fix(killtracker): v2.12 codex tracking#2336
Open
mrhoribu wants to merge 3 commits into
Open
Conversation
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughWalkthroughAdds codex find/search persistence and counters, parses codex-found and onslaught-search events, enforces weekly-cap eligibility, snapshots and backfills weekly codex totals, adds summary and detailed codex reports, supports external spreadsheet submission for codex records, and hardens YAML loading/validation. ChangesCodex Tracking Feature
🎯 4 (Complex) | ⏱️ ~45 minutes 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@scripts/killtracker.lic`:
- Around line 425-426: Don't reset $killtracker[:weekly_codex_searches] unless
you also rebuild it; remove the line that sets
$killtracker[:weekly_codex_searches] = 0 or replace it with logic that
recomputes weekly_codex_searches from the same data used to rebuild
$killtracker[:weekly_codex]. Locate the assignments to
$killtracker[:weekly_codex] and $killtracker[:weekly_codex_searches] and either
only zero/recompute weekly_codex or add code to aggregate existing kill
records/events into $killtracker[:weekly_codex_searches] (same
time-window/bucketing logic used for weekly_codex) so the count remains correct
after running the fix.
- Around line 1225-1228: The codex event is currently recording the gem search
counter ($killtracker[:weekly_ascension_searches]) into ev[:searches_week] which
miscounts codex-only eligibility; change the stored value to the codex counter
($killtracker[:weekly_codex]) so that the codex record created at
$killtracker[:codex_found][key] uses $killtracker[:searches_since_codex] and
$killtracker[:weekly_codex] (keep the existing keys searches_since and
searches_week).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: d9d5712d-6b9d-4984-8123-db387ee567f9
📒 Files selected for processing (1)
scripts/killtracker.lic
Comment on lines
+425
to
+426
| $killtracker[:weekly_codex] = 0 | ||
| $killtracker[:weekly_codex_searches] = 0 |
Contributor
There was a problem hiding this comment.
Don't zero weekly_codex_searches unless you also rebuild it.
This method recomputes weekly_codex, but not weekly_codex_searches. After ;kt fix find count, the codex summary added in this PR will show 0 current-week codex searches until more kills arrive, even if the previous value was correct.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@scripts/killtracker.lic` around lines 425 - 426, Don't reset
$killtracker[:weekly_codex_searches] unless you also rebuild it; remove the line
that sets $killtracker[:weekly_codex_searches] = 0 or replace it with logic that
recomputes weekly_codex_searches from the same data used to rebuild
$killtracker[:weekly_codex]. Locate the assignments to
$killtracker[:weekly_codex] and $killtracker[:weekly_codex_searches] and either
only zero/recompute weekly_codex or add code to aggregate existing kill
records/events into $killtracker[:weekly_codex_searches] (same
time-window/bucketing logic used for weekly_codex) so the count remains correct
after running the fix.
Comment on lines
+1225
to
+1228
| $killtracker[:weekly_codex] += 1 | ||
| $killtracker[:codex_found][key] = { | ||
| searches_since: $killtracker[:searches_since_codex], | ||
| searches_week: $killtracker[:weekly_ascension_searches], |
Contributor
There was a problem hiding this comment.
Persist the codex search counter here, not the gem search counter.
Line 1228 stores weekly_ascension_searches into codex events, but codex eligibility is now tracked independently. Once a character is gem-ineligible but still codex-eligible, detailed codex reports, averages, and sheet exports will all undercount because they read ev[:searches_week] from this record.
Suggested fix
$killtracker[:codex_found][key] = {
searches_since: $killtracker[:searches_since_codex],
- searches_week: $killtracker[:weekly_ascension_searches],
+ searches_week: $killtracker[:weekly_codex_searches],
name: name,
room: room,
creature: $killtracker[:creature]
}🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@scripts/killtracker.lic` around lines 1225 - 1228, The codex event is
currently recording the gem search counter
($killtracker[:weekly_ascension_searches]) into ev[:searches_week] which
miscounts codex-only eligibility; change the stored value to the codex counter
($killtracker[:weekly_codex]) so that the codex record created at
$killtracker[:codex_found][key] uses $killtracker[:searches_since_codex] and
$killtracker[:weekly_codex] (keep the existing keys searches_since and
searches_week).
This PR addresses: - Validate YAML loads before using persisted Killtracker data as Hash-backed state. - Guard legacy migration paths so malformed event entries do not call Hash methods on non-Hash values. The remaining items may be issues, but are historical in context and need careful evaluation before addressing: - Permissions to send data offsite may be ignored or overridden in some identified cases. - Startup performs gem installation for missing dependencies. - Network submissions have no timeout and treat any HTTP response code as success. - File paths include runtime identity values directly. - Restore command handling appears shadowed by the broader backup command. - Global mutable Killtracker state is exposed process-wide.
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.
Summary by CodeRabbit
New Features
Bug Fixes