Compare commits

...

131 Commits

Author SHA1 Message Date
github-actions[bot]
2d23a81926 release: v0.3.0 2025-12-09 12:51:28 +00:00
YeonGyu-Kim
31cb8616c2 chore: bump version to 0.2.0
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 21:47:21 +09:00
YeonGyu-Kim
1932257f82 docs(readme): add comprehensive Claude Code compatibility documentation
- Add new 'Claude Code Compatibility' section to both README.md and README.ko.md
- Document hooks integration (PreToolUse, PostToolUse, UserPromptSubmit, Stop)
- Document configuration loaders (Command, Skill, Agent, MCP loaders)
- Document data storage (Todo management, Transcript logging)
- Simplify 'Other Features' section by moving loaders to new section
- Clean up temporary planning files in local-ignore/

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 21:47:01 +09:00
YeonGyu-Kim
5a793bb526 fix(hooks): align Claude Code hooks with opencode-cc-plugin reference
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)
2025-12-09 19:00:01 +09:00
YeonGyu-Kim
2ec351d0d8 feat(hooks): implement UserPromptSubmit with chat.message hook and injectHookMessage
- 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)
2025-12-09 18:20:13 +09:00
YeonGyu-Kim
441fc1a219 feat(hooks): integrate Claude Code hooks with plugin system
- Create factory function createClaudeCodeHooksHook()
- Wire tool.execute.before → executePreToolUseHooks
- Wire tool.execute.after → executePostToolUseHooks
- Wire event (session.idle) → executeStopHooks
- Register hooks in src/index.ts
- Claude hooks execute first in handler chain

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 18:10:30 +09:00
YeonGyu-Kim
bd67419d1d feat(features): add hook message injector
- Port hook-message-injector from opencode-cc-plugin (4 files)
- constants.ts: XDG-based path definitions (MESSAGE_STORAGE, PART_STORAGE)
- types.ts: MessageMeta, OriginalMessageContext, TextPart interfaces
- injector.ts: injectHookMessage() implementation with message/part storage
- index.ts: Barrel export
- Self-contained module with no import path changes needed
- Preserves XDG_DATA_HOME environment variable support
- Preserves message fallback logic for incomplete originalMessage

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 18:02:45 +09:00
YeonGyu-Kim
dca98121ac feat(hooks): add UserPromptSubmit and Stop executors
- Port user-prompt-submit.ts from opencode-cc-plugin (118 lines)
- Port stop.ts from opencode-cc-plugin (119 lines)
- Preserve recursion prevention logic (<user-prompt-submit-hook> tags)
- Preserve inject_prompt support (message injection, stop prompt injection)
- Preserve stopHookActiveState management (per-session state)
- Import path adjustments: ../types → ./types, ../../config → ./plugin-config
- All exit code handling preserved (exitCode 2 → block, etc.)

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 18:00:16 +09:00
YeonGyu-Kim
3fcfedcec0 feat(hooks): add PostToolUse hook executor
- 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)
2025-12-09 17:55:06 +09:00
YeonGyu-Kim
530c4d63d5 feat(hooks): add PreToolUse hook executor
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 17:48:28 +09:00
YeonGyu-Kim
e0b43380cc feat(hooks): add Claude hooks config, transcript, and todo
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 17:41:39 +09:00
YeonGyu-Kim
a27cac96d5 feat(hooks): add Claude Code hooks type definitions
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 17:36:12 +09:00
YeonGyu-Kim
fef7f4ca03 feat(shared): add Claude hooks command executor and utilities
- 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)
2025-12-09 17:31:15 +09:00
YeonGyu-Kim
e147be7ed4 feat: update comment-checker to v0.5.0
BREAKING CHANGE: Docstrings are now detected as code smell.
See: https://github.com/code-yeongyu/go-claude-code-comment-checker/releases/tag/v0.5.0

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 16:59:22 +09:00
YeonGyu-Kim
124c3b3e8f docs: fix documentation inconsistencies identified by Oracle
- Add source path annotations to Command/Skill/Agent/MCP Loaders
- Add Session State feature documentation
- MCP Loader paths verified (match loader.ts: ~/.claude/.mcp.json, ./.mcp.json, ./.claude/.mcp.json)

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 16:59:22 +09:00
YeonGyu-Kim
5678e0bac6 docs(readme): document new claude-code feature loaders
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 16:59:22 +09:00
YeonGyu-Kim
207435450c refactor(index): integrate session-state module and remove local variables
- Add imports: agent-loader, mcp-loader, session-state, logger
- Remove local session variables (mainSessionID, currentSessionID, currentSessionTitle)
- Use setter/getter functions from session-state module
- Add agent loading in config hook (loadUserAgents, loadProjectAgents)
- Add MCP loading in config hook (loadMcpConfigs)
- Replace console.error with logger

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 16:59:22 +09:00
YeonGyu-Kim
376bf363af feat(features): add claude-code-agent-loader, mcp-loader, session-state 2025-12-09 16:59:22 +09:00
YeonGyu-Kim
c7a65af475 refactor(features): rename command-loader and skill-loader with claude-code prefix 2025-12-09 16:59:22 +09:00
YeonGyu-Kim
8e7447deee feat(shared): add file-based logger utility 2025-12-09 16:59:22 +09:00
YeonGyu-Kim
15a748b817 docs: add missing hooks and features to README
Add 4 missing hooks documentation:
- Think Mode: auto-detect deep thinking requests
- Anthropic Auto Compact: auto-compact context
- Empty Task Response Detector: handle empty responses
- Grep Output Truncator: prevent output overflow

Add 2 missing features documentation:
- Command Loader: load commands from multiple paths
- Skill Loader: load skills as executable commands

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 16:59:22 +09:00
YeonGyu-Kim
c0e0dc1f95 feat: integrate command/skill loaders and think-mode hook in main entry
- Add loadCommands() and loadSkills() to config
- Register think-mode hook for UserPromptSubmit event

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 16:59:22 +09:00
YeonGyu-Kim
7059407cbc feat(hooks): export createThinkModeHook from index
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 16:59:22 +09:00
YeonGyu-Kim
589cf60252 feat(hooks): add think-mode hook for automatic model switching
Detects thinking keywords (ultrathink, deepthink, etc.) and switches
to thinking-capable models automatically.

Supports model patterns:
- claude-sonnet-4-0 -> claude-sonnet-4-0-max-thinking
- claude-sonnet-4-20250514 -> claude-sonnet-4-20250514-max-thinking

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 16:59:22 +09:00
YeonGyu-Kim
e5cdaa5192 feat(tools): export slashcommand and skill tools from index
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 16:59:22 +09:00
YeonGyu-Kim
340eb30147 feat(tools): add skill tool for invoking skills in conversation
Provides 'skill' tool that invokes skills loaded by skill-loader.
Skills expand into detailed instructions when invoked.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 16:59:22 +09:00
YeonGyu-Kim
e72b927ccb feat(tools): add slashcommand tool for executing slash commands
Provides 'slashcommand' tool that executes commands loaded by command-loader.
Handles shell injection and file reference resolution.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 16:59:22 +09:00
YeonGyu-Kim
3c6ffe5d9c feat(skill-loader): add skill loader that converts skills to commands
Skills are loaded from:
- ~/.claude/skills/ (user scope)
- .claude/skills/ (project scope)

Each skill directory contains SKILL.md with frontmatter metadata.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 16:59:22 +09:00
YeonGyu-Kim
938a3709e1 feat(command-loader): add slash command loader from multiple paths
Load commands from 4 directory scopes:
- .opencode/command/ (opencode-project)
- .claude/commands/ (project)
- ~/.config/opencode/command/ (opencode)
- ~/.claude/commands/ (user)

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 16:59:22 +09:00
YeonGyu-Kim
47f218e33f feat(shared): add shared utilities for command and skill loading
- frontmatter.ts: YAML frontmatter parser
- file-reference-resolver.ts: resolve @file references in markdown
- command-executor.ts: execute shell commands in markdown
- model-sanitizer.ts: sanitize model names for OpenCode compatibility

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 16:59:22 +09:00
github-actions[bot]
e07a25baa4 release: v0.1.31 2025-12-09 05:42:03 +00:00
YeonGyu-Kim
08ede0a28d deps: bump @code-yeongyu/comment-checker to 0.4.4
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 14:41:07 +09:00
github-actions[bot]
a711d58289 release: v0.1.30 2025-12-09 02:50:19 +00:00
YeonGyu-Kim
431ec14991 docs: update notepad with cleanup task logs
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 11:49:17 +09:00
YeonGyu-Kim
62cae8114d refactor(comment-checker): simplify binary path resolution and add separator warning
- Remove platform-specific package lookup logic
- Remove homebrew path resolution
- Add code smell warning for comment separators

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 11:49:11 +09:00
YeonGyu-Kim
e6eafe267a refactor(ast-grep): remove NAPI-based tools
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 11:49:00 +09:00
YeonGyu-Kim
e4ef832405 feat(hooks): add anthropic-auto-compact hook
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 11:48:53 +09:00
YeonGyu-Kim
ef6d67645e refactor(hooks): remove pulse-monitor hook
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 11:48:46 +09:00
YeonGyu-Kim
227d93f106 docs(readme-ko): clarify nested AGENTS.md injection behavior with example
Added directory tree example showing how multiple AGENTS.md files are
collected and injected in hierarchical order when reading nested files.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 10:38:05 +09:00
github-actions[bot]
edff922afb release: v0.1.29 2025-12-09 01:37:46 +00:00
YeonGyu-Kim
45bdcf3580 docs(readme): clarify nested AGENTS.md injection behavior with example
Added directory tree example showing how multiple AGENTS.md files are
collected and injected in hierarchical order when reading nested files.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 10:36:34 +09:00
YeonGyu-Kim
b07dd22093 fix(pulse-monitor): reset heartbeat after tool execution to prevent false positives
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)
2025-12-09 10:36:34 +09:00
YeonGyu-Kim
c7d29fea48 refactor(mcp): remove unused builtinMcps export
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 10:36:34 +09:00
YeonGyu-Kim
55675497a5 refactor(session-recovery): remove unused ThinkingPart interface and fallbackRevertStrategy function
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 10:36:34 +09:00
YeonGyu-Kim
ae2d347d81 refactor(lsp): remove unused formatWorkspaceEdit import
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2025-12-09 10:36:34 +09:00
github-actions[bot]
2683de825a release: v0.1.28 2025-12-08 08:52:28 +00:00
YeonGyu-Kim
0b5c8250ca fix(pulse-monitor): prevent false positive stalled detection after tool execution
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)
2025-12-08 17:51:06 +09:00
github-actions[bot]
66fcd8570b release: v0.1.27 2025-12-08 08:01:03 +00:00
YeonGyu-Kim
5cd3f0cbf2 docs: add Directory AGENTS.md Injector hook documentation
🤖 GENERATED BY [OPENCODE](https://opencode.ai/)
2025-12-08 17:00:02 +09:00
YeonGyu-Kim
9a9512b705 test: add test directory with sample files 2025-12-08 17:00:02 +09:00
YeonGyu-Kim
6ece7476ef feat(hooks): add empty-task-response-detector hook 2025-12-08 17:00:02 +09:00
YeonGyu-Kim
9ed23d4037 feat(hooks): implement directory-agents-injector hook 2025-12-08 17:00:02 +09:00
YeonGyu-Kim
79b791117a fix(session-recovery): improve error message extraction 2025-12-08 17:00:02 +09:00
YeonGyu-Kim
4e328a937c feat(hooks): integrate directory-agents-injector hook into plugin pipeline
- 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
2025-12-08 17:00:02 +09:00
YeonGyu-Kim
a500f0c9ad export(hooks): add directory-agents-injector hook to public API
- Export createDirectoryAgentsInjectorHook from hooks index
- Fix: Formatting (add semicolons to match code style)
2025-12-08 17:00:02 +09:00
YeonGyu-Kim
16806da615 refactor(session-recovery): process entire message history for empty/thinking block recovery
- Scan all non-final assistant messages for empty content, orphan thinking blocks, and disabled thinking
- Add storage utility functions: findMessagesWithThinkingBlocks, findMessagesWithOrphanThinking, stripThinkingParts, prependThinkingPart
- Fix: Previously only processed single failed message, now handles multiple broken messages in history
- Improve: Use filesystem-based recovery instead of unreliable SDK APIs
2025-12-08 17:00:02 +09:00
YeonGyu-Kim
c5f651c0a9 refactor(hooks): remove grep-blocker (grep tool now overrides built-in)
The grep tool now properly overrides OpenCode's built-in grep,
making the blocker hook unnecessary.

Generated by [OpenCode](https://opencode.ai/)
2025-12-08 17:00:02 +09:00
YeonGyu-Kim
ed3d7a55f4 feat(tools): add glob tool with timeout protection
- Override OpenCode's built-in glob with 60s timeout
- Kill process on expiration to prevent indefinite hanging
- Reuse grep's CLI resolver for ripgrep detection

Generated by [OpenCode](https://opencode.ai/)
2025-12-08 17:00:02 +09:00
YeonGyu-Kim
b77dd2fcdf refactor(tools): rename safe-grep to grep with override capability 2025-12-08 17:00:02 +09:00
YeonGyu-Kim
64b3564760 refactor(session-recovery): extract storage utilities to separate module
Split session-recovery.ts into modular structure:
- types.ts: SDK-aligned type definitions
- constants.ts: storage paths and part type sets
- storage.ts: reusable read/write operations
- index.ts: main recovery hook logic
2025-12-08 17:00:02 +09:00
YeonGyu-Kim
0df7e9b10b fix(session-recovery): recognize 'tool' type as valid content
OpenCode storage uses 'tool' type for tool calls, but the hasContent
check only recognized 'tool_use' (Anthropic API format). This caused
messages with tool calls to be incorrectly identified as empty.
2025-12-08 17:00:02 +09:00
YeonGyu-Kim
aa35f2eab6 fix(session-recovery): detect empty messages with zero parts
Previously, findEmptyContentMessageFromStorage only detected messages
with parts.length > 0 that had no content. This missed the case where
a message has zero parts entirely, causing infinite recovery loops.
2025-12-08 17:00:02 +09:00
github-actions[bot]
64db980803 release: v0.1.26 2025-12-08 00:41:34 +00:00
YeonGyu-Kim
b86346a79d fix(lsp): add Push model support and fix JSON LSP diagnostics
- Add diagnosticsStore to capture Push model notifications
- Handle textDocument/publishDiagnostics notifications in processBuffer
- Fix workspace/configuration response for JSON LSP validation
- Add missing language mappings (json, html, css, sh, fish, md, tf)
- diagnostics() now tries Pull first, falls back to Push store
2025-12-08 09:38:00 +09:00
YeonGyu-Kim
4debb57402 feat(hooks): add pulse-monitor for token stall detection and auto-recovery
- Detect token stalls via message.part.updated heartbeat monitoring
- Support thinking/reasoning block detection with extended timeout
- Auto-recover: abort + 'continue' prompt on 5min stall
- Pause monitoring during tool execution
2025-12-06 11:17:55 +09:00
YeonGyu-Kim
a763db61cf improve(hooks): refine todo-continuation-enforcer message tone and status format 2025-12-06 10:54:36 +09:00
YeonGyu-Kim
341e5a959d feat(hooks): add grep-output-truncator for context-aware output limiting 2025-12-06 10:54:22 +09:00
YeonGyu-Kim
bac304c035 docs: add explicit agent invocation examples to README 2025-12-05 23:48:11 +09:00
YeonGyu-Kim
1aaeefac0e docs: enhance LSP tools description in README 2025-12-05 23:27:07 +09:00
github-actions[bot]
dda7b4f56d release: v0.1.25 2025-12-05 14:25:22 +00:00
YeonGyu-Kim
a287e59262 feat(session-recovery): add filesystem-based empty content recovery
- Replace API-based recovery with direct JSON file editing for empty content messages
- Add cross-platform storage path support via xdg-basedir (Linux/macOS/Windows)
- Inject '(interrupted)' text part to fix messages with only thinking/meta blocks
- Update README docs with detailed session recovery scenarios
2025-12-05 23:24:20 +09:00
github-actions[bot]
80fe3ae612 release: v0.1.24 2025-12-05 13:53:30 +00:00
YeonGyu-Kim
b045f6918e feat(lsp): add result limits to prevent token overflow
- Add DEFAULT_MAX_REFERENCES, DEFAULT_MAX_SYMBOLS, DEFAULT_MAX_DIAGNOSTICS (200 each)
- Apply limits to lsp_find_references, lsp_document_symbols, lsp_workspace_symbols, lsp_diagnostics
- Show truncation warning when results exceed limits
2025-12-05 22:52:33 +09:00
YeonGyu-Kim
725ec9b91d feat(ast-grep): add safety limits to prevent token overflow
- Add timeout (5min), output limit (1MB), match limit (500)
- Add SgResult type with truncation info
- Update formatSearchResult/formatReplaceResult for truncation display
- cli.ts: timeout + output truncation + graceful JSON recovery
2025-12-05 22:52:33 +09:00
github-actions[bot]
1f717a76be release: v0.1.23 2025-12-05 13:19:23 +00:00
YeonGyu-Kim
3bcb869a5d fix(ast-grep): add isValidBinary check to all path resolutions
- Check file size >10KB to filter out placeholder files
- Check cached binary first
- Then npm package paths with validation
- Homebrew paths as last resort
- Fixes SIGTRAP/ENOEXEC from invalid binaries
2025-12-05 22:18:17 +09:00
github-actions[bot]
54e13e4330 release: v0.1.22 2025-12-05 13:13:29 +00:00
YeonGyu-Kim
1780e2971d refactor(ast-grep): simplify binary resolution, rely on auto-download
- Remove hardcoded homebrew paths
- Remove npm package path resolution (prone to placeholder issues)
- Only check cached binary (~/.cache/oh-my-opencode/bin/sg)
- If not found, cli.ts will auto-download from GitHub releases

The download logic in cli.ts handles all cases properly.
2025-12-05 22:12:12 +09:00
github-actions[bot]
ded97701b8 release: v0.1.21 2025-12-05 13:04:11 +00:00
YeonGyu-Kim
316cdc1a62 fix(ast-grep): validate binary before using, prioritize homebrew path
- Add isValidBinary() check: file must be >10KB (placeholder files are ~100 bytes)
- Check homebrew paths first on macOS (most reliable)
- Check cached binary second
- npm package paths last (prone to placeholder issues)

Fixes ENOEXEC error when @ast-grep/cli has placeholder instead of real binary
2025-12-05 22:03:05 +09:00
YeonGyu-Kim
f19cd8fc71 improve(ast-grep): better Python pattern hints
- Show exact pattern without colon when pattern ends with ':'
- More actionable hint message
2025-12-05 21:57:58 +09:00
github-actions[bot]
181194ae3c release: v0.1.19 2025-12-05 12:00:31 +00:00
YeonGyu-Kim
b8f5599e61 feat(ast-grep): add helpful hints for incomplete Python patterns
- Show hints when Python class/function patterns return empty results
- Detect patterns ending with ':' that need body (class :, def ():)
- Removed validation that could cause false positives
- Hints only appear on empty results, not on successful matches
2025-12-05 20:59:05 +09:00
github-actions[bot]
ea2b09ebb9 release: v0.1.18 2025-12-05 11:07:21 +00:00
YeonGyu-Kim
143dd8aaa9 fix(session-recovery): improve error detection and add continue prompt
- Enhance error type detection for thinking block order issues
- Add continue prompt after successful session recovery
- Improve error message matching logic
2025-12-05 20:01:47 +09:00
YeonGyu-Kim
36169c83fb feat(ast-grep): add CLI path resolution and auto-download functionality
- Add automatic CLI binary path detection and resolution
- Implement lazy binary download with caching
- Add environment check utilities for CLI and NAPI availability
- Improve error handling and fallback mechanisms
- Export new utilities from index.ts
2025-12-05 20:01:35 +09:00
github-actions[bot]
bf9f033635 release: v0.1.17 2025-12-05 07:26:35 +00:00
YeonGyu-Kim
de2f9dfc86 chore: move schema to assets/, add dist/ to gitignore 2025-12-05 16:24:54 +09:00
YeonGyu-Kim
5f5218ccae docs: fix Agents config section - remove incorrect OpenCode link, add correct options 2025-12-05 16:17:00 +09:00
YeonGyu-Kim
41d3817910 docs: reorganize Configuration section to bottom, add LSP config docs 2025-12-05 16:13:25 +09:00
YeonGyu-Kim
a119429ebe docs: remove MCP config from Agent section (already in top-level Config) 2025-12-05 16:01:19 +09:00
github-actions[bot]
9bed2dd79a release: v0.1.16 2025-12-05 06:55:27 +00:00
YeonGyu-Kim
4c1d534093 docs: simplify agent configuration, add OpenCode doc links 2025-12-05 15:52:04 +09:00
github-actions[bot]
a04234eaab release: v0.1.15 2025-12-05 06:33:29 +00:00
YeonGyu-Kim
6d0e4c49c2 docs: add deployment workflow documentation to AGENTS.md 2025-12-05 15:32:09 +09:00
YeonGyu-Kim
8f39575264 fix(session-recovery): handle empty content from interrupted reasoning (#6)
* fix(publish): make git operations idempotent

- Check for staged changes before commit
- Check if tag exists before creating
- Check if release exists before creating

* fix(session-recovery): handle empty content from interrupted reasoning

- Add THINKING_TYPES set including 'reasoning' type (OpenCode's thinking)
- Add hasNonEmptyOutput() to detect messages with only thinking/meta parts
- Add findEmptyContentMessage() to scan all messages for empty content
- Handle step-start/step-finish meta parts in empty content detection
- Patch interrupted messages with '(interrupted)' text before falling back to revert
2025-12-05 15:28:22 +09:00
YeonGyu-Kim
2464473731 fix(ast-grep): add validation for incomplete function declaration patterns (#5)
* fix(publish): make git operations idempotent

- Check for staged changes before commit
- Check if tag exists before creating
- Check if release exists before creating

* fix(ast-grep): add validation for incomplete function declaration patterns

- Add validatePatternForCli function to detect incomplete patterns like
  'export async function $METHOD' (missing params and body)
- Only validates JS/TS languages (javascript, typescript, tsx)
- Provides helpful error message with correct pattern examples
- Update tool description to clarify complete AST nodes required

This fixes the issue where incomplete patterns would fail silently
with no results instead of providing actionable feedback.
2025-12-05 15:17:42 +09:00
YeonGyu-Kim
1b0a8adb2b refactor(comment-checker): remove WASM fallback, use CLI-only with lazy download
- Remove tree-sitter-wasms and web-tree-sitter dependencies
- Delete detector.ts (320 lines of WASM implementation)
- Add downloader.ts for lazy binary download from GitHub Releases
- Simplify index.ts to CLI-only mode
- Cache binary at ~/.cache/oh-my-opencode/bin/
- Fall back to 'Comment checking disabled' when binary unavailable
2025-12-05 14:51:47 +09:00
YeonGyu-Kim
4b7a4b04d0 docs: restructure README for better readability and UX (#4)
- Move TL;DR section before Installation for quick overview
- Wrap 'For LLM Agents' section in collapsible details tag
- Simplify Configuration section (remove verbose schema explanations)
- Move model override example to Features > Agents section
- Add context7 MCP to Korean README
2025-12-05 14:43:52 +09:00
YeonGyu-Kim
f6f2fad1fc fix: correct OpenCode docs link (404 -> valid URL) (#3)
- Change https://opencode.ai/docs/installation/ to https://opencode.ai/docs
- The /installation/ path returns 404, main docs page has Install section
2025-12-05 14:28:44 +09:00
YeonGyu-Kim
3ca9693de0 Merge pull request #2 from code-yeongyu/docs-schema-and-readme-config
docs: add comprehensive configuration documentation
2025-12-05 14:28:32 +09:00
YeonGyu-Kim
e2078763a6 fix: resolve merge conflict with master (include both config and LLM agent guide) 2025-12-05 14:28:11 +09:00
YeonGyu-Kim
5121d0eed2 docs: add comprehensive configuration documentation and include schema.json
- Add dist/oh-my-opencode.schema.json to repository (fix gitignore pattern)
- Document all configuration options in README.md (English)
- Add Configuration section to README.ko.md (Korean) - was completely missing
- Include agent configuration examples (Anthropic-only setup)
- Add MCP/Agent disable instructions
- Document permission options for agents
2025-12-05 14:24:12 +09:00
YeonGyu-Kim
973caf9b7d docs: add 'For LLM Agents' setup guide section (#1)
- Add step-by-step guide for LLM agents to setup oh-my-opencode
- Include OpenCode installation check with link to official docs
- Include oh-my-opencode plugin configuration script
- Update Table of Contents for both EN/KO README files
2025-12-05 14:17:48 +09:00
YeonGyu-Kim
b277d96de8 fix: remove Windows ARM64 support 2025-12-05 13:47:21 +09:00
YeonGyu-Kim
2c223d96a1 feat(comment-checker): add Windows support 2025-12-05 13:44:52 +09:00
YeonGyu-Kim
695aeafb86 fix(comment-checker): change npm scope to @code-yeongyu 2025-12-05 11:40:16 +09:00
YeonGyu-Kim
812c544bfa feat(comment-checker): add native CLI support with WASM fallback
- Add cli.ts for native binary resolution and spawning
- Update index.ts to use CLI when available, WASM as fallback
- Add Edit/MultiEdit support to types.ts for proper CLI input
2025-12-05 11:31:52 +09:00
github-actions[bot]
edf0e7d946 release: v0.1.12 2025-12-05 02:10:36 +00:00
YeonGyu-Kim
baa7fadab1 fix(comment-checker): use runtime wasm path resolution instead of require.resolve
require.resolve() was evaluated at build time, hardcoding CI paths.
Now uses import.meta.resolve() at runtime to find wasm files.
2025-12-05 11:09:41 +09:00
github-actions[bot]
a06bbeb9ee release: v0.1.11 2025-12-05 02:05:44 +00:00
YeonGyu-Kim
f3a92db203 chore: bump version to 0.1.12 2025-12-05 11:02:43 +09:00
YeonGyu-Kim
fd6e230889 perf(comment-checker): add LSP-style background language warming
- Warmup common languages (python, typescript, javascript, tsx, go, rust, java) on plugin init
- Non-blocking background initialization using Promise.then() pattern
- First parse call uses pre-cached language - zero user wait time
- Refactor parser manager with ManagedLanguage interface for better state tracking
2025-12-05 11:02:35 +09:00
YeonGyu-Kim
50ea492065 chore: bump version to 0.1.11 2025-12-05 10:56:21 +09:00
YeonGyu-Kim
f5f2053b7a fix(comment-checker): fix error skip bug and add parser/language caching
- Fix overly broad error detection that skipped comments when LSP warnings present
- Add Parser class and language WASM caching for ~3.5x faster subsequent parses
- Add debug logging controlled by COMMENT_CHECKER_DEBUG=1 env var
2025-12-05 10:56:08 +09:00
github-actions[bot]
6c16baea9a release: v0.1.10 2025-12-05 01:00:03 +00:00
YeonGyu-Kim
2ad7e193fd fix(comment-checker): support args.path for OpenCode Write/Edit tools 2025-12-05 09:57:50 +09:00
github-actions[bot]
d62f1dd207 release: v0.1.9 2025-12-05 00:45:40 +00:00
YeonGyu-Kim
aff7cad615 fix: resolve tree-sitter wasm initialization error with locateFile option 2025-12-05 09:45:04 +09:00
github-actions[bot]
e021ec954a release: v0.1.8 2025-12-05 00:30:07 +00:00
YeonGyu-Kim
1390970973 fix: skip publish if version already exists on registry 2025-12-05 09:29:08 +09:00
YeonGyu-Kim
a72bfe5c02 docs: consolidate README.en.md into README.md 2025-12-05 09:29:08 +09:00
YeonGyu-Kim
f10c15d83d feat: wire comment-checker hook to main plugin 2025-12-05 09:29:08 +09:00
github-actions[bot]
fdb39ba404 release: v0.1.7 2025-12-05 00:24:20 +00:00
YeonGyu-Kim
36ef885141 fix: trust @ast-grep/napi in CI to enable native module install scripts 2025-12-05 04:29:40 +09:00
YeonGyu-Kim
909ce37826 fix: remove --ignore-scripts from bun install, add build verification step 2025-12-05 04:19:13 +09:00
YeonGyu-Kim
132bb3c373 fix: add --ignore-scripts to npm publish to prevent CI build failure 2025-12-05 04:16:53 +09:00
YeonGyu-Kim
180d16b977 fix: prevent plugin crash by removing non-function exports from barrel files
BREAKING: OpenCode plugin loader calls all exports as functions.
Exporting non-function values (schemas, constants, types) causes TypeError.

Changes:
- Remove OhMyOpenCodeConfigSchema export from root index.ts
- Replace 'export *' with explicit function exports in hooks/index.ts
- Remove 'export *' from comment-checker/index.ts
2025-12-05 04:08:59 +09:00
YeonGyu-Kim
eba89a6626 hotfix: move McpNameSchema to src/mcp/types.ts for proper module organization 2025-12-05 03:58:21 +09:00
YeonGyu-Kim
0a82787614 hotfix: use McpName from config schema instead of duplicate type definition 2025-12-05 03:56:14 +09:00
YeonGyu-Kim
a1a2d2fdb3 hotfix: add empty content message recovery to session recovery 2025-12-05 03:54:51 +09:00
123 changed files with 8367 additions and 998 deletions

View File

@@ -48,10 +48,37 @@ jobs:
run: npm config set registry https://registry.npmjs.org
- name: Install dependencies
run: bun install --ignore-scripts
run: bun install
env:
BUN_INSTALL_ALLOW_SCRIPTS: "@ast-grep/napi"
- name: Debug environment
run: |
echo "=== Bun version ==="
bun --version
echo "=== Node version ==="
node --version
echo "=== Current directory ==="
pwd
echo "=== List src/ ==="
ls -la src/
echo "=== package.json scripts ==="
cat package.json | jq '.scripts'
- name: Build
run: bun run build
run: |
echo "=== Running bun build ==="
bun build src/index.ts --outdir dist --target bun --format esm --external @ast-grep/napi
echo "=== bun build exit code: $? ==="
echo "=== Running tsc ==="
tsc --emitDeclarationOnly
echo "=== Running build:schema ==="
bun run build:schema
- name: Verify build output
run: |
ls -la dist/
test -f dist/index.js || (echo "ERROR: dist/index.js not found!" && exit 1)
- name: Publish
run: bun run script/publish.ts

View File

@@ -84,9 +84,31 @@ bun run build
bun run rebuild
```
## DEPLOYMENT
**배포는 GitHub Actions workflow_dispatch로만 진행**
1. package.json 버전은 수정하지 않음 (워크플로우에서 자동 bump)
2. 변경사항 커밋 & 푸시
3. GitHub Actions에서 `publish` 워크플로우 수동 실행
- `bump`: major | minor | patch 선택
- `version`: (선택) 특정 버전 지정 가능
```bash
# 워크플로우 실행 (CLI)
gh workflow run publish -f bump=patch
# 워크플로우 상태 확인
gh run list --workflow=publish
```
**주의사항**:
- `bun publish` 직접 실행 금지 (OIDC provenance 문제)
- 로컬에서 버전 bump 하지 말 것
## NOTES
- **No tests**: Test framework not configured
- **No CI/CD**: GitHub workflows not present
- **CI/CD**: GitHub Actions publish workflow 사용
- **Version requirement**: OpenCode >= 1.0.132 (earlier versions have config bugs)
- **Multi-language docs**: README.md, README.en.md, README.ko.md

View File

@@ -1,191 +0,0 @@
English | [한국어](README.ko.md)
## Contents
- [Oh My OpenCode](#oh-my-opencode)
- [Installation](#installation)
- [Configuration](#configuration)
- [Disable specific MCPs](#disable-specific-mcps)
- [TL;DR](#tldr)
- [Why OpenCode \& Why Oh My OpenCode](#why-opencode--why-oh-my-opencode)
- [Features](#features)
- [Hooks](#hooks)
- [Agents](#agents)
- [Tools](#tools)
- [Built-in LSP Tools](#built-in-lsp-tools)
- [Built-in AST-Grep Tools](#built-in-ast-grep-tools)
- [Safe Grep](#safe-grep)
- [Built-in MCPs](#built-in-mcps)
- [Other Features](#other-features)
- [Author's Note](#authors-note)
- [Warnings](#warnings)
# Oh My OpenCode
Oh My OpenCode
oMoMoMoMoMo···
If you work in tech, you likely appreciated [Claude Code](https://www.claude.com/product/claude-code).
If you are a hacker, you will fucking falling in love with [OpenCode](https://github.com/sst/opencode).
You don't write code just for a paycheck? You write because you genuinely love it?
To you, OpenCode will feel like the paradigm shift from Windows to Linux. Not you? It's still worth the investment. Give it 10 minutes. Your work and life will improve. I promise.
## Installation
Add to `~/.config/opencode/opencode.json`:
```json
{
"plugin": [
"oh-my-opencode"
]
}
```
## Configuration
You can configure Oh My OpenCode by creating a `oh-my-opencode.json` (or `.oh-my-opencode.json`) file in your project root.
### JSON Schema Support
For autocompletion and validation in VS Code (or other editors), add the `$schema` property to your configuration file.
**Using Remote Schema (Recommended):**
```json
{
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/dist/oh-my-opencode.schema.json",
"disabled_mcps": ["context7"]
}
```
**Using Local Schema:**
```json
{
"$schema": "./node_modules/oh-my-opencode/dist/oh-my-opencode.schema.json"
}
```
### Disable specific MCPs
If you want to disable specific built-in MCPs, you can use the `disabled_mcps` option.
```json
{
"disabled_mcps": ["context7", "websearch_exa"]
}
```
## TL;DR
- **Model Setup Required**
- This plugin utilizes models from [OpenCode Zen](https://opencode.ai/docs/zen/), Google, OpenAI, and Anthropic.
- For Anthropic models, use [OpenCode's built-in Claude Code Max Plan login](https://opencode.ai/docs/providers/#anthropic).
- For OpenAI models, I recommend the [OpenCode-OpenAI-Codex-Auth plugin](https://github.com/numman-ali/opencode-openai-codex-auth).
- For Gemini and GPT, use [VibeProxy (macOS Only)](https://github.com/automazeio/vibeproxy) or [CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI).
- **Truth be told, the rest is optional. Just install it. Once set up, no further learning is required. It simply evolves.**
- **Paste this document into Claude Code, OpenCode, or Cursor, instruct it to install, and ask for assistance if needed. It works seamlessly.**
- If you are an LLM Agent, install the required plugins and dependencies, then run `opencode auth login` via tmux to assist the user with configuration.
## Why OpenCode & Why Oh My OpenCode
OpenCode is limitlessly extensible and customizable. Zero screen flicker.
[LSP](https://opencode.ai/docs/lsp/), [linters, formatters](https://opencode.ai/docs/formatters/)? Automatic and fully configurable.
You can mix and orchestrate models to your exact specifications.
It is feature-rich. It is elegant. It handles the terminal without hesitation. It is high-performance.
But here is the catch: the learning curve is steep. There is a lot to master.
Inspired by [AmpCode](https://ampcode.com) and [Claude Code](https://code.claude.com/docs/en/overview), I have implemented their features here—often with superior execution.
Because this is OpenCode.
Consider this a superior AmpCode, a superior Claude Code, or simply a specialized distribution.
I believe in the right tool for the job. For your wallet's sake, use CLIProxyAPI or VibeProxy. Employ the best LLMs from frontier labs. You are in command.
**Note**: This setup is highly opinionated. It represents the generic component of my personal configuration, so it evolves constantly. I have spent tokens worth $20,000 just for my personal programming usages, and this plugin represents the apex of that experience. You simply inherit the best. If you have superior ideas, PRs are welcome.
## Features
### Hooks
- **Todo Continuation Enforcer**: Forces the agent to complete all tasks before exiting. Eliminates the common LLM issue of "giving up halfway".
- **Context Window Monitor**: Implements [Context Window Anxiety Management](https://agentic-patterns.com/patterns/context-window-anxiety-management/). When context usage exceeds 70%, it reminds the agent that resources are sufficient, preventing rushed or low-quality output.
- **Session Notification**: Sends a native OS notification when the job is done (macOS, Linux, Windows).
- **Session Recovery**: Automatically recovers from API errors by injecting missing tool results and correcting thinking block violations, ensuring session stability.
- **Comment Checker**: Detects and reports unnecessary comments after code modifications. Smartly ignores valid patterns (BDD, directives, docstrings, shebangs) to keep the codebase clean from AI-generated artifacts.
### Agents
- **oracle** (`openai/gpt-5.1`): The architect. Expert in code reviews and strategy. Uses GPT-5.1 for its unmatched logic and reasoning capabilities. Inspired by AmpCode.
- **librarian** (`anthropic/claude-haiku-4-5`): Multi-repo analysis, documentation lookup, and implementation examples. Haiku is chosen for its speed, competence, excellent tool usage, and cost-efficiency. Inspired by AmpCode.
- **explore** (`opencode/grok-code`): Fast exploration and pattern matching. Claude Code uses Haiku; we use Grok. It is currently free, blazing fast, and intelligent enough for file traversal. Inspired by Claude Code.
- **frontend-ui-ux-engineer** (`google/gemini-3-pro-preview`): A designer turned developer. Creates stunning UIs. Uses Gemini because its creativity and UI code generation are superior.
- **document-writer** (`google/gemini-3-pro-preview`): A technical writing expert. Gemini is a wordsmith; it writes prose that flows naturally.
### Tools
#### Built-in LSP Tools
[OpenCode provides LSP](https://opencode.ai/docs/lsp/), but only for analysis. Oh My OpenCode equips you with navigation and refactoring tools matching the same specification.
- **lsp_hover**: Get type info, docs, signatures at position
- **lsp_goto_definition**: Jump to symbol definition
- **lsp_find_references**: Find all usages across workspace
- **lsp_document_symbols**: Get file's symbol outline
- **lsp_workspace_symbols**: Search symbols by name across project
- **lsp_diagnostics**: Get errors/warnings before build
- **lsp_servers**: List available LSP servers
- **lsp_prepare_rename**: Validate rename operation
- **lsp_rename**: Rename symbol across workspace
- **lsp_code_actions**: Get available quick fixes/refactorings
- **lsp_code_action_resolve**: Apply a code action
#### Built-in AST-Grep Tools
- **ast_grep_search**: AST-aware code pattern search (25 languages)
- **ast_grep_replace**: AST-aware code replacement
#### Safe Grep
- **safe_grep**: Content search with safety limits (5min timeout, 10MB output).
- The default `grep` lacks safeguards. On a large codebase, a broad pattern can cause CPU overload and indefinite hanging.
- `safe_grep` enforces strict limits.
- **Note**: Default `grep` is disabled to prevent Agent confusion. `safe_grep` delivers full `grep` functionality with safety assurance.
#### Built-in MCPs
- **websearch_exa**: Exa AI web search. Performs real-time web searches and can scrape content from specific URLs. Returns LLM-optimized context from relevant websites.
- **context7**: Library documentation lookup. Fetches up-to-date documentation for any library to assist with accurate coding.
### Other Features
- **Terminal Title**: Auto-updates terminal title with session status (idle ○, processing ◐, tool ⚡, error ✖). Supports tmux.
## Author's Note
Install Oh My OpenCode. Do not waste time configuring OpenCode from scratch.
I have resolved the friction so you don't have to. The answers are in this plugin. If OpenCode is Arch Linux, Oh My OpenCode is [Omarchy](https://omarchy.org/).
Enjoy the multi-model stability and rich feature set that other harnesses promise but fail to deliver.
I will continue testing and updating here. I am the primary user of this project.
- Who possesses the best raw logic?
- Who is the debugging god?
- Who writes the best prose?
- Who dominates frontend?
- Who owns backend?
- Which model is fastest for daily driving?
- What new features are other harnesses shipping?
Do not overthink it. I have done the thinking. I will integrate the best practices. I will update this.
If this sounds arrogant and you have a superior solution, send a PR. You are welcome.
As of now, I have no affiliation with any of the projects or models mentioned here. This plugin is purely based on personal experimentation and preference.
I constructed 99% of this project using OpenCode. I focused on functional verification. This documentation has been personally reviewed and comprehensively rewritten, so you can rely on it with confidence.
## Warnings
- If you are on [1.0.132](https://github.com/sst/opencode/releases/tag/v1.0.132) or lower, OpenCode has a bug that might break config.
- [The fix](https://github.com/sst/opencode/pull/5040) was merged after 1.0.132, so use a newer version.

View File

@@ -1,20 +1,23 @@
[English](README.en.md) | 한국어
[English](README.md) | 한국어
## 목차
- [Oh My OpenCode](#oh-my-opencode)
- [설치](#설치)
- [세 줄 요약](#세-줄-요약)
- [Why OpenCode \& Why Oh My OpenCode](#why-opencode--why-oh-my-opencode)
- [설치](#설치)
- [LLM Agent를 위한 안내](#llm-agent를-위한-안내)
- [Why OpenCode & Why Oh My OpenCode](#why-opencode--why-oh-my-opencode)
- [기능](#기능)
- [Hooks](#hooks)
- [Agents](#agents)
- [Tools](#tools)
- [내장 LSP Tools](#내장-lsp-tools)
- [내장 AST-Grep Tools](#내장-ast-grep-tools)
- [Safe Grep](#safe-grep)
- [Grep](#grep)
- [내장 MCPs](#내장-mcps)
- [Claude Code 호환성](#claude-code-호환성)
- [기타 편의 기능](#기타-편의-기능)
- [설정](#설정)
- [작성자의 노트](#작성자의-노트)
- [주의](#주의)
@@ -33,6 +36,17 @@ OpenCode 가 낭만이 사라진것같은 오늘날의 시대에, 당신에게
당신이 코딩을 좋아하고 컴퓨터를 좋아한다면, OpenCode 는 윈도우만 사용하다가 리눅스를 처음 접하게 된 그런 느낌일겁니다.
그렇지 않은 당신도 약간의 시간을 투자해서 당신의 실력과 생산성을 몇배로 부스트하세요.
## 세 줄 요약
- **모델 설정이 필요합니다**
- 이 플러그인은 [OpenCode Zen](https://opencode.ai/docs/zen/), Google, OpenAI, Anthropic 의 모델을 사용합니다.
- Anthropic 모델들을 사용하기 위해 [OpenCode 의 내장 Claude Code Max Plan 로그인 기능](https://opencode.ai/docs/providers/#anthropic)을 사용하세요. (Anthropic 플랜은 유료입니다)
- OpenAI 모델들을 사용하기 위해 이 [OpenCode-OpenAI-Codex-Auth 플러그인](https://github.com/numman-ali/opencode-openai-codex-auth)을 추천합니다. (OpenAI 플랜은 유료입니다)
- Gemini, GPT 를 위해 [VibeProxy (macOS Only)](https://github.com/automazeio/vibeproxy) 또는 [CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)를 추천합니다. (Gemini 는 구독하지 않아도 사용 할 수 있습니다)
- **사실 밑의 내용은 읽지 않아도 됩니다. 그냥 설치하시면 됩니다. 모델 설정하고나면 추가로 공부하거나 알 필요가 없고, 설치하고 나면 그냥 더 좋아집니다.**
- **이 문서도 그냥 Claude Code, OpenCode, Cursor에 붙여넣고, 설치하고, 사용자의 개입이 필요할 때 알려달라고 프롬프팅하세요. 그럼 그냥 깔립니다.**
- 당신이 LLM Agent 라면, 필요한 플러그인과 의존성을 설치하고, tmux 를 통해 opencode auth login 을 실행하여 사용자의 구성을 도와주세요.
## 설치
`~/.config/opencode/opencode.json`에 추가:
@@ -45,16 +59,56 @@ OpenCode 가 낭만이 사라진것같은 오늘날의 시대에, 당신에게
}
```
## 세 줄 요약
## LLM Agent를 위한 안내
- **모델 설정이 필요합니다**
- 이 플러그인은 [OpenCode Zen](https://opencode.ai/docs/zen/), Google, OpenAI, Anthropic 의 모델을 사용합니다.
- Anthropic 모델들을 사용하기 위해 [OpenCode 의 내장 Claude Code Max Plan 로그인 기능](https://opencode.ai/docs/providers/#anthropic)을 사용하세요. (Anthropic 플랜은 유료입니다)
- OpenAI 모델들을 사용하기 위해 이 [OpenCode-OpenAI-Codex-Auth 플러그인](https://github.com/numman-ali/opencode-openai-codex-auth)을 추천합니다. (OpenAI 플랜은 유료입니다)
- Gemini, GPT 를 위해 [VibeProxy (macOS Only)](https://github.com/automazeio/vibeproxy) 또는 [CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)를 추천합니다. (Gemini 는 구독하지 않아도 사용 할 수 있습니다)
- **사실 밑의 내용은 읽지 않아도 됩니다. 그냥 설치하시면 됩니다. 모델 설정하고나면 추가로 공부하거나 알 필요가 없고, 설치하고 나면 그냥 더 좋아집니다.**
- **이 문서도 그냥 Claude Code, OpenCode, Cursor에 붙여넣고, 설치하고, 사용자의 개입이 필요할 때 알려달라고 프롬프팅하세요. 그럼 그냥 깔립니다.**
- 당신이 LLM Agent 라면, 필요한 플러그인과 의존성을 설치하고, tmux 를 통해 opencode auth login 을 실행하여 사용자의 구성을 도와주세요.
<details>
<summary>LLM Agent를 위한 안내 (클릭하여 펼치기)</summary>
당신이 사용자의 oh-my-opencode 설정을 돕는 LLM Agent라면, 다음 단계를 따르세요:
### 1단계: OpenCode 설치 확인
```bash
if command -v opencode &> /dev/null; then
echo "OpenCode $(opencode --version) 설치됨"
else
echo "OpenCode가 설치되어 있지 않습니다. 먼저 설치해주세요."
echo "참고: https://opencode.ai/docs"
fi
```
OpenCode가 설치되어 있지 않다면, [OpenCode 설치 가이드](https://opencode.ai/docs)를 안내하세요.
### 2단계: oh-my-opencode 플러그인 설정
```bash
mkdir -p ~/.config/opencode
if [ -f ~/.config/opencode/opencode.json ]; then
# 기존 설정 파일이 있는 경우: jq 또는 python으로 plugin 추가
if command -v jq &> /dev/null; then
jq '.plugin = ((.plugin // []) + ["oh-my-opencode"] | unique)' \
~/.config/opencode/opencode.json > /tmp/oc.json && \
mv /tmp/oc.json ~/.config/opencode/opencode.json
else
echo "~/.config/opencode/opencode.json의 plugin 배열에 \"oh-my-opencode\"를 추가하세요"
fi
else
# 새 설정 파일 생성
echo '{"plugin":["oh-my-opencode"]}' > ~/.config/opencode/opencode.json
fi
```
### 3단계: 설정 확인
```bash
opencode --version # 1.0.132 이상이어야 함
cat ~/.config/opencode/opencode.json # plugin 배열에 "oh-my-opencode"가 있어야 함
```
> **참고**: 모델 인증이 필요하면, `opencode` 실행 후 `/connect` 명령어를 사용하거나, tmux를 통해 `opencode auth login`을 안내하세요.
</details>
## Why OpenCode & Why Oh My OpenCode
@@ -83,7 +137,27 @@ OpenCode 는 아주 확장가능하고 아주 커스터마이저블합니다.
- **Context Window Monitor**: [컨텍스트 윈도우 불안 관리](https://agentic-patterns.com/patterns/context-window-anxiety-management/) 패턴을 구현합니다.
- 사용량이 70%를 넘으면 에이전트에게 아직 토큰이 충분하다고 상기시켜, 급하게 불완전한 작업을 하는 것을 완화합니다.
- **Session Notification**: 에이전트가 작업을 마치면 OS 네이티브 알림을 보냅니다 (macOS, Linux, Windows).
- **Session Recovery**: API 에러로부터 자동으로 복구하여 세션 안정성을 보장합니다. 네 가지 시나리오를 처리합니다:
- **Tool Result Missing**: `tool_use` 블록이 있지만 `tool_result`가 없을 때 (ESC 인터럽트) → "cancelled" tool result 주입
- **Thinking Block Order**: thinking 블록이 첫 번째여야 하는데 아닐 때 → 빈 thinking 블록 추가
- **Thinking Disabled Violation**: thinking 이 비활성화인데 thinking 블록이 있을 때 → thinking 블록 제거
- **Empty Content Message**: 메시지가 thinking/meta 블록만 있고 실제 내용이 없을 때 → 파일시스템을 통해 "(interrupted)" 텍스트 주입
- **Comment Checker**: 코드 수정 후 불필요한 주석을 감지하여 보고합니다. BDD 패턴, 지시어, 독스트링 등 유효한 주석은 똑똑하게 제외하고, AI가 남긴 흔적을 제거하여 코드를 깨끗하게 유지합니다.
- **Directory AGENTS.md Injector**: 파일을 읽을 때 `AGENTS.md` 내용을 자동으로 주입합니다. 파일 디렉토리부터 프로젝트 루트까지 탐색하며, 경로 상의 **모든** `AGENTS.md` 파일을 수집합니다. 중첩된 디렉토리별 지침을 지원합니다:
```
project/
├── AGENTS.md # 프로젝트 전체 컨텍스트
├── src/
│ ├── AGENTS.md # src 전용 컨텍스트
│ └── components/
│ ├── AGENTS.md # 컴포넌트 전용 컨텍스트
│ └── Button.tsx # 이 파일을 읽으면 위 3개 AGENTS.md 모두 주입
```
`Button.tsx`를 읽으면 순서대로 주입됩니다: `project/AGENTS.md` → `src/AGENTS.md` → `components/AGENTS.md`. 각 디렉토리의 컨텍스트는 세션당 한 번만 주입됩니다. Claude Code의 CLAUDE.md 기능에서 영감을 받았습니다.
- **Think Mode**: 확장된 사고(Extended Thinking)가 필요한 상황을 자동으로 감지하고 모드를 전환합니다. 사용자가 깊은 사고를 요청하는 표현(예: "think deeply", "ultrathink")을 감지하면, 추론 능력을 극대화하도록 모델 설정을 동적으로 조정합니다.
- **Anthropic Auto Compact**: Anthropic 모델 사용 시 컨텍스트 한계에 도달하면 대화 기록을 자동으로 압축하여 효율적으로 관리합니다.
- **Empty Task Response Detector**: 서브 에이전트가 수행한 작업이 비어있거나 무의미한 응답을 반환하는 경우를 감지하여, 오류 없이 우아하게 처리합니다.
- **Grep Output Truncator**: Grep 검색 결과가 너무 길어 컨텍스트를 장악해버리는 것을 방지하기 위해, 과도한 출력을 자동으로 자릅니다.
### Agents
@@ -93,10 +167,22 @@ OpenCode 는 아주 확장가능하고 아주 커스터마이저블합니다.
- **frontend-ui-ux-engineer** (`google/gemini-3-pro-preview`): 개발자로 전향한 디자이너라는 설정을 갖고 있습니다. 멋진 UI를 만듭니다. 아름답고 창의적인 UI 코드를 생성하는 데 탁월한 Gemini를 사용합니다.
- **document-writer** (`google/gemini-3-pro-preview`): 기술 문서 전문가라는 설정을 갖고 있습니다. Gemini 는 문학가입니다. 글을 기가막히게 씁니다.
각 에이전트는 메인 에이전트가 알아서 호출하지만, 명시적으로 요청할 수도 있습니다:
```
@oracle 한테 이 부분 설계 고민하고서 아키텍쳐 제안을 부탁해줘
@librarian 한테 이 부분 어떻게 구현돼있길래 자꾸 안에서 동작이 바뀌는지 알려달라고 해줘
@explore 한테 이 기능 정책 알려달라고 해줘
```
에이전트의 모델, 프롬프트, 권한은 `oh-my-opencode.json`에서 커스텀할 수 있습니다. 자세한 내용은 [설정](#설정)을 참고하세요.
### Tools
#### 내장 LSP Tools
당신이 에디터에서 사용하는 그 기능을 다른 에이전트들은 사용하지 못합니다. Oh My OpenCode 는 당신만의 그 도구를 LLM Agent 에게 쥐어줍니다. 리팩토링하고, 탐색하고, 분석하는 모든 작업을 OpenCode 의 설정값을 그대로 사용하여 지원합니다.
[OpenCode 는 LSP 를 제공하지만](https://opencode.ai/docs/lsp/), 오로지 분석용으로만 제공합니다. 탐색과 리팩토링을 위한 도구는 OpenCode 와 동일한 스펙과 설정으로 Oh My OpenCode 가 제공합니다.
- **lsp_hover**: 위치의 타입 정보, 문서, 시그니처 가져오기
@@ -115,18 +201,175 @@ OpenCode 는 아주 확장가능하고 아주 커스터마이저블합니다.
- **ast_grep_search**: AST 인식 코드 패턴 검색 (25개 언어)
- **ast_grep_replace**: AST 인식 코드 교체
#### Safe Grep
- **safe_grep**: 안전 제한이 있는 콘텐츠 검색 (5분 타임아웃, 10MB 출력 제한).
#### Grep
- **grep**: 안전 제한이 있는 콘텐츠 검색 (5분 타임아웃, 10MB 출력 제한). OpenCode의 내장 `grep` 도구를 대체합니다.
- 기본 grep 도구는 시간제한이 걸려있지 않습니다. 대형 코드베이스에서 광범위한 패턴을 검색하면 CPU가 폭발하고 무한히 멈출 수 있습니다.
- safe_grep 은 timeout 과 더 엄격한 출력 제한을 적용합니다.
- **주의**: 기본 grep 도구는 Agent 를 햇갈리게 하지 않기 위해 비활성화됩니다. 그러나 SafeGrep 은 Grep 이 제공하는 모든 기능을 제공합니다.
- 이 도구는 엄격한 제한을 적용하며, 내장 `grep`을 완전히 대체합니다.
#### Glob
- **glob**: 타임아웃 보호가 있는 파일 패턴 매칭 (60초). OpenCode 내장 `glob` 도구를 대체합니다.
- 기본 `glob`은 타임아웃이 없습니다. ripgrep이 멈추면 무한정 대기합니다.
- 이 도구는 타임아웃을 강제하고 만료 시 프로세스를 종료합니다.
#### 내장 MCPs
- **websearch_exa**: Exa AI 웹 검색. 실시간 웹 검색과 콘텐츠 스크래핑을 수행합니다. 관련 웹사이트에서 LLM에 최적화된 컨텍스트를 반환합니다.
- **context7**: 라이브러리 문서 조회. 정확한 코딩을 위해 최신 라이브러리 문서를 가져옵니다.
필요 없다면 `oh-my-opencode.json`에서 비활성화할 수 있습니다:
```json
{
"disabled_mcps": ["websearch_exa"]
}
```
### Claude Code 호환성
Oh My OpenCode는 Claude Code 설정과 완벽하게 호환됩니다. Claude Code를 사용하셨다면, 기존 설정을 그대로 사용할 수 있습니다.
#### Hooks 통합
Claude Code의 `settings.json` 훅 시스템을 통해 커스텀 스크립트를 실행합니다. Oh My OpenCode는 다음 위치의 훅을 읽고 실행합니다:
- `~/.claude/settings.json` (사용자)
- `./.claude/settings.json` (프로젝트)
- `./.claude/settings.local.json` (로컬, git-ignored)
지원되는 훅 이벤트:
- **PreToolUse**: 도구 실행 전에 실행. 차단하거나 도구 입력을 수정할 수 있습니다.
- **PostToolUse**: 도구 실행 후에 실행. 경고나 컨텍스트를 추가할 수 있습니다.
- **UserPromptSubmit**: 사용자가 프롬프트를 제출할 때 실행. 차단하거나 메시지를 주입할 수 있습니다.
- **Stop**: 세션이 유휴 상태가 될 때 실행. 후속 프롬프트를 주입할 수 있습니다.
`settings.json` 예시:
```json
{
"hooks": {
"PostToolUse": [
{
"matcher": "Write|Edit",
"hooks": [{ "type": "command", "command": "eslint --fix $FILE" }]
}
]
}
}
```
#### 설정 로더
**Command Loader**: 4개 디렉토리에서 마크다운 기반 슬래시 명령어를 로드합니다:
- `~/.claude/commands/` (사용자)
- `./.claude/commands/` (프로젝트)
- `~/.config/opencode/command/` (opencode 전역)
- `./.opencode/command/` (opencode 프로젝트)
**Skill Loader**: `SKILL.md`가 있는 디렉토리 기반 스킬을 로드합니다:
- `~/.claude/skills/` (사용자)
- `./.claude/skills/` (프로젝트)
**Agent Loader**: 마크다운 파일에서 커스텀 에이전트 정의를 로드합니다:
- `~/.claude/agents/*.md` (사용자)
- `./.claude/agents/*.md` (프로젝트)
**MCP Loader**: `.mcp.json` 파일에서 MCP 서버 설정을 로드합니다:
- `~/.claude/.mcp.json` (사용자)
- `./.mcp.json` (프로젝트)
- `./.claude/.mcp.json` (로컬)
- 환경변수 확장 지원 (`${VAR}` 문법)
#### 데이터 저장소
**Todo 관리**: 세션 todo가 `~/.claude/todos/`에 Claude Code 호환 형식으로 저장됩니다.
**Transcript**: 세션 활동이 `~/.claude/transcripts/`에 JSONL 형식으로 기록되어 재생 및 분석이 가능합니다.
> **`claude-code-*` 네이밍에 대해**: `src/features/claude-code-*/` 아래의 기능들은 Claude Code의 설정 시스템에서 마이그레이션되었습니다. 이 네이밍 규칙은 어떤 기능이 Claude Code에서 유래했는지 명확히 식별합니다.
### 기타 편의 기능
- **Terminal Title**: 세션 상태에 따라 터미널 타이틀을 자동 업데이트합니다 (유휴 ○, 처리중 ◐, 도구 ⚡, 에러 ✖). tmux를 지원합니다.
- **Session State**: 이벤트 훅과 터미널 타이틀 업데이트에 사용되는 중앙집중식 세션 추적 모듈입니다.
## 설정
설정 파일 위치 (우선순위 순):
1. `.opencode/oh-my-opencode.json` (프로젝트)
2. `~/.config/opencode/oh-my-opencode.json` (사용자)
Schema 자동 완성이 지원됩니다:
```json
{
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json"
}
```
### Agents
내장 에이전트 설정을 오버라이드할 수 있습니다:
```json
{
"agents": {
"explore": {
"model": "anthropic/claude-haiku-4-5",
"temperature": 0.5
},
"frontend-ui-ux-engineer": {
"disable": true
}
}
}
```
각 에이전트에서 지원하는 옵션: `model`, `temperature`, `top_p`, `prompt`, `tools`, `disable`, `description`, `mode`, `color`, `permission`.
또는 `disabled_agents`로 비활성화할 수 있습니다:
```json
{
"disabled_agents": ["oracle", "frontend-ui-ux-engineer"]
}
```
사용 가능한 에이전트: `oracle`, `librarian`, `explore`, `frontend-ui-ux-engineer`, `document-writer`
### MCPs
내장된 MCP를 비활성화합니다:
```json
{
"disabled_mcps": ["context7", "websearch_exa"]
}
```
더 자세한 내용은 [OpenCode MCP Servers](https://opencode.ai/docs/mcp-servers)를 참조하세요.
### LSP
Oh My OpenCode의 LSP 도구는 오직 **리팩토링(이름 변경, 코드 액션)만을 위한 것**입니다. 분석용 LSP는 OpenCode 자체에서 처리합니다.
`lsp` 옵션을 통해 LSP 서버를 설정합니다:
```json
{
"lsp": {
"typescript-language-server": {
"command": ["typescript-language-server", "--stdio"],
"extensions": [".ts", ".tsx"],
"priority": 10
},
"pylsp": {
"disabled": true
}
}
}
```
각 서버는 다음을 지원합니다: `command`, `extensions`, `priority`, `env`, `initialization`, `disabled`.
## 작성자의 노트
@@ -153,5 +396,3 @@ OpenCode 를 사용하여 이 프로젝트의 99% 를 작성했습니다. 기능
- [1.0.132](https://github.com/sst/opencode/releases/tag/v1.0.132) 혹은 이것보다 낮은 버전을 사용중이라면, OpenCode 의 버그로 인해 제대로 구성이 되지 않을 수 있습니다.
- [이를 고치는 PR 이 1.0.132 배포 이후에 병합되었으므로](https://github.com/sst/opencode/pull/5040) 이 변경사항이 포함된 최신 버전을 사용해주세요.

View File

@@ -1 +0,0 @@
README.en.md

396
README.md Normal file
View File

@@ -0,0 +1,396 @@
English | [한국어](README.ko.md)
## Contents
- [Oh My OpenCode](#oh-my-opencode)
- [TL;DR](#tldr)
- [Installation](#installation)
- [For LLM Agents](#for-llm-agents)
- [Why OpenCode & Why Oh My OpenCode](#why-opencode--why-oh-my-opencode)
- [Features](#features)
- [Hooks](#hooks)
- [Agents](#agents)
- [Tools](#tools)
- [Built-in LSP Tools](#built-in-lsp-tools)
- [Built-in AST-Grep Tools](#built-in-ast-grep-tools)
- [Grep](#grep)
- [Built-in MCPs](#built-in-mcps)
- [Claude Code Compatibility](#claude-code-compatibility)
- [Other Features](#other-features)
- [Configuration](#configuration)
- [Author's Note](#authors-note)
- [Warnings](#warnings)
# Oh My OpenCode
Oh My OpenCode
oMoMoMoMoMo···
If you work in tech, you likely appreciated [Claude Code](https://www.claude.com/product/claude-code).
If you are a hacker, you will fucking falling in love with [OpenCode](https://github.com/sst/opencode).
You don't write code just for a paycheck? You write because you genuinely love it?
To you, OpenCode will feel like the paradigm shift from Windows to Linux. Not you? It's still worth the investment. Give it 10 minutes. Your work and life will improve. I promise.
## TL;DR
- **Model Setup Required**
- This plugin utilizes models from [OpenCode Zen](https://opencode.ai/docs/zen/), Google, OpenAI, and Anthropic.
- For Anthropic models, use [OpenCode's built-in Claude Code Max Plan login](https://opencode.ai/docs/providers/#anthropic).
- For OpenAI models, I recommend the [OpenCode-OpenAI-Codex-Auth plugin](https://github.com/numman-ali/opencode-openai-codex-auth).
- For Gemini and GPT, use [VibeProxy (macOS Only)](https://github.com/automazeio/vibeproxy) or [CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI).
- **Truth be told, the rest is optional. Just install it. Once set up, no further learning is required. It simply evolves.**
- **Paste this document into Claude Code, OpenCode, or Cursor, instruct it to install, and ask for assistance if needed. It works seamlessly.**
- If you are an LLM Agent, install the required plugins and dependencies, then run `opencode auth login` via tmux to assist the user with configuration.
## Installation
Add to `~/.config/opencode/opencode.json`:
```json
{
"plugin": [
"oh-my-opencode"
]
}
```
## For LLM Agents
<details>
<summary>For LLM Agents (Click to expand)</summary>
If you are an LLM Agent helping a user set up oh-my-opencode, follow these steps:
### Step 1: Verify OpenCode Installation
```bash
if command -v opencode &> /dev/null; then
echo "OpenCode $(opencode --version) is installed"
else
echo "OpenCode is not installed. Please install it first."
echo "See: https://opencode.ai/docs"
fi
```
If OpenCode is not installed, guide the user to [OpenCode Installation Guide](https://opencode.ai/docs).
### Step 2: Configure oh-my-opencode Plugin
```bash
mkdir -p ~/.config/opencode
if [ -f ~/.config/opencode/opencode.json ]; then
# Existing config: add plugin using jq or python
if command -v jq &> /dev/null; then
jq '.plugin = ((.plugin // []) + ["oh-my-opencode"] | unique)' \
~/.config/opencode/opencode.json > /tmp/oc.json && \
mv /tmp/oc.json ~/.config/opencode/opencode.json
else
echo "Add \"oh-my-opencode\" to plugin array in ~/.config/opencode/opencode.json"
fi
else
# New config
echo '{"plugin":["oh-my-opencode"]}' > ~/.config/opencode/opencode.json
fi
```
### Step 3: Verify Setup
```bash
opencode --version # Should be >= 1.0.132
cat ~/.config/opencode/opencode.json # Should contain "oh-my-opencode" in plugin array
```
> **Note**: If model authentication is needed, run `opencode` and use `/connect` command, or assist the user with `opencode auth login` via tmux.
</details>
## Why OpenCode & Why Oh My OpenCode
OpenCode is limitlessly extensible and customizable. Zero screen flicker.
[LSP](https://opencode.ai/docs/lsp/), [linters, formatters](https://opencode.ai/docs/formatters/)? Automatic and fully configurable.
You can mix and orchestrate models to your exact specifications.
It is feature-rich. It is elegant. It handles the terminal without hesitation. It is high-performance.
But here is the catch: the learning curve is steep. There is a lot to master.
Inspired by [AmpCode](https://ampcode.com) and [Claude Code](https://code.claude.com/docs/en/overview), I have implemented their features here—often with superior execution.
Because this is OpenCode.
Consider this a superior AmpCode, a superior Claude Code, or simply a specialized distribution.
I believe in the right tool for the job. For your wallet's sake, use CLIProxyAPI or VibeProxy. Employ the best LLMs from frontier labs. You are in command.
**Note**: This setup is highly opinionated. It represents the generic component of my personal configuration, so it evolves constantly. I have spent tokens worth $20,000 just for my personal programming usages, and this plugin represents the apex of that experience. You simply inherit the best. If you have superior ideas, PRs are welcome.
## Features
### Hooks
- **Todo Continuation Enforcer**: Forces the agent to complete all tasks before exiting. Eliminates the common LLM issue of "giving up halfway".
- **Context Window Monitor**: Implements [Context Window Anxiety Management](https://agentic-patterns.com/patterns/context-window-anxiety-management/). When context usage exceeds 70%, it reminds the agent that resources are sufficient, preventing rushed or low-quality output.
- **Session Notification**: Sends a native OS notification when the job is done (macOS, Linux, Windows).
- **Session Recovery**: Automatically recovers from API errors, ensuring session stability. Handles four scenarios:
- **Tool Result Missing**: When `tool_use` block exists without `tool_result` (ESC interrupt) → injects "cancelled" tool results
- **Thinking Block Order**: When thinking block must be first but isn't → prepends empty thinking block
- **Thinking Disabled Violation**: When thinking blocks exist but thinking is disabled → strips thinking blocks
- **Empty Content Message**: When message has only thinking/meta blocks without actual content → injects "(interrupted)" text via filesystem
- **Comment Checker**: Detects and reports unnecessary comments after code modifications. Smartly ignores valid patterns (BDD, directives, docstrings, shebangs) to keep the codebase clean from AI-generated artifacts.
- **Directory AGENTS.md Injector**: Automatically injects `AGENTS.md` contents when reading files. Searches upward from the file's directory to project root, collecting **all** `AGENTS.md` files along the path hierarchy. This enables nested, directory-specific instructions:
```
project/
├── AGENTS.md # Project-wide context
├── src/
│ ├── AGENTS.md # src-specific context
│ └── components/
│ ├── AGENTS.md # Component-specific context
│ └── Button.tsx # Reading this injects ALL 3 AGENTS.md files
```
When reading `Button.tsx`, the hook injects contexts in order: `project/AGENTS.md` → `src/AGENTS.md` → `components/AGENTS.md`. Each directory's context is injected only once per session. Inspired by Claude Code's CLAUDE.md feature.
- **Think Mode**: Automatic extended thinking detection and mode switching. Detects when user requests deep thinking (e.g., "think deeply", "ultrathink") and dynamically adjusts model settings for enhanced reasoning.
- **Anthropic Auto Compact**: Automatically compacts conversation history when approaching context limits for Anthropic models.
- **Empty Task Response Detector**: Detects when subagent tasks return empty or meaningless responses and handles gracefully.
- **Grep Output Truncator**: Prevents grep output from overwhelming the context by truncating excessively long results.
### Agents
- **oracle** (`openai/gpt-5.1`): The architect. Expert in code reviews and strategy. Uses GPT-5.1 for its unmatched logic and reasoning capabilities. Inspired by AmpCode.
- **librarian** (`anthropic/claude-haiku-4-5`): Multi-repo analysis, documentation lookup, and implementation examples. Haiku is chosen for its speed, competence, excellent tool usage, and cost-efficiency. Inspired by AmpCode.
- **explore** (`opencode/grok-code`): Fast exploration and pattern matching. Claude Code uses Haiku; we use Grok. It is currently free, blazing fast, and intelligent enough for file traversal. Inspired by Claude Code.
- **frontend-ui-ux-engineer** (`google/gemini-3-pro-preview`): A designer turned developer. Creates stunning UIs. Uses Gemini because its creativity and UI code generation are superior.
- **document-writer** (`google/gemini-3-pro-preview`): A technical writing expert. Gemini is a wordsmith; it writes prose that flows naturally.
Each agent is automatically invoked by the main agent, but you can also explicitly request them:
```
@oracle Please think through the design of this part and suggest an architecture.
@librarian Tell me how this is implemented — why does the behavior keep changing internally?
@explore Tell me about the policy for this feature.
```
Agent models, prompts, and permissions can be customized via `oh-my-opencode.json`. See [Configuration](#configuration) for details.
### Tools
#### Built-in LSP Tools
The features you use in your editor—other agents cannot access them. Oh My OpenCode hands those very tools to your LLM Agent. Refactoring, navigation, and analysis are all supported using the same OpenCode configuration.
[OpenCode provides LSP](https://opencode.ai/docs/lsp/), but only for analysis. Oh My OpenCode equips you with navigation and refactoring tools matching the same specification.
- **lsp_hover**: Get type info, docs, signatures at position
- **lsp_goto_definition**: Jump to symbol definition
- **lsp_find_references**: Find all usages across workspace
- **lsp_document_symbols**: Get file's symbol outline
- **lsp_workspace_symbols**: Search symbols by name across project
- **lsp_diagnostics**: Get errors/warnings before build
- **lsp_servers**: List available LSP servers
- **lsp_prepare_rename**: Validate rename operation
- **lsp_rename**: Rename symbol across workspace
- **lsp_code_actions**: Get available quick fixes/refactorings
- **lsp_code_action_resolve**: Apply a code action
#### Built-in AST-Grep Tools
- **ast_grep_search**: AST-aware code pattern search (25 languages)
- **ast_grep_replace**: AST-aware code replacement
#### Grep
- **grep**: Content search with safety limits (5min timeout, 10MB output). Overrides OpenCode's built-in `grep` tool.
- The default `grep` lacks safeguards. On a large codebase, a broad pattern can cause CPU overload and indefinite hanging.
- This tool enforces strict limits and completely replaces the built-in `grep`.
#### Glob
- **glob**: File pattern matching with timeout protection (60s). Overrides OpenCode's built-in `glob` tool.
- The default `glob` lacks timeout. If ripgrep hangs, it waits indefinitely.
- This tool enforces timeouts and kills the process on expiration.
#### Built-in MCPs
- **websearch_exa**: Exa AI web search. Performs real-time web searches and can scrape content from specific URLs. Returns LLM-optimized context from relevant websites.
- **context7**: Library documentation lookup. Fetches up-to-date documentation for any library to assist with accurate coding.
Don't need these? Disable them via `oh-my-opencode.json`:
```json
{
"disabled_mcps": ["websearch_exa"]
}
```
### Claude Code Compatibility
Oh My OpenCode provides seamless Claude Code configuration compatibility. If you've been using Claude Code, your existing setup works out of the box.
#### Hooks Integration
Execute custom scripts via Claude Code's `settings.json` hook system. Oh My OpenCode reads and executes hooks defined in:
- `~/.claude/settings.json` (user)
- `./.claude/settings.json` (project)
- `./.claude/settings.local.json` (local, git-ignored)
Supported hook events:
- **PreToolUse**: Runs before tool execution. Can block or modify tool input.
- **PostToolUse**: Runs after tool execution. Can add warnings or context.
- **UserPromptSubmit**: Runs when user submits a prompt. Can block or inject messages.
- **Stop**: Runs when session goes idle. Can inject follow-up prompts.
Example `settings.json`:
```json
{
"hooks": {
"PostToolUse": [
{
"matcher": "Write|Edit",
"hooks": [{ "type": "command", "command": "eslint --fix $FILE" }]
}
]
}
}
```
#### Configuration Loaders
**Command Loader**: Loads markdown-based slash commands from 4 directories:
- `~/.claude/commands/` (user)
- `./.claude/commands/` (project)
- `~/.config/opencode/command/` (opencode global)
- `./.opencode/command/` (opencode project)
**Skill Loader**: Loads directory-based skills with `SKILL.md`:
- `~/.claude/skills/` (user)
- `./.claude/skills/` (project)
**Agent Loader**: Loads custom agent definitions from markdown files:
- `~/.claude/agents/*.md` (user)
- `./.claude/agents/*.md` (project)
**MCP Loader**: Loads MCP server configurations from `.mcp.json` files:
- `~/.claude/.mcp.json` (user)
- `./.mcp.json` (project)
- `./.claude/.mcp.json` (local)
- Supports environment variable expansion (`${VAR}` syntax)
#### Data Storage
**Todo Management**: Session todos are stored in Claude Code compatible format at `~/.claude/todos/`.
**Transcript**: Session activity is logged to `~/.claude/transcripts/` in JSONL format, enabling replay and analysis.
> **Note on `claude-code-*` naming**: Features under `src/features/claude-code-*/` are migrated from Claude Code's configuration system. This naming convention clearly identifies which features originated from Claude Code.
### Other Features
- **Terminal Title**: Auto-updates terminal title with session status (idle ○, processing ◐, tool ⚡, error ✖). Supports tmux.
- **Session State**: Centralized session tracking module used by event hooks and terminal title updates.
## Configuration
Configuration file locations (in priority order):
1. `.opencode/oh-my-opencode.json` (project)
2. `~/.config/opencode/oh-my-opencode.json` (user)
Schema autocomplete is supported:
```json
{
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json"
}
```
### Agents
Override built-in agent settings:
```json
{
"agents": {
"explore": {
"model": "anthropic/claude-haiku-4-5",
"temperature": 0.5
},
"frontend-ui-ux-engineer": {
"disable": true
}
}
}
```
Each agent supports: `model`, `temperature`, `top_p`, `prompt`, `tools`, `disable`, `description`, `mode`, `color`, `permission`.
Or disable agents via `disabled_agents`:
```json
{
"disabled_agents": ["oracle", "frontend-ui-ux-engineer"]
}
```
Available agents: `oracle`, `librarian`, `explore`, `frontend-ui-ux-engineer`, `document-writer`
### MCPs
Disable built-in MCPs:
```json
{
"disabled_mcps": ["context7", "websearch_exa"]
}
```
See [OpenCode MCP Servers](https://opencode.ai/docs/mcp-servers) for more.
### LSP
Oh My OpenCode's LSP tools are for **refactoring only** (rename, code actions). Analysis LSP is handled by OpenCode itself.
Configure LSP servers via `lsp` option:
```json
{
"lsp": {
"typescript-language-server": {
"command": ["typescript-language-server", "--stdio"],
"extensions": [".ts", ".tsx"],
"priority": 10
},
"pylsp": {
"disabled": true
}
}
}
```
Each server supports: `command`, `extensions`, `priority`, `env`, `initialization`, `disabled`.
## Author's Note
Install Oh My OpenCode. Do not waste time configuring OpenCode from scratch.
I have resolved the friction so you don't have to. The answers are in this plugin. If OpenCode is Arch Linux, Oh My OpenCode is [Omarchy](https://omarchy.org/).
Enjoy the multi-model stability and rich feature set that other harnesses promise but fail to deliver.
I will continue testing and updating here. I am the primary user of this project.
- Who possesses the best raw logic?
- Who is the debugging god?
- Who writes the best prose?
- Who dominates frontend?
- Who owns backend?
- Which model is fastest for daily driving?
- What new features are other harnesses shipping?
Do not overthink it. I have done the thinking. I will integrate the best practices. I will update this.
If this sounds arrogant and you have a superior solution, send a PR. You are welcome.
As of now, I have no affiliation with any of the projects or models mentioned here. This plugin is purely based on personal experimentation and preference.
I constructed 99% of this project using OpenCode. I focused on functional verification. This documentation has been personally reviewed and comprehensively rewritten, so you can rely on it with confidence.
## Warnings
- If you are on [1.0.132](https://github.com/sst/opencode/releases/tag/v1.0.132) or lower, OpenCode has a bug that might break config.
- [The fix](https://github.com/sst/opencode/pull/5040) was merged after 1.0.132, so use a newer version.

View File

@@ -0,0 +1,159 @@
{
"$schema": "http://json-schema.org/draft-07/schema#",
"$id": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
"title": "Oh My OpenCode Configuration",
"description": "Configuration schema for oh-my-opencode plugin",
"type": "object",
"properties": {
"$schema": {
"type": "string"
},
"disabled_mcps": {
"type": "array",
"items": {
"type": "string",
"enum": [
"websearch_exa",
"context7"
]
}
},
"disabled_agents": {
"type": "array",
"items": {
"type": "string",
"enum": [
"oracle",
"librarian",
"explore",
"frontend-ui-ux-engineer",
"document-writer"
]
}
},
"agents": {
"type": "object",
"propertyNames": {
"type": "string",
"enum": [
"oracle",
"librarian",
"explore",
"frontend-ui-ux-engineer",
"document-writer"
]
},
"additionalProperties": {
"type": "object",
"properties": {
"model": {
"type": "string"
},
"temperature": {
"type": "number",
"minimum": 0,
"maximum": 2
},
"top_p": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"prompt": {
"type": "string"
},
"tools": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "boolean"
}
},
"disable": {
"type": "boolean"
},
"description": {
"type": "string"
},
"mode": {
"type": "string",
"enum": [
"subagent",
"primary",
"all"
]
},
"color": {
"type": "string",
"pattern": "^#[0-9A-Fa-f]{6}$"
},
"permission": {
"type": "object",
"properties": {
"edit": {
"type": "string",
"enum": [
"ask",
"allow",
"deny"
]
},
"bash": {
"anyOf": [
{
"type": "string",
"enum": [
"ask",
"allow",
"deny"
]
},
{
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string",
"enum": [
"ask",
"allow",
"deny"
]
}
}
]
},
"webfetch": {
"type": "string",
"enum": [
"ask",
"allow",
"deny"
]
},
"doom_loop": {
"type": "string",
"enum": [
"ask",
"allow",
"deny"
]
},
"external_directory": {
"type": "string",
"enum": [
"ask",
"allow",
"deny"
]
}
}
}
}
}
}
}
}

View File

@@ -7,13 +7,14 @@
"dependencies": {
"@ast-grep/cli": "^0.40.0",
"@ast-grep/napi": "^0.40.0",
"@code-yeongyu/comment-checker": "^0.4.4",
"@opencode-ai/plugin": "^1.0.7",
"tree-sitter-wasms": "^0.1.12",
"web-tree-sitter": "^0.24.7",
"xdg-basedir": "^5.1.0",
"zod": "^4.1.8",
},
"devDependencies": {
"bun-types": "latest",
"oh-my-opencode": "^0.1.30",
"typescript": "^5.7.3",
},
"peerDependencies": {
@@ -23,6 +24,8 @@
},
"trustedDependencies": [
"@ast-grep/cli",
"@ast-grep/napi",
"@code-yeongyu/comment-checker",
],
"packages": {
"@ast-grep/cli": ["@ast-grep/cli@0.40.0", "", { "dependencies": { "detect-libc": "2.1.2" }, "optionalDependencies": { "@ast-grep/cli-darwin-arm64": "0.40.0", "@ast-grep/cli-darwin-x64": "0.40.0", "@ast-grep/cli-linux-arm64-gnu": "0.40.0", "@ast-grep/cli-linux-x64-gnu": "0.40.0", "@ast-grep/cli-win32-arm64-msvc": "0.40.0", "@ast-grep/cli-win32-ia32-msvc": "0.40.0", "@ast-grep/cli-win32-x64-msvc": "0.40.0" }, "bin": { "sg": "sg", "ast-grep": "ast-grep" } }, "sha512-L8AkflsfI2ZP70yIdrwqvjR02ScCuRmM/qNGnJWUkOFck+e6gafNVJ4e4jjGQlEul+dNdBpx36+O2Op629t47A=="],
@@ -61,6 +64,8 @@
"@ast-grep/napi-win32-x64-msvc": ["@ast-grep/napi-win32-x64-msvc@0.40.0", "", { "os": "win32", "cpu": "x64" }, "sha512-Hk2IwfPqMFGZt5SRxsoWmGLxBXxprow4LRp1eG6V8EEiJCNHxZ9ZiEaIc5bNvMDBjHVSnqZAXT22dROhrcSKQg=="],
"@code-yeongyu/comment-checker": ["@code-yeongyu/comment-checker@0.4.4", "", { "os": [ "linux", "win32", "darwin", ], "cpu": [ "x64", "arm64", ], "bin": { "comment-checker": "bin/comment-checker" } }, "sha512-vsbdLMQYJJNDV/baTDnNqqg/MZwA+9nz7TE6Mybj8zjZVTCn4ZivH4hAdD5p4fLxhGZEJ5x1UDmXA6pAGA7lHA=="],
"@opencode-ai/plugin": ["@opencode-ai/plugin@1.0.128", "", { "dependencies": { "@opencode-ai/sdk": "1.0.128", "zod": "4.1.8" } }, "sha512-M5vjz3I6KeoBSNduWmT5iHXRtTLCqICM5ocs+WrB3uxVorslcO3HVwcLzrERh/ntpxJ/1xhnHQaeG6Mg+P744A=="],
"@opencode-ai/sdk": ["@opencode-ai/sdk@1.0.128", "", {}, "sha512-Kow3Ivg8bR8dNRp8C0LwF9e8+woIrwFgw3ZALycwCfqS/UujDkJiBeYHdr1l/07GSHP9sZPmvJ6POuvfZ923EA=="],
@@ -95,14 +100,16 @@
"detect-libc": ["detect-libc@2.1.2", "", {}, "sha512-Btj2BOOO83o3WyH59e8MgXsxEQVcarkUOpEYrubB0urwnN10yQ364rsiByU11nZlqWYZm05i/of7io4mzihBtQ=="],
"tree-sitter-wasms": ["tree-sitter-wasms@0.1.13", "", { "dependencies": { "tree-sitter-wasms": "^0.1.11" } }, "sha512-wT+cR6DwaIz80/vho3AvSF0N4txuNx/5bcRKoXouOfClpxh/qqrF4URNLQXbbt8MaAxeksZcZd1j8gcGjc+QxQ=="],
"oh-my-opencode": ["oh-my-opencode@0.1.30", "", { "dependencies": { "@ast-grep/cli": "^0.40.0", "@ast-grep/napi": "^0.40.0", "@code-yeongyu/comment-checker": "^0.4.1", "@opencode-ai/plugin": "^1.0.7", "xdg-basedir": "^5.1.0", "zod": "^4.1.8" }, "peerDependencies": { "bun": ">=1.0.0" } }, "sha512-pXGGgL/7Jcz3yuGJJTI72BKern2egwfRz2LQZTBq+jl+pNCybOvGvXtFmR+WGlF8O3ZjL1wIHypBbIVuHOBzxg=="],
"typescript": ["typescript@5.9.3", "", { "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" } }, "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw=="],
"undici-types": ["undici-types@7.16.0", "", {}, "sha512-Zz+aZWSj8LE6zoxD+xrjh4VfkIG8Ya6LvYkZqtUQGJPZjYl53ypCaUwWqo7eI0x66KBGeRo+mlBEkMSeSZ38Nw=="],
"web-tree-sitter": ["web-tree-sitter@0.24.7", "", {}, "sha512-CdC/TqVFbXqR+C51v38hv6wOPatKEUGxa39scAeFSm98wIhZxAYonhRQPSMmfZ2w7JDI0zQDdzdmgtNk06/krQ=="],
"xdg-basedir": ["xdg-basedir@5.1.0", "", {}, "sha512-GCPAHLvrIH13+c0SuacwvRYj2SxJXQ4kaVTT5xgL3kPrz56XxkF21IGhjSE1+W0aw7gpBWRGXLCPnPby6lSpmQ=="],
"zod": ["zod@4.1.8", "", {}, "sha512-5R1P+WwQqmmMIEACyzSvo4JXHY5WiAFHRMg+zBZKgKS+Q1viRa0C1hmUKtHltoIFKtIdki3pRxkmpP74jnNYHQ=="],
"oh-my-opencode/@code-yeongyu/comment-checker": ["@code-yeongyu/comment-checker@0.4.1", "", { "os": [ "linux", "win32", "darwin", ], "cpu": [ "x64", "arm64", ], "bin": { "comment-checker": "bin/comment-checker" } }, "sha512-E7p1V8CsRj9hMbwENd9BfxZGWYu+lKS5tXGuNNcNtkRMhWvwM/ononysKpLB7LXdxfSYAn0j7heJydyzEmm+lg=="],
}
}

View File

@@ -59,3 +59,787 @@ All tasks execution STARTED: Thu Dec 4 16:52:57 KST 2025
---
## [2025-12-08 18:56] - Task 1: Remove unused import formatWorkspaceEdit from LSP tools
### DISCOVERED ISSUES
- None - simple import cleanup task
### IMPLEMENTATION DECISIONS
- Removed only `formatWorkspaceEdit` from import list at line 17
- Kept all other imports intact (formatCodeActions, applyWorkspaceEdit, formatApplyResult remain)
- Verified the function exists in utils.ts:212 but is truly unused in tools.ts
### PROBLEMS FOR NEXT TASKS
- None identified for remaining tasks
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Ran: `bun run build` → exit 0, bundled 200 modules
- Ran: `rg "formatWorkspaceEdit" src/tools/lsp/tools.ts` → no matches (confirmed removal)
### LEARNINGS
- Convention: This project uses `bun run typecheck` (tsc --noEmit) and `bun run build` for verification
- The `formatWorkspaceEdit` function still exists in utils.ts - it's exported but just not used in tools.ts
소요 시간: ~2분
---
## [2025-12-08 19:00] - Task 2: Remove unused ThinkingPart interface and fallbackRevertStrategy function
### DISCOVERED ISSUES
- None - both items were genuinely unused (no callers found)
### IMPLEMENTATION DECISIONS
- Removed `ThinkingPart` interface (lines 37-40) - defined but never referenced
- Removed `fallbackRevertStrategy` function (lines 189-244) - defined but never called
- Added comment explaining removal reason as per task requirements
- Kept `ThinkingPartType`, `prependThinkingPart`, `stripThinkingParts` - these are different items and ARE used
### PROBLEMS FOR NEXT TASKS
- None identified
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Ran: `bun run build` → exit 0, bundled 200 modules
- Ran: `rg "ThinkingPart" src/hooks/session-recovery/` → only related types/functions found, interface removed
- Ran: `rg "fallbackRevertStrategy" src/hooks/session-recovery/` → only comment found, function removed
- Ran: `rg "createSessionRecoveryHook" src/hooks/` → exports intact
### LEARNINGS
- `ThinkingPart` interface vs `ThinkingPartType` type vs `prependThinkingPart` function - different entities, verify before removing
- `fallbackRevertStrategy` was likely a planned feature that never got integrated into the recovery flow
소요 시간: ~2분
---
## [2025-12-08 19:04] - Task 3: Remove unused builtinMcps export from MCP module
### DISCOVERED ISSUES
- None - `builtinMcps` export was genuinely unused (no external importers)
### IMPLEMENTATION DECISIONS
- Removed `export const builtinMcps = allBuiltinMcps` from line 24
- Kept `allBuiltinMcps` const - used internally by `createBuiltinMcps` function
- Kept `createBuiltinMcps` function - actively used in src/index.ts:89
### PROBLEMS FOR NEXT TASKS
- None identified
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Ran: `bun run build` → exit 0, bundled 200 modules
- Ran: `rg "builtinMcps" src/mcp/index.ts` → no matches (export removed)
- Ran: `rg "createBuiltinMcps" src/mcp/index.ts` → function still exists
### LEARNINGS
- `createBuiltinMcps` function vs `builtinMcps` export - function is used, direct export is not
- Internal const `allBuiltinMcps` should be kept since it's referenced by the function
소요 시간: ~2분
---
## [2025-12-09 16:13] - Task 1: Add file-based logger to shared module
### DISCOVERED ISSUES
- None - straightforward file copy and modification task
### IMPLEMENTATION DECISIONS
- Copied logger.ts from opencode-cc-plugin source
- Changed log file path from `opencode-cc-plugin.log` to `oh-my-opencode.log`
- Added barrel export from `src/shared/index.ts`
- Kept original comment for module description
### PROBLEMS FOR NEXT TASKS
- None identified - logger is now available for use in all new loaders
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Log file path verified: `/tmp/oh-my-opencode.log`
- Exports verified: `log()` and `getLogFilePath()` now accessible via `src/shared`
### LEARNINGS
- Source file location: `~/local-workspaces/opencode-cc-plugin/src/shared/logger.ts`
- Logger uses `fs.appendFileSync` for synchronous file writing
- Empty catch block intentionally swallows errors to prevent logging from breaking main operations
소요 시간: ~1분
---
## [2025-12-09 16:14] - Task 3: Rename skill-loader to claude-code-skill-loader
### DISCOVERED ISSUES
- None - straightforward directory rename task
### IMPLEMENTATION DECISIONS
- Used `mv` command to rename `src/features/skill-loader/``src/features/claude-code-skill-loader/`
- Updated import path in `src/index.ts` (lines 19-22)
- Did NOT modify internal imports (`../command-loader/types`) since command-loader still exists (Task 2 runs in parallel)
### PROBLEMS FOR NEXT TASKS
- If Task 2 renames command-loader to claude-code-command-loader, the internal imports in claude-code-skill-loader will need to be updated as part of Task 2's scope
- The skill-loader's loader.ts:6 and types.ts:1 import from `../command-loader/types`
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Ran: `bun run build` → exit 0, succeeded
- Directory structure verified: `skill-loader/` deleted, `claude-code-skill-loader/` exists
### LEARNINGS
- This project uses `mv` for directory rename (acceptable per ANTI-PATTERNS - file creation is forbidden, not rename)
- Command: `bun run typecheck` for type check, `bun run build` for build
- skill-loader internal imports use relative paths (`../command-loader/types`) which remain valid after rename
소요 시간: ~2분
---
## [2025-12-09 16:16] - Task 2: Rename command-loader to claude-code-command-loader
### DISCOVERED ISSUES
- skill-loader (now claude-code-skill-loader) was importing `CommandDefinition` from `../command-loader/types`
- After renaming command-loader, these references also needed updating
### IMPLEMENTATION DECISIONS
- Used `mv` command: `src/features/command-loader/``src/features/claude-code-command-loader/`
- Updated import path in `src/index.ts` (lines 13-18)
- Also updated `claude-code-skill-loader/loader.ts:6` and `types.ts:1` to reference new path
### PROBLEMS FOR NEXT TASKS
- None identified - all dependent imports updated
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Directory structure verified: `command-loader/` deleted, `claude-code-command-loader/` exists
- All imports updated: src/index.ts, claude-code-skill-loader/loader.ts, claude-code-skill-loader/types.ts
### LEARNINGS
- skill-loader depends on command-loader's `CommandDefinition` type via relative import
- When renaming shared modules, must update ALL dependent modules' imports
- Task 2 and Task 3 have an implicit dependency through the type import
소요 시간: ~2분
---
## [2025-12-09 16:24] - Task 4: Add claude-code-agent-loader feature
### DISCOVERED ISSUES
- None - straightforward file copy task
### IMPLEMENTATION DECISIONS
- Copied 3 files from opencode-cc-plugin: `index.ts`, `loader.ts`, `types.ts`
- Import path `../../shared/frontmatter` unchanged - already compatible with oh-my-opencode structure
- No `log()` usage in source files - no logger integration needed
### PROBLEMS FOR NEXT TASKS
- None identified - agent-loader is self-contained
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Directory structure verified: `claude-code-agent-loader/` created with 3 files
- Functions exported: `loadUserAgents()`, `loadProjectAgents()`
### LEARNINGS
- Source location: `~/local-workspaces/opencode-cc-plugin/src/features/agent-loader/`
- Agent loader uses `parseFrontmatter` from shared module
- Agent configs loaded from `~/.claude/agents/` (user) and `.claude/agents/` (project)
- Scope is appended to description: `(user)` or `(project)`
소요 시간: ~1분
---
## [2025-12-09 16:25] - Task 5: Add claude-code-mcp-loader feature
### DISCOVERED ISSUES
- None - straightforward file copy task
### IMPLEMENTATION DECISIONS
- Copied 5 files from opencode-cc-plugin: `index.ts`, `loader.ts`, `transformer.ts`, `env-expander.ts`, `types.ts`
- Import path `../../shared/logger` unchanged - already compatible with oh-my-opencode structure
- Kept `Bun.file()` usage - oh-my-opencode targets Bun runtime
- Environment variable expansion supports `${VAR}` and `${VAR:-default}` syntax
### PROBLEMS FOR NEXT TASKS
- None identified - mcp-loader is self-contained
- Does NOT conflict with src/mcp/ (builtin MCPs are separate)
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Directory structure verified: `claude-code-mcp-loader/` created with 5 files
- Functions exported: `loadMcpConfigs()`, `formatLoadedServersForToast()`, `transformMcpServer()`, `expandEnvVars()`, `expandEnvVarsInObject()`
### LEARNINGS
- Source location: `~/local-workspaces/opencode-cc-plugin/src/features/mcp-loader/`
- MCP configs loaded from:
- `~/.claude/.mcp.json` (user scope)
- `.mcp.json` (project scope)
- `.claude/.mcp.json` (local scope)
- Later scope overrides earlier scope for same server name
- Supports stdio, http, and sse server types
소요 시간: ~1분
---
## [2025-12-09 16:24] - Task 6: Add claude-code-session-state feature
### DISCOVERED ISSUES
- None - straightforward file copy task
### IMPLEMENTATION DECISIONS
- Copied 4 files from opencode-cc-plugin: `types.ts`, `state.ts`, `detector.ts`, `index.ts`
- No import path changes needed - files are completely self-contained
- No external dependencies - types are defined locally
### PROBLEMS FOR NEXT TASKS
- Task 7 should import from `./features/claude-code-session-state` in src/index.ts
- Task 7 should remove local session variables and use the module's getter/setters
### VERIFICATION RESULTS
- Directory created: `src/features/claude-code-session-state/` (4 files confirmed)
- Exports available: sessionErrorState, sessionInterruptState, subagentSessions, sessionFirstMessageProcessed (Maps/Sets)
- Exports available: currentSessionID, currentSessionTitle, mainSessionID (state vars)
- Exports available: setCurrentSession(), setMainSession(), getCurrentSessionID(), getCurrentSessionTitle(), getMainSessionID() (getters/setters)
- Exports available: detectInterrupt() function
### LEARNINGS
- Session state module is completely self-contained - no external dependencies
- Uses barrel export pattern: index.ts re-exports everything from types, state, detector
- Source directory: `~/local-workspaces/opencode-cc-plugin/src/features/session-state/`
소요 시간: ~1분
---
## [2025-12-09 16:32] - Task 7: Integrate new features into src/index.ts
### DISCOVERED ISSUES
- None - integration task with well-defined API from previous tasks
### IMPLEMENTATION DECISIONS
- Added imports for new modules:
- `loadUserAgents`, `loadProjectAgents` from `./features/claude-code-agent-loader`
- `loadMcpConfigs` from `./features/claude-code-mcp-loader`
- `setCurrentSession`, `setMainSession`, `getMainSessionID`, `getCurrentSessionTitle` from `./features/claude-code-session-state`
- `log` from `./shared/logger`
- Removed local session variables (lines 77-79): `mainSessionID`, `currentSessionID`, `currentSessionTitle`
- Replaced direct session assignments with setter functions:
- `mainSessionID = x``setMainSession(x)`
- `currentSessionID = x; currentSessionTitle = y``setCurrentSession(x, y)`
- Replaced session variable reads with getter functions:
- `mainSessionID` comparisons → `getMainSessionID()`
- `currentSessionTitle` reads → `getCurrentSessionTitle()`
- Added agent loading in config hook: `loadUserAgents()`, `loadProjectAgents()`
- Added MCP loading in config hook: `await loadMcpConfigs()` (async)
- Replaced `console.error` with `log()` for config validation errors
- Renamed local variable `agents` to `builtinAgents` to distinguish from loaded agents
### PROBLEMS FOR NEXT TASKS
- Task 8 (README update) should document the new Agent Loader and MCP Loader features
- Should explain the `claude-code-*` naming convention
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Ran: `bun run build` → exit 0, successful build
- Session tracking verified: all event handlers use getter/setter functions
- Agent loading verified: config.agent merges builtin + user + project agents
- MCP loading verified: config.mcp merges builtin MCPs + loaded MCP servers
### LEARNINGS
- `setCurrentSession(id, title)` sets both ID and title atomically
- `loadMcpConfigs()` is async - must use `await` in config hook
- MCP result has `.servers` property that returns the server configs
- Order matters in spread: later values override earlier (projectAgents > userAgents > builtinAgents)
소요 시간: ~4분
---
## [2025-12-09 16:35] - Task 8: Update README.md documentation
### DISCOVERED ISSUES
- None - documentation update task
### IMPLEMENTATION DECISIONS
- Added Agent Loader feature documentation under "Other Features" section (line 235-238)
- User scope: `~/.claude/agents/`
- Project scope: `./.claude/agents/`
- Format: `*.md` files with YAML frontmatter
- Added MCP Loader feature documentation (line 239-243)
- User scope: `~/.claude/.mcp.json`
- Project scope: `./.mcp.json`
- Local scope: `./.claude/.mcp.json`
- Environment variable expansion (`${VAR}` syntax)
- Added `claude-code-*` naming convention explanation as a blockquote note (line 245)
- Explains features migrated from Claude Code
- Lists examples: claude-code-command-loader, skill-loader, agent-loader, mcp-loader
### PROBLEMS FOR NEXT TASKS
- None - this is the final task
### VERIFICATION RESULTS
- README.md updated with new documentation
- Style matches existing documentation (bullet points, code blocks for paths)
- No sections removed or modified (only additions)
### LEARNINGS
- README.md "Other Features" section is at line 224
- Existing features: Terminal Title, Command Loader, Skill Loader
- Documentation style: bold feature name, bullet points for scopes/details
소요 시간: ~1분
---
## [2025-12-09 17:24] - Task 0: Shared Utilities 포팅
### DISCOVERED ISSUES
- command-executor.ts already existed but had minor whitespace differences (indentation inconsistency)
- pattern-matcher.ts and hook-disabled.ts import from `../claude-compat/types` which doesn't exist yet in oh-my-opencode
- Types will be created in Task 1 at `src/hooks/claude-code-hooks/types.ts`
### IMPLEMENTATION DECISIONS
- Created snake-case.ts and tool-name.ts (no dependencies) - exact copy from source
- Created temporary stub types at `src/hooks/claude-code-hooks/types.ts` with minimal definitions needed for shared utilities
- Created pattern-matcher.ts with adjusted import: `../claude-compat/types``../hooks/claude-code-hooks/types`
- Created hook-disabled.ts with adjusted import to point to stub types
- Added all new utilities to `src/shared/index.ts` using barrel export pattern
- Stub types include: HookCommand, HookMatcher, ClaudeHooksConfig, ClaudeHookEvent, PluginConfig
### PROBLEMS FOR NEXT TASKS
- Task 1 will replace stub types with full implementation from opencode-cc-plugin
- Stub types in `src/hooks/claude-code-hooks/types.ts` are marked with comments indicating they're temporary
- The real PluginConfig will likely be different - current stub only supports `disabledHooks` field
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- All 5 functions exported: executeHookCommand, objectToSnakeCase, transformToolName, findMatchingHooks, isHookDisabled
- Import paths verified: pattern-matcher.ts and hook-disabled.ts successfully import from stub types
### LEARNINGS
- Import paths must be adjusted when porting between different project structures
- opencode-cc-plugin structure: `src/claude-compat/` → oh-my-opencode structure: `src/hooks/claude-code-hooks/`
- Stub types strategy allows Task 0 to complete and typecheck to pass before Task 1 implements full types
- command-executor.ts in oh-my-opencode had indentation inconsistency (not 100% identical to source)
소요 시간: ~5분
---
## [2025-12-09 17:34] - Task 1: types.ts 포팅
### DISCOVERED ISSUES
- Stub types.ts had `PluginConfig` interface needed by hook-disabled.ts (from Task 0)
- Full types.ts from opencode-cc-plugin did NOT have `PluginConfig`
- Typecheck initially failed: Module has no exported member 'PluginConfig'
### IMPLEMENTATION DECISIONS
- Copied full types.ts (181 lines) from opencode-cc-plugin → oh-my-opencode
- Preserved ALL types: ClaudeHooksConfig, HookMatcher, PreToolUseInput/Output, PostToolUseInput/Output
- Preserved deprecated decision fields: `decision?: "allow" | "deny" | "approve" | "block" | "ask"`
- Added `PluginConfig` interface at end (oh-my-opencode specific type needed by hook-disabled.ts)
- Kept line 150 comment (`// "pending" | "in_progress" | "completed"`) - existing source comment
### PROBLEMS FOR NEXT TASKS
- PluginConfig is now available for all subsequent tasks
- Full type definitions ready for Task 2, 3, 4+ to use
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Verified: ClaudeHooksConfig, HookMatcher, HookCommand types exist
- Verified: PreToolUseInput/Output, PostToolUseInput/Output types exist
- Verified: deprecated decision field (approve/block) included in PreToolUseOutput
- Verified: PluginConfig export added (fixes hook-disabled.ts import)
### LEARNINGS
- opencode-cc-plugin types.ts: 181 lines, no PluginConfig
- oh-my-opencode requires PluginConfig for hook disabling functionality
- Stub-to-full replacement pattern works: stub allows Task 0 typecheck, Task 1 replaces with full implementation
- Must preserve project-specific types (PluginConfig) when porting from different codebases
소요 시간: ~2분
---
## [2025-12-09 17:39] - Task 3: tool-input-cache.ts 포팅
### DISCOVERED ISSUES
- None - straightforward file copy task
### IMPLEMENTATION DECISIONS
- Copied tool-input-cache.ts (48 lines) from opencode-cc-plugin → oh-my-opencode
- Preserved cache structure:
* Key format: `${sessionId}:${toolName}:${invocationId}`
* TTL: 60000ms (1 minute) as CACHE_TTL constant
* Periodic cleanup: setInterval every CACHE_TTL (60000ms)
- Preserved original comments from source file (lines 12, 39)
- Functions: cacheToolInput(), getToolInput()
- Cache behavior: getToolInput() deletes entry immediately after retrieval (single-use cache)
### PROBLEMS FOR NEXT TASKS
- Task 4 (pre-tool-use.ts) will call cacheToolInput() to store tool inputs
- Task 5 (post-tool-use.ts) will call getToolInput() to retrieve cached inputs for transcript building
- No import path changes needed - this file has no external dependencies
### VERIFICATION RESULTS
- File created: `src/hooks/claude-code-hooks/tool-input-cache.ts` (48 lines)
- Functions exported: cacheToolInput(), getToolInput()
- TTL verified: CACHE_TTL = 60000 (1 minute)
- Cleanup interval verified: setInterval(cleanup, CACHE_TTL)
### LEARNINGS
- Tool input cache is a temporary storage for PreToolUse → PostToolUse communication
- Single-use pattern: getToolInput() deletes entry after first retrieval (line 33)
- TTL check happens after deletion, so expired entries still return null
- setInterval runs in background for periodic cleanup of abandoned entries
- Source location: `~/local-workspaces/opencode-cc-plugin/src/claude-compat/hooks/tool-input-cache.ts`
소요 시간: ~2분
---
## [2025-12-09 17:39] - Task 2: config.ts + transcript.ts + todo.ts 포팅
### DISCOVERED ISSUES
- transcript.ts had unused imports (ClaudeCodeMessage, ClaudeCodeContent) - same as source file
- LSP warned about unused types - removed from import to clean up
### IMPLEMENTATION DECISIONS
- Copied config.ts (101 lines) - no import path changes needed (only uses `./types` and Node.js builtins)
- Copied transcript.ts (256 lines) - changed import path:
* Line 10: `../shared/tool-name``../../shared/tool-name` (opencode-cc-plugin depth 1, oh-my-opencode depth 2)
- Copied todo.ts (78 lines) - no import path changes needed (only uses `./types` and Node.js builtins)
- Removed unused imports from transcript.ts: ClaudeCodeMessage, ClaudeCodeContent (not used in function bodies)
- Preserved ALL original comments from source files - these are pre-existing comments
### PROBLEMS FOR NEXT TASKS
- Task 3 will import cacheToolInput/getToolInput for cache functionality
- Task 4 will import loadClaudeHooksConfig, buildTranscriptFromSession
- Task 5 will import transcript building functions for PostToolUse hook
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Files created: config.ts (101 lines), transcript.ts (256 lines), todo.ts (78 lines)
- Functions available: loadClaudeHooksConfig(), buildTranscriptFromSession(), appendTranscriptEntry(), loadTodoFile(), saveTodoFile()
- Import paths verified: transcript.ts successfully imports transformToolName from ../../shared
### LEARNINGS
- Import path depth difference: opencode-cc-plugin `src/claude-compat/` (1 level up) → oh-my-opencode `src/hooks/claude-code-hooks/` (2 levels up)
- transcript.ts unused imports were present in original source - cleaning them is optional but improves code hygiene
- config.ts uses Bun.file() for async file reading - compatible with oh-my-opencode's Bun runtime
- Bun.file().text() automatically handles encoding
소요 시간: ~3분
---
## [2025-12-09 17:48] - Task 4: pre-tool-use.ts 포팅 (+ plugin-config.ts, config-loader.ts)
### DISCOVERED ISSUES
- pre-tool-use.ts depends on DEFAULT_CONFIG and isHookCommandDisabled which weren't created yet
- Plan document listed plugin-config.ts and config-loader.ts as separate task (Section 4), but not mentioned in Task 4 instructions
- These dependency files needed to be created before pre-tool-use.ts could compile
### IMPLEMENTATION DECISIONS
- Created plugin-config.ts (9 lines) with DEFAULT_CONFIG containing forceZsh and zshPath settings
* Minimal version - only fields used by pre-tool-use.ts (not full opencode-cc-plugin config)
* forceZsh: true, zshPath: "/bin/zsh"
- Created config-loader.ts (105 lines) - full copy from opencode-cc-plugin
* Changed import: `../claude-compat/types``./types`
* Changed import: `../shared/logger``../../shared/logger`
* Functions: loadPluginExtendedConfig(), isHookCommandDisabled()
* Supports regex patterns for disabling specific hook commands
- Created pre-tool-use.ts (172 lines) - full copy with adjusted imports:
* `../types``./types`
* `../../shared``../../shared` (unchanged)
* `../../config``./plugin-config` (NEW file)
* `../../config-loader``./config-loader` (NEW file)
- Preserved ALL exit code logic:
* exitCode === 2 → decision = "deny"
* exitCode === 1 → decision = "ask"
* exitCode === 0 → parse JSON for decision
- Preserved ALL deprecated field support:
* decision: "approve" → "allow"
* decision: "block" → "deny"
- Original comments from source preserved (backward compat, spec references)
### PROBLEMS FOR NEXT TASKS
- Task 5 (post-tool-use.ts) can now import executePreToolUseHooks if needed
- plugin-config.ts and config-loader.ts are now available for all subsequent hook implementations
- isHookCommandDisabled pattern can be reused in PostToolUse, UserPromptSubmit, Stop hooks
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Ran: `bun run build` → exit 0, successful
- Committed: 530c4d6 "feat(hooks): add PreToolUse hook executor"
* 4 files: tool-input-cache.ts (Task 3), plugin-config.ts, config-loader.ts, pre-tool-use.ts (Task 4)
* 333 insertions total
- Functions available: executePreToolUseHooks(), isHookCommandDisabled(), loadPluginExtendedConfig()
- Exit code mapping verified: lines 96-116 check exitCode === 2/1/0
- Deprecated field mapping verified: lines 132-141 check decision === "approve"/"block"
### LEARNINGS
- Pre-tool-use.ts depends on plugin configuration that wasn't part of oh-my-opencode's original structure
- plugin-config.ts only needs subset of opencode-cc-plugin's config.ts (forceZsh, zshPath for executeHookCommand)
- config-loader.ts provides hook command filtering via regex patterns (disabledHooks config)
- executeHookCommand from shared/ accepts ExecuteHookOptions{ forceZsh, zshPath } parameter
- Task 3 + Task 4 grouped in single commit per plan requirement
- Source: `/Users/yeongyu/local-workspaces/opencode-cc-plugin/src/claude-compat/hooks/pre-tool-use.ts` (173 lines)
소요 시간: ~5분
---
## [2025-12-09 17:52] - Task 5: post-tool-use.ts 포팅
### DISCOVERED ISSUES
- None - straightforward file copy with import path adjustments
### IMPLEMENTATION DECISIONS
- Copied post-tool-use.ts (200 lines) from opencode-cc-plugin → oh-my-opencode
- Import path adjustments:
* `../types``./types`
* `../../shared``../../shared` (unchanged)
* `../../config``./plugin-config`
* `../transcript``./transcript`
* `../../config-loader``./config-loader`
- Preserved ALL transcript logic:
* buildTranscriptFromSession() call with client.session.messages() API
* Temp file creation in try block
* deleteTempTranscript() cleanup in finally block
- Preserved ALL exit code handling:
* exitCode === 2 → warning (continue)
* exitCode === 0 → parse JSON for decision: "block"
* Non-zero, non-2 → parse JSON for decision: "block"
- Preserved ALL output fields: block, reason, message, warnings, elapsedMs, additionalContext, continue, stopReason, suppressOutput, systemMessage
- Original comments from source preserved (PORT FROM DISABLED, cleanup explanation)
### PROBLEMS FOR NEXT TASKS
- Task 6 (user-prompt-submit.ts, stop.ts) can use similar pattern for hook execution
- plugin-config.ts, config-loader.ts, transcript.ts dependencies already in place
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Ran: `bun run build` → exit 0, successful
- File created: `src/hooks/claude-code-hooks/post-tool-use.ts` (200 lines)
- Functions available: executePostToolUseHooks()
- Transcript integration verified: buildTranscriptFromSession() imported from ./transcript
- Cleanup mechanism verified: deleteTempTranscript() in finally block (line 196)
### LEARNINGS
- PostToolUse differs from PreToolUse: no permission decision (allow/deny/ask), only block/continue
- PostToolUse provides hook results via message/warnings/additionalContext (observability, not control)
- Exit code 2 in PostToolUse = warning (not block), collected in warnings array
- Transcript temp file pattern: create in try, cleanup in finally (prevents disk accumulation)
- Source: `/Users/yeongyu/local-workspaces/opencode-cc-plugin/src/claude-compat/hooks/post-tool-use.ts` (200 lines)
소요 시간: ~5분
---
## [2025-12-09 17:58] - Task 6: user-prompt-submit.ts + stop.ts 포팅
### DISCOVERED ISSUES
- None - straightforward file copy with import path adjustments
### IMPLEMENTATION DECISIONS
- Copied user-prompt-submit.ts (118 lines) from opencode-cc-plugin → oh-my-opencode
- Copied stop.ts (119 lines) from opencode-cc-plugin → oh-my-opencode
- Import path adjustments (both files):
* `../types``./types`
* `../../shared``../../shared` (unchanged)
* `../../config``./plugin-config`
* `../../config-loader``./config-loader`
* `../todo``./todo` (stop.ts only)
- Preserved recursion prevention logic in user-prompt-submit.ts:
* Tags: `<user-prompt-submit-hook>` (open/close)
* Check if prompt already contains tags → return early
* Wrap hook stdout with tags to prevent infinite recursion
- Preserved inject_prompt support:
* user-prompt-submit: messages array collection for injection
* stop: injectPrompt field in result (from output.inject_prompt or output.reason)
- Preserved stopHookActiveState management in stop.ts:
* Module-level Map<string, boolean> for per-session state
* setStopHookActive(), getStopHookActive() exported
* State persists across hook invocations
- Preserved exit code handling:
* stop.ts: exitCode === 2 → block with reason
* user-prompt-submit.ts: exitCode !== 0 → check JSON for decision: "block"
### PROBLEMS FOR NEXT TASKS
- Task 7 (hook-message-injector) will use the message injection pattern
- Task 8 (Factory + Integration) will wire these hooks to OpenCode lifecycle events
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Ran: `bun run build` → exit 0, successful
- Files created:
* `src/hooks/claude-code-hooks/user-prompt-submit.ts` (115 lines)
* `src/hooks/claude-code-hooks/stop.ts` (119 lines)
- Functions available:
* executeUserPromptSubmitHooks() with UserPromptSubmitContext → UserPromptSubmitResult
* executeStopHooks() with StopContext → StopResult
* setStopHookActive(), getStopHookActive()
- Recursion prevention verified: lines 47-52 check for tag presence
- inject_prompt field verified: stop.ts line 102 sets injectPrompt from output
### LEARNINGS
- user-prompt-submit uses tag wrapping pattern to prevent infinite hook loops
- stop hook can inject prompts into session via injectPrompt result field
- stopHookActiveState Map persists across hook invocations (module-level state)
- getTodoPath() from ./todo provides todo file path for Stop hook context
- Source files:
* `/Users/yeongyu/local-workspaces/opencode-cc-plugin/src/claude-compat/hooks/user-prompt-submit.ts` (118 lines)
* `/Users/yeongyu/local-workspaces/opencode-cc-plugin/src/claude-compat/hooks/stop.ts` (119 lines)
소요 시간: ~3분
---
## [2025-12-09 17:58] - Task 7: hook-message-injector 포팅
### DISCOVERED ISSUES
- None - straightforward file copy task
### IMPLEMENTATION DECISIONS
- Created `src/features/hook-message-injector/` directory
- Copied 4 files from opencode-cc-plugin → oh-my-opencode:
* constants.ts (9 lines): XDG-based path definitions (MESSAGE_STORAGE, PART_STORAGE)
* types.ts (46 lines): MessageMeta, OriginalMessageContext, TextPart interfaces
* injector.ts (142 lines): injectHookMessage() implementation with message/part storage
* index.ts (3 lines): Barrel export
- No import path changes needed - module is self-contained
- Preserved XDG_DATA_HOME environment variable support
- Preserved message fallback logic: finds nearest message with agent/model/tools if not provided
### PROBLEMS FOR NEXT TASKS
- Task 8 (Factory + Integration) will import injectHookMessage from this module
- Hook executors (user-prompt-submit, stop) can use injectHookMessage to store hook messages
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Files created: src/features/hook-message-injector/ (4 files)
- Functions exported: injectHookMessage()
- Types exported: MessageMeta, OriginalMessageContext, TextPart
- Constants exported: MESSAGE_STORAGE, PART_STORAGE (XDG-based paths)
### LEARNINGS
- Message injector uses XDG_DATA_HOME for storage (~/.local/share/opencode/storage/)
- Message storage structure: sessionID → messageID.json (meta) + partID.json (content)
- Fallback logic: searches recent messages for agent/model/tools if originalMessage is incomplete
- Part-based storage allows incremental message building
- Source: `/Users/yeongyu/local-workspaces/opencode-cc-plugin/src/features/hook-message-injector/`
소요 시간: ~2분
---
## [2025-12-09 18:08] - Task 8: Factory 생성 + 통합
### DISCOVERED ISSUES
- None - final integration task with well-defined hook executors from previous tasks
### IMPLEMENTATION DECISIONS
- Created `src/hooks/claude-code-hooks/index.ts` (146 lines) with createClaudeCodeHooksHook() factory
- Factory returns hook handler object with 3 handlers:
* `tool.execute.before`: Executes executePreToolUseHooks()
- Loads config dynamically (async) on each invocation
- Maps OpenCode input → PreToolUseContext
- Caches tool input for PostToolUse
- Handles deny/ask decisions (deny throws error, ask logs warning)
* `tool.execute.after`: Executes executePostToolUseHooks()
- Retrieves cached tool input via getToolInput()
- Maps OpenCode input → PostToolUseContext with client wrapper
- Appends hook message to output if provided
- Throws error if block decision returned
* `event`: Executes executeStopHooks() for session.idle
- Filters event.type === "session.idle"
- Maps OpenCode event → StopContext
- Injects prompt via ctx.client.session.prompt() if injectPrompt returned
- Updated `src/hooks/index.ts`: Added createClaudeCodeHooksHook export
- Updated `src/index.ts`:
* Imported createClaudeCodeHooksHook
* Created claudeCodeHooks instance
* Registered handlers in tool.execute.before, tool.execute.after, event hooks
* Claude hooks run FIRST in execution order (before other hooks)
- Config loading: Async loadClaudeHooksConfig() and loadPluginExtendedConfig() called in each handler (not cached)
- Transcript path: Uses getTranscriptPath() function (not buildTranscriptPath which doesn't exist)
### PROBLEMS FOR NEXT TASKS
- None - this is the final task (Task 8)
- All Claude Code Hooks now integrated into oh-my-opencode plugin system
### VERIFICATION RESULTS
- Ran: `bun run typecheck` → exit 0, no errors
- Ran: `bun run build` → exit 0, successful build
- Files modified:
* src/hooks/claude-code-hooks/index.ts (created)
* src/hooks/index.ts (export added)
* src/index.ts (hook registration)
- Hook handler registration verified: claudeCodeHooks handlers called in all 3 hook points
- Execution order verified: Claude hooks run before existing hooks in tool.execute.*
### LEARNINGS
- OpenCode Plugin API: Factory pattern createXxxHook(ctx: PluginInput) → handlers object
- OpenCode does NOT have chat.params hook → UserPromptSubmit not implemented in factory
- Config loading must be async → call loadClaudeHooksConfig() in each handler, not once during initialization
- Tool input cache is module-level state → cacheToolInput/getToolInput work across handlers
- Stop hook only triggers on session.idle event → filter event.type
- Import path: getTranscriptPath (exists), not buildTranscriptPath (doesn't exist)
소요 시간: ~6분
---
## [2025-12-09 18:16] - hook-message-injector 사용 패턴 크로스체크
### DISCOVERED ISSUES
- **CRITICAL**: UserPromptSubmit hooks가 oh-my-opencode에 완전히 누락됨
- opencode-cc-plugin에서는 chat.message hook으로 UserPromptSubmit 처리
- oh-my-opencode에는 chat.message hook이 구현되지 않음
- user-prompt-submit.ts는 정의만 있고 실제 사용처 없음
### IMPLEMENTATION DECISIONS
- PostToolUse는 이미 올바르게 구현됨:
* opencode-cc-plugin: result.message를 tool output에 append
* oh-my-opencode: 동일한 방식 사용 (claude-code-hooks/index.ts:95-97)
* injectHookMessage() 불필요
- UserPromptSubmit 구현 추가:
* chat.message hook handler 추가 (claude-code-hooks/index.ts)
* executeUserPromptSubmitHooks() 호출
* sessionFirstMessageProcessed Set으로 첫 메시지 skip (title generation)
* result.messages가 있으면 injectHookMessage() 호출
* src/index.ts에 hook 등록
- Import 추가:
* executeUserPromptSubmitHooks, UserPromptSubmitContext, MessagePart from ./user-prompt-submit
* injectHookMessage from ../../features/hook-message-injector
### PROBLEMS FOR NEXT TASKS
- None - UserPromptSubmit 통합 완료
### VERIFICATION RESULTS
- Ran: `bunx tsc --noEmit` → exit 0, no errors
- Ran: `bun run build` → exit 0, successful build
- Files modified:
* src/hooks/claude-code-hooks/index.ts (chat.message handler 추가)
* src/index.ts (chat.message hook 등록)
- Verified OpenCode Plugin API: chat.message hook 공식 지원 확인 (@opencode-ai/plugin/dist/index.d.ts:112-123)
### LEARNINGS
- OpenCode Plugin API에 chat.message hook 존재:
* input: sessionID, agent?, model?, messageID?
* output: message, parts[]
- PostToolUse는 tool output에 직접 append (injectHookMessage 불필요)
- UserPromptSubmit는 file system injection 사용 (injectHookMessage 필수)
- opencode-cc-plugin 구조: src/plugin/chat-handler.ts → handleChatMessage()
- oh-my-opencode 구조: src/hooks/claude-code-hooks/index.ts → createClaudeCodeHooksHook()
- 첫 메시지 skip 로직: title generation을 위해 UserPromptSubmit hooks 실행 안 함
소요 시간: ~8분
---

View File

@@ -1,6 +1,6 @@
{
"name": "oh-my-opencode",
"version": "0.1.2",
"version": "0.3.0",
"description": "OpenCode plugin - custom agents (oracle, librarian) and enhanced features",
"main": "dist/index.js",
"types": "dist/index.d.ts",
@@ -44,19 +44,22 @@
"dependencies": {
"@ast-grep/cli": "^0.40.0",
"@ast-grep/napi": "^0.40.0",
"@code-yeongyu/comment-checker": "^0.5.0",
"@opencode-ai/plugin": "^1.0.7",
"tree-sitter-wasms": "^0.1.12",
"web-tree-sitter": "^0.24.7",
"xdg-basedir": "^5.1.0",
"zod": "^4.1.8"
},
"devDependencies": {
"bun-types": "latest",
"oh-my-opencode": "^0.1.30",
"typescript": "^5.7.3"
},
"peerDependencies": {
"bun": ">=1.0.0"
},
"trustedDependencies": [
"@ast-grep/cli"
"@ast-grep/cli",
"@ast-grep/napi",
"@code-yeongyu/comment-checker"
]
}

View File

@@ -2,7 +2,7 @@
import * as z from "zod"
import { OhMyOpenCodeConfigSchema } from "../src/config/schema"
const SCHEMA_OUTPUT_PATH = "dist/oh-my-opencode.schema.json"
const SCHEMA_OUTPUT_PATH = "assets/oh-my-opencode.schema.json"
async function main() {
console.log("Generating JSON Schema...")
@@ -14,7 +14,7 @@ async function main() {
const finalSchema = {
$schema: "http://json-schema.org/draft-07/schema#",
$id: "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/dist/oh-my-opencode.schema.json",
$id: "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
title: "Oh My OpenCode Configuration",
description: "Configuration schema for oh-my-opencode plugin",
...jsonSchema,

View File

@@ -63,10 +63,11 @@ async function generateChangelog(previous: string): Promise<string> {
async function buildAndPublish(): Promise<void> {
console.log("\nPublishing to npm...")
// --ignore-scripts: workflow에서 이미 빌드 완료, prepublishOnly 재실행 방지
if (process.env.CI) {
await $`npm publish --access public --provenance`
await $`npm publish --access public --provenance --ignore-scripts`
} else {
await $`npm publish --access public`
await $`npm publish --access public --ignore-scripts`
}
}
@@ -77,13 +78,44 @@ async function gitTagAndRelease(newVersion: string, changelog: string): Promise<
await $`git config user.email "github-actions[bot]@users.noreply.github.com"`
await $`git config user.name "github-actions[bot]"`
await $`git add package.json`
await $`git commit -m "release: v${newVersion}"`
await $`git tag v${newVersion}`
// Commit only if there are staged changes (idempotent)
const hasStagedChanges = await $`git diff --cached --quiet`.nothrow()
if (hasStagedChanges.exitCode !== 0) {
await $`git commit -m "release: v${newVersion}"`
} else {
console.log("No changes to commit (version already updated)")
}
// Tag only if it doesn't exist (idempotent)
const tagExists = await $`git rev-parse v${newVersion}`.nothrow()
if (tagExists.exitCode !== 0) {
await $`git tag v${newVersion}`
} else {
console.log(`Tag v${newVersion} already exists`)
}
// Push (idempotent - git push is already idempotent)
await $`git push origin HEAD --tags`
// Create release only if it doesn't exist (idempotent)
console.log("\nCreating GitHub release...")
const releaseNotes = changelog || "No notable changes"
await $`gh release create v${newVersion} --title "v${newVersion}" --notes ${releaseNotes}`
const releaseExists = await $`gh release view v${newVersion}`.nothrow()
if (releaseExists.exitCode !== 0) {
await $`gh release create v${newVersion} --title "v${newVersion}" --notes ${releaseNotes}`
} else {
console.log(`Release v${newVersion} already exists`)
}
}
async function checkVersionExists(version: string): Promise<boolean> {
try {
const res = await fetch(`https://registry.npmjs.org/${PACKAGE_NAME}/${version}`)
return res.ok
} catch {
return false
}
}
async function main() {
@@ -91,6 +123,11 @@ async function main() {
const newVersion = versionOverride || (bump ? bumpVersion(previous, bump) : bumpVersion(previous, "patch"))
console.log(`New version: ${newVersion}\n`)
if (await checkVersionExists(newVersion)) {
console.log(`Version ${newVersion} already exists on npm. Skipping publish.`)
process.exit(0)
}
await updatePackageVersion(newVersion)
const changelog = await generateChangelog(previous)
await buildAndPublish()

View File

@@ -1,4 +1,5 @@
import { z } from "zod"
import { McpNameSchema } from "../mcp/types"
const PermissionValue = z.enum(["ask", "allow", "deny"])
@@ -23,8 +24,6 @@ export const AgentNameSchema = z.enum([
"document-writer",
])
export const McpNameSchema = z.enum(["websearch_exa", "context7"])
export const AgentOverrideConfigSchema = z.object({
model: z.string().optional(),
temperature: z.number().min(0).max(2).optional(),
@@ -53,5 +52,6 @@ export const OhMyOpenCodeConfigSchema = z.object({
export type OhMyOpenCodeConfig = z.infer<typeof OhMyOpenCodeConfigSchema>
export type AgentOverrideConfig = z.infer<typeof AgentOverrideConfigSchema>
export type AgentOverrides = z.infer<typeof AgentOverridesSchema>
export type McpName = z.infer<typeof McpNameSchema>
export type AgentName = z.infer<typeof AgentNameSchema>
export { McpNameSchema, type McpName } from "../mcp/types"

View File

@@ -0,0 +1,2 @@
export * from "./types"
export * from "./loader"

View File

@@ -0,0 +1,93 @@
import { existsSync, readdirSync, readFileSync } from "fs"
import { homedir } from "os"
import { join, basename } from "path"
import type { AgentConfig } from "@opencode-ai/sdk"
import { parseFrontmatter } from "../../shared/frontmatter"
import type { AgentScope, AgentFrontmatter, LoadedAgent } from "./types"
function parseToolsConfig(toolsStr?: string): Record<string, boolean> | undefined {
if (!toolsStr) return undefined
const tools = toolsStr.split(",").map((t) => t.trim()).filter(Boolean)
if (tools.length === 0) return undefined
const result: Record<string, boolean> = {}
for (const tool of tools) {
result[tool.toLowerCase()] = true
}
return result
}
function isMarkdownFile(entry: { name: string; isFile: () => boolean }): boolean {
return !entry.name.startsWith(".") && entry.name.endsWith(".md") && entry.isFile()
}
function loadAgentsFromDir(agentsDir: string, scope: AgentScope): LoadedAgent[] {
if (!existsSync(agentsDir)) {
return []
}
const entries = readdirSync(agentsDir, { withFileTypes: true })
const agents: LoadedAgent[] = []
for (const entry of entries) {
if (!isMarkdownFile(entry)) continue
const agentPath = join(agentsDir, entry.name)
const agentName = basename(entry.name, ".md")
try {
const content = readFileSync(agentPath, "utf-8")
const { data, body } = parseFrontmatter<AgentFrontmatter>(content)
const name = data.name || agentName
const originalDescription = data.description || ""
const formattedDescription = `(${scope}) ${originalDescription}`
const config: AgentConfig = {
description: formattedDescription,
mode: "subagent",
prompt: body.trim(),
}
const toolsConfig = parseToolsConfig(data.tools)
if (toolsConfig) {
config.tools = toolsConfig
}
agents.push({
name,
path: agentPath,
config,
scope,
})
} catch {
continue
}
}
return agents
}
export function loadUserAgents(): Record<string, AgentConfig> {
const userAgentsDir = join(homedir(), ".claude", "agents")
const agents = loadAgentsFromDir(userAgentsDir, "user")
const result: Record<string, AgentConfig> = {}
for (const agent of agents) {
result[agent.name] = agent.config
}
return result
}
export function loadProjectAgents(): Record<string, AgentConfig> {
const projectAgentsDir = join(process.cwd(), ".claude", "agents")
const agents = loadAgentsFromDir(projectAgentsDir, "project")
const result: Record<string, AgentConfig> = {}
for (const agent of agents) {
result[agent.name] = agent.config
}
return result
}

View File

@@ -0,0 +1,17 @@
import type { AgentConfig } from "@opencode-ai/sdk"
export type AgentScope = "user" | "project"
export interface AgentFrontmatter {
name?: string
description?: string
model?: string
tools?: string
}
export interface LoadedAgent {
name: string
path: string
config: AgentConfig
scope: AgentScope
}

View File

@@ -0,0 +1,2 @@
export * from "./types"
export * from "./loader"

View File

@@ -0,0 +1,94 @@
import { existsSync, readdirSync, readFileSync } from "fs"
import { homedir } from "os"
import { join, basename } from "path"
import { parseFrontmatter } from "../../shared/frontmatter"
import { sanitizeModelField } from "../../shared/model-sanitizer"
import type { CommandScope, CommandDefinition, CommandFrontmatter, LoadedCommand } from "./types"
function isMarkdownFile(entry: { name: string; isFile: () => boolean }): boolean {
return !entry.name.startsWith(".") && entry.name.endsWith(".md") && entry.isFile()
}
function loadCommandsFromDir(commandsDir: string, scope: CommandScope): LoadedCommand[] {
if (!existsSync(commandsDir)) {
return []
}
const entries = readdirSync(commandsDir, { withFileTypes: true })
const commands: LoadedCommand[] = []
for (const entry of entries) {
if (!isMarkdownFile(entry)) continue
const commandPath = join(commandsDir, entry.name)
const commandName = basename(entry.name, ".md")
try {
const content = readFileSync(commandPath, "utf-8")
const { data, body } = parseFrontmatter<CommandFrontmatter>(content)
const wrappedTemplate = `<command-instruction>
${body.trim()}
</command-instruction>
<user-request>
$ARGUMENTS
</user-request>`
const formattedDescription = `(${scope}) ${data.description || ""}`
const definition: CommandDefinition = {
name: commandName,
description: formattedDescription,
template: wrappedTemplate,
agent: data.agent,
model: sanitizeModelField(data.model),
subtask: data.subtask,
argumentHint: data["argument-hint"],
}
commands.push({
name: commandName,
path: commandPath,
definition,
scope,
})
} catch {
continue
}
}
return commands
}
function commandsToRecord(commands: LoadedCommand[]): Record<string, CommandDefinition> {
const result: Record<string, CommandDefinition> = {}
for (const cmd of commands) {
result[cmd.name] = cmd.definition
}
return result
}
export function loadUserCommands(): Record<string, CommandDefinition> {
const userCommandsDir = join(homedir(), ".claude", "commands")
const commands = loadCommandsFromDir(userCommandsDir, "user")
return commandsToRecord(commands)
}
export function loadProjectCommands(): Record<string, CommandDefinition> {
const projectCommandsDir = join(process.cwd(), ".claude", "commands")
const commands = loadCommandsFromDir(projectCommandsDir, "project")
return commandsToRecord(commands)
}
export function loadOpencodeGlobalCommands(): Record<string, CommandDefinition> {
const opencodeCommandsDir = join(homedir(), ".config", "opencode", "command")
const commands = loadCommandsFromDir(opencodeCommandsDir, "opencode")
return commandsToRecord(commands)
}
export function loadOpencodeProjectCommands(): Record<string, CommandDefinition> {
const opencodeProjectDir = join(process.cwd(), ".opencode", "command")
const commands = loadCommandsFromDir(opencodeProjectDir, "opencode-project")
return commandsToRecord(commands)
}

View File

@@ -0,0 +1,26 @@
export type CommandScope = "user" | "project" | "opencode" | "opencode-project"
export interface CommandDefinition {
name: string
description?: string
template: string
agent?: string
model?: string
subtask?: boolean
argumentHint?: string
}
export interface CommandFrontmatter {
description?: string
"argument-hint"?: string
agent?: string
model?: string
subtask?: boolean
}
export interface LoadedCommand {
name: string
path: string
definition: CommandDefinition
scope: CommandScope
}

View File

@@ -0,0 +1,27 @@
export function expandEnvVars(value: string): string {
return value.replace(
/\$\{([^}:]+)(?::-([^}]*))?\}/g,
(_, varName: string, defaultValue?: string) => {
const envValue = process.env[varName]
if (envValue !== undefined) return envValue
if (defaultValue !== undefined) return defaultValue
return ""
}
)
}
export function expandEnvVarsInObject<T>(obj: T): T {
if (obj === null || obj === undefined) return obj
if (typeof obj === "string") return expandEnvVars(obj) as T
if (Array.isArray(obj)) {
return obj.map((item) => expandEnvVarsInObject(item)) as T
}
if (typeof obj === "object") {
const result: Record<string, unknown> = {}
for (const [key, value] of Object.entries(obj)) {
result[key] = expandEnvVarsInObject(value)
}
return result as T
}
return obj
}

View File

@@ -0,0 +1,11 @@
/**
* MCP Configuration Loader
*
* Loads Claude Code .mcp.json format configurations from multiple scopes
* and transforms them to OpenCode SDK format
*/
export * from "./types"
export * from "./loader"
export * from "./transformer"
export * from "./env-expander"

View File

@@ -0,0 +1,89 @@
import { existsSync } from "fs"
import { homedir } from "os"
import { join } from "path"
import type {
ClaudeCodeMcpConfig,
LoadedMcpServer,
McpLoadResult,
McpScope,
} from "./types"
import { transformMcpServer } from "./transformer"
import { log } from "../../shared/logger"
interface McpConfigPath {
path: string
scope: McpScope
}
function getMcpConfigPaths(): McpConfigPath[] {
const home = homedir()
const cwd = process.cwd()
return [
{ path: join(home, ".claude", ".mcp.json"), scope: "user" },
{ path: join(cwd, ".mcp.json"), scope: "project" },
{ path: join(cwd, ".claude", ".mcp.json"), scope: "local" },
]
}
async function loadMcpConfigFile(
filePath: string
): Promise<ClaudeCodeMcpConfig | null> {
if (!existsSync(filePath)) {
return null
}
try {
const content = await Bun.file(filePath).text()
return JSON.parse(content) as ClaudeCodeMcpConfig
} catch (error) {
log(`Failed to load MCP config from ${filePath}`, error)
return null
}
}
export async function loadMcpConfigs(): Promise<McpLoadResult> {
const servers: McpLoadResult["servers"] = {}
const loadedServers: LoadedMcpServer[] = []
const paths = getMcpConfigPaths()
for (const { path, scope } of paths) {
const config = await loadMcpConfigFile(path)
if (!config?.mcpServers) continue
for (const [name, serverConfig] of Object.entries(config.mcpServers)) {
if (serverConfig.disabled) {
log(`Skipping disabled MCP server "${name}"`, { path })
continue
}
try {
const transformed = transformMcpServer(name, serverConfig)
servers[name] = transformed
const existingIndex = loadedServers.findIndex((s) => s.name === name)
if (existingIndex !== -1) {
loadedServers.splice(existingIndex, 1)
}
loadedServers.push({ name, scope, config: transformed })
log(`Loaded MCP server "${name}" from ${scope}`, { path })
} catch (error) {
log(`Failed to transform MCP server "${name}"`, error)
}
}
}
return { servers, loadedServers }
}
export function formatLoadedServersForToast(
loadedServers: LoadedMcpServer[]
): string {
if (loadedServers.length === 0) return ""
return loadedServers
.map((server) => `${server.name} (${server.scope})`)
.join(", ")
}

View File

@@ -0,0 +1,53 @@
import type {
ClaudeCodeMcpServer,
McpLocalConfig,
McpRemoteConfig,
McpServerConfig,
} from "./types"
import { expandEnvVarsInObject } from "./env-expander"
export function transformMcpServer(
name: string,
server: ClaudeCodeMcpServer
): McpServerConfig {
const expanded = expandEnvVarsInObject(server)
const serverType = expanded.type ?? "stdio"
if (serverType === "http" || serverType === "sse") {
if (!expanded.url) {
throw new Error(
`MCP server "${name}" requires url for type "${serverType}"`
)
}
const config: McpRemoteConfig = {
type: "remote",
url: expanded.url,
enabled: true,
}
if (expanded.headers && Object.keys(expanded.headers).length > 0) {
config.headers = expanded.headers
}
return config
}
if (!expanded.command) {
throw new Error(`MCP server "${name}" requires command for stdio type`)
}
const commandArray = [expanded.command, ...(expanded.args ?? [])]
const config: McpLocalConfig = {
type: "local",
command: commandArray,
enabled: true,
}
if (expanded.env && Object.keys(expanded.env).length > 0) {
config.environment = expanded.env
}
return config
}

View File

@@ -0,0 +1,42 @@
export type McpScope = "user" | "project" | "local"
export interface ClaudeCodeMcpServer {
type?: "http" | "sse" | "stdio"
url?: string
command?: string
args?: string[]
env?: Record<string, string>
headers?: Record<string, string>
disabled?: boolean
}
export interface ClaudeCodeMcpConfig {
mcpServers?: Record<string, ClaudeCodeMcpServer>
}
export interface McpLocalConfig {
type: "local"
command: string[]
environment?: Record<string, string>
enabled?: boolean
}
export interface McpRemoteConfig {
type: "remote"
url: string
headers?: Record<string, string>
enabled?: boolean
}
export type McpServerConfig = McpLocalConfig | McpRemoteConfig
export interface LoadedMcpServer {
name: string
scope: McpScope
config: McpServerConfig
}
export interface McpLoadResult {
servers: Record<string, McpServerConfig>
loadedServers: LoadedMcpServer[]
}

View File

@@ -0,0 +1,21 @@
export function detectInterrupt(error: unknown): boolean {
if (!error) return false
if (typeof error === "object") {
const errObj = error as Record<string, unknown>
const name = errObj.name as string | undefined
const message = errObj.message as string | undefined
if (name === "MessageAbortedError" || name === "AbortError") return true
if (name === "DOMException" && message?.includes("abort")) return true
const msgLower = message?.toLowerCase()
if (msgLower?.includes("aborted") || msgLower?.includes("cancelled") || msgLower?.includes("interrupted")) return true
}
if (typeof error === "string") {
const lower = error.toLowerCase()
return lower.includes("abort") || lower.includes("cancel") || lower.includes("interrupt")
}
return false
}

View File

@@ -0,0 +1,3 @@
export * from "./types"
export * from "./state"
export * from "./detector"

View File

@@ -0,0 +1,31 @@
import type { SessionErrorState, SessionInterruptState } from "./types"
export const sessionErrorState = new Map<string, SessionErrorState>()
export const sessionInterruptState = new Map<string, SessionInterruptState>()
export const subagentSessions = new Set<string>()
export const sessionFirstMessageProcessed = new Set<string>()
export let currentSessionID: string | undefined
export let currentSessionTitle: string | undefined
export let mainSessionID: string | undefined
export function setCurrentSession(id: string | undefined, title: string | undefined) {
currentSessionID = id
currentSessionTitle = title
}
export function setMainSession(id: string | undefined) {
mainSessionID = id
}
export function getCurrentSessionID(): string | undefined {
return currentSessionID
}
export function getCurrentSessionTitle(): string | undefined {
return currentSessionTitle
}
export function getMainSessionID(): string | undefined {
return mainSessionID
}

View File

@@ -0,0 +1,8 @@
export interface SessionErrorState {
hasError: boolean
errorMessage?: string
}
export interface SessionInterruptState {
interrupted: boolean
}

View File

@@ -0,0 +1,2 @@
export * from "./types"
export * from "./loader"

View File

@@ -0,0 +1,85 @@
import { existsSync, readdirSync, readFileSync, statSync, readlinkSync } from "fs"
import { homedir } from "os"
import { join, resolve } from "path"
import { parseFrontmatter } from "../../shared/frontmatter"
import { sanitizeModelField } from "../../shared/model-sanitizer"
import type { CommandDefinition } from "../claude-code-command-loader/types"
import type { SkillScope, SkillMetadata, LoadedSkillAsCommand } from "./types"
function loadSkillsFromDir(skillsDir: string, scope: SkillScope): LoadedSkillAsCommand[] {
if (!existsSync(skillsDir)) {
return []
}
const entries = readdirSync(skillsDir, { withFileTypes: true })
const skills: LoadedSkillAsCommand[] = []
for (const entry of entries) {
if (entry.name.startsWith(".")) continue
const skillPath = join(skillsDir, entry.name)
if (!entry.isDirectory() && !entry.isSymbolicLink()) continue
let resolvedPath = skillPath
if (statSync(skillPath, { throwIfNoEntry: false })?.isSymbolicLink()) {
resolvedPath = resolve(skillPath, "..", readlinkSync(skillPath))
}
const skillMdPath = join(resolvedPath, "SKILL.md")
if (!existsSync(skillMdPath)) continue
try {
const content = readFileSync(skillMdPath, "utf-8")
const { data, body } = parseFrontmatter<SkillMetadata>(content)
const skillName = data.name || entry.name
const originalDescription = data.description || ""
const formattedDescription = `(${scope} - Skill) ${originalDescription}`
const wrappedTemplate = `<skill-instruction>
${body.trim()}
</skill-instruction>
<user-request>
$ARGUMENTS
</user-request>`
const definition: CommandDefinition = {
name: skillName,
description: formattedDescription,
template: wrappedTemplate,
model: sanitizeModelField(data.model),
}
skills.push({
name: skillName,
path: resolvedPath,
definition,
scope,
})
} catch {
continue
}
}
return skills
}
export function loadUserSkillsAsCommands(): Record<string, CommandDefinition> {
const userSkillsDir = join(homedir(), ".claude", "skills")
const skills = loadSkillsFromDir(userSkillsDir, "user")
return skills.reduce((acc, skill) => {
acc[skill.name] = skill.definition
return acc
}, {} as Record<string, CommandDefinition>)
}
export function loadProjectSkillsAsCommands(): Record<string, CommandDefinition> {
const projectSkillsDir = join(process.cwd(), ".claude", "skills")
const skills = loadSkillsFromDir(projectSkillsDir, "project")
return skills.reduce((acc, skill) => {
acc[skill.name] = skill.definition
return acc
}, {} as Record<string, CommandDefinition>)
}

View File

@@ -0,0 +1,16 @@
import type { CommandDefinition } from "../claude-code-command-loader/types"
export type SkillScope = "user" | "project"
export interface SkillMetadata {
name: string
description: string
model?: string
}
export interface LoadedSkillAsCommand {
name: string
path: string
definition: CommandDefinition
scope: SkillScope
}

View File

@@ -0,0 +1,8 @@
import { join } from "node:path"
import { homedir } from "node:os"
const xdgData = process.env.XDG_DATA_HOME || join(homedir(), ".local", "share")
export const OPENCODE_STORAGE = join(xdgData, "opencode", "storage")
export const MESSAGE_STORAGE = join(OPENCODE_STORAGE, "message")
export const PART_STORAGE = join(OPENCODE_STORAGE, "part")

View File

@@ -0,0 +1,2 @@
export { injectHookMessage } from "./injector"
export type { MessageMeta, OriginalMessageContext, TextPart } from "./types"

View File

@@ -0,0 +1,141 @@
import { existsSync, mkdirSync, readFileSync, readdirSync, writeFileSync } from "node:fs"
import { join } from "node:path"
import { MESSAGE_STORAGE, PART_STORAGE } from "./constants"
import type { MessageMeta, OriginalMessageContext, TextPart } from "./types"
interface StoredMessage {
agent?: string
model?: { providerID?: string; modelID?: string }
tools?: Record<string, boolean>
}
function findNearestMessageWithFields(messageDir: string): StoredMessage | null {
try {
const files = readdirSync(messageDir)
.filter((f) => f.endsWith(".json"))
.sort()
.reverse()
for (const file of files) {
try {
const content = readFileSync(join(messageDir, file), "utf-8")
const msg = JSON.parse(content) as StoredMessage
if (msg.agent && msg.model?.providerID && msg.model?.modelID) {
return msg
}
} catch {
continue
}
}
} catch {
return null
}
return null
}
function generateMessageId(): string {
const timestamp = Date.now().toString(16)
const random = Math.random().toString(36).substring(2, 14)
return `msg_${timestamp}${random}`
}
function generatePartId(): string {
const timestamp = Date.now().toString(16)
const random = Math.random().toString(36).substring(2, 10)
return `prt_${timestamp}${random}`
}
function getOrCreateMessageDir(sessionID: string): string {
if (!existsSync(MESSAGE_STORAGE)) {
mkdirSync(MESSAGE_STORAGE, { recursive: true })
}
const directPath = join(MESSAGE_STORAGE, sessionID)
if (existsSync(directPath)) {
return directPath
}
for (const dir of readdirSync(MESSAGE_STORAGE)) {
const sessionPath = join(MESSAGE_STORAGE, dir, sessionID)
if (existsSync(sessionPath)) {
return sessionPath
}
}
mkdirSync(directPath, { recursive: true })
return directPath
}
export function injectHookMessage(
sessionID: string,
hookContent: string,
originalMessage: OriginalMessageContext
): boolean {
const messageDir = getOrCreateMessageDir(sessionID)
const needsFallback =
!originalMessage.agent ||
!originalMessage.model?.providerID ||
!originalMessage.model?.modelID
const fallback = needsFallback ? findNearestMessageWithFields(messageDir) : null
const now = Date.now()
const messageID = generateMessageId()
const partID = generatePartId()
const resolvedAgent = originalMessage.agent ?? fallback?.agent ?? "general"
const resolvedModel =
originalMessage.model?.providerID && originalMessage.model?.modelID
? { providerID: originalMessage.model.providerID, modelID: originalMessage.model.modelID }
: fallback?.model?.providerID && fallback?.model?.modelID
? { providerID: fallback.model.providerID, modelID: fallback.model.modelID }
: undefined
const resolvedTools = originalMessage.tools ?? fallback?.tools
const messageMeta: MessageMeta = {
id: messageID,
sessionID,
role: "user",
time: {
created: now,
},
agent: resolvedAgent,
model: resolvedModel,
path:
originalMessage.path?.cwd
? {
cwd: originalMessage.path.cwd,
root: originalMessage.path.root ?? "/",
}
: undefined,
tools: resolvedTools,
}
const textPart: TextPart = {
id: partID,
type: "text",
text: hookContent,
synthetic: true,
time: {
start: now,
end: now,
},
messageID,
sessionID,
}
try {
writeFileSync(join(messageDir, `${messageID}.json`), JSON.stringify(messageMeta, null, 2))
const partDir = join(PART_STORAGE, messageID)
if (!existsSync(partDir)) {
mkdirSync(partDir, { recursive: true })
}
writeFileSync(join(partDir, `${partID}.json`), JSON.stringify(textPart, null, 2))
return true
} catch {
return false
}
}

View File

@@ -0,0 +1,45 @@
export interface MessageMeta {
id: string
sessionID: string
role: "user" | "assistant"
time: {
created: number
completed?: number
}
agent?: string
model?: {
providerID: string
modelID: string
}
path?: {
cwd: string
root: string
}
tools?: Record<string, boolean>
}
export interface OriginalMessageContext {
agent?: string
model?: {
providerID?: string
modelID?: string
}
path?: {
cwd?: string
root?: string
}
tools?: Record<string, boolean>
}
export interface TextPart {
id: string
type: "text"
text: string
synthetic: boolean
time: {
start: number
end: number
}
messageID: string
sessionID: string
}

View File

@@ -0,0 +1,74 @@
import type { AutoCompactState } from "./types"
type Client = {
session: {
messages: (opts: { path: { id: string }; query?: { directory?: string } }) => Promise<unknown>
summarize: (opts: {
path: { id: string }
body: { providerID: string; modelID: string }
query: { directory: string }
}) => Promise<unknown>
}
tui: {
submitPrompt: (opts: { query: { directory: string } }) => Promise<unknown>
}
}
export async function getLastAssistant(
sessionID: string,
// eslint-disable-next-line @typescript-eslint/no-explicit-any
client: any,
directory: string
): Promise<Record<string, unknown> | null> {
try {
const resp = await (client as Client).session.messages({
path: { id: sessionID },
query: { directory },
})
const data = (resp as { data?: unknown[] }).data
if (!Array.isArray(data)) return null
const reversed = [...data].reverse()
const last = reversed.find((m) => {
const msg = m as Record<string, unknown>
const info = msg.info as Record<string, unknown> | undefined
return info?.role === "assistant"
})
if (!last) return null
return (last as { info?: Record<string, unknown> }).info ?? null
} catch {
return null
}
}
export async function executeCompact(
sessionID: string,
msg: Record<string, unknown>,
autoCompactState: AutoCompactState,
// eslint-disable-next-line @typescript-eslint/no-explicit-any
client: any,
directory: string
): Promise<void> {
try {
const providerID = msg.providerID as string | undefined
const modelID = msg.modelID as string | undefined
if (providerID && modelID) {
await (client as Client).session.summarize({
path: { id: sessionID },
body: { providerID, modelID },
query: { directory },
})
setTimeout(async () => {
try {
await (client as Client).tui.submitPrompt({ query: { directory } })
} catch {}
}, 500)
}
autoCompactState.pendingCompact.delete(sessionID)
autoCompactState.errorDataBySession.delete(sessionID)
} catch {}
}

View File

@@ -0,0 +1,123 @@
import type { PluginInput } from "@opencode-ai/plugin"
import type { AutoCompactState, ParsedTokenLimitError } from "./types"
import { parseAnthropicTokenLimitError } from "./parser"
import { executeCompact, getLastAssistant } from "./executor"
function createAutoCompactState(): AutoCompactState {
return {
pendingCompact: new Set<string>(),
errorDataBySession: new Map<string, ParsedTokenLimitError>(),
}
}
export function createAnthropicAutoCompactHook(ctx: PluginInput) {
const autoCompactState = createAutoCompactState()
const eventHandler = async ({ event }: { event: { type: string; properties?: unknown } }) => {
const props = event.properties as Record<string, unknown> | undefined
if (event.type === "session.deleted") {
const sessionInfo = props?.info as { id?: string } | undefined
if (sessionInfo?.id) {
autoCompactState.pendingCompact.delete(sessionInfo.id)
autoCompactState.errorDataBySession.delete(sessionInfo.id)
}
return
}
if (event.type === "session.error") {
const sessionID = props?.sessionID as string | undefined
if (!sessionID) return
const parsed = parseAnthropicTokenLimitError(props?.error)
if (parsed) {
autoCompactState.pendingCompact.add(sessionID)
autoCompactState.errorDataBySession.set(sessionID, parsed)
}
return
}
if (event.type === "message.updated") {
const info = props?.info as Record<string, unknown> | undefined
const sessionID = info?.sessionID as string | undefined
if (sessionID && info?.role === "assistant" && info.error) {
const parsed = parseAnthropicTokenLimitError(info.error)
if (parsed) {
parsed.providerID = info.providerID as string | undefined
parsed.modelID = info.modelID as string | undefined
autoCompactState.pendingCompact.add(sessionID)
autoCompactState.errorDataBySession.set(sessionID, parsed)
}
}
return
}
if (event.type === "session.idle") {
const sessionID = props?.sessionID as string | undefined
if (!sessionID) return
if (!autoCompactState.pendingCompact.has(sessionID)) return
const errorData = autoCompactState.errorDataBySession.get(sessionID)
if (errorData?.providerID && errorData?.modelID) {
await ctx.client.tui
.showToast({
body: {
title: "Auto Compact",
message: "Token limit exceeded. Summarizing session...",
variant: "warning" as const,
duration: 3000,
},
})
.catch(() => {})
await executeCompact(
sessionID,
{ providerID: errorData.providerID, modelID: errorData.modelID },
autoCompactState,
ctx.client,
ctx.directory
)
return
}
const lastAssistant = await getLastAssistant(sessionID, ctx.client, ctx.directory)
if (!lastAssistant) {
autoCompactState.pendingCompact.delete(sessionID)
return
}
if (lastAssistant.summary === true) {
autoCompactState.pendingCompact.delete(sessionID)
return
}
if (!lastAssistant.modelID || !lastAssistant.providerID) {
autoCompactState.pendingCompact.delete(sessionID)
return
}
await ctx.client.tui
.showToast({
body: {
title: "Auto Compact",
message: "Token limit exceeded. Summarizing session...",
variant: "warning" as const,
duration: 3000,
},
})
.catch(() => {})
await executeCompact(sessionID, lastAssistant, autoCompactState, ctx.client, ctx.directory)
}
}
return {
event: eventHandler,
}
}
export type { AutoCompactState, ParsedTokenLimitError } from "./types"
export { parseAnthropicTokenLimitError } from "./parser"
export { executeCompact, getLastAssistant } from "./executor"

View File

@@ -0,0 +1,154 @@
import type { ParsedTokenLimitError } from "./types"
interface AnthropicErrorData {
type: "error"
error: {
type: string
message: string
}
request_id?: string
}
const TOKEN_LIMIT_PATTERNS = [
/(\d+)\s*tokens?\s*>\s*(\d+)\s*maximum/i,
/prompt.*?(\d+).*?tokens.*?exceeds.*?(\d+)/i,
/(\d+).*?tokens.*?limit.*?(\d+)/i,
/context.*?length.*?(\d+).*?maximum.*?(\d+)/i,
/max.*?context.*?(\d+).*?but.*?(\d+)/i,
]
const TOKEN_LIMIT_KEYWORDS = [
"prompt is too long",
"is too long",
"context_length_exceeded",
"max_tokens",
"token limit",
"context length",
"too many tokens",
]
function extractTokensFromMessage(message: string): { current: number; max: number } | null {
for (const pattern of TOKEN_LIMIT_PATTERNS) {
const match = message.match(pattern)
if (match) {
const num1 = parseInt(match[1], 10)
const num2 = parseInt(match[2], 10)
return num1 > num2 ? { current: num1, max: num2 } : { current: num2, max: num1 }
}
}
return null
}
function isTokenLimitError(text: string): boolean {
const lower = text.toLowerCase()
return TOKEN_LIMIT_KEYWORDS.some((kw) => lower.includes(kw.toLowerCase()))
}
export function parseAnthropicTokenLimitError(err: unknown): ParsedTokenLimitError | null {
if (typeof err === "string") {
if (isTokenLimitError(err)) {
const tokens = extractTokensFromMessage(err)
return {
currentTokens: tokens?.current ?? 0,
maxTokens: tokens?.max ?? 0,
errorType: "token_limit_exceeded_string",
}
}
return null
}
if (!err || typeof err !== "object") return null
const errObj = err as Record<string, unknown>
const dataObj = errObj.data as Record<string, unknown> | undefined
const responseBody = dataObj?.responseBody
const errorMessage = errObj.message as string | undefined
const errorData = errObj.error as Record<string, unknown> | undefined
const nestedError = errorData?.error as Record<string, unknown> | undefined
const textSources: string[] = []
if (typeof responseBody === "string") textSources.push(responseBody)
if (typeof errorMessage === "string") textSources.push(errorMessage)
if (typeof errorData?.message === "string") textSources.push(errorData.message as string)
if (typeof errObj.body === "string") textSources.push(errObj.body as string)
if (typeof errObj.details === "string") textSources.push(errObj.details as string)
if (typeof errObj.reason === "string") textSources.push(errObj.reason as string)
if (typeof errObj.description === "string") textSources.push(errObj.description as string)
if (typeof nestedError?.message === "string") textSources.push(nestedError.message as string)
if (typeof dataObj?.message === "string") textSources.push(dataObj.message as string)
if (typeof dataObj?.error === "string") textSources.push(dataObj.error as string)
if (textSources.length === 0) {
try {
const jsonStr = JSON.stringify(errObj)
if (isTokenLimitError(jsonStr)) {
textSources.push(jsonStr)
}
} catch {}
}
const combinedText = textSources.join(" ")
if (!isTokenLimitError(combinedText)) return null
if (typeof responseBody === "string") {
try {
const jsonPatterns = [
/data:\s*(\{[\s\S]*?\})\s*$/m,
/(\{"type"\s*:\s*"error"[\s\S]*?\})/,
/(\{[\s\S]*?"error"[\s\S]*?\})/,
]
for (const pattern of jsonPatterns) {
const dataMatch = responseBody.match(pattern)
if (dataMatch) {
try {
const jsonData: AnthropicErrorData = JSON.parse(dataMatch[1])
const message = jsonData.error?.message || ""
const tokens = extractTokensFromMessage(message)
if (tokens) {
return {
currentTokens: tokens.current,
maxTokens: tokens.max,
requestId: jsonData.request_id,
errorType: jsonData.error?.type || "token_limit_exceeded",
}
}
} catch {}
}
}
const bedrockJson = JSON.parse(responseBody)
if (typeof bedrockJson.message === "string" && isTokenLimitError(bedrockJson.message)) {
return {
currentTokens: 0,
maxTokens: 0,
errorType: "bedrock_input_too_long",
}
}
} catch {}
}
for (const text of textSources) {
const tokens = extractTokensFromMessage(text)
if (tokens) {
return {
currentTokens: tokens.current,
maxTokens: tokens.max,
errorType: "token_limit_exceeded",
}
}
}
if (isTokenLimitError(combinedText)) {
return {
currentTokens: 0,
maxTokens: 0,
errorType: "token_limit_exceeded_unknown",
}
}
return null
}

View File

@@ -0,0 +1,13 @@
export interface ParsedTokenLimitError {
currentTokens: number
maxTokens: number
requestId?: string
errorType: string
providerID?: string
modelID?: string
}
export interface AutoCompactState {
pendingCompact: Set<string>
errorDataBySession: Map<string, ParsedTokenLimitError>
}

View File

@@ -0,0 +1,105 @@
import { existsSync } from "fs"
import { homedir } from "os"
import { join } from "path"
import type { ClaudeHookEvent } from "./types"
import { log } from "../../shared/logger"
export interface DisabledHooksConfig {
Stop?: string[]
PreToolUse?: string[]
PostToolUse?: string[]
UserPromptSubmit?: string[]
}
export interface PluginExtendedConfig {
disabledHooks?: DisabledHooksConfig
}
const USER_CONFIG_PATH = join(homedir(), ".config", "opencode", "opencode-cc-plugin.json")
function getProjectConfigPath(): string {
return join(process.cwd(), ".opencode", "opencode-cc-plugin.json")
}
async function loadConfigFromPath(path: string): Promise<PluginExtendedConfig | null> {
if (!existsSync(path)) {
return null
}
try {
const content = await Bun.file(path).text()
return JSON.parse(content) as PluginExtendedConfig
} catch (error) {
log("Failed to load config", { path, error })
return null
}
}
function mergeDisabledHooks(
base: DisabledHooksConfig | undefined,
override: DisabledHooksConfig | undefined
): DisabledHooksConfig {
if (!override) return base ?? {}
if (!base) return override
return {
Stop: override.Stop ?? base.Stop,
PreToolUse: override.PreToolUse ?? base.PreToolUse,
PostToolUse: override.PostToolUse ?? base.PostToolUse,
UserPromptSubmit: override.UserPromptSubmit ?? base.UserPromptSubmit,
}
}
export async function loadPluginExtendedConfig(): Promise<PluginExtendedConfig> {
const userConfig = await loadConfigFromPath(USER_CONFIG_PATH)
const projectConfig = await loadConfigFromPath(getProjectConfigPath())
const merged: PluginExtendedConfig = {
disabledHooks: mergeDisabledHooks(
userConfig?.disabledHooks,
projectConfig?.disabledHooks
),
}
if (userConfig || projectConfig) {
log("Plugin extended config loaded", {
userConfigExists: userConfig !== null,
projectConfigExists: projectConfig !== null,
mergedDisabledHooks: merged.disabledHooks,
})
}
return merged
}
const regexCache = new Map<string, RegExp>()
function getRegex(pattern: string): RegExp {
let regex = regexCache.get(pattern)
if (!regex) {
try {
regex = new RegExp(pattern)
regexCache.set(pattern, regex)
} catch {
regex = new RegExp(pattern.replace(/[.*+?^${}()|[\]\\]/g, "\\$&"))
regexCache.set(pattern, regex)
}
}
return regex
}
export function isHookCommandDisabled(
eventType: ClaudeHookEvent,
command: string,
config: PluginExtendedConfig | null
): boolean {
if (!config?.disabledHooks) return false
const patterns = config.disabledHooks[eventType]
if (!patterns || patterns.length === 0) return false
return patterns.some((pattern) => {
const regex = getRegex(pattern)
return regex.test(command)
})
}

View File

@@ -0,0 +1,100 @@
import { homedir } from "os"
import { join } from "path"
import { existsSync } from "fs"
import type { ClaudeHooksConfig, HookMatcher, HookCommand } from "./types"
interface RawHookMatcher {
matcher?: string
pattern?: string
hooks: HookCommand[]
}
interface RawClaudeHooksConfig {
PreToolUse?: RawHookMatcher[]
PostToolUse?: RawHookMatcher[]
UserPromptSubmit?: RawHookMatcher[]
Stop?: RawHookMatcher[]
}
function normalizeHookMatcher(raw: RawHookMatcher): HookMatcher {
return {
matcher: raw.matcher ?? raw.pattern ?? "*",
hooks: raw.hooks,
}
}
function normalizeHooksConfig(raw: RawClaudeHooksConfig): ClaudeHooksConfig {
const result: ClaudeHooksConfig = {}
const eventTypes: (keyof RawClaudeHooksConfig)[] = [
"PreToolUse",
"PostToolUse",
"UserPromptSubmit",
"Stop",
]
for (const eventType of eventTypes) {
if (raw[eventType]) {
result[eventType] = raw[eventType].map(normalizeHookMatcher)
}
}
return result
}
export function getClaudeSettingsPaths(customPath?: string): string[] {
const home = homedir()
const paths = [
join(home, ".claude", "settings.json"),
join(process.cwd(), ".claude", "settings.json"),
join(process.cwd(), ".claude", "settings.local.json"),
]
if (customPath && existsSync(customPath)) {
paths.unshift(customPath)
}
return paths
}
function mergeHooksConfig(
base: ClaudeHooksConfig,
override: ClaudeHooksConfig
): ClaudeHooksConfig {
const result: ClaudeHooksConfig = { ...base }
const eventTypes: (keyof ClaudeHooksConfig)[] = [
"PreToolUse",
"PostToolUse",
"UserPromptSubmit",
"Stop",
]
for (const eventType of eventTypes) {
if (override[eventType]) {
result[eventType] = [...(base[eventType] || []), ...override[eventType]]
}
}
return result
}
export async function loadClaudeHooksConfig(
customSettingsPath?: string
): Promise<ClaudeHooksConfig | null> {
const paths = getClaudeSettingsPaths(customSettingsPath)
let mergedConfig: ClaudeHooksConfig = {}
for (const settingsPath of paths) {
if (existsSync(settingsPath)) {
try {
const content = await Bun.file(settingsPath).text()
const settings = JSON.parse(content) as { hooks?: RawClaudeHooksConfig }
if (settings.hooks) {
const normalizedHooks = normalizeHooksConfig(settings.hooks)
mergedConfig = mergeHooksConfig(mergedConfig, normalizedHooks)
}
} catch {
continue
}
}
}
return Object.keys(mergedConfig).length > 0 ? mergedConfig : null
}

View File

@@ -0,0 +1,336 @@
import type { PluginInput } from "@opencode-ai/plugin"
import { loadClaudeHooksConfig } from "./config"
import { loadPluginExtendedConfig } from "./config-loader"
import {
executePreToolUseHooks,
type PreToolUseContext,
} from "./pre-tool-use"
import {
executePostToolUseHooks,
type PostToolUseContext,
type PostToolUseClient,
} from "./post-tool-use"
import {
executeUserPromptSubmitHooks,
type UserPromptSubmitContext,
type MessagePart,
} from "./user-prompt-submit"
import {
executeStopHooks,
type StopContext,
} from "./stop"
import { cacheToolInput, getToolInput } from "./tool-input-cache"
import { recordToolUse, recordToolResult, getTranscriptPath, recordUserMessage } from "./transcript"
import type { PluginConfig } from "./types"
import { log, isHookDisabled } from "../../shared"
import { injectHookMessage } from "../../features/hook-message-injector"
const sessionFirstMessageProcessed = new Set<string>()
const sessionErrorState = new Map<string, { hasError: boolean; errorMessage?: string }>()
const sessionInterruptState = new Map<string, { interrupted: boolean }>()
export function createClaudeCodeHooksHook(ctx: PluginInput, config: PluginConfig = {}) {
return {
"chat.message": async (
input: {
sessionID: string
agent?: string
model?: { providerID: string; modelID: string }
messageID?: string
},
output: {
message: Record<string, unknown>
parts: Array<{ type: string; text?: string; [key: string]: unknown }>
}
): Promise<void> => {
const interruptState = sessionInterruptState.get(input.sessionID)
if (interruptState?.interrupted) {
log("chat.message hook skipped - session interrupted", { sessionID: input.sessionID })
return
}
const claudeConfig = await loadClaudeHooksConfig()
const extendedConfig = await loadPluginExtendedConfig()
const textParts = output.parts.filter((p) => p.type === "text" && p.text)
const prompt = textParts.map((p) => p.text ?? "").join("\n")
recordUserMessage(input.sessionID, prompt)
const messageParts: MessagePart[] = textParts.map((p) => ({
type: p.type as "text",
text: p.text,
}))
const interruptStateBeforeHooks = sessionInterruptState.get(input.sessionID)
if (interruptStateBeforeHooks?.interrupted) {
log("chat.message hooks skipped - interrupted during preparation", { sessionID: input.sessionID })
return
}
let parentSessionId: string | undefined
try {
const sessionInfo = await ctx.client.session.get({
path: { id: input.sessionID },
})
parentSessionId = sessionInfo.data?.parentID
} catch {}
const isFirstMessage = !sessionFirstMessageProcessed.has(input.sessionID)
sessionFirstMessageProcessed.add(input.sessionID)
if (isFirstMessage) {
log("Skipping UserPromptSubmit hooks on first message for title generation", { sessionID: input.sessionID })
return
}
if (!isHookDisabled(config, "UserPromptSubmit")) {
const userPromptCtx: UserPromptSubmitContext = {
sessionId: input.sessionID,
parentSessionId,
prompt,
parts: messageParts,
cwd: ctx.directory,
}
const result = await executeUserPromptSubmitHooks(
userPromptCtx,
claudeConfig,
extendedConfig
)
if (result.block) {
throw new Error(result.reason ?? "Hook blocked the prompt")
}
const interruptStateAfterHooks = sessionInterruptState.get(input.sessionID)
if (interruptStateAfterHooks?.interrupted) {
log("chat.message injection skipped - interrupted during hooks", { sessionID: input.sessionID })
return
}
if (result.messages.length > 0) {
const hookContent = result.messages.join("\n\n")
const message = output.message as {
agent?: string
model?: { modelID?: string; providerID?: string }
path?: { cwd?: string; root?: string }
tools?: Record<string, boolean>
}
const success = injectHookMessage(input.sessionID, hookContent, {
agent: message.agent,
model: message.model,
path: message.path ?? { cwd: ctx.directory, root: "/" },
tools: message.tools,
})
log(success ? "Hook message injected via file system" : "File injection failed", {
sessionID: input.sessionID,
})
}
}
},
"tool.execute.before": async (
input: { tool: string; sessionID: string; callID: string },
output: { args: Record<string, unknown> }
): Promise<void> => {
const claudeConfig = await loadClaudeHooksConfig()
const extendedConfig = await loadPluginExtendedConfig()
recordToolUse(input.sessionID, input.tool, output.args as Record<string, unknown>)
cacheToolInput(input.sessionID, input.tool, input.callID, output.args as Record<string, unknown>)
if (!isHookDisabled(config, "PreToolUse")) {
const preCtx: PreToolUseContext = {
sessionId: input.sessionID,
toolName: input.tool,
toolInput: output.args as Record<string, unknown>,
cwd: ctx.directory,
toolUseId: input.callID,
}
const result = await executePreToolUseHooks(preCtx, claudeConfig, extendedConfig)
if (result.decision === "deny") {
ctx.client.tui
.showToast({
body: {
title: "PreToolUse Hook Executed",
message: `${result.toolName ?? input.tool} ${result.hookName ?? "hook"}: BLOCKED ${result.elapsedMs ?? 0}ms\n${result.inputLines ?? ""}`,
variant: "error",
duration: 4000,
},
})
.catch(() => {})
throw new Error(result.reason ?? "Hook blocked the operation")
}
if (result.modifiedInput) {
Object.assign(output.args as Record<string, unknown>, result.modifiedInput)
}
}
},
"tool.execute.after": async (
input: { tool: string; sessionID: string; callID: string },
output: { title: string; output: string; metadata: unknown }
): Promise<void> => {
const claudeConfig = await loadClaudeHooksConfig()
const extendedConfig = await loadPluginExtendedConfig()
const cachedInput = getToolInput(input.sessionID, input.tool, input.callID) || {}
recordToolResult(input.sessionID, input.tool, cachedInput, (output.metadata as Record<string, unknown>) || {})
if (!isHookDisabled(config, "PostToolUse")) {
const postClient: PostToolUseClient = {
session: {
messages: (opts) => ctx.client.session.messages(opts),
},
}
const postCtx: PostToolUseContext = {
sessionId: input.sessionID,
toolName: input.tool,
toolInput: cachedInput,
toolOutput: {
title: input.tool,
output: output.output,
metadata: output.metadata as Record<string, unknown>,
},
cwd: ctx.directory,
transcriptPath: getTranscriptPath(input.sessionID),
toolUseId: input.callID,
client: postClient,
permissionMode: "bypassPermissions",
}
const result = await executePostToolUseHooks(postCtx, claudeConfig, extendedConfig)
if (result.block) {
ctx.client.tui
.showToast({
body: {
title: "PostToolUse Hook Warning",
message: result.reason ?? "Hook returned warning",
variant: "warning",
duration: 4000,
},
})
.catch(() => {})
}
if (result.warnings && result.warnings.length > 0) {
output.output = `${output.output}\n\n${result.warnings.join("\n")}`
}
if (result.message) {
output.output = `${output.output}\n\n${result.message}`
}
if (result.hookName) {
ctx.client.tui
.showToast({
body: {
title: "PostToolUse Hook Executed",
message: `${result.toolName ?? input.tool} ${result.hookName}: ${result.elapsedMs ?? 0}ms`,
variant: "success",
duration: 2000,
},
})
.catch(() => {})
}
}
},
event: async (input: { event: { type: string; properties?: unknown } }) => {
const { event } = input
if (event.type === "session.error") {
const props = event.properties as Record<string, unknown> | undefined
const sessionID = props?.sessionID as string | undefined
if (sessionID) {
sessionErrorState.set(sessionID, {
hasError: true,
errorMessage: String(props?.error ?? "Unknown error"),
})
}
return
}
if (event.type === "session.deleted") {
const props = event.properties as Record<string, unknown> | undefined
const sessionInfo = props?.info as { id?: string } | undefined
if (sessionInfo?.id) {
sessionErrorState.delete(sessionInfo.id)
sessionInterruptState.delete(sessionInfo.id)
sessionFirstMessageProcessed.delete(sessionInfo.id)
}
return
}
if (event.type === "session.idle") {
const props = event.properties as Record<string, unknown> | undefined
const sessionID = props?.sessionID as string | undefined
if (!sessionID) return
const claudeConfig = await loadClaudeHooksConfig()
const extendedConfig = await loadPluginExtendedConfig()
const errorStateBefore = sessionErrorState.get(sessionID)
const endedWithErrorBefore = errorStateBefore?.hasError === true
const interruptStateBefore = sessionInterruptState.get(sessionID)
const interruptedBefore = interruptStateBefore?.interrupted === true
let parentSessionId: string | undefined
try {
const sessionInfo = await ctx.client.session.get({
path: { id: sessionID },
})
parentSessionId = sessionInfo.data?.parentID
} catch {}
if (!isHookDisabled(config, "Stop")) {
const stopCtx: StopContext = {
sessionId: sessionID,
parentSessionId,
cwd: ctx.directory,
}
const stopResult = await executeStopHooks(stopCtx, claudeConfig, extendedConfig)
const errorStateAfter = sessionErrorState.get(sessionID)
const endedWithErrorAfter = errorStateAfter?.hasError === true
const interruptStateAfter = sessionInterruptState.get(sessionID)
const interruptedAfter = interruptStateAfter?.interrupted === true
const shouldBypass = endedWithErrorBefore || endedWithErrorAfter || interruptedBefore || interruptedAfter
if (shouldBypass && stopResult.block) {
const interrupted = interruptedBefore || interruptedAfter
const endedWithError = endedWithErrorBefore || endedWithErrorAfter
log("Stop hook block ignored", { sessionID, block: stopResult.block, interrupted, endedWithError })
} else if (stopResult.block && stopResult.injectPrompt) {
log("Stop hook returned block with inject_prompt", { sessionID })
ctx.client.session
.prompt({
path: { id: sessionID },
body: { parts: [{ type: "text", text: stopResult.injectPrompt }] },
query: { directory: ctx.directory },
})
.catch((err: unknown) => log("Failed to inject prompt from Stop hook", err))
} else if (stopResult.block) {
log("Stop hook returned block", { sessionID, reason: stopResult.reason })
}
}
sessionErrorState.delete(sessionID)
sessionInterruptState.delete(sessionID)
}
},
}
}

View File

@@ -0,0 +1,9 @@
/**
* Plugin configuration for Claude Code hooks execution
* Contains settings for hook command execution (zsh, etc.)
*/
export const DEFAULT_CONFIG = {
forceZsh: true,
zshPath: "/bin/zsh",
}

View File

@@ -0,0 +1,199 @@
import type {
PostToolUseInput,
PostToolUseOutput,
ClaudeHooksConfig,
} from "./types"
import { findMatchingHooks, executeHookCommand, objectToSnakeCase, transformToolName, log } from "../../shared"
import { DEFAULT_CONFIG } from "./plugin-config"
import { buildTranscriptFromSession, deleteTempTranscript } from "./transcript"
import { isHookCommandDisabled, type PluginExtendedConfig } from "./config-loader"
export interface PostToolUseClient {
session: {
messages: (opts: { path: { id: string }; query?: { directory: string } }) => Promise<unknown>
}
}
export interface PostToolUseContext {
sessionId: string
toolName: string
toolInput: Record<string, unknown>
toolOutput: Record<string, unknown>
cwd: string
transcriptPath?: string // Fallback for append-based transcript
toolUseId?: string
client?: PostToolUseClient
permissionMode?: "default" | "plan" | "acceptEdits" | "bypassPermissions"
}
export interface PostToolUseResult {
block: boolean
reason?: string
message?: string
warnings?: string[]
elapsedMs?: number
hookName?: string
toolName?: string
additionalContext?: string
continue?: boolean
stopReason?: string
suppressOutput?: boolean
systemMessage?: string
}
export async function executePostToolUseHooks(
ctx: PostToolUseContext,
config: ClaudeHooksConfig | null,
extendedConfig?: PluginExtendedConfig | null
): Promise<PostToolUseResult> {
if (!config) {
return { block: false }
}
const transformedToolName = transformToolName(ctx.toolName)
const matchers = findMatchingHooks(config, "PostToolUse", transformedToolName)
if (matchers.length === 0) {
return { block: false }
}
// PORT FROM DISABLED: Build Claude Code compatible transcript (temp file)
let tempTranscriptPath: string | null = null
try {
// Try to build full transcript from API if client available
if (ctx.client) {
tempTranscriptPath = await buildTranscriptFromSession(
ctx.client,
ctx.sessionId,
ctx.cwd,
ctx.toolName,
ctx.toolInput
)
}
const stdinData: PostToolUseInput = {
session_id: ctx.sessionId,
// Use temp transcript if available, otherwise fallback to append-based
transcript_path: tempTranscriptPath ?? ctx.transcriptPath,
cwd: ctx.cwd,
permission_mode: ctx.permissionMode ?? "bypassPermissions",
hook_event_name: "PostToolUse",
tool_name: transformedToolName,
tool_input: objectToSnakeCase(ctx.toolInput),
tool_response: objectToSnakeCase(ctx.toolOutput),
tool_use_id: ctx.toolUseId,
hook_source: "opencode-plugin",
}
const messages: string[] = []
const warnings: string[] = []
let firstHookName: string | undefined
const startTime = Date.now()
for (const matcher of matchers) {
for (const hook of matcher.hooks) {
if (hook.type !== "command") continue
if (isHookCommandDisabled("PostToolUse", hook.command, extendedConfig ?? null)) {
log("PostToolUse hook command skipped (disabled by config)", { command: hook.command, toolName: ctx.toolName })
continue
}
const hookName = hook.command.split("/").pop() || hook.command
if (!firstHookName) firstHookName = hookName
const result = await executeHookCommand(
hook.command,
JSON.stringify(stdinData),
ctx.cwd,
{ forceZsh: DEFAULT_CONFIG.forceZsh, zshPath: DEFAULT_CONFIG.zshPath }
)
if (result.stdout) {
messages.push(result.stdout)
}
if (result.exitCode === 2) {
if (result.stderr) {
warnings.push(`[${hookName}]\n${result.stderr.trim()}`)
}
continue
}
if (result.exitCode === 0 && result.stdout) {
try {
const output = JSON.parse(result.stdout) as PostToolUseOutput
if (output.decision === "block") {
return {
block: true,
reason: output.reason || result.stderr,
message: messages.join("\n"),
warnings: warnings.length > 0 ? warnings : undefined,
elapsedMs: Date.now() - startTime,
hookName: firstHookName,
toolName: transformedToolName,
additionalContext: output.hookSpecificOutput?.additionalContext,
continue: output.continue,
stopReason: output.stopReason,
suppressOutput: output.suppressOutput,
systemMessage: output.systemMessage,
}
}
if (output.hookSpecificOutput?.additionalContext || output.continue !== undefined || output.systemMessage || output.suppressOutput === true || output.stopReason !== undefined) {
return {
block: false,
message: messages.join("\n"),
warnings: warnings.length > 0 ? warnings : undefined,
elapsedMs: Date.now() - startTime,
hookName: firstHookName,
toolName: transformedToolName,
additionalContext: output.hookSpecificOutput?.additionalContext,
continue: output.continue,
stopReason: output.stopReason,
suppressOutput: output.suppressOutput,
systemMessage: output.systemMessage,
}
}
} catch {
}
} else if (result.exitCode !== 0 && result.exitCode !== 2) {
try {
const output = JSON.parse(result.stdout || "{}") as PostToolUseOutput
if (output.decision === "block") {
return {
block: true,
reason: output.reason || result.stderr,
message: messages.join("\n"),
warnings: warnings.length > 0 ? warnings : undefined,
elapsedMs: Date.now() - startTime,
hookName: firstHookName,
toolName: transformedToolName,
additionalContext: output.hookSpecificOutput?.additionalContext,
continue: output.continue,
stopReason: output.stopReason,
suppressOutput: output.suppressOutput,
systemMessage: output.systemMessage,
}
}
} catch {
}
}
}
}
const elapsedMs = Date.now() - startTime
return {
block: false,
message: messages.length > 0 ? messages.join("\n") : undefined,
warnings: warnings.length > 0 ? warnings : undefined,
elapsedMs,
hookName: firstHookName,
toolName: transformedToolName,
}
} finally {
// PORT FROM DISABLED: Cleanup temp file to avoid disk accumulation
deleteTempTranscript(tempTranscriptPath)
}
}

View File

@@ -0,0 +1,172 @@
import type {
PreToolUseInput,
PreToolUseOutput,
PermissionDecision,
ClaudeHooksConfig,
} from "./types"
import { findMatchingHooks, executeHookCommand, objectToSnakeCase, transformToolName, log } from "../../shared"
import { DEFAULT_CONFIG } from "./plugin-config"
import { isHookCommandDisabled, type PluginExtendedConfig } from "./config-loader"
export interface PreToolUseContext {
sessionId: string
toolName: string
toolInput: Record<string, unknown>
cwd: string
transcriptPath?: string
toolUseId?: string
permissionMode?: "default" | "plan" | "acceptEdits" | "bypassPermissions"
}
export interface PreToolUseResult {
decision: PermissionDecision
reason?: string
modifiedInput?: Record<string, unknown>
elapsedMs?: number
hookName?: string
toolName?: string
inputLines?: string
// Common output fields (Claude Code spec)
continue?: boolean
stopReason?: string
suppressOutput?: boolean
systemMessage?: string
}
function buildInputLines(toolInput: Record<string, unknown>): string {
return Object.entries(toolInput)
.slice(0, 3)
.map(([key, val]) => {
const valStr = String(val).slice(0, 40)
return ` ${key}: ${valStr}${String(val).length > 40 ? "..." : ""}`
})
.join("\n")
}
export async function executePreToolUseHooks(
ctx: PreToolUseContext,
config: ClaudeHooksConfig | null,
extendedConfig?: PluginExtendedConfig | null
): Promise<PreToolUseResult> {
if (!config) {
return { decision: "allow" }
}
const transformedToolName = transformToolName(ctx.toolName)
const matchers = findMatchingHooks(config, "PreToolUse", transformedToolName)
if (matchers.length === 0) {
return { decision: "allow" }
}
const stdinData: PreToolUseInput = {
session_id: ctx.sessionId,
transcript_path: ctx.transcriptPath,
cwd: ctx.cwd,
permission_mode: ctx.permissionMode ?? "bypassPermissions",
hook_event_name: "PreToolUse",
tool_name: transformedToolName,
tool_input: objectToSnakeCase(ctx.toolInput),
tool_use_id: ctx.toolUseId,
hook_source: "opencode-plugin",
}
const startTime = Date.now()
let firstHookName: string | undefined
const inputLines = buildInputLines(ctx.toolInput)
for (const matcher of matchers) {
for (const hook of matcher.hooks) {
if (hook.type !== "command") continue
if (isHookCommandDisabled("PreToolUse", hook.command, extendedConfig ?? null)) {
log("PreToolUse hook command skipped (disabled by config)", { command: hook.command, toolName: ctx.toolName })
continue
}
const hookName = hook.command.split("/").pop() || hook.command
if (!firstHookName) firstHookName = hookName
const result = await executeHookCommand(
hook.command,
JSON.stringify(stdinData),
ctx.cwd,
{ forceZsh: DEFAULT_CONFIG.forceZsh, zshPath: DEFAULT_CONFIG.zshPath }
)
if (result.exitCode === 2) {
return {
decision: "deny",
reason: result.stderr || result.stdout || "Hook blocked the operation",
elapsedMs: Date.now() - startTime,
hookName: firstHookName,
toolName: transformedToolName,
inputLines,
}
}
if (result.exitCode === 1) {
return {
decision: "ask",
reason: result.stderr || result.stdout,
elapsedMs: Date.now() - startTime,
hookName: firstHookName,
toolName: transformedToolName,
inputLines,
}
}
if (result.stdout) {
try {
const output = JSON.parse(result.stdout) as PreToolUseOutput
// Handle deprecated decision/reason fields (Claude Code backward compat)
let decision: PermissionDecision | undefined
let reason: string | undefined
let modifiedInput: Record<string, unknown> | undefined
if (output.hookSpecificOutput?.permissionDecision) {
decision = output.hookSpecificOutput.permissionDecision
reason = output.hookSpecificOutput.permissionDecisionReason
modifiedInput = output.hookSpecificOutput.updatedInput
} else if (output.decision) {
// Map deprecated values: approve->allow, block->deny, ask->ask
const legacyDecision = output.decision
if (legacyDecision === "approve" || legacyDecision === "allow") {
decision = "allow"
} else if (legacyDecision === "block" || legacyDecision === "deny") {
decision = "deny"
} else if (legacyDecision === "ask") {
decision = "ask"
}
reason = output.reason
}
// Return if decision is set OR if any common fields are set (fallback to allow)
const hasCommonFields = output.continue !== undefined ||
output.stopReason !== undefined ||
output.suppressOutput !== undefined ||
output.systemMessage !== undefined
if (decision || hasCommonFields) {
return {
decision: decision ?? "allow",
reason,
modifiedInput,
elapsedMs: Date.now() - startTime,
hookName: firstHookName,
toolName: transformedToolName,
inputLines,
continue: output.continue,
stopReason: output.stopReason,
suppressOutput: output.suppressOutput,
systemMessage: output.systemMessage,
}
}
} catch {
}
}
}
}
return { decision: "allow" }
}

View File

@@ -0,0 +1,118 @@
import type {
StopInput,
StopOutput,
ClaudeHooksConfig,
} from "./types"
import { findMatchingHooks, executeHookCommand, log } from "../../shared"
import { DEFAULT_CONFIG } from "./plugin-config"
import { getTodoPath } from "./todo"
import { isHookCommandDisabled, type PluginExtendedConfig } from "./config-loader"
// Module-level state to track stop_hook_active per session
const stopHookActiveState = new Map<string, boolean>()
export function setStopHookActive(sessionId: string, active: boolean): void {
stopHookActiveState.set(sessionId, active)
}
export function getStopHookActive(sessionId: string): boolean {
return stopHookActiveState.get(sessionId) ?? false
}
export interface StopContext {
sessionId: string
parentSessionId?: string
cwd: string
transcriptPath?: string
permissionMode?: "default" | "acceptEdits" | "bypassPermissions"
stopHookActive?: boolean
}
export interface StopResult {
block: boolean
reason?: string
stopHookActive?: boolean
permissionMode?: "default" | "plan" | "acceptEdits" | "bypassPermissions"
injectPrompt?: string
}
export async function executeStopHooks(
ctx: StopContext,
config: ClaudeHooksConfig | null,
extendedConfig?: PluginExtendedConfig | null
): Promise<StopResult> {
if (ctx.parentSessionId) {
return { block: false }
}
if (!config) {
return { block: false }
}
const matchers = findMatchingHooks(config, "Stop")
if (matchers.length === 0) {
return { block: false }
}
const stdinData: StopInput = {
session_id: ctx.sessionId,
transcript_path: ctx.transcriptPath,
cwd: ctx.cwd,
permission_mode: ctx.permissionMode ?? "bypassPermissions",
hook_event_name: "Stop",
stop_hook_active: stopHookActiveState.get(ctx.sessionId) ?? false,
todo_path: getTodoPath(ctx.sessionId),
hook_source: "opencode-plugin",
}
for (const matcher of matchers) {
for (const hook of matcher.hooks) {
if (hook.type !== "command") continue
if (isHookCommandDisabled("Stop", hook.command, extendedConfig ?? null)) {
log("Stop hook command skipped (disabled by config)", { command: hook.command })
continue
}
const result = await executeHookCommand(
hook.command,
JSON.stringify(stdinData),
ctx.cwd,
{ forceZsh: DEFAULT_CONFIG.forceZsh, zshPath: DEFAULT_CONFIG.zshPath }
)
// Check exit code first - exit code 2 means block
if (result.exitCode === 2) {
const reason = result.stderr || result.stdout || "Blocked by stop hook"
return {
block: true,
reason,
injectPrompt: reason,
}
}
if (result.stdout) {
try {
const output = JSON.parse(result.stdout) as StopOutput
if (output.stop_hook_active !== undefined) {
stopHookActiveState.set(ctx.sessionId, output.stop_hook_active)
}
const isBlock = output.decision === "block"
// Determine inject_prompt: prefer explicit value, fallback to reason if blocking
const injectPrompt = output.inject_prompt ?? (isBlock && output.reason ? output.reason : undefined)
return {
block: isBlock,
reason: output.reason,
stopHookActive: output.stop_hook_active,
permissionMode: output.permission_mode,
injectPrompt,
}
} catch {
// Ignore JSON parse errors - hook may return non-JSON output
}
}
}
}
return { block: false }
}

View File

@@ -0,0 +1,76 @@
import { join } from "path"
import { mkdirSync, writeFileSync, readFileSync, existsSync, unlinkSync } from "fs"
import { homedir } from "os"
import type { TodoFile, TodoItem, ClaudeCodeTodoItem } from "./types"
const TODO_DIR = join(homedir(), ".claude", "todos")
export function getTodoPath(sessionId: string): string {
return join(TODO_DIR, `${sessionId}-agent-${sessionId}.json`)
}
function ensureTodoDir(): void {
if (!existsSync(TODO_DIR)) {
mkdirSync(TODO_DIR, { recursive: true })
}
}
export interface OpenCodeTodo {
content: string
status: string
priority: string
id: string
}
function toClaudeCodeFormat(item: OpenCodeTodo | TodoItem): ClaudeCodeTodoItem {
return {
content: item.content,
status: item.status === "cancelled" ? "completed" : item.status,
activeForm: item.content,
}
}
export function loadTodoFile(sessionId: string): TodoFile | null {
const path = getTodoPath(sessionId)
if (!existsSync(path)) return null
try {
const content = JSON.parse(readFileSync(path, "utf-8"))
if (Array.isArray(content)) {
return {
session_id: sessionId,
items: content.map((item: ClaudeCodeTodoItem, idx: number) => ({
id: String(idx),
content: item.content,
status: item.status as TodoItem["status"],
created_at: new Date().toISOString(),
})),
created_at: new Date().toISOString(),
updated_at: new Date().toISOString(),
}
}
return content
} catch {
return null
}
}
export function saveTodoFile(sessionId: string, file: TodoFile): void {
ensureTodoDir()
const path = getTodoPath(sessionId)
const claudeCodeFormat: ClaudeCodeTodoItem[] = file.items.map(toClaudeCodeFormat)
writeFileSync(path, JSON.stringify(claudeCodeFormat, null, 2))
}
export function saveOpenCodeTodos(sessionId: string, todos: OpenCodeTodo[]): void {
ensureTodoDir()
const path = getTodoPath(sessionId)
const claudeCodeFormat: ClaudeCodeTodoItem[] = todos.map(toClaudeCodeFormat)
writeFileSync(path, JSON.stringify(claudeCodeFormat, null, 2))
}
export function deleteTodoFile(sessionId: string): void {
const path = getTodoPath(sessionId)
if (existsSync(path)) {
unlinkSync(path)
}
}

View File

@@ -0,0 +1,47 @@
/**
* Caches tool_input from PreToolUse for PostToolUse
*/
interface CacheEntry {
toolInput: Record<string, unknown>
timestamp: number
}
const cache = new Map<string, CacheEntry>()
const CACHE_TTL = 60000 // 1 minute
export function cacheToolInput(
sessionId: string,
toolName: string,
invocationId: string,
toolInput: Record<string, unknown>
): void {
const key = `${sessionId}:${toolName}:${invocationId}`
cache.set(key, { toolInput, timestamp: Date.now() })
}
export function getToolInput(
sessionId: string,
toolName: string,
invocationId: string
): Record<string, unknown> | null {
const key = `${sessionId}:${toolName}:${invocationId}`
const entry = cache.get(key)
if (!entry) return null
cache.delete(key)
if (Date.now() - entry.timestamp > CACHE_TTL) return null
return entry.toolInput
}
// Periodic cleanup (every minute)
setInterval(() => {
const now = Date.now()
for (const [key, entry] of cache.entries()) {
if (now - entry.timestamp > CACHE_TTL) {
cache.delete(key)
}
}
}, CACHE_TTL)

View File

@@ -0,0 +1,255 @@
/**
* Transcript Manager
* Creates and manages Claude Code compatible transcript files
*/
import { join } from "path"
import { mkdirSync, appendFileSync, existsSync, writeFileSync, unlinkSync } from "fs"
import { homedir, tmpdir } from "os"
import { randomUUID } from "crypto"
import type { TranscriptEntry } from "./types"
import { transformToolName } from "../../shared/tool-name"
const TRANSCRIPT_DIR = join(homedir(), ".claude", "transcripts")
export function getTranscriptPath(sessionId: string): string {
return join(TRANSCRIPT_DIR, `${sessionId}.jsonl`)
}
function ensureTranscriptDir(): void {
if (!existsSync(TRANSCRIPT_DIR)) {
mkdirSync(TRANSCRIPT_DIR, { recursive: true })
}
}
export function appendTranscriptEntry(
sessionId: string,
entry: TranscriptEntry
): void {
ensureTranscriptDir()
const path = getTranscriptPath(sessionId)
const line = JSON.stringify(entry) + "\n"
appendFileSync(path, line)
}
export function recordToolUse(
sessionId: string,
toolName: string,
toolInput: Record<string, unknown>
): void {
appendTranscriptEntry(sessionId, {
type: "tool_use",
timestamp: new Date().toISOString(),
tool_name: toolName,
tool_input: toolInput,
})
}
export function recordToolResult(
sessionId: string,
toolName: string,
toolInput: Record<string, unknown>,
toolOutput: Record<string, unknown>
): void {
appendTranscriptEntry(sessionId, {
type: "tool_result",
timestamp: new Date().toISOString(),
tool_name: toolName,
tool_input: toolInput,
tool_output: toolOutput,
})
}
export function recordUserMessage(
sessionId: string,
content: string
): void {
appendTranscriptEntry(sessionId, {
type: "user",
timestamp: new Date().toISOString(),
content,
})
}
export function recordAssistantMessage(
sessionId: string,
content: string
): void {
appendTranscriptEntry(sessionId, {
type: "assistant",
timestamp: new Date().toISOString(),
content,
})
}
// ============================================================================
// Claude Code Compatible Transcript Builder (PORT FROM DISABLED)
// ============================================================================
/**
* OpenCode API response type (loosely typed)
*/
interface OpenCodeMessagePart {
type: string
tool?: string
state?: {
status?: string
input?: Record<string, unknown>
}
}
interface OpenCodeMessage {
info?: {
role?: string
}
parts?: OpenCodeMessagePart[]
}
/**
* Claude Code compatible transcript entry (from disabled file)
*/
interface DisabledTranscriptEntry {
type: "assistant"
message: {
role: "assistant"
content: Array<{
type: "tool_use"
name: string
input: Record<string, unknown>
}>
}
}
/**
* Build Claude Code compatible transcript from session messages
*
* PORT FROM DISABLED: This calls client.session.messages() API to fetch
* the full session history and builds a JSONL file in Claude Code format.
*
* @param client OpenCode client instance
* @param sessionId Session ID
* @param directory Working directory
* @param currentToolName Current tool being executed (added as last entry)
* @param currentToolInput Current tool input
* @returns Temp file path (caller must call deleteTempTranscript!)
*/
export async function buildTranscriptFromSession(
client: {
session: {
messages: (opts: { path: { id: string }; query?: { directory: string } }) => Promise<unknown>
}
},
sessionId: string,
directory: string,
currentToolName: string,
currentToolInput: Record<string, unknown>
): Promise<string | null> {
try {
const response = await client.session.messages({
path: { id: sessionId },
query: { directory },
})
// Handle various response formats
const messages = (response as { "200"?: unknown[]; data?: unknown[] })["200"]
?? (response as { data?: unknown[] }).data
?? (Array.isArray(response) ? response : [])
const entries: string[] = []
if (Array.isArray(messages)) {
for (const msg of messages as OpenCodeMessage[]) {
if (msg.info?.role !== "assistant") continue
for (const part of msg.parts || []) {
if (part.type !== "tool") continue
if (part.state?.status !== "completed") continue
if (!part.state?.input) continue
const rawToolName = part.tool as string
const toolName = transformToolName(rawToolName)
const entry: DisabledTranscriptEntry = {
type: "assistant",
message: {
role: "assistant",
content: [
{
type: "tool_use",
name: toolName,
input: part.state.input,
},
],
},
}
entries.push(JSON.stringify(entry))
}
}
}
// Always add current tool call as the last entry
const currentEntry: DisabledTranscriptEntry = {
type: "assistant",
message: {
role: "assistant",
content: [
{
type: "tool_use",
name: transformToolName(currentToolName),
input: currentToolInput,
},
],
},
}
entries.push(JSON.stringify(currentEntry))
// Write to temp file
const tempPath = join(
tmpdir(),
`opencode-transcript-${sessionId}-${randomUUID()}.jsonl`
)
writeFileSync(tempPath, entries.join("\n") + "\n")
return tempPath
} catch {
// CRITICAL FIX: Even on API failure, create file with current tool entry only
// (matching original disabled behavior - never return null with incompatible format)
try {
const currentEntry: DisabledTranscriptEntry = {
type: "assistant",
message: {
role: "assistant",
content: [
{
type: "tool_use",
name: transformToolName(currentToolName),
input: currentToolInput,
},
],
},
}
const tempPath = join(
tmpdir(),
`opencode-transcript-${sessionId}-${randomUUID()}.jsonl`
)
writeFileSync(tempPath, JSON.stringify(currentEntry) + "\n")
return tempPath
} catch {
// If even this fails, return null (truly catastrophic failure)
return null
}
}
}
/**
* Delete temp transcript file (call in finally block)
*
* PORT FROM DISABLED: Cleanup mechanism to avoid disk accumulation
*/
export function deleteTempTranscript(path: string | null): void {
if (!path) return
try {
unlinkSync(path)
} catch {
// Ignore deletion errors
}
}

View File

@@ -0,0 +1,184 @@
/**
* Claude Code Hooks Type Definitions
* Maps Claude Code hook concepts to OpenCode plugin events
*/
export type ClaudeHookEvent =
| "PreToolUse"
| "PostToolUse"
| "UserPromptSubmit"
| "Stop"
export interface HookMatcher {
matcher: string
hooks: HookCommand[]
}
export interface HookCommand {
type: "command"
command: string
}
export interface ClaudeHooksConfig {
PreToolUse?: HookMatcher[]
PostToolUse?: HookMatcher[]
UserPromptSubmit?: HookMatcher[]
Stop?: HookMatcher[]
}
export interface PreToolUseInput {
session_id: string
transcript_path?: string
cwd: string
permission_mode?: PermissionMode
hook_event_name: "PreToolUse"
tool_name: string
tool_input: Record<string, unknown>
tool_use_id?: string
hook_source?: HookSource
}
export interface PostToolUseInput {
session_id: string
transcript_path?: string
cwd: string
permission_mode?: PermissionMode
hook_event_name: "PostToolUse"
tool_name: string
tool_input: Record<string, unknown>
tool_response: {
title?: string
output?: string
[key: string]: unknown
}
tool_use_id?: string
hook_source?: HookSource
}
export interface UserPromptSubmitInput {
session_id: string
cwd: string
permission_mode?: PermissionMode
hook_event_name: "UserPromptSubmit"
prompt: string
session?: {
id: string
}
hook_source?: HookSource
}
export type PermissionMode = "default" | "plan" | "acceptEdits" | "bypassPermissions"
export type HookSource = "opencode-plugin"
export interface StopInput {
session_id: string
transcript_path?: string
cwd: string
permission_mode?: PermissionMode
hook_event_name: "Stop"
stop_hook_active: boolean
todo_path?: string
hook_source?: HookSource
}
export type PermissionDecision = "allow" | "deny" | "ask"
/**
* Common JSON fields for all hook outputs (Claude Code spec)
*/
export interface HookCommonOutput {
/** If false, Claude stops entirely */
continue?: boolean
/** Message shown to user when continue=false */
stopReason?: string
/** Suppress output from transcript */
suppressOutput?: boolean
/** Warning/message displayed to user */
systemMessage?: string
}
export interface PreToolUseOutput extends HookCommonOutput {
/** Deprecated: use hookSpecificOutput.permissionDecision instead */
decision?: "allow" | "deny" | "approve" | "block" | "ask"
/** Deprecated: use hookSpecificOutput.permissionDecisionReason instead */
reason?: string
hookSpecificOutput?: {
hookEventName: "PreToolUse"
permissionDecision: PermissionDecision
permissionDecisionReason?: string
updatedInput?: Record<string, unknown>
}
}
export interface PostToolUseOutput extends HookCommonOutput {
decision?: "block"
reason?: string
hookSpecificOutput?: {
hookEventName: "PostToolUse"
/** Additional context to provide to Claude */
additionalContext?: string
}
}
export interface HookResult {
exitCode: number
stdout?: string
stderr?: string
}
export interface TranscriptEntry {
type: "tool_use" | "tool_result" | "user" | "assistant"
timestamp: string
tool_name?: string
tool_input?: Record<string, unknown>
tool_output?: Record<string, unknown>
content?: string
}
export interface TodoItem {
id: string
content: string
status: "pending" | "in_progress" | "completed" | "cancelled"
priority?: "low" | "medium" | "high"
created_at: string
updated_at?: string
}
export interface ClaudeCodeTodoItem {
content: string
status: string // "pending" | "in_progress" | "completed"
activeForm: string
}
export interface TodoFile {
session_id: string
items: TodoItem[]
created_at: string
updated_at: string
}
export interface StopOutput {
decision?: "block" | "continue"
reason?: string
stop_hook_active?: boolean
permission_mode?: PermissionMode
inject_prompt?: string
}
export type ClaudeCodeContent =
| { type: "text"; text: string }
| { type: "tool_use"; id: string; name: string; input: Record<string, unknown> }
| { type: "tool_result"; tool_use_id: string; content: string }
export interface ClaudeCodeMessage {
type: "user" | "assistant"
message: {
role: "user" | "assistant"
content: ClaudeCodeContent[]
}
}
export interface PluginConfig {
disabledHooks?: boolean | ClaudeHookEvent[]
}

View File

@@ -0,0 +1,117 @@
import type {
UserPromptSubmitInput,
PostToolUseOutput,
ClaudeHooksConfig,
} from "./types"
import { findMatchingHooks, executeHookCommand, log } from "../../shared"
import { DEFAULT_CONFIG } from "./plugin-config"
import { isHookCommandDisabled, type PluginExtendedConfig } from "./config-loader"
const USER_PROMPT_SUBMIT_TAG_OPEN = "<user-prompt-submit-hook>"
const USER_PROMPT_SUBMIT_TAG_CLOSE = "</user-prompt-submit-hook>"
export interface MessagePart {
type: "text" | "tool_use" | "tool_result"
text?: string
[key: string]: unknown
}
export interface UserPromptSubmitContext {
sessionId: string
parentSessionId?: string
prompt: string
parts: MessagePart[]
cwd: string
permissionMode?: "default" | "acceptEdits" | "bypassPermissions"
}
export interface UserPromptSubmitResult {
block: boolean
reason?: string
modifiedParts: MessagePart[]
messages: string[]
}
export async function executeUserPromptSubmitHooks(
ctx: UserPromptSubmitContext,
config: ClaudeHooksConfig | null,
extendedConfig?: PluginExtendedConfig | null
): Promise<UserPromptSubmitResult> {
const modifiedParts = ctx.parts
const messages: string[] = []
if (ctx.parentSessionId) {
return { block: false, modifiedParts, messages }
}
if (
ctx.prompt.includes(USER_PROMPT_SUBMIT_TAG_OPEN) &&
ctx.prompt.includes(USER_PROMPT_SUBMIT_TAG_CLOSE)
) {
return { block: false, modifiedParts, messages }
}
if (!config) {
return { block: false, modifiedParts, messages }
}
const matchers = findMatchingHooks(config, "UserPromptSubmit")
if (matchers.length === 0) {
return { block: false, modifiedParts, messages }
}
const stdinData: UserPromptSubmitInput = {
session_id: ctx.sessionId,
cwd: ctx.cwd,
permission_mode: ctx.permissionMode ?? "bypassPermissions",
hook_event_name: "UserPromptSubmit",
prompt: ctx.prompt,
session: { id: ctx.sessionId },
hook_source: "opencode-plugin",
}
for (const matcher of matchers) {
for (const hook of matcher.hooks) {
if (hook.type !== "command") continue
if (isHookCommandDisabled("UserPromptSubmit", hook.command, extendedConfig ?? null)) {
log("UserPromptSubmit hook command skipped (disabled by config)", { command: hook.command })
continue
}
const result = await executeHookCommand(
hook.command,
JSON.stringify(stdinData),
ctx.cwd,
{ forceZsh: DEFAULT_CONFIG.forceZsh, zshPath: DEFAULT_CONFIG.zshPath }
)
if (result.stdout) {
const output = result.stdout.trim()
if (output.startsWith(USER_PROMPT_SUBMIT_TAG_OPEN)) {
messages.push(output)
} else {
messages.push(`${USER_PROMPT_SUBMIT_TAG_OPEN}\n${output}\n${USER_PROMPT_SUBMIT_TAG_CLOSE}`)
}
}
if (result.exitCode !== 0) {
try {
const output = JSON.parse(result.stdout || "{}") as PostToolUseOutput
if (output.decision === "block") {
return {
block: true,
reason: output.reason || result.stderr,
modifiedParts,
messages,
}
}
} catch {
// Ignore JSON parse errors
}
}
}
}
return { block: false, modifiedParts, messages }
}

View File

@@ -0,0 +1,210 @@
import { spawn } from "bun"
import { createRequire } from "module"
import { dirname, join } from "path"
import { existsSync } from "fs"
import * as fs from "fs"
import { getCachedBinaryPath, ensureCommentCheckerBinary } from "./downloader"
const DEBUG = process.env.COMMENT_CHECKER_DEBUG === "1"
const DEBUG_FILE = "/tmp/comment-checker-debug.log"
function debugLog(...args: unknown[]) {
if (DEBUG) {
const msg = `[${new Date().toISOString()}] [comment-checker:cli] ${args.map(a => typeof a === 'object' ? JSON.stringify(a, null, 2) : String(a)).join(' ')}\n`
fs.appendFileSync(DEBUG_FILE, msg)
}
}
function getBinaryName(): string {
return process.platform === "win32" ? "comment-checker.exe" : "comment-checker"
}
function findCommentCheckerPathSync(): string | null {
const binaryName = getBinaryName()
try {
const require = createRequire(import.meta.url)
const cliPkgPath = require.resolve("@code-yeongyu/comment-checker/package.json")
const cliDir = dirname(cliPkgPath)
const binaryPath = join(cliDir, "bin", binaryName)
if (existsSync(binaryPath)) {
debugLog("found binary in main package:", binaryPath)
return binaryPath
}
} catch {
debugLog("main package not installed")
}
const cachedPath = getCachedBinaryPath()
if (cachedPath) {
debugLog("found binary in cache:", cachedPath)
return cachedPath
}
debugLog("no binary found in known locations")
return null
}
// Cached resolved path
let resolvedCliPath: string | null = null
let initPromise: Promise<string | null> | null = null
/**
* Asynchronously get comment-checker binary path.
* Will trigger lazy download if binary not found.
*/
export async function getCommentCheckerPath(): Promise<string | null> {
// Return cached path if already resolved
if (resolvedCliPath !== null) {
return resolvedCliPath
}
// Return existing promise if initialization is in progress
if (initPromise) {
return initPromise
}
initPromise = (async () => {
// First try sync path resolution
const syncPath = findCommentCheckerPathSync()
if (syncPath && existsSync(syncPath)) {
resolvedCliPath = syncPath
debugLog("using sync-resolved path:", syncPath)
return syncPath
}
// Lazy download if not found
debugLog("triggering lazy download...")
const downloadedPath = await ensureCommentCheckerBinary()
if (downloadedPath) {
resolvedCliPath = downloadedPath
debugLog("using downloaded path:", downloadedPath)
return downloadedPath
}
debugLog("no binary available")
return null
})()
return initPromise
}
/**
* Synchronously get comment-checker path (no download).
* Returns cached path or searches known locations.
*/
export function getCommentCheckerPathSync(): string | null {
return resolvedCliPath ?? findCommentCheckerPathSync()
}
/**
* Start background initialization.
* Call this early to trigger download while other init happens.
*/
export function startBackgroundInit(): void {
if (!initPromise) {
initPromise = getCommentCheckerPath()
initPromise.then(path => {
debugLog("background init complete:", path || "no binary")
}).catch(err => {
debugLog("background init error:", err)
})
}
}
// Legacy export for backwards compatibility (sync, no download)
export const COMMENT_CHECKER_CLI_PATH = findCommentCheckerPathSync()
export interface HookInput {
session_id: string
tool_name: string
transcript_path: string
cwd: string
hook_event_name: string
tool_input: {
file_path?: string
content?: string
old_string?: string
new_string?: string
edits?: Array<{ old_string: string; new_string: string }>
}
tool_response?: unknown
}
export interface CheckResult {
hasComments: boolean
message: string
}
/**
* Run comment-checker CLI with given input.
* @param input Hook input to check
* @param cliPath Optional explicit path to CLI binary
*/
export async function runCommentChecker(input: HookInput, cliPath?: string): Promise<CheckResult> {
const binaryPath = cliPath ?? resolvedCliPath ?? COMMENT_CHECKER_CLI_PATH
if (!binaryPath) {
debugLog("comment-checker binary not found")
return { hasComments: false, message: "" }
}
if (!existsSync(binaryPath)) {
debugLog("comment-checker binary does not exist:", binaryPath)
return { hasComments: false, message: "" }
}
const jsonInput = JSON.stringify(input)
debugLog("running comment-checker with input:", jsonInput.substring(0, 200))
try {
const proc = spawn([binaryPath], {
stdin: "pipe",
stdout: "pipe",
stderr: "pipe",
})
// Write JSON to stdin
proc.stdin.write(jsonInput)
proc.stdin.end()
const stdout = await new Response(proc.stdout).text()
const stderr = await new Response(proc.stderr).text()
const exitCode = await proc.exited
debugLog("exit code:", exitCode, "stdout length:", stdout.length, "stderr length:", stderr.length)
if (exitCode === 0) {
return { hasComments: false, message: "" }
}
if (exitCode === 2) {
// Comments detected - message is in stderr
return { hasComments: true, message: stderr }
}
// Error case
debugLog("unexpected exit code:", exitCode, "stderr:", stderr)
return { hasComments: false, message: "" }
} catch (err) {
debugLog("failed to run comment-checker:", err)
return { hasComments: false, message: "" }
}
}
/**
* Check if CLI is available (sync check, no download).
*/
export function isCliAvailable(): boolean {
const path = getCommentCheckerPathSync()
return path !== null && existsSync(path)
}
/**
* Check if CLI will be available (async, may trigger download).
*/
export async function ensureCliAvailable(): Promise<boolean> {
const path = await getCommentCheckerPath()
return path !== null && existsSync(path)
}

View File

@@ -1,117 +1,3 @@
import type { LanguageConfig } from "./types"
export const EXTENSION_TO_LANGUAGE: Record<string, string> = {
py: "python",
js: "javascript",
jsx: "javascript",
ts: "typescript",
tsx: "tsx",
go: "golang",
java: "java",
kt: "kotlin",
scala: "scala",
c: "c",
h: "c",
cpp: "cpp",
cc: "cpp",
cxx: "cpp",
hpp: "cpp",
rs: "rust",
rb: "ruby",
sh: "bash",
bash: "bash",
cs: "csharp",
swift: "swift",
ex: "elixir",
exs: "elixir",
lua: "lua",
php: "php",
ml: "ocaml",
mli: "ocaml",
sql: "sql",
html: "html",
htm: "html",
css: "css",
yaml: "yaml",
yml: "yaml",
toml: "toml",
hcl: "hcl",
tf: "hcl",
dockerfile: "dockerfile",
proto: "protobuf",
svelte: "svelte",
elm: "elm",
groovy: "groovy",
cue: "cue",
}
export const QUERY_TEMPLATES: Record<string, string> = {
python: "(comment) @comment",
javascript: "(comment) @comment",
typescript: "(comment) @comment",
tsx: "(comment) @comment",
golang: "(comment) @comment",
rust: `
(line_comment) @comment
(block_comment) @comment
`,
kotlin: `
(line_comment) @comment
(multiline_comment) @comment
`,
java: `
(line_comment) @comment
(block_comment) @comment
`,
c: "(comment) @comment",
cpp: "(comment) @comment",
csharp: "(comment) @comment",
ruby: "(comment) @comment",
bash: "(comment) @comment",
swift: "(comment) @comment",
elixir: "(comment) @comment",
lua: "(comment) @comment",
php: "(comment) @comment",
ocaml: "(comment) @comment",
sql: "(comment) @comment",
html: "(comment) @comment",
css: "(comment) @comment",
yaml: "(comment) @comment",
toml: "(comment) @comment",
hcl: "(comment) @comment",
dockerfile: "(comment) @comment",
protobuf: "(comment) @comment",
svelte: "(comment) @comment",
elm: "(comment) @comment",
groovy: "(comment) @comment",
cue: "(comment) @comment",
scala: "(comment) @comment",
}
export const DOCSTRING_QUERIES: Record<string, string> = {
python: `
(module . (expression_statement (string) @docstring))
(class_definition body: (block . (expression_statement (string) @docstring)))
(function_definition body: (block . (expression_statement (string) @docstring)))
`,
javascript: `
(comment) @jsdoc
(#match? @jsdoc "^/\\\\*\\\\*")
`,
typescript: `
(comment) @jsdoc
(#match? @jsdoc "^/\\\\*\\\\*")
`,
tsx: `
(comment) @jsdoc
(#match? @jsdoc "^/\\\\*\\\\*")
`,
java: `
(comment) @javadoc
(#match? @javadoc "^/\\\\*\\\\*")
`,
}
export const BDD_KEYWORDS = new Set([
"given",
"when",
@@ -186,19 +72,12 @@ PRIORITY-BASED ACTION GUIDELINES:
\t-> Make the code itself clearer so it can be understood without comments/docstrings.
\t-> For verbose docstrings: refactor code to be self-documenting instead of adding lengthy explanations.
CODE SMELL WARNING: Using comments as visual separators (e.g., "// =========", "# ---", "// *** Section ***")
is a code smell. If you need separators, your file is too long or poorly organized.
Refactor into smaller modules or use proper code organization instead of comment-based section dividers.
MANDATORY REQUIREMENT: You must acknowledge this hook message and take one of the above actions.
Review in the above priority order and take the corresponding action EVERY TIME this appears.
Detected comments/docstrings:
`
export function getLanguageByExtension(filePath: string): string | null {
const lastDot = filePath.lastIndexOf(".")
if (lastDot === -1) {
const baseName = filePath.split("/").pop()?.toLowerCase()
if (baseName === "dockerfile") return "dockerfile"
return null
}
const ext = filePath.slice(lastDot + 1).toLowerCase()
return EXTENSION_TO_LANGUAGE[ext] ?? null
}

View File

@@ -1,142 +0,0 @@
import type { CommentInfo, CommentType } from "./types"
import { getLanguageByExtension, QUERY_TEMPLATES, DOCSTRING_QUERIES } from "./constants"
export function isSupportedFile(filePath: string): boolean {
return getLanguageByExtension(filePath) !== null
}
function determineCommentType(text: string, nodeType: string): CommentType {
const stripped = text.trim()
if (nodeType === "line_comment") {
return "line"
}
if (nodeType === "block_comment" || nodeType === "multiline_comment") {
return "block"
}
if (stripped.startsWith('"""') || stripped.startsWith("'''")) {
return "docstring"
}
if (stripped.startsWith("//") || stripped.startsWith("#")) {
return "line"
}
if (stripped.startsWith("/*") || stripped.startsWith("<!--") || stripped.startsWith("--")) {
return "block"
}
return "line"
}
export async function detectComments(
filePath: string,
content: string,
includeDocstrings = true
): Promise<CommentInfo[]> {
const langName = getLanguageByExtension(filePath)
if (!langName) {
return []
}
const queryPattern = QUERY_TEMPLATES[langName]
if (!queryPattern) {
return []
}
try {
const Parser = (await import("web-tree-sitter")).default
await Parser.init()
const parser = new Parser()
let wasmPath: string
try {
const wasmModule = await import(`tree-sitter-wasms/out/tree-sitter-${langName}.wasm`)
wasmPath = wasmModule.default
} catch {
const languageMap: Record<string, string> = {
golang: "go",
csharp: "c_sharp",
cpp: "cpp",
}
const mappedLang = languageMap[langName] || langName
try {
const wasmModule = await import(`tree-sitter-wasms/out/tree-sitter-${mappedLang}.wasm`)
wasmPath = wasmModule.default
} catch {
return []
}
}
const language = await Parser.Language.load(wasmPath)
parser.setLanguage(language)
const tree = parser.parse(content)
const comments: CommentInfo[] = []
const query = language.query(queryPattern)
const matches = query.matches(tree.rootNode)
for (const match of matches) {
for (const capture of match.captures) {
const node = capture.node
const text = node.text
const lineNumber = node.startPosition.row + 1
const commentType = determineCommentType(text, node.type)
const isDocstring = commentType === "docstring"
if (isDocstring && !includeDocstrings) {
continue
}
comments.push({
text,
lineNumber,
filePath,
commentType,
isDocstring,
})
}
}
if (includeDocstrings) {
const docQuery = DOCSTRING_QUERIES[langName]
if (docQuery) {
try {
const docQueryObj = language.query(docQuery)
const docMatches = docQueryObj.matches(tree.rootNode)
for (const match of docMatches) {
for (const capture of match.captures) {
const node = capture.node
const text = node.text
const lineNumber = node.startPosition.row + 1
const alreadyAdded = comments.some(
(c) => c.lineNumber === lineNumber && c.text === text
)
if (!alreadyAdded) {
comments.push({
text,
lineNumber,
filePath,
commentType: "docstring",
isDocstring: true,
})
}
}
}
} catch {}
}
}
comments.sort((a, b) => a.lineNumber - b.lineNumber)
return comments
} catch {
return []
}
}

View File

@@ -0,0 +1,210 @@
import { spawn } from "bun"
import { existsSync, mkdirSync, chmodSync, unlinkSync, appendFileSync } from "fs"
import { join } from "path"
import { homedir } from "os"
import { createRequire } from "module"
const DEBUG = process.env.COMMENT_CHECKER_DEBUG === "1"
const DEBUG_FILE = "/tmp/comment-checker-debug.log"
function debugLog(...args: unknown[]) {
if (DEBUG) {
const msg = `[${new Date().toISOString()}] [comment-checker:downloader] ${args.map(a => typeof a === 'object' ? JSON.stringify(a, null, 2) : String(a)).join(' ')}\n`
appendFileSync(DEBUG_FILE, msg)
}
}
const REPO = "code-yeongyu/go-claude-code-comment-checker"
interface PlatformInfo {
os: string
arch: string
ext: "tar.gz" | "zip"
}
const PLATFORM_MAP: Record<string, PlatformInfo> = {
"darwin-arm64": { os: "darwin", arch: "arm64", ext: "tar.gz" },
"darwin-x64": { os: "darwin", arch: "amd64", ext: "tar.gz" },
"linux-arm64": { os: "linux", arch: "arm64", ext: "tar.gz" },
"linux-x64": { os: "linux", arch: "amd64", ext: "tar.gz" },
"win32-x64": { os: "windows", arch: "amd64", ext: "zip" },
}
/**
* Get the cache directory for oh-my-opencode binaries.
* Follows XDG Base Directory Specification.
*/
export function getCacheDir(): string {
const xdgCache = process.env.XDG_CACHE_HOME
const base = xdgCache || join(homedir(), ".cache")
return join(base, "oh-my-opencode", "bin")
}
/**
* Get the binary name based on platform.
*/
export function getBinaryName(): string {
return process.platform === "win32" ? "comment-checker.exe" : "comment-checker"
}
/**
* Get the cached binary path if it exists.
*/
export function getCachedBinaryPath(): string | null {
const binaryPath = join(getCacheDir(), getBinaryName())
return existsSync(binaryPath) ? binaryPath : null
}
/**
* Get the version from the installed @code-yeongyu/comment-checker package.
*/
function getPackageVersion(): string {
try {
const require = createRequire(import.meta.url)
const pkg = require("@code-yeongyu/comment-checker/package.json")
return pkg.version
} catch {
// Fallback to hardcoded version if package not found
return "0.4.1"
}
}
/**
* Extract tar.gz archive using system tar command.
*/
async function extractTarGz(archivePath: string, destDir: string): Promise<void> {
debugLog("Extracting tar.gz:", archivePath, "to", destDir)
const proc = spawn(["tar", "-xzf", archivePath, "-C", destDir], {
stdout: "pipe",
stderr: "pipe",
})
const exitCode = await proc.exited
if (exitCode !== 0) {
const stderr = await new Response(proc.stderr).text()
throw new Error(`tar extraction failed (exit ${exitCode}): ${stderr}`)
}
}
/**
* Extract zip archive using system commands.
*/
async function extractZip(archivePath: string, destDir: string): Promise<void> {
debugLog("Extracting zip:", archivePath, "to", destDir)
const proc = process.platform === "win32"
? spawn(["powershell", "-command", `Expand-Archive -Path '${archivePath}' -DestinationPath '${destDir}' -Force`], {
stdout: "pipe",
stderr: "pipe",
})
: spawn(["unzip", "-o", archivePath, "-d", destDir], {
stdout: "pipe",
stderr: "pipe",
})
const exitCode = await proc.exited
if (exitCode !== 0) {
const stderr = await new Response(proc.stderr).text()
throw new Error(`zip extraction failed (exit ${exitCode}): ${stderr}`)
}
}
/**
* Download the comment-checker binary from GitHub Releases.
* Returns the path to the downloaded binary, or null on failure.
*/
export async function downloadCommentChecker(): Promise<string | null> {
const platformKey = `${process.platform}-${process.arch}`
const platformInfo = PLATFORM_MAP[platformKey]
if (!platformInfo) {
debugLog(`Unsupported platform: ${platformKey}`)
return null
}
const cacheDir = getCacheDir()
const binaryName = getBinaryName()
const binaryPath = join(cacheDir, binaryName)
// Already exists in cache
if (existsSync(binaryPath)) {
debugLog("Binary already cached at:", binaryPath)
return binaryPath
}
const version = getPackageVersion()
const { os, arch, ext } = platformInfo
const assetName = `comment-checker_v${version}_${os}_${arch}.${ext}`
const downloadUrl = `https://github.com/${REPO}/releases/download/v${version}/${assetName}`
debugLog(`Downloading from: ${downloadUrl}`)
console.log(`[oh-my-opencode] Downloading comment-checker binary...`)
try {
// Ensure cache directory exists
if (!existsSync(cacheDir)) {
mkdirSync(cacheDir, { recursive: true })
}
// Download with fetch() - Bun handles redirects automatically
const response = await fetch(downloadUrl, { redirect: "follow" })
if (!response.ok) {
throw new Error(`HTTP ${response.status}: ${response.statusText}`)
}
const archivePath = join(cacheDir, assetName)
const arrayBuffer = await response.arrayBuffer()
await Bun.write(archivePath, arrayBuffer)
debugLog(`Downloaded archive to: ${archivePath}`)
// Extract based on file type
if (ext === "tar.gz") {
await extractTarGz(archivePath, cacheDir)
} else {
await extractZip(archivePath, cacheDir)
}
// Clean up archive
if (existsSync(archivePath)) {
unlinkSync(archivePath)
}
// Set execute permission on Unix
if (process.platform !== "win32" && existsSync(binaryPath)) {
chmodSync(binaryPath, 0o755)
}
debugLog(`Successfully downloaded binary to: ${binaryPath}`)
console.log(`[oh-my-opencode] comment-checker binary ready.`)
return binaryPath
} catch (err) {
debugLog(`Failed to download: ${err}`)
console.error(`[oh-my-opencode] Failed to download comment-checker: ${err instanceof Error ? err.message : err}`)
console.error(`[oh-my-opencode] Comment checking disabled.`)
return null
}
}
/**
* Ensure the comment-checker binary is available.
* First checks cache, then downloads if needed.
* Returns the binary path or null if unavailable.
*/
export async function ensureCommentCheckerBinary(): Promise<string | null> {
// Check cache first
const cachedPath = getCachedBinaryPath()
if (cachedPath) {
debugLog("Using cached binary:", cachedPath)
return cachedPath
}
// Download if not cached
return downloadCommentChecker()
}

View File

@@ -1,11 +1,24 @@
import type { PendingCall, FileComments } from "./types"
import { detectComments, isSupportedFile } from "./detector"
import { applyFilters } from "./filters"
import { formatHookMessage } from "./output"
import type { PendingCall } from "./types"
import { runCommentChecker, getCommentCheckerPath, startBackgroundInit, type HookInput } from "./cli"
import * as fs from "fs"
import { existsSync } from "fs"
const DEBUG = process.env.COMMENT_CHECKER_DEBUG === "1"
const DEBUG_FILE = "/tmp/comment-checker-debug.log"
function debugLog(...args: unknown[]) {
if (DEBUG) {
const msg = `[${new Date().toISOString()}] [comment-checker:hook] ${args.map(a => typeof a === 'object' ? JSON.stringify(a, null, 2) : String(a)).join(' ')}\n`
fs.appendFileSync(DEBUG_FILE, msg)
}
}
const pendingCalls = new Map<string, PendingCall>()
const PENDING_CALL_TTL = 60_000
let cliPathPromise: Promise<string | null> | null = null
function cleanupOldPendingCalls(): void {
const now = Date.now()
for (const [callID, call] of pendingCalls) {
@@ -18,30 +31,50 @@ function cleanupOldPendingCalls(): void {
setInterval(cleanupOldPendingCalls, 10_000)
export function createCommentCheckerHooks() {
debugLog("createCommentCheckerHooks called")
// Start background CLI initialization (may trigger lazy download)
startBackgroundInit()
cliPathPromise = getCommentCheckerPath()
cliPathPromise.then(path => {
debugLog("CLI path resolved:", path || "disabled (no binary)")
}).catch(err => {
debugLog("CLI path resolution error:", err)
})
return {
"tool.execute.before": async (
input: { tool: string; sessionID: string; callID: string },
output: { args: Record<string, unknown> }
): Promise<void> => {
debugLog("tool.execute.before:", { tool: input.tool, callID: input.callID, args: output.args })
const toolLower = input.tool.toLowerCase()
if (toolLower !== "write" && toolLower !== "edit" && toolLower !== "multiedit") {
debugLog("skipping non-write/edit tool:", toolLower)
return
}
const filePath = (output.args.filePath ?? output.args.file_path) as string | undefined
const filePath = (output.args.filePath ?? output.args.file_path ?? output.args.path) as string | undefined
const content = output.args.content as string | undefined
const oldString = output.args.oldString ?? output.args.old_string as string | undefined
const newString = output.args.newString ?? output.args.new_string as string | undefined
const edits = output.args.edits as Array<{ old_string: string; new_string: string }> | undefined
debugLog("extracted filePath:", filePath)
if (!filePath) {
debugLog("no filePath found")
return
}
if (!isSupportedFile(filePath)) {
return
}
debugLog("registering pendingCall:", { callID: input.callID, filePath, tool: toolLower })
pendingCalls.set(input.callID, {
filePath,
content,
oldString: oldString as string | undefined,
newString: newString as string | undefined,
edits,
tool: toolLower as "write" | "edit" | "multiedit",
sessionID: input.sessionID,
timestamp: Date.now(),
@@ -52,50 +85,79 @@ export function createCommentCheckerHooks() {
input: { tool: string; sessionID: string; callID: string },
output: { title: string; output: string; metadata: unknown }
): Promise<void> => {
debugLog("tool.execute.after:", { tool: input.tool, callID: input.callID })
const pendingCall = pendingCalls.get(input.callID)
if (!pendingCall) {
debugLog("no pendingCall found for:", input.callID)
return
}
pendingCalls.delete(input.callID)
debugLog("processing pendingCall:", pendingCall)
if (output.output.toLowerCase().includes("error")) {
// Only skip if the output indicates a tool execution failure
const outputLower = output.output.toLowerCase()
const isToolFailure =
outputLower.includes("error:") ||
outputLower.includes("failed to") ||
outputLower.includes("could not") ||
outputLower.startsWith("error")
if (isToolFailure) {
debugLog("skipping due to tool failure in output")
return
}
try {
let content: string
if (pendingCall.content) {
content = pendingCall.content
} else {
const file = Bun.file(pendingCall.filePath)
content = await file.text()
}
const rawComments = await detectComments(pendingCall.filePath, content)
const filteredComments = applyFilters(rawComments)
if (filteredComments.length === 0) {
// Wait for CLI path resolution
const cliPath = await cliPathPromise
if (!cliPath || !existsSync(cliPath)) {
// CLI not available - silently skip comment checking
debugLog("CLI not available, skipping comment check")
return
}
const fileComments: FileComments[] = [
{
filePath: pendingCall.filePath,
comments: filteredComments,
},
]
const message = formatHookMessage(fileComments)
output.output += `\n\n${message}`
} catch {}
// CLI mode only
debugLog("using CLI:", cliPath)
await processWithCli(input, pendingCall, output, cliPath)
} catch (err) {
debugLog("tool.execute.after failed:", err)
}
},
}
}
export * from "./types"
export * from "./constants"
export * from "./detector"
export * from "./filters"
export * from "./output"
async function processWithCli(
input: { tool: string; sessionID: string; callID: string },
pendingCall: PendingCall,
output: { output: string },
cliPath: string
): Promise<void> {
debugLog("using CLI mode with path:", cliPath)
const hookInput: HookInput = {
session_id: pendingCall.sessionID,
tool_name: pendingCall.tool.charAt(0).toUpperCase() + pendingCall.tool.slice(1),
transcript_path: "",
cwd: process.cwd(),
hook_event_name: "PostToolUse",
tool_input: {
file_path: pendingCall.filePath,
content: pendingCall.content,
old_string: pendingCall.oldString,
new_string: pendingCall.newString,
edits: pendingCall.edits,
},
}
const result = await runCommentChecker(hookInput, cliPath)
if (result.hasComments && result.message) {
debugLog("CLI detected comments, appending message")
output.output += `\n\n${result.message}`
} else {
debugLog("CLI: no comments detected")
}
}

View File

@@ -9,15 +9,12 @@ export interface CommentInfo {
metadata?: Record<string, string>
}
export interface LanguageConfig {
extensions: string[]
commentQuery: string
docstringQuery?: string
}
export interface PendingCall {
filePath: string
content?: string
oldString?: string
newString?: string
edits?: Array<{ old_string: string; new_string: string }>
tool: "write" | "edit" | "multiedit"
sessionID: string
timestamp: number

View File

@@ -0,0 +1,9 @@
import { join } from "node:path";
import { xdgData } from "xdg-basedir";
export const OPENCODE_STORAGE = join(xdgData ?? "", "opencode", "storage");
export const AGENTS_INJECTOR_STORAGE = join(
OPENCODE_STORAGE,
"directory-agents",
);
export const AGENTS_FILENAME = "AGENTS.md";

View File

@@ -0,0 +1,126 @@
import type { PluginInput } from "@opencode-ai/plugin";
import { existsSync, readFileSync } from "node:fs";
import { dirname, join, resolve } from "node:path";
import {
loadInjectedPaths,
saveInjectedPaths,
clearInjectedPaths,
} from "./storage";
import { AGENTS_FILENAME } from "./constants";
interface ToolExecuteInput {
tool: string;
sessionID: string;
callID: string;
}
interface ToolExecuteOutput {
title: string;
output: string;
metadata: unknown;
}
interface EventInput {
event: {
type: string;
properties?: unknown;
};
}
export function createDirectoryAgentsInjectorHook(ctx: PluginInput) {
const sessionCaches = new Map<string, Set<string>>();
function getSessionCache(sessionID: string): Set<string> {
if (!sessionCaches.has(sessionID)) {
sessionCaches.set(sessionID, loadInjectedPaths(sessionID));
}
return sessionCaches.get(sessionID)!;
}
function resolveFilePath(title: string): string | null {
if (!title) return null;
if (title.startsWith("/")) return title;
return resolve(ctx.directory, title);
}
function findAgentsMdUp(startDir: string): string[] {
const found: string[] = [];
let current = startDir;
while (true) {
const agentsPath = join(current, AGENTS_FILENAME);
if (existsSync(agentsPath)) {
found.push(agentsPath);
}
if (current === ctx.directory) break;
const parent = dirname(current);
if (parent === current) break;
if (!parent.startsWith(ctx.directory)) break;
current = parent;
}
return found.reverse();
}
const toolExecuteAfter = async (
input: ToolExecuteInput,
output: ToolExecuteOutput,
) => {
if (input.tool.toLowerCase() !== "read") return;
const filePath = resolveFilePath(output.title);
if (!filePath) return;
const dir = dirname(filePath);
const cache = getSessionCache(input.sessionID);
const agentsPaths = findAgentsMdUp(dir);
const toInject: { path: string; content: string }[] = [];
for (const agentsPath of agentsPaths) {
const agentsDir = dirname(agentsPath);
if (cache.has(agentsDir)) continue;
try {
const content = readFileSync(agentsPath, "utf-8");
toInject.push({ path: agentsPath, content });
cache.add(agentsDir);
} catch {}
}
if (toInject.length === 0) return;
for (const { path, content } of toInject) {
output.output += `\n\n[Directory Context: ${path}]\n${content}`;
}
saveInjectedPaths(input.sessionID, cache);
};
const eventHandler = async ({ event }: EventInput) => {
const props = event.properties as Record<string, unknown> | undefined;
if (event.type === "session.deleted") {
const sessionInfo = props?.info as { id?: string } | undefined;
if (sessionInfo?.id) {
sessionCaches.delete(sessionInfo.id);
clearInjectedPaths(sessionInfo.id);
}
}
if (event.type === "session.compacted") {
const sessionID = (props?.sessionID ??
(props?.info as { id?: string } | undefined)?.id) as string | undefined;
if (sessionID) {
sessionCaches.delete(sessionID);
clearInjectedPaths(sessionID);
}
}
};
return {
"tool.execute.after": toolExecuteAfter,
event: eventHandler,
};
}

View File

@@ -0,0 +1,48 @@
import {
existsSync,
mkdirSync,
readFileSync,
writeFileSync,
unlinkSync,
} from "node:fs";
import { join } from "node:path";
import { AGENTS_INJECTOR_STORAGE } from "./constants";
import type { InjectedPathsData } from "./types";
function getStoragePath(sessionID: string): string {
return join(AGENTS_INJECTOR_STORAGE, `${sessionID}.json`);
}
export function loadInjectedPaths(sessionID: string): Set<string> {
const filePath = getStoragePath(sessionID);
if (!existsSync(filePath)) return new Set();
try {
const content = readFileSync(filePath, "utf-8");
const data: InjectedPathsData = JSON.parse(content);
return new Set(data.injectedPaths);
} catch {
return new Set();
}
}
export function saveInjectedPaths(sessionID: string, paths: Set<string>): void {
if (!existsSync(AGENTS_INJECTOR_STORAGE)) {
mkdirSync(AGENTS_INJECTOR_STORAGE, { recursive: true });
}
const data: InjectedPathsData = {
sessionID,
injectedPaths: [...paths],
updatedAt: Date.now(),
};
writeFileSync(getStoragePath(sessionID), JSON.stringify(data, null, 2));
}
export function clearInjectedPaths(sessionID: string): void {
const filePath = getStoragePath(sessionID);
if (existsSync(filePath)) {
unlinkSync(filePath);
}
}

View File

@@ -0,0 +1,5 @@
export interface InjectedPathsData {
sessionID: string;
injectedPaths: string[];
updatedAt: number;
}

View File

@@ -0,0 +1,27 @@
import type { PluginInput } from "@opencode-ai/plugin"
const EMPTY_RESPONSE_WARNING = `[Task Empty Response Warning]
Task invocation completed but returned no response. This indicates the agent either:
- Failed to execute properly
- Did not terminate correctly
- Returned an empty result
Note: The call has already completed - you are NOT waiting for a response. Proceed accordingly.`
export function createEmptyTaskResponseDetectorHook(_ctx: PluginInput) {
return {
"tool.execute.after": async (
input: { tool: string; sessionID: string; callID: string },
output: { title: string; output: string; metadata: unknown }
) => {
if (input.tool !== "Task") return
const responseText = output.output?.trim() ?? ""
if (responseText === "") {
output.output = EMPTY_RESPONSE_WARNING
}
},
}
}

View File

@@ -1,18 +0,0 @@
import type { PluginInput } from "@opencode-ai/plugin"
const BLOCKED_MESSAGE =
"Error: [BLOCKED] grep has no timeout and can freeze the system. " +
"It is permanently disabled. Use 'safe_grep' instead."
export function createGrepBlocker(_ctx: PluginInput) {
return {
"tool.execute.before": async (
input: { tool: string; sessionID: string; callID: string },
_output: { args: unknown }
) => {
if (input.tool === "grep") {
throw new Error(BLOCKED_MESSAGE)
}
},
}
}

View File

@@ -0,0 +1,131 @@
import type { PluginInput } from "@opencode-ai/plugin"
const ANTHROPIC_ACTUAL_LIMIT = 200_000
const CHARS_PER_TOKEN_ESTIMATE = 4
const TARGET_MAX_TOKENS = 50_000
interface AssistantMessageInfo {
role: "assistant"
tokens: {
input: number
output: number
reasoning: number
cache: { read: number; write: number }
}
}
interface MessageWrapper {
info: { role: string } & Partial<AssistantMessageInfo>
}
function estimateTokens(text: string): number {
return Math.ceil(text.length / CHARS_PER_TOKEN_ESTIMATE)
}
function truncateToTokenLimit(output: string, maxTokens: number): { result: string; truncated: boolean } {
const currentTokens = estimateTokens(output)
if (currentTokens <= maxTokens) {
return { result: output, truncated: false }
}
const lines = output.split("\n")
if (lines.length <= 3) {
const maxChars = maxTokens * CHARS_PER_TOKEN_ESTIMATE
return {
result: output.slice(0, maxChars) + "\n\n[Output truncated due to context window limit]",
truncated: true,
}
}
const headerLines = lines.slice(0, 3)
const contentLines = lines.slice(3)
const headerText = headerLines.join("\n")
const headerTokens = estimateTokens(headerText)
const availableTokens = maxTokens - headerTokens - 50
if (availableTokens <= 0) {
return {
result: headerText + "\n\n[Content truncated due to context window limit]",
truncated: true,
}
}
let resultLines: string[] = []
let currentTokenCount = 0
for (const line of contentLines) {
const lineTokens = estimateTokens(line + "\n")
if (currentTokenCount + lineTokens > availableTokens) {
break
}
resultLines.push(line)
currentTokenCount += lineTokens
}
const truncatedContent = [...headerLines, ...resultLines].join("\n")
const removedCount = contentLines.length - resultLines.length
return {
result: truncatedContent + `\n\n[${removedCount} more lines truncated due to context window limit]`,
truncated: true,
}
}
export function createGrepOutputTruncatorHook(ctx: PluginInput) {
const GREP_TOOLS = ["safe_grep", "Grep"]
const toolExecuteAfter = async (
input: { tool: string; sessionID: string; callID: string },
output: { title: string; output: string; metadata: unknown }
) => {
if (!GREP_TOOLS.includes(input.tool)) return
const { sessionID } = input
try {
const response = await ctx.client.session.messages({
path: { id: sessionID },
})
const messages = (response.data ?? response) as MessageWrapper[]
const assistantMessages = messages
.filter((m) => m.info.role === "assistant")
.map((m) => m.info as AssistantMessageInfo)
if (assistantMessages.length === 0) return
const totalInputTokens = assistantMessages.reduce((sum, m) => {
const inputTokens = m.tokens?.input ?? 0
const cacheReadTokens = m.tokens?.cache?.read ?? 0
return sum + inputTokens + cacheReadTokens
}, 0)
const remainingTokens = ANTHROPIC_ACTUAL_LIMIT - totalInputTokens
const maxOutputTokens = Math.min(
remainingTokens * 0.5,
TARGET_MAX_TOKENS
)
if (maxOutputTokens <= 0) {
output.output = "[Output suppressed - context window exhausted]"
return
}
const { result, truncated } = truncateToTokenLimit(output.output, maxOutputTokens)
if (truncated) {
output.output = result
}
} catch {
// Graceful degradation
}
}
return {
"tool.execute.after": toolExecuteAfter,
}
}

View File

@@ -1,5 +1,11 @@
export * from "./todo-continuation-enforcer"
export * from "./context-window-monitor"
export * from "./session-notification"
export * from "./session-recovery"
export * from "./comment-checker"
export { createTodoContinuationEnforcer } from "./todo-continuation-enforcer";
export { createContextWindowMonitorHook } from "./context-window-monitor";
export { createSessionNotification } from "./session-notification";
export { createSessionRecoveryHook } from "./session-recovery";
export { createCommentCheckerHooks } from "./comment-checker";
export { createGrepOutputTruncatorHook } from "./grep-output-truncator";
export { createDirectoryAgentsInjectorHook } from "./directory-agents-injector";
export { createEmptyTaskResponseDetectorHook } from "./empty-task-response-detector";
export { createAnthropicAutoCompactHook } from "./anthropic-auto-compact";
export { createThinkModeHook } from "./think-mode";
export { createClaudeCodeHooksHook } from "./claude-code-hooks";

View File

@@ -0,0 +1,10 @@
import { join } from "node:path"
import { xdgData } from "xdg-basedir"
export const OPENCODE_STORAGE = join(xdgData ?? "", "opencode", "storage")
export const MESSAGE_STORAGE = join(OPENCODE_STORAGE, "message")
export const PART_STORAGE = join(OPENCODE_STORAGE, "part")
export const THINKING_TYPES = new Set(["thinking", "redacted_thinking", "reasoning"])
export const META_TYPES = new Set(["step-start", "step-finish"])
export const CONTENT_TYPES = new Set(["text", "tool", "tool_use", "tool_result"])

View File

@@ -1,23 +1,23 @@
/**
* Session Recovery - Message State Error Recovery
*
* Handles THREE specific scenarios:
* 1. tool_use block exists without tool_result
* - Recovery: inject tool_result with "cancelled" content
*
* 2. Thinking block order violation (first block must be thinking)
* - Recovery: prepend empty thinking block
*
* 3. Thinking disabled but message contains thinking blocks
* - Recovery: strip thinking/redacted_thinking blocks
*/
import type { PluginInput } from "@opencode-ai/plugin"
import type { createOpencodeClient } from "@opencode-ai/sdk"
import {
findEmptyMessages,
findMessagesWithOrphanThinking,
findMessagesWithThinkingBlocks,
injectTextPart,
prependThinkingPart,
stripThinkingParts,
} from "./storage"
import type { MessageData } from "./types"
type Client = ReturnType<typeof createOpencodeClient>
type RecoveryErrorType = "tool_result_missing" | "thinking_block_order" | "thinking_disabled_violation" | null
type RecoveryErrorType =
| "tool_result_missing"
| "thinking_block_order"
| "thinking_disabled_violation"
| "empty_content_message"
| null
interface MessageInfo {
id?: string
@@ -34,11 +34,6 @@ interface ToolUsePart {
input: Record<string, unknown>
}
interface ThinkingPart {
type: "thinking"
thinking: string
}
interface MessagePart {
type: string
id?: string
@@ -48,16 +43,15 @@ interface MessagePart {
input?: Record<string, unknown>
}
interface MessageData {
info?: MessageInfo
parts?: MessagePart[]
}
function getErrorMessage(error: unknown): string {
if (!error) return ""
if (typeof error === "string") return error.toLowerCase()
const errorObj = error as { data?: { message?: string }; message?: string }
return (errorObj.data?.message || errorObj.message || "").toLowerCase()
const errorObj = error as {
data?: { message?: string }
message?: string
error?: { message?: string }
}
return (errorObj.data?.message || errorObj.error?.message || errorObj.message || "").toLowerCase()
}
function detectErrorType(error: unknown): RecoveryErrorType {
@@ -67,7 +61,10 @@ function detectErrorType(error: unknown): RecoveryErrorType {
return "tool_result_missing"
}
if (message.includes("thinking") && message.includes("first block")) {
if (
message.includes("thinking") &&
(message.includes("first block") || message.includes("must start with") || message.includes("preceeding"))
) {
return "thinking_block_order"
}
@@ -75,6 +72,10 @@ function detectErrorType(error: unknown): RecoveryErrorType {
return "thinking_disabled_violation"
}
if (message.includes("non-empty content") || message.includes("must have non-empty content")) {
return "empty_content_message"
}
return null
}
@@ -103,7 +104,7 @@ async function recoverToolResultMissing(
try {
await client.session.prompt({
path: { id: sessionID },
// @ts-expect-error - SDK types may not include tool_result parts, but runtime accepts it
// @ts-expect-error - SDK types may not include tool_result parts
body: { parts: toolResultParts },
})
@@ -114,153 +115,77 @@ async function recoverToolResultMissing(
}
async function recoverThinkingBlockOrder(
client: Client,
_client: Client,
sessionID: string,
failedAssistantMsg: MessageData,
directory: string
_failedAssistantMsg: MessageData,
_directory: string
): Promise<boolean> {
const messageID = failedAssistantMsg.info?.id
if (!messageID) {
const orphanMessages = findMessagesWithOrphanThinking(sessionID)
if (orphanMessages.length === 0) {
return false
}
const existingParts = failedAssistantMsg.parts || []
const patchedParts: MessagePart[] = [{ type: "thinking", thinking: "" } as ThinkingPart, ...existingParts]
try {
// @ts-expect-error - Experimental API
await client.message?.update?.({
path: { id: messageID },
body: { parts: patchedParts },
})
return true
} catch {
// message.update not available
}
try {
// @ts-expect-error - Experimental API
await client.session.patch?.({
path: { id: sessionID },
body: {
messageID,
parts: patchedParts,
},
})
return true
} catch {
// session.patch not available
}
return await fallbackRevertStrategy(client, sessionID, failedAssistantMsg, directory)
}
async function recoverThinkingDisabledViolation(
client: Client,
sessionID: string,
failedAssistantMsg: MessageData
): Promise<boolean> {
const messageID = failedAssistantMsg.info?.id
if (!messageID) {
return false
}
const existingParts = failedAssistantMsg.parts || []
const strippedParts = existingParts.filter((p) => p.type !== "thinking" && p.type !== "redacted_thinking")
if (strippedParts.length === 0) {
return false
}
try {
// @ts-expect-error - Experimental API
await client.message?.update?.({
path: { id: messageID },
body: { parts: strippedParts },
})
return true
} catch {
// message.update not available
}
try {
// @ts-expect-error - Experimental API
await client.session.patch?.({
path: { id: sessionID },
body: {
messageID,
parts: strippedParts,
},
})
return true
} catch {
// session.patch not available
}
return false
}
async function fallbackRevertStrategy(
client: Client,
sessionID: string,
failedAssistantMsg: MessageData,
directory: string
): Promise<boolean> {
const parentMsgID = failedAssistantMsg.info?.parentID
const messagesResp = await client.session.messages({
path: { id: sessionID },
query: { directory },
})
const msgs = (messagesResp as { data?: MessageData[] }).data
if (!msgs || msgs.length === 0) {
return false
}
let targetUserMsg: MessageData | null = null
if (parentMsgID) {
targetUserMsg = msgs.find((m) => m.info?.id === parentMsgID) ?? null
}
if (!targetUserMsg) {
for (let i = msgs.length - 1; i >= 0; i--) {
if (msgs[i].info?.role === "user") {
targetUserMsg = msgs[i]
break
}
let anySuccess = false
for (const messageID of orphanMessages) {
if (prependThinkingPart(sessionID, messageID)) {
anySuccess = true
}
}
if (!targetUserMsg?.parts?.length) {
return false
}
await client.session.revert({
path: { id: sessionID },
body: { messageID: targetUserMsg.info?.id ?? "" },
query: { directory },
})
const textParts = targetUserMsg.parts
.filter((p) => p.type === "text" && p.text)
.map((p) => ({ type: "text" as const, text: p.text ?? "" }))
if (textParts.length === 0) {
return false
}
await client.session.prompt({
path: { id: sessionID },
body: { parts: textParts },
query: { directory },
})
return true
return anySuccess
}
async function recoverThinkingDisabledViolation(
_client: Client,
sessionID: string,
_failedAssistantMsg: MessageData
): Promise<boolean> {
const messagesWithThinking = findMessagesWithThinkingBlocks(sessionID)
if (messagesWithThinking.length === 0) {
return false
}
let anySuccess = false
for (const messageID of messagesWithThinking) {
if (stripThinkingParts(messageID)) {
anySuccess = true
}
}
return anySuccess
}
async function recoverEmptyContentMessage(
_client: Client,
sessionID: string,
failedAssistantMsg: MessageData,
_directory: string
): Promise<boolean> {
const emptyMessageIDs = findEmptyMessages(sessionID)
if (emptyMessageIDs.length === 0) {
const fallbackID = failedAssistantMsg.info?.id
if (!fallbackID) return false
return injectTextPart(sessionID, fallbackID, "(interrupted)")
}
let anySuccess = false
for (const messageID of emptyMessageIDs) {
if (injectTextPart(sessionID, messageID, "(interrupted)")) {
anySuccess = true
}
}
return anySuccess
}
// NOTE: fallbackRevertStrategy was removed (2025-12-08)
// Reason: Function was defined but never called - no error recovery paths used it.
// All error types have dedicated recovery functions (recoverToolResultMissing,
// recoverThinkingBlockOrder, recoverThinkingDisabledViolation, recoverEmptyContentMessage).
export function createSessionRecoveryHook(ctx: PluginInput) {
const processingErrors = new Set<string>()
let onAbortCallback: ((sessionID: string) => void) | null = null
@@ -308,20 +233,20 @@ export function createSessionRecoveryHook(ctx: PluginInput) {
tool_result_missing: "Tool Crash Recovery",
thinking_block_order: "Thinking Block Recovery",
thinking_disabled_violation: "Thinking Strip Recovery",
empty_content_message: "Empty Message Recovery",
}
const toastMessages: Record<RecoveryErrorType & string, string> = {
tool_result_missing: "Injecting cancelled tool results...",
thinking_block_order: "Fixing message structure...",
thinking_disabled_violation: "Stripping thinking blocks...",
empty_content_message: "Fixing empty message...",
}
const toastTitle = toastTitles[errorType]
const toastMessage = toastMessages[errorType]
await ctx.client.tui
.showToast({
body: {
title: toastTitle,
message: toastMessage,
title: toastTitles[errorType],
message: toastMessages[errorType],
variant: "warning",
duration: 3000,
},
@@ -336,6 +261,8 @@ export function createSessionRecoveryHook(ctx: PluginInput) {
success = await recoverThinkingBlockOrder(ctx.client, sessionID, failedMsg, ctx.directory)
} else if (errorType === "thinking_disabled_violation") {
success = await recoverThinkingDisabledViolation(ctx.client, sessionID, failedMsg)
} else if (errorType === "empty_content_message") {
success = await recoverEmptyContentMessage(ctx.client, sessionID, failedMsg, ctx.directory)
}
return success

View File

@@ -0,0 +1,235 @@
import { existsSync, mkdirSync, readdirSync, readFileSync, unlinkSync, writeFileSync } from "node:fs"
import { join } from "node:path"
import { MESSAGE_STORAGE, PART_STORAGE, THINKING_TYPES, META_TYPES } from "./constants"
import type { StoredMessageMeta, StoredPart, StoredTextPart } from "./types"
export function generatePartId(): string {
const timestamp = Date.now().toString(16)
const random = Math.random().toString(36).substring(2, 10)
return `prt_${timestamp}${random}`
}
export function getMessageDir(sessionID: string): string {
if (!existsSync(MESSAGE_STORAGE)) return ""
const directPath = join(MESSAGE_STORAGE, sessionID)
if (existsSync(directPath)) {
return directPath
}
for (const dir of readdirSync(MESSAGE_STORAGE)) {
const sessionPath = join(MESSAGE_STORAGE, dir, sessionID)
if (existsSync(sessionPath)) {
return sessionPath
}
}
return ""
}
export function readMessages(sessionID: string): StoredMessageMeta[] {
const messageDir = getMessageDir(sessionID)
if (!messageDir || !existsSync(messageDir)) return []
const messages: StoredMessageMeta[] = []
for (const file of readdirSync(messageDir)) {
if (!file.endsWith(".json")) continue
try {
const content = readFileSync(join(messageDir, file), "utf-8")
messages.push(JSON.parse(content))
} catch {
continue
}
}
return messages.sort((a, b) => a.id.localeCompare(b.id))
}
export function readParts(messageID: string): StoredPart[] {
const partDir = join(PART_STORAGE, messageID)
if (!existsSync(partDir)) return []
const parts: StoredPart[] = []
for (const file of readdirSync(partDir)) {
if (!file.endsWith(".json")) continue
try {
const content = readFileSync(join(partDir, file), "utf-8")
parts.push(JSON.parse(content))
} catch {
continue
}
}
return parts
}
export function hasContent(part: StoredPart): boolean {
if (THINKING_TYPES.has(part.type)) return false
if (META_TYPES.has(part.type)) return false
if (part.type === "text") {
const textPart = part as StoredTextPart
return !!(textPart.text?.trim())
}
if (part.type === "tool" || part.type === "tool_use") {
return true
}
if (part.type === "tool_result") {
return true
}
return false
}
export function messageHasContent(messageID: string): boolean {
const parts = readParts(messageID)
return parts.some(hasContent)
}
export function injectTextPart(sessionID: string, messageID: string, text: string): boolean {
const partDir = join(PART_STORAGE, messageID)
if (!existsSync(partDir)) {
mkdirSync(partDir, { recursive: true })
}
const partId = generatePartId()
const part: StoredTextPart = {
id: partId,
sessionID,
messageID,
type: "text",
text,
synthetic: true,
}
try {
writeFileSync(join(partDir, `${partId}.json`), JSON.stringify(part, null, 2))
return true
} catch {
return false
}
}
export function findEmptyMessages(sessionID: string): string[] {
const messages = readMessages(sessionID)
const emptyIds: string[] = []
for (let i = 0; i < messages.length; i++) {
const msg = messages[i]
if (msg.role !== "assistant") continue
const isLastMessage = i === messages.length - 1
if (isLastMessage) continue
if (!messageHasContent(msg.id)) {
emptyIds.push(msg.id)
}
}
return emptyIds
}
export function findFirstEmptyMessage(sessionID: string): string | null {
const emptyIds = findEmptyMessages(sessionID)
return emptyIds.length > 0 ? emptyIds[0] : null
}
export function findMessagesWithThinkingBlocks(sessionID: string): string[] {
const messages = readMessages(sessionID)
const result: string[] = []
for (let i = 0; i < messages.length; i++) {
const msg = messages[i]
if (msg.role !== "assistant") continue
const isLastMessage = i === messages.length - 1
if (isLastMessage) continue
const parts = readParts(msg.id)
const hasThinking = parts.some((p) => THINKING_TYPES.has(p.type))
if (hasThinking) {
result.push(msg.id)
}
}
return result
}
export function findMessagesWithOrphanThinking(sessionID: string): string[] {
const messages = readMessages(sessionID)
const result: string[] = []
for (let i = 0; i < messages.length; i++) {
const msg = messages[i]
if (msg.role !== "assistant") continue
const isLastMessage = i === messages.length - 1
if (isLastMessage) continue
const parts = readParts(msg.id)
if (parts.length === 0) continue
const sortedParts = [...parts].sort((a, b) => a.id.localeCompare(b.id))
const firstPart = sortedParts[0]
const hasThinking = parts.some((p) => THINKING_TYPES.has(p.type))
const firstIsThinking = THINKING_TYPES.has(firstPart.type)
if (hasThinking && !firstIsThinking) {
result.push(msg.id)
}
}
return result
}
export function prependThinkingPart(sessionID: string, messageID: string): boolean {
const partDir = join(PART_STORAGE, messageID)
if (!existsSync(partDir)) {
mkdirSync(partDir, { recursive: true })
}
const partId = `prt_0000000000_thinking`
const part = {
id: partId,
sessionID,
messageID,
type: "thinking",
thinking: "",
synthetic: true,
}
try {
writeFileSync(join(partDir, `${partId}.json`), JSON.stringify(part, null, 2))
return true
} catch {
return false
}
}
export function stripThinkingParts(messageID: string): boolean {
const partDir = join(PART_STORAGE, messageID)
if (!existsSync(partDir)) return false
let anyRemoved = false
for (const file of readdirSync(partDir)) {
if (!file.endsWith(".json")) continue
try {
const filePath = join(partDir, file)
const content = readFileSync(filePath, "utf-8")
const part = JSON.parse(content) as StoredPart
if (THINKING_TYPES.has(part.type)) {
unlinkSync(filePath)
anyRemoved = true
}
} catch {
continue
}
}
return anyRemoved
}

View File

@@ -0,0 +1,82 @@
export type ThinkingPartType = "thinking" | "redacted_thinking" | "reasoning"
export type MetaPartType = "step-start" | "step-finish"
export type ContentPartType = "text" | "tool" | "tool_use" | "tool_result"
export interface StoredMessageMeta {
id: string
sessionID: string
role: "user" | "assistant"
parentID?: string
time?: {
created: number
completed?: number
}
error?: unknown
}
export interface StoredTextPart {
id: string
sessionID: string
messageID: string
type: "text"
text: string
synthetic?: boolean
ignored?: boolean
}
export interface StoredToolPart {
id: string
sessionID: string
messageID: string
type: "tool"
callID: string
tool: string
state: {
status: "pending" | "running" | "completed" | "error"
input: Record<string, unknown>
output?: string
error?: string
}
}
export interface StoredReasoningPart {
id: string
sessionID: string
messageID: string
type: "reasoning"
text: string
}
export interface StoredStepPart {
id: string
sessionID: string
messageID: string
type: "step-start" | "step-finish"
}
export type StoredPart = StoredTextPart | StoredToolPart | StoredReasoningPart | StoredStepPart | {
id: string
sessionID: string
messageID: string
type: string
[key: string]: unknown
}
export interface MessageData {
info?: {
id?: string
role?: string
sessionID?: string
parentID?: string
error?: unknown
}
parts?: Array<{
type: string
id?: string
text?: string
thinking?: string
name?: string
input?: Record<string, unknown>
callID?: string
}>
}

View File

@@ -0,0 +1,57 @@
const ENGLISH_PATTERNS = [/\bultrathink\b/i, /\bthink\b/i]
const MULTILINGUAL_KEYWORDS = [
"생각", "고민", "검토", "제대로",
"思考", "考虑", "考慮",
"思考", "考え", "熟考",
"सोच", "विचार",
"تفكير", "تأمل",
"চিন্তা", "ভাবনা",
"думать", "думай", "размышлять", "размышляй",
"pensar", "pense", "refletir", "reflita",
"pensar", "piensa", "reflexionar", "reflexiona",
"penser", "pense", "réfléchir", "réfléchis",
"denken", "denk", "nachdenken",
"suy nghĩ", "cân nhắc",
"düşün", "düşünmek",
"pensare", "pensa", "riflettere", "rifletti",
"คิด", "พิจารณา",
"myśl", "myśleć", "zastanów",
"denken", "denk", "nadenken",
"berpikir", "pikir", "pertimbangkan",
"думати", "думай", "роздумувати",
"σκέψου", "σκέφτομαι",
"myslet", "mysli", "přemýšlet",
"gândește", "gândi", "reflectă",
"tänka", "tänk", "fundera",
"gondolkodj", "gondolkodni",
"ajattele", "ajatella", "pohdi",
"tænk", "tænke", "overvej",
"tenk", "tenke", "gruble",
"חשוב", "לחשוב", "להרהר",
"fikir", "berfikir",
]
const MULTILINGUAL_PATTERNS = MULTILINGUAL_KEYWORDS.map((kw) => new RegExp(kw, "i"))
const THINK_PATTERNS = [...ENGLISH_PATTERNS, ...MULTILINGUAL_PATTERNS]
const CODE_BLOCK_PATTERN = /```[\s\S]*?```/g
const INLINE_CODE_PATTERN = /`[^`]+`/g
function removeCodeBlocks(text: string): string {
return text.replace(CODE_BLOCK_PATTERN, "").replace(INLINE_CODE_PATTERN, "")
}
export function detectThinkKeyword(text: string): boolean {
const textWithoutCode = removeCodeBlocks(text)
return THINK_PATTERNS.some((pattern) => pattern.test(textWithoutCode))
}
export function extractPromptText(
parts: Array<{ type: string; text?: string }>
): string {
return parts
.filter((p) => p.type === "text")
.map((p) => p.text || "")
.join("")
}

View File

@@ -0,0 +1,73 @@
import { detectThinkKeyword, extractPromptText } from "./detector"
import { getHighVariant, isAlreadyHighVariant } from "./switcher"
import type { ThinkModeState, ThinkModeInput } from "./types"
export * from "./detector"
export * from "./switcher"
export * from "./types"
const thinkModeState = new Map<string, ThinkModeState>()
export function clearThinkModeState(sessionID: string): void {
thinkModeState.delete(sessionID)
}
export function createThinkModeHook() {
return {
"chat.params": async (
output: ThinkModeInput,
sessionID: string
): Promise<void> => {
const promptText = extractPromptText(output.parts)
const state: ThinkModeState = {
requested: false,
modelSwitched: false,
}
if (!detectThinkKeyword(promptText)) {
thinkModeState.set(sessionID, state)
return
}
state.requested = true
const currentModel = output.message.model
if (!currentModel) {
thinkModeState.set(sessionID, state)
return
}
state.providerID = currentModel.providerID
state.modelID = currentModel.modelID
if (isAlreadyHighVariant(currentModel.modelID)) {
thinkModeState.set(sessionID, state)
return
}
const highVariant = getHighVariant(currentModel.modelID)
if (!highVariant) {
thinkModeState.set(sessionID, state)
return
}
output.message.model = {
providerID: currentModel.providerID,
modelID: highVariant,
}
state.modelSwitched = true
thinkModeState.set(sessionID, state)
},
event: async ({ event }: { event: { type: string; properties?: unknown } }) => {
if (event.type === "session.deleted") {
const props = event.properties as { info?: { id?: string } } | undefined
if (props?.info?.id) {
thinkModeState.delete(props.info.id)
}
}
},
}
}

View File

@@ -0,0 +1,91 @@
const HIGH_VARIANT_MAP: Record<string, string> = {
"claude-sonnet-4-5": "claude-sonnet-4-5-high",
"claude-opus-4-5": "claude-opus-4-5-high",
"gpt-5.1": "gpt-5.1-high",
"gpt-5.1-medium": "gpt-5.1-high",
"gpt-5.1-codex": "gpt-5.1-codex-high",
"gemini-3-pro": "gemini-3-pro-high",
"gemini-3-pro-low": "gemini-3-pro-high",
}
const ALREADY_HIGH: Set<string> = new Set([
"claude-sonnet-4-5-high",
"claude-opus-4-5-high",
"gpt-5.1-high",
"gpt-5.1-codex-high",
"gemini-3-pro-high",
])
export const THINKING_CONFIGS: Record<string, Record<string, unknown>> = {
anthropic: {
thinking: {
type: "enabled",
budgetTokens: 64000,
},
},
"amazon-bedrock": {
reasoningConfig: {
type: "enabled",
budgetTokens: 32000,
},
},
google: {
providerOptions: {
google: {
thinkingConfig: {
thinkingLevel: "HIGH",
},
},
},
},
"google-vertex": {
providerOptions: {
"google-vertex": {
thinkingConfig: {
thinkingLevel: "HIGH",
},
},
},
},
}
const THINKING_CAPABLE_MODELS: Record<string, string[]> = {
anthropic: ["claude-sonnet-4", "claude-opus-4", "claude-3"],
"amazon-bedrock": ["claude", "anthropic"],
google: ["gemini-2", "gemini-3"],
"google-vertex": ["gemini-2", "gemini-3"],
}
export function getHighVariant(modelID: string): string | null {
if (ALREADY_HIGH.has(modelID)) {
return null
}
return HIGH_VARIANT_MAP[modelID] ?? null
}
export function isAlreadyHighVariant(modelID: string): boolean {
return ALREADY_HIGH.has(modelID) || modelID.endsWith("-high")
}
export function getThinkingConfig(
providerID: string,
modelID: string
): Record<string, unknown> | null {
if (isAlreadyHighVariant(modelID)) {
return null
}
const config = THINKING_CONFIGS[providerID]
const capablePatterns = THINKING_CAPABLE_MODELS[providerID]
if (!config || !capablePatterns) {
return null
}
const modelLower = modelID.toLowerCase()
const isCapable = capablePatterns.some((pattern) =>
modelLower.includes(pattern.toLowerCase())
)
return isCapable ? config : null
}

View File

@@ -0,0 +1,20 @@
export interface ThinkModeState {
requested: boolean
modelSwitched: boolean
providerID?: string
modelID?: string
}
export interface ModelRef {
providerID: string
modelID: string
}
export interface MessageWithModel {
model?: ModelRef
}
export interface ThinkModeInput {
parts: Array<{ type: string; text?: string }>
message: MessageWithModel
}

View File

@@ -7,18 +7,13 @@ interface Todo {
id: string
}
const CONTINUATION_PROMPT = `[SYSTEM REMINDER - TODO ENFORCEMENT]
const CONTINUATION_PROMPT = `[SYSTEM REMINDER - TODO CONTINUATION]
Your todo list is NOT complete. There are still incomplete tasks remaining.
Incomplete tasks remain in your todo list. Continue working on the next pending task.
CRITICAL INSTRUCTION:
- You MUST NOT stop working until ALL todos are marked as completed
- Continue working on the next pending task immediately
- Work honestly and diligently to finish every task
- Do NOT ask for permission to continue - just proceed with the work
- Mark each task as completed as soon as you finish it
Resume your work NOW.`
- Proceed without asking for permission
- Mark each task complete when finished
- Do not stop until all tasks are done`
function detectInterrupt(error: unknown): boolean {
if (!error) return false
@@ -113,7 +108,7 @@ export function createTodoContinuationEnforcer(ctx: PluginInput) {
parts: [
{
type: "text",
text: `${CONTINUATION_PROMPT}\n\n[Status: ${incomplete.length}/${todos.length} tasks remaining]`,
text: `${CONTINUATION_PROMPT}\n\n[Status: ${todos.length - incomplete.length}/${todos.length} completed, ${incomplete.length} remaining]`,
},
],
},

View File

@@ -1,132 +1,195 @@
import type { Plugin } from "@opencode-ai/plugin"
import { createBuiltinAgents } from "./agents"
import { createTodoContinuationEnforcer, createContextWindowMonitorHook, createSessionRecoveryHook } from "./hooks"
import { updateTerminalTitle } from "./features/terminal"
import { builtinTools } from "./tools"
import { createBuiltinMcps } from "./mcp"
import { OhMyOpenCodeConfigSchema, type OhMyOpenCodeConfig } from "./config"
import * as fs from "fs"
import * as path from "path"
import type { Plugin } from "@opencode-ai/plugin";
import { createBuiltinAgents } from "./agents";
import {
createTodoContinuationEnforcer,
createContextWindowMonitorHook,
createSessionRecoveryHook,
createCommentCheckerHooks,
createGrepOutputTruncatorHook,
createDirectoryAgentsInjectorHook,
createEmptyTaskResponseDetectorHook,
createThinkModeHook,
createClaudeCodeHooksHook,
} from "./hooks";
import {
loadUserCommands,
loadProjectCommands,
loadOpencodeGlobalCommands,
loadOpencodeProjectCommands,
} from "./features/claude-code-command-loader";
import {
loadUserSkillsAsCommands,
loadProjectSkillsAsCommands,
} from "./features/claude-code-skill-loader";
import {
loadUserAgents,
loadProjectAgents,
} from "./features/claude-code-agent-loader";
import { loadMcpConfigs } from "./features/claude-code-mcp-loader";
import {
setCurrentSession,
setMainSession,
getMainSessionID,
getCurrentSessionTitle,
} from "./features/claude-code-session-state";
import { updateTerminalTitle } from "./features/terminal";
import { builtinTools } from "./tools";
import { createBuiltinMcps } from "./mcp";
import { OhMyOpenCodeConfigSchema, type OhMyOpenCodeConfig } from "./config";
import { log } from "./shared/logger";
import * as fs from "fs";
import * as path from "path";
function loadPluginConfig(directory: string): OhMyOpenCodeConfig {
const configPaths = [
path.join(directory, "oh-my-opencode.json"),
path.join(directory, ".oh-my-opencode.json"),
]
];
for (const configPath of configPaths) {
try {
if (fs.existsSync(configPath)) {
const content = fs.readFileSync(configPath, "utf-8")
const rawConfig = JSON.parse(content)
const result = OhMyOpenCodeConfigSchema.safeParse(rawConfig)
const content = fs.readFileSync(configPath, "utf-8");
const rawConfig = JSON.parse(content);
const result = OhMyOpenCodeConfigSchema.safeParse(rawConfig);
if (!result.success) {
console.error(`[oh-my-opencode] Config validation error in ${configPath}:`)
for (const issue of result.error.issues) {
console.error(` - ${issue.path.join(".")}: ${issue.message}`)
}
return {}
log(`Config validation error in ${configPath}:`, result.error.issues);
return {};
}
return result.data
return result.data;
}
} catch {
// Ignore parse errors, use defaults
}
}
return {}
return {};
}
const OhMyOpenCodePlugin: Plugin = async (ctx) => {
const todoContinuationEnforcer = createTodoContinuationEnforcer(ctx)
const contextWindowMonitor = createContextWindowMonitorHook(ctx)
const sessionRecovery = createSessionRecoveryHook(ctx)
const pluginConfig = loadPluginConfig(ctx.directory);
updateTerminalTitle({ sessionId: "main" })
const todoContinuationEnforcer = createTodoContinuationEnforcer(ctx);
const contextWindowMonitor = createContextWindowMonitorHook(ctx);
const sessionRecovery = createSessionRecoveryHook(ctx);
const commentChecker = createCommentCheckerHooks();
const grepOutputTruncator = createGrepOutputTruncatorHook(ctx);
const directoryAgentsInjector = createDirectoryAgentsInjectorHook(ctx);
const emptyTaskResponseDetector = createEmptyTaskResponseDetectorHook(ctx);
const thinkMode = createThinkModeHook();
const claudeCodeHooks = createClaudeCodeHooksHook(ctx, {});
const pluginConfig = loadPluginConfig(ctx.directory)
let mainSessionID: string | undefined
let currentSessionID: string | undefined
let currentSessionTitle: string | undefined
updateTerminalTitle({ sessionId: "main" });
return {
tool: builtinTools,
"chat.message": async (input, output) => {
await claudeCodeHooks["chat.message"]?.(input, output)
},
config: async (config) => {
const agents = createBuiltinAgents(
const builtinAgents = createBuiltinAgents(
pluginConfig.disabled_agents,
pluginConfig.agents
)
pluginConfig.agents,
);
const userAgents = loadUserAgents();
const projectAgents = loadProjectAgents();
config.agent = {
...builtinAgents,
...userAgents,
...projectAgents,
...config.agent,
...agents,
}
};
config.tools = {
...config.tools,
grep: false,
}
};
const mcpResult = await loadMcpConfigs();
config.mcp = {
...config.mcp,
...createBuiltinMcps(pluginConfig.disabled_mcps),
}
...mcpResult.servers,
};
const userCommands = loadUserCommands();
const opencodeGlobalCommands = loadOpencodeGlobalCommands();
const systemCommands = config.command ?? {};
const projectCommands = loadProjectCommands();
const opencodeProjectCommands = loadOpencodeProjectCommands();
const userSkills = loadUserSkillsAsCommands();
const projectSkills = loadProjectSkillsAsCommands();
config.command = {
...userCommands,
...userSkills,
...opencodeGlobalCommands,
...systemCommands,
...projectCommands,
...projectSkills,
...opencodeProjectCommands,
};
},
event: async (input) => {
await todoContinuationEnforcer(input)
await contextWindowMonitor.event(input)
await claudeCodeHooks.event(input);
await todoContinuationEnforcer(input);
await contextWindowMonitor.event(input);
await directoryAgentsInjector.event(input);
await thinkMode.event(input);
const { event } = input
const props = event.properties as Record<string, unknown> | undefined
const { event } = input;
const props = event.properties as Record<string, unknown> | undefined;
if (event.type === "session.created") {
const sessionInfo = props?.info as { id?: string; title?: string; parentID?: string } | undefined
const sessionInfo = props?.info as
| { id?: string; title?: string; parentID?: string }
| undefined;
if (!sessionInfo?.parentID) {
mainSessionID = sessionInfo?.id
currentSessionID = sessionInfo?.id
currentSessionTitle = sessionInfo?.title
setMainSession(sessionInfo?.id);
setCurrentSession(sessionInfo?.id, sessionInfo?.title);
updateTerminalTitle({
sessionId: currentSessionID || "main",
sessionId: sessionInfo?.id || "main",
status: "idle",
directory: ctx.directory,
sessionTitle: currentSessionTitle,
})
sessionTitle: sessionInfo?.title,
});
}
}
if (event.type === "session.updated") {
const sessionInfo = props?.info as { id?: string; title?: string; parentID?: string } | undefined
const sessionInfo = props?.info as
| { id?: string; title?: string; parentID?: string }
| undefined;
if (!sessionInfo?.parentID) {
currentSessionID = sessionInfo?.id
currentSessionTitle = sessionInfo?.title
setCurrentSession(sessionInfo?.id, sessionInfo?.title);
updateTerminalTitle({
sessionId: currentSessionID || "main",
sessionId: sessionInfo?.id || "main",
status: "processing",
directory: ctx.directory,
sessionTitle: currentSessionTitle,
})
sessionTitle: sessionInfo?.title,
});
}
}
if (event.type === "session.deleted") {
const sessionInfo = props?.info as { id?: string } | undefined
if (sessionInfo?.id === mainSessionID) {
mainSessionID = undefined
currentSessionID = undefined
currentSessionTitle = undefined
const sessionInfo = props?.info as { id?: string } | undefined;
if (sessionInfo?.id === getMainSessionID()) {
setMainSession(undefined);
setCurrentSession(undefined, undefined);
updateTerminalTitle({
sessionId: "main",
status: "idle",
})
});
}
}
if (event.type === "session.error") {
const sessionID = props?.sessionID as string | undefined
const error = props?.error
const sessionID = props?.sessionID as string | undefined;
const error = props?.error;
if (sessionRecovery.isRecoverableError(error)) {
const messageInfo = {
@@ -134,67 +197,85 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
role: "assistant" as const,
sessionID,
error,
};
const recovered =
await sessionRecovery.handleSessionRecovery(messageInfo);
if (recovered && sessionID && sessionID === getMainSessionID()) {
await ctx.client.session
.prompt({
path: { id: sessionID },
body: { parts: [{ type: "text", text: "continue" }] },
query: { directory: ctx.directory },
})
.catch(() => {});
}
await sessionRecovery.handleSessionRecovery(messageInfo)
}
if (sessionID && sessionID === mainSessionID) {
if (sessionID && sessionID === getMainSessionID()) {
updateTerminalTitle({
sessionId: sessionID,
status: "error",
directory: ctx.directory,
sessionTitle: currentSessionTitle,
})
sessionTitle: getCurrentSessionTitle(),
});
}
}
if (event.type === "session.idle") {
const sessionID = props?.sessionID as string | undefined
if (sessionID && sessionID === mainSessionID) {
const sessionID = props?.sessionID as string | undefined;
if (sessionID && sessionID === getMainSessionID()) {
updateTerminalTitle({
sessionId: sessionID,
status: "idle",
directory: ctx.directory,
sessionTitle: currentSessionTitle,
})
sessionTitle: getCurrentSessionTitle(),
});
}
}
},
"tool.execute.before": async (input, _output) => {
if (input.sessionID === mainSessionID) {
"tool.execute.before": async (input, output) => {
await claudeCodeHooks["tool.execute.before"](input, output);
await commentChecker["tool.execute.before"](input, output);
if (input.sessionID === getMainSessionID()) {
updateTerminalTitle({
sessionId: input.sessionID,
status: "tool",
currentTool: input.tool,
directory: ctx.directory,
sessionTitle: currentSessionTitle,
})
sessionTitle: getCurrentSessionTitle(),
});
}
},
"tool.execute.after": async (input, output) => {
await contextWindowMonitor["tool.execute.after"](input, output)
await claudeCodeHooks["tool.execute.after"](input, output);
await grepOutputTruncator["tool.execute.after"](input, output);
await contextWindowMonitor["tool.execute.after"](input, output);
await commentChecker["tool.execute.after"](input, output);
await directoryAgentsInjector["tool.execute.after"](input, output);
await emptyTaskResponseDetector["tool.execute.after"](input, output);
if (input.sessionID === mainSessionID) {
if (input.sessionID === getMainSessionID()) {
updateTerminalTitle({
sessionId: input.sessionID,
status: "idle",
directory: ctx.directory,
sessionTitle: currentSessionTitle,
})
sessionTitle: getCurrentSessionTitle(),
});
}
},
}
}
};
};
export default OhMyOpenCodePlugin
export default OhMyOpenCodePlugin;
export { OhMyOpenCodeConfigSchema } from "./config"
export type {
OhMyOpenCodeConfig,
AgentName,
AgentOverrideConfig,
AgentOverrides,
McpName,
} from "./config"
} from "./config";

View File

@@ -1,7 +1,8 @@
import { websearch_exa } from "./websearch-exa"
import { context7 } from "./context7"
import type { McpName } from "./types"
export type McpName = "websearch_exa" | "context7"
export { McpNameSchema, type McpName } from "./types"
const allBuiltinMcps: Record<McpName, { type: "remote"; url: string; enabled: boolean }> = {
websearch_exa,
@@ -19,5 +20,3 @@ export function createBuiltinMcps(disabledMcps: McpName[] = []) {
return mcps
}
export const builtinMcps = allBuiltinMcps

5
src/mcp/types.ts Normal file
View File

@@ -0,0 +1,5 @@
import { z } from "zod"
export const McpNameSchema = z.enum(["websearch_exa", "context7"])
export type McpName = z.infer<typeof McpNameSchema>

View File

@@ -0,0 +1,203 @@
import { spawn } from "child_process"
import { exec } from "child_process"
import { promisify } from "util"
import { existsSync } from "fs"
const DEFAULT_ZSH_PATHS = ["/bin/zsh", "/usr/bin/zsh", "/usr/local/bin/zsh"]
function findZshPath(customZshPath?: string): string | null {
if (customZshPath && existsSync(customZshPath)) {
return customZshPath
}
for (const path of DEFAULT_ZSH_PATHS) {
if (existsSync(path)) {
return path
}
}
return null
}
const execAsync = promisify(exec)
export interface CommandResult {
exitCode: number
stdout?: string
stderr?: string
}
export interface ExecuteHookOptions {
forceZsh?: boolean
zshPath?: string
}
/**
* Execute a hook command with stdin input
*/
export async function executeHookCommand(
command: string,
stdin: string,
cwd: string,
options?: ExecuteHookOptions
): Promise<CommandResult> {
const home = process.env.HOME ?? ""
let expandedCommand = command
.replace(/^~(?=\/|$)/g, home)
.replace(/\s~(?=\/)/g, ` ${home}`)
.replace(/\$CLAUDE_PROJECT_DIR/g, cwd)
.replace(/\$\{CLAUDE_PROJECT_DIR\}/g, cwd)
let finalCommand = expandedCommand
if (options?.forceZsh) {
const zshPath = options.zshPath || findZshPath()
if (zshPath) {
const escapedCommand = expandedCommand.replace(/'/g, "'\\''")
finalCommand = `${zshPath} -lc '${escapedCommand}'`
}
}
return new Promise((resolve) => {
const proc = spawn(finalCommand, {
cwd,
shell: true,
env: { ...process.env, HOME: home, CLAUDE_PROJECT_DIR: cwd },
})
let stdout = ""
let stderr = ""
proc.stdout?.on("data", (data) => {
stdout += data.toString()
})
proc.stderr?.on("data", (data) => {
stderr += data.toString()
})
proc.stdin?.write(stdin)
proc.stdin?.end()
proc.on("close", (code) => {
resolve({
exitCode: code ?? 0,
stdout: stdout.trim(),
stderr: stderr.trim(),
})
})
proc.on("error", (err) => {
resolve({
exitCode: 1,
stderr: err.message,
})
})
})
}
/**
* Execute a simple command and return output
*/
export async function executeCommand(command: string): Promise<string> {
try {
const { stdout, stderr } = await execAsync(command)
const out = stdout?.toString().trim() ?? ""
const err = stderr?.toString().trim() ?? ""
if (err) {
if (out) {
return `${out}\n[stderr: ${err}]`
}
return `[stderr: ${err}]`
}
return out
} catch (error: unknown) {
const e = error as { stdout?: Buffer; stderr?: Buffer; message?: string }
const stdout = e?.stdout?.toString().trim() ?? ""
const stderr = e?.stderr?.toString().trim() ?? ""
const errMsg = stderr || e?.message || String(error)
if (stdout) {
return `${stdout}\n[stderr: ${errMsg}]`
}
return `[stderr: ${errMsg}]`
}
}
/**
* Find and execute embedded commands in text (!`command`)
*/
interface CommandMatch {
fullMatch: string
command: string
start: number
end: number
}
const COMMAND_PATTERN = /!`([^`]+)`/g
function findCommands(text: string): CommandMatch[] {
const matches: CommandMatch[] = []
let match: RegExpExecArray | null
COMMAND_PATTERN.lastIndex = 0
while ((match = COMMAND_PATTERN.exec(text)) !== null) {
matches.push({
fullMatch: match[0],
command: match[1],
start: match.index,
end: match.index + match[0].length,
})
}
return matches
}
/**
* Resolve embedded commands in text recursively
*/
export async function resolveCommandsInText(
text: string,
depth: number = 0,
maxDepth: number = 3
): Promise<string> {
if (depth >= maxDepth) {
return text
}
const matches = findCommands(text)
if (matches.length === 0) {
return text
}
const tasks = matches.map((m) => executeCommand(m.command))
const results = await Promise.allSettled(tasks)
const replacements = new Map<string, string>()
matches.forEach((match, idx) => {
const result = results[idx]
if (result.status === "rejected") {
replacements.set(
match.fullMatch,
`[error: ${result.reason instanceof Error ? result.reason.message : String(result.reason)}]`
)
} else {
replacements.set(match.fullMatch, result.value)
}
})
let resolved = text
for (const [pattern, replacement] of replacements.entries()) {
resolved = resolved.split(pattern).join(replacement)
}
if (findCommands(resolved).length > 0) {
return resolveCommandsInText(resolved, depth + 1, maxDepth)
}
return resolved
}

View File

@@ -0,0 +1,85 @@
import { existsSync, readFileSync, statSync } from "fs"
import { join, isAbsolute } from "path"
interface FileMatch {
fullMatch: string
filePath: string
start: number
end: number
}
const FILE_REFERENCE_PATTERN = /@([^\s@]+)/g
function findFileReferences(text: string): FileMatch[] {
const matches: FileMatch[] = []
let match: RegExpExecArray | null
FILE_REFERENCE_PATTERN.lastIndex = 0
while ((match = FILE_REFERENCE_PATTERN.exec(text)) !== null) {
matches.push({
fullMatch: match[0],
filePath: match[1],
start: match.index,
end: match.index + match[0].length,
})
}
return matches
}
function resolveFilePath(filePath: string, cwd: string): string {
if (isAbsolute(filePath)) {
return filePath
}
return join(cwd, filePath)
}
function readFileContent(resolvedPath: string): string {
if (!existsSync(resolvedPath)) {
return `[file not found: ${resolvedPath}]`
}
const stat = statSync(resolvedPath)
if (stat.isDirectory()) {
return `[cannot read directory: ${resolvedPath}]`
}
const content = readFileSync(resolvedPath, "utf-8")
return content
}
export async function resolveFileReferencesInText(
text: string,
cwd: string = process.cwd(),
depth: number = 0,
maxDepth: number = 3
): Promise<string> {
if (depth >= maxDepth) {
return text
}
const matches = findFileReferences(text)
if (matches.length === 0) {
return text
}
const replacements = new Map<string, string>()
for (const match of matches) {
const resolvedPath = resolveFilePath(match.filePath, cwd)
const content = readFileContent(resolvedPath)
replacements.set(match.fullMatch, content)
}
let resolved = text
for (const [pattern, replacement] of replacements.entries()) {
resolved = resolved.split(pattern).join(replacement)
}
if (findFileReferences(resolved).length > 0 && depth + 1 < maxDepth) {
return resolveFileReferencesInText(resolved, cwd, depth + 1, maxDepth)
}
return resolved
}

34
src/shared/frontmatter.ts Normal file
View File

@@ -0,0 +1,34 @@
export interface FrontmatterResult<T = Record<string, string>> {
data: T
body: string
}
export function parseFrontmatter<T = Record<string, string>>(
content: string
): FrontmatterResult<T> {
const frontmatterRegex = /^---\r?\n([\s\S]*?)\r?\n---\r?\n([\s\S]*)$/
const match = content.match(frontmatterRegex)
if (!match) {
return { data: {} as T, body: content }
}
const yamlContent = match[1]
const body = match[2]
const data: Record<string, string | boolean> = {}
for (const line of yamlContent.split("\n")) {
const colonIndex = line.indexOf(":")
if (colonIndex !== -1) {
const key = line.slice(0, colonIndex).trim()
let value: string | boolean = line.slice(colonIndex + 1).trim()
if (value === "true") value = true
else if (value === "false") value = false
data[key] = value
}
}
return { data: data as T, body }
}

View File

@@ -0,0 +1,22 @@
import type { ClaudeHookEvent, PluginConfig } from "../hooks/claude-code-hooks/types"
export function isHookDisabled(
config: PluginConfig,
hookType: ClaudeHookEvent
): boolean {
const { disabledHooks } = config
if (disabledHooks === undefined) {
return false
}
if (disabledHooks === true) {
return true
}
if (Array.isArray(disabledHooks)) {
return disabledHooks.includes(hookType)
}
return false
}

9
src/shared/index.ts Normal file
View File

@@ -0,0 +1,9 @@
export * from "./frontmatter"
export * from "./command-executor"
export * from "./file-reference-resolver"
export * from "./model-sanitizer"
export * from "./logger"
export * from "./snake-case"
export * from "./tool-name"
export * from "./pattern-matcher"
export * from "./hook-disabled"

20
src/shared/logger.ts Normal file
View File

@@ -0,0 +1,20 @@
// Shared logging utility for the plugin
import * as fs from "fs"
import * as os from "os"
import * as path from "path"
const logFile = path.join(os.tmpdir(), "oh-my-opencode.log")
export function log(message: string, data?: unknown): void {
try {
const timestamp = new Date().toISOString()
const logEntry = `[${timestamp}] ${message} ${data ? JSON.stringify(data) : ""}\n`
fs.appendFileSync(logFile, logEntry)
} catch {
}
}
export function getLogFilePath(): string {
return logFile
}

View File

@@ -0,0 +1,13 @@
/**
* Sanitizes model field from frontmatter.
* Always returns undefined to let SDK use default model.
*
* Claude Code and OpenCode use different model ID formats,
* so we ignore the model field and let OpenCode use its configured default.
*
* @param _model - Raw model value from frontmatter (ignored)
* @returns Always undefined to inherit default model
*/
export function sanitizeModelField(_model: unknown): undefined {
return undefined
}

View File

@@ -0,0 +1,29 @@
import type { ClaudeHooksConfig, HookMatcher } from "../hooks/claude-code-hooks/types"
export function matchesToolMatcher(toolName: string, matcher: string): boolean {
if (!matcher) {
return true
}
const patterns = matcher.split("|").map((p) => p.trim())
return patterns.some((p) => {
if (p.includes("*")) {
const regex = new RegExp(`^${p.replace(/\*/g, ".*")}$`, "i")
return regex.test(toolName)
}
return p.toLowerCase() === toolName.toLowerCase()
})
}
export function findMatchingHooks(
config: ClaudeHooksConfig,
eventName: keyof ClaudeHooksConfig,
toolName?: string
): HookMatcher[] {
const hookMatchers = config[eventName]
if (!hookMatchers) return []
return hookMatchers.filter((hookMatcher) => {
if (!toolName) return true
return matchesToolMatcher(toolName, hookMatcher.matcher)
})
}

51
src/shared/snake-case.ts Normal file
View File

@@ -0,0 +1,51 @@
export function camelToSnake(str: string): string {
return str.replace(/[A-Z]/g, (letter) => `_${letter.toLowerCase()}`)
}
export function snakeToCamel(str: string): string {
return str.replace(/_([a-z])/g, (_, letter) => letter.toUpperCase())
}
function isPlainObject(value: unknown): value is Record<string, unknown> {
return typeof value === "object" && value !== null && !Array.isArray(value)
}
export function objectToSnakeCase(
obj: Record<string, unknown>,
deep: boolean = true
): Record<string, unknown> {
const result: Record<string, unknown> = {}
for (const [key, value] of Object.entries(obj)) {
const snakeKey = camelToSnake(key)
if (deep && isPlainObject(value)) {
result[snakeKey] = objectToSnakeCase(value, true)
} else if (deep && Array.isArray(value)) {
result[snakeKey] = value.map((item) =>
isPlainObject(item) ? objectToSnakeCase(item, true) : item
)
} else {
result[snakeKey] = value
}
}
return result
}
export function objectToCamelCase(
obj: Record<string, unknown>,
deep: boolean = true
): Record<string, unknown> {
const result: Record<string, unknown> = {}
for (const [key, value] of Object.entries(obj)) {
const camelKey = snakeToCamel(key)
if (deep && isPlainObject(value)) {
result[camelKey] = objectToCamelCase(value, true)
} else if (deep && Array.isArray(value)) {
result[camelKey] = value.map((item) =>
isPlainObject(item) ? objectToCamelCase(item, true) : item
)
} else {
result[camelKey] = value
}
}
return result
}

26
src/shared/tool-name.ts Normal file
View File

@@ -0,0 +1,26 @@
const SPECIAL_TOOL_MAPPINGS: Record<string, string> = {
webfetch: "WebFetch",
websearch: "WebSearch",
todoread: "TodoRead",
todowrite: "TodoWrite",
}
function toPascalCase(str: string): string {
return str
.split(/[-_\s]+/)
.map((word) => word.charAt(0).toUpperCase() + word.slice(1).toLowerCase())
.join("")
}
export function transformToolName(toolName: string): string {
const lower = toolName.toLowerCase()
if (lower in SPECIAL_TOOL_MAPPINGS) {
return SPECIAL_TOOL_MAPPINGS[lower]
}
if (toolName.includes("-") || toolName.includes("_")) {
return toPascalCase(toolName)
}
return toolName.charAt(0).toUpperCase() + toolName.slice(1)
}

View File

@@ -1,6 +1,15 @@
import { spawn } from "bun"
import { SG_CLI_PATH } from "./constants"
import type { CliMatch, CliLanguage } from "./types"
import { existsSync } from "fs"
import {
getSgCliPath,
setSgCliPath,
findSgCliPathSync,
DEFAULT_TIMEOUT_MS,
DEFAULT_MAX_OUTPUT_BYTES,
DEFAULT_MAX_MATCHES,
} from "./constants"
import { ensureAstGrepBinary } from "./downloader"
import type { CliMatch, CliLanguage, SgResult } from "./types"
export interface RunOptions {
pattern: string
@@ -12,7 +21,47 @@ export interface RunOptions {
updateAll?: boolean
}
export async function runSg(options: RunOptions): Promise<CliMatch[]> {
let resolvedCliPath: string | null = null
let initPromise: Promise<string | null> | null = null
export async function getAstGrepPath(): Promise<string | null> {
if (resolvedCliPath !== null && existsSync(resolvedCliPath)) {
return resolvedCliPath
}
if (initPromise) {
return initPromise
}
initPromise = (async () => {
const syncPath = findSgCliPathSync()
if (syncPath && existsSync(syncPath)) {
resolvedCliPath = syncPath
setSgCliPath(syncPath)
return syncPath
}
const downloadedPath = await ensureAstGrepBinary()
if (downloadedPath) {
resolvedCliPath = downloadedPath
setSgCliPath(downloadedPath)
return downloadedPath
}
return null
})()
return initPromise
}
export function startBackgroundInit(): void {
if (!initPromise) {
initPromise = getAstGrepPath()
initPromise.catch(() => {})
}
}
export async function runSg(options: RunOptions): Promise<SgResult> {
const args = ["run", "-p", options.pattern, "--lang", options.lang, "--json=compact"]
if (options.rewrite) {
@@ -35,32 +84,147 @@ export async function runSg(options: RunOptions): Promise<CliMatch[]> {
const paths = options.paths && options.paths.length > 0 ? options.paths : ["."]
args.push(...paths)
const proc = spawn([SG_CLI_PATH, ...args], {
let cliPath = getSgCliPath()
if (!existsSync(cliPath) && cliPath !== "sg") {
const downloadedPath = await getAstGrepPath()
if (downloadedPath) {
cliPath = downloadedPath
}
}
const timeout = DEFAULT_TIMEOUT_MS
const proc = spawn([cliPath, ...args], {
stdout: "pipe",
stderr: "pipe",
})
const stdout = await new Response(proc.stdout).text()
const stderr = await new Response(proc.stderr).text()
const exitCode = await proc.exited
const timeoutPromise = new Promise<never>((_, reject) => {
const id = setTimeout(() => {
proc.kill()
reject(new Error(`Search timeout after ${timeout}ms`))
}, timeout)
proc.exited.then(() => clearTimeout(id))
})
let stdout: string
let stderr: string
let exitCode: number
try {
stdout = await Promise.race([new Response(proc.stdout).text(), timeoutPromise])
stderr = await new Response(proc.stderr).text()
exitCode = await proc.exited
} catch (e) {
const error = e as Error
if (error.message?.includes("timeout")) {
return {
matches: [],
totalMatches: 0,
truncated: true,
truncatedReason: "timeout",
error: error.message,
}
}
const nodeError = e as NodeJS.ErrnoException
if (
nodeError.code === "ENOENT" ||
nodeError.message?.includes("ENOENT") ||
nodeError.message?.includes("not found")
) {
const downloadedPath = await ensureAstGrepBinary()
if (downloadedPath) {
resolvedCliPath = downloadedPath
setSgCliPath(downloadedPath)
return runSg(options)
} else {
return {
matches: [],
totalMatches: 0,
truncated: false,
error:
`ast-grep CLI binary not found.\n\n` +
`Auto-download failed. Manual install options:\n` +
` bun add -D @ast-grep/cli\n` +
` cargo install ast-grep --locked\n` +
` brew install ast-grep`,
}
}
}
return {
matches: [],
totalMatches: 0,
truncated: false,
error: `Failed to spawn ast-grep: ${error.message}`,
}
}
if (exitCode !== 0 && stdout.trim() === "") {
if (stderr.includes("No files found")) {
return []
return { matches: [], totalMatches: 0, truncated: false }
}
if (stderr.trim()) {
throw new Error(stderr.trim())
return { matches: [], totalMatches: 0, truncated: false, error: stderr.trim() }
}
return []
return { matches: [], totalMatches: 0, truncated: false }
}
if (!stdout.trim()) {
return []
return { matches: [], totalMatches: 0, truncated: false }
}
const outputTruncated = stdout.length >= DEFAULT_MAX_OUTPUT_BYTES
const outputToProcess = outputTruncated ? stdout.substring(0, DEFAULT_MAX_OUTPUT_BYTES) : stdout
let matches: CliMatch[] = []
try {
return JSON.parse(stdout) as CliMatch[]
matches = JSON.parse(outputToProcess) as CliMatch[]
} catch {
return []
if (outputTruncated) {
try {
const lastValidIndex = outputToProcess.lastIndexOf("}")
if (lastValidIndex > 0) {
const bracketIndex = outputToProcess.lastIndexOf("},", lastValidIndex)
if (bracketIndex > 0) {
const truncatedJson = outputToProcess.substring(0, bracketIndex + 1) + "]"
matches = JSON.parse(truncatedJson) as CliMatch[]
}
}
} catch {
return {
matches: [],
totalMatches: 0,
truncated: true,
truncatedReason: "max_output_bytes",
error: "Output too large and could not be parsed",
}
}
} else {
return { matches: [], totalMatches: 0, truncated: false }
}
}
const totalMatches = matches.length
const matchesTruncated = totalMatches > DEFAULT_MAX_MATCHES
const finalMatches = matchesTruncated ? matches.slice(0, DEFAULT_MAX_MATCHES) : matches
return {
matches: finalMatches,
totalMatches,
truncated: outputTruncated || matchesTruncated,
truncatedReason: outputTruncated ? "max_output_bytes" : matchesTruncated ? "max_matches" : undefined,
}
}
export function isCliAvailable(): boolean {
const path = findSgCliPathSync()
return path !== null && existsSync(path)
}
export async function ensureCliAvailable(): Promise<boolean> {
const path = await getAstGrepPath()
return path !== null && existsSync(path)
}

View File

@@ -1,9 +1,18 @@
import { createRequire } from "module"
import { dirname, join } from "path"
import { existsSync } from "fs"
import { existsSync, statSync } from "fs"
import { getCachedBinaryPath } from "./downloader"
type Platform = "darwin" | "linux" | "win32" | "unsupported"
function isValidBinary(filePath: string): boolean {
try {
return statSync(filePath).size > 10000
} catch {
return false
}
}
function getPlatformPackageName(): string | null {
const platform = process.platform as Platform
const arch = process.arch
@@ -21,32 +30,37 @@ function getPlatformPackageName(): string | null {
return platformMap[`${platform}-${arch}`] ?? null
}
function findSgCliPath(): string {
// 1. Try to find from @ast-grep/cli package (installed via npm)
export function findSgCliPathSync(): string | null {
const binaryName = process.platform === "win32" ? "sg.exe" : "sg"
const cachedPath = getCachedBinaryPath()
if (cachedPath && isValidBinary(cachedPath)) {
return cachedPath
}
try {
const require = createRequire(import.meta.url)
const cliPkgPath = require.resolve("@ast-grep/cli/package.json")
const cliDir = dirname(cliPkgPath)
const sgPath = join(cliDir, process.platform === "win32" ? "sg.exe" : "sg")
const sgPath = join(cliDir, binaryName)
if (existsSync(sgPath)) {
if (existsSync(sgPath) && isValidBinary(sgPath)) {
return sgPath
}
} catch {
// @ast-grep/cli not installed, try platform-specific package
// @ast-grep/cli not installed
}
// 2. Try platform-specific package directly
const platformPkg = getPlatformPackageName()
if (platformPkg) {
try {
const require = createRequire(import.meta.url)
const pkgPath = require.resolve(`${platformPkg}/package.json`)
const pkgDir = dirname(pkgPath)
const binaryName = process.platform === "win32" ? "ast-grep.exe" : "ast-grep"
const binaryPath = join(pkgDir, binaryName)
const astGrepName = process.platform === "win32" ? "ast-grep.exe" : "ast-grep"
const binaryPath = join(pkgDir, astGrepName)
if (existsSync(binaryPath)) {
if (existsSync(binaryPath) && isValidBinary(binaryPath)) {
return binaryPath
}
} catch {
@@ -54,12 +68,39 @@ function findSgCliPath(): string {
}
}
// 3. Fallback to system PATH
if (process.platform === "darwin") {
const homebrewPaths = ["/opt/homebrew/bin/sg", "/usr/local/bin/sg"]
for (const path of homebrewPaths) {
if (existsSync(path) && isValidBinary(path)) {
return path
}
}
}
return null
}
let resolvedCliPath: string | null = null
export function getSgCliPath(): string {
if (resolvedCliPath !== null) {
return resolvedCliPath
}
const syncPath = findSgCliPathSync()
if (syncPath) {
resolvedCliPath = syncPath
return syncPath
}
return "sg"
}
// ast-grep CLI path (auto-detected from node_modules or system PATH)
export const SG_CLI_PATH = findSgCliPath()
export function setSgCliPath(path: string): void {
resolvedCliPath = path
}
export const SG_CLI_PATH = getSgCliPath()
// CLI supported languages (25 total)
export const CLI_LANGUAGES = [
@@ -94,6 +135,10 @@ export const CLI_LANGUAGES = [
export const NAPI_LANGUAGES = ["html", "javascript", "tsx", "css", "typescript"] as const
// Language to file extensions mapping
export const DEFAULT_TIMEOUT_MS = 300_000
export const DEFAULT_MAX_OUTPUT_BYTES = 1 * 1024 * 1024
export const DEFAULT_MAX_MATCHES = 500
export const LANG_EXTENSIONS: Record<string, string[]> = {
bash: [".bash", ".sh", ".zsh", ".bats"],
c: [".c", ".h"],
@@ -121,3 +166,99 @@ export const LANG_EXTENSIONS: Record<string, string[]> = {
tsx: [".tsx"],
yaml: [".yml", ".yaml"],
}
export interface EnvironmentCheckResult {
cli: {
available: boolean
path: string
error?: string
}
napi: {
available: boolean
error?: string
}
}
/**
* Check if ast-grep CLI and NAPI are available.
* Call this at startup to provide early feedback about missing dependencies.
*/
export function checkEnvironment(): EnvironmentCheckResult {
const result: EnvironmentCheckResult = {
cli: {
available: false,
path: SG_CLI_PATH,
},
napi: {
available: false,
},
}
// Check CLI availability
if (existsSync(SG_CLI_PATH)) {
result.cli.available = true
} else if (SG_CLI_PATH === "sg") {
// Fallback path - try which/where to find in PATH
try {
const { spawnSync } = require("child_process")
const whichResult = spawnSync(process.platform === "win32" ? "where" : "which", ["sg"], {
encoding: "utf-8",
timeout: 5000,
})
result.cli.available = whichResult.status === 0 && !!whichResult.stdout?.trim()
if (!result.cli.available) {
result.cli.error = "sg binary not found in PATH"
}
} catch {
result.cli.error = "Failed to check sg availability"
}
} else {
result.cli.error = `Binary not found: ${SG_CLI_PATH}`
}
// Check NAPI availability
try {
require("@ast-grep/napi")
result.napi.available = true
} catch (e) {
result.napi.available = false
result.napi.error = `@ast-grep/napi not installed: ${e instanceof Error ? e.message : String(e)}`
}
return result
}
/**
* Format environment check result as user-friendly message.
*/
export function formatEnvironmentCheck(result: EnvironmentCheckResult): string {
const lines: string[] = ["ast-grep Environment Status:", ""]
// CLI status
if (result.cli.available) {
lines.push(`✓ CLI: Available (${result.cli.path})`)
} else {
lines.push(`✗ CLI: Not available`)
if (result.cli.error) {
lines.push(` Error: ${result.cli.error}`)
}
lines.push(` Install: bun add -D @ast-grep/cli`)
}
// NAPI status
if (result.napi.available) {
lines.push(`✓ NAPI: Available`)
} else {
lines.push(`✗ NAPI: Not available`)
if (result.napi.error) {
lines.push(` Error: ${result.napi.error}`)
}
lines.push(` Install: bun add -D @ast-grep/napi`)
}
lines.push("")
lines.push(`CLI supports ${CLI_LANGUAGES.length} languages`)
lines.push(`NAPI supports ${NAPI_LANGUAGES.length} languages: ${NAPI_LANGUAGES.join(", ")}`)
return lines.join("\n")
}

View File

@@ -0,0 +1,151 @@
import { spawn } from "bun"
import { existsSync, mkdirSync, chmodSync, unlinkSync } from "fs"
import { join } from "path"
import { homedir } from "os"
import { createRequire } from "module"
const REPO = "ast-grep/ast-grep"
// IMPORTANT: Update this when bumping @ast-grep/cli in package.json
// This is only used as fallback when @ast-grep/cli package.json cannot be read
const DEFAULT_VERSION = "0.40.0"
function getAstGrepVersion(): string {
try {
const require = createRequire(import.meta.url)
const pkg = require("@ast-grep/cli/package.json")
return pkg.version
} catch {
return DEFAULT_VERSION
}
}
interface PlatformInfo {
arch: string
os: string
}
const PLATFORM_MAP: Record<string, PlatformInfo> = {
"darwin-arm64": { arch: "aarch64", os: "apple-darwin" },
"darwin-x64": { arch: "x86_64", os: "apple-darwin" },
"linux-arm64": { arch: "aarch64", os: "unknown-linux-gnu" },
"linux-x64": { arch: "x86_64", os: "unknown-linux-gnu" },
"win32-x64": { arch: "x86_64", os: "pc-windows-msvc" },
"win32-arm64": { arch: "aarch64", os: "pc-windows-msvc" },
"win32-ia32": { arch: "i686", os: "pc-windows-msvc" },
}
export function getCacheDir(): string {
if (process.platform === "win32") {
const localAppData = process.env.LOCALAPPDATA || process.env.APPDATA
const base = localAppData || join(homedir(), "AppData", "Local")
return join(base, "oh-my-opencode", "bin")
}
const xdgCache = process.env.XDG_CACHE_HOME
const base = xdgCache || join(homedir(), ".cache")
return join(base, "oh-my-opencode", "bin")
}
export function getBinaryName(): string {
return process.platform === "win32" ? "sg.exe" : "sg"
}
export function getCachedBinaryPath(): string | null {
const binaryPath = join(getCacheDir(), getBinaryName())
return existsSync(binaryPath) ? binaryPath : null
}
async function extractZip(archivePath: string, destDir: string): Promise<void> {
const proc =
process.platform === "win32"
? spawn(
[
"powershell",
"-command",
`Expand-Archive -Path '${archivePath}' -DestinationPath '${destDir}' -Force`,
],
{ stdout: "pipe", stderr: "pipe" }
)
: spawn(["unzip", "-o", archivePath, "-d", destDir], { stdout: "pipe", stderr: "pipe" })
const exitCode = await proc.exited
if (exitCode !== 0) {
const stderr = await new Response(proc.stderr).text()
const toolHint =
process.platform === "win32"
? "Ensure PowerShell is available on your system."
: "Please install 'unzip' (e.g., apt install unzip, brew install unzip)."
throw new Error(`zip extraction failed (exit ${exitCode}): ${stderr}\n\n${toolHint}`)
}
}
export async function downloadAstGrep(version: string = DEFAULT_VERSION): Promise<string | null> {
const platformKey = `${process.platform}-${process.arch}`
const platformInfo = PLATFORM_MAP[platformKey]
if (!platformInfo) {
console.error(`[oh-my-opencode] Unsupported platform for ast-grep: ${platformKey}`)
return null
}
const cacheDir = getCacheDir()
const binaryName = getBinaryName()
const binaryPath = join(cacheDir, binaryName)
if (existsSync(binaryPath)) {
return binaryPath
}
const { arch, os } = platformInfo
const assetName = `app-${arch}-${os}.zip`
const downloadUrl = `https://github.com/${REPO}/releases/download/${version}/${assetName}`
console.log(`[oh-my-opencode] Downloading ast-grep binary...`)
try {
if (!existsSync(cacheDir)) {
mkdirSync(cacheDir, { recursive: true })
}
const response = await fetch(downloadUrl, { redirect: "follow" })
if (!response.ok) {
throw new Error(`HTTP ${response.status}: ${response.statusText}`)
}
const archivePath = join(cacheDir, assetName)
const arrayBuffer = await response.arrayBuffer()
await Bun.write(archivePath, arrayBuffer)
await extractZip(archivePath, cacheDir)
if (existsSync(archivePath)) {
unlinkSync(archivePath)
}
if (process.platform !== "win32" && existsSync(binaryPath)) {
chmodSync(binaryPath, 0o755)
}
console.log(`[oh-my-opencode] ast-grep binary ready.`)
return binaryPath
} catch (err) {
console.error(
`[oh-my-opencode] Failed to download ast-grep: ${err instanceof Error ? err.message : err}`
)
return null
}
}
export async function ensureAstGrepBinary(): Promise<string | null> {
const cachedPath = getCachedBinaryPath()
if (cachedPath) {
return cachedPath
}
const version = getAstGrepVersion()
return downloadAstGrep(version)
}

View File

@@ -1,14 +1,12 @@
import {
ast_grep_search,
ast_grep_replace,
} from "./tools"
import { ast_grep_search, ast_grep_replace } from "./tools"
export const builtinTools = {
ast_grep_search,
ast_grep_replace,
}
export {
ast_grep_search,
ast_grep_replace,
}
export { ast_grep_search, ast_grep_replace }
export { ensureAstGrepBinary, getCachedBinaryPath, getCacheDir } from "./downloader"
export { getAstGrepPath, isCliAvailable, ensureCliAvailable, startBackgroundInit } from "./cli"
export { checkEnvironment, formatEnvironmentCheck } from "./constants"
export type { EnvironmentCheckResult } from "./constants"

View File

@@ -1,4 +1,5 @@
import { parse, Lang } from "@ast-grep/napi"
import { NAPI_LANGUAGES } from "./constants"
import type { NapiLanguage, AnalyzeResult, MetaVariable, Range } from "./types"
const LANG_MAP: Record<NapiLanguage, Lang> = {
@@ -10,7 +11,16 @@ const LANG_MAP: Record<NapiLanguage, Lang> = {
}
export function parseCode(code: string, lang: NapiLanguage) {
return parse(LANG_MAP[lang], code)
const parseLang = LANG_MAP[lang]
if (!parseLang) {
const supportedLangs = NAPI_LANGUAGES.join(", ")
throw new Error(
`Unsupported language for NAPI: "${lang}"\n` +
`Supported languages: ${supportedLangs}\n\n` +
`Use ast_grep_search for other languages (25 supported via CLI).`
)
}
return parse(parseLang, code)
}
export function findPattern(root: ReturnType<typeof parseCode>, pattern: string) {

View File

@@ -1,22 +1,46 @@
import { tool } from "@opencode-ai/plugin/tool"
import { CLI_LANGUAGES, NAPI_LANGUAGES, LANG_EXTENSIONS } from "./constants"
import { CLI_LANGUAGES } from "./constants"
import { runSg } from "./cli"
import { analyzeCode, transformCode, getRootInfo } from "./napi"
import { formatSearchResult, formatReplaceResult, formatAnalyzeResult, formatTransformResult } from "./utils"
import type { CliLanguage, NapiLanguage } from "./types"
import { formatSearchResult, formatReplaceResult } from "./utils"
import type { CliLanguage } from "./types"
function showOutputToUser(context: unknown, output: string): void {
const ctx = context as { metadata?: (input: { metadata: { output: string } }) => void }
ctx.metadata?.({ metadata: { output } })
}
function getEmptyResultHint(pattern: string, lang: CliLanguage): string | null {
const src = pattern.trim()
if (lang === "python") {
if (src.startsWith("class ") && src.endsWith(":")) {
const withoutColon = src.slice(0, -1)
return `💡 Hint: Remove trailing colon. Try: "${withoutColon}"`
}
if ((src.startsWith("def ") || src.startsWith("async def ")) && src.endsWith(":")) {
const withoutColon = src.slice(0, -1)
return `💡 Hint: Remove trailing colon. Try: "${withoutColon}"`
}
}
if (["javascript", "typescript", "tsx"].includes(lang)) {
if (/^(export\s+)?(async\s+)?function\s+\$[A-Z_]+\s*$/i.test(src)) {
return `💡 Hint: Function patterns need params and body. Try "function $NAME($$$) { $$$ }"`
}
}
return null
}
export const ast_grep_search = tool({
description:
"Search code patterns across filesystem using AST-aware matching. Supports 25 languages. " +
"Use meta-variables: $VAR (single node), $$$ (multiple nodes). " +
"IMPORTANT: Patterns must be complete AST nodes (valid code). " +
"For functions, include params and body: 'export async function $NAME($$$) { $$$ }' not 'export async function $NAME'. " +
"Examples: 'console.log($MSG)', 'def $FUNC($$$):', 'async function $NAME($$$)'",
args: {
pattern: tool.schema.string().describe("AST pattern with meta-variables ($VAR, $$$)"),
pattern: tool.schema.string().describe("AST pattern with meta-variables ($VAR, $$$). Must be complete AST node."),
lang: tool.schema.enum(CLI_LANGUAGES).describe("Target language"),
paths: tool.schema.array(tool.schema.string()).optional().describe("Paths to search (default: ['.'])"),
globs: tool.schema.array(tool.schema.string()).optional().describe("Include/exclude globs (prefix ! to exclude)"),
@@ -24,14 +48,23 @@ export const ast_grep_search = tool({
},
execute: async (args, context) => {
try {
const matches = await runSg({
const result = await runSg({
pattern: args.pattern,
lang: args.lang as CliLanguage,
paths: args.paths,
globs: args.globs,
context: args.context,
})
const output = formatSearchResult(matches)
let output = formatSearchResult(result)
if (result.matches.length === 0 && !result.error) {
const hint = getEmptyResultHint(args.pattern, args.lang as CliLanguage)
if (hint) {
output += `\n\n${hint}`
}
}
showOutputToUser(context, output)
return output
} catch (e) {
@@ -57,7 +90,7 @@ export const ast_grep_replace = tool({
},
execute: async (args, context) => {
try {
const matches = await runSg({
const result = await runSg({
pattern: args.pattern,
rewrite: args.rewrite,
lang: args.lang as CliLanguage,
@@ -65,7 +98,7 @@ export const ast_grep_replace = tool({
globs: args.globs,
updateAll: args.dryRun === false,
})
const output = formatReplaceResult(matches, args.dryRun !== false)
const output = formatReplaceResult(result, args.dryRun !== false)
showOutputToUser(context, output)
return output
} catch (e) {
@@ -76,83 +109,4 @@ export const ast_grep_replace = tool({
},
})
export const ast_grep_languages = tool({
description:
"List all supported languages for ast-grep tools with their file extensions. " +
"Use this to determine valid language options.",
args: {},
execute: async (_args, context) => {
const lines: string[] = [`Supported Languages (${CLI_LANGUAGES.length}):`]
for (const lang of CLI_LANGUAGES) {
const exts = LANG_EXTENSIONS[lang]?.join(", ") || ""
lines.push(` ${lang}: ${exts}`)
}
lines.push("")
lines.push(`NAPI (in-memory) languages: ${NAPI_LANGUAGES.join(", ")}`)
const output = lines.join("\n")
showOutputToUser(context, output)
return output
},
})
export const ast_grep_analyze = tool({
description:
"Parse code and extract AST structure with pattern matching (in-memory). " +
"Extracts meta-variable bindings. Only for: html, javascript, tsx, css, typescript. " +
"Use for detailed code analysis without file I/O.",
args: {
code: tool.schema.string().describe("Source code to analyze"),
lang: tool.schema.enum(NAPI_LANGUAGES).describe("Language (html, javascript, tsx, css, typescript)"),
pattern: tool.schema.string().optional().describe("Pattern to find (omit for root structure)"),
extractMetaVars: tool.schema.boolean().optional().describe("Extract meta-variable bindings (default: true)"),
},
execute: async (args, context) => {
try {
if (!args.pattern) {
const info = getRootInfo(args.code, args.lang as NapiLanguage)
const output = `Root kind: ${info.kind}\nChildren: ${info.childCount}`
showOutputToUser(context, output)
return output
}
const results = analyzeCode(args.code, args.lang as NapiLanguage, args.pattern, args.extractMetaVars !== false)
const output = formatAnalyzeResult(results, args.extractMetaVars !== false)
showOutputToUser(context, output)
return output
} catch (e) {
const output = `Error: ${e instanceof Error ? e.message : String(e)}`
showOutputToUser(context, output)
return output
}
},
})
export const ast_grep_transform = tool({
description:
"Transform code in-memory using AST-aware rewriting. " +
"Only for: html, javascript, tsx, css, typescript. " +
"Returns transformed code without writing to filesystem.",
args: {
code: tool.schema.string().describe("Source code to transform"),
lang: tool.schema.enum(NAPI_LANGUAGES).describe("Language"),
pattern: tool.schema.string().describe("Pattern to match"),
rewrite: tool.schema.string().describe("Replacement (can use $VAR from pattern)"),
},
execute: async (args, context) => {
try {
const { transformed, editCount } = transformCode(
args.code,
args.lang as NapiLanguage,
args.pattern,
args.rewrite
)
const output = formatTransformResult(args.code, transformed, editCount)
showOutputToUser(context, output)
return output
} catch (e) {
const output = `Error: ${e instanceof Error ? e.message : String(e)}`
showOutputToUser(context, output)
return output
}
},
})

View File

@@ -51,3 +51,11 @@ export interface TransformResult {
transformed: string
editCount: number
}
export interface SgResult {
matches: CliMatch[]
totalMatches: number
truncated: boolean
truncatedReason?: "max_matches" | "max_output_bytes" | "timeout"
error?: string
}

View File

@@ -1,13 +1,28 @@
import type { CliMatch, AnalyzeResult } from "./types"
import type { CliMatch, AnalyzeResult, SgResult } from "./types"
export function formatSearchResult(matches: CliMatch[]): string {
if (matches.length === 0) {
export function formatSearchResult(result: SgResult): string {
if (result.error) {
return `Error: ${result.error}`
}
if (result.matches.length === 0) {
return "No matches found"
}
const lines: string[] = [`Found ${matches.length} match(es):\n`]
const lines: string[] = []
for (const match of matches) {
if (result.truncated) {
const reason = result.truncatedReason === "max_matches"
? `showing first ${result.matches.length} of ${result.totalMatches}`
: result.truncatedReason === "max_output_bytes"
? "output exceeded 1MB limit"
: "search timed out"
lines.push(`⚠️ Results truncated (${reason})\n`)
}
lines.push(`Found ${result.matches.length} match(es)${result.truncated ? ` (truncated from ${result.totalMatches})` : ""}:\n`)
for (const match of result.matches) {
const loc = `${match.file}:${match.range.start.line + 1}:${match.range.start.column + 1}`
lines.push(`${loc}`)
lines.push(` ${match.lines.trim()}`)
@@ -17,15 +32,30 @@ export function formatSearchResult(matches: CliMatch[]): string {
return lines.join("\n")
}
export function formatReplaceResult(matches: CliMatch[], isDryRun: boolean): string {
if (matches.length === 0) {
export function formatReplaceResult(result: SgResult, isDryRun: boolean): string {
if (result.error) {
return `Error: ${result.error}`
}
if (result.matches.length === 0) {
return "No matches found to replace"
}
const prefix = isDryRun ? "[DRY RUN] " : ""
const lines: string[] = [`${prefix}${matches.length} replacement(s):\n`]
const lines: string[] = []
for (const match of matches) {
if (result.truncated) {
const reason = result.truncatedReason === "max_matches"
? `showing first ${result.matches.length} of ${result.totalMatches}`
: result.truncatedReason === "max_output_bytes"
? "output exceeded 1MB limit"
: "search timed out"
lines.push(`⚠️ Results truncated (${reason})\n`)
}
lines.push(`${prefix}${result.matches.length} replacement(s):\n`)
for (const match of result.matches) {
const loc = `${match.file}:${match.range.start.line + 1}:${match.range.start.column + 1}`
lines.push(`${loc}`)
lines.push(` ${match.text}`)

129
src/tools/glob/cli.ts Normal file
View File

@@ -0,0 +1,129 @@
import { spawn } from "bun"
import {
resolveGrepCli,
DEFAULT_TIMEOUT_MS,
DEFAULT_LIMIT,
DEFAULT_MAX_DEPTH,
DEFAULT_MAX_OUTPUT_BYTES,
RG_FILES_FLAGS,
} from "./constants"
import type { GlobOptions, GlobResult, FileMatch } from "./types"
import { stat } from "node:fs/promises"
function buildRgArgs(options: GlobOptions): string[] {
const args: string[] = [
...RG_FILES_FLAGS,
`--max-depth=${Math.min(options.maxDepth ?? DEFAULT_MAX_DEPTH, DEFAULT_MAX_DEPTH)}`,
]
if (options.hidden) args.push("--hidden")
if (options.noIgnore) args.push("--no-ignore")
args.push(`--glob=${options.pattern}`)
return args
}
function buildFindArgs(options: GlobOptions): string[] {
const args: string[] = ["."]
const maxDepth = Math.min(options.maxDepth ?? DEFAULT_MAX_DEPTH, DEFAULT_MAX_DEPTH)
args.push("-maxdepth", String(maxDepth))
args.push("-type", "f")
args.push("-name", options.pattern)
if (!options.hidden) {
args.push("-not", "-path", "*/.*")
}
return args
}
async function getFileMtime(filePath: string): Promise<number> {
try {
const stats = await stat(filePath)
return stats.mtime.getTime()
} catch {
return 0
}
}
export async function runRgFiles(options: GlobOptions): Promise<GlobResult> {
const cli = resolveGrepCli()
const timeout = Math.min(options.timeout ?? DEFAULT_TIMEOUT_MS, DEFAULT_TIMEOUT_MS)
const limit = Math.min(options.limit ?? DEFAULT_LIMIT, DEFAULT_LIMIT)
const isRg = cli.backend === "rg"
const args = isRg ? buildRgArgs(options) : buildFindArgs(options)
const paths = options.paths?.length ? options.paths : ["."]
if (isRg) {
args.push(...paths)
}
const cwd = paths[0] || "."
const proc = spawn([cli.path, ...args], {
stdout: "pipe",
stderr: "pipe",
cwd: isRg ? undefined : cwd,
})
const timeoutPromise = new Promise<never>((_, reject) => {
const id = setTimeout(() => {
proc.kill()
reject(new Error(`Glob search timeout after ${timeout}ms`))
}, timeout)
proc.exited.then(() => clearTimeout(id))
})
try {
const stdout = await Promise.race([new Response(proc.stdout).text(), timeoutPromise])
const stderr = await new Response(proc.stderr).text()
const exitCode = await proc.exited
if (exitCode > 1 && stderr.trim()) {
return {
files: [],
totalFiles: 0,
truncated: false,
error: stderr.trim(),
}
}
const truncatedOutput = stdout.length >= DEFAULT_MAX_OUTPUT_BYTES
const outputToProcess = truncatedOutput ? stdout.substring(0, DEFAULT_MAX_OUTPUT_BYTES) : stdout
const lines = outputToProcess.trim().split("\n").filter(Boolean)
const files: FileMatch[] = []
let truncated = false
for (const line of lines) {
if (files.length >= limit) {
truncated = true
break
}
const filePath = isRg ? line : `${cwd}/${line}`
const mtime = await getFileMtime(filePath)
files.push({ path: filePath, mtime })
}
files.sort((a, b) => b.mtime - a.mtime)
return {
files,
totalFiles: files.length,
truncated: truncated || truncatedOutput,
}
} catch (e) {
return {
files: [],
totalFiles: 0,
truncated: false,
error: e instanceof Error ? e.message : String(e),
}
}
}

View File

@@ -0,0 +1,12 @@
export { resolveGrepCli, type GrepBackend } from "../grep/constants"
export const DEFAULT_TIMEOUT_MS = 60_000
export const DEFAULT_LIMIT = 100
export const DEFAULT_MAX_DEPTH = 20
export const DEFAULT_MAX_OUTPUT_BYTES = 10 * 1024 * 1024
export const RG_FILES_FLAGS = [
"--files",
"--color=never",
"--glob=!.git/*",
] as const

3
src/tools/glob/index.ts Normal file
View File

@@ -0,0 +1,3 @@
import { glob } from "./tools"
export { glob }

36
src/tools/glob/tools.ts Normal file
View File

@@ -0,0 +1,36 @@
import { tool } from "@opencode-ai/plugin/tool"
import { runRgFiles } from "./cli"
import { formatGlobResult } from "./utils"
export const glob = tool({
description:
"Fast file pattern matching tool with safety limits (60s timeout, 100 file limit). " +
"Supports glob patterns like \"**/*.js\" or \"src/**/*.ts\". " +
"Returns matching file paths sorted by modification time. " +
"Use this tool when you need to find files by name patterns.",
args: {
pattern: tool.schema.string().describe("The glob pattern to match files against"),
path: tool.schema
.string()
.optional()
.describe(
"The directory to search in. If not specified, the current working directory will be used. " +
"IMPORTANT: Omit this field to use the default directory. DO NOT enter \"undefined\" or \"null\" - " +
"simply omit it for the default behavior. Must be a valid directory path if provided."
),
},
execute: async (args) => {
try {
const paths = args.path ? [args.path] : undefined
const result = await runRgFiles({
pattern: args.pattern,
paths,
})
return formatGlobResult(result)
} catch (e) {
return `Error: ${e instanceof Error ? e.message : String(e)}`
}
},
})

21
src/tools/glob/types.ts Normal file
View File

@@ -0,0 +1,21 @@
export interface FileMatch {
path: string
mtime: number
}
export interface GlobResult {
files: FileMatch[]
totalFiles: number
truncated: boolean
error?: string
}
export interface GlobOptions {
pattern: string
paths?: string[]
hidden?: boolean
noIgnore?: boolean
maxDepth?: number
timeout?: number
limit?: number
}

Some files were not shown because too many files have changed in this diff Show More