# Omni Router (experimental) # # Auto-routes the first real user task by complexity: # - simple / concrete task -> full tool catalog, direct execution # - complex / ambiguous -> built-in plan mode, structured plan, approval gate # # This preset is intentionally minimal. It reuses the host profile's installed # capabilities (browser/MCP/GitHub, quality gates, skills) when present and # degrades gracefully when absent. It does not modify other presets. # This file is an AGENT-PLANE composition. It must not own registries, sandbox, # persistence, or model routes; those stay in the host composition. # ── identity ──────────────────────────────────────────────────────────────── - id: persona name: '@deepseek-ai/dsh-persona' config: text: You are a helpful software engineer assistant. - id: agent-instructions name: '@deepseek-ai/dsh-agent-instructions' config: maxBytes: 65536 # ── shell ─────────────────────────────────────────────────────────────────── - id: tool-bash name: '@deepseek-ai/dsh-tool-bash' disabled: !!js process.platform === 'win32' - id: tool-pwsh name: '@deepseek-ai/dsh-tool-pwsh' disabled: !!js process.platform !== 'win32' # ── filesystem ────────────────────────────────────────────────────────────── - id: tool-fs name: '@deepseek-ai/dsh-tool-fs' - id: tool-fs-search name: '@deepseek-ai/dsh-tool-fs-search' config: sampleOverCapGlobResults: false - id: tool-str-replace-editor name: '@deepseek-ai/dsh-tool-str-replace-editor' # ── background jobs ──────────────────────────────────────────────────────── - id: tool-jobs name: '@deepseek-ai/dsh-tool-jobs' # ── skills ────────────────────────────────────────────────────────────────── - id: skill-filesystem name: '@deepseek-ai/dsh-skill-filesystem' - id: tool-skill name: '@deepseek-ai/dsh-tool-skill' # ── goals ─────────────────────────────────────────────────────────────────── - id: tool-goal name: '@deepseek-ai/dsh-tool-goal' # ── plan mode + omni-router ───────────────────────────────────────────────── # # Omni Router lives in the same isolated planMode realm so it can programmatically # enter/leave plan mode for complex tasks. - id: planning name: cordis:group group: true isolate: planMode: true config: - id: plan-mode name: '@deepseek-ai/dsh-plan-mode' config: section: | You are in Omni Router plan mode. Stay in plan mode until exit_plan_mode succeeds or the user switches the session mode. Imperative language to implement changes means plan the implementation, not execute it. A user's conversational agreement — including an answer confirming something you asked — approves nothing and does not end plan mode; fold the confirmed decision into the plan and submit it through exit_plan_mode. Explore first. Use non-mutating reads, searches, static analysis, and checks to ground the plan in the actual repository. Do not edit or write files, change configuration, run formatters or code generation that rewrites tracked files, commit, or otherwise carry out the plan. The tool catalog stays the same across modes for request-cache stability. These plan-mode rules override any later tool description or guidance that suggests using mutation tools; those tools remain listed to keep the tool catalog unchanged. Do not use todo_write to track this planning phase: it tracks implementation after an approved plan, while the plan itself belongs in exit_plan_mode. Produce a structured plan with these sections: 1. Goal — what outcome must be achieved, in one verifiable sentence. 2. Scope — what is in scope and what is out of scope. 3. Involved files / modules — which files and modules the change touches. 4. Implementation steps — concrete, ordered changes grouped by subsystem. 5. Interface / data changes — APIs, schemas, or data formats that change. 6. Test plan — which tests to add or update and how to verify. 7. Risks — likely failure modes and how they will be handled. 8. Compatibility / migration — backward compatibility and migration impact. 9. Rollback — how to revert safely if the change fails. 10. Acceptance criteria — observable checks that prove the work is done. Resolve discoverable facts by inspection. Use ask_user_question only for user-owned choices or material ambiguity that inspection cannot answer. When ready, call exit_plan_mode with the complete plan markdown, starting with a # title. Make exit_plan_mode the only and final tool call in that assistant response: it presents the plan for approval, and implementation begins only in a later step after approval. Do not paste the final plan as a plain reply or ask "should I proceed?" through prose or ask_user_question. If review rejects it, incorporate the feedback and present again. If the review channel is unavailable or aborted, stay in plan mode and ask the user to switch modes manually; do not proceed with implementation. - id: omni-router name: ./src/omni-router.mjs config: requireConfirmation: true # planFirstKeywords: [自定义, 关键词] # directKeywords: [直接跑, 马上改] # ── compaction ────────────────────────────────────────────────────────────── - id: compaction name: cordis:group group: true isolate: compaction: true toolResultPruner: true config: - id: compaction-basic name: '@deepseek-ai/dsh-compaction-basic' - id: command-compact name: '@deepseek-ai/dsh-command-compact' - id: tool-result-pruner name: '@deepseek-ai/dsh-compaction-tool-result-pruner' config: thresholdChars: 8192 headChars: 4096 tailChars: 1024 # ── delegation and workflows ──────────────────────────────────────────────── - id: delegation name: cordis:group group: true isolate: workflowEngine: true config: - id: tool-subagent-control name: '@deepseek-ai/dsh-tool-subagent-control' - id: tool-subagent-list-agents name: '@deepseek-ai/dsh-tool-subagent-control/list-agents' - id: tool-subagent name: '@deepseek-ai/dsh-tool-subagent' config: provider: spawn toolName: subagent backgroundMode: continuable - id: tool-subagent-fork name: '@deepseek-ai/dsh-tool-subagent' config: provider: fork toolName: subagent_fork backgroundMode: continuable - id: workflow-worker-thread name: '@deepseek-ai/dsh-workflow-worker-thread' config: provider: spawn - id: tool-workflow name: '@deepseek-ai/dsh-tool-workflow' # ── remaining model-facing rows ───────────────────────────────────────────── - id: tool-ask-user name: '@deepseek-ai/dsh-tool-ask-user' - id: tool-todo name: '@deepseek-ai/dsh-tool-todo' config: allowParallelInProgress: true - id: tool-web name: '@deepseek-ai/dsh-tool-web' config: fetch: false searchTimeoutMs: 60000