Introduce a new dynamic prompt generation system for Sisyphus orchestrator
that leverages agent metadata for intelligent delegation. This revives the
dynamic-sisyphus-agent-prompt branch with comprehensive refactoring.
Changes:
- Add AgentPromptMetadata, AgentCategory, AgentCost, DelegationTrigger types
- Create sisyphus-prompt-builder with dynamic prompt generation logic
- Add AGENT_PROMPT_METADATA exports to all agent modules (oracle, librarian,
explore, frontend-ui-ux-engineer, document-writer, multimodal-looker)
- Refactor sisyphus.ts to use buildDynamicSisyphusPrompt()
- Add AvailableAgent type export for type safety
This enables Sisyphus to make intelligent agent selection decisions based on
agent capabilities, costs, and delegation triggers, improving orchestration
efficiency.
🤖 Generated with assistance of OhMyOpenCode
(https://github.com/code-yeongyu/oh-my-opencode)
When overriding an agent's model to a different provider, the agent
now automatically gets provider-appropriate reasoning options:
- GPT models: `reasoningEffort`, `textVerbosity`
- Anthropic models: `thinking` with `budgetTokens`
## Why utils.ts changes are required
The original flow merges overrides onto pre-built agent configs:
mergeAgentConfig(sisyphusAgent, { model: "gpt-5.2" })
// Result: { model: "gpt-5.2", thinking: {...} }
The `thinking` config persists because it exists in the pre-built
`sisyphusAgent`. GPT models ignore `thinking` and need `reasoningEffort`.
The fix: call the agent factory with the resolved model, so the factory
can return the correct provider-specific config:
buildAgent(createSisyphusAgent, "gpt-5.2")
// Result: { model: "gpt-5.2", reasoningEffort: "medium" }
Closes#144🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Changed agent tools configuration from include pattern (listing allowed tools)
to exclude pattern (listing disabled tools only). This ensures MCP tools like
websearch_exa, context7, and grep_app are available to agents by default.
Affected agents: librarian, oracle, explore, multimodal-looker
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Restrict background_task tool access for all spawned subagents (oracle, explore, librarian, frontend-ui-ux-engineer, document-writer, multimodal-looker) to prevent potential infinite recursion and unintended background task creation.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Add task: false to oracle agent's tools configuration to prevent the oracle agent from calling the task() tool, which could lead to recursive self-invocation.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
