waypoint-codex 0.10.2 → 0.10.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md
CHANGED
|
@@ -163,6 +163,8 @@ For planning work, run `plan-reviewer` before presenting a non-trivial implement
|
|
|
163
163
|
|
|
164
164
|
When the user approves a reviewed plan or explicitly says to proceed, the intended Waypoint behavior is autonomous execution: keep going through implementation, verification, review, and repo-memory updates unless a real blocker or materially risky unresolved decision requires a pause. If reviewers, subagents, CI, or other external work are still running, Waypoint should wait as long as necessary rather than interrupting them for speed.
|
|
165
165
|
|
|
166
|
+
When browser-based reproduction or verification is part of the work, Waypoint should also send screenshots of the relevant UI states so the user can see the evidence directly.
|
|
167
|
+
|
|
166
168
|
## What makes it different
|
|
167
169
|
|
|
168
170
|
Waypoint is not trying to hide everything behind hooks and background machinery.
|
package/package.json
CHANGED
|
@@ -118,6 +118,7 @@ Anti-cheating rules:
|
|
|
118
118
|
- Use `playwright-interactive`.
|
|
119
119
|
- Exercise the actual UI instead of mocking the flow in code.
|
|
120
120
|
- Keep the scope focused on the feature the user asked you to verify.
|
|
121
|
+
- Capture screenshots of the important states you observe so the user can see the evidence directly.
|
|
121
122
|
|
|
122
123
|
## Step 7: Try To Break It On Purpose
|
|
123
124
|
|
|
@@ -151,6 +152,7 @@ As you test, keep expanding the break log with new "What if...?" cases that emer
|
|
|
151
152
|
- Update docs when the verification exposes stale assumptions about how the feature works.
|
|
152
153
|
- Update the break log entry for each attempted action with what happened and whether the feature survived.
|
|
153
154
|
- Require a short observed-result note for every executed item. "Worked" is too weak; capture what actually happened.
|
|
155
|
+
- Save screenshots for the key broken, risky, or fixed states as you go.
|
|
154
156
|
|
|
155
157
|
Do not stop at the first bug.
|
|
156
158
|
|
|
@@ -174,6 +176,7 @@ Summarize:
|
|
|
174
176
|
- the path to the break log markdown file
|
|
175
177
|
- how many attack items were recorded and exercised
|
|
176
178
|
- how coverage was distributed across steps and categories
|
|
179
|
+
- which screenshots you captured and what each one shows
|
|
177
180
|
- what break attempts you tried
|
|
178
181
|
- which issues you found
|
|
179
182
|
- what you fixed
|
|
@@ -54,6 +54,9 @@ If something important lives only in your head or in the chat transcript, the re
|
|
|
54
54
|
- When waiting on reviewers, subagents, CI, automated review, or external jobs, wait as long as required. There is no fixed timeout where waiting itself becomes the problem.
|
|
55
55
|
- Never interrupt in-flight work just to force a partial result, salvage something quickly, or avoid making the user wait longer.
|
|
56
56
|
- Only stop waiting when the work has actually finished, clearly failed, or the user explicitly redirects the work.
|
|
57
|
+
- When browser work is part of reproduction or verification, send screenshots of the relevant UI states to the user so they can visually confirm what you observed.
|
|
58
|
+
- Capture the states that matter, such as the broken state, the fixed state, or an important intermediate state that explains the issue.
|
|
59
|
+
- If the current environment cannot provide screenshots, state that explicitly instead of silently omitting visual evidence.
|
|
57
60
|
|
|
58
61
|
## Execution autonomy
|
|
59
62
|
|
|
@@ -68,6 +68,7 @@ Prefer existing persisted context over re-interviewing the user.
|
|
|
68
68
|
|
|
69
69
|
If the user approves a plan or explicitly tells you to proceed, treat that as authorization to execute the work end to end. Do not stop mid-implementation for incremental permission unless a real blocker, hidden-risk decision, or explicit user redirect requires a pause.
|
|
70
70
|
When work is in flight elsewhere — reviewer agents, subagents, CI, automated review, external jobs, or other waiting periods — wait as long as required. There is no fixed waiting limit, and slowness alone is not a reason to interrupt or abandon the work.
|
|
71
|
+
When using a browser to reproduce a bug, verify behavior, or confirm that a fix works, send the user screenshots of the relevant UI states so they can see the evidence directly. If screenshots are not possible in the current environment, say so explicitly.
|
|
71
72
|
|
|
72
73
|
Working rules:
|
|
73
74
|
- Keep `.waypoint/WORKSPACE.md` current as the live execution state, with timestamped new or materially revised entries in multi-topic sections
|