Files
codex/codex-rs/mcp-server/src/lib.rs
Ruslan Nigmatullin 4d201e340e state: pass state db handles through consumers (#20561)
## Why

SQLite state was still being opened from consumer paths, including lazy
`OnceCell`-backed thread-store call sites. That let one process
construct multiple state DB connections for the same Codex home, which
makes SQLite lock contention and `database is locked` failures much
easier to hit.

State DB lifetime should be chosen by main-like entrypoints and tests,
then passed through explicitly. Consumers should use the supplied
`Option<StateDbHandle>` or `StateDbHandle` and keep their existing
filesystem fallback or error behavior when no handle is available.

The startup path also needs to keep the rollout crate in charge of
SQLite state initialization. Opening `codex_state::StateRuntime`
directly bypasses rollout metadata backfill, so entrypoints should
initialize through `codex_rollout::state_db` and receive a handle only
after required rollout backfills have completed.

## What Changed

- Initialize the state DB in main-like entrypoints for CLI, TUI,
app-server, exec, MCP server, and the thread-manager sample.
- Pass `Option<StateDbHandle>` through `ThreadManager`,
`LocalThreadStore`, app-server processors, TUI app wiring, rollout
listing/recording, personality migration, shell snapshot cleanup,
session-name lookup, and memory/device-key consumers.
- Remove the lazy local state DB wrapper from the thread store so
non-test consumers use only the supplied handle or their existing
fallback path.
- Make `codex_rollout::state_db::init` the local state startup path: it
opens/migrates SQLite, runs rollout metadata backfill when needed, waits
for concurrent backfill workers up to a bounded timeout, verifies
completion, and then returns the initialized handle.
- Keep optional/non-owning SQLite helpers, such as remote TUI local
reads, as open-only paths that do not run startup backfill.
- Switch app-server startup from direct
`codex_state::StateRuntime::init` to the rollout state initializer so
app-server cannot skip rollout backfill.
- Collapse split rollout lookup/list APIs so callers use the normal
methods with an optional state handle instead of `_with_state_db`
variants.
- Restore `getConversationSummary(ThreadId)` to delegate through
`ThreadStore::read_thread` instead of a LocalThreadStore-specific
rollout path special case.
- Keep DB-backed rollout path lookup keyed on the DB row and file
existence, without imposing the filesystem filename convention on
existing DB rows.
- Verify readable DB-backed rollout paths against `session_meta.id`
before returning them, so a stale SQLite row that points at another
thread's JSONL falls back to filesystem search and read-repairs the DB
row.
- Keep `debug prompt-input` filesystem-only so a one-off debug command
does not initialize or backfill SQLite state just to print prompt input.
- Keep goal-session test Codex homes alive only in the goal-specific
helper, rather than leaking tempdirs from the shared session test
helper.
- Update tests and call sites to pass explicit state handles where DB
behavior is expected and explicit `None` where filesystem-only behavior
is intended.

## Validation

- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo check -p
codex-rollout -p codex-thread-store -p codex-app-server -p codex-core -p
codex-tui -p codex-exec -p codex-cli --tests`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout state_db_`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout find_thread_path`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout find_thread_path -- --nocapture`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout try_init_ -- --nocapture`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo clippy -p
codex-rollout --lib -- -D warnings`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-thread-store
read_thread_falls_back_when_sqlite_path_points_to_another_thread --
--nocapture`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-thread-store`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
shell_snapshot`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
--test all personality_migration`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
--test all rollout_list_find`
- `RUST_MIN_STACK=8388608 CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
--test all rollout_list_find::find_prefers_sqlite_path_by_id --
--nocapture`
- `RUST_MIN_STACK=8388608 CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
--test all rollout_list_find -- --nocapture`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
interrupt_accounts_active_goal_before_pausing`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-app-server get_auth_status -- --test-threads=1`
- `CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-app-server --lib`
- `CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo check -p codex-rollout
-p codex-app-server --tests`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db just fix -p codex-rollout
-p codex-thread-store -p codex-core -p codex-app-server -p codex-tui -p
codex-exec -p codex-cli`
- `CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db just fix -p codex-rollout -p
codex-app-server`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db just fix -p
codex-rollout`
- `CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db just fix -p codex-core`
- `just argument-comment-lint -p codex-core`
- `just argument-comment-lint -p codex-rollout`

Focused coverage added in `codex-rollout`:

- `recorder::tests::state_db_init_backfills_before_returning` verifies
the rollout metadata row exists before startup init returns.
- `state_db::tests::try_init_waits_for_concurrent_startup_backfill`
verifies startup waits for another worker to finish backfill instead of
disabling the handle for the process.
-
`state_db::tests::try_init_times_out_waiting_for_stuck_startup_backfill`
verifies startup does not hang indefinitely on a stuck backfill lease.
-
`tests::find_thread_path_accepts_existing_state_db_path_without_canonical_filename`
verifies DB-backed lookup accepts valid existing rollout paths even when
the filename does not include the thread UUID.
-
`tests::find_thread_path_falls_back_when_db_path_points_to_another_thread`
verifies DB-backed lookup ignores a stale row whose existing path
belongs to another thread and read-repairs the row after filesystem
fallback.

Focused coverage updated in `codex-core`:

- `rollout_list_find::find_prefers_sqlite_path_by_id` now uses a
DB-preferred rollout file with matching `session_meta.id`, so it still
verifies that valid SQLite paths win without depending on stale/empty
rollout contents.

`cargo test -p codex-app-server thread_list_respects_search_term_filter
-- --test-threads=1 --nocapture` was attempted locally but timed out
waiting for the app-server test harness `initialize` response before
reaching the changed thread-list code path.

`bazel test //codex-rs/thread-store:thread-store-unit-tests
--test_output=errors` was attempted locally after the thread-store fix,
but this container failed before target analysis while fetching `v8+`
through BuildBuddy/direct GitHub. The equivalent local crate coverage,
including `cargo test -p codex-thread-store`, passes.

A plain local `cargo check -p codex-rollout -p codex-app-server --tests`
also requires system `libcap.pc` for `codex-linux-sandbox`; the
follow-up app-server check above used `CODEX_SKIP_VENDORED_BWRAP=1` in
this container.
2026-05-04 11:46:03 -07:00

247 lines
8.6 KiB
Rust
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
//! Prototype MCP server.
#![deny(clippy::print_stdout, clippy::print_stderr)]
use std::io::ErrorKind;
use std::io::Result as IoResult;
use std::sync::Arc;
use codex_arg0::Arg0DispatchPaths;
use codex_core::config::Config;
use codex_exec_server::EnvironmentManager;
use codex_exec_server::EnvironmentManagerArgs;
use codex_exec_server::ExecServerRuntimePaths;
use codex_login::default_client::set_default_client_residency_requirement;
use codex_utils_cli::CliConfigOverrides;
use rmcp::model::ClientNotification;
use rmcp::model::ClientRequest;
use rmcp::model::JsonRpcMessage;
use serde_json::Value;
use tokio::io::AsyncBufReadExt;
use tokio::io::AsyncWriteExt;
use tokio::io::BufReader;
use tokio::io::{self};
use tokio::sync::mpsc;
use tracing::debug;
use tracing::error;
use tracing::info;
use tracing_subscriber::EnvFilter;
use tracing_subscriber::prelude::*;
mod codex_tool_config;
mod codex_tool_runner;
mod exec_approval;
pub(crate) mod message_processor;
mod outgoing_message;
mod patch_approval;
use crate::message_processor::MessageProcessor;
use crate::outgoing_message::OutgoingJsonRpcMessage;
use crate::outgoing_message::OutgoingMessage;
use crate::outgoing_message::OutgoingMessageSender;
pub use crate::codex_tool_config::CodexToolCallParam;
pub use crate::codex_tool_config::CodexToolCallReplyParam;
pub use crate::exec_approval::ExecApprovalElicitRequestParams;
pub use crate::exec_approval::ExecApprovalResponse;
pub use crate::patch_approval::PatchApprovalElicitRequestParams;
pub use crate::patch_approval::PatchApprovalResponse;
/// Size of the bounded channels used to communicate between tasks. The value
/// is a balance between throughput and memory usage 128 messages should be
/// plenty for an interactive CLI.
const CHANNEL_CAPACITY: usize = 128;
const DEFAULT_ANALYTICS_ENABLED: bool = true;
const OTEL_SERVICE_NAME: &str = "codex_mcp_server";
type IncomingMessage = JsonRpcMessage<ClientRequest, Value, ClientNotification>;
pub async fn run_main(
arg0_paths: Arg0DispatchPaths,
cli_config_overrides: CliConfigOverrides,
) -> IoResult<()> {
let environment_manager = Arc::new(
EnvironmentManager::new(EnvironmentManagerArgs::new(
ExecServerRuntimePaths::from_optional_paths(
arg0_paths.codex_self_exe.clone(),
arg0_paths.codex_linux_sandbox_exe.clone(),
)?,
))
.await,
);
// Parse CLI overrides once and derive the base Config eagerly so later
// components do not need to work with raw TOML values.
let cli_kv_overrides = cli_config_overrides.parse_overrides().map_err(|e| {
std::io::Error::new(
ErrorKind::InvalidInput,
format!("error parsing -c overrides: {e}"),
)
})?;
let config = Config::load_with_cli_overrides(cli_kv_overrides)
.await
.map_err(|e| {
std::io::Error::new(ErrorKind::InvalidData, format!("error loading config: {e}"))
})?;
set_default_client_residency_requirement(config.enforce_residency.value());
let state_db = codex_core::init_state_db(&config).await;
let otel = codex_core::otel_init::build_provider(
&config,
env!("CARGO_PKG_VERSION"),
Some(OTEL_SERVICE_NAME),
DEFAULT_ANALYTICS_ENABLED,
)
.map_err(|e| {
std::io::Error::new(
ErrorKind::InvalidData,
format!("error loading otel config: {e}"),
)
})?;
let fmt_layer = tracing_subscriber::fmt::layer()
.with_writer(std::io::stderr)
.with_filter(EnvFilter::from_default_env());
let otel_logger_layer = otel.as_ref().and_then(|provider| provider.logger_layer());
let otel_tracing_layer = otel.as_ref().and_then(|provider| provider.tracing_layer());
let _ = tracing_subscriber::registry()
.with(fmt_layer)
.with(otel_logger_layer)
.with(otel_tracing_layer)
.try_init();
// Set up channels.
let (incoming_tx, mut incoming_rx) = mpsc::channel::<IncomingMessage>(CHANNEL_CAPACITY);
let (outgoing_tx, mut outgoing_rx) = mpsc::unbounded_channel::<OutgoingMessage>();
// Task: read from stdin, push to `incoming_tx`.
let stdin_reader_handle = tokio::spawn({
async move {
let stdin = io::stdin();
let reader = BufReader::new(stdin);
let mut lines = reader.lines();
while let Some(line) = lines.next_line().await.unwrap_or_default() {
match serde_json::from_str::<IncomingMessage>(&line) {
Ok(msg) => {
if incoming_tx.send(msg).await.is_err() {
// Receiver gone nothing left to do.
break;
}
}
Err(e) => error!("Failed to deserialize JSON-RPC message: {e}"),
}
}
debug!("stdin reader finished (EOF)");
}
});
// Task: process incoming messages.
let processor_handle = tokio::spawn({
let outgoing_message_sender = OutgoingMessageSender::new(outgoing_tx);
let mut processor = MessageProcessor::new(
outgoing_message_sender,
arg0_paths,
Arc::new(config),
environment_manager,
state_db,
)
.await;
async move {
while let Some(msg) = incoming_rx.recv().await {
match msg {
JsonRpcMessage::Request(r) => processor.process_request(r).await,
JsonRpcMessage::Response(r) => processor.process_response(r).await,
JsonRpcMessage::Notification(n) => processor.process_notification(n).await,
JsonRpcMessage::Error(e) => processor.process_error(e),
}
}
info!("processor task exited (channel closed)");
}
});
// Task: write outgoing messages to stdout.
let stdout_writer_handle = tokio::spawn(async move {
let mut stdout = io::stdout();
while let Some(outgoing_message) = outgoing_rx.recv().await {
let msg: OutgoingJsonRpcMessage = outgoing_message.into();
match serde_json::to_string(&msg) {
Ok(json) => {
if let Err(e) = stdout.write_all(json.as_bytes()).await {
error!("Failed to write to stdout: {e}");
break;
}
if let Err(e) = stdout.write_all(b"\n").await {
error!("Failed to write newline to stdout: {e}");
break;
}
}
Err(e) => error!("Failed to serialize JSON-RPC message: {e}"),
}
}
info!("stdout writer exited (channel closed)");
});
// Wait for all tasks to finish. The typical exit path is the stdin reader
// hitting EOF which, once it drops `incoming_tx`, propagates shutdown to
// the processor and then to the stdout task.
let _ = tokio::join!(stdin_reader_handle, processor_handle, stdout_writer_handle);
Ok(())
}
#[cfg(test)]
mod tests {
use super::*;
use codex_config::types::OtelExporterKind;
use codex_core::config::ConfigBuilder;
use pretty_assertions::assert_eq;
use std::collections::HashMap;
use tempfile::TempDir;
#[test]
fn mcp_server_defaults_analytics_to_enabled() {
assert_eq!(DEFAULT_ANALYTICS_ENABLED, true);
}
#[tokio::test]
async fn mcp_server_builds_otel_provider_with_logs_traces_and_metrics() -> anyhow::Result<()> {
let codex_home = TempDir::new()?;
let mut config = ConfigBuilder::default()
.codex_home(codex_home.path().to_path_buf())
.build()
.await?;
let exporter = OtelExporterKind::OtlpGrpc {
endpoint: "http://localhost:4317".to_string(),
headers: HashMap::new(),
tls: None,
};
config.otel.exporter = exporter.clone();
config.otel.trace_exporter = exporter.clone();
config.otel.metrics_exporter = exporter;
config.analytics_enabled = None;
let provider = codex_core::otel_init::build_provider(
&config,
"0.0.0-test",
Some(OTEL_SERVICE_NAME),
DEFAULT_ANALYTICS_ENABLED,
)
.map_err(|err| anyhow::anyhow!(err.to_string()))?
.expect("otel provider");
assert!(provider.logger.is_some(), "expected log exporter");
assert!(
provider.tracer_provider.is_some(),
"expected trace exporter"
);
assert!(provider.metrics().is_some(), "expected metrics exporter");
provider.shutdown();
Ok(())
}
}