You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 02e4366
Browse filesBrowse the repository at this point in the historyBrowse files
fix(exec): keep the gate's full mxbuild output in a per-run log (#452)
fix(exec): keep the gate's full mxbuild output in a per-run log. Independent review: APPROVE.
Verdict: APPROVE
r3 on head after merging the fixed#451 (f4cc5ae, fd90628) into fix/gate-full-log; the merge was clean. r2 APPROVE stands. gate-log 24/24 and gate-retry 24/24 on the merged head, check-pr-discipline clean. Merges after #451.
Copy file name to clipboardExpand all lines: CHANGELOG.md
+1Lines changed: 1 addition & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -19,6 +19,7 @@ Sections dated before 2026-09-19 predate the cycle and stay as they are. Named m
19
19
20
20
## Unreleased
21
21
22
+
- fix(exec): **the gate keeps mxbuild's full output in a per-run log and names it on screen and in the BUILD-LOG row.** exec.sh printed `head -20` of the output and deleted the rest, so the evidence of a failed gate (a CE1613 detail among it) was lost in a field migration project (12 modules). A gate that does not pass now writes `.mpr-snapshots/.mxbuild-logs/<run>.log` (newest 30 kept; a dot dir, so `restore-mpr.sh` and the snapshot pruning skip it; a clean or delta-gate pass writes none, and a retry always keeps the first attempt's output next to the second); the screen shows the top lines plus the path and the row ends with `mxbuild log: <path>`. Test: `tests/wave2/test-exec-gate-log.sh` (Refs #442, #448, #171, #285, #424) — field migration project
22
23
- fix(exec): **the gate pauses this project's `mxcli run --local --watch` while mxbuild runs and retries once on an infra exit.** The gate's mxbuild and a live watcher both write `deployment/`; in a field migration project (12 modules) 17 of 27 failed gates were "gate could not run" (mxbuild exit 1, no CE code), against 0 of 22 in watcher-free copies. The watcher is stopped (SIGSTOP) for the gate and resumed (SIGCONT, also in the EXIT trap); an exit 1 or 3 with no CE code and no errors file is retried once and the BUILD-LOG row says `retry after infra exit`; a final failure still takes the #424 rollback. The match is exact (the watcher's project dir must equal this project's root, so a sibling `-copy` or a nested worktree watcher is never paused), and the paused pids are recorded in `.mpr-snapshots/.watcher-paused` so the next exec.sh resumes a watcher left stopped by a SIGKILLed one and says so. Test: `tests/wave2/test-exec-gate-retry.sh` (Refs #441, #444, #171, #285, #424) — field migration project
23
24
- learn(load-test): **trap 9, an unlicensed local runtime caps concurrent sessions at 6 ("Maximum number of sessions exceeded!") and stops itself after a random 2 to 4 hours, both reading as the app failing under load; more than 6 users needs a licensed runtime or a cloud sandbox.** Text only, ondemand skill. Source: a personal licence-budget gate written after parallel journey runs hit both — MendixMau
24
25
- fix(progress-report): **the full plan tables (one table per phase plus views A and B) now sit in one closed `<details>` card below the phase cards, so a large plan no longer pushes the rest of the report off screen; the phase cards above stay the summary, and nothing is written when the project has no plan fragment.** Test: P6 in `test-progress-report-polish.sh` — MendixMau
0 commit comments