@north-light/cli 0.3.452 → 0.3.454

package/dist/builtin-memory/00-runtime-base/01-escalation-unattended.md

@@ -1,8 +1,8 @@
 ---
 kind: preference
 when-and-why-to-read: When a run cannot reach a person and a decision still needs to be made, this preference should be read because waiting cannot produce an answer on this run.
-rationale: A run without `ask` cannot use the human branch, so it needs a completion path that records its decision rather than waiting forever.
-gate: {not: {scopes: ask}}
+rationale: A run without `crtr:act` cannot use the human branch, so it needs a completion path that records its decision rather than waiting forever.
+gate: {not: {scopes: crtr:act}}
 surfaces:
   - on: boot
     at: content

package/dist/builtin-memory/00-runtime-base/01-escalation.md

@@ -2,7 +2,7 @@
 kind: preference
 when-and-why-to-read: When progress depends on a person deciding, reviewing, or responding, or when a crtr command fails unexpectedly, this preference should be read because the runtime can deliver the needed signal to its actual recipient instead of leaving work stranded in conversation prose.
 rationale: The human inbox and system-feedback commands are delivery paths whose effects are otherwise invisible in ordinary conversation.
-gate: {scopes: ask}
+gate: {scopes: crtr:act}
 surfaces:
   - on: boot
     at: content

package/dist/builtin-memory/02-turn-lifecycle/01-terminal-user.md

@@ -1,7 +1,7 @@
 ---
 kind: preference
 when-and-why-to-read: When a terminal node needs a person, this preference should be read because its turn-by-turn output does not reach anyone.
-gate: {lifecycle: terminal, scopes: ask}
+gate: {lifecycle: terminal, scopes: crtr:act}
 surfaces:
   - on: boot
     at: content

package/dist/builtin-memory/crouter-sdk/guides/apps-on-northlight.md

@@ -345,7 +345,7 @@ if (outcome.kind === 'result') {
 }
 ```
 
-The runtime validates the value before it records it. A submission that does not match is refused with its field errors and never appears in `runs.get`, an event, or a report, so the agent fixes it and resubmits. `output_schema` accepts a plain JSON Schema object or anything with `toJSONSchema()`, such as a Zod v4 object. The SDK sends it as a JSON object and validates nothing itself. A schema that is not an object, or is over 256 KB serialized, is refused with `invalid_request` and `param: 'output_schema'`, and no run is created. A submitted result can be at most 1 MiB. The agent submits with its `submit_result` tool, which needs no scope, so a run that only reasons and answers can be started with `scopes: ['crtr:llm']`. The same value is in `runs.get(runId).result`, which `runs.wait` returns unchanged, and on the run's `node.settled` event.
+The runtime validates the value before it records it. A submission that does not match is refused with its field errors and never appears in `runs.get`, an event, or a report, so the agent fixes it and resubmits. `output_schema` accepts a plain JSON Schema object or anything with `toJSONSchema()`, such as a Zod v4 object. The SDK sends it as a JSON object and validates nothing itself. A schema that is not an object, or is over 256 KB serialized, is refused with `invalid_request` and `param: 'output_schema'`, and no run is created. A submitted result can be at most 1 MiB. The value is validated exactly as submitted, with no coercion: `null` is never turned into `0` or `""`, and `"5"` is not turned into `5`, so a mismatch is refused and the agent resubmits. The schema is one JSON object, so a `$ref` can point only into itself (`#/$defs/x`, `#anchor`) or at another schema document bundled under `$defs` with its own `$id` (`"$defs": { "common": { "$id": "common.schema.json", ... } }` resolves `common.schema.json#/$defs/x`). Files are never fetched. A schema with a `$ref` that resolves nowhere inside it, or one that cannot be compiled (a bad `pattern`), is refused with `invalid_request` and `param: 'output_schema'` and no run is created. The agent submits with its `submit_result` tool, which needs no scope, so a run that only reasons and answers can be started with `scopes: ['crtr:llm']`. The same value is in `runs.get(runId).result`, which `runs.wait` returns unchanged, and on the run's `node.settled` event.
 
 Do not parse assistant text out of `runs.trace` to get data back. `runs.trace` is for showing a person the transcript. Its text is whatever the model said, not a value anything checked.