Addresses cubic-dev-ai review feedback. The Haiku early-return now
runs immediately after model validation, ensuring it's always reached
regardless of any upstream variant normalization.
Haiku models do not support the effort parameter and return API errors
when it is passed. The hook now explicitly checks for Haiku model
patterns and skips effort injection, preventing silent title generation
failures.
Added EFFORT_UNSUPPORTED_PATTERN and isEffortUnsupportedModel() to
detect and skip Haiku models.
Fixes#3308
The canonical agent order is: sisyphus → hephaestus → prometheus → atlas
Changes:
- Export CANONICAL_CORE_AGENT_ORDER as single source of truth
- Sort non-core agents alphabetically for deterministic ordering
- Add 12 regression tests including 100-permutation stability test
This permanently resolves the agent ordering saga that caused 15+ commits,
8+ PRs, and multiple reverts due to ZWSP prefixes, Object.entries() order
dependencies, and inconsistent merge sequences.
Closes#3281
The grep tool's content and count output modes always returned 'No
matches found' on Windows due to two issues:
1. Regex ^(.+?):(\d+):(.*)$ fails on Windows paths like
C:\path\file.ts:42:content because lazy .+? matches only 'C',
then \d+ fails on '\path\...'
2. ripgrep outputs CRLF line endings on Windows. After split('\n'),
trailing \r breaks the $ anchor in the regex, causing every
line to fail matching.
Fix: update parseOutput and parseCountOutput regexes to handle
drive-letter prefixes ([A-Za-z]:[\/]), and strip trailing \r
from each line before matching.
Note: PR #2976 attempted to fix (1) with --path-separator=/ but
this flag gets expanded by MSYS2/Git Bash to a full path, causing
a separate rg error. This PR avoids --path-separator entirely.
Closes#2962
Addresses Cubic review: configs without prior _migrations now get the
full migration set written to config as fallback when sidecar write
fails, preventing migration tracking loss.
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
YeonGyu-Kim