Commit Graph
5 Commits
Author SHA1 Message Date
Marc-André Bombeck fb54b46034 fix(labs): reserve a proportionate budget for text-mode OCR
Text-mode OCR structures browser-extracted text rather than running a
vision call, so it reserved and reconciled the full vision budget even
though the spend is far lower. Add an ocrExtractText ceiling and reserve
that in text mode, and refund the reservation in full on a clean extract
failure instead of charging the reserved estimate.
2026-06-26 09:26:47 +02:00
Marc-André Bombeck 7f71f0e7a6 feat(ai): add optional vision inputs and capability resolution
Extend CompletionParams with optional images[] and documents[] so the
provider clients can carry an uploaded lab-report photo or PDF. Anthropic
folds image and native document blocks into the user turn; OpenAI and the
local OpenAI-compatible client fold image_url blocks. Text-only callers are
untouched. Add supportsVisionForConfig / supportsPdfForProvider and an
ocrExtract budget for the Lab-OCR ingestion path.
2026-06-20 12:24:38 +02:00
Marc-André Bombeck 5e541ebf4f refactor(ai): drop dead status-batch reverse map, consume the budget type
Remove the unused output-key reverse map the batch path never read, and
have the budget table satisfy the AiBudget interface directly so the type
is enforced rather than orphaned.
2026-06-19 21:51:22 +02:00
Marc-André Bombeck beb0be7452 refactor(insights): split weight-status at the provider boundary
Introduce a prepare -> run -> finalize contract for the per-metric status
cards so the snapshot build and the provider call can be driven separately.
The public generator keeps its signature and one-call-per-metric behaviour;
weight-status now resolves through the shared single-card path. Add the
status-batch AI budget entry sized for one combined seven-metric call.
2026-06-19 21:31:16 +02:00
Marc-André Bombeck 7530324fd1 refactor(ai): centralise per-surface generation budgets
Replace the scattered `?? 0.3` / `?? 1000` temperature and maxTokens
magic numbers across the status provider, Coach route, comprehensive
generator and period-narrative generator with a single typed
`ai-budgets.ts` map. Each entry documents the output contract that
fixes its token ceiling.

Right-size the per-metric status output from 1000 to 250 tokens: the
card renders one `{ "summary": "..." }` of 2-4 sentences (30-60 words),
so 1000 was an order of magnitude over the real ceiling.
2026-06-19 20:57:37 +02:00