@koda-sl/baker-cli 0.133.1 → 0.134.1

package/README.md

@@ -2185,7 +2185,7 @@ baker testimonials tags
 
 ### Winning Ads (`baker winning-ads`)
 
-Search the **ad-dna** corpus of scored "winning" competitor ads for reference creatives to reproduce (e.g. with `baker canvas`), and manage the brands your library tracks (`follow` / `following` / `unfollow`). Each result carries a presigned media URL (~1h TTL), the ad's DNA summary, and scores. The CLI authenticates with the normal `BAKER_API_KEY`; the Baker backend proxies the request to the ad-dna service with a server-held token — no extra credential in the sandbox.
+Search the **ad-dna** corpus of scored "winning" competitor ads for reference creatives to reproduce (e.g. with `baker canvas`), and manage the brands your library tracks (`follow` / `following` / `feed` / `unfollow`). Each result carries a presigned media URL (~1h TTL), the ad's DNA summary, and scores. The CLI authenticates with the normal `BAKER_API_KEY`; the Baker backend proxies the request to the ad-dna service with a server-held token — no extra credential in the sandbox.
 
 > The corpus has **Meta + LinkedIn** connectors, so `--platform` inputs are limited to `meta,linkedin`. (Older result rows may still carry a legacy platform string.)
 
@@ -2289,9 +2289,29 @@ List the brands you follow → `GET /api/ad-library/following`. Each row shows `
 baker winning-ads following --output md
 ```
 
+### `baker winning-ads feed`
+
+Winners across **every** brand you follow, in one library → `GET /api/ad-library/feed`. The advertiser set is derived server-side from your follows (never a client-supplied list), so this is the "what's winning across everyone I track" view. Start here, then trim to specific brands with `--advertiser adv_1,adv_2`. Capped per advertiser (`--per-advertiser`, default 5, `0` = no cap) so no single brand floods the feed — the cap is enforced server-side, so it holds even when you narrow to one advertiser. Same lean winner cards as `search` / `winners` (add `--full` for DNA + longevity).
+
+Response `data`: `winners`, `following_count` (how many brands you follow), `advertiser_ids` (the ids actually queried = follows ∩ requested), and — when relevant — `hints` (e.g. you follow nobody yet, or a requested id isn't in your follows and was skipped). In `--output md`/`files` the table is the payload and the hints are written to **stderr** so they still surface without corrupting the output.
+
+```bash
+baker winning-ads feed --per-advertiser 5 --output md
+baker winning-ads feed --advertiser adv_123,adv_456 --platform meta --output md
+```
+
+| Flag | Purpose |
+|---|---|
+| `--advertiser <ids>` | Trim to a comma-separated subset of your followed advertiser ids (ids you don't follow are skipped and reported) |
+| `--platform meta\|linkedin` | Filter to a single platform |
+| `--per-advertiser <n>` | Max winners kept per advertiser 0–50 (`0` = no cap, default 5) |
+| `--limit <n>` | Total winners across all follows 1–200 (default 40) |
+| `--winner-category <list>` | Restrict to specific winner categories |
+| `--format <list>` | Restrict to specific formats (e.g. `static,video`) |
+
 ### `baker winning-ads winners <advertiser>`
 
-Top winning ads for one advertiser id → `GET /api/ad-library/advertiser-winners`. Same lean winner cards as `search` (add `--full` for DNA + longevity). Supports `--top N` and `--platform meta|linkedin`.
+Top winning ads for one advertiser id → `GET /api/ad-library/advertiser-winners` (use `feed` for all your follows at once). Same lean winner cards as `search` (add `--full` for DNA + longevity). Supports `--top N` and `--platform meta|linkedin`.
 
 ```bash
 baker winning-ads winners adv_123 --top 15 --output md
@@ -3361,7 +3381,7 @@ Ref-image MIMEs: `image/png`, `image/jpeg`, `image/webp`, `image/gif` (via OpenR
 > - **gpt-image** (default frames): clean-plate exclusions placed **LAST** (OpenAI weights early text as composition), an explicit `photorealistic` cue, identity-critical reference **first**, and `quality=high` (gpt-image-2 forces high input fidelity automatically — the `input_fidelity` param is deliberately **not** sent). Gemini keeps exclusions inline; Recraft drops the photoreal cue.
 > - New advisories: `VIDEO_RAW_FACE_KEYFRAME` (a Seedance clip animating a RAW ingested image — real-person 422 risk), `IMAGE_PROMPT_PROFILE_MISSING`, `VIDEO_PROMPT_PROFILE_MISSING`.
 
-> **Content-policy blocks are deterministic, not flaky.** ByteDance's Seedance rejects any first/last frame that reads as a real-person likeness (even an AI-generated face) — surfaced as `content_policy_blocked` (HTTP 422, **non-retryable**). This is ByteDance's upstream filter, so it fires on **any** reseller (Replicate or otherwise) — a provider swap does **not** route around it. Retrying **never** succeeds and wastes credits. Fix the cause: use a **synthetic/AI-generated** (non-identifiable) presenter face, or route a real face to **Veo** (`person_generation: allow_adult`), or make the source frame less photorealistic.
+> **Content-policy blocks are deterministic, not flaky — and now auto-recover.** ByteDance's Seedance rejects any first/last frame that reads as a real-person likeness (even an AI-generated face) — surfaced as `content_policy_blocked` (HTTP 422/`E005` "flagged as sensitive", **non-retryable on the same model**). This is ByteDance's upstream filter, so it fires on **any** reseller (Replicate or otherwise) — a provider swap does **not** route around it. **When a Seedance `video_generate` clip is blocked, the backend automatically re-renders that same clip on `google/veo-3.1-fast` (`person_generation: allow_adult`) — the one curated model that clears the filter — so the run still completes.** The Seedance attempt is never billed (its output was never finalized); only the Veo render is charged. To skip that wasted first attempt entirely (and control look/cost), scaffold a photoreal-cast ad directly on Veo up front (`--real-face`, which also covers AI-generated photoreal faces), or make the source frame less photorealistic.
 
 ---
 
@@ -3966,7 +3986,7 @@ baker canvas run ./reference-ad.video.canvas.json
 | `--select-model <id>` | `~google/gemini-flash-latest` | Override the element-selection `text_generate` model. |
 | `--image-model <id>` | `openai/gpt-5.4-image-2` | Override the per-frame `image_generate` model (defaults to the strongest, matching `scaffold-static-ad`). |
 | `--video-model <id>` | scored router | Override the `video_generate` model **and skip the router**. Curated roster: `bytedance/seedance-2.0` (workhorse), `google/veo-3.1` (cine ceiling + real-face), `google/veo-3.1-fast` (cheap Veo), `kwaivgi/kling-v3.0-pro` (motion-transfer). |
-| `--real-face` | off | Brief needs a real human likeness → the router picks Veo (dodges the ByteDance real-person 422). |
+| `--real-face` | auto-detected | Force the Veo route for a photoreal human presenter (dodges the ByteDance real-person filter). **Usually unnecessary** — the scaffold auto-detects a photoreal on-camera person/animal cast from the deconstruct and routes it to Veo on its own; set this only to force it when the cast isn't detected. Covers AI-generated photoreal faces too, not just real ones. |
 | `--motion-transfer` | off | Motion driven from a reference / hyper-dynamic → the router picks Kling. |
 | `--identity` | off | Same character/product across clips → the router picks the Seedance workhorse. |
 | `--budget <tier>` | `standard` | Router cost posture: `economy` (cheap Veo-fast tier) / `standard` / `premium`. |
@@ -3975,7 +3995,10 @@ baker canvas run ./reference-ad.video.canvas.json
 **Scored model router.** When `--video-model` is omitted, a small weighted scorer picks from the curated
 roster and prints the choice as `models.video_route_reason` in the run report (mirroring Higgsfield's
 `models_explore`). Real-face → Veo, motion-transfer → Kling, else the Seedance workhorse; `--budget economy`
-shifts a Veo pick to the fast tier. The scaffolder also bakes **per-intent param recipes** so the hero/reveal
+shifts a Veo pick to the fast tier. **The router runs after the deconstruct, so a photoreal on-camera
+person/animal cast is auto-detected and routed to Veo up front** — that cast would be blocked on Seedance by
+ByteDance's real-person filter, so picking Seedance would only burn a wasted attempt before the runtime
+auto-fallback re-renders it on Veo anyway. The scaffolder also bakes **per-intent param recipes** so the hero/reveal
 beat claims the 1080p cine ceiling automatically and a Kling hook beat maxes prompt adherence.
 
 Each scene is captured in a **shoot mode** — `ugc_selfie` (talking heads, the default look), `ugc_broll`, `studio_product` (pack shot), `lifestyle_cinematic`, or `screen_ui`. The scaffold derives one per scene (UGC by default; the cinematic and screen lanes are opt-in) and bakes its capture block into the frame and a camera default into the clip; override per scene with a `shoot_mode` field in that scene's `scenes/sNN.json`. Capture aesthetic + depth-of-field follow the mode (UGC stays flat; studio/lifestyle allow shallow DoF). Clips also carry **diegetic native audio** — the scene's own ambience described in the Seedance prompt, never music (the music bed is a separate, ducked track); set a scene's `ambient` field to steer it.

package/dist/{chunk-Q4UI5JZN.js → chunk-CIF62V7L.js}

@@ -7307,8 +7307,8 @@ var videoGenerateNode = delegated({
   id: "video_generate",
   version: "2.0.0",
   category: "video",
-  summary: "Generate video for ad creatives. Curated roster: `bytedance/seedance-2.0` (identity/product workhorse), `google/veo-3.1` (photoreal cine ceiling + real-face fallback), `google/veo-3.1-fast` (cheap Veo iteration), `kwaivgi/kling-3.0` (motion-transfer/dynamic). Async with polling.",
-  when_to_use: "Use `bytedance/seedance-2.0` for identity/product output. Route real human likenesses to `google/veo-3.1` (dodges the ByteDance real-person filter); use `google/veo-3.1-fast` while iterating to keep cost low; `kwaivgi/kling-3.0` for motion-transfer/hyper-dynamic beats. The scaffolder's scored router picks for you. Each model gates its own durations/resolutions/aspect ratios in the registry \u2014 see the README per-model section.",
+  summary: "Generate video for ad creatives. Curated roster: `bytedance/seedance-2.0` (identity/product workhorse, NO photoreal human faces), `google/veo-3.1` (photoreal cine ceiling + the human-face model), `google/veo-3.1-fast` (cheap Veo iteration), `kwaivgi/kling-3.0` (motion-transfer/dynamic). Async with polling.",
+  when_to_use: "Use `bytedance/seedance-2.0` for identity/product output WITHOUT a photoreal human face on camera. Any clip whose frame shows a photoreal human face \u2014 a UGC creator, presenter, or testimonial speaker, REAL OR AI-GENERATED \u2014 must use `google/veo-3.1`: ByteDance's filter rejects photoreal human faces on Seedance (content_policy_blocked/E005), and a synthetic AI face does NOT clear it. Use `google/veo-3.1-fast` while iterating to keep cost low; `kwaivgi/kling-3.0` for motion-transfer/hyper-dynamic beats. `baker canvas scaffold-video` auto-routes a photoreal cast to Veo; a Seedance clip blocked at runtime also auto-recovers on Veo. Each model gates its own durations/resolutions/aspect ratios in the registry \u2014 see the README per-model section.",
   inputs: z28.object({
     first_frame: ImageRef.optional(),
     last_frame: ImageRef.optional(),
@@ -7798,4 +7798,4 @@ export {
   defaultRegistry,
   createEngineFromEnv
 };
-//# sourceMappingURL=chunk-Q4UI5JZN.js.map
+//# sourceMappingURL=chunk-CIF62V7L.js.map