ollama: default to Responses API for built-ins (#8798)

This is an alternate PR to solving the same problem as
<https://github.com/openai/codex/pull/8227>.

In this PR, when Ollama is used via `--oss` (or via `model_provider =
"ollama"`), we default it to use the Responses format. At runtime, we do
an Ollama version check, and if the version is older than when Responses
support was added to Ollama, we print out a warning.

Because there's no way of configuring the wire api for a built-in
provider, we temporarily add a new `oss_provider`/`model_provider`
called `"ollama-chat"` that will force the chat format.

Once the `"chat"` format is fully removed (see
<https://github.com/openai/codex/discussions/7782>), `ollama-chat` can
be removed as well

---------

Co-authored-by: Eric Traut <etraut@openai.com>
Co-authored-by: Michael Bolin <mbolin@openai.com>
This commit is contained in:
authored and GitHub committed 2026-01-13 09:51:41 -08:00
1 parent 2d56519ecd
commit fe03320791
19 files changed
+274 -14

No files matched your search

+2
View File
@@ -1599,7 +1599,9 @@ dependencies = [
"bytes",
"codex-core",
"futures",
"pretty_assertions",
"reqwest",
"semver",
"serde_json",
"tokio",
"tracing",