@agent-native/core 0.203.0 → 0.203.1-nightly-20261007154213

package/dist/templates/chat/.agents/skills/actions/SKILL.md

@@ -107,6 +107,31 @@ An action that hands control back to the user (question form, intake dialog) set
 
 Reach for `outputSchema` (validate the return), `_agentImages` (attach images the agent can see), `authorize` (gate who may call it), or `needsApproval` (require human sign-off per call) only when the action needs that guarantee — examples in `references/action-fields.md`.
 
+### Write receipts
+
+A write action that can check its own effect returns a plain-object result with a reserved `_receipt`, so the final answer is reconciled with what the write did, not with the model's reading of a JSON string that may be truncated:
+
+```ts
+import type { WriteReceipt } from "@agent-native/core/action";
+
+const _receipt: WriteReceipt = {
+  changed: true,
+  verified: false,
+  summary: "Saved; panel 3 returned no rows.",
+  checks: [{ id: "panel-3", ok: false, detail: "0 rows" }],
+};
+return { id, _receipt };
+```
+
+`verified` is `true` (the effect was observed), `false` (checked and did not hold), or `"unverified"` (could not be checked); `checks` and `warnings` are optional. The agent loop reads the receipt before the result is stringified and truncated (summary 200 chars, 8 checks, 5 warnings):
+
+- `verified: false` or `changed: false` forces one honest-reconciliation retry per turn: the model must say what the receipt shows and may not call the change visible or working. If the retry is spent, the answer is prefixed with the receipt block.
+- `verified: "unverified"` only prefixes that note; no retry.
+- A receipt that is present but malformed counts as `unverified`, never clean. `changed: false` also records the call as `completedSideEffect: false`.
+- Set `subject` (the stable target, such as a dashboard id) so a later `changed: true, verified: true` receipt for the same subject can supersede an earlier flagged one in the same turn. When the earlier receipt had failing or unverified `checks`, the later receipts (from this action or another that writes the same subject) must carry an `ok: true` check with the same `id` for each; a receipt without checks never clears one that had them. A flagged receipt with no failing checks is superseded only by the same action. Receipts without a `subject` are never superseded.
+
+A receipt is not an error channel. A write that did not achieve the requested state throws (`fail()`); return `changed: false` only for a benign no-op, such as the record already being in the requested state.
+
 ## Frontend Hooks
 
 Import from focused `@agent-native/core/client/*` entry points; the broad

package/dist/templates/default/.agents/skills/actions/SKILL.md

@@ -107,6 +107,31 @@ An action that hands control back to the user (question form, intake dialog) set
 
 Reach for `outputSchema` (validate the return), `_agentImages` (attach images the agent can see), `authorize` (gate who may call it), or `needsApproval` (require human sign-off per call) only when the action needs that guarantee — examples in `references/action-fields.md`.
 
+### Write receipts
+
+A write action that can check its own effect returns a plain-object result with a reserved `_receipt`, so the final answer is reconciled with what the write did, not with the model's reading of a JSON string that may be truncated:
+
+```ts
+import type { WriteReceipt } from "@agent-native/core/action";
+
+const _receipt: WriteReceipt = {
+  changed: true,
+  verified: false,
+  summary: "Saved; panel 3 returned no rows.",
+  checks: [{ id: "panel-3", ok: false, detail: "0 rows" }],
+};
+return { id, _receipt };
+```
+
+`verified` is `true` (the effect was observed), `false` (checked and did not hold), or `"unverified"` (could not be checked); `checks` and `warnings` are optional. The agent loop reads the receipt before the result is stringified and truncated (summary 200 chars, 8 checks, 5 warnings):
+
+- `verified: false` or `changed: false` forces one honest-reconciliation retry per turn: the model must say what the receipt shows and may not call the change visible or working. If the retry is spent, the answer is prefixed with the receipt block.
+- `verified: "unverified"` only prefixes that note; no retry.
+- A receipt that is present but malformed counts as `unverified`, never clean. `changed: false` also records the call as `completedSideEffect: false`.
+- Set `subject` (the stable target, such as a dashboard id) so a later `changed: true, verified: true` receipt for the same subject can supersede an earlier flagged one in the same turn. When the earlier receipt had failing or unverified `checks`, the later receipts (from this action or another that writes the same subject) must carry an `ok: true` check with the same `id` for each; a receipt without checks never clears one that had them. A flagged receipt with no failing checks is superseded only by the same action. Receipts without a `subject` are never superseded.
+
+A receipt is not an error channel. A write that did not achieve the requested state throws (`fail()`); return `changed: false` only for a benign no-op, such as the record already being in the requested state.
+
 ## Frontend Hooks
 
 Import from focused `@agent-native/core/client/*` entry points; the broad

package/dist/templates/headless/.agents/skills/actions/SKILL.md

@@ -107,6 +107,31 @@ An action that hands control back to the user (question form, intake dialog) set
 
 Reach for `outputSchema` (validate the return), `_agentImages` (attach images the agent can see), `authorize` (gate who may call it), or `needsApproval` (require human sign-off per call) only when the action needs that guarantee — examples in `references/action-fields.md`.
 
+### Write receipts
+
+A write action that can check its own effect returns a plain-object result with a reserved `_receipt`, so the final answer is reconciled with what the write did, not with the model's reading of a JSON string that may be truncated:
+
+```ts
+import type { WriteReceipt } from "@agent-native/core/action";
+
+const _receipt: WriteReceipt = {
+  changed: true,
+  verified: false,
+  summary: "Saved; panel 3 returned no rows.",
+  checks: [{ id: "panel-3", ok: false, detail: "0 rows" }],
+};
+return { id, _receipt };
+```
+
+`verified` is `true` (the effect was observed), `false` (checked and did not hold), or `"unverified"` (could not be checked); `checks` and `warnings` are optional. The agent loop reads the receipt before the result is stringified and truncated (summary 200 chars, 8 checks, 5 warnings):
+
+- `verified: false` or `changed: false` forces one honest-reconciliation retry per turn: the model must say what the receipt shows and may not call the change visible or working. If the retry is spent, the answer is prefixed with the receipt block.
+- `verified: "unverified"` only prefixes that note; no retry.
+- A receipt that is present but malformed counts as `unverified`, never clean. `changed: false` also records the call as `completedSideEffect: false`.
+- Set `subject` (the stable target, such as a dashboard id) so a later `changed: true, verified: true` receipt for the same subject can supersede an earlier flagged one in the same turn. When the earlier receipt had failing or unverified `checks`, the later receipts (from this action or another that writes the same subject) must carry an `ok: true` check with the same `id` for each; a receipt without checks never clears one that had them. A flagged receipt with no failing checks is superseded only by the same action. Receipts without a `subject` are never superseded.
+
+A receipt is not an error channel. A write that did not achieve the requested state throws (`fail()`); return `changed: false` only for a benign no-op, such as the record already being in the requested state.
+
 ## Frontend Hooks
 
 Import from focused `@agent-native/core/client/*` entry points; the broad

package/dist/templates/workspace-core/.agents/skills/actions/SKILL.md

@@ -107,6 +107,31 @@ An action that hands control back to the user (question form, intake dialog) set
 
 Reach for `outputSchema` (validate the return), `_agentImages` (attach images the agent can see), `authorize` (gate who may call it), or `needsApproval` (require human sign-off per call) only when the action needs that guarantee — examples in `references/action-fields.md`.
 
+### Write receipts
+
+A write action that can check its own effect returns a plain-object result with a reserved `_receipt`, so the final answer is reconciled with what the write did, not with the model's reading of a JSON string that may be truncated:
+
+```ts
+import type { WriteReceipt } from "@agent-native/core/action";
+
+const _receipt: WriteReceipt = {
+  changed: true,
+  verified: false,
+  summary: "Saved; panel 3 returned no rows.",
+  checks: [{ id: "panel-3", ok: false, detail: "0 rows" }],
+};
+return { id, _receipt };
+```
+
+`verified` is `true` (the effect was observed), `false` (checked and did not hold), or `"unverified"` (could not be checked); `checks` and `warnings` are optional. The agent loop reads the receipt before the result is stringified and truncated (summary 200 chars, 8 checks, 5 warnings):
+
+- `verified: false` or `changed: false` forces one honest-reconciliation retry per turn: the model must say what the receipt shows and may not call the change visible or working. If the retry is spent, the answer is prefixed with the receipt block.
+- `verified: "unverified"` only prefixes that note; no retry.
+- A receipt that is present but malformed counts as `unverified`, never clean. `changed: false` also records the call as `completedSideEffect: false`.
+- Set `subject` (the stable target, such as a dashboard id) so a later `changed: true, verified: true` receipt for the same subject can supersede an earlier flagged one in the same turn. When the earlier receipt had failing or unverified `checks`, the later receipts (from this action or another that writes the same subject) must carry an `ok: true` check with the same `id` for each; a receipt without checks never clears one that had them. A flagged receipt with no failing checks is superseded only by the same action. Receipts without a `subject` are never superseded.
+
+A receipt is not an error channel. A write that did not achieve the requested state throws (`fail()`); return `changed: false` only for a benign no-op, such as the record already being in the requested state.
+
 ## Frontend Hooks
 
 Import from focused `@agent-native/core/client/*` entry points; the broad

package/dist/triggers/actions/manage-automation.d.ts

@@ -13,6 +13,8 @@ declare const _default: import("../../action.js").ActionDefinition<{
     executionEngine?: string;
     executionCwd?: string;
 }, {
+    deleted?: undefined;
+    enabled?: undefined;
     created: boolean;
     name: string;
     scope: "organization" | "personal";
@@ -23,33 +25,31 @@ declare const _default: import("../../action.js").ActionDefinition<{
     reasoningEffort: "auto" | "high" | "low" | "max" | "medium" | "minimal" | "none" | "xhigh";
     webhookPath: string;
     nextRun: string;
-    deleted?: undefined;
-    enabled?: undefined;
     executionHostId?: undefined;
     executionEngine?: undefined;
     executionCwd?: undefined;
 } | {
-    created?: undefined;
     scope?: undefined;
+    enabled?: undefined;
+    nextRun?: undefined;
+    created?: undefined;
     triggerType?: undefined;
     event?: undefined;
     deleted: boolean;
     name: string;
-    enabled?: undefined;
     schedule?: undefined;
     timezone?: undefined;
     reasoningEffort?: undefined;
     executionHostId?: undefined;
     executionEngine?: undefined;
     executionCwd?: undefined;
-    nextRun?: undefined;
     webhookPath?: undefined;
 } | {
-    created?: undefined;
     scope?: undefined;
+    deleted?: undefined;
+    created?: undefined;
     triggerType?: undefined;
     event?: undefined;
-    deleted?: undefined;
     name: string;
     enabled: boolean;
     schedule: string;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@agent-native/core",
-  "version": "0.203.0",
+  "version": "0.203.1-nightly-20261007154213",
   "description": "The agentic application framework for building autonomous agents with intuitive UIs",
   "homepage": "https://github.com/BuilderIO/agent-native#readme",
   "bugs": {
@@ -682,7 +682,7 @@
     "yaml": "^2.9.0",
     "yjs": "^13.6.33",
     "zod": "^4.3.6",
-    "@agent-native/agentkit": "^0.203.0",
+    "@agent-native/agentkit": "^0.203.1-nightly-20261007154213",
     "@agent-native/recap-cli": "^0.5.64"
   },
   "devDependencies": {
@@ -753,7 +753,7 @@
     "xlsx": "^0.18.5"
   },
   "peerDependencies": {
-    "@agent-native/core-corpus": ">=0.196.0",
+    "@agent-native/core-corpus": "0.203.1-nightly-20261007154213",
     "@ai-sdk/anthropic": ">=3",
     "@ai-sdk/cohere": ">=3",
     "@ai-sdk/google": ">=3",

package/src/templates/chat/.agents/skills/actions/SKILL.md

@@ -107,6 +107,31 @@ An action that hands control back to the user (question form, intake dialog) set
 
 Reach for `outputSchema` (validate the return), `_agentImages` (attach images the agent can see), `authorize` (gate who may call it), or `needsApproval` (require human sign-off per call) only when the action needs that guarantee — examples in `references/action-fields.md`.
 
+### Write receipts
+
+A write action that can check its own effect returns a plain-object result with a reserved `_receipt`, so the final answer is reconciled with what the write did, not with the model's reading of a JSON string that may be truncated:
+
+```ts
+import type { WriteReceipt } from "@agent-native/core/action";
+
+const _receipt: WriteReceipt = {
+  changed: true,
+  verified: false,
+  summary: "Saved; panel 3 returned no rows.",
+  checks: [{ id: "panel-3", ok: false, detail: "0 rows" }],
+};
+return { id, _receipt };
+```
+
+`verified` is `true` (the effect was observed), `false` (checked and did not hold), or `"unverified"` (could not be checked); `checks` and `warnings` are optional. The agent loop reads the receipt before the result is stringified and truncated (summary 200 chars, 8 checks, 5 warnings):
+
+- `verified: false` or `changed: false` forces one honest-reconciliation retry per turn: the model must say what the receipt shows and may not call the change visible or working. If the retry is spent, the answer is prefixed with the receipt block.
+- `verified: "unverified"` only prefixes that note; no retry.
+- A receipt that is present but malformed counts as `unverified`, never clean. `changed: false` also records the call as `completedSideEffect: false`.
+- Set `subject` (the stable target, such as a dashboard id) so a later `changed: true, verified: true` receipt for the same subject can supersede an earlier flagged one in the same turn. When the earlier receipt had failing or unverified `checks`, the later receipts (from this action or another that writes the same subject) must carry an `ok: true` check with the same `id` for each; a receipt without checks never clears one that had them. A flagged receipt with no failing checks is superseded only by the same action. Receipts without a `subject` are never superseded.
+
+A receipt is not an error channel. A write that did not achieve the requested state throws (`fail()`); return `changed: false` only for a benign no-op, such as the record already being in the requested state.
+
 ## Frontend Hooks
 
 Import from focused `@agent-native/core/client/*` entry points; the broad

package/src/templates/default/.agents/skills/actions/SKILL.md

@@ -107,6 +107,31 @@ An action that hands control back to the user (question form, intake dialog) set
 
 Reach for `outputSchema` (validate the return), `_agentImages` (attach images the agent can see), `authorize` (gate who may call it), or `needsApproval` (require human sign-off per call) only when the action needs that guarantee — examples in `references/action-fields.md`.
 
+### Write receipts
+
+A write action that can check its own effect returns a plain-object result with a reserved `_receipt`, so the final answer is reconciled with what the write did, not with the model's reading of a JSON string that may be truncated:
+
+```ts
+import type { WriteReceipt } from "@agent-native/core/action";
+
+const _receipt: WriteReceipt = {
+  changed: true,
+  verified: false,
+  summary: "Saved; panel 3 returned no rows.",
+  checks: [{ id: "panel-3", ok: false, detail: "0 rows" }],
+};
+return { id, _receipt };
+```
+
+`verified` is `true` (the effect was observed), `false` (checked and did not hold), or `"unverified"` (could not be checked); `checks` and `warnings` are optional. The agent loop reads the receipt before the result is stringified and truncated (summary 200 chars, 8 checks, 5 warnings):
+
+- `verified: false` or `changed: false` forces one honest-reconciliation retry per turn: the model must say what the receipt shows and may not call the change visible or working. If the retry is spent, the answer is prefixed with the receipt block.
+- `verified: "unverified"` only prefixes that note; no retry.
+- A receipt that is present but malformed counts as `unverified`, never clean. `changed: false` also records the call as `completedSideEffect: false`.
+- Set `subject` (the stable target, such as a dashboard id) so a later `changed: true, verified: true` receipt for the same subject can supersede an earlier flagged one in the same turn. When the earlier receipt had failing or unverified `checks`, the later receipts (from this action or another that writes the same subject) must carry an `ok: true` check with the same `id` for each; a receipt without checks never clears one that had them. A flagged receipt with no failing checks is superseded only by the same action. Receipts without a `subject` are never superseded.
+
+A receipt is not an error channel. A write that did not achieve the requested state throws (`fail()`); return `changed: false` only for a benign no-op, such as the record already being in the requested state.
+
 ## Frontend Hooks
 
 Import from focused `@agent-native/core/client/*` entry points; the broad

package/src/templates/headless/.agents/skills/actions/SKILL.md

@@ -107,6 +107,31 @@ An action that hands control back to the user (question form, intake dialog) set
 
 Reach for `outputSchema` (validate the return), `_agentImages` (attach images the agent can see), `authorize` (gate who may call it), or `needsApproval` (require human sign-off per call) only when the action needs that guarantee — examples in `references/action-fields.md`.
 
+### Write receipts
+
+A write action that can check its own effect returns a plain-object result with a reserved `_receipt`, so the final answer is reconciled with what the write did, not with the model's reading of a JSON string that may be truncated:
+
+```ts
+import type { WriteReceipt } from "@agent-native/core/action";
+
+const _receipt: WriteReceipt = {
+  changed: true,
+  verified: false,
+  summary: "Saved; panel 3 returned no rows.",
+  checks: [{ id: "panel-3", ok: false, detail: "0 rows" }],
+};
+return { id, _receipt };
+```
+
+`verified` is `true` (the effect was observed), `false` (checked and did not hold), or `"unverified"` (could not be checked); `checks` and `warnings` are optional. The agent loop reads the receipt before the result is stringified and truncated (summary 200 chars, 8 checks, 5 warnings):
+
+- `verified: false` or `changed: false` forces one honest-reconciliation retry per turn: the model must say what the receipt shows and may not call the change visible or working. If the retry is spent, the answer is prefixed with the receipt block.
+- `verified: "unverified"` only prefixes that note; no retry.
+- A receipt that is present but malformed counts as `unverified`, never clean. `changed: false` also records the call as `completedSideEffect: false`.
+- Set `subject` (the stable target, such as a dashboard id) so a later `changed: true, verified: true` receipt for the same subject can supersede an earlier flagged one in the same turn. When the earlier receipt had failing or unverified `checks`, the later receipts (from this action or another that writes the same subject) must carry an `ok: true` check with the same `id` for each; a receipt without checks never clears one that had them. A flagged receipt with no failing checks is superseded only by the same action. Receipts without a `subject` are never superseded.
+
+A receipt is not an error channel. A write that did not achieve the requested state throws (`fail()`); return `changed: false` only for a benign no-op, such as the record already being in the requested state.
+
 ## Frontend Hooks
 
 Import from focused `@agent-native/core/client/*` entry points; the broad

package/src/templates/workspace-core/.agents/skills/actions/SKILL.md

@@ -107,6 +107,31 @@ An action that hands control back to the user (question form, intake dialog) set
 
 Reach for `outputSchema` (validate the return), `_agentImages` (attach images the agent can see), `authorize` (gate who may call it), or `needsApproval` (require human sign-off per call) only when the action needs that guarantee — examples in `references/action-fields.md`.
 
+### Write receipts
+
+A write action that can check its own effect returns a plain-object result with a reserved `_receipt`, so the final answer is reconciled with what the write did, not with the model's reading of a JSON string that may be truncated:
+
+```ts
+import type { WriteReceipt } from "@agent-native/core/action";
+
+const _receipt: WriteReceipt = {
+  changed: true,
+  verified: false,
+  summary: "Saved; panel 3 returned no rows.",
+  checks: [{ id: "panel-3", ok: false, detail: "0 rows" }],
+};
+return { id, _receipt };
+```
+
+`verified` is `true` (the effect was observed), `false` (checked and did not hold), or `"unverified"` (could not be checked); `checks` and `warnings` are optional. The agent loop reads the receipt before the result is stringified and truncated (summary 200 chars, 8 checks, 5 warnings):
+
+- `verified: false` or `changed: false` forces one honest-reconciliation retry per turn: the model must say what the receipt shows and may not call the change visible or working. If the retry is spent, the answer is prefixed with the receipt block.
+- `verified: "unverified"` only prefixes that note; no retry.
+- A receipt that is present but malformed counts as `unverified`, never clean. `changed: false` also records the call as `completedSideEffect: false`.
+- Set `subject` (the stable target, such as a dashboard id) so a later `changed: true, verified: true` receipt for the same subject can supersede an earlier flagged one in the same turn. When the earlier receipt had failing or unverified `checks`, the later receipts (from this action or another that writes the same subject) must carry an `ok: true` check with the same `id` for each; a receipt without checks never clears one that had them. A flagged receipt with no failing checks is superseded only by the same action. Receipts without a `subject` are never superseded.
+
+A receipt is not an error channel. A write that did not achieve the requested state throws (`fail()`); return `changed: false` only for a benign no-op, such as the record already being in the requested state.
+
 ## Frontend Hooks
 
 Import from focused `@agent-native/core/client/*` entry points; the broad