build(deps-dev): bump the dev-dependencies group across 1 directory with 7 updates

DE
5d ago
+295-793

Bumps the dev-dependencies group with 7 updates in the / directory:

PackageFromTo
@biomejs/biome2.5.152.6.3
@earendil-works/pi-agent-core1.0.41.4.0
@earendil-works/pi-ai1.0.41.4.0
@earendil-works/pi-coding-agent1.0.41.4.0
@earendil-works/pi-tui1.0.41.4.0
@types/node26.6.426.6.5
vitest5.0.35.0.5

Updates @biomejs/biome from 2.5.15 to 2.6.3

Release notes

Sourced from @​biomejs/biome's releases.

Biome CLI v2.6.3

2.6.3

Patch Changes

  • #12275 807e616 Thanks @​dyc3! - Added the new nursery rule noArraySortForMinMax, which reports sorting an array only to read its smallest or largest value. Use Math.min() or Math.max() instead.

    const minimum = array.toSorted((a, b) => a - b)[0];

  • #12432 cf61682 Thanks @​dyc3! - Added the nursery rule noBooleanSortComparator, which reports sort comparators that return a boolean instead of a number. For example, array.sort((a, b) => a > b) never puts the first item before the second, so the array isn't sorted correctly.

  • #12304 b4654c5 Thanks @​dyc3! - Added the new nursery rule noEagerArrayMethodsInLoops, which reports .map() and .filter() calls in the header of for...of loops. These calls build a new array that is only used by the loop.

    for (const name of users.map((user) => user.name)) {
  console.log(name);
}

  • #12121 66c3791 Thanks @​dyc3! - Added the nursery rule noNewRequire, which disallows calling require with new, such as new require("app-header").

  • #12316 34b520d Thanks @​dyc3! - Added the new nursery rule noObsoleteAttributes, which disallows obsolete attributes on HTML elements and suggests what to use instead.

    <table bgcolor="#ffffff" cellpadding="5"></table>

  • #12258 cce2385 Thanks @​dyc3! - Added the nursery rule noPathConcat, which disallows building file paths and URLs by joining strings to __dirname, __filename, import.meta.dirname, import.meta.filename, or import.meta.url.

    const fullPath = __dirname + "/foo.js"; // reported

  • #12287 e12ad78 Thanks @​dyc3! - Added the new nursery rule noPlaywrightNthMethods, which disallows selecting Playwright elements by position with first(), last(), and nth(). A test that relies on the position of an element can act on a different element when the page changes.

    await page.locator("button").first().click();

  • #12343 62ad123 Thanks @​vibbix! - Added the nursery rule noSelfNestedLayer, which disallows nesting a cascade layer inside a layer with the same name. Layer names inside an @layer block are relative to it, so the inner layer below creates the sublayer components.components instead of adding to components.

    @layer components {
  @layer components {
    .button {
      color: red;
    }

... (truncated)

Commits

Updates @earendil-works/pi-agent-core from 1.0.4 to 1.4.0

Release notes

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

v1.4.0

New Features

  • Image input for classifiers: codemode models.classify() accepts images for TypeSafe's Jev and Cloudflare's Clef models on typesafe, cloudflare-workers-ai, and OpenRouter. See Use classifier models and Codemode.
  • Models Configuration reference: every provider, model, model override, and compatibility field of models.json, generated from its schema. See Models Configuration.
  • Summaries without a fixed output cap: compaction and branch summaries use the model's output limit, so long reasoning no longer makes them fail. See Compaction.
  • Codemode waits for a free worker: parallel scripts and in-process subagents queue instead of failing, and PI_CODEMODE_MAX_WORKERS raises the limit. See Codemode limits.
  • Rex terminal support: OSC 8 hyperlinks, truecolor, and inline images.

Added

  • Added a Models Configuration reference generated from the models.json schema, listing all provider, model, model override, and compatibility fields (#10790)
  • Codemode models.classify() now accepts images for TypeSafe's Jev and Cloudflare's Clef models on typesafe, cloudflare-workers-ai, and OpenRouter, and lists Clef Omni and Jev 1.14 on Workers AI.
  • Provider-level compat in models.json now also applies to classifier models, with the System One fields imageInput and sendImageOptInHeader for proxies that serve another service's classifiers. Extension classifier models accept compat too.
  • Added MiniMax-M3.1-Flash to the minimax and minimax-cn providers, with thinking levels low through max (#11121)
  • Added support for the Rex terminal: OSC 8 hyperlinks, truecolor, and inline images (#11131, #11150 by @​petrroll, #11183 by @​nihaals)

Changed

  • Provider attribution headers now come from pi-ai's client identity. Extensions' before_provider_headers handlers no longer see the OpenRouter, NVIDIA NIM, and OpenCode attribution headers; returning null for one still removes it. Cloudflare requests send pi's detailed User-Agent instead of pi-coding-agent, as do GitHub release checks for tool downloads, and OpenCode requests send x-opencode-client whenever attribution is enabled, not only with a session.
  • generateSummary() and generateSummaryWithUsage() now ignore their reserveTokens parameter. Summary requests use the model's output limit instead.
  • Changed the default GitHub Copilot model from gpt-5.4, which Copilot retired, to gpt-6.1-sol.
  • Changed the default NVIDIA model to nvidia/nemotron-3.5-super-vl-120b-a12b (#10910 by @​cv)
  • Changed the default Xiaomi model to mimo-v2.6-pro for the xiaomi and Xiaomi Token Plan providers, since mimo-v2.5-pro left the catalog.
  • Grok 4.3 and Grok 4.5 on the xai provider now offer the xhigh thinking level.
  • Sign in with ChatGPT: ChatGPT Business workspace usage-limit errors are not retried and tell the user to ask their workspace admin to increase the limit.

Fixed

  • Fixed compaction and branch summaries failing with "generation hit the token cap" when reasoning used most of the fixed summary output limit. Summaries now use the model's output limit, and compaction.reserveTokens only controls when compaction starts (#9512, #9075).
  • Fixed models.schema.json missing descriptions for provider and model fields, so editors showed no hints for them (#10790)
  • Fixed pi update failing with "Managed install marker is missing or invalid" when managed-install.json starts with a UTF-8 BOM, which Windows PowerShell 5.1 adds when it rewrites the file.
  • Fixed HTML export showing literal asterisks for Markdown bold and italic next to CJK punctuation (#3353, #10154)
  • Fixed the terminal staying in mouse-tracking, focus-reporting, Kitty keyboard, and alternate-screen modes when pi exits without its normal terminal teardown, which flooded the shell prompt with escape sequences (#11170)
  • Fixed concurrent extension select/confirm/input/editor dialogs and inline custom() components in interactive mode: a second dialog replaced the first and the first promise never settled; closing the visible dialog now shows the previous one again (#11166, #9909)
  • Fixed pasting in the shell hanging after copying text in pi and suspending it with Ctrl+Z on Linux: the background wl-copy/xclip/xsel process that keeps serving the clipboard was suspended along with pi (#11179)
  • Fixed codemode scripts failing immediately when both codemode workers are busy, for example with parallel codemode calls or in-process subagents. Scripts now wait up to 60 seconds for a free worker, and PI_CODEMODE_MAX_WORKERS raises the limit of two workers (#11184)
  • Fixed extensions failing to load when importing @earendil-works/pi-ai/models (e.g. for clampThinkingLevel) by exposing the subpath through the extension loader aliases and virtual modules (#11156)
  • Fixed mcp.json files that start with a UTF-8 BOM failing to parse, which skipped all their MCP servers and made pi mcp add/pi mcp remove fail (#11191)
  • Fixed /compact <instructions> ignoring the instructions when summarizing the start of a turn that compaction splits. When the split turn was the only new content since the last compaction, the instructions were ignored entirely (#11058)
  • Fixed resumed sessions and /tree navigation leaving extension tools inactive when the branch recorded its tools before they were registered, such as tools from extensions installed after the session started. Extension tools the branch never added or removed are now active unless they are registered with defaultActive: false (#11062, #11075)
  • Fixed sessions breaking after recovery from a response cut off at the output limit: the truncated tool call was omitted but its tool results were kept, so providers rejected every later request (#11227, #11233 by @​petrroll)
  • Fixed the grep tool following RIPGREP_CONFIG_PATH, where options such as --fixed-strings silently changed regex searches into literal ones. The tool now runs rg --no-config (#11203, #11230 by @​petrroll)
  • Fixed Windows shell detection rejecting runnable Microsoft Store shell aliases (#9504 by @​petrroll)
  • Fixed Windows shell detection missing PowerShell outside PATH and the legacy WSL bash.exe launcher when Windows is not installed in C:\Windows. pi now checks %ProgramFiles%\PowerShell\7, %SystemRoot%\System32\WindowsPowerShell\v1.0, and %SystemRoot% (#9501 by @​petrroll)
  • Fixed GitHub Copilot sessions with large request bodies, such as many images, failing with HTTP 413 failed to parse request instead of compacting and retrying (#11016 by @​petrroll)
  • Fixed the openai-codex provider offering gpt-5.5 and gpt-5.3-codex-spark, which always fail for ChatGPT accounts (#11173 by @​lucasmeijer)
  • Fixed whitespace-only tool output (for example a bare \r\n from bash) making OpenAI Completions, OpenAI Responses, and Google requests fail with a 400 (#8720)
  • Fixed automatic retry not triggering for more gateway upstream failures, stream disconnected before completion errors relayed by Codex CLI proxies, and transient Google Vertex OAuth token refresh failures, and retrying errors because of digits inside request ids or byte counts (#10920, #11057, #10996)
  • Fixed OpenAI Responses models losing the prompt cache on every deferred tool load after a tool was removed (#10940)

... (truncated)

Changelog

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

[1.4.0] - 2026-10-21

Added

  • Added AgentOptions.identity and Agent.identity (a pi-ai ClientIdentity) to set the User-Agent and provider attribution of agent loop requests.

[1.3.0] - 2026-10-15

[1.2.0] - 2026-10-12

[1.1.0] - 2026-10-07

Added

  • Added durationMs to tool result messages, AgentToolCallOutcome, and tool_execution_end events: how long execute() took, measured with a monotonic clock and excluding hooks. Calls that did not run have none (#10549)

Changed

  • streamProxy() returns an AssistantMessageEventStream, so proxied responses get durationMs like direct ones
Commits
  • 4a08025 Release v1.4.0
  • 04a93ba fix(ai,agent,coding-agent,durable): client identity follow-ups
  • adc5fa9 feat(ai,agent,coding-agent): move client identity and provider attribution in...
  • ae7b16d Add [Unreleased] section for next cycle
  • 71023ae Release v1.3.0
  • f13c00f fix: pin internal dependencies to exact versions
  • d547949 Add [Unreleased] section for next cycle
  • 06a4669 Release v1.2.0
  • 75a9972 Add [Unreleased] section for next cycle
  • abe508e Release v1.1.0
  • Additional commits viewable in compare view

Updates @earendil-works/pi-ai from 1.0.4 to 1.4.0

Release notes

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

v1.4.0

New Features

  • Image input for classifiers: codemode models.classify() accepts images for TypeSafe's Jev and Cloudflare's Clef models on typesafe, cloudflare-workers-ai, and OpenRouter. See Use classifier models and Codemode.
  • Models Configuration reference: every provider, model, model override, and compatibility field of models.json, generated from its schema. See Models Configuration.
  • Summaries without a fixed output cap: compaction and branch summaries use the model's output limit, so long reasoning no longer makes them fail. See Compaction.
  • Codemode waits for a free worker: parallel scripts and in-process subagents queue instead of failing, and PI_CODEMODE_MAX_WORKERS raises the limit. See Codemode limits.
  • Rex terminal support: OSC 8 hyperlinks, truecolor, and inline images.

Added

  • Added a Models Configuration reference generated from the models.json schema, listing all provider, model, model override, and compatibility fields (#10790)
  • Codemode models.classify() now accepts images for TypeSafe's Jev and Cloudflare's Clef models on typesafe, cloudflare-workers-ai, and OpenRouter, and lists Clef Omni and Jev 1.14 on Workers AI.
  • Provider-level compat in models.json now also applies to classifier models, with the System One fields imageInput and sendImageOptInHeader for proxies that serve another service's classifiers. Extension classifier models accept compat too.
  • Added MiniMax-M3.1-Flash to the minimax and minimax-cn providers, with thinking levels low through max (#11121)
  • Added support for the Rex terminal: OSC 8 hyperlinks, truecolor, and inline images (#11131, #11150 by @​petrroll, #11183 by @​nihaals)

Changed

  • Provider attribution headers now come from pi-ai's client identity. Extensions' before_provider_headers handlers no longer see the OpenRouter, NVIDIA NIM, and OpenCode attribution headers; returning null for one still removes it. Cloudflare requests send pi's detailed User-Agent instead of pi-coding-agent, as do GitHub release checks for tool downloads, and OpenCode requests send x-opencode-client whenever attribution is enabled, not only with a session.
  • generateSummary() and generateSummaryWithUsage() now ignore their reserveTokens parameter. Summary requests use the model's output limit instead.
  • Changed the default GitHub Copilot model from gpt-5.4, which Copilot retired, to gpt-6.1-sol.
  • Changed the default NVIDIA model to nvidia/nemotron-3.5-super-vl-120b-a12b (#10910 by @​cv)
  • Changed the default Xiaomi model to mimo-v2.6-pro for the xiaomi and Xiaomi Token Plan providers, since mimo-v2.5-pro left the catalog.
  • Grok 4.3 and Grok 4.5 on the xai provider now offer the xhigh thinking level.
  • Sign in with ChatGPT: ChatGPT Business workspace usage-limit errors are not retried and tell the user to ask their workspace admin to increase the limit.

Fixed

  • Fixed compaction and branch summaries failing with "generation hit the token cap" when reasoning used most of the fixed summary output limit. Summaries now use the model's output limit, and compaction.reserveTokens only controls when compaction starts (#9512, #9075).
  • Fixed models.schema.json missing descriptions for provider and model fields, so editors showed no hints for them (#10790)
  • Fixed pi update failing with "Managed install marker is missing or invalid" when managed-install.json starts with a UTF-8 BOM, which Windows PowerShell 5.1 adds when it rewrites the file.
  • Fixed HTML export showing literal asterisks for Markdown bold and italic next to CJK punctuation (#3353, #10154)
  • Fixed the terminal staying in mouse-tracking, focus-reporting, Kitty keyboard, and alternate-screen modes when pi exits without its normal terminal teardown, which flooded the shell prompt with escape sequences (#11170)
  • Fixed concurrent extension select/confirm/input/editor dialogs and inline custom() components in interactive mode: a second dialog replaced the first and the first promise never settled; closing the visible dialog now shows the previous one again (#11166, #9909)
  • Fixed pasting in the shell hanging after copying text in pi and suspending it with Ctrl+Z on Linux: the background wl-copy/xclip/xsel process that keeps serving the clipboard was suspended along with pi (#11179)
  • Fixed codemode scripts failing immediately when both codemode workers are busy, for example with parallel codemode calls or in-process subagents. Scripts now wait up to 60 seconds for a free worker, and PI_CODEMODE_MAX_WORKERS raises the limit of two workers (#11184)
  • Fixed extensions failing to load when importing @earendil-works/pi-ai/models (e.g. for clampThinkingLevel) by exposing the subpath through the extension loader aliases and virtual modules (#11156)
  • Fixed mcp.json files that start with a UTF-8 BOM failing to parse, which skipped all their MCP servers and made pi mcp add/pi mcp remove fail (#11191)
  • Fixed /compact <instructions> ignoring the instructions when summarizing the start of a turn that compaction splits. When the split turn was the only new content since the last compaction, the instructions were ignored entirely (#11058)
  • Fixed resumed sessions and /tree navigation leaving extension tools inactive when the branch recorded its tools before they were registered, such as tools from extensions installed after the session started. Extension tools the branch never added or removed are now active unless they are registered with defaultActive: false (#11062, #11075)
  • Fixed sessions breaking after recovery from a response cut off at the output limit: the truncated tool call was omitted but its tool results were kept, so providers rejected every later request (#11227, #11233 by @​petrroll)
  • Fixed the grep tool following RIPGREP_CONFIG_PATH, where options such as --fixed-strings silently changed regex searches into literal ones. The tool now runs rg --no-config (#11203, #11230 by @​petrroll)
  • Fixed Windows shell detection rejecting runnable Microsoft Store shell aliases (#9504 by @​petrroll)
  • Fixed Windows shell detection missing PowerShell outside PATH and the legacy WSL bash.exe launcher when Windows is not installed in C:\Windows. pi now checks %ProgramFiles%\PowerShell\7, %SystemRoot%\System32\WindowsPowerShell\v1.0, and %SystemRoot% (#9501 by @​petrroll)
  • Fixed GitHub Copilot sessions with large request bodies, such as many images, failing with HTTP 413 failed to parse request instead of compacting and retrying (#11016 by @​petrroll)
  • Fixed the openai-codex provider offering gpt-5.5 and gpt-5.3-codex-spark, which always fail for ChatGPT accounts (#11173 by @​lucasmeijer)
  • Fixed whitespace-only tool output (for example a bare \r\n from bash) making OpenAI Completions, OpenAI Responses, and Google requests fail with a 400 (#8720)
  • Fixed automatic retry not triggering for more gateway upstream failures, stream disconnected before completion errors relayed by Codex CLI proxies, and transient Google Vertex OAuth token refresh failures, and retrying errors because of digits inside request ids or byte counts (#10920, #11057, #10996)
  • Fixed OpenAI Responses models losing the prompt cache on every deferred tool load after a tool was removed (#10940)

... (truncated)

Changelog

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

[1.4.0] - 2026-10-21

Breaking Changes

  • Renamed provider request option telemetryContext to telemetry?: TelemetrySpan, without a compatibility alias. Pass a parent span, not an adapter.
  • The default User-Agent is now pi/<version> (<platform>; <runtime>; <arch>) instead of pi (<platform> <release>; <arch>), and @earendil-works/pi-ai/utils/pi-user-agent (getPiUserAgent()) is removed; use formatUserAgent().
  • resolveTranscriptTools() now takes a TranscriptToolSupport ("none", "additions", or "changes") instead of a boolean, and TranscriptTools.anchorsAdditions is replaced by foldedSystemMessages, the number of leading system messages folded into requestTools (#10940)

Added

  • Added client identity configuration: an identity request option and createModels({ identity }) default choose the User-Agent ("detailed" with a version, "short", or custom) and provider attribution headers for OpenRouter, NVIDIA NIM, and OpenCode from attribution: { name, url, categories? }. withClientIdentity() applies an identity to a Models or MutableModels a library receives from its host. formatUserAgent(), getIdentityHeaders(), getOpenCodeSessionHeaders(), mergeClientIdentity(), PI_ATTRIBUTION, and PI_AI_VERSION are exported.
  • Bedrock, OpenRouter image generation, pi-messages, and classifier requests now send pi's User-Agent too.
  • Models requests with a sessionId to custom providers pointing at OpenCode (opencode.ai) now send the x-opencode-session header too, like the built-in OpenCode providers.
  • Added AI_TELEMETRY_SCHEMA and opt-in pi.ai.request/pi.ai.poll tracing around Models requests, with content-free first-event, block-size, and final usage attributes, plus duration, token, and USD cost metrics through telemetry.metrics.
  • Failed model request spans report provider_error status with up to 500 error-message characters; cancelled requests keep ok status with stop: "aborted".
  • Added MiniMax-M3.1-Flash to the minimax and minimax-cn providers, with thinking levels low through max sent as output_config.effort. Thinking cannot be turned off for this model. New MiniMax models from models.dev now appear without a manual allowlist entry; only the older M2, M2.1, M2.5, and M2.5-highspeed models stay hidden (#11121)
  • Sign in with ChatGPT: ChatGPT Business workspace usage-limit errors are not retried and tell the user to ask their workspace admin to increase the limit.
  • Added image input to System One classifiers: ClassifierContext.images now works with Jev on typesafe (experimental there, opted in with the TypeSafe-Danger-Zone-Images header) and cloudflare-workers-ai, with Clef on cloudflare-workers-ai, and with OpenRouter decision models whose catalog lists image input. Each service gets its own wire form: TypeSafe assets, Clef images data URLs, or OpenRouter image_url parts in the state.
  • Added compat to System One classifier models (SystemOneCompat, with imageInput and sendImageOptInHeader). Built-in catalog entries set it explicitly; models without it detect the form from the provider, baseUrl, and model ID.
  • Added the @cf/cloudflare/clef-omni and typesafe/jev-1.14.0 classifier models to cloudflare-workers-ai.

Changed

  • Grok 4.3 and Grok 4.5 on the xai provider now offer the xhigh thinking level, matching the reasoning efforts xAI supports for these models.

Fixed

  • Fixed Cloudflare Workers AI classifier catalog data: Clef Flash now costs $0.038 per million input tokens with a 24,576-token context window, and Jev costs $0.042 per million input tokens instead of being listed as free.
  • Fixed whitespace-only tool output (for example a bare \r\n from bash) being sent as-is to OpenAI Completions, OpenAI Responses, and Google providers; it now uses the same placeholder as empty output, since some providers reject whitespace-only tool content with a 400 (#8720)
  • Fixed automatic retry not triggering for gateway upstream failures such as upstream_error: Upstream request failed, upstream_stream_read_error, and Upstream HTTP/2 stream failed (#10920)
  • Fixed automatic retry not triggering when the Google Vertex OAuth token refresh fails with a transient network error such as request to https://oauth2.googleapis.com/token failed, reason: (#10996)
  • Fixed automatic retry not triggering for stream disconnected before completion errors relayed by proxies that wrap the Codex CLI (#11057)
  • Fixed automatic retry treating digits inside request ids or other numbers (for example req_011CU503xyz or 5242880 bytes) as retryable HTTP status codes (#11057)
  • Fixed OpenAI Responses deferred tool loads rewriting the top-level tool list, and losing the prompt cache, on every load after a tool removal. Models with additional_tools now declare all tools in additional_tools items, starting with one at the head of the input, so removals (announced as text) and redefinitions no longer rewrite the prefix. Tool search and Kimi tool messages rewrite the top-level tools once per removal or redeclaration and keep later loads anchored (#10940)
  • Fixed GitHub Copilot requests whose body exceeds Copilot's size limit (HTTP 413 failed to parse request, for example sessions with many large images) failing instead of being detected as context overflow. Any HTTP 413 now counts as context overflow, so callers can compact and retry (#11016 by @​petrroll)
  • Fixed the openai-codex provider listing gpt-5.5 and gpt-5.3-codex-spark, which the Codex backend rejects for ChatGPT accounts. Both models are removed (#11173 by @​lucasmeijer)

[1.3.0] - 2026-10-15

Breaking Changes

  • Removed AssistantMessageFrame, AssistantMessageFrameEncoder, and reduceAssistantMessageFrames(). They were only used by the removed experimental agent harness.

Added

  • Added cache-preserving thinking level changes for GPT-6 models on the openai provider: with an API key, the level is sent as configuration_update input items instead of changing reasoning.effort, controlled by compat.supportsMidConvoEffort (#10853)

Changed

  • Changed the kimi-coding provider to use OpenAI Chat Completions at https://api.kimi.com/coding/v1, the protocol used by the official Kimi Code client. K3, K3-256K, and Kimi For Coding now accept tools added mid-conversation without invalidating the prompt cache. models.json overrides of the kimi-coding base URL must now include /v1 (#10720)

... (truncated)

Commits
  • 4a08025 Release v1.4.0
  • 18e56a0 fix(ai): expect compat on OpenRouter decision models in catalog test
  • f76b248 docs(ai,tui,coding-agent): audit changelogs since v1.3.0
  • 7f225f2 feat(ai,coding-agent): image input for System One classifiers
  • 04a93ba fix(ai,agent,coding-agent,durable): client identity follow-ups
  • adc5fa9 feat(ai,agent,coding-agent): move client identity and provider attribution in...
  • 6e491cf fix(ai): match retryable status codes only as standalone numbers
  • 29057ec fix(ai): retry Codex CLI stream disconnect errors relayed by proxies
  • cedefc5 fix(ai): handle ChatGPT Business workspace usage limit errors
  • e5fe977 fix(ai,coding-agent): drop models retired upstream
  • Additional commits viewable in compare view

Updates @earendil-works/pi-coding-agent from 1.0.4 to 1.4.0

Release notes

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

v1.4.0

New Features

  • Image input for classifiers: codemode models.classify() accepts images for TypeSafe's Jev and Cloudflare's Clef models on typesafe, cloudflare-workers-ai, and OpenRouter. See Use classifier models and Codemode.
  • Models Configuration reference: every provider, model, model override, and compatibility field of models.json, generated from its schema. See Models Configuration.
  • Summaries without a fixed output cap: compaction and branch summaries use the model's output limit, so long reasoning no longer makes them fail. See Compaction.
  • Codemode waits for a free worker: parallel scripts and in-process subagents queue instead of failing, and PI_CODEMODE_MAX_WORKERS raises the limit. See Codemode limits.
  • Rex terminal support: OSC 8 hyperlinks, truecolor, and inline images.

Added

  • Added a Models Configuration reference generated from the models.json schema, listing all provider, model, model override, and compatibility fields (#10790)
  • Codemode models.classify() now accepts images for TypeSafe's Jev and Cloudflare's Clef models on typesafe, cloudflare-workers-ai, and OpenRouter, and lists Clef Omni and Jev 1.14 on Workers AI.
  • Provider-level compat in models.json now also applies to classifier models, with the System One fields imageInput and sendImageOptInHeader for proxies that serve another service's classifiers. Extension classifier models accept compat too.
  • Added MiniMax-M3.1-Flash to the minimax and minimax-cn providers, with thinking levels low through max (#11121)
  • Added support for the Rex terminal: OSC 8 hyperlinks, truecolor, and inline images (#11131, #11150 by @​petrroll, #11183 by @​nihaals)

Changed

  • Provider attribution headers now come from pi-ai's client identity. Extensions' before_provider_headers handlers no longer see the OpenRouter, NVIDIA NIM, and OpenCode attribution headers; returning null for one still removes it. Cloudflare requests send pi's detailed User-Agent instead of pi-coding-agent, as do GitHub release checks for tool downloads, and OpenCode requests send x-opencode-client whenever attribution is enabled, not only with a session.
  • generateSummary() and generateSummaryWithUsage() now ignore their reserveTokens parameter. Summary requests use the model's output limit instead.
  • Changed the default GitHub Copilot model from gpt-5.4, which Copilot retired, to gpt-6.1-sol.
  • Changed the default NVIDIA model to nvidia/nemotron-3.5-super-vl-120b-a12b (#10910 by @​cv)
  • Changed the default Xiaomi model to mimo-v2.6-pro for the xiaomi and Xiaomi Token Plan providers, since mimo-v2.5-pro left the catalog.
  • Grok 4.3 and Grok 4.5 on the xai provider now offer the xhigh thinking level.
  • Sign in with ChatGPT: ChatGPT Business workspace usage-limit errors are not retried and tell the user to ask their workspace admin to increase the limit.

Fixed

  • Fixed compaction and branch summaries failing with "generation hit the token cap" when reasoning used most of the fixed summary output limit. Summaries now use the model's output limit, and compaction.reserveTokens only controls when compaction starts (#9512, #9075).
  • Fixed models.schema.json missing descriptions for provider and model fields, so editors showed no hints for them (#10790)
  • Fixed pi update failing with "Managed install marker is missing or invalid" when managed-install.json starts with a UTF-8 BOM, which Windows PowerShell 5.1 adds when it rewrites the file.
  • Fixed HTML export showing literal asterisks for Markdown bold and italic next to CJK punctuation (#3353, #10154)
  • Fixed the terminal staying in mouse-tracking, focus-reporting, Kitty keyboard, and alternate-screen modes when pi exits without its normal terminal teardown, which flooded the shell prompt with escape sequences (#11170)
  • Fixed concurrent extension select/confirm/input/editor dialogs and inline custom() components in interactive mode: a second dialog replaced the first and the first promise never settled; closing the visible dialog now shows the previous one again (#11166, #9909)
  • Fixed pasting in the shell hanging after copying text in pi and suspending it with Ctrl+Z on Linux: the background wl-copy/xclip/xsel process that keeps serving the clipboard was suspended along with pi (#11179)
  • Fixed codemode scripts failing immediately when both codemode workers are busy, for example with parallel codemode calls or in-process subagents. Scripts now wait up to 60 seconds for a free worker, and PI_CODEMODE_MAX_WORKERS raises the limit of two workers (#11184)
  • Fixed extensions failing to load when importing @earendil-works/pi-ai/models (e.g. for clampThinkingLevel) by exposing the subpath through the extension loader aliases and virtual modules (#11156)
  • Fixed mcp.json files that start with a UTF-8 BOM failing to parse, which skipped all their MCP servers and made pi mcp add/pi mcp remove fail (#11191)
  • Fixed /compact <instructions> ignoring the instructions when summarizing the start of a turn that compaction splits. When the split turn was the only new content since the last compaction, the instructions were ignored entirely (#11058)
  • Fixed resumed sessions and /tree navigation leaving extension tools inactive when the branch recorded its tools before they were registered, such as tools from extensions installed after the session started. Extension tools the branch never added or removed are now active unless they are registered with defaultActive: false (#11062, #11075)
  • Fixed sessions breaking after recovery from a response cut off at the output limit: the truncated tool call was omitted but its tool results were kept, so providers rejected every later request (#11227, #11233 by @​petrroll)
  • Fixed the grep tool following RIPGREP_CONFIG_PATH, where options such as --fixed-strings silently changed regex searches into literal ones. The tool now runs rg --no-config (#11203, #11230 by @​petrroll)
  • Fixed Windows shell detection rejecting runnable Microsoft Store shell aliases (#9504 by @​petrroll)
  • Fixed Windows shell detection missing PowerShell outside PATH and the legacy WSL bash.exe launcher when Windows is not installed in C:\Windows. pi now checks %ProgramFiles%\PowerShell\7, %SystemRoot%\System32\WindowsPowerShell\v1.0, and %SystemRoot% (#9501 by @​petrroll)
  • Fixed GitHub Copilot sessions with large request bodies, such as many images, failing with HTTP 413 failed to parse request instead of compacting and retrying (#11016 by @​petrroll)
  • Fixed the openai-codex provider offering gpt-5.5 and gpt-5.3-codex-spark, which always fail for ChatGPT accounts (#11173 by @​lucasmeijer)
  • Fixed whitespace-only tool output (for example a bare \r\n from bash) making OpenAI Completions, OpenAI Responses, and Google requests fail with a 400 (#8720)
  • Fixed automatic retry not triggering for more gateway upstream failures, stream disconnected before completion errors relayed by Codex CLI proxies, and transient Google Vertex OAuth token refresh failures, and retrying errors because of digits inside request ids or byte counts (#10920, #11057, #10996)
  • Fixed OpenAI Responses models losing the prompt cache on every deferred tool load after a tool was removed (#10940)

... (truncated)

Changelog

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

[1.4.0] - 2026-10-21

New Features

  • Image input for classifiers: codemode models.classify() accepts images for TypeSafe's Jev and Cloudflare's Clef models on typesafe, cloudflare-workers-ai, and OpenRouter. See Use classifier models and Codemode.
  • Models Configuration reference: every provider, model, model override, and compatibility field of models.json, generated from its schema. See Models Configuration.
  • Summaries without a fixed output cap: compaction and branch summaries use the model's output limit, so long reasoning no longer makes them fail. See Compaction.
  • Codemode waits for a free worker: parallel scripts and in-process subagents queue instead of failing, and PI_CODEMODE_MAX_WORKERS raises the limit. See Codemode limits.
  • Rex terminal support: OSC 8 hyperlinks, truecolor, and inline images.

Added

  • Added a Models Configuration reference generated from the models.json schema, listing all provider, model, model override, and compatibility fields (#10790)
  • Codemode models.classify() now accepts images for TypeSafe's Jev and Cloudflare's Clef models on typesafe, cloudflare-workers-ai, and OpenRouter, and lists Clef Omni and Jev 1.14 on Workers AI.
  • Provider-level compat in models.json now also applies to classifier models, with the System One fields imageInput and sendImageOptInHeader for proxies that serve another service's classifiers. Extension classifier models accept compat too.
  • Added MiniMax-M3.1-Flash to the minimax and minimax-cn providers, with thinking levels low through max (#11121)
  • Added support for the Rex terminal: OSC 8 hyperlinks, truecolor, and inline images (#11131, #11150 by @​petrroll, #11183 by @​nihaals)

Changed

  • Provider attribution headers now come from pi-ai's client identity. Extensions' before_provider_headers handlers no longer see the OpenRouter, NVIDIA NIM, and OpenCode attribution headers; returning null for one still removes it. Cloudflare requests send pi's detailed User-Agent instead of pi-coding-agent, as do GitHub release checks for tool downloads, and OpenCode requests send x-opencode-client whenever attribution is enabled, not only with a session.
  • generateSummary() and generateSummaryWithUsage() now ignore their reserveTokens parameter. Summary requests use the model's output limit instead.
  • Changed the default GitHub Copilot model from gpt-5.4, which Copilot retired, to gpt-6.1-sol.
  • Changed the default NVIDIA model to nvidia/nemotron-3.5-super-vl-120b-a12b (#10910 by @​cv)
  • Changed the default Xiaomi model to mimo-v2.6-pro for the xiaomi and Xiaomi Token Plan providers, since ...

    Description has been truncated