feat(l1): match_or_build orchestrator + classify (match-first, gate-on-build)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

backend/app/services/match_or_build.py

@@ -0,0 +1,78 @@
+"""Intake orchestrator: match published flows first, gate generic build behind
+the account's enabled categories (spec §3). Match runs BEFORE the category gate
+so an authored flow is never blocked by category settings (Finding 4)."""
+import logging
+import re
+from typing import Any, Optional
+from uuid import UUID
+
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.core.ai_provider import get_ai_provider
+from app.core.config import settings
+from app.services import flow_matching_engine
+from app.services.l1_category_service import (
+    DEFAULT_L1_CATEGORIES, get_enabled_categories, is_category_enabled,
+)
+from app.services.llm_utils import parse_llm_json
+
+logger = logging.getLogger(__name__)
+
+MATCH_THRESHOLD = 0.75   # spec §5.3
+SUGGEST_THRESHOLD = 0.60  # spec §5.3
+
+_CLASSIFY_PROMPT = (
+    "Classify the IT support problem into exactly one of these category keys, "
+    "or 'unknown'. Return JSON {\"category\":\"<key>\"} only.\nKEYS: "
+    + ", ".join(DEFAULT_L1_CATEGORIES)
+)
+
+
+async def classify(problem_text: str) -> str:
+    """Map a problem to a category key via a short model call; keyword fallback."""
+    try:
+        provider = get_ai_provider(settings.get_model_for_action("l1_classify"))
+        raw, _, _ = await provider.generate_json(
+            system_prompt=_CLASSIFY_PROMPT,
+            messages=[{"role": "user", "content": problem_text}],
+            max_tokens=64,
+        )
+        cat = parse_llm_json(raw).get("category", "unknown")
+        return cat if cat in DEFAULT_L1_CATEGORIES else "unknown"
+    except Exception as e:  # noqa: BLE001 — fall back, never hard-fail intake
+        logger.warning("classify model call failed (%s); keyword fallback", e)
+        text = problem_text.lower()
+        for cat in DEFAULT_L1_CATEGORIES:
+            if any(re.search(rf"\b{re.escape(tok)}\b", text) for tok in cat.split("_")):
+                return cat
+        return "unknown"
+
+
+async def match_or_build(
+    account_id: UUID,
+    problem_text: str,
+    problem_domain: Optional[str],
+    ticket_ref: str,  # passed through for caller/session use; not consumed here (Task 10)
+    *,
+    db: AsyncSession,
+    force_build: bool = False,
+) -> dict[str, Any]:
+    if not force_build:
+        hits = await flow_matching_engine.find_matches(
+            problem_text, problem_domain, account_id, db)
+        best = max(hits, key=lambda h: h["score"], default=None) if hits else None
+        # find_matches returns tree_id as a UUID object; normalize the public
+        # contract to str so callers can re-parse with UUID(...) without TypeError.
+        if best and best["score"] >= MATCH_THRESHOLD:
+            return {"outcome": "matched", "flow_id": str(best["tree_id"]), "session_kind": "flow"}
+        if best and best["score"] >= SUGGEST_THRESHOLD:
+            return {"outcome": "suggest",
+                    "near_miss": {"flow_id": str(best["tree_id"]), "flow_name": best["tree_name"],
+                                  "score": best["score"]},
+                    "can_build": True}
+
+    category = await classify(problem_text)
+    enabled = await get_enabled_categories(account_id, db)
+    if not is_category_enabled(category, enabled):
+        return {"outcome": "out_of_scope", "category": category}
+    return {"outcome": "build", "session_kind": "ai_build", "category": category}

backend/tests/test_match_or_build.py

@@ -0,0 +1,98 @@
+import uuid
+import pytest
+from unittest.mock import AsyncMock, patch
+from app.services import match_or_build as mob
+
+
+@pytest.mark.asyncio
+async def test_match_wins_before_category_gate():
+    """A strong published-flow match returns 'matched' even if category disabled."""
+    with patch.object(mob.flow_matching_engine, "find_matches", new=AsyncMock(
+            return_value=[{"tree_id": str(uuid.uuid4()), "tree_name": "VPN", "score": 0.9}])), \
+         patch.object(mob, "get_enabled_categories", new=AsyncMock(return_value=[])):
+        res = await mob.match_or_build(uuid.uuid4(), "vpn down", None, "t1", db=AsyncMock(), force_build=False)
+    assert res["outcome"] == "matched"
+    assert res["session_kind"] == "flow"
+
+
+@pytest.mark.asyncio
+async def test_suggest_band():
+    with patch.object(mob.flow_matching_engine, "find_matches", new=AsyncMock(
+            return_value=[{"tree_id": str(uuid.uuid4()), "tree_name": "X", "score": 0.66}])):
+        res = await mob.match_or_build(uuid.uuid4(), "p", None, "t1", db=AsyncMock(), force_build=False)
+    assert res["outcome"] == "suggest"
+    assert res["near_miss"]["flow_name"] == "X"
+    assert "flow_id" in res["near_miss"] and isinstance(res["near_miss"]["flow_id"], str)
+    assert res["near_miss"]["score"] == 0.66
+    assert res["can_build"] is True
+
+
+@pytest.mark.asyncio
+async def test_out_of_scope_when_category_disabled_on_build_path():
+    with patch.object(mob.flow_matching_engine, "find_matches", new=AsyncMock(return_value=[])), \
+         patch.object(mob, "classify", new=AsyncMock(return_value="printer")), \
+         patch.object(mob, "get_enabled_categories", new=AsyncMock(return_value=["vpn_connect"])):
+        res = await mob.match_or_build(uuid.uuid4(), "printer jam", None, "t1", db=AsyncMock(), force_build=False)
+    assert res["outcome"] == "out_of_scope"
+
+
+@pytest.mark.asyncio
+async def test_build_when_enabled_and_no_match():
+    with patch.object(mob.flow_matching_engine, "find_matches", new=AsyncMock(return_value=[])), \
+         patch.object(mob, "classify", new=AsyncMock(return_value="printer")), \
+         patch.object(mob, "get_enabled_categories", new=AsyncMock(return_value=["printer"])):
+        res = await mob.match_or_build(uuid.uuid4(), "printer jam", None, "t1", db=AsyncMock(), force_build=False)
+    assert res["outcome"] == "build"
+    assert res["session_kind"] == "ai_build"
+
+
+@pytest.mark.asyncio
+async def test_force_build_skips_match_but_still_gates():
+    fm = AsyncMock(return_value=[{"tree_id": str(uuid.uuid4()), "tree_name": "X", "score": 0.99}])
+    with patch.object(mob.flow_matching_engine, "find_matches", new=fm), \
+         patch.object(mob, "classify", new=AsyncMock(return_value="printer")), \
+         patch.object(mob, "get_enabled_categories", new=AsyncMock(return_value=["printer"])):
+        res = await mob.match_or_build(uuid.uuid4(), "p", None, "t1", db=AsyncMock(), force_build=True)
+    fm.assert_not_called()
+    assert res["outcome"] == "build"
+
+
+@pytest.mark.asyncio
+async def test_score_exactly_match_threshold_is_matched():
+    with patch.object(mob.flow_matching_engine, "find_matches", new=AsyncMock(
+            return_value=[{"tree_id": str(uuid.uuid4()), "tree_name": "X", "score": 0.75}])):
+        res = await mob.match_or_build(uuid.uuid4(), "p", None, "t1", db=AsyncMock(), force_build=False)
+    assert res["outcome"] == "matched"
+
+
+@pytest.mark.asyncio
+async def test_score_exactly_suggest_threshold_is_suggest():
+    with patch.object(mob.flow_matching_engine, "find_matches", new=AsyncMock(
+            return_value=[{"tree_id": str(uuid.uuid4()), "tree_name": "X", "score": 0.60}])):
+        res = await mob.match_or_build(uuid.uuid4(), "p", None, "t1", db=AsyncMock(), force_build=False)
+    assert res["outcome"] == "suggest"
+
+
+@pytest.mark.asyncio
+async def test_score_below_suggest_falls_through_to_build_path():
+    with patch.object(mob.flow_matching_engine, "find_matches", new=AsyncMock(
+            return_value=[{"tree_id": str(uuid.uuid4()), "tree_name": "X", "score": 0.4}])), \
+         patch.object(mob, "classify", new=AsyncMock(return_value="printer")), \
+         patch.object(mob, "get_enabled_categories", new=AsyncMock(return_value=["printer"])):
+        res = await mob.match_or_build(uuid.uuid4(), "printer", None, "t1", db=AsyncMock(), force_build=False)
+    assert res["outcome"] == "build"
+
+
+@pytest.mark.asyncio
+async def test_classify_keyword_fallback_matches_word():
+    with patch.object(mob, "get_ai_provider", side_effect=RuntimeError("model down")):
+        cat = await mob.classify("the printer is jammed")
+    assert cat == "printer"
+
+
+@pytest.mark.asyncio
+async def test_classify_keyword_fallback_no_substring_false_match():
+    # "have" must NOT match teams_zoom_av via the 'av' token; no real category word present
+    with patch.object(mob, "get_ai_provider", side_effect=RuntimeError("model down")):
+        cat = await mob.classify("i have a general question")
+    assert cat == "unknown"