mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
e64b469bbc
## Why Workspace-specific `AGENTS.md` loading needs to use the selected environment filesystem so remote workspaces and child agents read instructions from their actual environment instead of the host filesystem. The app-server should report the same instruction sources the initialized thread actually loaded, rather than independently rescanning configuration and filesystem state. ## What changed - Introduce `LoadedAgentsMd` to retain ordered user, project, and internal instructions with their provenance. - Load and canonicalize workspace `AGENTS.md` paths through the primary `EnvironmentManager` environment, then render the loaded instructions when constructing turn context. - Expose cached loaded instruction sources from initialized threads and use them for app-server start, resume, and fork responses. - Preserve global `CODEX_HOME` loading and separator behavior while excluding empty project files that did not supply model-visible instructions. - Add integration coverage for CLI injection, selected-environment provenance and rendering, empty environment selection, and cached sources on loaded-thread resume. ## Validation - `just test -p codex-core agents_md` - `just test -p codex-core selected_environment_sources_match_model_visible_instructions` - `just test -p codex-exec agents_md` - `just test -p codex-app-server instruction_sources` - `just test -p codex-app-server --status-level fail`
765 lines
25 KiB
Rust
765 lines
25 KiB
Rust
use super::*;
|
||
use crate::config::ConfigBuilder;
|
||
use codex_exec_server::LOCAL_FS;
|
||
use codex_features::Feature;
|
||
use codex_utils_absolute_path::AbsolutePathBuf;
|
||
use core_test_support::PathBufExt;
|
||
use core_test_support::TempDirExt;
|
||
use pretty_assertions::assert_eq;
|
||
use std::fs;
|
||
use std::path::Path;
|
||
use std::path::PathBuf;
|
||
use tempfile::TempDir;
|
||
|
||
async fn get_user_instructions(config: &Config) -> Option<String> {
|
||
let mut warnings = Vec::new();
|
||
AgentsMdManager::new(config)
|
||
.user_instructions_with_fs(LOCAL_FS.as_ref(), &mut warnings)
|
||
.await
|
||
.map(|loaded| loaded.text())
|
||
}
|
||
|
||
async fn agents_md_paths(config: &Config) -> std::io::Result<Vec<AbsolutePathBuf>> {
|
||
AgentsMdManager::new(config)
|
||
.agents_md_paths(LOCAL_FS.as_ref())
|
||
.await
|
||
}
|
||
|
||
fn assert_invalid_utf8_warning(warnings: &[String], source: &str, path: &Path) {
|
||
let path_display = path.display().to_string();
|
||
assert_eq!(warnings.len(), 1, "expected one warning, got {warnings:?}");
|
||
let warning = &warnings[0];
|
||
assert!(
|
||
warning.contains(&format!("{source} AGENTS.md instructions"))
|
||
&& warning.contains(&path_display)
|
||
&& warning.contains("invalid UTF-8")
|
||
&& warning.contains("Invalid byte sequences were replaced."),
|
||
"unexpected invalid UTF-8 warning: {warning:?}"
|
||
);
|
||
}
|
||
|
||
/// Helper that returns a `Config` pointing at `root` and using `limit` as
|
||
/// the maximum number of bytes to embed from AGENTS.md. The caller can
|
||
/// optionally specify a custom `instructions` string – when `None` the
|
||
/// value is cleared to mimic a scenario where no system instructions have
|
||
/// been configured.
|
||
async fn make_config(root: &TempDir, limit: usize, instructions: Option<&str>) -> Config {
|
||
let codex_home = TempDir::new().unwrap();
|
||
let mut config = ConfigBuilder::default()
|
||
.codex_home(codex_home.path().to_path_buf())
|
||
.build()
|
||
.await
|
||
.expect("defaults for test should always succeed");
|
||
|
||
config.cwd = root.abs();
|
||
config.project_doc_max_bytes = limit;
|
||
|
||
config.user_instructions = instructions.map(|text| {
|
||
LoadedAgentsMd::new_user(
|
||
text.to_owned(),
|
||
config.codex_home.join(DEFAULT_AGENTS_MD_FILENAME),
|
||
)
|
||
});
|
||
config
|
||
}
|
||
|
||
async fn make_config_with_fallback(
|
||
root: &TempDir,
|
||
limit: usize,
|
||
instructions: Option<&str>,
|
||
fallbacks: &[&str],
|
||
) -> Config {
|
||
let mut config = make_config(root, limit, instructions).await;
|
||
config.project_doc_fallback_filenames = fallbacks
|
||
.iter()
|
||
.map(std::string::ToString::to_string)
|
||
.collect();
|
||
config
|
||
}
|
||
|
||
async fn make_config_with_project_root_markers(
|
||
root: &TempDir,
|
||
limit: usize,
|
||
instructions: Option<&str>,
|
||
markers: &[&str],
|
||
) -> Config {
|
||
let codex_home = TempDir::new().unwrap();
|
||
let cli_overrides = vec![(
|
||
"project_root_markers".to_string(),
|
||
TomlValue::Array(
|
||
markers
|
||
.iter()
|
||
.map(|marker| TomlValue::String((*marker).to_string()))
|
||
.collect(),
|
||
),
|
||
)];
|
||
let mut config = ConfigBuilder::default()
|
||
.codex_home(codex_home.path().to_path_buf())
|
||
.cli_overrides(cli_overrides)
|
||
.build()
|
||
.await
|
||
.expect("defaults for test should always succeed");
|
||
|
||
config.cwd = root.abs();
|
||
config.project_doc_max_bytes = limit;
|
||
config.user_instructions = instructions.map(|text| {
|
||
LoadedAgentsMd::new_user(
|
||
text.to_owned(),
|
||
config.codex_home.join(DEFAULT_AGENTS_MD_FILENAME),
|
||
)
|
||
});
|
||
config
|
||
}
|
||
|
||
/// AGENTS.md missing – should yield `None`.
|
||
#[tokio::test]
|
||
async fn no_doc_file_returns_none() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
|
||
let res =
|
||
get_user_instructions(&make_config(&tmp, /*limit*/ 4096, /*instructions*/ None).await)
|
||
.await;
|
||
assert!(
|
||
res.is_none(),
|
||
"Expected None when AGENTS.md is absent and no system instructions provided"
|
||
);
|
||
assert!(res.is_none(), "Expected None when AGENTS.md is absent");
|
||
}
|
||
|
||
#[test]
|
||
fn empty_loaded_instructions_are_empty() {
|
||
let source =
|
||
AbsolutePathBuf::from_absolute_path("/tmp/AGENTS.md").expect("absolute source path");
|
||
|
||
assert_eq!(
|
||
LoadedAgentsMd::new_user(String::new(), source.clone()),
|
||
LoadedAgentsMd::default()
|
||
);
|
||
assert_eq!(
|
||
LoadedAgentsMd::new_user(" \n\t".to_string(), source),
|
||
LoadedAgentsMd::default()
|
||
);
|
||
assert_eq!(
|
||
LoadedAgentsMd::from_text_for_testing(String::new()),
|
||
LoadedAgentsMd::default()
|
||
);
|
||
assert_eq!(
|
||
LoadedAgentsMd::from_text_for_testing(" \n\t"),
|
||
LoadedAgentsMd::default()
|
||
);
|
||
}
|
||
|
||
#[test]
|
||
fn loaded_instructions_with_only_empty_or_whitespace_entries_are_empty() {
|
||
let empty = LoadedAgentsMd {
|
||
entries: vec![InstructionEntry {
|
||
contents: String::new(),
|
||
provenance: InstructionProvenance::Internal,
|
||
}],
|
||
};
|
||
let whitespace = LoadedAgentsMd {
|
||
entries: vec![InstructionEntry {
|
||
contents: " \n\t".to_string(),
|
||
provenance: InstructionProvenance::Internal,
|
||
}],
|
||
};
|
||
|
||
assert!(empty.is_empty());
|
||
assert!(whitespace.is_empty());
|
||
}
|
||
|
||
/// Small file within the byte-limit is returned unmodified.
|
||
#[tokio::test]
|
||
async fn doc_smaller_than_limit_is_returned() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
fs::write(tmp.path().join("AGENTS.md"), "hello world").unwrap();
|
||
|
||
let res =
|
||
get_user_instructions(&make_config(&tmp, /*limit*/ 4096, /*instructions*/ None).await)
|
||
.await
|
||
.expect("doc expected");
|
||
|
||
assert_eq!(
|
||
res, "hello world",
|
||
"The document should be returned verbatim when it is smaller than the limit and there are no existing instructions"
|
||
);
|
||
}
|
||
|
||
#[tokio::test]
|
||
async fn global_doc_invalid_utf8_warns_and_uses_lossy_text() {
|
||
let codex_home = tempfile::tempdir().expect("tempdir");
|
||
let codex_home_abs = codex_home.abs();
|
||
let path = codex_home_abs.join(DEFAULT_AGENTS_MD_FILENAME);
|
||
fs::write(&path, b"global\xFF doc").unwrap();
|
||
|
||
let mut warnings = Vec::new();
|
||
let loaded = AgentsMdManager::load_global_instructions(
|
||
LOCAL_FS.as_ref(),
|
||
Some(&codex_home_abs),
|
||
&mut warnings,
|
||
)
|
||
.await
|
||
.expect("global doc expected");
|
||
|
||
assert_eq!(
|
||
loaded,
|
||
LoadedAgentsMd::new_user("global\u{FFFD} doc".to_string(), path.clone())
|
||
);
|
||
assert_invalid_utf8_warning(&warnings, "Global", path.as_path());
|
||
}
|
||
|
||
#[tokio::test]
|
||
async fn project_doc_invalid_utf8_warns_and_uses_lossy_text() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
let path = tmp.path().join("AGENTS.md");
|
||
fs::write(&path, b"project\xFF doc").unwrap();
|
||
|
||
let config = make_config(&tmp, /*limit*/ 4096, /*instructions*/ None).await;
|
||
let mut warnings = Vec::new();
|
||
let res = AgentsMdManager::new(&config)
|
||
.user_instructions_with_fs(LOCAL_FS.as_ref(), &mut warnings)
|
||
.await
|
||
.expect("doc expected")
|
||
.text();
|
||
|
||
assert_eq!(res, "project\u{FFFD} doc");
|
||
let canonical_path = dunce::canonicalize(&path).expect("canonical doc path");
|
||
assert_invalid_utf8_warning(&warnings, "Project", &canonical_path);
|
||
}
|
||
|
||
/// Oversize file is truncated to `project_doc_max_bytes`.
|
||
#[tokio::test]
|
||
async fn doc_larger_than_limit_is_truncated() {
|
||
const LIMIT: usize = 1024;
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
|
||
let huge = "A".repeat(LIMIT * 2); // 2 KiB
|
||
fs::write(tmp.path().join("AGENTS.md"), &huge).unwrap();
|
||
|
||
let res = get_user_instructions(&make_config(&tmp, LIMIT, /*instructions*/ None).await)
|
||
.await
|
||
.expect("doc expected");
|
||
|
||
assert_eq!(res.len(), LIMIT, "doc should be truncated to LIMIT bytes");
|
||
assert_eq!(res, huge[..LIMIT]);
|
||
}
|
||
|
||
/// When `cwd` is nested inside a repo, the search should locate AGENTS.md
|
||
/// placed at the repository root (identified by `.git`).
|
||
#[tokio::test]
|
||
async fn finds_doc_in_repo_root() {
|
||
let repo = tempfile::tempdir().expect("tempdir");
|
||
|
||
// Simulate a git repository. Note .git can be a file or a directory.
|
||
std::fs::write(
|
||
repo.path().join(".git"),
|
||
"gitdir: /path/to/actual/git/dir\n",
|
||
)
|
||
.unwrap();
|
||
|
||
// Put the doc at the repo root.
|
||
fs::write(repo.path().join("AGENTS.md"), "root level doc").unwrap();
|
||
|
||
// Now create a nested working directory: repo/workspace/crate_a
|
||
let nested = repo.path().join("workspace/crate_a");
|
||
std::fs::create_dir_all(&nested).unwrap();
|
||
|
||
// Build config pointing at the nested dir.
|
||
let mut cfg = make_config(&repo, /*limit*/ 4096, /*instructions*/ None).await;
|
||
cfg.cwd = nested.abs();
|
||
|
||
let res = get_user_instructions(&cfg).await.expect("doc expected");
|
||
assert_eq!(res, "root level doc");
|
||
}
|
||
|
||
/// Explicitly setting the byte-limit to zero disables project docs.
|
||
#[tokio::test]
|
||
async fn zero_byte_limit_disables_docs() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
fs::write(tmp.path().join("AGENTS.md"), "something").unwrap();
|
||
|
||
let res =
|
||
get_user_instructions(&make_config(&tmp, /*limit*/ 0, /*instructions*/ None).await).await;
|
||
assert!(
|
||
res.is_none(),
|
||
"With limit 0 the function should return None"
|
||
);
|
||
}
|
||
|
||
#[tokio::test]
|
||
async fn zero_byte_limit_disables_discovery() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
fs::write(tmp.path().join("AGENTS.md"), "something").unwrap();
|
||
|
||
let discovery = agents_md_paths(&make_config(&tmp, /*limit*/ 0, /*instructions*/ None).await)
|
||
.await
|
||
.expect("discover paths");
|
||
assert_eq!(discovery, Vec::<AbsolutePathBuf>::new());
|
||
}
|
||
|
||
/// When both system instructions and AGENTS.md docs are present the two
|
||
/// should be concatenated with the separator.
|
||
#[tokio::test]
|
||
async fn merges_existing_instructions_with_agents_md() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
fs::write(tmp.path().join("AGENTS.md"), "proj doc").unwrap();
|
||
|
||
const INSTRUCTIONS: &str = "base instructions";
|
||
|
||
let res = get_user_instructions(&make_config(&tmp, /*limit*/ 4096, Some(INSTRUCTIONS)).await)
|
||
.await
|
||
.expect("should produce a combined instruction string");
|
||
|
||
let expected = format!("{INSTRUCTIONS}{AGENTS_MD_SEPARATOR}{}", "proj doc");
|
||
|
||
assert_eq!(res, expected);
|
||
}
|
||
|
||
#[tokio::test]
|
||
async fn sourceless_user_instructions_preserve_separator_without_reporting_a_source() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
fs::write(tmp.path().join("AGENTS.md"), "project doc").unwrap();
|
||
|
||
let mut cfg = make_config(&tmp, /*limit*/ 4096, /*instructions*/ None).await;
|
||
cfg.user_instructions = Some(LoadedAgentsMd::from_text_for_testing(
|
||
"user instructions".to_string(),
|
||
));
|
||
|
||
let mut warnings = Vec::new();
|
||
let loaded = AgentsMdManager::new(&cfg)
|
||
.user_instructions_with_fs(LOCAL_FS.as_ref(), &mut warnings)
|
||
.await
|
||
.expect("instructions expected");
|
||
let project_agents = AbsolutePathBuf::try_from(
|
||
dunce::canonicalize(cfg.cwd.join("AGENTS.md")).expect("canonical project doc path"),
|
||
)
|
||
.expect("absolute project doc path");
|
||
|
||
assert_eq!(
|
||
loaded.text(),
|
||
format!("user instructions{AGENTS_MD_SEPARATOR}project doc")
|
||
);
|
||
assert_eq!(loaded.sources().collect::<Vec<_>>(), vec![&project_agents]);
|
||
}
|
||
|
||
/// If there are existing system instructions but AGENTS.md docs are
|
||
/// missing we expect the original instructions to be returned unchanged.
|
||
#[tokio::test]
|
||
async fn keeps_existing_instructions_when_doc_missing() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
|
||
const INSTRUCTIONS: &str = "some instructions";
|
||
|
||
let res =
|
||
get_user_instructions(&make_config(&tmp, /*limit*/ 4096, Some(INSTRUCTIONS)).await).await;
|
||
|
||
assert_eq!(res, Some(INSTRUCTIONS.to_string()));
|
||
}
|
||
|
||
/// When both the repository root and the working directory contain
|
||
/// AGENTS.md files, their contents are concatenated from root to cwd.
|
||
#[tokio::test]
|
||
async fn concatenates_root_and_cwd_docs() {
|
||
let repo = tempfile::tempdir().expect("tempdir");
|
||
|
||
// Simulate a git repository.
|
||
std::fs::write(
|
||
repo.path().join(".git"),
|
||
"gitdir: /path/to/actual/git/dir\n",
|
||
)
|
||
.unwrap();
|
||
|
||
// Repo root doc.
|
||
fs::write(repo.path().join("AGENTS.md"), "root doc").unwrap();
|
||
|
||
// Nested working directory with its own doc.
|
||
let nested = repo.path().join("workspace/crate_a");
|
||
std::fs::create_dir_all(&nested).unwrap();
|
||
fs::write(nested.join("AGENTS.md"), "crate doc").unwrap();
|
||
|
||
let mut cfg = make_config(&repo, /*limit*/ 4096, /*instructions*/ None).await;
|
||
cfg.cwd = nested.abs();
|
||
|
||
let mut warnings = Vec::new();
|
||
let loaded = AgentsMdManager::new(&cfg)
|
||
.user_instructions_with_fs(LOCAL_FS.as_ref(), &mut warnings)
|
||
.await
|
||
.expect("doc expected");
|
||
let root_agents = AbsolutePathBuf::try_from(
|
||
dunce::canonicalize(repo.path().join("AGENTS.md")).expect("canonical root doc path"),
|
||
)
|
||
.expect("absolute root doc path");
|
||
let crate_agents = AbsolutePathBuf::try_from(
|
||
dunce::canonicalize(cfg.cwd.join("AGENTS.md")).expect("canonical crate doc path"),
|
||
)
|
||
.expect("absolute crate doc path");
|
||
let expected = LoadedAgentsMd {
|
||
entries: vec![
|
||
InstructionEntry {
|
||
contents: "root doc".to_string(),
|
||
provenance: InstructionProvenance::Project(root_agents.clone()),
|
||
},
|
||
InstructionEntry {
|
||
contents: "crate doc".to_string(),
|
||
provenance: InstructionProvenance::Project(crate_agents.clone()),
|
||
},
|
||
],
|
||
};
|
||
|
||
assert_eq!(loaded, expected);
|
||
assert_eq!(loaded.text(), "root doc\n\ncrate doc");
|
||
assert_eq!(
|
||
loaded.sources().collect::<Vec<_>>(),
|
||
vec![&root_agents, &crate_agents]
|
||
);
|
||
}
|
||
|
||
#[tokio::test]
|
||
async fn project_root_markers_are_honored_for_agents_discovery() {
|
||
let root = tempfile::tempdir().expect("tempdir");
|
||
fs::write(root.path().join(".codex-root"), "").unwrap();
|
||
fs::write(root.path().join("AGENTS.md"), "parent doc").unwrap();
|
||
|
||
let nested = root.path().join("dir1");
|
||
fs::create_dir_all(nested.join(".git")).unwrap();
|
||
fs::write(nested.join("AGENTS.md"), "child doc").unwrap();
|
||
|
||
let mut cfg = make_config_with_project_root_markers(
|
||
&root,
|
||
/*limit*/ 4096,
|
||
/*instructions*/ None,
|
||
&[".codex-root"],
|
||
)
|
||
.await;
|
||
cfg.cwd = nested.abs();
|
||
|
||
let discovery = agents_md_paths(&cfg).await.expect("discover paths");
|
||
let expected_parent = AbsolutePathBuf::try_from(
|
||
dunce::canonicalize(root.path().join("AGENTS.md")).expect("canonical parent doc path"),
|
||
)
|
||
.expect("absolute parent doc path");
|
||
let expected_child = AbsolutePathBuf::try_from(
|
||
dunce::canonicalize(cfg.cwd.join("AGENTS.md")).expect("canonical child doc path"),
|
||
)
|
||
.expect("absolute child doc path");
|
||
assert_eq!(discovery.len(), 2);
|
||
assert_eq!(discovery[0], expected_parent);
|
||
assert_eq!(discovery[1], expected_child);
|
||
|
||
let res = get_user_instructions(&cfg).await.expect("doc expected");
|
||
assert_eq!(res, "parent doc\n\nchild doc");
|
||
}
|
||
|
||
#[tokio::test]
|
||
async fn child_agents_message_after_global_instructions_uses_plain_separator() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
let mut cfg = make_config(&tmp, /*limit*/ 4096, Some("global doc")).await;
|
||
cfg.features.enable(Feature::ChildAgentsMd).unwrap();
|
||
|
||
let mut warnings = Vec::new();
|
||
let loaded = AgentsMdManager::new(&cfg)
|
||
.user_instructions_with_fs(LOCAL_FS.as_ref(), &mut warnings)
|
||
.await
|
||
.expect("instructions expected");
|
||
let global_agents = cfg.codex_home.join(DEFAULT_AGENTS_MD_FILENAME);
|
||
let expected = LoadedAgentsMd {
|
||
entries: vec![
|
||
InstructionEntry {
|
||
contents: "global doc".to_string(),
|
||
provenance: InstructionProvenance::User(global_agents),
|
||
},
|
||
InstructionEntry {
|
||
contents: HIERARCHICAL_AGENTS_MESSAGE.to_string(),
|
||
provenance: InstructionProvenance::Internal,
|
||
},
|
||
],
|
||
};
|
||
|
||
assert_eq!(loaded, expected);
|
||
assert_eq!(
|
||
loaded.text(),
|
||
format!("global doc\n\n{HIERARCHICAL_AGENTS_MESSAGE}")
|
||
);
|
||
}
|
||
|
||
#[tokio::test]
|
||
async fn instruction_sources_include_global_before_agents_md_docs() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
fs::write(tmp.path().join("AGENTS.md"), "project doc").unwrap();
|
||
|
||
let cfg = make_config(&tmp, /*limit*/ 4096, Some("global doc")).await;
|
||
let global_agents = cfg.codex_home.join(DEFAULT_AGENTS_MD_FILENAME);
|
||
fs::create_dir_all(&cfg.codex_home).unwrap();
|
||
fs::write(&global_agents, "global doc").unwrap();
|
||
|
||
let mut warnings = Vec::new();
|
||
let loaded = AgentsMdManager::new(&cfg)
|
||
.user_instructions_with_fs(LOCAL_FS.as_ref(), &mut warnings)
|
||
.await
|
||
.expect("instructions expected");
|
||
let project_agents = AbsolutePathBuf::try_from(
|
||
dunce::canonicalize(cfg.cwd.join("AGENTS.md")).expect("canonical project doc path"),
|
||
)
|
||
.expect("absolute project doc path");
|
||
|
||
let expected = LoadedAgentsMd {
|
||
entries: vec![
|
||
InstructionEntry {
|
||
contents: "global doc".to_string(),
|
||
provenance: InstructionProvenance::User(global_agents.clone()),
|
||
},
|
||
InstructionEntry {
|
||
contents: "project doc".to_string(),
|
||
provenance: InstructionProvenance::Project(project_agents.clone()),
|
||
},
|
||
],
|
||
};
|
||
assert_eq!(loaded, expected);
|
||
assert_eq!(
|
||
loaded.sources().collect::<Vec<_>>(),
|
||
vec![&global_agents, &project_agents]
|
||
);
|
||
assert_eq!(
|
||
loaded.text(),
|
||
format!("global doc{AGENTS_MD_SEPARATOR}project doc")
|
||
);
|
||
}
|
||
|
||
#[tokio::test]
|
||
async fn child_agents_message_after_project_docs_is_not_an_instruction_source() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
fs::write(tmp.path().join("AGENTS.md"), "project doc").unwrap();
|
||
|
||
let mut cfg = make_config(&tmp, /*limit*/ 4096, Some("global doc")).await;
|
||
cfg.features.enable(Feature::ChildAgentsMd).unwrap();
|
||
let global_agents = cfg.codex_home.join(DEFAULT_AGENTS_MD_FILENAME);
|
||
fs::create_dir_all(&cfg.codex_home).unwrap();
|
||
fs::write(&global_agents, "global doc").unwrap();
|
||
|
||
let mut warnings = Vec::new();
|
||
let loaded = AgentsMdManager::new(&cfg)
|
||
.user_instructions_with_fs(LOCAL_FS.as_ref(), &mut warnings)
|
||
.await
|
||
.expect("instructions expected");
|
||
let project_agents = AbsolutePathBuf::try_from(
|
||
dunce::canonicalize(cfg.cwd.join("AGENTS.md")).expect("canonical project doc path"),
|
||
)
|
||
.expect("absolute project doc path");
|
||
|
||
let expected = LoadedAgentsMd {
|
||
entries: vec![
|
||
InstructionEntry {
|
||
contents: "global doc".to_string(),
|
||
provenance: InstructionProvenance::User(global_agents.clone()),
|
||
},
|
||
InstructionEntry {
|
||
contents: "project doc".to_string(),
|
||
provenance: InstructionProvenance::Project(project_agents.clone()),
|
||
},
|
||
InstructionEntry {
|
||
contents: HIERARCHICAL_AGENTS_MESSAGE.to_string(),
|
||
provenance: InstructionProvenance::Internal,
|
||
},
|
||
],
|
||
};
|
||
assert_eq!(loaded, expected);
|
||
assert_eq!(
|
||
loaded.sources().collect::<Vec<_>>(),
|
||
vec![&global_agents, &project_agents]
|
||
);
|
||
assert_eq!(
|
||
loaded.text(),
|
||
format!("global doc{AGENTS_MD_SEPARATOR}project doc\n\n{HIERARCHICAL_AGENTS_MESSAGE}")
|
||
);
|
||
}
|
||
|
||
/// AGENTS.override.md is preferred over AGENTS.md when both are present.
|
||
#[tokio::test]
|
||
async fn agents_local_md_preferred() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
fs::write(tmp.path().join(DEFAULT_AGENTS_MD_FILENAME), "versioned").unwrap();
|
||
fs::write(tmp.path().join(LOCAL_AGENTS_MD_FILENAME), "local").unwrap();
|
||
|
||
let cfg = make_config(&tmp, /*limit*/ 4096, /*instructions*/ None).await;
|
||
|
||
let res = get_user_instructions(&cfg)
|
||
.await
|
||
.expect("local doc expected");
|
||
|
||
assert_eq!(res, "local");
|
||
|
||
let discovery = agents_md_paths(&cfg).await.expect("discover paths");
|
||
assert_eq!(discovery.len(), 1);
|
||
assert_eq!(
|
||
discovery[0].file_name().unwrap().to_string_lossy(),
|
||
LOCAL_AGENTS_MD_FILENAME
|
||
);
|
||
}
|
||
|
||
/// When AGENTS.md is absent but a configured fallback exists, the fallback is used.
|
||
#[tokio::test]
|
||
async fn uses_configured_fallback_when_agents_missing() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
fs::write(tmp.path().join("EXAMPLE.md"), "example instructions").unwrap();
|
||
|
||
let cfg = make_config_with_fallback(
|
||
&tmp,
|
||
/*limit*/ 4096,
|
||
/*instructions*/ None,
|
||
&["EXAMPLE.md"],
|
||
)
|
||
.await;
|
||
|
||
let res = get_user_instructions(&cfg)
|
||
.await
|
||
.expect("fallback doc expected");
|
||
|
||
assert_eq!(res, "example instructions");
|
||
}
|
||
|
||
/// AGENTS.md remains preferred when both AGENTS.md and fallbacks are present.
|
||
#[tokio::test]
|
||
async fn agents_md_preferred_over_fallbacks() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
fs::write(tmp.path().join("AGENTS.md"), "primary").unwrap();
|
||
fs::write(tmp.path().join("EXAMPLE.md"), "secondary").unwrap();
|
||
|
||
let cfg = make_config_with_fallback(
|
||
&tmp,
|
||
/*limit*/ 4096,
|
||
/*instructions*/ None,
|
||
&["EXAMPLE.md", ".example.md"],
|
||
)
|
||
.await;
|
||
|
||
let res = get_user_instructions(&cfg)
|
||
.await
|
||
.expect("AGENTS.md should win");
|
||
|
||
assert_eq!(res, "primary");
|
||
|
||
let discovery = agents_md_paths(&cfg).await.expect("discover paths");
|
||
assert_eq!(discovery.len(), 1);
|
||
assert!(
|
||
discovery[0]
|
||
.file_name()
|
||
.unwrap()
|
||
.to_string_lossy()
|
||
.eq(DEFAULT_AGENTS_MD_FILENAME)
|
||
);
|
||
}
|
||
|
||
#[tokio::test]
|
||
async fn agents_md_directory_is_ignored() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
fs::create_dir(tmp.path().join("AGENTS.md")).unwrap();
|
||
|
||
let cfg = make_config(&tmp, /*limit*/ 4096, /*instructions*/ None).await;
|
||
|
||
let res = get_user_instructions(&cfg).await;
|
||
assert_eq!(res, None);
|
||
|
||
let discovery = agents_md_paths(&cfg).await.expect("discover paths");
|
||
assert_eq!(discovery, Vec::<AbsolutePathBuf>::new());
|
||
}
|
||
|
||
#[cfg(unix)]
|
||
#[tokio::test]
|
||
async fn agents_md_special_file_is_ignored() {
|
||
use std::ffi::CString;
|
||
use std::os::unix::ffi::OsStrExt;
|
||
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
let path = tmp.path().join("AGENTS.md");
|
||
let c_path = CString::new(path.as_os_str().as_bytes()).expect("path without nul");
|
||
// SAFETY: `c_path` is a valid, nul-terminated path and `mkfifo` does not
|
||
// retain the pointer after the call.
|
||
let rc = unsafe { libc::mkfifo(c_path.as_ptr(), 0o644) };
|
||
assert_eq!(rc, 0);
|
||
|
||
let cfg = make_config(&tmp, /*limit*/ 4096, /*instructions*/ None).await;
|
||
|
||
let res = get_user_instructions(&cfg).await;
|
||
assert_eq!(res, None);
|
||
|
||
let discovery = agents_md_paths(&cfg).await.expect("discover paths");
|
||
assert_eq!(discovery, Vec::<AbsolutePathBuf>::new());
|
||
}
|
||
|
||
#[tokio::test]
|
||
async fn override_directory_falls_back_to_agents_md_file() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
fs::create_dir(tmp.path().join(LOCAL_AGENTS_MD_FILENAME)).unwrap();
|
||
fs::write(tmp.path().join(DEFAULT_AGENTS_MD_FILENAME), "primary").unwrap();
|
||
|
||
let cfg = make_config(&tmp, /*limit*/ 4096, /*instructions*/ None).await;
|
||
|
||
let res = get_user_instructions(&cfg)
|
||
.await
|
||
.expect("AGENTS.md should be used when override is a directory");
|
||
assert_eq!(res, "primary");
|
||
|
||
let discovery = agents_md_paths(&cfg).await.expect("discover paths");
|
||
assert_eq!(discovery.len(), 1);
|
||
assert_eq!(
|
||
discovery[0]
|
||
.file_name()
|
||
.expect("file name")
|
||
.to_string_lossy(),
|
||
DEFAULT_AGENTS_MD_FILENAME
|
||
);
|
||
}
|
||
|
||
#[tokio::test]
|
||
async fn skills_are_not_appended_to_agents_md() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
fs::write(tmp.path().join("AGENTS.md"), "base doc").unwrap();
|
||
|
||
let cfg = make_config(&tmp, /*limit*/ 4096, /*instructions*/ None).await;
|
||
create_skill(
|
||
cfg.codex_home.to_path_buf(),
|
||
"pdf-processing",
|
||
"extract from pdfs",
|
||
);
|
||
|
||
let res = get_user_instructions(&cfg)
|
||
.await
|
||
.expect("instructions expected");
|
||
assert_eq!(res, "base doc");
|
||
}
|
||
|
||
#[tokio::test]
|
||
async fn apps_feature_does_not_emit_user_instructions_by_itself() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
let mut cfg = make_config(&tmp, /*limit*/ 4096, /*instructions*/ None).await;
|
||
cfg.features
|
||
.enable(Feature::Apps)
|
||
.expect("test config should allow apps");
|
||
|
||
let res = get_user_instructions(&cfg).await;
|
||
assert_eq!(res, None);
|
||
}
|
||
|
||
#[tokio::test]
|
||
async fn apps_feature_does_not_append_to_agents_md_user_instructions() {
|
||
let tmp = tempfile::tempdir().expect("tempdir");
|
||
fs::write(tmp.path().join("AGENTS.md"), "base doc").unwrap();
|
||
|
||
let mut cfg = make_config(&tmp, /*limit*/ 4096, /*instructions*/ None).await;
|
||
cfg.features
|
||
.enable(Feature::Apps)
|
||
.expect("test config should allow apps");
|
||
|
||
let res = get_user_instructions(&cfg)
|
||
.await
|
||
.expect("instructions expected");
|
||
assert_eq!(res, "base doc");
|
||
}
|
||
|
||
fn create_skill(codex_home: PathBuf, name: &str, description: &str) {
|
||
let skill_dir = codex_home.join(format!("skills/{name}"));
|
||
fs::create_dir_all(&skill_dir).unwrap();
|
||
let content = format!("---\nname: {name}\ndescription: {description}\n---\n\n# Body\n");
|
||
fs::write(skill_dir.join("SKILL.md"), content).unwrap();
|
||
}
|