Commit Graph

12 Commits

Author SHA1 Message Date
YeonGyu-Kim d188688dd8 feat(keyword-detector): enhance ultrawork mode with zero-tolerance execution rules
Add 'ZERO TOLERANCE FOR SHORTCUTS' section consolidating rigorous execution requirements:
- Explicit prohibitions table: mocking/stubbing, scope reduction, partial completion
- Lazy placeholder elimination (no TODO comments, ..., etc in code)
- Rigorous execution mandate: original intent parsing, no task too large, honest assessment
- Failure recovery protocol: stop, identify, create TODOs, complete 100%
- Strengthens commitment to honest, complete delivery over shortcuts

Expands from previous prove-yourself mode rules into comprehensive execution framework.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-01-03 14:33:26 +09:00
YeonGyu-Kim f26bf24c33 feat(keyword-detector): enhance ultrawork mode instructions with TODO emphasis
- Restructure ultrawork mode message with clearer priorities
- Add TODO IS YOUR LIFELINE section emphasizing TodoWrite usage
- Enhance agent utilization principles and execution rules
- Improve clarity of zero tolerance failure policies

🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-01-03 12:51:09 +09:00
YeonGyu-Kim 794b5263c2 fix(keyword-detector): remove word boundary requirement for ulw/ultrawork detection 2026-01-02 00:10:46 +09:00
YeonGyu-Kim b51d0bdf65 Revert "feat(keyword-detector): improve ultrawork-mode prompt with LSP in main session execution"
This reverts commit b2adda6e90.
2025-12-31 13:22:38 +09:00
YeonGyu-Kim b2adda6e90 feat(keyword-detector): improve ultrawork-mode prompt with LSP in main session execution
- Add LSP IN MAIN SESSION execution rule for parallel codemap building
- Restructure WORKFLOW step 2 as PARALLEL PHASE with two concurrent tracks:
  - Background agents spawned via background_task for exploration/research
  - Main session using LSP tools (lsp_document_symbols, lsp_workspace_symbols, lsp_goto_definition, lsp_find_references, lsp_hover) for codebase understanding
- Enables agent to build comprehensive codebase context while background agents explore in parallel

🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
2025-12-31 13:17:53 +09:00
YeonGyu-Kim 6bc9a31ee4 feat(ultrawork-prompt): add TDD workflow integration with conditional applicability (#246)
- Add TDD cycle specification (SPEC → RED → GREEN → REFACTOR → NEXT)
- Add applicability check for test infrastructure and implementation tasks
- Add TDD execution rules (TEST FIRST, MINIMAL IMPLEMENTATION, etc.)
- Add 'NO TEST DELETION' to ZERO TOLERANCE FAILURES section
- Add skip notation requirement for non-applicable tasks

Addresses: #243

🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
2025-12-28 00:14:06 +09:00
YeonGyu-Kim c804da43cf ulw 2025-12-25 19:05:15 +09:00
YeonGyu-Kim 8b8f21e794 refactor(keyword-detector): consolidate completion enforcement from prove-yourself into ultrawork mode
- Remove dedicated prove-yourself mode (frustration keyword detector)
- Add ZERO TOLERANCE FAILURES section to ultrawork mode
- Consolidate completion enforcement rules: no scope reduction, no partial completion, no assumed shortcuts, no premature stopping
- Simplify constants by removing separate frustration handler

🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
2025-12-20 11:37:31 +09:00
YeonGyu-Kim eccbfa5550 feat(keyword-detector): add prove-yourself mode for frustration keywords
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-19 16:42:56 +09:00
YeonGyu-Kim 85a3111253 refactor(keyword-detector): relax analyze-mode recommendations for practical agent usage
Reduce analyze-mode agent recommendations from aggressive (10+ agents, 3+ explore, 3+ librarian, 2+ general, 3+ oracle) to moderate (1-2 explore, 1-2 librarian, oracle only if complex) for simple requests like "살펴봐줘". Previous settings caused unnecessary agent spawning and token consumption for straightforward analysis tasks. New recommendation prioritizes context gathering with direct tools (Grep, AST-grep) for typical workflows, reserving oracle consultation for genuinely complex scenarios (architecture, multi-system, debugging after failures).

🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-19 13:38:54 +09:00
YeonGyu-Kim 7e4b633bbd feat(agents): add OmO and OmO-Plan as primary agents, demote build/plan
- OmO: Primary orchestrator (Claude Opus 4.5)
- OmO-Plan: Inherits ALL settings from OpenCode's plan agent at runtime
  - description appended with '(OhMyOpenCode version)'
  - Configurable via oh-my-opencode.json agents.OmO-Plan
- build/plan: Demoted to subagent when OmO enabled
- Add plan and OmO-Plan to OverridableAgentNameSchema

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-14 22:17:41 +09:00
YeonGyu-Kim 0fcfe21b27 refactor(hooks): rename ultrawork-mode to keyword-detector with multi-keyword support
- Detect ultrawork, search, analyze keywords (EN/KO/JP/CN/VN)
- Add session-based injection tracking (once per session)
- Remove unnecessary state management

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-14 11:38:33 +09:00