Packages

@earendil-works/pi-coding-agent

1.6.0 · 20 Nov 2026MIT6.6M / weekRepositoryHomepagenpmAtom feed

Upgrading @earendil-works/pi-coding-agent From 0.79.1 to 1.6.0

50 releases in betweenevery note read

Reading releases, release notes and advisories…

Other targets from 0.79.1Newest 0.x0.99.2
  1. 0.79.1yours
  2. 18 releases
  3. 0.81.0major
  4. 1 release
  5. 0.82.0security
  6. 1 release
  7. 0.83.0major
  8. 0.84.0security
  9. 1 release
  10. 0.84.2security
  11. 2 releases
  12. 0.85.0major
  13. 1 release
  14. 0.86.0major
  15. 1 release
  16. 0.87.0major
  17. 1 release
  18. 0.99.0major
  19. 2 releases
  20. 1.0.0major
  21. 1.0.1security
  22. 7 releases
  23. 1.5.0security
  24. 2 releases
  25. 1.6.0target

Start here

Before you upgrade

Tick each one off as you go
  • Breaking1.6.0
  • Breaking1.6.0
  • Breaking1.5.1
  • Breaking1.5.1
  • Breaking1.5.0
  • Breaking1.5.0
  • Breaking1.2.0
  • Breaking1.2.0
  • Breaking1.2.0
  • Breaking1.2.0

Security

  • Updated undici to 8.12.4 for security advisories GHSA-mqg3-3v4r-cm32, GHSA-7xg3-fphp-28hg, GHSA-5rm8-gv32-r954, GHSA-9v6h-8rgp-m69f, GHSA-3g9m-rv3r-w5w2, and GHSA-r4pc-4jcp-7pqc

    1.6.0
  • Updated undici to 8.12.3 and the Gondolin extension example to 0.14.0 for security advisories

    1.5.0
  • Fixed installations resolving vulnerable brace-expansion 5.0.9 by pinning brace-expansion 5.0.12 as a direct dependency (GHSA-q2hr-2g5m-vwhr, GHSA-qhr7-859c-m2p7, GHSA-6j4f-fj2g-mc7p)

    1.0.1
  • Updated the transitive nanoid development dependency to address a denial-of-service vulnerability.

    0.84.2
  • Updated the packaged brace-expansion dependency to 5.0.8 to address GHSA-mh99-v99m-4gvg (#7316).

    0.84.0
  • Updated undici to 8.9.0 and the packaged brace-expansion to 5.0.9 to address GHSA-8xcm-r25x-g524, GHSA-4cwx-7wf7-3272, GHSA-m8rv-5g2x-5cg5, GHSA-jr45-8vmc-qm54, GHSA-v3r7-h72x-cjcm, and GHSA-rgw5-rvv9-x895.

    0.84.0
  • Updated the packaged protobufjs dependency to 7.6.5 to address GHSA-j3f2-48v5-ccww (#7005).

    0.82.0

Release by release

  1. 1.6.0

    Security fix20 Nov 20265 new · 48 fixes
    • Security

      Updated undici to 8.12.4 for security advisories GHSA-mqg3-3v4r-cm32, GHSA-7xg3-fphp-28hg, GHSA-5rm8-gv32-r954, GHSA-9v6h-8rgp-m69f, GHSA-3g9m-rv3r-w5w2, and GHSA-r4pc-4jcp-7pqc

    • Breaking

      Extension components: render() now returns readonly string, and Container returns the same cached array while its children are unchanged. Extensions that modify render output in place, including super.render() in a Container subclass or an embedded component's output, must copy it first

    • Breaking

      Removed the retired deepseek-v3.2 and deepseek-v4-flash from the Qwen Token Plan Team providers; use deepseek-v4-flash-0731 or deepseek-v4.1-flash

    • New

      GPT-6.2 Astra and GPT-6.2 Sol: both models are available on the openai, azure, and openai-codex providers, and GPT-6.2 Sol is now the default model for all three. See Providers.

  2. 1.5.2

    10 Nov 20261 new · 2 fixes
    • New

      Fork sessions whose folder is gone: when a session's original folder was moved or deleted, you can now fork it into the current folder instead of only continuing, so later resumes no longer ask. See Continue or switch sessions.

    • Fixed

      Fixed /import of a session whose working directory no longer exists leaving a copy in the session directory, and continuing it leaving a second copy with the same ID (s.jsonl and s-1.jsonl); the failed copy is now removed

    • Fixed

      Fixed Anthropic OAuth requests reporting an outdated Claude Code version

  3. 1.5.1

    Migration needed9 Nov 202618 new · 72 fixes
    • Breaking

      Custom GrepOperations.readFile callbacks are no longer called for context lines. The field remains accepted as optional and deprecated so existing integrations still compile. The grep tool now takes context lines from ripgrep and no longer reads matched files itself. To search a remote system, override grep's execute(); see Remote Execution

    • Breaking

      OpenAI-compatible models no longer send "tools": when all tools are disabled in a session that has used tools; the field is omitted. This fixes 400 errors (tools must not be an empty array) from vLLM 0.20+, also behind LiteLLM. If your proxy requires tools once the history has tool calls, such as older LiteLLM versions in front of Anthropic, set compat.requiresToolsWithToolHistory: true for that model in models.json

    • New

      Shell login and logout: use pi auth login <provider> and pi auth logout <provider> without starting a session, with API-key and no-browser sign-in options. See Credential commands.

    • New

      Idle prompt cache warming: eligible caches now stay warm for up to 30 minutes between runs when a refresh is expected to pay for itself. See cacheWarming.

  4. 1.5.0

    Security fix2 Nov 202614 new · 71 fixes
    • Security

      Updated undici to 8.12.3 and the Gondolin extension example to 0.14.0 for security advisories

    • Breaking

      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).

    • Breaking

      Removed the native OS sandbox/ extension example and its dependency. Use the Gondolin example or the containerization guide.

    • New

      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.

  5. 1.4.0

    21 Oct 202610 new · 25 fixes
    • New

      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.

    • New

      Models Configuration reference: every provider, model, model override, and compatibility field of models.json, generated from its schema. See Models Configuration.

    • New

      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.

    • New

      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.

  6. 1.3.0

    15 Oct 20267 new · 23 fixes
    • New

      Choose where /share uploads: sessionShareDestination selects auto, gist, or radius. See Sessions and context and Export or share a session.

    • New

      Cache-preserving thinking level changes on OpenAI GPT-6: changing the thinking level mid-session with an API key keeps the prompt cache.

    • New

      Kimi Code over Chat Completions: tools added mid-conversation no longer invalidate the prompt cache. models.json base URL overrides must now include /v1. See Providers.

    • New

      Clean model switching: thinking from a previous model is dropped instead of being shown to the new model as text.

  7. 1.2.0

    Migration needed12 Oct 202610 new · 22 fixes
    • Breaking

      Published generated configuration schemas for models, settings, keybindings, and themes at https://pi.dev/schemas/*.schema.json. The theme schema moved to https://pi.dev/schemas/theme.schema.json; themes loaded during startup now receive the same schema validation as later reloads. Update theme $schema references, define reusable colors under vars, and remove unsupported metadata (#9880, #10751

    • Breaking

      Changed before_agent_start to also fire for runs started by pi.sendMessage(..., { triggerTurn: true }) while idle. BeforeAgentStartEvent is now a union on messageType: "user" events carry prompt and images, and "custom" events carry the starting message and no prompt. Messages returned by handlers are added to both kinds of run, and pending deliverAs: "nextTurn" messages are delivered with the custom-message run. Handlers that should act only on user prompts must check event.messageType === "user" (#10267, #5581, #10739

    • Breaking

      Changed the session to count as busy while a run starts, including during before_agent_start handlers: ctx.isIdle() is false, pi.sendMessage() queues into the starting run instead of starting a second run that failed with "Agent is already processing", pi.sendUserMessage() requires deliverAs, and an abort requested meanwhile aborts the run once it starts

    • Breaking

      Changed pi mcp list --json to report resources: true for servers that offer resources instead of resources and resourceTemplates counts; Pi no longer lists resources when connecting

  8. 1.1.0

    7 Oct 202614 new · 22 fixes
    • New

      Program status reporting: terminals and agent dashboards that support OSC 7501 see whether Pi is working, blocked on a dialog or login, done, or failed. See Program status.

    • New

      Claude Haiku 5.5: anthropic/claude-haiku-5-5, with adaptive thinking up to xhigh/max effort.

    • New

      Adjust default tools with +name/-name: --tools entries like pi -t +codemode,-write change the default selection instead of replacing it. See Tools.

    • New

      GPT-6 Luna and image classification: OpenAI's GPT-6 Luna is available as a classifier model through the Decisions API, and codemode's models.classify() accepts images for classifiers that support them. See Use classifier models.

107 other lines we could not sort, mostly version bumps
  • Qwen Token Plan providers now use the current gateways (token-plan.maas.qwencloudapi.com international, token-plan.maas.qianwenaiapi.com China), and qwen-token-plan and qwen-token-plan-cn are named "Qwen Token Plan Team" and "Qwen Token Plan Team CN". Provider IDs are unchanged, and the old aliyuncs.com hosts still work

    1.6.0
  • The default model for the openai, azure, and openai-codex providers is now GPT-6.2 Sol (gpt-6.2-sol) instead of GPT-6.1 Sol, at the same price

    1.6.0
  • The find tool's path patterns are now relative to the search directory, like grep's glob: src/*.ts finds src/a.ts but no longer pkg/src/a.ts; use **/src/*.ts to match at any depth. Patterns without / still match file names at any depth

    1.6.0
  • The llama.cpp extension now connects to http://127.0.0.1:9931 by default, the current llama-server default port, instead of port 8080

    1.6.0
  • Anthropic message threads are now on by default for any provider whose baseUrl is on api.anthropic.com, not only the anthropic provider

    1.6.0
  • The resume command printed on exit is now on its own line after To resume this session:, so it can be selected with a triple-click

    1.6.0
  • When a session's working directory no longer exists, for example after the project folder was renamed, interactive mode now offers Continue, Fork, or Cancel instead of only continuing. Continue runs the session in the current directory without storing the choice, as before; Fork copies it into the current directory as a new session with a new ID, like --fork, so the next resume no longer asks. This applies at startup (--session, --resume), to /resume, to /import, and to ctx.switchSession() from extensions

    1.5.2
  • The default model for the anthropic provider is now Claude Opus 5.5 (claude-opus-5-5) instead of Claude Opus 4.8

    1.5.1
  • Default models moved to newer models at the same or a lower price: amazon-bedrock Claude Opus 5.5, azure GPT-6.1 Sol, google and google-vertex Gemini 4 Argon, vercel-ai-gateway GLM 5.3, baseten GLM 5.3, minimax and minimax-cn MiniMax-M3, qwen-token-plan and qwen-token-plan-cn Qwen3.8 Max, opencode-go Kimi K3.1 Pro, and Kimi K2.7 Code instead of Kimi K2.6 for moonshotai, moonshotai-cn, huggingface, opencode, openrouter, cloudflare-workers-ai and cloudflare-ai-gateway

    1.5.1
  • cacheWarming now defaults to "idle" instead of "streaming": pi also keeps eligible prompt caches warm for up to 30 minutes between agent runs, but only when a refresh is expected to pay for itself. Set "cacheWarming": "streaming" in global settings for the previous behavior

    1.5.1

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.