← WI-017 Observability core (operation envelope, OTel trace tree + attributes/events, durable provider-attempt records, P3/P4/P5/P7 trace linkage, redaction, sampling, dashboards) ★ Live Board · Overview WI-058 Provider adapters + live tests (OpenAI + 2nd cloud + local stub) →

WI-056 · Platform & Contracts · provider-scan-harness

Provider scan test harness (Mark-testable): fire a real photo at a provider, see normalized result + cost

queued P2 medium risk   Owner: Paul   Reviewer: Mark Hilleary   0% · 0/1 tasks complete

Gates: P2 Requirements: — Updated: 2026-06-22

At a glance

CodeWI-056
PhasePlatform & Contracts
Order18 of 93
Story points5
Primary surfaceThin internal test surface (CLI + minimal web) over the P2 adapter
Retires—
Depends onProvider gateway + adapter boundary — core (registry, capability, schema+prompt compiler, image prep, ProviderAttempt)
Blocks—
Evidence
queued (P&C harness)

Goals

Give Mark a hands-on way to exercise real provider scans during P&C, so the P2 contract is validated against real photos (and provider cost/quality compared) before the full app is built.

Spec document

P2-provider-adapter → · source ↗

Implementation — what to build

Surface

  • Minimal web form + CLI: upload photo(s), choose scan_type + provider, POST through the P2 adapter.

Output

  • Show the P1-normalized canonical result (boxes/fields) overlaid + raw JSON + token/cost/latency per provider.

Safety

  • Non-prod; no inventory writes (candidates only, per P5); behind auth; bounded by P8 budgets.

Acceptance

  • Mark can run a real scan and compare ≥2 providers on the same photo without a dev present.

Checklist

  • ○ P2 Provider-adapter boundary normalizes OpenAI, Gemini, Claude, and local VLMs into one canonical result via strict structured output.

Gates & testing

  • ○ P2 Provider-adapter boundary normalizes OpenAI, Gemini, Claude, and local VLMs into one canonical result via strict structured output.
    CODE TEST HITL QA 💲 API COST

Requirements

No linked requirements.

Verify (done when)

A non-prod surface lets Mark upload a photo, pick a provider, and see the P1-normalized result + token/cost — used to validate P2 on real images and compare providers.

Cost triggers

💲 API COST

First real paid API spend: live multi-provider vision (OpenAI/Gemini/Claude). Bounded by P8 budgets.

Status & editing

queued   Sprint: P&C Wave 3: Vision Pipeline & Cost

Edit status / sprint on the ★ Live Board → — changes are logged live with who / when / why.

Human-in-the-loop

No human tasks linked.

Findings

None recorded yet.

Concerns

None recorded yet.

Risks

None recorded yet.

Tech debt

None recorded yet.

Tools used

No tool calls recorded.

Files & artifacts

No files / artifacts recorded.

Update log

No log entries yet.