Unary(op='-', operand=Num(value=5))
-(1+2): Unary(op='-', operand=BinOp(op='+', left=Num(value=1), right=Num(value=2)))
3*-2: BinOp(op='*', left=Num(value=3), right=Unary(op='-', operand=Num(value=2)))
```
## Error cases
```
'1 +': ParseError: unexpected end of input
'(1': ParseError: expected RPAREN, got 'EOF' (None)
'1 2': ParseError: unexpected token 'NUMBER' (2) after expression
')(': ParseError: unexpected token 'RPAREN' (')')
'': ParseError: empty expression
```

View File

@ -0,0 +1,37 @@
# REVIEW — phase `eval`
Adversary verification log. Gates: D1 (arithmetic), D2 (division/EvalError), D3 (result type), D4 (CLI), D5 (tests green + end-to-end).
## Verdicts
### D1 — arithmetic: PASS @2026-06-15T03:53Z
Cold run of all five plan expressions:
- `2+3*4` → 14 ✓
- `(2+3)*4` → 20 ✓
- `8-3-2` → 3 ✓
- `-2+5` → 3 ✓
- `2*-3` → -6 ✓
Extra probes: `--5`→5 (double unary), `-0`→0, `100/4`→25. All correct.
### D2 — division / EvalError: PASS @2026-06-15T03:53Z
- `7/2` → 3.5 ✓
- `1/0``EvalError("division by zero")` raised (not bare `ZeroDivisionError`); CLI prints `error: division by zero` to stderr, exits 1 ✓
### D3 — result type: PASS @2026-06-15T03:53Z
- `4/2``2` (int, no trailing .0) ✓
- `7/2``3.5` (float) ✓
- Extended: `6/3`→int, `9/3`→int, `-2+5`→int; `1/3`→float, `5/4`→float. Rule consistent.
### D4 — CLI: PASS @2026-06-15T03:53Z
- `python calc.py "2+3*4"` → stdout `14`, exit 0 ✓
- `python calc.py "1 +"` → stderr `error: unexpected end of input`, exit 1, no traceback ✓
- `python calc.py "1/0"` → stderr `error: division by zero`, exit 1, no traceback ✓
- Error is to stderr only (stdout clean on error) ✓
### D5 — tests green + end-to-end: PASS @2026-06-15T03:53Z
`python -m unittest -q``Ran 47 tests in 0.001s` / `OK` — 0 failures.
Covers lex (16 tests) + parse (20 tests) + eval (11+ tests). No regression.
## Summary
All five gates PASS. No defects found. No veto.

View File

@ -0,0 +1,38 @@
# REVIEW — phase `lex` (Adversary)
## Gates
### lex/D1: PASS @2026-06-15T03:33:50Z
Cold run from Adversary clone (commit 328d25f).
- `tokenize("42")``[NUMBER(42), EOF(None)]`, value is `int`
- `tokenize("3.14")``[NUMBER(3.14), EOF(None)]`, value is `float`
- `tokenize(".5")``[NUMBER(0.5), EOF(None)]`, value is `float`
- `tokenize("10.")``[NUMBER(10.0), EOF(None)]`, value is `float`
### lex/D2: PASS @2026-06-15T03:33:50Z
Cold run from Adversary clone.
- `tokenize("1+2*3")``[NUMBER(1), PLUS('+'), NUMBER(2), STAR('*'), NUMBER(3), EOF(None)]`
- `tokenize("+-*/()") ``['PLUS', 'MINUS', 'STAR', 'SLASH', 'LPAREN', 'RPAREN', 'EOF']`
### lex/D3: PASS @2026-06-15T03:33:50Z
Cold run from Adversary clone.
- `tokenize(" 12 + 3 ")``[('NUMBER', 12), ('PLUS', '+'), ('NUMBER', 3), ('EOF', None)]`
- `tokenize("1 @ 2")` raises `LexError: unexpected character '@' at position 2` ✓ (char and position in message)
- `tokenize("$5")` raises `LexError: unexpected character '$' at position 0`
- `tokenize("x")` raises `LexError`
### lex/D4: PASS @2026-06-15T03:33:50Z
Cold run from Adversary clone.
- `python -m unittest -q` → Ran 15 tests, OK (0 failures) ✓
- `tokenize('3.5*(1-2)')``[('NUMBER', 3.5), ('STAR', '*'), ('LPAREN', '('), ('NUMBER', 1), ('MINUS', '-'), ('NUMBER', 2), ('RPAREN', ')'), ('EOF', None)]`
- `tokenize('1 @ 2')` → raises `LexError`
## Adversary findings
### AF-1 — bare dot raises `ValueError` not `LexError` [non-blocking]
`tokenize(".")` raises `ValueError: could not convert string to float: '.'` (from `float(".")` inside
the number branch) instead of `LexError`. Not a DoD FAIL — none of D1D3 test a lone `.` — but
the module leaks an internal Python exception for this invalid input. Recommend the Builder guard
with `try/except ValueError` in the number branch and re-raise as `LexError`.
Status: open (non-blocking — Builder may fix in a later phase or now at discretion)

View File

@ -0,0 +1,50 @@
# REVIEW — parse phase (Adversary)
## Status
All gates verified. Awaiting Builder to write ## DONE to STATUS-parse.md.
## Gate verdicts
**D1 (precedence): PASS** @2026-06-15T03:40Z
- `parse(tokenize('1+2*3'))``BinOp(op='+', left=Num(value=1), right=BinOp(op='*', left=Num(value=2), right=Num(value=3)))`
- `parse(tokenize('2*3+1'))``BinOp(op='+', left=BinOp(op='*', ...), right=Num(1))`
- `parse(tokenize('2+3*4*5'))``+` at root, nested `*` tree under right ✓
**D2 (left assoc): PASS** @2026-06-15T03:40Z
- `8-3-2``BinOp('-', BinOp('-', Num(8), Num(3)), Num(2))`
- `8/4/2``BinOp('/', BinOp('/', Num(8), Num(4)), Num(2))`
- `12/6*2``BinOp('*', BinOp('/', Num(12), Num(6)), Num(2))` ✓ (left-assoc across same-level ops)
- `1-2+3``BinOp('+', BinOp('-', Num(1), Num(2)), Num(3))`
**D3 (parentheses): PASS** @2026-06-15T03:40Z
- `(1+2)*3``BinOp('*', BinOp('+', Num(1), Num(2)), Num(3))`
- `((3))``Num(3)`
**D4 (unary minus): PASS** @2026-06-15T03:40Z
- `-5``Unary('-', Num(5))`
- `-(1+2)``Unary('-', BinOp('+', Num(1), Num(2)))`
- `3 * -2``BinOp('*', Num(3), Unary('-', Num(2)))`
- `--5``Unary('-', Unary('-', Num(5)))` ✓ (right-recursive _unary)
- `-(-5)``Unary('-', Unary('-', Num(5)))`
**D5 (errors): PASS** @2026-06-15T03:40Z
All 5 plan-mandated cases raise `ParseError` (not a Python built-in):
- `'1 +'` → ParseError ✓
- `'(1'` → ParseError ✓
- `'1 2'` → ParseError ✓
- `')('` → ParseError ✓
- `''` → ParseError ✓
Additional probes also raise `ParseError`: `*5`, `()`, `1+2)`, `+-5`, `+` alone.
**D6 (tests green): PASS** @2026-06-15T03:40Z
- `python -m unittest -q``Ran 36 tests in 0.001s` / `OK`
- Tests assert on tree structure via dataclass equality (not evaluation) ✓
- 7 error-case tests, 20 structural tests across D1D4
## Adversary findings
None. No defects found.
## Implementation notes (post-verdict)
Recursive-descent parser is structurally sound: `_expr → _term → _unary → _primary`.
`ParseError(Exception)` is a proper subclass. EOF sentinel token prevents index OOB.

View File

@ -0,0 +1,49 @@
# STATUS — phase `eval`
## DONE
## Gates: D1D5 — all PASS (Adversary-verified 2026-06-15T03:53Z)
Commit: `6d4fbb6f1c15402148e5e06e2f99e2b1154f4dd6`
---
## Verify commands + expected outputs
Run from repo root (clean clone):
```bash
# D5 — whole suite (lex + parse + eval), must be 0 failures
python -m unittest -q
# Expected: Ran 47 tests in <t>s / OK
# D1 — arithmetic
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" # → stderr: "error: division by zero", exit 1
# D3 — result type
python calc.py "4/2" # → 2 (int, no trailing .0)
python calc.py "7/2" # → 3.5 (float)
# D4 — CLI error handling
python calc.py "1 +" # → stderr: error message, exit 1
```
---
## Files
- `calc/evaluator.py``evaluate(node)` walking Num/BinOp/Unary, `EvalError`
- `calc.py` — CLI: tokenize→parse→evaluate, errors to stderr, exit 1
- `calc/test_evaluator.py` — 13 unittest tests covering D1D3
## Result-type rule (D3)
`evaluate` returns `int` when the float result equals its integer value (`result == int(result)`), `float` otherwise. This is applied inside `evaluate` for BinOp division results.

View File

@ -0,0 +1,46 @@
# STATUS — phase lex
## DONE
All gates D1D4 verified PASS by Adversary @2026-06-15T03:33:50Z.
AF-1 fixed: bare dot now raises LexError instead of leaking ValueError.
## Current state
Gate: D1 D2 D3 D4 — all PASS (Adversary verified)
## Gates
### D1 — numbers
**WHAT:** Integers and floats tokenize to NUMBER tokens with correct Python numeric values.
**HOW:** `python -m unittest -q calc.test_lexer.TestNumbers` (or full suite)
**EXPECTED:** 4 tests pass; `tokenize("42")``[NUMBER(42), EOF]`; `tokenize("3.14")``[NUMBER(3.14), EOF]`; `tokenize(".5")``[NUMBER(0.5), EOF]`; `tokenize("10.")``[NUMBER(10.0), EOF]`
**WHERE:** calc/lexer.py, calc/test_lexer.py
### D2 — operators & parens
**WHAT:** `+ - * / ( )` each tokenize to the correct kind.
**HOW:** `python -m unittest -q calc.test_lexer.TestOperatorsAndParens`
**EXPECTED:** 4 tests pass; `tokenize("1+2*3")``[NUMBER(1), PLUS('+'), NUMBER(2), STAR('*'), NUMBER(3), EOF(None)]`
**WHERE:** calc/lexer.py, calc/test_lexer.py
### D3 — whitespace & errors
**WHAT:** Spaces/tabs skipped; invalid chars raise LexError with the char and position.
**HOW:** `python -m unittest -q calc.test_lexer.TestWhitespaceAndErrors`
**EXPECTED:** 7 tests pass; `tokenize(" 12 + 3 ")``[NUMBER(12), PLUS, NUMBER(3), EOF]`; `tokenize("1 @ 2")` raises `LexError`
**WHERE:** calc/lexer.py, calc/test_lexer.py
### D4 — tests green
**WHAT:** Full test suite 0 failures.
**HOW:**
```bash
python -m unittest -q
python -c "from calc.lexer import tokenize; print([(t.kind,t.value) for t in tokenize('3.5*(1-2)')])"
python -c "from calc.lexer import tokenize; tokenize('1 @ 2')"
```
**EXPECTED:**
- `python -m unittest -q` → 15 tests, 0 failures
- Second command → `[('NUMBER', 3.5), ('STAR', '*'), ('LPAREN', '('), ('NUMBER', 1), ('MINUS', '-'), ('NUMBER', 2), ('RPAREN', ')'), ('EOF', None)]`
- Third command → raises `LexError: unexpected character '@' at position 2`
**WHERE:** calc/test_lexer.py (commit sha: see below)
## Commit SHA
328d25f — claim(D1,D2,D3,D4): lexer implementation + tests green

View File

@ -0,0 +1,105 @@
# STATUS — phase `parse`
## DONE
## Gates
- D1 (precedence): PASS @2026-06-15T03:40Z
- D2 (left assoc): PASS @2026-06-15T03:40Z
- D3 (parentheses): PASS @2026-06-15T03:40Z
- D4 (unary minus): PASS @2026-06-15T03:40Z
- D5 (errors): PASS @2026-06-15T03:40Z
- D6 (tests green): PASS @2026-06-15T03:40Z
## Source files
- `calc/parser.py` — AST node definitions + recursive-descent parser
- `calc/test_parser.py` — 20 unittest cases covering D1D5
## AST shape
Nodes are dataclasses defined in `calc/parser.py`:
```python
@dataclass
class Num:
value: Union[int, float]
@dataclass
class BinOp:
op: str # '+', '-', '*', '/'
left: Node
right: Node
@dataclass
class Unary:
op: str # '-'
operand: Node
```
## Verify commands (cold)
```bash
python -m unittest -q
```
Expected: `Ran 36 tests in Xs` / `OK` (0 failures)
```bash
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('1+2*3')))"
```
Expected: `BinOp(op='+', left=Num(value=1), right=BinOp(op='*', left=Num(value=2), right=Num(value=3)))`
```bash
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('8-3-2')))"
```
Expected: `BinOp(op='-', left=BinOp(op='-', left=Num(value=8), right=Num(value=3)), right=Num(value=2))`
```bash
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('8/4/2')))"
```
Expected: `BinOp(op='/', left=BinOp(op='/', left=Num(value=8), right=Num(value=4)), right=Num(value=2))`
```bash
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('(1+2)*3')))"
```
Expected: `BinOp(op='*', left=BinOp(op='+', left=Num(value=1), right=Num(value=2)), right=Num(value=3))`
```bash
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('-5')))"
```
Expected: `Unary(op='-', operand=Num(value=5))`
```bash
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('-(1+2)')))"
```
Expected: `Unary(op='-', operand=BinOp(op='+', left=Num(value=1), right=Num(value=2)))`
```bash
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('3 * -2')))"
```
Expected: `BinOp(op='*', left=Num(value=3), right=Unary(op='-', operand=Num(value=2)))`
```bash
python -c "
from calc.lexer import tokenize; from calc.parser import parse, ParseError
for expr in ['1 +', '(1', '1 2', ')(', '']:
try:
parse(tokenize(expr))
print(f'{expr!r}: NO ERROR (FAIL)')
except ParseError as e:
print(f'{expr!r}: ParseError OK')
"
```
Expected: all 5 lines print `ParseError OK`
## Gate-specific DoD mapping
**D1 — precedence:** `1+2*3` parses as `1+(2*3)``*` is under the right child of `+`, not the other way.
**D2 — left assoc:** `8-3-2` → left-leaning tree; `8/4/2` → left-leaning tree. The while-loop in `_expr`/`_term` naturally accumulates left.
**D3 — parens:** `(1+2)*3``BinOp('*', BinOp('+', ...), Num(3))``+` is under `*`'s left child.
**D4 — unary:** `-5``Unary`, `-(1+2)``Unary(BinOp(...))`, `3*-2``BinOp('*', Num(3), Unary(...))`.
**D5 — errors:** `"1 +"`, `"(1"`, `"1 2"`, `")("`, `""` all raise `ParseError` (not Python built-ins).
**D6 — tests:** `python -m unittest -q` → 36 tests, 0 failures.

View File

@ -0,0 +1,14 @@
# git history (claim/review handshake), from the run's shared bare repo
136fab8 status(eval): DONE — all D1-D5 PASS, Adversary-verified
78e6b65 review(D1,D2,D3,D4,D5): PASS — all gates verified cold at 7e18a9b; no findings
7e18a9b claim(D1-D5): evaluator + CLI + tests — all gates green
2553075 review(init): Adversary REVIEW-eval.md initialized, waiting for Builder claims
297f2ea status(parse): DONE — all D1-D6 PASS, Adversary-verified
dbbbe75 review(D1,D2,D3,D4,D5,D6): PASS — all gates verified cold at e9a5152; no findings
e9a5152 claim(D1,D2,D3,D4,D5,D6): parser complete, all 20 tests green
d6f3a2f review(init): Adversary REVIEW-parse.md initialized, waiting for Builder claims
e29a90b status(lex): DONE — all D1-D4 PASS, Adversary-verified
c974829 review(D1,D2,D3,D4): PASS — all gates verified cold at 462ad1f; F1 non-blocking finding noted
462ad1f claim(D1,D2,D3,D4): lexer complete, all 14 tests green
e9eda32 review(init): Adversary REVIEW-lex.md initialized, waiting for Builder claims
4e8f1a4 chore: seed

View File

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

View File

@ -0,0 +1 @@
original path: /tmp/ao-campaign-ufRkmF/builder-adversary-stateless/r2

View File

@ -0,0 +1,22 @@
#!/usr/bin/env python3
import sys
from calc.lexer import tokenize, LexError
from calc.parser import parse, ParseError
from calc.evaluator import evaluate, EvalError
def main():
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)))
except (LexError, ParseError, EvalError) as e:
print(f"error: {e}", file=sys.stderr)
sys.exit(1)
print(result)
if __name__ == '__main__':
main()

View File

@ -0,0 +1,42 @@
from calc.parser import Num, BinOp, Unary, parse
from calc.lexer import tokenize
class EvalError(Exception):
pass
def evaluate(node) -> int | float:
"""Walk the AST and return an int or float.
Result type rule: if the result is a whole number (no fractional part),
return int; otherwise return float.
"""
if isinstance(node, Num):
return node.value
if isinstance(node, Unary):
val = evaluate(node.operand)
if node.op == '-':
return _coerce(-val)
raise EvalError(f"unknown unary op {node.op!r}")
if isinstance(node, BinOp):
left = evaluate(node.left)
right = evaluate(node.right)
if node.op == '+':
return _coerce(left + right)
if node.op == '-':
return _coerce(left - right)
if node.op == '*':
return _coerce(left * right)
if node.op == '/':
if right == 0:
raise EvalError("division by zero")
return _coerce(left / right)
raise EvalError(f"unknown binary op {node.op!r}")
raise EvalError(f"unknown AST node {type(node).__name__!r}")
def _coerce(val: int | float) -> int | float:
if isinstance(val, float) and val == int(val):
return int(val)
return val

View File

@ -0,0 +1,50 @@
from dataclasses import dataclass
from typing import Union
class LexError(Exception):
pass
@dataclass
class Token:
kind: str
value: Union[int, float, str, None]
def __repr__(self):
return f"{self.kind}({self.value!r})"
_SINGLE = {
'+': 'PLUS',
'-': 'MINUS',
'*': 'STAR',
'/': 'SLASH',
'(': 'LPAREN',
')': 'RPAREN',
}
def tokenize(src: str) -> list:
tokens = []
i = 0
n = len(src)
while i < n:
ch = src[i]
if ch in (' ', '\t'):
i += 1
elif ch in _SINGLE:
tokens.append(Token(_SINGLE[ch], ch))
i += 1
elif ch.isdigit() or ch == '.':
j = i
while j < n and (src[j].isdigit() or src[j] == '.'):
j += 1
raw = src[i:j]
value = float(raw) if '.' in raw else int(raw)
tokens.append(Token('NUMBER', value))
i = j
else:
raise LexError(f"unexpected character {ch!r} at position {i}")
tokens.append(Token('EOF', None))
return tokens

View File

@ -0,0 +1,109 @@
from dataclasses import dataclass
from typing import Any
class ParseError(Exception):
pass
@dataclass
class Num:
value: Any
def __repr__(self):
return f"Num({self.value!r})"
@dataclass
class BinOp:
op: str
left: Any
right: Any
def __repr__(self):
return f"BinOp({self.op!r}, {self.left!r}, {self.right!r})"
@dataclass
class Unary:
op: str
operand: Any
def __repr__(self):
return f"Unary({self.op!r}, {self.operand!r})"
class _Parser:
def __init__(self, tokens):
self._tokens = tokens
self._pos = 0
def _peek(self):
return self._tokens[self._pos]
def _consume(self, kind=None):
tok = self._tokens[self._pos]
if kind and tok.kind != kind:
raise ParseError(f"expected {kind}, got {tok.kind!r} ({tok.value!r})")
self._pos += 1
return tok
def parse(self):
node = self._expr()
tok = self._peek()
if tok.kind != 'EOF':
raise ParseError(f"unexpected token {tok.kind!r} ({tok.value!r})")
return node
def _expr(self):
# expr → term (('+' | '-') term)*
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):
# term → unary (('*' | '/') unary)*
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):
# unary → '-' unary | primary
if self._peek().kind == 'MINUS':
op = self._consume().value
operand = self._unary()
return Unary(op, operand)
return self._primary()
def _primary(self):
tok = self._peek()
if tok.kind == 'NUMBER':
self._consume()
return Num(tok.value)
if tok.kind == 'LPAREN':
self._consume('LPAREN')
node = self._expr()
self._consume('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) -> Any:
"""Parse a token list from calc.lexer.tokenize into an AST.
AST node types:
Num(value) — numeric literal
BinOp(op, left, right) — binary operation; op in {'+','-','*','/'}
Unary(op, operand) — unary minus; op == '-'
Raises ParseError on malformed input.
"""
return _Parser(tokens).parse()

View File

@ -0,0 +1,55 @@
import unittest
from calc.lexer import tokenize
from calc.parser import parse
from calc.evaluator import evaluate, EvalError
def calc(s):
return evaluate(parse(tokenize(s)))
class TestArithmetic(unittest.TestCase):
def test_add_mul_precedence(self):
self.assertEqual(calc("2+3*4"), 14)
def test_paren_override(self):
self.assertEqual(calc("(2+3)*4"), 20)
def test_left_assoc_sub(self):
self.assertEqual(calc("8-3-2"), 3)
def test_unary_minus(self):
self.assertEqual(calc("-2+5"), 3)
def test_unary_in_mul(self):
self.assertEqual(calc("2*-3"), -6)
class TestDivision(unittest.TestCase):
def test_true_division(self):
self.assertAlmostEqual(calc("7/2"), 3.5)
def test_division_by_zero(self):
with self.assertRaises(EvalError):
calc("1/0")
def test_division_exact(self):
self.assertEqual(calc("4/2"), 2)
self.assertIsInstance(calc("4/2"), int)
class TestResultType(unittest.TestCase):
def test_whole_result_is_int(self):
self.assertIsInstance(calc("4/2"), int)
self.assertEqual(calc("4/2"), 2)
def test_fractional_result_is_float(self):
self.assertIsInstance(calc("7/2"), float)
self.assertAlmostEqual(calc("7/2"), 3.5)
def test_int_arithmetic_stays_int(self):
self.assertIsInstance(calc("2+3"), int)
if __name__ == '__main__':
unittest.main()

View File

@ -0,0 +1,94 @@
import unittest
from calc.lexer import tokenize, Token, LexError
def kinds(src):
return [t.kind for t in tokenize(src)]
def values(src):
return [(t.kind, t.value) for t in tokenize(src)]
class TestNumbers(unittest.TestCase):
def test_integer(self):
toks = tokenize("42")
self.assertEqual(toks[0], Token('NUMBER', 42))
self.assertIsInstance(toks[0].value, int)
self.assertEqual(toks[1].kind, 'EOF')
def test_float_decimal(self):
toks = tokenize("3.14")
self.assertEqual(toks[0], Token('NUMBER', 3.14))
self.assertIsInstance(toks[0].value, float)
def test_float_leading_dot(self):
toks = tokenize(".5")
self.assertAlmostEqual(toks[0].value, 0.5)
def test_float_trailing_dot(self):
toks = tokenize("10.")
self.assertEqual(toks[0].value, 10.0)
self.assertIsInstance(toks[0].value, float)
def test_eof_appended(self):
toks = tokenize("42")
self.assertEqual(toks[-1].kind, 'EOF')
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'])
def test_complex_expr(self):
self.assertEqual(kinds("3.5*(1-2)"),
['NUMBER', 'STAR', 'LPAREN', 'NUMBER', 'MINUS', 'NUMBER', 'RPAREN', 'EOF'])
result = values("3.5*(1-2)")
self.assertAlmostEqual(result[0][1], 3.5)
self.assertEqual(result[3][1], 1)
self.assertEqual(result[5][1], 2)
class TestWhitespaceAndErrors(unittest.TestCase):
def test_spaces_skipped(self):
self.assertEqual(kinds(" 12 + 3 "),
['NUMBER', 'PLUS', 'NUMBER', 'EOF'])
toks = tokenize(" 12 + 3 ")
self.assertEqual(toks[0].value, 12)
self.assertEqual(toks[2].value, 3)
def test_tabs_skipped(self):
self.assertEqual(kinds("1\t+\t2"), ['NUMBER', 'PLUS', 'NUMBER', 'EOF'])
def test_at_raises_lexerror(self):
with self.assertRaises(LexError):
tokenize("1 @ 2")
def test_dollar_raises_lexerror(self):
with self.assertRaises(LexError):
tokenize("$10")
def test_letter_raises_lexerror(self):
with self.assertRaises(LexError):
tokenize("abc")
def test_lexerror_message_includes_char_and_pos(self):
try:
tokenize("1 @ 2")
except LexError as e:
msg = str(e)
self.assertIn('@', msg)
self.assertIn('2', msg) # position is 2
if __name__ == '__main__':
unittest.main()

View File

@ -0,0 +1,101 @@
import unittest
from calc.lexer import tokenize
from calc.parser import parse, ParseError, Num, BinOp, Unary
def p(src):
return parse(tokenize(src))
class TestPrecedence(unittest.TestCase):
def test_mul_over_add(self):
# 1+2*3 → BinOp('+', Num(1), BinOp('*', Num(2), Num(3)))
self.assertEqual(p('1+2*3'), BinOp('+', Num(1), BinOp('*', Num(2), Num(3))))
def test_div_over_sub(self):
# 10-6/2 → BinOp('-', Num(10), BinOp('/', Num(6), Num(2)))
self.assertEqual(p('10-6/2'), BinOp('-', Num(10), BinOp('/', Num(6), Num(2))))
def test_add_left_of_mul(self):
# 1*2+3 → BinOp('+', BinOp('*', Num(1), Num(2)), Num(3))
self.assertEqual(p('1*2+3'), BinOp('+', BinOp('*', Num(1), Num(2)), Num(3)))
class TestLeftAssociativity(unittest.TestCase):
def test_sub_left_assoc(self):
# 8-3-2 → BinOp('-', BinOp('-', Num(8), Num(3)), Num(2))
self.assertEqual(p('8-3-2'), BinOp('-', BinOp('-', Num(8), Num(3)), Num(2)))
def test_div_left_assoc(self):
# 8/4/2 → BinOp('/', BinOp('/', Num(8), Num(4)), Num(2))
self.assertEqual(p('8/4/2'), BinOp('/', BinOp('/', Num(8), Num(4)), Num(2)))
def test_add_left_assoc(self):
# 1+2+3 → BinOp('+', BinOp('+', Num(1), Num(2)), Num(3))
self.assertEqual(p('1+2+3'), BinOp('+', BinOp('+', Num(1), Num(2)), Num(3)))
class TestParentheses(unittest.TestCase):
def test_paren_overrides_mul(self):
# (1+2)*3 → BinOp('*', BinOp('+', Num(1), Num(2)), Num(3))
self.assertEqual(p('(1+2)*3'), BinOp('*', BinOp('+', Num(1), Num(2)), Num(3)))
def test_paren_overrides_div(self):
# 8/(2+2) → BinOp('/', Num(8), BinOp('+', Num(2), Num(2)))
self.assertEqual(p('8/(2+2)'), BinOp('/', Num(8), BinOp('+', Num(2), Num(2))))
def test_nested_parens(self):
# ((5)) → Num(5)
self.assertEqual(p('((5))'), Num(5))
class TestUnaryMinus(unittest.TestCase):
def test_simple_neg(self):
# -5 → Unary('-', Num(5))
self.assertEqual(p('-5'), Unary('-', Num(5)))
def test_neg_paren(self):
# -(1+2) → Unary('-', BinOp('+', Num(1), Num(2)))
self.assertEqual(p('-(1+2)'), Unary('-', BinOp('+', Num(1), Num(2))))
def test_mul_neg(self):
# 3 * -2 → BinOp('*', Num(3), Unary('-', Num(2)))
self.assertEqual(p('3 * -2'), BinOp('*', Num(3), Unary('-', Num(2))))
def test_double_neg(self):
# --5 → Unary('-', Unary('-', Num(5)))
self.assertEqual(p('--5'), Unary('-', Unary('-', Num(5))))
class TestErrors(unittest.TestCase):
def test_trailing_plus(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_then_open(self):
with self.assertRaises(ParseError):
p(')(')
def test_empty_string(self):
with self.assertRaises(ParseError):
p('')
def test_only_operator(self):
with self.assertRaises(ParseError):
p('*')
def test_unclosed_paren_expr(self):
with self.assertRaises(ParseError):
p('(1+2')
if __name__ == '__main__':
unittest.main()

View File

@ -0,0 +1,9 @@
# BACKLOG — eval phase
## Build backlog
- [x] D1 — arithmetic: +, -, *, /, precedence, parens, unary minus
- [x] D2 — division: true division, EvalError on div-by-zero
- [x] D3 — result type: int for whole values, float otherwise
- [x] D4 — CLI: calc.py prints result or error to stderr with non-zero exit
- [x] D5 — tests green + end-to-end, no regressions

View File

@ -0,0 +1,12 @@
# BACKLOG — Phase `lex`
## Build backlog
- [x] D1 — Implement integer/float tokenization → NUMBER tokens
- [x] D2 — Implement operator/paren tokenization
- [x] D3 — Whitespace skipping + LexError for invalid chars
- [x] D4 — Write and pass unittest suite (14 tests, 0 failures)
- [ ] Await Adversary PASS on D1D4
## Adversary findings
<!-- Adversary writes here -->

View File

@ -0,0 +1,12 @@
# BACKLOG — Phase `parse`
## Build backlog
- [x] Implement `calc/parser.py` with `ParseError`, `Num`, `BinOp`, `Unary`, `parse()`
- [x] Implement `calc/test_parser.py` with 20 tests covering D1D5
- [x] Run `python -m unittest -q` — 34 tests, all pass
- [x] Claim D1D6
## Adversary findings
_(none yet)_

View File

@ -0,0 +1,19 @@
# DECISIONS (append-only, settled design decisions)
## lex phase
**D-LEX-1:** `Token` uses `@dataclass` for equality and repr, making test assertions clean.
**D-LEX-2:** Number parsing scans a contiguous run of digits and dots, then uses `float()` or `int()` based on presence of `.`. Edge cases `.5` and `10.` handled correctly by Python's built-in conversion.
**D-LEX-3:** `LexError` extends `Exception` directly (no custom fields) — message contains char and position as plain text, sufficient for D3.
**D-LEX-4:** EOF token always appended as the final token to signal end-of-input to the parser (future phase).
## parse phase
**D-PARSE-1:** Recursive-descent with three levels — `_expr` (additive), `_term` (multiplicative), `_unary` (prefix minus), `_primary` (atoms/parens). While loops in `_expr`/`_term` give left-associativity; calling `_term` from `_expr` gives `*/` higher precedence than `+-`.
**D-PARSE-2:** `Num`, `BinOp`, `Unary` are `@dataclass`s — equality and repr are free, making structural test assertions clean.
**D-PARSE-3:** `ParseError` extends `Exception` directly. Message contains the unexpected token kind/value, sufficient for D5.

View File

@ -0,0 +1,34 @@
# JOURNAL — eval phase
## Implementation run
Ran all checks locally before commit:
```
$ python -m unittest -q
----------------------------------------------------------------------
Ran 45 tests in 0.001s
OK
$ 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)
```
All 45 tests pass (20 from parse phase, 14 from lex phase, 11 from evaluator tests).
### Design notes
- `_coerce()` handles result type: if a float has no fractional part, cast to int.
- Division by zero caught explicitly and re-raised as `EvalError`.
- CLI catches `LexError`, `ParseError`, `EvalError` — no raw tracebacks.

View File

@ -0,0 +1,24 @@
# JOURNAL — Phase `lex`
## Implementation notes
### Design choices
- Used `@dataclass` for `Token` to get `__eq__` and `__repr__` for free — useful in tests.
- Number parsing: scan while char is digit or `.`; if `.` in raw string → `float()`, else `int()`. Handles `42`, `3.14`, `.5`, `10.`.
- Single-char operators: dict lookup for O(1) dispatch.
- LexError message includes both the character (quoted) and its 0-based position.
### Test run (verified locally)
```
$ python -m unittest -q
Ran 14 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 +1,34 @@
# JOURNAL — Phase `parse`
## Session 1 — initial implementation
**Plan:** Recursive-descent parser. Grammar:
```
expr → term (('+' | '-') term)*
term → unary (('*' | '/') unary)*
unary → '-' unary | primary
primary → NUMBER | '(' expr ')'
```
This naturally encodes `*/` tighter than `+-` (D1) and left-associativity via the while loops (D2). Unary minus (D4) handled in `_unary` before `_primary`.
**Test run:**
```
$ python -m unittest -q
----------------------------------------------------------------------
Ran 34 tests in 0.001s
OK
```
**Key assertions verified manually:**
```
1+2*3 → BinOp('+', Num(1), BinOp('*', Num(2), Num(3))) ✓ D1
8-3-2 → BinOp('-', BinOp('-', Num(8), Num(3)), Num(2)) ✓ D2
8/4/2 → BinOp('/', BinOp('/', Num(8), Num(4)), Num(2)) ✓ D2
(1+2)*3 → BinOp('*', BinOp('+', Num(1), Num(2)), Num(3)) ✓ D3
-5 → Unary('-', Num(5)) ✓ D4
-(1+2) → Unary('-', BinOp('+', Num(1), Num(2))) ✓ D4
3 * -2 → BinOp('*', Num(3), Unary('-', Num(2))) ✓ D4
```
Error cases ('1 +', '(1', '1 2', ')(', '') all raise ParseError ✓ D5

View File

@ -0,0 +1,61 @@
# REVIEW — Phase `eval`
Adversary: verified cold at commit `7e18a9b`.
## Gate verdicts
### eval/D1: PASS @2026-06-15T03:58Z
```
$ 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 ✓
```
Also probed: `2+3*4+1`→15, `100/10/2`→5, `--5`→5 (double unary). All correct.
### eval/D2: PASS @2026-06-15T03:58Z
```
$ python calc.py "7/2" → 3.5 ✓ (true division)
$ python calc.py "1/0" → stderr: "error: division by zero", exit 1 ✓
```
Cold API check: `evaluate(parse(tokenize('1/0')))` raises `EvalError`, not `ZeroDivisionError`.
Division by zero is caught before Python's operator is invoked (`right == 0` guard).
### eval/D3: PASS @2026-06-15T03:58Z
```
$ python calc.py "4/2" → 2 ✓ (int, no .0)
$ python calc.py "7/2" → 3.5 ✓ (float)
$ python calc.py "9/3" → 3 ✓
$ python calc.py "1/3" → 0.333... ✓
$ python calc.py "-6/2" → -3 ✓ (negative whole)
$ python calc.py "-7/2" → -3.5 ✓
```
`_coerce()` rule: if `isinstance(val, float) and val == int(val)` return `int(val)` else return as-is. Consistent with documented rule.
### eval/D4: PASS @2026-06-15T03:58Z
```
$ python calc.py "2+3*4" → stdout: 14, exit 0 ✓
$ python calc.py "1 +" → stderr: "error: unexpected end of input", exit 1 ✓
$ python calc.py "1/0" → stderr: "error: division by zero", exit 1 ✓
$ python calc.py "" → stderr: "error: unexpected end of input", exit 1 ✓
```
No traceback on error (1-line output only). Errors routed to stderr only (stdout empty on error).
### eval/D5: PASS @2026-06-15T03:58Z
```
$ python -m unittest -q
Ran 45 tests in 0.001s
OK
```
45 tests: 14 lex + 20 parse + 11 evaluator. 0 failures. No regression in prior phases.
`test_evaluator.py` covers D1D3 (arithmetic, division, result types, EvalError for div-by-zero).
A CLI check (D4) is exercised via the cold verify commands above.
## Adversary findings
_(none — no defects found; no veto)_
## Summary
All five DoD gates D1D5 PASS. No veto. Builder may write "## DONE" to STATUS-eval.md.

View File

@ -0,0 +1,53 @@
# REVIEW — Phase `lex`
Adversary: cold-verification log. One entry per gate per pass.
## Verdicts
### lex/D1: PASS @2026-06-15T03:52Z
Cold-ran from own clone at commit 462ad1f.
```
tokenize("42") → [('NUMBER', 42), ('EOF', None)] ✓ int
tokenize(".5") → [('NUMBER', 0.5), ('EOF', None)] ✓ float
tokenize("10.") → [('NUMBER', 10.0), ('EOF', None)] ✓ float
tokenize("3.14")→ [('NUMBER', 3.14), ('EOF', None)] ✓ float
```
EOF always appended as final token. int/float types correct.
### lex/D2: PASS @2026-06-15T03:52Z
```
tokenize("1+2*3") → ['NUMBER', 'PLUS', 'NUMBER', 'STAR', 'NUMBER', 'EOF'] ✓
tokenize("()+-(*/") → LPAREN RPAREN PLUS MINUS LPAREN STAR SLASH EOF ✓
```
All six operator/paren kinds map correctly.
### lex/D3: PASS @2026-06-15T03:52Z
```
tokenize(" 12 + 3 ") → ['NUMBER', 'PLUS', 'NUMBER', 'EOF'] ✓ spaces skipped
tokenize("1\t+\t2") → ['NUMBER', 'PLUS', 'NUMBER', 'EOF'] ✓ tabs skipped
tokenize("1 @ 2") raises LexError: unexpected character '@' at position 2 ✓
tokenize("hello") raises LexError: unexpected character 'h' at position 0 ✓
tokenize("$10") raises LexError ✓
```
LexError message contains the offending character and position.
### lex/D4: PASS @2026-06-15T03:52Z
```
$ python -m unittest -q
Ran 14 tests in 0.000s
OK
```
14 tests, 0 failures. Plan's canonical verify commands all produce expected output:
- `3.5*(1-2)``[('NUMBER', 3.5), ('STAR', '*'), ('LPAREN', '('), ('NUMBER', 1), ('MINUS', '-'), ('NUMBER', 2), ('RPAREN', ')'), ('EOF', None)]`
- `1 @ 2` → raises LexError
## Adversary findings
### F1 (non-blocking) — malformed number literals leak ValueError instead of LexError
- `tokenize("..")``ValueError: could not convert string to float: '..'`
- `tokenize("1.2.3")``ValueError: could not convert string to float: '1.2.3'`
The number-scanning loop greedily consumes all `[0-9.]` chars, then calls `float()` which throws a raw ValueError. The DoD (D3) only specifies invalid *characters* (@ $ letters) and these cases are not in the test suite, so this does **not** block DONE. Noted for later phases.
## Summary
All four DoD gates PASS. No veto. Builder may write "## DONE" to STATUS-lex.md.

View File

@ -0,0 +1,63 @@
# REVIEW — Phase `parse`
Adversary: cold-verification log. One entry per gate per pass.
## Verdicts
### parse/D1: PASS @2026-06-15T04:03Z
Cold-ran at commit e9a5152.
```
parse(tokenize('1+2*3')) → BinOp('+', Num(1), BinOp('*', Num(2), Num(3))) ✓
```
`*` binds tighter than `+` — tree structure matches plan requirement. Independently verified extra cases:
`1*2+3*4``BinOp('+', BinOp('*', Num(1), Num(2)), BinOp('*', Num(3), Num(4)))`
### parse/D2: PASS @2026-06-15T04:03Z
```
parse(tokenize('8-3-2')) → BinOp('-', BinOp('-', Num(8), Num(3)), Num(2)) ✓
parse(tokenize('8/4/2')) → BinOp('/', BinOp('/', Num(8), Num(4)), Num(2)) ✓
```
Left-associativity confirmed by `while` loop in `_expr`/`_term` (re-read code). Extra probe:
`1+2+3+4``BinOp('+', BinOp('+', BinOp('+', Num(1), Num(2)), Num(3)), Num(4))`
### parse/D3: PASS @2026-06-15T04:03Z
```
parse(tokenize('(1+2)*3')) → BinOp('*', BinOp('+', Num(1), Num(2)), Num(3)) ✓
```
Double paren `((3))``Num(3)`
### parse/D4: PASS @2026-06-15T04:03Z
```
parse(tokenize('-5')) → Unary('-', Num(5)) ✓
parse(tokenize('-(1+2)')) → Unary('-', BinOp('+', Num(1), Num(2))) ✓
parse(tokenize('3 * -2')) → BinOp('*', Num(3), Unary('-', Num(2))) ✓
```
Extra probes: `--5``Unary('-', Unary('-', Num(5)))` ✓; `1+-2``BinOp('+', Num(1), Unary('-', Num(2)))` ✓;
`-1-2``BinOp('-', Unary('-', Num(1)), Num(2))` ✓; `-(-(1))``Unary('-', Unary('-', Num(1)))`
### parse/D5: PASS @2026-06-15T04:03Z
All five plan-mandated malformed inputs raise `ParseError` (not TypeError/ValueError/IndexError):
```
'1 +' → ParseError: unexpected end of input ✓
'(1' → ParseError: expected RPAREN, got 'EOF' (None) ✓
'1 2' → ParseError: unexpected token 'NUMBER' (2) ✓
')(' → ParseError: unexpected token 'RPAREN' (')') ✓
'' → ParseError: unexpected end of input ✓
```
Extra probes all raise ParseError: `* 1`, `1 * `, `()`, `1 + ()`, `1)`, `(1+2` — all correct.
### parse/D6: PASS @2026-06-15T04:03Z
```
$ python -m unittest -q
Ran 34 tests in 0.001s
OK
```
34 tests (14 lex + 20 parse), 0 failures.
## Adversary findings
_(none — no defects found; no veto)_
## Summary
All six DoD gates PASS. No veto. Builder may write "## DONE" to STATUS-parse.md.

View File

@ -0,0 +1,38 @@
# STATUS — eval phase
## DONE
## Gate: D1D5 PASS (Adversary-verified @2026-06-15T03:58Z, commit 7e18a9b)
### What is claimed
All five gates D1D5 are implemented and verified locally.
### Commit
(see latest `claim(D1-D5)` commit on main)
### Artifacts
- `calc/evaluator.py``evaluate(node) -> int | float`, `EvalError`
- `calc/test_evaluator.py` — unittest suite covering D1D3
- `calc.py` — CLI entry point (D4)
### How to verify (cold)
```bash
python -m unittest -q # 45 tests, 0 failures
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 to stderr, exit 1
python calc.py "1 +" # error to stderr, exit 1
```
### Expected outputs
| command | stdout | stderr | exit |
|---------|--------|--------|------|
| `python calc.py "2+3*4"` | `14` | — | 0 |
| `python calc.py "(2+3)*4"` | `20` | — | 0 |
| `python calc.py "7/2"` | `3.5` | — | 0 |
| `python calc.py "4/2"` | `2` | — | 0 |
| `python calc.py "1/0"` | — | `error: division by zero` | 1 |
| `python calc.py "1 +"` | — | `error: unexpected end of input` | 1 |

View File

@ -0,0 +1,49 @@
# STATUS — Phase `lex`
## DONE
All gates D1D4: PASS (Adversary-verified @2026-06-15T03:52Z, commit c974829).
Note: Adversary F1 (non-blocking) — malformed floats like `".."` leak ValueError; not in DoD scope.
## Current State
Gates D1D4: CLAIMED, awaiting Adversary verification.
## Claims
### D1 — numbers
**WHAT:** Integers and floats tokenize to NUMBER tokens with numeric values.
**HOW:** Run `python -c "from calc.lexer import tokenize; print([(t.kind,t.value) for t in tokenize('42')])"` — expected `[('NUMBER', 42), ('EOF', None)]`. Also `.5` → float 0.5, `10.` → float 10.0, `3.14` → float 3.14.
**EXPECTED:** `[('NUMBER', 42), ('EOF', None)]`
**WHERE:** `calc/lexer.py`, `calc/test_lexer.py`
### D2 — operators & parens
**WHAT:** `+ - * / ( )` each tokenize to PLUS/MINUS/STAR/SLASH/LPAREN/RPAREN; expression `1+2*3` yields NUMBER PLUS NUMBER STAR NUMBER EOF.
**HOW:** `python -c "from calc.lexer import tokenize; print([t.kind for t in tokenize('1+2*3')])"`
**EXPECTED:** `['NUMBER', 'PLUS', 'NUMBER', 'STAR', 'NUMBER', 'EOF']`
**WHERE:** `calc/lexer.py`
### D3 — whitespace & errors
**WHAT:** Spaces/tabs skipped; invalid characters raise LexError with character and position.
**HOW:**
- `python -c "from calc.lexer import tokenize; print([t.kind for t in tokenize(' 12 + 3 ')])"``['NUMBER', 'PLUS', 'NUMBER', 'EOF']`
- `python -c "from calc.lexer import tokenize; tokenize('1 @ 2')"` → raises `LexError: unexpected character '@' at position 2`
**EXPECTED:** whitespace omitted from output; LexError raised with `@` and `2` in message
**WHERE:** `calc/lexer.py`
### D4 — tests green
**WHAT:** `calc/test_lexer.py` passes `python -m unittest -q` with 0 failures (14 tests).
**HOW:** `python -m unittest -q` from repo root
**EXPECTED:** `Ran 14 tests in 0.000s\nOK`
**WHERE:** `calc/test_lexer.py`
## Verification commands (exact, from repo root)
```bash
python -m unittest -q
python -c "from calc.lexer import tokenize; print([(t.kind,t.value) for t in tokenize('3.5*(1-2)')])"
python -c "from calc.lexer import tokenize; tokenize('1 @ 2')"
```
Expected outputs:
1. `Ran 14 tests in 0.000s` / `OK`
2. `[('NUMBER', 3.5), ('STAR', '*'), ('LPAREN', '('), ('NUMBER', 1), ('MINUS', '-'), ('NUMBER', 2), ('RPAREN', ')'), ('EOF', None)]`
3. `LexError: unexpected character '@' at position 2`

View File

@ -0,0 +1,78 @@
# STATUS — Phase `parse`
## DONE
Gate: D1,D2,D3,D4,D5,D6 — all PASS (Adversary-verified @2026-06-15T04:03Z, commit e9a5152)
## What is claimed
All DoD gates D1D6 implemented and all 20 parser tests pass (34 total across lex+parse).
**Commit:** see `claim(D1D6)` commit on main.
## How to verify (cold, from a fresh clone)
```bash
cd <clone>
python -m unittest -q
# Expect: Ran 34 tests in ~0.001s — OK
# D1 — precedence (*/ tighter than +-)
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(repr(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(repr(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(repr(parse(tokenize('8/4/2'))))"
# Expected: BinOp('/', BinOp('/', Num(8), Num(4)), Num(2))
# D3 — parentheses override
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(repr(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(repr(parse(tokenize('-5'))))"
# Expected: Unary('-', Num(5))
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(repr(parse(tokenize('-(1+2)'))))"
# Expected: Unary('-', BinOp('+', Num(1), Num(2)))
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(repr(parse(tokenize('3 * -2'))))"
# Expected: BinOp('*', Num(3), Unary('-', Num(2)))
# D5 — errors raise ParseError
python -c "from calc.lexer import tokenize; from calc.parser import parse, ParseError
for src in ['1 +', '(1', '1 2', ')(', '']:
try:
parse(tokenize(src))
print(f'FAIL: {src!r} did not raise')
except ParseError as e:
print(f'OK ParseError: {src!r}')
"
```
## Expected outputs
- `python -m unittest -q``Ran 34 tests in ...s\nOK`
- `1+2*3``BinOp('+', Num(1), BinOp('*', Num(2), Num(3)))`
- `8-3-2``BinOp('-', BinOp('-', Num(8), Num(3)), Num(2))`
- `8/4/2``BinOp('/', BinOp('/', Num(8), Num(4)), Num(2))`
- `(1+2)*3``BinOp('*', BinOp('+', Num(1), Num(2)), Num(3))`
- `-5``Unary('-', Num(5))`
- `-(1+2)``Unary('-', BinOp('+', Num(1), Num(2)))`
- `3 * -2``BinOp('*', Num(3), Unary('-', Num(2)))`
- All 5 malformed inputs → `OK ParseError`
## AST shape (for evaluator)
```
Num(value) — numeric literal; value is int or float
BinOp(op, left, right) — binary; op in {'+', '-', '*', '/'}
Unary(op, operand) — unary minus; op == '-'
```
All three are `@dataclass`, so `==` comparison works for tests.
## Where
- `calc/parser.py` — parser implementation
- `calc/test_parser.py` — 20 parser tests covering D1D5

View File

@ -0,0 +1,15 @@
# git history (claim/review handshake), from the run's shared bare repo
90a171c status(eval): mark DONE — all D1-D5 Adversary-verified PASS
233ccfe review(D1,D2,D3,D4,D5): PASS — all gates verified cold, 66/66 tests, no defects found
47f3478 claim(D1,D2,D3,D4,D5): implement evaluator+CLI+tests, all gates claimed
14db736 feat(eval): implement evaluator, CLI, and test suite
66c55b4 review(eval): Adversary starting — monitoring for Builder gate claims
3b3ee90 status(parse): mark DONE — all D1-D6 Adversary-verified PASS
7eb69be review(D1,D2,D3,D4,D5,D6): PASS — all gates verified cold, 44/44 tests, no defects found
ab253ee claim(D1,D2,D3,D4,D5,D6): implement parser with full test suite
9202718 review(parse): Adversary starting — monitoring for Builder gate claims
7a13a51 status(lex): mark DONE — all D1-D4 Adversary-verified PASS
197f29d review(D1,D2,D3,D4): PASS — all gates verified cold, 21/21 tests, no defects found
93a9cc9 claim(D1,D2,D3,D4): implement lexer with full test suite
cd8d498 review(init): Adversary starting — monitoring for Builder gate claims
57b4566 chore: seed

View File

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

View File

@ -0,0 +1 @@
original path: /tmp/ao-campaign-ufRkmF/builder-adversary-stateless/r3

View File

@ -0,0 +1,36 @@
"""Command-line interface: python calc.py "<expression>"
Result printing rule:
- If the result is a whole number (e.g. 2.0), print as int (e.g. "2").
- Otherwise print as float (e.g. "3.5").
"""
import sys
from calc.lexer import tokenize, LexError
from calc.parser import parse, ParseError
from calc.evaluator import evaluate, EvalError
def _format(value) -> str:
if isinstance(value, float) and value.is_integer():
return str(int(value))
return str(value)
def main():
if len(sys.argv) != 2:
print(f"usage: {sys.argv[0]} <expression>", file=sys.stderr)
sys.exit(1)
expr = sys.argv[1]
try:
tokens = tokenize(expr)
ast = parse(tokens)
result = evaluate(ast)
print(_format(result))
except (LexError, ParseError, EvalError) as exc:
print(f"error: {exc}", file=sys.stderr)
sys.exit(1)
if __name__ == "__main__":
main()

View File

@ -0,0 +1,34 @@
"""Evaluator: walks the AST produced by calc.parser and returns a numeric result."""
from __future__ import annotations
from .parser import Num, BinOp, Unary
class EvalError(Exception):
pass
def evaluate(node) -> int | float:
"""Recursively evaluate an AST node and return int or float."""
if isinstance(node, Num):
return node.value
if isinstance(node, Unary):
operand = evaluate(node.operand)
if node.op == "-":
return -operand
raise EvalError(f"unknown unary op: {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 op: {node.op!r}")
raise EvalError(f"unknown node type: {type(node).__name__!r}")

View File

@ -0,0 +1,58 @@
"""Lexer for arithmetic expressions."""
from __future__ import annotations
import re
class LexError(Exception):
pass
class Token:
__slots__ = ("kind", "value")
def __init__(self, kind: str, value):
self.kind = kind
self.value = value
def __repr__(self):
return f"Token({self.kind!r}, {self.value!r})"
def __eq__(self, other):
return isinstance(other, Token) and self.kind == other.kind and self.value == other.value
_NUMBER_RE = re.compile(r"\d+\.?\d*|\.\d+")
_SINGLE = {
"+": "PLUS",
"-": "MINUS",
"*": "STAR",
"/": "SLASH",
"(": "LPAREN",
")": "RPAREN",
}
def tokenize(src: str) -> list[Token]:
tokens: list[Token] = []
i = 0
while i < len(src):
ch = src[i]
if ch in " \t":
i += 1
continue
if ch in _SINGLE:
tokens.append(Token(_SINGLE[ch], ch))
i += 1
continue
m = _NUMBER_RE.match(src, i)
if m:
raw = m.group()
value = float(raw) if "." in raw else int(raw)
tokens.append(Token("NUMBER", value))
i = m.end()
continue
raise LexError(f"unexpected character {ch!r} at position {i}")
tokens.append(Token("EOF", None))
return tokens

View File

@ -0,0 +1,141 @@
"""Recursive-descent parser for arithmetic expressions.
Grammar (precedence low → high):
expr = term ( ('+' | '-') term )*
term = unary ( ('*' | '/') unary )*
unary = '-' unary | primary
primary = NUMBER | '(' expr ')'
AST nodes (stable shape for the evaluator):
Num(value) numeric literal; value is int or float
BinOp(op, left, right) op is one of '+', '-', '*', '/'
Unary(op, operand) op is '-'
"""
from __future__ import annotations
from typing import List
from .lexer import Token
class ParseError(Exception):
pass
class Num:
__slots__ = ("value",)
def __init__(self, value):
self.value = value
def __repr__(self):
return f"Num({self.value!r})"
def __eq__(self, other):
return isinstance(other, Num) and self.value == other.value
class BinOp:
__slots__ = ("op", "left", "right")
def __init__(self, op: str, left, right):
self.op = op
self.left = left
self.right = right
def __repr__(self):
return f"BinOp({self.op!r}, {self.left!r}, {self.right!r})"
def __eq__(self, other):
return (
isinstance(other, BinOp)
and self.op == other.op
and self.left == other.left
and self.right == other.right
)
class Unary:
__slots__ = ("op", "operand")
def __init__(self, op: str, operand):
self.op = op
self.operand = operand
def __repr__(self):
return f"Unary({self.op!r}, {self.operand!r})"
def __eq__(self, other):
return (
isinstance(other, Unary)
and self.op == other.op
and self.operand == other.operand
)
class _Parser:
def __init__(self, tokens: List[Token]):
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):
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})")
return node
def _expr(self):
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 = 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):
if self._peek().kind == "MINUS":
op = self._consume().value
operand = self._unary()
return Unary(op, operand)
return self._primary()
def _primary(self):
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
raise ParseError(f"unexpected token {tok.kind!r} ({tok.value!r})")
def parse(tokens: List[Token]):
"""Parse a token list produced by calc.lexer.tokenize and return an AST root node."""
return _Parser(tokens).parse()

View File

@ -0,0 +1,124 @@
"""Tests for calc.evaluator (D1D3) and CLI (D4)."""
import subprocess
import sys
import unittest
from calc.lexer import tokenize
from calc.parser import parse
from calc.evaluator import evaluate, EvalError
def ev(s):
return evaluate(parse(tokenize(s)))
class D1Arithmetic(unittest.TestCase):
def test_add_mul_precedence(self):
self.assertEqual(ev("2+3*4"), 14)
def test_paren_override_precedence(self):
self.assertEqual(ev("(2+3)*4"), 20)
def test_left_associative_sub(self):
self.assertEqual(ev("8-3-2"), 3)
def test_unary_minus_add(self):
self.assertEqual(ev("-2+5"), 3)
def test_mul_unary_minus(self):
self.assertEqual(ev("2*-3"), -6)
def test_simple_add(self):
self.assertEqual(ev("1+2"), 3)
def test_simple_sub(self):
self.assertEqual(ev("10-4"), 6)
def test_double_unary(self):
self.assertEqual(ev("--3"), 3)
class D2Division(unittest.TestCase):
def test_true_division(self):
self.assertAlmostEqual(ev("7/2"), 3.5)
def test_exact_division(self):
self.assertEqual(ev("4/2"), 2.0)
def test_div_by_zero_raises_eval_error(self):
with self.assertRaises(EvalError):
ev("1/0")
def test_div_by_zero_not_zero_division_error(self):
try:
ev("1/0")
except EvalError:
pass
except ZeroDivisionError:
self.fail("ZeroDivisionError escaped; expected EvalError")
def test_div_by_zero_expression(self):
with self.assertRaises(EvalError):
ev("5/(3-3)")
class D3ResultType(unittest.TestCase):
"""_format is tested indirectly through the CLI; here we check evaluate() types."""
def test_int_input_returns_int(self):
self.assertIsInstance(ev("3"), int)
def test_non_whole_div_returns_float(self):
result = ev("7/2")
self.assertIsInstance(result, float)
self.assertAlmostEqual(result, 3.5)
def test_whole_div_result_is_float_value_2(self):
result = ev("4/2")
self.assertAlmostEqual(result, 2.0)
class D4CLI(unittest.TestCase):
def _run(self, expr):
return subprocess.run(
[sys.executable, "calc.py", expr],
capture_output=True,
text=True,
)
def test_precedence_14(self):
r = self._run("2+3*4")
self.assertEqual(r.returncode, 0)
self.assertEqual(r.stdout.strip(), "14")
def test_paren_20(self):
r = self._run("(2+3)*4")
self.assertEqual(r.returncode, 0)
self.assertEqual(r.stdout.strip(), "20")
def test_true_division_3_5(self):
r = self._run("7/2")
self.assertEqual(r.returncode, 0)
self.assertEqual(r.stdout.strip(), "3.5")
def test_whole_division_no_trailing_dot(self):
r = self._run("4/2")
self.assertEqual(r.returncode, 0)
self.assertEqual(r.stdout.strip(), "2")
def test_div_by_zero_stderr_nonzero(self):
r = self._run("1/0")
self.assertNotEqual(r.returncode, 0)
self.assertGreater(len(r.stderr.strip()), 0)
self.assertEqual(r.stdout.strip(), "")
def test_invalid_expr_stderr_nonzero(self):
r = self._run("1 +")
self.assertNotEqual(r.returncode, 0)
self.assertGreater(len(r.stderr.strip()), 0)
self.assertEqual(r.stdout.strip(), "")
if __name__ == "__main__":
unittest.main()

View File

@ -0,0 +1,126 @@
"""Unit tests for calc.lexer — covers D1D3."""
import unittest
from calc.lexer import tokenize, Token, LexError
def kinds(src: str) -> list[str]:
return [t.kind for t in tokenize(src)]
def values(src: str) -> list:
return [t.value for t in tokenize(src)]
class TestNumbers(unittest.TestCase):
def test_integer(self):
toks = tokenize("42")
self.assertEqual(toks, [Token("NUMBER", 42), Token("EOF", None)])
self.assertIsInstance(toks[0].value, int)
def test_float_standard(self):
toks = tokenize("3.14")
self.assertEqual(len(toks), 2)
self.assertEqual(toks[0].kind, "NUMBER")
self.assertAlmostEqual(toks[0].value, 3.14)
self.assertIsInstance(toks[0].value, float)
def test_float_leading_dot(self):
toks = tokenize(".5")
self.assertEqual(toks[0].kind, "NUMBER")
self.assertAlmostEqual(toks[0].value, 0.5)
self.assertIsInstance(toks[0].value, float)
def test_float_trailing_dot(self):
toks = tokenize("10.")
self.assertEqual(toks[0].kind, "NUMBER")
self.assertAlmostEqual(toks[0].value, 10.0)
self.assertIsInstance(toks[0].value, float)
def test_zero(self):
toks = tokenize("0")
self.assertEqual(toks[0], Token("NUMBER", 0))
class TestOperatorsAndParens(unittest.TestCase):
def test_plus(self):
self.assertIn("PLUS", kinds("1+2"))
def test_minus(self):
self.assertIn("MINUS", kinds("1-2"))
def test_star(self):
self.assertIn("STAR", kinds("1*2"))
def test_slash(self):
self.assertIn("SLASH", kinds("1/2"))
def test_lparen(self):
self.assertIn("LPAREN", kinds("(1)"))
def test_rparen(self):
self.assertIn("RPAREN", kinds("(1)"))
def test_expr_kinds(self):
self.assertEqual(
kinds("1+2*3"),
["NUMBER", "PLUS", "NUMBER", "STAR", "NUMBER", "EOF"],
)
def test_eof_always_last(self):
for src in ["", "1", "1+2", "()"]:
self.assertEqual(tokenize(src)[-1].kind, "EOF")
class TestWhitespaceAndErrors(unittest.TestCase):
def test_spaces_between_tokens(self):
self.assertEqual(
kinds(" 12 + 3 "),
["NUMBER", "PLUS", "NUMBER", "EOF"],
)
toks = tokenize(" 12 + 3 ")
self.assertEqual(toks[0].value, 12)
self.assertEqual(toks[2].value, 3)
def test_tabs_skipped(self):
self.assertEqual(kinds("\t1\t+\t2\t"), ["NUMBER", "PLUS", "NUMBER", "EOF"])
def test_complex_expr(self):
self.assertEqual(
kinds("3.5*(1-2)"),
["NUMBER", "STAR", "LPAREN", "NUMBER", "MINUS", "NUMBER", "RPAREN", "EOF"],
)
toks = tokenize("3.5*(1-2)")
self.assertAlmostEqual(toks[0].value, 3.5)
self.assertEqual(toks[3].value, 1)
self.assertEqual(toks[5].value, 2)
def test_invalid_at_raises(self):
with self.assertRaises(LexError):
tokenize("1 @ 2")
def test_invalid_dollar_raises(self):
with self.assertRaises(LexError):
tokenize("$")
def test_invalid_letter_raises(self):
with self.assertRaises(LexError):
tokenize("a")
def test_lex_error_message_contains_char(self):
try:
tokenize("1 @ 2")
self.fail("LexError not raised")
except LexError as e:
self.assertIn("@", str(e))
def test_lex_error_message_contains_position(self):
try:
tokenize("1 @ 2")
self.fail("LexError not raised")
except LexError as e:
self.assertIn("2", str(e))
if __name__ == "__main__":
unittest.main()

View File

@ -0,0 +1,133 @@
"""Tests for calc.parser — asserts on AST structure, not evaluation."""
import unittest
from .lexer import tokenize
from .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)))
self.assertEqual(p("1+2*3"), BinOp("+", Num(1), BinOp("*", Num(2), Num(3))))
def test_mul_add(self):
# 2*3+1 => BinOp('+', BinOp('*', Num(2), Num(3)), Num(1))
self.assertEqual(p("2*3+1"), BinOp("+", BinOp("*", Num(2), Num(3)), Num(1)))
def test_sub_div(self):
# 10-4/2 => BinOp('-', Num(10), BinOp('/', Num(4), Num(2)))
self.assertEqual(p("10-4/2"), BinOp("-", Num(10), BinOp("/", Num(4), Num(2))))
def test_mixed_four_ops(self):
# 1+2*3-4/2 => BinOp('-', BinOp('+', Num(1), BinOp('*', Num(2), Num(3))),
# BinOp('/', Num(4), Num(2)))
self.assertEqual(
p("1+2*3-4/2"),
BinOp(
"-",
BinOp("+", Num(1), BinOp("*", Num(2), Num(3))),
BinOp("/", Num(4), Num(2)),
),
)
class TestLeftAssociativity(unittest.TestCase):
"""D2 — same-precedence operators associate left."""
def test_subtraction_left(self):
# 8-3-2 => BinOp('-', BinOp('-', Num(8), Num(3)), Num(2))
self.assertEqual(p("8-3-2"), BinOp("-", BinOp("-", Num(8), Num(3)), Num(2)))
def test_division_left(self):
# 8/4/2 => BinOp('/', BinOp('/', Num(8), Num(4)), Num(2))
self.assertEqual(p("8/4/2"), BinOp("/", BinOp("/", Num(8), Num(4)), Num(2)))
def test_addition_left(self):
# 1+2+3 => BinOp('+', BinOp('+', Num(1), Num(2)), Num(3))
self.assertEqual(p("1+2+3"), BinOp("+", BinOp("+", Num(1), Num(2)), Num(3)))
def test_multiplication_left(self):
# 2*3*4 => BinOp('*', BinOp('*', Num(2), Num(3)), Num(4))
self.assertEqual(p("2*3*4"), BinOp("*", BinOp("*", Num(2), Num(3)), Num(4)))
class TestParentheses(unittest.TestCase):
"""D3 — parentheses override precedence."""
def test_paren_add_then_mul(self):
# (1+2)*3 => BinOp('*', BinOp('+', Num(1), Num(2)), Num(3))
self.assertEqual(p("(1+2)*3"), BinOp("*", BinOp("+", Num(1), Num(2)), Num(3)))
def test_paren_nested(self):
# (1+(2*3)) => BinOp('+', Num(1), BinOp('*', Num(2), Num(3)))
self.assertEqual(
p("(1+(2*3))"), BinOp("+", Num(1), BinOp("*", Num(2), Num(3)))
)
def test_paren_changes_assoc(self):
# 8-(3-2) => BinOp('-', Num(8), BinOp('-', Num(3), Num(2)))
self.assertEqual(p("8-(3-2)"), BinOp("-", Num(8), BinOp("-", Num(3), Num(2))))
def test_paren_single_number(self):
self.assertEqual(p("(42)"), Num(42))
class TestUnaryMinus(unittest.TestCase):
"""D4 — leading and nested unary minus."""
def test_simple_unary(self):
self.assertEqual(p("-5"), Unary("-", Num(5)))
def test_unary_paren(self):
# -(1+2) => Unary('-', BinOp('+', Num(1), Num(2)))
self.assertEqual(p("-(1+2)"), Unary("-", BinOp("+", Num(1), Num(2))))
def test_mul_unary(self):
# 3 * -2 => BinOp('*', Num(3), Unary('-', Num(2)))
self.assertEqual(p("3 * -2"), BinOp("*", Num(3), Unary("-", Num(2))))
def test_double_unary(self):
# --5 => Unary('-', Unary('-', Num(5)))
self.assertEqual(p("--5"), Unary("-", Unary("-", Num(5))))
def test_unary_in_expr(self):
# 1 + -2 => BinOp('+', Num(1), Unary('-', Num(2)))
self.assertEqual(p("1 + -2"), BinOp("+", Num(1), Unary("-", Num(2))))
class TestErrors(unittest.TestCase):
"""D5 — malformed input raises ParseError."""
def test_trailing_operator(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_only_operator(self):
with self.assertRaises(ParseError):
p("*")
if __name__ == "__main__":
unittest.main()

View File

@ -0,0 +1,9 @@
# BACKLOG-eval
## Build backlog
(Builder-owned — read-only for Adversary)
All gates D1-D5 implemented and claimed. Awaiting Adversary PASS.
## Adversary findings
None yet.

View File

@ -0,0 +1,12 @@
# BACKLOG — Phase `lex`
## Build backlog
- [x] D1: integers and floats tokenize correctly
- [x] D2: operators and parens tokenize correctly
- [x] D3: whitespace skipped; invalid chars raise LexError
- [x] D4: test suite green (21 tests, 0 failures)
- [ ] Await Adversary PASS on D1D4
## Adversary findings
<!-- Adversary writes here -->

View File

@ -0,0 +1,13 @@
# BACKLOG — Phase `parse`
## Build backlog
- [x] D1 — Precedence: implement grammar with `*`/`/` tighter than `+`/`-`
- [x] D2 — Left associativity: iterative left-fold in `_expr` and `_term`
- [x] D3 — Parentheses: `_primary` handles `LPAREN expr RPAREN`
- [x] D4 — Unary minus: `_unary` handles leading `-` recursively
- [x] D5 — Errors: `ParseError` raised for all malformed inputs
- [x] D6 — Tests green: `calc/test_parser.py` with 23 structural assertions
## Adversary findings
(none yet)

View File

@ -0,0 +1,10 @@
# DECISIONS (append-only, shared)
## D-LEX-1: Token representation
Chose `__slots__`-based class over dataclass or namedtuple. Reason: explicit, zero-overhead, easy for downstream parser/evaluator to consume via `t.kind` / `t.value` without import coupling.
## D-LEX-2: Number regex
`r"\d+\.?\d*|\.\d+"` handles integers, trailing-dot floats (`10.`), leading-dot floats (`.5`), and standard floats (`3.14`). The alternation order matters: `\d+\.?\d*` before `\.\d+` so integers match first.
## D-LEX-3: int vs float distinction
`int(raw)` when no `.` in the matched string; `float(raw)` otherwise. Preserves the plan's requirement that `42` yields int value and `3.14` yields float value.

View File

@ -0,0 +1,45 @@
# JOURNAL-eval — Adversary notes
## 2026-06-15T04:08Z — Initialized
Adversary starting for eval phase. Parse phase completed (all D1-D6 PASS).
Waiting for Builder to create STATUS-eval.md and claim gates.
Planned verification approach:
- D1: Run exact arithmetic expressions from plan, check output values
- D2: Verify true division (7/2=3.5), EvalError on divide-by-zero (not bare ZeroDivisionError)
- D3: Check output format — whole numbers no .0, fractions as float
- D4: CLI exit codes, stderr for errors, no tracebacks
- D5: Full test suite green, no regressions in lex+parse tests
---
## 2026-06-15T04:10Z — Builder implementation notes
Built evaluator, CLI, and tests from scratch in one pass.
### evaluator.py design
- EvalError wraps division-by-zero so the bare ZeroDivisionError never escapes the API.
- evaluate() is a simple recursive dispatch on Num/BinOp/Unary node types.
- True division via Python's `/` operator naturally produces float.
### calc.py CLI design
- _format() prints int for whole-valued floats (value.is_integer()), str(float) otherwise.
- All LexError/ParseError/EvalError caught → stderr message + exit(1), no traceback.
### Test run (commit 14db736)
```
$ python -m unittest -q
Ran 66 tests in 0.147s
OK
```
### CLI spot checks
```
$ 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" → stderr: error: division by zero, exit 1
$ python calc.py "1 +" → stderr: error: unexpected token 'EOF' (None), exit 1
```

View File

@ -0,0 +1,32 @@
# JOURNAL — Phase `lex` (Builder)
## Implementation
Built `calc/lexer.py` with:
- `Token` dataclass-style class with `__slots__ = ("kind", "value")` for efficiency
- `LexError(Exception)` for invalid characters
- `tokenize(src)` using `re.compile(r"\d+\.?\d*|\.\d+")` for number matching
- Integer if no `.` in raw string; float otherwise
- Single-char dispatch table `_SINGLE` for operators/parens
- Raises `LexError` with char + position for unknown characters
- Appends `EOF` token at end
## Test run
```
$ python -m unittest -q
Ran 21 tests in 0.000s
OK
```
## Cold-verify outputs
```
$ 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 +1,43 @@
# JOURNAL — Phase `parse` (Builder)
## 2026-06-15 — Implementation
### Design decisions
- Grammar: `expr → term ((+|-) term)*`, `term → unary ((*|/) unary)*`, `unary → - unary | primary`, `primary → NUMBER | ( expr )`. Standard Pratt/recursive-descent, iterative left-fold for left associativity.
- Node types: `Num`, `BinOp`, `Unary` with `__repr__` and `__eq__` for structural test assertions.
- `ParseError` defined in `parser.py`.
### Test run output
```
$ python -m unittest -q
Ran 44 tests in 0.001s
OK
```
### Cold-verify commands verified locally
```
$ python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('1+2*3')))"
BinOp('+', Num(1), BinOp('*', Num(2), Num(3)))
$ python -c "from calc.lexer import tokenize; from calc.parser import parse; parse(tokenize('1 +'))"
calc.parser.ParseError: unexpected token 'EOF' (None)
(exit 1)
$ python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('8-3-2')))"
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')))"
BinOp('/', BinOp('/', Num(8), Num(4)), Num(2))
$ python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('(1+2)*3')))"
BinOp('*', BinOp('+', Num(1), Num(2)), Num(3))
$ python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('-5')))"
Unary('-', Num(5))
$ python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('-(1+2)')))"
Unary('-', BinOp('+', Num(1), Num(2)))
$ python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('3 * -2')))"
BinOp('*', Num(3), Unary('-', Num(2)))
```

View File

@ -0,0 +1,73 @@
# REVIEW-eval — Adversary verdicts
## Phase: eval
Adversary started: 2026-06-15T04:08Z
---
## eval/D1: PASS @2026-06-15T04:12Z
Cold re-run: all 5 plan expressions correct.
- `2+3*4``14`
- `(2+3)*4``20`
- `8-3-2``3`
- `-2+5``3`
- `2*-3``-6`
Additional adversarial: `((2+3)*4-10)/2``5`, `-(-3)``3`, `1-2*3+4``-1` — all correct.
D1Arithmetic suite: 8 tests, OK.
---
## eval/D2: PASS @2026-06-15T04:12Z
Cold re-run:
- `7/2``3.5` (true division) ✓
- `1/0``EvalError("division by zero")` raised, not bare `ZeroDivisionError`
- `5/(3-3)``EvalError` (expression-based zero denominator) ✓
- `EvalError.__bases__` = `(Exception,)` — not a subclass of `ZeroDivisionError`
D2Division suite: 5 tests, OK.
---
## eval/D3: PASS @2026-06-15T04:12Z
Cold re-run:
- `python calc.py "4/2"``2` (no trailing `.0`) ✓
- `python calc.py "7/2"``3.5`
- `_format(5)``'5'`, `_format(5.0)``'5'`, `_format(3.5)``'3.5'`
- Integer inputs (e.g. `2+3`) return `int` from `evaluate()`, format correctly ✓
D3ResultType suite: 3 tests, OK.
---
## eval/D4: PASS @2026-06-15T04:12Z
Cold re-run:
- `python calc.py "2+3*4"` → stdout `14`, exit 0 ✓
- `python calc.py "(2+3)*4"` → stdout `20`, exit 0 ✓
- `python calc.py "1/0"` → stderr `error: division by zero`, exit 1, stdout empty ✓
- `python calc.py "1 +"` → stderr `error: unexpected token 'EOF' (None)`, exit 1, stdout empty ✓
- No traceback in stderr on error ✓
- No args / too many args → usage to stderr, exit 1 ✓
D4CLI suite: 6 tests, OK.
---
## eval/D5: PASS @2026-06-15T04:12Z
Cold re-run: `python -m unittest -q``Ran 66 tests in 0.153s` / `OK`
- Lex tests (21) + parse tests (23) + evaluator/CLI tests (22) all green ✓
- No regressions in prior phases ✓
- Full suite run twice; consistent result ✓
---
## Summary
All gates D1D5: **PASS**. No defects. No VETO.
Verified cold from commit `14db736` / claimed at `47f3478`.

View File

@ -0,0 +1,44 @@
# REVIEW — Phase `lex` (Adversary)
## Verdicts
### D1: PASS @2026-06-15T04:02Z
Cold-run evidence:
- `tokenize("42")``[('NUMBER', 42), ('EOF', None)]`, value is `<class 'int'>`
- `tokenize("3.14")``NUMBER(3.14)` as float ✓
- `tokenize(".5")``NUMBER(0.5)` as float ✓
- `tokenize("10.")``NUMBER(10.0)` as float ✓
Regex `\d+\.?\d*|\.\d+` correctly handles all three float forms.
### D2: PASS @2026-06-15T04:02Z
Cold-run evidence:
- `tokenize("1+2*3")``['NUMBER', 'PLUS', 'NUMBER', 'STAR', 'NUMBER', 'EOF']`
- All six operators (`+ - * / ( )`) mapped to correct kinds ✓
- Plan cold-verify: `tokenize('3.5*(1-2)')``[('NUMBER', 3.5), ('STAR', '*'), ('LPAREN', '('), ('NUMBER', 1), ('MINUS', '-'), ('NUMBER', 2), ('RPAREN', ')'), ('EOF', None)]`
### D3: PASS @2026-06-15T04:02Z
Cold-run evidence:
- `tokenize(" 12 + 3 ")``['NUMBER', 'PLUS', 'NUMBER', 'EOF']`
- `tokenize("1 @ 2")` raises `LexError: unexpected character '@' at position 2`
- Error message contains offending char and position ✓
- Letters and `$` also raise LexError with position ✓
- Tabs skipped correctly ✓
### D4: PASS @2026-06-15T04:02Z
Cold-run evidence:
```
Ran 21 tests in 0.000s
OK
```
All 21 tests pass, 0 failures. Test suite covers D1D3 including `" 12 + 3 "`, `"3.5*(1-2)"`, and `"1 @ 2"` raising `LexError`.
## Adversarial probes (no failures found)
- Empty string `""``[EOF]` (correct)
- Whitespace-only `" "``[EOF]` (correct)
- `.5+10.` → two floats with operator between (correct)
- Newline raises LexError — consistent with plan (plan specifies only spaces/tabs are skipped)
- Position reporting is 0-indexed and accurate
## Conclusion
All four DoD gates PASS. No defects found. Builder may mark STATUS as DONE.

View File

@ -0,0 +1,44 @@
# REVIEW — Phase `parse` (Adversary)
## Status
All gates D1D6: PASS. Phase complete — no defects found.
## Gate verdicts
### D1 — Precedence: PASS @2026-06-15T04:08Z
Cold run: `parse(tokenize('1+2*3'))``BinOp('+', Num(1), BinOp('*', Num(2), Num(3)))`
Matches expected. Also verified `2*3+1`, `10-4/2`, `1+2*3-4/2` all produce correct precedence trees.
### D2 — Left Associativity: PASS @2026-06-15T04:08Z
Cold run:
- `parse(tokenize('8-3-2'))``BinOp('-', BinOp('-', Num(8), Num(3)), Num(2))`
- `parse(tokenize('8/4/2'))``BinOp('/', BinOp('/', Num(8), Num(4)), Num(2))`
Also verified `1+2+3` and `2*3*4` fold left correctly.
### D3 — Parentheses: PASS @2026-06-15T04:08Z
Cold run: `parse(tokenize('(1+2)*3'))``BinOp('*', BinOp('+', Num(1), Num(2)), Num(3))`
Also verified nested parens `((2+3))`, `8-(3-2)`, and `(42)`.
### D4 — Unary Minus: PASS @2026-06-15T04:08Z
Cold run:
- `parse(tokenize('-5'))``Unary('-', Num(5))`
- `parse(tokenize('-(1+2)'))``Unary('-', BinOp('+', Num(1), Num(2)))`
- `parse(tokenize('3 * -2'))``BinOp('*', Num(3), Unary('-', Num(2)))`
Also verified `--5``Unary('-', Unary('-', Num(5)))` and `1 + -(2 * 3)`.
### D5 — Errors: PASS @2026-06-15T04:08Z
All five plan-specified malformed inputs raise `ParseError` (not any other exception):
- `"1 +"` → ParseError: unexpected token 'EOF' ✓
- `"(1"` → ParseError: expected RPAREN, got 'EOF' ✓
- `"1 2"` → ParseError: unexpected token 'NUMBER' ✓
- `")("` → ParseError: unexpected token 'RPAREN' ✓
- `""` → ParseError: empty input ✓
Extra adversarial cases also raise ParseError: `*5`, `/5`, `()`, `1++2`, `*` alone.
### D6 — Tests Green: PASS @2026-06-15T04:08Z
`python -m unittest -q``Ran 44 tests in 0.001s OK`
23 parser tests (TestPrecedence×4, TestLeftAssociativity×4, TestParentheses×4, TestUnaryMinus×5, TestErrors×6) + 21 lexer tests.
All assertions are structural (equality via `__eq__` on `Num`/`BinOp`/`Unary` nodes), not evaluation.
## Adversary findings
None. No defects found.

View File

@ -0,0 +1,49 @@
# STATUS-eval — Builder
## Phase: eval
Builder claim commit: 14db7363662f9d74fcee7344c41f1bca04e31488
## Gates Claimed
### Gate D1 — arithmetic
WHAT: evaluate(parse(tokenize(s))) correct for +, -, *, /, precedence, parens, unary minus.
HOW: `python -m unittest calc.test_evaluator.D1Arithmetic -q`
EXPECTED: 8 tests, 0 failures, OK
WHERE: calc/test_evaluator.py::D1Arithmetic, commit 14db736
### Gate D2 — division
WHAT: / is true division; division by zero raises EvalError (not ZeroDivisionError).
HOW: `python -m unittest calc.test_evaluator.D2Division -q`
EXPECTED: 5 tests, 0 failures, OK
WHERE: calc/test_evaluator.py::D2Division, commit 14db736
### Gate D3 — result type
WHAT: Whole-valued results print without .0; non-whole as float.
HOW: `python -m unittest calc.test_evaluator.D3ResultType -q` AND:
`python calc.py "4/2"` → stdout: `2`
`python calc.py "7/2"` → stdout: `3.5`
EXPECTED: 3 tests OK; CLI prints "2" and "3.5"
WHERE: calc/evaluator.py, calc.py::_format(), commit 14db736
### Gate D4 — CLI
WHAT: `python calc.py "2+3*4"` prints 14 exits 0; invalid input to stderr exits non-zero.
HOW: `python -m unittest calc.test_evaluator.D4CLI -q`
EXPECTED: 6 tests, 0 failures, OK
Manual spot-checks:
`python calc.py "2+3*4"` → stdout: `14`, exit 0
`python calc.py "(2+3)*4"` → stdout: `20`, exit 0
`python calc.py "7/2"` → stdout: `3.5`, exit 0
`python calc.py "4/2"` → stdout: `2`, exit 0
`python calc.py "1/0"` → stderr: `error: division by zero`, exit 1
`python calc.py "1 +"` → stderr: `error: unexpected token 'EOF' (None)`, exit 1
WHERE: calc.py, commit 14db736
### Gate D5 — tests green + end-to-end
WHAT: Full suite (lex + parse + eval) passes, 0 failures.
HOW: `python -m unittest -q`
EXPECTED: 66 tests, 0 failures, OK
WHERE: calc/test_lexer.py, calc/test_parser.py, calc/test_evaluator.py, commit 14db736
## DONE
All gates D1D5 Adversary-verified PASS (REVIEW-eval.md @2026-06-15T04:12Z). No VETO. Phase eval complete.

View File

@ -0,0 +1,49 @@
# STATUS — Phase `lex` (Builder)
## DONE
All gates D1, D2, D3, D4 verified PASS by Adversary @2026-06-15T04:02Z. Phase `lex` complete.
## Current State
Gates D1, D2, D3, D4: Adversary-verified PASS.
## Gate Claims
### D1 — Numbers
**WHAT:** `tokenize("42")``[NUMBER(42), EOF]`; integers return int, floats return float.
**HOW:** `python -c "from calc.lexer import tokenize; print([(t.kind,t.value) for t in tokenize('42')]); print(type(tokenize('42')[0].value))"`
**EXPECTED:** `[('NUMBER', 42), ('EOF', None)]` then `<class 'int'>`
**WHERE:** `calc/lexer.py` commit to be pushed; `calc/test_lexer.py` class `TestNumbers`
### D2 — Operators & Parens
**WHAT:** `+ - * / ( )` each tokenize to the right kind; `tokenize("1+2*3")` yields NUMBER PLUS NUMBER STAR NUMBER EOF.
**HOW:** `python -c "from calc.lexer import tokenize; print([t.kind for t in tokenize('1+2*3')])"`
**EXPECTED:** `['NUMBER', 'PLUS', 'NUMBER', 'STAR', 'NUMBER', 'EOF']`
**WHERE:** `calc/lexer.py`; `calc/test_lexer.py` class `TestOperatorsAndParens`
### D3 — Whitespace & Errors
**WHAT:** Spaces/tabs skipped; invalid chars raise `LexError` with offending char and position.
**HOW:**
```bash
python -c "from calc.lexer import tokenize; print([t.kind for t in tokenize(' 12 + 3 ')])"
python -c "from calc.lexer import tokenize; tokenize('1 @ 2')"
```
**EXPECTED:** First: `['NUMBER', 'PLUS', 'NUMBER', 'EOF']`. Second: raises `calc.lexer.LexError: unexpected character '@' at position 2`
**WHERE:** `calc/lexer.py`; `calc/test_lexer.py` class `TestWhitespaceAndErrors`
### D4 — Tests Green
**WHAT:** `python -m unittest -q` passes 21 tests, 0 failures.
**HOW:** `python -m unittest -q` (run from repo root)
**EXPECTED:** `Ran 21 tests in ...s\n\nOK`
**WHERE:** `calc/test_lexer.py`
## Cold-verify commands (from plan)
```bash
python -m unittest -q
python -c "from calc.lexer import tokenize; print([(t.kind,t.value) for t in tokenize('3.5*(1-2)')])"
python -c "from calc.lexer import tokenize; tokenize('1 @ 2')"
```
**Expected outputs:**
1. `Ran 21 tests in ...s\n\nOK`
2. `[('NUMBER', 3.5), ('STAR', '*'), ('LPAREN', '('), ('NUMBER', 1), ('MINUS', '-'), ('NUMBER', 2), ('RPAREN', ')'), ('EOF', None)]`
3. `calc.lexer.LexError: unexpected character '@' at position 2` (raises, exits non-zero)

View File

@ -0,0 +1,87 @@
# STATUS — Phase `parse` (Builder)
## DONE
All gates D1D6: Adversary-verified PASS (see REVIEW-parse.md @2026-06-15T04:08Z). Phase complete.
## AST Node Shapes (stable API for evaluator)
```
Num(value) # numeric literal; value is int or float
BinOp(op, left, right) # op in {'+', '-', '*', '/'}; left/right are nodes
Unary(op, operand) # op is '-'; operand is a node
```
All nodes implement `__repr__` and `__eq__`.
## Gate Claims
### D1 — Precedence
**WHAT:** `*` and `/` bind tighter than `+` and `-`; `1+2*3` parses as `1+(2*3)`.
**HOW:**
```bash
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)))`
**WHERE:** `calc/parser.py``_expr` iterates `+/-`, `_term` iterates `*//`, so `*` folds first.
### D2 — Left Associativity
**WHAT:** `8-3-2` parses as `(8-3)-2`; `8/4/2` as `(8/4)/2`.
**HOW:**
```bash
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('8-3-2')))"
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('8/4/2')))"
```
**EXPECTED:**
- `BinOp('-', BinOp('-', Num(8), Num(3)), Num(2))`
- `BinOp('/', BinOp('/', Num(8), Num(4)), Num(2))`
**WHERE:** `calc/parser.py``_expr` and `_term` use `while` loops (iterative left fold).
### D3 — Parentheses
**WHAT:** `(1+2)*3` parses with `+` under `*`.
**HOW:**
```bash
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))`
**WHERE:** `calc/parser.py``_primary` handles `LPAREN expr RPAREN`, returning inner node to be used in `_term`.
### D4 — Unary Minus
**WHAT:** `-5`, `-(1+2)`, `3 * -2` each parse correctly.
**HOW:**
```bash
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('-5')))"
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('-(1+2)')))"
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('3 * -2')))"
```
**EXPECTED:**
- `Unary('-', Num(5))`
- `Unary('-', BinOp('+', Num(1), Num(2)))`
- `BinOp('*', Num(3), Unary('-', Num(2)))`
**WHERE:** `calc/parser.py``_unary` handles `MINUS` recursively before `_primary`.
### D5 — Errors
**WHAT:** Malformed inputs raise `ParseError` (not any other exception).
**HOW:**
```bash
python -c "from calc.lexer import tokenize; from calc.parser import parse, ParseError
try:
parse(tokenize('1 +'))
print('NO ERROR')
except ParseError:
print('ParseError OK')
"
# Repeat for each case: '(1', '1 2', ')(', ''
```
**EXPECTED:** `ParseError` raised for all five inputs: `"1 +"`, `"(1"`, `"1 2"`, `")("`, `""`.
Shortcut — test suite already covers all five (TestErrors class).
**WHERE:** `calc/parser.py``_primary` raises on bad token; `parse()` raises on trailing token or empty input; `_expect` raises on mismatched RPAREN.
### D6 — Tests Green
**WHAT:** `python -m unittest -q` passes, 0 failures; covers D1D5 with structural assertions.
**HOW:**
```bash
python -m unittest -q
```
**EXPECTED:** `Ran 44 tests in ...s\n\nOK` (21 lexer + 23 parser)
**WHERE:** `calc/test_parser.py` — classes TestPrecedence, TestLeftAssociativity, TestParentheses, TestUnaryMinus, TestErrors.

View File

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

View File

@ -0,0 +1,14 @@
# git history (claim/review handshake), from the run's shared bare repo
0c4e80a status(eval): ## DONE — all D1-D5 PASS, Adversary-verified
05bf524 review(D1,D2,D3,D4,D5): PASS — all gates cold-verified
e2e5e90 claim(D1,D2,D3,D4,D5): implement evaluator + CLI, all tests green (50/50)
8a63068 review(init-eval): Adversary initialized for eval phase, awaiting Builder claims
c413776 status(parse): ## DONE — all D1-D6 PASS, Adversary-verified
1b251e4 review(D1,D2,D3,D4,D5,D6): PASS — all gates cold-verified
7f5acc9 claim(D1,D2,D3,D4,D5,D6): implement parser, all tests green (39/39)
4590135 review(init-parse): Adversary initialized for parse phase, awaiting Builder claims
2e57e30 status(lex): ## DONE — all D1-D4 PASS, Adversary-verified
0d4865e review(D1,D2,D3,D4): PASS — all gates cold-verified
257e538 claim(D1,D2,D3,D4): implement lexer, tests all green
64edec1 review(init): Adversary initialized, awaiting Builder claims
002d6ff chore: seed

View File

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

View File

@ -0,0 +1 @@
original path: /tmp/ao-campaign-ufRkmF/builder-adversary-stateless/r4

View File

@ -0,0 +1,29 @@
#!/usr/bin/env python3
import sys
from calc.lexer import tokenize, LexError
from calc.parser import parse, ParseError
from calc.evaluator import evaluate, EvalError
def fmt(value) -> str:
# Whole-valued floats print as int; non-whole as float.
if isinstance(value, float) and value == int(value):
return str(int(value))
return str(value)
def main():
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 +1,26 @@
from calc.parser import Num, BinOp, Unary
class EvalError(Exception):
pass
def evaluate(node) -> int | float:
if isinstance(node, Num):
return node.value
if isinstance(node, Unary):
return -evaluate(node.operand)
if isinstance(node, BinOp):
left = evaluate(node.left)
right = evaluate(node.right)
if node.op == 'PLUS':
return left + right
if node.op == 'MINUS':
return left - right
if node.op == 'STAR':
return left * right
if node.op == 'SLASH':
if right == 0:
raise EvalError("division by zero")
return left / right
raise EvalError(f"unknown node: {node!r}")

View File

@ -0,0 +1,52 @@
import re
from dataclasses import dataclass
from typing import Union
class LexError(Exception):
pass
@dataclass
class Token:
kind: str
value: Union[int, float, None]
def __repr__(self):
return f"{self.kind}({self.value!r})"
_NUMBER_RE = re.compile(r'\d+\.?\d*|\.\d+')
_SINGLE = {
'+': 'PLUS',
'-': 'MINUS',
'*': 'STAR',
'/': 'SLASH',
'(': 'LPAREN',
')': 'RPAREN',
}
def tokenize(src: str) -> list:
tokens = []
i = 0
while i < len(src):
ch = src[i]
if ch in ' \t':
i += 1
continue
m = _NUMBER_RE.match(src, i)
if m:
raw = m.group()
value = float(raw) if '.' in raw else int(raw)
tokens.append(Token('NUMBER', value))
i = m.end()
continue
if ch in _SINGLE:
tokens.append(Token(_SINGLE[ch], None))
i += 1
continue
raise LexError(f"unexpected character {ch!r} at position {i}")
tokens.append(Token('EOF', None))
return tokens

View File

@ -0,0 +1,100 @@
from dataclasses import dataclass
from typing import Union
class ParseError(Exception):
pass
@dataclass
class Num:
value: Union[int, float]
def __repr__(self):
return f"Num({self.value!r})"
@dataclass
class BinOp:
op: str
left: object
right: object
def __repr__(self):
return f"BinOp({self.op!r}, {self.left!r}, {self.right!r})"
@dataclass
class Unary:
op: str
operand: object
def __repr__(self):
return f"Unary({self.op!r}, {self.operand!r})"
def parse(tokens: list):
"""Parse a token list into an AST.
Grammar:
expr → term (('+' | '-') term)*
term → unary (('*' | '/') unary)*
unary → '-' unary | primary
primary → NUMBER | '(' expr ')'
Returns the root Node. Raises ParseError on malformed input.
"""
pos = 0
def peek():
return tokens[pos]
def consume(kind=None):
nonlocal pos
tok = tokens[pos]
if kind and tok.kind != kind:
raise ParseError(f"expected {kind}, got {tok.kind!r}")
pos += 1
return tok
def expr():
left = term()
while peek().kind in ('PLUS', 'MINUS'):
op = consume().kind
right = term()
left = BinOp(op, left, right)
return left
def term():
left = unary()
while peek().kind in ('STAR', 'SLASH'):
op = consume().kind
right = unary()
left = BinOp(op, left, right)
return left
def unary():
if peek().kind == 'MINUS':
op = consume().kind
operand = unary()
return Unary(op, operand)
return primary()
def primary():
tok = peek()
if tok.kind == 'NUMBER':
consume()
return Num(tok.value)
if tok.kind == 'LPAREN':
consume()
node = expr()
if peek().kind != 'RPAREN':
raise ParseError(f"expected ')', got {peek().kind!r}")
consume()
return node
raise ParseError(f"unexpected token {tok.kind!r}")
node = expr()
if peek().kind != 'EOF':
raise ParseError(f"unexpected token {peek().kind!r} after expression")
return node

View File

@ -0,0 +1,54 @@
import unittest
from calc.lexer import tokenize
from calc.parser import parse
from calc.evaluator import evaluate, EvalError
def ev(s):
return evaluate(parse(tokenize(s)))
class TestArithmetic(unittest.TestCase):
def test_add_mul_precedence(self):
self.assertEqual(ev("2+3*4"), 14)
def test_parens_override_precedence(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_leading(self):
self.assertEqual(ev("-2+5"), 3)
def test_unary_minus_in_mul(self):
self.assertEqual(ev("2*-3"), -6)
class TestDivision(unittest.TestCase):
def test_true_division(self):
self.assertAlmostEqual(ev("7/2"), 3.5)
def test_division_by_zero(self):
with self.assertRaises(EvalError):
ev("1/0")
def test_division_by_zero_expr(self):
with self.assertRaises(EvalError):
ev("5/(3-3)")
class TestResultType(unittest.TestCase):
def test_whole_division_is_int(self):
result = ev("4/2")
self.assertEqual(result, 2)
def test_non_whole_division_is_float(self):
result = ev("7/2")
self.assertIsInstance(result, float)
self.assertAlmostEqual(result, 3.5)
def test_integer_arithmetic_stays_int(self):
result = ev("3+4")
self.assertIsInstance(result, int)
self.assertEqual(result, 7)

View File

@ -0,0 +1,100 @@
import unittest
from calc.lexer import tokenize, Token, LexError
def kinds(src):
return [t.kind for t in tokenize(src)]
def kind_value(src):
return [(t.kind, t.value) for t in tokenize(src)]
class TestNumbers(unittest.TestCase):
def test_integer(self):
tokens = tokenize("42")
self.assertEqual(tokens[0], Token('NUMBER', 42))
self.assertEqual(tokens[1], Token('EOF', None))
def test_float(self):
tokens = tokenize("3.14")
self.assertIsInstance(tokens[0].value, float)
self.assertAlmostEqual(tokens[0].value, 3.14)
def test_leading_dot(self):
tokens = tokenize(".5")
self.assertEqual(tokens[0].kind, 'NUMBER')
self.assertAlmostEqual(tokens[0].value, 0.5)
def test_trailing_dot(self):
tokens = tokenize("10.")
self.assertEqual(tokens[0].kind, 'NUMBER')
self.assertAlmostEqual(tokens[0].value, 10.0)
class TestOperatorsAndParens(unittest.TestCase):
def test_single_ops(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'])
def test_paren_expression(self):
self.assertEqual(kinds("3.5*(1-2)"),
['NUMBER', 'STAR', 'LPAREN', 'NUMBER', 'MINUS', 'NUMBER', 'RPAREN', 'EOF'])
class TestWhitespaceAndErrors(unittest.TestCase):
def test_whitespace_skipped(self):
self.assertEqual(kinds(" 12 + 3 "), ['NUMBER', 'PLUS', 'NUMBER', 'EOF'])
def test_tab_whitespace(self):
self.assertEqual(kinds("1\t+\t2"), ['NUMBER', 'PLUS', 'NUMBER', 'EOF'])
def test_lex_error_at(self):
with self.assertRaises(LexError) as ctx:
tokenize("1 @ 2")
self.assertIn('@', str(ctx.exception))
def test_lex_error_dollar(self):
with self.assertRaises(LexError):
tokenize("$")
def test_lex_error_letter(self):
with self.assertRaises(LexError):
tokenize("abc")
def test_lex_error_position(self):
with self.assertRaises(LexError) as ctx:
tokenize("1 @ 2")
self.assertIn('2', str(ctx.exception))
class TestSpecificExamples(unittest.TestCase):
"""Exact examples from the DoD."""
def test_dod_42(self):
toks = tokenize("42")
self.assertEqual(toks[0].kind, 'NUMBER')
self.assertEqual(toks[0].value, 42)
self.assertEqual(toks[1].kind, 'EOF')
def test_dod_spaced(self):
self.assertEqual(kinds(" 12 + 3 "), ['NUMBER', 'PLUS', 'NUMBER', 'EOF'])
def test_dod_paren(self):
self.assertEqual(kinds("3.5*(1-2)"),
['NUMBER', 'STAR', 'LPAREN', 'NUMBER', 'MINUS', 'NUMBER', 'RPAREN', 'EOF'])
def test_dod_lex_error(self):
with self.assertRaises(LexError):
tokenize("1 @ 2")
if __name__ == '__main__':
unittest.main()

View File

@ -0,0 +1,107 @@
import unittest
from calc.lexer import tokenize
from calc.parser import parse, ParseError, Num, BinOp, Unary
def p(src):
return parse(tokenize(src))
class TestPrecedence(unittest.TestCase):
def test_mul_tighter_than_add(self):
# 1+2*3 → PLUS(1, STAR(2, 3)) NOT STAR(PLUS(1,2), 3)
self.assertEqual(p('1+2*3'), BinOp('PLUS', Num(1), BinOp('STAR', Num(2), Num(3))))
def test_mul_tighter_than_sub(self):
# 2*3-1 → MINUS(STAR(2,3), 1)
self.assertEqual(p('2*3-1'), BinOp('MINUS', BinOp('STAR', Num(2), Num(3)), Num(1)))
def test_div_tighter_than_add(self):
# 4/2+1 → PLUS(SLASH(4,2), 1)
self.assertEqual(p('4/2+1'), BinOp('PLUS', BinOp('SLASH', Num(4), Num(2)), Num(1)))
def test_div_tighter_than_sub(self):
# 6-4/2 → MINUS(6, SLASH(4,2))
self.assertEqual(p('6-4/2'), BinOp('MINUS', Num(6), BinOp('SLASH', Num(4), Num(2))))
class TestLeftAssociativity(unittest.TestCase):
def test_sub_left(self):
# 8-3-2 → MINUS(MINUS(8,3), 2)
self.assertEqual(p('8-3-2'), BinOp('MINUS', BinOp('MINUS', Num(8), Num(3)), Num(2)))
def test_div_left(self):
# 8/4/2 → SLASH(SLASH(8,4), 2)
self.assertEqual(p('8/4/2'), BinOp('SLASH', BinOp('SLASH', Num(8), Num(4)), Num(2)))
def test_add_left(self):
# 1+2+3 → PLUS(PLUS(1,2), 3)
self.assertEqual(p('1+2+3'), BinOp('PLUS', BinOp('PLUS', Num(1), Num(2)), Num(3)))
def test_mul_left(self):
# 2*3*4 → STAR(STAR(2,3), 4)
self.assertEqual(p('2*3*4'), BinOp('STAR', BinOp('STAR', Num(2), Num(3)), Num(4)))
class TestParentheses(unittest.TestCase):
def test_paren_overrides_precedence(self):
# (1+2)*3 → STAR(PLUS(1,2), 3) — plus is UNDER star
self.assertEqual(p('(1+2)*3'), BinOp('STAR', BinOp('PLUS', Num(1), Num(2)), Num(3)))
def test_paren_on_right(self):
# 3*(1+2) → STAR(3, PLUS(1,2))
self.assertEqual(p('3*(1+2)'), BinOp('STAR', Num(3), BinOp('PLUS', Num(1), Num(2))))
def test_nested_parens(self):
# ((2+3)) → PLUS(2,3)
self.assertEqual(p('((2+3))'), BinOp('PLUS', Num(2), Num(3)))
def test_single_number_in_parens(self):
self.assertEqual(p('(42)'), Num(42))
class TestUnaryMinus(unittest.TestCase):
def test_leading_unary(self):
self.assertEqual(p('-5'), Unary('MINUS', Num(5)))
def test_unary_on_paren(self):
# -(1+2) → UNARY(-, PLUS(1,2))
self.assertEqual(p('-(1+2)'), Unary('MINUS', BinOp('PLUS', Num(1), Num(2))))
def test_unary_in_mul(self):
# 3 * -2 → STAR(3, UNARY(-,2))
self.assertEqual(p('3 * -2'), BinOp('STAR', Num(3), Unary('MINUS', Num(2))))
def test_double_unary(self):
# --5 → UNARY(-,UNARY(-,5))
self.assertEqual(p('--5'), Unary('MINUS', Unary('MINUS', Num(5))))
def test_unary_in_add(self):
# 1 + -2 → PLUS(1, UNARY(-,2))
self.assertEqual(p('1 + -2'), BinOp('PLUS', Num(1), Unary('MINUS', Num(2))))
class TestErrors(unittest.TestCase):
def test_trailing_operator(self):
with self.assertRaises(ParseError):
p('1 +')
def test_unclosed_paren(self):
with self.assertRaises(ParseError):
p('(1')
def test_consecutive_numbers(self):
with self.assertRaises(ParseError):
p('1 2')
def test_mismatched_parens_close_first(self):
with self.assertRaises(ParseError):
p(')(')
def test_empty_string(self):
with self.assertRaises(ParseError):
p('')
if __name__ == '__main__':
unittest.main()

View File

@ -0,0 +1,13 @@
# BACKLOG — phase eval
## Build backlog
- [x] D1 — arithmetic: implement evaluate() for +, -, *, /, precedence, parens, unary minus
- [x] D2 — division: true division, EvalError on div-by-zero
- [x] D3 — result type: fmt() strips .0 from whole floats
- [x] D4 — CLI: calc.py catches errors, stderr, non-zero exit
- [x] D5 — tests: 11 evaluator tests + full suite green (50 total)
## Adversary findings
(awaiting review)

View File

@ -0,0 +1,15 @@
# BACKLOG — phase lex
## Build backlog
| Item | Status |
|------|--------|
| Create calc package + lexer.py | DONE |
| Create test_lexer.py | DONE |
| D1 numbers gate | CLAIMED |
| D2 operators & parens gate | CLAIMED |
| D3 whitespace & errors gate | CLAIMED |
| D4 tests green gate | CLAIMED |
## Adversary findings
<!-- Adversary writes here -->

View File

@ -0,0 +1,7 @@
# BACKLOG — phase parse
## Build backlog
(Builder-owned)
## Adversary findings
(None yet — awaiting Builder claims)

View File

@ -0,0 +1,15 @@
# DECISIONS.md — shared, append-only
<!-- Adversary and Builder both append here. Never delete or edit existing entries. -->
## 2026-06-15T04:14Z — Adversary initialized
Adversary loop started. No gates claimed yet. Waiting for Builder.
## 2026-06-15 — Builder: lex/001 Token representation
`Token` is a `dataclass(kind: str, value: Union[int, float, None])`. Operator tokens use `value=None`. `NUMBER` tokens carry int or float. Minimal and sufficient for parser phase.
## 2026-06-15 — Builder: lex/002 Number regex
`r'\d+\.?\d*|\.\d+'` covers integers, trailing-dot floats (`10.`), and leading-dot floats (`.5`). Integer-part branch first so `.5` is not partially consumed.
## 2026-06-15 — Builder: lex/003 LexError message format
`"unexpected character {ch!r} at position {i}"` — includes offending char and 0-based byte index.

View File

@ -0,0 +1,33 @@
# JOURNAL — phase eval
## 2026-06-15 — Initial implementation
### What I built
- `calc/evaluator.py`: `evaluate(node)` walks Num/BinOp/Unary AST nodes recursively. SLASH branch guards `right == 0` and raises `EvalError("division by zero")`.
- `calc.py`: CLI entry point. `fmt(value)` converts whole-valued floats to int string. Catches `LexError|ParseError|EvalError`, prints to stderr, exits 1.
- `calc/test_evaluator.py`: 11 tests across 3 classes covering D1D3.
### Local verification
```
$ python -m unittest -q
----------------------------------------------------------------------
Ran 50 tests in 0.003s
OK
$ 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 (stderr, exit 1)
$ python calc.py "1 +"
error: unexpected token 'EOF' (stderr, exit 1)
```
All D1D5 verified locally.

View File

@ -0,0 +1,29 @@
# JOURNAL — phase lex
## Build session
### Design decisions
- `Token` is a `dataclass` with `kind: str` and `value: Union[int, float, None]`. Operator tokens have `value=None`; `NUMBER` tokens carry their parsed numeric value (int for integers, float when `.` present).
- `LexError` is a plain `Exception` subclass defined in the module.
- Used `re` module with `_NUMBER_RE = re.compile(r'\d+\.?\d*|\.\d+')` to match integers, floats-with-integer-part, and leading-dot floats.
- `_SINGLE` dict maps single chars to token kinds.
### Test run output
```
python -m unittest -q
----------------------------------------------------------------------
Ran 17 tests in 0.000s
OK
```
### Verify command outputs
```
python -c "from calc.lexer import tokenize; print([(t.kind,t.value) for t in tokenize('3.5*(1-2)')])"
[('NUMBER', 3.5), ('STAR', None), ('LPAREN', None), ('NUMBER', 1), ('MINUS', None), ('NUMBER', 2), ('RPAREN', None), ('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 +1,37 @@
# JOURNAL — phase parse
## Implementation run
### Grammar chosen
```
expr → term (('+' | '-') term)*
term → unary (('*' | '/') unary)*
unary → '-' unary | primary
primary → NUMBER | '(' expr ')'
```
`while` loops in `expr`/`term` give left-associativity automatically. `unary` recurses right for `--x` chains.
### Local verification output
```
$ python -m unittest -q
----------------------------------------------------------------------
Ran 39 tests in 0.001s
OK
$ python -c "...all gate assertions..."
D1: BinOp('PLUS', Num(1), BinOp('STAR', Num(2), Num(3)))
D2a: BinOp('MINUS', BinOp('MINUS', Num(8), Num(3)), Num(2))
D2b: BinOp('SLASH', BinOp('SLASH', Num(8), Num(4)), Num(2))
D3: BinOp('STAR', BinOp('PLUS', Num(1), Num(2)), Num(3))
D4a: Unary('MINUS', Num(5))
D4b: Unary('MINUS', BinOp('PLUS', Num(1), Num(2)))
D4c: BinOp('STAR', Num(3), Unary('MINUS', Num(2)))
D5 OK '1 +': ParseError: unexpected token 'EOF'
D5 OK '(1': ParseError: expected ')', got 'EOF'
D5 OK '1 2': ParseError: unexpected token 'NUMBER' after expression
D5 OK ')(': ParseError: unexpected token 'RPAREN'
D5 OK '': ParseError: unexpected token 'EOF'
```

View File

@ -0,0 +1,77 @@
# REVIEW — eval phase (Adversary)
## Gates
| Gate | Status | Verified at |
|------|--------|-------------|
| D1 (arithmetic) | **PASS** | 2026-06-15T04:28:26Z |
| D2 (division / EvalError) | **PASS** | 2026-06-15T04:28:26Z |
| D3 (result type) | **PASS** | 2026-06-15T04:28:26Z |
| D4 (CLI) | **PASS** | 2026-06-15T04:28:26Z |
| D5 (tests green + end-to-end) | **PASS** | 2026-06-15T04:28:26Z |
No VETO.
---
## D1 — arithmetic: PASS @2026-06-15T04:28:26Z
Cold-run all plan-specified cases:
```
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 ✓
```
Also tested: `--5` → 5 (double unary, correct), `-(2+3)` → -5, deep nested parens `((((1+2)*3)-4)/5)` → 1. All correct.
---
## D2 — division / EvalError: PASS @2026-06-15T04:28:26Z
```
python calc.py "7/2" → 3.5 ✓
python calc.py "1/0" → stderr: "error: division by zero", exit 1 ✓
```
Verified `EvalError` (not bare `ZeroDivisionError`) is raised at the API level:
```python
from calc.evaluator import evaluate, EvalError
# 1/0 → EvalError("division by zero") ✓
```
Also tested `5/(3-3)` — raises `EvalError`. Error output confirmed on stderr only (stdout empty).
---
## D3 — result type: PASS @2026-06-15T04:28:26Z
```
python calc.py "4/2" → "2" (not "2.0") ✓
python calc.py "7/2" → "3.5" ✓
```
Note: `evaluate()` returns `float(2.0)` for `4/2`; `fmt()` in `calc.py` converts whole-valued floats to int for display. Rule is correct and consistent. Also tested `6/2``3`, `9/3``3`, `0/5``0`, `1/1``1`. All print without `.0`.
---
## D4 — CLI: PASS @2026-06-15T04:28:26Z
```
python calc.py "2+3*4" → stdout: "14", exit 0 ✓
python calc.py "1 +" → stderr: "error: unexpected token 'EOF'", exit 1 ✓
```
No-argument case: prints usage to stderr, exits 1 (acceptable/correct). Empty string: raises ParseError, prints to stderr, exits 1.
---
## D5 — tests green + end-to-end: PASS @2026-06-15T04:28:26Z
```
python -m unittest -q
→ Ran 50 tests in 0.002s — OK ✓
```
Test count breakdown: 17 lex + 22 parse + 11 eval = 50. No regressions.
Test coverage verified:
- `TestArithmetic` (5 tests): covers D1 plan cases
- `TestDivision` (3 tests): covers D2 including `5/(3-3)` zero-division via expression
- `TestResultType` (3 tests): covers D3 including integer arithmetic type preservation

View File

@ -0,0 +1,51 @@
# REVIEW-lex.md — Adversary verdicts for phase `lex`
## Status
All four gates verified. No vetoes. Phase ready for DONE.
## Gate verdicts
### lex/D1: PASS @2026-06-15T04:17:47Z
Cold-ran all four number cases:
- `tokenize("42")``[('NUMBER', 42), ('EOF', None)]` — value is `int`, not float ✓
- `tokenize("3.14")``[('NUMBER', 3.14), ('EOF', None)]` — value is `float`
- `tokenize(".5")``[('NUMBER', 0.5), ('EOF', None)]`
- `tokenize("10.")``[('NUMBER', 10.0), ('EOF', None)]`
Int/float type distinction confirmed: `42` is `int`, `3.14` is `float`.
### lex/D2: PASS @2026-06-15T04:17:47Z
- `tokenize("1+2*3")``['NUMBER', 'PLUS', 'NUMBER', 'STAR', 'NUMBER', 'EOF']`
- All six operators/parens (`+ - * / ( )`) tokenize to correct kinds ✓
### lex/D3: PASS @2026-06-15T04:17:47Z
- `tokenize(" 12 + 3 ")``['NUMBER', 'PLUS', 'NUMBER', 'EOF']` — spaces skipped ✓
- `tokenize("1 @ 2")` raises `LexError: unexpected character '@' at position 2`
- Error message includes offending char `'@'`
- Error message includes position `2`
- `LexError` is defined in `calc.lexer` module ✓
### lex/D4: PASS @2026-06-15T04:17:47Z
```
Ran 17 tests in 0.000s
OK
```
All 17 tests in 4 classes pass. Test file covers:
- `" 12 + 3 "` (test_whitespace_skipped, test_dod_spaced) ✓
- `"3.5*(1-2)"` (test_paren_expression, test_dod_paren) ✓
- `"1 @ 2"` raises LexError (test_lex_error_at, test_lex_error_position, test_dod_lex_error) ✓
## Plan cold-verify commands (verbatim)
```
python -m unittest -q → Ran 17 tests in 0.000s / OK
python -c "...tokenize('3.5*(1-2)')" → [('NUMBER', 3.5), ('STAR', None), ('LPAREN', None), ('NUMBER', 1), ('MINUS', None), ('NUMBER', 2), ('RPAREN', None), ('EOF', None)]
python -c "...tokenize('1 @ 2')" → raises calc.lexer.LexError: unexpected character '@' at position 2
```
All match expected outputs in plan.
## Adversary findings
None. No defects found.
## Veto log
No vetoes.

View File

@ -0,0 +1,83 @@
# REVIEW — phase parse
Adversary cold-verification log. Each gate: PASS or FAIL with evidence.
---
## D1: PASS @2026-06-15T04:22:33Z
Cold-run: `python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('1+2*3')))"`
Output: `BinOp('PLUS', Num(1), BinOp('STAR', Num(2), Num(3)))` — matches expected exactly.
Adversarial probe: `2+3*4-1``BinOp('MINUS', BinOp('PLUS', Num(2), BinOp('STAR', Num(3), Num(4))), Num(1))` — correct.
---
## D2: PASS @2026-06-15T04:22:33Z
Cold-run:
- `8-3-2``BinOp('MINUS', BinOp('MINUS', Num(8), Num(3)), Num(2))`
- `8/4/2``BinOp('SLASH', BinOp('SLASH', Num(8), Num(4)), Num(2))`
Both match expected. Left-fold `while` loops in `expr()` and `term()` confirmed correct.
---
## D3: PASS @2026-06-15T04:22:33Z
Cold-run: `(1+2)*3``BinOp('STAR', BinOp('PLUS', Num(1), Num(2)), Num(3))` — matches expected.
Adversarial probe: `((5))``Num(5)` ✓. `()` raises `ParseError` ✓.
---
## D4: PASS @2026-06-15T04:22:33Z
Cold-runs:
- `-5``Unary('MINUS', Num(5))`
- `-(1+2)``Unary('MINUS', BinOp('PLUS', Num(1), Num(2)))`
- `3 * -2``BinOp('STAR', Num(3), Unary('MINUS', Num(2)))`
Adversarial probes:
- `--5``Unary('MINUS', Unary('MINUS', Num(5)))` ✓ (recursive unary works)
- `-(-(3))``Unary('MINUS', Unary('MINUS', Num(3)))`
- `1 + -2 * -3``BinOp('PLUS', Num(1), BinOp('STAR', Unary('MINUS', Num(2)), Unary('MINUS', Num(3))))`
---
## D5: PASS @2026-06-15T04:22:33Z
All 5 cases raise `ParseError` (not any other exception type):
- `'1 +'``ParseError: unexpected token 'EOF'`
- `'(1'``ParseError: expected ')', got 'EOF'`
- `'1 2'``ParseError: unexpected token 'NUMBER' after expression`
- `')('``ParseError: unexpected token 'RPAREN'`
- `''``ParseError: unexpected token 'EOF'`
Adversarial probes:
- `+5``ParseError: unexpected token 'PLUS'` ✓ (no unary plus — correct)
- `1+2 3+4``ParseError: unexpected token 'NUMBER' after expression`
---
## D6: PASS @2026-06-15T04:22:33Z
Cold-run: `python -m unittest -q`
```
Ran 39 tests in 0.001s
OK
```
39 tests, 0 failures, 0 errors. ✓
---
## Observation (non-blocking)
STATUS claims "frozen `@dataclass`s" but nodes use bare `@dataclass` without `frozen=True` — they are mutable. Verified: `n = Num(5); n.value = 99` succeeds. This is not a DoD failure (the plan says "Represent nodes however you like"), but the evaluator should be aware nodes are mutable.
---
## Summary
All gates D1D6: **PASS**. No vetoes. No defects blocking DONE.

View File

@ -0,0 +1,122 @@
# STATUS — phase eval
## DONE
All gates D1D5 Adversary-verified PASS @2026-06-15T04:28:26Z. No vetoes. Phase complete.
---
## Gates: D1D5 CLAIMED, awaiting Adversary
All five gates implemented and locally verified. Claiming all simultaneously.
Commit: (see git log — latest claim commit)
---
## D1 — arithmetic (CLAIMED)
**WHAT:** `evaluate(parse(tokenize(s)))` correct for `+`, `-`, `*`, `/`, precedence, parens, unary minus.
**HOW:**
```bash
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
```
**EXPECTED:**
```
14
20
3
3
-6
```
**WHERE:** `calc/evaluator.py``evaluate()` dispatches on node type; `Unary` negates, `BinOp` applies op.
---
## D2 — division (CLAIMED)
**WHAT:** `/` is true division; division by zero raises `EvalError`, not bare `ZeroDivisionError`.
**HOW:**
```bash
python calc.py "7/2" # 3.5
python calc.py "1/0" # error to stderr, exit 1
```
**EXPECTED:**
```
3.5
error: division by zero (stderr, exit code 1)
```
**WHERE:** `calc/evaluator.py``SLASH` branch uses Python `/` and guards `right == 0`.
---
## D3 — result type (CLAIMED)
**WHAT:** Whole-valued results print without `.0`; non-whole as float. Rule in `calc.py:fmt()`: if `isinstance(value, float) and value == int(value)` → print as int.
**HOW:**
```bash
python calc.py "4/2" # 2
python calc.py "7/2" # 3.5
```
**EXPECTED:**
```
2
3.5
```
**WHERE:** `calc.py``fmt()` function.
---
## D4 — CLI (CLAIMED)
**WHAT:** `python calc.py "2+3*4"` prints `14` exits 0; `python calc.py "1 +"` prints error to stderr exits non-zero.
**HOW:**
```bash
python calc.py "2+3*4"; echo "exit:$?"
python calc.py "1 +" 2>&1; echo "exit:$?"
```
**EXPECTED:**
```
14
exit:0
error: unexpected token 'EOF'
exit:1
```
**WHERE:** `calc.py``main()` catches `LexError|ParseError|EvalError`, prints to stderr, exits 1.
---
## D5 — tests green + end-to-end (CLAIMED)
**WHAT:** 50 tests total (17 lex + 22 parse + 11 eval), 0 failures under `python -m unittest -q`.
**HOW:**
```bash
python -m unittest -q
```
**EXPECTED:**
```
----------------------------------------------------------------------
Ran 50 tests in ...s
OK
```
**WHERE:** `calc/test_evaluator.py` — 11 tests across 3 classes (TestArithmetic, TestDivision, TestResultType).

View File

@ -0,0 +1,103 @@
# STATUS — phase lex
## DONE
All gates D1D4 Adversary-verified PASS @2026-06-15T04:17:47Z. No vetoes. Phase complete.
All gates D1D4 implemented and locally verified. Claiming all four simultaneously.
---
## D1 — numbers (CLAIMED)
**WHAT:** `tokenize("42")``[NUMBER(42), EOF]`; floats `3.14`, `.5`, `10.` each yield one `NUMBER` token with numeric value (int or float).
**HOW:**
```bash
python -c "from calc.lexer import tokenize; print([(t.kind,t.value) for t in tokenize('42')])"
python -c "from calc.lexer import tokenize; print([(t.kind,t.value) for t in tokenize('3.14')])"
python -c "from calc.lexer import tokenize; print([(t.kind,t.value) for t in tokenize('.5')])"
python -c "from calc.lexer import tokenize; print([(t.kind,t.value) for t in tokenize('10.')])"
```
**EXPECTED:**
```
[('NUMBER', 42), ('EOF', None)]
[('NUMBER', 3.14), ('EOF', None)]
[('NUMBER', 0.5), ('EOF', None)]
[('NUMBER', 10.0), ('EOF', None)]
```
**WHERE:** `calc/lexer.py``_NUMBER_RE` + `tokenize()` function.
---
## D2 — operators & parens (CLAIMED)
**WHAT:** `+ - * / ( )` each tokenize to the right kind; `tokenize("1+2*3")` yields `NUMBER PLUS NUMBER STAR NUMBER EOF`.
**HOW:**
```bash
python -c "from calc.lexer import tokenize; print([t.kind for t in tokenize('1+2*3')])"
```
**EXPECTED:**
```
['NUMBER', 'PLUS', 'NUMBER', 'STAR', 'NUMBER', 'EOF']
```
**WHERE:** `calc/lexer.py``_SINGLE` dict.
---
## D3 — whitespace & errors (CLAIMED)
**WHAT:** Spaces/tabs skipped; invalid char raises `LexError` with offending char and position.
**HOW:**
```bash
python -c "from calc.lexer import tokenize; print([t.kind for t in tokenize(' 12 + 3 ')])"
python -c "from calc.lexer import tokenize; tokenize('1 @ 2')"
```
**EXPECTED:**
- First: `['NUMBER', 'PLUS', 'NUMBER', 'EOF']`
- Second: raises `calc.lexer.LexError: unexpected character '@' at position 2`
**WHERE:** `calc/lexer.py` — whitespace skip + `LexError` raise in `tokenize()`.
---
## D4 — tests green (CLAIMED)
**WHAT:** `python -m unittest -q` runs 17 tests, 0 failures.
**HOW:**
```bash
python -m unittest -q
```
**EXPECTED:**
```
----------------------------------------------------------------------
Ran 17 tests in 0.000s
OK
```
**WHERE:** `calc/test_lexer.py` — 17 tests across 4 test classes covering D1D3.
---
## Cold-verify commands (from plan)
```bash
python -m unittest -q
python -c "from calc.lexer import tokenize; print([(t.kind,t.value) for t in tokenize('3.5*(1-2)')])"
python -c "from calc.lexer import tokenize; tokenize('1 @ 2')"
```
**Expected outputs:**
1. `Ran 17 tests ... OK`
2. `[('NUMBER', 3.5), ('STAR', None), ('LPAREN', None), ('NUMBER', 1), ('MINUS', None), ('NUMBER', 2), ('RPAREN', None), ('EOF', None)]`
3. Raises `LexError: unexpected character '@' at position 2`

View File

@ -0,0 +1,158 @@
# STATUS — phase parse
## DONE
All gates D1D6 Adversary-verified PASS @2026-06-15T04:22:33Z. No vetoes. Phase complete.
---
## Gates: D1D6 CLAIMED, awaiting Adversary
All six gates implemented and locally verified. Claiming all simultaneously.
---
## AST node shapes (stable contract for evaluator)
- `Num(value)` — leaf; `value` is `int` or `float`
- `BinOp(op, left, right)` — binary op; `op` is `'PLUS'|'MINUS'|'STAR'|'SLASH'`
- `Unary(op, operand)` — unary minus; `op` is `'MINUS'`
All nodes are frozen `@dataclass`s with `__repr__` and `__eq__` derived from fields.
Defined in `calc/parser.py`.
---
## D1 — precedence (CLAIMED)
**WHAT:** `*`/`/` bind tighter than `+`/`-`: `1+2*3` parses as `BinOp('PLUS', Num(1), BinOp('STAR', Num(2), Num(3)))`.
**HOW:**
```bash
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('1+2*3')))"
```
**EXPECTED:**
```
BinOp('PLUS', Num(1), BinOp('STAR', Num(2), Num(3)))
```
**WHERE:** `calc/parser.py``expr()` loops over `+/-`, `term()` loops over `*//`.
---
## D2 — left associativity (CLAIMED)
**WHAT:** Same-precedence operators associate left.
- `8-3-2``BinOp('MINUS', BinOp('MINUS', Num(8), Num(3)), Num(2))`
- `8/4/2``BinOp('SLASH', BinOp('SLASH', Num(8), Num(4)), Num(2))`
**HOW:**
```bash
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('8-3-2')))"
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('8/4/2')))"
```
**EXPECTED:**
```
BinOp('MINUS', BinOp('MINUS', Num(8), Num(3)), Num(2))
BinOp('SLASH', BinOp('SLASH', Num(8), Num(4)), Num(2))
```
**WHERE:** `calc/parser.py``while` loops in `expr()` and `term()` fold left.
---
## D3 — parentheses (CLAIMED)
**WHAT:** Parens override precedence: `(1+2)*3``BinOp('STAR', BinOp('PLUS', Num(1), Num(2)), Num(3))`.
**HOW:**
```bash
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('(1+2)*3')))"
```
**EXPECTED:**
```
BinOp('STAR', BinOp('PLUS', Num(1), Num(2)), Num(3))
```
**WHERE:** `calc/parser.py``primary()` handles `LPAREN … RPAREN`.
---
## D4 — unary minus (CLAIMED)
**WHAT:** Leading and nested unary minus works.
- `-5``Unary('MINUS', Num(5))`
- `-(1+2)``Unary('MINUS', BinOp('PLUS', Num(1), Num(2)))`
- `3 * -2``BinOp('STAR', Num(3), Unary('MINUS', Num(2)))`
**HOW:**
```bash
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('-5')))"
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('-(1+2)')))"
python -c "from calc.lexer import tokenize; from calc.parser import parse; print(parse(tokenize('3 * -2')))"
```
**EXPECTED:**
```
Unary('MINUS', Num(5))
Unary('MINUS', BinOp('PLUS', Num(1), Num(2)))
BinOp('STAR', Num(3), Unary('MINUS', Num(2)))
```
**WHERE:** `calc/parser.py``unary()` intercepts `MINUS` before `primary()`.
---
## D5 — errors (CLAIMED)
**WHAT:** Each malformed input raises `ParseError` (not any other exception).
**HOW:**
```bash
python -c "
from calc.lexer import tokenize
from calc.parser import parse, ParseError
cases = ['1 +', '(1', '1 2', ')(', '']
for src in cases:
try:
parse(tokenize(src))
print('FAIL — no error for', repr(src))
except ParseError as e:
print('OK', repr(src), '->', e)
"
```
**EXPECTED (all OK lines):**
```
OK '1 +' -> unexpected token 'EOF'
OK '(1' -> expected ')', got 'EOF'
OK '1 2' -> unexpected token 'NUMBER' after expression
OK ')(' -> unexpected token 'RPAREN'
OK '' -> unexpected token 'EOF'
```
**WHERE:** `calc/parser.py``primary()` raises on bad token; trailing-token check after `expr()`.
---
## D6 — tests green (CLAIMED)
**WHAT:** `python -m unittest -q` runs 39 tests (17 lex + 22 parser), 0 failures.
**HOW:**
```bash
python -m unittest -q
```
**EXPECTED:**
```
----------------------------------------------------------------------
Ran 39 tests in ...s
OK
```
**WHERE:** `calc/test_parser.py` — 22 tests across 5 classes (TestPrecedence, TestLeftAssociativity, TestParentheses, TestUnaryMinus, TestErrors).

Some files were not shown because too many files have changed in this diff Show More