Skip to content

v18.0.9

Latest

Choose a tag to compare

@github-actions github-actions released this 28 Aug 06:14
· 41 commits to main since this release
cc14e04

@oh-my-pi/pi-agent-core

Fixed

  • Fixed /shake elide handling of mixed tool results so images are preserved and token savings are reported accurately.

@oh-my-pi/pi-ai

Fixed

  • Improved OAuth sign-in flows, including a fallback message when the browser cannot automatically close the OAuth success tab.
  • Fixed Cloudflare AI Gateway onboarding and routing so gateway account and endpoint configuration is preserved correctly while gateway credentials are not sent as upstream OpenAI authorization headers.
  • Fixed Codex OAuth quota handling so chat and Spark usage remain independent, legacy shared quota limits continue to work, and incomplete usage reports are not incorrectly treated as unlimited.

@oh-my-pi/pi-catalog

Added

  • Added Z.AI GLM-5.3-Flash to the bundled GLM Coding Plan catalog, with a 1M-token context window, 131,072-token output limit, native image input, and low/high/max thinking levels. It is now available through model discovery and the model picker.

Fixed

  • Fixed Google Antigravity Gemini 3.7 Flash tiered models failing with HTTP 400 errors at minimal or disabled thinking levels; those tiers now use the compatible Gemini 3.7 Flash model routing.
  • Fixed OpenCode Go and Zen GLM-5.3 Flash models exposing an unsupported extra-high reasoning level; they now use the supported low/high/max reasoning levels.
  • Fixed Cloudflare AI Gateway credential handling so stored credentials and routing metadata are parsed and used correctly.

@oh-my-pi/pi-coding-agent

Breaking Changes

  • Removed the git and jj wrapper modules from the SDK surface. VCS operations are now available through @oh-my-pi/pi-natives/vcs, including native handles and typed VcsError support; the package continues to re-export the github (gh CLI) helpers.

Changed

  • extendedContext now defaults to off: models with premium long-context pricing tiers (e.g. GPT-5.6 1M) stay capped at their standard-pricing window unless the setting or /extended-context on enables the extended window.

Fixed

  • Improved terminal readability on light backgrounds by ensuring TUI surfaces use contrasting foreground colors.
  • Coalesced simultaneous autonomous continuation requests to prevent repeated calls while the agent is busy, with clearer continuation diagnostics.
  • Fixed Snapcompact so it skips or falls back when compaction would not reduce context size, and now compacts text in mixed tool results while preserving all source images.
  • Added Google Antigravity daily quota usage to the status line.
  • Fixed status-line background-work counts so queued tasks and evaluation jobs remain visible without double-counting running subagents.
  • Fixed nested subagent visibility in RPC subscriptions, the subagent HUD, get_subagents, subagent_* events, and get_subagent_messages.
  • Fixed omp token refreshing local MCP OAuth credentials without blocking or losing rotating refresh tokens, and preserved OpenCode MCP OAuth configuration during discovery.
  • Prevented process crashes caused by socket-closed errors and unhandled promise rejections during concurrent subagent shutdowns, timeouts, and MCP transport disconnects.
  • Fixed automatic startup model selection so ambient AWS credentials do not incorrectly select an unavailable Amazon Bedrock model over a provider the user has authenticated with.
  • Kept embedded context usage visible in the status line when long session names or paths consume available space.
  • Added a status message when CTRL-O toggles tool-output expansion.
  • Fixed omp usage to report Codex Chat and Spark capacity meters separately when they share a usage window.

@oh-my-pi/pi-mnemopi

Fixed

  • Fixed working-memory search returning too few or no results when the most relevant matches had been superseded, ensuring valid older entries are still returned.

@oh-my-pi/pi-natives

Breaking Changes

  • Replaced the Git-specific watchHead and headWatchTarget API with the backend-neutral watch and VcsRepo.watchTarget APIs.

Added

  • Added portable repository discovery and read operations through VcsRepo, repo(), and require(), with support for Git and Jujutsu and explicit capability checks for staged and revision diffs.
  • Added the Vcs* API for repository operations across Git and Jujutsu, including repository discovery, refs and status, diffs, staging, commits, branches, worktrees, patch application, stash, cherry-pick, and CLI-backed push, fetch, and clone operations with cancellation support.

Fixed

  • Fixed Git intent-to-add files so they appear correctly as unstaged additions in statusPorcelain and are handled correctly when staging or applying patches.

@oh-my-pi/omp-stats

Fixed

  • Fixed inconsistent model colors between the Model Preference chart and Model Statistics table.

@oh-my-pi/pi-tui

Added

  • Exported TuiDebugServer for programmatic headless control
  • Added debug demonstration script to examples
  • Added an OMP_TUI_DEBUG Unix socket for headless TUI driving and structured inspection.

Changed

  • Inline hex colors now render with VS Code-style colored backgrounds and automatically selected black or white text for readability, alongside the color swatch.
  • LaTeX text formatting commands such as \textbf, \textit, \textsl, and \emph now render as terminal bold or italic text.

Fixed

  • Fixed inline color swatches rendering incorrectly inside highlighted lines.
  • Fixed terminal resizing in tmux panes and Windows consoles duplicating the current in-progress turn in scrollback.

@oh-my-pi/pi-utils

Fixed

  • Fixed error handling so unrelated aborted requests and closed-connection failures are no longer silently suppressed.

What's Changed

  • fix(coding-agent): stop the status bar counting subagents twice by @Hunter-124 in #9927
  • fix(coding-agent): keep embedded context usage visible by @641-git641 in #9946
  • fix(mnemopi): stop superseded rows from occupying FTS candidate slots by @BAKocska in #9948
  • fix(mcp): preserve OpenCode OAuth config by @ZanzyTHEbar in #9951
  • fix(cli): refresh local MCP OAuth tokens by @roboomp in #9955
  • fix(tui): stop the resize pre-erase archiving the unfinished frame into scrollback by @nategriffin26 in #9962
  • fix(catalog): include glm-5.3 flash in effort ladder by @roboomp in #9963
  • fix(theme): keep text readable on painted surfaces by @roboomp in #9965
  • fix(coding-agent): prefer concrete-auth provider for startup default model by @roboomp in #9968
  • fix(ai): correct Codex Spark quota isolation by @aleister1102 in #9978
  • fix(tui): preserve LaTeX terminal styles by @aleister1102 in #9980
  • fix(ai): make Cloudflare AI Gateway login self-contained by @AshishKumar4 in #9981
  • Show status message when toggling tool output expansion by @amnkarn in #9987
  • fix(session): coalesce continuation scheduler requests by @roboomp in #9992
  • fix(stats): keep model colors consistent across views by @rthiago in #9995
  • fix(agent): preserve images during shake elision by @Hunter-124 in #9997
  • fix(coding-agent): compact mixed-image tool results by @Hunter-124 in #9998
  • fix(tui): display Antigravity daily usage in status line by @roboomp in #10000
  • fix(catalog): fold gemini-3.7-flash-tiered into gemini-3.7-flash by @roboomp in #10018
  • fix(compaction): skip inflating snapcompact results by @roboomp in #10024
  • fix(coding-agent): prevent unhandled socket closures and floating promise leaks during subagent teardown by @jaimehgb in #9751
  • feat(catalog): add Z.AI GLM-5.3-Flash with native image input by @tmdgusya in #9835
  • fix(ai): degrade the OAuth close button when the tab is not script-closable by @Hunter-124 in #9926
  • docs: document BigModel balance-key setup by @roboomp in #9949
  • fix(rpc): nested subagent frames never reach RPC/observer surfaces (depth >= 2 invisible) by @cwr250 in #9952

New Contributors

Full Changelog: v18.0.8...v18.0.9