Skip to content

Commit 7e58e0a

Browse files
test(cli): put serve-mcp-stdio-early-initialize's test-budget on the 10 s grid at its CI reading (#23181 slice 6) (#24494)
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

File tree

‎packages/cli/test/serve-mcp-stdio-early-initialize.integration.test.ts‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
// Copyright (c) 2026 ObjectStack. Licensed under the Apache-2.0 license.
2-
// test-budget: 15 — spawns the real producer once per single-cause fixture: three runs of the built CLI (a `serve --dev` that mints the stdio key, an `os compile` for the artifact, then the `os serve` under test); 11.6 s, the slowest of four local runs on a shared container, x 1.25, no CI reading yet
2+
// test-budget: 20 — spawns the real producer once per single-cause fixture: three runs of the built CLI (a `serve --dev` that mints the stdio key, an `os compile` for the artifact, then the `os serve` under test); 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
33

44
/**
55
* #24191 — `os serve` with the stdio MCP transport enabled and NO config

0 commit comments

Comments
 (0)