build(deps): Bump the pi-packages group in /backend-ts with 2 updates by dependabot[bot] · Pull Request #147 · alexg-g/reznet-ai

dependabot · 2026-03-30T06:49:48Z

Bumps the pi-packages group in /backend-ts with 2 updates: @mariozechner/pi-agent-core and @mariozechner/pi-ai.

Updates @mariozechner/pi-agent-core from 0.55.0 to 0.64.0

Release notes

Sourced from @mariozechner/pi-agent-core's releases.

v0.64.0

New Features

Extensions and SDK callers can attach a prepareArguments hook to any tool definition, letting them normalize or migrate raw model arguments before schema validation. The built-in edit tool uses this to transparently support sessions created with the old single-edit schema. See https://github.com/badlogic/pi-mono/tree/HEAD/packages/agent/blob/HEAD/docs/extensions.md

Extensions can customize the collapsed thinking block label via ctx.ui.setHiddenThinkingLabel(). See https://github.com/badlogic/pi-mono/tree/HEAD/packages/agent/blob/HEAD/examples/extensions/hidden-thinking-label.ts (#2673)

Breaking Changes

ModelRegistry no longer has a public constructor. SDK callers and tests must use ModelRegistry.create(authStorage, modelsJsonPath?) for file-backed registries or ModelRegistry.inMemory(authStorage) for built-in-only registries. Direct new ModelRegistry(...) calls no longer compile.

Added

Added ToolDefinition.prepareArguments hook to prepare raw tool call arguments before schema validation, enabling compatibility shims for resumed sessions with outdated tool schemas

Built-in edit tool now uses prepareArguments to silently fold legacy top-level oldText/newText into edits[] when resuming old sessions

Added ctx.ui.setHiddenThinkingLabel() so extensions can customize the collapsed thinking label in interactive mode, with a no-op in RPC mode and a runnable example extension in examples/extensions/hidden-thinking-label.ts (#2673)

Fixed

Fixed extension-queued user messages to refresh the interactive pending-message list so messages submitted while a turn is active are no longer silently dropped (#2674 by @mrexodia)

Fixed monorepo tsconfig.json path mappings to resolve @mariozechner/pi-ai subpath exports to source files in development checkouts (#2625 by @ferologics)

Fixed TUI cell size response handling to consume only exact CSI 6 ; height ; width t replies, so bare Escape is no longer swallowed while waiting for terminal image metadata (#2661)

Fixed Kitty keyboard protocol keypad functional keys to normalize to logical digits, symbols, and navigation keys, so numpad input in terminals such as iTerm2 no longer inserts Private Use Area gibberish or gets ignored (#2650)

v0.63.2

New Features

Extension handlers can now use ctx.signal to forward cancellation into nested model calls, fetch(), and other abort-aware work. See https://github.com/badlogic/pi-mono/tree/HEAD/packages/agent/blob/HEAD/docs/extensions.md#ctxsignal (#2660)

Built-in edit tool input now uses edits[] as the only replacement shape, reducing invalid tool calls caused by mixed single-edit and multi-edit schemas (#2639)

Large multi-edit results no longer trigger full-screen redraws in the interactive TUI when the final diff is rendered (#2664)

Added

Added ctx.signal to ExtensionContext and wired it to the active agent turn so extension handlers can forward cancellation into nested model calls, fetch(), and other abort-aware work (#2660)

Fixed

Fixed built-in edit tool input to use edits[] as the only replacement shape, eliminating the mixed single-edit and multi-edit modes that caused repeated invalid tool calls and retries (#2639)

Fixed edit tool TUI rendering to defer large multi-edit diffs to the settled result, avoiding full-screen redraws when the tool completes (#2664)

v0.63.1

Added

Added gemini-3.1-pro-preview-customtools model availability for the google-vertex provider (#2610 by @gordonhwc)

Fixed

Documented tool_call input mutation as supported extension API behavior, clarified that post-mutation inputs are not re-validated, and added regression coverage for executing mutated tool arguments (#2611)

... (truncated)

Changelog

Sourced from @mariozechner/pi-agent-core's changelog.

[0.64.0] - 2026-03-29

Added

Added AgentTool.prepareArguments hook to prepare raw tool call arguments before schema validation, enabling compatibility shims for resumed sessions with outdated tool schemas

[0.63.2] - 2026-03-29

Added

Added Agent.signal to expose the active abort signal for the current turn, allowing callers to forward cancellation into nested async work (#2660)

[0.63.1] - 2026-03-27

[0.63.0] - 2026-03-27

[0.62.0] - 2026-03-23

[0.61.1] - 2026-03-20

[0.61.0] - 2026-03-20

[0.60.0] - 2026-03-18

[0.59.0] - 2026-03-17

[0.58.4] - 2026-03-16

Fixed

Fixed steering messages to wait until the current assistant message's tool-call batch fully finishes instead of skipping pending tool calls.

[0.58.3] - 2026-03-15

[0.58.2] - 2026-03-15

[0.58.1] - 2026-03-14

[0.58.0] - 2026-03-14

Added

Added beforeToolCall and afterToolCall hooks to AgentOptions and AgentLoopConfig for preflight blocking and post-execution tool result mutation.

Changed

Added configurable tool execution mode to Agent and agentLoop via toolExecution: "parallel" | "sequential", with parallel as the default. Parallel mode preflights tool calls sequentially, executes allowed tools concurrently, and emits final tool results in assistant source order.

[0.57.1] - 2026-03-07

... (truncated)

Commits

d0404a4 Release v0.64.0
b5f425a feat(agent,coding-agent): add prepareArguments hook for pre-validation argume...
567249e Add [Unreleased] section for next cycle
41039e8 Release v0.63.2
7d4faa0 fix: expose abort signal to extensions closes #2660
ec1cf54 Add [Unreleased] section for next cycle
d9727c4 Release v0.63.1
7fe7081 fix(coding-agent): document mutable tool_call input closes #2611
e24a61e Add [Unreleased] section for next cycle
83c8682 Release v0.63.0
Additional commits viewable in compare view

Updates @mariozechner/pi-ai from 0.55.0 to 0.64.0

Release notes

Sourced from @mariozechner/pi-ai's releases.

v0.64.0

New Features

Extensions and SDK callers can attach a prepareArguments hook to any tool definition, letting them normalize or migrate raw model arguments before schema validation. The built-in edit tool uses this to transparently support sessions created with the old single-edit schema. See https://github.com/badlogic/pi-mono/tree/HEAD/packages/ai/blob/HEAD/docs/extensions.md

Extensions can customize the collapsed thinking block label via ctx.ui.setHiddenThinkingLabel(). See https://github.com/badlogic/pi-mono/tree/HEAD/packages/ai/blob/HEAD/examples/extensions/hidden-thinking-label.ts (#2673)

Breaking Changes

ModelRegistry no longer has a public constructor. SDK callers and tests must use ModelRegistry.create(authStorage, modelsJsonPath?) for file-backed registries or ModelRegistry.inMemory(authStorage) for built-in-only registries. Direct new ModelRegistry(...) calls no longer compile.

Added

Added ToolDefinition.prepareArguments hook to prepare raw tool call arguments before schema validation, enabling compatibility shims for resumed sessions with outdated tool schemas

Built-in edit tool now uses prepareArguments to silently fold legacy top-level oldText/newText into edits[] when resuming old sessions

Added ctx.ui.setHiddenThinkingLabel() so extensions can customize the collapsed thinking label in interactive mode, with a no-op in RPC mode and a runnable example extension in examples/extensions/hidden-thinking-label.ts (#2673)

Fixed

Fixed extension-queued user messages to refresh the interactive pending-message list so messages submitted while a turn is active are no longer silently dropped (#2674 by @mrexodia)

Fixed monorepo tsconfig.json path mappings to resolve @mariozechner/pi-ai subpath exports to source files in development checkouts (#2625 by @ferologics)

Fixed TUI cell size response handling to consume only exact CSI 6 ; height ; width t replies, so bare Escape is no longer swallowed while waiting for terminal image metadata (#2661)

Fixed Kitty keyboard protocol keypad functional keys to normalize to logical digits, symbols, and navigation keys, so numpad input in terminals such as iTerm2 no longer inserts Private Use Area gibberish or gets ignored (#2650)

v0.63.2

New Features

Extension handlers can now use ctx.signal to forward cancellation into nested model calls, fetch(), and other abort-aware work. See https://github.com/badlogic/pi-mono/tree/HEAD/packages/ai/blob/HEAD/docs/extensions.md#ctxsignal (#2660)

Built-in edit tool input now uses edits[] as the only replacement shape, reducing invalid tool calls caused by mixed single-edit and multi-edit schemas (#2639)

Large multi-edit results no longer trigger full-screen redraws in the interactive TUI when the final diff is rendered (#2664)

Added

Added ctx.signal to ExtensionContext and wired it to the active agent turn so extension handlers can forward cancellation into nested model calls, fetch(), and other abort-aware work (#2660)

Fixed

Fixed built-in edit tool input to use edits[] as the only replacement shape, eliminating the mixed single-edit and multi-edit modes that caused repeated invalid tool calls and retries (#2639)

Fixed edit tool TUI rendering to defer large multi-edit diffs to the settled result, avoiding full-screen redraws when the tool completes (#2664)

v0.63.1

Added

Added gemini-3.1-pro-preview-customtools model availability for the google-vertex provider (#2610 by @gordonhwc)

Fixed

Documented tool_call input mutation as supported extension API behavior, clarified that post-mutation inputs are not re-validated, and added regression coverage for executing mutated tool arguments (#2611)

... (truncated)

Changelog

Sourced from @mariozechner/pi-ai's changelog.

[0.64.0] - 2026-03-29

Added

Added opt-in faux provider helpers for deterministic tests and scripted demos: registerFauxProvider(), fauxAssistantMessage(), fauxText(), fauxThinking(), and fauxToolCall().

[0.63.2] - 2026-03-29

[0.63.1] - 2026-03-27

Added

Added gemini-3.1-pro-preview-customtools model support for the google-vertex provider (#2610 by @gordonhwc)

Fixed

Fixed context overflow detection to recognize Ollama error responses like prompt too long; exceeded max context length ..., so callers can trigger compaction and retry instead of surfacing the raw overflow error (#2626)

[0.63.0] - 2026-03-27

Breaking Changes

Removed deprecated direct minimax and minimax-cn model IDs, keeping only MiniMax-M2.7 and MiniMax-M2.7-highspeed. Update pinned model IDs to one of those supported direct MiniMax models, or use another provider route that still exposes the older IDs (#2596 by @liyuan97)

Fixed

Fixed GitHub Copilot OpenAI Responses requests to omit the reasoning field entirely when no reasoning effort is requested, avoiding 400 errors from Copilot gpt-5-mini rejecting reasoning: { effort: "none" } during internal summary calls (#2567)

Fixed Google and Vertex cost calculation to subtract cached prompt tokens from billable input tokens instead of double-counting them when providers report cachedContentTokenCount (#2588 by @sparkleMing)

[0.62.0] - 2026-03-23

Added

Added requestMetadata option to BedrockOptions for AWS cost allocation tagging; key-value pairs are forwarded to the Bedrock Converse API requestMetadata field and appear in AWS Cost Explorer split cost allocation data (#2511 by @wjonaskr)

Exported BedrockOptions type from the package root entry point, consistent with other provider option types.

Fixed

Fixed OpenAI Responses replay for foreign tool-call item IDs by hashing foreign function_call.id values into bounded fc_<hash> IDs instead of preserving backend-specific normalized shapes that OpenAI Codex rejects.

Fixed Anthropic thinking disable handling to send thinking: { type: "disabled" } for reasoning-capable models when thinking is explicitly off, and added payload and env-gated end-to-end coverage for the Anthropic provider (#2022)

Fixed explicit thinking disable handling across Google, Google Vertex, Gemini CLI, OpenAI Responses, Azure OpenAI Responses, and OpenRouter-backed OpenAI-compatible completions. Gemini 3 models now fall back to the lowest supported thinking level when full disable is not supported, and OpenAI/OpenRouter reasoning models now send explicit none effort instead of relying on provider defaults (#2490)

Fixed OpenAI-compatible completions streams to ignore null chunks instead of crashing (#2466 by @Cheng-Zi-Qing)

[0.61.1] - 2026-03-20

Changed

Changed MiniMax model metadata to add missing MiniMax-M2.1-highspeed entries for the minimax and minimax-cn providers and normalize MiniMax Anthropic-compatible context limits to the provider's supported model set (#2445 by @1500256797)

[0.61.0] - 2026-03-20

... (truncated)

Commits

d0404a4 Release v0.64.0
182ebe5 docs: add changelog entries for faux provider and ModelRegistry
ef6af5e feat(ai,coding-agent): add faux provider and ModelRegistry factories
567249e Add [Unreleased] section for next cycle
41039e8 Release v0.63.2
ec1cf54 Add [Unreleased] section for next cycle
d9727c4 Release v0.63.1
8fba9e9 docs(changelog): audit unreleased entries
bc8eb74 fix(ai): detect Ollama overflow errors closes #2626
17625cc feat(ai): add google-vertex gemini-3.1-pro-preview-customtools (#2610)
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 <dependency name> major version will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself)
@dependabot ignore <dependency name> minor version will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself)
@dependabot ignore <dependency name> will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself)
@dependabot unignore <dependency name> will remove all of the ignore conditions of the specified dependency
@dependabot unignore <dependency name> <ignore condition> will remove the ignore condition of the specified dependency and ignore conditions

Bumps the pi-packages group in /backend-ts with 2 updates: [@mariozechner/pi-agent-core](https://github.com/badlogic/pi-mono/tree/HEAD/packages/agent) and [@mariozechner/pi-ai](https://github.com/badlogic/pi-mono/tree/HEAD/packages/ai). Updates `@mariozechner/pi-agent-core` from 0.55.0 to 0.64.0 - [Release notes](https://github.com/badlogic/pi-mono/releases) - [Changelog](https://github.com/badlogic/pi-mono/blob/main/packages/agent/CHANGELOG.md) - [Commits](https://github.com/badlogic/pi-mono/commits/v0.64.0/packages/agent) Updates `@mariozechner/pi-ai` from 0.55.0 to 0.64.0 - [Release notes](https://github.com/badlogic/pi-mono/releases) - [Changelog](https://github.com/badlogic/pi-mono/blob/main/packages/ai/CHANGELOG.md) - [Commits](https://github.com/badlogic/pi-mono/commits/v0.64.0/packages/ai) --- updated-dependencies: - dependency-name: "@mariozechner/pi-agent-core" dependency-version: 0.64.0 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: pi-packages - dependency-name: "@mariozechner/pi-ai" dependency-version: 0.64.0 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: pi-packages ... Signed-off-by: dependabot[bot] <support@github.com>

dependabot Bot added the dependabot label Mar 30, 2026

Navigation Menu

build(deps): Bump the pi-packages group in /backend-ts with 2 updates - #147

build(deps): Bump the pi-packages group in /backend-ts with 2 updates#147
dependabot[bot] wants to merge 1 commit into
mainfrom
dependabot/npm_and_yarn/backend-ts/pi-packages-6760ae0076

dependabot Bot commented on behalf of github Mar 30, 2026 •

edited

Loading

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

0 participants

Conversation

dependabot Bot commented on behalf of github Mar 30, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

v0.64.0

New Features

Breaking Changes

Added

Fixed

v0.63.2

New Features

Added

Fixed

v0.63.1

Added

Fixed

[0.64.0] - 2026-03-29

Added

[0.63.2] - 2026-03-29

Added

[0.63.1] - 2026-03-27

[0.63.0] - 2026-03-27

[0.62.0] - 2026-03-23

[0.61.1] - 2026-03-20

[0.61.0] - 2026-03-20

[0.60.0] - 2026-03-18

[0.59.0] - 2026-03-17

[0.58.4] - 2026-03-16

Fixed

[0.58.3] - 2026-03-15

[0.58.2] - 2026-03-15

[0.58.1] - 2026-03-14

[0.58.0] - 2026-03-14

Added

Changed

[0.57.1] - 2026-03-07

v0.64.0

New Features

Breaking Changes

Added

Fixed

v0.63.2

New Features

Added

Fixed

v0.63.1

Added

Fixed

[0.64.0] - 2026-03-29

Added

[0.63.2] - 2026-03-29

[0.63.1] - 2026-03-27

Added

Fixed

[0.63.0] - 2026-03-27

Breaking Changes

Fixed

[0.62.0] - 2026-03-23

Added

Fixed

[0.61.1] - 2026-03-20

Changed

[0.61.0] - 2026-03-20

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

0 participants

dependabot Bot commented on behalf of github Mar 30, 2026 •

edited

Loading