alternate port: claude-fable-5 — 37/37 gated effects, $54.82 vs $550 (beats by 90%), retrieval instead of context

[staccDOTsol]

alternate port: anthropic/claude-fable-5 — $54.9769 all-in vs $550 DHH paid for the same model (beats by 90.0%)

One of five frontier models given DHH's exact challenge (same plan.md, same
Python reference) with one change: the 396k-token reference was retrieved
per-ask through a holographic-memory layer instead of re-sent in context.

• 37/37 effects, each gated on compiling AND rendering styled ANSI animation
• $54.9769 total, provider-billed, every ask on the attached LEDGER.jsonl
• 9.8x measured vs carrying the corpus (real cold/warm sends, not assumed cache rates)
• watch the effects run from this binary: https://ttfx.awesomemcp.fun/show/fable

Full parity wasn't targeted — the 354 cases in this repo remain the bar. But on
the pure-math subset, we ran YOUR goldens against fable's code on your pinned
parity platform (Linux/glibc 2.35): 12/12 implemented easing functions,
12,012/12,012 samples — 100.00% bit-exact. (One $0.157 post-run ask, on the
attached ledger, closed a 1-ulp powi/powf expression-order gap; fable wrote its
own fix. Unimplemented easings are absent, not failing.)

This adds alternates/anthropic_claude-fable-5/: the same challenge, run on the
cost axis, with a receipt for every ask.

honesty section (condensed from the run's live during-mortem)

The harness was improved WHILE this ran, and every dollar of that is in the
numbers above, not edited out: a render gate added mid-run dropped and re-bought
already-paid effects; three reasoning-budget truncation bugs bought ~$7 of
unusable responses before diagnosis; early asks shipped 3x-fat retrieval chunks;
restarts re-bought cores. Projections use the blended all-waste rate (marginal
rates run ~5x lower). The "without retrieval" comparison is MEASURED, not
modeled — real cold+warm full-corpus sends at provider-billed prices, which
found NO default cache discount for Anthropic or DeepSeek-via-OpenRouter. DHH's
side counts only his published successes; ours counts every failure. The
finished Rust port in this repo was quarantined from the models throughout —
they saw only plan.md and the Python source. Full ledger of every ask attached
(LEDGER.jsonl: tokens, provider-billed USD, timestamps).

Close it if exhibits don't belong here — the branch and the live page stand on
their own either way.