chore: drop and clean from phase 1

codex-rs/Cargo.toml

@@ -340,7 +340,6 @@ ignored = [
     "icu_provider",
     "openssl-sys",
     "codex-utils-readiness",
-    "codex-utils-sanitizer",
     "codex-secrets",
 ]
 

codex-rs/core/Cargo.toml

@@ -49,6 +49,7 @@ codex-utils-absolute-path = { workspace = true }
 codex-utils-home-dir = { workspace = true }
 codex-utils-pty = { workspace = true }
 codex-utils-readiness = { workspace = true }
+codex-utils-sanitizer = { workspace = true }
 codex-utils-string = { workspace = true }
 codex-windows-sandbox = { package = "codex-windows-sandbox", path = "../windows-sandbox-rs" }
 dirs = { workspace = true }
@@ -67,7 +68,6 @@ notify = { workspace = true }
 once_cell = { workspace = true }
 os_info = { workspace = true }
 rand = { workspace = true }
-regex = { workspace = true }
 regex-lite = { workspace = true }
 reqwest = { workspace = true, features = ["json", "stream"] }
 rmcp = { workspace = true, default-features = false, features = [

codex-rs/core/src/memories/startup/dispatch.rs → codex-rs/core/src/memories/dispatch.rs

@@ -4,8 +4,8 @@ use crate::config::Constrained;
 use crate::memories::memory_root;
 use crate::memories::metrics;
 use crate::memories::phase_two;
+use crate::memories::phase2::spawn_phase2_completion_task;
 use crate::memories::prompts::build_consolidation_prompt;
-use crate::memories::startup::phase2::spawn_phase2_completion_task;
 use crate::memories::storage::rebuild_raw_memories_file_from_memories;
 use crate::memories::storage::sync_rollout_summaries_from_memories;
 use codex_protocol::protocol::AskForApproval;
@@ -19,6 +19,8 @@ use tracing::debug;
 use tracing::info;
 use tracing::warn;
 
+//TODO(jif) clean.
+
 fn completion_watermark(
     claimed_watermark: i64,
     latest_memories: &[codex_state::Stage1Output],
@@ -31,7 +33,7 @@ fn completion_watermark(
         .max(claimed_watermark)
 }
 
-pub(super) async fn run_global_memory_consolidation(
+pub(in crate::memories) async fn run_global_memory_consolidation(
     session: &Arc<Session>,
     config: Arc<Config>,
 ) -> bool {
@@ -261,7 +263,6 @@ pub(super) async fn run_global_memory_consolidation(
 #[cfg(test)]
 mod tests {
     use super::completion_watermark;
-    use super::memory_root;
     use super::run_global_memory_consolidation;
     use crate::CodexAuth;
     use crate::ThreadManager;
@@ -270,6 +271,7 @@ mod tests {
     use crate::codex::make_session_and_context;
     use crate::config::Config;
     use crate::config::test_config;
+    use crate::memories::memory_root;
     use crate::memories::raw_memories_file;
     use crate::memories::rollout_summaries_dir;
     use chrono::Utc;

codex-rs/core/src/memories/mod.rs

@@ -4,16 +4,20 @@
 //! - Phase 1: select rollouts, extract stage-1 raw memories, persist stage-1 outputs, and enqueue consolidation.
 //! - Phase 2: claim a global consolidation lock, materialize consolidation inputs, and dispatch one consolidation agent.
 
+mod dispatch;
+mod phase1;
+mod phase2;
 pub(crate) mod prompts;
-mod stage_one;
-mod startup;
+mod start;
 mod storage;
-
 #[cfg(test)]
 mod tests;
 
-use std::path::Path;
-use std::path::PathBuf;
+/// Starts the memory startup pipeline for eligible root sessions.
+/// This is the single entrypoint that `codex` uses to trigger memory startup.
+///
+/// This is the entry point to read and understand this module.
+pub(crate) use start::start_memories_startup_task;
 
 mod artifacts {
     pub(super) const ROLLOUT_SUMMARIES_SUBDIR: &str = "rollout_summaries";
@@ -22,10 +26,12 @@ mod artifacts {
 
 /// Phase 1 (startup extraction).
 mod phase_one {
+    /// Prompt used for phase 1.
+    pub(super) const PROMPT: &str = include_str!("../../templates/memories/stage_one_system.md");
     /// Maximum number of rollout candidates processed per startup pass.
     pub(super) const MAX_ROLLOUTS_PER_STARTUP: usize = 64;
     /// Concurrency cap for startup memory extraction and consolidation scheduling.
-    pub(super) const CONCURRENCY_LIMIT: usize = MAX_ROLLOUTS_PER_STARTUP;
+    pub(super) const CONCURRENCY_LIMIT: usize = 64;
     /// Fallback stage-1 rollout truncation limit (tokens) when model metadata
     /// does not include a valid context window.
     pub(super) const DEFAULT_STAGE_ONE_ROLLOUT_TOKEN_LIMIT: usize = 150_000;
@@ -46,6 +52,8 @@ mod phase_one {
     pub(super) const JOB_LEASE_SECONDS: i64 = 3_600;
     /// Backoff delay (seconds) before retrying a failed stage-1 extraction job.
     pub(super) const JOB_RETRY_DELAY_SECONDS: i64 = 3_600;
+    /// Maximum number of threads to scan.
+    pub(super) const THREAD_SCAN_LIMIT: usize = 5_000;
 }
 
 /// Phase 2 (aka `Consolidation`).
@@ -74,6 +82,9 @@ mod metrics {
     pub(super) const MEMORY_PHASE_TWO_INPUT: &str = "codex.memory.phase2.input";
 }
 
+use std::path::Path;
+use std::path::PathBuf;
+
 pub fn memory_root(codex_home: &Path) -> PathBuf {
     codex_home.join("memories")
 }
@@ -89,8 +100,3 @@ fn raw_memories_file(root: &Path) -> PathBuf {
 async fn ensure_layout(root: &Path) -> std::io::Result<()> {
     tokio::fs::create_dir_all(rollout_summaries_dir(root)).await
 }
-
-/// Starts the memory startup pipeline for eligible root sessions.
-///
-/// This is the single entrypoint that `codex` uses to trigger memory startup.
-pub(crate) use startup::start_memories_startup_task;