Plan an ad concept

Added value: +"clip length in seconds from that same refusal; use only the value it gave"

Added value: +"video model id from a refusal that offered a lighter draft; use only the value it gave"

Previous value: -"ONLY after a video refusal that offered a light draft: the {model, durationSeconds} it named. The plan is then authored to that length and priced on that model. Never invent one — a video the account cannot cover is refused BEFORE planning with the three options (image / add credits / this draft when one fits), and the user chooses."New value: +"Only after a video refusal that offered a lighter draft: the {model, durationSeconds} that refusal named. The plan is then written to that length and priced on that model. Use only the values the refusal gave; when an account cannot cover a video, the refusal comes before planning with three options (an image, adding credits, or this draft when one fits) and the user chooses."

Previous value: -"VIDEO ONLY — the total spot length the user explicitly asked for, in seconds, copied verbatim (30 for \"a 30 second ad\"). The planner authors the storyboard TO it: the scenes’ seconds sum to it and the script is word-budgeted for it. Supported range 4–180; anything outside is CLAMPED to it (the reply says so). A length that fits ONE clip of the render model renders as a single continuous pass; anything longer is STITCHED from acts filled to that model’s clip maximum with the remainder last (on a 15s-clip model, 40 -> 15+15+10 and 17 -> 13+4) — never time-compressed. The maximum is the model’s own: 15s on most, 30s on the longest-clip model, so a 30s ad can be one unbroken take rather than two acts. Omit when the user named no length; do NOT pass a guess: when it is omitted the planner picks a length suited to the format, and a length the user names always wins."New value: +"For video: the total length the user asked for, in seconds (30 for \"a 30 second ad\"). The storyboard’s scenes add up to it and the script is sized for it. Supported range 4 to 180 seconds; a value outside the range is clamped and the reply says so. A length that fits one clip of the render model renders as one continuous clip; a longer one is joined from clips filled to that model’s clip maximum, remainder last (on a 15s-clip model, 40 becomes 15+15+10 and 17 becomes 13+4), and is never sped up. The clip maximum depends on the model: 15s on most, 30s on the longest-clip model, so a 30s ad can be one take. Leave it out when the user named no length; the planner then picks one that suits the format."

Added value: +{
+  "description": "VIDEO ONLY: the user's own SCREENS (an app, a page, a dashboard, a document, a review, a chart) shown at these seconds as a rounded card over the upper middle of the footage, which keeps playing around it (look 'full' covers the frame, only when the user asked), the voice running underneath. Fewer and shorter: about one per 4 s of film, 1.2-2 s each, on the line that talks about it; never in the first second or the last 1.5 s. The plan frames those shots for the card, keeps them free of screens, and returns the pictures as creative.inserts for render_ad to lay in (about 2 credits). A photo of a person, product or place (kind 'photo') is not laid in: pass a product photo as the brand's product photo and a person as a saved creator. One that does not fit is left out and the reply says so.",
+  "items": {
+    "properties": {
+      "end": {
+        "description": "second it ends: at most 2 s after start (2.5 s full-screen), never in the last 1.5 s of the film",
+        "type": "number"
+      },
+      "image": {
+        "description": "an https or upload_file URL, a Library id (L0, L1…) or a local path on the CLI",
+        "type": "string"
+      },
+      "kind": {
+        "description": "screen (default): an app, a page, a dashboard, a document, a review, a chart. photo: a person, a product or a place, which is NOT laid over the video (a product photo goes in as the brand's product photo, a person to star as a saved creator)",
+        "enum": [
+          "screen",
+          "photo"
+        ],
+        "type": "string"
+      },
+      "look": {
+        "description": "card (default): a rounded card over the upper middle of the footage, which keeps playing. full: covers the whole frame, ONLY when the user asked for full-screen",
+        "enum": [
+          "card",
+          "full"
+        ],
+        "type": "string"
+      },
+      "start": {
+        "description": "second it appears (never before 1 s: the film opens on moving footage)",
+        "type": "number"
+      }
+    },
+    "required": [
+      "image",
+      "start",
+      "end"
+    ],
+    "type": "object"
+  },
+  "maxItems": 8,
+  "type": "array"
+}

Previous value: -"VIDEO ONLY — the total spot length the user explicitly asked for, in seconds, copied verbatim (30 for \"a 30 second ad\"). The planner authors the storyboard TO it: the scenes’ seconds sum to it and the script is word-budgeted for it. Supported range 4–180; anything outside is CLAMPED to it (the reply says so). A length that fits ONE clip of the render model renders as a single continuous pass; anything longer is STITCHED from acts filled to that model’s clip maximum with the remainder last (on a 15s-clip model, 40 -> 15+15+10 and 17 -> 13+4) — never time-compressed. The maximum is the model’s own: 15s on most, 30s on the longest-clip model, so a 30s ad can be one unbroken take rather than two acts. Omit when the user named no length; do NOT pass a guess: an omitted value is the default, a 15s spot in one take, or 30s for a two-person format such as a street interview (2026-10-14), and a length the user names always wins."New value: +"VIDEO ONLY — the total spot length the user explicitly asked for, in seconds, copied verbatim (30 for \"a 30 second ad\"). The planner authors the storyboard TO it: the scenes’ seconds sum to it and the script is word-budgeted for it. Supported range 4–180; anything outside is CLAMPED to it (the reply says so). A length that fits ONE clip of the render model renders as a single continuous pass; anything longer is STITCHED from acts filled to that model’s clip maximum with the remainder last (on a 15s-clip model, 40 -> 15+15+10 and 17 -> 13+4) — never time-compressed. The maximum is the model’s own: 15s on most, 30s on the longest-clip model, so a 30s ad can be one unbroken take rather than two acts. Omit when the user named no length; do NOT pass a guess: when it is omitted the planner picks a length suited to the format, and a length the user names always wins."

Previous value: -"VIDEO ONLY — the total spot length the user explicitly asked for, in seconds, copied verbatim (30 for \"a 30 second ad\"). The planner authors the storyboard TO it: the scenes’ seconds sum to it and the script is word-budgeted for it. Supported range 4–180; anything outside is CLAMPED to it (the reply says so). A length that fits ONE clip of the render model renders as a single continuous pass; anything longer is STITCHED from acts filled to that model’s clip maximum with the remainder last (on a 15s-clip model, 40 -> 15+15+10 and 17 -> 13+4) — never time-compressed. The maximum is the model’s own: 15s on most, 30s on the longest-clip model, so a 30s ad can be one unbroken take rather than two acts. Omit when the user named no length; do NOT pass a guess: an omitted value is the default, a 30s spot in one unbroken take (2026-09-29), and a length the user names always wins."New value: +"VIDEO ONLY — the total spot length the user explicitly asked for, in seconds, copied verbatim (30 for \"a 30 second ad\"). The planner authors the storyboard TO it: the scenes’ seconds sum to it and the script is word-budgeted for it. Supported range 4–180; anything outside is CLAMPED to it (the reply says so). A length that fits ONE clip of the render model renders as a single continuous pass; anything longer is STITCHED from acts filled to that model’s clip maximum with the remainder last (on a 15s-clip model, 40 -> 15+15+10 and 17 -> 13+4) — never time-compressed. The maximum is the model’s own: 15s on most, 30s on the longest-clip model, so a 30s ad can be one unbroken take rather than two acts. Omit when the user named no length; do NOT pass a guess: an omitted value is the default, a 15s spot in one take, or 30s for a two-person format such as a street interview (2026-10-14), and a length the user names always wins."

Previous value: -"VIDEO ONLY — the total spot length the user explicitly asked for, in seconds, copied verbatim (30 for \"a 30 second ad\"). The planner authors the storyboard TO it: the scenes’ seconds sum to it and the script is word-budgeted for it. Supported range 4–180; anything outside is CLAMPED to it (the reply says so). A length that fits ONE clip of the render model renders as a single continuous pass; anything longer is STITCHED from acts filled to that model’s clip maximum with the remainder last (on a 15s-clip model, 40 -> 15+15+10 and 17 -> 13+4) — never time-compressed. The maximum is the model’s own: 15s on most, 30s on the longest-clip model, so a 30s ad can be one unbroken take rather than two acts. Omit when the user named no length; do NOT pass a guess, an omitted value keeps the recipe-aware default."New value: +"VIDEO ONLY — the total spot length the user explicitly asked for, in seconds, copied verbatim (30 for \"a 30 second ad\"). The planner authors the storyboard TO it: the scenes’ seconds sum to it and the script is word-budgeted for it. Supported range 4–180; anything outside is CLAMPED to it (the reply says so). A length that fits ONE clip of the render model renders as a single continuous pass; anything longer is STITCHED from acts filled to that model’s clip maximum with the remainder last (on a 15s-clip model, 40 -> 15+15+10 and 17 -> 13+4) — never time-compressed. The maximum is the model’s own: 15s on most, 30s on the longest-clip model, so a 30s ad can be one unbroken take rather than two acts. Omit when the user named no length; do NOT pass a guess: an omitted value is the default, a 30s spot in one unbroken take (2026-09-29), and a length the user names always wins."

Added value: +{
+  "description": "who is on camera; omit to follow the format. Say 'someone new' in product to skip reusing a saved creator.",
+  "enum": [
+    "auto",
+    "creator",
+    "product_only"
+  ],
+  "type": "string"
+}

Added value: +{
+  "description": "ONLY after a video refusal that offered a light draft: the {model, durationSeconds} it named. The plan is then authored to that length and priced on that model. Never invent one — a video the account cannot cover is refused BEFORE planning with the three options (image / add credits / this draft when one fits), and the user chooses.",
+  "properties": {
+    "durationSeconds": {
+      "type": "number"
+    },
+    "model": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "model",
+    "durationSeconds"
+  ],
+  "type": "object"
+}

Previous value: -"VIDEO ONLY — the total spot length the user explicitly asked for, in seconds, copied verbatim (30 for \"a 30 second ad\"). The planner authors the storyboard TO it: the scenes’ seconds sum to it and the script is word-budgeted for it. Supported range 4–180; anything outside is CLAMPED to it (the reply says so). A length that fits ONE clip of the render model renders as a single continuous pass; anything longer is STITCHED from acts filled to that model’s clip maximum with the remainder last (on a 15s-clip model, 40 → 15+15+10 and 17 → 13+4) — never time-compressed. The maximum is the model’s own: 15s on most, 30s on the longest-clip model, so a 30s ad can be one unbroken take rather than two acts. Omit when the user named no length; do NOT pass a guess, an omitted value keeps the recipe-aware default."New value: +"VIDEO ONLY — the total spot length the user explicitly asked for, in seconds, copied verbatim (30 for \"a 30 second ad\"). The planner authors the storyboard TO it: the scenes’ seconds sum to it and the script is word-budgeted for it. Supported range 4–180; anything outside is CLAMPED to it (the reply says so). A length that fits ONE clip of the render model renders as a single continuous pass; anything longer is STITCHED from acts filled to that model’s clip maximum with the remainder last (on a 15s-clip model, 40 -> 15+15+10 and 17 -> 13+4) — never time-compressed. The maximum is the model’s own: 15s on most, 30s on the longest-clip model, so a 30s ad can be one unbroken take rather than two acts. Omit when the user named no length; do NOT pass a guess, an omitted value keeps the recipe-aware default."

Previous value: -"a reference to remix: an ad-library link (Facebook Ad Library, LinkedIn Ad Library, Google Ads Transparency — its real copy/advertiser are fetched) OR a VIDEO link — a TikTok, Instagram Reel, Facebook video, X post, YouTube Short/video or a direct video file — which is WATCHED first (frames + voiceover/on-screen-text transcript) so the concept keeps its hook, structure and pacing. To remake one video for this brand at its own length, clone_video is the direct tool"New value: +"a reference to clone: an ad-library link (Facebook Ad Library, LinkedIn Ad Library, Google Ads Transparency — its real copy/advertiser are fetched) OR a VIDEO link — a TikTok, Instagram Reel, Facebook video, X post, YouTube Short/video or a direct video file — which is WATCHED first (frames + voiceover/on-screen-text transcript) so the concept keeps its hook, structure and pacing. To remake one video for this brand at its own length, clone_video is the direct tool"

Previous value: -"a reference ad URL to remix the angle from — Facebook Ad Library, LinkedIn Ad Library or Google Ads Transparency links (the real ad’s copy/advertiser are fetched and fed into the concept)"New value: +"a reference to remix: an ad-library link (Facebook Ad Library, LinkedIn Ad Library, Google Ads Transparency — its real copy/advertiser are fetched) OR a VIDEO link — a TikTok, Instagram Reel, Facebook video, X post, YouTube Short/video or a direct video file — which is WATCHED first (frames + voiceover/on-screen-text transcript) so the concept keeps its hook, structure and pacing. To remake one video for this brand at its own length, clone_video is the direct tool"

Added value: +{
+  "description": "VIDEO ONLY — the total spot length the user explicitly asked for, in seconds, copied verbatim (30 for \"a 30 second ad\"). The planner authors the storyboard TO it: the scenes’ seconds sum to it and the script is word-budgeted for it. Supported range 4–180; anything outside is CLAMPED to it (the reply says so). A length that fits ONE clip of the render model renders as a single continuous pass; anything longer is STITCHED from acts filled to that model’s clip maximum with the remainder last (on a 15s-clip model, 40 → 15+15+10 and 17 → 13+4) — never time-compressed. The maximum is the model’s own: 15s on most, 30s on the longest-clip model, so a 30s ad can be one unbroken take rather than two acts. Omit when the user named no length; do NOT pass a guess, an omitted value keeps the recipe-aware default.",
+  "type": "number"
+}

Added value: +{
+  "description": "force the VISUAL scroll-stop mechanic the opening beat is built on — a hook id from list_hooks (e.g. \"direct_callout\", \"mid_problem\", \"macro_asmr\"). Omit to let the planner pick. A hook that cannot be delivered in this brief is DROPPED with the reason rather than rendered wrongly — an on-screen-text hook on an authentic/UGC ad is the one that bites, because that register carries zero on-screen text.",
+  "type": "string"
+}

Added value: +{
+  "description": "force the WHERE — a setting id from list_hooks (e.g. \"kitchen\", \"gym\", or a surreal one like \"volcano_rim\" / \"airplane_wing\", which are played 100% straight and never acknowledged). Omit for a neutral setting.",
+  "type": "string"
+}

Previous value: -{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "additionalProperties": false,
-  "properties": {
-    "brand": {
-      "description": "the brand grounding embedded in the creative (name, logo, palette, productImages)"
-    },
-    "concept": {
-      "description": "the one-line creative concept",
-      "type": "string"
-    },
-    "copy": {
-      "description": "copy variants ({headline, primary, cta})",
-      "items": {},
-      "type": "array"
-    },
-    "format": {
-      "description": "the resolved creative format — 'image' or 'video'",
-      "type": "string"
-    },
-    "image_concept": {
-      "description": "the render-ready image concept (prompt etc.) when format is image"
-    },
-    "imodel": {
-      "description": "the image model id to render with",
-      "type": "string"
-    },
-    "recipe": {
-      "description": "the resolved recipe id",
-      "type": "string"
-    },
-    "recipe_label": {
-      "description": "the resolved recipe display name",
-      "type": "string"
-    },
-    "render_plan": {
-      "description": "the routing plan (structure/duration) render_ad honors"
-    },
-    "video_storyboard": {
-      "description": "the timed storyboard (scenes, cta, music) when format is video"
-    },
-    "vmodel": {
-      "description": "the video model id to render with",
-      "type": "string"
-    }
-  },
-  "type": "object"
-}New value: +null