justinzeus/scholarr
1
0
Fork 0
Code Issues 2 Pull requests Projects Releases Packages Wiki Activity Actions

Prioritize the expiring reset window without reducing product scope

Browse source
This commit is contained in:
justinzeus 2026-10-03 12:16:15 +02:00
parent 44e7518071
commit 19c33057b2
1 changed files with 17 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

27
SPRINT.md
View file

@ -4,7 +4,7 @@
Justin authorized preparation, issue triage, and a new baseline commit. He has
not authorized launch. Review this document as the single product and execution
reference for the proposed 24-hour run. Approval tracking: justinzeus/scholarr#9.
reference for the proposed expiry-priority run. Approval tracking: justinzeus/scholarr#9.
Runner preparation: justinzeus/nightly#92; reset supervisor: justinzeus/nightly#93.
An explicit owner go for the concrete plan approves the proposed defaults below
@ -31,7 +31,9 @@ The target after the run is one integrated, runnable product branch and one
reviewed PR, with executable acceptance evidence and a usable installation path.
A pile of independent PRs, a static UI demonstration, mock-only provider clients,
or a service with omitted authentication modes does not meet the target.
Twenty-four hours is a delivery target, not a promise that unfinished work is done.
The original target was twenty-four hours. Justin selected expiry priority once
the remaining credit window became shorter: reduce the time budget, not these
product requirements. An unfinished gate is not completed delivery.
The run does not deploy, merge into main, publish a release, import the real
household database, or replace the existing workflow. Justin still performs
@ -227,7 +229,7 @@ not exercise a sanitized copy; list that validation as owner-side acceptance.
| Provider/model | `openai-codex/gpt-6.1-sol` in scope, writer, escalation, spec review, and standards review. |
| Thinking | `xhigh` in all five slots. Never change this sprint to `max`. |
| Codex budget/floor | 100 window points / 0% remaining reserve; the available subscription balance is the practical bound. |
| Night/issue wall | 1,440 active minutes each; subscription pauses do not consume the issue wall, but do consume the night wall. |
| Night/issue wall | At most 1,440 active minutes each, shortened for the actual go window to leave the 120-minute session allowance before the three-hour wind-down. Subscription pauses do not consume issue wall but do consume night wall. |
| Issue token guard | 100 million non-cached tokens; finite secondary guard, not a target. |
| Role session | Existing 120-minute cap and idle detection. |
| Concurrency | One project issue; the two independent review roles may run together. |
@ -235,15 +237,20 @@ not exercise a sanitized copy; list that validation as owner-side acceptance.
| Data-provider requests | Local fixtures in writer/review sandboxes; separate operator acceptance allowance of six real requests, never a crawl. |
| End | All acceptance complete, quota exhaustion, wall cutoff, or a reported safety/stuck condition. No filler work to burn remaining quota. |
Nightly checks the night wall between role sessions. A role or verification
already running may finish after the 24-hour scheduler cutoff; this plan does not
claim an exact process-kill deadline. Only reviewed, verified commits count as
output. Exhausting quota may interrupt an item and discard its uncommitted work;
completed items remain on the integration branch.
The final approval packet records the requested wall and latest safe go time,
derived from the pinned wind-down deadline minus that wall and the 120-minute
session allowance. If owner go arrives later, do not claim the original packet
still fits: re-evaluate timing before launch or arming. Nightly's walls are soft;
a running role or verification may finish after cutoff, and a draining stop is
honored between work items. This is not a process-kill deadline or a guarantee
of redemption. Only reviewed, verified commits count as output. Quota exhaustion
may interrupt an item and discard uncommitted work; completed items remain on
the integration branch.
Operator-owned ceiling configuration permits the larger wall/token/budget values;
ordinary presets keep their existing defaults. The Scholarr preset requests the
larger values explicitly. Freeze the runner settings in the saved draft and keep
ordinary presets keep their existing defaults. The Scholarr preset explicitly
requests the selected expiry-priority walls and larger token/budget guards.
Freeze the runner settings in the saved draft and keep
no model fallback. Approval builds/checks the Go and Node image without calling a
model. Launch spends subscription quota and requires Justin's explicit go on the
resolved plan, not merely permission to prepare it.