28423907fd
Three first-try-failure-surface fixes from Pavel's #185 trace + the template guidance question, all under PR #188's umbrella so they land together with the file_server / parallel pull / Tier 1 work. 1. CLI clean-error wrapper — new AgnesTransportError raised by the api_*/stream_download helpers when httpx times out / drops / refuses, plus a top-level Typer wrapper (cli/main.py) that prints one-line "Error: …" + actionable hint and exits non-zero. Full traceback goes to ~/.config/agnes/last-error.log for support forwarding. Unhandled Exceptions are caught at the same boundary so no Python traceback ever leaks to the analyst's terminal. Pavel's #185 Phase 3B: a 30-frame httpx traceback from a slow BQ --remote query made it look like a CLI bug. Now: clean message + hint pointing at `agnes snapshot create` / partition-column guidance. Entry point in pyproject.toml flipped from `cli.main:app` → `cli.main:_run_with_clean_errors` so the wrapper actually runs under the installed `agnes` binary. 2. agnes init / agnes pull --skip-materialize + progress bar. --skip-materialize omits query_mode='materialized' rows from the download set so a first init doesn't spend 44 minutes silently pulling a single 6 GB parquet (Pavel's #185 Phase 1). Rich-driven per-file progress bar with label/bytes/rate/ETA renders to stderr when not --quiet and not --json. Aggregates across the parallel ThreadPoolExecutor workers added earlier in this PR. 3. config/claude_md_template.txt: explicit one-line snippet pointing at `agnes catalog --json | jq '.tables[] | select(.id=="<id>")'` for per-table descriptions + restated invariant: "the description field on each catalog row is the authoritative business-rules text — re-read live, never copy into this file." Resolves the regression-or-feature debate between Pavel (wants annotations) and the user feedback that landed in the prior commit (don't embed table-specific content; tables change). Catalog command stays the source of truth.
120 lines
4.4 KiB
TOML
120 lines
4.4 KiB
TOML
[project]
|
|
name = "agnes-the-ai-analyst"
|
|
version = "0.35.1"
|
|
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
|
|
"httpx>=0.27.0",
|
|
# 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",
|
|
]
|