mirror of
https://github.com/Z3Prover/z3
synced 2026-07-04 06:16:09 +00:00
Add Copilot skill architecture with 10 skills, 2 agents, and shared infra
Introduce .github/skills/ with solve, prove, optimize, simplify, encode, explain, benchmark, memory-safety, static-analysis, and deeptest skills. Each skill follows a SKILL.md + scripts/ pattern with Python scripts backed by a shared SQLite logging library (z3db.py). Two orchestrator agents (z3-solver, z3-verifier) route requests to the appropriate skills. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
parent
1cba7cb5ee
commit
d349b93d1d
25 changed files with 2784 additions and 0 deletions
54
.github/skills/prove/SKILL.md
vendored
Normal file
54
.github/skills/prove/SKILL.md
vendored
Normal file
|
|
@ -0,0 +1,54 @@
|
|||
---
|
||||
name: prove
|
||||
description: Prove validity of logical statements by negation and satisfiability checking. If the negation is unsatisfiable, the original statement is valid. Otherwise a counterexample is returned.
|
||||
---
|
||||
|
||||
Given a conjecture (an SMT-LIB2 assertion or a natural language claim), determine whether it holds universally. The method is standard: negate the conjecture and check satisfiability. If the negation is unsatisfiable, the original is valid. If satisfiable, the model is a counterexample.
|
||||
|
||||
# Step 1: Prepare the negated formula
|
||||
|
||||
Wrap the conjecture in `(assert (not ...))` and append `(check-sat)(get-model)`.
|
||||
|
||||
Example: to prove that `(> x 3)` implies `(> x 1)`:
|
||||
```smtlib
|
||||
(declare-const x Int)
|
||||
(assert (not (=> (> x 3) (> x 1))))
|
||||
(check-sat)
|
||||
(get-model)
|
||||
```
|
||||
|
||||
# Step 2: Run the prover
|
||||
|
||||
```bash
|
||||
python3 scripts/prove.py --conjecture "(=> (> x 3) (> x 1))" --vars "x:Int"
|
||||
```
|
||||
|
||||
For file input where the file contains the full negated formula:
|
||||
```bash
|
||||
python3 scripts/prove.py --file negated.smt2
|
||||
```
|
||||
|
||||
With debug tracing:
|
||||
```bash
|
||||
python3 scripts/prove.py --conjecture "(=> (> x 3) (> x 1))" --vars "x:Int" --debug
|
||||
```
|
||||
|
||||
# Step 3: Interpret the output
|
||||
|
||||
- `valid`: the negation was unsat, so the conjecture holds for all inputs.
|
||||
- `invalid` followed by a counterexample: the negation was sat; the model shows a concrete assignment where the conjecture fails.
|
||||
- `unknown` or `timeout`: Z3 could not decide. The conjecture may require auxiliary lemmas or induction.
|
||||
|
||||
# Parameters
|
||||
|
||||
| Parameter | Type | Required | Default | Description |
|
||||
|-----------|------|----------|---------|-------------|
|
||||
| conjecture | string | no | | the assertion to prove (without negation) |
|
||||
| vars | string | no | | variable declarations as "name:sort" pairs, comma-separated |
|
||||
| file | path | no | | .smt2 file with the negated formula |
|
||||
| timeout | int | no | 30 | seconds |
|
||||
| z3 | path | no | auto | path to z3 binary |
|
||||
| debug | flag | no | off | verbose tracing |
|
||||
| db | path | no | .z3-agent/z3agent.db | logging database |
|
||||
|
||||
Either `conjecture` (with `vars`) or `file` must be provided.
|
||||
82
.github/skills/prove/scripts/prove.py
vendored
Normal file
82
.github/skills/prove/scripts/prove.py
vendored
Normal file
|
|
@ -0,0 +1,82 @@
|
|||
#!/usr/bin/env python3
|
||||
"""
|
||||
prove.py: prove validity by negation + satisfiability check.
|
||||
|
||||
Usage:
|
||||
python prove.py --conjecture "(=> (> x 3) (> x 1))" --vars "x:Int"
|
||||
python prove.py --file negated.smt2
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent.parent / "shared"))
|
||||
from z3db import Z3DB, run_z3, parse_model, setup_logging
|
||||
|
||||
|
||||
def build_formula(conjecture: str, vars_str: str) -> str:
|
||||
lines = []
|
||||
if vars_str:
|
||||
for v in vars_str.split(","):
|
||||
v = v.strip()
|
||||
name, sort = v.split(":")
|
||||
lines.append(f"(declare-const {name.strip()} {sort.strip()})")
|
||||
lines.append(f"(assert (not {conjecture}))")
|
||||
lines.append("(check-sat)")
|
||||
lines.append("(get-model)")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(prog="prove")
|
||||
parser.add_argument("--conjecture", help="assertion to prove")
|
||||
parser.add_argument("--vars", help="variable declarations, e.g. 'x:Int,y:Bool'")
|
||||
parser.add_argument("--file", help="path to .smt2 file with negated formula")
|
||||
parser.add_argument("--timeout", type=int, default=30)
|
||||
parser.add_argument("--z3", default=None)
|
||||
parser.add_argument("--db", default=None)
|
||||
parser.add_argument("--debug", action="store_true")
|
||||
args = parser.parse_args()
|
||||
|
||||
setup_logging(args.debug)
|
||||
|
||||
if args.file:
|
||||
formula = Path(args.file).read_text()
|
||||
elif args.conjecture:
|
||||
formula = build_formula(args.conjecture, args.vars or "")
|
||||
else:
|
||||
parser.error("provide --conjecture or --file")
|
||||
return
|
||||
|
||||
db = Z3DB(args.db)
|
||||
run_id = db.start_run("prove", formula)
|
||||
|
||||
result = run_z3(formula, z3_bin=args.z3, timeout=args.timeout, debug=args.debug)
|
||||
|
||||
if result["result"] == "unsat":
|
||||
verdict = "valid"
|
||||
elif result["result"] == "sat":
|
||||
verdict = "invalid"
|
||||
else:
|
||||
verdict = result["result"]
|
||||
|
||||
model = parse_model(result["stdout"]) if verdict == "invalid" else None
|
||||
|
||||
db.log_formula(run_id, formula, verdict, str(model) if model else None)
|
||||
db.finish_run(run_id, verdict, result["duration_ms"], result["exit_code"])
|
||||
|
||||
print(verdict)
|
||||
if model:
|
||||
print("counterexample:")
|
||||
for name, val in model.items():
|
||||
print(f" {name} = {val}")
|
||||
|
||||
db.close()
|
||||
# Exit 0 when we successfully determined validity or invalidity;
|
||||
# exit 1 only for errors/timeouts.
|
||||
sys.exit(0 if verdict in ("valid", "invalid") else 1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Loading…
Add table
Add a link
Reference in a new issue