fix: allow large validation and patch responses

[mldangelo-oai]

Accept Codex skill events and completed responses without the previous 1 MiB event or 256 KiB response limits. Validation and patching now process the normal JSONL stream directly instead of terminating an otherwise successful Codex process.

Keep final-response selection, credential-safe failure summaries, and interruption handling unchanged.

Validation:

• Full SDK suite: 978 passed, 11 expected skips.
• Focused skill-command suite: 12 passed, including malformed events above 1 MiB, completed responses above 2 MiB, and child-process completion after stdout closes.
• TypeScript and focused Prettier checks passed.

[mldangelo-oai]

@codex review

[mldangelo-oai]

@codex security review

[chatgpt-codex-connector]

Codex Review: Didn't find any major issues. Chef's kiss.

Reviewed commit: 41078d8a98

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Security review completed. No security issues were found in this pull request.

Reviewed commit: 41078d8a98

View security finding report

Only the user who started this review can view the report in Codex.

ℹ️ About Codex security reviews in GitHub

This is an experimental Codex feature. Security reviews are triggered when:

• You comment "@codex security review"
• A regular code review gets triggered (for example, "@codex review" or when a PR is opened), and you’re opted in so security review runs alongside code review

Once complete, Codex will leave suggestions, or a comment if no findings are found.

[mldangelo-oai]

@codex review

[chatgpt-codex-connector]

Codex Review: Didn't find any major issues. Can't wait for the next one!

Reviewed commit: 8699fa0ea0

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Security review completed. No security issues were found in this pull request.

Reviewed commit: 8699fa0ea0

View security finding report

Only the user who started this review can view the report in Codex.

ℹ️ About Codex security reviews in GitHub

This is an experimental Codex feature. Security reviews are triggered when:

• You comment "@codex security review"
• A regular code review gets triggered (for example, "@codex review" or when a PR is opened), and you’re opted in so security review runs alongside code review

Once complete, Codex will leave suggestions, or a comment if no findings are found.

[mldangelo-oai]

Superseded by #334, which removes the skill-output limits entirely and also simplifies the related CLI input and configuration limits. Thanks for taking the broader cleanup, @ianw-oai.