Repository navigation
Conversation
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.
Bugbot Autofix is ON, but it could not run because the branch was deleted or merged before autofix could start.
Reviewed by Cursor Bugbot for commit 77a7838. Configure here.
| 1. Reproduce it yourself on the matching surface via the control skill from Non-negotiables. Do not hand the repro to the user. A debug or instrumentation protocol that says to ask the user to reproduce does not override this; you drive the instrumented runtime through the control skill. Ask the user only with a stated, specific reason the control surface cannot reach the target, and only after driving it as far as it goes. | ||
| 2. `how` over the affected subsystem for the root cause; don't paper over symptoms. the **why** skill for regression history. Confirm the *mechanism* with runtime evidence before the step-3 architect/interrogate fan-out; a design grounded on a plausible-but-unconfirmed cause can be unanimously wrong while the real cause sits one subsystem over. | ||
| 1. Reproduce it yourself on the matching surface via the control skill from Non-negotiables. Do not hand the repro to the user. A debug or instrumentation protocol that says to ask the user to reproduce does not override this; you drive the instrumented runtime through the control skill. Ask the user only with a stated, specific reason the control surface cannot reach the target, and only after driving it as far as it goes. If it won't reproduce directly, force it. Synthesize the trigger, tighten the conditions, or instrument until it fires. A bug you can't reproduce, you can't prove fixed. | ||
| 2. Binary-search the cause. Form the candidate hypotheses, then rule them out until one survives. Seed them with `how` over the affected subsystem and the **why** skill for regression history. On each pass, take the split that cuts the most remaining problem space, get runtime evidence for or against it, and eliminate. When program state is unclear, add instrumentation or logging and read it as the code runs. Don't guess. Drive a long or stubborn hunt with Cursor's `/loop` command. Confirm the surviving *mechanism* with runtime evidence before the step-3 architect/interrogate fan-out; a design grounded on a plausible-but-unconfirmed cause can be unanimously wrong while the real cause sits one subsystem over. |
There was a problem hiding this comment.
Seeding listed after elimination
Medium Severity · Logic Bug
Step 2 tells agents to form candidate hypotheses and rule them out until one survives, then seed those hypotheses with how and why. Seeding is meant to generate candidates before the binary-search passes, so this order makes the playbook describe finishing elimination before gathering evidence.
Reviewed by Cursor Bugbot for commit 77a7838. Configure here.
Collaborator
Author
|
Already landed on main via the byte-identical #88. Closing this duplicate. |
Dahhrk
added a commit
to Dahhrk/plugins
that referenced
this pull request
Sep 29, 2026
Parity with Dahhrk/plug-factory PR cursor#87: httpnocontext gate, http_request_ctx template, fixture and selfcheck coverage.
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
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.
Summary
Sharpens the bug-fix playbook to make the scientific debugging method explicit.
/loop. Keeps the existing "confirm the mechanism before the fan-out" guard.No new steps; this sharpens how steps 1-2 are executed.
Note
Low Risk
Documentation-only playbook wording; no runtime, auth, or application code changes.
Overview
The bug-fix playbook steps 1–2 are tightened so repro and root-cause work read as an explicit scientific method, without adding new steps.
Step 1 now requires forcing a repro when direct reproduction fails: synthesize the trigger, tighten conditions, or instrument until the bug fires, with the line that you cannot prove a fix without a repro.
Step 2 is reframed as binary-search the cause: seed hypotheses with
howand why, eliminate candidates using runtime evidence on the split that removes the most uncertainty, instrument when state is unclear instead of guessing, and use Cursor/loopon long hunts. The guard against architect/interrogate fan-out before a confirmed mechanism is unchanged.Investigation still fans out
how+whyin parallel; steps 3–6 are untouched.Reviewed by Cursor Bugbot for commit 77a7838. Bugbot is set up for automated code reviews on this repo. Configure here.