ai: apply changes for #870 (2 review threads)

Addresses:
  - #3600313097 at .github/workflows/engineer-bot-followup.yml:155
  - #3600313099 at .github/workflows/engineer-bot.yml:88

Signed-off-by: peco-engineer-bot[bot] <peco-engineer-bot[bot]@users.noreply.github.com>

Author: peco-engineer-bot[bot]

.bot/prompts/engineer/system.md

@@ -78,6 +78,17 @@ warehouse connection env is set. Run tests through poetry:
   - Your E2E test (fastest loop): `poetry run python -m pytest tests/e2e/<file> -k <name>`
   - A unit test:                  `poetry run python -m pytest tests/unit/<file> -k <name>`
 
+**This runner installs `--all-extras`, so the REAL `databricks-sql-kernel` wheel
+is present.** The unit suite fakes `databricks_sql_kernel` in `sys.modules`
+(`tests/unit/test_kernel_client.py`), which shadows the real wheel in a shared
+session — and the `@pytest.mark.realkernel` routing test
+(`tests/unit/test_session.py::TestUseKernelRoutesThroughRealWheel`) `pytest.fail`s
+loudly when it detects that shadowing. So whenever you run a BROADER unit
+selection than a single `-k` test — a whole file, or `tests/unit` — append
+`-m "not realkernel"` (matching how `.github/workflows/code-coverage.yml` guards
+the same `--all-extras` install). Skipping this produces a confusing false red
+that has nothing to do with your fix.
+
 **Always `-k`-filter to your own test** — do NOT run the whole `tests/e2e` suite:
 this job provides a live connection but does not seed the full per-run fixture set
 the broader suite expects, so unrelated E2E tests would fail or skip and that noise

.github/workflows/engineer-bot-followup.yml

@@ -148,9 +148,13 @@ jobs:
           TRIGGER_COMMENT_ID: ${{ github.event.comment.id }}
           MODEL_ENDPOINT: https://${{ secrets.DATABRICKS_HOST }}/serving-endpoints/databricks-claude-opus-4-8/invocations
           DATABRICKS_TOKEN: ${{ secrets.DATABRICKS_TOKEN }}
-          # Live-warehouse connection env so a followup fixup can also run the
-          # REQUIRED E2E repro/verification test (see engineer/system.md). Mirrors
-          # the author run + code-coverage.yml; job is in `environment: azure-prod`.
+          # Live-warehouse connection env, provisioned for parity with the author
+          # run + code-coverage.yml (job is in `environment: azure-prod`). NOTE:
+          # unlike the author phase, the followup prompt
+          # (.bot/prompts/engineer-followup/system.md) tells the agent to run only
+          # the mocked `tests/unit` suite and NOT tests/e2e. These vars are wired
+          # for consistency with the author run, not an E2E step the followup runs;
+          # if followups should ever repair/run E2E repros, update that prompt too.
           DATABRICKS_SERVER_HOSTNAME: ${{ secrets.DATABRICKS_HOST }}
           DATABRICKS_HTTP_PATH: ${{ secrets.TEST_PECO_WAREHOUSE_HTTP_PATH }}
           DATABRICKS_CATALOG: peco