revert: restore GPT-5.6 Sol as the default model

[mluck-openai]

Summary

Revert #1078 to restore the shared CLI/SDK default model to gpt-5.6-sol with xhigh reasoning effort.

Changes

• Restore the previous default, configuration examples, documentation, and test expectations.
• Remove the GPT-6 Sol pricing entries introduced by feat: default CLI and SDK to GPT-6 Sol xhigh #1078.
• Retain model propagation assertions for fresh and resumed Deep Scan discovery and reducer workers, updated to the restored default.

Testing

• Affected CLI/SDK tests: 453 passed, 6 platform-dependent skips, 0 failed (Bun 1.3.14).
• Isolated CLI patch tests: 75 passed, 0 failed.
• Deep Scan executor tests passed with a canonical temporary directory.
• SDK CI and production builds, type/schema/model checks, and formatting passed.
• Ruff 0.16.8 lint and format checks passed; plugin source compatibility checks and all 9 checker tests passed.
• Built CLI info --json reports gpt-5.6-sol / xhigh; git diff --check passed.
• Full SDK suite attempts are incomplete: the seeded run was stopped after overlapping plugin builds caused temporary missing-bundle failures; affected patch tests passed in isolation afterward. The remaining run was stopped after unrelated publication tests encountered sandbox restrictions on process inspection and workbench database access. No passing full-suite result is claimed.

Risk and rollout

This restores the public model default for callers without an explicit override. Explicit model and reasoning settings remain authoritative; no commands or flags change. Reverting the pricing additions also removes cost estimation and cost-limit support for explicit gpt-6-sol selection. No release or version bump is included. Draft pending hosted checks and review.

Public disclosure review

• No customer, partner, prospect, or user identities, data, or identifying details are included.
• No credentials, personal data, private source, scan findings, or nonpublic links or tickets are included.
• I reviewed the branch name, title, description, commits, changes, comments, logs, screenshots, attachments, and links for public disclosure.

[chatgpt-codex-connector]

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review	Status	Commit	Review trigger
🔒 Security Review	✅ Completed 2026-10-01T21:09:51.995245Z	19ee788	Draft marked ready

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" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.