fix(email): don't cancel a retrying agent for a recoverable tool error

[itomek]

When the model calls a batch tool with a bad argument (e.g. archive_message_batch with a stray mailbox kwarg), the agent loop correctly rejects it and starts retrying — but the SSE layer couldn't tell that per-tool retry apart from a genuinely fatal failure, so it ended the response and cancelled the still-retrying agent, dead-ending the turn with no answer and no stats line. Reproduced 4/4 on-hardware before this fix. Now a recoverable error surfaces as a non-terminal status line (the user still sees the failure) and the retry can reach completion.

Closes #2515

Test plan

• python -m pytest tests/unit -k "sse or agent_error" -q — 399 passed
• python -m pytest hub/agents/email/python/tests -k "sse or translation or query_routes" -q — 64 passed
• New regression test drives the real /v1/email/query route + real SSEOutputHandler + real translation layer with a fake agent that emits a recoverable per-tool error then retries: asserts run.cancel_event and handler.cancelled stay unset mid-run and the stream reaches final with both the failed and retried tool calls streamed (test_recoverable_tool_error_does_not_terminate_stream_or_cancel_run)
• python util/lint.py --all — all blocking checks pass

[itomek-amd]

Verified. Clean threading of a recoverable flag from print_error through every SSE handler to the translator, where a recoverable agent_error folds to a non-terminal status line instead of a terminal error — so a per-tool retry (STATE_ERROR_RECOVERY) no longer gets the still-retrying agent cancelled out from under it. The flag is only set when True, keeping the wire shape unchanged for every existing fatal caller; recoverable: false and absence both stay terminal. The end-to-end route test proving both tool_calls stream and the run reaches final is the strong evidence here.