feat: add STRIX_REASONING_EFFORT env var to control thinking effort

- Add configurable reasoning effort via environment variable
- Default to "high", but use "medium" for quick scan mode
- Document in README and interface error panel

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

README.md

@@ -213,6 +213,7 @@ export LLM_API_KEY="your-api-key"
 # Optional
 export LLM_API_BASE="your-api-base-url"  # if using a local model, e.g. Ollama, LMStudio
 export PERPLEXITY_API_KEY="your-api-key"  # for search capabilities
+export STRIX_REASONING_EFFORT="high"  # control thinking effort (default: high, quick scan: medium)
 ```
 
 **Recommended models for best results:**

strix/interface/main.py

@@ -67,6 +67,9 @@ def validate_environment() -> None:  # noqa: PLR0912, PLR0915
     if not os.getenv("PERPLEXITY_API_KEY"):
         missing_optional_vars.append("PERPLEXITY_API_KEY")
 
+    if not os.getenv("STRIX_REASONING_EFFORT"):
+        missing_optional_vars.append("STRIX_REASONING_EFFORT")
+
     if missing_required_vars:
         error_text = Text()
         error_text.append("❌ ", style="bold red")
@@ -118,6 +121,13 @@ def validate_environment() -> None:  # noqa: PLR0912, PLR0915
                         " - API key for Perplexity AI web search (enables real-time research)\n",
                         style="white",
                     )
+                elif var == "STRIX_REASONING_EFFORT":
+                    error_text.append("• ", style="white")
+                    error_text.append("STRIX_REASONING_EFFORT", style="bold cyan")
+                    error_text.append(
+                        " - Reasoning effort level (default: high)\n",
+                        style="white",
+                    )
 
         error_text.append("\nExample setup:\n", style="white")
         error_text.append("export STRIX_LLM='openai/gpt-5'\n", style="dim white")
@@ -140,6 +150,11 @@ def validate_environment() -> None:  # noqa: PLR0912, PLR0915
                     error_text.append(
                         "export PERPLEXITY_API_KEY='your-perplexity-key-here'\n", style="dim white"
                     )
+                elif var == "STRIX_REASONING_EFFORT":
+                    error_text.append(
+                        "export STRIX_REASONING_EFFORT='high'\n",
+                        style="dim white",
+                    )
 
         panel = Panel(
             error_text,

strix/llm/llm.py

@@ -53,6 +53,9 @@ _LLM_API_BASE = (
     or os.getenv("LITELLM_BASE_URL")
     or os.getenv("OLLAMA_API_BASE")
 )
+_STRIX_REASONING_EFFORT = os.getenv(
+    "STRIX_REASONING_EFFORT"
+)  # "none", "minimal", "medium", "high", or "xhigh"
 
 
 class LLMRequestFailedError(Exception):
@@ -110,6 +113,13 @@ class LLM:
         self._total_stats = RequestStats()
         self._last_request_stats = RequestStats()
 
+        if _STRIX_REASONING_EFFORT:
+            self._reasoning_effort = _STRIX_REASONING_EFFORT
+        elif self.config.scan_mode == "quick":
+            self._reasoning_effort = "medium"
+        else:
+            self._reasoning_effort = "high"
+
         self.memory_compressor = MemoryCompressor(
             model_name=self.config.model_name,
             timeout=self.config.timeout,
@@ -467,7 +477,7 @@ class LLM:
         completion_args["stop"] = ["</function>"]
 
         if self._should_include_reasoning_effort():
-            completion_args["reasoning_effort"] = "high"
+            completion_args["reasoning_effort"] = self._reasoning_effort
 
         queue = get_global_queue()
         self._total_stats.requests += 1