docs: CG-21 — spending the reservation (design record + CHANGELOG precision)

Records both levers, the funding-pool design (and the per-file version that
dropped payslip_builder.go), the resolved memory-budget.ts exception, and the
two hermetic fixtures with their mutation matrix.

The CHANGELOG clause 'no longer trimmed while a smaller, weakly-related one is
included whole' was imprecise after CG-21: the smaller file often IS still
included whole now, when its share nearly covers it. Reworded to say what the
fix actually guarantees.

CHANGELOG.md

@@ -15,7 +15,7 @@ and adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ### Fixes
 
-- `codegraph_explore` now concentrates its answer on the code that actually answers your question, instead of spreading it across files that merely share a word with it — so more of the answer fits inside the same response, and the follow-up calls that used to be needed to fill in the gaps often aren't. Two things changed. Matches are weighted by what was matched: a function, class or route counts for far more than a local variable, and a variable that nothing else references counts for almost nothing, so a file whose only tie to your question is a same-named constant no longer competes with the file that implements the thing. And the room each file gets is now sized in proportion to how well it matches, decided before any source is written out, instead of every file receiving a similar slice under the same per-file limit — the file that answers you is no longer trimmed while a smaller, weakly-related one is included whole. Files far below the best match are listed by name, symbol and line number rather than spending the answer on their source, and one more `codegraph_explore` naming any of them returns it in full. Test and spec files in a repository's top-level `test/` or `spec/` directory are also recognized as such now, which they weren't before. Thanks @LeDuyViet for the detailed measurements and reproduction. (#1500)
+- `codegraph_explore` now concentrates its answer on the code that actually answers your question, instead of spreading it across files that merely share a word with it — so more of the answer fits inside the same response, and the follow-up calls that used to be needed to fill in the gaps often aren't. Two things changed. Matches are weighted by what was matched: a function, class or route counts for far more than a local variable, and a variable that nothing else references counts for almost nothing, so a file whose only tie to your question is a same-named constant no longer competes with the file that implements the thing. And the room each file gets is now sized in proportion to how well it matches, decided before any source is written out, instead of every file receiving a similar slice under the same per-file limit — the file that answers you is no longer trimmed just because a smaller, weakly-related one was small enough to include whole. Files far below the best match are listed by name, symbol and line number rather than spending the answer on their source, and one more `codegraph_explore` naming any of them returns it in full. Test and spec files in a repository's top-level `test/` or `spec/` directory are also recognized as such now, which they weren't before. Thanks @LeDuyViet for the detailed measurements and reproduction. (#1500)
 
 - A generated CRUD or protobuf layer no longer crowds out the hand-written code sitting beside it. Generated code is now recognized by what's written at the top of the file, not just by its filename: Go's own convention — a `// Code generated by … DO NOT EDIT.` line — is a comment, not a naming rule, so a generated file with an ordinary name was previously indistinguishable from hand-written source and could outrank the real implementation wherever both matched a name — in `codegraph_explore`, in search results, and in the callers and blast-radius answers built on them. CodeGraph now reads the header while indexing and recognizes the standard banners across languages (Go's, protoc's, `@generated` in JavaScript and TypeScript, `<auto-generated>` in C#, Thrift, OpenAPI Generator, FlatBuffers, ANTLR, bindgen and more), and generated files are down-weighted throughout the ranking rather than only breaking ties between otherwise equal matches. Re-index after upgrading to pick up the new detection. (#1500)