@@ -0,0 +1,17 @@
+---
+'@objectstack/formula': patch
+'@objectstack/lint': patch
+'@objectstack/mcp': patch
+---
+
+fix(formula,lint,mcp): a fail-closed date verdict says the write is refused, and a time-relative sweep's run-fails verdict names no firing write
+
+Clause-②: yes (widening)
+Metadata-protocol: none
+
+- **`@objectstack/formula`: three codes join `ExpressionRefusalCode`** (`EXPRESSION_REFUSAL_CODES`), with the params of the code they split from:
+  - `date-arithmetic-fail-closed` and `date-text-arithmetic-fail-closed`. On a site that fails closed (`faultOutcome: 'fail-closed'`: an `error` validation rule, a field `requiredWhen` / `readonlyWhen`, an option `visibleWhen`, a hook `condition`), date arithmetic used to be told "this faults at runtime, so the field silently evaluates to null". There the fault refuses the write instead, and the verdict now says so. A formula field and an advisory (`warning` / `info`) validation rule keep `date-arithmetic` / `date-text-arithmetic` and their sentence. A consumer keyed to the old codes on a fail-closed site re-keys to the new ones.
+  - `type-mismatch-sweep-run-fails`. A time-relative sweep of the typed object is graded `run-fails` like a record-triggered flow, but no write fires its run: the sweep starts one run per row it finds. Its condition's text-vs-number verdict used to say "the write that fired it still lands". Served where the new optional `ExprSchemaHint.timeRelativeSweep` is set beside `faultOutcome: 'run-fails'`, it now says the run for that row fails and nothing else happens. A record-triggered flow keeps `type-mismatch-run-fails` and its sentence.
+- The grade is unchanged at every site. What is refused, warned or passed is unchanged.
+- **`@objectstack/lint`**: the flow walk passes `timeRelativeSweep` on a `time_relative` flow. The nullable-comparison verdict, which also says "still lands", runs on record-triggered flows only, so it is unchanged.
+- **`@objectstack/mcp`**: `validate_expression` with `site: 'flow_condition'` and `triggerKind: 'time_relative'` passes the same key, so its answer stays the gate's.
@@ -242,7 +242,7 @@ come at two severities: **errors** fail the build; **warnings** are advisory
 | **Qualify field references** — a formula / validation / predicate binds only the `record` namespace, so a bare `amount` resolves to nothing and evaluates to `null`. Write `record.amount`. | `amount > 100` → `record.amount > 100` | error |
 | **Field must exist** — a typo'd `record.<field>` is flagged with a did-you-mean. | `record.amont` → `record.amount` | error |
 | **Unknown function** — a misspelled or nonexistent stdlib call. | `isBlnk(record.x)` | error |
-| **Type soundness** — a text or boolean field used with an arithmetic (`+ - * / %`) or ordering (`< > <= >=`) operator against a number faults at runtime unless the text is numeric. In a formula it evaluates to `null`. Where a fault does something else it is an error, worded for what happens: a validation rule, a field `requiredWhen` / `readonlyWhen`, an option `visibleWhen` or a hook `condition` refuses the write; a record-triggered flow's start, edge or `decision` branch condition fails the run (the write that fired it still lands), whether it reads the field bare or as `record.<field>`, and so does a time-relative flow's that sweeps the same object; a bare name that a declared flow variable or a `screen` field holds reads that value, so it is not judged as the field, and a bare name after a node that can bind any name (`script`, `connector_action`, `wait`, `subflow`, `map`, a screen with no fields) gets the warning instead, while its `record.<field>` read is still refused; an advisory (`severity: 'warning'` / `'info'`) validation rule is skipped, so it never gives its advisory. Store it as a number field, compare text with text, or convert explicitly (`size(record.name)` for the length; `double(record.name)`, which itself faults on text that is not a number). | `record.title * 2`; `record.name > 5` in a validation rule → `size(record.name) > 5` | warning in a formula or a display predicate, and in a condition of any other flow, where the warning says the run fails if the condition faults (what such a flow binds under the name depends on how it is started); error at the sites named |
+| **Type soundness** — a text or boolean field used with an arithmetic (`+ - * / %`) or ordering (`< > <= >=`) operator against a number faults at runtime unless the text is numeric. In a formula it evaluates to `null`. Where a fault does something else it is an error, worded for what happens: a validation rule, a field `requiredWhen` / `readonlyWhen`, an option `visibleWhen` or a hook `condition` refuses the write; a record-triggered flow's start, edge or `decision` branch condition fails the run (the write that fired it still lands), whether it reads the field bare or as `record.<field>`, and so does a time-relative flow's that sweeps the same object, where no write fires the run and only the run for that row fails; a bare name that a declared flow variable or a `screen` field holds reads that value, so it is not judged as the field, and a bare name after a node that can bind any name (`script`, `connector_action`, `wait`, `subflow`, `map`, a screen with no fields) gets the warning instead, while its `record.<field>` read is still refused; an advisory (`severity: 'warning'` / `'info'`) validation rule is skipped, so it never gives its advisory. Store it as a number field, compare text with text, or convert explicitly (`size(record.name)` for the length; `double(record.name)`, which itself faults on text that is not a number). | `record.title * 2`; `record.name > 5` in a validation rule → `size(record.name) > 5` | warning in a formula or a display predicate, and in a condition of any other flow, where the warning says the run fails if the condition faults (what such a flow binds under the name depends on how it is started); error at the sites named |
 | **Date arithmetic** — a `date` / `datetime` field used with `+` / `-` against a number (a `YYYY-MM-DD` value is a string at runtime, so this always faulted to `null`). Use the date helpers instead. | `record.end_date - record.start_date + 1` → `daysBetween(record.start_date, record.end_date) + 1`; `today() + 30` → `daysFromNow(30)`; `record.date + n` → `addDays(record.date, n)` | error (#3306) |
 | **Date subtraction** — the runtime holds a `date` / `datetime` field as its text (`YYYY-MM-DD`, or an ISO-8601 instant), so subtracting two of them faults and the formula reads `null`; a timestamp minus one computes a duration, which a field reads as `{}`. Use `daysBetween`. A condition may still compare a duration (`today() - record.start_date > duration("72h")`). | `record.end_date - record.start_date` → `daysBetween(record.start_date, record.end_date)`; `today() - record.start_date` → `daysBetween(record.start_date, today())` | error |
 
 
@@ -296,6 +296,23 @@ const PINS: { readonly [C in ExpressionRefusalCode]: readonly [Pin<C>, ...Pin<C>
         'in whole days, and `daysFromNow(n)` / `addDays(d, n)` / `addMonths(d, n)` to shift a date.',
     },
   ],
+  // [#30250] A fail-closed site: the fault refuses the write, nothing reads null.
+  'date-arithmetic-fail-closed': [
+    {
+      produce: () =>
+        onlyError('predicate', 'record.close_date + 1 > 3', {
+          scope: 'record',
+          fieldTypes: { close_date: 'date' },
+          faultOutcome: 'fail-closed',
+        }),
+      params: { operands: 'google.protobuf.Timestamp + int', reference: 'record.close_date' },
+      message:
+        'date arithmetic `google.protobuf.Timestamp + int` — `record.close_date` is a date, and CEL can\'t do arithmetic ' +
+        'on dates: this faults at runtime, and here an expression that cannot be evaluated fails closed: the write (or the operation ' +
+        'a hook guards) is refused, not skipped (it does not read null). ' +
+        'Use `daysBetween(a, b)` for the span in whole days, and `daysFromNow(n)` / `addDays(d, n)` / `addMonths(d, n)` to shift a date.',
+    },
+  ],
   // [#30016] A flattened (flow) condition: the fault fails the run, it never
   // reads null — `run-fails` where the run is proven to hold the field.
   'date-arithmetic-run-fails': [
@@ -343,6 +360,23 @@ const PINS: { readonly [C in ExpressionRefusalCode]: readonly [Pin<C>, ...Pin<C>
         'and `daysFromNow(n)` / `addDays(d, n)` / `addMonths(d, n)` to shift a date.',
     },
   ],
+  'date-text-arithmetic-fail-closed': [
+    {
+      produce: () =>
+        onlyError('predicate', 'record.end_date - record.start_date > duration("24h")', {
+          scope: 'record',
+          fieldTypes: { start_date: 'date', end_date: 'date' },
+          faultOutcome: 'fail-closed',
+        }),
+      params: { operands: 'DateText - DateText', reference: 'record.start_date' },
+      message:
+        'date arithmetic `DateText - DateText` — `record.start_date` is a date field, and the runtime holds a date field ' +
+        'as its text (`YYYY-MM-DD`, or an ISO-8601 instant for a date-time), which CEL can\'t do arithmetic on: ' +
+        'this faults at runtime, and here an expression that cannot be evaluated fails closed: the write (or the operation ' +
+        'a hook guards) is refused, not skipped (it does not read null). ' +
+        'Use `daysBetween(a, b)` for the span in whole days, and `daysFromNow(n)` / `addDays(d, n)` / `addMonths(d, n)` to shift a date.',
+    },
+  ],
   'date-text-arithmetic-run-fails': [
     {
       produce: () =>
@@ -458,6 +492,24 @@ const PINS: { readonly [C in ExpressionRefusalCode]: readonly [Pin<C>, ...Pin<C>
         'length, `double(name)` for its value (which itself faults on text that is not a number).',
     },
   ],
+  // [#30250] The same outcome on a time-relative sweep, which no write fires.
+  'type-mismatch-sweep-run-fails': [
+    {
+      produce: () =>
+        onlyError('predicate', 'name > 5', {
+          scope: 'flattened', fields: ['name'], fieldTypes: { name: 'text' }, faultOutcome: 'run-fails', timeRelativeSweep: true,
+        }),
+      params: { operands: 'string > int', operator: '>', held: 'text', reference: 'name' },
+      message:
+        'type mismatch `string > int` — `name` holds text but is used with `>` against a number. CEL has no such operation, so ' +
+        'wherever the value is not numeric text (an empty value included) the expression faults, and here ' +
+        'a flow condition that cannot be evaluated fails the run: the time-relative sweep starts one run per row it finds, ' +
+        'the run for this row stops at this condition and the work the flow exists to do is not done for that row, and ' +
+        'nothing else happens (the sweep logs the failure and goes on to the next row). ' +
+        'Compare like with like: use a number field, compare text with text, or convert explicitly — `size(name)` for its ' +
+        'length, `double(name)` for its value (which itself faults on text that is not a number).',
+    },
+  ],
   'type-mismatch-fail-open': [
     {
       produce: () =>
@@ -690,6 +742,24 @@ const SWEEP_SCHEMAS: readonly (ExprSchemaHint | undefined)[] = [
     fieldTypes: { name: 'text', active: 'boolean' },
     faultOutcome,
   })),
+  // [#30250] A fail-closed site with a date field reaches the date verdicts'
+  // `-fail-closed` codes; a time-relative sweep's `run-fails` condition
+  // reaches `type-mismatch-sweep-run-fails`.
+  {
+    scope: 'record',
+    objectName: 'deal',
+    fields: ['close_date'],
+    fieldTypes: { close_date: 'date' },
+    faultOutcome: 'fail-closed',
+  },
+  {
+    scope: 'flattened',
+    objectName: 'deal',
+    fields: ['amount', 'name', 'active'],
+    fieldTypes: { name: 'text', active: 'boolean' },
+    faultOutcome: 'run-fails',
+    timeRelativeSweep: true,
+  },
   // [#29959] A flattened (flow) condition with no declared outcome reaches
   // `type-mismatch-run-may-fail`, bare and through `record.`.
   { scope: 'flattened', objectName: 'deal', fields: ['amount', 'name', 'active'], fieldTypes: { name: 'text', active: 'boolean' } },
 
@@ -60,7 +60,7 @@ export type ExpressionSourceKind = 'array' | 'object' | 'number' | 'boolean' | '
 /**
  * The params every `type-mismatch*` code interpolates: the CEL operand types,
  * the `operator`, what the field holds, and the field as written when known.
- * The four codes differ in the outcome their sentence states, never in params.
+ * The codes differ in the outcome their sentence states, never in params.
  */
 interface TypeMismatchParams {
   readonly operands: string;
@@ -166,15 +166,17 @@ export interface ExpressionRefusalParams {
    * Arithmetic on a date field against a number. `operands` are the CEL
    * operand types; `reference` is the field as written, when it is known. A
    * flattened (flow) condition is `date-arithmetic-run-fails` /
-   * `date-arithmetic-run-may-fail`.
+   * `date-arithmetic-run-may-fail`; a fail-closed site is
+   * `date-arithmetic-fail-closed`. An advisory rule's stays this code.
    */
   'date-arithmetic': { readonly operands: string; readonly reference?: string };
   /**
    * Arithmetic on a date field's runtime TEXT that the evaluator cannot answer
    * (`record.end_date - record.start_date`), judged with the field declared as
    * that text. `operands` are the CEL operand types (the text is `DateText`);
    * `reference` is the field as written, when it is known. A flattened (flow)
-   * condition is `date-text-arithmetic-run-fails` / `-run-may-fail`.
+   * condition is `date-text-arithmetic-run-fails` / `-run-may-fail`; a
+   * fail-closed site is `date-text-arithmetic-fail-closed`.
    */
   'date-text-arithmetic': { readonly operands: string; readonly reference?: string };
   /**
@@ -193,6 +195,15 @@ export interface ExpressionRefusalParams {
   'date-text-arithmetic-run-fails': { readonly operands: string; readonly reference?: string };
   /** [#30016] ERROR: `date-text-arithmetic`, at a `date-arithmetic-run-may-fail` site. */
   'date-text-arithmetic-run-may-fail': { readonly operands: string; readonly reference?: string };
+  /**
+   * [#30250] ERROR: `date-arithmetic` at a site that FAILS CLOSED (an `error`
+   * validation rule, a field write rule, an option `visibleWhen`, a hook
+   * `condition`) — the fault refuses the write (or aborts the operation a
+   * hook guards). It never reads null.
+   */
+  'date-arithmetic-fail-closed': { readonly operands: string; readonly reference?: string };
+  /** [#30250] ERROR: `date-text-arithmetic`, at a `date-arithmetic-fail-closed` site. */
+  'date-text-arithmetic-fail-closed': { readonly operands: string; readonly reference?: string };
   /**
    * A formula that computes a `google.protobuf.Duration`
    * (`today() - record.start_date`), which a field reads as `{}`. `reference`
@@ -219,6 +230,13 @@ export interface ExpressionRefusalParams {
    * lands.
    */
   'type-mismatch-run-fails': TypeMismatchParams;
+  /**
+   * [#30250] ERROR: the same mismatch in a condition of a time-relative sweep
+   * of the typed object (`ExprSchemaHint.timeRelativeSweep`) — the run for
+   * that row fails at the condition; no write fired it, so nothing else
+   * happens.
+   */
+  'type-mismatch-sweep-run-fails': TypeMismatchParams;
   /**
    * [#29926] ERROR: the same mismatch in an advisory (`warning` / `info`)
    * validation rule — the rule is skipped, the write proceeds, and the
@@ -297,10 +315,13 @@ const CODE_TABLE = {
   'date-arithmetic-run-may-fail': true,
   'date-text-arithmetic-run-fails': true,
   'date-text-arithmetic-run-may-fail': true,
+  'date-arithmetic-fail-closed': true,
+  'date-text-arithmetic-fail-closed': true,
   'date-duration-value': true,
   'type-mismatch': true,
   'type-mismatch-fail-closed': true,
   'type-mismatch-run-fails': true,
+  'type-mismatch-sweep-run-fails': true,
   'type-mismatch-fail-open': true,
   'type-mismatch-run-may-fail': true,
   'field-near-miss': true,