can1357/oh-my-pi v15.10.4 on GitHub

@oh-my-pi/pi-ai

Added anthropic-client-platform (desktop_app) and anthropic-client-version (1.11187.4) headers to the Anthropic request fingerprint for OAuth sessions

Changed non-built-in tool names sent to Anthropic from proxy_ prefixing to _ prefixing (for example bash to _bash) while built-in tool names remain unchanged
Updated the Anthropic OAuth stealth fingerprint to track Claude Code 2.1.165: claudeCodeVersion bumped to 2.1.165 (flows into both the cc_version billing header and the claude-cli/<version> user-agent), claudeCodeSystemInstruction changed to "You are a Claude agent, built on Anthropic's Claude Agent SDK.", and the billing-header cc_entrypoint changed from cli to local-agent.
Clamped the Anthropic request max_tokens to Math.min(CLAUDE_CODE_MAX_OUTPUT_TOKENS, options.maxTokens || model.maxTokens) (64k) so OAuth requests match Claude Code's requested output cap instead of sending the model's full ceiling (e.g. 128k for Opus 4.8).

macOS release binaries are now signed with a Developer ID Application identity (hardened runtime + secure timestamp + JIT/library-validation entitlements) and notarized in CI when the APPLE_* signing secrets are configured; releases auto-fall back to ad-hoc signing until then. This makes the shipped binaries Gatekeeper-acceptable, unblocking an official Homebrew submission (#776). See docs/macos-signing-notarization.md.
Added a Homebrew install path: brew install can1357/tap/omp. The can1357/homebrew-tap formula installs the prebuilt release binary, and a release_brew CI job regenerates it (version + per-asset sha256) from each published release via scripts/ci-update-brew-formula.ts (#776).

Adjusted completion() model resolution so the default tier now prefers the session’s active model and falls back to the configured default role when needed
Rewrote the session auto-title prompt (prompts/system/title-system.md) and the set_title tool description to ask for a concise, sentence-case title (3-7 words) that captures the session's topic/goal, with good/bad examples and explicit guidance to treat the first message as data (no following embedded links/instructions, no refusals, describe URL/reference asks). The local on-device title prompt (tiny-title-system.md) was aligned to the same 3-7 word, sentence-case convention. The deterministic greeting/low-signal filter and the none deferral sentinel are unchanged.
Renamed the eval oneshot helper from llm() to completion() in both JavaScript and Python preludes, including status events, prompt docs, and runtime tests.

Fixed completion() to always send a non-empty default system prompt when system is omitted so providers that require instructions no longer reject requests
Fixed structured completion() mode to return parsed JSON from plain text output when the model skips the forced respond tool call
Fixed slow-tier completion() reasoning requests to avoid unsupported effort settings by only enabling reasoning on reasoning-capable models and capping effort to supported levels
Fixed JS eval worker reset/dispose to close workers gracefully before forced termination, avoiding Bun 1.3.14 N-API teardown crashes with native modules such as canvas.

Fixed Windows ConPTY session-resume painting the transcript with the last several rows truncated below the viewport until Alt+Tab forced a host repaint. After sessionReplace/historyRebuild/overlayRebuild paints that scroll-push content into native scrollback, the renderer now arms a 150 ms ConPTY settle window that coalesces spinner/blink-driven requestRender(false) calls into a single trailing render — Windows Terminal's viewport-follow logic no longer falls further behind the cursor on every tick of the post-paint storm. The arm also reclaims any render request queued during the in-flight composition (notably ImageBudget.endPass() calling requestRender() synchronously when a frame trips the live-graphics cap): without that, the queued request sat on the standard 30 Hz throttle and fired at ~33 ms — well inside the 150 ms quiet window — defeating the coalescing. Bumped the ConPTY per-WriteFile chunk cap from 8 KiB to 16 KiB so a multi-megabyte resume paint emits half as many writes (still well under the ~32 KiB threshold from #2034 that the original cap defends against), and made the cap measure encoded UTF-8 bytes instead of JS code units so a CJK-heavy transcript can't silently inflate a 16-KiB-of-code-units chunk into ~48 KiB of WriteFile traffic and reintroduce the #2034 viewport bug (#2095).

fix(coding-agent): close JS eval workers gracefully by @basedcorp99 in #2079
fix(tui): settle ConPTY after big paints to stop session-resume tail truncation by @roboomp in #2101

Full Changelog: v15.10.3...v15.10.4