feat(github-agent): add command usefulness feedback loop

[JSONbored]

Background

Gittensory needs to learn which answers are useful without making feedback part of deterministic scoring. Feedback helps improve product quality and value reporting.

Goal

Allow maintainers/miners to mark GitHub agent answers useful or not useful and feed that into product analytics.

Current Behavior

There is no structured usefulness signal for command responses.

Desired Behavior

Users can provide lightweight feedback and operators can see command usefulness trends.

Implementation Requirements

• Support reaction-based or link-based feedback where practical.
• Deduplicate feedback by actor/answer.
• Store feedback separately from deterministic scoring.
• Expose aggregate usefulness metrics.
• Do not include private source or secrets.

Public/Private Output Boundaries

Public GitHub output must never include wallets, hotkeys, payout/reward estimates, raw trust scores, public score estimates, private reviewability, private scoreability context, or farming language. Private API/MCP/control-panel surfaces may show authenticated scoreability, blockers, projections, and evidence, but must not claim guaranteed payout outcomes.

Acceptance Criteria

• Feedback is tracked without source or secret leakage.
• Feedback does not change deterministic scoring directly.
• Reports show command usefulness.
• Tests cover duplicate feedback and authorization.

Testing Requirements

• npm run test:ci must pass.
• Global coverage must remain at or above 97% for lines, statements, functions, and branches.
• Aim for 98%+ branch coverage locally.
• Add tests for every new branch, fallback path, sanitizer rule, and regression.
• Add invariant/property-style tests when behavior depends on sorting, gating, scoring, source-upload safety, public/private boundaries, or telemetry privacy.
• MCP/local tooling must prove source contents are not uploaded when local metadata is involved.
• Public GitHub output must be tested against forbidden language: wallet, hotkey, raw trust score, payout, reward estimate, farming, private reviewability, and public score estimate.