fix(agent): reuse collected vehicle counts and avoid repeated questions

evals/README.md

@@ -3,14 +3,27 @@
 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.
+transcripts. Cases cover the current LangGraph backend and workflow snapshots;
+import `workflow/20261027` when evaluating the current prompts through FastGPT.
+The original case comments retain their historical workflow versions.
 
 ## Case format
 
 Add YAML files anywhere under `evals/cases/`:
 
+- `customer_feedback/`: replay repeated connection checks and the customer's
+  complete single-car collision description in both client modes. A clearly
+  described motor vehicle hitting a fixed object, without other vehicle
+  involvement clues, must extract `vehicle_count: 1` and skip count questions.
+  Complaint wording must not discard known fields or restart confirmation.
+  `python -m evals.prompt_probes --runtime --output ...` additionally replays
+  the old erroneous count question to test recovery after a user challenges it.
 - `collection_skip_known_info/`: skip known fields and clarify missing information.
+  The two files retaining the historical `single_no_inferred_count` name now
+  follow the user-approved boundary: reversing into a fixed object, without
+  other vehicle involvement clues, extracts one car. After time confirmation,
+  route to single-car photography without a separate count answer. Both cases
+  check `form.vehicle_count: 1` and reject repeated count/type questions.
 - `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
@@ -28,6 +41,14 @@ Add YAML files anywhere under `evals/cases/`:
 - `photo_button_guidance/`: button help and failure handling.
 - `photo_skip_plate_confirm/`: current photo transitions without plate confirmation.
 
+Optional semantic probes support `--exclude-case <name-fragment>`; excluded
+names are recorded separately and are never counted as passes. For the current
+quantity-only iteration, defer the historical time-anchor boundary with:
+
+```bash
+python -m evals.prompt_probes --runtime --exclude-case missing_historical_time_anchor --output evals/results/quantity-probes.json
+```
+
 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