| 1 | //! Runs a coding agent on one pull request and reports back to g1t. |
| 2 | //! |
| 3 | //! This is the program a hosted sandbox starts. It clones the pull |
| 4 | //! request's fork, runs the agent harness headless, streams what the agent |
| 5 | //! does into the pull request's session as it happens, pushes the result |
| 6 | //! and marks the pull request ready for review. It talks to g1t only through the public API and git, exactly |
| 7 | //! as an agent on someone's own machine would. |
| 8 | //! |
| 9 | //! `MODE` selects another job instead: `checks` runs acceptance checks, |
| 10 | //! `update` brings a pull request up to date with its target branch, |
| 11 | //! `review` has an agent review one, and `revise` sends the author back to |
| 12 | //! address what the checks or a review found, `plan` turns an outcome |
| 13 | //! into issues, `queue` builds and checks a state of the merge queue, |
| 14 | //! `mergecheck` finds out whether a pull request merges cleanly, |
| 15 | //! `actions` runs one job of a GitHub Actions workflow, `backup` cuts a |
| 16 | //! repository's nightly backup bundle, `bump` makes a |
| 17 | //! security update: one package raised in its lockfiles, pushed as g1t, |
| 18 | //! and `computer` is a workspace agent's own computer, served for as long |
| 19 | //! as it is awake. See the modules of those names. |
| 20 | //! |
| 21 | //! Configuration comes from the environment: |
| 22 | //! |
| 23 | //! - `G1T_API`, `G1T_TOKEN`, `G1T_USER`: where and who to report as. |
| 24 | //! - `G1T_REPO`, `PULL_NUMBER`, `GIT_REMOTE`: the pull request and its fork. |
| 25 | //! - `PROMPT`: what the agent is asked to do. |
| 26 | //! - `COMMIT_MESSAGE`: used if the agent leaves changes uncommitted. |
| 27 | //! - `ANTHROPIC_API_KEY`: read by the harness itself. |
| 28 | //! |
| 29 | //! Every mode runs with the mining watch in `abuse`: a sandbox that looks |
| 30 | //! like it is mining stops itself and exits with `abuse::EXIT_CODE`. |
| 31 | //! |
| 32 | //! Given a command instead (`register`, `run`, `service`, `remove`, |
| 33 | //! `update`, `version`), it is a self-hosted runner on someone's own |
| 34 | //! machine, which runs work in these modes: see `selfhosted`. |
| 35 | //! |
| 36 | //! `deploy` and `detect` are for a workflow step: a g1t.page build of the |
| 37 | //! job's own checkout, and what that build would find (see `deploy`). |
| 38 | |
| 39 | mod abuse; |
| 40 | mod actions; |
| 41 | mod backup; |
| 42 | mod bump; |
| 43 | mod checks; |
| 44 | mod clone; |
| 45 | mod computer; |
| 46 | mod confidence; |
| 47 | mod customize; |
| 48 | mod deploy; |
| 49 | mod docker; |
| 50 | mod guard; |
| 51 | mod harness; |
| 52 | mod learned; |
| 53 | mod mergecheck; |
| 54 | mod plan; |
| 55 | mod progress; |
| 56 | mod queue; |
| 57 | mod reply; |
| 58 | mod report; |
| 59 | mod review; |
| 60 | mod revise; |
| 61 | mod selfhosted; |
| 62 | mod steer; |
| 63 | mod update; |
| 64 | |
| 65 | use std::path::Path; |
| 66 | use std::process::Command; |
| 67 | |
| 68 | use anyhow::{Context, Result, bail}; |
| 69 | use base64::Engine; |
| 70 | use base64::engine::general_purpose::STANDARD; |
| 71 | |
| 72 | use report::{Entry, Reporter}; |
| 73 | |
| 74 | pub(crate) const WORKDIR: &str = "/work/repo"; |
| 75 | /// The name and address on every commit g1t makes here, whether its agent |
| 76 | /// or g1t itself: `g1t_contracts::system::{USERNAME, EMAIL}`. |
| 77 | pub(crate) const AUTHOR_NAME: &str = "g1t"; |
| 78 | pub(crate) const AUTHOR_EMAIL: &str = "g1t@users.noreply.g1t.sh"; |
| 79 | |
| 80 | pub(crate) fn env(name: &str) -> Result<String> { |
| 81 | std::env::var(name).with_context(|| format!("{name} is not set")) |
| 82 | } |
| 83 | |
| 84 | /// Runs git and returns its trimmed output, failing on a non-zero exit. |
| 85 | pub(crate) fn git(dir: &Path, args: &[&str]) -> Result<String> { |
| 86 | let output = Command::new("git") |
| 87 | .current_dir(dir) |
| 88 | .args(args) |
| 89 | .output() |
| 90 | .context("could not run git")?; |
| 91 | if !output.status.success() { |
| 92 | bail!( |
| 93 | "git {} failed: {}", |
| 94 | args.first().unwrap_or(&""), |
| 95 | String::from_utf8_lossy(&output.stderr).trim() |
| 96 | ); |
| 97 | } |
| 98 | Ok(String::from_utf8_lossy(&output.stdout).trim().to_owned()) |
| 99 | } |
| 100 | |
| 101 | /// A git option that authenticates one command. The credential is passed |
| 102 | /// per command and never written to the clone's config or its remote URL, |
| 103 | /// where the agent would find it. |
| 104 | pub(crate) fn auth_option(user: &str, token: &str) -> String { |
| 105 | let credentials = STANDARD.encode(format!("{user}:{token}")); |
| 106 | format!("http.extraHeader=Authorization: Basic {credentials}") |
| 107 | } |
| 108 | |
| 109 | /// Clones the fork, runs the agent on `PROMPT`, commits and pushes what it |
| 110 | /// did, and returns its closing summary. |
| 111 | pub(crate) fn run(reporter: &mut Reporter) -> Result<String> { |
| 112 | let mut prompt = env("PROMPT")?; |
| 113 | let remote = env("GIT_REMOTE")?; |
| 114 | let auth = auth_option(&env("G1T_USER")?, &env("G1T_TOKEN")?); |
| 115 | let workdir = Path::new(WORKDIR); |
| 116 | |
| 117 | // Which model, and why: the router's one line names both. |
| 118 | let reason = std::env::var("AGENT_MODEL_REASON").unwrap_or_default(); |
| 119 | if !reason.trim().is_empty() { |
| 120 | reporter.record(Entry::new("note", reason.trim())); |
| 121 | } else if let Ok(model) = std::env::var("AGENT_MODEL_NAME") { |
| 122 | reporter.record(Entry::new("note", &format!("Running on {model}."))); |
| 123 | } |
| 124 | reporter.record(Entry::new("prompt", &prompt)); |
| 125 | reporter.flush(); |
| 126 | |
| 127 | std::fs::create_dir_all("/work")?; |
| 128 | clone::clone(Path::new("/work"), &auth, &[], &remote, WORKDIR).context("could not clone the pull request's fork")?; |
| 129 | git(workdir, &["config", "user.name", crate::AUTHOR_NAME])?; |
| 130 | git(workdir, &["config", "user.email", crate::AUTHOR_EMAIL])?; |
| 131 | let branch = git(workdir, &["rev-parse", "--abbrev-ref", "HEAD"])?; |
| 132 | let start = git(workdir, &["rev-parse", "HEAD"]).unwrap_or_default(); |
| 133 | |
| 134 | // Sent back to work that is already open: start from where the branch it |
| 135 | // will land on is now, so what passes here passes there too. |
| 136 | if let (Ok(upstream), Ok(upstream_branch)) = (env("UPSTREAM_REMOTE"), env("UPSTREAM_BRANCH")) { |
| 137 | clone::fetch(workdir, &auth, &upstream, &upstream_branch).context("could not fetch the branch this will land on")?; |
| 138 | // Shallow: deep enough to tell whether it is behind, and to merge. |
| 139 | clone::share_history(workdir, &auth, &[("origin", branch.as_str()), (upstream.as_str(), upstream_branch.as_str())], "HEAD", "FETCH_HEAD")?; |
| 140 | let behind = Command::new("git") |
| 141 | .current_dir(workdir) |
| 142 | .args(["merge-base", "--is-ancestor", "FETCH_HEAD", "HEAD"]) |
| 143 | .status() |
| 144 | .is_ok_and(|status| !status.success()); |
| 145 | if behind { |
| 146 | let message = format!("Catch up with {upstream_branch}"); |
| 147 | let merged = Command::new("git") |
| 148 | .current_dir(workdir) |
| 149 | .args(["merge", "--quiet", "--no-edit", "-m", &message, "FETCH_HEAD"]) |
| 150 | .status() |
| 151 | .is_ok_and(|status| status.success()); |
| 152 | if merged { |
| 153 | reporter.record(Entry::new( |
| 154 | "note", |
| 155 | &format!("Merged in the latest {upstream_branch} before starting."), |
| 156 | )); |
| 157 | } else { |
| 158 | let files = git(workdir, &["diff", "--name-only", "--diff-filter=U"])?; |
| 159 | let files: Vec<&str> = files.lines().collect(); |
| 160 | reporter.record(Entry::new( |
| 161 | "note", |
| 162 | &format!( |
| 163 | "Merged in the latest {upstream_branch} before starting; {} conflict.", |
| 164 | files.join(", ") |
| 165 | ), |
| 166 | )); |
| 167 | prompt.push_str(&format!( |
| 168 | "\n\nBefore you started, the latest {upstream_branch} was merged into this branch, and these files conflict: {}. Resolve the conflicts first, keeping what both sides meant, then address the points above. Leave no conflict markers.", |
| 169 | files.join(", ") |
| 170 | )); |
| 171 | } |
| 172 | reporter.flush(); |
| 173 | } |
| 174 | } |
| 175 | |
| 176 | // The agent is asked what it learned, which goes to memory, and how sure |
| 177 | // it is of its change, which g1t weighs with what it observes. Neither |
| 178 | // stays in the summary. |
| 179 | let asked = confidence::ask(&learned::ask(&prompt)); |
| 180 | let summary = confidence::finish(learned::finish(harness::run_claude(workdir, &asked, reporter)?)); |
| 181 | |
| 182 | // Commit whatever the agent left in the working tree. |
| 183 | if !git(workdir, &["status", "--porcelain"])?.is_empty() { |
| 184 | let message = std::env::var("COMMIT_MESSAGE").unwrap_or_else(|_| "Agent changes".into()); |
| 185 | git(workdir, &["add", "--all"])?; |
| 186 | git(workdir, &["commit", "--quiet", "--message", &message])?; |
| 187 | } |
| 188 | let head = git(workdir, &["rev-parse", "HEAD"])?; |
| 189 | if head == start { |
| 190 | // An agent woken to answer usually only answers. |
| 191 | if std::env::var("MODE").as_deref() == Ok("answer") { |
| 192 | return Ok(summary); |
| 193 | } |
| 194 | bail!("the agent finished without changing anything"); |
| 195 | } |
| 196 | git( |
| 197 | workdir, |
| 198 | &[ |
| 199 | "-c", |
| 200 | &auth, |
| 201 | "push", |
| 202 | "--quiet", |
| 203 | "origin", |
| 204 | &format!("HEAD:{branch}"), |
| 205 | ], |
| 206 | ) |
| 207 | .context("could not push the pull request's commits")?; |
| 208 | reporter.record(Entry::new( |
| 209 | "note", |
| 210 | &format!("Pushed {}.", &head[..head.len().min(12)]), |
| 211 | )); |
| 212 | Ok(summary) |
| 213 | } |
| 214 | |
| 215 | fn main() { |
| 216 | // The runc the job's Docker Engine starts containers with (docker/oci.rs). |
| 217 | if docker::oci::invoked_as_runc() { |
| 218 | docker::oci::main(); |
| 219 | } |
| 220 | // A self-hosted runner's commands; the modes below are what it, and |
| 221 | // g1t's sandboxes, run work with. |
| 222 | let args: Vec<String> = std::env::args().skip(1).collect(); |
| 223 | // From a workflow step: a g1t.page build of the job's own checkout, |
| 224 | // and what it would find (deploy.rs). |
| 225 | match args.first().map(String::as_str) { |
| 226 | Some("deploy") => std::process::exit(deploy::cli(&args[1..])), |
| 227 | Some("detect") => std::process::exit(deploy::detect_cli(&args[1..])), |
| 228 | _ => {} |
| 229 | } |
| 230 | if selfhosted::is_command(&args) { |
| 231 | std::process::exit(selfhosted::main(args)); |
| 232 | } |
| 233 | // A guarded sandbox's HTTPS is re-signed on its way out: trust that |
| 234 | // before anything is fetched. The guard hook runs before every tool |
| 235 | // call, so it skips this. |
| 236 | if std::env::var("MODE").as_deref() == Ok("guard") { |
| 237 | std::process::exit(guard::hook_main()); |
| 238 | } |
| 239 | guard::trust_egress_ca(); |
| 240 | // Watches for mining for as long as the sandbox runs (abuse.rs). Not in |
| 241 | // the hooks the harness runs after every tool call. |
| 242 | if std::env::var("MODE").as_deref() != Ok("steer") { |
| 243 | abuse::watch(); |
| 244 | } |
| 245 | // The same image does the other jobs a sandbox is started for. |
| 246 | match std::env::var("MODE").as_deref() { |
| 247 | Ok("actions") => std::process::exit(actions::main()), |
| 248 | Ok("backup") => std::process::exit(backup::main()), |
| 249 | Ok("bump") => std::process::exit(bump::main()), |
| 250 | Ok("checks") => std::process::exit(checks::main()), |
| 251 | // An agent's own computer: serves until it is put to sleep. |
| 252 | Ok("computer") => std::process::exit(computer::main()), |
| 253 | Ok("deploy") => std::process::exit(deploy::main()), |
| 254 | Ok("update") => std::process::exit(update::main()), |
| 255 | Ok("review") => std::process::exit(review::main()), |
| 256 | Ok("revise") => std::process::exit(revise::main()), |
| 257 | Ok("answer") => std::process::exit(revise::answer()), |
| 258 | Ok("plan") => std::process::exit(plan::main()), |
| 259 | Ok("reply") => std::process::exit(reply::main()), |
| 260 | Ok("queue") => std::process::exit(queue::main()), |
| 261 | Ok("mergecheck") => std::process::exit(mergecheck::main()), |
| 262 | Ok("steer") => std::process::exit(steer::main()), |
| 263 | _ => {} |
| 264 | } |
| 265 | let mut reporter = match Reporter::from_env() { |
| 266 | Ok(reporter) => reporter, |
| 267 | Err(error) => { |
| 268 | eprintln!("g1t-runner: {error:#}"); |
| 269 | std::process::exit(2); |
| 270 | } |
| 271 | }; |
| 272 | match run(&mut reporter) { |
| 273 | Ok(summary) => { |
| 274 | reporter.flush(); |
| 275 | if let Err(error) = reporter.ready(&summary) { |
| 276 | eprintln!("g1t-runner: could not mark the pull request ready: {error:#}"); |
| 277 | std::process::exit(1); |
| 278 | } |
| 279 | } |
| 280 | Err(error) => { |
| 281 | eprintln!("g1t-runner: {error:#}"); |
| 282 | // Stopped at a cap: like a person's stop, the pull request is |
| 283 | // left open for a person, not closed. |
| 284 | if guard::is_halt(&error) { |
| 285 | reporter.record(Entry::new("note", &format!("g1t stopped the agent: {error:#}."))); |
| 286 | reporter.flush(); |
| 287 | std::process::exit(1); |
| 288 | } |
| 289 | reporter.record(Entry::new("note", &format!("The run failed: {error:#}"))); |
| 290 | reporter.flush(); |
| 291 | let _ = reporter.close(); |
| 292 | std::process::exit(1); |
| 293 | } |
| 294 | } |
| 295 | } |