- Added a new SQuAD-based context-compression benchmark script for evaluating recall conditions.
- Added model and shape command-line arguments along with pricing and shape configurations.
- Updated default model variants and added an unknown billing family to shape resolution.
- Updated shape resolution and model resolution tests to verify the new defaults.
- Implemented a unified benchmark normalization layer to handle metrics and artifacts across harbor, edit, and snapcompact benchmarks.
- Integrated the TypeScript edit benchmark directly into the manager, migrating logic and deprecating the standalone package.
- Updated the API and database schema to support standardized benchmark configurations, metrics, and trace-based reporting.
- Enhanced the UI to visualize comparative performance metrics, including pass rate, cost, and latency deltas for benchmark runs.
- Updated `render`, `renderMany`, and native snapcompact methods to return promises, ensuring scalable async execution.
- Refactored `transformProviderContext` and `buildSideRequestContext` to support asynchronous operations in agent loops.
- Integrated `Promise.all` for improved concurrency when processing frame rendering and rendering batch operations.
- Updated all internal call sites, SDK hooks, and test suites to accommodate the asynchronous API signatures.
- Added 8on22-bw and 11on16-bw variants with spacing-tuned defaults for snapcompact.
- Changed provider defaults/mappings to use 11on16-bw for Anthropic and 8on22-bw for OpenAI/Google.
- Updated model frame rules so claude/fable/opus and gemini/gpt families map to new shapes and 2048 billing behavior.
- Fixed non-multiplexer resize dragging by using alternate screen during transient resize frames.
- Used per-frame palette usage statistics to remap global indices into a compact local palette before PNG encoding.
- Encoded indexed outputs with dynamic 1-, 2-, and 4-bit depths based on used color count.
- Raised PNG compression from Balanced to High for indexed and RGB paths and updated parity and decode tests for variable-bit palette decoding.
- Implemented model-specific frame-size billing for Anthropic, OpenAI, and Google.
- Changed compaction shape resolution to bind model variants to ideal frame sizes.
- Updated tests and docs to reflect new frame-size and budget behavior.
- Added chunked and cached Kimi mono-prod probing with hit/miss diagnostics.
- Added parse_robust fallback and cache re-score path for numbered QA answer parsing.
- Added multi-route probe execution modes including smoke, bill, frame, AB, and last-line checks.
- Changed mono_prod CLI to support custom shape JSON/name and pricing overrides.
- Previously, `anthropic-messages` requests using `resolveWireModelId` would always derive the non-thinking variant for `requestModelId`, even when reasoning was explicitly enabled.
- This change ensures the `reasoning` state is correctly passed to `resolveWireModelId`, allowing the API request to include the appropriate `X-thinking` model variant when thinking is active, standardizing behavior across providers.
- Resolved OpenAI shape resolution to `openai` and default to `8on16-bw`.
- Fixed catalog generation to collapse effort tiers before provider grouping.
- Updated help text and schemas to describe `8on16-bw` as the OpenAI auto default.
- Added production `render_pages` and `mono_prod` scripts for end-to-end QA output.
- Added `6x12-dim`, `8x13-bw`, `8on16-bw`, `doc-8on16-bw`, `doc-8on16-sent`, and `doc-8on16-sent-dim` to `SHAPE_VARIANTS`, backed by new `Shape` fields `stretch`, `columns`, and `stopwordDim` and the X.org `6x12`/`8x13` fonts.
- Added `dimStopwords()` (high-frequency function words printed in dim ink via zero-width markers, skipping already-dim spans) and `wrap()`, the greedy word-wrap used to typeset doc-layout pages; `geometry`/`render`/`renderMany`/`frames`/`compact` paginate doc shapes into `2 * rows`-line pages and persist `columns`/`stopwordDim` on compaction frames for mixed-shape detection.
- Changed `normalize()` to keep line structure (whitespace runs containing a line break collapse to `NEWLINE_GLYPH`, U+2588 FULL BLOCK) and to drop unrenderable characters — ANSI escape sequences, control characters, zero-width format characters, combining marks, lone surrogates — instead of printing `?` blanks.
- Explained the line-break marker in the frame-reading prompt `snapcompact-summary.md` and extended `snapcompact.test.ts` for the new variants, wrapping, and normalization.
- Added the `research/parity_check.py` and `research/parity_render.ts` parity tooling for the native renderer.
- Recorded the snapcompact changelog entries.
- Added a new @oh-my-pi/snapcompact package and redirected compaction call sites to it.
- Added provider-aware snapcompact shape resolution for model-specific mixed-frame behavior.
- Added optional image detail support by extending ImageContent and passing hints through OpenAI providers.
- Added native snapcompact render options, including 5x8/8x8 font loading and palette/geometry controls.
can1357