fix(semif): 0.1.4 — object states ending in ) ; } no longer 422 (INV-7)

SemIf's shared scorer trims one token at the state boundary. When an object
state's last value ends in ')', ';' or '}', the JSON that follows re-merges two
tokens back, so score_shared refused the request with 422. The engine now wraps
semif_phase1.shared._state_prefix to keep only the tokens the full prompts
share. Each row scores the same token sequence; only the prefill/suffix split
moves.

Startup proves the fix is in effect, not just installed (heid bug hunt SKAL,
folded). It checks that the hook is callable and is what score_shared resolves,
that an ordinary state keeps upstream's whole prefix, and that a merge-prone
state scores through the shared path.

Real tokenizer: 154 states, 23 refused before and 0 after, with no ordinary or
authored144 prefix changed. Acceptance: 144/144 parity. Shared vs direct 71/72;
the miss is a bf16 tie that flipped across a plain restart (see README).
This commit is contained in:
vh
2026-09-27 10:23:14 -07:00
parent 7e11cf247b
commit 47cad33dd1
11 changed files with 384 additions and 20 deletions
+1 -1
View File
@@ -991,7 +991,7 @@ dependencies = [
[[package]]
name = "semif-serve"
version = "0.1.3"
version = "0.1.4"
source = { editable = "." }
dependencies = [
{ name = "fastapi" },