LinearB Agent Plugins changelog

agentic-advisor 1.3.0

2026-10-12T00:00:00Z

The troubleshooting log is now on by default, so a missing event can be diagnosed without asking the user to re-run anything. Turn it off with LINEARB_DEBUG=0. It stays local and private (0600), rotates at 1 MB, and never contains the token, prompt or payload.
The log now covers the trigger hook too: when it nudged the agent to run the skill, and when it held a tool call for the grade or the verdict line.
Every line starts with the plugin version.

Errors are logged with their reason: network failures with curl's exit code and message, and rejected events (4xx/5xx) with the server's response, emails redacted.

2026-10-11T00:00:00Z

Ticket context: when the prompt or branch names a ticket (e.g. ABC-123), the skill fetches its type, priority, estimate and labels from LinearB (one call, same token) and uses them to raise the task-complexity grade, e.g. a Highest-priority bug. Skipped silently when there's no key or no PM integration. #10

2026-10-11T00:00:00Z

Opt-in troubleshooting log: LINEARB_DEBUG=1 writes each report's outcome (skip reason or HTTP status) to ${XDG_CACHE_HOME:-~/.cache}/agentic-advisor/report.log, rotated at 1 MB. Lines for sent events include the grade and repo name; no line contains the token, email, prompt or payload. The log stays private (folder 0700, file 0600, symlinked logs and rotation targets refused). #9

With no LINEARB_API_TOKEN, the verdict now says LINEARB_API_TOKEN not set and tells the user how to set it, instead of a generic "signals unavailable" that looked like a working setup. #9
Hooks no longer fail under set -u when HOME and XDG_CACHE_HOME are both unset. #9

2026-10-08T00:00:00Z

Send effort grades from interrupted turns at SessionEnd (tagged backfill: session_end). #4
Retry a grade whose Stop fired before the repo was resolved. #4

2026-10-07T00:00:00Z

Hold the next tool call once until the verdict line is printed, so grades kept in thinking are still recorded. #3
Verdict line format documented in SKILL.md, with a printf fallback. #3

2026-10-06T00:00:00Z

agentic-advisor skill: grades LOW / MEDIUM / HIGH effort from LinearB signals and local git history. #1
Trigger hook that runs the skill before the first code change in a repo. #1
Opt-out usage telemetry to your own LinearB org (LINEARB_TELEMETRY=0). #1