Repository navigation
Commit 7e58e0a
Part of #23181
Clause-②: no — basis: the diff is one header comment of a test file
under `packages/cli/test/`, outside `@objectstack/cli`'s `files`
(`dist`, `README.md`, `CHANGELOG.md`); nothing ships, and no accept set
or public surface moves.
This puts line 2 of
`packages/cli/test/serve-mcp-stdio-early-initialize.integration.test.ts`
on the 10 s grid, at its CI reading. The header declared 15 s from a
local timing, so `measure-test-shard-timings.mjs --diff` refused it
(`readTestBudget`: "the budget 15 s is not on the 10 s grid"). Because
of that refusal, the weekly refresh PR #24467 (run 39205844620) reports
"Regression readings: NOT MEASURED -- the diff refused (exit 1)" for
every lane. Only line 2 changes. The class, the test body and every
other file are untouched.
## The CI reading
- **Source.** The refresh run 39205844620 accumulated 7 hourly
full-battery `schedule` runs. Its log reads "Accumulated 7 run(s):
39202368342 39197429467 39192681060 39188268133 39184708096 39178996284
39174682274", and its dataset (PR #24467 head `1f11e11f0`) names the
same 7 in `provenance.runs`. I downloaded all 42 of their per-file
captures (`test-core-timings-N-of-6`, written by
`report-test-timings.mjs --capture`).
- **How it was read.** The script's own `readWindowCaptures` and
`windowFiles` read the captures, with declarations not read. That takes
the refusal out of the way without changing the script. The file
executed in all 7 runs, none of them replayed, in project `integration`
on Test Core shard 3/6:
| run | ms |
|:--|--:|
| 39174682274 | 8613 |
| 39178996284 | 13232 |
| 39184708096 | **14999** (slowest) |
| 39188268133 | 14838 |
| 39192681060 | 14699 |
| 39197429467 | 12025 |
| 39202368342 | 10872 |
- **Corroborated.** The job log of run 39184708096, `Test Core (3/6)`
(job 117844650149), prints
`test/serve-mcp-stdio-early-initialize.integration.test.ts (1 test)
14999ms`.
- **The same file.** The file is byte-identical at the oldest and newest
window heads (`2a1e48a1c1`, `725a5b1311`) and at this branch's base
`4bd7215a1` (`git diff --quiet`, exit 0 on each). The reading is a
reading of this file.
## The arithmetic
SECONDS is the measured CI reading x 1.25 (`CEILING_HEADROOM`), rounded
up to the next 10 s (ruling records 6181973363 item 2 and 6212133431
item 2):
14.999 s x 1.25 = 18.749 s, which rounds up to **20 s**. That is above
the 10 s line, so the file still owes a budget.
The CLASS is unchanged: `spawns the real producer once per single-cause
fixture`. The REASON keeps the producer description. It now names the
reading, its run, and why the number rose, in the shape the spec lane's
re-measured lines use: "re-measured 2026-10-19 over the 7 hourly runs
that executed it (39174682274 to 39202368342, the window of
shard-timings refresh run 39205844620): slowest CI reading 15.0 s (run
39184708096, 14999 ms) x 1.25, rounded up; rose from 15, which rested on
a local reading and was off the 10 s grid".
## The census
I ran `readTestBudget`, the script's own reader, over every tracked file
whose text has a test-budget-shaped comment. The file list comes from a
`git grep -I -i -E` that matches everything the script's attempt pattern
matches, and more. Three trees:
| tree | files | declare | refused | no declaration |
|:--|--:|--:|:--|--:|
| `e11ae4b6b` (the seat's census) | 21 | 19 | 1: this file, "the budget
15 s is not on the 10 s grid" | 1 (the script itself) |
| `4bd7215a1` (this branch's base) | 21 | 19 | 1: the same | 1 |
| `c79774fe1` (this branch) | 21 | 20 | **0** | 1 |
The seat's reading holds: this header was the only one off the grid.
With this line, the refusal set is empty.
**End to end.** I re-ran the refresh's own `--diff` in this worktree, on
the same inputs:
- prior: `scripts/test-shard-timings.json` at `ec951e29e`, the refresh's
base;
- refreshed: PR #24467's dataset;
- captures: the 42 above.
The results:
- On `4bd7215a1` it exits 1, with the same refusal as run 39205844620's
log.
- On `c79774fe1` it exits 0 and reports "127 file(s) over budget (10 s,
or the 20 declared)". This file is listed under "Held to the budget it
declares" as "15.00 s of its 20 s".
## No changeset
`skip-changeset` is applied in the create stroke. The basis:
- The file is under `packages/cli/test/`, and `@objectstack/cli`'s
`files` is `dist`, `README.md`, `CHANGELOG.md`.
- After a build of the package, `grep -rl -e
serve-mcp-stdio-early-initialize -e test-budget dist README.md
CHANGELOG.md` finds 0 files, with 652 files in `dist`.
- Positive control: `ignoreStdin`, the `serve` behaviour this file pins,
is found in `dist/commands/serve.js`.
## Local verification (head `c79774fe1`)
- **The file itself** (`--project integration`, this one file): 1 file
and 1 test passed, 13.76 s on a shared container.
- **`pnpm --filter @objectstack/cli typecheck`:** exit 0. That covers
tsc and the test layer's `check:test-typecheck`.
- **The `@objectstack/cli` unit tier** (`--project unit
--maxWorkers=2`): 311 files and 4610 tests passed, exit 0.
- **`dispatch-gates.mjs --commands`:** 52 families, all exit 0. The
three that read `dist/` passed after the build.
- **`--ran` reconciliation:** 52 run, 0 NOT-MEASURED, 0 UNRUN.
- **The 11 declared-wide families:** all exit 0.
- **Still to come:** `pnpm lint` and the CI check-runs for this head are
reported in the `os-dev-report` comment on the card.
## Acceptance notes
These readings come from the same window. They belong to the card's
rows, not to this PR, and are not changed here:
- Two `@objectstack/cli` files ran over the budgets they declare:
-
`src/commands/migrate/plan.declared-default-datasource.integration.test.ts`:
93.22 s against its 80 s;
- `test/start-stdio-stdout-purity.integration.test.ts`: 20.30 s against
its 20 s.
- Two cli headers still say "no CI reading yet", and their CI readings x
1.25 now round above what they declare:
- `test/start-mcp-stdio-early-initialize.integration.test.ts`: 18.96 s,
which gives 30;
- `test/start-stdio-stdout-purity.integration.test.ts`: 20.30 s, which
gives 30.
- `@objectstack/spec`'s `src/shared/alias-integrity.test.ts` read 51.09
s against its 50 s. That is the spec lane's row.
- The next refresh lists all of these, now that its diff can run.
---
_Generated by [Claude
Code](https://claude.ai/code/session_01SYEJqDL3NXxrJRBVqaMu9T)_
Co-authored-by: Claude <noreply@anthropic.com>
1 parent 959ee31 commit 7e58e0a
1 file changed
Lines changed: 1 addition & 1 deletion
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
1 | 1 | | |
2 | | - | |
| 2 | + | |
3 | 3 | | |
4 | 4 | | |
5 | 5 | | |
| |||
0 commit comments