Scope the builder Pre-Execution Protocol to task shape
メンテナーはふだん 1 日以内に返信
まだ誰も着手していません。
評価
- 難易度
- 4/5
- 見積もり時間
- 3〜5日
- 初心者へのやさしさ
- 66/100
- issue の種類
- 機能追加
- 明瞭さ
- おおむね明確
- 活発さ
- 活発
- 技術スタック
- sql, typescript
調査の方向性
packages/opencode/src/altimate/prompts/builder.txt から始め、実行モード固有のプロンプト注入に関する既存の SessionTermination.completionInstruction の先例を調査します。headless mode、builder agent、dbt プロジェクトの存在がどのように判定されるかを追跡します。完了条件は、dbt プロジェクトのない headless builder の実行時にのみ Pre-Execution Protocol が省略され、それ以外のすべての場合（未分類の workspace を含む）には残ることです。
索引モデルが issue の本文から書いたものです。
説明
Problem
packages/opencode/src/altimate/prompts/builder.txt carries a ## Pre-Execution Protocol section that makes sql_analyze + altimate_core_validate mandatory before every sql_execute. builder is a PRIMARY agent, so that section reaches every builder surface at once: dbt authoring, interactive chat, and headless question-answering runs.
An internal pre-registered paired prompt ablation (540 trials on a public data-question benchmark, one binary across both arms, per-trial system prompts verified by sha256) measured what the section costs on the question-answering surface:
| macro Pass@1 | |
|---|---|
| control | 0.6667 |
| treatment (protocol removed, among other changes) | 0.6807 |
| delta | +0.0140 |
- query-blocked sign-flip permutation, 20,000 resamples: p = 0.7358
- cluster-bootstrap 95% CI: [-0.0400, +0.0674]
That is a null on score. The point estimate is positive and the interval comfortably contains zero — it is not an improvement and must not be reported as one.
What did move:
| control | treatment | delta | |
|---|---|---|---|
| wall clock per trial (restricted mean) | 440.9s | 319.4s | -27.6% |
| model turns per trial | 11.9 | 8.6 | -27.7% |
| generation seconds per trial | 187.6 | 127.2 | -32.2% |
altimate_core_validate calls (arm total) |
1,476 | 0 | -1,476 |
sql_analyze calls (arm total) |
1,329 | 0 | -1,329 |
sql_execute calls (arm total) |
1,716 | 2,554 | +49% |
| trials hitting the 900s timeout | 27 | 16 | -11 |
The 2,805 ritual tool calls going to zero is the number directly attributable to this text. The ritual is prompt-ordered: deleting the order deletes it completely, not partially. The freed budget went into actual querying (sql_execute +49%).
Why not just delete it
Two reasons, both from the experiment's own caveats:
- The latency win is not attributable to this section alone. The treatment arm bundled five coupled changes; the experiment explicitly declined to attribute and a factorial was not run.
- The measurement covers data questions only. dbt authoring and interactive chat are unmeasured builder surfaces where a pre-execution discipline may genuinely earn its place. Deleting on this evidence would over-generalise from one workload.
Proposal
Scope the section to task shape rather than delete it, following the precedent already in the tree: SessionTermination.completionInstruction moved a run-mode-only instruction out of builder.txt and injects it only when headless AND the agent is builder.
Drop the protocol only in the cell that was measured (headless + builder + no dbt project in the workspace) and keep it everywhere else, including whenever the workspace cannot be classified. The cost of keeping it is 27% latency on one workload; the cost of wrongly dropping it is unmeasured.
Out of scope
main also carries a ## Finish Protocol section (shipped in #1171) — a second mandatory ritual in the same family, added after the binary the ablation measured was built. No measurement covers it and this issue does not propose touching it.
A follow-up measurement on dbt tasks is needed before the gate could be widened, or the section deleted outright.
- 主要言語
- TypeScript
- スター
- 813
- フォーク
- 134
- 平均マージ
- 1日 19時間
- マージ済み PR（30日）
- 64
環境構築
はじめの一歩
- issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
- 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
- リポジトリをフォークし、ブランチを切って変更します。
- issue 番号を参照したプルリクエストを送ります。
AltimateAI/altimate-code のほかの issue
-
難易度 2/5 1〜3時間 初心者へのやさしさ 70/100
AltimateAI/altimate-code#1359 ·
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 84/100
AltimateAI/altimate-code#1323 ·
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 86/100
AltimateAI/altimate-code#1288 ·
メンテナーはふだん 1 日以内に返信
-
難易度 1/5 1時間未満 初心者へのやさしさ 92/100
AltimateAI/altimate-code#1285 ·
メンテナーはふだん 1 日以内に返信
-
privacy: Altimate Base consent dialog no longer discloses persistent per-installation identifierオープン
難易度 1/5 1時間未満 初心者へのやさしさ 88/100
AltimateAI/altimate-code#1284 ·
メンテナーはふだん 1 日以内に返信
AltimateAI/altimate-code の issue をすべて見る
似ている issue
-
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
microsoft/vscode-livepreview#876 ·
メンテナーはふだん 1 日以内に返信
-
needs-triage
難易度 1/5 1時間未満 初心者へのやさしさ 90/100
JustJarethB/invoicer#54 ·
-
ICP 1.2.0 shows a scheduled task's interval in milliseconds under the label "Interval (In seconds)"オープンNeeds Triage Type/Bug
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
wso2/product-integrator#2585 ·
メンテナーはふだん 1 日以内に返信
-
check:passed streams:add
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
メンテナーはふだん 1 日以内に返信
-
design
難易度 2/5 1〜3時間 初心者へのやさしさ 72/100
MTES-MCT/monitor-field#119 ·
メンテナーはふだん 1 日以内に返信