Add new thread items and rewire event parsing to use them (#5418)

1. Adds AgentMessage,  Reasoning,  WebSearch items.
2. Switches the ResponseItem parsing to use new items and then also emit
3. Removes user-item kind and filters out "special" (environment) user
items when returning to clients.
This commit is contained in:
pakrym-oai
2025-10-22 10:14:50 -07:00
committed by GitHub
parent 34c5a9eaa9
commit 3c90728a29
23 changed files with 775 additions and 476 deletions

View File

@@ -1,3 +1,9 @@
use crate::protocol::AgentMessageEvent;
use crate::protocol::AgentReasoningEvent;
use crate::protocol::AgentReasoningRawContentEvent;
use crate::protocol::EventMsg;
use crate::protocol::UserMessageEvent;
use crate::protocol::WebSearchEndEvent;
use crate::user_input::UserInput;
use schemars::JsonSchema;
use serde::Deserialize;
@@ -7,6 +13,9 @@ use ts_rs::TS;
#[derive(Debug, Clone, Deserialize, Serialize, TS, JsonSchema)]
pub enum TurnItem {
UserMessage(UserMessageItem),
AgentMessage(AgentMessageItem),
Reasoning(ReasoningItem),
WebSearch(WebSearchItem),
}
#[derive(Debug, Clone, Deserialize, Serialize, TS, JsonSchema)]
@@ -15,6 +24,31 @@ pub struct UserMessageItem {
pub content: Vec<UserInput>,
}
#[derive(Debug, Clone, Deserialize, Serialize, TS, JsonSchema)]
pub enum AgentMessageContent {
Text { text: String },
}
#[derive(Debug, Clone, Deserialize, Serialize, TS, JsonSchema)]
pub struct AgentMessageItem {
pub id: String,
pub content: Vec<AgentMessageContent>,
}
#[derive(Debug, Clone, Deserialize, Serialize, TS, JsonSchema)]
pub struct ReasoningItem {
pub id: String,
pub summary_text: Vec<String>,
#[serde(default)]
pub raw_content: Vec<String>,
}
#[derive(Debug, Clone, Deserialize, Serialize, TS, JsonSchema)]
pub struct WebSearchItem {
pub id: String,
pub query: String,
}
impl UserMessageItem {
pub fn new(content: &[UserInput]) -> Self {
Self {
@@ -22,12 +56,104 @@ impl UserMessageItem {
content: content.to_vec(),
}
}
pub fn as_legacy_event(&self) -> EventMsg {
EventMsg::UserMessage(UserMessageEvent {
message: self.message(),
images: Some(self.image_urls()),
})
}
pub fn message(&self) -> String {
self.content
.iter()
.map(|c| match c {
UserInput::Text { text } => text.clone(),
_ => String::new(),
})
.collect::<Vec<String>>()
.join("")
}
pub fn image_urls(&self) -> Vec<String> {
self.content
.iter()
.filter_map(|c| match c {
UserInput::Image { image_url } => Some(image_url.clone()),
_ => None,
})
.collect()
}
}
impl AgentMessageItem {
pub fn new(content: &[AgentMessageContent]) -> Self {
Self {
id: uuid::Uuid::new_v4().to_string(),
content: content.to_vec(),
}
}
pub fn as_legacy_events(&self) -> Vec<EventMsg> {
self.content
.iter()
.map(|c| match c {
AgentMessageContent::Text { text } => EventMsg::AgentMessage(AgentMessageEvent {
message: text.clone(),
}),
})
.collect()
}
}
impl ReasoningItem {
pub fn as_legacy_events(&self, show_raw_agent_reasoning: bool) -> Vec<EventMsg> {
let mut events = Vec::new();
for summary in &self.summary_text {
events.push(EventMsg::AgentReasoning(AgentReasoningEvent {
text: summary.clone(),
}));
}
if show_raw_agent_reasoning {
for entry in &self.raw_content {
events.push(EventMsg::AgentReasoningRawContent(
AgentReasoningRawContentEvent {
text: entry.clone(),
},
));
}
}
events
}
}
impl WebSearchItem {
pub fn as_legacy_event(&self) -> EventMsg {
EventMsg::WebSearchEnd(WebSearchEndEvent {
call_id: self.id.clone(),
query: self.query.clone(),
})
}
}
impl TurnItem {
pub fn id(&self) -> String {
match self {
TurnItem::UserMessage(item) => item.id.clone(),
TurnItem::AgentMessage(item) => item.id.clone(),
TurnItem::Reasoning(item) => item.id.clone(),
TurnItem::WebSearch(item) => item.id.clone(),
}
}
pub fn as_legacy_events(&self, show_raw_agent_reasoning: bool) -> Vec<EventMsg> {
match self {
TurnItem::UserMessage(item) => vec![item.as_legacy_event()],
TurnItem::AgentMessage(item) => item.as_legacy_events(),
TurnItem::WebSearch(item) => vec![item.as_legacy_event()],
TurnItem::Reasoning(item) => item.as_legacy_events(show_raw_agent_reasoning),
}
}
}

View File

@@ -770,69 +770,13 @@ pub struct AgentMessageEvent {
pub message: String,
}
#[derive(Debug, Clone, Deserialize, Serialize, JsonSchema, TS)]
#[serde(rename_all = "snake_case")]
pub enum InputMessageKind {
/// Plain user text (default)
Plain,
/// XML-wrapped user instructions (<user_instructions>...)
UserInstructions,
/// XML-wrapped environment context (<environment_context>...)
EnvironmentContext,
}
#[derive(Debug, Clone, Deserialize, Serialize, JsonSchema, TS)]
pub struct UserMessageEvent {
pub message: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub kind: Option<InputMessageKind>,
#[serde(skip_serializing_if = "Option::is_none")]
pub images: Option<Vec<String>>,
}
impl<T, U> From<(T, U)> for InputMessageKind
where
T: AsRef<str>,
U: AsRef<str>,
{
fn from(value: (T, U)) -> Self {
let (_role, message) = value;
let message = message.as_ref();
let trimmed = message.trim();
if starts_with_ignore_ascii_case(trimmed, ENVIRONMENT_CONTEXT_OPEN_TAG)
&& ends_with_ignore_ascii_case(trimmed, ENVIRONMENT_CONTEXT_CLOSE_TAG)
{
InputMessageKind::EnvironmentContext
} else if starts_with_ignore_ascii_case(trimmed, USER_INSTRUCTIONS_OPEN_TAG)
&& ends_with_ignore_ascii_case(trimmed, USER_INSTRUCTIONS_CLOSE_TAG)
{
InputMessageKind::UserInstructions
} else {
InputMessageKind::Plain
}
}
}
fn starts_with_ignore_ascii_case(text: &str, prefix: &str) -> bool {
let text_bytes = text.as_bytes();
let prefix_bytes = prefix.as_bytes();
text_bytes.len() >= prefix_bytes.len()
&& text_bytes
.iter()
.zip(prefix_bytes.iter())
.all(|(a, b)| a.eq_ignore_ascii_case(b))
}
fn ends_with_ignore_ascii_case(text: &str, suffix: &str) -> bool {
let text_bytes = text.as_bytes();
let suffix_bytes = suffix.as_bytes();
text_bytes.len() >= suffix_bytes.len()
&& text_bytes[text_bytes.len() - suffix_bytes.len()..]
.iter()
.zip(suffix_bytes.iter())
.all(|(a, b)| a.eq_ignore_ascii_case(b))
}
#[derive(Debug, Clone, Deserialize, Serialize, JsonSchema, TS)]
pub struct AgentMessageDeltaEvent {
pub delta: String,