piotr/innercontext
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
innercontext/backend
History
Piotr Oleszczyk 5bb2ea5f08 feat(api): add short_id column for consistent LLM UUID handling 
Resolves validation failures where LLM fabricated full UUIDs from 8-char
prefixes shown in context, causing 'unknown product_id' errors.

Root Cause Analysis:
- Context showed 8-char short IDs: '77cbf37c' (Phase 2 optimization)
- Function tool returned full UUIDs: '77cbf37c-3830-4927-...'
- LLM saw BOTH formats, got confused, invented UUIDs for final response
- Validators rejected fabricated UUIDs as unknown products

Solution: Consistent 8-char short_id across LLM boundary:
1. Database: New short_id column (8 chars, unique, indexed)
2. Context: Shows short_id (was: str(id)[:8])
3. Function tools: Return short_id (was: full UUID)
4. Translation layer: Expands short_id → UUID before validation
5. Database: Stores full UUIDs (no schema change for existing data)

Changes:
- Added products.short_id column with unique constraint + index
- Migration populates from UUID prefix, handles collisions via regeneration
- Product model auto-generates short_id for new products
- LLM contexts use product.short_id consistently
- Function tools return product.short_id
- Added _expand_product_id() translation layer in routines.py
- Integrated expansion in suggest_routine() and suggest_batch()
- Validators work with full UUIDs (no changes needed)

Benefits:
✅ LLM never sees full UUIDs, no format confusion
✅ Maintains Phase 2 token optimization (~85% reduction)
✅ O(1) indexed short_id lookups vs O(n) pattern matching
✅ Unique constraint prevents collisions at DB level
✅ Clean separation: 8-char for LLM, 36-char for application

From production error:
  Step 1: unknown product_id 77cbf37c-3830-4927-9669-07447206689d
  (LLM invented the last 28 characters)

Now resolved: LLM uses '77cbf37c' consistently, translation layer
expands to real UUID before validation.
2026-03-06 10:58:26 +01:00
..
alembic feat(api): add short_id column for consistent LLM UUID handling 2026-03-06 10:58:26 +01:00
innercontext feat(api): add short_id column for consistent LLM UUID handling 2026-03-06 10:58:26 +01:00
jobs/2026-03-02__17-12-31 feat(api): add short_id column for consistent LLM UUID handling 2026-03-06 10:58:26 +01:00
tests style: apply black and isort formatting 2026-03-06 10:17:00 +01:00
.coverage feat(api): add short_id column for consistent LLM UUID handling 2026-03-06 10:58:26 +01:00
.env.example fix: load .env via python-dotenv; SQLite default for local dev 2026-02-26 20:51:13 +01:00
.python-version Initial commit: backend API, data models, and test suite 2026-02-26 15:10:24 +01:00
alembic.ini feat(backend): add Alembic migrations 2026-02-28 20:14:57 +01:00
db.py Initial commit: backend API, data models, and test suite 2026-02-26 15:10:24 +01:00
main.py style: apply black and isort formatting 2026-03-06 10:17:00 +01:00
pgloader.config feat(api): add short_id column for consistent LLM UUID handling 2026-03-06 10:58:26 +01:00
pyproject.toml chore(backend): enable psycopg binary dependency 2026-03-04 21:46:38 +01:00
README.md Initial commit: backend API, data models, and test suite 2026-02-26 15:10:24 +01:00
skincare.yaml Initial commit: backend API, data models, and test suite 2026-02-26 15:10:24 +01:00
test_query.py refactor(llm): optimize Gemini config profiles for extraction and creativity 2026-03-03 21:24:23 +01:00
uv.lock chore(backend): enable psycopg binary dependency 2026-03-04 21:46:38 +01:00

README.md

See the root README for setup and usage instructions.