Add repository hygiene checks

.github/workflows/tests.yml

@@ -7,6 +7,24 @@ on:
     branches: [main]
 
 jobs:
+  lint:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v5
+
+      - uses: actions/setup-python@v6
+        with:
+          python-version: "3.11"
+
+      - name: Install lint dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -e ".[dev]"
+
+      - name: Run Ruff
+        run: ruff check wavemind tests benchmarks examples
+
   pytest:
     runs-on: ubuntu-latest
     strategy:

benchmarks/agent_memory_benchmark.py

@@ -15,7 +15,7 @@
     sys.path.insert(0, str(PROJECT_ROOT))
 
 from wavemind import WaveMind
-from wavemind.encoders import HashingTextEncoder, create_text_encoder
+from wavemind.encoders import create_text_encoder
 
 
 @dataclass(frozen=True)

benchmarks/benchmark_registry.py

@@ -653,8 +653,6 @@ def _implemented_entries(root: Path) -> list[dict[str, Any]]:
     postgres_pitr_payload = _load_json(root / "benchmarks" / "postgres_pitr_plan.json")
     memory_competitor_payload = _load_json(root / "benchmarks" / "memory_competitor_results.json")
     answer_payload = _load_json(root / "benchmarks" / "longmemeval_answer_extractive_20_results.json")
-    vectordbbench_payload = _load_json(root / "benchmarks" / "vectordbbench_dataset_manifest.json")
-
     agent_results = _engine_results(agent_payload)
     agent_coherence_results = _engine_results(agent_coherence_payload)
     dynamic_results = _engine_results(dynamic_payload)
@@ -722,19 +720,6 @@ def _implemented_entries(root: Path) -> list[dict[str, Any]]:
     )
     postgres_pitr_validation = postgres_pitr_profile.get("validation", {})
     memory_competitor_results = _engine_results(memory_competitor_payload)
-    vectordbbench_summary = (
-        {
-            "WaveMind custom dataset export": {
-                "status": vectordbbench_payload.get("status"),
-                "vectors": vectordbbench_payload.get("dataset", {}).get("vectors"),
-                "queries": vectordbbench_payload.get("dataset", {}).get("queries"),
-                "dim": vectordbbench_payload.get("dataset", {}).get("dim"),
-                "top_k": vectordbbench_payload.get("dataset", {}).get("top_k"),
-            }
-        }
-        if vectordbbench_payload
-        else {}
-    )
     answer_qwen05_payload = _load_json(root / "benchmarks" / "longmemeval_answer_qwen25_0_5b_50_results.json")
     answer_qwen15_payload = _load_json(root / "benchmarks" / "longmemeval_answer_qwen25_1_5b_50_results.json")
     answer_results = {

benchmarks/kubernetes_serverless_lifecycle_smoke.py

@@ -5,7 +5,6 @@
 import json
 import math
 import os
-import statistics
 import subprocess
 import tempfile
 import time

benchmarks/memory_competitor_benchmark.py

@@ -12,7 +12,7 @@
 import time
 import uuid
 from collections import defaultdict
-from dataclasses import asdict, dataclass
+from dataclasses import dataclass
 from datetime import datetime, timedelta, timezone
 from pathlib import Path
 from typing import Any, Callable, Iterable
@@ -446,23 +446,32 @@ def run_zep(
                 from zep_cloud import Message
             except Exception as exc:
                 return skipped_result("Zep", f"Import zep-cloud failed: {exc}")
-            client_factory = lambda: Zep(base_url=api_url, api_key=api_key, timeout=timeout)
+            def create_zep_cloud_client() -> Any:
+                return Zep(base_url=api_url, api_key=api_key, timeout=timeout)
+
+            client_factory = create_zep_cloud_client
             message_factory = Message
         elif _module_available("zep_python"):
             try:
                 from zep_python.client import Zep
                 from zep_python.types.message import Message
             except Exception as exc:
                 return skipped_result("Zep", f"Import zep-python failed: {exc}")
-            client_factory = lambda: Zep(base_url=api_url, api_key=api_key, timeout=timeout)
+            def create_zep_python_client() -> Any:
+                return Zep(base_url=api_url, api_key=api_key, timeout=timeout)
+
+            client_factory = create_zep_python_client
             message_factory = Message
         else:
             return skipped_result(
                 "Zep",
                 'Install a Zep SDK to run this adapter profile: pip install "zep-cloud" or pip install "zep-python"',
             )
     if message_factory is None:
-        message_factory = lambda **kwargs: kwargs
+        def create_message(**kwargs: Any) -> dict[str, Any]:
+            return kwargs
+
+        message_factory = create_message
 
     client = client_factory()
     if hasattr(client, "memory"):

benchmarks/scale_readiness_benchmark.py

@@ -67,7 +67,6 @@
     operator_status,
     query_with_cache,
     query_with_vector_cache,
-    remember_payload,
     run_control_plane_consensus_profile,
     serverless_sample_bundle,
     sync_namespace_delta,
@@ -1798,8 +1797,6 @@ def run_api_cache_mutation_profile() -> dict[str, object]:
                 second_query.raise_for_status()
                 latencies.append((time.perf_counter() - started) * 1000.0)
                 second_results = second_query.json()["results"]
-                cache_keys_after_second_query = len(client.items)
-
                 feedback_response = api.post(
                     "/feedback",
                     json={

examples/agent_with_memory.py

@@ -3,7 +3,6 @@
 import argparse
 import json
 import os
-import re
 import sys
 import urllib.request
 from pathlib import Path

pyproject.toml

@@ -72,7 +72,9 @@ production = [
 dev = [
   "pytest>=8",
   "httpx>=0.27",
+  "httpx2>=2",
   "langchain-classic>=1.0",
+  "ruff>=0.12",
 ]
 
 [project.scripts]
@@ -85,3 +87,10 @@ Repository = "https://github.com/CaspianG/wavemind"
 [tool.setuptools.packages.find]
 where = ["."]
 include = ["wavemind*"]
+
+[tool.ruff]
+target-version = "py310"
+
+[tool.ruff.lint.per-file-ignores]
+"benchmarks/*.py" = ["E402"]
+"examples/*.py" = ["E402"]

wavemind/__init__.py

@@ -431,7 +431,6 @@
     "render_active_active_admission_markdown",
     "render_scale_gap_markdown",
     "render_serverless_admission_markdown",
-    "render_active_active_admission_markdown",
     "render_production_admission_markdown",
     "render_memory_os_canary_markdown",
     "render_memory_os_policy_evolution_markdown",
@@ -454,6 +453,7 @@
     "validate_precomputed_cross_modal_contract",
     "validate_external_multimodal_evidence",
     "validate_postgres_pitr_commands",
+    "video_payload",
     "write_memory_os_policy_evolution_artifacts",
     "write_production_evidence_env_artifacts",
 ]

wavemind/cli.py

@@ -60,7 +60,6 @@
     run_memory_os_canary,
 )
 from .memory_os_evolution import (
-    render_memory_os_policy_evolution_markdown,
     run_memory_os_policy_evolution,
     write_memory_os_policy_evolution_artifacts,
 )
@@ -102,7 +101,6 @@
 )
 from .production_evidence_env import (
     build_production_evidence_env_contract,
-    render_production_evidence_env_markdown,
     write_production_evidence_env_artifacts,
 )
 from .production_evidence_ingest import (

wavemind/cloud_run_evidence.py

@@ -75,11 +75,11 @@ def _annotation(service: Mapping[str, Any], *names: str) -> str | None:
         service.get("spec", {}).get("template", {}).get("metadata", {}).get("annotations", {}),
         service.get("template", {}).get("annotations", {}),
     ]
-    for annotations in candidates:
-        if not isinstance(annotations, Mapping):
+    for metadata_annotations in candidates:
+        if not isinstance(metadata_annotations, Mapping):
             continue
         for name in names:
-            value = annotations.get(name)
+            value = metadata_annotations.get(name)
             if value is not None and str(value).strip():
                 return str(value).strip()
     return None

wavemind/cluster.py

@@ -144,7 +144,6 @@ def quorum_report(self) -> dict[str, object]:
 
     def placement_health_report(self) -> dict[str, object]:
         namespace_count = len(self.placements)
-        zone_by_node = {node.id: node.zone for node in self.nodes}
         failure_domain_by_node = {
             node.id: node.zone or node.id
             for node in self.nodes

wavemind/production_evidence.py

@@ -1925,11 +1925,6 @@ def build_production_evidence_dispatch_plan(
     root = Path(root)
     strict = evaluate_production_evidence(root)
     preflight = evaluate_production_evidence_preflight(root, env=env)
-    strict_by_id = {
-        str(row.get("id")): row
-        for row in strict.get("requirements", [])
-        if isinstance(row, dict)
-    }
     preflight_by_id = {
         str(row.get("id")): row
         for row in preflight.get("checks", [])

wavemind/remote_lab.py

@@ -3,7 +3,6 @@
 import hashlib
 import ipaddress
 import json
-import os
 import re
 import socket
 import subprocess
@@ -12,7 +11,7 @@
 import urllib.request
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Any, Callable, Mapping, Sequence
+from typing import Any, Callable, Mapping
 from urllib.parse import quote, urlparse
 
 from .active_active_drill import run_active_active_drill