agent/codex
2
0
Fork 0
mirror of https://github.com/pchuan98/codex.git synced 2026-07-01 00:31:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

linearize history output normalization (#28309)

Browse Source 
## Why

When we prepare the conversation history, every tool call needs a
matching output.

Before this change, we scanned the full history again for every call. In
a tool-heavy conversation, that makes the work `O(items x calls)`, or
`O(n^2)` in the worst case.

## What

Scan the history once and collect the IDs of existing outputs. Then each
call can check its ID with an expected `O(1)` lookup.

The full normalization step is now expected `O(n)`. The output order and
missing-output behavior stay the same.

## Performance

Based on local rollout traces, one tool-heavy session reached roughly
17,050 transcript items with about 4,292 tool-call items. On a history
of that shape, the old `calls x items` scan does about 73.2 million
membership checks, while the new pass does about 21.3 thousand set
inserts/lookups. That is roughly 3.4k times less membership work in this
normalization step.

## Validation

- `just test -p codex-core normalize_` (19 passed)
This commit is contained in:
jif
2026-06-15 17:26:34 +01:00
committed by GitHub
Unverified
parent 11faf9af94
commit 828d7476a0
1 changed files with 73 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files
codex-rs/core/src/context_manager/normalize.rs
+73 -79
View File
@@ -12,6 +12,27 @@ const IMAGE_CONTENT_OMITTED_PLACEHOLDER: &str =
"image content omitted because you do not support image input";
pub(crate) fn ensure_call_outputs_present(items: &mut Vec<ResponseItem>) {
let mut function_output_ids = HashSet::new();
let mut tool_search_output_ids = HashSet::new();
let mut custom_tool_output_ids = HashSet::new();
for item in items.iter() {
match item {
ResponseItem::FunctionCallOutput { call_id, .. } => {
function_output_ids.insert(call_id.as_str());
}
ResponseItem::ToolSearchOutput {
call_id: Some(call_id),
..
} => {
tool_search_output_ids.insert(call_id.as_str());
}
ResponseItem::CustomToolCallOutput { call_id, .. } => {
custom_tool_output_ids.insert(call_id.as_str());
}
_ => {}
}
}
// Collect synthetic outputs to insert immediately after their calls.
// Store the insertion position (index of call) alongside the item so
// we can insert in reverse order and avoid index shifting.
@@ -19,99 +40,72 @@ pub(crate) fn ensure_call_outputs_present(items: &mut Vec<ResponseItem>) {
for (idx, item) in items.iter().enumerate() {
match item {
ResponseItem::FunctionCall { call_id, .. } => {
let has_output = items.iter().any(|i| match i {
ResponseItem::FunctionCall { call_id, .. }
if !function_output_ids.contains(call_id.as_str()) =>
{
info!("Function call output is missing for call id: {call_id}");
missing_outputs_to_insert.push((
idx,
ResponseItem::FunctionCallOutput {
call_id: existing, ..
} => existing == call_id,
_ => false,
});
if !has_output {
info!("Function call output is missing for call id: {call_id}");
missing_outputs_to_insert.push((
idx,
ResponseItem::FunctionCallOutput {
call_id: call_id.clone(),
output: FunctionCallOutputPayload::from_text("aborted".to_string()),
},
));
}
call_id: call_id.clone(),
output: FunctionCallOutputPayload::from_text("aborted".to_string()),
},
));
}
ResponseItem::ToolSearchCall {
call_id: Some(call_id),
..
} => {
let has_output = items.iter().any(|i| match i {
} if !tool_search_output_ids.contains(call_id.as_str()) => {
info!("Tool search output is missing for call id: {call_id}");
missing_outputs_to_insert.push((
idx,
ResponseItem::ToolSearchOutput {
call_id: Some(existing),
..
} => existing == call_id,
_ => false,
});
if !has_output {
info!("Tool search output is missing for call id: {call_id}");
missing_outputs_to_insert.push((
idx,
ResponseItem::ToolSearchOutput {
call_id: Some(call_id.clone()),
status: "completed".to_string(),
execution: "client".to_string(),
tools: Vec::new(),
},
));
}
call_id: Some(call_id.clone()),
status: "completed".to_string(),
execution: "client".to_string(),
tools: Vec::new(),
},
));
}
ResponseItem::CustomToolCall { call_id, .. } => {
let has_output = items.iter().any(|i| match i {
ResponseItem::CustomToolCall { call_id, .. }
if !custom_tool_output_ids.contains(call_id.as_str()) =>
{
error_or_panic(format!(
"Custom tool call output is missing for call id: {call_id}"
));
missing_outputs_to_insert.push((
idx,
ResponseItem::CustomToolCallOutput {
call_id: existing, ..
} => existing == call_id,
_ => false,
});
if !has_output {
error_or_panic(format!(
"Custom tool call output is missing for call id: {call_id}"
));
missing_outputs_to_insert.push((
idx,
ResponseItem::CustomToolCallOutput {
call_id: call_id.clone(),
name: None,
output: FunctionCallOutputPayload::from_text("aborted".to_string()),
},
));
}
call_id: call_id.clone(),
name: None,
output: FunctionCallOutputPayload::from_text("aborted".to_string()),
},
));
}
// LocalShellCall is represented in upstream streams by a FunctionCallOutput
ResponseItem::LocalShellCall { call_id, .. } => {
if let Some(call_id) = call_id.as_ref() {
let has_output = items.iter().any(|i| match i {
ResponseItem::FunctionCallOutput {
call_id: existing, ..
} => existing == call_id,
_ => false,
});
if !has_output {
error_or_panic(format!(
"Local shell call output is missing for call id: {call_id}"
));
missing_outputs_to_insert.push((
idx,
ResponseItem::FunctionCallOutput {
call_id: call_id.clone(),
output: FunctionCallOutputPayload::from_text("aborted".to_string()),
},
));
}
}
ResponseItem::LocalShellCall {
call_id: Some(call_id),
..
} if !function_output_ids.contains(call_id.as_str()) => {
error_or_panic(format!(
"Local shell call output is missing for call id: {call_id}"
));
missing_outputs_to_insert.push((
idx,
ResponseItem::FunctionCallOutput {
call_id: call_id.clone(),
output: FunctionCallOutputPayload::from_text("aborted".to_string()),
},
));
}
_ => {}
}
}
drop((
function_output_ids,
tool_search_output_ids,
custom_tool_output_ids,
));
// Insert synthetic outputs in reverse index order to avoid re-indexing.
for (idx, output_item) in missing_outputs_to_insert.into_iter().rev() {