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)
- 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)
- 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)
- 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)
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)
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)
- 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)
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)
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
- 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
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)
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)
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)
Tools can take arbitrary time, so we need a fresh baseline after execution.
Previously, lastHeartbeat wasn't updated after tool.execute.after, causing
stalled detection to trigger immediately after long-running tools.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Remove forced monitoring restart in tool.execute.after to avoid false positive
stalled session detection when LLM legitimately completes response after tool run.
Monitoring now resumes naturally on next session/message event.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add directoryAgentsInjector to plugin event handlers
- Wire up tool.execute.after hook for directory agents injection
- Fix: Format src/index.ts with consistent semicolon style
