[codex] Remove legacy shell output formatting paths (#22706)

## Why

The client and tool pipeline still carried compatibility code for legacy
structured shell output. Current shell and apply_patch responses are
already plain text for model consumption, so keeping a
JSON-serialization path plus shell-item rewrite logic makes the request
formatter and tests preserve a format we do not need anymore.

## What Changed

- Removed the client-side shell output rewrite from
`core/src/client_common.rs`.
- Removed the structured exec-output formatter and the shell `freeform`
switch so tool emitters use one model-facing formatter.
- Collapsed apply_patch/shell serialization tests around the remaining
plain-text output expectations and removed duplicate one-variant
parameterized cases.
- Kept the `ApplyPatchModelOutput::ShellCommandViaHeredoc` compatibility
input shape, but no longer treats it as a separate output-format mode.

## Validation

- `cargo test -p codex-core client_common`
- `cargo test -p codex-core shell_serialization`
- `cargo test -p codex-core apply_patch_cli`
- `just fix -p codex-core`

## Documentation

No external Codex documentation update is needed.
This commit is contained in:
pakrym-oai
2026-05-18 09:57:54 -07:00
committed by GitHub
Unverified
parent adca1b643f
commit 82061660ae
11 changed files with 186 additions and 707 deletions
+1 -110
View File
@@ -2,13 +2,10 @@ pub use codex_api::ResponseEvent;
use codex_config::types::Personality;
use codex_protocol::error::Result;
use codex_protocol::models::BaseInstructions;
use codex_protocol::models::FunctionCallOutputBody;
use codex_protocol::models::ResponseItem;
use codex_tools::ToolSpec;
use futures::Stream;
use serde::Deserialize;
use serde_json::Value;
use std::collections::HashSet;
use std::pin::Pin;
use std::task::Context;
use std::task::Poll;
@@ -64,116 +61,10 @@ impl Default for Prompt {
impl Prompt {
pub(crate) fn get_formatted_input(&self) -> Vec<ResponseItem> {
let mut input = self.input.clone();
// when using the *Freeform* apply_patch tool specifically, tool outputs
// should be structured text, not json. Do NOT reserialize when using
// the Function tool - note that this differs from the check above for
// instructions. We declare the result as a named variable for clarity.
let is_freeform_apply_patch_tool_present = self.tools.iter().any(|tool| match tool {
ToolSpec::Freeform(f) => f.name == "apply_patch",
_ => false,
});
if is_freeform_apply_patch_tool_present {
reserialize_shell_outputs(&mut input);
}
input
self.input.clone()
}
}
fn reserialize_shell_outputs(items: &mut [ResponseItem]) {
let mut shell_call_ids: HashSet<String> = HashSet::new();
items.iter_mut().for_each(|item| match item {
ResponseItem::LocalShellCall { call_id, id, .. } => {
if let Some(identifier) = call_id.clone().or_else(|| id.clone()) {
shell_call_ids.insert(identifier);
}
}
ResponseItem::CustomToolCall {
id: _,
status: _,
call_id,
name,
input: _,
} => {
if name == "apply_patch" {
shell_call_ids.insert(call_id.clone());
}
}
ResponseItem::FunctionCall { name, call_id, .. }
if is_shell_tool_name(name) || name == "apply_patch" =>
{
shell_call_ids.insert(call_id.clone());
}
ResponseItem::FunctionCallOutput {
call_id, output, ..
}
| ResponseItem::CustomToolCallOutput {
call_id, output, ..
} => {
if shell_call_ids.remove(call_id)
&& let Some(structured) = output
.text_content()
.and_then(parse_structured_shell_output)
{
output.body = FunctionCallOutputBody::Text(structured);
}
}
_ => {}
})
}
fn is_shell_tool_name(name: &str) -> bool {
name == "shell"
}
#[derive(Deserialize)]
struct ExecOutputJson {
output: String,
metadata: ExecOutputMetadataJson,
}
#[derive(Deserialize)]
struct ExecOutputMetadataJson {
exit_code: i32,
duration_seconds: f32,
}
fn parse_structured_shell_output(raw: &str) -> Option<String> {
let parsed: ExecOutputJson = serde_json::from_str(raw).ok()?;
Some(build_structured_output(&parsed))
}
fn build_structured_output(parsed: &ExecOutputJson) -> String {
let mut sections = Vec::new();
sections.push(format!("Exit code: {}", parsed.metadata.exit_code));
sections.push(format!(
"Wall time: {} seconds",
parsed.metadata.duration_seconds
));
let mut output = parsed.output.clone();
if let Some((stripped, total_lines)) = strip_total_output_header(&parsed.output) {
sections.push(format!("Total output lines: {total_lines}"));
output = stripped.to_string();
}
sections.push("Output:".to_string());
sections.push(output);
sections.join("\n")
}
fn strip_total_output_header(output: &str) -> Option<(&str, u32)> {
let after_prefix = output.strip_prefix("Total output lines: ")?;
let (total_segment, remainder) = after_prefix.split_once('\n')?;
let total_lines = total_segment.parse::<u32>().ok()?;
let remainder = remainder.strip_prefix('\n').unwrap_or(remainder);
Some((remainder, total_lines))
}
pub struct ResponseStream {
pub(crate) rx_event: mpsc::Receiver<Result<ResponseEvent>>,
/// Signals the mapper task that the consumer stopped polling before the