Files
yvgude--lean-ctx/rust/tests/p4_adaptive_mode_policy_eval.rs
T
wehub-resource-sync 26382a7ac6
CI / Clippy (push) Failing after 15m13s
CI / Test (ubuntu-latest) (push) Failing after 16m1s
CI / Test (macos-latest) (push) Has been cancelled
CI / Test (windows-latest) (push) Has been cancelled
CI / Build (no embeddings / no ORT) (push) Has been cancelled
CI / Format (push) Has been cancelled
CI / Cookbook (Node) (push) Has been cancelled
CI / Pi Extension (Node) (push) Has been cancelled
CI / Rust SDK (lean-ctx-client) (push) Has been cancelled
CI / Embed SDK (lean-ctx-sdk) (push) Has been cancelled
CI / Python SDK (leanctx) (push) Has been cancelled
CI / Hermes Plugin (Python) (push) Has been cancelled
CI / SDK Conformance Matrix (push) Has been cancelled
CI / Coverage (push) Has been cancelled
CI / cargo-deny (push) Has been cancelled
CI / Adversarial Safety (push) Has been cancelled
CI / Benchmarks (push) Has been cancelled
CI / Output-Quality Gate (eval A/B) (push) Has been cancelled
CI / Documentation (push) Has been cancelled
CI / CI Green (push) Has been cancelled
JetBrains Plugin / Actionlint (push) Has been cancelled
CodeQL / Analyze (actions) (push) Has been cancelled
CodeQL / Analyze (javascript-typescript) (push) Has been cancelled
CodeQL / Analyze (rust) (push) Has been cancelled
JetBrains Plugin / Validation (push) Has been cancelled
JetBrains Plugin / Build (push) Has been cancelled
JetBrains Plugin / Test (push) Has been cancelled
Security Check / Security Scan (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:35:30 +08:00

80 lines
2.7 KiB
Rust

use serde_json::json;
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
#[allow(clippy::await_holding_lock)]
async fn ctx_feedback_updates_adaptive_mode_policy() {
let _g = lean_ctx::core::data_dir::test_env_lock();
let dir = tempfile::tempdir().expect("tempdir");
let data_dir = dir.path().join("data");
std::fs::create_dir_all(&data_dir).expect("create data dir");
// TODO: Audit that the environment access only happens in single-threaded code.
unsafe { std::env::set_var("LEAN_CTX_DATA_DIR", &data_dir) };
assert_eq!(
lean_ctx::core::data_dir::lean_ctx_data_dir().expect("data dir"),
data_dir
);
let project = tempfile::tempdir().expect("project");
let file = project.path().join("big.json");
let payload = "{\"k\":\"v\"}\n".repeat(5000);
std::fs::write(&file, payload).expect("write json");
let engine = lean_ctx::engine::ContextEngine::with_project_root(project.path());
let _ = engine
.call_tool_text("ctx_feedback", Some(json!({"action":"reset"})))
.await
.expect("reset");
// Generate real ctx_read tool calls so ctx_feedback can attach ctx_read_modes.
for _ in 0..3 {
let _ = engine
.call_tool_text(
"ctx_read",
Some(json!({"path": file.to_string_lossy().to_string(), "mode":"aggressive"})),
)
.await
.expect("ctx_read aggressive");
}
let record_out = engine
.call_tool_text(
"ctx_feedback",
Some(json!({
"action":"record",
"agent_id":"test-agent",
"llm_input_tokens":100,
"llm_output_tokens":8000,
"note":"output explosion"
})),
)
.await
.expect("record");
assert!(
record_out.contains("feedback recorded"),
"record_out: {record_out}"
);
let status = engine
.call_tool_text("ctx_feedback", Some(json!({"action":"status"})))
.await
.expect("status");
assert!(
status.contains(data_dir.to_string_lossy().as_ref()),
"status: {status}"
);
let policy_path = lean_ctx::core::data_dir::lean_ctx_data_dir()
.expect("data dir2")
.join("adaptive_mode_policy.json");
let raw = std::fs::read_to_string(&policy_path).expect("policy exists");
let v: serde_json::Value = serde_json::from_str(&raw).expect("policy json");
let p = v["global"]["modes"]["aggressive"]["ema_badness"]
.as_f64()
.unwrap_or(0.0);
assert!(p > 0.0, "expected penalty > 0, got {p} ({raw})");
// TODO: Audit that the environment access only happens in single-threaded code.
unsafe { std::env::remove_var("LEAN_CTX_DATA_DIR") };
}