pixelkiln 0.92.1 → 0.92.3

package/docs/ENDPOINTS.md

@@ -27,6 +27,181 @@ listed so it is obvious what exists.
 
 ---
 
+## Validation ledger
+
+Which PixelLab endpoints PixelKiln calls, and how much is actually known about
+each, so live spending can be chosen by risk. Audited 5 November 2026 from
+`src/client.ts`, `src/pixellab-vfx.ts`, this file, the other docs, the skill
+references, the benchmark and showcase lockfiles, and git history. No PixelLab
+call was made for it. Each row is one endpoint (or one tightly coupled family
+of paths: a `POST` and the `GET` that polls it). The Evidence is the section
+named in the "What is known" cell.
+
+**Status**
+
+- **Measured live**: a real call was billed and the completed response shape
+  was seen. The cell says what was measured.
+- **Run live, not measured**: it ran against the account, but the bill or a
+  variant was not recorded.
+- **Mock only**: wrapped and unit-tested against mocked HTTP, with no live run
+  in the docs.
+- **Schema only**: wrapped from PixelLab's OpenAPI or MCP schema, with no live
+  run, and the docs call the completed-job shape or the price a guess.
+- **Not wrapped**: PixelLab has it and PixelKiln does not call it.
+- **Unknown**: the repo does not establish a status. See [Needs a human
+  look](#needs-a-human-look).
+
+**Money at risk** is how much a wrong estimate or an unreadable response could
+cost in one call: **Low** up to 3 generations, **Medium** 4 to 15, **High**
+over 15, or billed per direction or per batch. Failed requests are not billed,
+so a rejected body costs nothing; the exposure is an accepted job that bills
+more than planned or finishes in a shape PixelKiln cannot read.
+
+`target_palette` is sent on 17 routes since 0.92.0. Only `imagePro`,
+`imageProFlash` and `tiles` ran live with it (each matched the plan); the other
+14 are mock only (`objectPro` base, state and `pro` animation, `1dir`, Pro
+`terrain`, `uiAsset`, `uiElement`, Pro and Pro Flash character bases, states,
+portraits, outfit transfer, `interpolate`, `edit-animation`), and their rows
+say so. Since then `objectPro` base, `uiElement`, `interpolate` and
+`edit-animation` have each run live (November 2026), but without a palette, so
+the palette claim on them is still mock only.
+
+**Free acceptance probe** (November 2026): for 13 of those 14 routes, a request
+carrying only a valid four-colour `target_palette` and none of the required
+fields was answered with `422`s that named the missing fields and nothing about
+`target_palette`, while the same request with an invalid palette (a non-hex
+colour, `max_colors` 999) was answered with two `target_palette` errors. So
+PixelLab's validator knows the field and its shape on those routes, which a
+mocked test cannot show. The probe cannot show that the palette is obeyed or what
+the call costs, and a failed validation bills nothing. The 14th route,
+`/objects/{id}/animations` (the `objectPro` `pro` animation), has no required
+fields, so a palette-only request could have been accepted and billed; it was
+not probed.
+
+| Endpoint | PixelKiln feature | Status | What is known (cost / sizes / shape) | Gaps (never seen) | Money at risk |
+|---|---|---|---|---|---|
+| `GET /balance` | `doctor`, `gen` balance reads, gallery | Measured live | Free. Count is at `subscription.generations` ([Reproducing these numbers](#reproducing-these-numbers)). | Only the subscription shape is documented; a credit-only account's reply is not recorded. | Low |
+| `GET /pro-flash/cost` | Pro Flash estimates for `character` and `imageProFlash` | Measured live | Free quote. For `operation=character`: image 5 up to 96px, 6 to 208px, 9 above, plus rotations; two live jobs (7 and 2) billed exactly the quote ([Characters, measured](#characters-measured)). | Quotes for `create`, `edit` and `inpaint` are recorded from PixelLab's MCP `get_pro_flash_capabilities`, not from this route (roadmap, "Pro Flash for plain image create, edit, and inpaint"). | Low |
+| `GET /background-jobs/{id}` | every job poll; where the billed amount is read | Measured live | `usage` at the top level and again at `last_response.billing_usage`; confirmed for a `map` object (1), a standard character base (1) and the skeleton jobs ([Limits and billing](#limits-and-billing)). | Jobs are deleted 8 hours after finishing, so a bill not read in time is lost (the v3 base bill was). | Low |
+| `POST /create-image-pixflux` | `pixflux` | Measured live | 1 generation, PNG inline, about 10 s; `color_image` is a hard palette lock (130 badges, 65 of 65 in each set) ([Single-image generators, measured](#single-image-generators-measured)). Ran in `benchmarks/provider-environments/pixellab`. | None recorded. | Low |
+| `POST /map-objects` (+ `GET /map-objects/{id}`, falling back to `GET /objects`) | `map` | Measured live | 1 generation, job about 30 s; the job record expires after 8 hours but the image survives ([Object lifecycle](#object-lifecycle)). `color_image` returns 500. | The `scene` field (`background_image` + inpainting): "Unverified until a real call is billed" ([GENERATORS.md](./GENERATORS.md), `map`). | Low |
+| `POST /generate-image-v2` | `imagePro` | Measured live | A 64×64 call billed 10 (40 before the cut) and 10 again with `target_palette`; the completed job was read and a candidate downloaded through `gen` ([October 2026 Pro price cut](#october-2026-pro-price-cut), [Target palette](#target-palette-target_palette)). | Canvases above 65536px² (15 and 25 tiers) are priced from the shared Pro ladder, not measured here; `reference_images` and `style_image` are unmodeled. | High |
+| `POST /create-image-pro-flash` | `imageProFlash` | Measured live | A 32×32 still with a four-colour `target_palette` billed 5, in only those colours (November 2026; [GENERATORS.md](./GENERATORS.md#target-palette)). | Larger canvases (quote 9 at 256px) and the style-image path were never billed. | Medium |
+| `POST /edit-image-pro-flash` | revision `engine: "pro-flash"`, `image-to-image` | Mock only | Quote 5 at 64px, provisional, from MCP (roadmap, "Pro Flash for plain image create, edit, and inpaint"). | Never billed; completed-job shape never read live; the `reference` edit method is unmodeled. | Medium |
+| `POST /inpaint-image-pro-flash` | revision `engine: "pro-flash"`, `inpaint` | Mock only | Quotes 5 at 64px and 6 at 128px, provisional, from MCP (same roadmap entry). | Never billed; completed-job shape never read live; `context_image` and `output_methods` unmodeled. | Medium |
+| `POST /image-to-pixelart-pro-flash` | `pixelkiln pixelate` | Measured live | A 256×256 and a 384×384 render each billed 6; the image is `last_response.images[0]`; the result is opaque on a near-white field ([Image to Pixel Art Pro Flash, measured](#image-to-pixel-art-pro-flash-measured)). | Whether 6 is flat above 384px or with a larger source. | Medium |
+| `POST /inpaint-v3` | revision `inpaint` | Measured live | Nine pre-cut points from 32×32 to 512×512 (20 / 25 / 40); after the cut 256, 288, 352 and 384px billed 10, 15, 25, 25. `last_response.image` is a single object ([Limits and billing](#limits-and-billing), [October 2026 Pro price cut](#october-2026-pro-price-cut)). | The 20-to-25 break sits in (65536px², 82944px²] and 25-to-40 in (102400px², 123904px²]; 32px to 128px and 512px were not re-measured after the cut. | High |
+| `POST /edit-images-v2` | revision `image-to-image` | Measured live | One 32×32 call billed 20 (before the cut); `images` is an array of `{type, base64, width, height}` ([Limits and billing](#limits-and-billing)). | Nothing above 32×32 and nothing after the cut; the plan borrows `proTierCost`. | High |
+| `POST /remove-background` | revision `remove-background` | Measured live | 1 generation, synchronous `{usage, image}`; keeps the palette ([Post-processing utilities, measured](#post-processing-utilities-measured)). Measured as a loose call in the July 2026 reference. | The `complex` task and the foreground text hint (roadmap, "Remove background"). | Low |
+| `POST /reduce-colors` | revision `reduce-colors` | Measured live | 0.1 generations at 32×32, balance diff and `usage` agree ([Cleanup tier, measured](#cleanup-tier-measured), September 2026). | Larger canvases; the price of a multi-frame set call is unmeasured. | Low |
+| `POST /correct-pixelart` | revision `correct-pixelart` | Measured live | 0.1 generations at 32×32 ([Cleanup tier, measured](#cleanup-tier-measured)). | Larger canvases and multi-frame sets, as above. | Low |
+| `POST /unzoom` | `pixelkiln unzoom` | Unknown | "Cost unmeasured; PixelLab's MCP tool description claims 0.1" ([Cleanup tier, measured](#cleanup-tier-measured)). Nothing records a live run. | Everything. | Low |
+| `POST /normal-map` | revision `normal-map`, `pixelkiln normal-map` | Measured live | An 8-frame 1304×26 strip and a 64×64 revision each billed 0.5; the map comes back the input's size with matching alpha ([Normal map](#normal-map-post-normal-map-measured-once), October 2026). | The `directx` convention; strips near the 32-frame limit. | Low |
+| `POST /generate-ui-v2` | `uiElement` | Measured live | A 32×32 call billed 10 and the review page showed 64 candidates at 32×32 (November 2026, Tier 3; the plan said 1 candidate and now follows `uiElementCandidateCount`). Planned on the 10/15/25 ladder ([GENERATORS.md](./GENERATORS.md#uielement)). `target_palette` sent, mock only. | Other sizes (the 15 and 25 tiers and the other candidate bands, which come from PixelLab's published grid), and the concept-image path. | High |
+| `POST /create-1-direction-object` (+ `GET /objects/{id}`) | `1dir` | Measured live | A 32px, 3-description `batch` billed 20 (the pre-cut floor) and `item_descriptions[0]` owned slot 0 ([Candidates](#candidates)); candidate counts follow size. `target_palette` sent, mock only. | No bill since the October 2026 cut (10 / 15 / 25 is PixelLab's published ladder); tiers above the floor under `item_descriptions`. | High |
+| `POST /objects/{id}/select-frames` | `1dir` and `batch` pick | Run live, not measured | Promoted three candidates in the live batch run ([Candidates](#candidates)); `indices` is plural. | Its cost was not recorded. | Low |
+| `GET /objects?limit=&offset=` | `adopt`, `salvage` | Measured live | Free; a March 2026 sprite still resolved four months on ([Object lifecycle](#object-lifecycle)). | None recorded. | Low |
+| `POST /create-object-pro-flash` | `objectPro` base | Measured live | A 32px base billed 6 and returned 8 files at 32×32 (the rotations), matching the plan, which prices it like `character` pro-flash (November 2026, Tier 3; [GENERATORS.md](./GENERATORS.md#objectpro)). `target_palette` sent, mock only. | Other sizes and the 1-generation `reference` path. | Medium |
+| `POST /objects/{id}/states` | `objectPro` state | Mock only | Assumed to price like `character` pro-flash; the base ran live, this route did not. `target_palette` sent, mock only. | Price and shape. | Medium |
+| `POST /objects/{id}/animations` | `objectPro` animation (`v3`, `pro`) | Mock only | Same assumption as the state row; `pro` mode is documented 10 to 25 per direction. `target_palette` sent on `pro` only, mock only. | Price, shape, per-direction billing. | High |
+| `PATCH /objects/{id}/tags`, `PATCH /characters/{id}/tags` | tagging in `fetch`, `adopt`, `salvage` | Unknown | Only the negative is documented: pixflux, pixen and bitforge results "cannot be tagged" ([Object lifecycle](#object-lifecycle)). | A recorded live call. | Low |
+| `DELETE /objects/{id}`, `POST /objects/{id}/dismiss-review`, `DELETE /characters/{id}` | `salvage`, account cleanup | Unknown | Not discussed in the docs. | A recorded live call. | Low |
+| `DELETE /characters/{id}/animations` | replacing a loop's direction | Unknown | "Deleting one direction of a shared group has not been run live" ([Skeleton-driven motion, measured](#skeleton-driven-motion-measured)). | Whether the rest of the group keeps its motion. | Low |
+| `POST /create-tiles-pro` (+ `GET /tiles-pro/{id}`) | `tiles` | Measured live | One numbered description, 4 tiles at 16px, with a Game Boy `target_palette`, billed 10, every candidate in the palette (November 2026). `GET` has no `status`: 423 while drawing ([Tilesets: measured once per kind](#tilesets-measured-once-per-kind)). | `tile_feature` sets (`roads`, `tileset`, `building`) and `tile_rules`; large tile-size × variation canvases that reach the top tier. | High |
+| `POST /create-tileset` (+ `GET /tilesets/{id}`) | `terrain`, top-down | Measured live | Pro 32px billed 15 (three sets, one connected through `lower_base_tile_id`, one with edge slope); Pro 64px billed 25 and returned 25 tiles at transition 0.5; standard sets billed 3 each (planned 4), one connected through `upper_base_tile_id` ([Tilesets: measured once per kind](#tilesets-measured-once-per-kind), October 2026). `target_palette` on Pro, mock only. | Pro below 32px; standard above 32px; a standard set cannot connect to a Pro set. | High |
+| `POST /create-tileset-sidescroller` | `terrain`, `terrainOrientation: "sidescroller"` | Measured live | One 16px set at transition 0.25 billed 3; 16 tiles; `usage` is null on the `GET`, so the bill comes from the job ([Tilesets: measured once per kind](#tilesets-measured-once-per-kind)). | 32px tiles and other transition sizes (tile counts assumed 16); the call returned `metadata.transition_size: 0.0` for 0.25. | Low |
+| `POST /create-isometric-tile` (+ `GET /isometric-tiles/{id}`) | `isometricTile` | Measured live | One 32px `block` billed 1 generation, not the schema's `usd: 0.02` example ([Standalone isometric tile](#standalone-isometric-tile-schema-documented-cost-measured-once)). | Other sizes and shapes; flat pricing across 16 to 64px is an assumption. | Low |
+| `POST /create-ui-asset` (+ `GET /ui-assets/{id}`) | `uiAsset` | Measured live | One 256×192 call billed 20, the low end of the quoted 20 to 40; the plan prices 40 ([UI panels](#ui-panels-one-endpoint-schema-documented-cost-unverified), September 2026). | A second size; `pixelkiln plan` over-reads. | High |
+| `POST /generate-font-pro` (+ `GET /generate-font-pro/{id}`) | `pixelkiln font` | Unknown | Documented at 15 since the cut; "its cost is not yet measured" ([Not yet explored](#not-yet-explored)). Nothing records a live run. | Price and the non-`{usage, image}` response shape. | Medium |
+| `POST /create-character-with-8-directions`, `/create-character-with-4-directions` | `character` base, `mode: standard` | Measured live | 1 generation (read from the job's `usage`); canvas 28px larger than `image_size` ([Limits and billing](#limits-and-billing), [Characters, measured](#characters-measured), September 2026). | The 4-direction body and quadruped templates are not recorded. | Low |
+| `POST /create-character-v3` | `character` base, `mode: v3` | Run live, not measured | A base once recorded `billed: {amount: 0, unit: "usd"}` against an estimate of 2 while the submit reported 1 generation; the job had expired, so the real bill is unseen ([Limits and billing](#limits-and-billing)). | The real bill at any size. | Low (Medium at 256px, 9) |
+| `POST /create-character-pro` | `character` base, `mode: pro` | Unknown | Planned 10 to 25 by canvas ([GENERATORS.md](./GENERATORS.md)). No bill recorded in the docs. `target_palette` sent, mock only. | Everything. | High |
+| `POST /create-character-pro-flash` | `character` base, `mode: pro-flash` | Measured live | Two live jobs (7 and 2, the second from a `reference`) billed exactly the estimate; returns exactly the requested canvas ([Characters, measured](#characters-measured), September 2026). `target_palette` sent, mock only. | Sizes beyond 96px; `source_image_id` and the style-image path. | High |
+| `POST /create-character-state` | `character` state | Run live, not measured | A 64px state "moved the balance by about 22 against the 20 to 40 tier", with other jobs running ([Characters, measured](#characters-measured)). `target_palette` sent, mock only. | A clean bill, and any bill since the cut. | High |
+| `POST /animate-character`, `mode` template or v3 | `character` loops without skeleton-v3 | Run live, not measured | A v3 text loop on a 96px pro-flash base came back 108×108; template loops need a skeleton template ([Characters, measured](#characters-measured)). Plan: template 1, v3 `ceil(size² × frames / 65536)`. | Billed amounts were not recorded; billed per direction. | High |
+| `POST /animate-character`, `mode: pro` | `character` loops, `mode: pro` | Unknown | Planned 10 to 25 by canvas ([GENERATORS.md](./GENERATORS.md)). Nothing records a live run. | Everything. | High |
+| `POST /characters/animations`, `mode: skeleton-v3` | `character` loops, `mode: "skeleton-v3"` (template or sentence) | Measured live | On a v3 character: a template loop billed 3; a sentence loop (no template) billed 3, 8 frames at 96×96 from a 64px character; `west` added with `animation_group_id` billed 3 and joined the group. A standard-engine character is refused with a 500 "no stored 3D skeleton" ([Skeleton-driven motion, measured](#skeleton-driven-motion-measured), October 2026). | `pro` and `pro-flash` bases; other frame counts; the price per direction across 8 directions is untested. | High |
+| `POST /portrait-character-pro` (+ `GET /portrait-character-pro/{job_id}`) | `character` portrait | Measured live | A 16px `character_to_portrait` billed 20 (before the cut); the `GET` reports `usage: null`, so read the job ([Characters, measured](#characters-measured)). `target_palette` sent, mock only. | The price after the cut (10 to 25); larger sizes. | High |
+| `POST /characters/{id}/portrait` | `character` portrait attach | Measured live | Free (`usage.generations: 0`); the reply holds the only copy of the stored URL ([Characters, measured](#characters-measured)). | None recorded. | Low |
+| `POST /transfer-outfit-v2` | `character` outfit | Measured live | A 2-frame 92×92 job billed 20 (before the cut); frames return inline in `last_response.quantized_images` ([Characters, measured](#characters-measured)). `target_palette` sent, mock only. | Other frame counts (2 to 16) and canvases; the price after the cut. | High |
+| `GET /characters/{id}`, `GET /characters?limit=&offset=` | `adopt`, `fetch --refresh`, `salvage` | Measured live | Free; carries no `usage`; image URLs carry `?t=<updated_at>` ([Object lifecycle](#object-lifecycle)). | None recorded. | Low |
+| `POST /animate-with-text-v3` | revision `animate` | Measured live | A 64×64, 4-frame call billed 1 and returned 5 frames at 64×64 (the input frame plus 4); the plan, which borrows `character`'s v3 formula, said 1 (November 2026, Tier 3; [REVISIONS.md](./REVISIONS.md#animation-and-interpolation)). | Other sizes and frame counts (up to 16 frames at 256px reads 16 by the borrowed formula). | Medium |
+| `POST /animate-pixminimax` | revision `animate-pixminimax` | Measured live | 64×64 at 8 frames billed 1 and returned 9 frames at 64×64 (the input frame plus 8); at 16 frames billed 2 and returned 17. The plan said 1 for the 16-frame call because its old placeholder under-read; it now follows PixelLab's published table (64×64 at 4 / 8 / 16 / 40 frames: 1 / 1 / 2 / 6), see `pixMiniMaxCost` (November 2026, Tier 3; [roadmap](../skills/pixelkiln/references/pixellab-roadmap.md), "Generated effects with PixMiniMax"). | 40 frames and other sizes are unbilled (the table is PixelLab's, not a bill); `enhance_prompt`'s 0.05 is the schema's number. | Medium |
+| `POST /animate-with-skeleton-v3` | revision `animate-skeleton` | Measured live | 8 frames at 64×64 billed 3 and returned 8 frames at 64×64; `description` and `action` are both required, and sent with neither the endpoint returns 422 ([Skeleton-driven motion, measured](#skeleton-driven-motion-measured), October 2026). | Other frame counts (3 = 2 and 15 = 4 are PixelLab's anchors, unbilled). | Low |
+| `POST /estimate-skeleton` | `pixelkiln estimate-skeleton`, gallery pose helper | Run live, not measured | Ran on a 64×64 sprite before the 8-frame revision ([REVISIONS.md](./REVISIONS.md#skeleton-driven-animation)). | Its cost; the reply's `usage` is typed `unknown`. | Low |
+| `POST /interpolation-v2` | revision `interpolate` | Measured live | A 64×64 start sprite with a `lastFrame` keyframe and the default frame count billed 10 and returned 14 frames at 64×64 (November 2026, Tier 3; [REVISIONS.md](./REVISIONS.md#interpolate-between-two-keyframes)). The planner said 25, a 2.5× over-read, and now prices the canvas on the 10/15/25 ladder. `target_palette` sent, mock only. | Canvases above 65536px² (15 and 25 tiers, unbilled) and other frame counts. | High |
+| `POST /edit-animation-v2` | revision `edit-animation` | Measured live | One text edit of a 9-frame 64×64 set billed 10 and the edited set was accepted into review (November 2026, Tier 3). The planner said 25 and now prices the packed grid (nine 64×64 frames: 192×192) on the same ladder. `target_palette` sent, mock only. | Larger sets and canvases, where the packed grid crosses 65536px² (unbilled, assumed to follow the ladder). | High |
+| `POST /vfx`, lite artist, no sprite | `pixelkiln vfx --description`, `vfx` block `description` | Measured live | One effect billed 1 (balance 5104 to 5103); 163×26, 8 frames, sheet and atlas cut into 8 correct frames ([VFX artist](#vfx-artist-post-vfx-measured-once), October 2026). | The `files` shape (list or map) is undocumented; PixelKiln reads three. | Low |
+| `POST /vfx`, sprite, pro artist, `effect_id` change or `game_pack` | same | Mock only | Quoted from the OpenAPI table: pro 6 (8 with a sprite), 14 and 28 for larger sprites; plans count twice the quote ([VFX artist](#vfx-artist-post-vfx-measured-once)). | Every variant above. | High |
+| MCP `tools/call` `vfx_workbench` at `api.pixellab.ai/mcp` | `pixelkiln vfx`, `vfx` block `preset` or `recipe` | Measured live | Free on a subscription; same recipe re-rendered byte-identical; exports a sheet, GIF, atlas and optional game pack ([VFX workbench (MCP only), measured](#vfx-workbench-mcp-only-measured), October 2026). | "Busy, retry" is the only recorded error; sprites by asset are not wired. | Low |
+| `POST /create-image-pixen`, `/create-image-bitforge` | none | Not wrapped | Each 1 generation; bitforge returned blobs for a simple prompt ([Single-image generators, measured](#single-image-generators-measured)). | n/a | n/a |
+| `POST /rotate`, `/resize`, `/image-to-pixelart` | none | Not wrapped | Each 1 generation; all three break a locked palette ([Post-processing utilities, measured](#post-processing-utilities-measured)). | n/a | n/a |
+| `POST /inpaint`, `/edit-image` (not v2 or v3) | none | Not wrapped | "Untouched by any of this" ([Not yet explored](#not-yet-explored)). | n/a | n/a |
+| `POST /generate-with-style-v2`, `/image-to-pixelart-pro`, `/create-8-direction-object` | none | Not wrapped | Style transfer at 20 before the cut, not re-measured; `objectPro` covers the 8-direction object. | n/a | n/a |
+| `POST /animate-with-text-v2`, `/generate-8-rotations-v2`, `/tilesets`, `/tilesets-sidescroller`, legacy `/animate-with-skeleton` | none | Not wrapped | PixelKiln calls the `/create-tileset*` aliases, not `/tilesets*`; the legacy skeleton route takes exactly 3 frames (roadmap, "The legacy `/animate-with-skeleton`"). | n/a | n/a |
+| Character lip-sync, vocal animation, talking GIF, `portrait_to_character` | none | Not wrapped | Named out of scope in [PIXELLAB.md](./PIXELLAB.md). | n/a | n/a |
+
+### Where a wrong guess costs money
+
+The High and Medium rows that are Mock only, Schema only or Run live, not
+measured, most exposed first. A live run of the top ones also settles the most
+uncertainty per generation.
+
+1. **`/objects/{id}/animations`, `/objects/{id}/states`** (Mock only).
+   `objectPro` assumes `character` pro-flash prices; the base ran live and
+   matched (6 at 32px), but its `pro` animations are 10 to 25 per direction.
+2. **`/animate-character` template and v3** (Run live, not measured). One job
+   per direction, so an 8-direction loop is eight bills no one has recorded.
+3. **`/create-character-state`** (Run live, not measured). One rough bill
+   (about 22) taken beside other jobs and before the cut.
+4. **`/vfx` with a sprite, the pro artist, a change or a game pack** (Mock
+   only). Up to 28 generations a call, and plans reserve twice the quote.
+5. **`/edit-image-pro-flash`, `/inpaint-image-pro-flash`** (Mock only). 5 to 6
+   per call on provisional quotes, no completed response seen.
+6. **`/create-character-v3`** (Run live, not measured). 2 at 64px, up to 9 at
+   256px, and the one recorded bill was an unreadable zero.
+
+Measured in November 2026 and no longer on this list: `/animate-pixminimax`,
+`/animate-with-text-v3`, `/interpolation-v2`, `/edit-animation-v2`,
+`/generate-ui-v2` and the `objectPro` base. Their remaining exposure is the
+sizes and frame counts the row says were not billed. Two of the planners were
+wrong: `interpolate` and `edit-animation` over-read 2.5× (25 planned, 10 billed)
+and `animate-pixminimax` under-read a 16-frame clip (1 planned, 2 billed). Both
+are now calibrated to those bills, and the PixMiniMax planner follows PixelLab's
+published points at 4, 8, 16 and 40 frames, which the 40-frame point has not
+been billed against.
+
+Also worth a second look because they are measured on an old price list: the
+`1dir`, `/portrait-character-pro`, `/transfer-outfit-v2` and `/edit-images-v2`
+bills all predate the October 2026 cut, and `/inpaint-v3` was only re-measured
+from 256px to 384px.
+
+### Needs a human look
+
+The repo does not establish whether or how these ran live:
+
+- `POST /create-character-pro` and `POST /animate-character` with
+  `mode: "pro"`: the docs plan 10 to 25 and record no bill.
+- `POST /generate-font-pro`: documented price only (`pixelkiln font`).
+- `POST /unzoom`: documented price only (`pixelkiln unzoom`).
+- `PATCH` tags on objects and characters, `DELETE /objects/{id}`,
+  `DELETE /characters/{id}`, `POST /objects/{id}/dismiss-review`: used by
+  `fetch`, `adopt` and `salvage`, and no doc records a live call.
+- `DELETE /characters/{id}/animations`: only the one-direction-of-a-shared-group
+  case is called out as not run.
+
+### Keeping the ledger current
+
+Update the row in the same change that records a live call. When a call is
+billed, take the amount from the finished job's `usage` (or
+`last_response.billing_usage`), not from a balance diff taken straight after,
+since billing lags; read it before the job record expires 8 hours later. Move
+the row's status, write the measurement and its month into "What is known",
+and remove the gap it closes. If a call ran but the bill was not captured,
+set the row to Run live, not measured rather than leaving it Mock only.
+
+---
+
 ## Single-image generators, measured
 
 The endpoints that produce one standalone image. This is the decision that
@@ -54,10 +229,10 @@ canvas like the other Pro tools: a 64×64 call billed exactly 10.
 `generate-image-v2` is wrapped by pixelkiln's `imagePro` generator
 (skills/pixelkiln/references/pixellab.md): non-square and larger canvases
 than `pixflux` allows, at the 10–25 above. Its `reference_images` and
-`style_image` are not modeled, and its completed job's response shape is
-inferred from `edit-images-v2`'s (also unmeasured for this endpoint
-specifically) rather than confirmed live — see `pollImagePro` in
-`src/providers/pixellab.ts`. `generate-with-style-v2` is not wrapped at all.
+`style_image` are not modeled. Its completed job was read live (a 64×64
+call, October 2026, ran through `gen` and downloaded a picked candidate);
+`pollImagePro` in `src/providers/pixellab.ts` still reads it defensively.
+`generate-with-style-v2` is not wrapped at all.
 
 ### What the measurements actually showed
 
@@ -265,8 +440,10 @@ PixelLab 0.4.130 added a beta `target_palette` body field, then gave it to 27
 POST endpoints: `{ colors?: 2-256 hex, name?: string (≤100), max_colors?: 2-64,
 smart?: boolean }`. With `colors` every pixel is one of them; `max_colors` caps
 each image. The schema is documentation only so far: **cost with a palette is
-measured for `generate-image-v2` alone** (a 64×64 call billed 10, the same as
-without), and the rest are unmeasured. PixelKiln never sends `smart` (beta,
+measured for three routes**: `generate-image-v2` (a 64×64 call billed 10, the
+same as without), `create-image-pro-flash` (a 32×32 still billed 5) and
+`create-tiles-pro` (4 tiles at 16px billed 10), each matching the plan. The
+other 14 routes PixelKiln sends it to are mock only. PixelKiln never sends `smart` (beta,
 "single images only", needs `colors`, adds 15 to 60 s).
 
 | Endpoint | PixelKiln wrapper | Sent |
@@ -447,8 +624,8 @@ exactly its quote at 32px and 64px, and standard billed 3, under the plan.
 
 `POST /tilesets` (top-down) and `/tilesets-sidescroller` are the current
 versions; `/create-tileset*` are the older aliases with identical schemas.
-Both are wrapped by pixelkiln's `terrain` generator
-(skills/pixelkiln/references/pixellab.md), the sidescroller one with
+pixelkiln's `terrain` generator
+(skills/pixelkiln/references/pixellab.md) calls the aliases, the sidescroller one with
 `terrainOrientation: "sidescroller"`; the reference-image/`color_image`
 knobs below are not.
 
@@ -560,8 +737,9 @@ That is the only way to land new art on an existing sheet's ground plane.
 
 `GET /tiles-pro/{id}` carries no `status` field. It answers **423 while the set
 is still drawing** and 200 with `storage_urls` when it is done, so the HTTP code
-is the status. Cost is reported at submit time and lands on the same 20/25/40
-canvas tiers as `1dir`, but the canvas is tile size x variation count, not one
+is the status. Cost is reported at submit time and lands on the same canvas
+tiers as `1dir` (10/15/25 since the October 2026 cut, 20/25/40 before; a 4-tile
+16px set billed 10), but the canvas is tile size x variation count, not one
 sprite. A small tile in a large set still reaches the top tier.
 
 All response shapes used by the client are validated at runtime. The TypeScript
@@ -892,15 +1070,15 @@ Listed so the gaps are known rather than assumed away:
   across every frame of a set) are wired the same way, as the `interpolate`
   and `edit-animation` modes; see
   [Interpolate between two keyframes](./REVISIONS.md#interpolate-between-two-keyframes).
-  All four are schema-only for the *request* (live OpenAPI document, not an
-  observed call); the *completed job* response shape is a genuine unknown —
-  no usage example exists for either endpoint at all, only the generic
-  background-job one — so `pollAnimateRevision` checks several plausible
-  field names defensively rather than assume one. Cost borrows `character`'s
-  own measured v3-loop formula as a placeholder, for the same reason
-  `objectPro` borrowed `character` pro-flash's; `interpolate` and
-  `edit-animation` borrow the 20/25/40 Pro canvas tiers instead, since
-  neither schema carries a usage example.
+  All four ran live in November 2026 (Tier 3): 64×64 PixMiniMax at 8 and 16
+  frames billed 1 and 2, `animate-with-text-v3` at 4 frames billed 1,
+  `interpolate` billed 10, and `edit-animation` of a 9-frame set billed 10.
+  Every completed job was read correctly. PixMiniMax returned the frame count
+  plus the input frame (9 and 17 frames); `interpolate` returned 14 frames at
+  the default count. Cost: `animate` borrows `character`'s measured v3-loop
+  formula; `animate-pixminimax` follows PixelLab's published table, which the
+  borrowed formula under-read; `interpolate` and `edit-animation` price the
+  canvas on the 10/15/25 Pro ladder (the planner had read them as 25).
 - `/generate-font-pro` (+ `GET /generate-font-pro/{job_id}`) — an 80-glyph
   atlas PNG plus a `.ttf` from a style description, `weight`
   (`Bold`/`Regular`), and `glyph_px` (8/16/32/64). Documented at 15
@@ -918,14 +1096,11 @@ Listed so the gaps are known rather than assumed away:
 - `image-to-pixelart-pro` takes only `image` + `description`, no size fields.
   The non-Pro version is characterised above, and the Pro Flash version,
   which pixelkiln wraps, [below](#image-to-pixel-art-pro-flash-measured).
-- the tileset family, with schema documented above and costs unmeasured
-  (the standalone isometric tile endpoint alongside it now has one real
-  measured data point — see above)
 - `generate-font-pro`, job-based, with a response shape not in the simple
   `{usage, image}` form (wrapped by `pixelkiln font`, but its cost is not
   yet measured)
 - the character family beyond what the `character` generator uses: lip-sync,
-  skeleton animation, `portrait_to_character` (a full character from a bust),
+  `portrait_to_character` (a full character from a bust),
   and `source_image_id` on Pro Flash. The four creation engines, states,
   `animate-character`, portraits, and outfit transfer are covered in full; see
   the September 2026 measurements below.
@@ -942,6 +1117,9 @@ generations and finished in about two minutes:
   error for each, and a failed request bills nothing. The completed job's
   `last_response` carries `images` (base64, `width`, `height`), `flow_kind`,
   and `billing_usage` beside the top-level `usage`.
+- **`POST /characters/animations`, `mode: "skeleton-v3"` with a
+  `template_animation_id`** (a template `skeleton-v3` loop): one loop on a v3
+  character billed 3, inside PixelLab's quoted 2 to 4.
 - **`POST /characters/animations`, `mode: "skeleton-v3"` with no
   `template_animation_id`** (PixelLab's new custom motion): a one-sentence
   `action_description` and `frame_count` 8 returned 8 frames at **96×96**

package/docs/GENERATORS.md

@@ -19,9 +19,9 @@ account; [ENDPOINTS.md](./ENDPOINTS.md) contains the detailed experiments.
 | Controlled pose/expression sequence in ComfyUI | `frames` | 0 `free` provider units | one atomic ordered set |
 | Animated GIF or spritesheet from Retro Diffusion | `animation` | $0.07–$0.25 per animation (published price) | 1 GIF or PNG sheet |
 | A character facing 4 or 8 directions, its poses, and its animations | `character` | 1 per base (standard), 10–25 per pose or portrait, 1 per template loop (2–4 as `skeleton-v3`), 20 per outfit (measured once) | one set of directions, one ordered loop, or one portrait |
-| A prop, creature, or vehicle with rotations, states, or loops but no character rig | `objectPro` | about 6 per base at 64px (unmeasured) | one set of directions, or one ordered loop |
+| A prop, creature, or vehicle with rotations, states, or loops but no character rig | `objectPro` | 6 per base (measured at 32px; about 6 at 64px) | one set of directions, or one ordered loop |
 | UI chrome — panels, buttons, health bars, toolbars | `uiAsset` | 20 generations (measured once, at 256x192) | 1 composited image |
-| One UI element from a description, 16px and up, optionally guided by a concept image | `uiElement` | 10–25 generations (unmeasured) | 1 image |
+| One UI element from a description, 16px and up, optionally guided by a concept image | `uiElement` | 10–25 generations (a 32×32 call billed 10) | 1 image |
 | A styled still on the Pro Flash model, or the south sprite a Pro Flash character will rotate | `imageProFlash` | 5–9 generations (PixelLab's provisional quote) | 1 image |
 | An animated effect (spell, hit, explosion, aura), on its own or around a sprite | `vfx` | free from presets and parts; 1–28 when described to PixelLab's artist (lite measured at 1; plans at twice the quote) | one ordered frame set |
 
@@ -288,11 +288,13 @@ and regenerating the parent makes the child stale.
 | portrait | portrait-character-pro | 10–25 by `size` (16px billed exactly 20 live, before the October 2026 cut) |
 | outfit | transfer-outfit-v2 | 20 (a 2-frame, 92×92 job billed exactly this live; not yet measured at other frame counts or canvases) |
 
-The 20–40 tiers are PixelLab's; the tier is resolved from the canvas when
-the job runs and reserved against the floor, so `plan` reports the tier the
-canvas lands in. `plan` prices a 64px state at 40 (the 1dir tier for that
-many pixels); one live 64px state in September 2026 moved the balance by
-about 22, so the estimate reads high, which is the safe side for a budget.
+The 10–25 tiers are PixelLab's (20–40 before its October 2026 cut); the tier
+is resolved from the canvas when the job runs and reserved against the floor,
+so `plan` reports the tier the canvas lands in. `plan` prices a 64px state at
+25 (the 1dir tier for that many pixels); one live 64px state in September
+2026, before the cut, moved the balance by about 22 against the then 20–40
+tiers, so there is no bill on the new list, and the estimate is read as high,
+which is the safe side for a budget.
 `poll` now reads what a job like this actually billed and records it
 alongside the estimate as `billed`; `pixelkiln history`, `plan --json`, and
 the gallery show both when they differ, though `gen`'s wave budget still
@@ -351,12 +353,13 @@ ignored, since none of them reach the API for an object.
   restricted to the fields above (no `template`/`subject`, since neither
   applies). See [Working with a cast](./CHARACTERS.md#working-with-a-cast).
 
-**Cost is not independently measured.** `objectProCost()` assumes
-`/create-object-pro-flash`/its state/its animation price identically to
+**Cost: the base is measured, the rest is assumed.** `objectProCost()` prices
+`/create-object-pro-flash`/its state/its animation identically to
 `character`'s own measured pro-flash formula (`proFlashCharacterCost`),
-since the request bodies are near-identical minus `template_id` — treat it
-as a working assumption, not a confirmed number, until checked against a
-live account.
+since the request bodies are near-identical minus `template_id`. A 32px base
+billed exactly 6 live (November 2026, Tier 3) and returned 8 files at 32×32,
+matching the plan. The state route, the `pro` animation and other sizes
+are still mock only; treat them as a working assumption.
 
 Adoption (`pixelkiln adopt`) has not been extended for `objectPro`'s own
 `<object id>#<animation group id>` remote-id scheme yet, unlike `character`'s
@@ -440,12 +443,13 @@ plain `revision` (image-to-image) of the base panel, which already carries
 this for every other generator.
 
 **Cost: confirmed live at one data point — 20 generations for a 256x192
-canvas**, the low end of the `create_ui_asset` MCP tool's "20–40
-generations" claim. PixelKiln still estimates with the same canvas-tier
-formula as `1dir`/`tiles`, which predicts the 40 ceiling for every valid
-`uiAsset` size (its 192px floor is already past that formula's top tier) —
-the measured call proves the formula wrong here, since it billed the floor
-price at an area well above where `1dir`/`tiles` would bill the ceiling.
+canvas**, the low end of the `create_ui_asset` MCP tool's then "20–40
+generations" claim (before PixelLab's October 2026 cut to 10–25). PixelKiln
+still estimates with the same canvas-tier formula as `1dir`/`tiles`, which
+predicts the 25 ceiling for every valid `uiAsset` size (its 192px floor is
+already past that formula's top tier) — the measured call proves the
+formula wrong here, since it billed the floor price at an area well above
+where `1dir`/`tiles` would bill the ceiling.
 Left as an over-read for `--budget` until a second size is measured; see
 [ENDPOINTS.md](./ENDPOINTS.md) for the full writeup.
 
@@ -529,15 +533,20 @@ to 16×16, which suits icons and small widgets:
 - `uiColorPalette` is sent as `color_palette`, the same free-text hint
   `uiAsset` takes. PixelLab removes the background by default; set
   `noBackground: false` on the style to keep it.
-- One call is expected to return one image, recorded straight away. If the
-  endpoint ever returns several, they go to candidate review like
-  `imagePro`'s.
-
-**Unmeasured.** The schema carries no usage example and no call has been
-billed yet. The plan prices it on the same 10/15/25 canvas tiers as
-`1dir`/`tiles`, the safe over-read for a Pro endpoint, and the completed
-job's shape is read defensively (`pollUiElement` names the keys it got if
-the shape is not the documented `images` list).
+- A small element returns many candidates (64 at 32×32, measured), which go
+  to candidate review like `imagePro`'s; a call that returns one image is
+  recorded straight away.
+
+**Cost: measured once.** A 32×32 call billed 10 live (November 2026, Tier 3)
+and the review page showed **64 candidates** at 32×32, which the plan said as
+1 until it followed the `/generate-image-v2` size tiers (`uiElementCandidateCount`:
+64 up to 32px, 49 at 33–35, 36 at 36–41, 25 at 42–50, 16 at 51–64, 9 at
+65–84, 16 at 85, 4 at 86–170, 1 above). Only the 32px point is a bill; the
+other bands are PixelLab's published grid. A size with more than one candidate
+goes to review. The plan prices the canvas on the 10/15/25 tiers as
+`1dir`/`tiles` do; other sizes are unbilled, and the completed job's shape
+is still read defensively (`pollUiElement` names the keys it got if the shape
+is not the documented `images` list).
 
 ## `vfx`
 

package/docs/PIXELLAB.md

@@ -77,9 +77,9 @@ unapproved files. See [Manifest quality profiles](./MANIFEST.md#quality-profiles
 | `imageProFlash` | You need a still on the Pro Flash model, optionally styled from one image, 16 to 256px | 5 to 9 generations (provisional quote) |
 | `vfx` | You need an animated effect (spell, hit, explosion, aura), on its own or around a sprite | free from presets and parts; 1 to 28 when described to PixelLab's artist (lite measured at 1) |
 | `character` | You need a character in 4 or 8 directions, with states, loops, portraits, or outfits | See [Characters](./CHARACTERS.md) |
-| `objectPro` | You need a prop or creature with rotations, states, or loops but no character rig | about 6 at 64px (unmeasured) |
+| `objectPro` | You need a prop or creature with rotations, states, or loops but no character rig | 6 per base (measured at 32px) |
 | `uiAsset` | You need a UI panel composited from pieces and named elements, 192px and up | 20 generations (measured once) |
-| `uiElement` | You need one UI element from a description, 16px and up | 10 to 25 generations (unmeasured) |
+| `uiElement` | You need one UI element from a description, 16px and up | 10 to 25 generations (a 32×32 call billed 10) |
 
 `map` accepts these values:
 
@@ -139,9 +139,10 @@ joints, and `skeleton-preview` draws them over the sprite before you spend:
 - Each billed exactly 3 generations for 8 frames, measured live. The sentence
   loop came back at 96×96 from a 64px character; the posed one stayed 64×64.
   [The home page](https://pixelkiln.griffen.codes/#updates) shows both.
-- Each direction of a sentence loop is its own request for now, so a loop with
-  several directions can move a little differently in each. PixelLab can draw
-  every direction from one motion, but PixelKiln does not send that yet.
+- Each direction of a sentence loop is its own request, but the first
+  direction leads and every later one is sent into its animation group, so all
+  directions are drawn from one motion (a live append billed 3 and joined the
+  group).
 
 See [Loops from a sentence](./CHARACTERS.md#loops-from-a-sentence) and
 [Skeleton-driven animation](./REVISIONS.md#skeleton-driven-animation).

package/docs/REVISIONS.md

@@ -400,17 +400,20 @@ review** first (`pixelkiln pick`), not straight to downloadable output; there
 is no per-candidate choice to make (it is one ordered set, previewed as a
 loop), just accept or reject the whole thing.
 
-**Neither endpoint's completed-job response shape has been exercised against
-a live account.** The request fields above come from PixelLab's live OpenAPI
-document; the shape of a *finished* job (which key holds the frame list, and
-whether it's hosted URLs or inline base64) is an informed guess checked
-against several plausible shapes (see `pollAnimateRevision` in
-`src/providers/pixellab.ts`), the same defensive posture `pollRevision`
-already takes for `image-to-image`/`inpaint`. Cost is likewise unmeasured:
-`estimate()` borrows `character`'s own measured v3-loop formula
+**Both endpoints ran live in November 2026 (Tier 3), and every completed job
+was read correctly.** A 64×64 `animate` of 4 frames billed 1 and returned 5
+frames at 64×64; a 64×64 `animate-pixminimax` billed 1 at 8 frames (9 frames
+back) and 2 at 16 frames (17 back). PixelLab includes the input frame in the
+set, so a set holds the requested count plus one. `pollAnimateRevision` still
+checks several plausible field names defensively rather than assume one.
+Cost: `animate` borrows `character`'s measured v3-loop formula
 (`ceil(width × height × frames / 65536)`, since the request shapes are
-near-identical) as a placeholder, plus `enhancePrompt`'s own documented
-+0.05-generation surcharge, which is a real schema number rather than a guess.
+near-identical), which matched the one bill; `animate-pixminimax` follows
+PixelLab's published table (64×64 at 4 / 8 / 16 / 40 frames costs 1 / 1 / 2 /
+6), because that formula read the 16-frame clip as 1 against a bill of 2 (see
+`pixMiniMaxCost`; 40 frames is the published number, not a bill). Both add
+`enhancePrompt`'s documented +0.05-generation surcharge. Other sizes and
+frame counts are unbilled.
 
 ### Interpolate between two keyframes
 
@@ -468,10 +471,12 @@ time.
 
 `interpolate` and `edit-animation` land in candidate review like `animate`,
 take `fps` (defaulting to the parent's own rate when it has one, else 8), and
-reject `strength`. Neither has been exercised against a live account: request
-fields come from PixelLab's live OpenAPI document, the completed job is read
-by the same defensive frame-list lookup `animate` uses, and cost is an
-estimate (see [PixelLab](#pixellab) below).
+reject `strength`. Both ran live in November 2026 (Tier 3) and the completed
+job was read correctly by the same frame-list lookup `animate` uses: a 64×64
+`interpolate` with a `lastFrame` keyframe billed 10 and returned 14 frames at
+64×64, and an `edit-animation` of a 9-frame 64×64 set billed 10. The plan
+now prices them at those 10 (it used to read 25). Larger canvases are
+unbilled (see [PixelLab](#pixellab) below).
 
 ComfyUI supports none of the four frame-set modes: its revision path always
 writes a single output image, and an animation is a frame set — a structural
@@ -545,7 +550,7 @@ calls it directly, but nothing in `resolveSpecs`/`estimate()`/`submitRevision`
 ever calls it — planning stays offline by construction (the keypoints file is
 read like any other manifest input, never a network call), and the only
 PixelLab endpoint `animate-skeleton`'s submission composes is
-`animate-with-skeleton-v3` itself, not two never-tested-live calls chained
+`animate-with-skeleton-v3` itself, not two endpoints chained
 together. A future pipeline stage that budgets and tracks `estimate-skeleton`
 calls the way `gen` does everything else is tracked separately, once this
 mode has shipped and seen real use.
@@ -698,33 +703,33 @@ further — there is nothing to ask.
   image; a whole member set is still one call, but whether its price stays
   flat is unmeasured.
 - `interpolate` (`/interpolation-v2`) and `edit-animation`
-  (`/edit-animation-v2`) are both documented "Pro" endpoints with no usage
-  example in the schema and no live measurement. `estimate()` borrows the
-  same 10/15/25 canvas tiers the other unmeasured Pro edits use, sized on the
-  keyframe for `interpolate` and on the packed frame grid for
-  `edit-animation` (four 32×32 frames price as a 64×64 canvas, the 40 tier).
-  Over-reading is the safe direction for `--budget`; expect a live bill at or
-  below the plan.
+  (`/edit-animation-v2`) are "Pro" endpoints and bill on the 10/15/25 canvas
+  ladder (`proTierCost`: 10 up to 65536px², 15 up to 102400px², 25 above).
+  `estimate()` sizes the canvas on the keyframe for `interpolate` and on the
+  packed frame grid for `edit-animation` (nine 64×64 frames pack into
+  192×192). Measured live in November 2026: a 64×64 `interpolate` and a
+  9-frame 64×64 `edit-animation` each billed 10, where the plan used to say
+  25. Larger canvases are unbilled and follow the same ladder; over-reading
+  is the safe direction for `--budget`.
 - `animate` calls `/animate-with-text-v3`, `animate-pixminimax` calls
   `/animate-pixminimax` — both real async background jobs, unlike the two
   Cleanup-tier modes above, since they generate new frames rather than
   transform the source. Both take at most 256 pixels per side; `animate`
   additionally caps at 16 frames (`animate-pixminimax` allows up to 40). See
   [Animation and interpolation](#animation-and-interpolation) above for the
-  full field list, the frame-set output shape, and its own (still unmeasured)
-  cost caveat — unlike the Cleanup tier above, neither `animate` nor
-  `animate-pixminimax` has been exercised against a live account yet, and the
-  request/response shapes come from PixelLab's live OpenAPI document, not an
-  observed call. Treat the exact field names as provisional until a real
-  call confirms them.
+  full field list, the frame-set output shape, and the live bills: both ran
+  live in November 2026 (64×64 `animate` at 4 frames billed 1; `animate-pixminimax`
+  at 8 and 16 frames billed 1 and 2), and the completed jobs were read
+  correctly.
 - `animate-skeleton` calls `/animate-with-skeleton-v3`, also a real async
   background job, at most 256 pixels per side and 3-15 frames (the frame
   count comes from `keypointsFile`, not a manifest field). See
   [Skeleton-driven animation](#skeleton-driven-animation) above for the full
   field list, the `keypointsFile` shape, and the `estimateSkeleton`
-  CLI-only-and-never-in-the-submission-path decision. Same unverified-live
-  caveat as `animate`/`animate-pixminimax`, sourced from the live
-  `animate_with_skeleton_v3` MCP tool schema rather than an observed call.
+  CLI-only-and-never-in-the-submission-path decision. Unlike
+  `animate`/`animate-pixminimax`, it has run live: an 8-frame revision billed
+  exactly 3 generations (see that section); its field names came from the
+  `animate_with_skeleton_v3` MCP tool schema.
 - `normal-map` calls `/normal-map` (PixelLab 0.4.130), a background job whose
   map is `last_response.image`; a loop's frames go and come back as one
   horizontal strip, cut into per-frame files on poll. See

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pixelkiln",
-  "version": "0.92.1",
+  "version": "0.92.3",
   "description": "Manifest-driven pixel-art generation, review, recovery, and packaging with deterministic provenance.",
   "type": "module",
   "sideEffects": false,

package/skills/pixelkiln/references/pixellab-fidelity.md

@@ -46,7 +46,8 @@ Two engine-specific data points worth the same treatment:
   pro engine at the same canvas ("even at 256×256, we can generate eight
   animation frames, which we didn't have before even with the pro tools") —
   consistent with pixelkiln's documented `character` cost model, where v3
-  scales `ceil(size²×8/65536)` and pro sits in the flat 20–40 tier regardless.
+  scales `ceil(size²×8/65536)` and pro sits in the flat 10–25 tier regardless (20–40 before PixelLab's
+  October 2026 cut).
   Prefer v3 over pro for a loop unless pro's quality is specifically needed.
 - `portrait-character-pro` (not part of this adapter) renders sizes 128 and
   160 at "2K" internal resolution versus "1K" for 16–64, at a measured cost