Compare commits

...

14 Commits

Author SHA1 Message Date
pap
f421a33384 comments removed 2025-08-06 23:50:12 +01:00
pap
dca162336c re-use load_first_candidate previously here 2025-08-06 23:47:36 +01:00
pap
472aba59e9 library fix 2025-08-06 23:37:32 +01:00
pap
22716b597b fmt 2025-08-06 23:36:29 +01:00
pap
79ebe23623 less code/comments 2025-08-06 23:36:29 +01:00
pap-openai
44b830ec34 Merge branch 'main' into show-agents-md 2025-08-06 23:32:17 +01:00
pap
9c797f1f9b dynamically showing agents.md used or /init 2025-08-06 23:27:34 +01:00
pap-openai
90770add2b Merge branch 'main' into show-agents-md 2025-08-06 22:50:13 +01:00
pap
ed15163a65 removing duplicate code 2025-08-06 22:49:53 +01:00
pap
09e1ec811e agents doc path passed as sessionconfigured instead 2025-08-06 22:38:38 +01:00
pap-openai
a7540b5abe Merge branch 'main' into show-agents-md 2025-08-06 22:08:08 +01:00
pap
8b5b9cad63 fmt 2025-07-29 23:17:40 +01:00
pap-openai
9d64934f91 Merge branch 'main' into show-agents-md 2025-07-29 22:28:39 +01:00
pap
74669a387d show agents.md on login, decouple function to find and load agents.md, add unit tests for agents.md discovery 2025-07-29 22:27:05 +01:00
9 changed files with 278 additions and 14 deletions

View File

@@ -1,4 +1,5 @@
use codex_core::WireApi;
use codex_core::agents_doc_path_string;
use codex_core::config::Config;
use crate::sandbox_summary::summarize_sandbox_policy;
@@ -7,6 +8,10 @@ use crate::sandbox_summary::summarize_sandbox_policy;
pub fn create_config_summary_entries(config: &Config) -> Vec<(&'static str, String)> {
let mut entries = vec![
("workdir", config.cwd.display().to_string()),
(
"agents.md",
agents_doc_path_string(config).unwrap_or_else(|| "none".to_string()),
),
("model", config.model.clone()),
("provider", config.model_provider_id.clone()),
("approval", config.approval_policy.to_string()),

View File

@@ -857,6 +857,7 @@ async fn submission_loop(
msg: EventMsg::SessionConfigured(SessionConfiguredEvent {
session_id,
model,
agents_doc_path: crate::project_doc::agents_doc_path_string(&config),
history_log_id,
history_entry_count,
}),

View File

@@ -39,6 +39,8 @@ mod openai_model_info;
mod openai_tools;
pub mod plan_tool;
mod project_doc;
pub use project_doc::agents_doc_path_string;
pub use project_doc::discover_project_doc_path;
pub mod protocol;
mod rollout;
pub(crate) mod safety;

View File

@@ -12,7 +12,10 @@
//! exists, the search stops we do **not** walk past the Git root.
use crate::config::Config;
use std::fs;
use std::io::Read as _;
use std::path::Path;
use std::path::PathBuf;
use tokio::io::AsyncReadExt;
use tracing::error;
@@ -49,6 +52,10 @@ pub(crate) async fn get_user_instructions(config: &Config) -> Option<String> {
/// the function returns `Ok(None)`. Unexpected I/O failures bubble up as
/// `Err` so callers can decide how to handle them.
async fn find_project_doc(config: &Config) -> std::io::Result<Option<String>> {
if config.project_doc_max_bytes == 0 {
return Ok(None);
}
let max_bytes = config.project_doc_max_bytes;
// Attempt to load from the working directory first.
@@ -90,6 +97,124 @@ async fn find_project_doc(config: &Config) -> std::io::Result<Option<String>> {
Ok(None)
}
/// Public helper that returns the discovered AGENTS.md path.
/// Returns `Ok(None)` when no suitable file is found or `project_doc_max_bytes == 0`.
pub fn discover_project_doc_path(config: &Config) -> std::io::Result<Option<std::path::PathBuf>> {
if config.project_doc_max_bytes == 0 {
return Ok(None);
}
discover_project_doc_path_from_dir(&config.cwd, CANDIDATE_FILENAMES)
}
fn discover_project_doc_path_from_dir(
start_dir: &Path,
names: &[&str],
) -> std::io::Result<Option<std::path::PathBuf>> {
// Canonicalize the path so that we do not end up in an infinite loop when
// `cwd` contains `..` components.
let mut dir = start_dir.to_path_buf();
if let Ok(canon) = dir.canonicalize() {
dir = canon;
}
// Attempt in the working directory first.
if let Some(path) = first_nonempty_candidate_in_dir(&dir, names) {
return Ok(Some(path));
}
// Walk up towards the filesystem root, stopping once we encounter the Git root.
while let Some(parent) = dir.parent() {
let git_marker = dir.join(".git");
let git_exists = match fs::metadata(&git_marker) {
Ok(_) => true,
Err(e) if e.kind() == std::io::ErrorKind::NotFound => false,
Err(e) => return Err(e),
};
if git_exists {
if let Some(path) = first_nonempty_candidate_in_dir(&dir, names) {
return Ok(Some(path));
}
break; // do not walk past the Git root
}
dir = parent.to_path_buf();
}
Ok(None)
}
/// Return a humanreadable description of the AGENTS.md path(s) that will be
/// loaded for this session, or `None` if neither global nor project docs are
/// present.
///
/// This mirrors the discovery logic used by `get_user_instructions()`:
/// - If `~/.codex/AGENTS.md` (global) is nonempty, it is included.
/// - If a project AGENTS.md is found (respecting the byte limit and git root
/// stop), it is included.
/// - When the project_doc_max_bytes is set to 0, project docs are disabled.
pub fn agents_doc_path_string(config: &Config) -> Option<String> {
let mut parts: Vec<String> = Vec::new();
// Global AGENTS.md in CODEX_HOME.
if config.user_instructions.is_some() {
let global = config.codex_home.join("AGENTS.md");
parts.push(global.display().to_string());
}
// Project AGENTS.md, unless disabled via bytelimit == 0.
if config.project_doc_max_bytes > 0 {
if let Ok(Some(p)) = discover_project_doc_path(config) {
parts.push(p.display().to_string());
}
}
if parts.is_empty() {
None
} else {
Some(parts.join(" + "))
}
}
fn first_nonempty_candidate_in_dir(dir: &Path, names: &[&str]) -> Option<PathBuf> {
for name in names {
let candidate = dir.join(name);
// Fast path: must exist and be a file.
let md = match std::fs::metadata(&candidate) {
Ok(m) if m.is_file() => m,
_ => continue,
};
// If the file is zero bytes, skip without reading.
if md.len() == 0 {
continue;
}
// Read up to a modest limit to determine if the contents are effectively empty after trimming.
// Use the same limit as `project_doc_max_bytes` would permit by default.
const MAX_PEEK_BYTES: usize = 8 * 1024;
let mut file = match std::fs::File::open(&candidate) {
Ok(f) => f,
Err(_) => continue,
};
let mut buf = Vec::with_capacity(std::cmp::min(md.len() as usize, MAX_PEEK_BYTES));
if std::io::Read::by_ref(&mut file)
.take(MAX_PEEK_BYTES as u64)
.read_to_end(&mut buf)
.is_err()
{
continue;
}
let s = String::from_utf8_lossy(&buf);
if s.trim().is_empty() {
continue;
}
return Some(candidate);
}
None
}
/// Attempt to load the first candidate file found in `dir`. Returns the file
/// contents (truncated if it exceeds `max_bytes`) when successful.
async fn load_first_candidate(
@@ -237,6 +362,68 @@ mod tests {
assert_eq!(res, "root level doc");
}
/// Test if AGENTS.md located in the current working directory is preferred over the repo root.
#[tokio::test]
async fn prefers_cwd_doc_over_repo_root() {
let repo = tempfile::tempdir().expect("tempdir");
// Simulate a git repository at repo root.
std::fs::write(repo.path().join(".git"), "gitdir: /dev/null\n").unwrap();
// Create AGENTS.md at repo root and in a nested cwd.
fs::write(repo.path().join("AGENTS.md"), "root level doc").unwrap();
let nested = repo.path().join("workspace/crate_b");
std::fs::create_dir_all(&nested).unwrap();
fs::write(nested.join("AGENTS.md"), "nested cwd doc").unwrap();
// Build config pointing at the nested dir.
let mut cfg = make_config(&repo, 4096, None);
cfg.cwd = nested.clone();
// Path discovery should prefer the nested cwd doc.
let discovered = super::discover_project_doc_path(&cfg)
.expect("discovery should succeed")
.expect("path should be found");
let discovered_canon = fs::canonicalize(&discovered).expect("canonicalize discovered");
let expected_canon =
fs::canonicalize(nested.join("AGENTS.md")).expect("canonicalize expected");
assert_eq!(discovered_canon, expected_canon);
// get_user_instructions should load the nested document contents.
let res = get_user_instructions(&cfg).await.expect("doc expected");
assert_eq!(res, "nested cwd doc");
}
/// Test if AGENTS.md at the repo root is used when none exists in cwd.
#[tokio::test]
async fn falls_back_to_repo_root_when_cwd_missing_doc() {
let repo = tempfile::tempdir().expect("tempdir");
// Simulate a git repository at repo root.
std::fs::write(repo.path().join(".git"), "gitdir: /dev/null\n").unwrap();
// Create AGENTS.md only at repo root.
fs::write(repo.path().join("AGENTS.md"), "root level doc").unwrap();
// Nested cwd without its own AGENTS.md.
let nested = repo.path().join("nested/dir");
std::fs::create_dir_all(&nested).unwrap();
let mut cfg = make_config(&repo, 4096, None);
cfg.cwd = nested;
let discovered = super::discover_project_doc_path(&cfg)
.expect("discovery should succeed")
.expect("path should be found");
let discovered_canon = fs::canonicalize(&discovered).expect("canonicalize discovered");
let expected_canon =
fs::canonicalize(repo.path().join("AGENTS.md")).expect("canonicalize expected");
assert_eq!(discovered_canon, expected_canon);
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() {

View File

@@ -648,6 +648,10 @@ pub struct SessionConfiguredEvent {
/// Tell the client what model is being queried.
pub model: String,
/// The path(s) to AGENTS.md that were loaded for this session, if any.
#[serde(skip_serializing_if = "Option::is_none")]
pub agents_doc_path: Option<String>,
/// Identifier of the history log file (inode on Unix, 0 otherwise).
pub history_log_id: u64,
@@ -713,6 +717,7 @@ mod tests {
msg: EventMsg::SessionConfigured(SessionConfiguredEvent {
session_id,
model: "codex-mini-latest".to_string(),
agents_doc_path: None,
history_log_id: 0,
history_entry_count: 0,
}),

View File

@@ -494,6 +494,7 @@ impl EventProcessor for EventProcessorWithHumanOutput {
model,
history_log_id: _,
history_entry_count: _,
..
} = session_configured_event;
ts_println!(

View File

@@ -906,6 +906,7 @@ mod tests {
msg: EventMsg::SessionConfigured(codex_core::protocol::SessionConfiguredEvent {
session_id: uuid!("67e55044-10b1-426f-9247-bb680e5fe0c8"),
model: "codex-mini-latest".into(),
agents_doc_path: None,
history_log_id: 42,
history_entry_count: 3,
}),

View File

@@ -242,6 +242,7 @@ mod tests {
msg: EventMsg::SessionConfigured(SessionConfiguredEvent {
session_id: Uuid::new_v4(),
model: "gpt-4o".to_string(),
agents_doc_path: None,
history_log_id: 1,
history_entry_count: 1000,
}),
@@ -282,6 +283,7 @@ mod tests {
let session_configured_event = SessionConfiguredEvent {
session_id: Uuid::new_v4(),
model: "gpt-4o".to_string(),
agents_doc_path: None,
history_log_id: 1,
history_entry_count: 1000,
};

View File

@@ -166,12 +166,8 @@ impl HistoryCell {
event: SessionConfiguredEvent,
is_first_event: bool,
) -> Self {
let SessionConfiguredEvent {
model,
session_id: _,
history_log_id: _,
history_entry_count: _,
} = event;
let model = event.model.clone();
let agents_doc_path = event.agents_doc_path.clone();
if is_first_event {
let cwd_str = match relativize_to_home(&config.cwd) {
Some(rel) if !rel.as_os_str().is_empty() => format!("~/{}", rel.display()),
@@ -179,7 +175,7 @@ impl HistoryCell {
None => config.cwd.display().to_string(),
};
let lines: Vec<Line<'static>> = vec![
let mut lines: Vec<Line<'static>> = vec![
Line::from(vec![
Span::raw(">_ ").dim(),
Span::styled(
@@ -189,14 +185,78 @@ impl HistoryCell {
Span::raw(format!(" {cwd_str}")).dim(),
]),
Line::from("".dim()),
Line::from(" Try one of the following commands to get started:".dim()),
Line::from("".dim()),
Line::from(format!(" 1. /init - {}", SlashCommand::Init.description()).dim()),
Line::from(format!(" 2. /status - {}", SlashCommand::Status.description()).dim()),
Line::from(format!(" 3. /compact - {}", SlashCommand::Compact.description()).dim()),
Line::from(format!(" 4. /new - {}", SlashCommand::New.description()).dim()),
Line::from("".dim()),
];
// If AGENTS.md is configured (either user-level or project-level),
// show a concise summary and omit the /init hint, but still show the other onboarding commands.
let show_init = agents_doc_path.is_none();
if let Some(paths_str) = agents_doc_path {
let global_path = config.codex_home.join("AGENTS.md");
let parts: Vec<String> = paths_str
.split(" + ")
.map(|s| s.trim().to_string())
.filter(|s| !s.is_empty())
.collect();
let mut user_path: Option<String> = None;
let mut project_path: Option<String> = None;
for p in parts {
if p == global_path.display().to_string() {
user_path = Some(p);
} else {
project_path = Some(p);
}
}
let summary_line = match (user_path, project_path) {
(Some(u), Some(pr)) => {
format!(" Using user instructions ({u}) and project instructions ({pr})")
}
(Some(u), None) => format!("Using user instructions ({u})"),
(None, Some(pr)) => format!(" Using project instructions ({pr})"),
(None, None) => String::new(),
};
if !summary_line.is_empty() {
lines.push(Line::from(summary_line.dim()));
lines.push(Line::from("".dim()));
}
}
// Onboarding hints, with index based on whether /init is shown
lines.push(Line::from(
" Try one of the following commands to get started:".dim(),
));
lines.push(Line::from("".dim()));
let mut cmd_index = 1;
if show_init {
lines.push(Line::from(
format!(" {cmd_index}. /init - {}", SlashCommand::Init.description()).dim(),
));
cmd_index += 1;
}
lines.push(Line::from(
format!(
" {cmd_index}. /status - {}",
SlashCommand::Status.description()
)
.dim(),
));
cmd_index += 1;
lines.push(Line::from(
format!(
" {cmd_index}. /compact - {}",
SlashCommand::Compact.description()
)
.dim(),
));
cmd_index += 1;
lines.push(Line::from(
format!(" {cmd_index}. /new - {}", SlashCommand::New.description()).dim(),
));
lines.push(Line::from("".dim()));
HistoryCell::WelcomeMessage {
view: TextBlock::new(lines),
}