- Add AntigravityTokenRefreshError custom error class with code, description, and status fields
- Implement parseOAuthErrorPayload() for parsing Google's various OAuth error response formats
- Add retry logic with exponential backoff (3 retries, 1s→2s→4s delay) for transient failures
- Add special handling for invalid_grant error - immediately throws without retry and clears caches
- Add invalidateProjectContextByRefreshToken() for selective cache invalidation
- Update fetch.ts error handling to work with new error class and cache invalidation
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
The installed_plugins.json file has two versions:
- v1: plugins stored as direct objects
- v2: plugins stored as arrays
Use discriminated union types (InstalledPluginsDatabaseV1/V2) for proper
type narrowing based on version field.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* fix: defer config error toast to session.created for TUI readiness
Removed showToast calls from loadConfigFromPath() function. Error notifications were not visible during plugin initialization because the TUI was not ready yet.
Changes:
- Removed immediate showToast calls from validation error handler
- Removed immediate showToast calls from file load error handler
- Errors are still captured via addConfigLoadError() for later display
- auto-update-checker hook will display errors via showConfigErrorsIfAny() after session.created event
This ensures error messages are displayed when the TUI is fully ready and able to render them properly.
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* fix: await config error toast before showing startup toast
Ensure config errors are awaited and displayed before the startup spinner toast is shown. Changed showConfigErrorsIfAny(ctx).catch(() => {}) to await showConfigErrorsIfAny(ctx) to guarantee proper error handling order.
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Make DCP behavior opt-in via new 'dcp_on_compaction_failure' experimental flag (disabled by default).
When enabled, Dynamic Context Pruning only executes after summarization fails, then retries compaction. By default, DCP runs before truncation as before.
Changes:
- Add 'dcp_on_compaction_failure' boolean flag to experimental config (default: false)
- Update executor.ts to check flag before running DCP behavior
- Add corresponding documentation to all 4 README files (EN, KO, JA, ZH-CN)
- Update JSON schema
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
When getContextWindowUsage returns null (no assistant messages yet, API
failure, or first request in session), the truncator was returning
untruncated output. This caused context overflow crashes on early
requests or when usage lookup failed.
Now applies conservative truncation (50k tokens) as fallback, preventing
prompt-too-long errors that crash sessions.
Fixes#276 - The look_at tool was constructing invalid file:// URLs on Windows
by using template literals. Now uses Node.js pathToFileURL() which correctly
handles backslashes, spaces, and the triple-slash prefix required on Windows.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
The test mock for ctx.$ was not handling tagged template literals correctly,
causing it to ignore interpolated values. Additionally, utility functions that
check for command availability (osascript, notify-send, etc.) were returning
null in test environments, causing sendNotification to exit early.
Changes:
- Fixed template literal reconstruction in mock $ function
- Added spyOn mocks for all utility path functions
- All session-notification tests now passing (11/11)
Fixes#273
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
- Add process.exit(0) in runner.ts for immediate termination
- Fix Timer type to ReturnType<typeof setInterval> in manager.ts
- Add .unref() to BackgroundManager polling interval
- Add cleanup() method to BackgroundManager
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add new CLI command 'get-local-version' to display current version and check for updates
- Reuses existing version checking infrastructure from auto-update-checker
- Supports both human-readable and JSON output formats
- Handles edge cases: local dev mode, pinned versions, network errors
- Provides colored terminal output with picocolors
- Closes#260
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
Fixes#255
- Add getClaudeConfigDir() utility function that respects CLAUDE_CONFIG_DIR env var
- Update all hardcoded ~/.claude paths to use the new utility
- Add comprehensive tests for getClaudeConfigDir()
- Maintain backward compatibility with default ~/.claude when env var is not set
Files updated:
- src/shared/claude-config-dir.ts (new utility)
- src/shared/claude-config-dir.test.ts (tests)
- src/hooks/claude-code-hooks/config.ts
- src/hooks/claude-code-hooks/todo.ts
- src/hooks/claude-code-hooks/transcript.ts
- src/features/claude-code-command-loader/loader.ts
- src/features/claude-code-agent-loader/loader.ts
- src/features/claude-code-skill-loader/loader.ts
- src/features/claude-code-mcp-loader/loader.ts
- src/tools/session-manager/constants.ts
- src/tools/slashcommand/tools.ts
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
- Add thinking-block-validator hook for proactive prevention before API calls
- Enhance session-recovery to include previous thinking content
- Fix hook registration to actually invoke the validator
Addresses extended thinking errors with Claude Opus/Sonnet 4.5 using tool calls.
Related: https://github.com/vercel/ai/issues/7729
Related: https://github.com/sst/opencode/issues/2599
Include output tokens from last response in getContextWindowUsage calculation.
Output tokens become part of next request's input (conversation history), so
they must be counted to avoid overestimating remainingTokens. This aligns with
preemptive-compaction's calculation which already includes output tokens correctly.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Apply dynamic truncation to rules-injector, directory-readme-injector, and directory-agents-injector
- Add truncation notice encouraging users to read full content
- Save context window space while maintaining awareness of complete documentation
- Resolves#221 (part 1)
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
- Renamed sisyphus_agent.builder_enabled to default_builder_enabled for clarity
- Removed sisyphus_agent.replace_build option entirely
- Default build agent is now always demoted to subagent mode when Sisyphus is enabled
- Updated schema and regenerated JSON schema
- Updated all documentation (EN, KO, JA, ZH-CN)
BREAKING CHANGE: Configuration migration required for users using builder_enabled or replace_build options.
Closes#250
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
* fix: show error messages when oh-my-opencode.json config fails to load
- Add console.error output for config parse errors (syntax errors)
- Add console.error output for config validation errors (schema violations)
- Display helpful hints for JSON syntax errors
- List all validation errors clearly with proper formatting
- Errors now shown immediately regardless of hook configuration
Fixes#241
* refactor: replace console.error with toast notifications for config errors
- Replace console.error with ctx.client.tui.showToast() for better UX
- Show toast notifications for both syntax errors and validation errors
- Toast notifications persist for 10 seconds for visibility
- Display error details with bullet points for validation errors
- Include helpful hints for JSON syntax errors
This provides a more user-friendly notification system that integrates
with OpenCode's UI instead of just logging to console.
---------
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
Fixes#191
This commit ensures that the user's selected model is preserved when
background tasks complete and notify their parent sessions.
Changes:
- Add parentModel field to BackgroundTask and LaunchInput interfaces
- Capture model context when launching background tasks
- Pass model context when notifying parent sessions after task completion
Impact:
- Users with OAuth providers (Google, Anthropic) will now have their
model selection preserved across background task continuations
- Background agents no longer revert to hardcoded defaults
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
When session.error occurs with incomplete todos, the run command now:
- Captures the error via handleSessionError()
- Exits with code 1 instead of waiting indefinitely
- Shows clear error message to user
Previously, run command ignored session.error events, causing infinite
'Waiting: N todos remaining' loop when agent errors occurred.
🤖 Generated with assistance of OhMyOpenCode
https://github.com/code-yeongyu/oh-my-opencode
Fixes the race condition where the todo continuation hook would inject a
continuation prompt even when all todos had been completed during the
countdown period.
The root cause was that executeAfterCountdown() used stale todo data from
the initial session.idle check without re-verifying that incomplete todos
still existed after the countdown finished.
Changes:
- Add fresh todo verification in executeAfterCountdown() before prompt injection
- Use fresh todo data in the continuation prompt message
- Abort injection if no incomplete todos remain after countdown
This properly handles the case where:
1. session.idle fires (e.g., user enters shell mode in TUI)
2. Initial check finds incomplete todos, starts countdown
3. During countdown, todos get completed
4. Countdown ends, fresh check detects no incomplete todos
5. Hook aborts instead of injecting stale prompt
Fixes#234
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
- logEventVerbose() logs all event types including message content, tool calls, and results
- Session tags distinguish main vs child sessions for multi-session tracking
- completion.ts error logging instead of silently swallowing API errors
- Helps diagnose realtime streaming behavior in CI environments
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
- Remove DEFAULT_TIMEOUT_MS (set to 0) to allow CI agent runs to complete without timeout
- Add stdbuf -oL -eL for unbuffered realtime output in GitHub Actions
- Update timeout logic to only set timeout when value > 0
This fixes CI agent runs that were timing out after 30 minutes and not showing realtime output.
🤖 Generated with assistance of OhMyOpenCode
Previously, the condition '&&plannerEnabled&&replacePlan' caused agents to be
completely removed instead of demoted to subagent mode. The logic incorrectly
prevented agents from being added back as subagents when Sisyphus is enabled
with default config.
Fixed by simplifying to just 'replacePlan' condition - agents are now properly
demoted to subagent mode when replacement is enabled, which is the intended
behavior per the README.
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Renamed agent from 'Builder-Sisyphus' to 'OpenCode-Builder' in schema and config
- Removed BUILD_SYSTEM_PROMPT and BUILD_PERMISSION custom overrides
- Now uses OpenCode's default build agent configuration exactly
- Simplified agent configuration to rely on OpenCode defaults
🤖 Generated with assistance of OhMyOpenCode
Fixes#200
## Problem
When executeCompact() recovery fails unexpectedly or gets interrupted,
the compactionInProgress lock is never cleared, permanently blocking both
auto-compact AND manual /compact for the session.
## Root Cause
- No try/finally around lock acquisition (line 261)
- Silent blocking when lock held - no user feedback
- Lock cleanup scattered across 7 manual deletion points
- Any unexpected exception bypasses cleanup, leaving lock stuck forever
## Solution
1. **Try/Finally Lock Guarantee**: Wrapped entire executeCompact body in
try/finally block to guarantee lock cleanup, following the pattern
used in preemptive-compaction hook
2. **User Feedback**: Added toast notification when compact attempt is
blocked by existing lock, replacing silent failure with clear warning
3. **Removed Redundancy**: Removed 6 redundant manual lock deletions
(kept only clearSessionState and finally block)
## Testing Evidence
✅ 10/10 comprehensive tests pass
✅ Lock cleared on successful completion
✅ Lock cleared when summarize throws
✅ Lock cleared when revert throws
✅ Lock cleared when fixEmptyMessages executes
✅ Lock cleared when truncation is sufficient
✅ Lock cleared after max recovery attempts
✅ Lock cleared when toast fails
✅ Lock cleared when prompt_async throws
✅ Toast shown when lock already held
✅ TypeScript type check passes with zero errors
## Files Changed
- executor.ts: Added try/finally, toast notification, removed 6 redundant deletions
- executor.test.ts: New comprehensive test suite (10 tests, 13 assertions)
## Impact
- Severity: High → Fixed
- User Experience: No more stuck sessions requiring restart
- Behavior: Identical except lock now guaranteed to clear
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
- Filter out original 'build' and 'plan' agents when Builder-Sisyphus/Planner-Sisyphus are enabled with replacement
- Previously both agents could coexist even with replace_build/replace_plan: true
- Now only the replacement agent exists when both enabled and replacement flags are true
- Maintains backward compatibility for all configuration combinations
Fixes#231
The SDK yields events directly as the payload without wrapping in { payload: ... }.
Changed processEvents to treat event as the payload directly instead of looking
for event.payload. This fixes the 'Waiting for completion...' hang in GitHub
Actions where all events were being silently skipped.
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Added message.part.updated event handling for incremental text streaming
- Added tool.execute event to display tool calls with input previews
- Added tool.result event to show truncated tool result outputs
- Enhanced EventState with lastPartText and currentTool tracking
- Defined MessagePartUpdatedProps, ToolExecuteProps, ToolResultProps types
- Updated event tests to cover new state fields
This enables the CLI run command to display real-time agent output similar to the native opencode run command, improving user experience with immediate feedback on tool execution.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
Add missing mock exports (SESSION_LIST_DESCRIPTION, SESSION_READ_DESCRIPTION,
SESSION_SEARCH_DESCRIPTION, SESSION_INFO_DESCRIPTION, SESSION_DELETE_DESCRIPTION,
TOOL_NAME_PREFIX) to fix test failures when other test files import from constants.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
Tests now properly mock the constants module before importing storage functions,
ensuring test data is read/written to temp directories instead of real paths.
This fixes test isolation issues and allows tests to run independently.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
The tool() wrapper from @opencode-ai/plugin requires execute(args, context: ToolContext) signature. Updated all session-manager tool functions (session_list, session_read, session_search, session_info) to accept the context parameter, and updated corresponding tests with mockContext.
🤖 Generated with assistance of OhMyOpenCode
- Add new 'run' command using @opencode-ai/sdk to manage agent sessions
- Implement recursive descendant session checking (waits for ALL nested child sessions)
- Add completion conditions: all todos done + all descendant sessions idle
- Add SSE event processing for session state tracking
- Fix todo-continuation-enforcer to clean up session tracking
- Comprehensive test coverage with memory-safe test patterns
Unlike 'opencode run', this command ensures the agent completes all tasks
by recursively waiting for nested background agent sessions before exiting.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
* feat(tools): add session management tools for OpenCode sessions
- Add session_list tool for listing sessions with filtering
- Add session_read tool for reading session messages and history
- Add session_search tool for full-text search across sessions
- Add session_info tool for session metadata inspection
- Add comprehensive tests for storage, utils, and tools
- Update documentation in AGENTS.md
Closes#132
* fix(session-manager): add Windows compatibility for storage paths
- Create shared/data-path.ts utility for cross-platform data directory resolution
- On Windows: uses %LOCALAPPDATA% (e.g., C:\Users\Username\AppData\Local)
- On Unix: uses $XDG_DATA_HOME or ~/.local/share (XDG Base Directory spec)
- Update session-manager/constants.ts to use getOpenCodeStorageDir()
- Update hook-message-injector/constants.ts to use same utility
- Remove dependency on xdg-basedir package in session-manager
- Follows existing pattern from auto-update-checker for consistency
---------
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
- Change truncate_all_tool_outputs default from false to true
- Update schema.ts to use .default(true) instead of .optional()
- Update documentation in all README files (EN, KO, JA, ZH-CN)
- Rebuild JSON schema with new default value
This prevents prompts from becoming too long by dynamically truncating
all tool outputs based on context window usage. Users can opt-out by
setting experimental.truncate_all_tool_outputs to false.
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
- Changed truncate_all_tool_outputs default from false to true
- Updated schema documentation to reflect new default
- Added entry in README experimental features table
- Regenerated JSON schema
This prevents prompts from becoming too long by dynamically
truncating output from all tool calls, not just whitelisted ones.
Feature is experimental and enabled by default to help manage
context window usage across all tools.
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
Detects non-interactive environments (CI, opencode run) and prevents session idle when:
- Background tasks are still running
- Incomplete todos remain in the queue
Changes:
- Add isNonInteractive() detector for CI/headless environment detection
- Export detector from non-interactive-env hook module
- Enhance todo-continuation-enforcer to inject prompts BEFORE session.idle
- Pass BackgroundManager to todo-continuation-enforcer for task status checks
This fix prevents `opencode run` from exiting prematurely when work is pending.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
The api: "antigravity" field being added to opencode.json causes
authentication failures with the antigravity plugin.
Fixes: NoeFabris/opencode-antigravity-auth#49
