Repository navigation
Commit 452325e
<!-- claude-projects-attribution: {"github_login":"os-project-manager"}
-->
_Requested by **Leehom** · [project
thread](https://claude.ai/code/project/chan_01TenzsRopZj4jMbvjX8uz1X?thread=cmsg_01TenzsRopZj4jMbvjX8uz1XXuave2865k2HHU58dWCeVS)_
Part of #25521
Clause-②: no
Metadata-protocol: none
Ruling-ref: 6270097840
Ruling-ref: 6348891160
## 维护者速读
- **改了什么**:把 `sql-driver.ts` 里「延迟建表 DDL」小节的三个预览方法体(`os migrate plan`
用来列出待执行工作的 `previewDeferredSchemaWork`,以及它调用的日期时间、时间两类存储收敛预估
`previewDatetimeConvergence`、`previewTimeConvergence`)原样搬进已有的
`sql-driver-schema-sync.ts`;类上三个方法全部保留,只把方法体转交过去,`SchemaSyncHost` 按需增补 6
个成员。
- **为什么改**:#25521 拆分超大文件的第 18 刀;第 17
刀合入后重新测量,这是仍成一个区域、收益最大且不碰任何系列限制的部分,`sql-driver.ts` 减少 74 行。
- **风险与回滚**:纯搬移,无行为变化;三个 SQL 驱动的测试两端逐条一致,公开类型声明哈希不变,41 条探针读数两端一致(仅 2
条栈顶接收者名不同)。回滚即还原本 PR。
- **先看**:`sql-driver-schema-sync.ts` 头注释新增的第 18 刀段落与 `SchemaSyncHost`
新增成员;`sql-driver.ts` 中三个方法的转交桩;`sql-driver.ts` 顶部 `fieldHasColumn`
改为类型导入的那一行。
- **两分钟验证**:`pnpm --filter @objectstack/driver-sql exec vitest run
src/sql-driver-deferred-ddl.test.ts
src/sql-driver-deferred-datetime-convergence.test.ts
src/sql-driver-time-canonical-storage.test.ts
src/sql-driver-6009-backfill-julian-day-guard.test.ts`,预期全部通过。
- **需要你做的**:无,席位落地。
## What changes
Cut 18 of the `sql-driver.ts` split (#24586 ruling A, recorded in
`6270097840`). The claim is `6449288193`. Cut 17 (#26808) merged first,
as `f1cd529dd2`; this cut opens with a fresh seam table taken on that
commit (below) and takes the area cut 17 priced next, which still pays
best without breaking a series limit: the **deferred-DDL previews**
(`Schema Sync › Deferred schema DDL (#3917)`). Their bodies move
unedited into the **existing** seam module
`packages/drivers/driver-sql/src/sql-driver-schema-sync.ts`, through its
host `SchemaSyncHost`, beside the canonical-encoding convergence (cut
12) whose predicates and `information_schema` reads they call:
- `previewDeferredSchemaWork`, the read-only plan `os migrate plan` and
`os migrate apply` render: per deferred object, `create_table` or
`add_columns` (only fields that materialize a column), the #22506
rotation answer, and the two convergence entries below;
- `previewDatetimeConvergence` and `previewTimeConvergence`, which it
calls: the datetime and time storage-convergence work the SQLite
backfills and the MySQL widenings would do, measured and not performed
(#3954).
No module-level declaration moves. `fieldHasColumn` (from
`./schema-drift.js`) loses its last value reader in `sql-driver.ts`; the
staying docblock of `previewDeferredSchemaWork` still links it, so the
import there becomes `type fieldHasColumn` in place (a link-only import
is a type import, erased from the build, as cut 17 did for
`undeliveredStorageAttributes`). The module imports `fieldHasColumn` and
`type PendingSchemaWork` from `./schema-drift.js` through its existing
import line; `SQLITE_NON_TEMPORAL_TEXT_REFS` and `SQLITE_TIME_EXPR_REFS`
it already imported from `./sql-driver.js`.
The change is move-only, and the card stays open for later cuts. There
is no `docs/adr/**` edit, no `packages/spec/**` edit, no anchor entry
change, no gate edit, no test edit and no new gate. Branch
`claude/project-thread-m210nw` (the platform assigned it to this card
thread, as the claim records). The move is one commit, `028cda6cf`, on
`f1cd529dd2`, followed by one merge of `origin/main` (`5787df4d4b`, 15
commits, none in `packages/drivers/**`); the head is `7065d8e1d0`.
**Net line count (the seat's rule).** `sql-driver.ts` goes from 18,521
lines to 18,447: **-74**.
- **Out:** the three bodies, 119 lines plus their closing braces (45 +
37 + 37).
- **In:** the three stub bodies, 43 lines (13 + 15 + 15), and 2 comment
lines above the existing `sql-driver-schema-sync.js` import, whose one
line gains the three names. The `fieldHasColumn` import line changes in
place.
- `sql-driver-schema-sync.ts` goes from 1,914 to 2,066 lines (+152): the
three functions, 6 new `SchemaSyncHost` members (74 to 80) and a header
paragraph. No import line is added.
**Path readers.** No test, script, doc, ADR or anchor entry reads any of
the three bodies by path, so none is migrated (screen below).
**Serial with the file's in-flight PRs.** I read the file list of every
open PR on `objectstack-ai/objectstack` at the start (38) and again
before opening this one (40). None touches `sql-driver.ts`,
`sql-driver-schema-sync.ts`, `turso-driver.ts`, `sqlite-wasm-driver.ts`,
`check-tenant-chokepoint.mjs` or a driver-sql anchor entry; #26808 (cut
17) was the one that did, and it merged before this cut was measured.
#26556 (dependabot) touches only `driver-sql/package.json`.
## Seam table, fresh, on `f1cd529dd2`
- **Size and churn.** `sql-driver.ts` is 18,521 lines. The 30-day column
counts `git blame` lines from commits on or after 2026-09-27T17:26:58Z,
30 days before the base commit. `scripts/pm/git-history.mjs count`
proves 77 commits on the file in 30 days and 31 in the last 7. In all,
3,388 lines (18.3%) are from the last 30 days.
- **Class shape.** `SqlDriver` spans lines 4243-18446 with 350 members:
243 instance methods, 13 accessors and 32 statics, all 32 private or
protected.
- **How it was measured.** The same TypeScript compiler AST script cuts
9-17 used, which strips casts, parentheses, `!` and `satisfies` before
it reads `this`. Sections are the class's own banner comments.
| Lines | Section | First … last member | Lines | 30-day | Methods
(public) | Inferred public | getBuilder sites | Statics
(private/protected) |
|:--|:--|:--|--:|--:|:--|--:|--:|:--|
| 1-4242 | Module preamble | - | 4,242 | 692 | - | - | - | - |
| 4243-5834 | Class head: fields, statics, constructor, capability
getters | `name` … `assertDialectEmits` | 1,592 | 290 | 8 (1) | 1 | 0 |
18 (18) |
| 5835-6266 | Lifecycle | `connect` … `disconnect` | 432 | 155 | 8 (3) |
0 | 0 | 6 (6) |
| 6267-8673 | CRUD — IDataDriver core | `find` … `delete` | 2,407 | 745
| 43 (7) | 0 | 12 | 0 (0) |
| 8674-9203 | Bulk & Batch Operations | `bulkCreate` … `count` | 530 |
70 | 9 (6) | 0 | 7 | 0 (0) |
| 9204-9300 | Raw Execution | `rawStatementFault` …
`noteRuntimeIndexDdl` | 97 | 28 | 3 (1) | 0 | 0 | 0 (0) |
| 9301-9393 | Transactions | `beginTransaction` … `rollbackTransaction`
| 93 | 46 | 7 (5) | 0 | 0 | 0 (0) |
| 9394-9890 | Aggregation | `aggregate` …
`unresolvableAggregateColumnRefusal` | 497 | 70 | 5 (1) | 0 | 1 | 0 (0)
|
| 9891-10152 | Distinct | `distinct` …
`unresolvableDistinctColumnRefusal` | 262 | 26 | 3 (1) | 0 | 1 | 0 (0) |
| 10153-10268 | Window Functions | `findWithWindowFunctions` …
`findWithWindowFunctions` | 116 | 4 | 1 (1) | 0 | 1 | 0 (0) |
| 10269-10367 | Query Plan Analysis | `explain` … `analyzeQuery` | 99 |
1 | 2 (2) | 0 | 1 | 0 (0) |
| 10368-10426 | Schema Sync (syncSchema / init) | `syncSchema` …
`reclaimSpace` | 59 | 34 | 3 (3) | 0 | 0 | 0 (0) |
| 10427-11851 | Schema Sync (syncSchema / init) › Data-lifecycle
rotation (ADR-0057 P2) | `rotationStateByTable` …
`migrateMysqlTimeColumns` | 1,425 | 219 | 26 (4) | 0 | 0 | 0 (0) |
| 11852-12108 | Schema Sync (syncSchema / init) › Deferred schema DDL
(#3917) | `setDeferredDdl` … `flushDeferredSchemaDdl` | 257 | 25 | 6 (4)
| 0 | 0 | 0 (0) |
| 12109-12923 | Schema Sync (syncSchema / init) › Managed-schema drift &
reconcile (#2186) | `dialectName` … `createNullSafeUniqueIndex` | 815 |
237 | 23 (3) | 0 | 0 | 0 (0) |
| 12924-12975 | Schema Introspection | `listPhysicalColumns` …
`introspectSchema` | 52 | 46 | 2 (2) | 0 | 0 | 0 (0) |
| 12976-13246 | Internal helpers | `getKnex` … `auditMissingTenant` |
271 | 73 | 8 (1) | 0 | 1 | 0 (0) |
| 13247-15296 | Internal helpers › Filter helpers |
`tableNameForBuilder` … `applyFalseConstant` | 2,050 | 331 | 44 (2) | 0
| 0 | 0 (0) |
| 15297-15472 | Internal helpers › Field mapping | `mapSortField` …
`mapAggregateFunc` | 176 | 2 | 6 (0) | 0 | 0 | 0 (0) |
| 15473-15520 | Internal helpers › Window function builder |
`buildWindowFunction` … `buildWindowFunction` | 48 | 26 | 1 (0) | 0 | 0
| 0 (0) |
| 15521-17467 | Internal helpers › Column creation helper |
`nowColumnDefault` … `applyDeclaredColumnDefault` | 1,947 | 92 | 19 (0)
| 0 | 0 | 8 (8) |
| 17468-17765 | Internal helpers › Database helpers | `sqliteFilename` …
`isJsonField` | 298 | 76 | 9 (2) | 0 | 0 | 0 (0) |
| 17766-18242 | Internal helpers › SQLite serialisation | `formatInput`
… `formatOutput` | 477 | 27 | 2 (0) | 0 | 0 | 0 (0) |
| 18243-18446 | Internal helpers › Introspection internals |
`introspectColumnOrder` … `introspectUniqueConstraints` | 204 | 73 | 5
(0) | 0 | 0 | 0 (0) |
| 18447-18521 | After the class | - | 75 | 0 | - | - | - | - |
### Pricing the areas
Eligibility is as cuts 11-17 defined it: an annotated return type or not
public; no `getBuilder`, `this.FIELD.delete/insert/update(`,
private-static, `super`, bare-`this` or `this`-write site; not
`insertOnlyUpsertColumns`; not a member pinned in place (`createColumn`,
`applyFilterCondition`, `formatInput`/`formatOutput`, `initObjects`,
`ensureShardTable`, `computeTenantField`,
`migrateMysqlDatetimeColumns`/`migrateMysqlTimeColumns`,
`compileFilters`). Each area is priced as its stubs minus its bodies (a
stub costs 4 lines, +2 per field read, +1 per method read; one reading
no member costs 2), then net of the module-level declarations only it
reads and of its import edits.
| Area | Bodies | Bodies net | Declarations and imports | Disposition |
|:--|--:|--:|--:|:--|
| **Deferred-DDL previews** (`previewDeferredSchemaWork` -32,
`previewDatetimeConvergence` -22, `previewTimeConvergence` -22) | 3 |
-76 | 0 declarations move (`fieldHasColumn`, `PendingSchemaWork` and the
two `SQLITE_*` counts are shared); +2 for the import comment | **Moves
(this cut).** -74 measured. |
| Filter helpers remainder (14 small members, largest `presentReadValue`
-29) | 14 | -80 | 0; +2 or more for the import comment | Not taken:
fourteen members of four mechanisms (presentation, withheld-filter log,
canonical SQL, column expression), not one area; its largest coherent
mechanism, the withheld-filter log (`logWithheldFilterDiagnostic` -10,
`resolveWithheldFilterRefusal` -7, `withWithheldFilterLog` -6), pays
-23. `compileFilters` (-75) is refused (inferred return type). |
| Class head (`buildDateBucketExpr` -42, `installQueryTiming` -20) | 2 |
-62 | 0 | Not taken: two unrelated mechanisms, and smaller. |
| Column creation helper remainder (`nowColumnDefault` -39 and four
small members) | 5 | -62 | 0 | Not taken: smaller; the rest of that
sub-banner reads private statics. |
| `Internal helpers` tenant members (`auditMissingTenant` -26,
`applyTenantScope` -25, `getBuilder` -5, `injectTenantOnInsert` -2) | 4
| -58 | 0 | Not taken: smaller, and `applyTenantScope` holds 2 of the
file's 4 D8 predicates and `getBuilder` is the builder itself, which
`check:tenant-chokepoint` reads only in `sql-driver.ts` (series limit).
|
| CRUD remainder (`updateWithPresumedTimestamp` -31 and seven small
members) | 8 | -53 | 0 | Not taken: smaller, and two mechanisms
(autonumber probes, the presumed-timestamp update). |
## Why
### Why this area, as one area
- **One banner, one job.** The three are the members of the class's own
`Deferred schema DDL (#3917)` sub-banner that compute the plan;
`previewDeferredSchemaWork` is the only caller of the other two in the
class. They go beside the convergence code (cut 12) whose predicates
(`sqliteNonTemporalTextSql`, `sqliteCanonicalDatetimeSql`,
`sqliteCanonicalTimeSql`) and `information_schema` reads
(`legacyMysqlTimestampColumns`, `legacyMysqlTimeColumns`) they reuse, so
the plan and the work it predicts now live in one module, behind the
host that already exists.
- **It pays the most of any area that moves cleanly.** The filter-helper
remainder is larger on paper (-80) but is four mechanisms; no single one
of them pays more than -29.
- **What stays, and why.** `setDeferredDdl` and `flushDeferredSchemaDdl`
assign `this.deferredDdl` / `this.flushingDeferredDdl` (`this`-write);
`getSchemaSyncStats` reads two fields in one line (its stub would cost
more than its body); `deferredSchemaObjectCount` is an accessor.
- **No series limit is touched.** None of the three builds through
`getBuilder`, reads a static, has a `this.FIELD.delete/insert/update(`
site, uses `super` or a bare `this`, or assigns to `this`.
`previewDeferredSchemaWork` is public with an annotated return (a
promise of `PendingSchemaWork[]`); the other two are protected with the
same annotated return. `check:tenant-chokepoint`'s D8 predicates,
measured with its own `nullArmsOf`: **4 at base and 4 at head**, all in
`sql-driver.ts`, 0 in the moved bodies.
- **Durability gate.** The two convergence previews swallow a failed
probe to `[]` (by contract: under-reporting costs an unlisted step,
never a wrong one). Their `try` blocks call no member of the gate's
durability vocabulary, and `check:durability-log-level --list` gives the
same seams at both ends, line numbers aside (164 lines of output at each
end). I screened this before choosing the area, by moving the three
bodies on cut 17's head and diffing the census.
- **Subclasses.** `TursoDriver` and `SqliteWasmDriver` extend
`SqlDriver` and override none of the three. `TursoDriver`'s remote-face
ledger lists `previewDeferredSchemaWork` as `inherited`, and
`turso-remote-inherited-members.test.ts` checks that `SqlDriver`
declares it and `TursoDriver` does not redeclare it; both still hold
(the method keeps its name and signature on `SqlDriver`). Every member a
body calls is a late-bound closure on the instance (probe below).
- **Path readers, screened.** No script, test, doc or ADR names any of
the three by a `sql-driver.ts#…` pointer or a `sql-driver.ts::…` key,
and no `scripts/adr-anchors/**` record names them. Tests and the CLI
(`packages/cli/src/utils/schema-migrate.ts`) call them as driver
methods, which they still are; `turso-driver.ts` and
`remote-canonical-backfill.ts` name them in prose, which is still true.
## The shape (#23050 shape B, as cuts 1-17 apply it)
- Each class method keeps its docblock and signature, byte-identical,
less `async`. Its body is now one host literal plus `NAME.call(host,
...)`, marked `[#25521 cut 18]`. Each method returns the moved async
function's own promise, so the declared return type is unchanged and a
failure is still a rejection, never a synchronous throw (probe reading
7).
- The fields the bodies read (`deferredSchemaObjects`, `knex`,
`datetimeFields`, `timeFields`, and the getters `supportsRotation`,
`isSqlite`, `isMysql`) go as GETTERS that read the driver at call time;
the methods (`previewDatetimeConvergence`, `previewTimeConvergence`,
`rotationShardKey`, `legacyMysqlTimestampColumns`,
`legacyMysqlTimeColumns`, `sqliteCanonicalDatetimeSql`,
`sqliteCanonicalTimeSql`, `sqliteNonTemporalTextSql`) go as closures
that call the method on the driver at call time. So a subclass override,
an instance spy, or a field replaced after construction is still the one
the body reaches; in particular `previewDeferredSchemaWork` still
reaches the two convergence previews through the driver, not the module
functions directly.
- `SchemaSyncHost` grows by exactly the 6 members these bodies read that
it did not list yet (`deferredSchemaObjects`, `legacyMysqlTimeColumns`,
`legacyMysqlTimestampColumns`, `previewDatetimeConvergence`,
`previewTimeConvergence`, `supportsRotation`), each typed as the class
member's indexed access, in the interface's sorted order (74 to 80
members). There is no cast, and no member becomes public.
- **Comments.** The module header gains one `[#25521 cut 18]` paragraph
saying what moved, what stayed and where each read declaration comes
from. The `sql-driver.ts` import comment names cut 18 in 2 lines.
Neither cites an `ADR-NNNN` letter. The moved
`previewDeferredSchemaWork` body keeps its `[#22506]` comment, which
mentions `ADR-0057 P2` (not a decision letter; the count below is
unchanged).
- **How the move was made.** A script produced it from the source text;
nothing was retyped. Each body line is re-indented two columns; no body
line starts inside a template literal.
## Verification
### ADR anchors
- **The count.** `check:adr-anchors` counts **1898** decision-letter
citations at base `f1cd529dd2` (a clean detached worktree) and **1898**
at the move commit (a clean detached worktree), over 91 anchored files
at both ends; the two outputs are byte-identical. Both runs exit 0.
- **Why equal.** No comment inside the moved bodies or the new header
paragraph cites a decision letter. The stubs keep their docblocks, so
every `ADR-…` mention in them stays in `sql-driver.ts`.
- **No entry needs a new home.** No anchor entry names a moved member.
`check:adr-symbol-anchors`: 2687 resolve at both ends (output
byte-identical).
- **After the merge.** `main` moved under the cut, so I measured its tip
`5787df4d4b` against the merge head `7065d8e1d0`: **1898** letters at
both (91 anchored files, exit 0), and 2687 symbol anchors resolve at
both.
### The published `.d.ts` does not change
This is measured under the series bar (ruling `6348891160`, item 1).
- **How each end was built.** `pnpm turbo run build
--filter=@objectstack/driver-sql --force` at each end, against the same
dependency tree. The base leg writes base `sql-driver.ts` and base
`sql-driver-schema-sync.ts` into this worktree under an EXIT/INT/TERM
trap that restores HEAD. The restore is proved by the HEAD blob hashes,
an empty `git diff HEAD` and 0 status entries (`RESTORE-OK d2ff2d1…
d29e275…`).
- **The hashes.** The raw sha256 of `dist/index.d.ts` and
`dist/index.d.mts` is the same at base and at head,
`0f33bf3febaac3c7aa96f68a4226d752766b8203ab7acade523b69f9aaa44d74`
(unchanged since cut 8), on the move commit and again on the merge head.
These two are the dist's only declaration files (no chunk), so nothing
was re-ordered and the declaration-reorder bar of ruling `6441032442`
does not come into play.
- **Positive control.** I dropped `protected` from
`previewDatetimeConvergence` in the head `index.d.ts` (1 hit, then 0).
The result hashes to
`fd2f04595d02e10a86dd26debff0b40b4f8e3428699c28383e74d5a64193c0ad`, with
`cmp` exit 1.
- **Export lists.** CJS `require` of each dist gives 59 names (sha1
`05757ce5ae` at both ends); the ESM namespace of the base and head
`index.mjs` gives the same 59 names (sha1 `05757ce5ae` both). None of
the three moved functions or `SchemaSyncHost` is among them
(`fieldHasColumn` is, at both ends: `index.ts` re-exports it from
`schema-drift.ts`, which this cut does not touch).
- **The head dist carries the move.** `.call(host` sites in `index.mjs`
go from 64 at base to 67 at head (the three stubs).
### Move-only proof
The proof compares TypeScript compiler AST leaf tokens (JSDoc nodes
skipped), base `f1cd529dd2` against the move commit `028cda6cf`. It is a
scratch script and is not committed.
| Moved body | Body tokens | Comments | Parameter tokens less `this` |
Return type tokens | Body lines |
|:--|--:|--:|--:|--:|--:|
| `previewDeferredSchemaWork` | 469 | 13 | 0 | 6 | 45 |
| `previewDatetimeConvergence` | 374 | 0 | 17 | 6 | 37 |
| `previewTimeConvergence` | 377 | 0 | 17 | 6 | 37 |
- **Each moved body.** In every row, 0 tokens differ and every comment
is identical. Each body line is the base line less two leading spaces.
All three are `async` at both ends.
- **The three stubs.** Leading trivia (the docblock), modifiers and the
signature are identical to base, less `async`.
- **The class.** It has 350 members at both ends, in the same order, and
the 347 unmoved members are byte-identical, trivia included.
- **Top level of `sql-driver.ts`.** 177 of 180 base statements are
byte-identical; the other three are the class and the two edited imports
(`fieldHasColumn` gains `type`; the schema-sync import gains three names
and its 2-line comment).
- **The module.** Its 42 base statements are all in the head module
byte-identical except three: its first import (whose leading trivia is
the header, which gained the cut 18 paragraph), the `./schema-drift.js`
import (`fieldHasColumn` and `type PendingSchemaWork` added) and
`SchemaSyncHost` (6 members added). The head adds the three functions.
- **Result.** `PROOF OK`, exit 0; on the merge head its output is
byte-identical.
- **Negative control.** Through `scripts/ablation-replace.mjs`, I
changed `kind: 'widen_time_columns'` to `kind: 'widen_time_columnz'` in
the module's `previewTimeConvergence` (anchor 1 hit, then 0, checked on
disk). The proof then reports `previewTimeConvergence` as differing,
prints `PROOF FAILED`, and exits 1. The restore was proved (blob
`d29e275e18` equals HEAD, empty `git diff HEAD`).
### Tests
Each end ran under one `os-verify-lock` hold, after building that end's
driver-sql dist. I compared the vitest JSON per test name and status,
base `f1cd529dd2` against the move commit `028cda6cf`, and then again on
the merge head `7065d8e1d0`. Every part's exit code was captured on its
own (build, probe, three suites: all 0 at every leg).
| Suite | Base | Head | Lost / changed / added |
|:--|:--|:--|:--|
| `@objectstack/driver-sql` | 4061 (3847 passed, 214 skipped; 248 files)
| same | 0 / 0 / 0 |
| `@objectstack/driver-turso`, against that end's built driver-sql dist
| 2526 (2492 passed, 34 skipped; 95 files) | same | 0 / 0 / 0 |
| `@objectstack/driver-sqlite-wasm` | 746 (746 passed; 39 files) | same
| 0 / 0 / 0 |
On the merge head (it brings in `main` up to `5787df4d4b`: 15 commits,
none in `packages/drivers/**`), the three suites give the same totals
and the same per-test statuses as base, 0 / 0 / 0 in each.
- **Type check and lint.** `tsc --noEmit -p .` in driver-sql exits 0 on
the move commit and on the merge head. `pnpm exec eslint
--no-inline-config packages/drivers/driver-sql` exits 0.
- **Late-binding probe.** A scratch script, not committed. It runs node
against each end's built dist and prints 41 readings, each with the
result or the error's message, `code`, `status`, own keys and top stack
frame, plus the tables `sqlite_master` holds, the stored cells and the
log lines:
1. `previewDeferredSchemaWork` on SQLite: a table not created yet;
legacy datetime and time rows (epoch numbers, space-separated and offset
strings, a julian-day real, junk text, `null`) beside an added column
and two formula fields; a second preview (idempotent); the flush (the
plan it returns, the rewritten cells) and a re-plan after it; a
canonical table with two new ones (the sort);
2. the #22506 rotation answer: no shard yet, the flush, current shard
plus read view present, a view without a shard, and a rotation policy
without a unit;
3. `previewDatetimeConvergence` and `previewTimeConvergence` called
directly with every column subset, an unknown table, a declared table
that does not exist, and bad arguments;
4. both on unreachable Postgres and MySQL drivers (probe failures
swallowed to `[]`);
5. the MySQL branch with `legacyMysqlTimestampColumns` /
`legacyMysqlTimeColumns` stubbed on the instance and a fake `knex`
answering the count in both result shapes, with none, and throwing;
6. a SUBCLASS overriding the two convergence previews,
`rotationShardKey`, the three SQLite predicates and the
`supportsRotation` getter; then instance spies on two of them; then
`datetimeFields` and `deferredSchemaObjects` replaced after
construction, `knex` behind a getter, `isSqlite` forced false, and a
`null` deferral map (the new ones are the ones reached, in the same
order);
7. the async shape: a failure is a rejected promise, not a synchronous
throw, and each method returns a promise.
- **Probe result.** 39 of the 41 readings are identical, results, call
orders, cells and tables included. The other 2 differ only in the top
stack frame's receiver name, where a `null` deferral map throws inside
the moved body: `Sub.previewDeferredSchemaWork` /
`_SqlDriver.previewDeferredSchemaWork` at base and
`Object.previewDeferredSchemaWork` at head. That is shape B's receiver,
the same at every earlier cut, and no test or consumer reads it. One
reading depends on the calendar day (the shard name of the flushed
rotation object); every leg ran on 2026-10-27. On the merge head the
probe output is byte-identical to the move commit's.
- **Not run.** No ablation, because no tested behaviour changed.
- **`test:repo`.** Not run locally; it is CI's run on this PR.
### Gates
`node scripts/pm/dispatch-gates.mjs --commands --repo
objectstack-ai/objectstack` derives **48** families for this diff, the
same list on the move commit and on the merge head (and the same 48 cut
17 derived). I ran each one on its own and captured its exit code before
any pipe, after a full `pnpm build` of that tree (116 of 116 tasks).
- **Move commit `028cda6cf`: 48 run, all 48 exit 0.** `--ran`
reconciles: `48 derived famil(ies) accounted for — 48 run, 0
NOT-MEASURED`, exit 0. (I fetched the pinned fixture commit of
`check-plugin-teardown-shape.mjs --self-test` into this shallow clone
first, as cut 17 learned to.)
- **Merge head `7065d8e1d0`: 48 run, all 48 exit 0.** `--ran` reconciles
the same way, exit 0.
- **Hand gates on both heads, all exit 0:** `check-adr-anchors`,
`check-adr-symbol-anchors`, `check-tenant-audit-census` (244 write call
sites), `check-platform-checklist --changed-from origin/main`,
`check-commit-card-trailers --range origin/main..HEAD`, `eslint
--no-inline-config packages/drivers/driver-sql`,
`check-durability-degradation-log-level --list`. In clean detached
worktrees at base `f1cd529dd2` and at the move commit,
`check-adr-anchors`, `check-adr-symbol-anchors`,
`check-tenant-audit-census` and `check-object-def-param-keys` print
byte-identical output, and `check-durability-degradation-log-level
--list` prints the same seams, line numbers aside.
- **No gate silently empty.** Each derived gate's log prints a non-zero
population (for example `check:object-def-param-keys` compares 7
override parameter positions over 3370 files with every control firing;
`check:tenant-chokepoint` reads 24 `getBuilder()` bindings across 3
files; `check:durability-log-level` reads 88 read seams;
`check:dual-build-cjs-loads` loads 112 entry points across 69 packages).
The 48 derived commands: `node
scripts/check-closing-keyword-parity.mjs`, `node
scripts/check-closing-keyword-parity.mjs --self-test`, `node
scripts/check-comment-mask-adoption.mjs`, `node
scripts/check-comment-mask-adoption.mjs --self-test`, `node
scripts/check-comment-mask-corpus.mjs`, `node
scripts/check-dts-emitted.mjs --self-test`, `node
scripts/check-issue-citations.mjs`, `node
scripts/check-plugin-teardown-shape.mjs`, `node
scripts/check-plugin-teardown-shape.mjs --self-test`, `node
scripts/ci/assert-turbo-remote-cache.mjs --self-test`, `node
scripts/ci/plan-test-core-shards.mjs --self-test`, `node
scripts/ci/prune-turbo-cache.mjs --self-test`, `node
scripts/docs-audit/check-affected-docs.mjs`, `node
scripts/docs-audit/check-drift-comment.mjs`, `pnpm --filter
@objectstack/spec run check:duration-unit-keys`, `pnpm
check:ci-filter-parity`, `pnpm check:closed-ceremony-text`, `pnpm
check:cross-package-test-inputs`, `pnpm
check:dispatcher-error-vocabulary`, `pnpm check:doc-authoring`, `pnpm
check:driver-conformance`, `pnpm check:driver-memory-census`, `pnpm
check:dts-closure`, `pnpm check:dual-build-cjs-loads`, `pnpm
check:durability-log-level`, `pnpm check:error-status-conformance`,
`pnpm check:gitlink-declared`, `pnpm check:issue-citations`, `pnpm
check:keyed-text-bounds`, `pnpm check:lean-entry-closure`, `pnpm
check:logger-receiver-detach`, `pnpm check:nul-bytes`, `pnpm
check:object-def-param-keys`, `pnpm check:org-identifier`, `pnpm
check:page-declaration-shape`, `pnpm
check:platform-object-tenancy-census`, `pnpm check:published-files`,
`pnpm check:refd-timer-probe`, `pnpm check:registry-log-declared`, `pnpm
check:rest-log-spy-declared`, `pnpm check:slot-lookup`, `pnpm
check:sourcemap-no-sources-content`, `pnpm check:system-context-census`,
`pnpm check:tenant-chokepoint`, `pnpm check:test-source-alias`, `pnpm
check:tier-file-adoption`, `pnpm check:undeclared-dep-imports`, `pnpm
check:watch-hint-literal`.
## Acceptance notes
- **`check:tenant-chokepoint`'s `SCAN_FILES` does not list
`sql-driver-schema-sync.ts`.** The moved bodies hold 0 of the file's 4
tenant predicates and build no query through `getBuilder` (they read
`sqlite_master`, `columnInfo` and row counts through `knex`). Noted, not
filed: widening `SCAN_FILES` would be a gate change.
- **Stale links from cut 15 are unchanged.** `sql-driver.ts` has the
same 30 `{@link X}` sites (21 names) that are neither a top-level
binding nor a `SqlDriver` member at base and at head (the set is
identical); this cut adds none, because `fieldHasColumn` stays linkable
through its type import.
- **The series' remaining yield, priced on this base.** After this cut,
the largest single area that moves cleanly is about -62 (the class
head's date-bucket and query-timing pair, or the column-creation
remainder); the filter-helper remainder (-80) splits into four
mechanisms of -29 or less each. Every further area pays between about
-30 and -62.
## Human Minimum
- [x] 1. No `packages/spec` change.
- [x] 2. No new name; `SchemaSyncHost` gains members only.
- [x] 3. No formatter ran; scoped `eslint --no-inline-config` passes
(repo-wide `pnpm lint` is CI's run).
- [x] 4. One issue, one branch off an up-to-date `main`, one pull
request.
- [x] 5. No publishable behaviour change: `skip-changeset`; both
declaration lines above.
- [x] 6. `packages/spec` not touched.
- [x] 7. No hand edits to generated docs, changelogs or release notes.
- [x] 8. Title, body and comments are in English (the maintainer brief
excepted).
---
_Generated by [Claude
Code](https://claude.ai/code/session_01FEkQ5kNG4UuwLvtVwPNQqK)_
🤖 Generated with [Claude Code](https://claude.com/claude-code)
https://claude.ai/code/session_01FEkQ5kNG4UuwLvtVwPNQqK
Co-authored-by: Claude <noreply@anthropic.com>
1 parent 5782008 commit 452325e
2 files changed
Lines changed: 203 additions & 125 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
104 | 104 | | |
105 | 105 | | |
106 | 106 | | |
| 107 | + | |
| 108 | + | |
| 109 | + | |
| 110 | + | |
| 111 | + | |
| 112 | + | |
| 113 | + | |
| 114 | + | |
| 115 | + | |
| 116 | + | |
| 117 | + | |
| 118 | + | |
| 119 | + | |
| 120 | + | |
| 121 | + | |
107 | 122 | | |
108 | 123 | | |
109 | 124 | | |
| |||
135 | 150 | | |
136 | 151 | | |
137 | 152 | | |
138 | | - | |
| 153 | + | |
139 | 154 | | |
140 | 155 | | |
141 | 156 | | |
| |||
174 | 189 | | |
175 | 190 | | |
176 | 191 | | |
| 192 | + | |
177 | 193 | | |
178 | 194 | | |
179 | 195 | | |
| |||
197 | 213 | | |
198 | 214 | | |
199 | 215 | | |
| 216 | + | |
| 217 | + | |
200 | 218 | | |
201 | 219 | | |
202 | 220 | | |
| |||
208 | 226 | | |
209 | 227 | | |
210 | 228 | | |
| 229 | + | |
| 230 | + | |
211 | 231 | | |
212 | 232 | | |
213 | 233 | | |
| |||
220 | 240 | | |
221 | 241 | | |
222 | 242 | | |
| 243 | + | |
223 | 244 | | |
224 | 245 | | |
225 | 246 | | |
| |||
1912 | 1933 | | |
1913 | 1934 | | |
1914 | 1935 | | |
| 1936 | + | |
| 1937 | + | |
| 1938 | + | |
| 1939 | + | |
| 1940 | + | |
| 1941 | + | |
| 1942 | + | |
| 1943 | + | |
| 1944 | + | |
| 1945 | + | |
| 1946 | + | |
| 1947 | + | |
| 1948 | + | |
| 1949 | + | |
| 1950 | + | |
| 1951 | + | |
| 1952 | + | |
| 1953 | + | |
| 1954 | + | |
| 1955 | + | |
| 1956 | + | |
| 1957 | + | |
| 1958 | + | |
| 1959 | + | |
| 1960 | + | |
| 1961 | + | |
| 1962 | + | |
| 1963 | + | |
| 1964 | + | |
| 1965 | + | |
| 1966 | + | |
| 1967 | + | |
| 1968 | + | |
| 1969 | + | |
| 1970 | + | |
| 1971 | + | |
| 1972 | + | |
| 1973 | + | |
| 1974 | + | |
| 1975 | + | |
| 1976 | + | |
| 1977 | + | |
| 1978 | + | |
| 1979 | + | |
| 1980 | + | |
| 1981 | + | |
| 1982 | + | |
| 1983 | + | |
| 1984 | + | |
| 1985 | + | |
| 1986 | + | |
| 1987 | + | |
| 1988 | + | |
| 1989 | + | |
| 1990 | + | |
| 1991 | + | |
| 1992 | + | |
| 1993 | + | |
| 1994 | + | |
| 1995 | + | |
| 1996 | + | |
| 1997 | + | |
| 1998 | + | |
| 1999 | + | |
| 2000 | + | |
| 2001 | + | |
| 2002 | + | |
| 2003 | + | |
| 2004 | + | |
| 2005 | + | |
| 2006 | + | |
| 2007 | + | |
| 2008 | + | |
| 2009 | + | |
| 2010 | + | |
| 2011 | + | |
| 2012 | + | |
| 2013 | + | |
| 2014 | + | |
| 2015 | + | |
| 2016 | + | |
| 2017 | + | |
| 2018 | + | |
| 2019 | + | |
| 2020 | + | |
| 2021 | + | |
| 2022 | + | |
| 2023 | + | |
| 2024 | + | |
| 2025 | + | |
| 2026 | + | |
| 2027 | + | |
| 2028 | + | |
| 2029 | + | |
| 2030 | + | |
| 2031 | + | |
| 2032 | + | |
| 2033 | + | |
| 2034 | + | |
| 2035 | + | |
| 2036 | + | |
| 2037 | + | |
| 2038 | + | |
| 2039 | + | |
| 2040 | + | |
| 2041 | + | |
| 2042 | + | |
| 2043 | + | |
| 2044 | + | |
| 2045 | + | |
| 2046 | + | |
| 2047 | + | |
| 2048 | + | |
| 2049 | + | |
| 2050 | + | |
| 2051 | + | |
| 2052 | + | |
| 2053 | + | |
| 2054 | + | |
| 2055 | + | |
| 2056 | + | |
| 2057 | + | |
| 2058 | + | |
| 2059 | + | |
| 2060 | + | |
| 2061 | + | |
| 2062 | + | |
| 2063 | + | |
| 2064 | + | |
| 2065 | + | |
| 2066 | + | |
0 commit comments