CB-WP-0008-T02: cb-play — INTENT stage 0's CLI player
Some checks failed
ci / check (push) Failing after 3s
Some checks failed
ci / check (push) Failing after 3s
A human seat is a Policy like any bot, so the CLI adds no second driver: HumanPolicy renders the projection, lists the legal commands and reads an index or `pass`. `make play` runs it; `--all-bots` watches one. K13's Project trait gains its first implementor after six passes with none. Hidden: other seats' face-down selections until Reveal, hands and deck (counts only), a face-down Problem's suit and value, and the seed — not secret content, but a seat holding it can compute the deck. A played session becomes an artifact: --record writes it as a scenario the runner executes, --replay writes a .cbreplay bundle. record.rs is the inverse of parse_command and its warrant is a round-trip test over every command shape. The acceptance test for the projection passed vacuously twice. First it asserted the text contained "face-down", which every render does because of Problems. Counted, it then reported zero inspected entries: seats are asked in order, so a human at P1 is prompted before anyone has selected. Seated at P3 it inspects ten entries and dies when the projection is mutated to reveal everything. Counting what the harness examined caught both, which is the second time that remedy has worked where a stronger predicate would not have. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
parent
6197677126
commit
25531e9d01
13 changed files with 1523 additions and 60 deletions
313
tools/cb-play/src/main.rs
Normal file
313
tools/cb-play/src/main.rs
Normal file
|
|
@ -0,0 +1,313 @@
|
|||
//! cb-play — play GROUND headless, against bots (CB-WP-0008 T02;
|
||||
//! precursor of `cb play`).
|
||||
//!
|
||||
//! INTENT stage 0 asks for a **CLI player**. Everything else on that list
|
||||
//! shipped in CB-WP-0001..0006; until this binary existed, the engine was
|
||||
//! correct, measured and replayable, and nothing could play it.
|
||||
//!
|
||||
//! Exit codes: 0 the game finished, 1 it did not. There is no partial
|
||||
//! success — a session that ends without an outcome is a failure, and
|
||||
//! saying otherwise is how a stalled game passes for a played one.
|
||||
|
||||
mod table;
|
||||
|
||||
use table::Config;
|
||||
|
||||
const USAGE: &str = "\
|
||||
usage: cb-play [--seed N] [--players N] [--seat N]... [--bot greedy|random]
|
||||
[--replay DIR] [--all-bots]
|
||||
|
||||
--seed N game seed (default 1); the same seed replays identically
|
||||
--players N 2..6 seats (default 3)
|
||||
--seat N a seat you play, 0-based, repeatable (default 0)
|
||||
--all-bots no human seats; watch a game play itself
|
||||
--bot KIND policy for every other seat: greedy (default) or random
|
||||
--replay DIR write a .cbreplay bundle of the finished game to DIR
|
||||
--record FILE write the finished game as a scenario YAML
|
||||
";
|
||||
|
||||
fn parse_args(argv: &[String]) -> Result<Config, String> {
|
||||
let mut config = Config::default();
|
||||
let mut seats: Vec<u8> = Vec::new();
|
||||
let mut all_bots = false;
|
||||
let mut i = 0;
|
||||
let value = |i: usize, argv: &[String], flag: &str| -> Result<String, String> {
|
||||
argv.get(i + 1)
|
||||
.cloned()
|
||||
.ok_or_else(|| format!("{flag} needs a value"))
|
||||
};
|
||||
while i < argv.len() {
|
||||
let flag = argv[i].as_str();
|
||||
match flag {
|
||||
"--seed" => {
|
||||
config.seed = value(i, argv, flag)?
|
||||
.parse()
|
||||
.map_err(|e| format!("--seed: {e}"))?;
|
||||
i += 2;
|
||||
}
|
||||
"--players" => {
|
||||
config.players = value(i, argv, flag)?
|
||||
.parse()
|
||||
.map_err(|e| format!("--players: {e}"))?;
|
||||
i += 2;
|
||||
}
|
||||
"--seat" => {
|
||||
seats.push(
|
||||
value(i, argv, flag)?
|
||||
.parse()
|
||||
.map_err(|e| format!("--seat: {e}"))?,
|
||||
);
|
||||
i += 2;
|
||||
}
|
||||
"--bot" => {
|
||||
config.bot = value(i, argv, flag)?;
|
||||
i += 2;
|
||||
}
|
||||
"--record" => {
|
||||
config.record = Some(value(i, argv, flag)?.into());
|
||||
i += 2;
|
||||
}
|
||||
"--replay" => {
|
||||
config.replay_dir = Some(value(i, argv, flag)?.into());
|
||||
i += 2;
|
||||
}
|
||||
"--all-bots" => {
|
||||
all_bots = true;
|
||||
i += 1;
|
||||
}
|
||||
"-h" | "--help" => return Err(USAGE.into()),
|
||||
other => return Err(format!("unknown flag {other:?}\n\n{USAGE}")),
|
||||
}
|
||||
}
|
||||
if !(2..=6).contains(&config.players) {
|
||||
return Err(format!("GR-O01: {} players is outside 2–6", config.players));
|
||||
}
|
||||
config.human_seats = if all_bots {
|
||||
vec![]
|
||||
} else if seats.is_empty() {
|
||||
vec![0]
|
||||
} else {
|
||||
seats
|
||||
};
|
||||
if let Some(bad) = config.human_seats.iter().find(|s| **s >= config.players) {
|
||||
return Err(format!(
|
||||
"--seat {bad} is not one of {} seats",
|
||||
config.players
|
||||
));
|
||||
}
|
||||
Ok(config)
|
||||
}
|
||||
|
||||
fn main() {
|
||||
let argv: Vec<String> = std::env::args().skip(1).collect();
|
||||
let config = match parse_args(&argv) {
|
||||
Ok(c) => c,
|
||||
Err(message) => {
|
||||
eprintln!("{message}");
|
||||
std::process::exit(64);
|
||||
}
|
||||
};
|
||||
|
||||
let stdin = std::io::stdin();
|
||||
let stdout = std::io::stdout();
|
||||
match table::play(&config, stdin.lock(), stdout.lock()) {
|
||||
Ok(summary) => {
|
||||
println!(
|
||||
" {} round(s), {} commands, hash {}",
|
||||
summary.rounds,
|
||||
summary.scenario.commands.len(),
|
||||
summary.end_state_hash
|
||||
);
|
||||
if let Some(path) = summary.bundle {
|
||||
println!(" bundle {}", path.display());
|
||||
}
|
||||
if let Some(path) = summary.recorded {
|
||||
println!(" recorded {}", path.display());
|
||||
}
|
||||
}
|
||||
Err(message) => {
|
||||
eprintln!("cb-play: {message}");
|
||||
std::process::exit(1);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use cb_game_runtime::{run, RunOutcome};
|
||||
use games_ground::GroundState;
|
||||
|
||||
fn args(list: &[&str]) -> Vec<String> {
|
||||
list.iter().map(|s| s.to_string()).collect()
|
||||
}
|
||||
|
||||
/// A scripted transcript plays a full 3-player game to `GameEnded`.
|
||||
/// "0" always takes the first legal command, which is a real player
|
||||
/// input and needs no knowledge of the board.
|
||||
#[test]
|
||||
fn a_scripted_transcript_plays_a_full_game() {
|
||||
let config = Config {
|
||||
seed: 42,
|
||||
players: 3,
|
||||
human_seats: vec![0],
|
||||
bot: "greedy".into(),
|
||||
replay_dir: None,
|
||||
record: None,
|
||||
};
|
||||
let script = "0\n".repeat(200);
|
||||
let mut out: Vec<u8> = Vec::new();
|
||||
let summary = table::play(&config, script.as_bytes(), &mut out)
|
||||
.unwrap_or_else(|e| panic!("scripted game failed: {e}"));
|
||||
|
||||
assert_eq!(summary.rounds, 5, "GR-R09 runs five rounds");
|
||||
let text = String::from_utf8(out).expect("utf8");
|
||||
assert!(text.contains("OUTCOME"), "the game must report an outcome");
|
||||
assert!(
|
||||
text.contains("you are P1"),
|
||||
"the human seat must be prompted"
|
||||
);
|
||||
|
||||
// The transcript replays identically — through the scenario
|
||||
// runner, not through a second call to the same driver.
|
||||
match run::<GroundState>(&summary.scenario) {
|
||||
RunOutcome::Passed { .. } => {}
|
||||
RunOutcome::Failed { reason, .. } => panic!("replay failed: {reason}"),
|
||||
}
|
||||
}
|
||||
|
||||
/// K13 at the boundary that matters: what the human is *shown* must
|
||||
/// not contain another seat's face-down selection.
|
||||
///
|
||||
/// The human seat is **P3**, deliberately. Seats are asked in order,
|
||||
/// so a P1 human is always prompted before anyone has selected and
|
||||
/// never sees a hidden selection at all — a test seated there passes
|
||||
/// without exercising the rule.
|
||||
#[test]
|
||||
fn the_prompt_never_shows_a_hidden_selection() {
|
||||
let config = Config {
|
||||
seed: 42,
|
||||
players: 3,
|
||||
human_seats: vec![2],
|
||||
bot: "greedy".into(),
|
||||
replay_dir: None,
|
||||
record: None,
|
||||
};
|
||||
let mut out: Vec<u8> = Vec::new();
|
||||
table::play(&config, "0\n".repeat(200).as_bytes(), &mut out).expect("game");
|
||||
let text = String::from_utf8(out).expect("utf8");
|
||||
|
||||
// Every rendered Select-step block must show other seats as
|
||||
// face-down. A block naming a seat's action before Reveal is a
|
||||
// leak; `step Select` and `Shown` never co-occur.
|
||||
let mut checked = 0;
|
||||
for block in text.split("\nround ") {
|
||||
if !block.contains("step Select") {
|
||||
continue;
|
||||
}
|
||||
if let Some(line) = block
|
||||
.lines()
|
||||
.find(|l| l.trim_start().starts_with("selections:"))
|
||||
{
|
||||
let others: Vec<&str> = line
|
||||
.split(" ")
|
||||
.filter(|s| s.starts_with("P1") || s.starts_with("P2"))
|
||||
.collect();
|
||||
for seat in others {
|
||||
checked += 1;
|
||||
assert!(
|
||||
seat.contains("face-down"),
|
||||
"a Select-step prompt showed {seat:?}: {line}"
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
// The loop above passes trivially if it never found a selections
|
||||
// line to check — the harness-does-nothing class, which is why
|
||||
// this counts what it inspected.
|
||||
assert!(
|
||||
checked >= 4,
|
||||
"only {checked} other-seat entries inspected across the session"
|
||||
);
|
||||
}
|
||||
|
||||
/// A session whose input runs out must say so, not finish the game
|
||||
/// on the human's behalf.
|
||||
#[test]
|
||||
fn running_out_of_input_fails_loudly() {
|
||||
let config = Config::default();
|
||||
let mut out: Vec<u8> = Vec::new();
|
||||
let err = table::play(&config, "0\n".as_bytes(), &mut out)
|
||||
.expect_err("an exhausted transcript must not finish a game");
|
||||
assert!(err.contains("input ended"), "got {err:?}");
|
||||
}
|
||||
|
||||
/// `--all-bots` is the flag that makes a game watchable, and the
|
||||
/// control that proves the human path is not the only path.
|
||||
#[test]
|
||||
fn all_bots_needs_no_input_at_all() {
|
||||
let config = Config {
|
||||
seed: 42,
|
||||
players: 3,
|
||||
human_seats: vec![],
|
||||
bot: "random".into(),
|
||||
replay_dir: None,
|
||||
record: None,
|
||||
};
|
||||
let mut out: Vec<u8> = Vec::new();
|
||||
let summary = table::play(&config, "".as_bytes(), &mut out).expect("bot game");
|
||||
assert_eq!(summary.rounds, 5);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn flags_parse_and_bad_ones_are_refused() {
|
||||
let c = parse_args(&args(&["--seed", "9", "--players", "4", "--seat", "2"])).unwrap();
|
||||
assert_eq!((c.seed, c.players, c.human_seats.clone()), (9, 4, vec![2]));
|
||||
assert_eq!(parse_args(&args(&[])).unwrap().human_seats, vec![0]);
|
||||
assert!(parse_args(&args(&["--all-bots"]))
|
||||
.unwrap()
|
||||
.human_seats
|
||||
.is_empty());
|
||||
// GR-O01's range, refused at the door rather than at setup.
|
||||
assert!(parse_args(&args(&["--players", "7"])).is_err());
|
||||
assert!(parse_args(&args(&["--players", "1"])).is_err());
|
||||
// A seat nobody occupies would silently never be prompted.
|
||||
assert!(parse_args(&args(&["--players", "3", "--seat", "3"])).is_err());
|
||||
assert!(parse_args(&args(&["--seed"])).is_err());
|
||||
assert!(parse_args(&args(&["--nope"])).is_err());
|
||||
}
|
||||
|
||||
/// A bundle is written only when asked, and it replays.
|
||||
#[test]
|
||||
fn a_bundle_is_written_and_replays() {
|
||||
let dir = std::env::temp_dir().join(format!("cb-play-{}", std::process::id()));
|
||||
let _ = std::fs::remove_dir_all(&dir);
|
||||
std::fs::create_dir_all(&dir).expect("tmp");
|
||||
let config = Config {
|
||||
seed: 42,
|
||||
players: 3,
|
||||
human_seats: vec![],
|
||||
bot: "greedy".into(),
|
||||
replay_dir: Some(dir.clone()),
|
||||
record: Some(dir.join("session.yaml")),
|
||||
};
|
||||
let mut out: Vec<u8> = Vec::new();
|
||||
let summary = table::play(&config, "".as_bytes(), &mut out).expect("game");
|
||||
let bundle = summary.bundle.expect("bundle path");
|
||||
assert!(bundle.join("manifest.yaml").exists());
|
||||
assert!(bundle.join("commands.log").exists());
|
||||
let report = cb_game_runtime::replay::replay::<GroundState>(&bundle)
|
||||
.unwrap_or_else(|e| panic!("bundle does not replay: {e}"));
|
||||
assert_eq!(report.hash, summary.end_state_hash);
|
||||
|
||||
// The recorded scenario is a file the runner can execute, which
|
||||
// is what makes a played session a regression test.
|
||||
let text = std::fs::read_to_string(summary.recorded.expect("record path")).expect("read");
|
||||
let parsed = cb_game_runtime::ScenarioFile::from_yaml(&text).expect("parse");
|
||||
assert!(matches!(
|
||||
run::<GroundState>(&parsed),
|
||||
RunOutcome::Passed { .. }
|
||||
));
|
||||
let _ = std::fs::remove_dir_all(&dir);
|
||||
}
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue