feat: add severity classification for review comments

[hellomypastor]

Description

Add a 4-level severity system (critical / warning / suggestion / nitpick) for LLM-generated code review comments. This enables CI pipelines to gate merges based on issue severity and allows users to filter low-priority noise from review output.

Changes across the full stack:

• Model layer (internal/model/review.go): New Severity type with 4 constants, Rank() method for ordering, and ValidSeverity() validation helper.
• Tool definition (internal/config/toolsconfig/tools.json): Added severity enum parameter to code_comment tool, marked as required.
• Tool parser (internal/tool/code_comment.go): Extracts and validates severity from tool call arguments.
• Prompt engineering (internal/config/template/task_template.json): Added "Severity Classification" section to the MAIN_TASK system prompt, instructing the LLM to assign severity to every comment.
• CLI (cmd/opencodereview/flags.go): New --min-severity flag to filter comments below a threshold.
• Review pipeline (cmd/opencodereview/review_cmd.go): Applies severity filtering after line number resolution.
• Output (cmd/opencodereview/output.go): Color-coded severity badges in terminal output ([critical] red, [warning] yellow, [suggestion] cyan, [nitpick] dim). Severity field included in JSON output.

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Refactoring (no functional changes)
• Documentation update
• CI / Build / Tooling

How Has This Been Tested?

• make test passes locally
• Manual testing (describe below)

New unit tests added:

• internal/model/review_test.go — Severity rank ordering, ValidSeverity() for valid/invalid inputs
• cmd/opencodereview/output_test.go — filterBySeverity() with all threshold levels, empty input, and comments without severity

Checklist

• My code follows the project's coding style (go fmt, go vet)
• I have performed a self-review of my code
• I have added tests that prove my fix is effective or my feature works
• New and existing unit tests pass locally with my changes
• I have updated the documentation accordingly (if applicable)
• I have signed the CLA

Related Issues

None.

[github-actions]

🔍 OpenCodeReview found 2 issue(s) in this PR.

• ✅ 2 posted as inline comment(s)
• 📝 0 posted as summary (missing line info)