* feat(mcp): restrict grep_app tools to librarian agent only
Reduces token usage by disabling grep_app MCP tools globally and enabling them only for the librarian agent, which uses them for GitHub code search during documentation lookups.
Changes:
- Add grep_app_* tool disable globally in config.tools
- Add grep_app_* tool enable for librarian agent
- Remove grep_app references from explore agent prompt (no access)
Closes#394
* chore: changes by sisyphus-dev-ai
---------
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
Replace mock.module() with spyOn() in auto-slash-command test to prevent shared module mocking from leaking to other test files. Remove unused mock.module() from think-mode test. This ensures test isolation so ralph-loop tests pass in both isolation and full suite runs.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
This hook intercepts user messages starting with '/' and REPLACES them with the actual command template output instead of injecting instructions. The implementation includes:
- Slash command detection (detector.ts) - identifies messages starting with '/'
- Command discovery and execution (executor.ts) - loads templates from ~/.claude/commands/ or similar
- Hook integration (index.ts) - registers with chat.message event to replace output.parts
- Comprehensive test coverage - 37 tests covering detection, replacement, error handling, and command exclusions
- Configuration support in HookNameSchema
Key features:
- Supports excluded commands to skip processing
- Loads command templates from user's command directory
- Replaces user input before reaching the LLM
- Tests all edge cases including missing files, malformed templates, and special commands
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
- Change charsPerToken from 4 to 2 for more aggressive truncation calculation
- Remove revert fallback (PHASE 2.5)
- Always try Continue after truncation if anything was truncated
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
When over token limit after truncation, use session.revert to remove last message instead of attempting summarize (which would also fail). Skip summarize entirely when still over limit to prevent infinite loop.
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
When session hits token limit (e.g. 207k > 200k), the summarize API also fails
because it needs to process the full 207k tokens. By truncating FIRST, we reduce
token count before attempting summarize.
Changes:
- PHASE 1: DCP (Dynamic Context Pruning) - prune duplicate tool calls first
- PHASE 2: Aggressive Truncation - always try when over limit
- PHASE 3: Summarize - last resort after DCP and truncation
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* feat(keyword-detector): show toast notification when ultrawork mode is activated
When users trigger ultrawork mode (via 'ultrawork' or 'ulw' keywords), a toast
notification now appears to confirm the mode is active. The notification is
shown once per session to avoid spamming.
Changes:
- Add detectKeywordsWithType() to identify which keyword type triggered
- Show 'Ultrawork Mode Activated' toast with success variant
- Track notified sessions to prevent duplicate toasts
Closes#392
* fix(keyword-detector): fix index bug in detectKeywordsWithType and add error logging
- Fix P1: detectKeywordsWithType now maps before filtering to preserve
original KEYWORD_DETECTORS indices. Previously, the index used was from
the filtered array, causing incorrect type assignment (e.g., 'search'
match would incorrectly return 'ultrawork' type).
- Fix P2: Replace silent .catch(() => {}) with proper error logging using
the log function for easier debugging when toast notifications fail.
---------
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
Support organizing commands in subdirectories with colon-separated naming
(e.g., myproject/deploy.md becomes myproject:deploy).
- Recursively traverse subdirectories and load all .md command files
- Prefix nested command names with directory path (colon-separated)
- Protect against circular symlinks via visited path tracking
- Skip hidden directories (consistent with other loaders)
- Graceful error handling with logging for debugging
Add doctor check for GitHub CLI (gh) that verifies:
- Binary installation status
- Authentication status with GitHub
- Account details and token scopes when authenticated
Closes#374
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
- Add LSP IN MAIN SESSION execution rule for parallel codemap building
- Restructure WORKFLOW step 2 as PARALLEL PHASE with two concurrent tracks:
- Background agents spawned via background_task for exploration/research
- Main session using LSP tools (lsp_document_symbols, lsp_workspace_symbols, lsp_goto_definition, lsp_find_references, lsp_hover) for codebase understanding
- Enables agent to build comprehensive codebase context while background agents explore in parallel
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
- Add SESSION_STORAGE constant for session metadata directory
- Add getMainSessions() function to retrieve main sessions with filtering:
- Sorts sessions by updated time (newest first)
- Filters out child sessions (with parentID)
- Filters sessions by directory path
- Update session_list tool to use new getMainSessions():
- Add project_path parameter (default: current working directory)
- Maintains existing date range filtering and limit behavior
🤖 Generated with assistance of OhMyOpenCode
Removes inline migration logic from index.ts and imports from shared/migration module.
This completes the refactoring to extract testable migration logic into a dedicated module.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Extract AGENT_NAME_MAP, HOOK_NAME_MAP, and migration functions to src/shared/migration.ts
- Add comprehensive BDD-style test suite in src/shared/migration.test.ts with 15 test cases
- Export migration functions from src/shared/index.ts
- Improves testability and maintainability of config migration logic
Tests cover:
- Agent name migrations (omo → Sisyphus, OmO-Plan → Planner-Sisyphus)
- Hook name migrations (anthropic-auto-compact → anthropic-context-window-limit-recovery)
- Config key migrations (omo_agent → sisyphus_agent)
- Case-insensitive lookups and edge cases
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Remove the FallbackState interface and related fallback recovery mechanism that deleted message pairs when all other compaction attempts failed. This simplifies the recovery strategy by eliminating the last-resort fallback approach.
Changes:
- Removed FallbackState interface and FALLBACK_CONFIG from types.ts
- Removed fallbackStateBySession from AutoCompactState
- Removed getOrCreateFallbackState and getLastMessagePair functions
- Removed emergency revert block that deleted user+assistant message pairs
- Updated clearSessionState and timeout reset logic
- Removed related test cases
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Slash commands with arguments were silently failing in OpenCode TUI because
command definitions included 'name' and 'argumentHint' fields that don't exist
in OpenCode's Command schema. Strip these fields before registration across
all command/skill loaders to ensure compatibility.
Affected loaders:
- builtin commands
- claude-code command loader
- opencode skill loader
- claude-code plugin loader
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Introduce a new dynamic prompt generation system for Sisyphus orchestrator
that leverages agent metadata for intelligent delegation. This revives the
dynamic-sisyphus-agent-prompt branch with comprehensive refactoring.
Changes:
- Add AgentPromptMetadata, AgentCategory, AgentCost, DelegationTrigger types
- Create sisyphus-prompt-builder with dynamic prompt generation logic
- Add AGENT_PROMPT_METADATA exports to all agent modules (oracle, librarian,
explore, frontend-ui-ux-engineer, document-writer, multimodal-looker)
- Refactor sisyphus.ts to use buildDynamicSisyphusPrompt()
- Add AvailableAgent type export for type safety
This enables Sisyphus to make intelligent agent selection decisions based on
agent capabilities, costs, and delegation triggers, improving orchestration
efficiency.
🤖 Generated with assistance of OhMyOpenCode
(https://github.com/code-yeongyu/oh-my-opencode)
- Step 1: Fire ALL background explore agents immediately (non-blocking)
- Step 2: Main session builds codemap understanding using LSP tools while background runs
- Step 3: Collect background results after main session analysis
This maximizes throughput by having agents discover patterns while the main session
analyzes code structure semantically via LSP.
OpenCode doesn't pass transcriptPath in the session.idle event properties,
which caused detectCompletionPromise to always return false (the first check
returns early if transcriptPath is undefined).
This fix:
- Imports getTranscriptPath from claude-code-hooks/transcript
- Generates the transcript path from sessionID instead of reading from event
- Adds optional getTranscriptPath callback to RalphLoopOptions for testability
Fixes#354
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
Enable tool-output-truncator hook by default instead of requiring experimental config opt-in. Users can disable it via disabled_hooks if needed.
Changes:
- Add tool-output-truncator to HookNameSchema
- Remove tool_output_truncator from ExperimentalConfigSchema
- Update all README files (EN, KO, JA, ZH-CN)
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Fix comment-checker/downloader.ts to use Windows-appropriate cache paths (%LOCALAPPDATA% or %APPDATA%) instead of Unix-style ~/.cache
- Guard against undefined import.meta.url in cli.ts which can occur during Windows plugin loading
- Reorder cache check before module resolution for safer fallback behavior
Fixes#347
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
- Add error classification helpers for permission, file-not-found, and filesystem errors
- Handle empty/corrupt config files gracefully with recovery suggestions
- Add 60-second timeout to runBunInstall() to prevent hanging forever
- Improve error messages with specific recovery suggestions for each error type
- Export BunInstallResult type with detailed error info (success, timedOut, error)
- Handle SyntaxError in JSON parsing with user-friendly suggestions
- Add validation for config file contents (empty, whitespace-only, non-object)
Fixes#338
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
The CLI build was missing --external @ast-grep/napi flag, causing the bundler
to inline absolute paths from the CI environment (/home/runner/work/...).
This made the doctor check for @ast-grep/napi always fail on user machines.
Fixes#344
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
