chore(release): v1.91.37.0 changelog and TODOS

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
This commit is contained in:
garrytanandcapy-ai[bot] committed 2026-10-08 06:23:03 +00:00
1 parent 8b8b34d41e
commit b69616278c
5 files changed
+45 -3

No files matched your search

+25
View File
@@ -1,5 +1,30 @@
# Changelog
## [1.91.37.0] - 2026-10-07
**Your first /office-hours session gets the first-session closing again, and you see the design doc before you approve it.**
/office-hours logged the session to your builder profile and then read the profile to choose its closing, so every run counted itself as history. A first-time user got the "welcome back" closing, never saw the introduction, and was asked how the assignment they had just been given went. Every later tier was one session early too. Separately, the approval question showed up while the design doc sat in a collapsed tool output, and a session that never wrote a doc could still be logged as a success.
### What this means for you
Run `/gstack-upgrade`, then start `/office-hours` on a new idea. Before the doc is saved you'll see a `Builder profile before this session:` line. On a first session it says `SESSION_TIER=introduction PRIOR_SESSION_COUNT=0`, and the closing is the introduction. `gstack-timeline-read --limit 1abc` now exits 2 and shows an example instead of quietly reading one event.
### Itemized changes
#### Fixed
- /office-hours reads your builder profile before it logs the session and carries the earlier tier, count and last assignment to the closing. This session is counted as the prior count plus one. If the profile can't be read, it treats the session as your first and tells you so. (#2801)
- /office-hours prints the complete design doc in the conversation before asking you to approve it. (#879)
- /office-hours logs `success` only when this run's own design doc exists and isn't empty. It checks the doc's exact path under your gstack state root. A session that ends without a doc is logged as `abort` or `error` with failed step `design_doc`. (#1049)
- `/plan-ceo-review`, `/plan-eng-review`, `/plan-devex-review` and `/autoplan` skip the "run /office-hours first?" offer in spawned and headless sessions, where nobody can answer it, and continue with the standard review. (#1958)
- `gstack-timeline-read --limit` takes only a positive integer. A missing value, `0`, `-5`, `abc` or `1abc` exits 2 with `--limit must be a positive integer (got '<value>'); example: --limit 20`, whether or not the project has a timeline. Without the flag you still get 20 events. (#1723)
- Skill start prints `SESSIONS: N`, the number of gstack sessions active in the last two hours, so CLAUDE.md rules that read the session count have a value. (#1651, part A)
#### For contributors
- New tests in `test/gen-skill-docs.test.ts` run the rendered office-hours profile read, session log and design-doc check against a temporary state root. `test/timeline.test.ts` covers each bad `--limit` on empty and populated histories. `test/gstack-skill-start.test.ts` covers the `SESSIONS` count. The office-hours, plan-eng-review and autoplan parity caps include the measured growth.
Contributed by @kikearciniegas (#2801), @kichinosukey (#879), @RyanAlberts (#1116), @walton-chris (#1049), @aviraldua93 (#1958), @jbetala7 (#1723, #1724), @TJ-NomoAI (#1651) and @0xDevNinja (#1747).
## [1.91.36.0] - 2026-10-07
**Python and Rails repairs can now reach `runtime_tested` and replay, and a killed verification leaves nothing behind.**
+17
View File
@@ -2,6 +2,23 @@
## NEXT PRIORITY
### P2/P3: office-hours and timeline follow-ups (filed 2026-10-07, v1.91.37.0)
Left open by the office-hours tier fix (#2801, #879, #1049, #1958, #1723, #1651 part A).
- **Session markers that reflect "currently active" (#1651 part B)** — skill
start touches `sessions/<pid>` only when a skill starts, so a long session
with no new skill for two hours drops out of `SESSIONS: N`. Fix shape: refresh
the marker per tool call from a hook. **Effort:** M. **Priority:** P3.
- **Live eval for the first-session closing** — free tests run the rendered
profile read and session log in order, but no paid case checks that a model
follows the carried `SESSION_TIER` through Phase 6 (first run gets the
introduction, second run asks about the earlier assignment). No office-hours
quality judge exists either. **Effort:** M. **Priority:** P2.
- **`gstack-timeline-read --since`/`--branch` without a value** — both still
read an unbound `$2` under `set -u` and crash with exit 1, the class #1723
fixed for `--limit`. **Effort:** S. **Priority:** P3.
### P2/P3: Oct 7 fix-wave follow-ups (filed 2026-10-07)
Left open by the Oct 7 wave (docs/designs/FOLLOWUP_WAVE_2026_10_07.md), each with its reason.
+1 -1
View File
@@ -1 +1 @@
1.91.36.0
1.91.37.0
+1 -1
View File
@@ -1,4 +1,4 @@
# gstack digest v1.91.36.0 — regenerate/re-copy after upgrading gstack
# gstack digest v1.91.37.0 — regenerate/re-copy after upgrading gstack
Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed
for agent hosts without a full skill install. The full skills add workflows,
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "gstack",
"version": "1.91.36",
"version": "1.91.37",
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
"license": "MIT",
"type": "module",