135 lines
4.9 KiB
Markdown
135 lines
4.9 KiB
Markdown
# Workflow evaluations
|
|
|
|
The evaluation runner calls a live FastAPI service backed by FastGPT. Each
|
|
conversation step checks the SSE `stage_code.nextStageCode` value and optional
|
|
form / reply expectations. During the run it prints the dialogue and saves
|
|
transcripts. Cases target `workflow/20261021`; import that workflow into FastGPT
|
|
before running against a service.
|
|
|
|
## Case format
|
|
|
|
Add YAML files anywhere under `evals/cases/`:
|
|
|
|
- `collection_skip_known_info/`: skip known fields and clarify missing information.
|
|
- `non_motor_vehicle/`: both client modes, with separate flow and extraction cases.
|
|
`all_info`, `self_collision`, `no_other_vehicle`, and `explicit_correction`
|
|
cover conversation flow and known facts. `electric_bicycle` verifies an
|
|
electric bicycle hitting a fixed object and transferring to `0003` without
|
|
asking for car counts. These cases accept the described non-motor-vehicle
|
|
collision as having `vehicle_count: 0` from the first accident description.
|
|
`zero_count_bundle` / `zero_count_history` check zero extraction and retention.
|
|
Explicit correction to one car must update the count to `1`.
|
|
Both collection and extraction prompts in `workflow/20261021` use this policy
|
|
only for an explicitly described non-motor-vehicle single-party collision with
|
|
a fixed object; other vehicle involvement or unclear relations do not imply zero.
|
|
- `time_confirmation/`: mandatory full-date confirmation, retaining supplemental
|
|
information while confirmation is pending, and confirming corrected times.
|
|
- `no_false/`: ASR noise must not cause premature transfer.
|
|
- `photo_button_guidance/`: button help and failure handling.
|
|
- `photo_skip_plate_confirm/`: current photo transitions without plate confirmation.
|
|
|
|
Obsolete scripts requiring repeated time/count confirmations or the removed
|
|
`2004` / `2016` photo states have been removed. Photo transition cases use a
|
|
complete accident description, confirm its standardized time, then reach their
|
|
target branch. Time confirmation is mandatory even when all other information
|
|
is already known; an unchanged time is confirmed only once.
|
|
|
|
```yaml
|
|
name: direct_initial_stage
|
|
clientMode: direct
|
|
|
|
steps:
|
|
- input: 新对话
|
|
expect:
|
|
stageCode: "1001"
|
|
|
|
- input: 继续办理
|
|
expect:
|
|
stageCode: "1002"
|
|
```
|
|
|
|
`clientMode` in the case file is the API request setting (`direct` or
|
|
`browser_addon`). Steps in one file share the same generated `sessionId`.
|
|
Different cases always use different session IDs.
|
|
|
|
Optional `expect` fields:
|
|
|
|
- `form`: partial equality against the cumulative form, including value types.
|
|
- `formMatches`: field-to-regex mapping for free-text descriptions.
|
|
- `formAbsent`: fields that must not have been extracted yet.
|
|
- `replyMatches` / `replyNotMatches`: required / forbidden reply regexes.
|
|
|
|
If any step has a form expectation, the runner sends `needFormUpdate: true`
|
|
throughout that case, merges SSE `formUpdate` deltas across turns, and records
|
|
both updates and form snapshots. Thus an omitted unchanged field is accepted,
|
|
while a later incorrect overwrite fails. SSE errors also fail the step.
|
|
Existing cases without reply expectations still require manual review of their
|
|
commented wording requirements.
|
|
|
|
```yaml
|
|
- input: 没有人员伤亡。
|
|
expect:
|
|
stageCode: "1002"
|
|
form: {has_injury: false, has_non_motor_vehicle_hit: true}
|
|
replyMatches: "(什么时候|几点|事故.*时间)"
|
|
replyNotMatches: "(有没有|是否).*非机动车"
|
|
```
|
|
|
|
## Run
|
|
|
|
Start the API, then execute:
|
|
|
|
```bash
|
|
python evals/run.py
|
|
```
|
|
|
|
Use another API address:
|
|
|
|
```bash
|
|
python evals/run.py --base-url http://192.168.1.10:8000
|
|
```
|
|
|
|
Run selected cases:
|
|
|
|
```bash
|
|
python evals/run.py --case direct
|
|
python evals/run.py --case browser_addon
|
|
python evals/run.py --case non_motor_vehicle
|
|
python evals/run.py --case non_motor_vehicle_electric_bicycle
|
|
python evals/run.py --case non_motor_vehicle_zero_count
|
|
python evals/run.py --case time_confirmation
|
|
python evals/run.py --case photo_skip_plate_confirm
|
|
```
|
|
|
|
There are 14 non-motor-vehicle cases: 10 flow cases and 4 zero-count extraction
|
|
cases. Both groups require `vehicle_count: 0` for the described non-motor-vehicle
|
|
collisions, while unrelated chatter must leave accident fields absent. Vehicle
|
|
type corrections, time confirmation, and transfer checks remain active. The
|
|
runner still stops each case at its first failure.
|
|
|
|
## Dialogue and transcripts
|
|
|
|
While a case runs, each step prints the user input, bot reply (`text_delta`),
|
|
and stage-code check result.
|
|
|
|
By default, after the run finishes, transcripts are written under
|
|
`evals/results/<timestamp>/`:
|
|
|
|
- `*.md` — readable conversation log
|
|
- `*.json` — structured step results
|
|
|
|
Save to a specific directory:
|
|
|
|
```bash
|
|
python evals/run.py --output-dir evals/results/manual-run --case direct
|
|
```
|
|
|
|
Print live dialogue only, without writing files:
|
|
|
|
```bash
|
|
python evals/run.py --no-save --case direct
|
|
```
|
|
|
|
The process exits with code `1` when an expectation fails and code `2` when
|
|
case configuration is invalid.
|