can1357/oh-my-pi v18.1.5 on GitHub

@oh-my-pi/pi-ai

Added /login abliteration with API key validation against /v1/models, supporting the ABLITERATION_API_KEY and ABLIT_KEY environment variables.

Modernized provider authentication and token refresh across the catalog, with shared support for API-key, authorization-code, and device-code sign-in flows and clearer sign-in progress messages for OpenRouter, Kimi, and xAI.

GitHub Copilot now uses the official Copilot CLI identity and OAuth application for requests and new sign-ins, restoring access to client-gated models while preserving existing credentials.
GitHub Copilot now reports model_not_supported responses immediately instead of repeatedly retrying unsupported models.
Improved account recovery after Google rate limits are lifted earlier than the reported reset time.
Fixed unmetered autocomplete models being reported as exhausted when quota is limited.
Fixed Gemini 3 cross-model sessions in Cloud Code Assist when replaying tool calls without a thought signature.
Fixed Cursor models behind an authentication gateway incorrectly retrying valid client-declared tool calls.
Fixed reasoning from models that prefill <think> (including DeepSeek-R1 and hosted Qwen3-Thinking) being shown in the response instead of as a separate thinking block.

Added the Abliteration (abliteration.ai) provider, including its documented abliterated-model catalog and live model discovery.
Added the GLM 5.3 Promo 50 model.
Added computer-use capability metadata to model configurations.
Added declarative provider authentication policies covering login, refresh, environment-key, and credential behavior, with generated compatibility data and typed accessors.

GitHub Copilot model discovery now respects the Copilot CLI identity, ensuring eligible enterprise and experimental models are available.
Fixed startup failures when discovering Bedrock-style Mistral Mixtral models.
Fixed Muse Spark 1.3 contributor models on OpenCode gateways so they use the correct Responses API route.
Updated Meta and OpenCode Muse Spark 1.3 model metadata and capabilities, including context windows, reasoning levels, image input, pricing, and model naming; media-only Muse SKUs are no longer presented as chat models.

Added Abliteration provider support to /login, including ABLITERATION_API_KEY configuration and help text.
Added clone-first Git worktree support that carries over ignored build artifacts when creating worktrees, with a configurable worktree.clone setting and fallback to a standard checkout. This is supported by github pr_checkout, omp worktree add, and git worktree add commands entered through the Bash tool.
Added the omp worktree add command with Git-compatible branch, detach, path, and commit options.
Added /wt (alias /worktree) to create a linked worktree with uncommitted changes and move the current session into it while leaving the original checkout untouched.

Foreign user-level configuration sources (~/.cursor, ~/.codex, ~/.claude, ~/.gemini, ~/.config/opencode, ~/.codeium/windsurf) are now opt-in via enabledProviders, while project-level configurations in CWD and .agents continue to load by default.
Split subagent isolation configuration into task.isolation.enabled and isolation.backend; existing task.isolation.mode settings are migrated automatically.
Updated the built-in smol and slow model priority chains to favor newer recommended models and remove older model generations.
Improved unsupported-model error messages by removing retry guidance that does not apply.

Fixed automatic title generation so --no-title also prevents todo-initialization title refreshes, while automatic titles retain the selected OAuth account without sharing foreground request identity.
Fixed provider errors so they wrap to the terminal width and remain readable in the transcript and pinned error banner, with long messages available through the expansion hint.
Fixed Gemini malformed function-call turns so textual tool-call output is rejected conversationally and the session can continue instead of stopping with a pinned error.
Fixed auto-compaction recovery getting stuck in repeated retries when models return empty length-limited responses; it now stops with an actionable error.
Fixed MCP servers failing to reconnect after transient startup handshake timeouts.
Fixed programs supervised by hub start hanging when querying terminal capabilities.
Fixed large pastes followed immediately by Enter so the input is submitted with the pasted content instead of being left in the large-paste menu.

Removed the bundled designer subagent and designer model role; modelRoles.designer and @designer are no longer built in.

Updated worktreeAdd to support additional worktree creation options, including preserving uncommitted changes.

Fixed terminal query support in supervised PTY processes, including cursor position reports.
Fixed paste-and-submit handling so an Enter keypress received with a bracketed paste is delivered to the previously focused component; Editor.onLargePaste now receives PasteOptions describing the queued submit.

Added TerminalQueryResponder to @oh-my-pi/pi-utils/vterm, enabling headless PTY consumers to answer common terminal queries for cursor position, device status and attributes, and foreground/background colors without maintaining a screen buffer.

fix(mcp): retry transient startup handshake timeouts by @roboomp in #10570
fix(cursor): acknowledge auth-gateway tool handoffs by @roboomp in #10590
fix(compaction): bound response.incomplete recovery retries by @roboomp in #10596
fix(catalog): resolve namespaced family ambiguity by @roboomp in #10599
fix(ai): handled unsigned-first CCA tool calls by @roboomp in #10604
fix(catalog): route opencode muse-spark-1.3 over responses api by @roboomp in #10611
feat(catalog,ai,coding-agent): add Abliteration (abliteration.ai) provider by @kmccleary3301 in #10515
fix(session): honor no-title during replan refresh by @roboomp in #10621

Full Changelog: v18.1.4...v18.1.5