diff --git a/.changeset/bootstrap-honest-status.md b/.changeset/bootstrap-honest-status.md
deleted file mode 100644
index 31c57b6..0000000
--- a/.changeset/bootstrap-honest-status.md
+++ /dev/null
@@ -1,7 +0,0 @@
----
-'@smooai/observability': minor
----
-
-Rust bootstrap now reports whether it is actually EXPORTING, not just whether it
-ran, and warns loudly when no OTLP endpoint is configured. `installed: true` with
-no endpoint used to read as success while nothing left the process.
diff --git a/.changeset/ts-gen-ai-openai.md b/.changeset/ts-gen-ai-openai.md
deleted file mode 100644
index 07b187c..0000000
--- a/.changeset/ts-gen-ai-openai.md
+++ /dev/null
@@ -1,11 +0,0 @@
----
-'@smooai/observability': minor
----
-
-Instrument the OpenAI Node SDK, and stop leaking prompt content into GenAI span events.
-
-`wrapOpenAI(client, options)` returns a proxy of an OpenAI client whose `chat.completions.create` emits OTel GenAI semantic-convention spans — request model / sampling params / tool names on the way out, response model, id, finish reason, and token usage on the way back. Streaming is handled: the span stays open until the stream drains (or the consumer breaks out early), and picks up the usage chunk emitted under `stream_options.include_usage`. The client is duck-typed, so this adds no dependency on `openai` and works against Groq, Together, Fireworks, DeepSeek, Azure OpenAI, and any OpenAI-compatible gateway via `{ system: 'groq' }`.
-
-Cost has a seam now: nothing in the platform computes an LLM price on its own, which is why the dashboard's cost column is empty. Pass `costUsd({ requestModel, responseModel, inputTokens, outputTokens, cachedTokens })` and it lands on `gen_ai.usage.cost_usd`.
-
-`recordGenAIMessage` now routes content through the SDK's PII scrub before it leaves the process. Prompts are the most PII-dense payload this SDK can touch, and `wrapOpenAI` keeps content recording **off** by default (`{ recordContent: true }` opts in).
diff --git a/packages/core/CHANGELOG.md b/packages/core/CHANGELOG.md
index c776c3b..61fcb6f 100644
--- a/packages/core/CHANGELOG.md
+++ b/packages/core/CHANGELOG.md
@@ -1,5 +1,20 @@
 # @smooai/observability
 
+## 0.16.0
+
+### Minor Changes
+
+- d40f623: Rust bootstrap now reports whether it is actually EXPORTING, not just whether it
+  ran, and warns loudly when no OTLP endpoint is configured. `installed: true` with
+  no endpoint used to read as success while nothing left the process.
+- 1104624: Instrument the OpenAI Node SDK, and stop leaking prompt content into GenAI span events.
+
+  `wrapOpenAI(client, options)` returns a proxy of an OpenAI client whose `chat.completions.create` emits OTel GenAI semantic-convention spans — request model / sampling params / tool names on the way out, response model, id, finish reason, and token usage on the way back. Streaming is handled: the span stays open until the stream drains (or the consumer breaks out early), and picks up the usage chunk emitted under `stream_options.include_usage`. The client is duck-typed, so this adds no dependency on `openai` and works against Groq, Together, Fireworks, DeepSeek, Azure OpenAI, and any OpenAI-compatible gateway via `{ system: 'groq' }`.
+
+  Cost has a seam now: nothing in the platform computes an LLM price on its own, which is why the dashboard's cost column is empty. Pass `costUsd({ requestModel, responseModel, inputTokens, outputTokens, cachedTokens })` and it lands on `gen_ai.usage.cost_usd`.
+
+  `recordGenAIMessage` now routes content through the SDK's PII scrub before it leaves the process. Prompts are the most PII-dense payload this SDK can touch, and `wrapOpenAI` keeps content recording **off** by default (`{ recordContent: true }` opts in).
+
 ## 0.15.0
 
 ### Minor Changes
diff --git a/packages/core/package.json b/packages/core/package.json
index 2773766..02f33bb 100644
--- a/packages/core/package.json
+++ b/packages/core/package.json
@@ -1,6 +1,6 @@
 {
     "name": "@smooai/observability",
-    "version": "0.15.0",
+    "version": "0.16.0",
     "description": "Smoo AI Observability SDK — OTel-first error capture, traces, metrics, and React/Next.js integrations in a single package with subpath exports",
     "homepage": "https://github.com/SmooAI/observability",
     "bugs": {