Updated test structure and assertions to match current output format.
Improved test clarity while maintaining complete coverage of markdown
validation and write restriction behavior.
Verification reminders are now centralized in sisyphus-orchestrator hook,
eliminating redundant code in start-work. The orchestrator hook handles all
verification messaging across both boulder and standalone modes.
When subagent work fails verification, show exact sisyphus_task(resume="...")
command with session_id for immediate retry. Consolidates verification workflow
across boulder and standalone modes.
- Create task-toast-manager feature with singleton pattern
- Show running task list (newest first) when new task starts
- Track queued tasks status from ConcurrencyManager
- Integrate with BackgroundManager and sisyphus-task tool
🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode) assistance
When Prometheus (Planner) spawns subagents via task tools (sisyphus_task, task, call_omo_agent), a system directive is injected into the prompt to ensure subagents understand they are in a planning consultation context and must NOT modify files.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Add hook for orchestrating Sisyphus agent workflows:
- Coordinates task execution between agents
- Manages workflow state persistence
- Handles agent handoffs
Includes comprehensive test coverage.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Add hook for detecting /start-work command and triggering
orchestrator-sisyphus agent for plan execution.
Includes test coverage.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Add hook that restricts Prometheus planner to writing only .md files
in the .sisyphus/ directory. Prevents planners from implementing.
Includes test coverage.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Add hook for injecting task resume information into tool outputs.
Enables seamless continuation of background agent sessions.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Update hook constants and configuration across agent-usage-reminder, keyword-detector, and claude-code-hooks.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- executor.ts: Added `auto: true` to summarize body, removed subsequent prompt_async call
- preemptive-compaction/index.ts: Added `auto: true` to summarize body, removed subsequent promptAsync call
- executor.test.ts: Updated test expectation to include `auto: true`
Instead of sending 'Continue' prompt after compaction, use SessionCompaction's `auto: true` feature which auto-resumes the session.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* fix: respect disabled_hooks for keyword-detector in claude-code-hooks
The keyword detection in claude-code-hooks was running regardless of
whether keyword-detector was in disabled_hooks. This caused analyze
and search modes to trigger even when explicitly disabled.
Pass keywordDetectorDisabled flag to createClaudeCodeHooksHook and
skip keyword detection when the hook is disabled.
Fixes#530
* refactor: restore keyword types in log output
Add types array back to keyword detection log for better observability
* revert: undo PR #543 changes (bun shell GC crash was misdiagnosed)
This reverts commit 4a38e70 (PR #543) and 2064568 (follow-up fix).
## Why This Revert
The original diagnosis was incorrect. PR #543 assumed Bun's
ShellInterpreter GC bug was causing Windows crashes, but further
investigation revealed the actual root cause:
**The crash occurs when oh-my-opencode's session-notification runs
alongside external notification plugins (e.g., @mohak34/opencode-notifier).**
Evidence:
- User removed opencode-notifier plugin → crashes stopped
- Release version (with original ctx.$ code) works fine when used alone
- No widespread crash reports from users without external notifiers
- Both plugins listen to session.idle and send concurrent notifications
The real issue is a conflict between two notification systems:
1. oh-my-opencode: ctx.$ → PowerShell → Windows.UI.Notifications
2. opencode-notifier: node-notifier → SnoreToast.exe
A proper fix will detect and handle this conflict gracefully.
Refs: #543, oven-sh/bun#23177, oven-sh/bun#24368
See: docs/CRASH_INVESTIGATION_TIMELINE.md (in follow-up commit)
* fix(session-notification): detect and avoid conflict with external notification plugins
When oh-my-opencode's session-notification runs alongside external
notification plugins like opencode-notifier, both listen to session.idle
and send concurrent notifications. This can cause crashes on Windows
due to resource contention between different notification mechanisms:
- oh-my-opencode: ctx.$ → PowerShell → Windows.UI.Notifications
- opencode-notifier: node-notifier → SnoreToast.exe
This commit adds:
1. External plugin detection (checks opencode.json for known notifiers)
2. Auto-disable of session-notification when conflict detected
3. Console warning explaining the situation
4. Config option 'notification.force_enable' to override
Known notification plugins detected:
- opencode-notifier
- @mohak34/opencode-notifier
- mohak34/opencode-notifier
This is the actual fix for the Windows crash issue previously
misdiagnosed as a Bun.spawn GC bug (PR #543).
Refs: #543
* docs: add crash investigation timeline explaining the real root cause
Documents the investigation journey from initial misdiagnosis (Bun GC bug)
to discovering the actual root cause (notification plugin conflict).
Key findings:
- PR #543 was based on incorrect assumption
- The real issue is concurrent notification plugins
- oh-my-opencode + opencode-notifier = crash on Windows
- Either plugin alone works fine
* fix: address review feedback - add PowerShell escaping and use existing JSONC parser
- Add back single-quote escaping for PowerShell soundPath to prevent command failures
- Replace custom stripJsonComments with existing parseJsoncSafe from jsonc-parser
- All 655 tests pass
---------
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
The keyword-detector was using ctx.client.session.get() to check parentID for
determining subagent sessions, but this API didn't reliably return parentID.
This caused non-ultrawork keywords (search, analyze) to be injected in subagent
sessions when they should only work in main sessions.
Changed to use getMainSessionID() comparison, consistent with other hooks like
session-notification and todo-continuation-enforcer.
- Replace unreliable parentID API check with mainSessionID comparison
- Add comprehensive test coverage for session filtering behavior
- Remove unnecessary session.get API call
- Fix#542: slashcommand tool returns empty content for skills
- Add lazyContentLoader to CommandInfo type
- Load skill content in formatLoadedCommand when content is empty
- Filter non-ultrawork keywords in subagent sessions
Replace Bun shell template literals (ctx.$) with node:child_process.spawn
to work around Bun's ShellInterpreter garbage collection bug on Windows.
This bug causes segmentation faults in deinitFromFinalizer during heap
sweeping when shell operations are used repeatedly over time.
Bug references:
- oven-sh/bun#23177 (closed incomplete)
- oven-sh/bun#24368 (still open)
- Pending fix: oven-sh/bun#24093
The fix applies to all platforms for consistency and safety.
Added comprehensive VERIFICATION GUARANTEE section to ultrawork prompt to enforce proof-based task completion. Includes:
- Pre-implementation success criteria definition (Functional, Observable, Pass/Fail)
- Mandatory Test Plan template for non-trivial tasks
- Execution & Evidence requirements table (Build, Test, Manual Verify, Regression)
- TDD workflow with evidence requirements
- Verification anti-patterns and blocking violations
This enhancement ensures agents must provide PROOF that something works before claiming completion - eliminating vague "it should work now" claims without evidence.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Restore [CODE RED] maximum precision requirement
- Restore YOU MUST LEVERAGE ALL AVAILABLE AGENTS directive
- Restore TELL THE USER WHAT AGENTS YOU WILL LEVERAGE NOW
- Restore explicit parallel exploration/librarian spawn workflow
- Keep mandatory ULTRAWORK MODE ENABLED! message
- Simplify constants structure for better maintainability
This addresses the issue where explore/librarian agents were being called less frequently after recent prompt changes.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Wire agent information through keyword detector hooks:
- Pass input.agent to detectKeywordsWithType in keyword-detector hook
- Pass input.agent to detectKeywordsWithType in claude-code-hooks
- Enables agent-aware ultrawork message generation
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Restructure ultrawork message generation to support agent-specific instructions.
- Extract ultrawork message components into modular constants
- Add getUltraworkMessage(agentName) function that adapts instructions based on agent type
- Support planner-specific vs default agent execution patterns
- Pass agentName parameter through detector.ts for message resolution
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Remove all sync functions from command loader (async now default)
- Remove sync load functions from skill loader (async now default)
- Add resolveSymlinkAsync to file-utils.ts
- Update all callers to use async versions:
- config-handler.ts
- index.ts
- tools/slashcommand/tools.ts
- tools/skill/tools.ts
- hooks/auto-slash-command/executor.ts
- loader.test.ts
- All 607 tests pass, build succeeds
Generated with assistance of 🤖 [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Move keyword detection from experimental.chat.messages.transform to claude-code-hooks
chat.message handler. Uses proven injectHookMessage file system approach for reliable
context injection.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Add MockMessage interface to match new message structure
- Update client mock to include messages() method
- Remove abort error detection tests that were unreliable
- Simplify error handling logic for better testability
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
- Add ContextCollector class for managing and merging context entries across sessions
- Add types and interfaces for context management (ContextEntry, ContextPriority, PendingContext)
- Create context-injector hook for injection coordination
- Refactor keyword-detector to use context-injector instead of hook-message-injector
- Update src/index.ts to initialize context-injector infrastructure
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
When using custom providers with model ID prefixes (e.g., vertex_ai/claude-sonnet-4-5),
the think mode switcher was stripping the prefix when mapping to high variants,
causing routing failures in custom LLM proxies.
Changes:
- Add extractModelPrefix() to parse and preserve prefixes like vertex_ai/, openai/, etc.
- Update getHighVariant() to preserve prefix when mapping to -high variants
- Update isAlreadyHighVariant() to check base model name (without prefix)
- Update getThinkingConfig() to check capability using base model name
- Add comprehensive tests for custom provider prefix scenarios
This fix ensures backward compatibility while supporting custom providers
that use prefixed model IDs for routing.
Fixes issue where think mode would break custom providers with prefixed models
by stripping the routing prefix during model variant switching.
- Update preemptive-compaction hook to use 1M limit when env vars set
- Update dynamic-truncator to use 1M limit for output truncation
- Update context-window-monitor to use 1M limit for usage tracking
Previously hardcoded 200k limits caused compaction at 140k tokens even
with 1M context enabled. Now respects env vars consistently with base
opencode implementation.
Fixes compaction triggering too early with Claude Sonnet 4.5 1M context.
Related to anomalyco/opencode#6660
Previous `VAR=val cmd` format only applied to first command in chains.
New `export VAR=val; cmd` format ensures variables persist for all commands.
Also increased test timeouts for todo-continuation-enforcer stability.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* fix(ralph-loop): clear orphaned state when original session no longer exists
When a session with an active ralph-loop terminates abnormally (abort, window close),
the state file remains with active: true. Previously, when a new session started,
the hook would skip the orphaned state without cleaning it up.
This fix adds session existence validation:
- Before skipping a loop owned by a different session, check if that session still exists
- If the original session no longer exists, clear the orphan state and log
- If the original session still exists, skip as before (it's another active session's loop)
Changes:
- Add checkSessionExists option to RalphLoopOptions for dependency injection
- Wire up sessionExists from session-manager as the default implementation
- Add tests for orphan state cleanup and active session preservation
* fix(ralph-loop): add error handling around checkSessionExists call
Wraps the async checkSessionExists call in try/catch for consistency
with other async operations in this file. If the check throws, logs
the error and falls back to the original behavior (not clearing state).
---------
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
- Restructure ultrawork mode message with clearer priorities
- Add TODO IS YOUR LIFELINE section emphasizing TodoWrite usage
- Enhance agent utilization principles and execution rules
- Improve clarity of zero tolerance failure policies
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Root cause: DEFAULT_TARGET_MAX_TOKENS (50k tokens ~200k chars) was too high
for webfetch outputs. Web pages can be large but most content doesn't exceed
this limit, so truncation rarely triggered.
Changes:
- Add WEBFETCH_MAX_TOKENS = 10k tokens (~40k chars) for web content
- Introduce TOOL_SPECIFIC_MAX_TOKENS map for per-tool limits
- webfetch/WebFetch now use aggressive 10k token limit
- Other tools continue using default 50k token limit
- Add comprehensive tests for truncation behavior
Fixes#195
Co-authored-by: sisyphus-dev-ai <sisyphus-dev-ai@users.noreply.github.com>
Improves readability by placing the git command on its own line instead of concatenating it directly after environment variables. The VAR=value prefix now continues to the next line with proper shell escaping.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
OpenCode's bash tool ignores args.env and uses hardcoded process.env in spawn().
Work around this by prepending GIT_EDITOR, EDITOR, VISUAL, and PAGER env vars
directly to the command string. Only applies to git commands to avoid bloating
non-git commands.
Added shellEscape() and buildEnvPrefix() helper functions to properly escape
env var values and construct the prefix string.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
The prompt_async method expects path parameter named 'id' (not 'sessionID').
This bug prevented the 'Continue' message from being sent after compaction,
causing the recovery process to fail silently due to silent error swallowing
in the empty catch block.
Fixes:
- Type definition: changed path: { sessionID: string } to path: { id: string }
- Implementation: changed path: { sessionID } to path: { id: sessionID } at 2 locations (lines 411, 509)
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
