config: subagents -> opencode/deepseek-v4-flash (zen, not tinfoil) #21

Merged
autonomic-bot merged 1 commits from config/deepseek-flash-zen into main 2026-08-16 02:40:17 +00:00
Owner

Route deepseek-v4-flash through the opencode zen subscription (opencode/deepseek-v4-flash) instead of tinfoil pay-per-use. The zen subscription is already paid for; flash consumes balance far more slowly than glm-5.2, so a full weekly run is much less likely to exhaust it (operator has reset the balance).

Completes the fleet-wide move to deepseek-flash on zen: upgrader parent (LOOP_MODEL) + report (REPORT_MODEL) in upgrader.env, and this PR sets the subagents. Supervisor stays on opencode-go/glm-5.2.

Verified: zen endpoint serves deepseek-v4-flash (HTTP 200, 1.2s, $0.0000077/35tok).

Supersedes the tinfoil routing from #20 (still on main — this just flips the provider prefix).

Route deepseek-v4-flash through the opencode zen subscription (`opencode/deepseek-v4-flash`) instead of tinfoil pay-per-use. The zen subscription is already paid for; flash consumes balance far more slowly than glm-5.2, so a full weekly run is much less likely to exhaust it (operator has reset the balance). Completes the fleet-wide move to deepseek-flash on zen: upgrader parent (LOOP_MODEL) + report (REPORT_MODEL) in upgrader.env, and this PR sets the subagents. Supervisor stays on opencode-go/glm-5.2. Verified: zen endpoint serves deepseek-v4-flash (HTTP 200, 1.2s, $0.0000077/35tok). Supersedes the tinfoil routing from #20 (still on main — this just flips the provider prefix).
autonomic-bot added 1 commit 2026-08-16 02:40:14 +00:00
Route deepseek-v4-flash through the opencode zen subscription endpoint
(opencode/deepseek-v4-flash) instead of tinfoil pay-per-use. The zen
subscription is already paid for; flash consumes the balance far more
slowly than glm-5.2 did (flash cost ~$0.0000002/tok vs glm's higher rate),
so a full weekly run is much less likely to exhaust the balance — and
the operator has reset it.

Completes the fleet-wide move: upgrader parent (LOOP_MODEL) + report
(REPORT_MODEL) in upgrader.env, and this PR sets the subagents. Supervisor
stays on opencode-go/glm-5.2.

Verified: zen endpoint serves deepseek-v4-flash (HTTP 200, 1.2s).
autonomic-bot merged commit c0b473328d into main 2026-08-16 02:40:17 +00:00
Sign in to join this conversation.
No Reviewers
No labels
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: recipe-maintainers/cc-ci#21