Previously, errorBypass mode was cleared on session.idle, causing continuation
to fire again on next idle event. This led to unwanted task resumption after
user abort.
Changes:
- Don't clear errorBypass on session.idle - stay in errorBypass mode
- Clear errorBypass to idle only when user sends a new message
This ensures that once user aborts, the enforcer respects that decision until
the user explicitly sends a message to resume.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
Fixes race conditions, enables continuous enforcement, and eliminates false positives/negatives.
- Complete redesign using version-token state machine for race condition prevention
- Replaced 5 separate Sets with single Map<sessionID, SessionState>
- Changed cancelCountdown() to invalidate() that ALWAYS bumps version regardless of mode
- Added background task check BEFORE starting countdown (prevents toast spam when bg tasks running)
- Added lastAttemptedAt throttling (10s minimum between attempts, set BEFORE API call)
- Removed non-interactive preemptive injection (all paths now use countdown)
- Added 3 version checks in executeInjection (start, after todo fetch, before API call)
- Removed remindedSessions flag for continuous enforcement
Fixes:
1. Race condition where session.idle fired before message.updated cleared reminded state
2. Single-shot behavior that prevented multiple reminders
3. Phantom reminders sent even after agent started working
4. Toast spam when background tasks are running
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
DCP was failing to find session messages because it was looking in
~/.config/opencode/sessions instead of ~/.local/share/opencode/storage.
Unified all hooks to use getOpenCodeStorageDir() for cross-platform consistency.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* fix: disable todo-continuation for plan mode agents
Plan mode agents (e.g., 'plan', 'Planner-Sisyphus') only analyze and plan,
they don't implement. The todo-continuation hook was incorrectly triggering
for these agents because the existing write permission check only looked at
the stored message's tools field, not the agent's permission configuration.
This fix adds an explicit check for plan mode agents by name to skip the
todo continuation prompt injection.
Fixes#293
* chore: changes by sisyphus-dev-ai
* fix: address review comments for plan mode agent check
- Use exact match for plan mode agents instead of substring match to
prevent false positives on agents like 'deployment-planner'
- Add plan mode agent check to preemptive injection path (non-interactive
mode) which was missing from the initial fix
---------
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
- Remove eager SG_CLI_PATH constant; use getSgCliPath() lazily in checkEnvironment()
- Move setInterval to inside createCommentCheckerHooks() with guard flag
These changes eliminate module-level side effects that could trigger segfaults
during plugin initialization on Bun 1.3.5 + macOS 15 due to createRequire()
being called during module evaluation.
Fixes#292
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
Refactored state management to use a single source of truth per-session using
a state machine pattern with versioning. Key improvements:
- Replace multiple Sets with unified SessionState map for cleaner logic
- Add version tokens to invalidate pending callbacks on state changes
- Improve countdown timer management with proper cleanup
- Add throttle check to prevent rapid injection spam (10s minimum interval)
- Enhance injection checks: re-verify todos before injection, check bg tasks
- Handle message.part.updated events for streaming activity detection
- Add isMainSession() helper for consistent session filtering
- Clearer event handler logic with inline comments explaining state transitions
- Better logging for debugging state changes and decision points
State modes: idle → countingDown → injecting → idle (with recovery/errorBypass)
Prevents race conditions from async operations and UI state changes during countdown.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
The DCP pruning modules were using a hardcoded path (~/.config/opencode/sessions) that doesn't exist.
Sessions are actually stored at ~/.local/share/opencode/storage/message.
All pruning modules now import MESSAGE_STORAGE from hook-message-injector, which uses the correct path via getOpenCodeStorageDir().
This fixes the issue where DCP would fail with 'message dir not found' when trying to recover from token limit errors.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
- Add customPrompt parameter to runCommentChecker function
- Pass --prompt flag to comment-checker CLI when custom_prompt is configured
- Wire up config from plugin initialization
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Previously, the validator only checked for tool_use parts, causing 'Expected thinking but found text' errors when messages had text content. Renamed hasToolParts to hasContentParts to include both tool_use and text types.
Also added CommentCheckerConfigSchema support for custom prompt configuration.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
Expand the search range when finding empty messages by index to better handle API index vs storage index mismatches. This increases robustness when searching for messages to sanitize with more fallback indices.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
Pre-emptively fix empty messages in sessions before running document compression to prevent summarization failures. This prevents accumulation of empty message placeholders that can interfere with context management.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
- Refactored DCP (Dynamic Context Pruning) to execute FIRST when token limit errors occur
- Previously, DCP only ran as a fallback after compaction failed
- Now DCP runs first to prune redundant context, then compaction executes immediately
- Simplified config flag: dcp_on_compaction_failure → dcp_for_compaction
- Updated documentation in all 4 README files (EN, KO, JA, ZH-CN)
- Updated schema.ts with new config field name and documentation
- Updated executor.ts with new DCP-first logic flow
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- 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)
* 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)
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>
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
- 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>
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>
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>
- 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)
- 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)
* fix: Notification hook works weirdly for subagent sessions
- Added mainSessionID check to prevent notifications in subagent sessions
- Only trigger notifications for main session when waiting for user input
- Added comprehensive tests to validate the fix
Issue: https://github.com/code-yeongyu/oh-my-opencode/issues/92
* chore: changes by sisyphus-dev-ai
---------
Co-authored-by: codingsh <codingsh@pm.me>
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
Create directory-specific knowledge bases for high-complexity directories:
- src/hooks/AGENTS.md: Documents 21 hooks across 86 files
- src/tools/AGENTS.md: Documents 11 LSP tools, AST-Grep, MCP, background tasks (50 files)
- src/features/AGENTS.md: Documents 6 Claude Code compatibility features (24 files)
Root AGENTS.md updated to reference these specialized guides while maintaining project overview. Enables better navigation and reduces cognitive load for developers working in specific areas.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
- Check if metadata is empty before using it
- Wrap output.output in structured object when metadata is missing
- Ensures plugin tools (call_omo_agent, background_task, task) that return strings are properly recorded in transcripts instead of empty {}
🤖 Generated with assistance of OhMyOpenCode
When sending the 'Continue' message after compaction, now includes the
original agent parameter from the stored message. Previously, the Continue
message was sent without the agent parameter, causing OpenCode to use the
default 'build' agent instead of preserving the original agent context
(e.g., Sisyphus).
Implementation:
- Get messageDir using getMessageDir(sessionID)
- Retrieve storedMessage using findNearestMessageWithFields
- Pass agent: storedMessage?.agent to promptAsync body
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Previously, first messages were skipped entirely to avoid interfering with title generation.
Now, keywords detected on the first message are injected directly into the message parts
instead of using the hook message injection system, allowing keywords like 'ultrawork' to
activate on the first message of a session.
This change:
- Removes the early return that skipped first message keyword detection
- Moves keyword context generation before the isFirstMessage check
- For first messages: transforms message parts directly by prepending keyword context
- For subsequent messages: maintains existing hook message injection behavior
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Detect and warn about interactive commands (vim, nano, less, etc.)
- Filter out descriptive entries with parentheses from pattern matching
🤖 GENERATED WITH ASSISTANCE OF OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
- Add npm_config_yes, PIP_NO_INPUT, YARN_ENABLE_IMMUTABLE_INSTALLS env vars
- Add SHELL_COMMAND_PATTERNS documentation for common command patterns
- Document good/bad patterns for npm, apt, pip, git, system commands
- List banned commands that will always hang (editors, pagers, REPLs)
- Include workarounds for scripts requiring input (yes pipe, heredoc)
Adds getMessageDir() helper function and fallback logic in the session.idle event handler to retrieve stored model information (providerID/modelID) when the API response lacks these fields. This mirrors the approach used in todo-continuation-enforcer hook to ensure preemptive compaction can proceed even when model info is missing from the initial response.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Previously, remindedSessions was only cleared when assistant finished
with finish=true. If agent stopped mid-task (ESC, error), the session
stayed 'reminded' forever, preventing future continuations.
Now also clears remindedSessions when user sends a new message,
allowing continuation to trigger again after user interaction.
* Fix AGENTS.md injection not working with batch tool (#141)
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
* Extend batch tool support to rules-injector
The rules-injector hook now captures file paths from batch tool calls, enabling it to inject rules into files read via the batch tool. This ensures all injection hooks work correctly for all file access patterns.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
- Limit preemptive compaction to Claude models only (opus, sonnet, haiku pattern)
- Add support for detecting `anthropic-beta: context-1m-*` header to use 1M context limit for Sonnet models
- Add `getModelLimit` callback to read model limits from OpenCode config (`provider.*.models.*.limit.context`)
- Remove hardcoded MODEL_CONTEXT_LIMITS and replace with pattern-based model detection
- Cache model context limits from config at startup for performance
This enables flexible per-model context limit configuration without hardcoding limits in the plugin.
Generated with assistance of OhMyOpenCode
- Fixed bug where remindedSessions was never cleared after assistant response
- Now clears reminded state when assistant finishes (finish: true)
- Allows TODO continuation to trigger again after each assistant response
- Ensures continuation prompt can be injected multiple times if needed in long sessions
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Added BeforeSummarizeCallback type to allow injecting context before session summarization
- Added onBeforeSummarize option to PreemptiveCompactionOptions
- Created compaction-context-injector module that injects summarization instructions with sections:
- User Requests (As-Is)
- Final Goal
- Work Completed
- Remaining Tasks
- MUST NOT Do (Critical Constraints)
- Wired up callback invocation in preemptive-compaction before calling summarize API
- Exported new hook from src/hooks/index.ts
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add messageIndex field to ParsedTokenLimitError type for tracking message position
- Extract message index from 'messages.N' format in error messages using regex
- Update fixEmptyMessages to accept optional messageIndex parameter
- Target specific empty message by index instead of fixing all empty messages
- Apply replaceEmptyTextParts before injectTextPart for better coverage
- Remove experimental flag requirement - non-empty content errors now auto-recover by default
- Fixes issue where compaction could create empty messages at positions other than the last message
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Raise the preemptive compaction trigger point from 80% to 85% to reduce false-positive compactions and allow longer session contexts before automatic compaction kicks in.
🤖 Generated with assistance of OhMyOpenCode
