> It's also is a godsend if you use an MCP like oracle to automate the process of calling the Pro model on particularly tough problems
As far as I know Codex (at least the GUI) can automatically call the ChatGPT Chat models (including Astra 6 Pro), you just need to @ a ChatGPT Chat conversation from within Codex and tell it when to use it.
> There used to be a toml file workaround for Codex to extend the GPT context window to 1m, but this stopped working on the plans and only on per-token billing
Not true, it works again[1]. I confirm that it works both on 5.6 Sol and Astra 6, possibly other models too.
I actually haven't played with the GUI. I probably should now that the Linux version is in beta. My situation is kind of the reverse: I like using oracle to basically zip up my repo, ask GPT Pro to propose some sort of design or refactor based on the code, then provide a step by step implementation plan for a cheaper model to implement directly in a harness on my machine. It often takes upwards of 90 minutes to come up with something but I've never been disappointed by the results. I suppose I could do this and then save a step by referencing the oracle-created thread with the @ you mentioned
And re: the toml workaround, AWESOME! I appreciate you pointing these two things out, this is my highest-ROI HN comment thus far.