@vatio-ai/skills 1.27.0 → 1.27.2
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.
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "vatio",
|
|
3
3
|
"description": "Vatio skills for Claude Code, Cursor and Codex: add an AI agent to the app you're building with /vatio-init, then improve it daily with /vatio-improve and learn what people ask it with /vatio-analyze.",
|
|
4
|
-
"version": "1.27.
|
|
4
|
+
"version": "1.27.2",
|
|
5
5
|
"author": {
|
|
6
6
|
"name": "Vatio",
|
|
7
7
|
"url": "https://vatio.ai"
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@vatio-ai/skills",
|
|
3
|
-
"version": "1.27.
|
|
3
|
+
"version": "1.27.2",
|
|
4
4
|
"description": "Vatio skills for Claude Code, Cursor and Codex: add an AI agent to the app you're building with /vatio-init, then improve it daily with /vatio-improve and learn what people ask it with /vatio-analyze.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"vatio",
|
|
@@ -40,7 +40,12 @@ In short:
|
|
|
40
40
|
calls. `vatio tools --env live` shows each tool's error rate, timeouts and
|
|
41
41
|
latency, and the calls that failed with what the backend answered: a
|
|
42
42
|
failing tool rarely gets reported, because the agent apologizes and moves
|
|
43
|
-
on. Fix those too.
|
|
43
|
+
on. Fix those too. The digest ends with the tests the agent answers
|
|
44
|
+
differently each time (the same version passes and fails them): work
|
|
45
|
+
those too, as its section says. Usually the agent is inconsistent and
|
|
46
|
+
the fix is in `vatio.yml` or knowledge; when the note is what is vague,
|
|
47
|
+
rewrite it; when it no longer applies, propose removing it to the
|
|
48
|
+
developer. Never remove a test because it fails.
|
|
44
49
|
3. `vatio push`. It updates preview and runs no tests. No branch or
|
|
45
50
|
environment to set up: preview is the one. If it is refused because
|
|
46
51
|
preview has changes made outside the files (someone edited the agent from
|
|
@@ -56,7 +61,8 @@ In short:
|
|
|
56
61
|
comes with the `vatio chat show CHAT_ID` of its replay. Iterate (fix, push,
|
|
57
62
|
test) until the reports pass and nothing that passes on live fails. A case
|
|
58
63
|
marked "not tested (Vatio's side)" says nothing about your fix: run
|
|
59
|
-
`vatio test --wait` again.
|
|
64
|
+
`vatio test --wait` again. One not tested because a tool needs a
|
|
65
|
+
signed-in visitor replays signed in with `vatio test --as-subject ID`. Name reports by id (`F-7K2QX`).
|
|
60
66
|
5. Show the developer what passes now, and `vatio publish` once they agree:
|
|
61
67
|
it changes what visitors get. In a draft (no conversation from outside
|
|
62
68
|
the team yet) live already runs every push, and `vatio publish` says
|
|
@@ -45,7 +45,9 @@ you recommend, and ask them to confirm.
|
|
|
45
45
|
`vatio.yml` (and `tools/` for their APIs, with one that alerts their
|
|
46
46
|
team when a person should take over: **Human in the loop** in the docs).
|
|
47
47
|
3. `vatio diff`, `vatio push`, then try it with `vatio chat`, including a
|
|
48
|
-
conversation that should hand off.
|
|
48
|
+
conversation that should hand off. A tool that needs the visitor's
|
|
49
|
+
phone or a team role runs with `vatio chat --as-phone me` (or a test
|
|
50
|
+
phone); an `access: private` one with `--as-subject ID`.
|
|
49
51
|
4. **Keep the replies that came out right.** For each one,
|
|
50
52
|
`vatio test add "what the answer has to say"` right after the
|
|
51
53
|
`vatio chat` that produced it. Three or four is enough to start. This is
|