Tom Boucher 1a499aecb2 fix: clamp 'minimal' thinking level to 'low' for gpt-5.x models (#688) ... gpt-5.x models (via Copilot/OpenAI/Azure) don't support 'minimal' as a reasoning effort level — they only accept 'none', 'low', 'medium', 'high', and 'xhigh'. Setting /thinking minimal with gpt-5.4 causes a 400 error. The openai-codex-responses provider already had this clamping, but the openai-responses and azure-openai-responses providers passed the value through unclamped. Add clampReasoningForModel() to both providers that maps 'minimal' to 'low' for gpt-5.x models, matching the existing behavior in openai-codex-responses. Fixes the bug portion of #688		2026-03-16 16:02:54 -04:00
..
native	perf: optimize discovery and interactive hot paths	2026-03-14 16:03:44 -05:00
pi-agent-core	fix(agent-core): await event queue in tool hooks for safe parallel execution (#439)	2026-03-14 21:16:17 -06:00
pi-ai	fix: clamp 'minimal' thinking level to 'low' for gpt-5.x models (#688)	2026-03-16 16:02:54 -04:00
pi-coding-agent	Merge pull request #666 from jeremymcs/fix/v2.19.0-phase1-quick-wins	2026-03-16 12:44:17 -06:00
pi-tui	fix: move @types/mime-types to devDependencies, align chalk versions	2026-03-16 13:31:15 -05:00