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>

codex-rs/core/src/config/mod.rs

@@ -24,6 +24,7 @@ use crate::features::FeaturesToml;
 use crate::git_info::resolve_root_git_project_for_trust;
 use crate::model_provider_info::LMSTUDIO_OSS_PROVIDER_ID;
 use crate::model_provider_info::ModelProviderInfo;
+use crate::model_provider_info::OLLAMA_CHAT_PROVIDER_ID;
 use crate::model_provider_info::OLLAMA_OSS_PROVIDER_ID;
 use crate::model_provider_info::built_in_model_providers;
 use crate::project_doc::DEFAULT_PROJECT_DOC_FILENAME;
@@ -648,14 +649,14 @@ pub fn set_project_trust_level(
 pub fn set_default_oss_provider(codex_home: &Path, provider: &str) -> std::io::Result<()> {
     // Validate that the provider is one of the known OSS providers
     match provider {
-        LMSTUDIO_OSS_PROVIDER_ID | OLLAMA_OSS_PROVIDER_ID => {
+        LMSTUDIO_OSS_PROVIDER_ID | OLLAMA_OSS_PROVIDER_ID | OLLAMA_CHAT_PROVIDER_ID => {
             // Valid provider, continue
         }
         _ => {
             return Err(std::io::Error::new(
                 std::io::ErrorKind::InvalidInput,
                 format!(
-                    "Invalid OSS provider '{provider}'. Must be one of: {LMSTUDIO_OSS_PROVIDER_ID}, {OLLAMA_OSS_PROVIDER_ID}"
+                    "Invalid OSS provider '{provider}'. Must be one of: {LMSTUDIO_OSS_PROVIDER_ID}, {OLLAMA_OSS_PROVIDER_ID}, {OLLAMA_CHAT_PROVIDER_ID}"
                 ),
             ));
         }
@@ -861,7 +862,7 @@ pub struct ConfigToml {
     pub experimental_compact_prompt_file: Option<AbsolutePathBuf>,
     pub experimental_use_unified_exec_tool: Option<bool>,
     pub experimental_use_freeform_apply_patch: Option<bool>,
-    /// Preferred OSS provider for local models, e.g. "lmstudio" or "ollama".
+    /// Preferred OSS provider for local models, e.g. "lmstudio", "ollama", or "ollama-chat".
     pub oss_provider: Option<String>,
 }
 

codex-rs/core/src/lib.rs

@@ -57,6 +57,7 @@ pub use model_provider_info::DEFAULT_LMSTUDIO_PORT;
 pub use model_provider_info::DEFAULT_OLLAMA_PORT;
 pub use model_provider_info::LMSTUDIO_OSS_PROVIDER_ID;
 pub use model_provider_info::ModelProviderInfo;
+pub use model_provider_info::OLLAMA_CHAT_PROVIDER_ID;
 pub use model_provider_info::OLLAMA_OSS_PROVIDER_ID;
 pub use model_provider_info::WireApi;
 pub use model_provider_info::built_in_model_providers;

codex-rs/core/src/model_provider_info.rs

@@ -265,6 +265,7 @@ pub const DEFAULT_OLLAMA_PORT: u16 = 11434;
 
 pub const LMSTUDIO_OSS_PROVIDER_ID: &str = "lmstudio";
 pub const OLLAMA_OSS_PROVIDER_ID: &str = "ollama";
+pub const OLLAMA_CHAT_PROVIDER_ID: &str = "ollama-chat";
 
 /// Built-in default provider list.
 pub fn built_in_model_providers() -> HashMap<String, ModelProviderInfo> {
@@ -278,6 +279,10 @@ pub fn built_in_model_providers() -> HashMap<String, ModelProviderInfo> {
         ("openai", P::create_openai_provider()),
         (
             OLLAMA_OSS_PROVIDER_ID,
+            create_oss_provider(DEFAULT_OLLAMA_PORT, WireApi::Responses),
+        ),
+        (
+            OLLAMA_CHAT_PROVIDER_ID,
             create_oss_provider(DEFAULT_OLLAMA_PORT, WireApi::Chat),
         ),
         (