feat: classifier-based addressee detection (T74.1)
Replace the substring _detect_addressee_id helper with a classifier call for the multi-entity case. The substring helper is kept as a fast-path for the no-guest case (no LLM round-trip needed when only one bot is present, preserves throughput). - New service chat/services/addressee.py wrapping the existing classifier wrapper. AddresseeDecision carries addressee_id + confidence + reason; classifier failure falls back to the host with reason="fallback" (graceful-degradation, matches the relationship_seed / interjection pattern). - chat/web/turns.py post_turn now calls detect_addressee in the multi-entity branch; 1:1 keeps the substring path. - tests/test_addressee.py: 3 new tests (guest pick, host pick, classifier-failure fallback). - tests/test_turn_flow.py: existing multi-entity tests now feed a canned addressee response in the queue. The addressee-routing test is updated to assert classifier-driven routing rather than substring.
This commit is contained in:
@@ -0,0 +1,99 @@
|
||||
"""Addressee classifier service tests (T74.1).
|
||||
|
||||
Covers :func:`chat.services.addressee.detect_addressee`:
|
||||
|
||||
- Classifier picks the guest -> ``addressee_id == guest_id``.
|
||||
- Classifier picks the host -> ``addressee_id == host_id``.
|
||||
- Classifier flakes (3 bad-JSON responses, exhausting the built-in
|
||||
retry budget in :func:`chat.llm.classify.classify`) -> fallback to
|
||||
the host with ``reason="fallback"``.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
|
||||
import pytest
|
||||
|
||||
from chat.llm.mock import MockLLMClient
|
||||
from chat.services.addressee import AddresseeDecision, detect_addressee
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_classifier_picks_guest():
|
||||
"""Classifier returns the guest id verbatim — caller propagates it."""
|
||||
canned = [
|
||||
json.dumps(
|
||||
{
|
||||
"addressee_id": "bot_b",
|
||||
"confidence": "high",
|
||||
"reason": "user named BotB",
|
||||
}
|
||||
)
|
||||
]
|
||||
client = MockLLMClient(canned=canned)
|
||||
|
||||
result = await detect_addressee(
|
||||
client,
|
||||
classifier_model="test-model",
|
||||
user_prose="BotB, what do you think?",
|
||||
host_id="bot_a",
|
||||
host_name="BotA",
|
||||
guest_id="bot_b",
|
||||
guest_name="BotB",
|
||||
)
|
||||
|
||||
assert isinstance(result, AddresseeDecision)
|
||||
assert result.addressee_id == "bot_b"
|
||||
assert result.confidence == "high"
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_classifier_picks_host():
|
||||
"""Classifier returns the host id — caller propagates it."""
|
||||
canned = [
|
||||
json.dumps(
|
||||
{
|
||||
"addressee_id": "bot_a",
|
||||
"confidence": "medium",
|
||||
"reason": "narration aimed at host",
|
||||
}
|
||||
)
|
||||
]
|
||||
client = MockLLMClient(canned=canned)
|
||||
|
||||
result = await detect_addressee(
|
||||
client,
|
||||
classifier_model="test-model",
|
||||
user_prose="I lean back and stretch.",
|
||||
host_id="bot_a",
|
||||
host_name="BotA",
|
||||
guest_id="bot_b",
|
||||
guest_name="BotB",
|
||||
)
|
||||
|
||||
assert result.addressee_id == "bot_a"
|
||||
assert result.confidence == "medium"
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_classifier_failure_falls_back_to_host():
|
||||
"""Three bad-JSON responses exhaust the retry budget and the
|
||||
classifier-failure fallback returns ``host_id`` with
|
||||
``reason="fallback"``."""
|
||||
canned = ["not json", "still not json", "garbage"]
|
||||
client = MockLLMClient(canned=canned)
|
||||
|
||||
result = await detect_addressee(
|
||||
client,
|
||||
classifier_model="test-model",
|
||||
user_prose="anything",
|
||||
host_id="bot_a",
|
||||
host_name="BotA",
|
||||
guest_id="bot_b",
|
||||
guest_name="BotB",
|
||||
)
|
||||
|
||||
assert result.addressee_id == "bot_a"
|
||||
assert result.reason == "fallback"
|
||||
assert result.confidence == "low"
|
||||
Reference in New Issue
Block a user