Sub-Agents May Not Allow Model Selection
robleclerc · x · 2026-07-13
This thread points out that in the "sol" orchestration system, when spawning sub-agents, you cannot choose the specific model behind them, which is a major transparency/control issue.
Key points:
- spawnagent only allows specifying task, prompt, and context copy amount.
- The API does not expose a model= parameter.
- No receipt confirms which model actually runs.
- The thinking/reasoning level cannot be independently set, only inheriting from the parent or platform default.
The discussion highlights that in multi-agent orchestration, many seemingly configurable "roles" lack fully independent model control.
More from coding & agent
- Codex helps build Valdiluce, an open-world game with climbing, gliding and gondolas — Dimillian · 2026-07-22
- HeyGen adds a media-sourcing skill for coding agents with 75k images and 10k tracks — HeyGen · 2026-07-22
- Agent search bottlenecks are now about variance, not raw latency — rohanpaul_ai · 2026-07-22
- LangSmith adds tracing for Pipecat, LiveKit, OpenAI Realtime, and Gemini Live — LangChain · 2026-07-22
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22
- Annotated transcript of a Claude Code team interview is now available — trq212 · 2026-07-22