@jaypie/mcp 0.8.185 → 0.8.187

package/dist/assets.js

@@ -55,11 +55,11 @@ function getMcpAssetPaths() {
  */
 function getMcpBuildInfo() {
     return {
-        commit: "a5a715a3"
+        commit: "30803408"
             ,
-        version: "0.8.185"
+        version: "0.8.187"
             ,
-        versionString: "@jaypie/mcp@0.8.185#a5a715a3"
+        versionString: "@jaypie/mcp@0.8.187#30803408"
             ,
     };
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jaypie/mcp",
-  "version": "0.8.185",
+  "version": "0.8.187",
   "description": "Jaypie MCP",
   "repository": {
     "type": "git",

package/release-notes/jaypie/1.2.121.md

@@ -0,0 +1,9 @@
+---
+version: 1.2.121
+date: 2026-10-08
+summary: Pulls @jaypie/llm 1.3.62
+---
+
+## Changes
+
+- **`@jaypie/llm` 1.3.62**: Anthropic `format` schemas with more than 16 nullable or union-typed parameters answer through the `structured_output` tool path.

package/release-notes/llm/1.3.62.md

@@ -0,0 +1,22 @@
+---
+version: 1.3.62
+date: 2026-10-08
+summary: Anthropic format schemas with more than 16 nullable or union-typed parameters answer through the structured_output tool path
+---
+
+## Changes
+
+### Union parameter limit (issue #616)
+
+Anthropic rejects native structured output (`output_config.format`) when a schema carries more than 16 union-typed parameters, and every `.nullable()` field is one. The 400 ("Schemas contains too many parameters with union types") matched none of the patterns that trigger the `structured_output` tool fallback, so `operate` failed, and an Anthropic fallback in a chain could not serve such a schema.
+
+- `AnthropicAdapter.buildRequest` counts the schema's union-typed parameters (`anyOf` or a `type` array, at any depth) and sends a schema over 16 straight to the tool path, avoiding the rejected round trip.
+- The union-limit 400 is retried through the tool path for the request that received it.
+- Neither path demotes the model. The limit belongs to the schema, so the same model keeps native `output_config.format` for smaller schemas.
+- Both log at debug.
+- Citations and deprecated-field 400s still propagate unchanged.
+
+## Testing
+
+- `AnthropicAdapter.spec.ts` covers the retry, the model staying native afterward, the count at 16 and 17, `type` arrays and nested unions, and the debug log on each path.
+- Verified live on `claude-sonnet-5-5` and `claude-opus-5-5`: the API accepts 16 union-typed parameters natively and rejects 17.

package/release-notes/llm/1.3.63.md

@@ -0,0 +1,26 @@
+---
+version: 1.3.63
+date: 2026-10-08
+summary: MODEL.HAIKU points at Claude Haiku 5.5
+---
+
+## Changes
+
+### Claude Haiku 5.5
+
+- `MODEL.HAIKU` is now `claude-haiku-5-5`, superseding `claude-haiku-4-5`. Every `MODEL.HAIKU` consumer follows, including the live matrix.
+- `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.
+- Streaming requests resolve Haiku 5.5's 128,000 output-token maximum. Haiku 4.5 keeps 64,000.
+- `AnthropicAdapter` strips `temperature` for Haiku 5 and later, which reject non-default sampling parameters with a 400.
+- The deprecated `PROVIDER.ANTHROPIC.MODEL.TINY` tier stays frozen on `claude-haiku-4-5`.
+
+### Behavior to expect from the new model
+
+- 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.
+- Cost per token drops tenfold against Haiku 4.5, though the newer tokenizer counts the same text as about 30% more tokens.
+
+## Testing
+
+- `maxOutputTokens.spec.ts` covers the 128,000 ceiling for `claude-haiku-5-5` alongside 64,000 for `claude-haiku-4-5`.
+- `AnthropicAdapter.spec.ts` covers the temperature strip for `claude-haiku-5-5`.
+- Verified live: `claude-haiku-5-5` passes all seven capability matrix cells.

package/release-notes/mcp/0.8.186.md

@@ -0,0 +1,10 @@
+---
+version: 0.8.186
+date: 2026-10-08
+summary: Release notes for @jaypie/llm 1.3.62 and jaypie 1.2.121; llm skill documents Anthropic's union parameter limit
+---
+
+## Changes
+
+- **Release notes**: `@jaypie/llm` 1.3.62 and `jaypie` 1.2.121
+- **`llm` skill**: Anthropic's limit of 16 union-typed parameters on native structured output

package/skills/llm.md

@@ -410,6 +410,8 @@ const result = await Llm.operate(
 );
 ```
 
+Anthropic's native structured output accepts at most 16 union-typed parameters per schema, and every `.nullable()` field counts as one. A larger schema is answered through a `structured_output` tool call instead and still returns parsed JSON in `content`.
+
 ### Bare JSON Schema
 
 `format` also duck-types a bare JSON Schema object node — `{ type: "object", properties: {...} }` — without needing the OpenAI-style `{ type: "json_schema", ... }` envelope. `required` is honored.
@@ -1344,7 +1346,7 @@ truncate:
 - **Non-streaming** (`operate()`, `send()`): capped at 16,384 tokens —
   larger non-streaming responses risk HTTP timeouts (stream instead)
 - **Streaming** (`stream()`): the model maximum — e.g., 128,000 for current
-  Claude models (64,000 for Haiku), 65,536 for Gemini 2.5/3.x
+  Claude models (64,000 for Haiku 4.5), 65,536 for Gemini 2.5/3.x
 
 Override per model with `modelOptions`: