Message hooks like todo-continuation-enforcer and background-notification
now preserve the agent mode from the previous message when sending follow-up
prompts. This ensures that continuation messages and task completion
notifications use the same agent that was active in the conversation.
- Export findNearestMessageWithFields and MESSAGE_STORAGE from hook-message-injector
- Add getMessageDir helper to locate session message directories
- Pass agent field to session.prompt in todo-continuation-enforcer
- Pass agent field to session.prompt in BackgroundManager.notifyParentSession
Closes#59🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
When OpenCode API doesn't return parts in message response,
read directly from filesystem using readParts(messageID).
This fixes session recovery failures where tool_use IDs couldn't
be extracted because API response had empty parts array.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Replace regex-based command blocking with environment configuration
- Add cross-platform null device support (NUL for Windows, /dev/null for Unix)
- Wrap all bash commands with non-interactive environment variables
- Only block TUI programs that require full PTY
- Update schema, README docs, and all imports/exports
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Instead of blocking commands via regex pattern matching (which caused false
positives like 'startup', 'support'), now wraps all bash commands with:
- CI=true
- DEBIAN_FRONTEND=noninteractive
- GIT_TERMINAL_PROMPT=0
- stdin redirected to /dev/null
TUI programs (text editors, system monitors, etc.) are still blocked as they
require full PTY. Other interactive commands now fail naturally when stdin
is unavailable.
Closes#55 via alternative approach.
- Prevent interactive bash commands from being executed automatically
- Block commands in tool.execute.before hook
- Register in schema and main plugin initialization
- Add findMessagesWithThinkingOnly() to detect orphan thinking messages
- Inject [user interrupted] placeholder for thinking-only messages
- Expand index offset handling from 2 to 3 attempts for better error recovery
- Use constant PLACEHOLDER_TEXT for consistency across recovery functions
- 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)
- 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)
Add .catch() to notify-send command to prevent GDBus.Error logs
when org.freedesktop.Notifications service is unavailable in WSL environments.
Fixes#47🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add stripJsonComments() to handle // comments in opencode.json
- Add findPackageJsonUp() for robust package.json discovery
- Replace import.meta.dirname with fileURLToPath(import.meta.url) for ESM compatibility
- Fix version showing 'unknown' when config contains JSONC comments
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add getLocalDevPath() and getLocalDevVersion() functions
- Improve getCachedVersion() with fallback to bundled package.json
- Display correct version in startup toast for local dev mode
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add configurable build agent hiding (omo_agent.disable_build)
- Add startup-toast hook to show version on OpenCode startup
- Fix auto-update-checker to respect version pinning
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add findFileRecursive function using native Node.js fs API
- Remove glob package from dependencies
- Add unit tests for findFileRecursive
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Disable 'task' and 'call_omo_agent' tools in BackgroundManager
- Disable recursive background operation tools in call_omo_agent sync execution
- Prevents agents from spawning background tasks or calling themselves
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Claude Code commands (user, project scope): sanitize model to undefined
- OpenCode commands (opencode, opencode-project scope): preserve model as-is
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Disable 'task' and 'call_omo_agent' tools in BackgroundManager
- Disable recursive background operation tools in call_omo_agent sync execution
- Prevents agents from spawning background tasks or calling themselves
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Refactor grep-output-truncator into a general-purpose tool-output-truncator
that applies dynamic truncation to multiple tools based on context window usage.
Truncated tools:
- Grep, safe_grep (existing)
- Glob, safe_glob (new)
- lsp_find_references (new)
- lsp_document_symbols (new)
- lsp_workspace_symbols (new)
- lsp_diagnostics (new)
- ast_grep_search (new)
Uses the new dynamic-truncator utility from shared/ for context-aware
output size limits based on remaining context window tokens.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Extract and generalize dynamic output truncation logic from grep-output-truncator.
Provides context window-aware truncation that adapts based on remaining tokens.
Features:
- truncateToTokenLimit(): Sync truncation with configurable header preservation
- getContextWindowUsage(): Get current context window usage from session
- dynamicTruncate(): Async truncation that queries context window state
- createDynamicTruncator(): Factory for creating truncator instance
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Port ripgrep auto-installation feature from original OpenCode (sst/opencode).
When ripgrep is not available, automatically downloads and installs it from
GitHub releases.
Features:
- Platform detection (darwin/linux/win32, arm64/x64)
- Archive extraction (tar.gz/zip)
- Caches binary in ~/.cache/oh-my-opencode/bin/
- New resolveGrepCliWithAutoInstall() async function
- Falls back to grep if auto-install fails
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Fix background_output to check completion status before block flag
- Update call_omo_agent return message to correctly indicate block=false as default
- Add system notification guidance in return message
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
When an invalid or unregistered agent is passed to background_task or
call_omo_agent, OpenCode crashes with "TypeError: undefined is not an
object (evaluating 'agent.name')". This fix:
- Validates agent parameter is not empty before launching
- Catches prompt errors and returns friendly error message
- Notifies parent session when background task fails
- Improves error message to guide user on resolution
Fixes#37🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add BUILD_AGENT_PROMPT_EXTENSION for orchestrator-focused main agent behavior
- Introduce OverridableAgentName type to allow build agent customization
- Update config schema to support build agent override in oh-my-opencode.json
- Inject orchestration prompt into build agent's system prompt
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Change TARGET_TOOLS and AGENT_TOOLS to Set<string> for O(1) lookup
- Normalize tool names to lowercase for case-insensitive comparison
- Remove unnecessary parentSessionID guard that blocked main session triggers
- Fixes issue where Glob/Grep tool calls weren't showing agent usage reminder
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Implements hook that tracks whether explore/librarian agents have been used in a session.
When target tools (Grep, Glob, WebFetch, context7, websearch_exa, grep_app) are called
without prior agent usage, appends reminder message recommending parallel background_task calls.
State persists across tool calls and resets on session compaction, allowing fresh reminders
after context compaction - similar to directory-readme-injector pattern.
Files:
- src/hooks/agent-usage-reminder/: New hook implementation
- types.ts: AgentUsageState interface
- constants.ts: TARGET_TOOLS, AGENT_TOOLS, REMINDER_MESSAGE
- storage.ts: File-based state persistence with compaction handling
- index.ts: Hook implementation with tool.execute.after and event handlers
- src/config/schema.ts: Add 'agent-usage-reminder' to HookNameSchema
- src/hooks/index.ts: Export createAgentUsageReminderHook
- src/index.ts: Instantiate and register hook handlers
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Remove always-zero tool call count from status display
- Show last tool only when available
- Add status-specific notes:
- running: remind no explicit wait needed (system notifies)
- error: indicate task failed, check last message
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
The agent was missing from AgentNameSchema and AgentOverridesSchema,
causing model overrides in oh-my-opencode.json to be silently dropped.
Co-authored-by: Amp <amp@ampcode.com>
- 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)
