CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-09 14:38:59 +02:00
Code Issues Packages Projects Releases Wiki Activity

test: absorb the ponytail-import wave into the guard fixtures — ceilings, schema pin, triad phrasing

Browse Source 
Skeleton ceilings re-captured for the 17 carved skills the wave deliberately
grew (reuse ladder + bounded closer + shortcut trail, net of the gated -236B
AUQ cut), each with its measured size in the comment per the carve-guards
protocol. eval-store schema pin updated to v2 (harvest gains
insertions/deletions/net). The AUQ prose-triad keeps its pinned per-choice
phrasing ('explicit on EACH choice') while still deferring the score scale to
the canonical Format rule — the shipped cut is strictly closer to the pre-cut
text than the render that already passed the NOT-WORSE gate. Autoplan carve
anchors follow the Phase 2.5 renumbering. Golden ship baselines re-captured.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-08-28 02:36:09 +00:00
co-authored by Claude Fable 5
parent 4c20eca33b
commit 76f38fcd0d
46 changed files with 64 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/resolvers/preamble/generate-ask-user-format.ts
+1 -1
View File
@@ -26,7 +26,7 @@ Tell three outcomes apart:
**Prose fallback — render the decision brief as a markdown message, not a tool call.** Same information as the tool format below, different structure (paragraphs, not ✅/❌ bullets). It MUST surface this triad:
1. **A clear ELI10 of the issue itself** — plain English on what's being decided and why it matters (the question, not per-choice), naming the stakes. Lead with it.
2. **Completeness scores per choice** — per the Completeness rule in the Format section below; never silently drop the score.
2. **Completeness scores per choice** — explicit on EACH choice, per the Completeness rule in the Format section below; never silently drop the score.
3. **The recommendation and why** — the \`Recommendation: <choice> because <reason>\` line plus the \`(recommended)\` marker on that choice.
Layout: a \`D<N>\` title + a one-line note to reply with a letter (in Conductor this is the normal path; elsewhere it means AskUserQuestion was unavailable or errored); the issue ELI10; the Recommendation line; then ONE paragraph per choice carrying its \`(recommended)\` marker, its \`Completeness: X/10\`, and 2-4 sentences of reasoning — never a bare bullet list; a closing \`Net:\` line. Split chains / 5+ options: one prose block per per-option call, in sequence. Then STOP and wait — the user's typed answer is the decision. In plan mode this satisfies end-of-turn like a tool call.