From 7be0ab3fd011bba2100a2043257562a900b6b2b1 Mon Sep 17 00:00:00 2001 From: toki Date: Fri, 19 Jun 2026 17:04:17 +0900 Subject: [PATCH] sync: agent-ops from agentic-framework v1.1.151 --- agent-ops/.version | 2 +- agent-ops/skills/common/code-review/SKILL.md | 1 + agent-ops/skills/common/plan/SKILL.md | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) diff --git a/agent-ops/.version b/agent-ops/.version index 4f706ff..3d370b4 100644 --- a/agent-ops/.version +++ b/agent-ops/.version @@ -1 +1 @@ -1.1.149 +1.1.151 diff --git a/agent-ops/skills/common/code-review/SKILL.md b/agent-ops/skills/common/code-review/SKILL.md index c135920..75dea4c 100644 --- a/agent-ops/skills/common/code-review/SKILL.md +++ b/agent-ops/skills/common/code-review/SKILL.md @@ -95,6 +95,7 @@ Review routing rules: - `local-G01` through `local-G10` and `cloud-G01` through `cloud-G10` are valid. Lane is capability fit; grade is complexity within the chosen lane. Do not raise `local-GNN` to compensate for missing judgment, missing context, weak verification, or a previous loop failure. - Repair non-behavioral review artifact drift during review instead of failing solely for it when implementation correctness, tests, and contracts remain judgeable. - `cloud-G07` or higher is mandatory only when terminal-agent or external interactive behavior is central and cannot be made deterministic for local review, or when the review requires more source/test/diff/log context than local can hold without omitting material evidence: shell/CLI workflow implementation, bin script orchestration, process control, stdout/stderr parsing, exit-status contracts, long-running command diagnosis, terminal benchmark-style tasks, real bin/smoke/integration failures after unit tests passed, TUI/PTY/browser/screen repaint/cursor stream behavior, rerun-mismatched verification trust failures, or very large cross-module/cross-domain changes that cannot be safely split for review. +- On WARN/FAIL follow-up with 5+ `Required` findings, reassess lane/grade and default to `cloud-G07` or higher unless all findings are one narrow mechanical fix pattern; if keeping `local`, record why local conditions still hold. - Previous loop lane does not matter. Recompute lane from the current review or follow-up scope using these rules. Directory states: diff --git a/agent-ops/skills/common/plan/SKILL.md b/agent-ops/skills/common/plan/SKILL.md index c32895f..d98ee20 100644 --- a/agent-ops/skills/common/plan/SKILL.md +++ b/agent-ops/skills/common/plan/SKILL.md @@ -100,6 +100,7 @@ Routing rules: - Use `cloud` when any local condition is false, including when a plausible but wrong implementation could pass local checks while breaking behavior promised outside the bounded context. - `local-G01` through `local-G10` and `cloud-G01` through `cloud-G10` are valid. Lane is capability fit; grade is complexity within the chosen lane. Do not raise `local-GNN` to compensate for missing judgment, missing context, weak verification, or a previous loop failure. - Use `cloud-G07` or higher only when terminal-agent or external interactive behavior is central and cannot be made deterministic for local handling, or when the task requires more source/test/diff/log context than local can hold without omitting material evidence: shell/CLI workflow implementation, bin script orchestration, process control, stdout/stderr parsing, exit-status contracts, long-running command diagnosis, terminal benchmark-style tasks, TUI/PTY/browser/screen repaint/cursor stream behavior, real bin/smoke/integration failures after unit tests passed, or very large cross-module/cross-domain changes that cannot be safely split. +- For follow-ups from a review with 5+ `Required` findings, reassess lane/grade and default to `cloud-G07` or higher unless all findings are one narrow mechanical fix pattern; if keeping `local`, record why local conditions still hold. - Previous loop lane does not matter. Recompute lane from the current plan or follow-up scope using these rules. - Treat non-behavioral review artifact drift as reviewer-repairable unless it prevents judging implementation correctness, tests, or contracts. - Treat obvious non-behavioral source nits as reviewer-repairable too: typos, stale comments, docs, or formatting only, with no behavior/test/API contract change.