diff --git a/codex-rs/app-server-protocol/schema/json/ClientRequest.json b/codex-rs/app-server-protocol/schema/json/ClientRequest.json
index 9b676f8e520..4a40cc9ce9b 100644
--- a/codex-rs/app-server-protocol/schema/json/ClientRequest.json
+++ b/codex-rs/app-server-protocol/schema/json/ClientRequest.json
@@ -1171,6 +1171,7 @@
     },
     "Personality": {
       "enum": [
+        "none",
         "friendly",
         "pragmatic"
       ],
diff --git a/codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.schemas.json b/codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.schemas.json
index f0b16e23586..87220712eb2 100644
--- a/codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.schemas.json
+++ b/codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.schemas.json
@@ -12120,6 +12120,7 @@
       },
       "Personality": {
         "enum": [
+          "none",
           "friendly",
           "pragmatic"
         ],
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ThreadResumeParams.json b/codex-rs/app-server-protocol/schema/json/v2/ThreadResumeParams.json
index cc05de490a3..8167ea779e8 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ThreadResumeParams.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ThreadResumeParams.json
@@ -251,6 +251,7 @@
     },
     "Personality": {
       "enum": [
+        "none",
         "friendly",
         "pragmatic"
       ],
diff --git a/codex-rs/app-server-protocol/schema/json/v2/ThreadStartParams.json b/codex-rs/app-server-protocol/schema/json/v2/ThreadStartParams.json
index 03bed7f93c6..f2b0052e6db 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/ThreadStartParams.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/ThreadStartParams.json
@@ -29,6 +29,7 @@
     },
     "Personality": {
       "enum": [
+        "none",
         "friendly",
         "pragmatic"
       ],
diff --git a/codex-rs/app-server-protocol/schema/json/v2/TurnStartParams.json b/codex-rs/app-server-protocol/schema/json/v2/TurnStartParams.json
index 6a739b31ac2..be351a48ead 100644
--- a/codex-rs/app-server-protocol/schema/json/v2/TurnStartParams.json
+++ b/codex-rs/app-server-protocol/schema/json/v2/TurnStartParams.json
@@ -66,6 +66,7 @@
     },
     "Personality": {
       "enum": [
+        "none",
         "friendly",
         "pragmatic"
       ],
diff --git a/codex-rs/app-server-protocol/schema/typescript/Personality.ts b/codex-rs/app-server-protocol/schema/typescript/Personality.ts
index b9ccad4dc2c..45165f4e33d 100644
--- a/codex-rs/app-server-protocol/schema/typescript/Personality.ts
+++ b/codex-rs/app-server-protocol/schema/typescript/Personality.ts
@@ -2,4 +2,4 @@
 
 // This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
 
-export type Personality = "friendly" | "pragmatic";
+export type Personality = "none" | "friendly" | "pragmatic";
diff --git a/codex-rs/app-server/README.md b/codex-rs/app-server/README.md
index 055ca6f32a1..69a75247173 100644
--- a/codex-rs/app-server/README.md
+++ b/codex-rs/app-server/README.md
@@ -147,6 +147,8 @@ Start a fresh thread when you need a new Codex conversation.
 { "method": "thread/started", "params": { "thread": { … } } }
 ```
 
+Valid `personality` values are `"friendly"`, `"pragmatic"`, and `"none"`. When `"none"` is selected, the personality placeholder is replaced with an empty string.
+
 To continue a stored session, call `thread/resume` with the `thread.id` you previously recorded. The response shape matches `thread/start`, and no additional notifications are emitted. You can also pass the same configuration overrides supported by `thread/start`, such as `personality`:
 
 ```json
diff --git a/codex-rs/core/config.schema.json b/codex-rs/core/config.schema.json
index 138b71e2dca..8e9550c092f 100644
--- a/codex-rs/core/config.schema.json
+++ b/codex-rs/core/config.schema.json
@@ -708,6 +708,7 @@
     },
     "Personality": {
       "enum": [
+        "none",
         "friendly",
         "pragmatic"
       ],
diff --git a/codex-rs/core/tests/common/responses.rs b/codex-rs/core/tests/common/responses.rs
index 86a332874ef..7d3b0770859 100644
--- a/codex-rs/core/tests/common/responses.rs
+++ b/codex-rs/core/tests/common/responses.rs
@@ -375,6 +375,10 @@ pub fn sse(events: Vec<Value>) -> String {
     out
 }
 
+pub fn sse_completed(id: &str) -> String {
+    sse(vec![ev_response_created(id), ev_completed(id)])
+}
+
 /// Convenience: SSE event for a completed response with a specific id.
 pub fn ev_completed(id: &str) -> Value {
     serde_json::json!({
diff --git a/codex-rs/core/tests/suite/personality.rs b/codex-rs/core/tests/suite/personality.rs
index 919ce852edf..ff2c0cfec02 100644
--- a/codex-rs/core/tests/suite/personality.rs
+++ b/codex-rs/core/tests/suite/personality.rs
@@ -19,12 +19,10 @@ use codex_protocol::openai_models::TruncationPolicyConfig;
 use codex_protocol::openai_models::default_input_modalities;
 use codex_protocol::user_input::UserInput;
 use core_test_support::load_default_config_for_test;
-use core_test_support::responses::ev_completed;
-use core_test_support::responses::ev_response_created;
 use core_test_support::responses::mount_models_once;
 use core_test_support::responses::mount_sse_once;
 use core_test_support::responses::mount_sse_sequence;
-use core_test_support::responses::sse;
+use core_test_support::responses::sse_completed;
 use core_test_support::responses::start_mock_server;
 use core_test_support::skip_if_no_network;
 use core_test_support::test_codex::test_codex;
@@ -78,11 +76,7 @@ async fn user_turn_personality_none_does_not_add_update_message() -> anyhow::Res
     skip_if_no_network!(Ok(()));
 
     let server = start_mock_server().await;
-    let resp_mock = mount_sse_once(
-        &server,
-        sse(vec![ev_response_created("resp-1"), ev_completed("resp-1")]),
-    )
-    .await;
+    let resp_mock = mount_sse_once(&server, sse_completed("resp-1")).await;
     let mut builder = test_codex()
         .with_model("gpt-5.2-codex")
         .with_config(|config| {
@@ -128,11 +122,7 @@ async fn config_personality_some_sets_instructions_template() -> anyhow::Result<
     skip_if_no_network!(Ok(()));
 
     let server = start_mock_server().await;
-    let resp_mock = mount_sse_once(
-        &server,
-        sse(vec![ev_response_created("resp-1"), ev_completed("resp-1")]),
-    )
-    .await;
+    let resp_mock = mount_sse_once(&server, sse_completed("resp-1")).await;
     let mut builder = test_codex()
         .with_model("gpt-5.2-codex")
         .with_config(|config| {
@@ -181,6 +171,111 @@ async fn config_personality_some_sets_instructions_template() -> anyhow::Result<
     Ok(())
 }
 
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn config_personality_none_sends_no_personality() -> anyhow::Result<()> {
+    skip_if_no_network!(Ok(()));
+
+    let server = start_mock_server().await;
+    let resp_mock = mount_sse_once(&server, sse_completed("resp-1")).await;
+    let mut builder = test_codex()
+        .with_model("gpt-5.2-codex")
+        .with_config(|config| {
+            config.features.disable(Feature::RemoteModels);
+            config.features.enable(Feature::Personality);
+            config.personality = Some(Personality::None);
+        });
+    let test = builder.build(&server).await?;
+
+    test.codex
+        .submit(Op::UserTurn {
+            items: vec![UserInput::Text {
+                text: "hello".into(),
+                text_elements: Vec::new(),
+            }],
+            final_output_json_schema: None,
+            cwd: test.cwd_path().to_path_buf(),
+            approval_policy: test.config.approval_policy.value(),
+            sandbox_policy: SandboxPolicy::ReadOnly,
+            model: test.session_configured.model.clone(),
+            effort: test.config.model_reasoning_effort,
+            summary: ReasoningSummary::Auto,
+            collaboration_mode: None,
+            personality: None,
+        })
+        .await?;
+
+    wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
+
+    let request = resp_mock.single_request();
+    let instructions_text = request.instructions_text();
+    assert!(
+        !instructions_text.contains(LOCAL_FRIENDLY_TEMPLATE),
+        "expected no friendly personality template, got: {instructions_text:?}"
+    );
+    assert!(
+        !instructions_text.contains(LOCAL_PRAGMATIC_TEMPLATE),
+        "expected no pragmatic personality template, got: {instructions_text:?}"
+    );
+    assert!(
+        !instructions_text.contains("{{ personality }}"),
+        "expected personality placeholder to be removed, got: {instructions_text:?}"
+    );
+
+    let developer_texts = request.message_input_texts("developer");
+    assert!(
+        !developer_texts
+            .iter()
+            .any(|text| text.contains("<personality_spec>")),
+        "did not expect a personality update message when personality is None"
+    );
+
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn default_personality_is_friendly_without_config_toml() -> anyhow::Result<()> {
+    skip_if_no_network!(Ok(()));
+
+    let server = start_mock_server().await;
+    let resp_mock = mount_sse_once(&server, sse_completed("resp-1")).await;
+    let mut builder = test_codex()
+        .with_model("gpt-5.2-codex")
+        .with_config(|config| {
+            config.features.disable(Feature::RemoteModels);
+            config.features.enable(Feature::Personality);
+        });
+    let test = builder.build(&server).await?;
+
+    test.codex
+        .submit(Op::UserTurn {
+            items: vec![UserInput::Text {
+                text: "hello".into(),
+                text_elements: Vec::new(),
+            }],
+            final_output_json_schema: None,
+            cwd: test.cwd_path().to_path_buf(),
+            approval_policy: test.config.approval_policy.value(),
+            sandbox_policy: SandboxPolicy::ReadOnly,
+            model: test.session_configured.model.clone(),
+            effort: test.config.model_reasoning_effort,
+            summary: ReasoningSummary::Auto,
+            collaboration_mode: None,
+            personality: None,
+        })
+        .await?;
+
+    wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
+
+    let request = resp_mock.single_request();
+    let instructions_text = request.instructions_text();
+    assert!(
+        instructions_text.contains(LOCAL_FRIENDLY_TEMPLATE),
+        "expected default friendly template, got: {instructions_text:?}"
+    );
+
+    Ok(())
+}
+
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn user_turn_personality_some_adds_update_message() -> anyhow::Result<()> {
     skip_if_no_network!(Ok(()));
@@ -188,10 +283,7 @@ async fn user_turn_personality_some_adds_update_message() -> anyhow::Result<()>
     let server = start_mock_server().await;
     let resp_mock = mount_sse_sequence(
         &server,
-        vec![
-            sse(vec![ev_response_created("resp-1"), ev_completed("resp-1")]),
-            sse(vec![ev_response_created("resp-2"), ev_completed("resp-2")]),
-        ],
+        vec![sse_completed("resp-1"), sse_completed("resp-2")],
     )
     .await;
     let mut builder = test_codex()
@@ -287,10 +379,7 @@ async fn user_turn_personality_same_value_does_not_add_update_message() -> anyho
     let server = start_mock_server().await;
     let resp_mock = mount_sse_sequence(
         &server,
-        vec![
-            sse(vec![ev_response_created("resp-1"), ev_completed("resp-1")]),
-            sse(vec![ev_response_created("resp-2"), ev_completed("resp-2")]),
-        ],
+        vec![sse_completed("resp-1"), sse_completed("resp-2")],
     )
     .await;
     let mut builder = test_codex()
@@ -397,10 +486,7 @@ async fn user_turn_personality_skips_if_feature_disabled() -> anyhow::Result<()>
     let server = start_mock_server().await;
     let resp_mock = mount_sse_sequence(
         &server,
-        vec![
-            sse(vec![ev_response_created("resp-1"), ev_completed("resp-1")]),
-            sse(vec![ev_response_created("resp-2"), ev_completed("resp-2")]),
-        ],
+        vec![sse_completed("resp-1"), sse_completed("resp-2")],
     )
     .await;
     let mut builder = test_codex()
@@ -537,11 +623,7 @@ async fn ignores_remote_personality_if_remote_models_disabled() -> anyhow::Resul
     )
     .await;
 
-    let resp_mock = mount_sse_once(
-        &server,
-        sse(vec![ev_response_created("resp-1"), ev_completed("resp-1")]),
-    )
-    .await;
+    let resp_mock = mount_sse_once(&server, sse_completed("resp-1")).await;
 
     let mut builder = test_codex()
         .with_auth(codex_core::CodexAuth::create_dummy_chatgpt_auth_for_testing())
@@ -657,11 +739,7 @@ async fn remote_model_friendly_personality_instructions_with_feature() -> anyhow
     )
     .await;
 
-    let resp_mock = mount_sse_once(
-        &server,
-        sse(vec![ev_response_created("resp-1"), ev_completed("resp-1")]),
-    )
-    .await;
+    let resp_mock = mount_sse_once(&server, sse_completed("resp-1")).await;
 
     let mut builder = test_codex()
         .with_auth(codex_core::CodexAuth::create_dummy_chatgpt_auth_for_testing())
@@ -774,10 +852,7 @@ async fn user_turn_personality_remote_model_template_includes_update_message() -
 
     let resp_mock = mount_sse_sequence(
         &server,
-        vec![
-            sse(vec![ev_response_created("resp-1"), ev_completed("resp-1")]),
-            sse(vec![ev_response_created("resp-2"), ev_completed("resp-2")]),
-        ],
+        vec![sse_completed("resp-1"), sse_completed("resp-2")],
     )
     .await;
 
diff --git a/codex-rs/docs/codex_mcp_interface.md b/codex-rs/docs/codex_mcp_interface.md
index 8847b6b4ee9..8b1b5f70457 100644
--- a/codex-rs/docs/codex_mcp_interface.md
+++ b/codex-rs/docs/codex_mcp_interface.md
@@ -73,6 +73,8 @@ Send input to the active turn:
 - `sendUserMessage` → enqueue items to the conversation
 - `sendUserTurn` → structured turn with explicit `cwd`, `approvalPolicy`, `sandboxPolicy`, `model`, optional `effort`, `summary`, optional `personality`, and optional `outputSchema` (JSON Schema for the final assistant message)
 
+Valid `personality` values are `friendly`, `pragmatic`, and `none`. When `none` is selected, the personality placeholder is replaced with an empty string.
+
 For v2 threads, `turn/start` also accepts `outputSchema` to constrain the final assistant message for that turn.
 
 Interrupt a running turn: `interruptConversation`.
diff --git a/codex-rs/docs/protocol_v1.md b/codex-rs/docs/protocol_v1.md
index 8f68ecc9a60..4d4e5c147c7 100644
--- a/codex-rs/docs/protocol_v1.md
+++ b/codex-rs/docs/protocol_v1.md
@@ -72,6 +72,9 @@ For complete documentation of the `Op` and `EventMsg` variants, refer to [protoc
   - `Op::UserInputAnswer` – Provide answers for a `request_user_input` tool call
   - `Op::ListSkills` – Request skills for one or more cwd values (optionally `force_reload`)
   - `Op::UserTurn` and `Op::OverrideTurnContext` accept an optional `personality` override that updates the model’s communication style
+
+Valid `personality` values are `friendly`, `pragmatic`, and `none`. When `none` is selected, the personality placeholder is replaced with an empty string.
+
 - `EventMsg`
   - `EventMsg::AgentMessage` – Messages from the `Model`
   - `EventMsg::AgentMessageContentDelta` – Streaming assistant text
diff --git a/codex-rs/protocol/src/config_types.rs b/codex-rs/protocol/src/config_types.rs
index aa28e1a6fac..f7d7b4f4317 100644
--- a/codex-rs/protocol/src/config_types.rs
+++ b/codex-rs/protocol/src/config_types.rs
@@ -96,6 +96,7 @@ pub enum WindowsSandboxLevel {
 #[serde(rename_all = "lowercase")]
 #[strum(serialize_all = "lowercase")]
 pub enum Personality {
+    None,
     Friendly,
     Pragmatic,
 }
diff --git a/codex-rs/protocol/src/openai_models.rs b/codex-rs/protocol/src/openai_models.rs
index 90cf34f3935..36298e9ca50 100644
--- a/codex-rs/protocol/src/openai_models.rs
+++ b/codex-rs/protocol/src/openai_models.rs
@@ -335,6 +335,7 @@ impl ModelInstructionsVariables {
     pub fn get_personality_message(&self, personality: Option<Personality>) -> Option<String> {
         if let Some(personality) = personality {
             match personality {
+                Personality::None => Some(String::new()),
                 Personality::Friendly => self.personality_friendly.clone(),
                 Personality::Pragmatic => self.personality_pragmatic.clone(),
             }
@@ -546,6 +547,10 @@ mod tests {
             model.get_model_instructions(Some(Personality::Pragmatic)),
             "Hello\n"
         );
+        assert_eq!(
+            model.get_model_instructions(Some(Personality::None)),
+            "Hello\n"
+        );
         assert_eq!(model.get_model_instructions(None), "Hello\n");
 
         let model_no_personality = test_model(Some(ModelMessages {
@@ -564,6 +569,10 @@ mod tests {
             model_no_personality.get_model_instructions(Some(Personality::Pragmatic)),
             "Hello\n"
         );
+        assert_eq!(
+            model_no_personality.get_model_instructions(Some(Personality::None)),
+            "Hello\n"
+        );
         assert_eq!(model_no_personality.get_model_instructions(None), "Hello\n");
     }
 
@@ -603,6 +612,10 @@ mod tests {
             personality_variables.get_personality_message(Some(Personality::Pragmatic)),
             Some("pragmatic".to_string())
         );
+        assert_eq!(
+            personality_variables.get_personality_message(Some(Personality::None)),
+            Some(String::new())
+        );
         assert_eq!(
             personality_variables.get_personality_message(None),
             Some("default".to_string())
@@ -621,6 +634,10 @@ mod tests {
             personality_variables.get_personality_message(Some(Personality::Pragmatic)),
             None
         );
+        assert_eq!(
+            personality_variables.get_personality_message(Some(Personality::None)),
+            Some(String::new())
+        );
         assert_eq!(
             personality_variables.get_personality_message(None),
             Some("default".to_string())
@@ -639,6 +656,10 @@ mod tests {
             personality_variables.get_personality_message(Some(Personality::Pragmatic)),
             Some("pragmatic".to_string())
         );
+        assert_eq!(
+            personality_variables.get_personality_message(Some(Personality::None)),
+            Some(String::new())
+        );
         assert_eq!(personality_variables.get_personality_message(None), None);
     }
 }
diff --git a/codex-rs/tui/src/app.rs b/codex-rs/tui/src/app.rs
index 878d4d5da2d..99164efa61a 100644
--- a/codex-rs/tui/src/app.rs
+++ b/codex-rs/tui/src/app.rs
@@ -2326,6 +2326,7 @@ impl App {
 
     fn personality_label(personality: Personality) -> &'static str {
         match personality {
+            Personality::None => "None",
             Personality::Friendly => "Friendly",
             Personality::Pragmatic => "Pragmatic",
         }
diff --git a/codex-rs/tui/src/chatwidget.rs b/codex-rs/tui/src/chatwidget.rs
index 191873ca5f8..f29403f68c4 100644
--- a/codex-rs/tui/src/chatwidget.rs
+++ b/codex-rs/tui/src/chatwidget.rs
@@ -5505,6 +5505,7 @@ impl ChatWidget {
 
     fn personality_label(personality: Personality) -> &'static str {
         match personality {
+            Personality::None => "None",
             Personality::Friendly => "Friendly",
             Personality::Pragmatic => "Pragmatic",
         }
@@ -5512,6 +5513,7 @@ impl ChatWidget {
 
     fn personality_description(personality: Personality) -> &'static str {
         match personality {
+            Personality::None => "No personality instructions.",
             Personality::Friendly => "Warm, collaborative, and helpful.",
             Personality::Pragmatic => "Concise, task-focused, and direct.",
         }