Constrained decoding is ~10x slower and consumes hidden tokens for constraint
processing, causing truncation at ~1000 chars even with 8192 max_output_tokens.
The system prompt already instructs the model to output raw minified JSON; our
NaN/markdown-fence sanitisation handles edge cases.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace truncation-recovery heuristic with a higher token budget.
On JSON parse failure, log finish_reason and 160-char error context
to make the root cause visible.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Pretty-printed JSON wastes 2-3x tokens on indentation/newlines.
Minified output fits more data (e.g. long INCI lists) within the
8192 output token limit.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Models sometimes emit JS-style literals for unknown numeric fields.
Replace NaN, Infinity, undefined with null before parsing.
Also add error logging to capture raw response on parse failure.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Increase max_output_tokens 4096 → 8192 to prevent truncated JSON on
products with long INCI lists
- Return explicit 502 when response.text is None (safety filter blocks)
- Fallback JSON extraction strips markdown fences or leading preamble
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Switch to Node.js 24 LTS via nvm
- Install uv to /usr/local/bin via UV_INSTALL_DIR for system-wide access
- Install pnpm as standalone binary from GitHub releases (not corepack
shim which breaks when copied out of its nvm directory)
- Add libpq5 to apt deps (psycopg3 requires libpq at runtime)
- Add GEMINI_API_KEY and GEMINI_MODEL to backend .env template
- Add ORIGIN to frontend .env.production (SvelteKit CSRF protection)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add alembic 1.14 to dependencies (uv sync → 1.18.4 installed)
- Configure alembic/env.py: loads DATABASE_URL from env, imports all
SQLModel models so metadata is fully populated for autogenerate
- Generate initial migration (c2d626a2b36c) covering all 9 tables:
products, product_inventory, medication_entries, medication_usages,
lab_results, routines, routine_steps, grooming_schedule,
skin_condition_snapshots — with all indexes and constraints
- Add ExecStartPre to innercontext.service: runs alembic upgrade head
before uvicorn starts (idempotent, safe on every restart)
- Update DEPLOYMENT.md: add migration step to backend setup and update
flow; document alembic stamp head for existing installations
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Remove s.trend from dashboard (field removed from SkinConditionSnapshot)
- Replace trend with texture in SkinPhotoAnalysisResponse (api.ts)
- Use record_id instead of id for LabResult and MedicationEntry keyed each blocks
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add backend/innercontext/mcp_server.py with tools covering products,
inventory, routines, skin snapshots, medications, lab results, and
grooming schedule
- Mount MCP app at /mcp in main.py using combine_lifespans
- Fix test isolation: patch app.router.lifespan_context in conftest to
avoid StreamableHTTPSessionManager single-run limitation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Remove the derived `trend` field (better computed from history by the MCP
agent) and add `texture: smooth|rough|flaky|bumpy` which LLM can reliably
assess from photos. Updates model, API, system prompt, tests, and frontend.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Pass `text=` as keyword arg to Part.from_text() and raise max_output_tokens
from 1024 to 2048 to prevent JSON truncation in the notes field.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Remove the All/AM/PM filter buttons and part_of_day param from
the routines list page — date-based sorting/filtering is preferred.
Add missing keyed {#each} blocks across all pages to follow
Svelte 5 best practice (dashboard, products, medications,
lab results, routines list and detail, skin).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add POST /skincare/analyze-photos endpoint that accepts 1–3 skin
photos, sends them to Gemini vision, and returns a structured
SkinPhotoAnalysisResponse for pre-filling the snapshot form.
Extract shared Gemini client setup into innercontext/llm.py
(get_gemini_client) so both products and skincare use a single
default model (gemini-flash-latest) and API key check.
Frontend: AI photo card on /skin page with file picker, previews,
and auto-fill of all form fields from the analysis result.
New fields (skin_type, sebum_tzone, sebum_cheeks) added to form
and server action.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Previously redirected to /products/{id} (edit page) which looks
identical to the create form, making it appear as if nothing happened.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add POST /products/parse-text endpoint that accepts raw product text,
calls Gemini (google-genai) with a structured extraction prompt, and
returns a partial ProductParseResponse. Frontend gains a collapsible
"AI pre-fill" card at the top of ProductForm that merges the LLM
response into all form fields reactively.
- Backend: ProductParseRequest/Response schemas, system prompt with
enum constraints, temperature=0.0 for deterministic extraction,
effect_profile always returned in full
- Frontend: parseProductText() in api.ts; controlled $state bindings
for all text/number/checkbox inputs; applyAiResult() merges response
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Wrap all prop-derived $state initializers with untrack() to explicitly
signal that one-time capture from the product prop is intentional.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds full_weight_g and empty_weight_g to ProductBase (inherited by Product
and response models) so per-product package weight specs are captured.
Adds last_weighed_at to ProductInventory to record when a package was last
weighed. Wires up all fields through API schemas, frontend types, forms, and
the product detail page (add/edit/display).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Classification: replace fragmented layout (full-width + 3-col + full-width)
with a single 2-column grid; Category spans full width via col-span-2
- Effect profile: replace flex + fixed w-40 label with CSS grid using
minmax(7rem,10rem) label column to prevent overflow at narrow viewports
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add ProductBase, ProductPublic, ProductWithInventory and
SkinConditionSnapshotBase, SkinConditionSnapshotPublic. Table models now inherit
from their Base counterpart and override JSON fields with sa_column. All
field_serializer hacks removed; FastAPI response models use the non-table Public
classes so Pydantic coerces raw DB dicts → typed models cleanly. ProductCreate
and SnapshotCreate now simply inherit their respective Base classes.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Extract shared ProductForm.svelte component covering actives (dynamic
rows with ingredient function checkboxes), product_effect_profile
(range sliders 0–5), context_rules (tristate selects), synergizes_with,
incompatible_with (dynamic rows), and contraindications.
Replace the Quick edit stub on the product detail page with the full
edit form pre-populated from the existing product. Update both server
actions to parse all new fields including JSON payloads for complex
nested objects.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Drop Product.personal_rating from model, API schemas, and all frontend
views (list table, detail view, quick-edit form, new-product form)
- Extract get_or_404 into backend/innercontext/api/utils.py; remove five
duplicate copies from individual API modules
- Fix all ty type errors: generic get_or_404 with TypeVar, cast() in
coerce_effect_profile validator, col() for ilike on SQLModel column,
dict[str, Any] annotation in test helper, ty: ignore for CORSMiddleware
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
shadcn-svelte components import these types from \$lib/utils — add
re-exports from bits-ui to resolve 25 type errors.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Drop fields identified as redundant or low-value from the Product model,
API schemas, frontend types, and forms. Raise effect_profile threshold in
to_llm_context() from >0 to >=2 to suppress noise values. Remove sku/barcode
from LLM context output (kept on model for catalog use).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Rename skincare route prefix /skin-snapshots → /skincare to match API client
- Add redirect_slashes=False to FastAPI app; change collection routes from "/" to ""
to eliminate 307 redirects on POST/GET without trailing slash
- Fix redirect() inside try/catch in products/new and routines/new server actions
(SvelteKit redirect() throws and was being caught as a 500 error)
- Eagerly load inventory and steps relationships via explicit SELECT + model_dump(mode="json"),
working around SQLModel 0.0.37 not serializing Relationship fields in response_model
- Add field_validator for product_effect_profile to coerce DB-returned dict → ProductEffectProfile,
eliminating Pydantic serializer warning
- Update all tests to use routes without trailing slash
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
FastAPI backend for personal health and skincare data with MCP export.
Includes SQLModel models for products, inventory, medications, lab results,
routines, and skin condition snapshots. Pytest suite with 111 tests running
on SQLite in-memory (no PostgreSQL required).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
