chore(bench): harden skill smoke + delete dead mock loop#295
Merged
Conversation
… mock loop - skill-sandbox-smoke: old verdict (/reproduce-first/ && /SKILL.md/ over agent prose) false-positived on opencode's bundled /nix/store skills and checked the wrong path. Now keys on a UNIQUE marker the in-session agent reads back from the materialized file at the correct ~/.opencode/skill/<name>/SKILL.md (opencode singular dir; claude-code uses ~/.claude/skills), and documents the session-view gotcha (bare box.exec sees a different FS than the agent session). - delete observe-steer-workspace-loop.mts: unreferenced dead mock-executor loop (cloud-loop.mts is the real observe->steer proof); orphaned back onto main by an earlier squash-merge.
tangletools
approved these changes
Jun 14, 2026
tangletools
left a comment
tangletools
left a comment
Contributor
There was a problem hiding this comment.
✅ Auto-approved PR — e45262ea
Blanket team auto-approval is enabled for this reviewer service.
The full PR reviewer audit still runs separately and will publish findings if it detects issues.
tangletools · auto-approval · reason: blanket_auto_approve · 2026-06-14T14:42:29Z
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Two safe, capability-preserving cleanups.
Harden
skill-sandbox-smoke.mts— the old verdict (/reproduce-first/ && /SKILL.md/over the agent's prose) false-positived on opencode's bundled/nix/storeskills and checked the wrong discovery path. It now keys on a unique marker the in-session agent reads back out of the materialized file, at the correct~/.opencode/skill/<name>/SKILL.md(opencode's singular dir; claude-code uses~/.claude/skills). Documents the two gotchas that produced false readings during bring-up: the singularskillpath, and that a barebox.exec(no sessionId) sees a different filesystem than the agent session.Delete
observe-steer-workspace-loop.mts— unreferenced dead mock-executor loop;cloud-loop.mtsis the real observe→steer proof. It was orphaned back onto main by an earlier squash-merge.No capability change.