@jaypie/mcp 0.8.47 → 0.8.50

package/dist/suites/docs/index.js

@@ -9,7 +9,7 @@ import { gt } from 'semver';
 /**
  * Docs Suite - Documentation services (skill, version, release_notes)
  */
-const BUILD_VERSION_STRING = "@jaypie/mcp@0.8.47#d4678bbc"
+const BUILD_VERSION_STRING = "@jaypie/mcp@0.8.50#a1804d0f"
     ;
 const __filename$1 = fileURLToPath(import.meta.url);
 const __dirname$1 = path.dirname(__filename$1);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jaypie/mcp",
-  "version": "0.8.47",
+  "version": "0.8.50",
   "description": "Jaypie MCP",
   "repository": {
     "type": "git",

package/release-notes/fabricator/0.3.2.md

@@ -0,0 +1,28 @@
+---
+version: 0.3.2
+date: 2026-04-24
+summary: Adds fab.corpus() for seeded corpus text generation
+---
+
+## Changes
+
+- New `fab.corpus(words?, options?)` method on `Fabricator` for generating deterministic prose fixtures.
+- Default 108 words; pass a number for any other size.
+- Custom corpus support: pass `corpus` (raw text) or `words` (explicit weights). Custom and default English pools blend 50/50 by default; tune with `blend` or skip defaults with `replaceDefaults: true`.
+- Custom token functions via `functions` option — each function receives the fabricator and emits one token per draw, with weight subtracted from the main word stream. Useful for UUIDs, dollar amounts, emails, and other non-word-shaped tokens. Shorthand `[fn, weight]` for one function, `[[fn1, w1], [fn2, w2]]` for many.
+- Full passthrough of typo rate, phonotactic rate, sentence/punctuation density, and a `chars` escape hatch for char-length output.
+- `CorpusOptions`, `CorpusTokenFunction`, and `CorpusFunctionEntry` types exported from `@jaypie/fabricator`.
+
+## Determinism contract
+
+- Each call advances the fabricator's faker state, so successive calls with the same params return different output (`fab.corpus(100) !== fab.corpus(100)`).
+- Replaying from a fresh `fabricator(seed)` reproduces the same sequence.
+- Word count and options are folded into the per-call seed, so different params produce independent streams — `corpus(100)` and `corpus(101)` are not off-by-one variants of each other.
+
+## Why
+
+Test fixtures and seeded benchmarks frequently want bulk prose with stable, reproducible content. `lorem` is too uniform; ad-hoc generators are non-deterministic. `corpus()` fills that gap with a single ergonomic call that respects the fabricator's seeding contract.
+
+## Implementation note
+
+Generator internals (`babble`, `phonotactic`, English word/typo data, `Rng`) live in `src/corpus/` as a private vendored module. They are not exported — only the `corpus()` method and `CorpusOptions` type.

package/release-notes/jaypie/1.2.43.md

@@ -0,0 +1,12 @@
+---
+version: 1.2.43
+date: 2026-04-29
+summary: Pull in @jaypie/llm 1.2.31 (native structured outputs across all providers)
+---
+
+## Changes
+
+- Bumped `@jaypie/llm` peer-dep range to `^1.2.31`, exposing:
+  - Anthropic, OpenAI, Gemini 3, and xAI all use native structured outputs by default (no more `structured_output` fake-tool emulation in the happy path).
+  - Per-provider runtime fallback that engages the legacy fake-tool path transparently when a model rejects native structured output, with a `log.warn` so silent degradations don't hide.
+  - Anthropic specifically: native field is `output_config.format` (the earlier `output_format` was deprecated by the API).

package/release-notes/llm/1.2.30.md

@@ -0,0 +1,29 @@
+---
+version: 1.2.30
+date: 2026-04-28
+summary: Anthropic provider uses native structured outputs in place of the structured_output fake-tool emulation
+---
+
+## Changes
+
+- `AnthropicAdapter` (`operate()`/`stream()`):
+  - When `format` is set, the request body now includes `output_config: { format: { type: "json_schema", schema } }` instead of injecting a synthetic `structured_output` tool with `tool_choice: "any"`.
+  - JSON schemas are sanitized for Anthropic's grammar compiler: objects always get `additionalProperties: false`, unsupported numeric/string/array constraints (`minimum`, `maxLength`, `multipleOf`, …) are appended to `description` rather than sent to the API, unsupported string formats are stripped, and `minItems` is preserved only when 0 or 1.
+  - Responses to structured-output requests are parsed from the first `text` content block (guaranteed valid JSON by the Anthropic grammar). `stop_reason: "refusal"` and `stop_reason: "max_tokens"` are recognized and surface as text rather than triggering a parse error.
+  - Streaming structured outputs now arrive as `LlmStreamChunkType.Text` deltas (consumers concat to assemble JSON), instead of a single `ToolCall` chunk.
+- `AnthropicProvider.send(message, { response })`: the system prompt is no longer stuffed with the JSON schema, and the regex JSON extraction is gone. The native `output_config.format` field handles the contract.
+- A runtime fallback re-engages the legacy fake-tool emulation transparently when a model rejects `output_config` (cached per model in `runtimeNoStructuredOutputModels`). Citations-related 400s and `output_format`-deprecation 400s are explicitly excluded so they propagate instead of being masked by a retry.
+
+## Why
+
+Anthropic launched native structured outputs publicly on 2025-11-14 (now GA on Claude 4.5+). The previous tool-emulation hack predates the feature. Native:
+- Removes a fragile regex extraction in `provider.send`.
+- Removes the synthetic `structured_output` tool from the operate loop.
+- Returns guaranteed-valid JSON via grammar-constrained generation rather than relying on the model to comply with a system-prompt instruction.
+- Keeps a fallback path for any model that does not (yet) support `output_config`.
+
+## Notes
+
+- Streaming consumers that previously branched on a `tool_call` chunk to receive structured output will now see `text` chunks. Concatenate to assemble the final JSON, or use `operate()` for the parsed object.
+- Schema constraints not supported by Anthropic's grammar (regex `pattern`, `minLength`, numeric ranges, recursion) are stripped at request time. The original constraints are still enforced client-side by the caller's Zod schema during result validation.
+- Gemini and OpenRouter still use the fake-tool emulation pattern; native migration for those adapters is a separate task.

package/release-notes/llm/1.2.31.md

@@ -0,0 +1,33 @@
+---
+version: 1.2.31
+date: 2026-04-29
+summary: OpenRouter and Gemini adapters drop the structured_output fake-tool hack in favor of native response_format / responseJsonSchema (with runtime fallback for unsupported models)
+---
+
+## Changes
+
+- `OpenRouterAdapter` (`operate()`/`stream()`):
+  - When `format` is set, the request body now includes `response_format: { type: "json_schema", json_schema: { name, schema, strict: true } }` instead of injecting a synthetic `structured_output` tool.
+  - `formatTools` no longer injects the synthetic tool. The legacy fake tool is added in `buildRequest` only as a runtime fallback for models cached as not supporting native `response_format`.
+  - `formatOutputSchema` now forces `additionalProperties: false` on every object (required for `strict: true`).
+  - `executeRequest` annotates the response with a `__jaypieStructuredOutput` flag so `hasStructuredOutput` / `extractStructuredOutput` can detect intent statelessly. The native path parses `choices[0].message.content` as JSON; the fallback path keeps the existing tool-call extraction.
+  - 400/422 errors mentioning `response_format`/`json_schema`/`structured_output`/`require_parameters` cache the model in `runtimeNoStructuredOutputModels` and trigger a one-shot retry via the legacy fake-tool path. Unrelated 4xx propagate.
+  - `log.warn` at both fallback entry points (initial cached-model build and 4xx retry).
+- `GeminiAdapter` (`operate()`/`stream()`):
+  - Format **and** tools combined now uses native `responseJsonSchema` + tools when the model id matches `^gemini-3` (Gemini 3 preview). Gemini 2.5 (including thinking) and earlier keep the `structured_output` fake-tool emulation with the system-prompt nudge.
+  - `formatTools` no longer injects the synthetic structured_output tool; the fake tool is added in `buildRequest` only when the runtime falls back.
+  - 400 errors mentioning `responseJsonSchema`/`responseSchema`/`responseMime`/`function_call`/`tools` cache the model in `runtimeNoStructuredOutputComboModels` and trigger a one-shot retry via the legacy fake-tool path.
+  - `log.warn` at both fallback entry points.
+
+## Why
+
+OpenRouter exposes the OpenAI-style structured-outputs shape end-to-end, and Gemini 3 launched as a preview supporting tools + `responseJsonSchema` together. The `structured_output` fake-tool emulation predates both. Native:
+- Returns guaranteed-valid JSON via grammar-constrained generation rather than relying on the model to comply with a system-prompt instruction.
+- Removes the synthetic tool from the operate-loop tool list (cleaner traces, no risk of the model ignoring the nudge).
+- Keeps a fallback path that re-engages the fake-tool emulation transparently when a model rejects the native field.
+
+## Notes
+
+- Anthropic was migrated in 1.2.30; with this release, all four LLM providers (Anthropic, OpenAI, OpenRouter, Gemini) use native structured outputs by default. xAI inherits from `OpenAiAdapter` and was already native.
+- Gemini 2.5 thinking models stay on the fake-tool path because the combo is unreliable on 2.5; this matches Google's documentation that the combo is a Gemini 3 preview feature.
+- Streaming consumers that previously branched on a `tool_call` chunk to receive structured output from OpenRouter/Gemini will now see `text` chunks. Concatenate to assemble the final JSON, or use `operate()` for the parsed object.

package/release-notes/mcp/0.8.48.md

@@ -0,0 +1,10 @@
+---
+version: 0.8.48
+date: 2026-04-24
+summary: Update fabricator skill with corpus() coverage
+---
+
+## Changes
+
+- Added a Corpus section to `skill("fabricator")` covering `fab.corpus()`: signatures, determinism contract (advance per call, replay across runs, params-folded-into-seed), custom corpus blending (`corpus`, `words`, `blend`, `replaceDefaults`), and custom token functions (`functions` shorthand and array forms).
+- Documented the full `CorpusOptions` shape and `CorpusTokenFunction` type.

package/release-notes/mcp/0.8.49.md

@@ -0,0 +1,9 @@
+---
+version: 0.8.49
+date: 2026-04-28
+summary: Add release notes for @jaypie/llm 1.2.30 (Anthropic native structured outputs)
+---
+
+## Changes
+
+- Added `release-notes/llm/1.2.30.md` covering the Anthropic provider's switch from the `structured_output` fake-tool emulation to Anthropic's native `output_format` structured outputs (with a runtime fallback to the legacy path for unsupported models).

package/release-notes/mcp/0.8.50.md

@@ -0,0 +1,9 @@
+---
+version: 0.8.50
+date: 2026-04-29
+summary: Add release notes for @jaypie/llm 1.2.31 (OpenRouter and Gemini native structured outputs)
+---
+
+## Changes
+
+- Added `release-notes/llm/1.2.31.md` covering the OpenRouter and Gemini adapters' migration from the `structured_output` fake-tool emulation to native `response_format: json_schema` (OpenRouter) and `responseJsonSchema` + tools (Gemini 3), with a runtime fallback for unsupported models.

package/skills/fabricator.md

@@ -85,6 +85,82 @@ fab.generate.person();
 - **RARE (2.1%)**: firstName is a surname, lastName is hyphenated
 - **EPIC (0.307%)**: double middle names
 
+### Corpus
+
+Generate deterministic prose for fixtures, snapshots, or seeded benchmarks.
+
+```typescript
+const fab = fabricator("seed");
+
+fab.corpus();              // 108 words of English-ish prose (default)
+fab.corpus(1000);          // 1000 words
+fab.corpus({ wordsPerPeriod: 10 });
+fab.corpus(500, { typoRate: 0.20 });
+```
+
+#### Determinism contract
+
+- Each call **advances** the fabricator's faker state, so successive calls with the same params return different output (`fab.corpus(100) !== fab.corpus(100)`).
+- Replaying from a fresh `fabricator(seed)` reproduces the same sequence.
+- Word count and options are folded into the per-call seed, so different params produce **independent** streams. `corpus(100)` and `corpus(101)` differ across the whole text — not by one word.
+
+#### Custom corpus
+
+Mix domain vocabulary into the output. By default the custom pool blends 50/50 with default English; typo (~6%) and phonotactic invention (~3%) rates stay at their defaults.
+
+```typescript
+fab.corpus(500, { corpus: deployLogText });            // raw text → derived weights
+fab.corpus(500, { words: [["deploy", 5], ["lambda", 2]] });
+
+fab.corpus(500, { corpus: deployLogText, blend: 0.7 }); // tune the mix
+fab.corpus(500, { corpus: deployLogText, replaceDefaults: true }); // pure custom
+```
+
+#### Custom token functions
+
+For non-word-shaped tokens (UUIDs, dollar amounts, IDs), pass `functions`. Each function receives the fabricator and emits one token per draw. Weight is the share of total content tokens taken from the main word stream.
+
+```typescript
+// Shorthand for a single function
+fab.corpus(500, {
+  functions: [({ fab }) => fab.string.uuid(), 0.03],
+});
+
+// Multiple functions
+fab.corpus(500, {
+  functions: [
+    [({ fab }) => fab.string.uuid(), 0.03],
+    [({ fab }) => "$" + fab.finance.amount(), 0.04],
+    [({ fab }) => fab.internet.email(), 0.02],
+  ],
+});
+```
+
+#### Full options
+
+```typescript
+interface CorpusOptions {
+  corpus?: string;                                  // raw text → derive weights
+  words?: ReadonlyArray<readonly [string, number]>; // explicit weights
+  blend?: number;                                   // share given to custom pool, default 0.5
+  replaceDefaults?: boolean;                        // skip default English entirely
+  typos?: ReadonlyArray<readonly [string, number]>; // override typo pool
+  phonotactic?: PhonotacticOptions;                 // tune invented words
+  typoRate?: number;                                // default 0.06
+  phonotacticRate?: number;                         // default 0.03
+  wordsPerPeriod?: number;                          // default 17
+  wordsPerComma?: number;                           // default 22
+  periodsPerBreak?: number;                         // default 5
+  sentences?: boolean;                              // default true
+  chars?: number;                                   // generate by char length instead of word count
+  functions?:                                       // custom token functions
+    | readonly [CorpusTokenFunction, number]
+    | ReadonlyArray<readonly [CorpusTokenFunction, number]>;
+}
+
+type CorpusTokenFunction = (params: { fab: Fabricator }) => string;
+```
+
 ## CHANCE Constants
 
 ```typescript