@oh-my-pi/snapcompact 15.12.4 → 15.13.0

package/CHANGELOG.md

@@ -2,16 +2,14 @@
 
 ## [Unreleased]
 
-## [15.12.1] - 2026-06-12
-
-### Changed
-
-- `serializeConversation` now skips tool call/result pairs whose result is flagged contextually useless (`useless: true`, non-error), so archived frames stop carrying zero-match searches and timed-out waits
+### Breaking Changes
 
-## [15.11.7] - 2026-06-12
+- Renamed every export to drop the `snapcompact`/`Snapcompact`/`SNAPCOMPACT_` qualifier — the package is meant to be consumed via `import * as snapcompact from "@oh-my-pi/snapcompact"`. Functions: `snapcompactCompact` → `compact`, `renderSnapcompactFrame` → `render`, `snapcompactGeometry` → `geometry`, `normalizeForSnapcompact` → `normalize`, `serializeSnapcompactConversation` → `serializeConversation`, `snapcompactImages` → `images`, `getPreservedSnapcompactArchive` → `getPreservedArchive`, `isSnapcompactShape` → `isShape`, `resolveSnapcompactShape` → `resolveShape`, `createSnapcompactFileOps` → `createFileOps`, `computeSnapcompactFileLists` → `computeFileLists`, `upsertSnapcompactFileOperations` → `upsertFileOperations`. Types: `SnapcompactShape` → `Shape`, `SnapcompactFrame` → `Frame`, `SnapcompactArchive` → `Archive`, `SnapcompactGeometry` → `Geometry`, `SnapcompactOptions` → `Options`, `SnapcompactSerializeOptions` → `SerializeOptions`, `SnapcompactFileOperations` → `FileOperations`, `SnapcompactCompactionDetails`/`Preparation`/`Result` → `CompactionDetails`/`CompactionPreparation`/`CompactionResult`, `SnapcompactConvertToLlm` → `ConvertToLlm`. Constants: `SNAPCOMPACT_X` → `X` (`SHAPES`, `FRAME_SIZE`, `MAX_FRAMES`, `FRAME_TOKEN_ESTIMATE`, `PRESERVE_KEY`, `TOOL_RESULT_MAX_CHARS`, `TOOL_ARG_MAX_CHARS`, `TOOL_CALL_MAX_CHARS`, `TRUNCATE_HEAD_RATIO`, `DIM_ON`, `DIM_OFF`).
+- Changed `renderSnapcompactFrame` output from `png: Uint8Array` to `data: string` base64, requiring consumers to read frame payloads from `frame.data`
 
 ### Added
 
+- Added two spacing-tuned frame variants to `SHAPE_VARIANTS`: `8on22-bw` (8x13 glyphs on a 22px pitch — extra line spacing) and `11on16-bw` (8x13 glyphs on an 11px advance — extra letter spacing). Both pin the indexed `stretch: false` path, so the native renderer draws natural-size glyphs on the padded cell box (the Rust path already advances by `cellWidth` and the new variants validate horizontal padding)
 - Added `SHAPE_VARIANTS`, the catalog of research-eval frame variants the native renderer reproduces faithfully (`8x8r`/`8x8u`/`6x6u`/`5x8` × `sent`/`bw`), with `ShapeVariantName`, `SHAPE_VARIANT_NAMES`, and the `isShapeVariantName` guard
 - `resolveShape(api, variant?)` now accepts an explicit variant name (or `"auto"`); forced variants keep their geometry but are re-priced for the target provider's image billing (token estimate and OpenAI `original` detail hint)
 - Added the six research-eval winning frame variants to `SHAPE_VARIANTS`: `6x12-dim` (Claude fable), `8x13-bw` (Opus), `8on16-bw` (GPT grid runner-up), `doc-8on16-bw` (GPT), `doc-8on16-sent` (GLM), and `doc-8on16-sent-dim` (Gemini/Kimi), backed by new `Shape` fields `stretch` (disable Lanczos stretch: natural glyphs on a larger cell pitch), `columns` (two word-wrapped newspaper columns), `stopwordDim`, and the X.org `6x12`/`8x13` fonts
@@ -20,34 +18,7 @@
 - `resolveShape` now also resolves an ideal **frame size** per model line, and billing estimates come from verified per-family formulas instead of flat 1568px constants: Anthropic bills 28px patches capped at 4,784 visual tokens (+5% margin), Gemini 3.x bills a fixed 1,120-token `media_resolution` budget per image at any pixel size, and OpenAI bills 32px patches × 1.2 under the 10,000-patch `detail: "original"` budget. High-res Claude lines (Opus 4.7+, Fable, Mythos — native 2576px-edge ingestion) get 1932px frames (same recall and cost, a third fewer frames); Gemini gets 2048px frames (+70% chars per frame at the same bill); GPT and Kimi stay at 1568px (area-proportional billing and a model-side 1792px processor cap, respectively). `idealShapeVariant` now returns an `IdealShape` (`{ variant, frameSize? }`)
 - Added per-provider image-count budgets: `PROVIDER_IMAGE_BUDGETS`, `DEFAULT_PROVIDER_IMAGE_BUDGET`, `providerImageBudget()`, and `providerFrameBudget()` (the image budget clamped to `MAX_FRAMES`). OpenRouter is capped at its measured hard limit of 8 images per request (excess images are silently dropped with no error); unknown providers get a safe floor of 5
 - Added `Archive.textTail`: archive content past the frame budget is no longer dropped — `compact()` stops rendering at the budget and keeps the newest unframed slice as verbatim text on the summary (capped at two frame capacities with middle elision, counted into `truncatedChars` when elided). The tail persists in `preserveData` and is folded back into frames by the next compaction
-
-### Changed
-
-- Frames are no longer padded to a square: the native renderer clips each PNG's height to the text rows actually printed, so a partially filled frame (typically the newest) bills only the pixel rows it uses
-- **Changed the OpenAI default shape from `6x6u-sent` to `8on16-bw`.** A production-regime mono eval (gpt-5.5, the full 800k-char SQuAD flow in one request, n=50) scored the old dense default f1 .602 vs .851 for `8on16-bw` rendered by the production pipeline, at near-equal total cost (the dense cells burned the frame savings on reasoning tokens); chunked exp14 had already scored `8on16-bw` .906. `SHAPES.openaiDense` is renamed to `SHAPES.openai`
-- **Changed the Google default shape from `8x8r-sent` to `doc-8on16-sent-dim`.** Production-rendered mono eval on gemini-3.5-flash (400k chars, one request, n=25): f1 .900 vs .853 for the repeated grid at lower cost, agreeing with the chunked round-2 winner
-- **Changed the Anthropic default shape from `8x8r-bw` to `6x12-dim`.** Production mono eval on claude-fable (400k chars, one request, n=25): f1 .840 vs .877 for the repeated grid — within noise — at 37% lower cost (12 frames instead of 21 per 400k chars), with clean completions in every probe; opus reads the same trade (.800 vs .833 at 42% lower cost)
-- `normalize()` now keeps line structure: whitespace runs containing a line break collapse to `NEWLINE_GLYPH` (U+2588 FULL BLOCK, drawn by the native renderer as a pitch-black cell one character wide) instead of a plain space; leading/trailing breaks are trimmed, and the frame-reading prompt explains the marker
-- `normalize()` now skips characters the fonts cannot render instead of printing `?` blanks: whole ANSI escape sequences are stripped, and bare control characters, zero-width format characters (ZWSP, BOM, directional marks), combining marks, and lone surrogates are dropped without occupying a cell; `?` remains the fallback for unsupported graphic characters only
-
-## [15.11.4] - 2026-06-12
-
-### Breaking Changes
-
-- Renamed every export to drop the `snapcompact`/`Snapcompact`/`SNAPCOMPACT_` qualifier — the package is meant to be consumed via `import * as snapcompact from "@oh-my-pi/snapcompact"`. Functions: `snapcompactCompact` → `compact`, `renderSnapcompactFrame` → `render`, `snapcompactGeometry` → `geometry`, `normalizeForSnapcompact` → `normalize`, `serializeSnapcompactConversation` → `serializeConversation`, `snapcompactImages` → `images`, `getPreservedSnapcompactArchive` → `getPreservedArchive`, `isSnapcompactShape` → `isShape`, `resolveSnapcompactShape` → `resolveShape`, `createSnapcompactFileOps` → `createFileOps`, `computeSnapcompactFileLists` → `computeFileLists`, `upsertSnapcompactFileOperations` → `upsertFileOperations`. Types: `SnapcompactShape` → `Shape`, `SnapcompactFrame` → `Frame`, `SnapcompactArchive` → `Archive`, `SnapcompactGeometry` → `Geometry`, `SnapcompactOptions` → `Options`, `SnapcompactSerializeOptions` → `SerializeOptions`, `SnapcompactFileOperations` → `FileOperations`, `SnapcompactCompactionDetails`/`Preparation`/`Result` → `CompactionDetails`/`CompactionPreparation`/`CompactionResult`, `SnapcompactConvertToLlm` → `ConvertToLlm`. Constants: `SNAPCOMPACT_X` → `X` (`SHAPES`, `FRAME_SIZE`, `MAX_FRAMES`, `FRAME_TOKEN_ESTIMATE`, `PRESERVE_KEY`, `TOOL_RESULT_MAX_CHARS`, `TOOL_ARG_MAX_CHARS`, `TOOL_CALL_MAX_CHARS`, `TRUNCATE_HEAD_RATIO`, `DIM_ON`, `DIM_OFF`).
-
-### Added
-
 - Added `renderMany()` for paging arbitrary text into snapcompact PNG frames as LLM image blocks, and `frames()` for predicting the frame count without rendering
-
-## [15.11.0] - 2026-06-10
-
-### Breaking Changes
-
-- Changed `renderSnapcompactFrame` output from `png: Uint8Array` to `data: string` base64, requiring consumers to read frame payloads from `frame.data`
-
-### Added
-
 - Added new serialization options `toolResultMaxChars`, `toolArgMaxChars`, `toolCallMaxChars`, `truncateHeadRatio`, and `dimToolResults` to `snapcompactCompact`/`serializeSnapcompactConversation` so callers can tune how tool results and arguments are archived
 - Added exported default constants `SNAPCOMPACT_TOOL_RESULT_MAX_CHARS`, `SNAPCOMPACT_TOOL_ARG_MAX_CHARS`, `SNAPCOMPACT_TOOL_CALL_MAX_CHARS`, and `SNAPCOMPACT_TRUNCATE_HEAD_RATIO` for reuse when configuring truncation limits
 - Added provider-specific snapcompact frame-shape presets and shape helpers (`SNAPCOMPACT_SHAPES`, `resolveSnapcompactShape`, `isSnapcompactShape`) so callers can consistently select validated image-frame geometry for archive renders
@@ -58,6 +29,14 @@
 
 ### Changed
 
+- **Changed the per-provider default shapes to the spacing-tuned cells.** The previous shapes were tuned on the SQuAD *prose* eval, where dense cells won; a new tool-result legibility benchmark (`research/toolbench.py` — real `search`/`read`/`find` output with structure-sensitive QA) showed the prose-era density erases the line numbers and indentation that code/search output depends on. Anthropic moves from `6x12-dim` to `11on16-bw` (opus-4.8 f1 .806 vs .755 for plain `8on16-bw` and .351 for `6x12-dim`, which fell below the OCR ~16px/char floor and abstained); OpenAI and Google move to `8on22-bw` (gemini-3.5-flash f1 .934 vs .807 for `8on16-bw` and .287 for `doc-8on16-sent-dim`; same leading win on gpt-5.5/gpt-5.4-mini). Kimi and GLM keep their measured `8on16-bw`. The bigger cells pack fewer chars per frame, so inline frame-swapping now breaks even at a larger tool-result size
+- `serializeConversation` now skips tool call/result pairs whose result is flagged contextually useless (`useless: true`, non-error), so archived frames stop carrying zero-match searches and timed-out waits
+- Frames are no longer padded to a square: the native renderer clips each PNG's height to the text rows actually printed, so a partially filled frame (typically the newest) bills only the pixel rows it uses
+- **Changed the OpenAI default shape from `6x6u-sent` to `8on16-bw`.** A production-regime mono eval (gpt-5.5, the full 800k-char SQuAD flow in one request, n=50) scored the old dense default f1 .602 vs .851 for `8on16-bw` rendered by the production pipeline, at near-equal total cost (the dense cells burned the frame savings on reasoning tokens); chunked exp14 had already scored `8on16-bw` .906. `SHAPES.openaiDense` is renamed to `SHAPES.openai`
+- **Changed the Google default shape from `8x8r-sent` to `doc-8on16-sent-dim`.** Production-rendered mono eval on gemini-3.5-flash (400k chars, one request, n=25): f1 .900 vs .853 for the repeated grid at lower cost, agreeing with the chunked round-2 winner
+- **Changed the Anthropic default shape from `8x8r-bw` to `6x12-dim`.** Production mono eval on claude-fable (400k chars, one request, n=25): f1 .840 vs .877 for the repeated grid — within noise — at 37% lower cost (12 frames instead of 21 per 400k chars), with clean completions in every probe; opus reads the same trade (.800 vs .833 at 42% lower cost)
+- `normalize()` now keeps line structure: whitespace runs containing a line break collapse to `NEWLINE_GLYPH` (U+2588 FULL BLOCK, drawn by the native renderer as a pitch-black cell one character wide) instead of a plain space; leading/trailing breaks are trimmed, and the frame-reading prompt explains the marker
+- `normalize()` now skips characters the fonts cannot render instead of printing `?` blanks: whole ANSI escape sequences are stripped, and bare control characters, zero-width format characters (ZWSP, BOM, directional marks), combining marks, and lone surrogates are dropped without occupying a cell; `?` remains the fallback for unsupported graphic characters only
 - Changed truncation in archived tool output to keep both the beginning and end of long text using a configurable head/tail ratio instead of a single hard cut
 - Changed tool-result text rendering so archived tool results are shown in dim gray ink by default and the summary prompt notes that dim text is archived tool output
 - Changed `RenderedFrame` visible-character accounting so `chars` no longer includes invisible dim-control markers
@@ -67,3 +46,13 @@
 
 - Fixed frame rendering at archive chunk boundaries to reopen dim spans when a chunk ends inside a dimmed tool-result segment
 - Fixed message serialization to strip user- and assistant-provided dim markers so only renderer-generated dim spans can be applied
+
+## [15.13.0] - 2026-06-14
+
+## [15.12.1] - 2026-06-12
+
+## [15.11.7] - 2026-06-12
+
+## [15.11.4] - 2026-06-12
+
+## [15.11.0] - 2026-06-10

package/dist/types/snapcompact.d.ts

@@ -7,25 +7,28 @@
  * reader. Frames are `frameSize` wide; their height hugs the text rows
  * actually printed, so a partially filled frame never bills blank rows.
  *
- * The frame shape is provider-aware, following the snapcompact SQuAD evals
- * (`packages/snapcompact`, 200k-token monolithic runs):
+ * The frame shape is provider-aware. Original choices came from the SQuAD
+ * prose evals (`packages/snapcompact`, 200k-token monolithic runs); the
+ * spacing choices below come from the tool-result legibility bench
+ * (`research/toolbench.py`, real search/read/find output with structure QA),
+ * which exposed that the prose-tuned dense cells erase the line numbers and
+ * indentation that code/search output depends on:
  *
- * - **Anthropic** (`6x12-dim`): X.org 6x12 glyphs, black ink, stopwords
- *   dimmed gray — recall within noise of the repeated `8x8r-bw` grid at
- *   ~40% lower cost; `8x8r-bw` remains the max-recall choice via the shape
- *   setting. Opus 4.7+/Fable/Mythos ingest high-res natively (2576px edge,
- *   4,784 visual-token cap, no flag needed), so those lines get 1932px
- *   frames: same recall and cost, a third fewer frames. Older Claude lines
- *   downscale past 1568px and keep the standard frame.
- * - **Google** (`doc-8on16-sent-dim` @2048): two word-wrapped newspaper
- *   columns of 8x13 glyphs, sentence-hue ink, dimmed stopwords. Gemini 3.x
- *   bills a fixed `media_resolution` budget per image (default 1,120
- *   tokens) regardless of pixels, so the 2048px frame carries +70% chars at
- *   the same bill (f1 .88 vs .90 at 1568). `ULTRA_HIGH` doubles the budget
- *   and reads 3072px frames, but loses on chars/$ — deliberately unused.
- * - **OpenAI** (`8on16-bw`): 8x13 glyphs on a patch-aligned 16px pitch,
- *   black ink (gpt-5.5 mono F1 .867 vs .602 for the previous `6x6u-sent`).
- *   Patch billing (32px × 1.2, 10k-patch budget at `detail: "original"`) is
+ * - **Anthropic** (`11on16-bw`): 8x13 glyphs on an 11px advance (extra
+ *   letter-spacing), black ink. On the tool-result bench, tracking the
+ *   readable cell beat plain `8on16-bw` (opus-4.8 f1 .806 vs .755) and far
+ *   beat the prior dense `6x12-dim` (.351, which fell below the OCR ~16px/char
+ *   floor and abstained). Opus 4.7+/Fable/Mythos ingest high-res natively
+ *   (2576px edge, 4,784 visual-token cap), so those lines get 1932px frames:
+ *   same bill, fewer frames. Older Claude lines downscale past 1568px.
+ * - **Google** (`8on22-bw` @2048): 8x13 glyphs on a 22px pitch (extra line
+ *   spacing), black ink. Leading lifted gemini-3.5-flash to f1 .934 vs .807
+ *   for `8on16-bw` and .287 for the prior `doc-8on16-sent-dim`. Gemini 3.x
+ *   bills a fixed `media_resolution` budget per image (default 1,120 tokens)
+ *   regardless of pixels, so the 2048px frame carries more chars at the same
+ *   bill.
+ * - **OpenAI** (`8on22-bw`): same leading win (gpt-5.5/gpt-5.4-mini). Patch
+ *   billing (32px × 1.2, 10k-patch budget at `detail: "original"`) is
  *   area-proportional, so resolution cannot improve chars/$ — 1568 stays.
  *   `detail: "high"` would downgrade (2,500-patch cap); `original` is sent.
  * - **Unknown providers** default to the Anthropic shape. Gateways can
@@ -82,9 +85,11 @@ export type ShapeGeometry = Omit<Shape, "frameTokenEstimate" | "imageDetail">;
  * (redundancy coding), `6x6u` unscii Lanczos-squeezed to 6x6 (densest
  * readable cell), `5x8` the X.org legacy font on its 2576px frame, `6x12`
  * and `8x13` the X.org misc fonts, `8on16` 8x13 glyphs on an 8x16 cell pitch
- * (no stretch, extra leading), `doc-` prefixed shapes a two-column
- * word-wrapped newspaper layout. Ink: `sent` cycles six hues at sentence
- * boundaries, `bw` is plain black, `-dim` suffix prints stopwords in gray.
+ * (no stretch, extra leading), `8on22` the same glyphs on a 22px pitch (more
+ * leading), `11on16` the same glyphs on an 11px advance (more tracking),
+ * `doc-` prefixed shapes a two-column word-wrapped newspaper layout. Ink:
+ * `sent` cycles six hues at sentence boundaries, `bw` is plain black, `-dim`
+ * suffix prints stopwords in gray.
  */
 export declare const SHAPE_VARIANTS: {
     readonly "8x8r-bw": {
@@ -177,6 +182,24 @@ export declare const SHAPE_VARIANTS: {
         readonly lineRepeat: 1;
         readonly frameSize: 1568;
     };
+    readonly "8on22-bw": {
+        readonly font: "8x13";
+        readonly cellWidth: 8;
+        readonly cellHeight: 22;
+        readonly stretch: false;
+        readonly variant: "bw";
+        readonly lineRepeat: 1;
+        readonly frameSize: 1568;
+    };
+    readonly "11on16-bw": {
+        readonly font: "8x13";
+        readonly cellWidth: 11;
+        readonly cellHeight: 16;
+        readonly stretch: false;
+        readonly variant: "bw";
+        readonly lineRepeat: 1;
+        readonly frameSize: 1568;
+    };
     readonly "doc-8on16-bw": {
         readonly font: "8x13";
         readonly cellWidth: 8;
@@ -217,19 +240,20 @@ export declare const SHAPE_VARIANT_NAMES: readonly ShapeVariantName[];
 export declare function isShapeVariantName(value: unknown): value is ShapeVariantName;
 /** Eval-validated shapes, keyed by the provider family they won on. */
 export declare const SHAPES: {
-    /** `6x12-dim`: X.org 6x12 glyphs, black ink with stopwords dimmed gray.
-     *  Production mono eval on claude-fable: f1 .840 vs .877 for the repeated
-     *  `8x8r-bw` grid (within noise at n=25) at 37% lower cost — 12 frames
-     *  instead of 21 per 400k chars. Never refused in any run. */
+    /** `11on16-bw`: 8x13 glyphs on an 11px advance (extra tracking), black ink.
+     *  Tool-result legibility bench (real search/read/find output, structure QA)
+     *  on opus-4.8: f1 .806 vs .755 for plain `8on16-bw` and .351 for the prior
+     *  `6x12-dim` default — letter-spacing the readable cell wins; the dense
+     *  6x12 was below the OCR ~16px/char floor and abstained. */
     anthropic: Shape;
-    /** `doc-8on16-sent-dim`: two word-wrapped columns, sentence hues, dimmed
-     *  stopwords. Production mono eval on gemini-3.5-flash: f1 .900 vs .853
-     *  for the repeated grid, at lower cost; also the chunked round-2 winner. */
+    /** `8on22-bw`: 8x13 glyphs on a 22px pitch (extra leading), black ink.
+     *  Tool-result legibility bench on gemini-3.5-flash: f1 .934 vs .807 for
+     *  plain `8on16-bw` and .287 for the prior `doc-8on16-sent-dim`; the
+     *  line-spacing reduces row crowding so line numbers stay legible. */
     google: Shape;
-    /** `8on16-bw`: 8x13 X.org glyphs on a 16px pitch, black ink. Mono eval on
-     *  gpt-5.5 (200k-token single request, n=50): f1 .851 vs .602 for the
-     *  previous `6x6u-sent` default at near-equal total cost; chunked exp14
-     *  scored it .906. */
+    /** `8on22-bw`: 8x13 glyphs on a 22px pitch (extra leading), black ink.
+     *  Same line-spacing win for OpenAI; bench on gpt-5.5/gpt-5.4-mini showed
+     *  leading lifts recall on the readable cell over plain `8on16-bw`. */
     openai: Shape;
     /** Original 5x8 X.org shape (pre-shape-table sessions rendered this). */
     legacy: Shape;

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/snapcompact",
-	"version": "15.12.4",
+	"version": "15.13.0",
 	"description": "Bitmap-frame context compression for vision-capable LLMs",
 	"homepage": "https://omp.sh",
 	"author": "Can Boluk",
@@ -31,9 +31,9 @@
 		"fmt": "biome format --write ."
 	},
 	"dependencies": {
-		"@oh-my-pi/pi-ai": "15.12.4",
-		"@oh-my-pi/pi-natives": "15.12.4",
-		"@oh-my-pi/pi-utils": "15.12.4"
+		"@oh-my-pi/pi-ai": "15.13.0",
+		"@oh-my-pi/pi-natives": "15.13.0",
+		"@oh-my-pi/pi-utils": "15.13.0"
 	},
 	"devDependencies": {
 		"@types/bun": "^1.3.14"

package/src/snapcompact.ts

@@ -7,25 +7,28 @@
  * reader. Frames are `frameSize` wide; their height hugs the text rows
  * actually printed, so a partially filled frame never bills blank rows.
  *
- * The frame shape is provider-aware, following the snapcompact SQuAD evals
- * (`packages/snapcompact`, 200k-token monolithic runs):
+ * The frame shape is provider-aware. Original choices came from the SQuAD
+ * prose evals (`packages/snapcompact`, 200k-token monolithic runs); the
+ * spacing choices below come from the tool-result legibility bench
+ * (`research/toolbench.py`, real search/read/find output with structure QA),
+ * which exposed that the prose-tuned dense cells erase the line numbers and
+ * indentation that code/search output depends on:
  *
- * - **Anthropic** (`6x12-dim`): X.org 6x12 glyphs, black ink, stopwords
- *   dimmed gray — recall within noise of the repeated `8x8r-bw` grid at
- *   ~40% lower cost; `8x8r-bw` remains the max-recall choice via the shape
- *   setting. Opus 4.7+/Fable/Mythos ingest high-res natively (2576px edge,
- *   4,784 visual-token cap, no flag needed), so those lines get 1932px
- *   frames: same recall and cost, a third fewer frames. Older Claude lines
- *   downscale past 1568px and keep the standard frame.
- * - **Google** (`doc-8on16-sent-dim` @2048): two word-wrapped newspaper
- *   columns of 8x13 glyphs, sentence-hue ink, dimmed stopwords. Gemini 3.x
- *   bills a fixed `media_resolution` budget per image (default 1,120
- *   tokens) regardless of pixels, so the 2048px frame carries +70% chars at
- *   the same bill (f1 .88 vs .90 at 1568). `ULTRA_HIGH` doubles the budget
- *   and reads 3072px frames, but loses on chars/$ — deliberately unused.
- * - **OpenAI** (`8on16-bw`): 8x13 glyphs on a patch-aligned 16px pitch,
- *   black ink (gpt-5.5 mono F1 .867 vs .602 for the previous `6x6u-sent`).
- *   Patch billing (32px × 1.2, 10k-patch budget at `detail: "original"`) is
+ * - **Anthropic** (`11on16-bw`): 8x13 glyphs on an 11px advance (extra
+ *   letter-spacing), black ink. On the tool-result bench, tracking the
+ *   readable cell beat plain `8on16-bw` (opus-4.8 f1 .806 vs .755) and far
+ *   beat the prior dense `6x12-dim` (.351, which fell below the OCR ~16px/char
+ *   floor and abstained). Opus 4.7+/Fable/Mythos ingest high-res natively
+ *   (2576px edge, 4,784 visual-token cap), so those lines get 1932px frames:
+ *   same bill, fewer frames. Older Claude lines downscale past 1568px.
+ * - **Google** (`8on22-bw` @2048): 8x13 glyphs on a 22px pitch (extra line
+ *   spacing), black ink. Leading lifted gemini-3.5-flash to f1 .934 vs .807
+ *   for `8on16-bw` and .287 for the prior `doc-8on16-sent-dim`. Gemini 3.x
+ *   bills a fixed `media_resolution` budget per image (default 1,120 tokens)
+ *   regardless of pixels, so the 2048px frame carries more chars at the same
+ *   bill.
+ * - **OpenAI** (`8on22-bw`): same leading win (gpt-5.5/gpt-5.4-mini). Patch
+ *   billing (32px × 1.2, 10k-patch budget at `detail: "original"`) is
  *   area-proportional, so resolution cannot improve chars/$ — 1568 stays.
  *   `detail: "high"` would downgrade (2,500-patch cap); `original` is sent.
  * - **Unknown providers** default to the Anthropic shape. Gateways can
@@ -94,9 +97,11 @@ export type ShapeGeometry = Omit<Shape, "frameTokenEstimate" | "imageDetail">;
  * (redundancy coding), `6x6u` unscii Lanczos-squeezed to 6x6 (densest
  * readable cell), `5x8` the X.org legacy font on its 2576px frame, `6x12`
  * and `8x13` the X.org misc fonts, `8on16` 8x13 glyphs on an 8x16 cell pitch
- * (no stretch, extra leading), `doc-` prefixed shapes a two-column
- * word-wrapped newspaper layout. Ink: `sent` cycles six hues at sentence
- * boundaries, `bw` is plain black, `-dim` suffix prints stopwords in gray.
+ * (no stretch, extra leading), `8on22` the same glyphs on a 22px pitch (more
+ * leading), `11on16` the same glyphs on an 11px advance (more tracking),
+ * `doc-` prefixed shapes a two-column word-wrapped newspaper layout. Ink:
+ * `sent` cycles six hues at sentence boundaries, `bw` is plain black, `-dim`
+ * suffix prints stopwords in gray.
  */
 export const SHAPE_VARIANTS = {
 	"8x8r-bw": { font: "8x8", cellWidth: 8, cellHeight: 8, variant: "bw", lineRepeat: 2, frameSize: 1568 },
@@ -126,6 +131,24 @@ export const SHAPE_VARIANTS = {
 		lineRepeat: 1,
 		frameSize: 1568,
 	},
+	"8on22-bw": {
+		font: "8x13",
+		cellWidth: 8,
+		cellHeight: 22,
+		stretch: false,
+		variant: "bw",
+		lineRepeat: 1,
+		frameSize: 1568,
+	},
+	"11on16-bw": {
+		font: "8x13",
+		cellWidth: 11,
+		cellHeight: 16,
+		stretch: false,
+		variant: "bw",
+		lineRepeat: 1,
+		frameSize: 1568,
+	},
 	"doc-8on16-bw": {
 		font: "8x13",
 		cellWidth: 8,
@@ -223,20 +246,21 @@ function priceShape(base: ShapeGeometry, family: BillingFamily): Shape {
 
 /** Eval-validated shapes, keyed by the provider family they won on. */
 export const SHAPES = {
-	/** `6x12-dim`: X.org 6x12 glyphs, black ink with stopwords dimmed gray.
-	 *  Production mono eval on claude-fable: f1 .840 vs .877 for the repeated
-	 *  `8x8r-bw` grid (within noise at n=25) at 37% lower cost — 12 frames
-	 *  instead of 21 per 400k chars. Never refused in any run. */
-	anthropic: priceShape(SHAPE_VARIANTS["6x12-dim"], "anthropic"),
-	/** `doc-8on16-sent-dim`: two word-wrapped columns, sentence hues, dimmed
-	 *  stopwords. Production mono eval on gemini-3.5-flash: f1 .900 vs .853
-	 *  for the repeated grid, at lower cost; also the chunked round-2 winner. */
-	google: priceShape(SHAPE_VARIANTS["doc-8on16-sent-dim"], "google"),
-	/** `8on16-bw`: 8x13 X.org glyphs on a 16px pitch, black ink. Mono eval on
-	 *  gpt-5.5 (200k-token single request, n=50): f1 .851 vs .602 for the
-	 *  previous `6x6u-sent` default at near-equal total cost; chunked exp14
-	 *  scored it .906. */
-	openai: priceShape(SHAPE_VARIANTS["8on16-bw"], "openai"),
+	/** `11on16-bw`: 8x13 glyphs on an 11px advance (extra tracking), black ink.
+	 *  Tool-result legibility bench (real search/read/find output, structure QA)
+	 *  on opus-4.8: f1 .806 vs .755 for plain `8on16-bw` and .351 for the prior
+	 *  `6x12-dim` default — letter-spacing the readable cell wins; the dense
+	 *  6x12 was below the OCR ~16px/char floor and abstained. */
+	anthropic: priceShape(SHAPE_VARIANTS["11on16-bw"], "anthropic"),
+	/** `8on22-bw`: 8x13 glyphs on a 22px pitch (extra leading), black ink.
+	 *  Tool-result legibility bench on gemini-3.5-flash: f1 .934 vs .807 for
+	 *  plain `8on16-bw` and .287 for the prior `doc-8on16-sent-dim`; the
+	 *  line-spacing reduces row crowding so line numbers stay legible. */
+	google: priceShape(SHAPE_VARIANTS["8on22-bw"], "google"),
+	/** `8on22-bw`: 8x13 glyphs on a 22px pitch (extra leading), black ink.
+	 *  Same line-spacing win for OpenAI; bench on gpt-5.5/gpt-5.4-mini showed
+	 *  leading lifts recall on the readable cell over plain `8on16-bw`. */
+	openai: priceShape(SHAPE_VARIANTS["8on22-bw"], "openai"),
 	/** Original 5x8 X.org shape (pre-shape-table sessions rendered this). */
 	legacy: priceShape(SHAPE_VARIANTS["5x8-sent"], "anthropic"),
 } satisfies Record<string, Shape>;
@@ -271,9 +295,9 @@ export function isShape(value: unknown): value is Shape {
 /** Eval-winning variant per provider family (billing fallback when the
  *  model id matches no known reader line). */
 const FAMILY_VARIANT: Record<BillingFamily, ShapeVariantName> = {
-	anthropic: "6x12-dim",
-	google: "doc-8on16-sent-dim",
-	openai: "8on16-bw",
+	anthropic: "11on16-bw",
+	google: "8on22-bw",
+	openai: "8on22-bw",
 };
 
 const FAMILY_SHAPE: Record<BillingFamily, Shape> = {
@@ -297,16 +321,16 @@ export interface IdealShape {
 const MODEL_VARIANTS: readonly (readonly [RegExp, IdealShape])[] = [
 	// Opus 4.7+ and Fable/Mythos read high-res natively (2576px edge under a
 	// 4,784 visual-token cap → 1932px square sweet spot): same recall and
-	// cost as 1568, a third fewer frames (12 → 8 per 400k chars).
-	[/claude.*(fable|mythos)/i, { variant: "6x12-dim", frameSize: 1932 }],
-	[/claude-?opus-?4[.-][7-9]/i, { variant: "6x12-dim", frameSize: 1932 }],
+	// cost as 1568, a third fewer frames.
+	[/claude.*(fable|mythos)/i, { variant: "11on16-bw", frameSize: 1932 }],
+	[/claude-?opus-?4[.-][7-9]/i, { variant: "11on16-bw", frameSize: 1932 }],
 	// Older Claude lines downscale past 1568px — keep the safe size.
-	[/claude/i, { variant: "6x12-dim" }],
+	[/claude/i, { variant: "11on16-bw" }],
 	// Gemini 3.x bills a fixed 1,120-token budget per image regardless of
-	// pixels: 2048px packs +70% chars per frame at the same bill.
-	[/gemini/i, { variant: "doc-8on16-sent-dim", frameSize: 2048 }],
+	// pixels: 2048px packs more chars per frame at the same bill.
+	[/gemini/i, { variant: "8on22-bw", frameSize: 2048 }],
 	// gpt-5.5 patch billing is area-proportional; 1568 is already optimal.
-	[/gpt|codex/i, { variant: "8on16-bw" }],
+	[/gpt|codex/i, { variant: "8on22-bw" }],
 	// kimi's image processor downscales past 1792px (64×64 28px patches);
 	// 1568 wins on chars/$ and reads at f1 .973 (≤8 frames per request).
 	[/kimi/i, { variant: "8on16-bw" }],