Commit Graph

4 Commits

Author SHA1 Message Date
iomgaa 3cb5331950 docs: correct the equivalence claim T2 disproved 2026-09-05 00:48:01 -04:00
iomgaa 862fc3f5a9 docs: say which way the capability table leans when a source disagrees 2026-09-04 23:57:55 -04:00
iomgaa c920ab4b83 docs: record the human approval and the tier-mapping call it settled
Codex argued `effort_fallback` had no verifiable consumer and could wait.
The human overruled that: swapping models is routine, and between "it
stops booting" and "it silently costs more" the caller deserves a middle
option it selects on purpose. So the mapping ships with this round.
2026-09-04 23:51:25 -04:00
iomgaa 5577812a16 docs: design reasoning effort as a tier the boolean cannot express
issue #20 asks for one zhipu profile. Adding it does not fix what the
issue describes: GLM-5.3 mandates thinking (three sources agree, the
vendor included), so `none` is an undefined value we were sending, and
`medium` — the tier our minimax profile hardcodes — does not exist on
GLM, kimi or deepseek at all.

So the gap is the type, not the table. Capability becomes a tier list
where `none`'s presence answers "can it be turned off", and refusal
carries the cheapest tier that model does support — a refusal with no
way forward is what sent the caller to extra_body in the first place.

Reviewed by Codex, which caught two claims that were wrong: source-level
extra_body and enable_thinking already reach the cache key through the
model fingerprint, and the three reference projects are not in the
workspace, so "no callers" was a grep against absent directories.
2026-09-04 23:43:06 -04:00