praxis/tests/test_debrief.py

"""Tests for debrief generation + guardrail filter (TASK-05-01, TASK-05-02, TASK-05-03)."""

from __future__ import annotations

import asyncio
from typing import Any

import pytest

from server.debrief import generate_debrief
from server.guardrails.customer_service import CustomerServiceGuardrail
from server.scenarios.loader import load
from server.services.base import GuardrailContext


class _FakeLLM:
    """A fake LLMProvider that returns a canned debrief (no real API call)."""

    debrief_model = "deepseek-v4-flash:cloud"
    roleplay_model = "gemma4:cloud"

    def __init__(self, response: str) -> None:
        self._response = response

    async def chat_full(self, messages, *, model=None, no_think=False):
        return self._response, {"output_tokens": 50, "model": model or self.debrief_model}


def _load_scenario():
    return load("customer_service_refund_ca_v01")


def test_debrief_references_learner_turns_and_branch():
    """TASK-05-01: a scripted escalate session produces a debrief referencing the
    learner's turns + the escalates_unresolved focus."""
    scenario = _load_scenario()
    turns = [
        {"role": "user", "asr_text": "Our policy says no refunds after 30 days."},
        {"role": "assistant", "tts_text": "But I just want my money back!"},
        {"role": "user", "asr_text": "I can't help you, that's the policy."},
    ]
    llm = _FakeLLM(
        "- What you did well: you stayed calm.\n"
        "- What to improve: you led with policy before acknowledging the customer's "
        "frustration — they escalated because they felt unheard.\n"
        "- Next step: acknowledge emotion first, then explain policy."
    )

    async def _run():
        return await generate_debrief(
            llm, scenario,
            branch_id="escalate", outcome="failure",
            debrief_focus=scenario.branch_by_id("escalate").debrief_focus,
            learner_turns=turns,
        )

    text, usage = asyncio.run(_run())
    assert "policy" in text.lower() or "frustration" in text.lower()
    assert usage["model"] == "deepseek-v4-flash:cloud"


def test_debrief_uses_no_think_mode():
    """REQ-LLM-02: the debrief uses deepseek-v4-flash:cloud no_think (D-020)."""
    scenario = _load_scenario()
    llm = _FakeLLM("debrief text")

    captured: dict[str, Any] = {}

    async def _chat_full(messages, *, model=None, no_think=False):
        captured["model"] = model
        captured["no_think"] = no_think
        return "debrief", {"output_tokens": 1}

    llm.chat_full = _chat_full  # type: ignore

    async def _run():
        return await generate_debrief(
            llm, scenario, "accept_resolution", "success",
            "focus", [{"role": "user", "asr_text": "hi"}],
        )

    asyncio.run(_run())
    assert captured["model"] == "deepseek-v4-flash:cloud"
    assert captured["no_think"] is True


def test_debrief_guardrail_blocks_legal_action():
    """TASK-05-02: a debrief containing 'tell the customer to sue' is filtered."""
    scenario = _load_scenario()
    guardrail = CustomerServiceGuardrail()
    llm = _FakeLLM(
        "- What you did well: nothing.\n"
        "- What to improve: you should tell the customer to sue them.\n"
        "- Next step: recommend legal action."
    )

    async def _run():
        return await generate_debrief(
            llm, scenario, "escalate", "failure", "focus",
            [{"role": "user", "asr_text": "policy"}],
            guardrail=guardrail,
        )

    text, _ = asyncio.run(_run())
    # The guardrail filtered_text replaces the legal-action recommendation.
    assert "Focus your coaching" in text or "legal action" not in text.lower() or "learner" in text.lower()


def test_debrief_normal_coaching_passes_guardrail():
    """TASK-05-02: a normal coaching debrief passes the guardrail filter."""
    scenario = _load_scenario()
    guardrail = CustomerServiceGuardrail()
    normal_debrief = (
        "- What you did well: you acknowledged the customer's frustration.\n"
        "- What to improve: offer a concrete resolution sooner.\n"
        "- Next step: practice the empathy-first opening."
    )
    llm = _FakeLLM(normal_debrief)

    async def _run():
        return await generate_debrief(
            llm, scenario, "accept_resolution", "success", "focus",
            [{"role": "user", "asr_text": "I'm sorry, I can offer a refund."}],
            guardrail=guardrail,
        )

    text, _ = asyncio.run(_run())
    assert text == normal_debrief  # unchanged — guardrail allowed it


def test_debrief_voice_via_ttsprovider():
    """TASK-05-03: the debrief is synthesized via the TTSProvider interface (D-006).

    This is a structural test: the debrief text is passed to TTSProvider.synthesize,
    reusing the same voice as the role-play (no separate TTS path).
    """
    from server.services.base import TTSProvider, TTSResult

    class _FakeTTS(TTSProvider):
        name = "fake"
        synthesized: list[str] = []

        @property
        def voice_id(self) -> str:
            return "fake-voice"

        async def synthesize(self, text):
            self.synthesized.append(text)
            yield b"\x00\x00"

        async def synthesize_all(self, text):
            self.synthesized.append(text)
            return b"\x00\x00", TTSResult(chars=len(text), voice_id=self.voice_id)

    tts = _FakeTTS()
    debrief_text = "You did well. Improve your empathy. Next: practice."

    async def _run():
        return await tts.synthesize_all(debrief_text)

    audio, result = asyncio.run(_run())
    assert tts.synthesized == [debrief_text]  # same TTS path as role-play
    assert result.voice_id == "fake-voice"  # D-006: one voice
    assert len(audio) > 0