bvandeusen
807f478cac
CI & Build / Python lint (push) Successful in 2s
CI & Build / integration (push) Successful in 16s
CI & Build / TypeScript typecheck (push) Successful in 32s
CI & Build / Python tests (push) Successful in 44s
CI & Build / Build & push image (push) Successful in 58s
Add retrieval_logs (migration 0068) + services/retrieval_telemetry with a fire-and-forget record_retrieval(), wired into the MCP search tool (source=mcp_search) and the REST search route (source=rest_search). Captures query, effective params, and the per-result score distribution so KB-injection thresholds can be tuned from data rather than guessed. Scribe: project 2, milestone 93, task 1032. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Xz4j1H7pjYSjKsEpgcNH5E
61 lines
2.4 KiB
Python
61 lines
2.4 KiB
Python
"""retrieval_logs: per-call semantic-retrieval telemetry for KB-injection tuning
|
|
|
|
Revision ID: 0068
|
|
Revises: 0067
|
|
Create Date: 2026-06-22
|
|
|
|
One row per semantic-retrieval call (MCP search tool, REST search route, and —
|
|
once it lands — the title-first auto-inject path). Captures the effective query
|
|
params and the score distribution of the results so the similarity threshold
|
|
and top-k can be tuned from real usage. FK-free on user_id (mirrors app_logs):
|
|
telemetry should outlive the row it describes.
|
|
"""
|
|
from alembic import op
|
|
import sqlalchemy as sa
|
|
from sqlalchemy.dialects.postgresql import JSONB
|
|
|
|
|
|
revision = "0068"
|
|
down_revision = "0067"
|
|
branch_labels = None
|
|
depends_on = None
|
|
|
|
|
|
def upgrade() -> None:
|
|
op.create_table(
|
|
"retrieval_logs",
|
|
sa.Column("id", sa.Integer(), primary_key=True),
|
|
sa.Column(
|
|
"created_at", sa.DateTime(timezone=True), nullable=False,
|
|
server_default=sa.text("now()"),
|
|
),
|
|
sa.Column("user_id", sa.Integer(), nullable=True),
|
|
sa.Column("source", sa.Text(), nullable=False),
|
|
sa.Column("query", sa.Text(), nullable=True),
|
|
sa.Column("threshold", sa.Float(), nullable=True),
|
|
sa.Column("limit_n", sa.Integer(), nullable=True),
|
|
sa.Column("project_id", sa.Integer(), nullable=True),
|
|
sa.Column("is_task", sa.Boolean(), nullable=True),
|
|
sa.Column("result_count", sa.Integer(), nullable=False, server_default="0"),
|
|
sa.Column("top_score", sa.Float(), nullable=True),
|
|
sa.Column("min_score", sa.Float(), nullable=True),
|
|
sa.Column("result_ids", JSONB(), nullable=False, server_default=sa.text("'[]'::jsonb")),
|
|
sa.Column("duration_ms", sa.Float(), nullable=True),
|
|
)
|
|
op.create_index("ix_retrieval_logs_created_at", "retrieval_logs", ["created_at"])
|
|
op.create_index("ix_retrieval_logs_user_id", "retrieval_logs", ["user_id"])
|
|
op.create_index("ix_retrieval_logs_source", "retrieval_logs", ["source"])
|
|
op.create_index(
|
|
"ix_retrieval_logs_source_created_at",
|
|
"retrieval_logs",
|
|
["source", sa.text("created_at DESC")],
|
|
)
|
|
|
|
|
|
def downgrade() -> None:
|
|
op.drop_index("ix_retrieval_logs_source_created_at", table_name="retrieval_logs")
|
|
op.drop_index("ix_retrieval_logs_source", table_name="retrieval_logs")
|
|
op.drop_index("ix_retrieval_logs_user_id", table_name="retrieval_logs")
|
|
op.drop_index("ix_retrieval_logs_created_at", table_name="retrieval_logs")
|
|
op.drop_table("retrieval_logs")
|