@mariozechner/pi-agent-core
0.73.1 · 7 May 2026MIT523.2k / weekRepositoryHomepagenpmAtom feed
Upgrading @mariozechner/pi-agent-core From 0.27.1 to 0.73.1
154 releases in betweennotes for 95
Reading releases, release notes and advisories…
- 69+
- changes to make
- 0
- advisories fixed
- 397+
- new
- 572+
- fixes
Counted from 95 of 154 release notes. Advisories are counted from the advisory database, in full.
Before you upgrade
Tick each one off as you go- Breaking0.73.0
- Breaking0.72.0
- Breaking0.71.0
- Breaking0.71.0
- Breaking0.71.0
- Breaking0.70.0
- Breaking0.69.0
- Breaking0.69.0
- Breaking0.68.0
- Breaking0.68.0
Release by release
- New
Self-update support for the npm scope migration:
pi update --selfnow supports the upcoming package rename from@mariozechner/pi-coding-agentto@earendil-works/pi-coding-agent. After the new package is published, existing global installs can update through the normal self-update flow; pi will uninstall the old global package and install the package name returned by the version check endpoint. - New
Interactive OAuth login selection: OAuth providers can now present multiple login choices in
/login, enabling provider-specific interactive authentication flows. See Providers. - New
JSONC-style
models.jsonparsing:models.jsonnow allows comments and trailing commas, making custom provider and model configuration easier to maintain. See Providers and Custom Providers. - New
Added interactive login selection support so OAuth providers can present multiple login choices
- New
- Breaking
Switched the built-in
xiaomiprovider from Token Plan AMS to Xiaomi's API billing endpoint, and renamed its/logindisplay from "Xiaomi MiMo Token Plan" to "Xiaomi MiMo".XIAOMI_API_KEYnow refers to the API billing key from platform.xiaomimimo.com. Users on Token Plan should switch to the appropriatexiaomi-token-plan-*provider and set the corresponding env var - New
Xiaomi MiMo API billing and regional Token Plan providers -
xiaominow uses API billing, with separatexiaomi-token-plan-{cn,ams,sgp}providers. See docs/providers.md#api-keys and README.md#providers--models. - New
Incremental bash output streaming - Bash tool output now appears while commands run instead of only after completion.
- New
Compact read rendering - Interactive
readoutput for Pi docs, context files, and skills is collapsed by default and shows selected line ranges.
- Breaking
0.72.1nothing new or fixed in the note
- Breaking
Replaced
compat.reasoningEffortMapinmodels.jsonandpi.registerProvider()model definitions with model-levelthinkingLevelMap(#3208). Migration: move old mappings fromcompat.reasoningEffortMaptothinkingLevelMap. Use string values for provider-specific thinking values andnullfor unsupported pi levels that should be hidden and skipped by cycling. Seedocs/models.md#thinking-level-mapanddocs/custom-provider.md. - New
Added Xiaomi MiMo Token Plan provider support with
XIAOMI_API_KEY, default model resolution,/logindisplay support, and provider documentation - New
Added
shouldStopAfterTurnagent loop callback for post-turn stop control, inherited from@mariozechner/pi-agent-core. Seepackages/agent/README.md. - Fixed
Fixed
pi.registerProvider()to honor per-modelbaseUrloverrides (#4063). - Fixed
- Breaking
- New
Added
websocket-cachedto the transport setting options for the OpenAI Codex provider used with ChatGPT subscription auth. This keeps the same WebSocket open for a session and, after the first request, sends only the new conversation items instead of resending the full chat history when possible.
- New
- Breaking
Removed built-in Google Gemini CLI and Google Antigravity support. Existing configurations using those providers must switch to another supported provider.
- Breaking
Removed the discontinued Qwen CLI OAuth custom provider extension example
- Breaking
Removed Google Gemini CLI and Google Antigravity built-in login, default model, documentation, and example extension support.
- New
Cloudflare AI Gateway provider support with
CLOUDFLARE_API_KEY/CLOUDFLARE_ACCOUNT_ID/CLOUDFLARE_GATEWAY_ID, default model resolution, and/logindisplay. See docs/providers.md#cloudflare-ai-gateway.
- Breaking
- New
Cloudflare Workers AI provider support with
CLOUDFLARE_API_KEY/CLOUDFLARE_ACCOUNT_IDsetup. See docs/providers.md#api-keys. - New
Pi update checks now use
pi.devand identify Pi with api/<version>user agent. See docs/packages.md. - New
Added Cloudflare Workers AI as a built-in provider with
CLOUDFLARE_API_KEY/CLOUDFLARE_ACCOUNT_IDsetup, default model resolution,/loginsupport, and provider documentation - Fixed
Fixed config selector scroll indicators to show item counts instead of line counts
- New
- Fixed
Fixed HTML export preserving ANSI-renderer trailing padding as extra blank wrapped lines.
- Fixed
71 other lines we could not sort, mostly version bumps
- 0.73.1
Changed
pi update --selfto honor the active package name returned by the Pi version check endpoint, defaulting to the current package when omitted and uninstalling the old global package before installing a renamed package. - 0.73.1
Changed extension loading to use upstream
jiti2.7 instead of the@mariozechner/jitifork - 0.73.1
Changed
models.jsonparsing to allow comments and trailing commas - 0.73.0
Changed
readtool rendering to collapse Pi documentation, AGENTS/CLAUDE context files, andSKILL.mdcontents by default in interactive output. - 0.72.1
Changed the default agent transport to
autoso providers can use their best available transport by default (#4083). - 0.70.6
Changed Pi version checks to identify Pi with a
pi/<version>user agent - 0.70.0
Updated default model selection across providers to current recommended models.
- 0.70.0
Improved stale extension context errors after session replacement or reload to tell extension authors to avoid captured
pi/commandctxand usewithSessionfor post-replacement work. - 0.68.0
Changed
pi updateto batch npm package updates per scope and run git package updates with bounded parallelism, reducing multi-package update time while preserving skip behavior for pinned and already-current packages - 0.68.0
Changed Bedrock session requests to omit
maxTokenswhen model token limits are unknown and to omittemperaturewhen unset, letting Bedrock use provider defaults and avoid unnecessary TPM quota reservation
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.