xinyin025/LangBot
1
0
Fork 0
mirror of https://github.com/langbot-app/LangBot.git synced 2026-06-27 16:04:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

test(skills): add debug chat timing and isolation probes

Browse Source
This commit is contained in:
huanghuoguoguo
2026-06-25 13:34:30 +08:00
parent 7e36869494
commit 9b0f5b36f3
10 changed files with 1501 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/docs/user-guide.md
+4
View File
@@ -123,6 +123,7 @@ Controlled Debug Chat message-path load gate:
bin/lbs suite plan langbot-debug-chat-load-gate
bin/lbs test run langbot-fake-provider-debug-chat-load --run-id langbot-fake-load-local
bin/lbs test run langbot-fake-provider-debug-chat-slow-load --run-id langbot-fake-slow-local
bin/lbs test run langbot-fake-provider-debug-chat-cross-pipeline-isolation --run-id langbot-fake-cross-pipeline-local
bin/lbs test run langbot-fake-provider-debug-chat-fault-recovery --run-id langbot-fake-fault-local
bin/lbs test run langbot-space-debug-chat-concurrency-smoke --run-id langbot-space-smoke-local
```
@@ -132,6 +133,9 @@ OpenAI-compatible fake provider, creates the matching provider/model/pipeline,
then sends concurrent WebSocket Debug Chat messages through the real backend.
Use `langbot-fake-provider-debug-chat-slow-load` to measure the same path under
deterministic streaming latency. Use
`langbot-fake-provider-debug-chat-cross-pipeline-isolation` to verify that
concurrent Debug Chat traffic on two pipelines does not leak assistant
responses across pipeline boundaries. Use
`langbot-fake-provider-debug-chat-fault-recovery` to inject bounded provider
HTTP failures and confirm later Debug Chat requests recover.
Use `langbot-space-debug-chat-concurrency-smoke` only as a low-volume live