fix(learning): correct MODEL_ENDPOINT to the concrete serving-endpoint form

The learning workflow set MODEL_ENDPOINT to
`.../serving-endpoints/anthropic/invocations`. That is NOT translated the way the
old comment claimed: sdk_agent.translate_endpoint has an early-return for URLs
already containing `/serving-endpoints/anthropic`, which keeps the trailing
`/invocations` — so the CLI appends `/v1/messages` and calls
`.../serving-endpoints/anthropic/invocations/v1/messages`, which the gateway
rejects with `400 Unsupported native API path`.

Proof: databricks-sql-python's learning cron (same endpoint form) has failed
every scheduled run with exactly this 400. The reviewer-bot flagged it on the
sibling PRs (Low), and it is the real cause.

Use the concrete `.../serving-endpoints/databricks-claude-opus-4-8/invocations`
form that reviewer-bot.yml / engineer-bot.yml already use successfully:
translate_endpoint strips `<model>/invocations` to the `.../serving-endpoints/
anthropic` base the CLI needs. Comment corrected to explain the trap.

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

Author: eric-wang-1990

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

@@ -99,11 +99,15 @@ jobs:
         env:
           GH_TOKEN: ${{ steps.prelude.outputs.token }}
           GITHUB_REPOSITORY: ${{ github.repository }}
-          # Only the `<workspace>/serving-endpoints/` prefix matters:
-          # sdk_agent.translate_endpoint rewrites this to `.../serving-endpoints/anthropic`
-          # and discards the model path segment. The effective model comes from
-          # .bot/config.yaml `retrospective.model` (or the engine default).
-          MODEL_ENDPOINT: https://${{ secrets.DATABRICKS_HOST }}/serving-endpoints/anthropic/invocations
+          # Use the concrete `.../serving-endpoints/<model>/invocations` form (same
+          # as reviewer-bot.yml / engineer-bot.yml). sdk_agent.translate_endpoint
+          # strips it to the `.../serving-endpoints/anthropic` base the CLI needs.
+          # Do NOT use `.../serving-endpoints/anthropic/invocations` here: that hits
+          # translate_endpoint's already-v2 early-return, which keeps the trailing
+          # `invocations`, so the CLI appends `/v1/messages` →
+          # `.../anthropic/invocations/v1/messages` → HTTP 400 (unsupported path).
+          # The effective model is set by the engine default (no retrospective.model).
+          MODEL_ENDPOINT: https://${{ secrets.DATABRICKS_HOST }}/serving-endpoints/databricks-claude-opus-4-8/invocations
           DATABRICKS_TOKEN: ${{ secrets.DATABRICKS_TOKEN }}
           RUNNER_TEMP: ${{ runner.temp }}
           SINCE: ${{ inputs.since }}