f726090d48
Titling fired on the first response, so a session sat unnamed for the whole opening turn - p50 151s, p90 1212s across real sessions, because a turn is tool calls, not one round-trip. A turn that failed or was interrupted never got a title at all. Four surfaces each carried their own copy of the call. Move it into the shared turn prologue and split it in two: a deterministic title derived from the user's opening message, written inline before the model runs, then one small-model call that upgrades it. The response is constrained to a JSON object so there is no preamble to strip, and control wrappers are stripped rather than refused, so a slash command titles as what the user asked for instead of the command itself. |
||
|---|---|---|
| .. | ||
| assets | ||
| builtin_hooks | ||
| platforms | ||
| relay | ||
| __init__.py | ||
| agent_cache_pressure.py | ||
| authz_mixin.py | ||
| cgroup_cleanup.py | ||
| channel_directory.py | ||
| code_skew.py | ||
| config.py | ||
| cwd_placeholder.py | ||
| dead_targets.py | ||
| delivery.py | ||
| delivery_ledger.py | ||
| display_config.py | ||
| drain_control.py | ||
| hooks.py | ||
| kanban_watchers.py | ||
| lifecycle_ledger.py | ||
| memory_monitor.py | ||
| message_timestamps.py | ||
| mirror.py | ||
| pairing.py | ||
| platform_registry.py | ||
| profile_routing.py | ||
| readiness.py | ||
| response_filters.py | ||
| restart.py | ||
| restart_loop_guard.py | ||
| rich_sent_store.py | ||
| run.py | ||
| runtime_footer.py | ||
| scale_to_zero.py | ||
| session.py | ||
| session_context.py | ||
| session_stall.py | ||
| session_state.py | ||
| shutdown_flush.py | ||
| shutdown_forensics.py | ||
| shutdown_watchdog.py | ||
| slash_access.py | ||
| slash_commands.py | ||
| status.py | ||
| status_phrases.py | ||
| sticker_cache.py | ||
| stream_consumer.py | ||
| stream_dispatch.py | ||
| stream_events.py | ||
| streaming_tts_consumer.py | ||
| systemd_notify.py | ||
| turn_context.py | ||
| turn_lease.py | ||
| wake.py | ||
| whatsapp_identity.py | ||