build(deps): bump the root-npm group across 1 directory with 6 updates

[dependabot]

Bumps the root-npm group with 6 updates in the / directory:

Package	From	To
@oh-my-pi/pi-agent-core	16.1.20	18.0.11
@oh-my-pi/pi-ai	16.1.20	18.0.11
@oh-my-pi/pi-coding-agent	16.1.20	18.0.11
@oh-my-pi/pi-utils	16.1.20	18.0.11
katex	0.17.0	0.18.4
typescript	6.0.3	7.0.2

Updates @oh-my-pi/pi-agent-core from 16.1.20 to 18.0.11

Release notes

Sourced from @​oh-my-pi/pi-agent-core's releases.

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.

... (truncated)

Changelog

Sourced from @​oh-my-pi/pi-agent-core's changelog.

[18.0.11] - 2026-08-29

Fixed

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

[18.0.10] - 2026-08-28

Added

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

[18.0.9] - 2026-08-28

Fixed

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

[18.0.7] - 2026-08-26

Fixed

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

[18.0.5] - 2026-08-25

Fixed

• Corrected remote compaction summaries so they accurately report the number of input tokens processed.

[18.0.4] - 2026-08-24

Changed

• Improved performance in append-only context mode by memoizing message serialization, keeping per-call sync overhead flat as conversations grow.

Fixed

• Fixed an issue where onTurnEnd was skipped for turns ended by a terminal tool result (such as a subagent's final yield).

[18.0.0] - 2026-08-22

Fixed

• Fixed Anthropic Claude tool calls containing provider-visible private-use icon glyphs by reversibly tokenizing glyphs at the wire boundary and rejecting model-invented or unresolved glyph tokens before execution.
• Fixed agent identity confusion after session handoffs by clarifying context framing and ensuring successor instances seamlessly resume existing execution plans.

[17.4.1] - 2026-08-21

Fixed

... (truncated)

Commits

• 1122061 chore: bump version to 18.0.11
• a782faf chore: rewrite changelogs
• 0618d95 fix(agent): keep tokenizer fallback conservative
• aa8b053 fix(agent): fall back when native tokenizer encoding is unknown
• b16f4f1 chore: bump version to 18.0.10
• 423f76b feat(coding-agent): added manual tool-replay retry affordance
• d3924b6 chore: bump version to 18.0.9
• 8d882aa chore: rewrite changelogs
• 8eb3d90 fix(agent): replay images from elided tool results
• 1ffa63b fix(agent): preserve images during shake elision
• Additional commits viewable in compare view

Updates @oh-my-pi/pi-ai from 16.1.20 to 18.0.11

Release notes

Sourced from @​oh-my-pi/pi-ai's releases.

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.

... (truncated)

Changelog

Sourced from @​oh-my-pi/pi-ai's changelog.

[18.0.11] - 2026-08-29

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.

[18.0.9] - 2026-08-28

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.

[18.0.8] - 2026-08-27

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.

[18.0.7] - 2026-08-26

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).

[18.0.6] - 2026-08-26

Added

• Added the backgroundIdleMs option to customize how long background auth-broker activity remains active before automatically parking.

... (truncated)

Commits

• 1122061 chore: bump version to 18.0.11
• a782faf chore: rewrite changelogs
• 3947a88 chore: normalized changelogs and formatting after merging sweep fixes
• 5e8fbd0 Merge PR #10160: fix(auth): prevent unregistered Z.AI callback ports (@​roboomp)
• 2ea86e1 fix(coding-agent): harden unreadable image guard
• 08ab197 test(ai): cover qianfan model-scoped login
• 5912429 Merge PR #10073: fix(ai): tolerate qianfan invalid_model during api key valid...
• c8b7af7 Merge PR #10059: fix(ai): complete Perplexity TOTP login (@​spcbot)
• 1453cc7 Merge PR #10181: fix(ai): classify HTTP 402 as usage limit to rotate sibling ...
• 61bbd01 Merge PR #10173: fix(ai): preserve Gemini thought signatures (@​roboomp)
• Additional commits viewable in compare view

Updates @oh-my-pi/pi-coding-agent from 16.1.20 to 18.0.11

Release notes

Sourced from @​oh-my-pi/pi-coding-agent's releases.

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.

... (truncated)

Changelog

Sourced from @​oh-my-pi/pi-coding-agent's changelog.

[18.0.11] - 2026-08-29

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.

[18.0.10] - 2026-08-28

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

... (truncated)

Commits

• 1122061 chore: bump version to 18.0.11
• a782faf chore: rewrite changelogs
• 3947a88 chore: normalized changelogs and formatting after merging sweep fixes
• 7a8870c fix: reconciled merged fixes with gallery and typecheck gates
• b62b451 Merge PR #10190: test(coding-agent): make issue-966 repro deterministic again...
• 2a05b43 Merge PR #10069: fix(coding-agent): correct compact limit label (@​kidonng)
• 60e1e7b Merge PR #10039: fix(tui): keep transparent composer text readable (@​roboomp)
• dd0d37b fix(tui): apply hyperlink policy during settings init
• db2f558 Merge PR #10196: fix(tui): honor tui.hyperlinks setting for chat markdown lin...
• 1b04173 Merge PR #10106: fix(tui): preserve relative image URL pastes (@​roboomp)
• Additional commits viewable in compare view

Updates @oh-my-pi/pi-utils from 16.1.20 to 18.0.11

Release notes

Sourced from @​oh-my-pi/pi-utils's releases.

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.

... (truncated)

Changelog

Sourced from @​oh-my-pi/pi-utils's changelog.

[18.0.11] - 2026-08-29

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.

[18.0.10] - 2026-08-28

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.

[18.0.9] - 2026-08-28

Fixed

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

[18.0.8] - 2026-08-27

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.

[18.0.7] - 2026-08-26

Added

• Added math-delimiters, the LaTeX span/block delimiter grammar (mathStartIndex, mathOpenerAt, mathSpanAt, mathBlockAt) shared by every Markdown renderer: pandoc's anti-currency rules for $…$, own-line display blocks, and delimiters matched by backslash parity, so an escaped \$x$ stays literal and a TeX row break cannot end a span early.
• Added RequestError.sessionBusy(message, data) to represent ACP session-busy errors (-32003) through the shared JSON-RPC transport.
• Exported getComposerCacheDir for resolving the per-project Composer cache directory, including support for XDG_CACHE_HOME.

Fixed

• Fixed OMP sessions unexpectedly exiting during socket cleanup or optional-worker communication on Bun.

[18.0.6] - 2026-08-26

... (truncated)

Commits

• 1122061 chore: bump version to 18.0.11
• a782faf chore: rewrite changelogs
• 7b8df15 fix(utils): recover crashed compatibility reservation
• f91f375 fix(utils): reclaim legacy install lock only when stale
• 45978c9 fix(utils): reserved legacy lock during runtime install
• fd6e727 fix(utils): hand off in-flight legacy install lock during migration
• 2f8979a fix(utils): make runtime install lock crash-safe
• b16f4f1 chore: bump version to 18.0.10
• 423f76b feat(coding-agent): added manual tool-replay retry affordance
• 99b16c8 fix(utils): joined late cleanup promises into the active postmortem pass
• Additional commits viewable in compare view

Updates katex from 0.17.0 to 0.18.4

Release notes

Sourced from katex's releases.

v0.18.4

0.18.4 (2026-08-10)

Bug Fixes

• environment: report invalid environment names as ParseError (#4256) (e507f75), closes #3760 #3760

v0.18.3

0.18.3 (2026-08-09)

Bug Fixes

• allow braced arguments for delimsizing (#4255) (1c973ae)

v0.18.2

0.18.2 (2026-08-08)

Bug Fixes

• prevent prototype pollution in settings (#4260) (0adf7e7)

v0.18.1

0.18.1 (2026-07-19)

Bug Fixes

• htmlData: allow escaped commas in \htmlData (#4236) (87a2b30), closes #4204 #4218

v0.18.0

0.18.0 (2026-07-17)

Features

• prefix css classes (#4229) (6f5c44f)

BREAKING CHANGES

• users who apply custom styles or have allowlists targeting KaTeX's internal classes must update their selectors.

Changelog

Sourced from katex's changelog.

0.18.4 (2026-08-10)

Bug Fixes

• environment: report invalid environment names as ParseError (#4256) (e507f75), closes #3760 #3760

0.18.3 (2026-08-09)

Bug Fixes

• allow braced arguments for delimsizing (#4255) (1c973ae)

0.18.2 (2026-08-08)

Bug Fixes

• prevent prototype pollution in settings (#4260) (0adf7e7)

0.18.1 (2026-07-19)

Bug Fixes

• htmlData: allow escaped commas in \htmlData (#4236) (87a2b30), closes #4204 #4218

0.18.0 (2026-07-17)

Features

• prefix css classes (#4229) (6f5c44f)

BREAKING CHANGES

• users who apply custom styles or have allowlists targeting KaTeX's internal classes must update their selectors.

Commits

• 49dc3d9 chore(release): 0.18.4 [ci skip]
• e507f75 fix(environment): report invalid environment names as ParseError (#4256)
• f0f46a8 chore(release): 0.18.3 [ci skip]
• 1c973ae fix: allow braced arguments for delimsizing (#4255)
• a11ce72 docs: update migration guide (#4248)
• 95322e1 docs: add Deno section (#4254)
• dd88e46 chore(deps): update dependency js-yaml to v4.3.1 [security] (#4263)
• 93c362b chore(release): 0.18.2 [ci skip]
• 0adf7e7 fix: prevent prototype pollution in settings (#4260)
• 5a5bf20 chore(deps): update dependency postcss to v8.5.23 [security] (#4259)
• Additional commits viewable in compare view

Install script changes

This version adds prepare script that runs during installation. Review the package contents before updating.

Updates typescript from 6.0.3 to 7.0.2

Release notes

Sourced from typescript's releases.

TypeScript 7.0.2

https://devblogs.microsoft.com/typescript/announcing-typescript-7-0/

This tag was originally released at: https://github.com/microsoft/typescript-go/releases/tag/typescript%2Fv7.0.2

Commits

• 1e4744d Merge branch 'main' into ts7-release
• a5a219cmicrosoft/typescript-go#4558
• ecfe30d Update status localization
• 5de25b5 Hide executable name in TypeScript status
• d7ce74a Show bundled TypeScript version for packaged servers
• 29be66a Correct TS 7 release version to 7.0.2
• ed2bd1b Merge branch 'main' into ts7-release
• 8873075 Bump the github-actions group across 1 directory with 3 updates (microsoft/ty...
• 9427131 Set up stable / nightly extension split, other prep (microsoft/typescript-go#...
• d4eaca5microsoft/typescript-go#4549
• Additional commits viewable in compare view

Maintainer changes

This version was pushed to npm by microsoft1es, a new releaser for typescript since your current version.

[dependabot]

Labels

The following labels could not be found: dependencies. Please create it before Dependabot can add it to a pull request.

Please fix the above issues or remove invalid values from dependabot.yml.