feat: Introduce bot-descarga service for PDF downloads and remote bot control. Add Docker configuration, environment variables, and a GUI for agent management. Enhance README with bot details and installation instructions.

This commit is contained in:
erik
2026-07-12 21:20:29 -05:00
parent a75ccce13f
commit 103bcea15b
66 changed files with 4469 additions and 13 deletions
@@ -0,0 +1,120 @@
"""Bot descarga: download_workers, download_jobs, download_job_events.
Revision ID: 0004
Revises: 0003
Create Date: 2026-07-12
"""
from __future__ import annotations
from typing import Sequence, Union
import sqlalchemy as sa
from alembic import op
from sqlalchemy.dialects import postgresql
revision: str = "0004"
down_revision: Union[str, None] = "0003"
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def _table_exists(conn: sa.engine.Connection, table: str) -> bool:
return sa.inspect(conn).has_table(table)
def upgrade() -> None:
conn = op.get_bind()
json_type = (
postgresql.JSONB()
if conn.dialect.name == "postgresql"
else sa.JSON()
)
if not _table_exists(conn, "download_workers"):
op.create_table(
"download_workers",
sa.Column("id", sa.String(36), primary_key=True),
sa.Column("hostname", sa.Text(), nullable=False, server_default=""),
sa.Column("max_concurrent", sa.Integer(), nullable=False, server_default="1"),
sa.Column("status", sa.String(32), nullable=False),
sa.Column("last_heartbeat", sa.DateTime(timezone=True), nullable=False),
sa.Column("current_job_id", sa.String(36), nullable=True),
)
op.create_index("ix_download_workers_status", "download_workers", ["status"])
if not _table_exists(conn, "download_jobs"):
op.create_table(
"download_jobs",
sa.Column("id", sa.String(36), primary_key=True),
sa.Column("job_id", sa.String(36), sa.ForeignKey("jobs.id"), nullable=True),
sa.Column("task_id", sa.String(36), sa.ForeignKey("tasks.id"), nullable=True),
sa.Column("worker_id", sa.String(36), nullable=False),
sa.Column("status", sa.String(32), nullable=False, server_default="pending"),
sa.Column("title", sa.Text(), nullable=True),
sa.Column("excel_key", sa.Text(), nullable=False, server_default=""),
sa.Column("downloads_prefix", sa.Text(), nullable=False, server_default=""),
sa.Column("original_filename", sa.Text(), nullable=False, server_default=""),
sa.Column("cancel_requested", sa.Boolean(), nullable=False, server_default=sa.false()),
sa.Column("result", json_type, nullable=False, server_default=sa.text("'{}'::jsonb") if conn.dialect.name == "postgresql" else sa.text("'{}'")),
sa.Column("error", sa.Text(), nullable=True),
sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
sa.Column("started_at", sa.DateTime(timezone=True), nullable=True),
sa.Column("finished_at", sa.DateTime(timezone=True), nullable=True),
)
op.create_index("ix_download_jobs_job_id", "download_jobs", ["job_id"])
op.create_index("ix_download_jobs_task_id", "download_jobs", ["task_id"])
op.create_index("ix_download_jobs_worker_id", "download_jobs", ["worker_id"])
op.create_index("ix_download_jobs_status", "download_jobs", ["status"])
op.create_index(
"ix_download_jobs_worker_status",
"download_jobs",
["worker_id", "status"],
)
if not _table_exists(conn, "download_job_events"):
op.create_table(
"download_job_events",
sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
sa.Column(
"download_job_id",
sa.String(36),
sa.ForeignKey("download_jobs.id"),
nullable=False,
),
sa.Column("event_type", sa.String(64), nullable=False),
sa.Column("message", sa.Text(), nullable=False),
sa.Column("timestamp", sa.DateTime(timezone=True), nullable=False),
sa.Column("radicado", sa.String(255), nullable=True),
sa.Column("nit", sa.String(64), nullable=True),
sa.Column("idx", sa.Integer(), nullable=True),
sa.Column("total", sa.Integer(), nullable=True),
sa.Column(
"metadata",
json_type,
nullable=False,
server_default=sa.text("'{}'::jsonb") if conn.dialect.name == "postgresql" else sa.text("'{}'"),
),
)
op.create_index(
"ix_download_job_events_job_id",
"download_job_events",
["download_job_id", "id"],
)
def downgrade() -> None:
conn = op.get_bind()
if _table_exists(conn, "download_job_events"):
op.drop_index("ix_download_job_events_job_id", table_name="download_job_events")
op.drop_table("download_job_events")
if _table_exists(conn, "download_jobs"):
op.drop_index("ix_download_jobs_worker_status", table_name="download_jobs")
op.drop_index("ix_download_jobs_status", table_name="download_jobs")
op.drop_index("ix_download_jobs_worker_id", table_name="download_jobs")
op.drop_index("ix_download_jobs_task_id", table_name="download_jobs")
op.drop_index("ix_download_jobs_job_id", table_name="download_jobs")
op.drop_table("download_jobs")
if _table_exists(conn, "download_workers"):
op.drop_index("ix_download_workers_status", table_name="download_workers")
op.drop_table("download_workers")