can1357/oh-my-pi v15.5.7 on GitHub

@oh-my-pi/pi-ai

SimpleStreamOptions.openrouterVariant ("nitro", "floor", "online", "exacto", …) — when set, appends :<variant> to OpenRouter model IDs at request time, leaving ids that already carry an explicit :suffix untouched. Plumbed through openai-completions and the pi-native gateway forwarder.
xAI Grok OAuth (SuperGrok Subscription) provider in /login. Loopback PKCE flow on 127.0.0.1:56121; the token unlocks Grok-4.x chat. Ported from NousResearch/hermes-agent (MIT).
OpenRouter provider in /login. API-key paste flow validated against https://openrouter.ai/api/v1/auth/key (the /models endpoint is public and cannot validate auth). The pasted key is stored under the existing openrouter provider id used by OPENROUTER_API_KEY.
XAI_OAUTH_TOKEN environment variable accepted as a headless fallback for the xAI Grok OAuth provider.

OpenAIResponsesOptions gains four optional, provider-agnostic fields that adapter wrappers can use to compose provider-specific behavior on top of the generic transport: includeEncryptedReasoning (gates include: ["reasoning.encrypted_content"]; default true, preserves current behavior), filterReasoningHistory (strips replayed type: "reasoning" items from conversation history; default false), headers (merged onto the client's default headers), and extraBody (merged into the request payload).
The existing XAI_API_KEY path is unchanged — it continues to use the OpenAI-completions transport.

Fixed OpenRouter DeepSeek V4 tool-call follow-up requests replaying normalized reasoning as-is instead of DeepSeek's required reasoning_content, which caused HTTP 400 errors in thinking mode. (#1445)

providers.openrouterVariant setting (Settings → Providers → "OpenRouter Routing") to default OpenRouter requests to a routing-variant suffix (:nitro, :floor, :online, :exacto). Selectors that already name a variant (e.g. openrouter/anthropic/claude-haiku:nitro) keep precedence.
generate_image supports xAI Grok Imagine via providers.image=xai. Supports grok-imagine-image (default) and grok-imagine-image-quality at aspect ratios 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3. Uses the xAI Grok OAuth credential when available, otherwise XAI_API_KEY.
New tts tool synthesises speech via xAI Grok Voice behind the disabled-by-default tts.enabled setting. Built-in voices ara, eve (default), leo, rex, sal; custom voice IDs also accepted. Output codec inferred from the output_path suffix (.wav → wav, else mp3). Up to 15,000 characters per request.

Fixed plan-mode re-entry after approval reopening a fresh local://PLAN.md instead of the approved titled plan artifact, which could duplicate plan content and fail approval on an existing destination.
Fixed read URL reader mode aborting after a stalled Jina request instead of falling back to trafilatura/lynx/native: Jina (and Parallel extract) now have their own per-attempt sub-budget capped at 10s, the catch handler honours only real user cancellation, and the in-process native renderer is always attempted on already-loaded HTML (#1449)

fix(coding-agent): reopen approved plan on plan-mode reentry by @metaphorics in #1448
fix(ai,coding-agent): stabilize xAI Grok OAuth by @metaphorics in #1446
fix(agent): compaction reasoning effort — fallback to off when reasoning unsupported by @metaphorics in #1444
fix(ai): replay OpenRouter DeepSeek reasoning_content by @roboomp in #1447
fix(search): wrap native regex-build errors in ToolError by @oldschoola in #1425
fix(providers): prune stale synthetic model cache entries by @roboomp in #1418
fix(hashline): require anchor-content alignment in session-chain replay recovery by @oldschoola in #1422
fix(xiaomi): add CN token-plan cluster as last fallback by @hanbinnoh in #1442

Full Changelog: v15.5.6...v15.5.7