pjandro/OmniRoute
1
0
Fork 0
mirror of https://github.com/diegosouzapw/OmniRoute.git synced 2026-08-08 08:12:20 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix(test): align emergency fallback budget-exhaustion test with #6912 max_tokens normalization (#6967)

Browse Source 
The test asserted both max_tokens and max_completion_tokens=4096 on the
nvidia/openai/gpt-oss-120b emergency fallback request. Commit a34fb6b3e
(#6912, merged into this release tip) added a symmetric normalization in
chatCore.ts that renames/deletes the redundant max_completion_tokens field
whenever the target provider supportsMaxTokens() (nvidia does), so only
max_tokens reaches the upstream request. The old dual-field assertion is
an outdated contract, not a regression. Align the test to the new
intentional behavior while keeping the max_tokens=4096 cap assertion as
the fallback-cap guard.
This commit is contained in:
Diego Rodrigues de Sa e Souza
2026-07-12 20:46:23 -03:00
parent 7a5b51be68
commit f34ddb0cf2
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tests/unit/chat-route-coverage.test.ts
View File

@@ -444,7 +444,10 @@ test("handleChat uses the emergency fallback model on budget exhaustion", async
assert.equal(seenBodies.length, 2);
assert.equal(seenBodies[1].model, "openai/gpt-oss-120b");
assert.equal(seenBodies[1].max_tokens, 4096);
assert.equal(seenBodies[1].max_completion_tokens, 4096);
// nvidia supports the legacy `max_tokens` field (#6912 symmetric normalization in
// chatCore.ts), so the redundant `max_completion_tokens` is renamed away rather than
// sent alongside it — only one output-token field reaches the upstream request.
assert.equal(seenBodies[1].max_completion_tokens, undefined);
assert.equal(json.choices[0].message.content, "Emergency fallback answered");
});