Merge origin/main (v1.57.2.0) into garrytan/upgrade-gbrain-use

Resolves VERSION/CHANGELOG/package.json (branch keeps its higher v1.57.5.0; my
CHANGELOG entry on top, main's v1.57.2.0 entry below). Regenerated SKILL.md across
hosts from the merged templates. Bumped maxSizeRatio to 1.07 for investigate, cso,
and design-consultation: the cross-cutting preamble growth (v1.57.2.0 AUQ-failure
prose fallback + the decision-memory nudge) lands them just over the strict 1.05.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-06-07 22:45:39 -07:00
71 changed files with 2045 additions and 210 deletions
+10 -10
View File
@@ -20,16 +20,16 @@
"test": "bun test browse/test/ test/ make-pdf/test/ --ignore 'test/skill-e2e-*.test.ts' --ignore test/skill-llm-eval.test.ts --ignore test/skill-routing-e2e.test.ts --ignore test/codex-e2e.test.ts --ignore test/gemini-e2e.test.ts && (bun run slop:diff 2>/dev/null || true)",
"test:free": "bun run scripts/test-free-shards.ts",
"test:windows": "bun run scripts/test-free-shards.ts --windows-only",
"test:evals": "EVALS=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
"test:evals:all": "EVALS=1 EVALS_ALL=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
"test:e2e": "EVALS=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
"test:e2e:all": "EVALS=1 EVALS_ALL=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
"test:gate": "EVALS=1 EVALS_TIER=gate bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
"test:periodic": "EVALS=1 EVALS_TIER=periodic EVALS_ALL=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
"test:codex": "EVALS=1 bun test test/codex-e2e.test.ts",
"test:codex:all": "EVALS=1 EVALS_ALL=1 bun test test/codex-e2e.test.ts",
"test:gemini": "EVALS=1 bun test test/gemini-e2e.test.ts",
"test:gemini:all": "EVALS=1 EVALS_ALL=1 bun test test/gemini-e2e.test.ts",
"test:evals": "EVALS=1 GSTACK_HEADLESS=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
"test:evals:all": "EVALS=1 GSTACK_HEADLESS=1 EVALS_ALL=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
"test:e2e": "EVALS=1 GSTACK_HEADLESS=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
"test:e2e:all": "EVALS=1 GSTACK_HEADLESS=1 EVALS_ALL=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
"test:gate": "EVALS=1 GSTACK_HEADLESS=1 EVALS_TIER=gate bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
"test:periodic": "EVALS=1 GSTACK_HEADLESS=1 EVALS_TIER=periodic EVALS_ALL=1 bun test --retry 2 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/gemini-e2e.test.ts",
"test:codex": "EVALS=1 GSTACK_HEADLESS=1 bun test test/codex-e2e.test.ts",
"test:codex:all": "EVALS=1 GSTACK_HEADLESS=1 EVALS_ALL=1 bun test test/codex-e2e.test.ts",
"test:gemini": "EVALS=1 GSTACK_HEADLESS=1 bun test test/gemini-e2e.test.ts",
"test:gemini:all": "EVALS=1 GSTACK_HEADLESS=1 EVALS_ALL=1 bun test test/gemini-e2e.test.ts",
"skill:check": "bun run scripts/skill-check.ts",
"dev:skill": "bun run scripts/dev-skill.ts",
"start": "bun run browse/src/server.ts",