mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
5267e805fb
## Description This PR adds a new `historyMode = "legacy" | "paginated"` to `Thread`. This will be stored in `SessionMeta` in the JSONL rollout file and as a new column in the SQLite thread_metadata table, and exposed on `thread/start` and on the `Thread` object in app-server. ## What changed - Added canonical `ThreadHistoryMode` with `legacy` and `paginated`, defaulting old and new SessionMeta to `legacy`. - Carried `history_mode` through core session config, ThreadStore stored metadata, local/in-memory stores, rollout metadata extraction, and the existing SQLite `threads` table. - Added experimental `historyMode` to app-server v2 `Thread` and `thread/start`. - Made paginated stored threads metadata-discoverable but unsupported for legacy full-history reads, `load_history`, live resume, and create paths. - Regenerated app-server schema fixtures and added protocol/state/thread-store/app-server coverage for persistence and fail-closed behavior. ## Compatibility floor Because users may be running various versions of Codex binaries on the same machine (TUI, Codex App, etc.), we will need to establish a compatibility floor for upcoming paginated threads, which will change how thread storage reads and writes work. The overall plan here: ``` Release N: - Add historyMode to SessionMeta / Thread / SQLite metadata. - Teach binaries to understand paginated threads. - If a binary sees `historyMode="paginated"` but does not support the paginated contract, it refuses to resume/mutate the thread. - Default remains `"legacy"`. Release N+1: - First-party clients start opting into paginated threads where appropriate. - Internal dogfood / staged rollout. - Measure old-client usage and paginated-thread unsupported errors. Release N+2: - Only after Release N+ is overwhelmingly deployed, make paginated the default. - Accept that a small tail of N-1-or-older binaries may not understand paginated threads. ``` The important behavior change is fail-closed handling for a binary that encounters a persisted `paginated` thread before it knows how to fully support paginated history. In app-server, if a thread is `paginated`, we will: - allow metadata-only discovery paths like `thread/list` and `thread/read(includeTurns=false)`, so clients can still see the thread and inspect its `historyMode` - reject legacy full-history/live-thread paths like `thread/read(includeTurns=true)` and `thread/resume` with an unsupported JSON-RPC error - avoid silently treating an unknown or future `historyMode` as `legacy` Under the hood, the ThreadStore layer also rejects legacy operations that would need to load or replay the full thread history for a paginated thread. That gives us the behavior we want for Release N: future paginated threads are visible, but this binary fails closed instead of trying to operate on them as if they were legacy threads.
337 lines
9.9 KiB
Rust
337 lines
9.9 KiB
Rust
use anyhow::Result;
|
|
use codex_protocol::SessionId;
|
|
use codex_protocol::ThreadId;
|
|
use codex_protocol::protocol::EventMsg;
|
|
use codex_protocol::protocol::GitInfo;
|
|
use codex_protocol::protocol::SessionMeta;
|
|
use codex_protocol::protocol::SessionMetaLine;
|
|
use codex_protocol::protocol::SessionSource;
|
|
use codex_protocol::protocol::TokenCountEvent;
|
|
use codex_protocol::protocol::TokenUsage;
|
|
use codex_protocol::protocol::TokenUsageInfo;
|
|
use serde_json::json;
|
|
use std::fs;
|
|
use std::fs::FileTimes;
|
|
use std::path::Path;
|
|
use std::path::PathBuf;
|
|
use uuid::Uuid;
|
|
|
|
pub fn rollout_path(codex_home: &Path, filename_ts: &str, thread_id: &str) -> PathBuf {
|
|
let year = &filename_ts[0..4];
|
|
let month = &filename_ts[5..7];
|
|
let day = &filename_ts[8..10];
|
|
codex_home
|
|
.join("sessions")
|
|
.join(year)
|
|
.join(month)
|
|
.join(day)
|
|
.join(format!("rollout-{filename_ts}-{thread_id}.jsonl"))
|
|
}
|
|
|
|
/// Create a minimal rollout file under `CODEX_HOME/sessions/YYYY/MM/DD/`.
|
|
///
|
|
/// - `filename_ts` is the filename timestamp component in `YYYY-MM-DDThh-mm-ss` format.
|
|
/// - `meta_rfc3339` is the envelope timestamp used in JSON lines.
|
|
/// - `preview` is the user message preview text.
|
|
/// - `model_provider` optionally sets the provider in the session meta payload.
|
|
///
|
|
/// Returns the generated conversation/session UUID as a string.
|
|
pub fn create_fake_rollout(
|
|
codex_home: &Path,
|
|
filename_ts: &str,
|
|
meta_rfc3339: &str,
|
|
preview: &str,
|
|
model_provider: Option<&str>,
|
|
git_info: Option<GitInfo>,
|
|
) -> Result<String> {
|
|
create_fake_rollout_with_source(
|
|
codex_home,
|
|
filename_ts,
|
|
meta_rfc3339,
|
|
preview,
|
|
model_provider,
|
|
git_info,
|
|
SessionSource::Cli,
|
|
)
|
|
}
|
|
|
|
/// Creates a minimal rollout whose history includes a persisted token usage event.
|
|
///
|
|
/// Resume and fork tests use this fixture to verify lifecycle replay of restored
|
|
/// usage without starting a model turn. The exact token values are intentionally
|
|
/// non-zero and asymmetric so assertions catch swapped total/last fields and
|
|
/// dropped cached or reasoning counters.
|
|
pub fn create_fake_rollout_with_token_usage(
|
|
codex_home: &Path,
|
|
filename_ts: &str,
|
|
meta_rfc3339: &str,
|
|
preview: &str,
|
|
model_provider: Option<&str>,
|
|
) -> Result<String> {
|
|
let thread_id = create_fake_rollout(
|
|
codex_home,
|
|
filename_ts,
|
|
meta_rfc3339,
|
|
preview,
|
|
model_provider,
|
|
/*git_info*/ None,
|
|
)?;
|
|
let payload = serde_json::to_value(EventMsg::TokenCount(TokenCountEvent {
|
|
info: Some(TokenUsageInfo {
|
|
total_token_usage: TokenUsage {
|
|
input_tokens: 120,
|
|
cached_input_tokens: 20,
|
|
output_tokens: 30,
|
|
reasoning_output_tokens: 10,
|
|
total_tokens: 150,
|
|
},
|
|
last_token_usage: TokenUsage {
|
|
input_tokens: 70,
|
|
cached_input_tokens: 10,
|
|
output_tokens: 20,
|
|
reasoning_output_tokens: 5,
|
|
total_tokens: 90,
|
|
},
|
|
model_context_window: Some(200_000),
|
|
}),
|
|
rate_limits: None,
|
|
}))?;
|
|
let file_path = rollout_path(codex_home, filename_ts, &thread_id);
|
|
let line = json!({
|
|
"timestamp": meta_rfc3339,
|
|
"type": "event_msg",
|
|
"payload": payload
|
|
})
|
|
.to_string();
|
|
fs::write(
|
|
&file_path,
|
|
format!("{}{}\n", fs::read_to_string(&file_path)?, line),
|
|
)?;
|
|
Ok(thread_id)
|
|
}
|
|
|
|
/// Create a minimal rollout file with an explicit session source.
|
|
pub fn create_fake_rollout_with_source(
|
|
codex_home: &Path,
|
|
filename_ts: &str,
|
|
meta_rfc3339: &str,
|
|
preview: &str,
|
|
model_provider: Option<&str>,
|
|
git_info: Option<GitInfo>,
|
|
source: SessionSource,
|
|
) -> Result<String> {
|
|
create_fake_rollout_with_source_and_parent_thread_id(
|
|
codex_home,
|
|
filename_ts,
|
|
meta_rfc3339,
|
|
preview,
|
|
model_provider,
|
|
git_info,
|
|
source,
|
|
/*session_id*/ None,
|
|
/*parent_thread_id*/ None,
|
|
)
|
|
}
|
|
|
|
/// Create a minimal rollout file with an explicit root session and control parent.
|
|
#[allow(clippy::too_many_arguments)]
|
|
pub fn create_fake_parented_rollout_with_source(
|
|
codex_home: &Path,
|
|
filename_ts: &str,
|
|
meta_rfc3339: &str,
|
|
preview: &str,
|
|
model_provider: Option<&str>,
|
|
git_info: Option<GitInfo>,
|
|
source: SessionSource,
|
|
session_id: SessionId,
|
|
parent_thread_id: ThreadId,
|
|
) -> Result<String> {
|
|
create_fake_rollout_with_source_and_parent_thread_id(
|
|
codex_home,
|
|
filename_ts,
|
|
meta_rfc3339,
|
|
preview,
|
|
model_provider,
|
|
git_info,
|
|
source,
|
|
Some(session_id),
|
|
Some(parent_thread_id),
|
|
)
|
|
}
|
|
|
|
#[allow(clippy::too_many_arguments)]
|
|
fn create_fake_rollout_with_source_and_parent_thread_id(
|
|
codex_home: &Path,
|
|
filename_ts: &str,
|
|
meta_rfc3339: &str,
|
|
preview: &str,
|
|
model_provider: Option<&str>,
|
|
git_info: Option<GitInfo>,
|
|
source: SessionSource,
|
|
session_id: Option<SessionId>,
|
|
parent_thread_id: Option<ThreadId>,
|
|
) -> Result<String> {
|
|
let uuid = Uuid::new_v4();
|
|
let uuid_str = uuid.to_string();
|
|
let conversation_id = ThreadId::from_string(&uuid_str)?;
|
|
let session_id = session_id.unwrap_or_else(|| conversation_id.into());
|
|
|
|
let file_path = rollout_path(codex_home, filename_ts, &uuid_str);
|
|
let dir = file_path
|
|
.parent()
|
|
.ok_or_else(|| anyhow::anyhow!("missing rollout parent directory"))?;
|
|
fs::create_dir_all(dir)?;
|
|
|
|
// Build JSONL lines
|
|
let meta = SessionMeta {
|
|
session_id,
|
|
id: conversation_id,
|
|
forked_from_id: None,
|
|
parent_thread_id,
|
|
timestamp: meta_rfc3339.to_string(),
|
|
cwd: PathBuf::from("/"),
|
|
originator: "codex".to_string(),
|
|
cli_version: "0.0.0".to_string(),
|
|
source,
|
|
thread_source: None,
|
|
agent_path: None,
|
|
agent_nickname: None,
|
|
agent_role: None,
|
|
model_provider: model_provider.map(str::to_string),
|
|
base_instructions: None,
|
|
dynamic_tools: None,
|
|
selected_capability_roots: Vec::new(),
|
|
memory_mode: None,
|
|
history_mode: Default::default(),
|
|
multi_agent_version: None,
|
|
context_window: None,
|
|
};
|
|
let payload = serde_json::to_value(SessionMetaLine {
|
|
meta,
|
|
git: git_info,
|
|
})?;
|
|
|
|
let lines = [
|
|
json!({
|
|
"timestamp": meta_rfc3339,
|
|
"type": "session_meta",
|
|
"payload": payload
|
|
})
|
|
.to_string(),
|
|
json!({
|
|
"timestamp": meta_rfc3339,
|
|
"type":"response_item",
|
|
"payload": {
|
|
"type":"message",
|
|
"role":"user",
|
|
"content":[{"type":"input_text","text": preview}]
|
|
}
|
|
})
|
|
.to_string(),
|
|
json!({
|
|
"timestamp": meta_rfc3339,
|
|
"type":"event_msg",
|
|
"payload": {
|
|
"type":"user_message",
|
|
"message": preview,
|
|
"kind": "plain"
|
|
}
|
|
})
|
|
.to_string(),
|
|
];
|
|
|
|
fs::write(&file_path, lines.join("\n") + "\n")?;
|
|
let parsed = chrono::DateTime::parse_from_rfc3339(meta_rfc3339)?.with_timezone(&chrono::Utc);
|
|
let times = FileTimes::new().set_modified(parsed.into());
|
|
std::fs::OpenOptions::new()
|
|
.append(true)
|
|
.open(&file_path)?
|
|
.set_times(times)?;
|
|
Ok(uuid_str)
|
|
}
|
|
|
|
pub fn create_fake_rollout_with_text_elements(
|
|
codex_home: &Path,
|
|
filename_ts: &str,
|
|
meta_rfc3339: &str,
|
|
preview: &str,
|
|
text_elements: Vec<serde_json::Value>,
|
|
model_provider: Option<&str>,
|
|
git_info: Option<GitInfo>,
|
|
) -> Result<String> {
|
|
let uuid = Uuid::new_v4();
|
|
let uuid_str = uuid.to_string();
|
|
let conversation_id = ThreadId::from_string(&uuid_str)?;
|
|
|
|
// sessions/YYYY/MM/DD derived from filename_ts (YYYY-MM-DDThh-mm-ss)
|
|
let year = &filename_ts[0..4];
|
|
let month = &filename_ts[5..7];
|
|
let day = &filename_ts[8..10];
|
|
let dir = codex_home.join("sessions").join(year).join(month).join(day);
|
|
fs::create_dir_all(&dir)?;
|
|
|
|
let file_path = dir.join(format!("rollout-{filename_ts}-{uuid}.jsonl"));
|
|
|
|
// Build JSONL lines
|
|
let meta = SessionMeta {
|
|
session_id: conversation_id.into(),
|
|
id: conversation_id,
|
|
forked_from_id: None,
|
|
parent_thread_id: None,
|
|
timestamp: meta_rfc3339.to_string(),
|
|
cwd: PathBuf::from("/"),
|
|
originator: "codex".to_string(),
|
|
cli_version: "0.0.0".to_string(),
|
|
source: SessionSource::Cli,
|
|
thread_source: None,
|
|
agent_path: None,
|
|
agent_nickname: None,
|
|
agent_role: None,
|
|
model_provider: model_provider.map(str::to_string),
|
|
base_instructions: None,
|
|
dynamic_tools: None,
|
|
selected_capability_roots: Vec::new(),
|
|
memory_mode: None,
|
|
history_mode: Default::default(),
|
|
multi_agent_version: None,
|
|
context_window: None,
|
|
};
|
|
let payload = serde_json::to_value(SessionMetaLine {
|
|
meta,
|
|
git: git_info,
|
|
})?;
|
|
|
|
let lines = [
|
|
json!( {
|
|
"timestamp": meta_rfc3339,
|
|
"type": "session_meta",
|
|
"payload": payload
|
|
})
|
|
.to_string(),
|
|
json!( {
|
|
"timestamp": meta_rfc3339,
|
|
"type":"response_item",
|
|
"payload": {
|
|
"type":"message",
|
|
"role":"user",
|
|
"content":[{"type":"input_text","text": preview}]
|
|
}
|
|
})
|
|
.to_string(),
|
|
json!( {
|
|
"timestamp": meta_rfc3339,
|
|
"type":"event_msg",
|
|
"payload": {
|
|
"type":"user_message",
|
|
"message": preview,
|
|
"text_elements": text_elements,
|
|
"local_images": []
|
|
}
|
|
})
|
|
.to_string(),
|
|
];
|
|
|
|
fs::write(file_path, lines.join("\n") + "\n")?;
|
|
Ok(uuid_str)
|
|
}
|