c3e82972c8
* feat(bq): decouple table_registry bucket from BQ dataset name (#343) Adds optional `bq_fqn` column (schema v51) carrying the fully-qualified BigQuery path (project.dataset.table) so the rebuild path no longer has to reconstruct it from the dual-purpose `bucket` field (which is also a UX/RBAC label). - Schema v51 migration + _SYSTEM_SCHEMA carry the nullable column; rows without it keep using the legacy bucket+source_table+ remote_attach.project path (backwards compat). - BQ extractor honors bq_fqn per row when present: dataset/table override on same-project rows; cross-project VIEW path works via bigquery_query(billing, ...); cross-project BASE TABLE skipped with a clear warning (multi-ATTACH per project deferred to follow-up). - Orchestrator pre-pass detects drift between extract.duckdb _remote_attach.url and overlay data_source.bigquery.project, calls rebuild_from_registry to regenerate when they differ. Closes the operational hazard where /admin/server-config edits silently left the on-disk extract pointing at the old project until the next manual sync. - Startup config check warns when project ≠ billing_project without location set (the on-disk symptom is "provider returned no data" silently in metadata cache), and when a warehouse-like data project has no billing_project override (silent 403 serviceusage path). - _resolve_bq_location warning now points at the location config key explicitly so operators see the actionable fix in the log. - POST /api/admin/register-table and PUT /api/admin/registry/{id} accept bq_fqn; malformed values rejected at the API boundary (422). - 25 tests covering parse_bq_fqn matrix, extractor override paths (same-project + cross-project VIEW + cross-project BASE TABLE skip), orchestrator drift sync, startup-validator heuristic, admin models. UI surface for bq_fqn input in /admin/tables intentionally omitted from this PR (3.5k-line template change) — admins can register through the REST API or `agnes admin` CLI in the meantime. Multi-project ATTACH support is the same scope deferral as the cross-project BASE TABLE skip; both ride a follow-up PR. * review fixes: abstract CHANGELOG, merge duplicate Changed, bump docs schema version - CHANGELOG.md: remove customer-specific hostname + incident date range from the orchestrator drift-sync entry (vendor-agnostic OSS rule), fold the entry into the existing [Unreleased] ### Changed section instead of opening a duplicate heading. - docs/architecture.md: bump 'Current schema version' from 19 to 51 to match SCHEMA_VERSION (per agnes-orchestrator skill rule #4). * review fixes: vendor-agnostic test fixture + Schema v51 internal bullet - tests/test_bq_fqn.py: replace customer GCP project ID with generic 'my-warehouse-project' placeholder (vendor-agnostic OSS rule). Test asserts on the warehouse-like heuristic, not the literal project name, so the rename is behavior-neutral. - CHANGELOG.md: add explicit '\*\*Schema v51\*\*' bullet under `### Internal` naming the new version + summarizing the additive nullable column (matches the convention from v47/v48 bullets). * fix(bq): cross-project _detect_table_type bills against extractor project Addresses Devin review on #346 — pre-fix _detect_table_type passed the data project as BOTH the FROM-clause target AND the bigquery_query() first arg (billing project). For cross-project bq_fqn rows where fqn_project != project_id, the data SA holds bigquery.dataViewer on fqn_project but the serviceusage.services.use permission only on project_id, so the call 403'd. init_extract's broad except Exception swallowed the error and silently skipped the row, meaning the cross-project VIEW path at extractor.py:~696 — the PR's primary cross-project use case — never executed. - Add optional billing_project kwarg to _detect_table_type; defaults to project for backwards compat (same-project callers unaffected). - Update the init_extract call site to pass billing_project=project_id explicitly. Same-project rows (fqn_project == project_id) are a no-op; cross-project rows now route billing to the project where the SA actually has services.use. - 2 new tests in TestDetectTableTypeBilling cover (a) explicit billing_project routing to bigquery_query 1st arg + data project staying in FROM, and (b) the backwards-compat default. Plus test_cross_project_detect_call_bills_against_extractor_project pins the call-site wiring — captures the (project, billing_project) pair the extractor passes for a cross-project bq_fqn row. * release: 0.54.29 — bq_fqn decoupling + marketplace refactor + setup-script UX Accumulated [Unreleased] content from #342 (flea marketplace refactor), #344 (setup script step-2 cwd check), and #346 (this PR — bq_fqn column + orchestrator drift sync + startup config check). Schema v51.
187 lines
8.2 KiB
TOML
187 lines
8.2 KiB
TOML
[project]
|
||
name = "agnes-the-ai-analyst"
|
||
version = "0.54.29"
|
||
description = "Agnes — AI Data Analyst platform for AI analytical systems"
|
||
requires-python = ">=3.11,<3.14"
|
||
license = "MIT"
|
||
readme = "README.md"
|
||
|
||
dependencies = [
|
||
# Core database
|
||
# 1.5.2 fixes a FK-dependency regression that affected ALTER TABLE on
|
||
# tables referenced by other tables — broke the test_db migration
|
||
# ladder replay on 1.5.1. CI runs 1.5.2; local devs need it too.
|
||
"duckdb>=1.5.2",
|
||
# Web framework (FastAPI)
|
||
"fastapi>=0.115.0",
|
||
"uvicorn[standard]>=0.32.0",
|
||
"python-multipart>=0.0.27",
|
||
"jinja2>=3.1.0",
|
||
"starlette>=0.41.0",
|
||
# Authentication
|
||
"PyJWT>=2.8.0",
|
||
"itsdangerous>=2.1.0",
|
||
"authlib>=1.6.12",
|
||
"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",
|
||
# Keboola Storage API SDK — used by:
|
||
# - `connectors/keboola/client.py` for admin-side bucket / table list
|
||
# (consumed from `app/api/admin.py` discover-and-register, table
|
||
# metadata refresh).
|
||
# Extraction itself uses the lightweight `connectors/keboola/storage_api.py`
|
||
# module (export-async + signed-URL download) which talks to Storage API
|
||
# directly via `requests` — no SDK dependency on the data-path side. The
|
||
# SDK stays for the metadata reads.
|
||
#
|
||
# NOTE: kbcstorage moved to the [server] extra below — see the rationale
|
||
# in [project.optional-dependencies].server. CLI wheels installed via
|
||
# `uv tool install` deliberately ship without it.
|
||
"sse-starlette>=2.0",
|
||
# Optional observability — pure-Python, no compilation. Lazily initialized
|
||
# in src/observability/posthog_client.py and only emits events when
|
||
# POSTHOG_API_KEY is set in the environment. With the key unset the
|
||
# integration is fully off (no network, no init). See docs/observability.md.
|
||
"posthog>=3.7.0",
|
||
# Rust-backed (ammonia) HTML sanitizer for admin-edited rich content
|
||
# (news intro + body, curated marketplace-metadata.json descriptions).
|
||
# Allowlist-based with per-tag attribute scoping; closes the bypass
|
||
# shapes the legacy regex sanitizer in src/welcome_template.py was
|
||
# vulnerable to. Pre-built wheels published for all supported
|
||
# (mac/linux/windows × arm64/x86_64) targets.
|
||
"nh3>=0.2",
|
||
# CommonMark markdown renderer for curator-authored marketplace-metadata.json
|
||
# rich content (plugin description / sample_interaction.assistant). Pure
|
||
# Python, no compilation. Rendered output is funneled through nh3 above.
|
||
"markdown-it-py>=3.0",
|
||
# Cross-platform advisory file locking for the `agnes push` single-instance
|
||
# guard. Wraps fcntl.flock on POSIX and msvcrt.locking on Windows behind
|
||
# a uniform API; OS releases the lock automatically on process exit (no
|
||
# stale-lock detection required). Used by cli/lib/push_lock.py.
|
||
"filelock>=3.13,<4",
|
||
# Transitive dependency hardened directly to dodge 5 dependabot advisories
|
||
# (4 high, 1 medium) flagged on urllib3<2.7.0: cross-origin sensitive
|
||
# header leak on proxied low-level redirects, decompression-bomb bypass
|
||
# + unbounded decompression chain on the streaming API, redirects-when-
|
||
# retries-disabled. The `[server]` extra below adds kbcstorage which
|
||
# transitively caps urllib3<2.0.0; `[tool.uv] override-dependencies`
|
||
# forces 2.7+ in workspace installs (Dockerfile + dev). Wheel consumers
|
||
# who install only the CLI (`uv tool install <wheel>`) get no kbcstorage
|
||
# and no conflict.
|
||
"urllib3>=2.7.0",
|
||
]
|
||
|
||
[project.optional-dependencies]
|
||
# Server-side connectors. The CLI wheel does NOT need these — analysts who
|
||
# `uv tool install` the wheel never reach a kbcstorage import. Splitting it
|
||
# out keeps the wheel's METADATA `Requires-Dist` set free of the
|
||
# `kbcstorage<=0.9.5 → urllib3<2.0.0` cap that conflicts with our
|
||
# `urllib3>=2.7.0` security pin under any fresh resolver context (where
|
||
# `[tool.uv] override-dependencies` does NOT apply — see comment on
|
||
# [tool.uv] below). Server install pulls it in via Dockerfile's
|
||
# `uv pip install --system --no-cache .[server]`.
|
||
server = [
|
||
"kbcstorage>=0.9.0",
|
||
]
|
||
observability = [
|
||
# Already in base dependencies — listed here so operators who want to
|
||
# be explicit can `pip install -e ".[observability]"` and signal intent.
|
||
"posthog>=3.7.0",
|
||
]
|
||
dev = [
|
||
"pytest>=9.0.0",
|
||
"pytest-timeout>=2.0.0",
|
||
"pytest-xdist>=3.0.0",
|
||
# pytest-split shards the suite across parallel CI jobs (`--splits N
|
||
# --group K`); see the `test-shard` matrix in `.github/workflows/ci.yml`.
|
||
# Balanced by the committed `.test_durations` file.
|
||
"pytest-split>=0.9.0",
|
||
"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:main"
|
||
|
||
[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",
|
||
"pytest-split>=0.9.0",
|
||
"faker>=24.0.0",
|
||
"anthropic>=0.30.0",
|
||
"openai>=1.30.0",
|
||
"fastapi-debug-toolbar>=0.6.3",
|
||
]
|
||
# Override the urllib3<2.0.0 ceiling kbcstorage 0.9.5 declares (upstream
|
||
# hasn't relaxed it as of 2026-05-12 but the SDK works fine against
|
||
# urllib3 2.x in practice — we only use `Client` + `Tables` from it and
|
||
# both go through `requests`, which natively supports both lines). Lets
|
||
# the resolver pick a urllib3 line that closes Dependabot advisories
|
||
# CVE-2024-37891 / CVE-2025-{xxx}. See `urllib3>=2.7.0` in [project]
|
||
# dependencies above for the security rationale.
|
||
override-dependencies = ["urllib3>=2.7.0"]
|