Fix an issue where the AI Assistant was not retaining conversation context between messages, with chat history compaction to manage token budgets.

* Address CodeRabbit review feedback for chat context and compaction.

- Track tool-use turns as groups instead of one-to-one pairs, so
  multi-tool assistant messages don't leave orphaned results.
- Add fallback to shrink the recent window when protected messages
  alone exceed the token budget, preventing compaction no-ops.
- Fix low-value test fixtures to keep transient messages short so
  they actually classify as low-importance.
- Guard Clear button against in-flight stream race conditions by
  adding a clearedRef flag and cancelling active streams.
- Assert that conversation history is actually passed through to
  chat_with_database in the "With History" test.

* Address remaining CodeRabbit review feedback for compaction module.

- Expand protected set to cover full tool groups, preventing orphaned
  tool call/result messages when a turn straddles the recent window.
- Add input validation in deserialize_history() for non-list/non-dict data.
- Strengthen test assertion for preserved recent window tail.


* Fix CI test failures in compaction and NLQ chat tests.

- Lower max_tokens budget in test_drops_low_value to reliably force
  compaction (500 was borderline, use 200).
- Consume SSE response data before asserting mock calls in NLQ chat
  test, since Flask's streaming generator only executes on iteration.


* Clarify mock patch target in NLQ chat test.

Add comment explaining why we patch the source module rather than the
use site: the endpoint uses a local import inside the function body,
so there is no module-level binding to patch.

Author: dpage

docs/en_US/release_notes_9_14.rst

@@ -32,6 +32,7 @@ Bug fixes
 *********
 
   | `Issue #9279 <https://github.com/pgadmin-org/pgadmin4/issues/9279>`_ -  Fixed an issue where OAuth2 authentication fails with 'object has no attribute' if OAUTH2_AUTO_CREATE_USER is False.
+  | `Issue #9736 <https://github.com/pgadmin-org/pgadmin4/issues/9736>`_ -  Fixed an issue where the AI Assistant was not retaining conversation context between messages, with chat history compaction to manage token budgets.
   | `Issue #9392 <https://github.com/pgadmin-org/pgadmin4/issues/9392>`_ -  Ensure that the Geometry Viewer refreshes when re-running queries or switching geometry columns, preventing stale data from being displayed.
   | `Issue #9694 <https://github.com/pgadmin-org/pgadmin4/issues/9694>`_ -  Fixed an issue where AI Reports are grayed out after setting an API key by auto-selecting the default provider.
   | `Issue #9702 <https://github.com/pgadmin-org/pgadmin4/issues/9702>`_ -  Fixed misleading AI activity messages that could be mistaken for actual database operations.