You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Azure provider silently uses local compaction instead of POST /responses/compact #17773
When using an Azure OpenAI provider (name = "Azure" or an Azure base URL), Codex silently falls back to local model-generated compaction instead of calling POST /responses/compact, even though Azure's Responses API fully supports it. No error or warning is shown.
Root Cause
The compaction routing gate in core/src/compact.rs checks only is_openai():
pub(crate)fnshould_use_remote_compact_task(provider:&ModelProviderInfo) -> bool{
provider.is_openai()// true only when name == "OpenAI" (exact, case-sensitive)}
The standard Azure configuration requires name = "Azure" to activate attach_item_ids via is_azure_responses_endpoint() (case-insensitive check in codex-api/src/provider.rs). But that same name makes is_openai() return false, silently disabling remote compaction. The two checks are mutually exclusive — no single name value satisfies both.
name
is_openai()
is_azure_responses_endpoint()
Result
"OpenAI"
✓
✗
Remote compaction on, attach_item_ids off (breaks Azure)
Activity
Support remote compaction for Azure responses providers (openai#17958)
Support remote compaction for Azure responses providers (openai#17958)
Support remote compaction for Azure responses providers (openai#17958)