Extract the inline pure-tool-call tail check to a named helper using
flatten_message_text (canonical content extraction). Fix a SQLite
durability regression: the incremental tool-call persist
(conversation_loop.py:4990) stamps _DB_PERSISTED_MARKER on the assistant
row, so the next _persist_session flush skips it — the filled content
reaches the in-memory transcript but NOT the durable store, and /resume
reloads content="". Pop the marker so the next flush re-writes the row.
Tests pass, ruff clean.
`finalize_turn` guarantees the invariant "delivered final_response =>
assistant row in transcript" (#43849 / #44100) for recovery paths that
return a response without appending a closing assistant message. It
enforces it by checking only the tail's ROLE:
if _tail_role != "assistant":
messages.append({"role": "assistant", "content": final_response})
A tail that is a *pure tool-call turn* — `assistant(tool_calls=[...])`
with no text of its own — satisfies that check while carrying none of the
delivered answer. The append is skipped and the response is never
persisted, so the durable transcript ends at an assistant row the user
never saw as the reply. On the next turn the model replays the user
backlog and re-answers it: exactly the symptom the block was added to
prevent, just reached through a different tail shape.
Observed with the real finalizer: with messages ending
`user -> assistant(content="", tool_calls=[t1])` and
`final_response="Here is your answer."`, the persisted transcript keeps
`content=""` and the answer is absent.
Fill that row's empty content instead of appending. This keeps the
invariant without disturbing the tool-call structure and without creating
an assistant->assistant pair. A tail tool-call row that already carries
model text is left untouched, so no model output is ever overwritten.
Adds regression tests for both: the empty tool-call tail is filled, and a
tool-call tail with existing text is not clobbered.
Close a recovery/fallback final_response with an assistant transcript entry before session persistence so durable history cannot end at a tool/user message after the caller receives a final answer.
Adds a regression for a tool-tail transcript with a non-empty final_response. Related to #46071 / #46053, but covers the adjacent case where the assistant message was never appended before persistence.
