@koda-sl/baker-cli 0.408.0 → 0.410.0-dev.53b577900

package/README.md

@@ -3080,6 +3080,23 @@ baker testimonials search "competitor support" --source trustpilot --sentiment n
 baker testimonials search "[product/offer] for [persona] that delivers [USP/outcome]" --rating-min 4 --language en --output md --full --limit 12
 ```
 
+### `baker testimonials sources`
+
+The review pages testimonials are imported from — Google Maps, Trustpilot, Yelp, Tripadvisor, G2, Capterra, Amazon, App Store, Google Play. Adding or removing one applies immediately and shows on the chat as an already-applied change.
+
+| Command | What it does |
+| --- | --- |
+| `baker testimonials sources add <link \| business name> [--platform <site>] [--every never\|daily\|weekly\|monthly]` | Recognise the page from its link (a business name finds a Google Maps listing) and import its reviews in the background. Idempotent. |
+| `baker testimonials sources list` | Every source: id, site, status, reviews imported, auto-sync. |
+| `baker testimonials sources sync <id>` | Import new reviews now. |
+| `baker testimonials sources schedule <id> --every <interval>` | Set the auto-sync cadence. |
+| `baker testimonials sources remove <id>` | Remove the source and every testimonial it imported. |
+
+```bash
+baker testimonials sources add https://www.trustpilot.com/review/acme.com
+baker testimonials sources add "Acme Bakery Madrid"
+```
+
 ### `baker testimonials get <id>`
 
 Get a single testimonial by ID.
@@ -3237,11 +3254,11 @@ Search the **ad-dna** corpus of scored "winning" competitor ads for reference cr
 
 ### `baker winning-ads search <query>`
 
-Semantic search (dense recall + BM25 + rerank) → `POST /api/ad-library/winners/search`. The CLI projects each result to a **lean, decision-focused** shape so the agent's context stays small — default fields: `advertiser`, `advertiser_id`, `platform`, `format`, `relevance`, `winner_score`, `summary` (what the ad is about), `media_url`, and `visual` (what the viewer sees) + `container` (a static's layout pattern) + `mechanism` (why it works) when known; plus top-level `pool_size`, `match_confidence` (`high|medium|low`), and `below_floor_count` (matches dropped under the relevance floor). `--full` adds DNA detail (`angle`, `target_persona`, `hook_archetype`, `awareness_stage`, `industry`) + longevity (`days_active`, `reach`, `active`, `winner_category`, `media_kind`). `--output json` (default) returns the lean objects; `--output md` prints a table.
+Semantic search (dense recall + BM25 + rerank) → `POST /api/ad-library/winners/search`. The CLI projects each result to a **lean, decision-focused** shape so the agent's context stays small — default fields: `advertiser`, `advertiser_id`, `platform`, `format`, `relevance`, `winner_score`, `summary` (what the ad is about), `media_url`, and `visual` (what the viewer sees) + `container` (a static's layout pattern) + `mechanism` (why it works) when known; plus top-level `pool_size`, `match_confidence` (`high|medium|low`), and `below_floor_count` (matches dropped under the relevance floor). The proof signals ride along (`winner_category`, `days_active`, `active`); `--full` adds DNA detail (`angle`, `target_persona`, `hook_archetype`, `awareness_stage`, `industry`) + `reach` and `media_kind`. By default the search draws from the brands the company follows first (`--scope followed-first`) and tops up from the shared library; every result says `source: followed|library`. `--output json` (default) returns the lean objects; `--output md` prints a table.
 
 > `media_url` is the creative itself: for `static` it's the image, for `video` it's the video file. ad-dna stores **no separate poster** for videos, so a video result has only the video URL.
 
-> Results are already de-junked and winner-first: the corpus auto-drops measured failures (duds, thrash) and ranks `final = relevance^0.25 × winner_score^0.75`. So `--winner-category winner` is usually unnecessary — it's a stricter filter that also removes `untested` (unproven-but-maybe-fresh) ads. Rely on the default + `--min-relevance`; only add `--winner-category` to force-exclude unproven creatives. (With a query, restricting to a single `--advertiser-id` turns the failure-exclusion and the per-advertiser cap off: you then see that brand's duds too. A search with no query is a browse, which always drops failures and `untested` ads. A company that follows one brand keeps both with `--scope followed`/`followed-first`.)
+> Results are already de-junked and winner-first: the corpus auto-drops measured failures (duds, thrash) and ranks `final = relevance^0.5 × winner_score^0.5`, so a direct match beats a stronger-but-tangential ad. So `--winner-category winner` is usually unnecessary — it's a stricter filter that also removes `untested` (unproven-but-maybe-fresh) ads. Rely on the default + `--min-relevance`; only add `--winner-category` to force-exclude unproven creatives. (With a query, restricting to a single `--advertiser-id` turns the failure-exclusion and the per-advertiser cap off: you then see that brand's duds too. A search with no query is a browse, which always drops failures and `untested` ads. A company that follows one brand keeps both with `--scope followed`/`followed-first`.)
 
 ```bash
 # Only LinkedIn video ads:
@@ -3260,6 +3277,8 @@ baker winning-ads search --format-pattern comparison_table --platform meta --out
 |---|---|
 | `query` (positional) | Free-text natural-language query |
 | `--ref-ad-id <id>` | Find ads similar to this ad (instead of free text) |
+| `--scope followed-first\|followed\|all` | Which brands to draw from (default `followed-first`: the company's followed brands, topped up from the shared library; the whole library when it follows nobody) |
+| `--sort winner\|longest_running\|newest` | Order of a no-query browse (default `winner`); ignored when a query is given |
 | `--limit <n>` | Max results 1–100 (**default 10** — shortlist size) |
 | `--max-per-advertiser <n>` | Cap results per advertiser 0–50 (default 3; `0` = no cap) |
 | `--min-relevance <0-1>` | Relevance floor; trims weak matches |
@@ -3287,7 +3306,7 @@ Read the **winner-weighted rollup** of the ad-dna corpus → `GET /api/ad-librar
 mechanism / static-format patterns that actually win, ranked by `winner_score` among the ads of the segment you
 pass (`--platform`, `--awareness`, `--industry`; an unset one means any), keyed on the closed seeds/enums the
 extractor emits (no clustering). Ground a creative in a **proven** pattern for the exact segment instead of
-guessing. The rollup is recomputed daily. (Distinct from `winning-ads patterns`, which contrasts two ad cohorts.)
+guessing. The rollup is recomputed daily.
 
 ```bash
 # Top winning hook seeds for problem-aware SaaS on Meta:
@@ -3390,24 +3409,6 @@ Stop following a brand by advertiser id → `POST /api/ad-library/unfollow`. Ret
 baker winning-ads unfollow adv_123
 ```
 
-### `baker winning-ads brief`
-
-Generate a creative brief grounded in strategically-similar winners → `POST /api/ad-library/brief`. Optionally describe the target creative with `--dna` (a JSON object), steer with `--notes`, and cap references with `--k`. Returns `brief_markdown` + `reference_ad_ids`.
-
-```bash
-baker winning-ads brief --dna '{"angle":"cost savings","awareness_stage":"solution_aware"}' --notes "B2B, LinkedIn video" --k 8
-```
-
-### `baker winning-ads patterns --winners <adIds> --duds <adIds>`
-
-Mine what separates two cohorts of ads → `POST /api/ad-library/patterns`. Pass a comma-list of winning ad ids (`--winners`, cohort A) and weaker/dud ad ids (`--duds`, cohort B), plus optional `--top-n`. Returns each discriminating DNA field with the cohort it `favors` (`winners`/`duds`), a `score`, and the top values on each side.
-
-```bash
-baker winning-ads patterns --winners a_1,a_2,a_3 --duds a_9,a_8 --top-n 10 --output md
-```
-
----
-
 ### Scheduled agents (`baker scheduled-agents`)
 
 A Scheduled agent is a **trigger** and a **prompt**. When the trigger fires, a Session opens with that prompt and does the job — there is no Task in between. `create`, `update`, and `delete` stage draft ops on `BAKER_CHAT_ID` and apply when the chat is published. `unstage` takes back what this chat staged on one item before Publish (`--index <n>` for one change only, by its index in `list` → `draft.ops`). `list` and `get` include draft state when `BAKER_CHAT_ID` is set; `get` on a published item also returns `runsAs` — who each run acts as and which tools it loads. `run` fires a published item immediately and does not require a chat id. Publishing every run unreviewed is switched on by the user on the item, never through the CLI: `--auto-publish` is refused with an `ask_user` fix.
@@ -5737,7 +5738,7 @@ The two scaffold passes are billed (the full `video_deconstruct` is the heavy on
 
 **New-creative limit:** a chat makes at most 10 new creatives. The eleventh `scaffold-static-ad`, `scaffold-ad` or `scaffold-video` with a new `--slug` exits 2 with `CREATIVE_LIMIT` before any billed pass. Re-scaffolding a creative already made in the chat, or one whose `_definition.md` existed before, does not count.
 
-`<image>` is a **local path or an `http(s)` URL** (e.g. a presigned S3 link from ad-dna). With `--slug` the source is localized to durable, content-addressed storage before anything bills, so the emitted canvas stays runnable in any sandbox; without a slug a URL is passed straight into the `original` ingest node (a presigned one expires). For the URL case, `--out` defaults to the current directory — pass `--out` to scaffold two URL sources into distinct files, or the second run overwrites the first.
+`<image>` is a **local path or an `http(s)` URL** (e.g. a presigned S3 link from ad-dna), and it is **optional when `--source-ad-id` is given**: the library's picture is used. With `--slug` the source is localized to durable, content-addressed storage before anything bills, so the emitted canvas stays runnable in any sandbox; without a slug a URL is passed straight into the `original` ingest node (a presigned one expires). For the URL case, `--out` defaults to the current directory — pass `--out` to scaffold two URL sources into distinct files, or the second run overwrites the first.
 
 Turn a source/inspiration image into a **runnable, self-validated static-ad canvas** — the static counterpart of `scaffold-video`. It runs **billed Gemini passes** up front:
 
@@ -5759,7 +5760,11 @@ The canvas is validated before it is written. stdout returns `{ ok, canvas_path,
 
 The render prompt is **model-aware**: for **gpt-image** the exclusions (no invented badges/watermark) are hoisted to the very *end* of the prompt where the model reads them as pure exclusions rather than composition. Run `baker canvas critique` on the scaffolded canvas for an advisory read before you spend.
 
+**A reference from the winners library goes in by id.** `--source-ad-id <ad_id> --source-platform meta|linkedin|tiktok [--source-advertiser-id <id>]` (the ids beside the ad in `baker winning-ads search`) fetches the library's structured read of that ad, the same one `baker winning-ads content <ad_id> --full` returns, and writes it into `prompt.json` as a `reference` block: `{ ad_id, platform, advertiser, advertiser_id, format_pattern, layout: { composition, focal_subject, aspect_ratio, background, palette_mood, colors, production, aesthetic, cta_in_image, markers }, message: { mechanism, awareness, sophistication, angle, hook_archetype, pain_points, desires, value_props, objections_handled, proof, risk_reversal }, offer: { offer_type, pricing_model, entry_price, no_credit_card, guarantee, guarantee_days, urgency, bonus }, text_blocks: [{ text, role, position }], copy: { primary_text, headline, cta } }` (filled fields only). The describe pass still reads the pixels but is told that read as grounding, so the two cannot disagree on the container or the mechanism; when it names no `winning_mechanisms`, the library's container + mechanism seeds the list. The source ids (`sourceAdId`, `sourcePlatform`, `sourceAdvertiserId`, and `sourceAdvertiser` from the library when `--advertiser` is absent) are written to `_definition.md` and synced to the creative at scaffold time. A library read that fails warns, records the ids anyway and scaffolds from the picture alone (`hints`: `REFERENCE NOT READ`); with no picture either, the command exits 2 (`source_unavailable`). `baker canvas sync-definition` re-reads the three ids from `_definition.md` on every sync.
+
 ```bash
+baker canvas scaffold-static-ad --source-ad-id adg_123 --source-platform meta --slug spring-offer --platform meta
+# → the library's picture and read; writes src/creatives/spring-offer/{spring-offer.canvas.json, prompt.json, _definition.md}
 baker canvas scaffold-static-ad ./reference-ad.png --context "competitor ad for <brand>, <category>, <market>"
 # → writes ./static-ad.canvas.json + ./prompt.json
 # edit prompt.json into your ad + replace each [TODO] ingest path with a real file, then:
@@ -5769,7 +5774,10 @@ baker canvas run ./static-ad.canvas.json
 
 | Flag | Default | Effect |
 |---|---|---|
-| `--context <text>` | — | Known provenance (advertiser, category, market) to ground the describe. |
+| `--source-ad-id <ad_id>` | — | The winners-library ad this creative adapts. Fetches its structured read into `prompt.json` `reference`, grounds the describe pass with it, and records the source on the creative. Makes `<image>` optional. |
+| `--source-platform <platform>` | `meta` | Platform the library ad is on: `meta`\|`linkedin`\|`tiktok`. Another value exits 2 (`invalid_source_platform`). |
+| `--source-advertiser-id <id>` | the library's | The reference's library advertiser id, recorded as `sourceAdvertiserId`. |
+| `--context <text>` | — | Known provenance (advertiser, category, market) to ground the describe. Appended to the library's read when `--source-ad-id` is given. |
 | `--out <path>` | `<image-dir>/static-ad.canvas.json` (cwd when `<image>` is a URL) | Where to write the canvas (`prompt.json` is written alongside). |
 | `--slug <slug>` | — | Creative slug (lowercase kebab): writes the canvas to `src/creatives/<slug>/<slug>.canvas.json` — the repo convention that attaches every run to the creative's dashboard generation history. `--out` wins over `--slug`. With a slug, the reference image is localized to durable storage and normalized to a model-safe format (SVG/AVIF/HEIC/… → PNG), so the canvas ingests a stable URL instead of an expiring one. |
 | `--describe-model <id>` | registry default (`~google/gemini-pro-latest`) | Override the `image_describe` model. |

package/dist/{chunk-N72QYDJY.js → chunk-ISCXDKWB.js}

@@ -951,7 +951,26 @@ function bakerUses(value) {
   const uses = asRecord(value);
   const companies = typeof uses.companies === "number" ? uses.companies : 0;
   if (companies === 0) return {};
-  return { baker_uses: companies, ...uses.ours === true ? { already_adapted: true } : {} };
+  const count = (n) => typeof n === "number" && n > 0 ? n : void 0;
+  const approved = count(uses.approved);
+  const rejected = count(uses.rejected);
+  return {
+    baker_uses: companies,
+    ...uses.ours === true ? { already_adapted: true } : {},
+    ...approved !== void 0 ? { approved } : {},
+    ...rejected !== void 0 ? { rejected } : {}
+  };
+}
+function dnaMove(dna) {
+  const text = (value) => typeof value === "string" && value ? value : void 0;
+  const visual = text(dna.visual);
+  const container = text(dna.container);
+  const mechanism = text(dna.mechanism);
+  return {
+    ...visual ? { visual } : {},
+    ...container ? { container } : {},
+    ...mechanism ? { mechanism } : {}
+  };
 }
 function compactWinningAd(record) {
   const dna = asRecord(record.dna);
@@ -961,13 +980,14 @@ function compactWinningAd(record) {
     format: String(record.format ?? ""),
     relevance: round2(record.relevance),
     winner_score: round2(record.winner_score),
+    winner_category: typeof record.winner_category === "string" ? record.winner_category : null,
+    days_active: typeof record.days_active === "number" ? record.days_active : null,
+    active: typeof record.active === "boolean" ? record.active : null,
     summary: String(dna.creative_concept ?? ""),
     advertiser_id: String(record.advertiser_id ?? ""),
     ad_id: String(record.ad_id ?? ""),
     media_url: String(record.media_url ?? ""),
-    ...typeof dna.visual === "string" && dna.visual ? { visual: dna.visual } : {},
-    ...typeof dna.container === "string" && dna.container ? { container: dna.container } : {},
-    ...typeof dna.mechanism === "string" && dna.mechanism ? { mechanism: dna.mechanism } : {},
+    ...dnaMove(dna),
     ...bakerUses(record.baker_uses),
     ...record.source === "followed" || record.source === "library" ? { source: record.source } : {}
   };
@@ -977,11 +997,8 @@ function fullWinningAd(record) {
   const dna = asRecord(record.dna);
   return {
     ...compact,
-    winner_category: String(record.winner_category ?? ""),
     media_kind: record.media_kind ?? null,
-    days_active: record.days_active ?? null,
     reach: record.reach ?? null,
-    active: typeof record.active === "boolean" ? record.active : null,
     angle: dna.angle ?? null,
     awareness_stage: dna.awareness_stage ?? null,
     target_persona: dna.target_persona ?? null,
@@ -1339,4 +1356,4 @@ export {
   captureVimeoCookie,
   childEnvWith
 };
-//# sourceMappingURL=chunk-N72QYDJY.js.map
+//# sourceMappingURL=chunk-ISCXDKWB.js.map