[evaluation] backport 1.16.6 release notes; bump version to 1.16.7 (#46574)

- Set 1.16.6 release date to 2026-04-27 (matches PyPI release)

- Add #46502 token usage bullet to 1.16.6 (shipped in hotfix)

- Add empty 1.16.7 (Unreleased) section

- Bump _version.py to 1.16.7

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: slister1001

sdk/evaluation/azure-ai-evaluation/CHANGELOG.md

@@ -1,13 +1,20 @@
 # Release History
 
-## 1.16.6 (Unreleased)
+## 1.16.7 (Unreleased)
 
 ### Features Added
 
 ### Breaking Changes
 
 ### Bugs Fixed
 
+### Other Changes
+
+## 1.16.6 (2026-04-27)
+
+### Bugs Fixed
+
+- Fixed evaluation token usage not being emitted in the genai evaluation event, causing token consumption metrics to be missing from telemetry.
 - Fixed multi-turn red team attacks (`RedTeamingAttack`-based strategies like `MultiTurn`) failing silently with PyRIT 0.11. Two bugs were patched at the SDK level: (1) `RedTeamingAttack._setup_async` raised `RuntimeError: Conversation already exists` because it seeded prepended conversation messages before calling `set_system_prompt`; now patched per-instance on the adversarial chat target to tolerate existing conversation history. (2) `RedTeamingAttack._generate_next_prompt_async` returned `context.next_message` without calling `.duplicate_message()`, causing `sqlite3.IntegrityError: UNIQUE constraint failed: PromptMemoryEntries.id` on the second turn; now patched at module load with an idempotent wrapper that duplicates the message before returning.
 - Fixed `sensitive_data_leakage` red team attacks producing 100% false-pass rates. `_extract_context_items` in the Foundry execution path only handled `list` or `dict` shapes for `messages[0].context`; pre-curated SDL attack objectives store the document text as a `str` with sibling `context_type`/`tool_name` fields, so the document was silently dropped and a fallback synthesized a context item from the user prompt. The agent never received the sensitive document content and could not leak it, causing the evaluator to score every attempt as a pass. Added `str` handling (both message-level and top-level), normalized raw string entries inside list-shaped context, and gated the `context_type` fallback so it only runs when no usable context was extracted (including the `context: null` case).
 

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_version.py

@@ -3,4 +3,4 @@
 # ---------------------------------------------------------
 # represents upcoming version
 
-VERSION = "1.16.6"
+VERSION = "1.16.7"

sdk/evaluation/azure-ai-evaluation/cspell.json

@@ -31,7 +31,8 @@
         "etests",
         "redteam",
         "redef",
-        "smode"
+        "smode",
+        "genai"
     ],
     "ignorePaths": [
         "sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_common/onedp/models/_enums.py",