Agent
Use OpenRouter Fusion's panel-and-judge workflow through OpenCode's tool and file loop. This bundled seat uses the general-budget preset. Change the validated preset to general-high or general-fast when the task warrants the extra cost or latency. Fusion is intended for research, critique, and synthesis; use a…
Agent
This optional seat uses OpenCode as the tool-loop gateway to OpenRouter's paid z-ai/glm-5.3-flash model, the model formerly previewed as Ox Alpha. Pricing, discounts, model availability, context limits, and rate limits remain live provider facts. Refresh the roster and usage evidence rather than assuming the preview…
Agent
This historical seat remains pinned to the exact former stealth/ox-alpha identity so old receipts are never relabeled. The preview ended and the route now returns 404. Summon refuses this retired seat before provider contact and points callers to the distinct openrouter-glm-5-3-flash-opencode successor.
Agent
General-purpose coding companion on Claude Sonnet. Quick, balanced, gets things done.
Agent
Turns a task into a concrete, ordered implementation plan on Claude Opus (deep reasoning); investigates the code but does not modify files.
Agent
Composes a PR title and description from a diff or branch state on Claude Sonnet. Concise, accurate, ready to paste.
Agent
Fast, balanced code review on Claude Sonnet. Lighter than reviewer (codex) or adversarial-reviewer (codex). Use for quick second opinions and PR self-review.
Agent
This seat is pinned to the live-verified gemini-3.7-flash-high model. It is Summon's primary evidence/research seat and the recommended fast secondary voice for /council; it is not the chairman, policy arbiter, or a provider-execution seat. The agy backend does not enforce read-only permissions, so use this yolo seat…
Agent
Reviews code/diffs; verifies behavior via tests, linters, and PowerShell; reports file:line findings.
Agent
Deep security audit on Claude Opus: threat boundaries, OWASP issues, secrets, and dependencies. Reports risks; does not modify code.
Agent
Pinned GPT-5.6 Sol seat for adversarial architecture, release, and reliability reviews. The explicit model pin is intentional: a Sol review must not inherit the Codex account default.
Agent
Pinned GPT-5.6 Terra seat for balanced, cost-conscious code and release reviews. Terra is an explicit candidate route; the dispatch receipt must still prove the provider-served model before the result is treated as verified.
Agent
Writes tests for given code and runs them to confirm they pass.
Agent
This optional, broad-authority seat targets the explicit Z.AI Coding Plan model selector through the locally configured OpenCode provider. Use it for code, research, or review work only inside a disposable clone, isolated worktree, or other reversible boundary. Do not point it at shared Git state, credentials…
Agent
This optional direct Z.AI Coding Plan seat makes one OpenAI-compatible text request to the coding-only endpoint. It does not provide a tool loop, filesystem access, session resume, or a sandbox. Give it self-contained text such as a design question, pasted diff, or review packet; use the OpenCode Z.AI seat for toolful…
Agent
This historical name was misleading: the native ZCode CLI uses its locally configured provider and does not certify that a Z.AI Coding Plan model served the turn. Use zcode-native for the generic preview route, or an explicit zai-glm-5-3-flash seat when a reviewed GLM-5.3 Flash selector is required.
Agent
This optional native ZCode seat uses the locally configured ZCode provider. ZCode is ambient/multi-provider until its app-server model selection and terminal provider provenance are reviewed end-to-end. It intentionally does not claim a provider, a model pin, or GLM-5.3 Flash. Use the explicit direct or OpenCode Z.AI…