@jaypie/mcp 0.8.182 → 0.8.183
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.
package/dist/assets.js
CHANGED
|
@@ -55,11 +55,11 @@ function getMcpAssetPaths() {
|
|
|
55
55
|
*/
|
|
56
56
|
function getMcpBuildInfo() {
|
|
57
57
|
return {
|
|
58
|
-
commit: "
|
|
58
|
+
commit: "77ae81b6"
|
|
59
59
|
,
|
|
60
|
-
version: "0.8.
|
|
60
|
+
version: "0.8.183"
|
|
61
61
|
,
|
|
62
|
-
versionString: "@jaypie/mcp@0.8.
|
|
62
|
+
versionString: "@jaypie/mcp@0.8.183#77ae81b6"
|
|
63
63
|
,
|
|
64
64
|
};
|
|
65
65
|
}
|
package/package.json
CHANGED
|
@@ -0,0 +1,9 @@
|
|
|
1
|
+
---
|
|
2
|
+
version: 1.2.118
|
|
3
|
+
date: 2026-10-05
|
|
4
|
+
summary: Pulls @jaypie/llm 1.3.59
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
## Changes
|
|
8
|
+
|
|
9
|
+
- **`@jaypie/llm` 1.3.59**: the structured-output corrective turn is taken once per run; an empty Gemini reply makes 2 requests before failing over instead of 24.
|
|
@@ -0,0 +1,18 @@
|
|
|
1
|
+
---
|
|
2
|
+
version: 1.3.59
|
|
3
|
+
date: 2026-10-05
|
|
4
|
+
summary: The structured-output corrective turn is taken once per run instead of repeating until the turn budget runs out
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
## Changes
|
|
8
|
+
|
|
9
|
+
### One corrective turn (issue #610)
|
|
10
|
+
|
|
11
|
+
A `format` request answered with prose or with nothing took the corrective turn (only the `structured_output` tool offered) on every turn until `turns` ran out. With the default budget of 24, an empty Gemini reply cost 24 requests, each resending the full prompt, before the chain failed over.
|
|
12
|
+
|
|
13
|
+
- The corrective turn is taken at most once per run. A second miss settles: empty content fails over as in 1.3.58, and prose completes as it did when turns ran out.
|
|
14
|
+
- Applies to every adapter with a corrective turn: Fireworks, Google, and Mistral.
|
|
15
|
+
|
|
16
|
+
## Testing
|
|
17
|
+
|
|
18
|
+
- `OperateLoop` specs cover one corrective turn with the default budget for empty content and for prose.
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
---
|
|
2
|
+
version: 0.8.183
|
|
3
|
+
date: 2026-10-05
|
|
4
|
+
summary: Release notes for @jaypie/llm 1.3.59 and jaypie 1.2.118; llm skill documents the single corrective turn
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
## Changes
|
|
8
|
+
|
|
9
|
+
- **Release notes**: `@jaypie/llm` 1.3.59 and `jaypie` 1.2.118
|
|
10
|
+
- **`llm` skill**: the corrective turn is taken once per run
|
package/skills/llm.md
CHANGED
|
@@ -384,7 +384,7 @@ string. The operate loop first parses the text as JSON, stripping a Markdown
|
|
|
384
384
|
code fence — this runs for every provider. If that fails, adapters that opt in
|
|
385
385
|
(`supportsStructuredOutputRetry`: **Fireworks** and **Google**) take a
|
|
386
386
|
corrective turn offering only the `structured_output` tool and demanding it be
|
|
387
|
-
called,
|
|
387
|
+
called. The corrective turn is taken once per run, within the `turns` budget. That turn withholds the caller's own
|
|
388
388
|
tools and does not send the schema natively, leaving one unambiguous way to
|
|
389
389
|
answer.
|
|
390
390
|
|