Add sora 2 support (#1834)

* Update OpenAI package to version 6.7.0 and add video generation capabilities

- Updated `openai` dependency in `package-lock.json` and `package.json`.
- Introduced new permissions for video generation in `hardcoded-permissions.js`.
- Added video generation service in `AIInterfaceService.js` and registered it in `PuterAIModule.js`.
- Implemented coercion for video streams in `CoercionService.js`.
- Updated driver service to include video generation.
- Added `txt2video` method and options in `AI.js` and corresponding TypeScript definitions in `index.d.ts`.

* Update openaiVideoCostMap.ts

* Revert "Update openaiVideoCostMap.ts"

This reverts commit 9e66f93.

* change `txt2video` to `txt2vid`

Author: jelveh

package-lock.json

@@ -63,7 +63,7 @@
     "murmurhash": "^2.0.1",
     "nodemailer": "^6.9.3",
     "on-finished": "^2.4.1",
-    "openai": "^4.73.1",
+    "openai": "^6.7.0",
     "otpauth": "9.2.4",
     "prompt-sync": "^4.2.0",
     "proxyquire": "^2.1.3",

src/backend/package.json

@@ -23,6 +23,7 @@ const default_implicit_user_app_permissions = {
     'driver:puter-ocr:recognize': {},
     'driver:puter-chat-completion': {},
     'driver:puter-image-generation': {},
+    'driver:puter-video-generation': {},
     'driver:puter-tts': {},
     'driver:puter-apps': {},
     'driver:puter-subdomains': {},
@@ -58,6 +59,7 @@ const implicit_user_app_permissions = [
             'driver:puter-kvstore:flush': {},
             'driver:puter-chat-completion:complete': {},
             'driver:puter-image-generation:generate': {},
+            'driver:puter-video-generation:generate': {},
             'driver:puter-analytics:create_trace': {},
             'driver:puter-analytics:record': {},
         },

src/backend/src/data/hardcoded-permissions.js

@@ -125,6 +125,44 @@ class AIInterfaceService extends BaseService {
             }
         });
 
+        col_interfaces.set('puter-video-generation', {
+            description: 'AI Video Generation.',
+            methods: {
+                generate: {
+                    description: 'Generate a video from a prompt.',
+                    parameters: {
+                        prompt: { type: 'string' },
+                        model: { type: 'string', optional: true },
+                        seconds: { type: 'number', optional: true },
+                        duration: { type: 'number', optional: true },
+                        size: { type: 'string', optional: true },
+                        resolution: { type: 'string', optional: true },
+                        input_reference: { type: 'file', optional: true },
+                    },
+                    result_choices: [
+                        {
+                            names: ['url'],
+                            type: {
+                                $: 'string:url:web',
+                                content_type: 'video',
+                            }
+                        },
+                        {
+                            names: ['video'],
+                            type: {
+                                $: 'stream',
+                                content_type: 'video',
+                            }
+                        },
+                    ],
+                    result: {
+                        description: 'Video asset descriptor or URL for the generated video.',
+                        type: 'json'
+                    }
+                }
+            }
+        });
+
         col_interfaces.set('puter-tts', {
             description: 'Text-to-speech.',
             methods: {