[codex] Add rollout-backed thread content search (#23519)

## Summary - add experimental `thread/search` for local rollout-backed thread search using `rg` over JSONL rollouts - return search-specific result rows with optional previews instead of storing preview data on `StoredThread` or ordinary `Thread` responses - keep `thread/list` separate from full-content search and document the new app-server surface ## Testing - `cargo test -p codex-app-server-protocol` - `cargo test -p codex-app-server thread_search_returns_content_and_title_matches -- --nocapture`
2026-07-01 00:31:56 +08:00 · 2026-05-21 11:52:24 -07:00
parent 4acb456bfe
commit ac0bff27e7
22 changed files with 935 additions and 2 deletions
@@ -88,6 +88,7 @@ use codex_app_server_protocol::ThreadRealtimeStartParams;
 use codex_app_server_protocol::ThreadRealtimeStopParams;
 use codex_app_server_protocol::ThreadResumeParams;
 use codex_app_server_protocol::ThreadRollbackParams;
+use codex_app_server_protocol::ThreadSearchParams;
 use codex_app_server_protocol::ThreadSetNameParams;
 use codex_app_server_protocol::ThreadSettingsUpdateParams;
 use codex_app_server_protocol::ThreadShellCommandParams;
@@ -508,6 +509,15 @@ impl McpProcess {
        self.send_request("thread/list", params).await
    }

+    /// Send a `thread/search` JSON-RPC request.
+    pub async fn send_thread_search_request(
+        &mut self,
+        params: ThreadSearchParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("thread/search", params).await
+    }
+
    /// Send a `thread/loaded/list` JSON-RPC request.
    pub async fn send_thread_loaded_list_request(
        &mut self,
@@ -17,6 +17,7 @@ use codex_app_server_protocol::SessionSource;
 use codex_app_server_protocol::SortDirection;
 use codex_app_server_protocol::ThreadListCwdFilter;
 use codex_app_server_protocol::ThreadListResponse;
+use codex_app_server_protocol::ThreadSearchResponse;
 use codex_app_server_protocol::ThreadSortKey;
 use codex_app_server_protocol::ThreadSourceKind;
 use codex_app_server_protocol::ThreadStartParams;
@@ -660,6 +661,161 @@ sqlite = true
    Ok(())
 }

+#[tokio::test]
+async fn thread_search_returns_content_matches() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let older_match = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-02T10-00-00",
+        "2025-01-02T10:00:00Z",
+        "match: needle",
+        Some("mock_provider"),
+        /*git_info*/ None,
+    )?;
+    let _non_match = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-02T11-00-00",
+        "2025-01-02T11:00:00Z",
+        "no hit here",
+        Some("mock_provider"),
+        /*git_info*/ None,
+    )?;
+    let newer_match = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-02T12-00-00",
+        "2025-01-02T12:00:00Z",
+        "needle suffix",
+        Some("mock_provider"),
+        /*git_info*/ None,
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+    let request_id = mcp
+        .send_thread_search_request(codex_app_server_protocol::ThreadSearchParams {
+            cursor: None,
+            limit: Some(10),
+            sort_key: None,
+            sort_direction: None,
+            source_kinds: None,
+            archived: None,
+            search_term: "needle".to_string(),
+        })
+        .await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let ThreadSearchResponse {
+        data, next_cursor, ..
+    } = to_response::<ThreadSearchResponse>(resp)?;
+
+    assert_eq!(next_cursor, None);
+    let ids: Vec<_> = data
+        .iter()
+        .map(|result| result.thread.id.as_str())
+        .collect();
+    assert_eq!(ids, vec![newer_match, older_match]);
+    assert_eq!(data[0].snippet, "needle suffix");
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_search_matches_json_escaped_content() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let search_term = r#"quoted "needle" \ path"#;
+    let thread_id = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-02T10-00-00",
+        "2025-01-02T10:00:00Z",
+        search_term,
+        Some("mock_provider"),
+        /*git_info*/ None,
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+    let request_id = mcp
+        .send_thread_search_request(codex_app_server_protocol::ThreadSearchParams {
+            cursor: None,
+            limit: Some(10),
+            sort_key: None,
+            sort_direction: None,
+            source_kinds: None,
+            archived: None,
+            search_term: search_term.to_string(),
+        })
+        .await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let ThreadSearchResponse { data, .. } = to_response::<ThreadSearchResponse>(resp)?;
+
+    assert_eq!(data.len(), 1);
+    assert_eq!(data[0].thread.id, thread_id);
+    assert_eq!(data[0].snippet, search_term);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_search_filters_by_source_kind() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let cli_id = create_fake_rollout(
+        codex_home.path(),
+        "2025-02-01T10-00-00",
+        "2025-02-01T10:00:00Z",
+        "shared needle",
+        Some("mock_provider"),
+        /*git_info*/ None,
+    )?;
+    let exec_id = create_fake_rollout_with_source(
+        codex_home.path(),
+        "2025-02-01T11-00-00",
+        "2025-02-01T11:00:00Z",
+        "shared needle",
+        Some("mock_provider"),
+        /*git_info*/ None,
+        CoreSessionSource::Exec,
+    )?;
+
+    let mut mcp = init_mcp(codex_home.path()).await?;
+    let request_id = mcp
+        .send_thread_search_request(codex_app_server_protocol::ThreadSearchParams {
+            cursor: None,
+            limit: Some(10),
+            sort_key: None,
+            sort_direction: None,
+            source_kinds: Some(vec![ThreadSourceKind::Exec]),
+            archived: None,
+            search_term: "needle".to_string(),
+        })
+        .await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let ThreadSearchResponse { data, .. } = to_response::<ThreadSearchResponse>(resp)?;
+
+    let ids: Vec<_> = data
+        .iter()
+        .map(|result| result.thread.id.as_str())
+        .collect();
+    assert_eq!(ids, vec![exec_id.as_str()]);
+    assert_ne!(cli_id, exec_id);
+
+    Ok(())
+}
+
 #[tokio::test]
 async fn thread_list_state_db_only_returns_sqlite_without_jsonl_repair() -> Result<()> {
    let codex_home = TempDir::new()?;