build(deps): bump @earendil-works/pi-ai from 0.82.1 to 0.85.1 #10

2026-10-08T07:44:21Z

xixu-me commented

2026-10-08 07:44:21 +00:00

Bumps @earendil-works/pi-ai from 0.82.1 to 0.85.1.

Release notes

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

v0.85.1

New Features

GPT-6 Astra — Available through OpenAI API keys and OpenAI Codex subscriptions. See API Keys and OpenAI Codex.

Added

Added GPT-6 Astra for OpenAI API keys and OpenAI Codex subscriptions.

Added five-times-faster mouse wheel scrolling while holding Alt in fullscreen mode (#9166 by @xl0).

Fixed

Fixed configurable save keybindings in the model and thinking selectors (#9149 by @rwachtler).

Fixed SDK import failures caused by unintentionally publishing internal experimental code and dependencies in 0.85.0. The experimental client and experimental/plugin subpaths and server/client commands are now source-only through pi-test.sh; the supported local SDK and stdio RPC API are unchanged (#9132).

Fixed mouse hover changing selection and recentering autocomplete and settings lists, causing clicks to target a different item.

Fixed long prompt-cache requests for GPT-5.6+ Responses models to use prompt_cache_options.ttl: "30m" instead of prompt_cache_retention: "24h".

v0.85.0

New Features

Persistent Claude thinking effort — Supported Anthropic transports preserve per-turn effort and recover safely from signed-thinking mismatches. See Model Configuration.

Fullscreen transcript controls — Jump to the latest message from a scrolled transcript and use the embedded working indicator. See TUI Fullscreen Viewport.

Restorable in-memory sessions — Resume externally stored session entries through the SDK. See Session Management.

Added

Added SessionManager.inMemory() support for restoring externally managed session entries (#8980 by @y-nk).

Added inherited OpenAI-compatible vllmPriority and supportsMaxOutputTokens model settings for vLLM scheduler priority and OpenAI Responses output-token limits (#9004 by @AppleDannyClegg, #8941 by @scturtle).

Added inherited LaTeX rendering for relational algebra join symbols (#9050 by @haoqixu).

Added a clickable "Jump to latest message" label with the tui.altScreen.bottom shortcut to the fullscreen transcript while it is scrolled up (#9080 by @rwachtler).

Changed

Moved the streaming working indicator into the default editor border and matched its default spinner and label to the thinking-level border color. Custom editors retain the standalone indicator unless they opt in to embedding it (#8799 by @cristinaponcela).

Reduced inherited fullscreen transcript search latency on large transcripts by caching unchanged search results, indexing ASCII runs, and limiting highlight work to visible matches (#8800 by @cristinaponcela).

Fixed

Fixed managed fd and ripgrep downloads on Linux musl systems (#9070 by @Charlie0113-T).

Removed the unavailable inherited Grok Build 0.1 model from /model (#9093 by @Jaaneek).

Fixed inherited provider streams emitting incompatible event sequences and custom tool-call deltas.

Restored the @earendil-works/pi-coding-agent/client compatibility entry point.

Fixed the inherited Qwen Token Plan Individual catalog to include Qwen3.8 Flash (#9021).

Fixed inherited OpenAI Codex SSE parsing to process terminal events that are not followed by a blank line (#9047).

Fixed inherited GitHub Copilot Claude Fable 5 requests so selected reasoning levels are sent (#8961).

Fixed inherited Baseten GLM-5.2 models incorrectly advertising image input support (#8293 by @Panoplos).

Fixed skills being unavailable when Bash is the only enabled tool (#8552 by @xl0).

Fixed concurrent session shares overwriting one another (#8613 by @wutongyuonce).

Fixed image orientation detection skipping EXIF data after non-EXIF APP1 segments (#8616 by @wutongyuonce).

Fixed imported sessions overwriting an existing session with the same filename (#8985 by @wutongyuonce).

... (truncated)

Changelog

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

[0.85.1] - 2026-09-05

Added

Added GPT-6 Astra for OpenAI API keys and OpenAI Codex subscriptions.

Fixed

Fixed long prompt-cache requests for GPT-5.6+ Responses models to use prompt_cache_options.ttl: "30m" instead of prompt_cache_retention: "24h".

[0.85.0] - 2026-09-04

Breaking Changes

Replaced createGatewayBindingFetch() with createAiBindingFetch() for Cloudflare Workers AI bindings. Configure the model's Workers AI Gateway passthrough baseUrl directly; requests now pass through the binding unchanged (#8287 by @Maximo-Guk).

Added

Added compact, persistable assistant-message frames with AssistantMessageFrameEncoder and reduceAssistantMessageFrames().

Added the vllmPriority OpenAI-compatible model setting for forwarding scheduler priority to vLLM (#9004 by @AppleDannyClegg).

Added the supportsMaxOutputTokens OpenAI Responses compatibility setting (#8941 by @scturtle).

Added an optional timestamp argument to uuidv7() for follower IDs.

Added narrow api, providers, and utils subpath exports for direct imports without loading the package barrel.

Added Anthropic per-turn effort persistence, deterministic historical effort markers, and signed-thinking mismatch recovery for supported Claude models across Anthropic Messages transports, including OpenRouter.

Added Meta provider (Model API key and Muse subscription OAuth) with Muse Spark models.

Fixed

Removed the unavailable Grok Build 0.1 model from the built-in xAI catalog (#9093 by @Jaaneek).

Fixed assistant-message frames preserving the provider thinking level.

Fixed simple provider streams to consistently emit standard stream events and custom tool-call deltas.

Fixed the Qwen Token Plan Individual catalog to include Qwen3.8 Flash (#9021).

Fixed Baseten GLM-5.2 models incorrectly advertising image input support (#8293 by @Panoplos).

Fixed Fireworks GLM models using the wrong API adapter.

Removed the unnecessary Chord dependency from pi-ai by defining its exported JsonValue type directly.

Fixed GitHub Copilot Claude Fable 5 requests to use the Anthropic Messages adapter so selected reasoning levels are sent (#8961).

Fixed OpenAI Codex SSE parsing to process terminal events that are not followed by a blank line (#9047).

Fixed NO_PROXY matching for both root domains and subdomains (#8737 by @MeiSiristhebest).

[0.84.4] - 2026-08-28

Added

Added the experimental vision-capable deepseek-v4-flash-vision-exp model to the DeepSeek catalog.

Fixed

Fixed OpenAI-compatible Chat Completions ignoring an explicitly requested toolChoice when no tools are defined.

Fixed thinking signature serialization to run once after the signature is complete (#8671).

Fixed fragmented Mistral tool calls splitting when continuation chunks omit the tool-call ID (#8387).

... (truncated)

Commits

d981de1 Release v0.85.1
fbc87d2 feat(ai): refresh generated image model catalog
1a46b92 docs: audit changelogs for v0.85.1
17de82d feat(ai): add GPT-6 Astra support
dd7e816 Add [Unreleased] section for next cycle
107d79f Release v0.85.0
1148f79 docs: audit unreleased changelogs
ef41a24 fix(ai): keep Copilot tests aligned with current model catalog
0dbf2b7 fix(ai): remove Grok Build 0.1 from built-in xAI model catalog (#9093)
0fdec07 fix(ai): preserve provider thinking level in frames
Additional commits viewable 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 this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
@dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
@dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

GitHub 来源：https://github.com/xixu-me/deepseek-harness/pull/10
作者：dependabot[bot] · 创建时间：2026-10-08T07:16:16Z

Bumps [@earendil-works/pi-ai](https://github.com/earendil-works/pi/tree/HEAD/packages/ai) from 0.82.1 to 0.85.1. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/earendil-works/pi/releases">@earendil-works/pi-ai's releases</a>.</em></p> <blockquote> <h2>v0.85.1</h2> <h3>New Features</h3> <ul> <li><strong>GPT-6 Astra</strong> — Available through OpenAI API keys and OpenAI Codex subscriptions. See <a href="https://github.com/earendil-works/pi/blob/v0.85.1/packages/coding-agent/docs/providers.md#api-keys">API Keys</a> and <a href="https://github.com/earendil-works/pi/blob/v0.85.1/packages/coding-agent/docs/providers.md#openai-codex">OpenAI Codex</a>.</li> </ul> <h3>Added</h3> <ul> <li>Added GPT-6 Astra for OpenAI API keys and OpenAI Codex subscriptions.</li> <li>Added five-times-faster mouse wheel scrolling while holding Alt in fullscreen mode (<a href="https://redirect.github.com/earendil-works/pi/pull/9166">#9166</a> by <a href="https://github.com/xl0"><code>@xl0</code></a>).</li> </ul> <h3>Fixed</h3> <ul> <li>Fixed configurable save keybindings in the model and thinking selectors (<a href="https://redirect.github.com/earendil-works/pi/pull/9149">#9149</a> by <a href="https://github.com/rwachtler"><code>@rwachtler</code></a>).</li> <li>Fixed SDK import failures caused by unintentionally publishing internal experimental code and dependencies in 0.85.0. The experimental <code>client</code> and <code>experimental/plugin</code> subpaths and server/client commands are now source-only through <code>pi-test.sh</code>; the supported local SDK and stdio RPC API are unchanged (<a href="https://redirect.github.com/earendil-works/pi/issues/9132">#9132</a>).</li> <li>Fixed mouse hover changing selection and recentering autocomplete and settings lists, causing clicks to target a different item.</li> <li>Fixed long prompt-cache requests for GPT-5.6+ Responses models to use <code>prompt_cache_options.ttl: "30m"</code> instead of <code>prompt_cache_retention: "24h"</code>.</li> </ul> <h2>v0.85.0</h2> <h3>New Features</h3> <ul> <li><strong>Persistent Claude thinking effort</strong> — Supported Anthropic transports preserve per-turn effort and recover safely from signed-thinking mismatches. See <a href="https://github.com/earendil-works/pi/blob/v0.85.0/packages/coding-agent/docs/models.md#model-configuration">Model Configuration</a>.</li> <li><strong>Fullscreen transcript controls</strong> — Jump to the latest message from a scrolled transcript and use the embedded working indicator. See <a href="https://github.com/earendil-works/pi/blob/v0.85.0/packages/coding-agent/docs/keybindings.md#tui-fullscreen-viewport">TUI Fullscreen Viewport</a>.</li> <li><strong>Restorable in-memory sessions</strong> — Resume externally stored session entries through the SDK. See <a href="https://github.com/earendil-works/pi/blob/v0.85.0/packages/coding-agent/docs/sdk.md#session-management">Session Management</a>.</li> </ul> <h3>Added</h3> <ul> <li>Added <code>SessionManager.inMemory()</code> support for restoring externally managed session entries (<a href="https://redirect.github.com/earendil-works/pi/pull/8980">#8980</a> by <a href="https://github.com/y-nk"><code>@y-nk</code></a>).</li> <li>Added inherited OpenAI-compatible <code>vllmPriority</code> and <code>supportsMaxOutputTokens</code> model settings for vLLM scheduler priority and OpenAI Responses output-token limits (<a href="https://redirect.github.com/earendil-works/pi/pull/9004">#9004</a> by <a href="https://github.com/AppleDannyClegg"><code>@AppleDannyClegg</code></a>, <a href="https://redirect.github.com/earendil-works/pi/pull/8941">#8941</a> by <a href="https://github.com/scturtle"><code>@scturtle</code></a>).</li> <li>Added inherited LaTeX rendering for relational algebra join symbols (<a href="https://redirect.github.com/earendil-works/pi/pull/9050">#9050</a> by <a href="https://github.com/haoqixu"><code>@haoqixu</code></a>).</li> <li>Added a clickable "Jump to latest message" label with the <code>tui.altScreen.bottom</code> shortcut to the fullscreen transcript while it is scrolled up (<a href="https://redirect.github.com/earendil-works/pi/pull/9080">#9080</a> by <a href="https://github.com/rwachtler"><code>@rwachtler</code></a>).</li> </ul> <h3>Changed</h3> <ul> <li>Moved the streaming working indicator into the default editor border and matched its default spinner and label to the thinking-level border color. Custom editors retain the standalone indicator unless they opt in to embedding it (<a href="https://redirect.github.com/earendil-works/pi/pull/8799">#8799</a> by <a href="https://github.com/cristinaponcela"><code>@cristinaponcela</code></a>).</li> <li>Reduced inherited fullscreen transcript search latency on large transcripts by caching unchanged search results, indexing ASCII runs, and limiting highlight work to visible matches (<a href="https://redirect.github.com/earendil-works/pi/pull/8800">#8800</a> by <a href="https://github.com/cristinaponcela"><code>@cristinaponcela</code></a>).</li> </ul> <h3>Fixed</h3> <ul> <li>Fixed managed <code>fd</code> and ripgrep downloads on Linux musl systems (<a href="https://redirect.github.com/earendil-works/pi/pull/9070">#9070</a> by <a href="https://github.com/Charlie0113-T"><code>@Charlie0113-T</code></a>).</li> <li>Removed the unavailable inherited Grok Build 0.1 model from <code>/model</code> (<a href="https://redirect.github.com/earendil-works/pi/pull/9093">#9093</a> by <a href="https://github.com/Jaaneek"><code>@Jaaneek</code></a>).</li> <li>Fixed inherited provider streams emitting incompatible event sequences and custom tool-call deltas.</li> <li>Restored the <code>@earendil-works/pi-coding-agent/client</code> compatibility entry point.</li> <li>Fixed the inherited Qwen Token Plan Individual catalog to include Qwen3.8 Flash (<a href="https://redirect.github.com/earendil-works/pi/issues/9021">#9021</a>).</li> <li>Fixed inherited OpenAI Codex SSE parsing to process terminal events that are not followed by a blank line (<a href="https://redirect.github.com/earendil-works/pi/issues/9047">#9047</a>).</li> <li>Fixed inherited GitHub Copilot Claude Fable 5 requests so selected reasoning levels are sent (<a href="https://redirect.github.com/earendil-works/pi/issues/8961">#8961</a>).</li> <li>Fixed inherited Baseten GLM-5.2 models incorrectly advertising image input support (<a href="https://redirect.github.com/earendil-works/pi/pull/8293">#8293</a> by <a href="https://github.com/Panoplos"><code>@Panoplos</code></a>).</li> <li>Fixed skills being unavailable when Bash is the only enabled tool (<a href="https://redirect.github.com/earendil-works/pi/pull/8552">#8552</a> by <a href="https://github.com/xl0"><code>@xl0</code></a>).</li> <li>Fixed concurrent session shares overwriting one another (<a href="https://redirect.github.com/earendil-works/pi/pull/8613">#8613</a> by <a href="https://github.com/wutongyuonce"><code>@wutongyuonce</code></a>).</li> <li>Fixed image orientation detection skipping EXIF data after non-EXIF APP1 segments (<a href="https://redirect.github.com/earendil-works/pi/pull/8616">#8616</a> by <a href="https://github.com/wutongyuonce"><code>@wutongyuonce</code></a>).</li> <li>Fixed imported sessions overwriting an existing session with the same filename (<a href="https://redirect.github.com/earendil-works/pi/pull/8985">#8985</a> by <a href="https://github.com/wutongyuonce"><code>@wutongyuonce</code></a>).</li> </ul>  </blockquote> <p>... (truncated)</p> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/earendil-works/pi/blob/main/packages/ai/CHANGELOG.md">@earendil-works/pi-ai's changelog</a>.</em></p> <blockquote> <h2>[0.85.1] - 2026-09-05</h2> <h3>Added</h3> <ul> <li>Added GPT-6 Astra for OpenAI API keys and OpenAI Codex subscriptions.</li> </ul> <h3>Fixed</h3> <ul> <li>Fixed long prompt-cache requests for GPT-5.6+ Responses models to use <code>prompt_cache_options.ttl: "30m"</code> instead of <code>prompt_cache_retention: "24h"</code>.</li> </ul> <h2>[0.85.0] - 2026-09-04</h2> <h3>Breaking Changes</h3> <ul> <li>Replaced <code>createGatewayBindingFetch()</code> with <code>createAiBindingFetch()</code> for Cloudflare Workers AI bindings. Configure the model's Workers AI Gateway passthrough <code>baseUrl</code> directly; requests now pass through the binding unchanged (<a href="https://redirect.github.com/earendil-works/pi/pull/8287">#8287</a> by <a href="https://github.com/Maximo-Guk"><code>@Maximo-Guk</code></a>).</li> </ul> <h3>Added</h3> <ul> <li>Added compact, persistable assistant-message frames with <code>AssistantMessageFrameEncoder</code> and <code>reduceAssistantMessageFrames()</code>.</li> <li>Added the <code>vllmPriority</code> OpenAI-compatible model setting for forwarding scheduler priority to vLLM (<a href="https://redirect.github.com/earendil-works/pi/pull/9004">#9004</a> by <a href="https://github.com/AppleDannyClegg"><code>@AppleDannyClegg</code></a>).</li> <li>Added the <code>supportsMaxOutputTokens</code> OpenAI Responses compatibility setting (<a href="https://redirect.github.com/earendil-works/pi/pull/8941">#8941</a> by <a href="https://github.com/scturtle"><code>@scturtle</code></a>).</li> <li>Added an optional timestamp argument to <code>uuidv7()</code> for follower IDs.</li> <li>Added narrow <code>api</code>, <code>providers</code>, and <code>utils</code> subpath exports for direct imports without loading the package barrel.</li> <li>Added Anthropic per-turn effort persistence, deterministic historical effort markers, and signed-thinking mismatch recovery for supported Claude models across Anthropic Messages transports, including OpenRouter.</li> <li>Added Meta provider (Model API key and Muse subscription OAuth) with Muse Spark models.</li> </ul> <h3>Fixed</h3> <ul> <li>Removed the unavailable Grok Build 0.1 model from the built-in xAI catalog (<a href="https://redirect.github.com/earendil-works/pi/pull/9093">#9093</a> by <a href="https://github.com/Jaaneek"><code>@Jaaneek</code></a>).</li> <li>Fixed assistant-message frames preserving the provider thinking level.</li> <li>Fixed simple provider streams to consistently emit standard stream events and custom tool-call deltas.</li> <li>Fixed the Qwen Token Plan Individual catalog to include Qwen3.8 Flash (<a href="https://redirect.github.com/earendil-works/pi/issues/9021">#9021</a>).</li> <li>Fixed Baseten GLM-5.2 models incorrectly advertising image input support (<a href="https://redirect.github.com/earendil-works/pi/pull/8293">#8293</a> by <a href="https://github.com/Panoplos"><code>@Panoplos</code></a>).</li> <li>Fixed Fireworks GLM models using the wrong API adapter.</li> <li>Removed the unnecessary Chord dependency from pi-ai by defining its exported <code>JsonValue</code> type directly.</li> <li>Fixed GitHub Copilot Claude Fable 5 requests to use the Anthropic Messages adapter so selected reasoning levels are sent (<a href="https://redirect.github.com/earendil-works/pi/issues/8961">#8961</a>).</li> <li>Fixed OpenAI Codex SSE parsing to process terminal events that are not followed by a blank line (<a href="https://redirect.github.com/earendil-works/pi/issues/9047">#9047</a>).</li> <li>Fixed <code>NO_PROXY</code> matching for both root domains and subdomains (<a href="https://redirect.github.com/earendil-works/pi/pull/8737">#8737</a> by <a href="https://github.com/MeiSiristhebest"><code>@MeiSiristhebest</code></a>).</li> </ul> <h2>[0.84.4] - 2026-08-28</h2> <h3>Added</h3> <ul> <li>Added the experimental vision-capable <code>deepseek-v4-flash-vision-exp</code> model to the DeepSeek catalog.</li> </ul> <h3>Fixed</h3> <ul> <li>Fixed OpenAI-compatible Chat Completions ignoring an explicitly requested <code>toolChoice</code> when no tools are defined.</li> <li>Fixed thinking signature serialization to run once after the signature is complete (<a href="https://redirect.github.com/earendil-works/pi/pull/8671">#8671</a>).</li> <li>Fixed fragmented Mistral tool calls splitting when continuation chunks omit the tool-call ID (<a href="https://redirect.github.com/earendil-works/pi/issues/8387">#8387</a>).</li> </ul>  </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/earendil-works/pi/commit/d981de1229ef899957bbe968bc8dcda02a21f477"><code>d981de1</code></a> Release v0.85.1</li> <li><a href="https://github.com/earendil-works/pi/commit/fbc87d25a8254cf82590e7279285e89889f1e445"><code>fbc87d2</code></a> feat(ai): refresh generated image model catalog</li> <li><a href="https://github.com/earendil-works/pi/commit/1a46b923d7c725e4d0759139f8687f04797a33d4"><code>1a46b92</code></a> docs: audit changelogs for v0.85.1</li> <li><a href="https://github.com/earendil-works/pi/commit/17de82d7bea18a6589677a9761baabc2060c9efb"><code>17de82d</code></a> feat(ai): add GPT-6 Astra support</li> <li><a href="https://github.com/earendil-works/pi/commit/dd7e816b57dedbe971d159b388f48317a6139079"><code>dd7e816</code></a> Add [Unreleased] section for next cycle</li> <li><a href="https://github.com/earendil-works/pi/commit/107d79f11072bbc8a3a757ed7fd69596bee7d68c"><code>107d79f</code></a> Release v0.85.0</li> <li><a href="https://github.com/earendil-works/pi/commit/1148f7958c260188b03488496044dcfa852ef580"><code>1148f79</code></a> docs: audit unreleased changelogs</li> <li><a href="https://github.com/earendil-works/pi/commit/ef41a24b391bb90043e28eb8925911bb3f8acf2a"><code>ef41a24</code></a> fix(ai): keep Copilot tests aligned with current model catalog</li> <li><a href="https://github.com/earendil-works/pi/commit/0dbf2b76fe7919d5fe4184523898507b4ae19ee0"><code>0dbf2b7</code></a> fix(ai): remove Grok Build 0.1 from built-in xAI model catalog (<a href="https://github.com/earendil-works/pi/tree/HEAD/packages/ai/issues/9093">#9093</a>)</li> <li><a href="https://github.com/earendil-works/pi/commit/0fdec07ba3973f9bd008cbfffb0eaa10ace8c5b3"><code>0fdec07</code></a> fix(ai): preserve provider thinking level in frames</li> <li>Additional commits viewable in <a href="https://github.com/earendil-works/pi/commits/v0.85.1/packages/ai">compare view</a></li> </ul> </details> <br /> [![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=@earendil-works/pi-ai&package-manager=npm_and_yarn&previous-version=0.82.1&new-version=0.85.1)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) 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-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> 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 this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> --- GitHub 来源：https://github.com/xixu-me/deepseek-harness/pull/10 作者：dependabot[bot] · 创建时间：2026-10-08T07:16:16Z

xixu-me added 1 commit 2026-10-08 07:44:22 +00:00

build(deps): bump @earendil-works/pi-ai from 0.82.1 to 0.85.1 0113b74ed5

Bumps [@earendil-works/pi-ai](https://github.com/earendil-works/pi/tree/HEAD/packages/ai) from 0.82.1 to 0.85.1.
- [Release notes](https://github.com/earendil-works/pi/releases)
- [Changelog](https://github.com/earendil-works/pi/blob/main/packages/ai/CHANGELOG.md)
- [Commits](https://github.com/earendil-works/pi/commits/v0.85.1/packages/ai)

---
updated-dependencies:
- dependency-name: "@earendil-works/pi-ai"
  dependency-version: 0.85.1
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

xixu-me commented

2026-10-08 07:44:24 +00:00

Labels

The following labels could not be found: area/infra, kind/dependency. Please create them before Dependabot can add them to a pull request.

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

GitHub 来源：https://github.com/xixu-me/deepseek-harness/pull/10#issuecomment-6054696487
作者：dependabot[bot] · 创建时间：2026-10-08T07:16:16Z

### Labels The following labels could not be found: `area/infra`, `kind/dependency`. Please create them before Dependabot can add them to a pull request. Please fix the above issues or remove invalid values from `dependabot.yml`. --- GitHub 来源：https://github.com/xixu-me/deepseek-harness/pull/10#issuecomment-6054696487 作者：dependabot[bot] · 创建时间：2026-10-08T07:16:16Z

xixu-me commented

2026-10-08 07:44:24 +00:00

Review the following changes in direct dependencies. Learn more about Socket for GitHub.

Diff	Package	Supply Chain Security	Vulnerability	Quality	Maintenance	License
	npm/@earendil-works/pi-ai@0.82.1 ⏵ 0.85.1	⁺¹		⁺¹	⁺¹

View full report

GitHub 来源：https://github.com/xixu-me/deepseek-harness/pull/10#issuecomment-6054717525
作者：socket-security[bot] · 创建时间：2026-10-08T07:17:26Z

**Review the following changes in direct dependencies.** Learn more about [Socket for GitHub](https://socket.dev?utm_medium=gh). <table> <thead> <tr> <th>Diff</th> <th width="200px">Package</th> <th align="left" width="100px">Supply Chain<br/>Security</th> <th align="left" width="100px">Vulnerability</th> <th align="left" width="100px">Quality</th> <th align="left" width="100px">Maintenance</th> <th align="left" width="100px">License</th> </tr> </thead> <tbody> <tr><td align="center"><a href="https://socket.dev/dashboard/org/default-4lfzp/diff-scan/d5c642a3-c2dc-46aa-b260-126bd01105b1?tab=dependencies&dependency_item_key=101944262579"><img src="https://github-app-statics.socket.dev/diff-updated.svg" title="Updated" alt="Updated" width="20" height="20"></a></td><td><a href="https://socket.dev/dashboard/org/default-4lfzp/diff-scan/d5c642a3-c2dc-46aa-b260-126bd01105b1?tab=dependencies&dependency_item_key=101944262579">npm/@earendil-works/pi-ai@0.82.1 ⏵ 0.85.1</a></td><td align="left"><a href="https://socket.dev/dashboard/org/default-4lfzp/diff-scan/d5c642a3-c2dc-46aa-b260-126bd01105b1?tab=dependencies&dependency_item_key=101944262579"><img src="https://github-app-statics.socket.dev/score-100.svg" title="Supply Chain Security" width="40" height="40" alt="100"></a> <sup>+1</sup></td><td align="left"><a href="https://socket.dev/dashboard/org/default-4lfzp/diff-scan/d5c642a3-c2dc-46aa-b260-126bd01105b1?tab=dependencies&dependency_item_key=101944262579"><img src="https://github-app-statics.socket.dev/score-100.svg" title="Vulnerability" width="40" height="40" alt="100"></a></td><td align="left"><a href="https://socket.dev/dashboard/org/default-4lfzp/diff-scan/d5c642a3-c2dc-46aa-b260-126bd01105b1?tab=dependencies&dependency_item_key=101944262579"><img src="https://github-app-statics.socket.dev/score-100.svg" title="Quality" width="40" height="40" alt="100"></a> <sup>+1</sup></td><td align="left"><a href="https://socket.dev/dashboard/org/default-4lfzp/diff-scan/d5c642a3-c2dc-46aa-b260-126bd01105b1?tab=dependencies&dependency_item_key=101944262579"><img src="https://github-app-statics.socket.dev/score-98.svg" title="Maintenance" width="40" height="40" alt="98"></a> <sup>+1</sup></td><td align="left"><a href="https://socket.dev/dashboard/org/default-4lfzp/diff-scan/d5c642a3-c2dc-46aa-b260-126bd01105b1?tab=dependencies&dependency_item_key=101944262579"><img src="https://github-app-statics.socket.dev/score-100.svg" title="License" width="40" height="40" alt="100"></a></td></tr> </tbody> </table> [View full report](https://socket.dev/dashboard/org/default-4lfzp/diff-scan/d5c642a3-c2dc-46aa-b260-126bd01105b1?tab=dependencies)  --- GitHub 来源：https://github.com/xixu-me/deepseek-harness/pull/10#issuecomment-6054717525 作者：socket-security[bot] · 创建时间：2026-10-08T07:17:26Z

You are not authorized to merge this pull request.

This pull request can be merged automatically.

View command line instructions

Checkout

From your project repository, check out a new branch and test the changes.

git fetch -u origin dependabot/npm_and_yarn/earendil-works/pi-ai-0.85.1:dependabot/npm_and_yarn/earendil-works/pi-ai-0.85.1

git checkout dependabot/npm_and_yarn/earendil-works/pi-ai-0.85.1

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: xixu-me/deepseek-harness#10