[Codex][CLI] Gate image inputs by model modalities (#10271)

###### Summary

- Add input_modalities to model metadata so clients can determine
supported input types.
- Gate image paste/attach in TUI when the selected model does not
support images.
- Block submits that include images for unsupported models and show a
clear warning.
- Propagate modality metadata through app-server protocol/model-list
responses.
  - Update related tests/fixtures.

  ###### Rationale

  - Models support different input modalities.
- Clients need an explicit capability signal to prevent unsupported
requests.
- Backward-compatible defaults preserve existing behavior when modality
metadata is absent.

  ###### Scope

  - codex-rs/protocol, codex-rs/core, codex-rs/tui
  - codex-rs/app-server-protocol, codex-rs/app-server
  - Generated app-server types / schema fixtures

  ###### Trade-offs

- Default behavior assumes text + image when field is absent for
compatibility.
  - Server-side validation remains the source of truth.

  ###### Follow-up

- Non-TUI clients should consume input_modalities to disable unsupported
attachments.
- Model catalogs should explicitly set input_modalities for text-only
models.

  ###### Testing

  - cargo fmt --all
  - cargo test -p codex-tui
  - env -u GITHUB_APP_KEY cargo test -p codex-core --lib
  - just write-app-server-schema
- cargo run -p codex-cli --bin codex -- app-server generate-ts --out
app-server-types
  - test against local backend
  
<img width="695" height="199" alt="image"
src="https://github.com/user-attachments/assets/d22dd04f-5eba-4db9-a7c5-a2506f60ec44"
/>

---------

Co-authored-by: Josh McKinney <joshka@openai.com>

codex-rs/app-server-protocol/schema/json/codex_app_server_protocol.schemas.json

@@ -11280,6 +11280,25 @@
         },
         "type": "object"
       },
+      "InputModality": {
+        "description": "Canonical user-input modality tags advertised by a model.",
+        "oneOf": [
+          {
+            "description": "Plain text turns and tool payloads.",
+            "enum": [
+              "text"
+            ],
+            "type": "string"
+          },
+          {
+            "description": "Image attachments included in user turns.",
+            "enum": [
+              "image"
+            ],
+            "type": "string"
+          }
+        ]
+      },
       "ItemCompletedNotification": {
         "$schema": "http://json-schema.org/draft-07/schema#",
         "properties": {
@@ -11780,6 +11799,16 @@
           "id": {
             "type": "string"
           },
+          "inputModalities": {
+            "default": [
+              "text",
+              "image"
+            ],
+            "items": {
+              "$ref": "#/definitions/v2/InputModality"
+            },
+            "type": "array"
+          },
           "isDefault": {
             "type": "boolean"
           },

codex-rs/app-server-protocol/schema/json/v2/ModelListResponse.json

@@ -1,6 +1,25 @@
 {
   "$schema": "http://json-schema.org/draft-07/schema#",
   "definitions": {
+    "InputModality": {
+      "description": "Canonical user-input modality tags advertised by a model.",
+      "oneOf": [
+        {
+          "description": "Plain text turns and tool payloads.",
+          "enum": [
+            "text"
+          ],
+          "type": "string"
+        },
+        {
+          "description": "Image attachments included in user turns.",
+          "enum": [
+            "image"
+          ],
+          "type": "string"
+        }
+      ]
+    },
     "Model": {
       "properties": {
         "defaultReasoningEffort": {
@@ -15,6 +34,16 @@
         "id": {
           "type": "string"
         },
+        "inputModalities": {
+          "default": [
+            "text",
+            "image"
+          ],
+          "items": {
+            "$ref": "#/definitions/InputModality"
+          },
+          "type": "array"
+        },
         "isDefault": {
           "type": "boolean"
         },

codex-rs/app-server-protocol/schema/typescript/InputModality.ts

@@ -0,0 +1,8 @@
+// GENERATED CODE! DO NOT MODIFY BY HAND!
+
+// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
+
+/**
+ * Canonical user-input modality tags advertised by a model.
+ */
+export type InputModality = "text" | "image";

codex-rs/app-server-protocol/schema/typescript/index.ts

@@ -90,6 +90,7 @@ export type { InitializeCapabilities } from "./InitializeCapabilities";
 export type { InitializeParams } from "./InitializeParams";
 export type { InitializeResponse } from "./InitializeResponse";
 export type { InputItem } from "./InputItem";
+export type { InputModality } from "./InputModality";
 export type { InterruptConversationParams } from "./InterruptConversationParams";
 export type { InterruptConversationResponse } from "./InterruptConversationResponse";
 export type { ItemCompletedEvent } from "./ItemCompletedEvent";

codex-rs/app-server-protocol/schema/typescript/v2/Model.ts

@@ -1,7 +1,8 @@
 // GENERATED CODE! DO NOT MODIFY BY HAND!
 
 // This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
+import type { InputModality } from "../InputModality";
 import type { ReasoningEffort } from "../ReasoningEffort";
 import type { ReasoningEffortOption } from "./ReasoningEffortOption";
 
-export type Model = { id: string, model: string, displayName: string, description: string, supportedReasoningEfforts: Array<ReasoningEffortOption>, defaultReasoningEffort: ReasoningEffort, supportsPersonality: boolean, isDefault: boolean, };
+export type Model = { id: string, model: string, displayName: string, description: string, supportedReasoningEfforts: Array<ReasoningEffortOption>, defaultReasoningEffort: ReasoningEffort, inputModalities: Array<InputModality>, supportsPersonality: boolean, isDefault: boolean, };

codex-rs/app-server-protocol/src/protocol/v2.rs

@@ -19,7 +19,9 @@ use codex_protocol::mcp::Resource as McpResource;
 use codex_protocol::mcp::ResourceTemplate as McpResourceTemplate;
 use codex_protocol::mcp::Tool as McpTool;
 use codex_protocol::models::ResponseItem;
+use codex_protocol::openai_models::InputModality;
 use codex_protocol::openai_models::ReasoningEffort;
+use codex_protocol::openai_models::default_input_modalities;
 use codex_protocol::parse_command::ParsedCommand as CoreParsedCommand;
 use codex_protocol::plan_tool::PlanItemArg as CorePlanItemArg;
 use codex_protocol::plan_tool::StepStatus as CorePlanStepStatus;
@@ -992,6 +994,8 @@ pub struct Model {
     pub description: String,
     pub supported_reasoning_efforts: Vec<ReasoningEffortOption>,
     pub default_reasoning_effort: ReasoningEffort,
+    #[serde(default = "default_input_modalities")]
+    pub input_modalities: Vec<InputModality>,
     #[serde(default)]
     pub supports_personality: bool,
     // Only one model should be marked as default.