Enhance evaluation runner with transcript handling and new case formats

- Updated the evaluation runner to support live dialogue printing and transcript saving in both Markdown and JSON formats.
- Introduced new data classes for managing transcripts and their components, improving structure and readability.
- Modified existing YAML case files to align with the new direct client mode and updated stage codes.
- Added new test cases for the direct client mode, ensuring comprehensive coverage of user interactions.

evals/README.md

@@ -2,27 +2,29 @@
 
 The evaluation runner calls a live FastAPI service backed by FastGPT. For now,
 each conversation step checks only the SSE `stage_code.nextStageCode` value.
+During the run it also prints the live dialogue and saves transcripts.
 
 ## Case format
 
 Add YAML files anywhere under `evals/cases/`:
 
 ```yaml
-name: browser_addon_example
-clientMode: browser_addon
+name: direct_initial_stage
+clientMode: direct
 
 steps:
-  - input: hi
+  - input: 新对话
     expect:
-      stageCode: browser_addon.1001
+      stageCode: "1001"
 
-  - input: 继续
+  - input: 继续办理
     expect:
-      stageCode: browser_addon.1002
+      stageCode: "1002"
 ```
 
-Steps in one file share the same generated `sessionId`. Different cases always
-use different session IDs.
+`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.
 
 ## Run
 
@@ -41,8 +43,32 @@ 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
 ```
 
+## 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.