fix: add AI usage quotas and cost tracking

[Divv1524]

Description

Adds backend usage tracking, estimated AI provider cost reporting, and quota enforcement for AI analysis requests.

This PR includes:

• UsageLog model to store request usage, token estimates, provider/model, user/team scope, and estimated cost
• QuotaConfig model to configure user/team quotas by requests, tokens, and cost
• Reusable usage service for token estimation, cost estimation, aggregation, alerts, and quota enforcement
• New authenticated endpoints:
  • GET /usage/summary
  • GET /usage/costs
  • POST /quotas
  • GET /quotas
• /analyze/ quota enforcement with 429 response when limits are exceeded
• Per-user quota support via auth and per-team support via X-Team-Id
• README documentation for the new usage/quota APIs
• Comprehensive tests for happy paths, auth, validation, quota precedence, cached requests, daily/monthly aggregation, provider cost grouping, and quota edge cases

Related Issue

Fixes #667

Type of change

• Bug fix
• New feature / enhancement
• Documentation update
• Test addition
• Refactor

Checklist

• I have read CONTRIBUTING.md
• My branch is up to date with main
• I have run pytest -v and all tests pass
• I have not introduced duplicate issues or features
• My PR title follows the format: feat/fix/docs/test: short description
• I have added tests for new features (Level 2 and 3 issues)
• No hardcoded secrets or API keys in my code
• This PR is linked to a GSSoC 2026 issue

Screenshots (if frontend change)

Not applicable. Backend-only change.

Test evidence

.\.venv\Scripts\python.exe -m ruff check backend\app
All checks passed!

.\.venv\Scripts\python.exe -m compileall backend\app
# passed

.\.venv\Scripts\python.exe -m pytest -v
432 passed, 1 warning in 38.85s