feat(automation): schema-aware flow-condition validation at registration (#1928)

registerFlow now runs the same schema-aware condition checks as objectstack
build, so a flow registered dynamically (API/Studio, bypassing the build lint)
still gets the guardrail. When an object-schema resolver is wired, a condition
that references an unknown field, likely-typos a field, or does arithmetic/
ordering on a text/boolean field against a number is surfaced as an advisory
warning (logged), against the object's real schema.

- New AutomationEngine.setObjectSchemaResolver bridge (mirrors
  setFunctionResolver); AutomationServicePlugin wires it to
  objectql.registry.getObject in start(), before the flow pull.
- Strictly additive: the fatal set is unchanged (syntax, brace-in-CEL,
  unknown-function still throw); schema findings are logged, never thrown;
  no-op when unwired. Flattened scope — flow variables stay dyn, equality safe.
- parseObjectFieldSchema helper normalizes the registry's field map/array.

Tests: service-automation 316 (+10: 6 engine resolver, 4 parser); no regression.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Hnji7EEYR2mGt6pY53a8Bm

Author: claude

.changeset/flow-registration-schema-aware-validation.md

@@ -0,0 +1,26 @@
+---
+"@objectstack/service-automation": minor
+---
+
+feat(automation): schema-aware flow-condition validation at registration (#1928)
+
+`registerFlow` now runs the same schema-aware condition checks as
+`objectstack build` — so a flow registered dynamically (via the API / Studio,
+bypassing the build lint) still gets the guardrail. When the host wires an
+object-schema resolver, a flow condition that references an unknown field,
+likely-typos a field name, or does arithmetic/ordering on a text/boolean field
+against a number is surfaced as an **advisory warning** (logged), pointing at
+the object's real schema.
+
+- New `AutomationEngine.setObjectSchemaResolver(resolver)` bridge (mirrors
+  `setFunctionResolver`); `AutomationServicePlugin` wires it to
+  `objectql.registry.getObject` in `start()`, before the flow pull, so
+  registry-sourced flows are covered too.
+- **Strictly additive / zero regression**: the fatal set is unchanged (syntax,
+  brace-in-CEL, unknown-function still throw); everything the schema pass adds is
+  logged, never thrown, and the whole thing is a no-op when no resolver is wired.
+  Flow conditions bind fields flat, so the check runs in `flattened` scope
+  (flow variables stay `dyn` and are never flagged; equality is runtime-safe).
+
+Builds on the tier-4 type-soundness check in `@objectstack/formula` /
+`@objectstack/lint` (#1928).

packages/services/service-automation/src/engine.test.ts

@@ -3,7 +3,7 @@
 import { describe, it, expect, beforeEach } from 'vitest';
 import { LiteKernel } from '@objectstack/core';
 import { AutomationEngine, DEFAULT_MAX_EXECUTION_LOG_SIZE } from './engine.js';
-import { AutomationServicePlugin } from './plugin.js';
+import { AutomationServicePlugin, parseObjectFieldSchema } from './plugin.js';
 import { registerScreenNodes } from './builtin/screen-nodes.js';
 import { InMemorySuspendedRunStore } from './suspended-run-store.js';
 import type { NodeExecutor } from './engine.js';
@@ -821,6 +821,117 @@ describe('AutomationEngine', () => {
     });
 });
 
+// ─── Schema-aware condition validation at registration (#1928) ───────
+
+describe('Schema-aware condition validation at registration (#1928)', () => {
+    // A logger that captures warnings, so we can assert the advisory channel.
+    function loggerCapturing(warns: string[]) {
+        const l: any = {
+            info: () => {}, error: () => {}, debug: () => {},
+            warn: (m: string) => warns.push(m),
+            child: () => l,
+        };
+        return l;
+    }
+
+    const OPP_SCHEMA = {
+        crm_opportunity: {
+            fields: ['stage', 'amount', 'is_active', 'title'],
+            fieldTypes: { stage: 'select', amount: 'currency', is_active: 'boolean', title: 'text' } as Record<string, string>,
+        } as { fields: string[]; fieldTypes: Record<string, string> },
+    };
+
+    function makeFlow(condition: string) {
+        return {
+            name: 'opp_flow', label: 'Opp Flow', type: 'record_change',
+            nodes: [
+                { id: 'start', type: 'start', label: 'Start', config: { objectName: 'crm_opportunity' } },
+                { id: 'check', type: 'decision', label: 'Check', config: { condition } },
+                { id: 'end', type: 'end', label: 'End' },
+            ],
+            edges: [
+                { id: 'e1', source: 'start', target: 'check' },
+                { id: 'e2', source: 'check', target: 'end' },
+            ],
+        };
+    }
+
+    it('logs an advisory warning (does NOT throw) for a text field misused in arithmetic — tier 4', () => {
+        const warns: string[] = [];
+        const engine = new AutomationEngine(loggerCapturing(warns));
+        engine.setObjectSchemaResolver((name) => (OPP_SCHEMA as Record<string, unknown>)[name] as any);
+        expect(() => engine.registerFlow('opp_flow', makeFlow('title * 2 > 10'))).not.toThrow();
+        const w = warns.filter((m) => /type mismatch/i.test(m));
+        expect(w).toHaveLength(1);
+        expect(w[0]).toMatch(/`title`/);
+    });
+
+    it('logs an advisory warning for a likely field typo — tier 3', () => {
+        const warns: string[] = [];
+        const engine = new AutomationEngine(loggerCapturing(warns));
+        engine.setObjectSchemaResolver((name) => (OPP_SCHEMA as Record<string, unknown>)[name] as any);
+        expect(() => engine.registerFlow('opp_flow', makeFlow('stagee == "closed_won"'))).not.toThrow();
+        expect(warns.some((m) => /did you mean `stage`/.test(m))).toBe(true);
+    });
+
+    it('logs an advisory warning for an unknown record field — tier 2', () => {
+        const warns: string[] = [];
+        const engine = new AutomationEngine(loggerCapturing(warns));
+        engine.setObjectSchemaResolver((name) => (OPP_SCHEMA as Record<string, unknown>)[name] as any);
+        expect(() => engine.registerFlow('opp_flow', makeFlow('record.amont > 5'))).not.toThrow();
+        expect(warns.some((m) => /unknown field `amont`/.test(m))).toBe(true);
+    });
+
+    it('does not warn on sound conditions (number arithmetic, equality, flow variables)', () => {
+        const warns: string[] = [];
+        const engine = new AutomationEngine(loggerCapturing(warns));
+        engine.setObjectSchemaResolver((name) => (OPP_SCHEMA as Record<string, unknown>)[name] as any);
+        engine.registerFlow('opp_flow', makeFlow('amount / 100 > 5 && stage == "won" && expiring_count * 2 > 3'));
+        expect(warns.filter((m) => /type mismatch|did you mean|unknown field/i.test(m))).toHaveLength(0);
+    });
+
+    it('still HARD-FAILS a malformed condition (fatal set unchanged)', () => {
+        const warns: string[] = [];
+        const engine = new AutomationEngine(loggerCapturing(warns));
+        engine.setObjectSchemaResolver((name) => (OPP_SCHEMA as Record<string, unknown>)[name] as any);
+        expect(() => engine.registerFlow('opp_flow', makeFlow('{record.stage} == "won"'))).toThrow(/template braces|bare CEL/);
+    });
+
+    it('is a no-op when no resolver is wired (registration behaviour unchanged)', () => {
+        const warns: string[] = [];
+        const engine = new AutomationEngine(loggerCapturing(warns));
+        // No setObjectSchemaResolver — a tier-4 mistake registers with NO advisory.
+        expect(() => engine.registerFlow('opp_flow', makeFlow('title * 2 > 10'))).not.toThrow();
+        expect(warns.filter((m) => /type mismatch|did you mean|unknown field/i.test(m))).toHaveLength(0);
+    });
+});
+
+describe('parseObjectFieldSchema (#1928 — object-registry → schema hint)', () => {
+    it('normalizes a name-keyed field map (the ObjectQL ServiceObject shape)', () => {
+        const r = parseObjectFieldSchema({ title: { type: 'text' }, amount: { type: 'currency' }, done: { type: 'boolean' } });
+        expect(r?.fields.sort()).toEqual(['amount', 'done', 'title']);
+        expect(r?.fieldTypes).toEqual({ title: 'text', amount: 'currency', done: 'boolean' });
+    });
+
+    it('normalizes an array of {name, type}', () => {
+        const r = parseObjectFieldSchema([{ name: 'title', type: 'text' }, { name: 'amount', type: 'currency' }]);
+        expect(r?.fields).toEqual(['title', 'amount']);
+        expect(r?.fieldTypes).toEqual({ title: 'text', amount: 'currency' });
+    });
+
+    it('lists a field with a non-string type but assigns it no type (→ dyn)', () => {
+        const r = parseObjectFieldSchema({ meta: {}, name: { type: 'text' } });
+        expect(r?.fields.sort()).toEqual(['meta', 'name']);
+        expect(r?.fieldTypes).toEqual({ name: 'text' });
+    });
+
+    it('returns undefined for a non-object fields value', () => {
+        expect(parseObjectFieldSchema(undefined)).toBeUndefined();
+        expect(parseObjectFieldSchema(null)).toBeUndefined();
+        expect(parseObjectFieldSchema('nope')).toBeUndefined();
+    });
+});
+
 // ─── Plugin Integration Tests ────────────────────────────────────────
 
 describe('AutomationServicePlugin (Kernel Integration)', () => {

packages/services/service-automation/src/engine.ts

@@ -234,6 +234,22 @@ export type FlowFunctionHandler = (ctx: FlowFunctionContext) => unknown | Promis
  */
 export type FlowFunctionResolver = (name: string) => FlowFunctionHandler | undefined;
 
+/**
+ * Resolves the schema of the object a flow's conditions bind against — its field
+ * names and (spec) types — so `registerFlow` can run the same schema-aware
+ * expression checks as `objectstack build` (ADR-0032 tiers 2–4): unknown
+ * `record.<field>` refs, likely bare-field typos, and text/boolean fields
+ * misused in arithmetic (#1928). Injected by the host (bridged to the object
+ * registry), so the engine stays decoupled from any metadata store. Returns
+ * `undefined` for an unknown object. When unwired, registration validation is
+ * unchanged (syntax + bare-ref only). Everything it surfaces is advisory (logged
+ * as a warning, never thrown) — a resolver can never break a flow that used to
+ * register cleanly.
+ */
+export type FlowObjectSchemaResolver = (
+  objectName: string,
+) => { fields?: readonly string[]; fieldTypes?: Record<string, string> } | undefined;
+
 /**
  * A designer-facing view of one connector action — identity + its JSON-Schema
  * input/output. The runtime handler is intentionally omitted; this is metadata.
@@ -516,6 +532,9 @@ export class AutomationEngine implements IAutomationService {
     private connectorProviders = new Map<string, ConnectorProviderFactory>();
     /** Bridge to the host function registry for `script`-node calls (#1870), if wired. */
     private functionResolver: FlowFunctionResolver | null = null;
+    /** Bridge to the host object registry for schema-aware condition validation at
+     *  registration (#1928), if wired. Advisory-only — see {@link FlowObjectSchemaResolver}. */
+    private objectSchemaResolver: FlowObjectSchemaResolver | null = null;
     private executionLogs: ExecutionLogEntry[] = [];
     private readonly maxLogSize: number;
     private logger: Logger;
@@ -934,6 +953,18 @@ export class AutomationEngine implements IAutomationService {
         this.functionResolver = resolver;
     }
 
+    /**
+     * Wire the engine to the host's object registry (#1928) so `registerFlow`
+     * runs the same schema-aware condition checks as `objectstack build` —
+     * unknown-field refs, likely bare-field typos, and text/boolean fields
+     * misused in arithmetic. Everything it adds is advisory (logged, never
+     * thrown); passing `null` detaches the bridge (registration reverts to
+     * syntax + bare-ref validation only).
+     */
+    setObjectSchemaResolver(resolver: FlowObjectSchemaResolver | null): void {
+        this.objectSchemaResolver = resolver;
+    }
+
     /**
      * Resolve a named function for a `script` node. Returns `undefined` when no
      * resolver is wired or the name is unregistered — the node then fails the
@@ -2066,19 +2097,49 @@ export class AutomationEngine implements IAutomationService {
      * Only the *predicate* surfaces are checked here (start/node `config.condition`
      * and `edge.condition`) — node string fields are templates (a different
      * dialect) and are validated by the template engine, not as CEL.
+     *
+     * #1928 — when an object-schema resolver is wired ({@link setObjectSchemaResolver}),
+     * a second, schema-aware pass surfaces the checks `objectstack build` runs
+     * (unknown-field refs, likely bare-field typos, text/boolean fields misused
+     * in arithmetic) as ADVISORY warnings (logged, never thrown). Flow conditions
+     * bind the record's fields flat, so the schema pass uses `flattened` scope.
+     * The fatal set is unchanged — a resolver can never break a flow that used to
+     * register cleanly.
      */
     private validateFlowExpressions(flowName: string, flow: FlowParsed): void {
         const failures: string[] = [];
 
+        // Resolve the flow's record-change target object (start node's
+        // `config.objectName`) so `record.*`/bare field refs can be checked
+        // against the real schema. Absent resolver / non-record flow → the hint
+        // is undefined and only the fatal syntax/bare-ref pass runs (unchanged).
+        const startNode = flow.nodes.find((n) => n.type === 'start');
+        const objectName = ((startNode?.config ?? {}) as Record<string, unknown>).objectName;
+        const schemaHint = typeof objectName === 'string'
+            ? (() => {
+                const s = this.objectSchemaResolver?.(objectName);
+                return s ? { objectName, fields: s.fields, fieldTypes: s.fieldTypes, scope: 'flattened' as const } : undefined;
+            })()
+            : undefined;
+
         const check = (where: string, raw: unknown): void => {
             if (raw == null) return;
-            // Conditions are predicates (bare CEL). Delegate to the one shared
-            // validator (ADR-0032 §5) so the corrective message matches the CLI
-            // build and the agent `validate_expression` tool exactly.
+            // Fatal pass — syntax, brace-in-CEL, unknown-function (ADR-0032 §5).
+            // Unchanged: matches the CLI build's fatal set exactly.
             const result = validateExpression('predicate', raw as string | { dialect?: string; source?: string });
             for (const e of result.errors) {
                 failures.push(`  • ${where}: ${e.message}\n      source: \`${e.source}\``);
             }
+            // Advisory schema-aware pass — only when the source is syntactically
+            // valid (else it would just re-report the fatal error). Everything it
+            // finds (field-existence, tier-3 typo, tier-4 type mismatch) is LOGGED,
+            // never thrown, so registration behaviour is strictly additive (#1928).
+            if (result.errors.length === 0 && schemaHint) {
+                const schemaPass = validateExpression('predicate', raw as string | { dialect?: string; source?: string }, schemaHint);
+                for (const issue of [...schemaPass.errors, ...schemaPass.warnings]) {
+                    this.logger.warn(`[flow '${flowName}'] ${where}: ${issue.message}\n      source: \`${issue.source}\``);
+                }
+            }
         };
 
         for (const node of flow.nodes) {

packages/services/service-automation/src/plugin.ts

@@ -18,6 +18,37 @@ import {
     type SuspendedRunStoreEngine,
 } from './suspended-run-store.js';
 
+/**
+ * #1928 — normalize an ObjectQL object's `fields` (a name-keyed map, or an
+ * array of `{name, type}`) into the `{ fields, fieldTypes }` shape the flow
+ * condition validator consumes. Fields whose `type` isn't a string are still
+ * listed (so existence checks work) but contribute no type (→ treated as `dyn`).
+ * Returns `undefined` when there is nothing usable. Exported for unit testing.
+ */
+export function parseObjectFieldSchema(
+    fieldsDef: unknown,
+): { fields: string[]; fieldTypes: Record<string, string> } | undefined {
+    if (!fieldsDef || typeof fieldsDef !== 'object') return undefined;
+    const fields: string[] = [];
+    const fieldTypes: Record<string, string> = {};
+    if (Array.isArray(fieldsDef)) {
+        for (const f of fieldsDef as Array<Record<string, unknown>>) {
+            const n = (f as { name?: unknown })?.name;
+            if (typeof n !== 'string') continue;
+            fields.push(n);
+            const t = (f as { type?: unknown })?.type;
+            if (typeof t === 'string') fieldTypes[n] = t;
+        }
+    } else {
+        for (const [n, def] of Object.entries(fieldsDef as Record<string, unknown>)) {
+            fields.push(n);
+            const t = (def as { type?: unknown })?.type;
+            if (typeof t === 'string') fieldTypes[n] = t;
+        }
+    }
+    return { fields, fieldTypes };
+}
+
 /**
  * Configuration options for the AutomationServicePlugin.
  */
@@ -439,6 +470,27 @@ export class AutomationServicePlugin implements Plugin {
             ctx.logger.debug('[Automation] objectql not present — script-node function calls will fail loudly when used');
         }
 
+        // #1928 — bridge the object registry so `registerFlow` runs the same
+        // schema-aware condition checks as `objectstack build`: unknown-field
+        // refs, likely bare-field typos, and text/boolean fields misused in
+        // arithmetic. Everything it surfaces is advisory (logged, never thrown),
+        // so a dynamically-registered flow (which bypasses the build lint) still
+        // gets the guardrail. Wired BEFORE the flow pull below so pulled flows
+        // are covered too. Best-effort: without ObjectQL, registration falls back
+        // to syntax + bare-ref validation only.
+        try {
+            const ql = ctx.getService<{
+                registry?: { getObject?: (name: string) => unknown };
+            }>('objectql');
+            if (ql?.registry && typeof ql.registry.getObject === 'function') {
+                this.engine.setObjectSchemaResolver((objectName) =>
+                    parseObjectFieldSchema((ql.registry!.getObject!(objectName) as { fields?: unknown } | undefined)?.fields));
+                ctx.logger.debug('[Automation] object-schema resolver bridged to objectql.registry (#1928 condition checks)');
+            }
+        } catch {
+            ctx.logger.debug('[Automation] objectql registry not present — flow-condition checks limited to syntax');
+        }
+
         // Pull flow definitions from the ObjectQL schema registry. AppPlugin.init()
         // calls manifest.register(payload), which routes to ql.registerApp() and
         // stores each inline flow under type 'flow'. By the time start() runs,