b5b16e98a0
Pre-fix flow: 1. extractor subprocess writes _meta with N remote rows + creates N inner views in extract.duckdb (rebuild_from_registry skips materialized rows per design — explicit `continue` at line 389) 2. _run_materialized_pass calls materialize_query, which writes parquet atomically + returns stats — but never updates _meta 3. orchestrator.rebuild scans _meta, finds only the N remote rows, creates master views only for them. Materialized parquet is on disk but invisible to /api/query → 400 'not yet materialized' Symptom appears after every container recreate (the previous run's _meta state is wiped because docker compose down nukes the named volume that backs extract.duckdb on some compose layouts; even on volumes that persist, the next extractor pass calls _create_meta_table which DROPs + CREATEs _meta cleanly). Fix: after os.replace(tmp_path, parquet_path) in materialize_query, open extract.duckdb (read-write), DELETE existing _meta row for table_id, INSERT new one with query_mode='materialized', and CREATE OR REPLACE VIEW <table_id> AS SELECT * FROM read_parquet(<path>). All inside a single transaction so concurrent reads see either old or new state, not torn rows. Fail-soft on lock contention or schema drift — parquet remains canonical, next sync pass recovers. Tests: 3 new in test_bq_materialize.py covering: - meta + inner view registered after materialize, alongside existing remote rows - re-run replaces (not duplicates) the meta row - skips inner-view registration when extract.duckdb doesn't exist yet (fresh BQ-only deployment edge case)
125 lines
4.7 KiB
TOML
125 lines
4.7 KiB
TOML
[project]
|
|
name = "agnes-the-ai-analyst"
|
|
version = "0.40.0"
|
|
description = "Agnes — AI Data Analyst platform for AI analytical systems"
|
|
requires-python = ">=3.11,<3.14"
|
|
license = "MIT"
|
|
readme = "README.md"
|
|
|
|
dependencies = [
|
|
# Core database
|
|
"duckdb>=0.9.0",
|
|
# Web framework (FastAPI)
|
|
"fastapi>=0.115.0",
|
|
"uvicorn[standard]>=0.32.0",
|
|
"python-multipart>=0.0.26",
|
|
"jinja2>=3.1.0",
|
|
"starlette>=0.41.0",
|
|
# Authentication
|
|
"PyJWT>=2.8.0",
|
|
"itsdangerous>=2.1.0",
|
|
"authlib>=1.6.11",
|
|
"argon2-cffi>=23.1.0",
|
|
# HTTP client. `h2` enables HTTP/2 multiplexing for the persistent
|
|
# CLI client used by `agnes pull` (one TCP connection serves N
|
|
# concurrent parquet streams + range chunks). `cli/client.py`
|
|
# gracefully falls back to HTTP/1.1 if h2 is missing, so this
|
|
# extra is for performance, not correctness.
|
|
"httpx>=0.27.0",
|
|
"h2>=4.1.0",
|
|
# CLI
|
|
"typer>=0.12.0",
|
|
"rich>=13.0.0",
|
|
# Configuration
|
|
"python-dotenv>=1.0.0",
|
|
"pyyaml>=6.0",
|
|
# Data processing
|
|
"pandas>=2.0.0",
|
|
"pyarrow>=12.0.0",
|
|
"pytz>=2024.1",
|
|
# SQL parsing — server-side WHERE validator for /api/v2/scan (app/api/where_validator.py)
|
|
# Minimum 30.x — older versions had walk() yielding (node, parent, key)
|
|
# tuples instead of expression nodes, which would silently bypass the
|
|
# WHERE-validator structural checks (isinstance(tuple, exp.Subquery)
|
|
# is always False). 30.x yields nodes directly.
|
|
"sqlglot>=30.0.0",
|
|
# Data source connectors
|
|
"google-cloud-bigquery>=3.0.0",
|
|
"google-cloud-bigquery-storage>=2.0.0",
|
|
# Google Workspace Cloud Identity / Admin SDK (Workspace group membership sync)
|
|
"google-api-python-client>=2.0.0",
|
|
# Profiler visualizations
|
|
"matplotlib>=3.8.0",
|
|
"numpy>=1.24.0",
|
|
# Claude Code marketplace endpoint — pure-Python git server mounted in FastAPI
|
|
"dulwich>=0.22.0",
|
|
"a2wsgi>=1.10.0",
|
|
# In-process TTL cache for marketplace etag (transitively present via
|
|
# google-auth, declared explicitly here because we depend on it directly).
|
|
"cachetools>=5.3.0",
|
|
# Per-IP rate limiting on auth endpoints (#45). In-process counters by
|
|
# default — fine for single-replica deploys. Multi-replica rollouts can
|
|
# swap the storage backend via slowapi's `storage_uri` (Redis, Memcached).
|
|
"slowapi>=0.1.9",
|
|
# LLM provider SDKs — core (not dev) because connectors/llm/*_provider.py
|
|
# is imported by services/{corporate_memory, verification_detector} which
|
|
# the scheduler drives in production. Promoted from [dev] in #176 to fix
|
|
# ModuleNotFoundError boot loops on default Compose deploys.
|
|
"anthropic>=0.30.0",
|
|
"openai>=1.30.0",
|
|
# Legacy Keboola Storage API client. The primary Keboola path is the
|
|
# DuckDB community extension (`connectors/keboola/access.py`,
|
|
# `connectors/keboola/extractor.py`), but it routes scans through
|
|
# Keboola QueryService — and on projects whose Snowflake backend
|
|
# doesn't expose bucket schemas to the storage-token-derived role
|
|
# the extension fails with `Schema '..."in.c-..."' does not exist
|
|
# or not authorized` while the same token reads fine via the
|
|
# `/v2/storage/tables/{id}/data-preview` REST endpoint
|
|
# (keboola/duckdb-extension#17). The extractor has had a `kbcstorage`
|
|
# fallback path since the extension landed
|
|
# (`connectors/keboola/extractor.py:_extract_via_legacy`); making
|
|
# the dep core means that fallback is actually importable in the
|
|
# default install instead of crashing with `ModuleNotFoundError`.
|
|
"kbcstorage>=0.9.0",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest>=9.0.0",
|
|
"pytest-timeout>=2.0.0",
|
|
"pytest-xdist>=3.0.0",
|
|
"faker>=24.0.0",
|
|
# jsonschema validates the corporate-memory extraction-tool golden fixtures
|
|
# under tests/test_corporate_memory_v1.py (extraction.json, correction.json,
|
|
# confidence_calibration.json). Production code does not depend on it.
|
|
"jsonschema>=4.0.0",
|
|
# FastAPI debug toolbar — gated behind DEBUG=1 env var in app/main.py.
|
|
# Provides per-request panels (headers, routes, timer, profiling, etc.)
|
|
# for local development. Never loaded in production (no DEBUG=1 there).
|
|
"fastapi-debug-toolbar>=0.6.3",
|
|
]
|
|
|
|
[project.scripts]
|
|
agnes = "cli.main:_run_with_clean_errors"
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["app", "src", "connectors", "cli", "services", "config"]
|
|
|
|
[tool.ruff]
|
|
line-length = 120
|
|
target-version = "py313"
|
|
|
|
[tool.uv]
|
|
dev-dependencies = [
|
|
"pytest>=9.0.0",
|
|
"pytest-timeout>=2.0.0",
|
|
"pytest-xdist>=3.0.0",
|
|
"faker>=24.0.0",
|
|
"anthropic>=0.30.0",
|
|
"openai>=1.30.0",
|
|
"fastapi-debug-toolbar>=0.6.3",
|
|
]
|