@jaypie/mcp 0.8.71 → 0.8.73

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@0.8.71#38772586"
+const BUILD_VERSION_STRING = "@jaypie/mcp@0.8.73#8addc2dd"
     ;
 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": "0.8.71",
+  "version": "0.8.73",
   "description": "Jaypie MCP",
   "repository": {
     "type": "git",

package/release-notes/constructs/1.2.64.md

@@ -0,0 +1,13 @@
+---
+version: 1.2.64
+date: 2026-06-17
+summary: Pass Datadog LLM Observability env vars to Lambdas; bump Datadog layer versions
+---
+
+## Changes
+
+- `jaypieLambdaEnv` (and therefore every `JaypieLambda` derivative) now passes Datadog LLM Observability environment variables through to the Lambda at synth time:
+  - `DD_LLMOBS_ENABLED` is forwarded from `process.env` when set.
+  - `DD_LLMOBS_ML_APP` is forwarded when set, **unless** observability is disabled (`DD_LLMOBS_ENABLED` resolves to `"false"` or `"0"`).
+  - Explicit `environment` props win over `process.env`, including for the disable gate — `environment: { DD_LLMOBS_ENABLED: "false" }` suppresses the `DD_LLMOBS_ML_APP` passthrough.
+- Bumps Datadog Lambda layers to `NODE: 139` and `EXTENSION: 97`.

package/release-notes/llm/1.2.40.md

@@ -0,0 +1,14 @@
+---
+version: 1.2.40
+date: 2026-06-17
+summary: Opt-in Datadog LLM Observability span emission from operate()/stream() via DD_LLMOBS_ENABLED
+---
+
+## @jaypie/llm 1.2.40
+
+### Features
+
+- **LLM Observability**: When `DD_LLMOBS_ENABLED` is set, `operate()` and `stream()` emit Datadog `llm`/`tool` spans (annotated with input, output, and token metrics) plus an enclosing `agent`/`llm` span — no code changes required (#373).
+  - Lazy, **bundler-safe** `dd-trace` resolution (computed module specifier); `dd-trace` is not a dependency. Fully no-op when the flag is unset or `dd-trace` is absent, and instrumentation failures never break the underlying call.
+  - Parenting is AsyncLocalStorage-based: spans attach to any active enclosing LLMObs span (e.g. a consumer `llmobs.trace({ kind: "workflow" })`).
+  - `operate()` spans nest fully (model + tool under the enclosing span). `stream()` spans attach to an active enclosing span but are siblings within a single stream (the held-open streamed model span is not active when tools run).

package/release-notes/mcp/0.8.72.md

@@ -0,0 +1,10 @@
+---
+version: 0.8.72
+date: 2026-06-17
+summary: Add @jaypie/llm 1.2.40 release notes; document LLM Observability (DD_LLMOBS_ENABLED) in the llm skill
+---
+
+## Changes
+
+- Adds release notes for `@jaypie/llm` 1.2.40 (opt-in Datadog LLM Observability span emission).
+- Documents the `DD_LLMOBS_ENABLED` LLM Observability behavior and span parenting semantics in the `llm` skill.

package/release-notes/mcp/0.8.73.md

@@ -0,0 +1,10 @@
+---
+version: 0.8.73
+date: 2026-06-17
+summary: Add @jaypie/constructs 1.2.64 release notes; document LLM Observability env passthrough in the cdk skill
+---
+
+## Changes
+
+- Adds release notes for `@jaypie/constructs` 1.2.64 (Datadog LLM Observability env passthrough; Datadog layer bumps).
+- Documents the `DD_LLMOBS_ENABLED` / `DD_LLMOBS_ML_APP` synth-time passthrough behavior in the `cdk` skill.

package/skills/cdk.md

@@ -292,6 +292,10 @@ const handler = new JaypieLambda(this, "Handler", {
 });
 ```
 
+### LLM Observability passthrough
+
+If `DD_LLMOBS_ENABLED` is set at synth time, `JaypieLambda` (and every derivative) forwards it to the Lambda environment. `DD_LLMOBS_ML_APP` is forwarded too — **unless** observability is disabled (`DD_LLMOBS_ENABLED` resolves to `"false"` or `"0"`). Explicit `environment` props win over `process.env`, including the disable gate, so `environment: { DD_LLMOBS_ENABLED: "false" }` suppresses the `DD_LLMOBS_ML_APP` passthrough. This is the deploy-time half of the runtime opt-in documented in `skill("llm")`.
+
 ## JaypieNextJs
 
 Deploy Next.js applications:

package/skills/llm.md

@@ -336,6 +336,28 @@ XAI_API_KEY         # Required for xAI (Grok)
 
 Keys are resolved via `getEnvSecret()` which supports AWS Secrets Manager.
 
+## LLM Observability (Datadog)
+
+Set `DD_LLMOBS_ENABLED` (any truthy value except `false`/`0`) and `operate()`/`stream()` emit Datadog [LLM Observability](https://docs.datadoghq.com/llm_observability/) spans with **no code changes**:
+
+- Enclosing span per call (`agent` when tools are configured, else `llm`)
+- Child `llm` span per model request — annotated with input, output, token metrics
+- Child `tool` span per tool execution — annotated with args + result
+
+```bash
+DD_LLMOBS_ENABLED=true   # opt in; unset = fully no-op
+DD_LLMOBS_ML_APP=my-app  # ML app name (dd-trace standard)
+```
+
+Behavior:
+
+- **Opt-in and lazy** — `dd-trace` is resolved at runtime via a computed module specifier, so it is **bundler-safe** (esbuild will not bundle it) and **not** a dependency. Absence is a silent no-op; instrumentation failures never break the LLM call.
+- **Parenting is AsyncLocalStorage-based** — spans attach to whatever LLMObs span is active when created. Wrapping a call in a consumer span (e.g. `llmobs.trace({ kind: "workflow" }, () => Llm.operate(...))`) nests ours under it. The Datadog Lambda layer provides APM spans automatically, but not an enclosing *LLMObs* span around an arbitrary handler.
+- **`operate()`** spans form a full tree (model + tool nest under the enclosing span).
+- **`stream()`** spans attach to any active enclosing span, but within a single stream the `llm` and `tool` spans are **siblings** — the streamed model span is held open across `yield` boundaries, so it is not the active span when tools run.
+
+For esbuild-bundled Lambda handlers that also want dd-trace auto-instrumentation, wire the `dd-trace/esbuild` plugin with `keepNames: true`; the spans above do not require it.
+
 ## Error Handling
 
 The package auto-retries rate limits and transient errors: