fix(slopguard): default Claude reviews to the 1M Opus 5.5 window

[altaywtf]

Closes #166

Default Claude model becomes claude-opus-5-5[1m]: same model, 1M context instead of Claude Code's 200K default for the bare ID. An explicit --model still wins.

Proof: claude -p --model 'claude-opus-5-5[1m]' --output-format json reports contextWindow: 1000000 (bare ID: 200000) on CLI 2.1.280; slopguard doctor --engine claude reports ready.

[chatgpt-codex-connector]

Codex Review Summary

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

Review	Status	Commit	Review trigger
📝 Code Review	✅ Completed 2026-09-23T05:36:24.386606Z	026aeee	PR opened

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.

[Copilot]

Copilot review overview

🟢 Approval recommended

The change is a small, low-risk constant update that cleanly propagates through existing model-selection logic without introducing new behavior paths.

Review effort: Lite
Findings: None

What changed in this PR

Updates slopguard’s Claude provider default model string to use the 1M-context Opus 5.5 variant by default, aligning Claude-based reviews with the intended larger context window while preserving explicit --model overrides.

Changes:

• Change DefaultClaudeModel from claude-opus-5-5 to claude-opus-5-5[1m].

File	Description
cli/​slopguard/​internal/​provider/​types.go	Switches the Claude default model constant to the 1M-context window selector.

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.