OpenClaw v2026.4.14: OpenAI Codex/models, provider notes

v2026.4.14 changes how an agent selects, calls, or remembers a provider. The official record describes a provider, model, voice, or context change; the useful test is a small request with the provider boundary recorded.

This is a stable release line; read the exact record for migrations and fixes before applying it to a live Gateway. The release body cannot certify every local combination of provider, channel, platform, and account; use the bounded test below for the path you actually run.

Provider and model consequences

01 / OpenAI Codex/models

Source signal. add forward-compat support for gpt-5.4-pro, including Codex pricing/limits and list/status visibility before the upstream catalog catches up.

A catalog label for OpenAI Codex/models is only the first signal. Confirm the account, endpoint, context limit, and tool policy that the running Gateway actually selected.

02 / Telegram/forum topics

Source signal. surface human topic names in agent context, prompt metadata, and plugin hook metadata by learning names from Telegram forum service messages.

The operator question around Telegram/forum topics is where the reply lands after a restart. Record the conversation identifiers before testing and compare them after the channel is healthy again.

03 / Agents/Ollama

Source signal. forward the configured embedded-run timeout into the global undici stream timeout tuning so slow local Ollama runs no longer inherit the default stream cutoff instead of the operator-set run timeout.

The best check for Agents/Ollama is deliberately narrow. Run one normal case and one boundary case, then compare the result with the previous release.

04 / Models/Codex

Source signal. include apiKey in the codex provider catalog output so the Pi ModelRegistry validator no longer rejects the entry and silently drops all custom models from every provider in models.json.

Models/Codex changes a capability choice, not automatically a billing or privacy agreement. Record provider, model id, context setting, and fallback behavior before changing a default.

What changes outside the chat box

A bounded check for this version

1. Start with a disposable checkpoint: record the version, host, provider, and workspace tied to OpenAI Codex/models.
2. Check the release's migration notes and make a restorable backup before changing persistent state.
3. Use a disposable conversation for one send, one reconnect, and one retry; keep the destination identifiers with the result.
4. Leave the channel disabled after the test if its credentials or pairing were created only for this rehearsal.
5. If the result differs from the release body, stop the rollout and attach the log, screenshot, or transcript to the version record.

openclaw --version
openclaw gateway status
openclaw models

Close the loop with evidence

A useful maintenance record names the changed behavior, the behavior that stayed stable, the identity that approved the test, and the step that would undo it. Preserve that record beside the release tag.

Edge cases in this tag

Agents/Ollama. forward the configured embedded-run timeout into the global undici stream timeout tuning so slow local Ollama runs no longer inherit the default stream cutoff instead of the operator-set run timeout. Record the failure that this correction addresses before declaring the upgrade complete.

Models/Codex. include apiKey in the codex provider catalog output so the Pi ModelRegistry validator no longer rejects the entry and silently drops all custom models from every provider in models.json. This is the edge case to include in a regression check, especially when the release is pre-release.

The authoritative record is the v2026.4.14 GitHub release. The release index gives the surrounding sequence, while the model provider reference supplies the operational background.