fix extract_files_direct backend default: auto-detect instead of kimi (closes #1086)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

README.md

@@ -367,6 +367,7 @@ These are only needed for **headless / CI extraction** (`graphify extract`). Whe
 - **Code files** — processed locally via tree-sitter. Nothing leaves your machine.
 - **Video / audio** — transcribed locally with faster-whisper. Nothing leaves your machine.
 - **Docs, PDFs, images** — sent to your AI assistant for semantic extraction (via the `/graphify` skill, using whatever model your IDE session runs). Headless `graphify extract` requires `GEMINI_API_KEY` / `GOOGLE_API_KEY` (Gemini), `MOONSHOT_API_KEY` (Kimi), `ANTHROPIC_API_KEY` (Claude), `OPENAI_API_KEY` (OpenAI), `DEEPSEEK_API_KEY` (DeepSeek), a running Ollama instance (`OLLAMA_BASE_URL`), AWS credentials via the standard provider chain (Bedrock - no API key needed, uses IAM), or the `claude` CLI binary (Claude Code - no API key needed, uses your Claude subscription). The `--dedup-llm` flag uses the same key.
+- **Data residency** — `graphify extract` auto-detects which provider to use based on which API key is set (priority: Gemini → Kimi → Claude → OpenAI → DeepSeek → Bedrock → Ollama). For code with data-residency requirements, use `--backend ollama` (fully local) or pass an explicit `--backend` flag. Kimi (`MOONSHOT_API_KEY`) routes to Moonshot AI servers in China.
 - No telemetry, no usage tracking, no analytics.
 
 ---

graphify/llm.py

@@ -629,7 +629,7 @@ def _call_bedrock(model: str, user_message: str, max_tokens: int = 8192, *, deep
 
 def extract_files_direct(
     files: list[Path],
-    backend: str = "kimi",
+    backend: str | None = None,
     api_key: str | None = None,
     model: str | None = None,
     root: Path = Path("."),
@@ -639,8 +639,17 @@ def extract_files_direct(
     """Extract semantic nodes/edges from a list of files using the given backend.
 
     Returns dict with nodes, edges, hyperedges, input_tokens, output_tokens.
-    Raises ValueError for unknown backends. Raises ImportError if SDK missing.
+    Raises ValueError for unknown backends or when no API key is configured.
+    Raises ImportError if SDK missing.
     """
+    if backend is None:
+        backend = detect_backend()
+        if backend is None:
+            raise ValueError(
+                "No LLM backend configured. Set one of: GEMINI_API_KEY, ANTHROPIC_API_KEY, "
+                "OPENAI_API_KEY, DEEPSEEK_API_KEY, MOONSHOT_API_KEY, OLLAMA_BASE_URL, "
+                "or AWS credentials. Pass backend= explicitly to select a provider."
+            )
     if backend not in BACKENDS:
         raise ValueError(f"Unknown backend {backend!r}. Available: {sorted(BACKENDS)}")