+ status: "NARROWED AGAIN 2026-07-06: the var-alias gap is FIXED (analyzeVar consults current_ns.aliases first, ADR-0035 D3 precedence; e2e phase14_var_special var_alias/var_alias_reader/var_alias_deref/var_fqn — corpus line infeasible: `(var alias/x)` is analysis-time so a `(do …)`-wrapped corpus expr fails in BOTH runtimes identically; cljw top-level-do sequential eval verified matching clj). instaparse.core now LOADS, `(insta/parser \"S = 'a'\")` builds, and string-literal grammars PARSE correctly (`[:S \"a\"]`, nested parens, == clj) — the ORIGINAL mis-tokenization divergence is GONE (was the GC-rooting family, ADR-0169). NEW FRONTIER (deterministic, reproduced 2026-07-06): grammars exercising regexp-full-parse (e.g. `A = 'a'+`) fail at gll.cljc:774 `(count text)` — text is instaparse's Segment deftype (declares CharSequence, defines length); cljw countFn's typed_instance arm lacks clj RT.countFrom's `instanceof CharSequence -> .length()` fallback -> protocol_no_satisfies. Fix: after the isPersistentCollection walk check, dispatch `-cs-length` (protocol CharSequence, host_interface.zig:175 remap) when the descriptor declares CharSequence. AFTER count: probe re-matcher/re-find with a Segment arg (clj Matcher accepts any CharSequence; cljw regex surface expects string — likely needs a toString coercion at the regex boundary). PRIOR HISTORY: 3-layer GC-rooting family fixed via ADR-0169 (AnalysisFrame; formToValue accumulators; TypeDescriptor trace); load-blocking var-alias fixed 2026-07-06."
0 commit comments