6 Commits

Author SHA1 Message Date
Steven Chong 76f4fd2282 feat: add Sol Messages bridge and history compression 2026-07-15 15:15:58 -04:00
Steven Chong 318d90e882 feat(profile): use 5x8 rendering for opt-in Sol 2026-07-11 18:22:46 -04:00
Steven Chong 8b525a1acc feat: Grok packing + IDS, keep Fable-only default, honest chart
Ship Grok 5×8 white/IDS packing and universal IDS/factsheet plumbing while
keeping DEFAULT_MODEL_BASES Fable-only: live pure-image Grok is not
Fable-level; image+factsheet is the working exact path.

Chart shows Grok as a text-window series only (no Grok+pxpipe overlay) and
Fable as the measured pxpipe density point. Add Codex-path quality harnesses
and receipts (multi-seed, fix-matrix, shipped smoke).
2026-07-10 23:50:37 -04:00
teamchong 5deffdc757 test: pin PXPIPE_MODELS in savings-math e2e so CI is hermetic
The GPT tests drive gpt-5.6-sol, which is intentionally outside the
built-in default scope (Fable 5 only). Without pinning, the file's
result depended on the developer's ambient PXPIPE_MODELS — passing
locally but failing in CI's clean env. Snapshot/pin/restore, same
convention as proxy-usage.test.ts.
2026-07-09 22:41:42 -04:00
Steven Chong cd4c9efddd feat: add model-specific render profiles and recall evidence 2026-07-09 22:25:06 -04:00
teamchong 8417380061 test: e2e guards for cache stability, dashboard honesty, and design behaviors
Test-only (no src changes). Adds fake-upstream + real-createProxy suites:

- cache-stability-e2e: byte-identical cacheable prefix across growth, marker
  conservation + relocation onto the history image, tool-pair integrity.
- savings-math-e2e: gate never images at a net loss; baselineImagedTokens
  cross-checked against the real o200k tokenizer; baselineTokens wired from
  the count_tokens probe.
- savings-honesty: categorical no-overclaim invariants (warm <= cold,
  saved==delta*weight, zero credit on passthrough) + per-model pricing guards
  (Anthropic 1.25/0.1 shared policy; GPT 0.1x model-gated).
- design-behavior-e2e: system-prompt imaging, history collapse (old imaged /
  recent legible), tools-in-recent-turns kept usable.
- dashboard-api: GPT cold-cache parity (full text delta, not 0.1x warm rate).

Each guard mutation-verified (broke source, confirmed red, reverted).
2026-06-23 12:30:16 -04:00