refactor(api): remove MCP server integration and docs references

This commit is contained in:
Piotr Oleszczyk 2026-03-04 12:28:30 +01:00
parent 5dd8242985
commit 1d8a8eafb8
9 changed files with 9 additions and 1195 deletions

View file

@ -40,14 +40,12 @@ No test suite exists yet (backend has some test files but they're not integrated
## Architecture
**innercontext** collects personal health and skincare data and exposes it via MCP to an LLM agent.
**innercontext** collects personal health and skincare data and exposes it to an LLM agent.
**Backend Stack:** Python 3.12, SQLModel (0.0.37) + SQLAlchemy, Pydantic v2, FastAPI, PostgreSQL (psycopg3).
**Frontend Stack:** SvelteKit 5, Tailwind CSS v4, bits-ui, inlang/paraglide (i18n), svelte-dnd-action.
### MCP Server (`backend/innercontext/mcp_server.py`)
### Models (`backend/innercontext/models/`)
| File | Tables |
@ -57,7 +55,7 @@ No test suite exists yet (backend has some test files but they're not integrated
| `routine.py` | `routines`, `routine_steps` |
| `skincare.py` | `skin_condition_snapshots` |
**`Product`** is the core model. JSON columns store `inci` (list), `actives` (list of `ActiveIngredient`), `recommended_for`, `targets`, `incompatible_with`, `synergizes_with`, `context_rules`, and `product_effect_profile`. The `to_llm_context()` method returns a token-optimised dict for MCP.
**`Product`** is the core model. JSON columns store `inci` (list), `actives` (list of `ActiveIngredient`), `recommended_for`, `targets`, `incompatible_with`, `synergizes_with`, `context_rules`, and `product_effect_profile`. The `to_llm_context()` method returns a token-optimised dict for LLM usage.
**`ProductInventory`** tracks physical packages (opened status, expiry, remaining weight). One product → many inventory entries.