mirror of
https://github.com/teamchong/pxpipe.git
synced 2026-07-22 02:02:51 +02:00
teamchong
b563751cf6
Production telemetry (N=10 events with history_reason="not_profitable", 2026-05-18..05-20) shows body-level chars-per-token on rejected history events: median 1.09, max 1.10. The gate at cpt=4 was estimating text as 3.7× cheaper than reality on every history-collapse decision in the sampled traffic — same shape of bug as the slab path fixed inc36ec3f. Why this matters more than the slab fix: • The slab is cached (cache_create×1.25 once, cache_read×0.10 after). Slab compression saves bytes mostly on cold misses + 2k tok/warm hit. • History content is NOT cached. Once turns leave the cache breakpoint budget (4 max per request), every subsequent request pays 100% for them. A long agentic session re-bills the same closed-prefix turns on every turn — exactly the workload Variant C was designed to compress, and exactly the path the gate was silently rejecting. Apply same fix asc36ec3f: HISTORY_CHARS_PER_TOKEN=2.5 (upper bound of empirical data, identical safety property to SLAB_CHARS_PER_TOKEN since history content shape ⊆ slab content shape in tool-heavy sessions). Host can still override via TransformOptions.charsPerToken. The override-gate `o.charsPerToken !== CHARS_PER_TOKEN` means unspecified requests (DEFAULTS.charsPerToken=4) get the empirical cpt while explicit non-default host values win — same intentional pattern as the slab path. Test: regression fixture pinning a 14-turn × 1500 chars/turn conversation where: • cpt=4 path → 'not_profitable' rejection (image cost 5k > text 4k) • cpt=2.5 path → 'collapsed' with 10 turns merged (text 6.4k > image 5k) Counterfactual half uses cpt=4.5 to bypass the override-gate (passing exactly 4 collides with the DEFAULTS sentinel). 273 tests pass, typecheck clean, build clean.