- 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)
- Embed files directly in message parts using file:// URL format
- Remove dependency on Read tool for multimodal-looker agent
- Add inferMimeType helper for proper MIME type detection
- Disable read tool in agent tools config (no longer needed)
- Upgrade multimodal-looker model to gemini-3-flash
- Update all README docs to reflect gemini-3-flash change
Fixes#126🤖 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)
OpenCode has native skill support that automatically scans .claude/skills/
and injects available_skills into system prompt. The agent reads SKILL.md
files directly via the Read tool, making our separate skill tool a duplicate.
The claude-code-skill-loader feature (which converts skills to slash
commands) is intentionally kept - only the redundant skill tool is removed.
🤖 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.
Previously, the code was explicitly removing the model property from user config overrides before merging, which prevented users from overriding agent models via config.
This change allows user config like:
{
"agents": {
"librarian": {
"model": "google/gemini-3-flash-preview"
}
}
}
to properly override the default agent models.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* 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)
Change the 'Frontend Files' section from a hard block that delegates ALL frontend changes to a more nuanced decision gate that classifies changes before action. Visual/UI/UX changes (styling, layout, animation) should be delegated to frontend-ui-ux-engineer, while pure logic changes can be handled directly.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
- Convert XML tags to Markdown headers for better Gemini compatibility
- Preserve all essential content while condensing verbose sections
- Add back missing principles like 'Understand why code is structured'
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
When overriding an agent's model to a different provider, the agent
now automatically gets provider-appropriate reasoning options:
- GPT models: `reasoningEffort`, `textVerbosity`
- Anthropic models: `thinking` with `budgetTokens`
## Why utils.ts changes are required
The original flow merges overrides onto pre-built agent configs:
mergeAgentConfig(sisyphusAgent, { model: "gpt-5.2" })
// Result: { model: "gpt-5.2", thinking: {...} }
The `thinking` config persists because it exists in the pre-built
`sisyphusAgent`. GPT models ignore `thinking` and need `reasoningEffort`.
The fix: call the agent factory with the resolved model, so the factory
can return the correct provider-specific config:
buildAgent(createSisyphusAgent, "gpt-5.2")
// Result: { model: "gpt-5.2", reasoningEffort: "medium" }
Closes#144🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
- 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
The empty message recovery is now enabled by default (no longer experimental).
Removes the config option from schema and all README files.
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- 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)
This file exported BUILD_AGENT_PROMPT_EXTENSION but was never imported
or used anywhere in the codebase, making it dead code that could be safely removed.
🤖 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
Monitor token usage after assistant responses and automatically trigger session
compaction when exceeding configured threshold (default 80%). Toast notifications
provide user feedback on compaction status.
Controlled via experimental.preemptive_compaction config option.
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
Implements dual-path config resolution on Windows to ensure backward compatibility
while maintaining cross-platform consistency. Checks ~/.config first (new standard),
falls back to %APPDATA% for existing installations.
Resolves#129🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Reduce COUNTDOWN_SECONDS from 5 to 2 for faster reminder display
- Remove logic that clears remindedSessions on assistant response to prevent re-triggering
- Ensures todo continuation reminder displays exactly once per session
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Remove dedicated prove-yourself mode (frustration keyword detector)
- Add ZERO TOLERANCE FAILURES section to ultrawork mode
- Consolidate completion enforcement rules: no scope reduction, no partial completion, no assumed shortcuts, no premature stopping
- Simplify constants by removing separate frustration handler
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
- Replace recursive retry mechanism with explicit session.prompt_async('Continue')
- Clear all compaction state after successful revert to prevent state corruption
- Prevents infinite retry loops and improves session reliability
🤖 Generated with assistance of oh-my-opencode
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Changes:
- Add main session check: skip toast for subagent sessions
- Move todo validation BEFORE countdown: only start countdown when incomplete todos actually exist
- Improve toast message to show remaining task count
This fixes the issue where countdown toast was showing on every idle event, even when no todos existed or in subagent sessions.
Implement countdown toast feature showing visual feedback before todo continuation:
- Changed from 5-second timeout to interval-based countdown
- Shows toast every second: "Resuming in 5s...", "Resuming in 4s...", etc.
- Toast duration set to 900ms to prevent overlap
- Countdown cancels on user message, session error, or session deletion
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- GIT_EDITOR, EDITOR, VISUAL, GIT_SEQUENCE_EDITOR set to 'true' to block editor invocations during git operations like rebase
- GIT_PAGER, PAGER set to 'cat' to disable pagination
- Fixes issue where git rebase --continue was still opening nvim despite existing non-interactive env vars
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Run update check in background after startup (non-blocking)
- Auto-update pinned versions in config file when newer version available
- Add auto_update config option to disable auto-updating
- Properly invalidate package cache after config update
- Scoped regex replacement to avoid editing outside plugin array
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Reduce analyze-mode agent recommendations from aggressive (10+ agents, 3+ explore, 3+ librarian, 2+ general, 3+ oracle) to moderate (1-2 explore, 1-2 librarian, oracle only if complex) for simple requests like "살펴봐줘". Previous settings caused unnecessary agent spawning and token consumption for straightforward analysis tasks. New recommendation prioritizes context gathering with direct tools (Grep, AST-grep) for typical workflows, reserving oracle consultation for genuinely complex scenarios (architecture, multi-system, debugging after failures).
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
The grep-output-truncator hook was never registered in index.ts, so grep
output was not being truncated since commit 03a4501 which removed grep/Grep
from tool-output-truncator's TRUNCATABLE_TOOLS list.
- Remove unused grep-output-truncator.ts
- Add "grep" and "Grep" back to tool-output-truncator's TRUNCATABLE_TOOLS
Co-authored-by: Claude <noreply@anthropic.com>
- Removes package from node_modules, package.json dependencies, AND bun.lock (workspaces.dependencies + packages)
- Fixes issue where 'update available' notification appeared but actual update didn't happen on restart due to bun.lock pinning old version
- Added BunLockfile interface and stripTrailingCommas helper for JSON parsing
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* docs: rename OmO agent to Sisyphus, OmO-Plan to Planner-Sisyphus
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* refactor: rename OmO agent to Sisyphus with automatic config migration
- Rename OmO agent to Sisyphus (uses mythological pushing-the-boulder concept)
- Rename OmO-Plan to Planner-Sisyphus for consistency
- Update config schema: omo_agent → sisyphus_agent
- Add backward compatibility: automatically migrate user's oh-my-opencode.json files
- Migration handles old keys (OmO, omo, OmO-Plan, omo-plan) and rewrites config when detected
- Update agent name mappings, index files, and type definitions
- Add Sisyphus PNG asset to brand identity
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* docs: add Sisyphus mythology introduction and teammates concept to all READMEs
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* feat(startup-toast): show Sisyphus steering message when enabled
- Updated startup toast to show "Sisyphus on steroids is steering OpenCode" when Sisyphus agent is enabled
- Refactored getToastMessage function to handle conditional message rendering
- Pass isSisyphusEnabled flag from plugin configuration to auto-update-checker hook
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* docs(sisyphus): add philosophical context to Sisyphus agent identity
- Add "Why Sisyphus?" explanation connecting the daily work cycle of humans and AI agents
- Emphasize code quality expectations: indistinguishable from senior engineer's work
- Concise identity statement: work, delegate, verify, ship without AI slop
This clarifies the agent's purpose and reinforces the principle that quality code should not reveal whether it was written by human or AI.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Remove the config file path from the startup toast message. The toast now
only displays 'OpenCode is now on Steroids. oMoMoMoMo...' for a cleaner
user experience. Also removed the unused getUserConfigPath import.
🤖 Generated with assistance of OhMyOpenCode
* feat(anthropic-auto-compact): add aggressive truncation and empty message recovery
Add truncateUntilTargetTokens method, empty content recovery mechanism, and
emptyContentAttemptBySession tracking for robust message handling.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* feat(session-recovery): add auto-resume and recovery callbacks
Implement ResumeConfig, resumeSession() method, and callback support for
enhanced session recovery and resume functionality.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
* feat(config): add experimental config schema for gating unstable features
This adds a new 'experimental' config field to the OhMyOpenCode schema that enables fine-grained control over unstable/experimental features:
- aggressive_truncation: Enables aggressive token truncation in anthropic-auto-compact hook for more aggressive token limit handling
- empty_message_recovery: Enables empty message recovery mechanism in anthropic-auto-compact hook for fixing truncation-induced empty message errors
- auto_resume: Enables automatic session resume after recovery in session-recovery hook for seamless recovery experience
The experimental config is optional and all experimental features are disabled by default, ensuring backward compatibility while allowing early adopters to opt-in to cutting-edge features.
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
- Created src/shared/config-errors.ts to isolate config error state management
- Removed function re-exports (getConfigLoadErrors, clearConfigLoadErrors) from main index.ts
- Only ConfigLoadError type is re-exported from main module to avoid OpenCode calling it as a plugin
- Updated auto-update-checker hook to import from shared/config-errors instead of main index
- Fixes "TypeError: undefined is not an object" crash when OpenCode iterated through ALL exports and called clearConfigLoadErrors(input) which returned undefined
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Previously, background_cancel(all=true) only cancelled direct child tasks, leaving grandchildren and deeper nested tasks uncancelled. This caused background agents to continue running even when their parent session was cancelled.
Changes:
- Added getAllDescendantTasks() method to BackgroundTaskManager for recursive task collection
- Updated background_cancel to use getAllDescendantTasks instead of getTasksByParentSession
- Added comprehensive test coverage for nested task cancellation scenarios
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
