openai/codex
1
0
Fork 0
mirror of https://github.com/openai/codex.git synced 2026-11-02 19:43:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

Disambiguate snapshot cwd placeholders

Browse Source 
Co-authored-by: Codex <noreply@openai.com>
This commit is contained in:
Charles Cunningham
2026-03-13 11:01:30 -07:00
co-authored by Codex
parent 85880b4495
commit 217eeaee9c
2 changed files with 118 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files
codex-rs/core/tests/common/context_snapshot.rs
+114 -44
View File
@@ -1,4 +1,5 @@
use serde_json::Value;
use std::collections::HashMap;
use crate::responses::ResponsesRequest;
@@ -42,6 +43,7 @@ pub fn format_request_input_snapshot(
}
pub fn format_response_items_snapshot(items: &[Value], options: &ContextSnapshotOptions) -> String {
let mut canonicalizer = SnapshotCanonicalizer::default();
items
.iter()
.enumerate()
@@ -70,7 +72,11 @@ pub fn format_response_items_snapshot(items: &[Value], options: &ContextSnapshot
.iter()
.map(|entry| {
if let Some(text) = entry.get("text").and_then(Value::as_str) {
return format_snapshot_text(text, options);
return format_snapshot_text(
text,
options,
&mut canonicalizer,
);
}
let Some(content_type) =
entry.get("type").and_then(Value::as_str)
@@ -123,7 +129,7 @@ pub fn format_response_items_snapshot(items: &[Value], options: &ContextSnapshot
let output = item
.get("output")
.and_then(Value::as_str)
.map(|output| format_snapshot_text(output, options))
.map(|output| format_snapshot_text(output, options, &mut canonicalizer))
.unwrap_or_else(|| "<NON_STRING_OUTPUT>".to_string());
format!("{idx:02}:function_call_output:{output}")
}
@@ -139,7 +145,9 @@ pub fn format_response_items_snapshot(items: &[Value], options: &ContextSnapshot
.collect::<Vec<&str>>()
.join(" ")
})
.map(|command| format_snapshot_text(&command, options))
.map(|command| {
format_snapshot_text(&command, options, &mut canonicalizer)
})
.filter(|cmd| !cmd.is_empty())
.unwrap_or_else(|| "<NO_COMMAND>".to_string());
format!("{idx:02}:local_shell_call:{command}")
@@ -151,7 +159,7 @@ pub fn format_response_items_snapshot(items: &[Value], options: &ContextSnapshot
.and_then(|summary| summary.first())
.and_then(|entry| entry.get("text"))
.and_then(Value::as_str)
.map(|text| format_snapshot_text(text, options))
.map(|text| format_snapshot_text(text, options, &mut canonicalizer))
.unwrap_or_else(|| "<NO_SUMMARY>".to_string());
let has_encrypted_content = item
.get("encrypted_content")
@@ -211,17 +219,71 @@ pub fn format_labeled_items_snapshot(
format!("Scenario: {scenario}\n\n{sections}")
}
fn format_snapshot_text(text: &str, options: &ContextSnapshotOptions) -> String {
#[derive(Default)]
struct SnapshotCanonicalizer {
cwd_placeholders: HashMap<String, usize>,
}
impl SnapshotCanonicalizer {
fn canonicalize_text(&mut self, text: &str) -> String {
if text.starts_with("<permissions instructions>") {
return "<PERMISSIONS_INSTRUCTIONS>".to_string();
}
if text.starts_with("# AGENTS.md instructions for ") {
return "<AGENTS_MD>".to_string();
}
if text.starts_with("<environment_context>") {
if let (Some(cwd_start), Some(cwd_end)) = (text.find("<cwd>"), text.find("</cwd>")) {
let cwd = &text[cwd_start + "<cwd>".len()..cwd_end];
return if cwd.ends_with("PRETURN_CONTEXT_DIFF_CWD") {
"<ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>".to_string()
} else {
let next_idx = self.cwd_placeholders.len() + 1;
let idx = *self
.cwd_placeholders
.entry(cwd.to_string())
.or_insert(next_idx);
format!("<ENVIRONMENT_CONTEXT:cwd=<CWD#{idx}>>")
};
}
return "<ENVIRONMENT_CONTEXT>".to_string();
}
if text.starts_with("<subagents>") {
let subagent_count = text
.lines()
.filter(|line| line.trim_start().starts_with("- "))
.count();
return format!("<SUBAGENTS:count={subagent_count}>");
}
if text.starts_with("You are performing a CONTEXT CHECKPOINT COMPACTION.") {
return "<SUMMARIZATION_PROMPT>".to_string();
}
if text.starts_with("Another language model started to solve this problem")
&& let Some((_, summary)) = text.split_once('\n')
{
return format!("<COMPACTION_SUMMARY>\n{summary}");
}
text.to_string()
}
}
fn format_snapshot_text(
text: &str,
options: &ContextSnapshotOptions,
canonicalizer: &mut SnapshotCanonicalizer,
) -> String {
match options.render_mode {
ContextSnapshotRenderMode::RedactedText => {
normalize_snapshot_line_endings(&canonicalize_snapshot_text(text)).replace('\n', "\\n")
normalize_snapshot_line_endings(&canonicalizer.canonicalize_text(text))
.replace('\n', "\\n")
}
ContextSnapshotRenderMode::FullText => {
normalize_snapshot_line_endings(text).replace('\n', "\\n")
}
ContextSnapshotRenderMode::KindWithTextPrefix { max_chars } => {
let normalized = normalize_snapshot_line_endings(&canonicalize_snapshot_text(text))
.replace('\n', "\\n");
let normalized =
normalize_snapshot_line_endings(&canonicalizer.canonicalize_text(text))
.replace('\n', "\\n");
if normalized.chars().count() <= max_chars {
normalized
} else {
@@ -237,42 +299,6 @@ fn normalize_snapshot_line_endings(text: &str) -> String {
text.replace("\r\n", "\n").replace('\r', "\n")
}
fn canonicalize_snapshot_text(text: &str) -> String {
if text.starts_with("<permissions instructions>") {
return "<PERMISSIONS_INSTRUCTIONS>".to_string();
}
if text.starts_with("# AGENTS.md instructions for ") {
return "<AGENTS_MD>".to_string();
}
if text.starts_with("<environment_context>") {
if let (Some(cwd_start), Some(cwd_end)) = (text.find("<cwd>"), text.find("</cwd>")) {
let cwd = &text[cwd_start + "<cwd>".len()..cwd_end];
return if cwd.ends_with("PRETURN_CONTEXT_DIFF_CWD") {
"<ENVIRONMENT_CONTEXT:cwd=PRETURN_CONTEXT_DIFF_CWD>".to_string()
} else {
"<ENVIRONMENT_CONTEXT:cwd=<CWD>>".to_string()
};
}
return "<ENVIRONMENT_CONTEXT>".to_string();
}
if text.starts_with("<subagents>") {
let subagent_count = text
.lines()
.filter(|line| line.trim_start().starts_with("- "))
.count();
return format!("<SUBAGENTS:count={subagent_count}>");
}
if text.starts_with("You are performing a CONTEXT CHECKPOINT COMPACTION.") {
return "<SUMMARIZATION_PROMPT>".to_string();
}
if text.starts_with("Another language model started to solve this problem")
&& let Some((_, summary)) = text.split_once('\n')
{
return format!("<COMPACTION_SUMMARY>\n{summary}");
}
text.to_string()
}
#[cfg(test)]
mod tests {
use super::ContextSnapshotOptions;
@@ -360,6 +386,50 @@ mod tests {
assert_eq!(rendered, "00:message/developer:<SUBAGENTS:count=2>");
}
#[test]
fn redacted_text_mode_assigns_distinct_cwd_placeholders_within_one_snapshot() {
let items = vec![
json!({
"type": "message",
"role": "user",
"content": [{
"type": "input_text",
"text": "<environment_context>\n <cwd>/tmp/one</cwd>\n</environment_context>"
}]
}),
json!({
"type": "message",
"role": "user",
"content": [{
"type": "input_text",
"text": "<environment_context>\n <cwd>/tmp/two</cwd>\n</environment_context>"
}]
}),
json!({
"type": "message",
"role": "user",
"content": [{
"type": "input_text",
"text": "<environment_context>\n <cwd>/tmp/one</cwd>\n</environment_context>"
}]
}),
];
let rendered = format_response_items_snapshot(
&items,
&ContextSnapshotOptions::default().render_mode(ContextSnapshotRenderMode::RedactedText),
);
assert_eq!(
rendered,
concat!(
"00:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD#1>>\n",
"01:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD#2>>\n",
"02:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD#1>>"
)
);
}
#[test]
fn kind_with_text_prefix_mode_normalizes_crlf_line_endings() {
let items = vec![json!({
codex-rs/core/tests/suite/snapshots/all__suite__model_visible_layout__model_visible_layout_cwd_change_refreshes_agents.snap
+4 -4
View File
@@ -8,19 +8,19 @@ Scenario: Second turn changes cwd to a directory with different AGENTS.md; updat
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user[2]:
[01] <AGENTS_MD>
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD#1>>
02:message/user:first turn in agents_one
## Second Request (agents_two cwd)
00:message/developer:<PERMISSIONS_INSTRUCTIONS>
01:message/user[2]:
[01] <AGENTS_MD>
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD#1>>
02:message/developer:<PERMISSIONS_INSTRUCTIONS>
03:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD>>
03:message/user:<ENVIRONMENT_CONTEXT:cwd=<CWD#2>>
04:message/user:first turn in agents_one
05:message/assistant:turn one complete
06:message/user[2]:
[01] <AGENTS_MD>
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD>>
[02] <ENVIRONMENT_CONTEXT:cwd=<CWD#2>>
07:message/user:second turn in agents_two