4 Commits

Author SHA1 Message Date
teamchong 7af6c200c3 eval+demo: route harnesses through interactive cci.py; opus → claude-opus-4-8[1m]
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.
2026-06-18 23:43:37 -04:00
teamchong 8af9829872 feat(render): raise page ceiling to ~1932x1932 and align gate/paging geometry
Fable 5 / Opus 4.8 accept up to 2576px / 4784 visual tokens per image, but a
request with >20 images (pxpipe always sends many) is held to the stricter
<=2000px/side rule, so the real ceiling is ~1932x1932 (1928x1928 = 69x69 = 4761
tokens). MAX_HEIGHT_PX 1568->1932; dense tool/history pages now render at
DENSE_CONTENT_COLS=384 / DENSE_CONTENT_CHARS_PER_IMAGE=92160 (1928x1928 full
page) -- fewer image blocks at the same OCR-validated 5x8 cell. The static slab
is unchanged (313 cols / 1573x1280).

Also fixes a regression the code review caught: the break-even gate,
truncateForBudget, and estimateImageCount predicted against the slab geometry
(313 cols / 159 rows) while the dense renderer emits 384 cols / 240 rows, so
large tool_results were truncated far earlier than the 10-image cap required --
silently dropping output that would have rendered. A per-page char budget is
threaded through the prediction chain (defaults to READABLE so the slab and unit
tests are byte-identical) plus a denseGateGeometry helper, so the gate prices the
same page the renderer actually produces.
2026-06-17 10:01:33 -04:00
teamchong c369b931e5 chore: rename remaining pixelpipe mentions in eval scripts/docs
frozen eval outputs under eval/results*/ left as-is (historical records)
2026-06-09 19:07:13 -04:00
teamchong 2b7b98f685 feat(render): add R3 reflow to recover line-end dead margin (~29% glyph fill → dense)
Pack text into a continuous sentinel-delimited stream (↵ = U+21B5) so
wrapLines fills every row to `cols` instead of leaving dead right-margin.
Adds reflow/dereflow, renderTextToPngsReflow{,MultiCol} variants, a full
test suite, and an A/B eval harness with L1 OCR + L2 session results.
2026-05-21 23:14:00 -04:00