Commit Graph

15 Commits

Author SHA1 Message Date
YeonGyu-Kim df0a9e6773 Prevent OmO from proactively implementing without explicit user request (#106)
* fix(todo-continuation-enforcer): increase delay to 5s and add write permission check (#89)

- Increase delay from 200ms to 5000ms to prevent firing too quickly before users can respond
- Add write permission check to skip continuation when previous agent lacks write/edit permissions
- Fixes destructive behavior where hook was overriding user wait commands

Resolves #89

🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)

* improve omo to only work when requested
2025-12-19 01:45:58 +09:00
YeonGyu-Kim 2b368ad84f feat(omo): improve orchestration with key triggers and tool guidance (#100)
Add Key Triggers section, improve tool selection guidance, and update
delegation table for better agent orchestration and decision making.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-19 01:02:58 +09:00
YeonGyu-Kim 17b4304a5f Expand Todo Management section with detailed guidelines
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-17 19:11:06 +09:00
YeonGyu-Kim 6ab0ff7420 refactor(agents): improve librarian agent framing as 'Reference Grep' for parallel structure with explore
- Rename 'Research Specialist' → 'Reference Grep' for consistent Grep naming pattern
- Update table headers: 'Contextual Grep (Internal)' vs 'Reference Grep (External)'
- Clarify agent distinctions with clearer column organization
- Add explicit comments in code examples showing parallel firing pattern
- Enhance prompt engineering by positioning both as peer grep tools

🤖 Generated with assistance of oh-my-opencode
2025-12-16 21:02:38 +09:00
YeonGyu-Kim 2706fe436a refactor(agents): restructure OmO system prompt with Phase-based architecture
- Reduce prompt length from 866 to ~375 lines
- Implement Phase-based execution flow (0-3)
- Add codebase maturity assessment
- Include user design challenge mechanism
- Maintain core delegation and verification protocols

🤖 Generated with assistance of OhMyOpenCode
2025-12-16 21:02:38 +09:00
YeonGyu-Kim 4112be7ad5 feat(background-task): add all parameter to cancel all running tasks at once
Allows OmO agent to cleanup all running background tasks before providing final answers.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-16 21:02:38 +09:00
YeonGyu-Kim cb360e0d05 refactor(omo): balance proactivity with user confirmation in prompt
OmO had a tendency to act without asking questions compared to Claude Code. Even in situations with implicit assumptions, it would rush into work like an unleashed puppy the moment a prompt came in. This commit enhances the Intent Gate prompt to prevent such behavior.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-16 21:02:38 +09:00
YeonGyu-Kim 689c568e52 enhance(agents): Add comprehensive guardrails, Oracle examples, and specialized playbooks to OmO prompt
- Add dedicated <Oracle> section with 4 use cases, situation-action table, and 5 concrete examples
- Add <Failure_Handling> section: Type Error Guardrails, Build/Test/Runtime protocols, Infinite Loop Prevention
- Add <Playbooks> section: 4 specialized workflows (Bugfix, Refactor, Debugging, Migration/Upgrade)
- Enhance <Anti_Patterns> section with 5 new categories (Type Safety, Error Handling, Code Quality, Testing, Git)
- Improve Oracle delegation guidance with practical patterns

🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
2025-12-15 19:14:06 +09:00
YeonGyu-Kim 906d3040a9 Restore model to claude-opus-4-5 with thinking enabled, fix maxTokens to 64000 (correct max output for Opus 4.5 per Anthropic docs)
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-15 19:14:06 +09:00
YeonGyu-Kim 424723f7ce refactor(agents): Complete rewrite of OmO system prompt with Task Complexity assessment
- Added comprehensive Task Complexity assessment before agent delegation (TRIVIAL/EXPLORATION/IMPLEMENTATION/ORCHESTRATION)
- Redefined Explore agent as 'contextual grep' - cheap, parallel background agent for internal codebase search (Level 2 in search strategy)
- Restricted Librarian agent to 3 explicit use cases: Official Documentation, GitHub Context, Famous OSS Implementation
- Added mandatory delegation gate (GATE 2.5) for ALL frontend files (.tsx/.jsx/.vue/.svelte/.css/.scss) - NO direct edits allowed
- Implemented obsessive Todo Management framework with BLOCKING evidence requirements for every action
- Introduced comprehensive Search Strategy Framework with 3-level approach (Direct Tools → Explore → Librarian)
- Restructured Blocking Gates with explicit Pre-Search gate and Pre-Completion verification
- Enhanced Delegation Rules with clear agent purposes and parallelization strategies
- Added Implementation Flow and Exploration Flow with phase-based workflows
- Introduced Decision Matrix for quick action selection
- Enhanced Anti-Patterns section with comprehensive BLOCKING rules for frontend work
- Updated Tool Selection guide with clear preferences (Direct Tools > Agent Tools)
- Improved parallel execution guidelines for explore/librarian agents
- Strengthened verification protocol with evidence requirements

🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-15 19:14:06 +09:00
YeonGyu-Kim 9f636e1abc fix(agents): enforce English prompting for all subagents (#58)
- Add Language Rule (MANDATORY) section in OmO Delegation_Rules
- Clarify that subagent prompts must always be in English
- Update background-task tool documentation with English requirement
- Update call-omo-agent tool documentation with English language rule
- LLMs perform significantly better with English prompts
- Improves consistency and performance across all agent-to-subagent communication

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-15 19:14:06 +09:00
YeonGyu-Kim aa2f9a6ca5 OmO to not to call Explore every single time, only when required 2025-12-15 19:14:06 +09:00
YeonGyu-Kim f19a7a564e Specify agents 2025-12-15 19:14:06 +09:00
YeonGyu-Kim f44555a021 feat(agents): make OmO default agent via build name hack
- Set build agent's display name to 'OmO' (keeps builtIn: true priority)
- Add OmO as subagent (actual execution target when selected)
- Remove explicit tools list from OmO agent (inherit all)
- Rename omo_agent.disable_build to omo_agent.disabled

This hack works around OpenCode's agent selection by key name.
TODO: Use config.default_agent when PR #5313 is released.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-14 21:59:17 +09:00
YeonGyu-Kim 96088381e2 feat(agents): add OmO orchestrator agent
- Add OmO agent: powerful AI orchestrator for complex task delegation
- Implements parallel background agent execution and todo-driven workflows
- Emphasizes aggressive subagent delegation with 7-section prompt structure

Co-authored-by: huynguyen03dev <huynguyen03dev@users.noreply.github.com>
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-14 17:16:32 +09:00