feat(llm): add OpenAI adapter, entity archive policy, process chapters 5-7

Add OpenAIAdapter for the OpenAI chat completions API (apikey-chatgpt.txt
or OPENAI_API_KEY). Set default model to arcee-ai/trinity-large-preview:free
for the infospace pipeline and increase max_tokens from 4096 to 8192.

Reprocess chapter 05 with Trinity Large (was Gemini: 1 truncated entity,
now 19 complete entities). Process chapters 06 (Aurora Alpha, 10 entities)
and 07 (Trinity Large, 15 entities including regenerated violent-policy.md).
Canonical set now at 85 unique entities.

Add entity archive policy: entities are never silently deleted. Retired
entities move to output/entities/archive/ with a dated reason header.
New CLI option: --archive-entity <slug> --reason "...". The --list
output shows the archive count alongside the canonical set.

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

markitect/llm/__init__.py

@@ -16,6 +16,7 @@ from markitect.llm.factory import create_adapter
 from markitect.llm.openrouter import OpenRouterAdapter
 from markitect.llm.claude_code import ClaudeCodeAdapter
 from markitect.llm.gemini import GeminiAdapter
+from markitect.llm.openai import OpenAIAdapter
 from markitect.llm.config import LLMConfig, load_config
 from markitect.llm.exceptions import (
     LLMError,
@@ -31,6 +32,7 @@ __all__ = [
     "OpenRouterAdapter",
     "ClaudeCodeAdapter",
     "GeminiAdapter",
+    "OpenAIAdapter",
     "LLMConfig",
     "load_config",
     "LLMError",