GPT-6 Astra output quality dropped by half after account-level capacity throttling (same prompt, effort and client core)

What version of the Codex App are you using (From “About Codex” dialog)?

26.903.71938, bundling codex-cli 0.153.4. The two good runs below (09-08 and 09-09) were on 26.901.51231 with the same codex-cli 0.153.4.

What subscription do you have?

ChatGPT Pro

What platform is your computer?

macOS 26.5.2, Apple Silicon (arm64)

What issue are you seeing?

After my account was throttled with "Selected model is at capacity" (fully blocked on 2026-09-10 from 11:06 to about 18:00 UTC+8, intermittent since), gpt-6-astra produces much shallower work on this account. With the same prompt, the same reasoning effort and the same client core, output tokens, reasoning tokens and result quality all dropped by roughly half or more. The model also stopped verifying its own work.

Task (Chinese prompt): 创建一个HTML，内容是svg绘制一个鹈鹕骑自行车的2D动画，放到桌面上，以你模型名字命名文件 ("Create an HTML file with an SVG 2D animation of a pelican riding a bicycle, save it to the Desktop and name it after your model"). The 09-08 run and the 09-11 23:33 run used only the first sentence, word for word. The other runs used the full prompt. Screenshots of the 09-08 and 09-11 23:33 results are attached below.

Token counts are main-thread totals summed from the rollout token_count events. Both desktop ultra runs spawned one sub-agent, which is excluded on both sides. One of the three CLI runs was cut off by a capacity error after writing its file, so its tokens are not included.

What I ruled out:

• Reasoning effort. Every sampling request in logs_2.sqlite carries the selected effort: high for the high runs, ultra for the ultra runs. There is no silent reset to medium (compare #44668).
• Model field and fallback. Every sampling request is sent as gpt-6-astra. There are no fallback or model-switch events in the logs.
• service_tier. It is not set in any of these runs, so none of them used priority.
• Client. The core binary is codex-cli 0.153.4 in all runs. The desktop shell changed, but the codex exec runs bypass the desktop app and the user config, and they show the same drop.
• Context. The projectless desktop context on 09-08 and 09-11 differs only in plugin and skill list updates and a new "Inline Artifact Follow-Ups" formatting section. Adding the 09-09 repo's AGENTS.md back in a CLI run did not restore the output: 11.4 KB versus 24.8 KB.
• Prompt. On the same day, gpt-5.6-sol at ultra with the exact same prompt produced a 21.9 KB file, in the same range as the pre-throttling Astra output.

What steps can reproduce the bug?

On the affected account, run:

codex exec --ignore-user-config --ephemeral --skip-git-repo-check -C "$(mktemp -d)" -s workspace-write -m gpt-6-astra -c 'model_reasoning_effort="ultra"' --json '创建一个HTML，内容是svg绘制一个鹈鹕骑自行车的2D动画，放到当前目录下，以你模型名字命名文件'

Compare the output tokens, reasoning tokens and file size with the pre-09-10 runs listed below. On 09-11 all three CLI runs landed at 8.8–11.4 KB, against 24.8 KB for the same prompt and effort on 09-09.

What is the expected behavior?

The same model at the same reasoning effort should work at a comparable depth before and after a capacity event. On this account before 09-10, Astra at high used about 7.6k output tokens and checked its own result in the browser, and Astra at ultra used about 14k output tokens.

If capacity is being managed by lowering the reasoning budget or serving a different model, the client should say so instead of labeling the response gpt-6-astra at the selected effort.

Additional information

Caveats:

• The sample is small: 2 runs before throttling and 6 after, and SVG generation is noisy. Still, all 6 post-throttling runs, including ultra, fall below the pre-throttling high run.
• I can't see which model actually served these requests, because the client only records the model it asked for (see #44598). The knowledge-cutoff question doesn't help either: on this account both gpt-6-astra and gpt-5.5 answer "June 2024".

Thread IDs:

• 09-08 high, good: 01a080b3-baaf-74a1-912d-b9c29135ea27
• 09-09 ultra, good: 01a08593-d43a-7b83-9844-d0dde12688e9
• 09-11 high, degraded: 01a0903c-b518-7310-b242-ab1bac153be4
• 09-11 ultra, degraded: 01a0903f-b7cf-7491-b331-15b8f3323a7c
• 09-11 23:33 high, identical prompt to 09-08, degraded: 01a09119-e84a-7570-aded-a11eb18fedd5

Related: #43329 (suspected Astra degradation), #43337 (account-specific capacity errors), #44598 (serving-model provenance).

Start with the codex exec reproduction command and the account-specific runs described in the issue, then compare the referenced logs_2.sqlite data and related issues #43329, #43337, and #44598. Done means determining whether capacity events change the served model or reasoning budget and identifying how that state should be exposed to the client.