thread-master/docs/product/brand-product-radar/tasks/T743-product-fit-ai-structu...

53 lines
1.7 KiB
Markdown
Raw Normal View History

2026-08-13 02:22:24 +00:00
# T743 — product fit ai structured fallback
> Status: `done`
> Milestone: `M4` · Phase C
> Kind: `feat` · Est. change: `~190 lines`
## Goal
產品適配優先使用結構化 AI 判定,輸出不完整時安全回 deterministic scorer不保存腦補證據。
## Depends on
- T741、T742
## Inputs
- `apps/backend/internal/module/radar/usecase/judge.go`、AI provider abstraction
- `../spec.md` §3.2、§8
## Outputs
| 路徑 | 動作 | 說明 |
|------|------|------|
| `apps/backend/internal/module/radar/usecase/product_fit_ai.go` | add | prompt、JSON parse、evidence validation、fallback |
| `apps/backend/internal/module/radar/usecase/judge.go` | edit | product mode 接 fitgeneric 保留舊 fit |
| AI tests | add | validmissing dimensionsinvented excerptprovider failure |
## Behavior
- excerpt 必須可在候選文字找到basis 必須可在 snapshot 找到。
- AI 結果缺契約即丟棄fallback 仍需四維完整。
- 新 match 計 `ai_research``radar.product_fit`;既有 generic 計費不變。
## Out of scope
- merge 與 primaryT744
- 準確度樣本T773
## Acceptance
- [x] provider failure 不產生空 reasons且 token 不當會員 auth。
```bash
cd apps/backend && go test ./internal/module/radar/usecase/... -count=1
```
Implementation result (2026-08-10): product watches now attach a structured
four-dimension fit during judging and meter it as `ai_research`
`radar.product_fit`. AI output is accepted only when every positive excerpt is
found in the candidate and every basis exists in the immutable snapshot;
malformed, invented, or provider-failed responses fall back to T742's
deterministic scorer, preserving complete reasons and hard exclusions.