#271 build(deps-dev): bump @earendil-works/pi-ai from 1.4.0 to 1.5.0

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

v1.5.0

New Features

• Extension update changelogs: see what changed in installed extension packages on the next fresh launch after an update. Package authors can choose the changelog path, and collapseChangelog condenses the notices. See Show a changelog.
• Faster streaming: large tool calls are parsed incrementally, and code-heavy answers and tool rows reuse highlighting and rendered Markdown instead of repeating the work on every update. See Keep rendering responsive.
• Custom self-update commands: use PI_SELF_UPDATE_COMMAND or selfUpdateCommand to update pi through a wrapper or another package manager. See Custom update command.
• GPT-6.1 Terra: available through OpenAI, Azure OpenAI Responses, and OpenAI Codex, with tool search, mid-conversation thinking-level changes, and thinking off. Codex offers a 500K context window. See Models.

Breaking Changes

• Tool argument validation runs on @earendil-works/pi-schema. TypeBox features outside JSON Schema (Type.Refine(), Type.BigInt(), Type.Undefined(), codecs, Format.Set() formats) no longer apply to tool arguments; see Tool parameter schemas and TypeBox. Plain JSON Schema tools, including MCP tools, now get the same coercion as TypeBox tools, such as converting numeric strings and wrapping a single value into an array. Validation failures the model sees list pi-schema's messages (- path: missing, - limit: expected number, got string) instead of TypeBox's (must have required properties path, must be number).

Added

• Extension packages can now show their changelog after an update. Pi reads pi.changelogPath from the package's package.json, or CHANGELOG.md in the package root, and on the next fresh launch shows entries newer than the last seen version under "Extension Updates". The collapseChangelog setting condenses this to one line per package (#5958, #8790)
• pi.exec() accepts a maxBuffer option that limits stdout and stderr combined, and its result has a truncated field that is true when output exceeded the limit (#11360)
• Device-code login (for example GitHub Copilot) now opens the verification page and copies the code when you press Enter. Providers can turn either action off with openBrowserOnConfirm: false or copyCodeOnConfirm: false (#9282, #9301)
• pi update can update Pi through a wrapper or another package manager. Set PI_SELF_UPDATE_COMMAND (for example mise use -g npm:{packageName}@{version}) or the global selfUpdateCommand setting; pi update runs it when pi.dev reports a newer release and fills {packageName}, {version}, and {installSpec} from that release. See Custom update command (#7756, #5607)
• Extensions can format the user's configured keybindings with keyText() and keyHint() from the tool render context and the message and entry renderer options. Importing these functions from @earendil-works/pi-coding-agent can resolve the extension's own copy of the package, which does not see pi's keybindings, so hints such as keyHint("app.tools.expand", "to expand") rendered without the key. The docs now recommend the injected functions (#4748)
• Added persisted session-entry messageId and ISO timestamp to MarkdownTransformContext. They are available when rendering saved entries and undefined for live rendering (#7952 by @​vipentti)
• Added a blocked option to inline ctx.ui.custom() components so approval prompts and other custom dialogs can report that pi is waiting for user input. Overlays ignore the option. See Custom screens and overlays (#11428)
• Added Usage.cost.totalFromProvider to distinguish billed totals from catalog estimates in SDK and extension usage data; combined usage is marked provider-reported only when every part is (#11178)
• Added concrete responseModel metadata to messages from pi-messages providers such as Radius, including when a virtual model is requested. See AssistantMessage (#11265)
• Added GPT-6.1 Terra for OpenAI, Azure OpenAI Responses, and OpenAI Codex, with tool search and mid-conversation thinking-level changes. It supports thinking off; Codex offers a 500K context window

Changed

• Extensions keep importing Type, Static and TSchema from @earendil-works/pi-ai: Pi maps that import to pi-ai's compat entry plus the TypeBox it bundles, now that pi-ai itself no longer re-exports TypeBox, and its StringEnum there stays a TypeBox TUnsafe<T>. The built-in tool factories (createReadTool() and the others) return TypeBoxAgentTool<typeof schema>, which keeps params typed for TypeBox.
• Tightened system prompt
• pi update for installs from the pi.dev installer no longer passes --min-release-age=0 to npm ci. The release lockfile pins every package, so the flag had no effect, and security scanners that block it stopped the update (#11262)
• /model and /scoped-models now show a model's name next to its ID when the name adds words the ID lacks, such as a renamed models.json override (#5916, #11347)
• MCP OAuth sign-in now uses pi's Client ID Metadata Document by default when the authorization server supports it for public clients, and registers a client dynamically otherwise, like Codex, Claude Code, and opencode. Clients registered before stay in use while their redirect URI matches. The new default oauth.clientRegistration: "auto" registers when clientName or a non-default callbackUrl is set; "dcr" always registers. pi mcp add --oauth-client-registration sets the mode (#11426)
• Changed the default OpenAI model from gpt-5.5 to gpt-6.1-sol, including after ChatGPT sign-in when no model is selected (#11442)
• Updated the built-in model catalog to models.dev v2. Realtime and image-only models are no longer offered as chat models; newer OpenAI and Google chat models are included

Fixed

• Updated glob matching to prevent denial of service from amplified glob patterns.
• Fixed a saved "Do not trust" decision being ignored for projects without trust-requiring resources, for example a folder with only AGENTS.md. pi auto-trusted such projects, so ctx.isProjectTrusted() returned true and package commands treated them as trusted. A saved decision in trust.json now takes precedence; auto-trust applies only when no decision is saved (#10947)
• Fixed Shift+Enter queueing a follow-up instead of inserting a newline in Apple Terminal setups that send ESC + Return. pi now checks the local Shift key state for that sequence, as it already did for plain Return; Alt+Enter without Shift still queues a follow-up (#11559)
• Fixed the working status (OSC 7501) disappearing in Rex and iTerm2 during runs in regular TUI mode. Rendered messages wrote OSC 133 prompt markers to the terminal, which the terminal treats as a new shell prompt; regular mode no longer writes them (#11519)
• Fixed compaction, branch summaries, and bug-report summaries in SDK sessions passing the stored OAuth token back to the model runtime as an explicit API key. Provider auth that treats explicit keys differently from stored OAuth now sees the OAuth login, as normal prompts do (#11520)
• Fixed a redundant system prompt update (tools, rules) when an extension set the same active tools in a different order, for example a reversed pi.setActiveTools() list. Tools that stay active now keep their order and newly activated tools are appended (#11495)
• Fixed pi.exec() crashing pi with RangeError: Invalid string length when a command printed more output than fits in a string. The default output cap is the smaller of 256 MiB and the runtime string limit; past the cap, the command is terminated and the result has truncated: true and a nonzero exit code (#11360)
• Fixed pi.exec() never returning when a command ignored SIGTERM after a timeout or abort. pi now sends SIGKILL 5 seconds later, as intended
• Fixed pi install and pi remove adding ever deeper nested entries to the npm package-lock.json when the agent directory is reached through a symlink, such as ~/.pi linked into a dotfiles repo. pi now passes the resolved real path to npm (#11358)
• MCP sign-in now rejects authorization endpoints and other OAuth metadata URLs that are not http: or https:. Before, a malicious MCP server could supply a file: or custom protocol URL, which pi passed to the platform URL handler.
• Automatic fd and rg downloads no longer fetch x86-64 binaries on ARM32 and other architectures without a prebuilt release. pi now warns and recommends installing the tool with the system package manager (#11209)
• Fixed /model search ranking letters scattered over an earlier part of an entry above a real match, for example opus listing gpt-oss-120b and claude-sonnet-4.5 before claude-opus-4.1 (#11220, #11296)
• Fixed /resume search matching scattered letters anywhere in session messages and IDs, for example 1024 matching inside a session UUID. Session names and working directories still match fuzzily; IDs and message text now match only as exact substrings (#11220, #11024, #11296)

... (truncated)

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

[1.5.0] - 2026-11-02

Breaking Changes

• The main entry no longer re-exports TypeBox (Type, Static, TSchema), and typebox is no longer a dependency. Tool.parameters is any JSON Schema object (Tool<TParameters extends object>): @earendil-works/pi-schema's builders, which also type the arguments through pi-schema's Static, TypeBox schemas, or plain objects. validateToolCall()/validateToolArguments() validate with pi-schema (compile(schema, { coerce: true }).parse()): every schema gets the same coercion, the superset of TypeBox's Value.Convert rules (which only applied to TypeBox-built schemas) and pi-ai's own, so plain JSON Schema tools (MCP tools) now also get, for example, null to "null" for a required string, "3.5" to 3 for an integer and a single value wrapped into an array. The error text lists pi-schema's messages (- edits.0.oldText: missing, - limit: expected number, got string) instead of TypeBox's. StringEnum() returns a pi-schema Schema<T> with the same JSON ({ type: "string", enum }). The model and compat schemas (providers/model-schema, providers/compat-schema) are built with pi-schema, with the same JSON Schema, and their types come from pi-schema's Static; ProviderCompat is exported. Migration:

  // Before
  import { Type, type Static, StringEnum } from "@earendil-works/pi-ai";
  const params = Type.Object({ path: Type.String(), mode: StringEnum(["a", "b"]) });
  type Params = Static<typeof params>;
  // After: pi-schema builders (closed objects; pass { open: true } to allow other properties)
  import { StringEnum } from "@​earendil-works/pi-ai";
  import { obj, type Static, str } from "@​earendil-works/pi-schema";
  const params = obj({ path: str(), mode: StringEnum(["a", "b"]) });
  type Params = Static<typeof params>;
  // Or keep TypeBox, imported from typebox itself (its schemas are JSON Schema)
  import { Type, type Static } from "typebox";
  

• Tool arguments are validated as JSON Schema only; nothing runs through TypeBox's own validator any more, so TypeBox features outside JSON Schema no longer apply to tool arguments:

  • Type.Refine() refinements are not run: arguments they would reject are accepted.
  • Type.BigInt(), Type.Undefined() and Type.Void() reject every JSON argument (TypeBox converted to them).
  • Codecs (Type.Codec()) do not decode: the tool receives the encoded JSON value.
  • Formats registered with TypeBox's Format.Set() are not checked; the standard formats plus url and json-pointer-uri-fragment are.
  • Property names are names, not regular expressions: "a.b" no longer also converts the argument axb.
  • additionalProperties converts only undeclared properties; TypeBox also converted declared ones with it when an object had more than one property.

• A $ref that names nothing (a missing definition, an external document) rejects only arguments at its place (- t: unresolved reference #/definitions/Missing) instead of failing every call of the tool, as TypeBox's rejection did before.

• appendGrammarToolInputJsonDelta() (api/constrained-sampling) takes the input delta instead of the whole input so far and no longer closes the input; close it with the new closeGrammarToolInputJson() (#9265)

Added

• Added optional openBrowserOnConfirm and copyCodeOnConfirm to device_code auth events and OAuthDeviceCodeInfo. Both default to true; set them to false to stop clients from offering to open the verification page or copy the code (#9282, #9301)
• Added StreamingJsonParser, an incremental, tolerant parser for JSON text that arrives in pieces (each piece is read once; snapshots of the partial value never change once returned), and ToolCallArgumentsStream, which every provider now uses for streamed tool-call arguments; its append() also returns the changes each piece made (JsonChange: a value set at a path, or text appended to a string), for writers that keep their own copy (#9265)
• Added GPT-6.1 Terra to the OpenAI, Azure OpenAI Responses, and OpenAI Codex providers with official pricing ($1 input, $0.05 cached input, $1.25 cache writes, $5 output, long-context tier above 272k), tool search, and mid-conversation effort changes. Unlike GPT-6.1 Sol it supports off (reasoning effort none); Codex serves it with a 500K context window
• Added Usage.cost.totalFromProvider to distinguish provider-reported billed totals from catalog estimates. Missing or false means an estimate; combined usage is marked provider-reported only when every part is (#11178)
• Added responseModel to pi-messages terminal events, preserving the concrete model reported by providers such as Radius when a virtual model is requested (#11265)

Changed

• The faux provider streams partial tool-call arguments, so toolcall_delta partials show growing arguments as real providers do (#9265)
• The built-in model catalog is generated from models.dev's v2 catalog, and its per-provider rules moved from scripts/generate-models.ts into one TypeScript definition per provider under catalog/. Models that models.dev types as realtime or image models (gpt-realtime-2.1, gemini-3.1-flash-live-preview, gemini-3.1-flash-lite-image) are no longer offered as chat models, and models.dev's newer OpenAI and Google chat models (chat-latest, gpt-5.6-cyber, gemini-robotics-er-2-preview) are now included

Fixed

• Fixed Claude models that accept mid-conversation system messages rejecting a session with a 400 (role 'system' must precede an 'assistant' message) when a system update was followed by an assistant reply with nothing to send to Anthropic, such as an empty reply or another model's reasoning-only reply (#11091)
• Fixed Claude models with mid-conversation effort failing with Invalid effort level on accounts whose organization caps effort below high, even at low or medium thinking, by sending a fixed low top-level effort (#10063)
• Fixed streamed tool-call arguments being re-parsed in full on every delta, which made CPU time and memory grow quadratically with the size of a tool call (a 90 KB write on Anthropic peaked at about 140 MB of heap; a 500 KB one took minutes). Every provider and the pi-messages client now read each delta once, and keep the raw argument text and their other stream state (partialJson, partialArgs, index, customInput, streamIndex, Bedrock's encrypted reasoning bytes) off the content blocks, so it no longer reaches partial messages or transcripts of failed streams (#9265)
• Fixed grammar (custom) tool input streaming copying the whole input so far on every delta (#9265)

... (truncated)

• f9a2636 Release v1.5.0
• ddbe02c docs: audit changelogs and add release highlights
• 6536f80 feat(ai,agent,coding-agent): validate tool arguments with pi-schema, drop Typ...
• b4c2e92 fix: remove vulnerable dependency chains
• c719d5b fix(ai): do not retry Zhipu usage limit errors (code 1308) (#11572)
• 2e0f175 feat(ai): refactor provider definitions (#11368)
• 068e972 fix(ai): remove adaptive thinking metadata test that duplicated generator logic
• 44f6851 fix(ai): use Anthropic Messages for OpenRouter ~anthropic latest aliases
• d3398f8 fix(ai): detect LiteLLM ContextWindowExceededError as context overflow (#11494)
• 842c731 fix(ai): fall back on Bedrock strict tool limits
• Additional commits viewable in compare view

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)