Update various modules to use centralized constants from plugin-identity:
- get-local-version/formatter: Use PUBLISHED_PACKAGE_NAME
- run/session-resolver: Use PUBLISHED_PACKAGE_NAME
- background-agent/task-poller: Use PUBLISHED_PACKAGE_NAME
- mcp-oauth/provider: Use PUBLISHED_PACKAGE_NAME
- auto-update-checker/constants: Use ACCEPTED_PACKAGE_NAMES
- comment-checker/downloader: Use PUBLISHED_PACKAGE_NAME
- legacy-plugin-toast/hook: Use PLUGIN_NAME
- shared/data-path: Use CACHE_DIR_NAME
- shared/external-plugin-detector: Use ACCEPTED_PACKAGE_NAMES
- shared/logger: Use LOG_FILENAME
- tools/ast-grep/downloader: Use PUBLISHED_PACKAGE_NAME
- tools/call-omo-agent/tools: Use PUBLISHED_PACKAGE_NAME
- tools/delegate-task/category-resolver: Use PUBLISHED_PACKAGE_NAME
- tools/grep/constants: Use PUBLISHED_PACKAGE_NAME
- tools/grep/downloader: Use PUBLISHED_PACKAGE_NAME
- tools/lsp/lsp-client-wrapper: Use PUBLISHED_PACKAGE_NAME
🤖 Generated with assistance of OhMyOpenCode
Update doctor checks to use centralized constants from plugin-identity:
- PACKAGE_NAME now references PUBLISHED_PACKAGE_NAME
- System check uses PLUGIN_NAME and LEGACY_PLUGIN_NAME for plugin
registration validation and legacy name detection
- Formatters updated for consistency
🤖 Generated with assistance of OhMyOpenCode
Update CLI installer to show oh-my-opencode (published name) instead
of oh-my-openagent (plugin name) in usage instructions.
🤖 Generated with assistance of OhMyOpenCode
Update systemLoadedVersion check to detect installs under both
oh-my-opencode and oh-my-openagent package names. Adds package
candidate selection logic for dual-published packages.
🤖 Generated with assistance of OhMyOpenCode
Update writeOmoConfig to detect and migrate legacy config files before
writing. Adds logic to handle oh-my-opencode.json -> oh-my-openagent.json
migration with proper path resolution and fallback handling.
🤖 Generated with assistance of OhMyOpenCode
Add CONFIG_BASENAME and LEGACY_CONFIG_BASENAME constants to support
migrating from oh-my-opencode.json to oh-my-openagent.json naming.
🤖 Generated with assistance of OhMyOpenCode
Extract hardcoded GPT apply_patch permission logic into a reusable module
to ensure consistent behavior across all agents. This prevents GPT models
from using the unreliable apply_patch tool while allowing other models.
- Add gpt-apply-patch-guard.ts with GPT_APPLY_PATCH_GUIDANCE and getGptApplyPatchPermission
- Update Hephaestus agent to use centralized permission logic
- Update Sisyphus-Junior agent to use centralized permission logic
- Update all GPT prompt builders to reference shared guidance constant
🤖 Generated with assistance of OhMyOpenCode
When a hook returns exit code 2 (deny) or 1 (ask), previously accumulated
modifiedInput and common fields from earlier allow hooks were discarded.
Now all exit paths (exit code and JSON) include accumulated state.
When a hook returns 'allow' with updatedInput or common fields
(suppressOutput, systemMessage, etc.), these values were silently
dropped. Now they are accumulated across hooks and included in the
final result, matching Claude Code's behavior where allow hooks can
still modify tool input and set metadata.
Revert the create-hooks.ts change — claudeCodeHooks is already created
in createTransformHooks() with proper config and contextCollector.
The previous commit overwrote it with a degraded instance (empty config,
no contextCollector).
Add 8 unit tests for executePreToolUseHooks covering:
- null/empty config handling
- exit code 2 (deny) and 1 (ask) behavior
- multiple merged hooks: allow continues to next hook (the actual bug)
- deny short-circuits remaining hooks
- modifiedInput propagation between hooks
TDD verified: tests fail with original code, pass with fix.
When multiple hook sources are merged (global ~/.claude/settings.json +
project .claude/settings.json), a global catch-all hook returning 'allow'
caused early return before project-level hooks could execute.
Only 'deny' and 'ask' decisions should short-circuit. 'allow' should
continue processing remaining hooks so project-specific guards (e.g.,
file budget enforcement) get a chance to block.
createClaudeCodeHooksHook() was fully implemented but never instantiated
in createHooks(). All .claude/settings.json hooks (PreToolUse, PostToolUse,
Stop, UserPromptSubmit) were silently skipped because hooks.claudeCodeHooks
was always undefined (optional chaining masked the issue).
Add claudeCodeHooks creation to createHooks() using the existing
isHookEnabled('claude-code-hooks') gate and safeCreateHook wrapper.
Note: This is a necessary fix but may require additional debugging for
full hook execution — the dispatch/stdin format compatibility between
OpenCode and Claude Code hook scripts needs runtime verification.
Fixes#3297
The /stop-continuation command was ineffective because the stop-
continuation-guard cleared its stopped state on the very next
chat.message event. Since any user message (including normal chat
after stopping) triggers chat.message, the continuation would
resume immediately.
Root cause: the chat.message handler called clear(sessionID) on
every user message, treating it as a 'user resumed work' signal.
But the user expects /stop-continuation to persist until they
explicitly start work again.
Changes:
- stop-continuation-guard chat.message: no longer clears stop state
- tool-execute-before: /start-work, /ralph-loop, /ulw-loop now
explicitly clear the stop state (so continuation resumes when
user intentionally restarts work)
- Updated and added tests: 12 pass (3 new), 125 related tests pass
Closes#3276
The resolveModelPipeline test was consistently failing on CI
(resolveModelPipeline > does not return unused explicit user config
metadata in override result) while passing locally. Root cause is the
same mock.module contamination pattern as #3243: when bun runs all test
files in a single process, mock.module calls from other files (e.g.
model-resolver.test.ts) leak into this file's module scope.
Add mock.module('./logger', ...) so run-ci-tests.ts auto-detects the
file and runs it in its own isolated bun process.
This unblocks the v3.16.1 publish workflow which hit this flake twice.
Remap the core agent keys, default agent, and command routing back to\nlist display names so OpenCode's name-based sorting keeps the\ncanonical Sisyphus -> Hephaestus -> Prometheus -> Atlas order.\n\nAlso teach tool config lookups to resolve the prefixed list keys and\nadd regression tests that exercise the real ordering and routing path.
YeonGyu-Kim