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	0.80.10	0.81.1
@earendil-works/pi-ai	0.80.10	0.81.1
@earendil-works/pi-coding-agent	0.80.10	0.81.1
@earendil-works/pi-tui	0.80.10	0.81.1
@biomejs/biome	2.5.4	2.5.5
@tailwindcss/postcss	4.3.2	4.3.3
tailwindcss	4.3.2	4.3.3

Updates @earendil-works/pi-agent-core from 0.80.10 to 0.81.1

Release notes

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

v0.81.1

New Features

• Verifiable release source archives — GitHub releases now include deterministic, checksummed source archives with instructions for rebuilding standalone binaries. See Building standalone binaries from release source.
• Resilient compaction and branch summaries — Transient provider failures now follow the configured retry policy, with retry lifecycle events available to interactive, JSON, RPC, and SDK consumers. See Compaction & Branch Summarization and RPC retry events.

Added

• Added deterministic, checksummed source archives to GitHub releases with documented standalone binary rebuild instructions (#6913 by @​christianklotz).

Fixed

• Fixed compaction and branch summarization to retry transient provider failures using the configured retry policy, with retry lifecycle events exposed to interactive, JSON, RPC, and SDK consumers (#6901 by @​davidbrai).
• Fixed interactive startup waiting for background model catalog refresh while computing the footer provider count.
• Restored the default stream fallback for extensions using the pre-0.81 agent-core API (#6915).
• Fixed inherited Kimi K3 models from Moonshot AI and Moonshot AI China to use the OpenAI thinking format and expose reasoning effort support.

v0.81.0

New Features

• Local llama.cpp model management — Connect to a llama.cpp router, search and download Hugging Face models, and explicitly load or unload models with live progress. See llama.cpp.
• Full provider extensions — Extensions can register complete pi-ai providers with authentication, model refresh, filtering, and custom streaming. See Register New Provider.
• Qwen Token Plan providers — Use the built-in international and China subscription providers with regional endpoints and API-key authentication. See API Keys.
• Expanded usage accounting — Tool, compaction, and branch-summary usage is persisted and included in session totals. See Compaction & Branch Summarization.

Added

• Added Qwen Token Plan and Qwen Token Plan China to built-in provider setup, default model resolution, and provider documentation (#6858 by @​QuintinShaw).
• Added the get_available_thinking_levels RPC command and RpcClient.getAvailableThinkingLevels() method (#6865 by @​cristinaponcela).
• Exported message and tool execution lifecycle event types from the package root (#6772 by @​davidbrai).
• Added built-in llama.cpp router support with /login connection setup and /llama Hugging Face model search and downloads, explicit loading, unloading, and live progress. See llama.cpp.
• Added extension registration for complete pi-ai providers, including native authentication, model refresh, filtering, and streaming behavior.
• Added usage accounting for tools, compaction, and branch summaries in persisted sessions, footer totals, and session statistics (#6671 by @​davidbrai).

Fixed

• Updated the packaged brace-expansion dependency to 5.0.7 (#6896 by @​davidbrai).
• Fixed persisted remote model catalogs from overriding newer bundled catalogs after an upgrade.
• Fixed inherited stored API-key credentials to apply their provider-scoped env values, including Amazon Bedrock profiles (#6864 by @​cristinaponcela).
• Fixed inherited OpenAI-compatible cross-provider replay to keep tool call IDs unique when multiple calls share a provider call ID (#6854 by @​cristinaponcela).
• Fixed inherited Kimi K3 thinking levels to expose low, high, and max, and normalized the k2p7 alias to kimi-for-coding.
• Fixed inherited OpenCode Go models routed through the OpenAI Responses API.
• Fixed inherited pi-ai package metadata to avoid repeated consumer lockfile changes (#6812 by @​jmfederico).
• Fixed inherited terminal shutdown to clear the editor's inverted software cursor before restoring the hardware cursor (#6790 by @​dam9000).
• Fixed inherited ANSI-aware text wrapping to recognize CRLF and CR line endings while preserving styles (#6764 by @​xz-dev).
• Fixed inherited editor paste registry corruption after deleting and undoing paste markers, preventing literal or mismatched paste markers in submitted prompts (#6844).
• Fixed sessionless OpenAI Codex WebSocket requests to use UUIDv7 request IDs (#6834 by @​xl0).
• Fixed inherited GPT-5.6 Codex models to default to the 272K context window, avoiding automatic long-context pricing (#6853 by @​aadishv).
• Fixed messages queued during compaction to preserve steering and follow-up delivery behavior (#6730 by @​dannote).
• Fixed read tool errors being syntax-highlighted as if they were file contents (#6731 by @​dannote).

... (truncated)

Changelog

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

[0.81.1] - 2026-07-21

Added

• Added retry policy support and lifecycle events for compaction and branch-summary operations in AgentHarness (#6901 by @​davidbrai).

Fixed

• Restored the Agent streamFn option and host-configurable fallback for omitted agent-loop stream functions without reintroducing a pi-ai/compat dependency (#6915).

[0.81.0] - 2026-07-21

Breaking Changes

• Changed SessionStorage to use getPathToRootOrCompaction(), require session name and statistics methods, support cursor-based entry reads, and store retained compaction tails as self-contained checkpoints (#6594 by @​cristinaponcela).
• Moved the uuidv7 export to @earendil-works/pi-ai (#6834 by @​xl0).
• Replaced the optional Agent streamFn fallback with a required streamFunction and made low-level loop stream functions required, preventing @earendil-works/pi-ai/compat and all built-in providers from entering selective-provider bundles (#6851).

Added

• Added usage metadata to tool results, compaction entries, and branch summaries in the agent harness (#6671 by @​davidbrai).

Commits

• 20be4b1 Release v0.81.1
• b9e5c5d fix(agent): restore streamFn extension compatibility
• 7540da4 add docs for new event types
• ceac988 Merge remote-tracking branch 'origin/main' into fix/issue-6647-retry-summary-...
• 3dcb411 Add [Unreleased] section for next cycle
• 9c480b6 Release v0.81.0
• d35237c fix: build packages before release tests
• c901d9a docs: audit unreleased changelogs
• 109c412 feat(agent): prepare SQLite storage package for publishing
• 162179a add branch/compact retries to agent-harness
• Additional commits viewable in compare view

Updates @earendil-works/pi-ai from 0.80.10 to 0.81.1

Release notes

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

v0.81.1

New Features

• Verifiable release source archives — GitHub releases now include deterministic, checksummed source archives with instructions for rebuilding standalone binaries. See Building standalone binaries from release source.
• Resilient compaction and branch summaries — Transient provider failures now follow the configured retry policy, with retry lifecycle events available to interactive, JSON, RPC, and SDK consumers. See Compaction & Branch Summarization and RPC retry events.

Added

• Added deterministic, checksummed source archives to GitHub releases with documented standalone binary rebuild instructions (#6913 by @​christianklotz).

Fixed

• Fixed compaction and branch summarization to retry transient provider failures using the configured retry policy, with retry lifecycle events exposed to interactive, JSON, RPC, and SDK consumers (#6901 by @​davidbrai).
• Fixed interactive startup waiting for background model catalog refresh while computing the footer provider count.
• Restored the default stream fallback for extensions using the pre-0.81 agent-core API (#6915).
• Fixed inherited Kimi K3 models from Moonshot AI and Moonshot AI China to use the OpenAI thinking format and expose reasoning effort support.

v0.81.0

New Features

• Local llama.cpp model management — Connect to a llama.cpp router, search and download Hugging Face models, and explicitly load or unload models with live progress. See llama.cpp.
• Full provider extensions — Extensions can register complete pi-ai providers with authentication, model refresh, filtering, and custom streaming. See Register New Provider.
• Qwen Token Plan providers — Use the built-in international and China subscription providers with regional endpoints and API-key authentication. See API Keys.
• Expanded usage accounting — Tool, compaction, and branch-summary usage is persisted and included in session totals. See Compaction & Branch Summarization.

Added

• Added Qwen Token Plan and Qwen Token Plan China to built-in provider setup, default model resolution, and provider documentation (#6858 by @​QuintinShaw).
• Added the get_available_thinking_levels RPC command and RpcClient.getAvailableThinkingLevels() method (#6865 by @​cristinaponcela).
• Exported message and tool execution lifecycle event types from the package root (#6772 by @​davidbrai).
• Added built-in llama.cpp router support with /login connection setup and /llama Hugging Face model search and downloads, explicit loading, unloading, and live progress. See llama.cpp.
• Added extension registration for complete pi-ai providers, including native authentication, model refresh, filtering, and streaming behavior.
• Added usage accounting for tools, compaction, and branch summaries in persisted sessions, footer totals, and session statistics (#6671 by @​davidbrai).

Fixed

• Updated the packaged brace-expansion dependency to 5.0.7 (#6896 by @​davidbrai).
• Fixed persisted remote model catalogs from overriding newer bundled catalogs after an upgrade.
• Fixed inherited stored API-key credentials to apply their provider-scoped env values, including Amazon Bedrock profiles (#6864 by @​cristinaponcela).
• Fixed inherited OpenAI-compatible cross-provider replay to keep tool call IDs unique when multiple calls share a provider call ID (#6854 by @​cristinaponcela).
• Fixed inherited Kimi K3 thinking levels to expose low, high, and max, and normalized the k2p7 alias to kimi-for-coding.
• Fixed inherited OpenCode Go models routed through the OpenAI Responses API.
• Fixed inherited pi-ai package metadata to avoid repeated consumer lockfile changes (#6812 by @​jmfederico).
• Fixed inherited terminal shutdown to clear the editor's inverted software cursor before restoring the hardware cursor (#6790 by @​dam9000).
• Fixed inherited ANSI-aware text wrapping to recognize CRLF and CR line endings while preserving styles (#6764 by @​xz-dev).
• Fixed inherited editor paste registry corruption after deleting and undoing paste markers, preventing literal or mismatched paste markers in submitted prompts (#6844).
• Fixed sessionless OpenAI Codex WebSocket requests to use UUIDv7 request IDs (#6834 by @​xl0).
• Fixed inherited GPT-5.6 Codex models to default to the 272K context window, avoiding automatic long-context pricing (#6853 by @​aadishv).
• Fixed messages queued during compaction to preserve steering and follow-up delivery behavior (#6730 by @​dannote).
• Fixed read tool errors being syntax-highlighted as if they were file contents (#6731 by @​dannote).

... (truncated)

Changelog

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

[0.81.1] - 2026-07-21

Added

• Added retryAssistantCall() for bounded retries of transient assistant failures with lifecycle callbacks and abort handling (#6901 by @​davidbrai).

Fixed

• Fixed Kimi K3 models from Moonshot AI and Moonshot AI China to use the OpenAI thinking format and expose reasoning effort support.

[0.81.0] - 2026-07-21

Added

• Added Qwen Token Plan and Qwen Token Plan China as built-in providers with regional endpoints, API-key authentication, and generated model catalogs (#6858 by @​QuintinShaw).
• Added contentText for extracting joined text from message content (#6840 by @​xl0).
• Added a shared uuidv7 utility for time-ordered identifiers (#6834 by @​xl0).
• Added optional usage metadata to tool result messages (#6671 by @​davidbrai).
• Added Kimi Code subscription OAuth login (device authorization grant) for the kimi-coding provider, with token refresh and KIMI_CODE_OAUTH_HOST/KIMI_OAUTH_HOST host overrides.

Changed

• Changed generated model catalogs to keep TypeScript model shapes separate from ignored JSON model values, reducing generated source churn (#6765 by @​mitsuhiko).
• Changed model generation to validate ignored provider data before compilation; npm run build refreshes model data as before, while npm run build:offline reuses existing data without network access.

Fixed

• Fixed stored API-key credentials to apply their provider-scoped env values during auth resolution, including Amazon Bedrock profiles (#6864 by @​cristinaponcela).
• Fixed OpenAI-compatible cross-provider replay to preserve unique tool call IDs when multiple calls share a provider call ID (#6854 by @​cristinaponcela).
• Fixed Kimi K3 to expose its supported low, high, and max thinking levels, and normalized the k2p7 alias to the canonical kimi-for-coding model.
• Fixed the OpenCode Go provider to support models routed through the OpenAI Responses API.
• Fixed the pi-ai executable path to match npm registry metadata, avoiding repeated consumer lockfile changes (#6812 by @​jmfederico).
• Fixed sessionless OpenAI Codex WebSocket requests to use UUIDv7 request IDs, enabling models that reject UUIDv4 IDs (#6834 by @​xl0).
• Fixed GitHub Copilot long-context pricing tiers in generated model metadata (#6668).
• Fixed Kimi Coding subscription models to report API-equivalent implied costs when models.dev reports zero pricing.
• Fixed OpenAI Responses early stream endings to be classified as retryable provider errors (#6727).
• Fixed GPT-5.6 Codex models to default to the 272K context window, avoiding automatic long-context pricing (#6853 by @​aadishv).

Commits

• 20be4b1 Release v0.81.1
• b9e5c5d fix(agent): restore streamFn extension compatibility
• a822896 feat(ai): add new Gemini generated models
• 243f64b report aborted retry attempts as unsuccessful
• ceac988 Merge remote-tracking branch 'origin/main' into fix/issue-6647-retry-summary-...
• 959cc18 fix moonshot/kimi3 compat properties
• 3dcb411 Add [Unreleased] section for next cycle
• 9c480b6 Release v0.81.0
• c23b58a feat(ai): update generated image models
• c901d9a docs: audit unreleased changelogs
• Additional commits viewable in compare view

Updates @earendil-works/pi-coding-agent from 0.80.10 to 0.81.1

Release notes

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

v0.81.1

New Features

• Verifiable release source archives — GitHub releases now include deterministic, checksummed source archives with instructions for rebuilding standalone binaries. See Building standalone binaries from release source.
• Resilient compaction and branch summaries — Transient provider failures now follow the configured retry policy, with retry lifecycle events available to interactive, JSON, RPC, and SDK consumers. See Compaction & Branch Summarization and RPC retry events.

Added

• Added deterministic, checksummed source archives to GitHub releases with documented standalone binary rebuild instructions (#6913 by @​christianklotz).

Fixed

• Fixed compaction and branch summarization to retry transient provider failures using the configured retry policy, with retry lifecycle events exposed to interactive, JSON, RPC, and SDK consumers (#6901 by @​davidbrai).
• Fixed interactive startup waiting for background model catalog refresh while computing the footer provider count.
• Restored the default stream fallback for extensions using the pre-0.81 agent-core API (#6915).
• Fixed inherited Kimi K3 models from Moonshot AI and Moonshot AI China to use the OpenAI thinking format and expose reasoning effort support.

v0.81.0

New Features

• Local llama.cpp model management — Connect to a llama.cpp router, search and download Hugging Face models, and explicitly load or unload models with live progress. See llama.cpp.
• Full provider extensions — Extensions can register complete pi-ai providers with authentication, model refresh, filtering, and custom streaming. See Register New Provider.
• Qwen Token Plan providers — Use the built-in international and China subscription providers with regional endpoints and API-key authentication. See API Keys.
• Expanded usage accounting — Tool, compaction, and branch-summary usage is persisted and included in session totals. See Compaction & Branch Summarization.

Added

• Added Qwen Token Plan and Qwen Token Plan China to built-in provider setup, default model resolution, and provider documentation (#6858 by @​QuintinShaw).
• Added the get_available_thinking_levels RPC command and RpcClient.getAvailableThinkingLevels() method (#6865 by @​cristinaponcela).
• Exported message and tool execution lifecycle event types from the package root (#6772 by @​davidbrai).
• Added built-in llama.cpp router support with /login connection setup and /llama Hugging Face model search and downloads, explicit loading, unloading, and live progress. See llama.cpp.
• Added extension registration for complete pi-ai providers, including native authentication, model refresh, filtering, and streaming behavior.
• Added usage accounting for tools, compaction, and branch summaries in persisted sessions, footer totals, and session statistics (#6671 by @​davidbrai).

Fixed

• Updated the packaged brace-expansion dependency to 5.0.7 (#6896 by @​davidbrai).
• Fixed persisted remote model catalogs from overriding newer bundled catalogs after an upgrade.
• Fixed inherited stored API-key credentials to apply their provider-scoped env values, including Amazon Bedrock profiles (#6864 by @​cristinaponcela).
• Fixed inherited OpenAI-compatible cross-provider replay to keep tool call IDs unique when multiple calls share a provider call ID (#6854 by @​cristinaponcela).
• Fixed inherited Kimi K3 thinking levels to expose low, high, and max, and normalized the k2p7 alias to kimi-for-coding.
• Fixed inherited OpenCode Go models routed through the OpenAI Responses API.
• Fixed inherited pi-ai package metadata to avoid repeated consumer lockfile changes (#6812 by @​jmfederico).
• Fixed inherited terminal shutdown to clear the editor's inverted software cursor before restoring the hardware cursor (#6790 by @​dam9000).
• Fixed inherited ANSI-aware text wrapping to recognize CRLF and CR line endings while preserving styles (#6764 by @​xz-dev).
• Fixed inherited editor paste registry corruption after deleting and undoing paste markers, preventing literal or mismatched paste markers in submitted prompts (#6844).
• Fixed sessionless OpenAI Codex WebSocket requests to use UUIDv7 request IDs (#6834 by @​xl0).
• Fixed inherited GPT-5.6 Codex models to default to the 272K context window, avoiding automatic long-context pricing (#6853 by @​aadishv).
• Fixed messages queued during compaction to preserve steering and follow-up delivery behavior (#6730 by @​dannote).
• Fixed read tool errors being syntax-highlighted as if they were file contents (#6731 by @​dannote).

... (truncated)

Changelog

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

[0.81.1] - 2026-07-21

New Features

• Verifiable release source archives — GitHub releases now include deterministic, checksummed source archives with instructions for rebuilding standalone binaries. See Building standalone binaries from release source.
• Resilient compaction and branch summaries — Transient provider failures now follow the configured retry policy, with retry lifecycle events available to interactive, JSON, RPC, and SDK consumers. See Compaction & Branch Summarization and RPC retry events.

Added

• Added deterministic, checksummed source archives to GitHub releases with documented standalone binary rebuild instructions (#6913 by @​christianklotz).

Fixed

• Fixed compaction and branch summarization to retry transient provider failures using the configured retry policy, with retry lifecycle events exposed to interactive, JSON, RPC, and SDK consumers (#6901 by @​davidbrai).
• Fixed interactive startup waiting for background model catalog refresh while computing the footer provider count.
• Restored the default stream fallback for extensions using the pre-0.81 agent-core API (#6915).
• Fixed inherited Kimi K3 models from Moonshot AI and Moonshot AI China to use the OpenAI thinking format and expose reasoning effort support.

[0.81.0] - 2026-07-21

New Features

• Local llama.cpp model management — Connect to a llama.cpp router, search and download Hugging Face models, and explicitly load or unload models with live progress. See llama.cpp.
• Full provider extensions — Extensions can register complete pi-ai providers with authentication, model refresh, filtering, and custom streaming. See Register New Provider.
• Qwen Token Plan providers — Use the built-in international and China subscription providers with regional endpoints and API-key authentication. See API Keys.
• Expanded usage accounting — Tool, compaction, and branch-summary usage is persisted and included in session totals. See Compaction & Branch Summarization.

Added

• Added Qwen Token Plan and Qwen Token Plan China to built-in provider setup, default model resolution, and provider documentation (#6858 by @​QuintinShaw).
• Added the get_available_thinking_levels RPC command and RpcClient.getAvailableThinkingLevels() method (#6865 by @​cristinaponcela).
• Exported message and tool execution lifecycle event types from the package root (#6772 by @​davidbrai).
• Added built-in llama.cpp router support with /login connection setup and /llama Hugging Face model search and downloads, explicit loading, unloading, and live progress. See llama.cpp.
• Added extension registration for complete pi-ai providers, including native authentication, model refresh, filtering, and streaming behavior.
• Added usage accounting for tools, compaction, and branch summaries in persisted sessions, footer totals, and session statistics (#6671 by @​davidbrai).

Fixed

• Updated the packaged brace-expansion dependency to 5.0.7 (#6896 by @​davidbrai).
• Fixed persisted remote model catalogs from overriding newer bundled catalogs after an upgrade.
• Fixed inherited stored API-key credentials to apply their provider-scoped env values, including Amazon Bedrock profiles (#6864 by @​cristinaponcela).
• Fixed inherited OpenAI-compatible cross-provider replay to keep tool call IDs unique when multiple calls share a provider call ID (#6854 by @​cristinaponcela).
• Fixed inherited Kimi K3 thinking levels to expose low, high, and max, and normalized the k2p7 alias to kimi-for-coding.
• Fixed inherited OpenCode Go models routed through the OpenAI Responses API.
• Fixed inherited pi-ai package metadata to avoid repeated consumer lockfile changes (#6812 by @​jmfederico).
• Fixed inherited terminal shutdown to clear the editor's inverted software cursor before restoring the hardware cursor (#6790 by @​dam9000).
• Fixed inherited ANSI-aware text wrapping to recognize CRLF and CR line endings while preserving styles (#6764 by @​xz-dev).
• Fixed inherited editor paste registry corruption after deleting and undoing paste markers, preventing literal or mismatched paste markers in submitted prompts (#6844).
• Fixed sessionless OpenAI Codex WebSocket requests to use UUIDv7 request IDs (#6834 by @​xl0).
• Fixed inherited GPT-5.6 Codex models to default to the 272K context window, avoiding automatic long-context pricing (#6853 by @​aadishv).

... (truncated)

Commits

• 20be4b1 Release v0.81.1
• b9e5c5d fix(agent): restore streamFn extension compatibility
• b142504 fix(coding-agent): defer catalog refresh until after TUI startup
• 7540da4 add docs for new event types
• ceac988 Merge remote-tracking branch 'origin/main' into fix/issue-6647-retry-summary-...
• 899fe26 fix: flaky test (#6905)
• 3dcb411 Add [Unreleased] section for next cycle
• 9c480b6 Release v0.81.0
• c901d9a docs: audit unreleased changelogs
• 864b35c fix(coding-agent): show llama download progress
• Additional commits viewable in compare view

Updates @earendil-works/pi-tui from 0.80.10 to 0.81.1

Release notes

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

v0.81.1

New Features

• Verifiable release source archives — GitHub releases now include deterministic, checksummed source archives with instructions for rebuilding standalone binaries. See Building standalone binaries from release source.
• Resilient compaction and branch summaries — Transient provider failures now follow the configured retry policy, with retry lifecycle events available to interactive, JSON, RPC, and SDK consumers. See Compaction & Branch Summarization and RPC retry events.

Added

• Added deterministic, checksummed source archives to GitHub releases with documented standalone binary rebuild instructions (#6913 by @​christianklotz).

Fixed

• Fixed compaction and branch summarization to retry transient provider failures using the configured retry policy, with retry lifecycle events exposed to interactive, JSON, RPC, and SDK consumers (#6901 by @​davidbrai).
• Fixed interactive startup waiting for background model catalog refresh while computing the footer provider count.
• Restored the default stream fallback for extensions using the pre-0.81 agent-core API (#6915).
• Fixed inherited Kimi K3 models from Moonshot AI and Moonshot AI China to use the OpenAI thinking format and expose reasoning effort support.

v0.81.0

New Features

• Local llama.cpp model management — Connect to a llama.cpp router, search and download Hugging Face models, and explicitly load or unload models with live progress. See llama.cpp.
• Full provider extensions — Extensions can register complete pi-ai providers with authentication, model refresh, filtering, and custom streaming. See Register New Provider.
• Qwen Token Plan providers — Use the built-in international and China subscription providers with regional endpoints and API-key authentication. See API Keys.
• Expanded usage accounting — Tool, compaction, and branch-summary usage is persisted and included in session totals. See Compaction & Branch Summarization.

Added

• Added Qwen Token Plan and Qwen Token Plan China to built-in provider setup, default model resolution, and provider documentation (#6858 by @​QuintinShaw).
• Added the get_available_thinking_levels RPC command and RpcClient.getAvailableThinkingLevels() method (#6865 by @​cristinaponcela).
• Exported message and tool execution lifecycle event types from the package root (#6772 by @​davidbrai).
• Added built-in llama.cpp router support with /login connection setup and /llama Hugging Face model search and downloads, explicit loading, unloading, and live progress. See llama.cpp.
• Added extension registration for complete pi-ai providers, including native authentication, model refresh, filtering, and streaming behavior.
• Added usage accounting for tools, compaction, and branch summaries in persisted sessions, footer totals, and session statistics (#6671 by @​davidbrai).

Fixed

• Updated the packaged brace-expansion dependency to 5.0.7 (#6896 by @​davidbrai).
• Fixed persisted remote model catalogs from overriding newer bundled catalogs after an upgrade.
• Fixed inherited stored API-key credentials to apply their provider-scoped env values, including Amazon Bedrock profiles (#6864 by @​cristinaponcela).
• Fixed inherited OpenAI-compatible cross-provider replay to keep tool call IDs unique when multiple calls share a provider call ID (#6854 by @​cristinaponcela).
• Fixed inherited Kimi K3 thinking levels to expose low, high, and max, and normalized the k2p7 alias to kimi-for-coding.
• Fixed inherited OpenCode Go models routed through the OpenAI Responses API.
• Fixed inherited pi-ai package metadata to avoid repeated consumer lockfile changes (#6812 by @​jmfederico).
• Fixed inherited terminal shutdown to clear the editor's inverted software cursor before restoring the hardware cursor (#6790 by @​dam9000).
• Fixed inherited ANSI-aware text wrapping to recognize CRLF and CR line endings while preserving styles (#6764 by @​xz-dev).
• Fixed inherited editor paste registry corruption after deleting and undoing paste markers, preventing literal or mismatched paste markers in submitted prompts (#6844).
• Fixed sessionless OpenAI Codex WebSocket requests to use UUIDv7 request IDs (#6834 by @​xl0).
• Fixed inherited GPT-5.6 Codex models to default to the 272K context window, avoiding automatic long-context pricing (#6853 by @​aadishv).
• Fixed messages queued during compaction to preserve steering and follow-up delivery behavior (#6730 by @​dannote).
• Fixed read tool errors being syntax-highlighted as if they were file contents (#6731 by @​dannote).

... (truncated)

Changelog

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

[0.81.1] - 2026-07-21

[0.81.0] - 2026-07-21

Fixed

• Fixed terminal shutdown to clear the editor's inverted software cursor before restoring the hardware cursor, avoiding a duplicate cursor artifact (#6790 by @​dam9000).
• Fixed ANSI-aware text wrapping to recognize CRLF and CR line endings while preserving styles across lines (#6764 by @​xz-dev).
• Fixed editor paste registry corruption when deleting paste markers: undo now restores the paste registry together with the text, and marker renumbering shifts registry entries in ascending id order, so submitted prompts no longer contain literal [paste #N ...] markers or the wrong paste's content (#6844).

Commits

• 20be4b1 Release v0.81.1
• 3dcb411 Add [Unreleased] section for next cycle
• 9c480b6 Release v0.81.0
• c901d9a docs: audit unreleased changelogs
• 3595e08 fix(tui): keep paste registry in sync when deleting paste markers
• 5f2f7d0 fix(tui): clear inverted cursor on exit to avoid dual cursor appearance (#6790)
• 00b0326 fix(tui): handle CRLF and CR line endings (#6764)
• 216e672 Add [Unreleased] section for next cycle
• See full diff in compare view

Updates @biomejs/biome from 2.5.4 to 2.5.5

Release notes

Sourced from @​biomejs/biome's releases.

Biome CLI v2.5.5

2.5.5

Patch Changes

• #10972 ab8c21b Thanks @​ematipico! - Fixed useExhaustiveSwitchCases for unions of bigint literals. The rule now reports missing bigint cases and compares bigint literals by value, including binary, octal, hexadecimal, and separator-containing spellings. For example, this switch now reports the missing 2n case:

  declare const value: 1n | 2n;
  switch (value) {
    case 1n:
      break;
  }

• #10972 ab8c21b Thanks @​ematipico! - Fixed false positives in noBaseToString and useNullishCoalescing when member, stringification, or nullish inference cannot complete. These rules now suppress diagnostics instead of reporting from partial type information. For example, neither expression is reported when a recursive type cannot be fully resolved:

  type Recursive = Recursive;
  declare const value: Recursive;
  String(value);
  value || "fallback";

• #10977 0bf7486 Thanks @​ematipico! - Fixed #10922: the action useSortedAttributes no longer triggers for HTML instructions.

• #10957 cf263c4 Thanks @​dyc3! - Fixed noThenProperty failing to detect Object.fromEntries, Object.defineProperty, and Reflect.defineProperty calls with comments between their tokens.

• #10983 edc0ed7 Thanks @​ayaangazali! - Fixed #10980: useAriaPropsSupportedByRole no longer reports false positives when the attribute that determines an element's implicit ARIA role is written as a shorthand attribute, such as <a {href} aria-label="..."> in Astro and Svelte files.

  Shorthand attributes are now taken into account when computing the implicit role, so the anchor above correctly resolves to the link role instead of generic.

• #10889 89526e3 Thanks @​denbezrukov! - Fixed CSS formatter casing for syntax-owned names while preserving author-defined names, including scoped keyframes and container scroll-state queries.

  - A:HOVER { COLOR: INITIAL; }
  + A:hover { color: initial; }
  - @KEYFRAMES :GLOBAL KeepFrames { FROM { COLOR: RED; } }
  + @keyframes :GLOBAL KeepFrames { from { color: RED; } }
  - @CONTAINER scroll-state((SCROLLED: TOP) AND (STUCK)) { A:HOVER { COLOR: RED; } }
  + @container scroll-state((SCROLLED: TOP) AND (STUCK)) { A:hover { color: RED; } }

• #10964 794ccd0 Thanks @​denbezrukov! - Fixed CSS formatting for comments between declaration values and !important.

  -a { color: /* before */ /* after */ red !important; }
  +a { color: /* before */ red /* after */ !important; }

... (truncated)

Changelog

Sourced from @​biomejs/biome's changelog.

2.5.5

Patch Changes

• #10972 ab8c21b Thanks @​ematipico! - Fixed useExhaustiveSwitchCases for unions of bigint literals. The rule now reports missing bigint cases and compares bigint literals by value, including binary, octal, hexadecimal, and separator-containing spellings. For example, this switch now reports the missing 2n case:

  declare const value: 1n | 2n;
  switch (value) {
    case 1n:
      break;
  }

• Description has been truncated