Files
oh-my-pi/packages/coding-agent/test
can1357 c4ea6c920f fix: restore Copilot prompt budgets and align task/model-registry expectations with opus 4.7
Three fixes to make CI green after the opus 4.7 and auto-bump landed:

1. github-copilot model mapper: prefer capabilities.limits.max_prompt_tokens
   over the root-level context_length field (which mirrors max_context_window_tokens, i.e.
   total window). Copilot's real /models response returns both for the gpt-5.x family, and
   context_length inflates contextWindow with the output budget. Also restore the bundled
   Copilot limits (claude-opus-4.6, gpt-5.2, gpt-5.4, gpt-5.4-mini, grok-code-fast-1) to
   the values the fixed mapper produces so tests that depend on truthful offline fallbacks
   pass. Update the two Copilot discovery tests whose payloads conflated context_length
   with prompt capacity.

2. coding-agent task schema: make the per-task assignment description context-mode-aware.
   The previous description unconditionally told agents that 'shared background belongs
   in context', which is wrong for independent mode where shared context is disabled.

3. coding-agent model-registry test: update the anthropic-latest canonical collapse case
   to claude-opus-4-7 since opus 4.7 is now the newest official opus in models.json.
2026-04-17 19:24:03 +02:00
..
2026-03-14 10:46:26 +01:00
2026-04-12 01:36:28 +02:00
WIP
2026-03-23 08:54:54 -04:00