fix(#3770): require intentional RED evidence before GREEN (#4279)

* test(3770): add failing tests for intentional RED evidence gate

RED: classifyRedEvidence / buildRedEvidenceRecord / check tdd-red-evidence do
not exist yet; every row fails on require. Per #3770 only an intentional
target-test failure may authorize GREEN; zero-test discovery, fixture crashes,
unrelated failures, and unexpected green are INVALID_RED.

* fix(3770): require intentional RED evidence before GREEN

Only an intentional failure of the TARGET test (distinctly named, TAP-reported
assertion failure) classifies as RED_EVIDENCE_OK and authorizes GREEN. Zero-test
discovery, fixture/load crashes (file-named failures), nonzero exits without a
failing test, unrelated failures, unexpected greens, and malformed/missing
records are INVALID_RED and block GREEN.

- src/tdd-red-evidence.cts: pure classifier + persisted record builder (reuses
  the prohibition-enforcement TAP primitives; fail-closed, never throws)
- check tdd-red-evidence <record.json>: validates the persisted record
  (command, exit code, failing test, expected, actual)
- gsd-executor.md / references/tdd.md / references/execute-mvp-tdd.md: RED now
  requires the evidence record + gate verdict, not a nonzero exit or a RED: tag

* chore(3770): regenerate inventory manifest for tdd-red-evidence.cjs

* fix(3770): fit executor fail-fast under size cap, fix unrelated-failure fixture, ignore generated lib

- gsd-executor.md: compress the #3770 fail-fast rule to one line (49149 B <
  49152 cap; line-count parity keeps the #2751 PROSE_ALLOWLIST line 816 valid)
- tests: the row-6 fixture used String.replace (first-occurrence), so the
  `not ok` line still named the target test and the classifier was right to
  accept it; replaceAll makes the failure genuinely unrelated
- eslint.config.mjs: ignore tsc-generated bin/lib/tdd-red-evidence.cjs
  (lint the src/*.cts source, per ADR-457 migration rule)

Emitted-Drift-Ack-Growth: gsd-executor.md — the #3770 fail-fast rule now requires intentional RED evidence (check tdd-red-evidence) before GREEN; +172 bytes, kept under the LARGE cap and on one line

* chore(3770): add changeset

* chore(3770): backfill PR number in changeset

---------

Co-authored-by: sim <sim@local>

agents/gsd-executor.md

@@ -408,7 +408,7 @@ reference is the single source; do not improvise a variant.
 
 When the plan frontmatter has `type: tdd`, the entire plan follows the RED/GREEN/REFACTOR cycle as a single feature. Gate sequence is mandatory:
 
-**Fail-fast rule:** If a test passes unexpectedly during the RED phase (before any implementation), STOP. The feature may already exist or the test is not testing what you think. Investigate and fix the test before proceeding to GREEN. Do NOT skip RED by proceeding with a passing test.
+**Fail-fast rules (#3770):** If a test passes unexpectedly during RED, STOP — do NOT skip RED. A nonzero exit alone is NOT RED either: persist the RED evidence (command, exit code, failing test, expected, actual) and verify with `gsd_run check tdd-red-evidence <record.json>` — only `RED_EVIDENCE_OK` (the TARGET test failed an assertion for the behavior) authorizes GREEN; any INVALID_RED (zero tests, fixture crash, parser error, wrong test) blocks it.
 
 **Gate sequence validation:** After completing the plan, verify in git log:
 1. A `test(...)` commit exists (RED gate)