The PRD's first acceptance gate now holds: grep -RinE '\bx\.ai\b|grok' crates/ --include='*.rs' → 0 matches (exempt: NOTICE and third-party license archives, README provenance, and the required 'Based on Grok Build Open Source' attribution, now sourced from version_attribution.txt). Wire-visible renames (both sides in this repo, changed in lockstep): - Auth method id 'grok.com' → 'kimi-code' (AuthMethodKind::KimiCode). - Every x.ai/* and _x.ai/* ACP ext method and meta key → kigi/* / _kigi/* (~200 names; grokShell → kigiShell). Session-file replay keeps a read-side alias for the legacy '_x.ai/session/update' method so existing updates.jsonl histories load; writes emit only the new name (both directions test-pinned). - Agent types grok-build* → kigi* with a documented legacy-prefix alias at resolution time so persisted sessions keep resolving. - ToolNamespace/BuiltinAgentName GrokBuild* → Kigi* (wire snake_case kigi/kigi_concise/kigi_hashline; schema regenerated); grok_build implementation dirs renamed to kigi*. - x-grok-* headers → x-kigi-*, __GROK_* sentinels → __KIGI_*, themes grokday/groknight → kigiday/kiginight (old persisted values fall back to the default theme), web_fetch allowlist xAI hosts → kimi.com + moonshot platforms, changelog CDN → this repo, grok-build changelog archives deleted. - BYOK default endpoint removed: [endpoints] api_base_url is now truly optional with NO default — consumers fail fast with the flag name when unset (no silent x.ai egress). Mock harnesses inject it explicitly. - System-prompt identity fixed: 'released by xAI' → 'an unofficial community CLI for Kimi' (template + regenerated encrypted form). Also repaired pre-existing grok-era test debt found by the sweep: the stale trace_classify default-model pin, the grok-pager UA label test, pty-harness stale-binary reuse and non-hermetic moonshot routing (a PTY test could previously reach the real api.moonshot.cn), and the outdated oauth fixture scope key. Gates: §9 grep 0; fmt clean; workspace check/clippy 0/0 (-D warnings); FULL cargo test --workspace: 234 suites, 21,961 passed, 0 failed; deny advisories ok.
124 lines
5.1 KiB
Rust
124 lines
5.1 KiB
Rust
//! Cross-suite e2e flow helpers over [`PtyHarness`] / [`ContentController`].
|
|
//!
|
|
//! The single canonical home for driving/seeding helpers shared by the
|
|
//! pager's `pty_e2e` and `leader_pty_e2e` test targets (both depend on this
|
|
//! crate); suite-local constants (sizes, sentinels, timeouts) stay in each
|
|
//! suite's `common.rs`.
|
|
|
|
use std::time::{Duration, Instant};
|
|
|
|
use crate::{ContentController, PtyHarness};
|
|
|
|
/// Pump PTY output until every label is absent from the visible screen.
|
|
pub fn wait_for_labels_absent(h: &mut PtyHarness, labels: &[&str], timeout: Duration) {
|
|
let _ = h.wait_until("screen labels to disappear", timeout, |h| {
|
|
labels.iter().all(|label| !h.contains_text(label))
|
|
});
|
|
}
|
|
|
|
/// Submit `prompt` from `h`, then keep re-pressing Enter until the turn
|
|
/// actually starts streaming (`sentinel` appears) or `timeout` elapses.
|
|
///
|
|
/// In a heavy multi-client leader cluster the driver's submit Enter can be
|
|
/// dropped when it races the other client attaching / replaying on the shared
|
|
/// leader: the typed prompt is left sitting unsubmitted in the composer, the
|
|
/// turn never starts, and a plain `wait_for_text` then times out (the observed
|
|
/// `leader_two_clients_shared_session` flake — A idle with `again` still in the
|
|
/// composer at 75s). Re-pressing Enter is safe and idempotent: submitting takes
|
|
/// the composer draft synchronously (`std::mem::take` in `dispatch`), so once a
|
|
/// turn has really been sent the composer is empty and an extra Enter is a
|
|
/// no-op. It can only submit a still-stuck prompt, never double-submit a sent
|
|
/// one (which would break exactly-once scrollback asserts).
|
|
pub fn submit_turn(h: &mut PtyHarness, prompt: &str, sentinel: &str, timeout: Duration) {
|
|
h.inject_keys(format!("{prompt}\r").as_bytes())
|
|
.expect("inject prompt submit");
|
|
let deadline = Instant::now() + timeout;
|
|
loop {
|
|
let remaining = deadline.saturating_duration_since(Instant::now());
|
|
// Per-attempt sub-budget, generous enough that a genuinely in-flight
|
|
// submit resolves before we re-nudge (so the re-nudge only ever fires
|
|
// on an empty composer, where it is a no-op).
|
|
if h.wait_for_text(sentinel, Duration::from_secs(10).min(remaining))
|
|
.is_ok()
|
|
{
|
|
return;
|
|
}
|
|
assert!(
|
|
Instant::now() < deadline,
|
|
"timed out after {timeout:?} waiting for {sentinel:?}\nscreen:\n{}",
|
|
h.screen_contents()
|
|
);
|
|
let _ = h.inject_keys(b"\r");
|
|
}
|
|
}
|
|
|
|
/// Count only inference requests (chat completions / responses / messages),
|
|
/// ignoring incidental GETs like /v1/models and /v1/settings, so a replay
|
|
/// invariant means "no turn was re-driven" rather than "no HTTP at all".
|
|
pub fn inference_request_count(content: &ContentController) -> usize {
|
|
content
|
|
.requests()
|
|
.iter()
|
|
.filter(|e| {
|
|
e.path.contains("/chat/completions")
|
|
|| e.path.contains("/responses")
|
|
|| e.path.contains("/messages")
|
|
})
|
|
.count()
|
|
}
|
|
|
|
/// Seed a fake Kimi Code OAuth entry into the isolated home's `auth.json` so
|
|
/// the shell has session auth (the harness's `XAI_API_KEY` is ApiKey/BYOK mode
|
|
/// and never enters the auth manager). Load-bearing details: the map key must
|
|
/// be the Kimi Code scope key (`oauth/kimi-code`), `auth_mode` must be
|
|
/// `oauth`, and `expires_at` must be far-future so no network refresh is
|
|
/// attempted; the mock server accepts any bearer. Pair with
|
|
/// [`oauth_env_for_pager`].
|
|
pub fn seed_fake_oauth(content: &ContentController, user: &str) {
|
|
let kigi_home = content.home().join(".kigi");
|
|
std::fs::create_dir_all(&kigi_home).expect("create temp .kigi");
|
|
std::fs::write(
|
|
kigi_home.join("auth.json"),
|
|
format!(
|
|
r#"{{
|
|
"oauth/kimi-code": {{
|
|
"key": "pty-test-oauth-token",
|
|
"auth_mode": "oauth",
|
|
"create_time": "2026-01-01T00:00:00Z",
|
|
"user_id": "{user}",
|
|
"email": "{user}@test.invalid",
|
|
"expires_at": "2030-01-01T00:00:00Z",
|
|
"refresh_token": "pty-test-refresh-token"
|
|
}}
|
|
}}"#
|
|
),
|
|
)
|
|
.expect("seed fake oauth auth.json");
|
|
}
|
|
|
|
/// [`ContentController::env_for_pager`] minus `XAI_API_KEY`, so the entry
|
|
/// written by [`seed_fake_oauth`] is the active credential.
|
|
pub fn oauth_env_for_pager(content: &ContentController) -> Vec<(String, String)> {
|
|
let mut env = content.env_for_pager();
|
|
env.retain(|(k, _)| k != "XAI_API_KEY");
|
|
env
|
|
}
|
|
|
|
/// Drive `/new` until `model` shows on screen. Campaigns apply to **new
|
|
/// sessions only** and the pager's settings prefetch is deliberately 2s-capped,
|
|
/// so on a loaded runner the first session can legitimately open pre-campaign;
|
|
/// each `/new` after the settings fetch lands re-resolves with the campaign.
|
|
pub fn wait_for_model_via_new_sessions(h: &mut PtyHarness, model: &str, timeout: Duration) -> bool {
|
|
let deadline = Instant::now() + timeout;
|
|
loop {
|
|
if h.contains_text(model) {
|
|
return true;
|
|
}
|
|
if Instant::now() >= deadline {
|
|
return false;
|
|
}
|
|
let _ = h.inject_keys(b"/new\r");
|
|
h.update(Duration::from_millis(3000));
|
|
}
|
|
}
|