fix(bots): set TEST_REPO_ROOT in engineer follow-up (was resolving .bot/ under internal-repo/)

The engineer follow-up run step never set TEST_REPO_ROOT, so run.py defaulted the
.bot/ lookup root to `internal-repo` (the driver-repo layout) and failed at
load_bot with:
  FileNotFoundError: .../databricks-sql-python/internal-repo/.bot/config.yaml

We check out at the workspace root, not internal-repo/, so point TEST_REPO_ROOT
at github.workspace — matching the author step (which already sets it, hence the
author path worked while followup failed). This fixes the failing
engineer-bot-followup runs that kicked off on the PR's open review threads.

Signed-off-by: Eric Wang <e.wang@databricks.com>
Co-authored-by: Isaac
Signed-off-by: eric-wang-1990 <e.wang@databricks.com>

Author: eric-wang-1990

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

@@ -124,6 +124,12 @@ jobs:
           MODEL_ENDPOINT: https://${{ secrets.DATABRICKS_HOST }}/serving-endpoints/databricks-claude-opus-4-8/invocations
           DATABRICKS_TOKEN: ${{ secrets.DATABRICKS_TOKEN }}
           RUNNER_TEMP: ${{ runner.temp }}
+          # The agent's working tree AND the .bot/ lookup root. run.py resolves
+          # the config at <TEST_REPO_ROOT>/.bot/config.yaml, defaulting to
+          # `internal-repo` (the driver-repo layout) when unset — which does NOT
+          # exist here (we check out at the workspace root), so this MUST be set
+          # or load_bot fails with "No such file … internal-repo/.bot/config.yaml".
+          TEST_REPO_ROOT: ${{ github.workspace }}
         run: |
           git remote set-url origin "https://x-access-token:${GH_TOKEN}@github.com/${GITHUB_REPOSITORY}.git"
           python -m databricks_bot_engine.engineer_bot.run --phase followup \