feat: unify rewrite mode and prepare 0.2.0 release

[OneNoted]

Summary

• unify the public rewrite flow onto a single rewrite mode
• shift cue-led opening handling to LLM adjudication instead of deterministic replacement
• bump the crate to 0.2.0 and update docs/config examples

Validation

• cargo fmt --all -- --check
• cargo test
• cargo test --no-default-features --features osd
• cargo check --no-default-features --features osd
• cargo clippy --all-targets --all-features -- -D warnings
• cargo clippy --all-targets --no-default-features --features osd -- -D warnings
• cargo publish --dry-run --allow-dirty --locked

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: b7137411d2

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]

Preserve rewrite policy settings during model selection

update_config_rewrite_selection now overwrites rewrite.policy_path, rewrite.glossary_path, and rewrite.default_correction_policy with defaults every time a model is selected (via setup or rewrite-model select). In the unified rewrite mode these fields are active runtime settings, so this silently discards user customization and can change rewrite behavior after an unrelated model switch. This should keep existing values unless they are unset/missing.

Useful? React with 👍 / 👎.

[OneNoted]

Superseded by #3, which reflects the published 0.2.1 release from current main.