Praxis CI
47e24dbe59
server/services/base.py defines three abstract base classes with type annotations: TTSProvider (async synthesize/synthesize_all, voice_id), LLMProvider (async chat/chat_full, roleplay_model, debrief_model), Guardrail (async check, session_start_disclaimer). GuardrailVerdict/Context/TTSResult/LLMStreamChunk dataclasses carry typed metadata. server/services/registry.py resolves the active adapter from env (PRAXIS_TTS, PRAXIS_GUARDRAIL) so the pipeline never imports a concrete adapter directly — D-014/D-019/D-020 swap wiring. Verified: 'from server.services import TTSProvider, LLMProvider, Guardrail' succeeds. ---ci--- phase: 1 milestone: v0.1 plan: 02 task: 02-01 status: execute persona: backend-engineer requirements: covered: [REQ-VOICE-02, REQ-LLM-01, REQ-ORCH-02] ---/ci---
74 lines
2.5 KiB
Python
74 lines
2.5 KiB
Python
"""Adapter registry — resolves the active TTS / LLM / Guardrail from env.
|
|
|
|
Centralizes the D-014 (TTS swap), D-020 (LLM swap), D-019 (guardrail plug) wiring
|
|
so the Pipecat pipeline never imports a concrete adapter directly.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
from functools import lru_cache
|
|
|
|
|
|
def _require(key: str, *, default: str | None = None) -> str:
|
|
val = os.environ.get(key, default or "").strip()
|
|
if not val:
|
|
raise RuntimeError(
|
|
f"Required env var {key} is not set. See .env.example."
|
|
)
|
|
return val
|
|
|
|
|
|
@lru_cache(maxsize=1)
|
|
def get_tts() -> "TTSProvider": # type: ignore[name-defined]
|
|
"""Return the active TTSProvider based on PRAXIS_TTS (D-014)."""
|
|
# Imported lazily so importing the registry doesn't drag in Pipecat/TTS deps
|
|
# for tools that only need the interfaces.
|
|
choice = os.environ.get("PRAXIS_TTS", "cartesia").strip().lower()
|
|
if choice == "piper":
|
|
from server.tts.piper_tts import PiperTTS
|
|
|
|
return PiperTTS()
|
|
if choice == "cartesia":
|
|
from server.tts.cartesia_tts import CartesiaTTS
|
|
|
|
return CartesiaTTS()
|
|
raise RuntimeError(
|
|
f"Unknown PRAXIS_TTS={choice!r}; expected 'cartesia' or 'piper'."
|
|
)
|
|
|
|
|
|
@lru_cache(maxsize=1)
|
|
def get_llm() -> "LLMProvider": # type: ignore[name-defined]
|
|
"""Return the active LLMProvider (Ollama Cloud direct API, D-020)."""
|
|
from server.llm.ollama_cloud import OllamaCloudLLM
|
|
|
|
return OllamaCloudLLM()
|
|
|
|
|
|
@lru_cache(maxsize=1)
|
|
def get_guardrail() -> "Guardrail": # type: ignore[name-defined]
|
|
"""Return the active Guardrail (D-019).
|
|
|
|
v0.1 SLICE-02 returns NoOpGuardrail; SLICE-03 swaps in CustomerServiceGuardrail.
|
|
Selection via PRAXIS_GUARDRAIL=none|customer_service (default: customer_service
|
|
once implemented; falls back to none if the ruleset isn't importable yet).
|
|
"""
|
|
choice = os.environ.get("PRAXIS_GUARDRAIL", "customer_service").strip().lower()
|
|
if choice == "none":
|
|
from server.guardrails.noop import NoOpGuardrail
|
|
|
|
return NoOpGuardrail()
|
|
if choice == "customer_service":
|
|
try:
|
|
from server.guardrails.customer_service import CustomerServiceGuardrail
|
|
|
|
return CustomerServiceGuardrail()
|
|
except ImportError:
|
|
# SLICE-02 fallback — real ruleset arrives in SLICE-03.
|
|
from server.guardrails.noop import NoOpGuardrail
|
|
|
|
return NoOpGuardrail()
|
|
raise RuntimeError(
|
|
f"Unknown PRAXIS_GUARDRAIL={choice!r}; expected 'none' or 'customer_service'."
|
|
) |