Skip to content

chore(deps): update dependency @oh-my-pi/pi-coding-agent to v18.0.11 - #4

Open
renovate[bot] wants to merge 1 commit into
mainfrom
renovate/patch-oh-my-pi
Open

chore(deps): update dependency @oh-my-pi/pi-coding-agent to v18.0.11#4
renovate[bot] wants to merge 1 commit into
mainfrom
renovate/patch-oh-my-pi

Conversation

@renovate

@renovate renovate Bot commented Sep 30, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

Note

This PR body was truncated due to platform limits.

This PR contains the following updates:

Package Change Age Confidence
@oh-my-pi/pi-coding-agent (source) 18.0.0 → 18.0.11 age confidence

Release Notes

can1357/oh-my-pi (@​oh-my-pi/pi-coding-agent)

v18.0.11

Compare Source

@​oh-my-pi/pi-agent-core

Fixed
  • Fixed agent startup and context compaction failures for models with unrecognized tokenizer encodings.

@​oh-my-pi/pi-ai

Fixed
  • Fixed automatic session retries for Anthropic-compatible streams that end prematurely without a completion signal.
  • Fixed Gemini 3.x tool-call continuations through OpenAI-compatible endpoints.
  • Fixed credential fallback for HTTP 402 payment-required and deactivated-workspace responses, preventing them from being misclassified as quota exhaustion.
  • Fixed Perplexity email sign-in for accounts protected by authenticator-based two-factor authentication.
  • Fixed Qianfan API-key login validation for keys that cannot access the validation model.
  • Fixed Z.AI browser sign-in to report an occupied callback port before opening the browser.

@​oh-my-pi/pi-catalog

Fixed
  • Fixed Baseten GLM models, including GLM-5.3-Flash, being incorrectly classified as non-reasoning models.
  • Fixed Cloudflare AI Gateway catalog refreshes so active Workers AI chat models, including newly released models, are discovered correctly.
  • Fixed Cursor Kimi K3, Grok 4, and Composer 2.5 models being incorrectly treated as text-only when they support image attachments.
  • Fixed OpenRouter routed model variants, including GLM-5.3 and dated DeepSeek V4 Pro, so their reasoning effort options are preserved correctly.
  • Fixed MiniMax-M3 max output regressing to the upstream 512K pricing-tier boundary; all MiniMax providers keep the documented 128K output cap.
  • Fixed GLM-5.3-Flash bundling the 50%-off launch promotion price; the catalog stays on the documented list price.
  • Fixed Synthetic model discovery re-adding image input from the bundled reference when the route advertises text-only modalities.

@​oh-my-pi/pi-coding-agent

Added
  • Added gallery previews for composer and status-line components, with CLI filters for browsing by surface, composer, or segment.
Changed
  • The status line now displays the thinking level as a compact icon alongside the model name by default; set statusLine.compactThinkingLevel to false to restore the previous display.
Fixed
  • Fixed MCP OAuth discovery for shared API gateways and authorization servers with nested paths, including Keycloak realms, so authentication targets the correct resource issuer and supports endpoint and dynamic client-registration discovery.
  • Fixed credential rotation for HTTP 402 payment-required responses so sibling credentials are tried before model fallback without misclassifying informative non-quota errors.
  • Transport errors after a complete, non-executed tool call can now retry through configured retry budgets and fallback chains when it is safe to do so, instead of ending the turn prematurely.
  • Improved handling of truncated or otherwise undecodable images so they produce an actionable error and no longer permanently block subsequent requests or resumed sessions.
  • Fixed Sharpshooter consolidation preserving memory files and queued changes when an empty replacement is returned.
  • Fixed omp plugin features so it discovers marketplace-installed plugins.
  • Fixed Escape handling when closing the /session information panel; the panel now retains focus until dismissed.
  • Fixed the thinking-block visibility toggle so streamed reasoning is correctly hidden when thinking blocks are set to hidden.
  • Reduced high idle CPU usage while the agent is working.
  • Fixed resumed advisor subscription usage being displayed as a dollar amount instead of as a subscription.
  • Fixed relative API addresses whose names end in image extensions being pasted as text instead of incorrectly treated as missing local image files.
  • Fixed chat Markdown links and bare URLs so they become clickable OSC 8 hyperlinks when tui.hyperlinks=always is enabled.
  • Fixed unreadable composer text on light terminal backgrounds when using transparent composer styles.
  • Fixed retry.fallbackChains warnings for valid selectors from providers whose model discovery is still pending; validation now updates after discovery completes.
  • Fixed visible browser windows launched by OMP so page content resizes with the operating-system window.
  • Fixed Python evaluation hanging on Windows when importing native-extension modules such as NumPy.
  • Fixed subagent extension context helpers so ctx.getContextUsage() and ctx.compact() operate on the child session.
  • Fixed lsp diagnostics incorrectly reporting success for project-aware pull-diagnostic servers when diagnostics time out or fail.
  • Corrected labels under Settings > Context > Compaction Token Limit.
  • Fixed orphaned pages, iframes, and workers accumulating in the shared headless browser after abnormal OMP session termination.

@​oh-my-pi/pi-mnemopi

Fixed
  • Fixed working-memory recall returning too few or no results after matching memories were invalidated.

@​oh-my-pi/pi-natives

Fixed
  • Fixed staging and committing files through a reused Git repository handle, ensuring newly staged changes are correctly included in commits even on filesystems with coarse timestamp resolution.

@​oh-my-pi/pi-tui

Added
  • Added setTerminalHyperlinks() to let hosts control OSC 8 hyperlink behavior in rendered Markdown links.
Fixed
  • Fixed inline color swatches appearing for words with hex-like prefixes, such as #each; swatches now appear only when the entire word is a valid color.

@​oh-my-pi/pi-utils

Fixed
  • Fixed runtime installation getting stuck for up to 60 seconds after an installer crash or forced termination, allowing subsequent installation attempts to proceed normally.

What's Changed

New Contributors

Full Changelog: can1357/oh-my-pi@v18.0.10...v18.0.11

v18.0.10

Compare Source

@​oh-my-pi/pi-agent-core

Added
  • Added support for continuing interrupted agent runs with pending tool calls, allowing those calls to be retried before requesting the next model response.

@​oh-my-pi/pi-coding-agent

Added
  • Added the Sharpshooter memory backend for tracking friction-earned project decisions, with /memory queue and /memory sync controls.
  • Added /restart to relaunch omp with its original launch flags and resume the current session in place.
  • Added the band composer shape, a flush powerline status band above the prompt; it is now the default while existing composer.shape settings remain unchanged.
  • Added in-place retry for interrupted or failed tool calls: use F5, Alt+R (app.retry), or /retry to replay an intact failed batch without an additional model round trip.
  • Improved the working status display with a timed braille spinner, streamed intent, session accent colors across relevant status elements, and theme-aware session accent generation.
  • Updated the unicode and ascii symbol presets to use π/pi for the brand icon, avoiding tofu on fonts without the nerd-font glyph.
Changed
  • The /review command's PR-style comparison now uses the merge base against the current branch, excluding commits that exist only on the base branch; selecting the current branch reports no changes.
  • Prompt history is now persisted immediately when submitted, and session database state is checkpointed on exit to improve durability and prevent unbounded WAL growth.
Fixed
  • Fixed edit-tool parsing of －-prefixed MATCH lines so they correctly represent whole-line deletions and can be replaced by a following ＋ run.
  • Fixed interrupted and failed Python evaluation cells being reported as successful results instead of errors, improving model handling, telemetry, retries, and background-job failure reporting.
  • Fixed native-extension imports such as numpy hanging indefinitely in the Python evaluation tool on Windows.
  • Fixed a macOS composer display issue where undercurl could remain attached to stale text after rapid typing.
  • Improved xd:// MCP failure messages with actionable transport stages, failure categories, server and tool context, retryability, trace IDs, and redacted JSON-RPC details.
  • Fixed ACP read tool-call locations so clients such as Zed Follow receive the resolved filesystem path rather than the OMP line-range selector.

@​oh-my-pi/pi-natives

Added
  • Added native process replacement support for the CLI’s /restart command.
  • Added VcsGitRepo.mergeBase(a, b) to find the best common ancestor of two Git revisions, returning null when the histories are unrelated.

@​oh-my-pi/pi-tui

Added
  • Press the Right Arrow at the end of a line to accept autocomplete suggestions, inline ghost-text completions, and spelling corrections, just like Tab.
  • Added a smooth brand-color transition and an elapsed turn timer to the status line while the agent is working.
  • Added a full-width “band” composer style for flush status lines.

@​oh-my-pi/pi-utils

Added
  • Added postmortem.drainStdout to flush buffered standard output before process exit or exec-replacement.
  • Added an exitOnly option to postmortem.register for resources that should remain available during keep-alive cleanup and be released only on actual process exit.
  • Added hexToOklch and oklchToHex color conversion utilities with sRGB gamut mapping that reduces chroma when necessary.
  • Added checkpointWal to checkpoint committed SQLite WAL frames without blocking concurrent readers.
Fixed
  • Fixed repeatable postmortem cleanup behavior so persistent resources and callbacks registered during cleanup remain active until the eventual process exit.
  • Fixed asynchronous postmortem cleanup so callbacks registered during a cleanup pass are awaited before cleanup completes, including during signal-driven exits.

What's Changed

Full Changelog: can1357/oh-my-pi@v18.0.9...v18.0.10

v18.0.9

Compare Source

@​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

New Contributors

Full Changelog: can1357/oh-my-pi@v18.0.8...v18.0.9

v18.0.8

Compare Source

@​oh-my-pi/pi-ai

Added
  • Added Z.AI GLM Coding Plan usage tracking: credit-based CREDIT_LIMIT windows (5h + weekly) now surface in omp usage and the status line with the plan tier (plan: lite/pro/max).
Fixed
  • Fixed Amazon Bedrock requests to OpenAI-schema models (the gpt-5.x SKUs) failing with HTTP 400 unknown_parameter: 'thinking' when reasoning was enabled, by sending reasoning.effort instead of Anthropic's thinking budget block for models the catalog marks as effort-controlled.
  • Fixed Cursor replay rejecting sessions with orphaned tool results while preserving their output as assistant context.

@​oh-my-pi/pi-catalog

Fixed
  • Fixed the thinking control mode for OpenAI models served over Bedrock Converse (global.openai.gpt-5.6-luna, -sol, -terra), which are now classified as effort rather than budget so requests use OpenAI's reasoning schema.
  • Fixed LiteLLM discovery leaking a colliding bundled model's provider-specific transport onto custom endpoints: a discovered alias (e.g. kimi-k3) matching a bundled Fireworks model no longer inherits that model's wire-id transform, which had caused requests to POST a model id the endpoint never advertised and return HTTP 400 (#​9938).

@​oh-my-pi/pi-coding-agent

Added
  • Transcript usage rows now show the total prompt-to-yield time (Δ + clock, including tool calls) after the turn timestamp, opt-in via display.showTurnTime (off by default).
  • omp usage now shows Z.AI GLM Coding Plan credit quotas (5h + weekly) with the subscribed plan tier.
  • The usage status line now labels untiered quota windows with the report's plan tier, surfacing Z.AI Coding Plan (pro) and Codex plan names next to the 5h/7d percentages.
Fixed
  • Fixed corrupt session headers silently overwriting recoverable transcripts during resume (#​9915).
  • Fixed a startup race that left a new session with almost no tools and an empty skill inventory. An early reconcile could commit a small live tool set as the permanent enabled set. The enabled set is now seeded from the construction-time tool slate, and reconcileCodeMode samples it inside the registry mutation lock.
  • Fixed snapcompact compaction frames larger than the persistence limit being truncated into invalid image base64 on session resume, which made the provider reject every subsequent request with HTTP 400; already-corrupted archives now resume from their retained source text instead (#​9901).
  • Fixed prompts hanging when a successful automatic retry ended through an early terminal path such as yield.
  • Fixed hub send await:true blocking for the full IRC timeout when the awaited agent finished without replying; the send now settles as soon as the peer stops (#​9913).
  • Fixed workspace symbol searches reporting success when every configured language server failed; partial failures now remain visible alongside successful results (#​8387).
  • Handle denied working-directory changes without crashing resume, move, or startup flows.
  • Fixed Cursor-only sessions becoming permanently unusable after replaying orphaned async tool results.
  • Fixed !command config values (auth.broker.url, auth.broker.token, custom headers) passing inherited file descriptors to the resolution command; on POSIX these commands now run under /bin/sh (Windows keeps the built-in shell and is unchanged)
  • Fixed providers.amazon-bedrock guardrail, transport, and header settings being dropped for models referenced by an inference-profile ARN.
  • Fixed the welcome screen staying at its original width after a terminal resize; a settled rebuild now recomposes it at the new width like the rest of the transcript.
  • Fixed omp if-bench ending an Anthropic model's run on a transient Refusal (cyber) classification; the cyber classifier is stochastic near the threshold, so a refused turn is now retried with a fresh session (up to 3 attempts) before it is scored as a run-ending provider failure.
  • Fixed streamed assistant responses crashing when a later provider delta revised earlier Markdown; assistant output now stays mutable until finalization.
  • Fixed an orphaned foreground tool card surviving a later agent turn and pinning the entire transcript outside native scrollback; new turns now seal abandoned cards while preserving background-task updates.
  • Fixed resize and display replays to include naturally emitted active-head rows in one atomic bottom-first transaction without rewinding lifecycle state, while graceful shutdown still drains every eligible final suffix.
  • Fixed terminal resizes lagging on large transcripts: the transient resize repaint now renders only the visible tail instead of the entire committed transcript per resize event.
  • Fixed cache-miss dividers crashing completed streamed assistant messages after stable rows had entered native history; cache-miss status now trails the assistant output.
  • Fixed quitting re-streaming the entire committed transcript when a resize-triggered scrollback replay was still pending; shutdown now flushes only genuinely un-retired rows.
  • Fixed fast tool completions leaving a permanent running summary that blocked transcript retirement and squeezed later tool output.
  • Fixed omp git hunk navigation (alt+↓/alt+↑) appearing to do nothing while the file sidebar had focus: the diff cursor band now stays visible (dimmed) when the pane is unfocused.
  • Fixed the git TUI sidebar jumping back to the top of the file list after staging or unstaging a file; selection now stays on the nearest remaining row
  • Fixed the aarch64-linux nix build output segfaulting in the dynamic loader before startup by repointing the stale DT_VERDEF that patchelf leaves behind when it grows .dynamic, and surfaced smoke-test signal deaths in the build log instead of masking them (#​9881).
  • Added custom RPC launcher builders so embedded clients can transport omp RPC through SSH and remote process managers.

@​oh-my-pi/collab-web

Added
  • Transcript Markdown now renders LaTeX: $…$ and \(…\) inline, $$…$$ and \[…\] in display mode, plus own-line $$/\[ blocks. Currency ("$5 and $10"), escaped dollars, and code spans stay literal, and half-streamed delimiters stay visible until the equation closes.
  • Note: parity with the TUI covers these delimited forms only. Bare \begin{…}…\end{…} environments without $$/\[ fences remain literal here (the TUI typesets them); web support is a follow-up.

@​oh-my-pi/pi-natives

Fixed
  • Large session histories no longer leave macOS Terminal unresponsive during repaint.
  • Bounded the interactive PTY reader→JS queue (64 × ≤64 KiB) and forward chunks through a separate call_async pump so a fast child plus a stalled JS consumer cannot accumulate unbounded output in-process, without freezing PTY input/resize/kill. After a finite child exit, wait until accepted output reaches on_chunk; only a permanently open slave skips that wait. Cancel, timeout, and that stuck-open path abort the pump before start() resolves. Same defect class as the non-PTY bash bridge (#​4078).

@​oh-my-pi/pi-tui

Added
  • ProcessTerminal accepts a conpty option to force ConPTY-hosted behavior on or off, keeping terminal tests hermetic on WSL where live env detection would otherwise flip kitty-keyboard flags and write chunking (#​9887).
Fixed
  • Fixed pending-work animations repeatedly composing expensive frames without applying their full render cost to CPU backpressure.
  • Fixed unfinished live viewport rows entering tmux pane history and duplicating streamed output (#​9780).

@​oh-my-pi/pi-utils

Added
  • Added the Linux subreaper spawn option to retain reparented descendants for process-tree cleanup.
Fixed
  • Keep project-directory state unchanged when changing directories fails.
  • Fixed ptree timeout cleanup and output capture so timed commands retain their deadline through descendant-held pipes and untimed commands read output to EOF.

What's Changed

New Contributors

Full Changelog: can1357/oh-my-pi@v18.0.7...v18.0.8

v18.0.7

Compare Source

@​oh-my-pi/pi-agent-core

Fixed
  • Fixed Codex remote compaction to preserve images returned by image-reading tools, preventing them from being replayed as incorrect synthetic user messages.

@​oh-my-pi/pi-ai

Added
  • Added application-level usage attribution for billing and usage reporting, with per-application aggregation and automatic client identification. Applications can set their label with OMP_APP_NAME (default: omp); update the broker before clients to support the new usage reports.
Fixed
  • Fixed Anthropic Claude subscription OAuth requests being rejected by the upstream service (#​9801).
  • Fixed OpenAI-compatible streaming errors being reported as empty successful completions, enabling retries and model fallback when queue admission fails.
  • Fixed multimodal tool results in OpenAI Responses requests so inline, remote, and OpenAI file-backed images are preserved correctly.
  • Fixed resumed and forked Cursor sessions failing when their history came from a Responses-based provider such as Codex (#​9754).
  • Fixed Cursor composer-2.5 selections using the Fast variant instead of the Standard tier (#​9012).

@​oh-my-pi/browser-relay

Changed
  • Clarified the scope of the two browser relay opt-in paths: per-call app.relay: true enables relay access for an individual call, while the browser.relay setting enables it by default across projects in a profile.

@​oh-my-pi/pi-catalog

Added
  • Added cached background refresh from the shared models.dev catalog so newly published models for known providers can appear without a new OMP release, while bundled models remain the offline fallback.
Fixed
  • Fixed LiteLLM model discovery so model pricing is correctly populated when pricing information is provided by a later metadata endpoint.

@​oh-my-pi/pi-coding-agent

Added
  • Added nonblocking shared model-catalog refresh with cached startup hydration and source freshness diagnostics, allowing newly published models for known providers to appear without a binary release.
  • Added omp usage clients to report per-client token usage recorded by the auth broker, including the machine and application responsible for usage by provider. Supports --days and --json output.
Changed
  • Improved omp git responsiveness by streaming file contents, rendering complete lines promptly, progressively applying syntax highlighting, and deferring large commit statistics until after the first interactive frame.
  • Expanded omp git navigation and editing shortcuts: refresh with r, stage or unstage files and directories with s, u, or space, navigate hunks and files with keyboard shortcuts, use Vim-style motions in both panes, select diff views with 1–4, and open the commit form with c.
  • Standardized completed edit results across edit modes with hashline-style paths and numbered previews.
  • Documented browser relay behavior more clearly, including that browser.relay can enable relay access independently of app.relay and that a relayed session operates in the user's logged-in browser.
  • Clarified the computer tool documentation: desktop.window() must be awaited, and win.ax() returns a textual accessibility-tree snapshot rather than a structured node list.
Fixed
  • Fixed hub process waits being incorrectly prolonged or satisfied by a replacement process after an automatic restart.
  • Preserved an explicitly empty tools: [] configuration for agent definitions instead of adding default work tools.
  • Corrected MCP per-tool approval configuration documentation and behavior to use registered tool names for deny policies.
  • Made /branch consistently open the branch-from-message selector regardless of the doubleEscapeAction setting.
  • Improved ACP behavior when prompting during an active turn by returning a typed session_busy JSON-RPC error instead of an opaque internal error.
  • Fixed --model <id>:<effort> losing its effort setting when cycling back to the default role; an explicit --thinking setting continues to take precedence.
  • Fixed extension-registered Codex models configured with preferWebsockets: false from attempting a WebSocket connection.
  • Fixed stale command-generated provider and model-override credentials after HTTP 401 responses by refreshing credentials before retrying.
  • Fixed extensions configured in .omp/config.yml not exposing their bundled skills, hooks, tools, commands, rules, prompts, and MCP configuration for discovery.
  • Fixed compiled extensions that could not import public coding-agent registry modules.
  • Fixed extension-provided environment variables being lost in user shell commands and prevented environment changes from one hook from affecting later commands.
  • Fixed imported and legacy sessions with missing usage metadata from dropping RPC lifecycle events.
  • Fixed GitHub and GitHub Enterprise issue, pull-request, and tool lookups to preserve and use the repository's actual host.
  • Fixed binary installation when GitHub returns minified release metadata.
  • Fixed omp bench and omp if-bench resolving credential-scoped dynamic models already listed by omp models.
  • Fixed checkpoint and rewind recovery in Codex Code Mode.
  • Fixed truncated ask questions being displayed incorrectly when expanded with Ctrl+O.
  • Fixed the welcome screen and transcript layout not adapting correctly after terminal resizes.
  • Made omp if-bench retry transient Anthropic cyber-safety refusals before treating them as run-ending failures.
  • Fixed streamed assistant responses when later provider updates revise earlier Markdown.
  • Fixed abandoned foreground tool cards and fast tool completions from blocking transcript scrolling or later output.
  • Improved transcript replay and shutdown behavior so terminal resizes and exits do not duplicate, lose, or unnecessarily re-render committed output.
  • Fixed cache-miss status messages from disrupting completed streamed assistant responses.
  • Fixed YAML rewrites for settings, migrated configuration, and keybindings from adding trailing spaces to nested mapping headers.
  • Fixed /model role-cycle icons overlapping their ordinal on terminals with full-width icon rendering.
  • Improved /collab QR-code

[!IMPORTANT]
✂ PR body was truncated to here.

Configuration

📅 Schedule: (in timezone Europe/Warsaw)

  • Branch creation
    • "before 6am on monday"
  • Automerge
    • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

  • If you want to rebase/retry this PR, check this box

This PR was generated by Mend Renovate. View the repository job log.

@coldtea-pr-lens

coldtea-pr-lens Bot commented Sep 30, 2026

Copy link
Copy Markdown

◈ PR Lens

Note

renovate[bot] opened this pull request, so PR Lens left it undrawn. Comment @pr-lens draw to draw it

github.comment.notice: false in .github/pr-lens.yml turns this note off

@renovate
renovate Bot force-pushed the renovate/patch-oh-my-pi branch from ee70117 to 9f81266 Compare October 2, 2026 20:49
@renovate
renovate Bot requested a review from oritwoen as a code owner October 2, 2026 20:49
@renovate
renovate Bot force-pushed the renovate/patch-oh-my-pi branch from 9f81266 to f208aa2 Compare October 5, 2026 13:16
@cloudflare-workers-and-pages

cloudflare-workers-and-pages Bot commented Oct 5, 2026 •
edited
Loading

Copy link
Copy Markdown

🚀 Deploying Preview to Cloudflare 🚀

Preview URL: https://renovate-patch-oh-my-pi-agntn-tools.oritwoen.workers.dev (commit f208aa2)

This URL reflects your latest Preview deployment

Preview Deployments by commit

Status Deployment URL Commit Updated (UTC) See this deployment's details
  • Build: Success ✅
  • Deployment: Success ✅

View logs ↗		 https://79ab225a-agntn-tools.oritwoen.workers.dev f208aa2 2026-10-05T13:18:43.890Z Visit the dashboard ↗

@renovate
renovate Bot force-pushed the renovate/patch-oh-my-pi branch from f208aa2 to 64fe3cc Compare October 19, 2026 01:25
@renovate
renovate Bot force-pushed the renovate/patch-oh-my-pi branch from 64fe3cc to 4a407b5 Compare October 26, 2026 00:59
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@oritwoen oritwoen Awaiting requested review from oritwoen oritwoen is a code owner

Assignees

No one assigned

Labels

dependencies

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

0 participants