Merge branch 'main' into add-github-action-for-nix

Author: jessfraz

codex-rs/core/src/bash.rs

@@ -73,6 +73,9 @@ pub fn try_parse_word_only_commands_sequence(tree: &Tree, src: &str) -> Option<V
         }
     }
 
+    // Walk uses a stack (LIFO), so re-sort by position to restore source order.
+    command_nodes.sort_by_key(|node| node.start_byte());
+
     let mut commands = Vec::new();
     for node in command_nodes {
         if let Some(words) = parse_plain_command_from_node(node, src) {
@@ -150,10 +153,10 @@ mod tests {
         let src = "ls && pwd; echo 'hi there' | wc -l";
         let cmds = parse_seq(src).unwrap();
         let expected: Vec<Vec<String>> = vec![
-            vec!["wc".to_string(), "-l".to_string()],
-            vec!["echo".to_string(), "hi there".to_string()],
-            vec!["pwd".to_string()],
             vec!["ls".to_string()],
+            vec!["pwd".to_string()],
+            vec!["echo".to_string(), "hi there".to_string()],
+            vec!["wc".to_string(), "-l".to_string()],
         ];
         assert_eq!(cmds, expected);
     }

codex-rs/core/src/codex.rs

@@ -456,8 +456,6 @@ impl Session {
             client,
             tools_config: ToolsConfig::new(&ToolsConfigParams {
                 model_family: &config.model_family,
-                approval_policy,
-                sandbox_policy: sandbox_policy.clone(),
                 include_plan_tool: config.include_plan_tool,
                 include_apply_patch_tool: config.include_apply_patch_tool,
                 include_web_search_request: config.tools_web_search_request,
@@ -1237,8 +1235,6 @@ async fn submission_loop(
 
                 let tools_config = ToolsConfig::new(&ToolsConfigParams {
                     model_family: &effective_family,
-                    approval_policy: new_approval_policy,
-                    sandbox_policy: new_sandbox_policy.clone(),
                     include_plan_tool: config.include_plan_tool,
                     include_apply_patch_tool: config.include_apply_patch_tool,
                     include_web_search_request: config.tools_web_search_request,
@@ -1325,8 +1321,6 @@ async fn submission_loop(
                         client,
                         tools_config: ToolsConfig::new(&ToolsConfigParams {
                             model_family: &model_family,
-                            approval_policy,
-                            sandbox_policy: sandbox_policy.clone(),
                             include_plan_tool: config.include_plan_tool,
                             include_apply_patch_tool: config.include_apply_patch_tool,
                             include_web_search_request: config.tools_web_search_request,
@@ -1553,8 +1547,6 @@ async fn spawn_review_thread(
         .unwrap_or_else(|| parent_turn_context.client.get_model_family());
     let tools_config = ToolsConfig::new(&ToolsConfigParams {
         model_family: &review_model_family,
-        approval_policy: parent_turn_context.approval_policy,
-        sandbox_policy: parent_turn_context.sandbox_policy.clone(),
         include_plan_tool: false,
         include_apply_patch_tool: config.include_apply_patch_tool,
         include_web_search_request: false,
@@ -2724,6 +2716,21 @@ async fn handle_container_exec_with_params(
     sub_id: String,
     call_id: String,
 ) -> ResponseInputItem {
+    if params.with_escalated_permissions.unwrap_or(false)
+        && !matches!(turn_context.approval_policy, AskForApproval::OnRequest)
+    {
+        return ResponseInputItem::FunctionCallOutput {
+            call_id,
+            output: FunctionCallOutputPayload {
+                content: format!(
+                    "approval policy is {policy:?}; reject command — you should not ask for escalated permissions if the approval policy is {policy:?}",
+                    policy = turn_context.approval_policy
+                ),
+                success: None,
+            },
+        };
+    }
+
     // check if this was a patch, and apply it if so
     let apply_patch_exec = match maybe_parse_apply_patch_verified(&params.command, &params.cwd) {
         MaybeApplyPatchVerified::Body(changes) => {
@@ -3345,6 +3352,7 @@ mod tests {
     use mcp_types::ContentBlock;
     use mcp_types::TextContent;
     use pretty_assertions::assert_eq;
+    use serde::Deserialize;
     use serde_json::json;
     use std::path::PathBuf;
     use std::sync::Arc;
@@ -3594,8 +3602,6 @@ mod tests {
         );
         let tools_config = ToolsConfig::new(&ToolsConfigParams {
             model_family: &config.model_family,
-            approval_policy: config.approval_policy,
-            sandbox_policy: config.sandbox_policy.clone(),
             include_plan_tool: config.include_plan_tool,
             include_apply_patch_tool: config.include_apply_patch_tool,
             include_web_search_request: config.tools_web_search_request,
@@ -3735,4 +3741,105 @@ mod tests {
 
         (rollout_items, live_history.contents())
     }
+
+    #[tokio::test]
+    async fn rejects_escalated_permissions_when_policy_not_on_request() {
+        use crate::exec::ExecParams;
+        use crate::protocol::AskForApproval;
+        use crate::protocol::SandboxPolicy;
+        use crate::turn_diff_tracker::TurnDiffTracker;
+        use std::collections::HashMap;
+
+        let (session, mut turn_context) = make_session_and_context();
+        // Ensure policy is NOT OnRequest so the early rejection path triggers
+        turn_context.approval_policy = AskForApproval::OnFailure;
+
+        let params = ExecParams {
+            command: if cfg!(windows) {
+                vec![
+                    "cmd.exe".to_string(),
+                    "/C".to_string(),
+                    "echo hi".to_string(),
+                ]
+            } else {
+                vec![
+                    "/bin/sh".to_string(),
+                    "-c".to_string(),
+                    "echo hi".to_string(),
+                ]
+            },
+            cwd: turn_context.cwd.clone(),
+            timeout_ms: Some(1000),
+            env: HashMap::new(),
+            with_escalated_permissions: Some(true),
+            justification: Some("test".to_string()),
+        };
+
+        let params2 = ExecParams {
+            with_escalated_permissions: Some(false),
+            ..params.clone()
+        };
+
+        let mut turn_diff_tracker = TurnDiffTracker::new();
+
+        let sub_id = "test-sub".to_string();
+        let call_id = "test-call".to_string();
+
+        let resp = handle_container_exec_with_params(
+            params,
+            &session,
+            &turn_context,
+            &mut turn_diff_tracker,
+            sub_id,
+            call_id,
+        )
+        .await;
+
+        let ResponseInputItem::FunctionCallOutput { output, .. } = resp else {
+            panic!("expected FunctionCallOutput");
+        };
+
+        let expected = format!(
+            "approval policy is {policy:?}; reject command — you should not ask for escalated permissions if the approval policy is {policy:?}",
+            policy = turn_context.approval_policy
+        );
+
+        pretty_assertions::assert_eq!(output.content, expected);
+
+        // Now retry the same command WITHOUT escalated permissions; should succeed.
+        // Force DangerFullAccess to avoid platform sandbox dependencies in tests.
+        turn_context.sandbox_policy = SandboxPolicy::DangerFullAccess;
+
+        let resp2 = handle_container_exec_with_params(
+            params2,
+            &session,
+            &turn_context,
+            &mut turn_diff_tracker,
+            "test-sub".to_string(),
+            "test-call-2".to_string(),
+        )
+        .await;
+
+        let ResponseInputItem::FunctionCallOutput { output, .. } = resp2 else {
+            panic!("expected FunctionCallOutput on retry");
+        };
+
+        #[derive(Deserialize, PartialEq, Eq, Debug)]
+        struct ResponseExecMetadata {
+            exit_code: i32,
+        }
+
+        #[derive(Deserialize)]
+        struct ResponseExecOutput {
+            output: String,
+            metadata: ResponseExecMetadata,
+        }
+
+        let exec_output: ResponseExecOutput =
+            serde_json::from_str(&output.content).expect("valid exec output json");
+
+        pretty_assertions::assert_eq!(exec_output.metadata, ResponseExecMetadata { exit_code: 0 });
+        assert!(exec_output.output.contains("hi"));
+        pretty_assertions::assert_eq!(output.success, Some(true));
+    }
 }

codex-rs/core/src/exec.rs

@@ -45,7 +45,7 @@ const AGGREGATE_BUFFER_INITIAL_CAPACITY: usize = 8 * 1024; // 8 KiB
 /// Aggregation still collects full output; only the live event stream is capped.
 pub(crate) const MAX_EXEC_OUTPUT_DELTAS_PER_CALL: usize = 10_000;
 
-#[derive(Debug, Clone)]
+#[derive(Clone, Debug)]
 pub struct ExecParams {
     pub command: Vec<String>,
     pub cwd: PathBuf,