@jaypie/mcp 0.8.173 → 0.8.174
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: "6d3baca1"
|
|
59
59
|
,
|
|
60
|
-
version: "0.8.
|
|
60
|
+
version: "0.8.174"
|
|
61
61
|
,
|
|
62
|
-
versionString: "@jaypie/mcp@0.8.
|
|
62
|
+
versionString: "@jaypie/mcp@0.8.174#6d3baca1"
|
|
63
63
|
,
|
|
64
64
|
};
|
|
65
65
|
}
|
package/package.json
CHANGED
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
---
|
|
2
|
+
version: 1.3.51
|
|
3
|
+
date: 2026-09-26
|
|
4
|
+
summary: providerOptions reach only the model they were written for; fallback entries carry their own providerOptions; MODEL.FIREWORKS.DEEPSEEK moves to deepseek-v4p1-flash
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
## Changes
|
|
8
|
+
|
|
9
|
+
- Per-call `providerOptions` on `operate` and `ocr` reach the primary only, its linger pass included. Previously every fallback received them verbatim, so options shaped for one provider (OpenAI `reasoning`) broke a fallback on another (Gemini rejected `reasoning` in `generation_config`) and the chain provided no resilience (#591)
|
|
10
|
+
- `LlmFallbackConfig` gains `providerOptions`, sent only to that entry
|
|
11
|
+
- Fallbacks derived from a `model` array carry no `providerOptions`
|
|
12
|
+
- `MODEL.FIREWORKS.DEEPSEEK` is now `accounts/fireworks/models/deepseek-v4p1-flash`, the same id as `DEEPSEEK_FLASH`. Fireworks withdrew `deepseek-v4-pro-0813` from serverless (404 "Model not found"); its `COST` entry stays
|
|
13
|
+
|
|
14
|
+
## Testing
|
|
15
|
+
|
|
16
|
+
- `npm run test -w packages/llm`: new specs cover operate (cross-provider fallback, per-entry options, linger pass) and ocr scoping
|
|
17
|
+
- Fireworks hot spec passes for every catalog id, deepseek-v4p1-flash included
|
package/skills/llm.md
CHANGED
|
@@ -809,6 +809,23 @@ const response = await Llm.operate(input, {
|
|
|
809
809
|
});
|
|
810
810
|
```
|
|
811
811
|
|
|
812
|
+
### Provider Options in a Chain
|
|
813
|
+
|
|
814
|
+
`providerOptions` belongs to the model it was written for. Per-call `providerOptions` reach the primary only (including its linger pass); a fallback receives only the `providerOptions` on its own entry, or none. Options shaped for one provider (OpenAI `reasoning`, Gemini `thinkingConfig`) would otherwise break every other provider in the chain. Prefer first-class `effort` and `temperature`, which translate per provider.
|
|
815
|
+
|
|
816
|
+
```typescript
|
|
817
|
+
const response = await llm.operate(input, {
|
|
818
|
+
fallback: [
|
|
819
|
+
{
|
|
820
|
+
provider: "google",
|
|
821
|
+
model: LLM.MODEL.GEMINI_FLASH,
|
|
822
|
+
providerOptions: { thinkingConfig: { thinkingBudget: 1024 } },
|
|
823
|
+
},
|
|
824
|
+
],
|
|
825
|
+
providerOptions: { reasoning: { summary: "detailed" } }, // primary only
|
|
826
|
+
});
|
|
827
|
+
```
|
|
828
|
+
|
|
812
829
|
### Fallback Response Metadata
|
|
813
830
|
|
|
814
831
|
```typescript
|