Bump the development group with 4 updates

[dependabot]

⚠️ Dependabot is rebasing this PR ⚠️

Rebasing might not happen immediately, so don't worry if this takes some time.

Note: if you make any changes to this PR yourself, they will take precedence over the rebase.

---

Bumps the development group with 4 updates: @earendil-works/pi-coding-agent, @earendil-works/pi-tui, @types/node and tsx.

Updates @earendil-works/pi-coding-agent from 0.85.1 to 0.86.1

Release notes

Sourced from @​earendil-works/pi-coding-agent's releases.

v0.86.1

New Features

• Meta Muse provider — Sign in with Meta using /login meta or use META_API_KEY to access Muse Spark models. See Meta (Muse subscription).

Added

• Added Meta (Muse subscription) login via /login meta with automatic Model API key refresh, plus META_API_KEY support (#9096 by @​xl0).

Changed

• Enabled Node's persistent compile cache before loading the bundled CLI runtime, reducing repeat launch time.

Fixed

• Fixed /bug descriptions dropping line breaks from pasted diagnostics.
• Fixed /bug hints appearing for user cancellations and retryable provider failures such as service unavailability.
• Fixed clipboard copy failing in containers and WSL without WSLg by restoring the OSC 52 fallback when no display is available, and added a verified Windows clipboard backend for WSL (#9688).
• Fixed inherited z.ai Prompt too long errors not being recognized as context overflow (#9805).
• Fixed inherited Cerebras models advertising unsupported strict tool schemas, which caused HTTP 400 errors when strict and non-strict tools were mixed (#9804 by @​EdenGottlieb).

v0.86.0

New Features

• Prompt cache warming — Keep valuable prompt caches alive during long tool runs and optionally while idle using cost-aware refreshes. See Cache Warming.
• Bug reporting — Report problems with /bug using redacted diagnostics, optional transcripts, or exported ZIP archives. See Reporting Bugs.
• Transcript-aware prompt and tool updates — Preserve instruction and tool changes across resume and branch navigation while retaining cached prefixes. See before_agent_start.
• Offline Radius model catalog — Select Radius models immediately, with cached and live catalogs overlaid when available. See Radius.
• Per-model compaction budgets — Configure reserved and recent-token budgets by model. See Per-model overrides.

Breaking Changes

• Changed inherited pi-ai provider stream inputs from Context to normalized TranscriptContext values. Custom providers must read system prompts and tool declarations from context.messages with getCurrentSystemPrompt() and getCurrentTools(). See Custom Streaming API.
• Restricted inherited ToolCall.arguments and ToolResultMessage.details to JSON-compatible values, changed ToolResultMessage into a conditional type, and made JsonValue arrays readonly.
• user_bash now fails closed: errors or invalid defined results abort the command without invoking later handlers or executing locally. Return undefined to continue propagation; otherwise return { operations } or { result } (#9068).

Added

• Added transcript-backed mid-conversation system prompt and tool changes so instruction and tool updates survive resume and branch navigation while preserving cached prefixes on supported models. See before_agent_start and Entry Types (#9548).
• Added inherited native deferred tool loading for Fireworks Messages models. Use ToolSearch or tool_search as the loader name for prompt-prefix deferral (#9323).
• Added click toggling for branch summaries, compaction summaries, and skill invocation entries.
• Added the public Radius model catalog for immediate and offline model selection, with cached and live gateway catalogs overlaid when available.
• Added ctx.modelRegistry.stream() and streamSimple() for extension model calls through configured providers with resolved authentication (#8964).
• Added per-model reserveTokens and keepRecentTokens settings through compaction.modelOverrides, with ordinary compaction settings as fallback (#8133).
• Added compat.allowedFallbackModels configuration for overriding or disabling Anthropic server-side fallback models (#9294).
• Added an unsubscribe function from pi.on() so extensions can drop event handlers. Handlers added or removed during a dispatch apply to later dispatches, not the current one (#8967).
• Exported extension hook event and result types that were previously omitted from the package entry points (#9642).
• Added /bug [description] to report a bug to the Pi developers. The report bundles environment, model, provider, extension, and settings metadata (secrets redacted), assistant message diagnostics from the session, optionally the session transcript, or a model-written summary of what went wrong instead. It is uploaded to Radius (no login required; attributed when logged in) or exported as a zip archive, and the report id is recorded in the session as a pi.bug-report entry. Crashes are recorded in ~/.pi/agent/crashes.json, announced once on the next start, and attached to the next report; unexplained errors and exhausted retries point at /bug once per session.
• Added cost-aware prompt-cache warming during long tool runs and optionally while idle, with configurable modes, model cache-lifetime metadata, /session diagnostics, transcript notices, and the cache_warming_decision extension event. See Cache Warming (#9668).

... (truncated)

Changelog

Sourced from @​earendil-works/pi-coding-agent's changelog.

[0.86.1] - 2026-09-20

New Features

• Meta Muse provider — Sign in with Meta using /login meta or use META_API_KEY to access Muse Spark models. See Meta (https://github.com/earendil-works/pi/blob/main/packages/coding-agent/Muse subscription).

Added

• Added Meta (Muse subscription) login via /login meta with automatic Model API key refresh, plus META_API_KEY support (#9096 by @​xl0).

Changed

• Enabled Node's persistent compile cache before loading the bundled CLI runtime, reducing repeat launch time.

Fixed

• Fixed /bug descriptions dropping line breaks from pasted diagnostics.
• Fixed /bug hints appearing for user cancellations and retryable provider failures such as service unavailability.
• Fixed clipboard copy failing in containers and WSL without WSLg by restoring the OSC 52 fallback when no display is available, and added a verified Windows clipboard backend for WSL (#9688).
• Fixed inherited z.ai Prompt too long errors not being recognized as context overflow (#9805).
• Fixed inherited Cerebras models advertising unsupported strict tool schemas, which caused HTTP 400 errors when strict and non-strict tools were mixed (#9804 by @​EdenGottlieb).

[0.86.0] - 2026-09-19

New Features

• Prompt cache warming — Keep valuable prompt caches alive during long tool runs and optionally while idle using cost-aware refreshes. See Cache Warming.
• Bug reporting — Report problems with /bug using redacted diagnostics, optional transcripts, or exported ZIP archives. See Reporting Bugs.
• Transcript-aware prompt and tool updates — Preserve instruction and tool changes across resume and branch navigation while retaining cached prefixes. See before_agent_start.
• Offline Radius model catalog — Select Radius models immediately, with cached and live catalogs overlaid when available. See Radius.
• Per-model compaction budgets — Configure reserved and recent-token budgets by model. See Per-model overrides.

Breaking Changes

• Changed inherited pi-ai provider stream inputs from Context to normalized TranscriptContext values. Custom providers must read system prompts and tool declarations from context.messages with getCurrentSystemPrompt() and getCurrentTools(). See Custom Streaming API.
• Restricted inherited ToolCall.arguments and ToolResultMessage.details to JSON-compatible values, changed ToolResultMessage into a conditional type, and made JsonValue arrays readonly.
• user_bash now fails closed: errors or invalid defined results abort the command without invoking later handlers or executing locally. Return undefined to continue propagation; otherwise return { operations } or { result } (#9068).

Added

• Added transcript-backed mid-conversation system prompt and tool changes so instruction and tool updates survive resume and branch navigation while preserving cached prefixes on supported models. See before_agent_start and Entry Types (#9548).
• Added inherited native deferred tool loading for Fireworks Messages models. Use ToolSearch or tool_search as the loader name for prompt-prefix deferral (#9323).
• Added click toggling for branch summaries, compaction summaries, and skill invocation entries.
• Added the public Radius model catalog for immediate and offline model selection, with cached and live gateway catalogs overlaid when available.
• Added ctx.modelRegistry.stream() and streamSimple() for extension model calls through configured providers with resolved authentication (#8964).
• Added per-model reserveTokens and keepRecentTokens settings through compaction.modelOverrides, with ordinary compaction settings as fallback (#8133).
• Added compat.allowedFallbackModels configuration for overriding or disabling Anthropic server-side fallback models (#9294).
• Added an unsubscribe function from pi.on() so extensions can drop event handlers. Handlers added or removed during a dispatch apply to later dispatches, not the current one (#8967).
• Exported extension hook event and result types that were previously omitted from the package entry points (#9642).
• Added /bug [description] to report a bug to the Pi developers. The report bundles environment, model, provider, extension, and settings metadata (secrets redacted), assistant message diagnostics from the session, optionally the session transcript, or a model-written summary of what went wrong instead. It is uploaded to Radius (no login required; attributed when logged in) or exported as a zip archive, and the report id is recorded in the session as a pi.bug-report entry. Crashes are recorded in ~/.pi/agent/crashes.json, announced once on the next start, and attached to the next report; unexplained errors and exhausted retries point at /bug once per session.

... (truncated)

Commits

• 13cbf77 Release v0.86.1
• 68f9802 docs: audit Cerebras fix changelog entries
• 199160a docs(coding-agent): document inherited z.ai overflow fix
• 6dff740 fix(coding-agent): restore OSC 52 clipboard fallback for headless sessions
• ee2df31 docs: audit post-release changelog entries
• d875512 fix(coding-agent): suppress bug hints for expected failures
• 6074099 feat(coding-agent): cache compiled Node CLI modules
• b73412a feat(ai,coding-agent): add Meta provider with Muse subscription OAuth (#9096)
• d1230ea fix(coding-agent): preserve multiline bug descriptions
• 50d766c Add [Unreleased] section for next cycle
• Additional commits viewable in compare view

Updates @earendil-works/pi-tui from 0.85.1 to 0.86.1

Release notes

Sourced from @​earendil-works/pi-tui's releases.

v0.86.1

New Features

• Meta Muse provider — Sign in with Meta using /login meta or use META_API_KEY to access Muse Spark models. See Meta (Muse subscription).

Added

• Added Meta (Muse subscription) login via /login meta with automatic Model API key refresh, plus META_API_KEY support (#9096 by @​xl0).

Changed

• Enabled Node's persistent compile cache before loading the bundled CLI runtime, reducing repeat launch time.

Fixed

• Fixed /bug descriptions dropping line breaks from pasted diagnostics.
• Fixed /bug hints appearing for user cancellations and retryable provider failures such as service unavailability.
• Fixed clipboard copy failing in containers and WSL without WSLg by restoring the OSC 52 fallback when no display is available, and added a verified Windows clipboard backend for WSL (#9688).
• Fixed inherited z.ai Prompt too long errors not being recognized as context overflow (#9805).
• Fixed inherited Cerebras models advertising unsupported strict tool schemas, which caused HTTP 400 errors when strict and non-strict tools were mixed (#9804 by @​EdenGottlieb).

v0.86.0

New Features

• Prompt cache warming — Keep valuable prompt caches alive during long tool runs and optionally while idle using cost-aware refreshes. See Cache Warming.
• Bug reporting — Report problems with /bug using redacted diagnostics, optional transcripts, or exported ZIP archives. See Reporting Bugs.
• Transcript-aware prompt and tool updates — Preserve instruction and tool changes across resume and branch navigation while retaining cached prefixes. See before_agent_start.
• Offline Radius model catalog — Select Radius models immediately, with cached and live catalogs overlaid when available. See Radius.
• Per-model compaction budgets — Configure reserved and recent-token budgets by model. See Per-model overrides.

Breaking Changes

• Changed inherited pi-ai provider stream inputs from Context to normalized TranscriptContext values. Custom providers must read system prompts and tool declarations from context.messages with getCurrentSystemPrompt() and getCurrentTools(). See Custom Streaming API.
• Restricted inherited ToolCall.arguments and ToolResultMessage.details to JSON-compatible values, changed ToolResultMessage into a conditional type, and made JsonValue arrays readonly.
• user_bash now fails closed: errors or invalid defined results abort the command without invoking later handlers or executing locally. Return undefined to continue propagation; otherwise return { operations } or { result } (#9068).

Added

• Added transcript-backed mid-conversation system prompt and tool changes so instruction and tool updates survive resume and branch navigation while preserving cached prefixes on supported models. See before_agent_start and Entry Types (#9548).
• Added inherited native deferred tool loading for Fireworks Messages models. Use ToolSearch or tool_search as the loader name for prompt-prefix deferral (#9323).
• Added click toggling for branch summaries, compaction summaries, and skill invocation entries.
• Added the public Radius model catalog for immediate and offline model selection, with cached and live gateway catalogs overlaid when available.
• Added ctx.modelRegistry.stream() and streamSimple() for extension model calls through configured providers with resolved authentication (#8964).
• Added per-model reserveTokens and keepRecentTokens settings through compaction.modelOverrides, with ordinary compaction settings as fallback (#8133).
• Added compat.allowedFallbackModels configuration for overriding or disabling Anthropic server-side fallback models (#9294).
• Added an unsubscribe function from pi.on() so extensions can drop event handlers. Handlers added or removed during a dispatch apply to later dispatches, not the current one (#8967).
• Exported extension hook event and result types that were previously omitted from the package entry points (#9642).
• Added /bug [description] to report a bug to the Pi developers. The report bundles environment, model, provider, extension, and settings metadata (secrets redacted), assistant message diagnostics from the session, optionally the session transcript, or a model-written summary of what went wrong instead. It is uploaded to Radius (no login required; attributed when logged in) or exported as a zip archive, and the report id is recorded in the session as a pi.bug-report entry. Crashes are recorded in ~/.pi/agent/crashes.json, announced once on the next start, and attached to the next report; unexplained errors and exhausted retries point at /bug once per session.
• Added cost-aware prompt-cache warming during long tool runs and optionally while idle, with configurable modes, model cache-lifetime metadata, /session diagnostics, transcript notices, and the cache_warming_decision extension event. See Cache Warming (#9668).

... (truncated)

Changelog

Sourced from @​earendil-works/pi-tui's changelog.

[0.86.1] - 2026-09-20

[0.86.0] - 2026-09-19

Added

• Added bundled asynchronous native clipboard readers for macOS, Windows, and X11 through the exported getNativeClipboard() API, replacing the external native clipboard dependency in consumers (#9163).

Changed

• Reduced fuzzy search latency for long texts by using native substring search instead of scanning each character in JavaScript (#9267).

Fixed

• Fixed LaTeX legacy font switches falling back to raw source, centered cases layouts around surrounding equations, and vertically laid out unsupported and nested display scripts (#8827, #9564, #7929).
• Fixed fullscreen clipboard failures hiding actionable backend error messages behind a generic notice, and extended failure notices to five seconds (#9618).
• Fixed fullscreen Kitty images being erased by later row clears in WezTerm (#9169).
• Fixed skill slash-command autocomplete ranking the skill: prefix instead of the bare skill name (#9120 by @​yearth).
• Fixed file autocomplete boundaries and path quoting around CJK punctuation (#9746 by @​haoqixu).

Commits

• 13cbf77 Release v0.86.1
• 50d766c Add [Unreleased] section for next cycle
• ecac0a9 Release v0.86.0
• 12032de docs: complete unreleased changelog audit
• 803f0e9 fix(tui): preserve fullscreen images in WezTerm
• d7951ec fix(tui): rank skill autocomplete by bare name (#9120)
• fa0e1f4 fix(tui): improve LaTeX compatibility and layouts
• bfa6862 fix(tui): handle CJK punctuation in file autocomplete (#9746)
• eba6198 docs: audit unreleased changelogs
• 5901446 fix(tui): reduce fuzzy search latency
• Additional commits viewable in compare view

Updates @types/node from 22.20.3 to 22.20.4

Commits

• See full diff in compare view

Updates tsx from 4.23.13 to 4.23.15

Release notes

Sourced from tsx's releases.

v4.23.15

4.23.15 (2026-09-20)

Bug Fixes

• exclude bare builtins from namespace inheritance (38e1588)
• expose require.cache and require.extensions to tsImport CommonJS modules (2da3407)
• make namespaced register() overloads portable for declaration emit (562c434)

---

This release is also available on:

• npm package (@​latest dist-tag)

v4.23.14

4.23.14 (2026-09-20)

Bug Fixes

• restore the CJS bridge namespace for Node 24 require(esm) under tsImport() (#802) (6e5236b)

---

This release is also available on:

• npm package (@​latest dist-tag)

Commits

• ca66105 test: fix drive-less file URLs in ESM resolver fixtures
• 2da3407 fix: expose require.cache and require.extensions to tsImport CommonJS modules
• 38e1588 fix: exclude bare builtins from namespace inheritance
• 562c434 fix: make namespaced register() overloads portable for declaration emit
• edfb1f0 build: upgrade pkgroll and externalize CJS loader reference
• 70e7828 test: upgrade tinyspy for disposable API
• 9ed2022 ci: avoid duplicate release notifications
• 872e77f refactor: use disposables for cleanup
• 6e5236b fix: restore the CJS bridge namespace for Node 24 require(esm) under tsImport...
• See full diff in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore <dependency name> major version will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself)
• @dependabot ignore <dependency name> minor version will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself)
• @dependabot ignore <dependency name> will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself)
• @dependabot unignore <dependency name> will remove all of the ignore conditions of the specified dependency
• @dependabot unignore <dependency name> <ignore condition> will remove the ignore condition of the specified dependency and ignore conditions