Highlights
Hashline Editing — Enabled by Default
Inspired by 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 hex hashes - Batch mismatch reporting: All mismatches reported in one error, not just the first
- Inline diff display: See unified diffs in the TUI for every edit
To disable: { "hashline_edit": false }
Slash Commands Are Gone — Everything is Skills Now
The slashcommand tool has been removed. All functionality is now unified under the skill tool.
Use skill(name="...") for both skills and commands. Priority: project → user → opencode → built-in. If the name does not match, OmO suggests the closest matches.
Ultrawork Model Override — Per-Agent Configuration
Configure a dedicated model for ultrawork mode on any agent. When you type ultrawork or ulw, OmO upgrades to your configured model for that turn. API calls use the upgraded model while the TUI bottom bar stays on the original.
Smarter Agents — Intent Verbalization
Sisyphus, Hephaestus, and Prometheus received major prompt upgrades. Before classifying your request, agents now explicitly verbalize what they think you want, eliminating the class of failures where agents stop at "research" when you wanted full implementation.
Prometheus now works with GPT models. A dedicated GPT-5.2 optimized prompt variant activates automatically.
Runtime Fallback — Automatic Model Switching on API Errors
When rate limits or server errors hit, OmO automatically switches to the next model in your fallback chain and keeps working. Set fallback_models on any agent or category.
Other Changes
- Session Recovery for Unavailable Tools: Sessions continue gracefully when tools do not exist
- Ralph Loop Fresh Context: New
strategyoption creates fresh child sessions per iteration - Hephaestus GPT Enforcement: Auto-switches to Sisyphus if run with non-GPT models
- Tmux Split-or-Defer: Sessions queue automatically when tmux panes are full
$EXISTING_BODY