[codex] allow AGENTS.md and skills to authorize delegation (#30274)

Prompt update of MAv2 to include agents.md and skills more explicitly

should mimic: https://github.com/openai/codex/pull/27919

codex-rs/app-server/tests/suite/v2/turn_start.rs

@@ -1817,7 +1817,9 @@ async fn turn_start_ignores_deprecated_multi_agent_mode() -> Result<()> {
         .single_request()
         .message_input_texts("developer");
     assert!(developer_texts.iter().any(|text| {
-        text.contains("Do not spawn sub-agents unless the user explicitly asks for sub-agents")
+        text.contains(
+            "Do not spawn sub-agents unless the user or applicable AGENTS.md/skill instructions explicitly ask for sub-agents",
+        )
     }));
     assert!(
         !developer_texts
@@ -1898,8 +1900,9 @@ async fn thread_start_ignores_deprecated_multi_agent_mode() -> Result<()> {
         .message_input_texts("developer");
     assert!(developer_texts.iter().any(|text| {
         text.contains(MULTI_AGENT_MODE_OPEN_TAG)
-            && text
-                .contains("Do not spawn sub-agents unless the user explicitly asks for sub-agents")
+            && text.contains(
+                "Do not spawn sub-agents unless the user or applicable AGENTS.md/skill instructions explicitly ask for sub-agents",
+            )
     }));
     assert!(
         !developer_texts

codex-rs/core/src/context/multi_agent_mode_instructions.rs

@@ -3,7 +3,7 @@ use codex_protocol::config_types::MultiAgentMode;
 use codex_protocol::protocol::MULTI_AGENT_MODE_CLOSE_TAG;
 use codex_protocol::protocol::MULTI_AGENT_MODE_OPEN_TAG;
 
-const EXPLICIT_REQUEST_ONLY_MULTI_AGENT_MODE_TEXT: &str = "Do not spawn sub-agents unless the user explicitly asks for sub-agents, delegation, or parallel agent work.";
+const EXPLICIT_REQUEST_ONLY_MULTI_AGENT_MODE_TEXT: &str = "Do not spawn sub-agents unless the user or applicable AGENTS.md/skill instructions explicitly ask for sub-agents, delegation, or parallel agent work.";
 const NO_MULTI_AGENT_MODE_TEXT: &str = "Multi-agent delegation mode instructions are inactive. Any earlier multi-agent mode developer message no longer applies.";
 const PROACTIVE_MULTI_AGENT_MODE_TEXT: &str = "Proactive multi-agent delegation is active. Any earlier instruction requiring an explicit user request before spawning sub-agents no longer applies. Use sub-agents when parallel work would materially improve speed or quality. This mode remains active until a later multi-agent mode developer message changes it.";
 

codex-rs/core/src/tools/handlers/multi_agents_spec.rs

@@ -673,7 +673,7 @@ fn spawn_agent_tool_description(
         {tool_description}
 This spawn_agent tool provides you access to sub-agents that inherit your current model by default. Do not set the `model` field unless the user explicitly asks for a different model or there is a clear task-specific reason. You should follow the rules and guidelines below to use this tool.
 
-Do not spawn sub-agents unless the user explicitly asks for sub-agents, delegation, or parallel agent work.
+Do not spawn sub-agents unless the user or applicable AGENTS.md/skill instructions explicitly ask for sub-agents, delegation, or parallel agent work.
 {agent_role_usage_hint}
 
 ### Designing delegated subtasks

codex-rs/core/tests/suite/multi_agent_mode.rs

@@ -21,7 +21,7 @@ use core_test_support::wait_for_event;
 use pretty_assertions::assert_eq;
 use serde_json::Value;
 
-const NO_SPAWN_TEXT: &str = "Do not spawn sub-agents unless the user explicitly asks for sub-agents, delegation, or parallel agent work.";
+const NO_SPAWN_TEXT: &str = "Do not spawn sub-agents unless the user or applicable AGENTS.md/skill instructions explicitly ask for sub-agents, delegation, or parallel agent work.";
 const PROACTIVE_TEXT: &str = "Proactive multi-agent delegation is active.";
 
 fn add_ultra_reasoning(model_info: &mut ModelInfo) {

codex-rs/core/tests/suite/search_tool.rs

@@ -858,7 +858,7 @@ async fn tool_search_returns_deferred_v1_multi_agent_tools() -> Result<()> {
         .and_then(Value::as_str)
         .expect("spawn_agent description should be present");
     assert!(description.contains(
-        "Do not spawn sub-agents unless the user explicitly asks for sub-agents, delegation, or parallel agent work."
+        "Do not spawn sub-agents unless the user or applicable AGENTS.md/skill instructions explicitly ask for sub-agents, delegation, or parallel agent work."
     ));
     assert!(description.contains("### Designing delegated subtasks"));
     assert!(!description.contains("### When to delegate vs. do the subtask yourself"));

codex-rs/core/tests/suite/spawn_agent_description.rs

@@ -213,7 +213,7 @@ async fn spawn_agent_description_lists_visible_models_and_reasoning_efforts() ->
     );
     assert!(
         description.contains(
-            "Do not spawn sub-agents unless the user explicitly asks for sub-agents, delegation, or parallel agent work."
+            "Do not spawn sub-agents unless the user or applicable AGENTS.md/skill instructions explicitly ask for sub-agents, delegation, or parallel agent work."
         ),
         "expected explicit authorization rule in spawn_agent description: {description:?}"
     );