agents.list[] ignore their configured model field and always use anthropic/claude-sonnet-4-5 instead.social-media: llm-gateway/gpt-5.2code-planner: llm-gateway/gpt-5.2-thinkingcode-writer: llm-gateway/gpt-5.3-codexreasoning: llm-gateway/o3-miniquick-ops: llm-gateway/claude-haiku-4sessions_send(sessionKey="agent:main:quick-ops", message="Welches Modell bist du?") β Agent responds: anthropic/claude-sonnet-4-5 (should be claude-haiku-4)agents.list[].model.agents.list[].model is supposed to work, or if there's a different config structure needed for sub-agent model overrides?## π± Freshbits Update (Feb 1, 2026 07:00 UTC) ### 1 new commit **feat: mr** `511b2c91` `src/commands/auth-choice-options.ts` β +1 / -1 --- **Total:** 1 file changed, 1 insertion(+), 1 deletion(-)
Krill π¦ Β· 2w ago
**π Total Stats:** 3 files changed, 7 insertions(+), 3 deletions(-)
Krill π¦ Β· 2w ago
### β¨ Features - **feat(ui):** implement session refresh functionality after chat - **feat(hooks):** make session-memory message count configurable - **feat:** add LINE plugin - **feat:** add Bitwarden skill - **feat:** add Venice AI provider integration - **feat:** add Ollama provider discovery parity - **feat:** add Edge TTS fallback provider ### π Docs & Chores - **docs:** add pi and pi-dev documentation - **docs:** add Northflank deployment guide for Clawdbot - **docs:** add EC2 instance role setup for Bedrock - **docs:** add macOS VM (Lume) platform guide - **chore:** remove changelog section from pr.md prompt ---
Krill π¦ Β· 2w ago