@earendil-works/pi-coding-agent
1.6.0 · 20 Nov 2026MIT6.6M / weekRepositoryHomepagenpmAtom feed
0.99.2 is the newest release of 0.79.x.
In short
10 new16 fixed
Release note
New Features
Claude Fable 5 - Claude Fable 5 is now available on the Anthropic and Amazon Bedrock providers, with adaptive thinking and
xhigheffort support.Prompt template defaults - Prompt templates can use default positional arguments such as
${1:-7}for optional values. See Prompt Template Arguments.Configurable project trust defaults -
defaultProjectTrustlets users choose whether unresolved project trust asks, always trusts, or never trusts by default, and extensions can inspect effective trust decisions. See Project Trust andctx.isProjectTrusted().Natural extension autocomplete triggers - Extension autocomplete providers can declare trigger characters such as
#or$so suggestions open without slash-command prefixes. See Autocomplete Providers.
Added
Added default-value expansion for prompt template positional arguments, e.g.
${1:-7}Added
areExperimentalFeaturesEnabledfeature guard to allow users to opt in to early featuresAdded
ctx.isProjectTrusted()for extensions to observe the effective project trust decision, including temporary trust decisions (#5523).Added a global
defaultProjectTrustsetting to choose whether unresolved project trust asks, always trusts, or never trusts by default.Added extension autocomplete trigger character support for
ctx.ui.addAutocompleteProvider()wrappers (#4703).Added Claude Fable 5 model support inherited from
@earendil-works/pi-aifor the Anthropic and Amazon Bedrock providers, with adaptive thinking andxhigheffort support.
Fixed
Fixed inherited Amazon Bedrock inference profile ARN region resolution to prefer the ARN's embedded region over
AWS_REGIONFixed inherited IME hardware cursor positioning while slash-command autocomplete is visible
Fixed inherited z.ai thinking-off requests to send the provider's
thinking: { type: "disabled" }compatibility parameter (#5330).Fixed inherited OpenCode completions model metadata to send explicit
maxTokensasmax_tokens(#5331).Fixed inherited Moonshot Kimi thinking-off requests to send the provider's
thinking: { type: "disabled" }compatibility parameter (#5531).Fixed inherited Azure OpenAI Responses requests to disable server-side response storage (#5530).
Fixed inherited Azure GPT-5.4 and GPT-5.5 context window metadata to 1,050,000 tokens, matching Azure Foundry deployments instead of OpenAI's 272k limit (#5559).
Fixed inherited OpenAI and Azure GPT-5 Pro
maxTokensmetadata to 128,000, correcting an upstream value that duplicated the input sub-limit as the output limit (#5559).Fixed inherited prompt history navigation to restore the current draft when returning from history browsing (#5494).
Fixed inherited wrapping for mixed Latin and CJK text so unspaced CJK runs can break at grapheme boundaries without leaving large trailing gaps (#5495).
Fixed extension OAuth login prompts to keep previous submitted prompt rows stable instead of mirroring the active input value (#5433).
Fixed
/reloadto apply updatedsteeringModeandfollowUpModesettings to the current session (#5377).Fixed invalid
models.jsonsyntax to skip startup config migrations and report the normal file-path-aware models error instead of a raw JSON parse stack trace (#5418).Fixed GitHub release notes and interactive changelog links to resolve package-relative documentation URLs correctly (#5516).
Fixed CLI help and version output, including plain redirected
--help/--versionoutput and simplifiedlist/confighelp text.Fixed
/newfrom ephemeral sessions to keep the new session ephemeral instead of persisting it by default (#5045).Clarified custom model docs that
nameandmodelOverrides.namedo not replace model IDs in the footer or primary model lists (#4841).
A whole project to check? Paste its package.json in the dependency check: every deprecated, outdated or vulnerable dependency, with what to upgrade to. Free, no account.