oh-my-opencode
The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools
Description
The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools
Release History
| Version | Changes | Urgency | Date |
|---|---|---|---|
| 3.17.4 | Imported from npm (3.17.4) | Low | 4/21/2026 |
| v3.17.4 | ## Minor Compatibility and Stability Release This release carries compatibility-facing behavior changes and operational hardening. Read the summary below before upgrading or publishing. - Task and tool behavior updates, including delegate-task contract and runtime registration behavior. ## Commit Summary - 9b72bf8e Merge pull request #3467 from code-yeongyu/refactor/delegate-task-metadata-hardening - d612549b Merge pull request #3468 from code-yeongyu/fix/bugs-3429-3459 - 7bc170fb fix: insta | High | 4/16/2026 |
| v3.17.3 | ## What's Changed ### Fixes - **fix(posthog): disable exception autocapture to stay within free tier** by @code-yeongyu in #3441 - Error tracking exceeded 100K free tier limit (188K in 5 days) - Disabled `enableExceptionAutocapture` in both CLI and plugin clients - Manual `captureException` for critical run failures preserved - **fix(cli): use getAgentRuntimeName for agent resolution in run command** by @code-yeongyu - **fix(grep): handle Windows drive-letter paths and CRLF in parseOutput | High | 4/15/2026 |
| v3.17.2 | ## Minor Compatibility and Stability Release This release carries compatibility-facing behavior changes and operational hardening. Read the summary below before upgrading or publishing. - Rename transition updates across package detection, plugin/config compatibility, and install surfaces. - Task and tool behavior updates, including delegate-task contract and runtime registration behavior. - Install and publish workflow hardening, including safer release sequencing and package/install fixes. | Medium | 4/13/2026 |
| v3.17.0 | ## Minor Compatibility and Stability Release This release carries compatibility-facing behavior changes and operational hardening. Read the summary below before upgrading or publishing. - Rename transition updates across package detection, plugin/config compatibility, and install surfaces. - Task and tool behavior updates, including delegate-task contract and runtime registration behavior. - Task-system default behavior alignment so omitted configuration behaves consistently across runtime pat | Medium | 4/11/2026 |
| v3.16.0 | ## Minor Compatibility and Stability Release This release carries compatibility-facing behavior changes and operational hardening. Read the summary below before upgrading or publishing. - Rename transition updates across package detection, plugin/config compatibility, and install surfaces. - Task and tool behavior updates, including delegate-task contract and runtime registration behavior. - Task-system default behavior alignment so omitted configuration behaves consistently across runtime pat | Medium | 4/8/2026 |
| v3.15.3 | ## Minor Compatibility and Stability Release This release carries compatibility-facing behavior changes and operational hardening. Read the summary below before upgrading or publishing. - Rename transition updates across package detection, plugin/config compatibility, and install surfaces. - Task and tool behavior updates, including delegate-task contract and runtime registration behavior. - Task-system default behavior alignment so omitted configuration behaves consistently across runtime pat | Medium | 4/6/2026 |
| v3.15.2 | ## Minor Compatibility and Stability Release This release carries compatibility-facing behavior changes and operational hardening. Read the summary below before upgrading or publishing. - Rename transition updates across package detection, plugin/config compatibility, and install surfaces. - Task and tool behavior updates, including delegate-task contract and runtime registration behavior. - Task-system default behavior alignment so omitted configuration behaves consistently across runtime pat | Medium | 4/5/2026 |
| v3.15.1 | ## Minor Compatibility and Stability Release This release carries compatibility-facing behavior changes and operational hardening. Read the summary below before upgrading or publishing. - Rename transition updates across package detection, plugin/config compatibility, and install surfaces. - Task and tool behavior updates, including delegate-task contract and runtime registration behavior. - Task-system default behavior alignment so omitted configuration behaves consistently across runtime pat | Medium | 4/5/2026 |
| v3.14.0 | - 1c9f4148 fix(publish-ci): sync mock-heavy test isolation with ci.yml - 8dd0191e fix(ci): isolate mock-heavy shared tests to prevent cross-file contamination - 9daaeedc fix(test): restore shared Bun mocks after suite cleanup - 3e13a4cf fix(session-recovery): filter invalid prt_* part IDs from tool_use_id reconstruction - 8e65d6cf fix(test): make legacy-plugin-warning tests isolation-safe - f419a3a9 fix(test): use Bun.spawnSync in command discovery test to avoid execFileSync mock leakage - 1c54f | Medium | 3/26/2026 |
| v3.13.1 | - 77424f86 Merge pull request #2816 from code-yeongyu/fix/keep-agent-with-explicit-model - 919f7e40 fix(data-path): writable directory fallback for data/cache paths - 78a3e985 fix(mcp-oauth): robust port binding for callback server - 42fb2548 fix(agent): always keep agent when model is explicitly configured - bff74f42 Merge pull request #2695 from MoerAI/fix/provider-agnostic-fallback - 038b8a79 Revert "Merge pull request #2611 from MoerAI/fix/keep-default-builder-agent" - 0aa8bfe8 Merge pull re | Medium | 3/25/2026 |
| v3.13.0 | - f0b58354 fix(publish): correct repo guard to oh-my-openagent (GitHub renamed repo) - 2a495c2e Merge pull request #2813 from code-yeongyu/fix/tmux-test-flake-20260325 - 0edb87b1 test(tmux): remove flaky live env wrapper assertion - cca057dc Merge pull request #2812 from code-yeongyu/fix/non-interactive-env-win-bash-prefix - e000a3bb fix(non-interactive-env): force unix prefix for bash git commands - c19fc4ba Merge pull request #2811 from code-yeongyu/fix/publish-workflow-guard-topology-20260325 | Medium | 3/25/2026 |
| v3.12.3 | - 1669c837 revert(todo-continuation): remove [TODO-DIAG] console.error debug logging | Low | 3/18/2026 |
| v3.12.2 | - 09cfd0b4 diag(todo-continuation): add comprehensive debug logging for session idle handling - d48ea025 refactor(circuit-breaker): replace sliding window with consecutive call detection - c5c7ba4e perf: pre-compile regex patterns and optimize hot-path string operations - 90aa3a30 perf(hooks,tools): optimize string operations and reduce redundant iterations - c2f7d059 perf(shared): optimize hot-path utilities across plugin - 7a96a167 perf(claude-code-hooks): defer config loading until after disa | Low | 3/18/2026 |
| v3.12.1 | - 57757a34 refactor: improve test isolation and DI for cache/port-utils/resolve-file-uri - 3caae141 fix(ralph-loop): abort stale Oracle sessions before ulw verification restart - 55ac653e feat(hooks): add todo-description-override hook to enforce atomic todo format - 1d5652df Merge pull request #2655 from tad-hq/infinite-circuit-target-fix - 76c46053 docs(start-work): update worktree and task breakdown guidance - b067d4a2 @ogormans-deptstack has signed the CLA in code-yeongyu/oh-my-openagent#265 | Low | 3/18/2026 |
| v3.12.0 | - d8083389 @HaD0Yun has signed the CLA in code-yeongyu/oh-my-openagent#2640 - d50c38f0 refactor(tests): rename benchmarks/ to tests/hashline/, remove FriendliAI dependency - f2d5f4ca improve(hashline-edit): rewrite tool description with examples and fix lines schema - b788586c relax task timeouts: stale timeout 3min→20min, session wait 30s→1min - 90351e44 update look_at tool description to discourage visual precision use cases - 4ad88b25 feat(task-toast): show model name before category in | Low | 3/17/2026 |
| v3.11.2 | - a7d8c1cd feat: dual-publish platform binaries for oh-my-openagent - beb89faa Merge pull request #2388 from code-yeongyu/fix/background-output-undefined-status-2387 - dc370f7f fix: handle undefined sessionStatus in pollRunningTasks (#2387) - a5fe6eb1 @vaur94 has signed the CLA in code-yeongyu/oh-my-openagent#2385 - ba6fc35a Merge pull request #2376 from acamq/fix/idle-notification-grace-period - 8a827f99 @acamq has signed the CLA in code-yeongyu/oh-my-openagent#2012 - 4e352f9c fix(session-notif | Low | 3/8/2026 |
| v3.11.1 | - adaeaca8 fix: add NODE_AUTH_TOKEN to publish-main job for npm auth - 63ed7a54 fix: update repository URLs to oh-my-openagent for npm provenance - e2444031 ci(publish): deploy both oh-my-opencode and oh-my-openagent simultaneously | Low | 3/7/2026 |
| v3.11.0 | # First release as an oh-my-openagent This is a first release as an oh-my-openagent. We have changed our name to make it less confused; OmO and Sisyphus is about the whole architecture- not just a plugin. Just to help opencode community spending whole day answering OmO questions, we are changing our project name. We know that the name is ultralong, so just call our plugin as 'oh-mo' or Sisyphus. ## The GPT Era Begins — Sisyphus, Multimodal-Looker, and the Full Agent Catalog Now GPT-Native | Low | 3/7/2026 |
| v3.10.0 | ## Security Hardening & Stability This release locks down HTTP hook execution and fixes several determinism bugs that caused subtle issues across process restarts and parallel sessions. ### Hook Security HTTP hooks now validate URL schemes before execution — only `http:` and `https:` are allowed. Previously, `file://`, `data:`, and other dangerous schemes could be used to read local files through hook URLs. The disable mechanism (`disabled_hooks`) now works for HTTP hooks too, not just comman | Low | 3/2/2026 |
| v3.9.0 | # oh-my-opencode v3.9.0 **187 files changed. +7,046/−1,891 lines. 3,391 tests. 0 failures.** --- ## 🔧 Worktree-Aware Planning `/start-work` now accepts `--worktree` — Prometheus creates plans that know which worktree they belong to. Atlas picks up the worktree path in boulder continuation. Parallel feature branches without stepping on each other. ## 🧠 Smarter Model Routing Gemini 3 → 3.1 Pro across the board. GPT model detection simplified to name-based matching — cleaner, faster, no mor | Low | 2/26/2026 |
| v3.8.5 | ## ✏️ Significantly Improved Editing Accuracy This release is the result of [@minpeter](https://github.com/minpeter)'s careful and sustained work to properly fix the hashline implementation that had been incorrectly ported from oh-my-pi. The effort involved deep understanding of how models actually interpret and apply structured line references — the kind of problem that looks simple on the surface but isn't. The outcome: agent editing accuracy has improved substantially. Based on our current | Low | 2/24/2026 |
| v3.8.4 | - 9f804c2a fix(test): sync AGENTS_WITH_TODO_DENY with tool-config-handler implementation - 05c04838 test(hashline-edit): cover concise responses and anchor alias normalization - 86671ad2 refactor(hashline-edit): adopt normalized single-shape edit input - ab768029 refactor(hashline-edit): stabilize hashes and tighten prefix stripping - afec1f29 @DMax1314 has signed the CLA in code-yeongyu/oh-my-opencode#2068 - 41fe6ad2 fix(tools/call-omo-agent): replace as any with Record type cast in session-cre | Low | 2/23/2026 |
| v3.8.3 | - 07e8a7c5 feat(write-existing-file-guard): allow writes outside session directory | Low | 2/22/2026 |
| v3.8.2 | ## 🧪 Experimental: Gemini Model Support We've added Gemini-optimized prompts for Sisyphus, Sisyphus-Junior, Prometheus, and Atlas agents. This is **experimental** and not yet recommended for production use — we're still iterating on prompt quality and compatibility. Feedback welcome if you want to test it out. --- ## 🔍 Better Grep Output The `files_with_matches` mode now returns clean file paths without extra formatting clutter. Easier to scan, easier to pipe into other tools. --- ## ✍️ | Low | 2/22/2026 |
| v3.8.1 | ## 🚀 Background Agent Refactoring & Hashline Edit Improvements This patch release focuses on internal stability improvements and enhanced editing capabilities. ### 🔧 Background Agent Stability The background agent system has been refactored for better maintainability and testability. Inline logic from `manager.ts` has been extracted into focused modules, with comprehensive unit test coverage added for all extracted components. This sets the foundation for more reliable background task manag | Low | 2/22/2026 |
| v3.8.0 | ## Highlights ### Hashline Editing — Enabled by Default Inspired by [oh-my-pi](https://github.com/can1357/oh-my-pi), the hashline edit tool is now **enabled by default**. No configuration needed. Every line comes back tagged with a content hash. The agent edits by referencing the hash. If the file changed since the last read, the hash won't match and the edit is rejected — before corruption happens. **What's new:** - **CID-based hashing**: 2-character alphabet (`ZPMQVRWSNKTXJBYH`) instead of | Low | 2/21/2026 |
| v3.7.4 | - ebd97c85 @kang-heewon has signed the CLA in code-yeongyu/oh-my-opencode#1936 - b4183339 fix(tests): stabilize auto-update-checker isolation under bun - 8c726f55 Merge pull request #1946 from code-yeongyu/fix/failing-tests-v3.8.0 - 6e160877 fix(tests): update atlas hook and auto-update-checker tests - b0e8f5ec feat(run): print agent/model/duration on assistant completion - 6bf36559 refactor: replace opencode/glm-4.7-free with opencode/big-pickle model - 096db593 fix(run): inherit main-session t | Low | 2/18/2026 |
| v3.7.3 | - 1e05f477 fix(cli-run): retry server start on port binding race condition - b1c43aeb @codeg-dev has signed the CLA in code-yeongyu/oh-my-opencode#1927 | Low | 2/18/2026 |
| v3.7.2 | - c21e0b09 fix(cli-run): strip ANSI codes in think block test assertions for CI compatibility - 2f659e9b fix(cli-run): improve agent header and think block spacing - d9751bd5 fix(cli-run): deduplicate tool headers and message counter resets on repeated events - 04e95d7e refactor(cli-run): stream reasoning text instead of summarized thinking line - 0bffdc44 feat(hooks): add sisyphus-gpt-hephaestus-reminder hook - eaf315a8 feat(cli-run): add streaming delta, think block rendering, and rich tool he | Low | 2/17/2026 |
| v3.7.1 | - 462e2ec2 refactor: remove 3 orphaned files and prefix unused parameter - 9acdd6b8 refactor: remove 3 orphaned files from call-omo-agent and delegate-task - 1fb6a7cc refactor: remove 16 orphaned files from background-agent - d3b79064 refactor: remove orphaned modules/ directory from background-task - 744dee70 refactor: remove 3 orphaned files and unused import from tmux-subagent - 0265fa69 refactor: remove 3 orphaned files from background-agent/spawner | Low | 2/17/2026 |
| v3.7.0 | # **Hashline Edit — hash-verified file editing, now in experimental.** Agents can now edit files using line-level hash anchors (`5:a3|const x = 1`). Every edit is verified against a hash of the current line content before applying — if the file changed since it was last read, the edit fails instead of silently corrupting your code. This ships as `experimental.hashline_edit` alongside our existing task management system (Claude Code's tasklist), both marked experimental for the same reason: Ope | Low | 2/17/2026 |
| v3.6.0 | # **OpenCode 1.2.x ready. Agents got names. Dead code is dead.** Your SQLite backend just got full plugin support. Every read, every write, every recovery path — dual-wired for the new storage layer. Oh, and your agents finally tell you who they are. https://github.com/code-yeongyu/oh-my-opencode/releases/tag/v3.6.0 **87 commits. 186 files changed. +4,723/−2,634 lines.** --- ### Highlights **SQLite Backend — Full Support** - `isSqliteBackend()` auto-detects OpenCode ≥ 1.1.53 (version + DB | Low | 2/16/2026 |
| v3.5.6 | - 9ba93374 fix: update prometheus prompt test to match compressed plan template wording - cb4a165c Merge pull request #1882 from code-yeongyu/fix/resume-completion-timer-cleanup - d3574a39 fix: cancel completion timer on resume and prevent silent notification drop - 0ef68296 fix: detect interrupted/error/cancelled status in unstable-agent-task polling loop - dd11d5df refactor: compress plan template while recovering lost specificity guidelines - 130aaaf9 enhance: enforce mandatory per-task QA sc | Low | 2/16/2026 |
| v3.5.5 | ## 🛠️ Background Agent Stability for OpenCode 1.2.0+ OpenCode 1.2.0 changed its event stream format — background agents were dropping heartbeats because they didn't recognize the new `message.part.delta` event type. This release fixes that, so background tasks no longer appear stale or get prematurely killed when running on OpenCode ≥1.2.0. The stale-task guard also now reads the correct session status field, preventing false positives where healthy tasks were incorrectly flagged as stuck. # | Low | 2/15/2026 |
| v3.5.4 | # v3.5.4 — The Reliability Patch Background agents used to silently die. Stale tasks would haunt your session like ghosts — spawned but never finished, timing out on tasks that were still actively running. This release kills that bug dead, alongside 30+ fixes that make oh-my-opencode rock-solid for daily driving. **200 files changed. +10,921/−4,755 lines.** --- ### Highlights **Background Agent Staleness Overhaul** - Fix stale timeout from killing actively running background tasks — the cor | Low | 2/15/2026 |
| v3.5.3 | ## v3.5.3 — Bug Fixes & Stability ### Background Agent - Handle `session.error` events — zombie tasks that held concurrency slots forever are now properly cleaned up with error status, concurrency release, and full timer/queue cleanup - Error-status tasks are now skipped during queue processing, preventing attempts to start dead tasks - Stale pending tasks are now removed from `queuesByKey` when pruned, eliminating orphan queue entries - Extracted `session.idle` handling and shared cleanup logi | Low | 2/12/2026 |
| v3.5.2 | v3.5.2 is a stability patch with targeted fixes for auto-update reliability, subagent lifecycle, and MCP tool safety. ### Highlights **Auto-Update Safety** - Pinned plugin versions are now respected — auto-update skips when you've explicitly locked a version - If an update install fails, the config pin reverts to prevent version mismatch between config and disk **Subagent Lifecycle** - Fixed zombie sessions caused by `permission.question=deny` override in subagent spawning - Added optional ch | Low | 2/11/2026 |
| v3.5.1 | ## Bug Fixes - `13d960f3` fix(look-at): revert to sync prompt to fix race condition with async polling - The `look_at` tool was not waiting for the multimodal-looker agent response before returning results. This was caused by `df0b9f76` switching from synchronous `session.prompt` to async `session.promptAsync` + polling, which introduced a race condition where the poller would fire before the server registered the session as busy. --- ## What's Changed **Full Changelog**: https://github.co | Low | 2/11/2026 |
| v3.5.0 | # v3.5.0 — Atlas Trusts No One Atlas was naive. A subagent said "done" — Atlas moved on. Tests failing, code half-baked, requirements missing entirely. Didn't matter. "Done" meant done. **Not anymore.** Atlas now enforces mandatory manual code review. You `Read` every file the subagent touched. You cross-check claims against reality. You verify imports, logic, edge cases — or you don't proceed. No rubber-stamping. No skipping Step 2. But that wasn't the only thing Atlas got wrong. --- ## W | Low | 2/10/2026 |
| v3.4.0 | # v3.4.0 — Context Continuity ## What's New ### 🎯 Context Preservation: `/handoff` The headline feature. Your subagent is deep in work. Compaction is coming. Context is about to vanish. **`/handoff` solves this.** Synthetically transfer session context—programmatically—to a new session before compaction strikes. Preemptively preserve what matters. Continue where you left off. ```typescript // Preserve context before compaction await handoff({ targetSession: 'new-session-id', context: s | Low | 2/8/2026 |
| v3.3.2 | ## What's Changed **Full Changelog**: https://github.com/code-yeongyu/oh-my-opencode/compare/v3.3.2...v3.3.2 | Low | 2/8/2026 |
| v3.3.1 | ## What's Changed **Full Changelog**: https://github.com/code-yeongyu/oh-my-opencode/compare/v3.3.1...v3.3.1 | Low | 2/7/2026 |
| v3.3.0 | # Hi Subagents! 👋 **The headline:** Subagents are no longer black boxes. Click on a `task` tool call in the UI and see exactly what you delegated — prompt, description, model, session ID, the whole story. ## `delegate_task` → `task`: From Mystery to Transparency Before v3.3.0, spawning a subagent meant sending it off into the void. You gave it a prompt, crossed your fingers, and waited. Want to know what instructions you actually sent? Tough luck — `delegate_task` kept its secrets. **Now wi | Low | 2/7/2026 |
| v3.2.4 | # What a wild day. GPT 5.3 Codex and Claude Opus 4.6 dropped on the same day. That's not a coincidence — that's the universe telling us we're living through something historic. Two frontier model providers, shipping simultaneously. Monumental. And we adopted both **the same day they shipped**. **108 files changed. +4,666/-4,625 lines.** A same-day sweep from one end of the codebase to the other. When the frontier moves, we move with it. --- ### **Hephaestus: The Legitimate Craftsman Evolve | Low | 2/6/2026 |
| v3.2.3 | ## What's Changed ### ✨ Features - **Multi-provider websearch support** - Choose between Exa (default) and Tavily for web search (#1371 by @YanzheL) - **Nested skill directories** - Skills can now be organized in subdirectories for better organization (#1254 by @LeekJay) - **Disabled skills support** - Add `disabledSkills` config to selectively disable skills ### 🐛 Bug Fixes #### Authentication & Server - Fix OpenCode Desktop server unauthorized error on subagent spawn (#1399 by | Low | 2/4/2026 |
| v3.2.2 | ## v3.2.2 ### 🚀 GPT-5.2 Prompt Optimization - **Atlas, Sisyphus-Junior, Oracle**: Model-based prompt routing with GPT-5.2 optimized prompts (XML structure, verbosity constraints, explicit decision criteria) ### 🧪 Experimental: Claude Code-style Task System - **New Tools**: `TaskCreate`, `TaskGet`, `TaskList`, `TaskUpdate` for structured task management - **File-based Storage**: Tasks stored in `.sisyphus/tasks/` with Claude Code compatible schema - ⚠️ **Important Limitation**: This is **expe | Low | 2/3/2026 |
| v3.2.1 | ## Bug Fixes - **background-agent**: prevent concurrency slot leaks on task startup failures - **cli**: add -preview suffix for GitHub Copilot Gemini model names - **ci**: add shell: bash to retry action for Windows compatibility | Low | 2/1/2026 |
| v3.2.0 | # 3.2.0 — Meet Hephaestus 🔨 ## Highlights ### 🔥 Hephaestus: The Legitimate Craftsman Agent  In Greek mythology, Hephaestus was the god of forge, fire, metalworking, and craftsmanship—the divine blacksmith who crafted weapons for the gods. **Meet our new autonomous deep worker: Hephaestus (GPT 5.2 Codex Medium).** *Why "Legitimate"? When Anthropic blocked third-party access citing ToS v | Low | 2/1/2026 |
| v3.1.11 | ## What's Changed ### Features - **Oracle Safety Review**: Added Oracle deployment safety review to `/get-unpublished-changes` command for pre-release analysis - **Stop Continuation Command**: New `/stop-continuation` command to halt all continuation mechanisms (ralph loop, todo continuation, boulder) - **GLM-4.7 Thinking Mode**: Added thinking mode support for GLM-4.7 model ### Bug Fixes - **Memory Leak Prevention**: Track and cancel completion timers in background-agent to prevent memory lea | Low | 2/1/2026 |
| v3.1.10 | No notable changes | Low | 1/31/2026 |
Dependencies & License Audit
Loading dependencies...
Similar Packages
@hexitlabs/hexosHexOS — The operating system for AI-powered businesses. Deploy AI agent teams that work 24/7.2026.1.24-24