fix(learning): drop retired retrospective.model key

The model key was added earlier but is RETIRED in the engine (retrospective.py
warns "retrospective.model is no longer honored") — the learning run always uses
the engine-owned engineer-bot model. Keeping it only emits a per-run ::warning::.
Remove it to match the other driver repos.

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

Author: eric-wang-1990

.bot/config.yaml

@@ -126,14 +126,11 @@ flow: bug-fix
 # author phase has something to read before the first retrospective PR lands; the
 # retrospective appends dated sections to that same file thereafter.
 retrospective:
-  # Pin the model explicitly for parity with the sibling bots (reviewer-bot.yml /
-  # engineer-bot.yml both route to databricks-claude-opus-4-8). Learning
-  # extraction is the task that most benefits from the strongest model, so we do
-  # NOT leave it to the engine default — an unpinned key would silently track
-  # whatever that default is and could drift quality/cost out from under us.
-  # (translate_endpoint discards the model path segment, so this key is the only
-  # place the effective retrospective model is chosen.)
-  model: databricks-claude-opus-4-8
+  # No `model:` key: it is RETIRED in the engine (retrospective.py warns
+  # "`retrospective.model` is no longer honored") — the learning run always uses
+  # the engine-owned engineer-bot model (databricks-claude-opus-4-8[1m], override
+  # via the ENGINEER_BOT_MODEL_OVERRIDE workflow env). Setting it here only emits a
+  # per-run ::warning::. Matches the other driver repos' retrospective blocks.
   log_path: .claude/knowledge/learning-log.md   # MUST match author.knowledge_log above
   branch_prefix: ai/learning-pr-
   pr_label: engineer-bot-learning