Files
chat/chat/web/search.py
T

217 lines
8.2 KiB
Python

"""T100 (Phase 4): cross-chat search UX route.
Wraps T93's :func:`chat.services.cross_chat_search.search_all_memories`
in a small read-only HTML surface so the top-bar search input has
somewhere to land. The route does no filtering of its own beyond the
empty-query fast-path that T93 already implements; ranking, owner
scope, and witness scope all live in the service layer.
For each match we hydrate just enough metadata to render a row:
* the owner bot's display name (so users see "BOTA" not "bot_a"),
* the originating ``chat_id`` (the link target — there's no per-turn
anchor today because memories don't carry an ``event_id`` column,
so we deep-link to the chat as a whole),
* the originating scene title when one exists,
* and the ``pov_summary`` itself.
T106 (Phase 4.5): hydration is batched. Pre-T106 the route called
``get_bot``/``get_chat``/``get_scene`` once per result row — N+1 with
``DEFAULT_SEARCH_K=50`` meaning up to 150 individual SELECTs per page
load. We now collect distinct ids first and fan-in via three
``WHERE id IN (...)`` queries, then map back per row.
We deliberately keep this module synchronous and template-only — no
HTMX swaps, no JSON API — because the search box is a "leave the
current chat to look something up" surface, not an inline drawer.
"""
from __future__ import annotations
import json
from pathlib import Path
from sqlite3 import Connection
from fastapi import APIRouter, Depends, Request
from fastapi.responses import HTMLResponse
from fastapi.templating import Jinja2Templates
from chat.services.cross_chat_search import search_all_memories
from chat.state.entities import get_bot
from chat.state.world import get_chat, get_scene
from chat.web.bots import get_conn
TEMPLATES = Jinja2Templates(
directory=str(Path(__file__).resolve().parent.parent / "templates")
)
#: Maximum cross-chat FTS matches surfaced per ``/search`` page load.
#: Extracted as a module-level constant (T106) so the cap is tunable
#: without touching the route body. ``search_all_memories`` itself
#: defaults to a smaller ``k=20``; we override here because the
#: top-bar search is a "scan everything I've seen" surface, not an
#: inline drawer.
DEFAULT_SEARCH_K = 50
router = APIRouter()
def _fetch_bots_by_ids(conn: Connection, ids: set[str]) -> dict[str, dict]:
"""Batched sibling of :func:`chat.state.entities.get_bot`.
Inlined here (not exported from ``state.entities``) to keep T106's
scope confined to ``search.py`` per the Phase 4.5 plan. Returns
``{bot_id: bot_dict}`` for every id present in ``ids``; ids with
no matching row are simply absent from the map (the caller falls
back to the raw id string the same way it did pre-T106).
Empty ``ids`` short-circuits to ``{}`` because SQLite rejects
``WHERE id IN ()`` as a syntax error.
"""
if not ids:
return {}
placeholders = ",".join("?" * len(ids))
cols = [c[1] for c in conn.execute("PRAGMA table_info(bots)").fetchall()]
rows = conn.execute(
f"SELECT * FROM bots WHERE id IN ({placeholders})",
tuple(ids),
).fetchall()
out: dict[str, dict] = {}
for row in rows:
d = dict(zip(cols, row))
d["voice_samples"] = json.loads(d.pop("voice_samples_json"))
d["traits"] = json.loads(d.pop("traits_json"))
out[d["id"]] = d
return out
def _fetch_chats_by_ids(conn: Connection, ids: set[str]) -> dict[str, dict]:
"""Batched sibling of :func:`chat.state.world.get_chat`.
Mirrors that helper's ``chats``/``chat_state`` JOIN so the returned
dicts have the same shape (``narrative_anchor``, ``time``,
``weather``, ``active_scene_id``, etc.). Empty ``ids`` returns
``{}`` to dodge the ``IN ()`` syntax error.
"""
if not ids:
return {}
placeholders = ",".join("?" * len(ids))
rows = conn.execute(
"SELECT c.id, c.host_bot_id, c.guest_bot_id, c.created_at, "
" s.time, s.weather, s.active_scene_id, s.narrative_anchor "
f"FROM chats c JOIN chat_state s ON s.chat_id = c.id "
f"WHERE c.id IN ({placeholders})",
tuple(ids),
).fetchall()
return {
row[0]: {
"id": row[0],
"host_bot_id": row[1],
"guest_bot_id": row[2],
"created_at": row[3],
"time": row[4],
"weather": row[5],
"active_scene_id": row[6],
"narrative_anchor": row[7],
}
for row in rows
}
def _fetch_scenes_by_ids(conn: Connection, ids: set[int]) -> dict[int, dict]:
"""Batched sibling of :func:`chat.state.world.get_scene`.
Returns ``{scene_id: scene_dict}`` with ``participants`` already
JSON-decoded so callers see the same shape as the per-row helper.
Empty ``ids`` returns ``{}``.
"""
if not ids:
return {}
placeholders = ",".join("?" * len(ids))
cols = [c[1] for c in conn.execute("PRAGMA table_info(scenes)").fetchall()]
rows = conn.execute(
f"SELECT * FROM scenes WHERE id IN ({placeholders})",
tuple(ids),
).fetchall()
out: dict[int, dict] = {}
for row in rows:
d = dict(zip(cols, row))
d["participants"] = json.loads(d.pop("participants_json"))
out[d["id"]] = d
return out
@router.get("/search", response_class=HTMLResponse)
async def search(request: Request, q: str = "", conn=Depends(get_conn)):
"""Render ``search.html`` with up to :data:`DEFAULT_SEARCH_K` matches.
``q`` is intentionally allowed to be empty — that path renders the
page's "enter a query" placeholder rather than a 400, because the
top-bar form submits to this URL even with an empty input. T93's
service short-circuits whitespace-only queries to ``[]`` so there
is no FTS5 ``MATCH ''`` syntax error to guard against here.
Hydration (T106) is batched: rather than calling ``get_bot`` /
``get_chat`` / ``get_scene`` per row (worst case 3 * k individual
SELECTs), we collect distinct ids and issue one ``IN (...)`` query
per entity kind, then map back during the row build. ``get_bot``
et al. remain imported for test-time monkeypatching but are no
longer invoked on the hot path.
"""
raw_results = (
search_all_memories(conn, query=q, k=DEFAULT_SEARCH_K) if q else []
)
# Collect distinct ids up front so the IN-list queries dedupe (a
# popular bot or scene shows up many times across the result set).
bot_ids: set[str] = {r["owner_id"] for r in raw_results if r["owner_id"]}
chat_ids: set[str] = {r["chat_id"] for r in raw_results if r["chat_id"]}
scene_ids: set[int] = {
r["scene_id"] for r in raw_results if r["scene_id"]
}
bots_by_id = _fetch_bots_by_ids(conn, bot_ids)
chats_by_id = _fetch_chats_by_ids(conn, chat_ids)
scenes_by_id = _fetch_scenes_by_ids(conn, scene_ids)
# Hydrate display fields per row from the batched maps. We do this
# in the route (not the service) so the service stays a pure FTS
# shim that other UIs can reuse.
results = []
for row in raw_results:
bot = bots_by_id.get(row["owner_id"])
chat = chats_by_id.get(row["chat_id"])
scene = (
scenes_by_id.get(row["scene_id"]) if row["scene_id"] else None
)
results.append(
{
"memory_id": row["memory_id"],
"owner_id": row["owner_id"],
"owner_name": bot["name"] if bot else row["owner_id"],
"chat_id": row["chat_id"],
"chat_name": (
chat.get("narrative_anchor") if chat else None
),
"scene_id": row["scene_id"],
# Scenes have no ``title`` column today; surface the
# ``started_at`` timestamp as a human-friendly label
# when a scene is set, otherwise leave it blank.
"scene_label": (
scene.get("started_at") if scene else None
),
"pov_summary": row["pov_summary"],
"significance": row["significance"],
"ts": row["ts"],
}
)
return TEMPLATES.TemplateResponse(
request,
"search.html",
{
"query": q,
"results": results,
"active_nav": "search",
},
)