- Add grep_app MCP configuration (https://mcp.grep.app)
- Update explore agent with grep_app usage guide:
- Always launch 5+ grep_app calls with query variations
- Always add 2+ other search tools for verification
- grep_app is fast but potentially outdated, use as starting point only
- Update README.md and README.ko.md with grep_app documentation
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Upgrade librarian agent to use claude-sonnet-4 instead of claude-haiku-4-5
for improved code search and documentation capabilities.
Closes#22🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Add a new tool and agent for analyzing media files (PDFs, images, diagrams)
that require visual interpretation beyond raw text.
- Add `multimodal-looker` agent using Gemini 2.5 Flash model
- Add `look_at` tool that spawns multimodal-looker sessions
- Restrict multimodal-looker from calling task/call_omo_agent/look_at tools
Inspired by Sourcegraph Ampcode's look_at tool design.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Replace direct parts[idx].text modification with injectHookMessage
- Context now injected via filesystem (like UserPromptSubmitHook)
- Preserves original user message without modification
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Actually inject THINKING_CONFIGS into message (was defined but unused)
- Add maxTokens: 128000 for Anthropic (required for extended thinking)
- Add maxTokens: 64000 for Amazon Bedrock
- Track thinkingConfigInjected state
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
When "ultrawork" or "ulw" keyword is detected in user prompt:
- Injects ULTRAWORK_CONTEXT with agent-agnostic guidance
- Executes AFTER CC hooks (UserPromptSubmit etc.)
- Follows existing hook pattern (think-mode style)
Key features:
- Agent orchestration principles (by capability, not name)
- Parallel execution rules
- TODO tracking enforcement
- Delegation guidance
Closes#31🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add retry logic for 403 GCP permission errors (max 10 retries)
- Implement exponential backoff with 2s cap (200ms → 400ms → 800ms → 2000ms)
- Detect patterns: PERMISSION_DENIED, Cloud AI Companion API not enabled, etc.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Change warning to allow Google Auth setup (google_auth: true) by default
- Clarify that only model changes and feature disabling require explicit user request
- Add missing disabled_hooks documentation to README.ko.md
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add prompt field to BackgroundTask to store original prompt
- Add lastMessage/lastMessageAt to TaskProgress for real-time monitoring
- Extract last assistant message during polling
- Update formatTaskStatus() to display prompt (truncated 300 chars) and
last message (truncated 500 chars) with timestamp
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add Google Auth subsection to Configuration in README.md/README.ko.md
- Add google_auth and lsp options to oh-my-opencode.schema.json
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Fixes#30. OpenCode's plugin loader treats subpath exports like
"oh-my-opencode/google-auth" as separate npm packages, causing
BunInstallFailedError.
Solution: Enable Google auth via `google_auth: true` in
oh-my-opencode.json instead of a separate subpath plugin.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add isRetryableResponse() to detect SUBSCRIPTION_REQUIRED 403 errors for retry handling
- Remove JSDoc comments from isRetryableError() for clarity
- Add debug logging for request/response details (streaming flag, status, content-type)
- Refactor transformStreamingResponse() to use TransformStream for true streaming
- Replace buffering approach with incremental chunk processing
- Implement createSseTransformStream() for line-by-line transformation
- Reduces memory footprint and Time-To-First-Byte (TTFB)
- Update SSE content-type detection to include alt=sse URL parameter
- Simplify response transformation logic for non-streaming path
- Add more granular debug logging for thought signature extraction
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add message-converter.ts for OpenAI messages to Gemini contents conversion
- Use SKIP_THOUGHT_SIGNATURE_VALIDATOR as default signature (CLIProxyAPI approach)
- Restore loadCodeAssist API call to get user's actual project ID
- Improve debug logging for troubleshooting
- Fix tool normalization edge cases
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Try both targetIndex and targetIndex-1 to handle system message offset
- Remove 'last assistant message' skip logic (API error means it's not final)
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Add step-by-step instructions for Anthropic, Google Gemini (Antigravity OAuth),
and OpenAI (Codex Auth) authentication setup.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Checks npm registry for latest version on session.created, invalidates
cache and shows toast notification when update is available.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Change background_output default from block=true to block=false
- Add documentation about system auto-notification on task completion
- Clarify that block=false returns full status info, not empty
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Gemini 3 Pro requires thoughtSignature on function call blocks in
subsequent requests. This commit:
- Add thought-signature-store for session-based signature storage
- Extract signature from both streaming (SSE) and non-streaming responses
- Inject signature into functionCall parts on subsequent requests
- Maintain consistent sessionId per fetch instance
Debug logging available via ANTIGRAVITY_DEBUG=1
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Previously, token calculation accumulated ALL assistant messages' tokens,
causing incorrect usage display (e.g., 524.9%) after compaction.
Now uses only the last message's input tokens, which reflects the actual
current context window usage.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Separate Google Antigravity auth to 'oh-my-opencode/google-auth' subpath
- 'oh-my-opencode/auth' now exports OpenAI Codex auth plugin
- Implement dynamic port allocation to avoid port conflicts
- Add userAgent, requestId, sessionId fields for Antigravity API compatibility
- Add debug logging for troubleshooting (ANTIGRAVITY_DEBUG=1)
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Pass-through path (non-string body) now preserves Authorization header.
This ensures authentication works even when request transformation is bypassed.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Handle both SDK response patterns: .data wrapper vs direct array
- Add null/empty message checks for robustness
- Improve type safety with explicit interface definitions
- Prevent errors when messages array is undefined
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Implement createGoogleAntigravityAuthPlugin factory function
- Add OAuth method with PKCE for Google authentication
- Create custom fetch interceptor loader for Antigravity API
- Update auth.ts to export Google Antigravity plugin as default
- Update barrel export in antigravity/index.ts
- Add Google Antigravity auth location to AGENTS.md
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Remove unused chat message notification handler
- Remove formatDuration and formatNotifications helpers
- Simplify to event-only handling
- Remove chat.message hook call from main plugin
Background task notifications now rely on event-based system only.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Rename src/codex-auth.ts → src/auth.ts
- Update package.json exports: ./codex-auth → ./auth
- Update build script to include auth.ts
Users can now use oh-my-opencode/auth as OpenAI auth plugin.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Previously only checked assistant messages for empty content.
Now checks all messages except the final assistant message,
following Anthropic API rules.
Fixes: "messages.N: all messages must have non-empty content" error
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Rename omo-task to call-omo-agent with mandatory run_in_background parameter
- Implement background mode using BackgroundManager (fire-and-forget abort)
- Implement sync mode with existing subagent logic
- Fix background_cancel: use fire-and-forget abort to prevent parent session interruption
- Add call_omo_agent to tool disable list in explore/librarian agents
- Add call_omo_agent to tool disable list in BackgroundManager
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Implements retry logic with up to 5 attempts when compaction fails.
Uses exponential backoff strategy (2s → 4s → 8s → 16s → 30s).
Shows toast notifications for retry status and final failure.
Prevents infinite loops by clearing state after max attempts.
🤖 GENERATED WITH ASSISTANCE OF OhMyOpenCode
Background task tool이 child session을 생성할 때 background_task, background_output, background_cancel 도구를 자동으로 비활성화합니다. OpenCode Task tool 패턴과 동일하게 무한 재귀 호출을 방지합니다.
- manager.ts: promptAsync 호출 시 tools 설정 추가
- index.ts: 불필요한 agent 레벨 disable 설정 제거 (manager에서 처리)
- notification: tool calls 카운트 제거 (정확하게 트래킹되지 않음)
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Merge background_status into background_output with block parameter
- Replace background_result references with background_output throughout codebase
- Update tool descriptions to reflect new unified API
- Remove background-tasks.json (memory-based only)
- Simplify notification messages and tool usage instructions
session.prompt() fails due to response Zod validation.
promptAsync is fire-and-forget, no response parsing.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
TUI API sends to active session (could be subagent).
Use getMainSessionID() to explicitly target main session.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
session.prompt() fails with validation errors in background context.
Switch to TUI API which directly manipulates the main session input.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Previous implementation had too many defensive checks that blocked
normal cases. Simplified to: Toast -> 200ms delay -> session.prompt()
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Replace promptAsync() with session.prompt() for visible TUI updates
- Add main session check to skip subagent sessions
- Add session status idle check before sending prompt
- Add 200ms debounce with re-check to prevent race conditions
- Fallback to pending queue when session is busy
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Use `promptAsync` instead of `prompt` to avoid session state conflicts
- Use `tui.showToast` for immediate visible feedback
- Hack: Trigger `tui.submitPrompt` after message injection to force TUI refresh and trigger AI response
- Update `BackgroundManager` to accept `PluginInput` for directory access
prompt() waits for AI response, ensuring message is actually processed.
Added response logging to debug if message delivery works.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
promptAsync() doesn't show visible message to user.
Use tui.showToast() instead for immediate visible notification.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
session.get() doesn't return status field - it was always undefined.
Now using session.status() API which returns { type: 'idle' | 'busy' | 'retry' }
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Change prompt() to promptAsync() for parent session notification
- Only mark 404 errors as permanent task failure
- Add defensive progress initialization
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add notifyParentSession() to send message to parent session via prompt()
- Agent receives completion notification immediately, not waiting for next chat.message
- Includes task ID, description, duration, tool calls in notification
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Replace unreliable event-based tracking with 2-second polling
- Use SDK session.get() to detect completion (status === idle)
- Use SDK session.messages() to count tool_use parts for progress
- Auto-start polling on launch, auto-stop when no running tasks
- Resume polling on restore if running tasks exist
Fixes: Child session events not reaching plugin event handler
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Add comprehensive documentation about omo_task tool feature in both English and Korean READMEs.
- Document omo_task tool purpose: spawn explore/librarian as subagents
- Explain use case: agents can delegate specialized tasks to subagents
- Note recursion prevention: explore and librarian cannot use omo_task directly
- Add to Agents section under Tools for discoverability
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Register omo_task tool in main plugin and disable it for explore/librarian agents to prevent infinite recursion.
- Export createOmoTask from src/tools/index.ts
- Initialize omo_task in main plugin with ctx
- Spread omo_task into builtinTools export
- Add recursion prevention: disable omo_task tool for explore agent config
- Add recursion prevention: disable omo_task tool for librarian agent config
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Implement omo_task tool that allows main agents (oracle, frontend-ui-ux-engineer, etc.) to spawn explore or librarian as subagents.
- Add constants: ALLOWED_AGENTS, TASK_TOOL_DESCRIPTION_TEMPLATE
- Add types: AllowedAgentType, OmoTaskArgs, OmoTaskResult
- Implement createOmoTask function with session management
- Support both new session creation and existing session continuation
- Include proper error handling and logging
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Automatically disables these Claude Code hooks that duplicate oh-my-opencode functionality:
- inject_rules.py (replaced by rules-injector hook)
- inject_readme.py (replaced by directory-readme-injector hook)
- inject_knowledge.py (replaced by directory-agents-injector hook)
- remind*rules*.py (replaced by rules-injector hook)
Users can override via opencode-cc-plugin.json if needed.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add findMessageByIndexNeedingThinking for precise message targeting
- Detect "expected X found Y" error pattern for thinking block order
- Remove isLastMessage skip - recovery now handles final assistant messages
- Simplify orphan detection: any non-thinking first part is orphan
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* feat(agents): enhance librarian and explore prompts with parallel execution and evidence-based citations
Librarian agent enhancements:
- Add mandatory 5+ parallel tool execution requirement
- Add WebSearch integration for latest information
- Add repository cloning to /tmp for deep source analysis
- Require GitHub permalinks for all code citations
- Add evidence-based reasoning with specific code references
- Enhanced gh CLI usage with permalink construction
Explore agent enhancements:
- Add mandatory 3+ parallel tool execution requirement
- Extensive Git CLI integration for repository analysis
- Add git log, git blame, git diff commands for exploration
- Add parallel execution examples and best practices
* feat(agents): add LSP and AST-grep tools to librarian and explore prompts
Librarian agent:
- Added LSP tools section (lsp_hover, lsp_goto_definition, lsp_find_references, etc.)
- Added AST-grep section with pattern examples for structural code search
- Updated parallel execution examples to include LSP and AST-grep tools
- Added guidance on when to use AST-grep vs Grep vs LSP
Explore agent:
- Added LSP tools section for semantic code analysis
- Added AST-grep section with examples for TypeScript/React patterns
- Updated parallel execution examples to include 6 tools
- Added tool selection guidance for LSP and AST-grep
* fix(agents): remove explore agent references from librarian prompt
Subagents cannot call other agents, so replaced all Explore agent
references with direct tool usage (Glob, Grep, ast_grep_search).
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Add Zod schema validation following Anthropic Agent Skills Spec v1.0
- Include basePath in skill output for path resolution
- Simplify tool description and output format
- Add validation error logging for invalid skills
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Implements README.md injection similar to existing AGENTS.md injector.
Automatically injects README.md contents when reading files, searching
upward from file directory to project root.
Closes#14🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Enables automatic session summarization when Anthropic token limits are exceeded.
The hook detects token limit errors and triggers compact operation on session idle.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Replace blocking await with non-blocking timer scheduling to handle race
condition between session.idle and session.error events. When ESC abort
occurs, session.error immediately cancels the pending timer, preventing
unwanted continuation prompts.
Changes:
- Add pendingTimers Map to track scheduled continuation checks
- Cancel timer on session.error (especially abort cases)
- Cancel timer on message.updated and session.deleted for cleanup
- Reduce delay to 200ms for faster response
- Maintain existing Set-based flag logic for compatibility
This fixes the issue where ESC abort would not prevent continuation
prompts due to event ordering (idle before error)
- Extract message index from Anthropic error messages (messages.N format)
- Sort messages by time.created instead of id for accurate ordering
- Remove last message skip logic that prevented recovery
- Prioritize recovery targets: index-matched > failedMsg > all empty
- Add error logging for debugging recovery failures
Fixes issue where 'messages.83: all messages must have non-empty content' errors were not being recovered properly due to incorrect message ordering and overly restrictive filtering.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Replace multiple Set-based tracking with explicit SessionStatus state machine
- Implement setTimeout+clearTimeout pattern for robust race condition handling
- SessionStatus tracks: idle → continuation-sent or aborted states
- Increase grace period to 500ms to accommodate event ordering delays
- Add cleanupSession utility for proper resource cleanup
This addresses ESC abort not canceling continuation prompts when session.idle
arrives before session.error event, which can occur due to async event processing
in OpenCode plugin system
100% port verification via Oracle agent parallel checks:
- PreToolUse: recordToolUse(), isHookDisabled(), Object.assign(), error message
- PostToolUse: recordToolResult(), isHookDisabled(), permissionMode, title field
- Stop: isHookDisabled(), parentSessionId, error/interrupt state tracking
- UserPromptSubmit: interrupt checks, recordUserMessage(), log messages
All four hooks now match opencode-cc-plugin/src/plugin/*.ts exactly.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add chat.message handler to createClaudeCodeHooksHook factory
- Integrate executeUserPromptSubmitHooks() for user prompt processing
- Use injectHookMessage() for file system based message injection
- Add sessionFirstMessageProcessed tracking for title generation skip
- Register chat.message hook in plugin entry point
This completes 100% port of Claude Code hooks from opencode-cc-plugin.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Port post-tool-use.ts from opencode-cc-plugin (200 lines)
- Implement executePostToolUseHooks() with full transcript support
- Include temp file cleanup in finally block
- Preserve all exit code handling and output fields
- Update notepad.md with Task 5 completion log
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add snake-case.ts: objectToSnakeCase, objectToCamelCase utilities
- Add tool-name.ts: transformToolName with PascalCase conversion
- Add pattern-matcher.ts: findMatchingHooks for hook config matching
- Add hook-disabled.ts: isHookDisabled for hook config validation
- Add temporary stub types at src/hooks/claude-code-hooks/types.ts
- Export all new utilities from src/shared/index.ts
Stub types will be replaced with full implementation in Task 1.
Import paths adjusted from opencode-cc-plugin structure to oh-my-opencode.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
YeonGyu-Kim
