hermes-agent/tests/hermes_cli/test_plugins_transcription_registration.py
kshitijk4poor 2cd952e110 feat(stt): add register_transcription_provider() plugin hook
Add an opt-in Python plugin surface for speech-to-text backends,
mirroring the TTS hook pattern. New backends (OpenRouter, SenseAudio,
Gemini-STT, custom proprietary engines) can be implemented as plugins
without modifying tools/transcription_tools.py.

Built-ins always win
--------------------
The 6 built-in STT providers (local/faster-whisper, local_command,
groq, openai, mistral, xai) keep their native handlers. Plugins
attempting to register under a built-in name are rejected at
registration time with a warning and re-checked defensively at
dispatch.

Resolution order
----------------
1. stt.provider matches a built-in → built-in dispatch (unchanged)
2. stt.provider matches a registered plugin →
   a. if plugin.is_available() returns False → unavailability envelope
      identifying the plugin (not the generic "No STT provider"
      message — the user explicitly opted into this plugin)
   b. otherwise plugin.transcribe() with model + language forwarded
      from stt.<provider>.{model,language} config
3. No match → legacy "No STT provider available" error (unchanged)

Per-provider config namespace
-----------------------------
Plugins read their config from stt.<provider> in config.yaml, mirroring
how built-ins read stt.openai.model / stt.mistral.model. The dispatcher
forwards `model` and `language` from this section. Caller's explicit
`model=` argument overrides the config-set model.

Files
-----
- agent/transcription_provider.py: TranscriptionProvider ABC
- agent/transcription_registry.py: register/get/list providers,
  built-in shadow guard, _reset_for_tests
- hermes_cli/plugins.py: register_transcription_provider() on
  PluginContext
- tools/transcription_tools.py: BUILTIN_STT_PROVIDERS frozenset,
  _dispatch_to_plugin_provider() with availability gate, wire-in
  after xai branch and before "No STT provider" error
- tests/agent/test_transcription_registry.py: 27 tests
- tests/hermes_cli/test_plugins_transcription_registration.py: 3 tests
- tests/tools/test_transcription_plugin_dispatch.py: 28 tests
  (covering built-in short-circuit, plugin dispatch, exception
  envelope, non-dict guard, availability gate, language forwarding)
- tests/plugins/transcription/check_parity_vs_main.py: 10-scenario
  subprocess-pinned parity harness vs origin/main
- website/docs/user-guide/features/{tts,plugins}.md: docs

Behavior parity
---------------
10 scenarios, 8 OK + 2 expected DIFFs:
  no_provider_error → plugin (plugin-installed scenario)
  no_provider_error → plugin_unavailable (plugin-installed-unavailable
  scenario; PR returns cleaner envelope)
Zero behavior change for users not opting into a plugin.

Issue follow-up to #30398.
2026-05-25 01:41:19 -07:00

148 lines
5.1 KiB
Python

"""Tests for PluginContext.register_transcription_provider().
Exercises the plugin context hook end-to-end: drops a fake plugin into
``$HERMES_HOME/plugins/``, runs ``PluginManager().discover_and_load()``,
and asserts the registration result.
Mirrors the shape of ``test_plugins_tts_registration.py`` (companion
TTS hook from issue #30398).
"""
from __future__ import annotations
import os
from pathlib import Path
from typing import Any, Dict
import yaml
def _write_plugin(
root: Path,
name: str,
*,
manifest_extra: Dict[str, Any] | None = None,
register_body: str = "pass",
) -> Path:
plugin_dir = root / name
plugin_dir.mkdir(parents=True, exist_ok=True)
manifest = {
"name": name,
"version": "0.1.0",
"description": f"Test plugin {name}",
}
if manifest_extra:
manifest.update(manifest_extra)
(plugin_dir / "plugin.yaml").write_text(yaml.dump(manifest))
(plugin_dir / "__init__.py").write_text(
f"def register(ctx):\n {register_body}\n"
)
return plugin_dir
def _enable(hermes_home: Path, name: str) -> None:
cfg_path = hermes_home / "config.yaml"
cfg: dict = {}
if cfg_path.exists():
try:
cfg = yaml.safe_load(cfg_path.read_text()) or {}
except Exception:
cfg = {}
plugins_cfg = cfg.setdefault("plugins", {})
enabled = plugins_cfg.setdefault("enabled", [])
if isinstance(enabled, list) and name not in enabled:
enabled.append(name)
cfg_path.write_text(yaml.safe_dump(cfg))
class TestRegisterTranscriptionProvider:
def test_accepts_valid_provider(self):
from hermes_cli.plugins import PluginManager
from agent import transcription_registry
transcription_registry._reset_for_tests()
hermes_home = Path(os.environ["HERMES_HOME"])
_write_plugin(
hermes_home / "plugins",
"my-stt-plugin",
register_body=(
"from agent.transcription_provider import TranscriptionProvider\n"
" class P(TranscriptionProvider):\n"
" @property\n"
" def name(self): return 'fake-stt'\n"
" def transcribe(self, file_path, **kw):\n"
" return {'success': True, 'transcript': 'hi', 'provider': 'fake-stt'}\n"
" ctx.register_transcription_provider(P())"
),
)
_enable(hermes_home, "my-stt-plugin")
mgr = PluginManager()
mgr.discover_and_load()
assert mgr._plugins["my-stt-plugin"].enabled is True, (
f"Plugin failed to load: {mgr._plugins['my-stt-plugin'].error}"
)
assert transcription_registry.get_provider("fake-stt") is not None
transcription_registry._reset_for_tests()
def test_rejects_non_provider(self, caplog):
from hermes_cli.plugins import PluginManager
from agent import transcription_registry
transcription_registry._reset_for_tests()
hermes_home = Path(os.environ["HERMES_HOME"])
_write_plugin(
hermes_home / "plugins",
"bad-stt-plugin",
register_body="ctx.register_transcription_provider('not a provider')",
)
_enable(hermes_home, "bad-stt-plugin")
with caplog.at_level("WARNING"):
mgr = PluginManager()
mgr.discover_and_load()
assert mgr._plugins["bad-stt-plugin"].enabled is True
assert transcription_registry.get_provider("not a provider") is None
assert transcription_registry.list_providers() == []
assert "does not inherit from TranscriptionProvider" in caplog.text
transcription_registry._reset_for_tests()
def test_rejects_builtin_shadow(self, caplog):
from hermes_cli.plugins import PluginManager
from agent import transcription_registry
transcription_registry._reset_for_tests()
hermes_home = Path(os.environ["HERMES_HOME"])
_write_plugin(
hermes_home / "plugins",
"shadow-stt-plugin",
register_body=(
"from agent.transcription_provider import TranscriptionProvider\n"
" class P(TranscriptionProvider):\n"
" @property\n"
" def name(self): return 'openai'\n"
" def transcribe(self, file_path, **kw):\n"
" return {'success': True, 'transcript': 'hi'}\n"
" ctx.register_transcription_provider(P())"
),
)
_enable(hermes_home, "shadow-stt-plugin")
with caplog.at_level("WARNING"):
mgr = PluginManager()
mgr.discover_and_load()
# Plugin still loaded normally — built-in shadowing is a warning,
# not an exception. The registry rejects the entry though.
assert mgr._plugins["shadow-stt-plugin"].enabled is True
assert transcription_registry.get_provider("openai") is None
assert "shadows a built-in name" in caplog.text
transcription_registry._reset_for_tests()