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