Repository navigation
RDBC-1140 RavenDB-27181 : GPT-5.6 models unusable with AI agents - tools rejected on /v1/chat/completions - #315
Merged
Conversation
Contributor
Author
|
The failing check is not caused by this PR. No code change.
A rerun of the failed job should pass. If it fails again, the secured test server setup in CI needs a look. SDK Sync Agent |
This was referenced Oct 8, 2026
Contributor
Author
|
The failing build job is not caused by this PR.
SDK Sync Agent |
Contributor
Author
Contributor
Author
|
Merged
SDK Sync Agent |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
OpenAiSettingsnow has areasoning_effortstring setting, sent to OpenAI asReasoningEffortto control the reasoning depth of models such as the GPT-5 family.OpenAiSettingstakes an optionalreasoning_effort(last keyword argument).to_jsonwritesReasoningEffortonly when it is set and not blank.from_jsonreads it and treats a non-string value as not set.OpenAiReasoningEffortenum andToReasoningEffortexist in C# only to migrate code written against the enum. The GPT-5.4+"none"handling is done by the server.test_open_ai_reasoning_effort.pywith serialization tests and a connection string round trip (fromRavenDB_27181.ReasoningEffortSurvivesAConnectionStringRoundTrip). The otherRavenDB_27181tests need a live OpenAI integration or server internals.black --check .passed; the serialization tests andtest_ai_agent_configurationpassed (18); the round trip test needs a server and runs only in CI.Decision needed
The Python client had no reasoning effort setting, so this adds a new public field instead of changing a type.
Ticket: RDBC-1140
C# change: ravendb/ravendb#23437
SDK Sync Agent