Skip to content

AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He

fix(confirm-ui): expose fallback AI rendering choices

hugohe3fcb0710c0b96
diff --git a/skills/ppt-master/references/strategist-image.md b/skills/ppt-master/references/strategist-image.md
index e1560bf6..38d6b555 100644
--- a/skills/ppt-master/references/strategist-image.md
+++ b/skills/ppt-master/references/strategist-image.md
@@ -4,7 +4,7 @@
Conditional extension for formula assets, proposed / confirmed image elaboration, AI rendering selection, and `design_spec.md §VIII` resource planning.
-**Trigger**: Core first derives proposed `recommend.image_usage`. Load this module before Stage-2 direction construction when that proposal contains any non-`none` source, when the user supplied an explicit non-`none` image constraint, or when formula handling is triggered. After confirmation, the confirmed sources bound production: confirmed `none` with no formula trigger stops before resource authoring. On a formula-only path, read §3 and the formula-row rules in §4; skip non-formula planning. [`strategist.md`](./strategist.md) owns source recommendation; this module owns image-dependent candidates, production detail, and §VIII rows.
+**Trigger**: Load before Stage-2 directions for a proposed non-`none` source, an explicit non-`none` constraint, or formulas. If confirmed `none` becomes non-`none`, load after Stage 2 without backfilling candidates. Confirmed `none` without formulas stops before resources. A formula-only path reads §3 and §4 formula rows only. [`strategist.md`](./strategist.md) owns source recommendation; this module owns image-dependent candidates, production detail, and §VIII rows.
---
@@ -18,12 +18,14 @@ For illustration, apply this precedence: confirmed `none` → explicit user inte
**Default — one coherent sheet for compatible same-family spots (may override when aspect, detail, quality, or semantic needs differ)**: prefer one Illustration Sheet when several AI-generated spots can share a useful cell shape and production treatment; generate them independently when forcing one sheet would weaken a planned element. When a sheet is chosen, plan one unplaced `ai` Illustration Sheet row plus one placed `slice` row per used element; only slice rows enter `spec_lock.md images`. State the intended placement shape family in the sheet reference and use separate sheets for incompatible shapes. [`image-generator.md`](./image-generator.md) §4.3 owns grid, ratio, slicing, and execution details. Stage 3 chooses the AI execution path under `image-generator.md` §7; do not pre-empt or re-pick it here.
-## 2. AI Image Strategy — propose before Stage 2; lock only for confirmed `ai`
+## 2. AI Image Strategy — propose only for recommended `ai`; lock any confirmed `ai`
When proposed sources include `ai`, read [`image-renderings/_index.md`](./image-renderings/_index.md) before constructing Stage 2. Unless the user or active template already names a rendering, place at least three credible, distinct preset renderings across the coordinated safe/shifted/bold directions; a genuine compatibility shortfall may return fewer with a reason. Each preset `image_strategy` carries localized `rendering`, `visual`, and `mood` only. Mood includes a recognizable real-world analogy. Image colors always inherit that direction's deck HEX roles; never add an image palette or alter deck colors to rescue a rendering.
Also write one `custom_candidates.image_strategy` under the Confirm UI contract: localized `name` / `visual` / `mood`, `rendering: custom`, and non-empty localized `behavior` satisfying the catalog grammar. If it combines or borrows existing renderings, name every exact id in the visible proposal and read every corresponding `image-renderings/<id>.md` before writing the synthesis. If it is genuinely novel, read no preset file and name no catalog basis. Keep it unselected unless the user supplied it (`recommend.image_strategy: custom`); under a template it obeys inherited identity and application. Only a selected custom locks its edited behavior as `image_rendering_behavior`; when catalog material is actually used, also project the exact ids as `image_rendering_references`, otherwise omit that field. Discard an unselected candidate downstream. Ignore legacy `image_palette`.
+Post-confirmation AI activation creates no candidates: read the selected preset, or consume custom behavior/references.
+
For specialized or regulated paper-figure subjects, preserve the prompt depth required by [`image-generator.md`](./image-generator.md) §4.2 rather than shortening to a generic brief. Scan the outline for genuine image-led pages, list the proposed hero pages in Stage-2 `image_notes` so the user can retain, edit, or remove them in the same confirmation, then mark only the confirmed pages' AI rows `page_role: hero_page`; local is the default. `text_policy: embedded` is reserved for stable figure-internal identifiers or lettering deliberately fused into the artwork; page titles, editable data values/labels, and prose remain SVG. Resolve confirmed provided assets through the context-first boundary above before writing §VIII.
## 3. Formula Asset Policy
diff --git a/skills/ppt-master/references/strategist.md b/skills/ppt-master/references/strategist.md
index daff634c..c399cede 100644
--- a/skills/ppt-master/references/strategist.md
+++ b/skills/ppt-master/references/strategist.md
@@ -266,7 +266,7 @@ Formula policy and formula-asset planning are conditional. If the source contain
**Conditional module — two-stage trigger**:
1. First derive the proposed `recommend.image_usage` in core. If it contains any non-`none` source—especially `ai`—read [`strategist-image.md`](./strategist-image.md) **before authoring the Stage-2 design directions** so rendering and other image-dependent candidate details are real, not backfilled after confirmation. An explicit non-`none` image constraint or the formula trigger from §g activates the module at the same point.
-2. After confirmation, the confirmed value is the production boundary. A confirmed non-`none` set continues into resource planning; confirmed `none` with no formula trigger skips all downstream image rows even if the proposed recommendation had loaded the module.
+2. Confirmed sources bound production. Non-`none` loads or retains [`strategist-image.md`](./strategist-image.md) for resource planning without backfilling candidates; `none` without formulas writes no image rows.
The module owns formula policy, AI rendering alternatives, acquisition paths, resource rows, prompt depth, page roles, and placement intent.
diff --git a/skills/ppt-master/scripts/confirm_ui/server.py b/skills/ppt-master/scripts/confirm_ui/server.py
index 4887ae21..1b5ebffc 100644
--- a/skills/ppt-master/scripts/confirm_ui/server.py
+++ b/skills/ppt-master/scripts/confirm_ui/server.py
@@ -995,6 +995,16 @@ def _stage2_solution_error(
)
if typography_error:
return typography_error
+
+ if _uses_ai_images(result):
+ image_strategy = result.get('image_strategy')
+ if not isinstance(image_strategy, dict) or not str(
+ image_strategy.get('rendering') or ''
+ ).strip():
+ return 'image_usage includes ai, so image_strategy.rendering must be non-empty'
+ rendering = image_strategy['rendering'].strip()
+ if rendering != 'custom' and rendering not in _ai_rendering_ids():
+ return f'image_strategy.rendering is not a known preset: {rendering}'
return None
@@ -1530,6 +1540,11 @@ def _ai_comparison_items(kind: str) -> list[dict[str, str]]:
return items
+def _ai_rendering_ids() -> set[str]:
+ """Return the rendering presets exposed by the confirmation UI."""
+ return {item['id'] for item in _ai_comparison_items('rendering')}
+
+
def _build_ai_image_comparison() -> dict:
return {
'rendering': _ai_comparison_items('rendering'),
diff --git a/skills/ppt-master/scripts/confirm_ui/static/app.js b/skills/ppt-master/scripts/confirm_ui/static/app.js
index 722bc91d..2dfcddf3 100644
--- a/skills/ppt-master/scripts/confirm_ui/static/app.js
+++ b/skills/ppt-master/scripts/confirm_ui/static/app.js
@@ -80,7 +80,12 @@
formula_policy: "Formula rendering policy",
image_ai_path: "AI image source",
image_strategy: "Generated image style",
- image_strategy_empty: "No generated-image style candidates were provided.",
+ image_strategy_empty: "No preset style references are available. You can still use a custom style.",
+ image_strategy_required: "Choose a generated-image preset or describe a custom style.",
+ image_strategy_invalid: "The selected generated-image preset is not available.",
+ image_strategy_select_placeholder: "Choose a generated-image preset…",
+ image_strategy_recommended_group: "Recommended for this deck",
+ image_strategy_all_group: "All preset styles",
image_strategy_rendering: "Rendering",
image_strategy_visual: "Visual",
image_strategy_mood: "Mood",
@@ -234,7 +239,12 @@
formula_policy: "数式レンダリング方針",
image_ai_path: "AI画像の生成元",
image_strategy: "生成画像のスタイル",
- image_strategy_empty: "生成画像スタイルの候補がまだありません。",
+ image_strategy_empty: "プリセットのスタイル見本を利用できません。カスタムスタイルは引き続き使用できます。",
+ image_strategy_required: "生成画像のプリセットを選ぶか、カスタムスタイルを記述してください。",
+ image_strategy_invalid: "選択した生成画像プリセットは利用できません。",
+ image_strategy_select_placeholder: "生成画像のプリセットを選択…",
+ image_strategy_recommended_group: "この資料へのおすすめ",
+ image_strategy_all_group: "すべてのプリセットスタイル",
image_strategy_rendering: "レンダリング",
image_strategy_visual: "ビジュアル",
image_strategy_mood: "ムード",
@@ -388,7 +398,12 @@
formula_policy: "公式渲染策略",
image_ai_path: "生成配图来源",
image_strategy: "生成图风格",
- image_strategy_empty: "还没有提供生成图风格候选。",
+ image_strategy_empty: "当前没有可用的预设风格参考,仍可使用自定义风格。",
+ image_strategy_required: "请选择一种生成图预设,或填写自定义风格。",
+ image_strategy_invalid: "所选生成图预设当前不可用。",
+ image_strategy_select_placeholder: "选择生成图预设…",
+ image_strategy_recommended_group: "本项目推荐",
+ image_strategy_all_group: "全部预设风格",
image_strategy_rendering: "渲染风格",
image_strategy_visual: "视觉",
image_strategy_mood: "情绪",
@@ -598,6 +613,7 @@
var CAT = null; // catalogs.json — finite option universe
var REC = null; // current recommendation stage — AI picks + candidates
var ICON_PREVIEWS = {}; // /api/icon-previews — real SVG samples from templates/icons
+ var AI_IMAGE_COMPARISON = {}; // /api/ai-image-comparison — preset rendering catalog
var STATE = {};
var REC_ALIASES = {
icons: {
@@ -1343,6 +1359,23 @@
}).slice(0, 3);
}
+ function imageStrategyCatalogCandidates() {
+ var items = AI_IMAGE_COMPARISON && AI_IMAGE_COMPARISON.rendering;
+ if (!Array.isArray(items)) return [];
+ return items.map(function (item) {
+ return item && item.id ? { rendering: item.id } : null;
+ }).filter(Boolean);
+ }
+
+ function imageStrategySelectableCandidates() {
+ var recommended = imageStrategyRecommendationCandidates();
+ var seen = {};
+ recommended.forEach(function (candidate) { seen[candidate.rendering] = true; });
+ return recommended.concat(imageStrategyCatalogCandidates().filter(function (candidate) {
+ return !seen[candidate.rendering];
+ }));
+ }
+
function imageStrategyCustomCandidate() {
var candidate = customCandidateSpec("image_strategy");
if (!customCandidateBehavior("image_strategy")) {
@@ -1350,10 +1383,9 @@
return item && item.rendering === "custom";
})[0] || {};
}
- if (!candidate || typeof candidate !== "object") return null;
+ if (!candidate || typeof candidate !== "object") candidate = {};
candidate = Object.assign({}, candidate, { rendering: "custom" });
- var normalized = normalizedImageStrategy(candidate);
- return String(normalized.behavior || "").trim() ? normalized : null;
+ return normalizedImageStrategy(candidate);
}
function normalizedImageStrategy(candidate) {
@@ -2516,8 +2548,13 @@
visual.innerHTML = "";
var row = appendImageStrategyPreviews(visual, strategy);
visual.classList.toggle("image-strategy-preview-empty", !row);
- if (!row) visual.appendChild(el("div", "toggle-desc", t("image_strategy_no_reference")));
- title.textContent = strategy.name || t("image_strategy_ai_custom");
+ if (!row) visual.appendChild(el("div", "toggle-desc",
+ strategy.rendering === "custom" ? t("image_strategy_no_reference") :
+ t("image_strategy_select_placeholder")));
+ title.textContent = strategy.name ||
+ (strategy.rendering === "custom" ? t("image_strategy_ai_custom") :
+ (strategy.rendering ? comparisonValueLabel("rendering", strategy.rendering) :
+ t("image_strategy_select_placeholder")));
var parts = [];
if (strategy.rendering) {
parts.push(t("image_strategy_rendering") + ": " +
@@ -2592,22 +2629,21 @@
var strategySub = el("div", "subfield image-strategy-subfield");
strategySub.appendChild(el("div", "subfield-label", t("image_strategy")));
strategySub.appendChild(el("div", "toggle-desc", t("image_strategy_reference_hint")));
- var strategyGrid = el("div", "font-grid image-strategy-grid");
- var strategyCands = imageStrategyRecommendationCandidates();
+ var recommendedStrategies = imageStrategyRecommendationCandidates();
+ var strategyCands = imageStrategySelectableCandidates();
+ var hasRecommendedStrategies = recommendedStrategies.length > 0;
var customStrategy = STATE.image_strategy_custom || imageStrategyCustomCandidate();
+ var presetPicker = el("div", "image-strategy-picker");
+ var presetSelect = el("select", "font-select image-strategy-select");
var customCard = null;
var syncCustomStrategy = function () {};
var selectCustomImageStrategy = function () {};
- function markStrategyCard(selectedCard) {
- strategyGrid.querySelectorAll(".font-card").forEach(function (card) {
- card.classList.toggle("selected", card === selectedCard);
- });
- }
-
- function selectImageStrategy(idx, selectedCard) {
+ function selectImageStrategy(idx) {
+ if (!strategyCands[idx]) return;
STATE.image_strategy = normalizedImageStrategy(strategyCands[idx]);
- markStrategyCard(selectedCard || strategyGrid.querySelector('[data-strategy-index="' + idx + '"]'));
+ presetSelect.value = String(idx);
+ if (customCard) customCard.classList.remove("selected");
syncCustomStrategy(false);
refreshImageStrategyPreview();
}
@@ -2620,28 +2656,44 @@
return -1;
}
- strategyCands.forEach(function (candidate, idx) {
- var card = el("div", "font-card");
- card.setAttribute("data-strategy-index", String(idx));
- var top = el("div", "font-card-head");
- top.appendChild(el("span", "font-card-name",
- localized(candidate, "name") || (t("option_prefix") + " " + (idx + 1))));
- if (candidate.rendering) {
- top.appendChild(el("span", "font-card-meta",
- t("image_strategy_rendering") + ": " + comparisonValueLabel("rendering", candidate.rendering)));
+ function strategyOptionLabel(candidate, idx) {
+ var renderingLabel = comparisonValueLabel("rendering", candidate.rendering);
+ var candidateName = localized(candidate, "name") || renderingLabel ||
+ (t("option_prefix") + " " + (idx + 1));
+ return candidateName !== renderingLabel ?
+ candidateName + " · " + renderingLabel : candidateName;
+ }
+
+ function appendStrategyOptions(label, start, end) {
+ if (start >= end) return;
+ var group = document.createElement("optgroup");
+ group.label = label;
+ for (var idx = start; idx < end; idx += 1) {
+ var option = document.createElement("option");
+ option.value = String(idx);
+ option.textContent = strategyOptionLabel(strategyCands[idx], idx);
+ group.appendChild(option);
}
- card.appendChild(top);
- appendImageStrategyPreviews(card, candidate);
- [
- ["image_strategy_visual", localized(candidate, "visual")],
- ["image_strategy_mood", localized(candidate, "mood")]
- ].forEach(function (row) {
- if (row[1]) card.appendChild(el("div", "color-note", t(row[0]) + ":" + row[1]));
- });
- card.addEventListener("click", function () { selectImageStrategy(idx, card); });
- strategyGrid.appendChild(card);
+ presetSelect.appendChild(group);
+ }
+
+ var placeholderOption = document.createElement("option");
+ placeholderOption.value = "";
+ placeholderOption.textContent = t("image_strategy_select_placeholder");
+ placeholderOption.disabled = true;
+ placeholderOption.selected = true;
+ presetSelect.appendChild(placeholderOption);
+ appendStrategyOptions(t("image_strategy_recommended_group"), 0, recommendedStrategies.length);
+ appendStrategyOptions(t("image_strategy_all_group"), recommendedStrategies.length, strategyCands.length);
+ presetSelect.disabled = !strategyCands.length;
+ presetSelect.addEventListener("change", function () {
+ selectImageStrategy(parseInt(presetSelect.value, 10));
});
- if (!strategyCands.length) strategyGrid.appendChild(el("div", "toggle-desc", t("image_strategy_empty")));
+ presetPicker.appendChild(presetSelect);
+ if (!strategyCands.length) {
+ presetPicker.appendChild(el("div", "toggle-desc", t("image_strategy_empty")));
+ }
+ strategySub.appendChild(presetPicker);
if (customStrategy) {
customStrategy = normalizedImageStrategy(customStrategy);
@@ -2658,7 +2710,8 @@
].forEach(function (row) {
if (row[1]) customCard.appendChild(el("div", "color-note", t(row[0]) + ":" + row[1]));
});
- var customCopy = el("div", "ai-custom-candidate-copy", customStrategy.behavior);
+ var customCopy = el("div", "ai-custom-candidate-copy",
+ customStrategy.behavior || t("image_strategy_custom_placeholder"));
customCard.appendChild(customCopy);
var customInput = el("textarea", "text-input image-strategy-custom-input");
setNaturalInputDirection(customInput);
@@ -2669,7 +2722,7 @@
customCard.appendChild(customInput);
syncCustomStrategy = function (selected) {
- customCopy.textContent = customStrategy.behavior || "";
+ customCopy.textContent = customStrategy.behavior || t("image_strategy_custom_placeholder");
customCopy.style.display = selected ? "none" : "block";
customInput.style.display = selected ? "block" : "none";
if (selected && customInput.value !== customStrategy.behavior) {
@@ -2679,7 +2732,8 @@
selectCustomImageStrategy = function () {
STATE.image_strategy = normalizedImageStrategy(customStrategy);
- markStrategyCard(customCard);
+ presetSelect.value = "";
+ customCard.classList.add("selected");
syncCustomStrategy(true);
refreshImageStrategyPreview();
};
@@ -2695,9 +2749,8 @@
customInput.focus();
});
syncCustomStrategy(false);
- strategyGrid.appendChild(customCard);
+ strategySub.appendChild(customCard);
}
- strategySub.appendChild(strategyGrid);
var recommendedIds = selectedImageUsageIds(recValue("image_usage"));
if (!recommendedIds.length) recommendedIds = [defaultImageUsageId()];
@@ -2748,10 +2801,9 @@
selectCustomImageStrategy();
} else if (STATE.image_strategy && imageStrategyCandidateIndex(STATE.image_strategy) >= 0) {
selectImageStrategy(imageStrategyCandidateIndex(STATE.image_strategy));
- } else if (strategyCands.length) {
+ } else if (needsGeneratedImagesForUsage(STATE.image_usage) &&
+ hasRecommendedStrategies && strategyCands.length) {
selectImageStrategy(imageStrategySelectedIndex());
- } else if (customCard) {
- selectCustomImageStrategy();
}
refreshUsageChips();
host.appendChild(sec);
@@ -3082,8 +3134,6 @@
);
} else if (directionStrategy) {
STATE.image_strategy = normalizedImageStrategy(directionStrategy);
- } else if (STATE.image_strategy_custom) {
- STATE.image_strategy = normalizedImageStrategy(STATE.image_strategy_custom);
}
}
@@ -3166,6 +3216,24 @@
return !!valid;
}
+ function imageStrategyValid(payload) {
+ if (!needsGeneratedImagesForUsage(payload.image_usage)) return true;
+ var imageStrategy = payload.image_strategy || {};
+ var rendering = String(imageStrategy.rendering || "").trim();
+ if (!rendering) {
+ document.getElementById("confirm-status").textContent = t("image_strategy_required");
+ return false;
+ }
+ var presetIds = imageStrategyCatalogCandidates().map(function (candidate) {
+ return candidate.rendering;
+ });
+ if (rendering !== "custom" && presetIds.length && presetIds.indexOf(rendering) < 0) {
+ document.getElementById("confirm-status").textContent = t("image_strategy_invalid");
+ return false;
+ }
+ return true;
+ }
+
function positiveNumber(value) {
var number = parseFloat(value);
return isFinite(number) && number > 0;
@@ -3256,6 +3324,7 @@
function submitStage2() {
var payload = stage2Payload();
if (!imageUsageValid(payload.image_usage)) return;
+ if (!imageStrategyValid(payload)) return;
if (!designSystemValid(payload)) return;
if (!customSelectionsValid(payload)) return;
submitStage(payload, 3);
@@ -3322,6 +3391,7 @@
payload.image_strategy = normalizedImageStrategy(payload.image_strategy);
}
normalizeCreativePayload(payload);
+ if (!imageStrategyValid(payload)) return;
if (!designSystemValid(payload)) return;
if (!customSelectionsValid(payload)) return;
btn.disabled = true;
@@ -3381,6 +3451,11 @@
.catch(function () { return {}; });
}
+ function loadAiImageComparison() {
+ return fetchJson("/api/ai-image-comparison", "AI image comparison")
+ .catch(function () { return {}; });
+ }
+
function boot() {
applyStaticTranslations();
var toggleBtn = document.getElementById("btn-lang-toggle");
@@ -3466,11 +3541,13 @@
Promise.all([
loadCatalogs(),
fetchJson("/api/recommendations", "recommendations"),
- loadIconPreviews()
+ loadIconPreviews(),
+ loadAiImageComparison()
]).then(function (res) {
CAT = res[0];
REC = res[1];
ICON_PREVIEWS = res[2] || {};
+ AI_IMAGE_COMPARISON = res[3] || {};
if (REC.lang === "zh" || REC.lang === "en" || REC.lang === "ja") {
var hasStored = false;
try { hasStored = !!window.localStorage.getItem("ppt_lang"); } catch (e) { /* ignore */ }
diff --git a/skills/ppt-master/scripts/confirm_ui/static/style.css b/skills/ppt-master/scripts/confirm_ui/static/style.css
index 70fcf027..b708f733 100644
--- a/skills/ppt-master/scripts/confirm_ui/static/style.css
+++ b/skills/ppt-master/scripts/confirm_ui/static/style.css
@@ -497,19 +497,7 @@ textarea.text-input { resize: vertical; line-height: 1.5; }
gap: 8px;
margin: 8px 0 10px;
}
-.image-strategy-grid {
- display: grid;
- grid-template-columns: repeat(3, minmax(0, 1fr));
- align-items: stretch;
-}
-.image-strategy-grid > .font-card:not(.image-strategy-custom-card) {
- min-width: 0;
- padding: 10px;
-}
-.image-strategy-grid > .image-strategy-custom-card,
-.image-strategy-grid > .toggle-desc {
- grid-column: 1 / -1;
-}
+.image-strategy-picker { margin-top: 10px; }
.image-strategy-preview {
position: relative;
aspect-ratio: 16 / 9;
@@ -554,6 +542,7 @@ textarea.text-input { resize: vertical; line-height: 1.5; }
}
.image-strategy-custom-card {
background: var(--card);
+ margin-top: 10px;
}
.font-sample-heading { font-size: 24px; font-weight: 700; line-height: 1.3; }
.font-sample-body { font-size: 14px; color: #333; margin-top: 4px; }
diff --git a/skills/ppt-master/scripts/docs/confirm_ui.md b/skills/ppt-master/scripts/docs/confirm_ui.md
index 620e14b7..ac8e615f 100644
--- a/skills/ppt-master/scripts/docs/confirm_ui.md
+++ b/skills/ppt-master/scripts/docs/confirm_ui.md
@@ -241,7 +241,7 @@ After Stage 1 is confirmed, create `recommendations.stage2.json` with the comple
}
```
-The example abbreviates the required ≥3 directions. Custom mode/style candidates remain mandatory; AI usage also requires the custom image candidate. Stage 2 rejects fewer than three bundles, incomplete six-role palettes, and incomplete heading/body stacks. Legacy grids remain readable only with three complete palettes and complete typography.
+The example abbreviates the required ≥3 directions. Custom mode/style candidates remain mandatory; only a recommendation containing AI requires the custom image candidate. Stage 2 rejects fewer than three bundles, incomplete six-role palettes, and incomplete heading/body stacks. Legacy grids remain readable only with three complete palettes and complete typography.
After Stage 2 is confirmed, create `recommendations.stage3.json` with production recommendations only; leave both earlier files unchanged:
@@ -276,7 +276,7 @@ After Stage 2 is confirmed, create `recommendations.stage3.json` with production
- **Per-role size override** (parallel to color's per-role HEX override): besides `body_size`, the page exposes editable inputs for `title` / `subtitle` / `annotation`. The browser applies one documented deterministic dependency chain: `reading mode → body baseline → unpinned role sizes` (role ramp: `body ×` the §g ratios). Changing reading mode updates the body and all unpinned roles locally; changing body updates unpinned roles locally. Editing body or a role pins that value, so later reading-mode changes do not overwrite it. Font / direction-card selection preserves all current sizes. This is a browser-only state update: it performs no fetch, asks the backend to author no new recommendations, and a re-render preserves exactly what the user sees. Each role input is labelled as px and shows an approximate pt equivalent (`1px = 0.75pt`) for orientation. The final values are written to `result.json` as `typography.sizes: { "title", "subtitle", "annotation" }` in **px** — every canvas, no pt and no `sizes_pt` provenance. These confirmed values are Strategist input anchors: the completed page plan may add recurring roles, and downstream execution owns bounded per-occurrence treatment. Candidate `sizes` remain accepted for compatibility, but the fresh Stage-2 baseline is normalized through the same local ramp before first render.
- **`delivery_purpose` compatibility key / Reading mode** (enumerable, PPT only) decides where meaning is carried, not merely how large type is: `text` makes pages self-contained with complete sentences, short prose, captions, tables, and necessary detail; `balanced` shares explanation between page and presenter; `presentation` uses one idea, concise claims, and visual evidence while speech / notes carry the detail. It therefore governs page grammar, granularity, density / rhythm, and note burden. Reading-mode cards intentionally show **no px value**; the typography section owns the separately visible body / role sizes and applies any local default. It is surfaced in Stage 2 beside the visual system, separate from communication intent. `recommend.delivery_purpose` pre-selects one; `result.json` retains the key, while `spec_lock.md` uses canonical `consumption_mode`. Non-PPT canvases omit it.
- **Combined style preview** — a compact live "overall impression" strip sits just above the color section and is **sticky**: it pins under the topbar so it stays visible while the user scrolls through the color / icon / typography sections, keeping the picking controls and their combined effect on screen together. It applies the currently selected color palette **and** typography (heading sample in `primary` over `background`, body sample in `body_text`, an `accent` bar, a `secondary_bg` chip) and repaints on every color / HEX-override / font / `body_size` change. It does not replace the per-candidate swatches or font samples (those stay for picking); it is deliberately an abstract style chip, **not** a slide-layout preview — page layout preview remains the live-preview server's job (Step 6). No schema field; it derives entirely from the existing color + typography selections.
-- **Generated-image direction** appears only for `image_usage: ai`: up to three preset cards plus one full-width AI custom proposal. Custom has no preset dropdown; selection makes it editable and submits `rendering: "custom"` + `behavior`. If that behavior uses catalog renderings, it visibly names their exact ids; Strategist retains that confirmed basis as optional `image_rendering_references` in `spec_lock.md`. A genuinely novel behavior produces no reference row. The live preview follows the selection. No image palette is written; deck colors remain authoritative, and legacy `image_strategy.palette` is ignored.
+- **Generated-image direction** appears only for `image_usage: ai`. One preset dropdown contains project recommendations when present plus the 20 system styles; Custom remains a separate card and is blank when AI was added manually. A preset submits its id; Custom submits `rendering: "custom"` + non-empty `behavior`; closing AI omits `image_strategy`. Catalog-based custom behavior names exact ids for optional `image_rendering_references`; a novel behavior has none. The left preview follows selection. No image palette is written; deck colors remain authoritative, and legacy `image_strategy.palette` is ignored.
- **`design_directions`** is the canonical Stage-2 spectrum: ≥3 safe / shifted / bold bundles with localized copy, style, icons, conditional image strategy, complete language-aware typography, and HEX `background`, `secondary_bg`, `primary`, `accent`, `secondary_accent`, `body_text`. Selection applies the bundle; component controls override it. `result.json` stores components, not a direction id.
- `recommend.generation_mode` and `refine_spec` mirror [`generate-pptx`](../../workflows/generate-pptx.md) Step 4. `split` / `true` are explicit opt-ins. Refinement adds no UI stage: after Gate 1 it stops before the lock for unrestricted chat revision until approval.
- `content_divergence` is a **free-text** Stage-1 source-treatment field. Blank means a balanced default; facts stay sourced at every level. Strategist consumes it while authoring §IX and records it in `design_spec.md §I`; it is not written to `spec_lock.md`. Beautify sends `{ "value": "keep source wording and page structure verbatim", "locked": true }`, so the UI displays it read-only and the server restores it on every staged submit. Template-fill does not use this confirmation flow and does not surface it.
@@ -325,7 +325,7 @@ The shape above is final. The proactive-execution values are independent flat bo
- Bespoke mode / style prose lives only in the required behavior sibling; image custom prose lives in `image_strategy.behavior`. Canvas / icons retain free-text edge cases, color / typography retain `name: "custom"`, and image usage remains a source-id array plus `image_notes`.
- `image_ai_path` and `image_strategy` appear only with `image_usage: ai` and remain confirmed downstream. The page is default; explicit/failure chat fallback keeps identical fields. `image_ai_path` selects the Step 5 path, and [`strategist-image.md`](../../references/strategist-image.md) §2 retains the selected rendering or custom behavior as the deck-level image identity anchor; individual prompts still adapt subject, composition, and atmosphere within it.
-- After the user clicks the **final Confirm** (Stage 3, or single-pass), the page saves `result.json` and shuts the server down (auto-close). Stage-1 **Confirm contract & continue** and Stage-2 **Confirm solution & continue** keep the page open while it polls for the downstream stage file. The default flow is `--daemon` → Stage-1 chat handoff → `--wait-only --wait-stage stage1` → Stage-2 wait → final wait; the AI reads each result immediately. Chat fallback shows the same initially-unselected custom proposals. Either way, Step 4 ends with `--shutdown` so a never-confirmed page cannot hold port 5050 ahead of Step 6 live preview.
+- After the user clicks the **final Confirm** (Stage 3, or single-pass), the page saves `result.json` and shuts the server down (auto-close). Stage-1 **Confirm contract & continue** and Stage-2 **Confirm solution & continue** keep the page open while it polls for the downstream stage file. The default flow is `--daemon` → Stage-1 chat handoff → `--wait-only --wait-stage stage1` → Stage-2 wait → final wait; the AI reads each result immediately. Chat fallback mirrors the same preset/custom choices. Either way, Step 4 ends with `--shutdown` so a never-confirmed page cannot hold port 5050 ahead of Step 6 live preview.
## Scope
diff --git a/skills/ppt-master/workflows/generate-pptx.md b/skills/ppt-master/workflows/generate-pptx.md
index 7fe96ffe..9cb45b55 100644
--- a/skills/ppt-master/workflows/generate-pptx.md
+++ b/skills/ppt-master/workflows/generate-pptx.md
@@ -178,7 +178,7 @@ Read references/strategist.md
| Step 3 installed an explicit Brand/Layout/Deck workspace | `references/strategist-template.md` |
| The core's proposed Stage 2 `image_usage` contains a source other than `none`, the user supplied an explicit non-`none` image constraint, or formula-worthy content activates formula planning | `references/strategist-image.md` + `references/image-layout-spec.md` + `references/image-layout-patterns.md` before authoring image renderings, production detail, formula resources, or §VIII |
-The core chooses proposed Stage 2 source ids first. Load this bundle for a non-`none` proposal; after confirmation, retain it only for confirmed non-`none` sources or an active formula plan. Confirmed `none` without formulas writes no image rows. Bare template names and style language do not load the template module.
+Core chooses Stage-2 sources. Load it before Stage 2 for non-`none`, or after confirmation if `none` changes; do not backfill candidates. Retain for confirmed non-`none` or formulas; otherwise write no image rows. Bare template/style names do not load the template module.
> ⚠️ **Mandatory artifact gates**: after final confirmation, author complete `design_spec.md` from `${SKILL_DIR}/templates/design_spec_reference.md`. After Gate 1 and any refinement approval, author `spec_lock.md` from `${SKILL_DIR}/templates/spec_lock_reference.md` plus approved Design Spec/context. Author each new artifact once without placeholders or `scaffold-*` (manual-only). Schema validity does not prove semantic fidelity.
@@ -232,7 +232,7 @@ If the user rejects the current recommendation before confirming it, regenerate
python3 ${SKILL_DIR}/scripts/confirm_ui/server.py <project_path> --wait-only --wait-stage stage2
```
-3. Read the Stage 2 result, create `confirm_ui/recommendations.stage3.json` without changing either earlier stage, then perform the final blocking wait:
+3. Read Stage 2; load the image bundle if it newly confirms non-`none`. Create `confirm_ui/recommendations.stage3.json` without changing prior stages and wait:
```bash
python3 ${SKILL_DIR}/scripts/confirm_ui/server.py <project_path> --wait-only