v18.0.11

@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

• fix(tui): hide thinking blocks emitted as append-only stable rows by @roboomp in #10178
• fix(coding-agent): resolve marketplace plugin features by @thebtf in #10183
• test(coding-agent): make issue-966 repro deterministic against stale gix index by @Mustaqeem66 in #10190
• fix(tui): honor tui.hyperlinks setting for chat markdown links by @roboomp in #10196
• fix(sharpshooter): refuse all-empty replacement to prevent memory wipe by @STRML in #10200
• fix(browser): reap orphaned shared-browser targets from dead sessions by @roboomp in #10025
• fix(catalog,coding-agent): strip OpenRouter route suffixes in bareModelId by @yudhiesh-oc in #10034
• fix(lsp): surface slow or failed pull diagnostics instead of reporting OK by @roboomp in #10036
• fix(tui): keep transparent composer text readable by @roboomp in #10039
• fix(mcp): support sub-path OAuth issuer discovery by @roboomp in #10045
• fix(session): defer retry.fallbackChains warnings for pending discovery by @roboomp in #10050
• fix(coding-agent): stop an undecodable image wedging a session by @dungartoriaaa in #10055
• fix(ai): complete Perplexity TOTP login by @spcbot in #10059
• fix(coding-agent): correct compact limit label by @kidonng in #10069
• fix(ai): tolerate qianfan invalid_model during api key validation by @kindredzhang in #10073
• Enable image input for supported Cursor models by @HarryFalse in #10076
• fix(catalog): mirror Workers AI models into Cloudflare gateway by @AshishKumar4 in #10084
• fix(browser): don't pin viewport on visible headless launches by @mgarmash in #10095
• fix(mnemopi): also exclude expired rows from FTS candidate slots by @BAKocska in #10096
• fix(extensions): restore subagent context callbacks by @roboomp in #10098
• fix(catalog): Fix Baseten GLM models being marked as non-reasoning (including GLM 5.3 Flash) by @jcfrancisco in #10100
• fix(tui): preserve relative image URL pastes by @roboomp in #10106
• fix(coding-agent): close /session panel with Esc without aborting the session by @brunowowk in #10110
• fix(ai): classify zero-content message_stop stream truncation as transient by @bk-ty in #10112
• fix(ai): retry empty Anthropic stream truncations by @roboomp in #10114
• fix(utils): make runtime install lock crash-safe by @roboomp in #10123
• fix(coding-agent): stop per-frame model-catalog scan in cost status segment by @roboomp in #10131
• fix(pi-vcs): read the git index from disk to avoid stale snapshot by @roboomp in #10132
• fix(auth): prevent unregistered Z.AI callback ports by @roboomp in #10160
• fix(coding-agent): prefer RFC 9728 path-inserted protected-resource metadata by @Chityanj in #10168
• fix(coding-agent): auto-retry transport errors after proven-unexecuted tool calls by @1Morganmore in #10171
• fix(ai): preserve Gemini thought signatures by @roboomp in #10173
• fix(agent): fall back when native tokenizer encoding is unknown by @atacolak in #10174
• docs: sync documentation with code and changelogs as of 18.0.10 by @KamijoToma in #10176
• fix(ai): classify HTTP 402 as usage limit to rotate sibling OAuth credentials before model fallback by @sshantiomm-coder in #10181

New Contributors

• @thebtf made their first contribution in #10183
• @yudhiesh-oc made their first contribution in #10034
• @spcbot made their first contribution in #10059
• @kindredzhang made their first contribution in #10073
• @HarryFalse made their first contribution in #10076
• @mgarmash made their first contribution in #10095
• @brunowowk made their first contribution in #10110
• @bk-ty made their first contribution in #10112
• @Chityanj made their first contribution in #10168
• @1Morganmore made their first contribution in #10171
• @sshantiomm-coder made their first contribution in #10181

Full Changelog: v18.0.10...v18.0.11