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

docs(image): clarify Failed is a non-terminal status the Step 5 gate must resolve

hugohe3554d54b6a6f9
diff --git a/skills/ppt-master/SKILL.md b/skills/ppt-master/SKILL.md
index 90b2b47a..3c34b28a 100644
--- a/skills/ppt-master/SKILL.md
+++ b/skills/ppt-master/SKILL.md
@@ -513,10 +513,10 @@ A deck with only `ai` rows never loads `image-searcher.md`; a deck with only `we
Workflow:
-1. Extract all resource rows from the design spec and group them by `Acquire Via`; rows with `Status: Pending` and `Acquire Via ∈ {ai, web, slice}` must all reach a terminal state before Executor starts
+1. Extract all resource rows from the design spec and group them by `Acquire Via`; rows with `Status: Pending` or `Status: Failed` and `Acquire Via ∈ {ai, web, slice}` must all reach a terminal state before Executor starts
2. Generate prompts (ai rows) and/or run search (web rows) per [image-base.md](references/image-base.md) §3 dispatch table
2.5. **Slice any spot-illustration sheets (only if `slice` rows exist).** For each generated `ai` **sheet** row, run `slice_images.py` (grid + the element `--names` matching the `slice` rows, `--trim --alpha`) so every element file lands in `images/`; mark each `slice` row `Generated`. A sheet still in `Needs-Manual` cannot be sliced — leave its `slice` rows `Needs-Manual` and surface them at the Step 7 readiness gate. Contract: [image-generator.md](references/image-generator.md) §4.3.
-3. Verify every row reaches a terminal status: `Generated` (ai success / sliced element), `Sourced` (web success), or `Needs-Manual`
+3. Verify every row reaches a terminal status: `Generated` (ai success / sliced element), `Sourced` (web success), or `Needs-Manual`. `Failed` is not a terminal status: it means the current run did not generate that item, but the item remains retryable. The agent must resolve every residual `Failed` item by rerunning the confirmed path or marking it `Needs-Manual` before Executor starts
4. Re-derive image facts now that web / AI / sliced files are in the folder — `python3 ${SKILL_DIR}/scripts/analyze_images.py <project_path>/images` — so `analysis/image_analysis.csv` reflects every acquired image **including the sliced elements** (real measured sizes) before the Executor lays them out. Image facts are regenerated on use, never a stale store (see Step 4's image-facts note).
**✅ Checkpoint — Confirm acquisition attempted for every row**:
@@ -526,7 +526,7 @@ Workflow:
- [x] image_prompts.md sidecar rendered (when any ai rows processed)
- [x] image_sources.json created (when any web rows processed)
- [x] Spot-illustration sheets sliced (when any `slice` rows exist); every element file present in `images/` and listed in `spec_lock.md images`
-- [x] Each row: status is `Generated` / `Sourced` / `Needs-Manual` (no `Pending` remaining)
+- [x] Each row: status is `Generated` / `Sourced` / `Needs-Manual` (no `Pending` or `Failed` remaining)
- [x] analyze_images.py re-run so image_analysis.csv covers the acquired web / AI / sliced images
```
diff --git a/skills/ppt-master/references/image-base.md b/skills/ppt-master/references/image-base.md
index a7f40233..0916191a 100644
--- a/skills/ppt-master/references/image-base.md
+++ b/skills/ppt-master/references/image-base.md
@@ -65,8 +65,8 @@ After all rows reach terminal status:
- Every non-skipped row has a file at `project/images/<filename>`, or is marked `Needs-Manual`
- Every `slice` row has a generated element file, or is marked `Needs-Manual` because its parent sheet is not available
-- No `Pending` rows remain
-- `image_prompts.json` exists when ≥1 ai row processed; every entry has `status ∈ {Generated, Failed, Needs-Manual}` (no `Pending` remaining)
+- No `Pending` or `Failed` rows remain
+- `image_prompts.json` exists when ≥1 ai row processed; every entry has `status ∈ {Generated, Needs-Manual}` (no `Pending` or `Failed` remaining)
- `image_sources.json` exists when ≥1 web row processed; every entry has `license_tier ∈ {no-attribution, attribution-required, manual}` (`manual` = a user-supplied `--from-url` replacement)
> `Needs-Manual` is a legitimate terminal state for ai rows — Step 7 entry waits for the user to place the file. See [`image-generator.md`](./image-generator.md) §3.2 Offline Manual Mode.
diff --git a/skills/ppt-master/scripts/image_gen.py b/skills/ppt-master/scripts/image_gen.py
index ae41496b..1c26b716 100644
--- a/skills/ppt-master/scripts/image_gen.py
+++ b/skills/ppt-master/scripts/image_gen.py
@@ -484,7 +484,9 @@ def _run_manifest(manifest: dict, manifest_path: str, backend_module, *,
- On any rate-limit error in a batch, halve concurrency (min 1) and
requeue the rate-limited items.
- Per-item failures are recorded as `status: Failed` + `last_error`
- and not retried within this run.
+ and not retried within this run. `Failed` remains retryable and
+ non-terminal; the Step 5 gate must resolve it by rerunning this
+ manifest or marking the item `Needs-Manual`.
- Status is written back to the manifest file after each completion;
a Ctrl-C in the middle still preserves done items.
- `Needs-Manual` items are skipped (user processes them externally).
@@ -563,7 +565,10 @@ def _run_manifest(manifest: dict, manifest_path: str, backend_module, *,
item["status"] = STATUS_FAILED
item["last_error"] = str(exc)[:500]
fail_count += 1
- print(f" [FAIL] {item['filename']}: {exc}")
+ print(
+ f" [FAIL] {item['filename']}: {exc} "
+ "(status=Failed; retry or mark Needs-Manual before Executor)"
+ )
save_manifest(manifest_path, manifest)
if rate_limited and current > 1:
@@ -581,6 +586,12 @@ def _run_manifest(manifest: dict, manifest_path: str, backend_module, *,
f"\n[Manifest] Done: {ok_count} ok / {fail_count} failed "
f"({skipped} pre-skipped). Manifest written to {manifest_path}"
)
+ if fail_count:
+ print(
+ "[Manifest] Failed is retryable and non-terminal. "
+ "Resolve failed item(s) by rerunning this manifest or marking them "
+ "Needs-Manual before entering Executor."
+ )
return ok_count, fail_count, skipped