Update gpt55 and other models

[svilupp]

Added

• Added support for Anthropic's Claude Sonnet 5 model (claude-sonnet-5, alias claudes). 1M context, 128K output. Standard pricing $3/$15 per 1M input/output tokens (introductory pricing of $2/$10 applies through 2026-08-31). The claude and claudes aliases now point to this model.
• Added support for Anthropic's Claude Fable 5 model (claude-fable-5, alias claudef), the first Claude 5 family model in the new Mythos-class tier above Opus. 1M context, 128K output. Pricing: $10/$50 per 1M input/output tokens.
• Added support for Anthropic's Claude Opus 4.8 model (claude-opus-4-8, alias claudeo). 1M context, 128K output. Pricing: $5/$25 per 1M input/output tokens (unchanged from Opus 4.6). The claudeo alias now points to this model instead of claude-opus-4-6.
• Added support for OpenAI's GPT-5.5 model (gpt-5.5, alias gpt55). 1M context, 128K output. Pricing: $5/$30 per 1M input/output tokens.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 92.84%. Comparing base (e7f40ab) to head (26efa97).

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #332   +/-   ##
=======================================
  Coverage   92.84%   92.84%           
=======================================
  Files          40       40           
  Lines        3506     3506           
=======================================
  Hits         3255     3255           
  Misses        251      251           

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.