lee/puter
1
0
Fork 0
mirror of https://github.com/HeyPuter/puter.git synced 2026-09-12 08:15:58 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

test(ai): point the provider-level replay test at the real driver fallback test

Browse Source 
The comment claimed the fallback loop cannot be driven from a test — false
since ChatCompletionDriver.test.ts gained a two-attempt fallback test that
drives the actual loop. Say where that test lives instead.

Co-Authored-By: Claude Fable 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
404oops
2026-08-28 01:09:14 +02:00
co-authored by Claude Fable 5
parent 04d12d9524
commit 07998c32ed
1 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/backend/drivers/ai-chat/providers/claude/ClaudeProvider.test.ts
+4 -3
View File
@@ -471,9 +471,10 @@ describe('ClaudeProvider.complete request shape', () => {
// reuses one messages array across attempts, so if attempt 1 strips
// `reasoning_details` in place, attempt 2 sends a message with no
// thinking blocks and Anthropic rejects the continuation. Two
// sequential calls over one shared array reproduce that directly — the
// harness wires only one provider per model, so the real fallback loop
// cannot be driven from here.
// sequential calls over one shared array reproduce that at the
// provider level; the real fallback loop is driven end-to-end by
// "hands every fallback attempt the same messages array" in
// ChatCompletionDriver.test.ts.
const { provider } = makeProvider();
messagesCreateMock
.mockResolvedValueOnce(baseResponse)