docs(changelog): attribute Groq catalog fix

Author: code-yeongyu

packages/ai/CHANGELOG.md

@@ -14,7 +14,8 @@
   `qwen/qwen3.6-27b`: the active multimodal model now receives Groq's documented
   `reasoning_effort` compatibility (`off` to `none`, thinking mode to `default`), the typed request regression
   follows the replacement catalog ID, and reviewed provider snapshots are refreshed so live generation no longer
-  breaks root TypeScript validation before a release can be committed.
+  breaks root TypeScript validation before a release can be committed
+  ([#716](https://github.com/code-yeongyu/senpi/pull/716)).
 
 ### Removed
 

packages/coding-agent/CHANGELOG.md

@@ -20,7 +20,8 @@
 - Fixed release preparation failing after Groq replaced `qwen/qwen3-32b` with the multimodal
   `qwen/qwen3.6-27b`: Senpi's generated model catalog and typed request regression now follow the active model,
   preserve Groq's `none`/`default` reasoning controls, and include the reviewed live provider metadata refresh so
-  `senpi --list-models` and release-time validation agree.
+  `senpi --list-models` and release-time validation agree
+  ([#716](https://github.com/code-yeongyu/senpi/pull/716)).
 - Fixed Claude SDK OAuth full-history re-sends repeatedly billing accumulated `<ultrawork-mode>` directives by
   post-processing both resident flatten/bootstrap prompts and the non-resident full-prompt path: every earlier
   complete directive becomes a one-line superseded marker while the most recent copy, surrounding text, non-text