RaymondVerhoefandClaude Opus 4.7 40eff976b4 Fix: exclude temperature parameter for reasoning-tier models ...

Anthropic has deprecated the temperature parameter for their reasoning
models (claude-opus-4-7). This was causing a 400 error when analyzeGraph
called callLLM with tier: 'reasoning'.

Solution: conditionally exclude temperature from the request body when
tier === 'reasoning'. Fast and standard tiers retain their temperature
parameter.

This unblocks the "Analyse and Optimize" button in the Knowledge Graph
admin panel post-Phase-2 deployment.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-20 17:14:17 +02:00

..

assets

feat: initialize learning platform project with React, Vite, and baseline application structure

2026-05-10 10:30:30 +02:00

components

feat: phase 2 of AI pipeline hardening — tool-based structured outputs + prompt caching

2026-05-20 15:47:20 +02:00

lib

Fix: exclude temperature parameter for reasoning-tier models

2026-05-20 17:14:17 +02:00

pages

feat: phase 1 of AI pipeline hardening — single LLM client + tier-aware models

2026-05-20 13:50:09 +02:00

store

feat: phase 1 of AI pipeline hardening — single LLM client + tier-aware models

2026-05-20 13:50:09 +02:00

App.css

feat: initialize learning platform project with React, Vite, and baseline application structure

2026-05-10 10:30:30 +02:00

App.jsx

feat: show build SHA + timestamp in a small footer for deploy verification

2026-05-20 15:20:46 +02:00

index.css

feat: implement R42 chat infrastructure with Anthropic API integration and custom design system

2026-05-17 16:48:40 +02:00

main.jsx

feat: initialize learning platform project with React, Vite, and baseline application structure

2026-05-10 10:30:30 +02:00