chore(deps-dev): bump the dev-dependencies group with 7 updates

[dependabot]

Bumps the dev-dependencies group with 7 updates:

Package	From	To
@earendil-works/pi-agent-core	0.83.0	0.84.1
@earendil-works/pi-ai	0.83.0	0.84.1
@earendil-works/pi-coding-agent	0.83.0	0.84.1
@earendil-works/pi-tui	0.83.0	0.84.1
@types/node	26.1.1	26.2.0
typebox	1.3.10	1.3.11
@biomejs/biome	2.5.6	2.5.7

Updates @earendil-works/pi-agent-core from 0.83.0 to 0.84.1

Release notes

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

v0.84.1

New Features

• Qwen Token Plan Individual — Use the built-in provider for models documented for Individual subscriptions. See API Keys.
• Authentication readiness checks — Use pi auth check to verify provider or model credentials, optionally emitting the resolved credential.
• Improved fullscreen interaction — Select words and paragraphs with multiple clicks and configure half-page transcript scrolling. See TUI Fullscreen Viewport.
• Terminating blocked tool calls — Extension tool_call handlers can stop all-terminating batches without another model call. See Tool Events.

Added

• Added Qwen Token Plan Individual as a built-in provider with its documented subscription model catalog and the shared international QWEN_TOKEN_PLAN_API_KEY. See API Keys (#7659 by @​arasovic).
• Added pi auth check provider/model auth preflight with optional credential output (#7152).
• Added terminate support to blocked extension tool_call events so all-terminating batches can skip the automatic follow-up model call. See Tool Events (#7715 by @​muyiyr).
• Added inherited double-click word and whitespace selection, granularity-aware drag selection, and triple-click paragraph selection in fullscreen mode (#7725, #7733 by @​volsa).
• Added inherited unbound half-page transcript scrolling actions for fullscreen mode. See TUI Fullscreen Viewport (#7735).

Changed

• Softened the bash tool's PI_* environment guideline in an attempt to reduce unnecessary inspection commands (#7128).
• Reduced worst-case automatic terminal theme detection delay from 200 ms to 100 ms by probing color-scheme and background support concurrently.

Fixed

• Fixed Bun standalone binaries crashing on startup when the cwd contains a bunfig.toml with preload by compiling with --no-compile-autoload-bunfig (#7685 by @​geril07).
• Fixed extension TUI method wrappers recursing indefinitely when delegating to the original method (#7731).
• Fixed right-click not pasting clipboard text in fullscreen mode on Windows.
• Fixed inherited Agent.reset() clearing transcript and runtime state during active runs; it now rejects until the agent is idle (#7717 by @​wesleyzhangwq).
• Fixed inherited LaTeX relation, multiplication, and named-operator spacing, and matrix composition with stacked fractions, operator limits, and adjacent matrices.
• Reduced inherited fullscreen mouse event volume under tmux, Zellij, and GNU Screen by using button-motion tracking instead of all-motion tracking.

v0.84.0

New Features

• Fullscreen TUI mode — Switch between regular and fullscreen modes at runtime, with a sticky editor and footer, independently scrollable transcript, and draggable scrollbars. See UI & Display.
• Mermaid and LaTeX rendering — Render Mermaid diagrams and terminal-friendly Unicode math in interactive transcripts. See Markdown settings and TUI Markdown.
• Per-directory context overrides — Use AGENTS.override.md to replace context files for a specific directory. See Context Files.
• Advanced custom model sampling — Configure arbitrary OpenAI-compatible samplingParams and opt-in vLLM thinking_token_budget values. See Sampling Parameters.
• Baseten provider — Use built-in Baseten authentication and model support. See API Keys.

Breaking Changes

• Renamed the inherited pi-ai ModelsStreamTransforms interface to ModelsRequestTransforms because its header transformation now applies to all authenticated provider requests.

• Changed JSON and RPC message_update events to emit only assistantMessageEvent deltas, removing the cumulative message and assistantMessageEvent.partial fields that caused quadratic output growth. Clients that need partial messages must assemble deltas between message_start and message_end; the latter remains authoritative (#7290).

• ModelRegistry.getApiKeyAndHeaders() now returns ProviderHeaders with string | null values and preserves null header-deletion markers. Extensions that inspect returned headers must handle null; extensions forwarding them to pi-ai streams should pass them through unchanged. This prevents placeholder OpenAI credentials from being sent through Cloudflare AI Gateway (#7030).

• Changed ModelRegistry.refresh() to accept ModelsRefreshOptions and return ModelsRefreshResult instead of discarding cancellation and provider errors.

• Changed ModelRuntime.setRuntimeApiKey() to accept auth cancellation options rather than catalog refresh options. Call refresh({ providers: [providerId], signal }) separately when remote freshness is required.

• Required config-form extension OAuth refreshToken(credentials, signal) callbacks to accept and honor a concrete abort signal.

• Replaced dynamic provider refresh context store access with the read-only context.stored snapshot and generation-checked context.publish() transaction.

  Providers built with createProvider({ fetchModels }): no catalog-publication migration is required. Before and after, return the fetched models and register the resulting provider; createProvider() owns restoration, persistence, and in-memory publication.

... (truncated)

Changelog

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

[0.84.1] - 2026-08-07

Added

• Added BeforeToolCallResult.terminate so blocked tool calls can participate in the existing batch early-termination rule (#7715 by @​muyiyr).

Fixed

• Fixed Agent.reset() clearing transcript and runtime state during active runs; it now rejects until the agent is idle (#7717 by @​wesleyzhangwq).

[0.84.0] - 2026-08-06

Breaking Changes

• Replaced the legacy harness session model with the v4 lane-based Session, SessionStorage, and SessionRepo APIs, including durable operation records, global facts, shared sequence numbers, and tree-scoped lane views.
• Promoted the v2 session and AgentHarness API from the experimental entrypoint to the default package export and removed the experimental subpaths.
• Removed the legacy JSONL and in-memory repository APIs. Use the v4 JsonlSessionRepo or InMemorySessionRepo, both implementing the new SessionRepo contract.
• Added the required FileSystem.renameFile() operation to harness execution environments for atomic JSONL publication; custom file-system implementations must provide same-filesystem replacement semantics (#7707 by @​davidbrai).

Added

• Added typed AI-request and harness telemetry schemas, their combined schema tuple, callback helpers, and a generated schema reference.
• Added bounded Session.findEntriesOnBranch() and findEntryOnBranch() queries with explicit traversal, filtering, ordering, and limit options.
• Added a compile-complete AgentHarness v2 scaffold; unfinished operation paths reject with HarnessNotImplemented while durable execution is implemented.
• Added JsonlSessionRepo, a v4 append-only JSONL session repository with metadata validation and shared storage semantics (#7611 by @​davidbrai).
• Added indexed Session.findOpenOperations() recovery queries and RecordQuery.operationKind filtering (#7646).
• Added AgentOptions.shouldStopAfterTurn for gracefully stopping after a completed turn before queued messages or another model call are processed. See Agent Options (#7367 by @​acmerfight).
• Added proxy forwarding for arbitrary OpenAI-compatible samplingParams (#7568 by @​mrexodia).

Fixed

• Fixed Windows path handling for NodeExecutionEnv file basenames, recursive skill loading, and prompt template names.
• Fixed JsonlSessionRepo enforcing session IDs globally across working directories; IDs are now unique within each working directory.
• Fixed JSONL session forks and torn-tail repairs to publish atomically, avoiding partially written or corrupted sessions after interrupted writes (#7707 by @​davidbrai).

Commits

• 53fa77c Release v0.84.1
• 6ba4d23 docs: audit changelogs since v0.84.0
• 6fb2d76 feat(coding-agent): add configurable Harness factory (#7686)
• 1eb988c feat(agent): allow blocked tool calls to terminate (#7715)
• 1532c99 fix(agent): reject reset during active runs (#7717)
• d406aa3 docs: reserve L1
• 38e8f28 Add [Unreleased] section for next cycle
• a5f43bf Release v0.84.0
• 6d0455f docs: audit unreleased changelogs
• 5cd46ee docs(agent): simplify harness work package workflow
• Additional commits viewable in compare view

Updates @earendil-works/pi-ai from 0.83.0 to 0.84.1

Release notes

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

v0.84.1

New Features

• Qwen Token Plan Individual — Use the built-in provider for models documented for Individual subscriptions. See API Keys.
• Authentication readiness checks — Use pi auth check to verify provider or model credentials, optionally emitting the resolved credential.
• Improved fullscreen interaction — Select words and paragraphs with multiple clicks and configure half-page transcript scrolling. See TUI Fullscreen Viewport.
• Terminating blocked tool calls — Extension tool_call handlers can stop all-terminating batches without another model call. See Tool Events.

Added

• Added Qwen Token Plan Individual as a built-in provider with its documented subscription model catalog and the shared international QWEN_TOKEN_PLAN_API_KEY. See API Keys (#7659 by @​arasovic).
• Added pi auth check provider/model auth preflight with optional credential output (#7152).
• Added terminate support to blocked extension tool_call events so all-terminating batches can skip the automatic follow-up model call. See Tool Events (#7715 by @​muyiyr).
• Added inherited double-click word and whitespace selection, granularity-aware drag selection, and triple-click paragraph selection in fullscreen mode (#7725, #7733 by @​volsa).
• Added inherited unbound half-page transcript scrolling actions for fullscreen mode. See TUI Fullscreen Viewport (#7735).

Changed

• Softened the bash tool's PI_* environment guideline in an attempt to reduce unnecessary inspection commands (#7128).
• Reduced worst-case automatic terminal theme detection delay from 200 ms to 100 ms by probing color-scheme and background support concurrently.

Fixed

• Fixed Bun standalone binaries crashing on startup when the cwd contains a bunfig.toml with preload by compiling with --no-compile-autoload-bunfig (#7685 by @​geril07).
• Fixed extension TUI method wrappers recursing indefinitely when delegating to the original method (#7731).
• Fixed right-click not pasting clipboard text in fullscreen mode on Windows.
• Fixed inherited Agent.reset() clearing transcript and runtime state during active runs; it now rejects until the agent is idle (#7717 by @​wesleyzhangwq).
• Fixed inherited LaTeX relation, multiplication, and named-operator spacing, and matrix composition with stacked fractions, operator limits, and adjacent matrices.
• Reduced inherited fullscreen mouse event volume under tmux, Zellij, and GNU Screen by using button-motion tracking instead of all-motion tracking.

v0.84.0

New Features

• Fullscreen TUI mode — Switch between regular and fullscreen modes at runtime, with a sticky editor and footer, independently scrollable transcript, and draggable scrollbars. See UI & Display.
• Mermaid and LaTeX rendering — Render Mermaid diagrams and terminal-friendly Unicode math in interactive transcripts. See Markdown settings and TUI Markdown.
• Per-directory context overrides — Use AGENTS.override.md to replace context files for a specific directory. See Context Files.
• Advanced custom model sampling — Configure arbitrary OpenAI-compatible samplingParams and opt-in vLLM thinking_token_budget values. See Sampling Parameters.
• Baseten provider — Use built-in Baseten authentication and model support. See API Keys.

Breaking Changes

• Renamed the inherited pi-ai ModelsStreamTransforms interface to ModelsRequestTransforms because its header transformation now applies to all authenticated provider requests.

• Changed JSON and RPC message_update events to emit only assistantMessageEvent deltas, removing the cumulative message and assistantMessageEvent.partial fields that caused quadratic output growth. Clients that need partial messages must assemble deltas between message_start and message_end; the latter remains authoritative (#7290).

• ModelRegistry.getApiKeyAndHeaders() now returns ProviderHeaders with string | null values and preserves null header-deletion markers. Extensions that inspect returned headers must handle null; extensions forwarding them to pi-ai streams should pass them through unchanged. This prevents placeholder OpenAI credentials from being sent through Cloudflare AI Gateway (#7030).

• Changed ModelRegistry.refresh() to accept ModelsRefreshOptions and return ModelsRefreshResult instead of discarding cancellation and provider errors.

• Changed ModelRuntime.setRuntimeApiKey() to accept auth cancellation options rather than catalog refresh options. Call refresh({ providers: [providerId], signal }) separately when remote freshness is required.

• Required config-form extension OAuth refreshToken(credentials, signal) callbacks to accept and honor a concrete abort signal.

• Replaced dynamic provider refresh context store access with the read-only context.stored snapshot and generation-checked context.publish() transaction.

  Providers built with createProvider({ fetchModels }): no catalog-publication migration is required. Before and after, return the fetched models and register the resulting provider; createProvider() owns restoration, persistence, and in-memory publication.

... (truncated)

Changelog

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

[0.84.1] - 2026-08-07

Added

• Added Qwen Token Plan Individual as a built-in provider with its documented subscription model catalog and the shared international QWEN_TOKEN_PLAN_API_KEY (#7659 by @​arasovic).

[0.84.0] - 2026-08-06

Breaking Changes

• Renamed the exported ModelsStreamTransforms interface to ModelsRequestTransforms because its header transformation now applies to all authenticated provider requests.

• Required dynamic model providers to accept a concrete RefreshModelsContext.signal; Models.refresh() remains unbounded when callers omit its optional signal.

• Required provider login, API-key check/resolution, and OAuth refresh implementations to accept a concrete abort signal; public auth and credential operations remain unbounded when callers omit their optional signal.

• Replaced raw RefreshModelsContext.store access with the read-only context.stored snapshot and generation-checked context.publish() transaction.

  createProvider({ fetchModels }): no catalog-publication migration is required. Before and after, return the fetched list; createProvider() restores stored models and publishes and persists refreshed models itself. signal is now guaranteed to be present.

  // Before
  const beforeProvider = createProvider({
    // ...
    fetchModels: async ({ signal }) => {
      const response = await fetch(catalogUrl, { signal });
      return parseModels(await response.json());
    },
  });
  // After: unchanged
  const afterProvider = createProvider({
  // ...
  fetchModels: async ({ signal }) => {
  const response = await fetch(catalogUrl, { signal });
  return parseModels(await response.json());
  },
  });

  Handwritten Provider.refreshModels(): replace direct store access and pre-publication mutation with generation-guarded publications.

  // Before
  refreshModels: async (context) => {
    const stored = await context.store.read();
    if (stored) currentModels = stored.models;
    if (!context.allowNetwork) return;
  const refreshed = await fetchModels(context.signal);
  currentModels = refreshed;
  await context.store.write({ models: refreshed, checkedAt: Date.now() });
  },

... (truncated)

Commits

• 53fa77c Release v0.84.1
• 6ba4d23 docs: audit changelogs since v0.84.0
• c03d78b feat(ai): add Qwen Token Plan Individual provider (#7659)
• 38e8f28 Add [Unreleased] section for next cycle
• a5f43bf Release v0.84.0
• b9497c8 fix(ai): correct Fireworks GLM prompt caching, closes #7676
• c0947e6 fix(ai): remove stale adaptive thinking model expectation
• b0bd0ff fix(coding-agent): only label known subscriptions in footer
• 6b461b7 feat: extract telemetry package
• db48124 docs: audit unreleased changelogs
• Additional commits viewable in compare view

Updates @earendil-works/pi-coding-agent from 0.83.0 to 0.84.1

Release notes

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

v0.84.1

New Features

• Qwen Token Plan Individual — Use the built-in provider for models documented for Individual subscriptions. See API Keys.
• Authentication readiness checks — Use pi auth check to verify provider or model credentials, optionally emitting the resolved credential.
• Improved fullscreen interaction — Select words and paragraphs with multiple clicks and configure half-page transcript scrolling. See TUI Fullscreen Viewport.
• Terminating blocked tool calls — Extension tool_call handlers can stop all-terminating batches without another model call. See Tool Events.

Added

• Added Qwen Token Plan Individual as a built-in provider with its documented subscription model catalog and the shared international QWEN_TOKEN_PLAN_API_KEY. See API Keys (#7659 by @​arasovic).
• Added pi auth check provider/model auth preflight with optional credential output (#7152).
• Added terminate support to blocked extension tool_call events so all-terminating batches can skip the automatic follow-up model call. See Tool Events (#7715 by @​muyiyr).
• Added inherited double-click word and whitespace selection, granularity-aware drag selection, and triple-click paragraph selection in fullscreen mode (#7725, #7733 by @​volsa).
• Added inherited unbound half-page transcript scrolling actions for fullscreen mode. See TUI Fullscreen Viewport (#7735).

Changed

• Softened the bash tool's PI_* environment guideline in an attempt to reduce unnecessary inspection commands (#7128).
• Reduced worst-case automatic terminal theme detection delay from 200 ms to 100 ms by probing color-scheme and background support concurrently.

Fixed

• Fixed Bun standalone binaries crashing on startup when the cwd contains a bunfig.toml with preload by compiling with --no-compile-autoload-bunfig (#7685 by @​geril07).
• Fixed extension TUI method wrappers recursing indefinitely when delegating to the original method (#7731).
• Fixed right-click not pasting clipboard text in fullscreen mode on Windows.
• Fixed inherited Agent.reset() clearing transcript and runtime state during active runs; it now rejects until the agent is idle (#7717 by @​wesleyzhangwq).
• Fixed inherited LaTeX relation, multiplication, and named-operator spacing, and matrix composition with stacked fractions, operator limits, and adjacent matrices.
• Reduced inherited fullscreen mouse event volume under tmux, Zellij, and GNU Screen by using button-motion tracking instead of all-motion tracking.

v0.84.0

New Features

• Fullscreen TUI mode — Switch between regular and fullscreen modes at runtime, with a sticky editor and footer, independently scrollable transcript, and draggable scrollbars. See UI & Display.
• Mermaid and LaTeX rendering — Render Mermaid diagrams and terminal-friendly Unicode math in interactive transcripts. See Markdown settings and TUI Markdown.
• Per-directory context overrides — Use AGENTS.override.md to replace context files for a specific directory. See Context Files.
• Advanced custom model sampling — Configure arbitrary OpenAI-compatible samplingParams and opt-in vLLM thinking_token_budget values. See Sampling Parameters.
• Baseten provider — Use built-in Baseten authentication and model support. See API Keys.

Breaking Changes

• Renamed the inherited pi-ai ModelsStreamTransforms interface to ModelsRequestTransforms because its header transformation now applies to all authenticated provider requests.

• Changed JSON and RPC message_update events to emit only assistantMessageEvent deltas, removing the cumulative message and assistantMessageEvent.partial fields that caused quadratic output growth. Clients that need partial messages must assemble deltas between message_start and message_end; the latter remains authoritative (#7290).

• ModelRegistry.getApiKeyAndHeaders() now returns ProviderHeaders with string | null values and preserves null header-deletion markers. Extensions that inspect returned headers must handle null; extensions forwarding them to pi-ai streams should pass them through unchanged. This prevents placeholder OpenAI credentials from being sent through Cloudflare AI Gateway (#7030).

• Changed ModelRegistry.refresh() to accept ModelsRefreshOptions and return ModelsRefreshResult instead of discarding cancellation and provider errors.

• Changed ModelRuntime.setRuntimeApiKey() to accept auth cancellation options rather than catalog refresh options. Call refresh({ providers: [providerId], signal }) separately when remote freshness is required.

• Required config-form extension OAuth refreshToken(credentials, signal) callbacks to accept and honor a concrete abort signal.

• Replaced dynamic provider refresh context store access with the read-only context.stored snapshot and generation-checked context.publish() transaction.

  Providers built with createProvider({ fetchModels }): no catalog-publication migration is required. Before and after, return the fetched models and register the resulting provider; createProvider() owns restoration, persistence, and in-memory publication.

... (truncated)

Changelog

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

[0.84.1] - 2026-08-07

New Features

• Qwen Token Plan Individual — Use the built-in provider for models documented for Individual subscriptions. See API Keys.
• Authentication readiness checks — Use pi auth check to verify provider or model credentials, optionally emitting the resolved credential.
• Improved fullscreen interaction — Select words and paragraphs with multiple clicks and configure half-page transcript scrolling. See TUI Fullscreen Viewport.
• Terminating blocked tool calls — Extension tool_call handlers can stop all-terminating batches without another model call. See Tool Events.

Added

• Added Qwen Token Plan Individual as a built-in provider with its documented subscription model catalog and the shared international QWEN_TOKEN_PLAN_API_KEY. See API Keys (#7659 by @​arasovic).
• Added pi auth check provider/model auth preflight with optional credential output (#7152).
• Added terminate support to blocked extension tool_call events so all-terminating batches can skip the automatic follow-up model call. See Tool Events (#7715 by @​muyiyr).
• Added inherited double-click word and whitespace selection, granularity-aware drag selection, and triple-click paragraph selection in fullscreen mode (#7725, #7733 by @​volsa).
• Added inherited unbound half-page transcript scrolling actions for fullscreen mode. See TUI Fullscreen Viewport (#7735).

Changed

• Softened the bash tool's PI_* environment guideline in an attempt to reduce unnecessary inspection commands (#7128).
• Reduced worst-case automatic terminal theme detection delay from 200 ms to 100 ms by probing color-scheme and background support concurrently.

Fixed

• Fixed Bun standalone binaries crashing on startup when the cwd contains a bunfig.toml with preload by compiling with --no-compile-autoload-bunfig (#7685 by @​geril07).
• Fixed extension TUI method wrappers recursing indefinitely when delegating to the original method (#7731).
• Fixed right-click not pasting clipboard text in fullscreen mode on Windows.
• Fixed inherited Agent.reset() clearing transcript and runtime state during active runs; it now rejects until the agent is idle (#7717 by @​wesleyzhangwq).
• Fixed inherited LaTeX relation, multiplication, and named-operator spacing, and matrix composition with stacked fractions, operator limits, and adjacent matrices.
• Reduced inherited fullscreen mouse event volume under tmux, Zellij, and GNU Screen by using button-motion tracking instead of all-motion tracking.

[0.84.0] - 2026-08-06

New Features

• Fullscreen TUI mode — Switch between regular and fullscreen modes at runtime, with a sticky editor and footer, independently scrollable transcript, and draggable scrollbars. See UI & Display.
• Mermaid and LaTeX rendering — Render Mermaid diagrams and terminal-friendly Unicode math in interactive transcripts. See Markdown settings and TUI Markdown.
• Per-directory context overrides — Use AGENTS.override.md to replace context files for a specific directory. See Context Files.
• Advanced custom model sampling — Configure arbitrary OpenAI-compatible samplingParams and opt-in vLLM thinking_token_budget values. See Sampling Parameters.
• Baseten provider — Use built-in Baseten authentication and model support. See API Keys.

Breaking Changes

• Renamed the inherited pi-ai ModelsStreamTransforms interface to ModelsRequestTransforms because its header transformation now applies to all authenticated provider requests.
• Changed JSON and RPC message_update events to emit only assistantMessageEvent deltas, removing the cumulative message and assistantMessageEvent.partial fields that caused quadratic output growth. Clients that need partial messages must assemble deltas between message_start and message_end; the latter remains authoritative (#7290).
• ModelRegistry.getApiKeyAndHeaders() now returns ProviderHeaders with string | null values and preserves null header-deletion markers. Extensions that inspect returned headers must handle null; extensions forwarding them to pi-ai streams should pass them through unchanged. This prevents placeholder OpenAI credentials from being sent through Cloudflare AI Gateway (#7030).
• Changed ModelRegistry.refresh() to accept ModelsRefreshOptions and return ModelsRefreshResult instead of discarding cancellation and provider errors.
• Changed ModelRuntime.setRuntimeApiKey() to accept auth cancellation options rather than catalog refresh options. Call refresh({ providers: [providerId], signal }) separately when remote freshness is required.
• Required config-form extension OAuth refreshToken(credentials, signal) callbacks to accept and honor a concrete abort signal.
• Replaced dynamic provider refresh context store access with the read-only context.stored snapshot and generation-checked context.publish() transaction.

... (truncated)

Commits

• 53fa77c Release v0.84.1
• 6ba4d23 docs: audit changelogs since v0.84.0
• 666d897 fix(coding-agent): preserve TUI wrapper routing (closes #7731)
• 7cb2a51 fix(coding-agent): reduce automatic theme detection delay
• 4688e4f docs(coding-agent): reconcile keybinding behavior (#7729)
• 4e64de6 fix(coding-agent): soften PI environment guideline
• c96bfac fix(coding-agent): support Windows fullscreen right-click paste
• a3e93ec feat(tui): add half-page transcript scrolling
• 6fb2d76 feat(coding-agent): add configurable Harness factory (#7686)
• a261366 feat(coding-agent): add auth preflight
• Additional commits viewable in compare view

Updates @earendil-works/pi-tui from 0.83.0 to 0.84.1

Release notes

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

v0.84.1

New Features

• Qwen Token Plan Individual — Use the built-in provider for models documented for Individual subscriptions. See API Keys.
• Authentication readiness checks — Use pi auth check to verify provider or model credentials, optionally emitting the resolved credential.
• Improved fullscreen interaction — Select words and paragraphs with multiple clicks and configure half-page transcript scrolling. See TUI Fullscreen Viewport.
• Terminating blocked tool calls — Extension tool_call handlers can stop all-terminating batches without another model call. See Tool Events.

Added

• Added Qwen Token Plan Individual as a built-in provider with its documented subscription model catalog and the shared international QWEN_TOKEN_PLAN_API_KEY. See API Keys (#7659 by @​arasovic).
• Added pi auth check provider/model auth preflight with optional credential output (#7152).
• Added terminate support to blocked extension tool_call events so all-terminating batches can skip the automatic follow-up model call. See Tool Events (#7715 by @​muyiyr).
• Added inherited double-click word and whitespace selection, granularity-aware drag selection, and triple-click paragraph selection in fullscreen mode (#7725, #7733 by @​volsa).
• Added inherited unbound half-page transcript scrolling actions for fullscreen mode. See TUI Fullscreen Viewport (#7735).

Changed

• Softened the bash tool's PI_* environment guideline in an attempt to reduce unnecessary inspection commands (#7128).
• Reduced worst-case automatic terminal theme detection delay from 200 ms to 100 ms by probing color-scheme and background support concurrently.

Fixed

• Fixed Bun standalone binaries crashing on startup when the cwd contains a bunfig.toml with preload by compiling with --no-compile-autoload-bunfig (#7685 by @​geril07).
• Fixed extension TUI method wrappers recursing indefinitely when delegating to the original method (#7731).
• Fixed right-click not pasting clipboard text in fullscreen mode on Windows.
• Fixed inherited Agent.reset() clearing transcript and runtime state during active runs; it now rejects until the agent is idle (#7717 by @​wesleyzhangwq).
• Fixed inherited LaTeX relation, multiplication, and named-operator spacing, and matrix composition with stacked fractions, operator limits, and adjacent matrices.
• Reduced inherited fullscreen mouse event volume under tmux, Zellij, and GNU Screen by using button-motion tracking instead of all-motion tracking.

v0.84.0

New Features

• Fullscreen TUI mode — Switch between regular and fullscreen modes at runtime, with a sticky editor and footer, independently scrollable transcript, and draggable scrollbars. See UI & Display.
• Mermaid and LaTeX rendering — Render Mermaid diagrams and terminal-friendly Unicode math in interactive transcripts. See Markdown settings and TUI Markdown.
• Per-directory context overrides — Use AGENTS.override.md to replace context files for a specific directory. See Context Files.
• Advanced custom model sampling — Configure arbitrary OpenAI-compatible samplingParams and opt-in vLLM thinking_token_budget values. See Sampling Parameters.
• Baseten provider — Use built-in Baseten authentication and model support. See API Keys.

Breaking Changes

• Renamed the inherited pi-ai ModelsStreamTransforms interface to ModelsRequestTransforms because its header transformation now applies to all authenticated provider requests.

• Changed JSON and RPC message_update events to emit only assistantMessageEvent deltas, removing the cumulative message and assistantMessageEvent.partial fields that caused quadratic output growth. Clients that need partial messages must assemble deltas between message_start and message_end; the latter remains authoritative (#7290).

• ModelRegistry.getApiKeyAndHeaders() now returns ProviderHeaders with string | null values and preserves null header-deletion markers. Extensions that inspect returned headers must handle null; extensions forwarding them to pi-ai streams should pass them through unchanged. This prevents placeholder OpenAI credentials from being sent through Cloudflare AI Gateway (#7030).

• Changed ModelRegistry.refresh() to accept ModelsRefreshOptions and return ModelsRefreshResult instead of discarding cancellation and provider errors.

• Changed ModelRuntime.setRuntimeApiKey() to accept auth cancellation options rather than catalog refresh options. Call refresh({ providers: [providerId], signal }) separately when remote freshness is required.

• Required config-form extension OAuth refreshToken(credentials, signal) callbacks to accept and honor a concrete abort signal.

• Replaced dynamic provider refresh context store access with the read-only context.stored snapshot and generation-checked context.publish() transaction.

  Providers built with createProvider({ fetchModels }): no catalog-publication migration is required. Before and after, return the fetched models and register the resulting provider; createProvider() owns restoration, persistence, and in-memory publication.

... (truncated)

Changelog

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

[0.84.1] - 2026-08-07

Added

• Added unbound half-page transcript scrolling actions, tui.altScreen.halfPageUp and tui.altScreen.halfPageDown, for fullscreen TUI keybindings (#7735).
• Added double-click word and whitespace selection, granularity-aware drag selection, and triple-click paragraph selection in the fullscreen TUI (#7725, #7733 by @​volsa).
• Added an optional right-click paste handler to the alternate-screen TUI, currently enabled on Windows.

Fixed

• Fixed LaTeX relation, multiplication, and named-operator spacing, and correctly composed matrices with stacked fractions, operator limits, and adjacent matrices.
• Reduced fullscreen mouse event volume under tmux, Zellij, and GNU Screen by using button-motion tracking instead of all-motion tracking.

[0.84.0] - 2026-08-06

Added

• Added terminal-friendly Unicode rendering for LaTeX expressions in Markdown, including inline and display math, fractions, scripts, common symbols, aligned equations, cases, and matrices.
• Added the shared TuiMode type and mode discriminants to the main-screen and alternate-screen TUI renderers.
• Added TUI lifecycle and render-state handoff APIs for replacing renderers without replaying main-screen content.
• Exported the bundled Marked parser and token types.
• Added width-aware source transforms to the Markdown component.
• Added interface-compatible main-screen and alternate-screen TUI renderers with application-owned scrolling (#7304).
• Added alternate-screen VStack, HStack, and nested ScrollView layouts with constrained sizing, sticky regions, and pointer-targeted scrolling.
• Added edge auto-scrolling for alternate-screen drag selection across off-screen scroll-view content.
• Added proportional scrollbars with mouse dragging, Home/End document navigation, transient auto mode, and an always mode that reserves the rightmost column; scrollbar modes can be changed at runtime.
• Added page scrolling and OSC 133 semantic prompt navigation to the alternate-screen viewport.
• Added configurable previous/next prompt history actions for navigation independent of vertical cursor movement.
• Added stacked transient notifications to the alternate-screen renderer (#7361).

Changed

• Reduced the default alternate-screen mouse wheel step from three lines to one for finer scrolling.

Fixed

• Fixed Windows Shift+Enter detection by extending the native Win32 helper to report modifier key state.
• Fixed the npm package omitting the source and build script needed to rebuild the Windows native addon.
• Fixed the npm package omitting the source and build script needed to rebuild the Darwin native addon.
• Fixed Windows console truecolor detection when Windows Terminal does not provide WT_SESSION to child shells.
• Fixed terminal width accounting for Indic conjunct grapheme clusters (#6987 by @​petrroll).
• Fixed phantom alternate-screen text selection from unmatched mouse events when changing terminal pane focus.
• Fixed spaces in searchable settings queries changing the selected value instead of filtering multi-word labels.
• Fixed alternate-screen Kitty images crossing vertical layout clip boundaries and overlapping sticky regions while scrolling.
• Fixed alternate-screen redraws retransmitting Kitty image data when placements move or recently offscreen images return, dropping adjacent row content when reusing placements, rendering fixed-basis scroll content twice per frame, and scanning clipped transcript rows while painting.
• Fixed fullscreen transcript navigation leaving no editor-accessible Home, End, PageUp, or PageDown variants by adding Ctrl-modified editor bindings (#7574).
• Fixed keyboard input rendering latency on Windows by letting input preempt the throttled render timer.
• Fixed nested stack layouts ignoring child minimum sizes.
• Fixed batched terminal color-scheme reports being parsed as one malformed response (#7550).
• Fixed terminal progress clearing to emit the complete OSC 9;4 sequence (#7581).

... (truncated)

Commits

• 53fa77c Release v0.84.1
• 6ba4d23 docs: audit changelogs since v0.84.0
• 79f72fc docs(tui): Clarify TUI test runner and remove stale Vitest config (#7732)
• c96bfac fix(coding-agent): support Windows fullscreen right-click paste
• a3e93ec feat(tui): add half-page transcript scrolling
• 171c6b5 fix(tui): correct multi-click text selection (Description has been truncated