# Telegram reply lifecycle

Status: implemented and verified. The built-in-model/startup and multi-model
live acceptance work continues under `WO-built-in-free-model-startup-20261012.md`.

Read-only live history and delivery receipts confirm that public ping 5804
received acknowledged reply 5805. ESP32 input 5806 failed later and has no
delivery receipt. The display reused one chat view across inputs and reported
later chat failures through an already-completed attention view, mixing these
separate outcomes. Generic exhausted-fallback errors also became unclassified
quick-chat failures.

Reply views are now bound to their exact input. Attention/reply labels identify
the phase; later errors preserve earlier successful replies and do not overwrite
completed attention. Terminal callbacks are idempotent. Exhausted remote fallback
has a typed diagnosis, preserving its nonretryable policy.

Provider acknowledgement is retained immediately. Optional memory/display/notes
or latency observers cannot turn an acknowledged delivery into failure or cause
regeneration. Observation failures are recorded as hashes in a local diagnostic
archive. Durable intake writes and ambiguous send handling retain their existing
authority and no-replay behavior. Manual fallback wording now distinguishes an
unavailable local endpoint from a selected remote provider.

53 lifecycle, recovery, telemetry and public routing regression tests passed;
CLI TypeScript and whitespace checks passed. Transport acknowledgements in these
tests are fixtures, not real Telegram sends. Live inference coverage is recorded
separately in the multi-model work order.
