@jaypie/mcp 0.8.186 → 0.8.187
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 +3 -3
- package/package.json +1 -1
- package/release-notes/llm/1.3.63.md +26 -0
- package/skills/llm.md +1 -1
package/dist/assets.js
CHANGED
|
@@ -55,11 +55,11 @@ function getMcpAssetPaths() {
|
|
|
55
55
|
*/
|
|
56
56
|
function getMcpBuildInfo() {
|
|
57
57
|
return {
|
|
58
|
-
commit: "
|
|
58
|
+
commit: "30803408"
|
|
59
59
|
,
|
|
60
|
-
version: "0.8.
|
|
60
|
+
version: "0.8.187"
|
|
61
61
|
,
|
|
62
|
-
versionString: "@jaypie/mcp@0.8.
|
|
62
|
+
versionString: "@jaypie/mcp@0.8.187#30803408"
|
|
63
63
|
,
|
|
64
64
|
};
|
|
65
65
|
}
|
package/package.json
CHANGED
|
@@ -0,0 +1,26 @@
|
|
|
1
|
+
---
|
|
2
|
+
version: 1.3.63
|
|
3
|
+
date: 2026-10-08
|
|
4
|
+
summary: MODEL.HAIKU points at Claude Haiku 5.5
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
## Changes
|
|
8
|
+
|
|
9
|
+
### Claude Haiku 5.5
|
|
10
|
+
|
|
11
|
+
- `MODEL.HAIKU` is now `claude-haiku-5-5`, superseding `claude-haiku-4-5`. Every `MODEL.HAIKU` consumer follows, including the live matrix.
|
|
12
|
+
- `COST` prices `claude-haiku-5-5` at $0.10 input and $0.50 output per million tokens, with cache reads at $0.01 and cache writes at $0.125 (5m) and $0.20 (1h). This is the rate card for prompts up to 100K tokens; the $0.50 / $2.50 long-prompt rate is not modeled. The `claude-haiku-4-5` entry stays so historic usage remains replayable.
|
|
13
|
+
- Streaming requests resolve Haiku 5.5's 128,000 output-token maximum. Haiku 4.5 keeps 64,000.
|
|
14
|
+
- `AnthropicAdapter` strips `temperature` for Haiku 5 and later, which reject non-default sampling parameters with a 400.
|
|
15
|
+
- The deprecated `PROVIDER.ANTHROPIC.MODEL.TINY` tier stays frozen on `claude-haiku-4-5`.
|
|
16
|
+
|
|
17
|
+
### Behavior to expect from the new model
|
|
18
|
+
|
|
19
|
+
- Thinking is adaptive and on by default, and it counts toward `max_tokens`. A caller passing a small explicit output limit may see a response stop before any text.
|
|
20
|
+
- Cost per token drops tenfold against Haiku 4.5, though the newer tokenizer counts the same text as about 30% more tokens.
|
|
21
|
+
|
|
22
|
+
## Testing
|
|
23
|
+
|
|
24
|
+
- `maxOutputTokens.spec.ts` covers the 128,000 ceiling for `claude-haiku-5-5` alongside 64,000 for `claude-haiku-4-5`.
|
|
25
|
+
- `AnthropicAdapter.spec.ts` covers the temperature strip for `claude-haiku-5-5`.
|
|
26
|
+
- Verified live: `claude-haiku-5-5` passes all seven capability matrix cells.
|
package/skills/llm.md
CHANGED
|
@@ -1346,7 +1346,7 @@ truncate:
|
|
|
1346
1346
|
- **Non-streaming** (`operate()`, `send()`): capped at 16,384 tokens —
|
|
1347
1347
|
larger non-streaming responses risk HTTP timeouts (stream instead)
|
|
1348
1348
|
- **Streaming** (`stream()`): the model maximum — e.g., 128,000 for current
|
|
1349
|
-
Claude models (64,000 for Haiku), 65,536 for Gemini 2.5/3.x
|
|
1349
|
+
Claude models (64,000 for Haiku 4.5), 65,536 for Gemini 2.5/3.x
|
|
1350
1350
|
|
|
1351
1351
|
Override per model with `modelOptions`:
|
|
1352
1352
|
|