valknar/llmx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Never store requests (#3212)

Browse Source 
When item ids are sent to Responses API it will load them from the
database ignoring the provided values. This adds extra latency.

Not having the mode to store requests also allows us to simplify the
code.

## Breaking change

The `disable_response_storage` configuration option is removed.
This commit is contained in:
pakrym-oai
2025-09-05 10:41:47 -07:00
committed by GitHub
parent ba631e7928
commit 5775174ec2
17 changed files with 12 additions and 118 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/config.md
View File

@@ -182,7 +182,6 @@ Here is an example of a `config.toml` that defines multiple profiles:
```toml
model = "o3"
approval_policy = "untrusted"
disable_response_storage = false
# Setting `profile` is equivalent to specifying `--profile o3` on the command
# line, though the `--profile` flag can still be used to override this value.
@@ -209,7 +208,6 @@ model_provider = "openai-chat-completions"
model = "o3"
model_provider = "openai"
approval_policy = "on-failure"
disable_response_storage = true
```
Users can specify config values at multiple levels. Order of precedence is as follows:
@@ -362,14 +360,6 @@ args = ["-y", "mcp-server"]
env = { "API_KEY" = "value" }
```
## disable_response_storage
Currently, customers whose accounts are set to use Zero Data Retention (ZDR) must set `disable_response_storage` to `true` so that Codex uses an alternative to the Responses API that works with ZDR:
```toml
disable_response_storage = true
```
## shell_environment_policy
Codex spawns subprocesses (e.g. when executing a `local_shell` tool-call suggested by the assistant). By default it now passes **your full environment** to those subprocesses. You can tune this behavior via the **`shell_environment_policy`** block in `config.toml`: