@restoai/resto-datacli 0.1.11 → 0.1.12
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
|
@@ -16,6 +16,17 @@ Use `resto-datacli` as evidence-backed tools for restaurant reporting data. Agen
|
|
|
16
16
|
- Ask clarification when metric meaning is ambiguous, for example when "sales" could mean net sales, gross sales, paid amount, quantity, or order count.
|
|
17
17
|
- Treat missing fields as capability gaps. Explain the gap, cite what was searched or inspected, and offer alternatives such as nearby fields, another report, narrower scope, or asking the data owner.
|
|
18
18
|
|
|
19
|
+
## Startup Freshness Check
|
|
20
|
+
|
|
21
|
+
At the start of a Resto data task or a new Agent session, check tool and knowledge freshness before discovery:
|
|
22
|
+
|
|
23
|
+
1. Run `resto --version`.
|
|
24
|
+
2. Run `npm view @restoai/resto-datacli version --cache /private/tmp/resto-datacli-npm-cache`.
|
|
25
|
+
3. If npm has a newer version, run `npm install -g @restoai/resto-datacli@latest --cache /private/tmp/resto-datacli-npm-cache`, then run `resto install-skill`, and tell the user to restart the current Agent or open a new session so the updated skill is loaded.
|
|
26
|
+
4. run `resto knowledge status` to inspect local knowledge.
|
|
27
|
+
5. run `resto knowledge check` with the task's env and schema version when auth is available.
|
|
28
|
+
6. run `resto knowledge sync` when local knowledge is missing, stale, or older than the remote manifest. For China production, use `--env bj --schema-version 1` unless the user or deployment context says otherwise.
|
|
29
|
+
|
|
19
30
|
## Prerequisites
|
|
20
31
|
|
|
21
32
|
- run `resto knowledge status` to see the current local package.
|