From ad9cd3fdbe053a37acab67e9bbf73aff2ed87c31 Mon Sep 17 00:00:00 2001 From: "[._.]/ Adam Eivy" Date: Sun, 16 Aug 2026 07:36:59 -0700 Subject: [PATCH 1/2] release: v3.31.0 --- .changelogs/v3.31.0.md | 14 ++++++++++++++ package.json | 2 +- 2 files changed, 15 insertions(+), 1 deletion(-) create mode 100644 .changelogs/v3.31.0.md diff --git a/.changelogs/v3.31.0.md b/.changelogs/v3.31.0.md new file mode 100644 index 0000000..3033240 --- /dev/null +++ b/.changelogs/v3.31.0.md @@ -0,0 +1,14 @@ +# Release v3.31.0 + +Released: 2026-08-16 + +## Highlights + +- **Per-reviewer reasoning effort suffix (`~effort=`) on `--review-with`**: Any slot in a `--review-with` list across all review commands (`/do:pr`, `/do:release`, `/do:review`, `/do:better`, `/do:better-swift`, `/do:depfree`, `/do:rpr`, `/do:config`) can now specify its reasoning effort level (`low`, `medium`, `high`, `xhigh`, `max`) — e.g. `--review-with=codex[gpt-5.6-luna]~effort=max~opt`, `claude~effort=high~max=2`. +- **Suffix chaining & saved defaults**: Suffixes (`~opt`, `~max=`, `~effort=`) chain in any order and ride through `/do:config` saved defaults in canonical order (`~opt` -> `~max=` -> `~effort=`). +- **Updated documentation & workflow examples**: `README.md` includes a Typical Developer Loop example (`plan-task` -> `next` -> `pr`) and explicit assistant invocation syntax details for Claude Code (`/do:*`), Codex (`$do-*`), Antigravity (`/do-*`), OpenCode (`/do-*`), and Grok Build (`/do-*`). + +## Details + +- **Reviewer Loop Threading**: Per-reviewer reasoning effort is forwarded as `{REVIEW_EFFORT}` to local agent review loops (`local-agent-review-loop.md`) and as `{OLLAMA_EFFORT}` to local Ollama review loops (`ollama-review-loop.md`). +- **CLI Flags & Prompt Construction**: Local agent invocations pass `${EFFORT_FLAG[@]+"${EFFORT_FLAG[@]}"}` (`--effort `) where supported, and Ollama review loops append reasoning effort instructions directly to the prompt. diff --git a/package.json b/package.json index 5e23f89..1d7f0bd 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "slash-do", - "version": "3.30.0", + "version": "3.31.0", "description": "Curated slash commands for AI coding assistants — Claude Code, OpenCode, Antigravity CLI, Codex, and Grok Build", "author": "Adam Eivy ", "license": "MIT", From 10d0dd55ff434ca8e7821ca37b34c68477e3b893 Mon Sep 17 00:00:00 2001 From: "[._.]/ Adam Eivy" Date: Sun, 16 Aug 2026 07:37:41 -0700 Subject: [PATCH 2/2] address review (codex): add Full Changelog section to .changelogs/v3.31.0.md --- .changelogs/v3.31.0.md | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/.changelogs/v3.31.0.md b/.changelogs/v3.31.0.md index 3033240..8bd0bed 100644 --- a/.changelogs/v3.31.0.md +++ b/.changelogs/v3.31.0.md @@ -12,3 +12,8 @@ Released: 2026-08-16 - **Reviewer Loop Threading**: Per-reviewer reasoning effort is forwarded as `{REVIEW_EFFORT}` to local agent review loops (`local-agent-review-loop.md`) and as `{OLLAMA_EFFORT}` to local Ollama review loops (`ollama-review-loop.md`). - **CLI Flags & Prompt Construction**: Local agent invocations pass `${EFFORT_FLAG[@]+"${EFFORT_FLAG[@]}"}` (`--effort `) where supported, and Ollama review loops append reasoning effort instructions directly to the prompt. + +## Full Changelog + +**Full Diff**: https://github.com/atomantic/slashdo/compare/v3.30.0...v3.31.0 +