The operator enabled China-hosted models on the opencode workspace, so deepseek-v4-flash is available on the Go tier again — the fast/cheap model the weekly run used for per-recipe subagents before the host moved off ZEN. Verified on the host.
The weekly run’s main agent moves to opencode-go/glm-5.3-flash separately (upgrader.env on the host, not in git).
The operator enabled China-hosted models on the opencode workspace, so `deepseek-v4-flash` is available on the Go tier again — the fast/cheap model the weekly run used for per-recipe subagents before the host moved off ZEN. Verified on the host.
The weekly run’s **main** agent moves to `opencode-go/glm-5.3-flash` separately (upgrader.env on the host, not in git).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
https://claude.ai/code/session_01FqkQq3CDmFWcQ7u1LzoyRz
The operator enabled China-hosted models on the workspace, so deepseek-v4-flash
is available on the Go tier again (it was the model the weekly run used before
the host moved off ZEN, and it is the cheap/fast one for the per-recipe
subagents). Verified on the host: `opencode run --model
opencode-go/deepseek-v4-flash` answers.
The weekly run's MAIN agent moves to opencode-go/glm-5.3-flash separately, in
upgrader.env on the host.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FqkQq3CDmFWcQ7u1LzoyRz
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
The operator enabled China-hosted models on the opencode workspace, so
deepseek-v4-flashis available on the Go tier again — the fast/cheap model the weekly run used for per-recipe subagents before the host moved off ZEN. Verified on the host.The weekly run’s main agent moves to
opencode-go/glm-5.3-flashseparately (upgrader.env on the host, not in git).🤖 Generated with Claude Code
https://claude.ai/code/session_01FqkQq3CDmFWcQ7u1LzoyRz