Two per-call WARNING surfaces were still outside the warn-once reporter:
- agent/plugin_stream_hooks.py::_worker — the on_stream_start/on_stream_delta/
on_stream_end consumer, which fires once per streaming delta (far more often than
per tool call). A mis-declared callback (signature naming tool_data) logged
"Hook ... raised" at WARNING on every delta: 20 deltas -> 20 WARNING lines.
- hermes_cli/plugins_dispatch.py::_deliver_event — plugin event subscribers that
raise identically were warned on every emit.
Both now go through PluginManager._report_hook_failure (keyed by module/qualname,
cleared on unload): the first failure warns and names the fields the hook/event
provides, identical repeats are DEBUG. Skip-and-continue semantics are unchanged.
Part of #111922
PluginLlm's four public entry points share _gate/_finish/_host_kwargs; drop
dead classify_failure_scope/_REASON_SCOPES (and their tests) and unify the
three _norm_* helpers; should_skip_candidate routes through a scope predicate
table. Injected caller kwargs, audit dicts and log lines unchanged.
Salvage of PR #64317 (@deaneeth) onto current main, implementing #64161:
observer-only on_stream_start / on_stream_delta / on_stream_end /
on_interim_message plugin hooks dispatched through a host-owned bounded
queue (one worker per callback) so plugin callbacks never run inline on
the token path. Reasoning deltas are opt-in via
plugins.stream_reasoning_deltas.
