feat: add centralized Config class with auto-save to ~/.strix/cli-config.json

- Add Config class with all env var defaults in one place
- Auto-load saved config on startup (env vars take precedence)
- Auto-save config after successful LLM warm-up
- Replace scattered os.getenv() calls with Config.get()

strix/llm/config.py

@@ -1,4 +1,4 @@
-import os
+from strix.config import Config
 
 
 class LLMConfig:
@@ -10,7 +10,7 @@ class LLMConfig:
         timeout: int | None = None,
         scan_mode: str = "deep",
     ):
-        self.model_name = model_name or os.getenv("STRIX_LLM", "openai/gpt-5")
+        self.model_name = model_name or Config.get("strix_llm")
 
         if not self.model_name:
             raise ValueError("STRIX_LLM environment variable must be set and not empty")
@@ -18,6 +18,6 @@ class LLMConfig:
         self.enable_prompt_caching = enable_prompt_caching
         self.skills = skills or []
 
-        self.timeout = timeout or int(os.getenv("LLM_TIMEOUT", "300"))
+        self.timeout = timeout or int(Config.get("llm_timeout"))  # type: ignore[arg-type]
 
         self.scan_mode = scan_mode if scan_mode in ["quick", "standard", "deep"] else "deep"

strix/llm/dedupe.py

@@ -1,11 +1,12 @@
 import json
 import logging
-import os
 import re
 from typing import Any
 
 import litellm
 
+from strix.config import Config
+
 
 logger = logging.getLogger(__name__)
 
@@ -154,13 +155,13 @@ def check_duplicate(
 
         comparison_data = {"candidate": candidate_cleaned, "existing_reports": existing_cleaned}
 
-        model_name = os.getenv("STRIX_LLM", "openai/gpt-5")
-        api_key = os.getenv("LLM_API_KEY")
+        model_name = Config.get("strix_llm")
+        api_key = Config.get("llm_api_key")
         api_base = (
-            os.getenv("LLM_API_BASE")
-            or os.getenv("OPENAI_API_BASE")
-            or os.getenv("LITELLM_BASE_URL")
-            or os.getenv("OLLAMA_API_BASE")
+            Config.get("llm_api_base")
+            or Config.get("openai_api_base")
+            or Config.get("litellm_base_url")
+            or Config.get("ollama_api_base")
         )
 
         messages = [

strix/llm/llm.py

@@ -1,6 +1,5 @@
 import asyncio
 import logging
-import os
 from collections.abc import AsyncIterator
 from dataclasses import dataclass
 from enum import Enum
@@ -16,6 +15,7 @@ from jinja2 import (
 from litellm import completion_cost, stream_chunk_builder, supports_reasoning
 from litellm.utils import supports_prompt_caching, supports_vision
 
+from strix.config import Config
 from strix.llm.config import LLMConfig
 from strix.llm.memory_compressor import MemoryCompressor
 from strix.llm.request_queue import get_global_queue
@@ -46,16 +46,14 @@ logger = logging.getLogger(__name__)
 litellm.drop_params = True
 litellm.modify_params = True
 
-_LLM_API_KEY = os.getenv("LLM_API_KEY")
+_LLM_API_KEY = Config.get("llm_api_key")
 _LLM_API_BASE = (
-    os.getenv("LLM_API_BASE")
-    or os.getenv("OPENAI_API_BASE")
-    or os.getenv("LITELLM_BASE_URL")
-    or os.getenv("OLLAMA_API_BASE")
+    Config.get("llm_api_base")
+    or Config.get("openai_api_base")
+    or Config.get("litellm_base_url")
+    or Config.get("ollama_api_base")
 )
-_STRIX_REASONING_EFFORT = os.getenv(
-    "STRIX_REASONING_EFFORT"
-)  # "none", "minimal", "low", "medium", "high", or "xhigh"
+_STRIX_REASONING_EFFORT = Config.get("strix_reasoning_effort")
 
 
 class LLMRequestFailedError(Exception):

strix/llm/memory_compressor.py

@@ -1,9 +1,10 @@
 import logging
-import os
 from typing import Any
 
 import litellm
 
+from strix.config import Config
+
 
 logger = logging.getLogger(__name__)
 
@@ -150,7 +151,7 @@ class MemoryCompressor:
         timeout: int = 600,
     ):
         self.max_images = max_images
-        self.model_name = model_name or os.getenv("STRIX_LLM", "openai/gpt-5")
+        self.model_name = model_name or Config.get("strix_llm")
         self.timeout = timeout
 
         if not self.model_name:

strix/llm/request_queue.py

@@ -1,5 +1,4 @@
 import asyncio
-import os
 import threading
 import time
 from collections.abc import AsyncIterator
@@ -8,16 +7,13 @@ from typing import Any
 from litellm import acompletion
 from litellm.types.utils import ModelResponseStream
 
+from strix.config import Config
+
 
 class LLMRequestQueue:
     def __init__(self, max_concurrent: int = 1, delay_between_requests: float = 4.0):
-        rate_limit_delay = os.getenv("LLM_RATE_LIMIT_DELAY")
-        if rate_limit_delay:
-            delay_between_requests = float(rate_limit_delay)
-
-        rate_limit_concurrent = os.getenv("LLM_RATE_LIMIT_CONCURRENT")
-        if rate_limit_concurrent:
-            max_concurrent = int(rate_limit_concurrent)
+        delay_between_requests = float(Config.get("llm_rate_limit_delay"))  # type: ignore[arg-type]
+        max_concurrent = int(Config.get("llm_rate_limit_concurrent"))  # type: ignore[arg-type]
 
         self.max_concurrent = max_concurrent
         self.delay_between_requests = delay_between_requests