Merge pull request 'perf(citation-view): cache מבוסס-טביעה — 24.6 שנ׳ לטעינה חוזרת → 0.01 שנ׳' (#464) from worktree-citation-view-cache into main

mcp-server/src/legal_mcp/services/case_citation_verification.py

@@ -20,6 +20,7 @@ from __future__ import annotations
 
 import asyncio
 import logging
+import time
 from uuid import UUID
 
 from legal_mcp.services import (
@@ -74,7 +75,92 @@ def _passes_floor(hit: dict) -> bool:
 _RETRIEVAL_BUDGET_S = 22.0
 
 
-async def build_view(case_number: str) -> dict:
+#: Cached views, keyed by case number → (fingerprint, expires_at|None, view).
+#: Assembling a view costs 20+ seconds of Voyage embeds and vector searches, and
+#: the result changes only when its inputs do. Keyed by a FINGERPRINT of those
+#: inputs rather than a guessed TTL: a chair who verifies a precedent must see it
+#: reflected on the next load, not after a timer expires.
+_view_cache: dict[str, tuple[str, float | None, dict]] = {}
+
+#: One lock per case so two concurrent loads of the same page don't both compute.
+#: Reload-during-a-slow-load is how the original outage compounded into Postgres
+#: deadlocks; the second reader now waits for the first and gets its result.
+_view_locks: dict[str, asyncio.Lock] = {}
+
+#: A partial view (retrieval budget exhausted) is still worth caching — otherwise
+#: every reload re-pays 22 seconds — but only briefly, so the missing suggestions
+#: get another chance while the corpus is quieter.
+_PARTIAL_TTL_S = 90.0
+
+
+async def _inputs_fingerprint(case_id: UUID) -> str:
+    """Cheap signature of everything the view is derived from.
+
+    Changes when: arguments are re-aggregated, the chair attaches or verifies a
+    precedent, or the corpus grows (new rulings change the suggestions). One
+    round-trip — the point is to be far cheaper than the 20s it guards.
+    """
+    pool = await db.get_pool()
+    async with pool.acquire() as conn:
+        row = await conn.fetchrow(
+            """
+            SELECT
+              (SELECT count(*)::text || ':' || coalesce(max(updated_at)::text, '-')
+                 FROM legal_arguments WHERE case_id = $1)               AS args,
+              (SELECT count(*)::text || ':' || coalesce(max(updated_at)::text, '-')
+                 FROM case_precedents WHERE case_id = $1)               AS attached,
+              (SELECT count(*)::text || ':' || coalesce(max(created_at)::text, '-')
+                 FROM case_law WHERE searchable = true)                 AS corpus
+            """,
+            case_id,
+        )
+    return f"{row['args']}|{row['attached']}|{row['corpus']}"
+
+
+def invalidate(case_number: str = "") -> None:
+    """Drop cached views — one case, or all when called with no argument.
+
+    Callers that mutate the inputs may use this for immediacy, but correctness
+    does not depend on it: the fingerprint check catches any change on the next
+    read regardless of whether anyone remembered to invalidate (G1 — the guard
+    lives at the source of truth, not in every writer's memory).
+    """
+    if case_number:
+        _view_cache.pop(case_number, None)
+    else:
+        _view_cache.clear()
+
+
+async def build_view(case_number: str, *, use_cache: bool = True) -> dict:
+    """Assemble the citation-verification view, served from cache when unchanged."""
+    if not use_cache:
+        return await _build_view_uncached(case_number)
+
+    lock = _view_locks.setdefault(case_number, asyncio.Lock())
+    async with lock:
+        case = await db.get_case_by_number(case_number)
+        if not case:
+            return {"status": "case_not_found", "case_number": case_number,
+                    "arguments": []}
+        cid = case["id"]
+        fp = await _inputs_fingerprint(UUID(cid) if isinstance(cid, str) else cid)
+
+        hit = _view_cache.get(case_number)
+        if hit is not None:
+            cached_fp, expires_at, view = hit
+            fresh = cached_fp == fp and (expires_at is None or time.monotonic() < expires_at)
+            if fresh:
+                return {**view, "cached": True}
+
+        view = await _build_view_uncached(case_number)
+        if view.get("status") == "ok":
+            expires_at = (None if view.get("retrieval_complete", True)
+                          else time.monotonic() + _PARTIAL_TTL_S)
+            _view_cache[case_number] = (fp, expires_at, view)
+        return {**view, "cached": False}
+
+
+async def _build_view_uncached(case_number: str) -> dict:
     case = await db.get_case_by_number(case_number)
     if not case:
         return {"status": "case_not_found", "case_number": case_number, "arguments": []}

mcp-server/tests/test_citation_view_cache.py

@@ -0,0 +1,125 @@
+"""The citation view is cached by input fingerprint, not by a guessed TTL.
+
+Assembling it costs 20+ seconds of Voyage embeds and vector searches. A TTL
+would force a choice between staleness and cost: a chair who verifies a
+precedent must see it on the very next load, and a timer cannot promise that.
+Keying on a fingerprint of the inputs (arguments · attachments · corpus) makes
+freshness a property of the data rather than of the clock.
+"""
+
+import asyncio
+
+import pytest
+
+from legal_mcp.services import case_citation_verification as ccv
+
+
+@pytest.fixture(autouse=True)
+def _clean_cache():
+    ccv.invalidate()
+    yield
+    ccv.invalidate()
+
+
+def _stub(monkeypatch, fingerprint: str, calls: list, *, complete: bool = True):
+    """Point build_view at a fake case, a controllable fingerprint, and a
+    counted assembler, so these tests never touch the corpus."""
+    async def fake_case(_cn):
+        return {"id": "00000000-0000-0000-0000-000000000001"}
+
+    async def fake_fp(_cid):
+        return fingerprint
+
+    async def fake_build(cn):
+        calls.append(cn)
+        return {"status": "ok", "case_number": cn, "arguments": [],
+                "retrieval_complete": complete, "summary": {}}
+
+    monkeypatch.setattr(ccv.db, "get_case_by_number", fake_case)
+    monkeypatch.setattr(ccv, "_inputs_fingerprint", fake_fp)
+    monkeypatch.setattr(ccv, "_build_view_uncached", fake_build)
+
+
+@pytest.mark.asyncio
+async def test_second_load_is_served_from_cache(monkeypatch):
+    calls: list = []
+    _stub(monkeypatch, "fp-1", calls)
+    first = await ccv.build_view("1069-04-26")
+    second = await ccv.build_view("1069-04-26")
+    assert first["cached"] is False
+    assert second["cached"] is True
+    assert len(calls) == 1, "the expensive assembly must run once"
+
+
+@pytest.mark.asyncio
+async def test_changed_inputs_invalidate_without_anyone_calling_invalidate(monkeypatch):
+    """The chair verifies a precedent → fingerprint moves → next load rebuilds.
+    Correctness must not depend on a writer remembering to clear the cache."""
+    calls: list = []
+    _stub(monkeypatch, "fp-before", calls)
+    await ccv.build_view("1069-04-26")
+
+    _stub(monkeypatch, "fp-after", calls)  # e.g. a new case_precedents row
+    again = await ccv.build_view("1069-04-26")
+    assert again["cached"] is False
+    assert len(calls) == 2
+
+
+@pytest.mark.asyncio
+async def test_concurrent_loads_do_not_stampede(monkeypatch):
+    """Reload-during-a-slow-load is how the original outage compounded into
+    Postgres deadlocks. The later readers must wait, not pile on."""
+    calls: list = []
+
+    async def fake_case(_cn):
+        return {"id": "00000000-0000-0000-0000-000000000001"}
+
+    async def fake_fp(_cid):
+        return "fp-1"
+
+    async def slow_build(cn):
+        calls.append(cn)
+        await asyncio.sleep(0.05)
+        return {"status": "ok", "case_number": cn, "arguments": [],
+                "retrieval_complete": True, "summary": {}}
+
+    monkeypatch.setattr(ccv.db, "get_case_by_number", fake_case)
+    monkeypatch.setattr(ccv, "_inputs_fingerprint", fake_fp)
+    monkeypatch.setattr(ccv, "_build_view_uncached", slow_build)
+
+    await asyncio.gather(*(ccv.build_view("1069-04-26") for _ in range(6)))
+    assert len(calls) == 1, "six concurrent loads, one assembly"
+
+
+@pytest.mark.asyncio
+async def test_partial_view_expires_so_missing_suggestions_get_retried(monkeypatch):
+    """A budget-exhausted view is cached to stop reload storms, but it must not
+    become permanent — the arguments with no suggestions deserve another try."""
+    calls: list = []
+    _stub(monkeypatch, "fp-1", calls, complete=False)
+    await ccv.build_view("1069-04-26")
+    _fp, expires_at, _view = ccv._view_cache["1069-04-26"]
+    assert expires_at is not None, "a partial view must carry an expiry"
+
+    monkeypatch.setattr(ccv.time, "monotonic", lambda: expires_at + 1)
+    after = await ccv.build_view("1069-04-26")
+    assert after["cached"] is False
+    assert len(calls) == 2
+
+
+@pytest.mark.asyncio
+async def test_complete_view_does_not_expire_on_a_timer(monkeypatch):
+    calls: list = []
+    _stub(monkeypatch, "fp-1", calls, complete=True)
+    await ccv.build_view("1069-04-26")
+    _fp, expires_at, _view = ccv._view_cache["1069-04-26"]
+    assert expires_at is None, "freshness comes from the fingerprint, not a clock"
+
+
+@pytest.mark.asyncio
+async def test_use_cache_false_always_rebuilds(monkeypatch):
+    calls: list = []
+    _stub(monkeypatch, "fp-1", calls)
+    await ccv.build_view("1069-04-26")
+    await ccv.build_view("1069-04-26", use_cache=False)
+    assert len(calls) == 2