重写为 AI 情报 Agent 并接入 Jenkins 流水线

2026-07-08 21:41:46 +08:00
commit f471c2a08a
45 changed files with 2163 additions and 0 deletions
@@ -0,0 +1,81 @@
+"""initial schema
+
+Revision ID: 202605071200
+Revises:
+Create Date: 2026-05-07 12:00:00
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+revision: str = "202605071200"
+down_revision: Union[str, None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # Topics define durable intelligence goals instead of one-off prompts.
+    op.create_table(
+        "topics",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("name", sa.String(length=120), nullable=False, unique=True),
+        sa.Column("description", sa.Text(), nullable=False),
+        sa.Column("enabled", sa.Boolean(), nullable=False, server_default=sa.true()),
+        sa.Column("created_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        sa.Column("updated_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+    )
+
+    # Runs are the audit trail for every scheduled or manual agent execution.
+    op.create_table(
+        "agent_runs",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("status", sa.String(length=32), nullable=False),
+        sa.Column("started_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        sa.Column("finished_at", sa.DateTime(), nullable=True),
+        sa.Column("error", sa.Text(), nullable=True),
+        sa.Column("request_payload", sa.JSON(), nullable=False),
+        sa.Column("raw_response", sa.JSON(), nullable=True),
+    )
+
+    # Signals store normalized facts that the reporter and future memory layer can query.
+    op.create_table(
+        "signals",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("run_id", sa.Integer(), sa.ForeignKey("agent_runs.id"), nullable=False),
+        sa.Column("topic", sa.String(length=120), nullable=False),
+        sa.Column("title", sa.String(length=300), nullable=False),
+        sa.Column("summary", sa.Text(), nullable=False),
+        sa.Column("source_url", sa.Text(), nullable=False),
+        sa.Column("source_url_hash", sa.String(length=64), nullable=False),
+        sa.Column("source_name", sa.String(length=200), nullable=False),
+        sa.Column("published_at", sa.DateTime(), nullable=True),
+        sa.Column("importance", sa.Integer(), nullable=False),
+        sa.Column("entities", sa.JSON(), nullable=False),
+        sa.Column("created_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        sa.UniqueConstraint("source_url_hash", name="uq_signals_source_url_hash"),
+    )
+    op.create_index("ix_signals_run_id", "signals", ["run_id"])
+    op.create_index("ix_signals_topic", "signals", ["topic"])
+
+    # Reports are persisted both in MySQL and as markdown files for human reading.
+    op.create_table(
+        "reports",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("run_id", sa.Integer(), sa.ForeignKey("agent_runs.id"), nullable=False),
+        sa.Column("title", sa.String(length=200), nullable=False),
+        sa.Column("content_md", sa.Text(), nullable=False),
+        sa.Column("file_path", sa.String(length=1024), nullable=True),
+        sa.Column("created_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("reports")
+    op.drop_index("ix_signals_topic", table_name="signals")
+    op.drop_index("ix_signals_run_id", table_name="signals")
+    op.drop_table("signals")
+    op.drop_table("agent_runs")
+    op.drop_table("topics")
@@ -0,0 +1,66 @@
+"""source subscriptions and raw items
+
+Revision ID: 202605080900
+Revises: 202605071200
+Create Date: 2026-05-08 09:00:00
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+revision: str = "202605080900"
+down_revision: Union[str, None] = "202605071200"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # Subscriptions are stable source inputs that run before model-side search.
+    op.create_table(
+        "source_subscriptions",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("name", sa.String(length=160), nullable=False, unique=True),
+        sa.Column("source_type", sa.String(length=32), nullable=False),
+        sa.Column("url", sa.Text(), nullable=False),
+        sa.Column("url_hash", sa.String(length=64), nullable=False, unique=True),
+        sa.Column("category", sa.String(length=120), nullable=False),
+        sa.Column("enabled", sa.Boolean(), nullable=False, server_default=sa.true()),
+        sa.Column("created_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        sa.Column("updated_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+    )
+
+    # Raw items preserve source evidence before the final signal layer deduplicates and summarizes it.
+    op.create_table(
+        "raw_items",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("run_id", sa.Integer(), sa.ForeignKey("agent_runs.id"), nullable=False),
+        sa.Column(
+            "subscription_id",
+            sa.Integer(),
+            sa.ForeignKey("source_subscriptions.id"),
+            nullable=False,
+        ),
+        sa.Column("title", sa.String(length=300), nullable=False),
+        sa.Column("summary", sa.Text(), nullable=False),
+        sa.Column("source_url", sa.Text(), nullable=False),
+        sa.Column("source_url_hash", sa.String(length=64), nullable=False),
+        sa.Column("source_name", sa.String(length=200), nullable=False),
+        sa.Column("category", sa.String(length=120), nullable=False),
+        sa.Column("published_at", sa.DateTime(), nullable=True),
+        sa.Column("raw_payload", sa.JSON(), nullable=False),
+        sa.Column("created_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        sa.UniqueConstraint("source_url_hash", name="uq_raw_items_source_url_hash"),
+    )
+    op.create_index("ix_raw_items_run_id", "raw_items", ["run_id"])
+    op.create_index("ix_raw_items_subscription_id", "raw_items", ["subscription_id"])
+    op.create_index("ix_raw_items_category", "raw_items", ["category"])
+
+
+def downgrade() -> None:
+    op.drop_index("ix_raw_items_category", table_name="raw_items")
+    op.drop_index("ix_raw_items_subscription_id", table_name="raw_items")
+    op.drop_index("ix_raw_items_run_id", table_name="raw_items")
+    op.drop_table("raw_items")
+    op.drop_table("source_subscriptions")
@@ -0,0 +1,60 @@
+"""drop subscription tables
+
+Revision ID: 202607080900
+Revises: 202605080900
+Create Date: 2026-07-08 09:00:00
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+revision: str = "202607080900"
+down_revision: Union[str, None] = "202605080900"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # Agent主路径已经改为模型结构化情报，历史订阅源表从运行模型中移除。
+    op.drop_index("ix_raw_items_category", table_name="raw_items")
+    op.drop_index("ix_raw_items_subscription_id", table_name="raw_items")
+    op.drop_index("ix_raw_items_run_id", table_name="raw_items")
+    op.drop_table("raw_items")
+    op.drop_table("source_subscriptions")
+
+
+def downgrade() -> None:
+    # 回滚时恢复旧表结构，便于数据库迁移链保持可逆。
+    op.create_table(
+        "source_subscriptions",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("name", sa.String(length=160), nullable=False, unique=True),
+        sa.Column("source_type", sa.String(length=32), nullable=False),
+        sa.Column("url", sa.Text(), nullable=False),
+        sa.Column("url_hash", sa.String(length=64), nullable=False, unique=True),
+        sa.Column("category", sa.String(length=120), nullable=False),
+        sa.Column("enabled", sa.Boolean(), nullable=False, server_default=sa.true()),
+        sa.Column("created_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        sa.Column("updated_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+    )
+    op.create_table(
+        "raw_items",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("run_id", sa.Integer(), sa.ForeignKey("agent_runs.id"), nullable=False),
+        sa.Column("subscription_id", sa.Integer(), sa.ForeignKey("source_subscriptions.id"), nullable=False),
+        sa.Column("title", sa.String(length=300), nullable=False),
+        sa.Column("summary", sa.Text(), nullable=False),
+        sa.Column("source_url", sa.Text(), nullable=False),
+        sa.Column("source_url_hash", sa.String(length=64), nullable=False),
+        sa.Column("source_name", sa.String(length=200), nullable=False),
+        sa.Column("category", sa.String(length=120), nullable=False),
+        sa.Column("published_at", sa.DateTime(), nullable=True),
+        sa.Column("raw_payload", sa.JSON(), nullable=False),
+        sa.Column("created_at", sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        sa.UniqueConstraint("source_url_hash", name="uq_raw_items_source_url_hash"),
+    )
+    op.create_index("ix_raw_items_run_id", "raw_items", ["run_id"])
+    op.create_index("ix_raw_items_subscription_id", "raw_items", ["subscription_id"])
+    op.create_index("ix_raw_items_category", "raw_items", ["category"])