feat: expand ruff lint rules with tier 1+2 quality rulesets

pyproject.toml

@@ -67,7 +67,40 @@ line-length = 100
 src = ["src", "tests"]
 
 [tool.ruff.lint]
-select = ["E", "F", "I", "W"]
+select = [
+    # Tier 1 — high value, very safe
+    "E",    # pycodestyle errors
+    "F",    # pyflakes
+    "I",    # isort
+    "W",    # pycodestyle warnings
+    "UP",   # pyupgrade — modern Python syntax
+    "B",    # bugbear — common bug patterns
+    "SIM",  # simplify — reduce complexity
+    "C4",   # flake8-comprehensions
+    "RUF",  # Ruff-specific rules
+    # Tier 2 — strong value, minor tuning
+    "PIE",  # misc cleanup
+    "RET",  # return simplification
+    "PERF", # performance anti-patterns
+    "PT",   # pytest style
+    # "C90",  # mccabe complexity — enable after refactoring complex functions
+    "FURB", # modernization
+    "FLY",  # f-string conversion
+]
+ignore = [
+    "E501",   # line length (formatter handles this)
+    "SIM108", # ternary operator (opinionated)
+    "SIM117", # nested with statements (clearer in test mocking patterns)
+    "PT018",  # composite assertions (splitting weakens error messages)
+    "PT019",  # fixture without value (usefixtures less readable)
+    "PT017",  # assert in except (valid test pattern)
+]
+
+[tool.ruff.lint.mccabe]
+max-complexity = 10
+
+[tool.ruff.lint.per-file-ignores]
+"src/mlx_stack/_version.py" = ["RUF022"]  # auto-generated by hatch-vcs
 
 [tool.pyright]
 pythonVersion = "3.13"

src/mlx_stack/cli/bench.py

@@ -168,23 +168,16 @@ def _display_results(result: BenchmarkResult_, out: Console, save: bool = False)
         out.print(Text("Tool Calling", style="bold cyan"))
         tc = result.tool_call_result
         if tc.success:
-            out.print(
-                f"  [green]✓ Valid tool call[/green] — "
-                f"round-trip: {tc.round_trip_time:.2f}s"
-            )
+            out.print(f"  [green]✓ Valid tool call[/green] — round-trip: {tc.round_trip_time:.2f}s")
         else:
-            out.print(
-                f"  [red]✗ Tool call failed[/red] — {tc.error}"
-            )
+            out.print(f"  [red]✗ Tool call failed[/red] — {tc.error}")
         out.print()
     elif not result.tool_call_result:
         # Check if model supports tool calling from entry
         if not result.catalog_data_available:
             pass  # Skip silently if no catalog data
         else:
-            out.print(
-                "[dim]Tool calling: skipped (model does not support tool calling)[/dim]"
-            )
+            out.print("[dim]Tool calling: skipped (model does not support tool calling)[/dim]")
             out.print()
 
     # Iteration details
@@ -212,6 +205,8 @@ def _display_results(result: BenchmarkResult_, out: Console, save: bool = False)
 
     # Save confirmation
     if save:
-        out.print("[green]✓ Results saved.[/green] "
-                  "These will be used by 'recommend' and 'init' for scoring.")
+        out.print(
+            "[green]✓ Results saved.[/green] "
+            "These will be used by 'recommend' and 'init' for scoring."
+        )
         out.print()

src/mlx_stack/cli/config.py

@@ -138,9 +138,7 @@ def config_reset(yes: bool, force: bool) -> None:
         # Check if stdin is a TTY for interactive confirmation
         try:
             if click.get_text_stream("stdin").isatty():
-                confirmed = click.confirm(
-                    "Reset all configuration to defaults?", default=False
-                )
+                confirmed = click.confirm("Reset all configuration to defaults?", default=False)
             else:
                 console.print(
                     "[bold red]Error:[/bold red] Reset requires --yes or --force flag "

src/mlx_stack/cli/init.py

@@ -64,13 +64,10 @@ def _display_summary(result: dict) -> None:
     budget_gb = result["memory_budget_gb"]
     total_memory_gb = result.get("total_memory_gb", 0.0)
     out.print(
-        f"[dim]Hardware: {profile.chip} ({profile.memory_gb} GB) · "
-        f"Budget: {budget_gb:.1f} GB[/dim]"
+        f"[dim]Hardware: {profile.chip} ({profile.memory_gb} GB) · Budget: {budget_gb:.1f} GB[/dim]"
     )
     if total_memory_gb > 0:
-        out.print(
-            f"[dim]Total estimated memory: {total_memory_gb:.1f} GB[/dim]"
-        )
+        out.print(f"[dim]Total estimated memory: {total_memory_gb:.1f} GB[/dim]")
 
     # Warnings (e.g., memory budget exceeded with --add)
     init_warnings = result.get("warnings", [])
@@ -83,8 +80,7 @@ def _display_summary(result: dict) -> None:
     if stack.get("cloud_fallback"):
         out.print()
         out.print(
-            "[bold green]☁ Cloud Fallback[/bold green]  "
-            "Premium tier via OpenRouter configured"
+            "[bold green]☁ Cloud Fallback[/bold green]  Premium tier via OpenRouter configured"
         )
 
     # Missing models warning

src/mlx_stack/cli/install.py

@@ -42,9 +42,7 @@ def _display_status(status: AgentStatus) -> None:
     if not status.installed:
         out.print(Text("Status: not installed", style="dim"))
     elif status.running and status.pid is not None:
-        out.print(
-            Text(f"Status: installed and running (PID {status.pid})", style="green")
-        )
+        out.print(Text(f"Status: installed and running (PID {status.pid})", style="green"))
     else:
         out.print(Text("Status: installed but not running", style="yellow"))
 

src/mlx_stack/cli/logs.py

@@ -6,6 +6,7 @@
 
 from __future__ import annotations
 
+import contextlib
 import sys
 
 import click
@@ -78,7 +79,7 @@ def _display_rotation_results(results: list) -> None:
             out.print(f"[green]✓[/green] {result.service}: rotated")
             any_rotated = True
         else:
-            out.print(f"[dim]–[/dim] {result.service}: no rotation needed")
+            out.print(f"[dim]-[/dim] {result.service}: no rotation needed")
 
     if not results:
         out.print(Text("No log files found to rotate.", style="yellow"))
@@ -213,11 +214,8 @@ def logs(
     # Handle --follow mode
     if follow:
         num = tail_lines if tail_lines is not None else DEFAULT_TAIL_LINES
-        try:
+        with contextlib.suppress(KeyboardInterrupt):
             follow_log(log_path, num_lines=num, output_callback=click.echo)
-        except KeyboardInterrupt:
-            # Belt-and-suspenders: ensure clean exit
-            pass
         return
 
     # Default: show tail of log

src/mlx_stack/cli/models.py

@@ -80,7 +80,7 @@ def _display_local_models() -> None:
             indicator_style = "bold green" if model.is_active else ""
 
             # Display name: prefer catalog name, fall back to directory name
-            display_name = model.catalog_name if model.catalog_name else model.name
+            display_name = model.catalog_name or model.name
 
             # Size
             size_str = format_size(model.disk_size_bytes)
@@ -217,7 +217,7 @@ def _display_catalog(
         local_style = "bold green" if cm.is_local else ""
 
         # Parameters
-        params_str = f"{cm.params_b:.1f}B" if cm.params_b >= 1.0 else f"{cm.params_b:.1f}B"
+        params_str = f"{cm.params_b:.1f}B"
 
         # Quantizations
         quants_str = ", ".join(cm.quants)
@@ -270,7 +270,9 @@ def _display_catalog(
 @click.option("--family", default=None, help="Filter catalog by model family (e.g., 'qwen3.5').")
 @click.option("--tag", default=None, help="Filter catalog by tag (e.g., 'agent-ready').")
 @click.option(
-    "--tool-calling", "tool_calling", is_flag=True,
+    "--tool-calling",
+    "tool_calling",
+    is_flag=True,
     help="Filter catalog to tool-calling-capable models only.",
 )
 def models(

src/mlx_stack/cli/profile.py

@@ -52,12 +52,8 @@ def profile() -> None:
 
     if hw.is_estimate:
         out.print()
-        out.print(
-            "[yellow]⚠ Bandwidth is estimated for unknown chip.[/yellow]"
-        )
-        out.print(
-            "  Run [bold]mlx-stack bench --save[/bold] to calibrate with real measurements."
-        )
+        out.print("[yellow]⚠ Bandwidth is estimated for unknown chip.[/yellow]")
+        out.print("  Run [bold]mlx-stack bench --save[/bold] to calibrate with real measurements.")
 
     out.print()
     from mlx_stack.core.paths import get_profile_path

src/mlx_stack/cli/pull.py

@@ -115,20 +115,13 @@ def _run_post_download_bench(model_id: str, quant: str, out: Console) -> None:
         from mlx_stack.core.benchmark import BenchmarkError, run_benchmark
 
         result = run_benchmark(target=model_id, save=True)
-        out.print(
-            f"  Prompt TPS: {result.prompt_tps_mean:.1f} ± {result.prompt_tps_std:.1f} tok/s"
-        )
-        out.print(
-            f"  Gen TPS:    {result.gen_tps_mean:.1f} ± {result.gen_tps_std:.1f} tok/s"
-        )
+        out.print(f"  Prompt TPS: {result.prompt_tps_mean:.1f} ± {result.prompt_tps_std:.1f} tok/s")
+        out.print(f"  Gen TPS:    {result.gen_tps_mean:.1f} ± {result.gen_tps_std:.1f} tok/s")
         out.print()
-        out.print(
-            "[dim]Results saved for use by 'recommend' and 'init' scoring.[/dim]"
-        )
+        out.print("[dim]Results saved for use by 'recommend' and 'init' scoring.[/dim]")
     except BenchmarkError as exc:
         out.print(
-            f"[yellow]Benchmark failed: {exc}[/yellow]\n"
-            f"Run 'mlx-stack bench {model_id}' to retry."
+            f"[yellow]Benchmark failed: {exc}[/yellow]\nRun 'mlx-stack bench {model_id}' to retry."
         )
     except Exception as exc:
         out.print(

src/mlx_stack/cli/recommend.py

@@ -67,9 +67,7 @@ def parse_budget(raw: str) -> float:
 
     value = float(match.group(1))
     if value <= 0:
-        msg = (
-            f"Invalid budget '{raw}'. Budget must be a positive value."
-        )
+        msg = f"Invalid budget '{raw}'. Budget must be a positive value."
         raise click.BadParameter(msg, param_hint="'--budget'")
 
     return value
@@ -96,8 +94,7 @@ def _resolve_profile() -> HardwareProfile:
     # Auto-detect (in-memory only — recommend is display-only, no file writes)
     console.print("[dim]No saved profile found — detecting hardware...[/dim]")
     try:
-        profile = detect_hardware()
-        return profile
+        return detect_hardware()
     except HardwareError as exc:
         console.print(f"[bold red]Error:[/bold red] {exc}")
         raise SystemExit(1) from None
@@ -206,12 +203,8 @@ def _display_tier_table(result: RecommendationResult) -> None:
     has_estimates = any(t.model.is_estimated for t in result.tiers)
     if has_estimates:
         out.print()
-        out.print(
-            "[yellow]⚠ Some performance values are estimated from bandwidth ratio.[/yellow]"
-        )
-        out.print(
-            "  Run [bold]mlx-stack bench --save[/bold] to calibrate with real measurements."
-        )
+        out.print("[yellow]⚠ Some performance values are estimated from bandwidth ratio.[/yellow]")
+        out.print("  Run [bold]mlx-stack bench --save[/bold] to calibrate with real measurements.")
 
     out.print()
     out.print("[dim]This is a recommendation only — no files were written.[/dim]")
@@ -268,20 +261,15 @@ def _display_all_models(result: RecommendationResult) -> None:
     if openrouter_key:
         out.print()
         out.print(
-            "[bold green]☁ Cloud Fallback[/bold green]  "
-            "Premium tier via OpenRouter also available."
+            "[bold green]☁ Cloud Fallback[/bold green]  Premium tier via OpenRouter also available."
         )
 
     # Estimated warning
     has_estimates = any(m.is_estimated for m in result.all_scored)
     if has_estimates:
         out.print()
-        out.print(
-            "[yellow]⚠ Some performance values are estimated from bandwidth ratio.[/yellow]"
-        )
-        out.print(
-            "  Run [bold]mlx-stack bench --save[/bold] to calibrate with real measurements."
-        )
+        out.print("[yellow]⚠ Some performance values are estimated from bandwidth ratio.[/yellow]")
+        out.print("  Run [bold]mlx-stack bench --save[/bold] to calibrate with real measurements.")
 
     out.print()
     out.print("[dim]This is a recommendation only — no files were written.[/dim]")
@@ -329,8 +317,7 @@ def recommend(budget: str | None, intent: str | None, show_all: bool) -> None:
     elif intent not in VALID_INTENTS:
         valid = ", ".join(sorted(VALID_INTENTS))
         console.print(
-            f"[bold red]Error:[/bold red] Invalid intent '{intent}'. "
-            f"Valid intents: {valid}"
+            f"[bold red]Error:[/bold red] Invalid intent '{intent}'. Valid intents: {valid}"
         )
         raise SystemExit(1)