Add native Google AI Studio transformation, measured token accounting, dashboard support, and a production 312×728 profile for Gemini 3.6 Flash.
Gemini uses 26% fewer vision tokens than Fable 5 per full page and matches or exceeds Fable across the production-profile quality suite.
* fix(render): glyph surgery so Spleen 5x8 K no longer reads as H
The stock Spleen K was H with one crossbar pixel removed (Hamming 1), the
worst confusable pair in the atlas. Because the API downscales images and the
model infers rather than scans, that difference vanishes and K is silently
misread as H - with no signal of uncertainty.
gen-atlas.ts now repaints K with a diagonal-legged bitmap: Hamming 8 from H,
and >=6 from every other ASCII glyph. Scoped to the narrow Spleen 5x8 primary
cell, so the JetBrains-Mono and CJK-fallback atlases are untouched. Zero
token-cost change - the glyph occupies the same 5x8 box.
Guarded by a regression test asserting no alphanumeric pair sits below
Hamming 2. Reproduce with: npx tsx eval/glyph-matrix/demo-glyph.mts
Closes the "optional glyph surgery" item in the 2026-07-01 legibility audit.
- FINDINGS.md 2026-07-05 entry: capacity argument (misreads are
resolution-bound, receipts from the 2026-06-16 sweep), proposal-by-
proposal rejection table, and three documented follow-up threads
(glyph-style A/B with banked pages, runtime canary + re-fetch,
surrogate-reader pre-flight) for successors.
- docs/NOT-OCR.md: how VLM vision reads renders (patches, not glyphs),
why misses are silent confabulations, and why DeepSeek-OCR-era
skepticism predates the Opus 4.8 to Fable 5 capability jump.
- README: Roadmap now points at the parked state; two new FAQ entries
link to the doc instead of inlining it.
- Wording states observables only: token cost scales with pixel area,
dense text carries more information per token, and computer use
already ships models reading screenshots. No arbitrage/exploit
framing, no claims about pricing intent.
Adds the 2026-06-23 entry: pxpipe's right comparison is /compact (itself lossy),
not perfect recall. compact-vs-gist analysis (same job, opposite loss profiles —
pxpipe wins on Fable, peer-on-Opus with abstention, recoverability as the
structural edge); code-grounded notes on the open-source harnesses (codex,
opencode); ties to the agent-memory (reducer/channel-routing) direction. n=1
behavioral parts flagged; eval numbers cross-checked against existing entries.
Docs only — not shipped in the npm package.
eval:
- Add eval/lib/cci.py: drop-in interactive Claude session shim (pexpect/PTY)
replacing headless `claude -p`. Drives the real TUI on Max-subscription auth
(no ANTHROPIC_API_KEY), scrapes the reply + /context + /cost, and is
argv/stdin/--output-format json compatible with the old call sites.
- Wire every call site to cci.py: gist-recall (run/run2/run3),
needle-haystack (sweep/crux), gsm8k (bench), swe-bench (run_pilot),
swe-bench-pro (rep_nav/run_pro), and eval/lib/anthropic-client.mjs.
- Isolation per call: --setting-sources project --strict-mcp-config
--dangerously-skip-permissions. Recall evals keep --allowedTools Read;
swe-bench keeps the full agentic toolset. Each trial is a fresh process.
demo:
- Resolve the `opus` shorthand to the full claude-opus-4-8[1m] model in
cost-ab and effective-context a.sh/b.sh. setup.sh intentionally keeps the
base id: the proxy scope gate strips [1m] from the request before matching,
so [1m]-on-launch + base-in-scope is the correct pairing.
docs:
- FINDINGS.md: drop the 2026-06-16 Opus 4.8 re-test sections.
- applicability: isPxpipeSupportedModel reads PXPIPE_MODELS (comma-sep,
default claude-fable-5 only) and strips bracket/variant tags like [1m];
Opus becomes opt-in with no code change. Default behavior unchanged.
- FINDINGS: Opus 4.8 re-test - arithmetic 98/100 (-2pp), verbatim 6/15
(was 93/100, 0/15): improved but still taxed -> default stays Fable-only.
- FINDINGS + eval/glyph-matrix/sweep: root cause of the read tax is per-glyph
RESOLUTION, not font shape (confusions scale with px and vanish by 10x16).
Opus needs ~4x glyph area to read reliably; the 1568px ceiling makes that
break-even, so there is no profitable Opus operating point.
- FINDINGS.md: dated 2026-06-12 entry logging in-the-wild verbatim
misreads (7/10 exact, ~3.3% per-char, 2/3 silent) alongside flawless
gist-tier recall in the same session. Explicitly anecdotal, n=1,
non-reproducible — motivation only.
- eval/glyph-matrix/PLAN.md: public plan for the paused confusion-matrix
experiment (Task #7) so the pending work is visible outside README,
per the measured-numbers-only README rule.
The prior commit captured only the rename (a stale pathspec aborted the
content staging). This applies the actual edits: retitle to FINDINGS,
'## Verdict' + superseded TL;DR, and the two cross-reference updates.
The project isn't dead (verdict reversed to working ~68% gist-compressor),
so 'postmortem' was a misnomer. Rename to FINDINGS, retitle, promote the
correction to '## Verdict', and mark the old TL;DR as superseded. Update the
two cross-references (eval README link, public-api test comment).
Steven