Only automation bot PRs re-check source-issue pending comments before
mark-ready, so maintainer Fixes-only PRs are not stuck draft. Write
WebSearch/WebFetch denials after the isolated research pass so classify
and follow-up research can still call those tools.
Embed self-hosted light/dark star history charts after api.star-history.com
stopped serving public embeds, and add a weekly workflow that refreshes them
via RELEASE_TOKEN.
- Format recovery dispatches triage before clearing invalid-format
- Shared CJK-friendly title rules; codex label terminal state machine
- Research steps in classify; agent TITLE + PR body for bot PRs
- Single @codex review via CODEX_REQUEST_GITHUB_TOKEN (binaricat)
Use TRIAGE_GITHUB_TOKEN for Codex review loop jobs. Treat convert-to-draft
and mark-ready permission errors, and closed PRs, as warnings so @codex
still runs instead of failing the whole automation job.
Public issue comments no longer show a generated-by line. Grounding stays
in code_findings/reasoning only so reply can use UI language without file
paths, symbols, or dense parentheses. Classify prompt and rewrite templates
match that tone.
Use the bot PAT for classify prepare/apply and implement needs-human
comments so issue activity shows netcatty-bot instead of github-actions.
Treat netcatty-bot as an own actor for automation PR loops.
* fix(ci): stop Cursor issue triage crashing on Search pagination
Octokit normalizes Search API pages so response.data is already the items
array. Mapping response.data.items returned undefined and then crashed on
candidate.user during daily-limit admission — so every valid new issue
failed before Cursor classify could run.
* fix(ci): classify already-available issues with how-to and auto-close
Add an already_available triage category for requests the product already
ships: after code-grounded inspection, reply with the concrete UI entry
path, then close as completed. Low confidence falls back to other instead
of closing. Keeps the Search pagination fix so new issues can classify.
Classification must open real source files first. The prompt mandates
search→read→classify, JSON now requires code_paths/code_findings, and
normalizeClassification rejects ungrounded replies so agents cannot answer
from issue text alone.
Cursor's --sandbox enabled fails on ubuntu-latest due to AppArmor, so classify
and implement jobs never ran. Use --sandbox disabled and keep secret isolation
via token stripping, frozen helpers, and post-run scans.