Close local release-quality gaps and reconcile workplan status

Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0e332-3365-77c0-8491-084e9ea33ac1

llm_connect/server.py

@@ -30,14 +30,14 @@ import time
 import uuid
 from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 from pathlib import Path
-from typing import Optional
+from typing import Any
 from urllib.parse import parse_qs, urlsplit
 
 from llm_connect._diagnostics import capture_diagnostics
 from llm_connect.adapter import LLMAdapter
 from llm_connect.exceptions import (
-    LLMBudgetExceededError,
     LLMAPIError,
+    LLMBudgetExceededError,
     LLMConfigurationError,
     LLMError,
     LLMRateLimitError,
@@ -48,15 +48,21 @@ from llm_connect.profiles import ProfiledLLMAdapter, default_runtime_profiles
 from llm_connect.usage import maybe_record_usage, suppress_auto_usage_record
 
 
+class _AdapterHTTPServer(ThreadingHTTPServer):
+    adapter: LLMAdapter
+
+
 class _Handler(BaseHTTPRequestHandler):
     """Request handler — adapter injected via server.adapter."""
 
-    def log_message(self, format, *args):  # suppress default access log
+    server: _AdapterHTTPServer
+
+    def log_message(self, format: str, *args: Any) -> None:  # suppress default access log
         pass
 
     # ── GET ────────────────────────────────────────────────────────
 
-    def do_GET(self):
+    def do_GET(self) -> None:
         parsed = urlsplit(self.path)
         if parsed.path == "/health":
             self._respond(200, {"status": "ok"})
@@ -65,7 +71,7 @@ class _Handler(BaseHTTPRequestHandler):
 
     # ── POST ───────────────────────────────────────────────────────
 
-    def do_POST(self):
+    def do_POST(self) -> None:
         parsed = urlsplit(self.path)
         if parsed.path != "/execute":
             self._respond(404, {"error": "not found"})
@@ -96,7 +102,7 @@ class _Handler(BaseHTTPRequestHandler):
         diagnostics_enabled = debug_enabled or bool(audit_dir)
         try:
             with capture_diagnostics(diagnostics_enabled) as diagnostics:
-                adapter = self.server.adapter  # type: ignore[attr-defined]
+                adapter = self.server.adapter
                 if not adapter.validate_config(config):
                     raise LLMConfigurationError(
                         "Adapter rejected RunConfig",
@@ -152,9 +158,9 @@ class LLMServer:
         host: str = "127.0.0.1",
         port: int = 8080,
     ) -> None:
-        self._httpd = ThreadingHTTPServer((host, port), _Handler)
-        self._httpd.adapter = adapter  # type: ignore[attr-defined]
-        self._thread: Optional[threading.Thread] = None
+        self._httpd = _AdapterHTTPServer((host, port), _Handler)
+        self._httpd.adapter = adapter
+        self._thread: threading.Thread | None = None
 
     @property
     def port(self) -> int:
@@ -163,7 +169,7 @@ class LLMServer:
 
     @property
     def host(self) -> str:
-        return self._httpd.server_address[0]
+        return str(self._httpd.server_address[0])
 
     def start(self) -> None:
         """Start serving in a daemon background thread."""
@@ -185,7 +191,7 @@ class LLMServer:
 
 def _build_adapter(
     provider: str,
-    model: Optional[str],
+    model: str | None,
     *,
     enable_profiles: bool = True,
     strict_profiles: bool = False,
@@ -240,7 +246,7 @@ def _error_response(exc: Exception) -> tuple[int, dict]:
 
 
 def _error_body(code: str, exc: Exception) -> dict:
-    body = {
+    body: dict[str, Any] = {
         "error": code,
         "message": _sanitize_text(_message(exc)),
         "type": exc.__class__.__name__,
@@ -260,7 +266,7 @@ def _message(exc: Exception) -> str:
 
 
 def _safe_context(context: dict) -> dict:
-    safe = {}
+    safe: dict[str, Any] = {}
     for key, value in context.items():
         lowered = str(key).lower()
         if any(secret_word in lowered for secret_word in ("key", "secret", "token", "password")):
@@ -321,7 +327,7 @@ def _safe_filename(value: str) -> str:
     return re.sub(r"[^A-Za-z0-9_.-]+", "-", value).strip("-") or "response"
 
 
-def main(argv=None) -> None:
+def main(argv: list[str] | None = None) -> None:
     parser = argparse.ArgumentParser(
         prog="python -m llm_connect.server",
         description="Start llm_connect HTTP serve mode.",