Add URL previews for chat messages (#43)

Slack/Discord-style link unfurling: the first http(s) URL in a message's
content gets a small preview card (title/description/image/site name)
fetched from the page's Open Graph tags.

Backend:
- Message.preview_url (extracted at create/edit time, cheap regex, no
  I/O) points at a link_previews cache row keyed by URL -- the same URL
  posted in different messages/rooms fetches once, and a failed fetch is
  cached too so a dead URL isn't retried on every reference.
- The actual fetch runs in a background asyncio.create_task from
  broadcast_new_message/broadcast_message_update, on its own DB session,
  so a slow third-party site never delays message delivery. A separate
  "link_preview" WS envelope carries the result once it resolves.
- SSRF protection reuses app/services/ssrf.py's validate_target_url
  (renamed from UnsafeWebhookUrlError to UnsafeUrlError now that it's
  shared with webhooks), but re-validates before every hop of a redirect
  chain rather than once up front -- redirects are followed manually so
  each intermediate URL is checked before it's ever connected to.
- Parsed with stdlib html.parser -- no new dependency.

Frontend: a LinkPreviewCard rendered under message content when present,
patched into state live via the new WS envelope and included in message
history for reloads.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
2026-08-17 17:50:55 -06:00
co-authored by Claude Sonnet 5
parent 752da74c5a
commit 760d2cf5dd
18 changed files with 835 additions and 21 deletions
@@ -0,0 +1,53 @@
"""link previews for URL unfurling in chat messages
Revision ID: d00f93766fa5
Revises: ffdd409227bb
Create Date: 2026-08-17 17:31:13.598917
"""
from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision: str = 'd00f93766fa5'
down_revision: Union[str, Sequence[str], None] = 'ffdd409227bb'
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
"""Upgrade schema."""
op.create_table(
"link_previews",
sa.Column("id", sa.Uuid(), nullable=False),
sa.Column("url", sa.String(length=2048), nullable=False),
sa.Column("title", sa.String(length=500), nullable=True),
sa.Column("description", sa.String(length=1000), nullable=True),
sa.Column("image_url", sa.String(length=2048), nullable=True),
sa.Column("site_name", sa.String(length=200), nullable=True),
sa.Column("fetch_failed", sa.Boolean(), nullable=False),
sa.Column(
"fetched_at",
sa.DateTime(timezone=True),
server_default=sa.text("clock_timestamp()"),
nullable=False,
),
sa.PrimaryKeyConstraint("id"),
)
op.create_index(
op.f("ix_link_previews_url"), "link_previews", ["url"], unique=True
)
# Nullable, no default -- just adds a column to the catalog, no table
# rewrite, no lock beyond the instant one ALTER TABLE ADD COLUMN always
# takes for a nullable column with no default.
op.add_column("messages", sa.Column("preview_url", sa.String(length=2048), nullable=True))
def downgrade() -> None:
"""Downgrade schema."""
op.drop_column("messages", "preview_url")
op.drop_index(op.f("ix_link_previews_url"), table_name="link_previews")
op.drop_table("link_previews")