chore: clean sweep — lint, format, stale refs, generated artifacts

- Fix all 72 ruff lint errors (unused imports, unused variables, E402)
- Format all 14 unformatted dev/scripts files
- Move generated artifacts to assets/ (dag.html, pfs.html)
- Remove duplicate root coverage.svg (already in assets/icons/)
- Update .dockerignore for infra/ tree layout
- Update .gitignore: add .env.bak, mirrors/, htmlcov/
- Fix stale path refs in coverage_badge.py, woodpecker backend,
  test_network_isolation.sh, docs custom.css
- Add .gitkeep to empty dirs (infra/polaris, cloud/*/terraform)
- Delete 12 stale local branches, 10 stale remote branches

.dockerignore

@@ -12,13 +12,8 @@ logs/
 tuva/
 dev/
 tests/
-grafana/
+infra/
-prometheus/
+assets/
-loki/
+cloud/
-trino/
+mirrors/
-traefik/
-nginx/
-gitea/
-styles/
-.woodpecker/
 .claude/

.gitignore

@@ -13,17 +13,28 @@ bundle/sql/
 
 # Marimo cache
 notebooks/__marimo__/
+
+# Secrets and keys
 .deploy_key
-.env
 .deploy_key.pub
+.env
+.env.bak
+
+# Python build artifacts
 __pycache__/
 *.pyc
 .coverage
 dist/
 *.egg-info/
+htmlcov/
+
+# IDE / tool settings
 .claude/settings.local.json
 notebooks/aco.duckdb
 
+# Package mirrors (local cache, not tracked)
+mirrors/
+
 # Docs (auto-generated at build time)
 docs/docs/api/
 docs/static/library.json

coverage.svg

@@ -1,20 +0,0 @@
-<svg xmlns="http://www.w3.org/2000/svg" width="116" height="20">
-  <linearGradient id="b" x2="0" y2="100%">
-    <stop offset="0" stop-color="#bbb" stop-opacity=".1"/>
-    <stop offset="1" stop-opacity=".1"/>
-  </linearGradient>
-  <clipPath id="a">
-    <rect width="116" height="20" rx="3" fill="#fff"/>
-  </clipPath>
-  <g clip-path="url(#a)">
-    <path fill="#555" d="M0 0h65v20H0z"/>
-    <path fill="#4c1" d="M65 0h51v20H65z"/>
-    <path fill="url(#b)" d="M0 0h116v20H0z"/>
-  </g>
-  <g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" font-size="11">
-    <text x="32.5" y="15" fill="#010101" fill-opacity=".3">coverage</text>
-    <text x="32.5" y="14">coverage</text>
-    <text x="90" y="15" fill="#010101" fill-opacity=".3">99%</text>
-    <text x="90" y="14">99%</text>
-  </g>
-</svg>

dev/scripts/add_carrier_to_zotero.py

@@ -7,11 +7,8 @@ Usage:
     uv run python dev/scripts/add_carrier_to_zotero.py
 """
 
-import os
 import random
-import shutil
 import sqlite3
-import string
 import subprocess
 import zipfile
 from datetime import datetime, timezone

dev/scripts/add_zipcode_to_zotero.py

@@ -9,7 +9,6 @@ Usage:
 
 import random
 import sqlite3
-import string
 import subprocess
 import zipfile
 from datetime import datetime, timezone

dev/scripts/backends/databricks.py

@@ -30,8 +30,11 @@ yaml.add_representer(
 
 def _dump(data: dict) -> str:
     return yaml.dump(
-        data, default_flow_style=False, sort_keys=False,
+        data,
-        width=120, allow_unicode=True,
+        default_flow_style=False,
+        sort_keys=False,
+        width=120,
+        allow_unicode=True,
     )
 
 
@@ -69,9 +72,7 @@ class SQLPlugin(DabPlugin):
                     output_mode="ctas",
                 )
             except Exception as e:
-                result[f"bundle/sql/{pipe_name}/_error.txt"] = (
+                result[f"bundle/sql/{pipe_name}/_error.txt"] = f"Transpile failed: {e}"
-                    f"Transpile failed: {e}"
-                )
                 continue
 
             for expr_name, sql in sql_map.items():
@@ -80,8 +81,7 @@ class SQLPlugin(DabPlugin):
                 schema, table = expr_name.split(".", 1)
                 path = f"bundle/sql/{pipe_name}/{table}.sql"
                 header = (
-                    f"-- {expr_name}\n"
+                    f"-- {expr_name}\n-- Generated by gen_config.py — DO NOT EDIT\n\n"
-                    f"-- Generated by gen_config.py — DO NOT EDIT\n\n"
                 )
                 result[path] = header + sql + "\n"
 
@@ -102,27 +102,58 @@ class JobsPlugin(DabPlugin):
         job_clusters = []
         for profile_name in sorted(used_profiles):
             cluster_spec = dict(clusters_cfg.get(profile_name, {}))
-            job_clusters.append(OrderedDict([
+            job_clusters.append(
+                OrderedDict(
+                    [
                         ("job_cluster_key", f"{profile_name}_cluster"),
-                ("new_cluster", OrderedDict([
+                        (
-                    ("spark_version", cluster_spec.get("spark_version", "15.4.x-scala2.12")),
+                            "new_cluster",
-                    ("node_type_id", cluster_spec.get("node_type_id", "i3.xlarge")),
+                            OrderedDict(
+                                [
+                                    (
+                                        "spark_version",
+                                        cluster_spec.get(
+                                            "spark_version", "15.4.x-scala2.12"
+                                        ),
+                                    ),
+                                    (
+                                        "node_type_id",
+                                        cluster_spec.get("node_type_id", "i3.xlarge"),
+                                    ),
                                     ("num_workers", cluster_spec.get("num_workers", 1)),
-                ])),
+                                ]
-            ]))
+                            ),
+                        ),
+                    ]
+                )
+            )
 
         # DDL tasks — one per schema to create tables before SQL runs
         ddl_tasks = []
         for schema_name in sorted(catalog_schemas):
-            ddl_tasks.append(OrderedDict([
+            ddl_tasks.append(
+                OrderedDict(
+                    [
                         ("task_key", f"ddl_{schema_name}"),
                         ("job_cluster_key", "default_cluster"),
-                ("sql_task", OrderedDict([
+                        (
-                    ("file", OrderedDict([
+                            "sql_task",
+                            OrderedDict(
+                                [
+                                    (
+                                        "file",
+                                        OrderedDict(
+                                            [
                                                 ("path", f"bundle/ddl/{schema_name}/"),
-                    ])),
+                                            ]
-                ])),
+                                        ),
-            ]))
+                                    ),
+                                ]
+                            ),
+                        ),
+                    ]
+                )
+            )
 
         # Pipeline tasks — each expression becomes a sql_task
         pipeline_tasks = []
@@ -143,12 +174,19 @@ class JobsPlugin(DabPlugin):
             # Each pipeline task runs all its SQL files in order
             # We use a for_each or sequential notebook; simplest is
             # a single SQL file per pipeline that sources all expressions
-            task["sql_task"] = OrderedDict([
+            task["sql_task"] = OrderedDict(
-                ("file", OrderedDict([
+                [
+                    (
+                        "file",
+                        OrderedDict(
+                            [
                                 ("path", f"bundle/sql/{pipe_name}/"),
-                ])),
+                            ]
+                        ),
+                    ),
                     ("warehouse_id", "${var.warehouse_id}"),
-            ])
+                ]
+            )
             pipeline_tasks.append(task)
 
         schedule = cfg.get("schedule", "0 0 6 * * ?")
@@ -156,11 +194,15 @@ class JobsPlugin(DabPlugin):
 
         job = OrderedDict()
         job["name"] = f"{cfg.get('bundle_name', 'stack')}-pipelines"
-        job["description"] = f"Run all {len(registry)} ACO pipelines in dependency order"
+        job["description"] = (
-        job["schedule"] = OrderedDict([
+            f"Run all {len(registry)} ACO pipelines in dependency order"
+        )
+        job["schedule"] = OrderedDict(
+            [
                 ("quartz_cron_expression", schedule),
                 ("timezone_id", timezone),
-        ])
+            ]
+        )
         job["job_clusters"] = job_clusters
         job["tasks"] = pipeline_tasks
 
@@ -175,10 +217,12 @@ class SchemasPlugin(DabPlugin):
             return {}
         schemas = OrderedDict()
         for schema_name in sorted(catalog_schemas):
-            schemas[schema_name] = OrderedDict([
+            schemas[schema_name] = OrderedDict(
+                [
                     ("name", schema_name),
                     ("catalog_name", "${var.catalog}"),
-            ])
+                ]
+            )
         return {"schemas": schemas}
 
 
@@ -186,14 +230,23 @@ class VolumesPlugin(DabPlugin):
     """Generate a staging volume for data upload."""
 
     def resources(self, cfg: dict, registry: dict, catalog_schemas: list) -> dict:
-        return {"volumes": OrderedDict([
+        return {
-            ("staging", OrderedDict([
+            "volumes": OrderedDict(
+                [
+                    (
+                        "staging",
+                        OrderedDict(
+                            [
                                 ("name", "staging"),
                                 ("catalog_name", "${var.catalog}"),
                                 ("schema_name", "default"),
                                 ("volume_type", "MANAGED"),
-            ])),
+                            ]
-        ])}
+                        ),
+                    ),
+                ]
+            )
+        }
 
 
 # ── Core generator ───────────────────────────────────────────────
@@ -214,6 +267,7 @@ _DEFAULT_PLUGINS: list[DabPlugin] = [
 def _get_catalog_schemas() -> list[str]:
     try:
         from aco.lake.catalog import Catalog
+
         return Catalog().schemas()
     except Exception:
         return []
@@ -252,19 +306,33 @@ def emit(cfg_data: dict) -> dict[str, str]:
     bundle["bundle"] = OrderedDict([("name", bundle_name)])
 
     # Sync SQL files to workspace
-    bundle["sync"] = OrderedDict([
+    bundle["sync"] = OrderedDict(
+        [
             ("include", ["bundle/**"]),
-    ])
+        ]
+    )
 
-    bundle["variables"] = OrderedDict([
+    bundle["variables"] = OrderedDict(
-        ("catalog", OrderedDict([
+        [
+            (
+                "catalog",
+                OrderedDict(
+                    [
                         ("description", "Unity Catalog name for table references"),
                         ("default", targets_cfg.get("prod", {}).get("catalog", "aco")),
-        ])),
+                    ]
-        ("warehouse_id", OrderedDict([
+                ),
+            ),
+            (
+                "warehouse_id",
+                OrderedDict(
+                    [
                         ("description", "SQL warehouse ID for query execution"),
-        ])),
+                    ]
-    ])
+                ),
+            ),
+        ]
+    )
 
     bundle["workspace"] = OrderedDict([("host", "${DATABRICKS_HOST}")])
 
@@ -276,17 +344,21 @@ def emit(cfg_data: dict) -> dict[str, str]:
             target["mode"] = tcfg["mode"]
         if tcfg.get("default"):
             target["default"] = True
-        target["variables"] = OrderedDict([
+        target["variables"] = OrderedDict(
+            [
                 ("catalog", tcfg.get("catalog", "aco")),
-        ])
+            ]
+        )
         if tcfg.get("warehouse_id"):
             target["variables"]["warehouse_id"] = tcfg["warehouse_id"]
         if tcfg.get("mode") == "production":
             run_as = dab_cfg.get("run_as", {})
             if run_as.get("service_principal_name"):
-                target["run_as"] = OrderedDict([
+                target["run_as"] = OrderedDict(
+                    [
                         ("service_principal_name", run_as["service_principal_name"]),
-                ])
+                    ]
+                )
         targets[tname] = target
     bundle["targets"] = targets
 

dev/scripts/backends/woodpecker.py

@@ -242,7 +242,7 @@ steps:
       UV_PROJECT_ENVIRONMENT: .venv
     commands:
       - uv run pytest tests/ --cov=src --cov-report=term-missing --cov-fail-under=99 -q 2>&1 | tee pytest.out
-      - uv run python dev/scripts/coverage_badge.py < pytest.out > coverage.svg
+      - uv run python dev/scripts/coverage_badge.py < pytest.out > assets/icons/coverage.svg
     depends_on:
       - lint
 
@@ -273,7 +273,7 @@ steps:
     commands:
       - git config user.name woodpecker-ci
       - git config user.email ci@${{CI_REPO_OWNER}}.io
-      - git add coverage.svg
+      - git add assets/icons/coverage.svg
       - git diff --cached --quiet && echo "no change" && exit 0
       - git commit -m "update coverage badge [skip ci]"
       - git push http://$REGISTRY_USER:$REGISTRY_PASS@gitea:3000/${{CI_REPO}}.git HEAD:main
@@ -293,7 +293,7 @@ steps:
         from_secret: s3_access_key
       secret_key:
         from_secret: s3_secret_key
-      source: "coverage.svg"
+      source: "assets/icons/coverage.svg"
       target: /badges/${{CI_REPO}}/
       path_style: true
       overwrite: true

dev/scripts/bootstrap_certs.py

@@ -15,7 +15,6 @@ import argparse
 import os
 import shutil
 import subprocess
-import sys
 from pathlib import Path
 
 REPO_ROOT = Path(__file__).resolve().parents[2]
@@ -33,7 +32,7 @@ CA_SUBJECT = "/CN=Homelab CA/O=fhirworx"
 CA_DAYS = 3650
 TLS_DAYS = 3650
 
-from conf import cfg
+from conf import cfg  # noqa: E402
 
 DOMAIN = os.environ.get("DOMAIN", cfg.platform.domain)
 HOST_IP = os.environ.get("HOST_IP", cfg.platform.host_ip)

dev/scripts/coverage_badge.py

@@ -8,7 +8,7 @@ Usage:
     # CI_COMMIT_SHA from environment):
     uv run python dev/scripts/coverage_badge.py --post pytest.out
 
-    # Update styles/coverage.svg in the repo via Gitea API:
+    # Update assets/icons/coverage.svg in the repo via Gitea API:
     uv run python dev/scripts/coverage_badge.py --upload coverage.svg
 """
 
@@ -44,7 +44,7 @@ TEMPLATE = """\
   </g>
 </svg>"""
 
-FILE_PATH = "styles/coverage.svg"
+FILE_PATH = "assets/icons/coverage.svg"
 
 
 def color_for(pct: int) -> str:
@@ -73,11 +73,13 @@ def post_status(pct: int) -> None:
     token, url = _gitea_env()
     sha = os.environ["CI_COMMIT_SHA"]
     endpoint = f"{url}/api/v1/repos/homelab/stack/statuses/{sha}"
-    body = json.dumps({
+    body = json.dumps(
+        {
             "state": "success",
             "description": f"{pct}% coverage",
             "context": "coverage",
-    }).encode()
+        }
+    ).encode()
     req = urllib.request.Request(
         endpoint,
         data=body,
@@ -92,7 +94,7 @@ def post_status(pct: int) -> None:
 
 
 def upload_badge(svg_path: str) -> None:
-    """Update styles/coverage.svg in the repo via Gitea contents API."""
+    """Update assets/icons/coverage.svg in the repo via Gitea contents API."""
     token, url = _gitea_env()
     endpoint = f"{url}/api/v1/repos/homelab/stack/contents/{FILE_PATH}"
     svg_data = open(svg_path, "rb").read()

dev/scripts/fix_zotero_dates.py

@@ -40,7 +40,6 @@ def main() -> int:
     for col in COLUMNS:
         for op in ("INSERT", "UPDATE"):
             trigger = f"fix_{col}_{op.lower()}"
-            of_clause = f"OF {col} " if op == "UPDATE" else ""
             db.execute(f"""
                 CREATE TRIGGER IF NOT EXISTS {trigger}
                 AFTER {op} ON items

dev/scripts/generate_alr_filenames.py

@@ -219,7 +219,11 @@ def generate_module() -> str:
 def main():
     """Generate src/aco/table/alr_filenames.py."""
     output_path = (
-        Path(__file__).resolve().parents[2] / "src" / "aco" / "table" / "alr_filenames.py"
+        Path(__file__).resolve().parents[2]
+        / "src"
+        / "aco"
+        / "table"
+        / "alr_filenames.py"
     )
 
     code = generate_module()
@@ -228,9 +232,9 @@ def main():
     output_path.write_text(code)
 
     print(f"Generated {output_path}")
-    print(f"  18 ALR table patterns (9 annual + 9 quarterly)")
+    print("  18 ALR table patterns (9 annual + 9 quarterly)")
-    print(f"  2 ASR patterns (annual + quarterly)")
+    print("  2 ASR patterns (annual + quarterly)")
-    print(f"  4 package patterns")
+    print("  4 package patterns")
 
     return 0
 

dev/scripts/generate_alr_table_models.py

@@ -25,7 +25,7 @@ def extract_alr_table_specs(pdf_path: str) -> dict:
 
     Returns dict mapping table_id -> {title, fields: list[dict]}
     """
-    pdf = pdfplumber.open(pdf_path)
+    pdfplumber.open(pdf_path)
 
     # Manual field specifications based on PDF extraction
     # Table 1-1 is on pages 8-15, others follow
@@ -163,7 +163,7 @@ def extract_alr_table_specs(pdf_path: str) -> dict:
             {
                 "name": f"HCC_Position_{i:02d}",
                 "type": "int",
-                "desc": f"HCC indicator (0=no, 1=yes) - maps to specific HCC via data dictionary",
+                "desc": "HCC indicator (0=no, 1=yes) - maps to specific HCC via data dictionary",
             }
         )
 
@@ -530,7 +530,7 @@ def generate_module(tables: dict) -> str:
         lines.append("    Source: ALRASRGuide.pdf")
         lines.append('    """')
         lines.append("")
-        lines.append(f'    __schema__ = "alr"')
+        lines.append('    __schema__ = "alr"')
         lines.append(f'    __tablename__ = "{tbl}"')
 
         for field in info["fields"]:

dev/scripts/generate_asr_table_models.py

@@ -370,7 +370,7 @@ def generate_module(tables: dict) -> str:
         lines.append("    Source: ALRASRGuide.pdf")
         lines.append('    """')
         lines.append("")
-        lines.append(f'    __schema__ = "asr"')
+        lines.append('    __schema__ = "asr"')
         lines.append(f'    __tablename__ = "{tbl}"')
 
         for field in info["fields"]:
@@ -398,7 +398,9 @@ def generate_module(tables: dict) -> str:
 
 def main():
     """Generate src/aco/table/asr.py from ALRASRGuide.pdf."""
-    output_path = Path(__file__).resolve().parents[2] / "src" / "aco" / "table" / "asr.py"
+    output_path = (
+        Path(__file__).resolve().parents[2] / "src" / "aco" / "table" / "asr.py"
+    )
 
     tables = extract_asr_table_specs()
     code = generate_module(tables)

dev/scripts/generate_cclf_models.py

@@ -14,7 +14,6 @@ Source: https://www.cms.gov/files/document/cclf-information-packet.pdf
 from __future__ import annotations
 
 import re
-from datetime import date
 from pathlib import Path
 
 import pdfplumber
@@ -206,7 +205,7 @@ def generate_module(tables: dict) -> str:
         lines.append(f"    {len(info['fields'])} fields, fixed-width layout.")
         lines.append('    """')
         lines.append("")
-        lines.append(f'    __schema__ = "cclf"')
+        lines.append('    __schema__ = "cclf"')
         lines.append(f'    __tablename__ = "{tbl_name}"')
 
         seen_names: set[str] = set()

dev/scripts/generate_ccw_docs.py

@@ -17,8 +17,7 @@ from __future__ import annotations
 
 import argparse
 import re
-import textwrap
+from dataclasses import dataclass
-from dataclasses import dataclass, field
 from pathlib import Path
 
 import pdfplumber
@@ -146,7 +145,7 @@ def parse_entry(raw: str) -> Variable | None:
 
     # Parse the remaining structured fields
     # Rejoin everything from LABEL: onward
-    body = "\n".join(lines[label_idx:])
+    "\n".join(lines[label_idx:])
 
     # Extract each field by finding the label and collecting text
     # until the next label
@@ -211,9 +210,9 @@ def variable_to_py(var: Variable) -> str:
     primary_name = var.name.split("\n")[0].strip()
 
     lines = [
-        f'"""',
+        '"""',
         f"Variable: {primary_name}",
-        f"",
+        "",
     ]
 
     if var.label and var.label != "—":
@@ -289,7 +288,9 @@ def main() -> None:
         "--pdf",
         default=str(
             Path(__file__).resolve().parents[2]
-            / "dev" / "seeds" / "codebook-ffs-claims.pdf"
+            / "dev"
+            / "seeds"
+            / "codebook-ffs-claims.pdf"
         ),
         help="Path to the CCW codebook PDF",
     )

dev/scripts/generate_ccw_models.py

@@ -16,11 +16,9 @@ Defaults:
 from __future__ import annotations
 
 import argparse
-import re
 from pathlib import Path
 
 import fastexcel
-import polars as pl
 
 # ── Sheets and their slug names ──────────────────────────────────────────────
 
@@ -169,7 +167,7 @@ def generate_model(
         f"class {cls}(SQLTable):",
         f'    """CCW FFS Claims: {claim_slug.upper()} / {section}"""',
         "",
-        f'    __schema__ = "ccw"',
+        '    __schema__ = "ccw"',
         f'    __tablename__ = "{claim_slug}_{table}"',
         "",
     ]
@@ -214,7 +212,9 @@ def main() -> None:
         "--xlsx",
         default=str(
             Path(__file__).resolve().parents[2]
-            / "dev" / "seeds" / "record-layout-ffs-claims.xlsx"
+            / "dev"
+            / "seeds"
+            / "record-layout-ffs-claims.xlsx"
         ),
         help="Path to the CCW record layout Excel file",
     )

dev/scripts/generate_cms_express.py

@@ -224,9 +224,9 @@ def generate_function(table: dict) -> str:
         "@nw.narwhalify",
         f"def {tablename}({param}: FrameT) -> FrameT:",
         f'    """Clean and type-cast cms.{tablename}.',
-        f"",
+        "",
         f"    {field_count} fields.  Numeric columns auto-cast to Float64.",
-        f'    """',
+        '    """',
         f"    return auto_cast({param})",
     ]
     return "\n".join(lines)
@@ -236,18 +236,18 @@ def generate_module(domain: str, tables: list[dict]) -> str:
     """Generate a full express module for a domain group."""
     lines = [
         f'"""CMS express — {domain} domain.',
-        f"",
+        "",
         f"Auto-generated narwhals functions for {len(tables)} CMS tables.",
-        f"Each function takes the raw table and returns a typed frame",
+        "Each function takes the raw table and returns a typed frame",
-        f"with numeric columns cast to Float64.",
+        "with numeric columns cast to Float64.",
-        f'"""',
+        '"""',
-        f"",
+        "",
-        f"from __future__ import annotations",
+        "from __future__ import annotations",
-        f"",
+        "",
-        f"import narwhals as nw",
+        "import narwhals as nw",
-        f"from narwhals.typing import FrameT",
+        "from narwhals.typing import FrameT",
-        f"",
+        "",
-        f"from cms.express._helpers import auto_cast",
+        "from cms.express._helpers import auto_cast",
     ]
 
     for tbl in sorted(tables, key=lambda t: t["tablename"]):

dev/scripts/generate_expressions.py

@@ -14,7 +14,6 @@ import argparse
 import re
 from collections import defaultdict
 from pathlib import Path
-from textwrap import dedent, indent
 
 import duckdb
 
@@ -268,7 +267,7 @@ def col_expr_to_nw(expr: str) -> str:
     # date_diff('unit', a, b)
     dd_m = re.match(r"date_diff\('(\w+)',\s*(.+?),\s*(.+)\)", expr, re.IGNORECASE)
     if dd_m:
-        unit, a, b = dd_m.group(1), dd_m.group(2).strip(), dd_m.group(3).strip()
+        _unit, a, b = dd_m.group(1), dd_m.group(2).strip(), dd_m.group(3).strip()
         if alias:
             return f'({_col_ref(b)} - {_col_ref(a)}).alias("{alias}")'
         return f"{_col_ref(b)} - {_col_ref(a)}"
@@ -712,13 +711,13 @@ def generate_function(
     doc_ops = ", ".join(ops)
 
     lines: list[str] = []
-    lines.append(f"@nw.narwhalify")
+    lines.append("@nw.narwhalify")
     lines.append(f"def {func_name}({param_str}) -> FrameT:")
     lines.append(f'    """Build {schema}.{view_name}')
-    lines.append(f"")
+    lines.append("")
     lines.append(f"    Operations: {doc_ops}")
     lines.append(f"    Dependencies: {doc_deps}")
-    lines.append(f'    """')
+    lines.append('    """')
 
     if "passthrough" in ops:
         p = params[0].split(":")[0]
@@ -880,7 +879,7 @@ def _gen_select_body(lines: list[str], deps: list[tuple[str, str]], sql: str) ->
     if nw_cols:
         lines.append(f"    return {p}.select(")
         _emit_exprs(lines, nw_cols)
-        lines.append(f"    )")
+        lines.append("    )")
     else:
         lines.append(f"    return {p}")
 
@@ -902,13 +901,13 @@ def _gen_filter_body(lines: list[str], deps: list[tuple[str, str]], sql: str) ->
                 lines.append(f"    # {comment_part}")
             lines.append(f"    return {p}.filter(")
             lines.append(f"        {code_part}")
-            lines.append(f"    )")
+            lines.append("    )")
         else:
             safe = clause.replace('"', "'")[:80]
             lines.append(f"    # TODO: complex filter: {safe}")
             lines.append(f"    return {p}")
     else:
-        lines.append(f"    # WHERE clause could not be parsed")
+        lines.append("    # WHERE clause could not be parsed")
         lines.append(f"    return {p}")
 
 
@@ -994,9 +993,9 @@ def _gen_join_body(
             keys_str = ", ".join(f'"{k}"' for k in keys)
             lines.append(f"    result = result.group_by({keys_str}).agg()")
         else:
-            lines.append(f"    # TODO: complex GROUP BY")
+            lines.append("    # TODO: complex GROUP BY")
 
-    lines.append(f"    return result")
+    lines.append("    return result")
 
 
 def _gen_group_by_body(lines: list[str], deps: list[tuple[str, str]], sql: str) -> None:
@@ -1023,7 +1022,7 @@ def _gen_group_by_body(lines: list[str], deps: list[tuple[str, str]], sql: str)
                 keys.append(c_clean)
                 break
     if not keys:
-        lines.append(f"    # TODO: complex GROUP BY could not be parsed")
+        lines.append("    # TODO: complex GROUP BY could not be parsed")
         lines.append(f"    return {p}")
         return
     keys_str = ", ".join(f'"{k}"' for k in keys)
@@ -1045,7 +1044,7 @@ def _gen_group_by_body(lines: list[str], deps: list[tuple[str, str]], sql: str)
     if agg_cols:
         lines.append(f"    return {p}.group_by({keys_str}).agg(")
         _emit_exprs(lines, agg_cols)
-        lines.append(f"    )")
+        lines.append("    )")
     else:
         lines.append(f"    return {p}.group_by({keys_str}).agg()")
 
@@ -1061,20 +1060,20 @@ def _gen_window_body(lines: list[str], deps: list[tuple[str, str]], sql: str) ->
 
     lines.append(f"    return {p}.with_columns(")
     _emit_exprs(lines, nw_cols)
-    lines.append(f"    )")
+    lines.append("    )")
 
 
 def _gen_union_body(lines: list[str], deps: list[tuple[str, str]], sql: str) -> None:
     params = [ref_to_param(s, t) for s, t in deps]
     if len(params) >= 2:
-        lines.append(f"    return nw.concat([")
+        lines.append("    return nw.concat([")
         for p in params:
             lines.append(f"        {p},")
-        lines.append(f"    ])")
+        lines.append("    ])")
     elif params:
         lines.append(f"    return {params[0]}")
     else:
-        lines.append(f"    return df")
+        lines.append("    return df")
 
 
 # ── Module generation ───────────────────────────────────────────────────────
@@ -1121,9 +1120,7 @@ def main() -> None:
         default=str(_conf_path("db.aco")),
         help="Path to DuckDB file",
     )
-    parser.add_argument(
+    parser.add_argument("--out", default="../src/aco/express", help="Output directory")
-        "--out", default="../src/aco/express", help="Output directory"
-    )
     args = parser.parse_args()
 
     db_path = Path(args.db)

dev/scripts/generate_models.py

@@ -147,13 +147,12 @@ def generate_model(
             escaped = comment.replace('"', '\\"')
             if nullable:
                 field_lines.append(
-                    f'    {fname}: {py} | None = Field('
+                    f"    {fname}: {py} | None = Field("
                     f'default=None, description="{escaped}")'
                 )
             else:
                 field_lines.append(
-                    f'    {fname}: {py} = Field('
+                    f'    {fname}: {py} = Field(description="{escaped}")'
-                    f'description="{escaped}")'
                 )
         else:
             if nullable:
@@ -202,14 +201,13 @@ def generate_schema_module(
     return f"{header}\n\n\n{body}\n"
 
 
-
-
 # ── Main ────────────────────────────────────────────────────────────────────
 
 
 def main() -> None:
     parser = argparse.ArgumentParser(description="Generate Pydantic models from DuckDB")
-    from conf import cfg, path as _conf_path
+    from conf import cfg
+    from conf import path as _conf_path
 
     parser.add_argument(
         "--db",

dev/scripts/generate_quality_measure_docs.py

@@ -58,7 +58,6 @@ Design notes
 
 from __future__ import annotations
 
-import argparse
 import re
 import textwrap
 import zipfile
@@ -68,7 +67,6 @@ from typing import NamedTuple
 import pdfplumber
 
 # ── Path constants ────────────────────────────────────────────────────────────
-
 from conf import ROOT as _ROOT
 from conf import path as _conf_path
 
@@ -176,8 +174,9 @@ def _extract_from_zip(
     return None
 
 
-def _resolve_pdf(pdf_basename: str, zip_basename: str | None,
+def _resolve_pdf(
-                 zotero_root: Path, work_dir: Path) -> Path | None:
+    pdf_basename: str, zip_basename: str | None, zotero_root: Path, work_dir: Path
+) -> Path | None:
     """Return path to a MIF PDF, extracting from zip if necessary."""
     direct = _find_in_zotero(pdf_basename, zotero_root)
     if direct:
@@ -187,8 +186,12 @@ def _resolve_pdf(pdf_basename: str, zip_basename: str | None,
     return None
 
 
-def _resolve_xlsx(xlsx_basename: str | None, zip_basename: str | None,
+def _resolve_xlsx(
-                  zotero_root: Path, work_dir: Path) -> Path | None:
+    xlsx_basename: str | None,
+    zip_basename: str | None,
+    zotero_root: Path,
+    work_dir: Path,
+) -> Path | None:
     """Return path to a value set Excel file, extracting from zip if needed."""
     if xlsx_basename is None:
         return None
@@ -329,7 +332,9 @@ def _read_sheet_summaries(xlsx_path: Path) -> dict[str, SheetSummary]:
         for row in rows[:3]:
             non_none = [str(c).strip() for c in row if c is not None]
             if len(non_none) >= 2:
-                header = [str(c).strip().replace("\n", " ") for c in row if c is not None]
+                header = [
+                    str(c).strip().replace("\n", " ") for c in row if c is not None
+                ]
                 break
         summaries[sheet_name] = SheetSummary(sheet_name, max(0, row_count), header)
     wb.close()
@@ -407,13 +412,13 @@ def build_uamcc_passages(
     paa4_info = _vs_info("UAMCC PAA4")
     cohort_info = _vs_info("UAMCC Cohort")
     excl_info = _vs_info("UAMCC Exclusions")
-    ccs_cm_info = _vs_info("UAMCC CCS-ICD10CM")
+    _vs_info("UAMCC CCS-ICD10CM")
-    ccs_pcs_info = _vs_info("UAMCC CCS-ICD10PCS")
+    _vs_info("UAMCC CCS-ICD10PCS")
 
     cite_pp = _cite(pdf_name, "§3.8", denom_page)
-    cite_num = _cite(pdf_name, "§3.6–3.7", num_page)
+    _cite(pdf_name, "§3.6–3.7", num_page)
     cite_excl = _cite(pdf_name, "§3.10", denom_excl_page)
-    cite_risk = _cite(pdf_name, "§3.12", risk_page)
+    _cite(pdf_name, "§3.12", risk_page)
     cite_paa = _cite(pdf_name, "§3.7 PAA v4.0", num_d_page)
 
     passages: dict[str, str] = {}
@@ -423,13 +428,13 @@ def build_uamcc_passages(
         f"Return the UAMCC performance period anchor row.\n\n"
         f"Source: {_cite(pdf_name, '§1 Effective Date + §2.2', 1)}\n\n"
         f"UAMCC §2.2 Measure Description:\n"
-        f"  \"This outcome measure is calculated using 12 consecutive months\n"
+        f'  "This outcome measure is calculated using 12 consecutive months\n'
         f"  of Medicare fee-for-service (FFS) claims data.  The measure is a\n"
         f"  risk-standardized acute admission rate (RSAAR) that adjusts for\n"
         f"  age, clinical comorbidities, and other clinical and frailty risk\n"
         f"  factors present at the start of the 12-month measurement period,\n"
         f"  as well as social risk factors.  Lower RSAARs indicate better\n"
-        f"  performance.\"\n\n"
+        f'  performance."\n\n'
         f"NQF ID: #2888 (ACO RSAAR Quality Measure)\n"
         f"Measurement duration: 12 consecutive months (Jan 1 – Dec 31).\n"
         f"Performance Year: {py_version}.\n\n"
@@ -443,10 +448,10 @@ def build_uamcc_passages(
         f"Identify each beneficiary's qualifying chronic condition groups.\n\n"
         f"Source: {_cite(pdf_name, '§3.9', denom_d_page)}\n\n"
         f"UAMCC §3.9 Denominator Details:\n"
-        f"  \"The cohort is Medicare FFS beneficiaries 66 years of age and\n"
+        f'  "The cohort is Medicare FFS beneficiaries 66 years of age and\n'
         f"  older assigned to the REACH ACO during the measurement period\n"
         f"  with diagnoses that fall into two or more of nine chronic disease\n"
-        f"  groups.\"\n\n"
+        f'  groups."\n\n'
         f"Nine chronic disease groups (MIF §3.9, pp.7–8):\n"
         f"  1. Acute myocardial infarction (AMI)\n"
         f"  2. Alzheimer's disease and related disorders or senile dementia\n"
@@ -471,7 +476,7 @@ def build_uamcc_passages(
         f"Build the UAMCC denominator: MCC-eligible beneficiaries aged ≥66.\n\n"
         f"Source: {cite_pp}\n\n"
         f"UAMCC §3.8 Denominator Statement:\n"
-        f"  \"{denom_stmt_trimmed[:400]}\"\n\n"
+        f'  "{denom_stmt_trimmed[:400]}"\n\n'
         f"Inclusion criteria (MIF §3.9):\n"
         f"  1. Age ≥66 at the first day of the measurement period\n"
         f"  2. Two or more distinct MCC groups identified in the lookback year\n"
@@ -501,13 +506,15 @@ def build_uamcc_passages(
     )
 
     # ── Planned admission (PAA) ───────────────────────────────────────
-    paa_snippet = ""
     if num_detail:
         # Find the PAA description paragraph
-        m = re.search(r"planned admission algorithm.+?(?=\n\n|\Z)", num_detail,
+        m = re.search(
-                      re.DOTALL | re.IGNORECASE)
+            r"planned admission algorithm.+?(?=\n\n|\Z)",
+            num_detail,
+            re.DOTALL | re.IGNORECASE,
+        )
         if m:
-            paa_snippet = m.group(0)[:600]
+            m.group(0)[:600]
     passages["uamcc_int_planned_admission"] = (
         f"Apply PAA v4.0 {py_version} to classify inpatient admissions as planned.\n\n"
         f"Source: {cite_paa}\n\n"
@@ -516,7 +523,7 @@ def build_uamcc_passages(
         f"  Readmission Algorithm Version 4.0, which CMS originally created\n"
         f"  to identify planned readmissions for the hospital-wide readmission\n"
         f"  measure.  In brief, the algorithm uses a flowchart and four tables\n"
-        f"  of procedure and/or discharge diagnosis categories.\"\n\n"
+        f'  of procedure and/or discharge diagnosis categories."\n\n'
         f"PAA Rules (first match wins):\n"
         f"  Rule 1 — Any procedure in an always-planned CCS category (PAA1).\n"
         f"  Rule 2 — Principal diagnosis in an always-planned CCS diagnosis\n"
@@ -562,14 +569,14 @@ def build_uamcc_passages(
         f"Calculate at-risk person-time for each UAMCC-eligible beneficiary.\n\n"
         f"Source: {_cite(pdf_name, '§3.11', denom_d_page)}\n\n"
         f"UAMCC §3.11 Denominator Exclusion Details:\n"
-        f"  \"Persons are considered at risk for admission if they are alive,\n"
+        f'  "Persons are considered at risk for admission if they are alive,\n'
         f"  enrolled in Medicare FFS, and not admitted to an acute care\n"
         f"  hospital.  In addition to time spent in the hospital, excluded\n"
         f"  from at-risk time are:\n"
         f"    (1) time spent in an SNF or acute rehabilitation facility;\n"
         f"    (2) time within 10 days following discharge from a hospital,\n"
         f"        SNF, or acute rehabilitation facility;\n"
-        f"    (3) time after entering hospice care.\"\n\n"
+        f'    (3) time after entering hospice care."\n\n'
         f"Person-years = at_risk_days / 365.25\n\n"
         f"Performance Year: {py_version}."
     )

dev/scripts/generate_reach_docs.py

@@ -19,7 +19,6 @@ Source: dev/PY2023 ACO REACH Reporting and Data Sharing Overview_v20232203.pdf
 from __future__ import annotations
 
 import re
-import textwrap
 from pathlib import Path
 
 import pdfplumber
@@ -29,10 +28,7 @@ import pdfplumber
 _ROOT = Path(__file__).resolve().parents[2]
 _SEEDS = _ROOT / "dev" / "seeds"
 
-PDF_PATH = (
+PDF_PATH = _SEEDS / "PY2023 ACO REACH Reporting and Data Sharing Overview_v20232203.pdf"
-    _SEEDS
-    / "PY2023 ACO REACH Reporting and Data Sharing Overview_v20232203.pdf"
-)
 ALIGNMENT_PATH = _ROOT / "src" / "aco" / "table" / "reach_alignment.py"
 FINANCE_PATH = _ROOT / "src" / "aco" / "table" / "reach_finance.py"
 QUALITY_PATH = _ROOT / "src" / "aco" / "table" / "reach_quality.py"

dev/scripts/generate_reach_models.py

@@ -21,7 +21,6 @@ Source: dev/PY2023 ACO REACH Reporting and Data Sharing Overview_v20232203.pdf
 
 from __future__ import annotations
 
-import re
 from pathlib import Path
 
 # Define all table specifications based on extracted data dictionary

dev/scripts/generate_reach_participants.py

@@ -336,7 +336,9 @@ def main():
     """Generate REACH participants table model and rex parser."""
     project_root = Path(__file__).resolve().parents[2]
     xlsx_path = (
-        project_root / "dev" / "seeds"
+        project_root
+        / "dev"
+        / "seeds"
         / "ACO_REACH_bulk_upload_participants 5-19 (1).xlsx"
     )
 

dev/scripts/generate_zot_tables.py

@@ -79,15 +79,12 @@ def sanitize_field(name: str) -> str:
 def get_tables(con: sqlite3.Connection) -> list[str]:
     """Return all user tables, sorted alphabetically."""
     rows = con.execute(
-        "SELECT name FROM sqlite_master WHERE type='table' "
+        "SELECT name FROM sqlite_master WHERE type='table' ORDER BY name"
-        "ORDER BY name"
     ).fetchall()
     return [r[0] for r in rows]
 
 
-def get_columns(
+def get_columns(con: sqlite3.Connection, table: str) -> list[tuple[str, str, bool]]:
-    con: sqlite3.Connection, table: str
-) -> list[tuple[str, str, bool]]:
     """Return [(col_name, sqlite_type, nullable), ...].
 
     SQLite PRAGMA table_info returns:

dev/scripts/migrate_zotero.py

@@ -63,9 +63,7 @@ def _get_item_tags(zcon: sqlite3.Connection, item_id: int) -> list[str]:
     return [r["name"] for r in rows]
 
 
-def _get_item_collections(
+def _get_item_collections(zcon: sqlite3.Connection, item_id: int) -> list[str]:
-    zcon: sqlite3.Connection, item_id: int
-) -> list[str]:
     """Read collection keys for a Zotero item."""
     rows = zcon.execute(
         """SELECT c.key FROM collectionItems ci
@@ -76,9 +74,7 @@ def _get_item_collections(
     return [r["key"] for r in rows]
 
 
-def _get_item_creators(
+def _get_item_creators(zcon: sqlite3.Connection, item_id: int) -> list[dict]:
-    zcon: sqlite3.Connection, item_id: int
-) -> list[dict]:
     """Read creators for a Zotero item."""
     rows = zcon.execute(
         """SELECT c.firstName, c.lastName, ct.creatorType,
@@ -101,9 +97,7 @@ def _get_item_creators(
     ]
 
 
-def _classify_item(
+def _classify_item(zotero_type: str, fields: dict) -> str:
-    zotero_type: str, fields: dict
-) -> str:
     """Map Zotero itemType + fields to bib item_type."""
     if zotero_type == "statute":
         code = fields.get("code", "")
@@ -134,14 +128,16 @@ def _build_extra_json(item_type: str, fields: dict) -> str:
                 rule_type = part[6:]
             elif part.startswith("Effective: "):
                 eff_date = part[11:]
-        return json.dumps({
+        return json.dumps(
+            {
                 "fr_volume": fields.get("codeNumber", ""),
                 "fr_page": fields.get("pages", ""),
                 "document_number": doc_num,
                 "cms_id": fields.get("session", ""),
                 "rule_type": rule_type,
                 "effective_date": eff_date,
-        })
+            }
+        )
 
     if item_type == "regulation":
         history = fields.get("history", "")
@@ -152,13 +148,15 @@ def _build_extra_json(item_type: str, fields: dict) -> str:
                 part = segment[5:]
             elif segment.startswith("Authority: "):
                 authority = segment[11:]
-        return json.dumps({
+        return json.dumps(
+            {
                 "cfr_title": fields.get("codeNumber", ""),
                 "cfr_part": part,
                 "cfr_section": fields.get("section", ""),
                 "authority": authority,
                 "effective_date": fields.get("dateEnacted", ""),
-        })
+            }
+        )
 
     if item_type == "manual":
         extra = fields.get("extra", "")
@@ -169,33 +167,37 @@ def _build_extra_json(item_type: str, fields: dict) -> str:
         chapter = fields.get("seriesNumber", "")
         if chapter.startswith("Chapter "):
             chapter = chapter[8:]
-        return json.dumps({
+        return json.dumps(
+            {
                 "manual_name": fields.get("seriesTitle", ""),
                 "pub_number": fields.get("reportNumber", ""),
                 "chapter": chapter,
                 "transmittal": transmittal,
-        })
+            }
+        )
 
     if item_type == "download":
         extra = fields.get("extra", "")
         file_urls: list[str] = []
         for line in extra.split("\n"):
             if line.startswith("Files: "):
-                file_urls = [
+                file_urls = [u.strip() for u in line[7:].split(";") if u.strip()]
-                    u.strip() for u in line[7:].split(";") if u.strip()
+        return json.dumps(
-                ]
+            {
-        return json.dumps({
                 "page_type": "",
                 "file_urls": file_urls,
                 "year": None,
                 "quarter": "",
                 "website_title": fields.get("websiteTitle", ""),
-        })
+            }
+        )
 
     if item_type == "source":
-        return json.dumps({
+        return json.dumps(
+            {
                 "doc_type": fields.get("type", ""),
-        })
+            }
+        )
 
     return "{}"
 
@@ -255,8 +257,7 @@ def migrate(src: str, dst: str) -> dict[str, int]:
                     parent_id = row["id"]
 
         bcon.execute(
-            "INSERT OR IGNORE INTO collections (key, name, parent_id) "
+            "INSERT OR IGNORE INTO collections (key, name, parent_id) VALUES (?, ?, ?)",
-            "VALUES (?, ?, ?)",
             (zc["key"], zc["collectionName"], parent_id),
         )
         counts["collections"] += 1
@@ -322,8 +323,7 @@ def migrate(src: str, dst: str) -> dict[str, int]:
         for tag_name in ztags:
             tag_id = store._ensure_tag(tag_name)
             bcon.execute(
-                "INSERT OR IGNORE INTO item_tags (item_id, tag_id) "
+                "INSERT OR IGNORE INTO item_tags (item_id, tag_id) VALUES (?, ?)",
-                "VALUES (?, ?)",
                 (bib_id, tag_id),
             )
             counts["tags"] += 1
@@ -346,16 +346,14 @@ def migrate(src: str, dst: str) -> dict[str, int]:
         for cr in creators:
             # Find or create creator
             crow = bcon.execute(
-                "SELECT id FROM creators "
+                "SELECT id FROM creators WHERE first_name = ? AND last_name = ?",
-                "WHERE first_name = ? AND last_name = ?",
                 (cr["first_name"], cr["last_name"]),
             ).fetchone()
             if crow:
                 creator_id = crow["id"]
             else:
                 cur = bcon.execute(
-                    "INSERT INTO creators (first_name, last_name) "
+                    "INSERT INTO creators (first_name, last_name) VALUES (?, ?)",
-                    "VALUES (?, ?)",
                     (cr["first_name"], cr["last_name"]),
                 )
                 creator_id = cur.lastrowid
@@ -462,9 +460,7 @@ def migrate(src: str, dst: str) -> dict[str, int]:
 
 
 def main() -> None:
-    parser = argparse.ArgumentParser(
+    parser = argparse.ArgumentParser(description="Migrate Zotero SQLite to bib SQLite")
-        description="Migrate Zotero SQLite to bib SQLite"
-    )
     from conf import path as _conf_path
 
     parser.add_argument(

dev/scripts/populate_quality_measure_value_sets.py

@@ -60,7 +60,6 @@ from typing import Any
 import polars as pl
 
 # ── Path constants ────────────────────────────────────────────────────────────
-
 from conf import ROOT as _ROOT
 from conf import path as _conf_path
 

dev/scripts/register_seeds.py

@@ -319,16 +319,12 @@ def _ensure_value(con: sqlite3.Connection, value: str) -> int:
     ).fetchone()
     if row:
         return row[0]
-    cur = con.execute(
+    cur = con.execute("INSERT INTO itemDataValues (value) VALUES (?)", (value,))
-        "INSERT INTO itemDataValues (value) VALUES (?)", (value,)
-    )
     return cur.lastrowid
 
 
 def _ensure_tag(con: sqlite3.Connection, name: str) -> int:
-    row = con.execute(
+    row = con.execute("SELECT tagID FROM tags WHERE name = ?", (name,)).fetchone()
-        "SELECT tagID FROM tags WHERE name = ?", (name,)
-    ).fetchone()
     if row:
         return row[0]
     cur = con.execute("INSERT INTO tags (name) VALUES (?)", (name,))
@@ -342,8 +338,7 @@ def _set_zotero_field(
         return
     value_id = _ensure_value(con, value)
     con.execute(
-        "INSERT OR REPLACE INTO itemData (itemID, fieldID, valueID) "
+        "INSERT OR REPLACE INTO itemData (itemID, fieldID, valueID) VALUES (?, ?, ?)",
-        "VALUES (?, ?, ?)",
         (item_id, field_id, value_id),
     )
 
@@ -392,8 +387,7 @@ def tag_existing_zotero(
     for tag_name in all_tags:
         tag_id = _ensure_tag(con, tag_name)
         con.execute(
-            "INSERT OR IGNORE INTO itemTags (itemID, tagID, type) "
+            "INSERT OR IGNORE INTO itemTags (itemID, tagID, type) VALUES (?, ?, 0)",
-            "VALUES (?, ?, 0)",
             (parent_id, tag_id),
         )
     return True
@@ -416,9 +410,9 @@ def register_in_zotero(
         return
 
     now = _now_iso()
-    next_id = con.execute(
+    next_id = con.execute("SELECT COALESCE(MAX(itemID), 0) + 1 FROM items").fetchone()[
-        "SELECT COALESCE(MAX(itemID), 0) + 1 FROM items"
+        0
-    ).fetchone()[0]
+    ]
     parent_key = _zotero_key()
 
     # Create parent webpage item
@@ -434,9 +428,7 @@ def register_in_zotero(
     _set_zotero_field(con, next_id, ZOTERO_FIELD_URL, spec.url)
     _set_zotero_field(con, next_id, ZOTERO_FIELD_DATE, now[:10])
     _set_zotero_field(con, next_id, ZOTERO_FIELD_ACCESS_DATE, now)
-    _set_zotero_field(
+    _set_zotero_field(con, next_id, ZOTERO_FIELD_WEBSITE_TYPE, "Government Data Portal")
-        con, next_id, ZOTERO_FIELD_WEBSITE_TYPE, "Government Data Portal"
-    )
     _set_zotero_field(
         con,
         next_id,
@@ -449,8 +441,7 @@ def register_in_zotero(
     for tag_name in all_tags:
         tag_id = _ensure_tag(con, tag_name)
         con.execute(
-            "INSERT OR IGNORE INTO itemTags (itemID, tagID, type) "
+            "INSERT OR IGNORE INTO itemTags (itemID, tagID, type) VALUES (?, ?, 0)",
-            "VALUES (?, ?, 0)",
             (next_id, tag_id),
         )
 
@@ -464,13 +455,9 @@ def register_in_zotero(
 
         # Copy to Zotero storage
         storage_dir = ZOTERO_STORAGE / att_key
-        subprocess.run(
+        subprocess.run(["sudo", "mkdir", "-p", str(storage_dir)], check=True)
-            ["sudo", "mkdir", "-p", str(storage_dir)], check=True
-        )
         dest = storage_dir / seed_path.name
-        subprocess.run(
+        subprocess.run(["sudo", "cp", str(seed_path), str(dest)], check=True)
-            ["sudo", "cp", str(seed_path), str(dest)], check=True
-        )
         subprocess.run(
             ["sudo", "chown", "-R", "100999:100999", str(storage_dir)],
             check=True,
@@ -496,8 +483,7 @@ def register_in_zotero(
         )
         title_val = _ensure_value(con, seed_path.name)
         con.execute(
-            "INSERT INTO itemData (itemID, fieldID, valueID) "
+            "INSERT INTO itemData (itemID, fieldID, valueID) VALUES (?, ?, ?)",
-            "VALUES (?, ?, ?)",
             (att_id, ZOTERO_FIELD_TITLE, title_val),
         )
 
@@ -567,7 +553,7 @@ def pull_from_zotero(*, dry_run: bool = False) -> int:
         zpath = row[0]  # "storage:filename"
         if not zpath.startswith("storage:"):
             continue
-        filename = zpath[len("storage:"):]
+        filename = zpath[len("storage:") :]
 
         dest = SEEDS_DIR / filename
         if dest.exists():

dev/scripts/setup_unity_catalog.py

@@ -97,11 +97,11 @@ def main():
                 print(f"    ... and {len(tables) - 3} more tables")
 
         print("\n" + "=" * 70)
-        print(f"\nTo create these in Unity Catalog, run without --show-schemas flag")
+        print("\nTo create these in Unity Catalog, run without --show-schemas flag")
         return
 
     # Create Unity client
-    print(f"Connecting to Unity Catalog...")
+    print("Connecting to Unity Catalog...")
     print(f"  Workspace ID: {args.workspace_id}")
     print(f"  Catalog:      {args.catalog}")
     print()
@@ -114,7 +114,7 @@ def main():
     # Test connection
     try:
         catalogs = client.list_catalogs()
-        print(f"✓ Connected to Unity Catalog")
+        print("✓ Connected to Unity Catalog")
         print(f"  Found {len(catalogs)} existing catalogs:")
         for cat in catalogs:
             print(f"    - {cat.name}")
@@ -130,7 +130,7 @@ def main():
         print("=" * 70)
         print()
 
-    print(f"Setting up catalog structure...")
+    print("Setting up catalog structure...")
     print()
 
     report = setup_catalog_from_schemas(

dev/scripts/test_network_isolation.sh

@@ -20,11 +20,11 @@ fi
 
 # Image definitions — matches stack.toml [images]
 declare -A DOCKERFILES=(
-    [api]="api/Dockerfile"
+    [api]="infra/images/api.Dockerfile"
-    [notebooks]="notebooks/Dockerfile"
+    [notebooks]="infra/images/notebooks.Dockerfile"
-    [docs]="docs/Dockerfile"
+    [docs]="infra/images/docs.Dockerfile"
-    [zotero]="zotero/Dockerfile"
+    [zotero]="infra/images/zotero.Dockerfile"
-    [mc]="rustfs/Dockerfile.mc"
+    [mc]="infra/images/mc.Dockerfile"
 )
 
 declare -A CONTEXTS=(
@@ -32,7 +32,7 @@ declare -A CONTEXTS=(
     [notebooks]="notebooks/"
     [docs]="."
     [zotero]="zotero/"
-    [mc]="rustfs/"
+    [mc]="infra/rustfs/"
 )
 
 # Select images to test

dev/scripts/unity_catalog_example.py

@@ -23,7 +23,6 @@ import os
 
 from aco.lake import IcebergContext, UnityClient
 from aco.lake.catalog import Catalog
-from aco.lake.engine import execute
 
 
 def example_unity_client_basics():
@@ -185,7 +184,7 @@ def example_iceberg_context():
         },
     )
 
-    print(f"✓ IcebergContext configured")
+    print("✓ IcebergContext configured")
     print(f"  Catalog URI: {ctx.catalog_uri}")
     print(f"  Warehouse: {ctx.warehouse}")
     print()
@@ -222,7 +221,7 @@ def example_pipeline_execution():
         }
     )
 
-    ctx = IcebergContext(
+    IcebergContext(
         catalog_uri=f"https://dbc-{workspace_id}.cloud.databricks.com/api/2.1/unity-catalog/iceberg",
         warehouse="aco_dev",
         catalog=catalog,

docs/src/css/custom.css

@@ -1,4 +1,4 @@
-/* LOCH — deep-navy design system — matches styles/inject.css */
+/* LOCH — deep-navy design system — matches assets/css/inject.css */
 
 :root {
   --ifm-color-primary: #4488dd;

src/aco/dag.py

@@ -17,7 +17,7 @@ Usage::
 CLI::
 
     uv run python -m aco.dag
-    uv run python -m aco.dag -p readmissions --html dag.html
+    uv run python -m aco.dag -p readmissions --html assets/dag.html
     uv run python -m aco.dag --dot dag.dot
     uv run python -m aco.dag -p pharmacy --mermaid
 """