Phase 1 prerequisite for local LLM support. Adapters now declare
capability flags (supports_tool_calling, max_context_tokens, etc.) so
the engine can reason about what backend is available.
OpenAI adapter accepts fusion_accounting.openai_base_url config -- point
it at LM Studio (http://host.docker.internal:1234/v1) or Ollama
(http://host.docker.internal:11434/v1) and the existing OpenAI adapter
works unchanged.
Implementation note: existing Odoo AbstractModel adapters
(fusion.accounting.adapter.openai/claude) are preserved untouched to
avoid breaking the chat panel; the new plain-Python OpenAIAdapter and
ClaudeAdapter classes (LLMProvider subclasses) are added alongside them.
Made-with: Cursor
Phase 0 Task 7. Pre-Phase-0 all AI code lived in module='fusion_accounting';
the code now lives in 'fusion_accounting_ai' but existing ir_model_data
rows still record the old module name. This post-migration rewrites them.
Handles duplicate-key conflicts by deleting old orphan rows when data-load
has already created a new row under the same name in the new module.
Idempotent: second run reassigns 0 rows.
Made-with: Cursor
