agent/pi - pi - Penguin

chore(deps): Kill small dependencies (#4467 )

Armin Ronacher · 2026-05-13 10:44:56 +02:00

2829146dde

Merge pull request #4383 from maximilianzuern/docs/fixToolConfig

fix(coding-agent) docs: update tool configuration API in SDK docs

Mario Zechner · 2026-05-13 00:16:50 +02:00

6ff6dc6278

Merge remote-tracking branch 'origin/main'

Mario Zechner · 2026-05-12 23:35:17 +02:00

24e370fde5

fix(coding-agent): retry Anthropic message_stop stream endings

closes #4433

Mario Zechner · 2026-05-12 23:25:15 +02:00

5ac874c849

fix(compaction): clamp summary output tokens

Fixes #4390.

Armin Ronacher · 2026-05-11 16:36:27 +02:00

3d9e14d748

fix tool config in example in sdk.ts

Maximilian · 2026-05-10 23:32:15 +02:00

c3ce1d33d4

feat(ai): add Together AI provider

Mario Zechner · 2026-05-08 16:44:18 +02:00

7adb8e7634

Merge pull request #4299 from aliou/fix/resource-location-in-config-tui

fix(coding-agent): preserve .agents provenance in skill metadata

Mario Zechner · 2026-05-08 15:32:01 +02:00

dfb9ffa9ee

fix(coding-agent): disambiguate resource paths

Armin Ronacher · 2026-05-08 00:16:28 +02:00

3421726e86

chore: migrate pi packages to earendil works scope

Mario Zechner · 2026-05-07 15:59:42 +02:00

3e5ad67e0f

chore(coding-agent): switch back from fork to upstream jiti 2.7 (#4244 )

Pooya Parsa · 2026-05-07 01:04:51 +02:00

50993d743d

fix(coding-agent): strip skill wrapper XML from HTML export user messages (#4234 )

Skill slash commands store a structural <skill>...</skill> wrapper in raw
user messages. The TUI uses parseSkillBlock() to split this into separate
SkillInvocationMessageComponent and UserMessageComponent siblings, but the
HTML export renderer passed the full raw text through markdown, causing
broken/dangling XML tags to appear in exported HTML.

Add parseSkillBlock() to the export template and render skill-invocation
and user-message as separate sibling blocks:
- Sidebar tree shows skill name + user prompt separately
- Content area shows a clickable skill-invocation block (collapsed by
  default, markdown content on expand) followed by the user message
- Copy-link button preserved on the wrapper element
- Toggle tools (O key) expands/collapses skill invocations alongside
  compaction and tool output blocks

Aliou Diallo · 2026-05-06 18:06:37 +02:00

88619669e2

fix(coding-agent): preserve .agents provenance in skill metadata

fixes #3978

Aliou Diallo · 2026-05-06 09:40:37 +02:00

0f95975103

feat(coding-agent): allow comments and trailing commas in models.json (#4162 )

* feat(coding-agent): allow comments and trailing commas in models.json

Run user-supplied models.json through a small `stripJsonComments` helper
before JSON.parse so users can annotate their config and leave trailing
commas without breaking the loader.

Co-Authored-By: julien-agent <Agents+cyolo@huggingface.co>

* fix(coding-agent): strip comments before trailing commas in models.json

The single-pass regex couldn't see a trailing comma when a `//` comment sat
between the comma and its closer. Split into two passes: strip comments
first, then strip trailing commas on the cleaned input.

Co-Authored-By: julien-agent <Agents+cyolo@huggingface.co>

---------

Co-authored-by: julien-agent <Agents+cyolo@huggingface.co>

Julien Chaumond · 2026-05-04 22:44:35 +02:00

bb25a3944c

fix(coding-agent): stream bash output incrementally (#4165 )

fixes #4145

Armin Ronacher · 2026-05-04 19:06:07 +02:00

6b18cdbac1

fix(coding-agent): show compact read line ranges

Armin Ronacher · 2026-05-04 09:39:12 +02:00

e355696d8a

fix(coding-agent): render compact read calls directly

Render compact read classifications in the call row and leave the collapsed result row empty. The previous implementation used shared renderer state to let renderResult hide renderCall, which leaked an internal ReadRenderState type through the tool definition and coupled two render phases unnecessarily. The call renderer has all context needed to choose the compact presentation itself.

Mario Zechner · 2026-05-04 00:52:56 +02:00

324aa1d647

fix(coding-agent): decouple codex session cleanup

Mario Zechner · 2026-05-04 00:45:56 +02:00

23420012ab

fix(coding-agent): close codex websocket sessions

Fixes #4103

Armin Ronacher · 2026-05-03 23:25:56 +02:00

5fa277b320

fix(ai): fall back from codex websocket to sse (#4133 )

Armin Ronacher · 2026-05-03 22:51:42 +02:00

370fdae6fa

feat(ai): switch xiaomi default to api billing, add per-region token plan providers (#4112 )

Built-in `xiaomi` provider now targets the API billing endpoint (https://api.xiaomimimo.com/anthropic) — a single stable URL for keys issued at platform.xiaomimimo.com. The Token Plan endpoints are exposed as three sibling providers, each with its own env var:

- xiaomi-token-plan-cn: XIAOMI_TOKEN_PLAN_CN_API_KEY
- xiaomi-token-plan-ams: XIAOMI_TOKEN_PLAN_AMS_API_KEY
- xiaomi-token-plan-sgp: XIAOMI_TOKEN_PLAN_SGP_API_KEY

BREAKING CHANGE: users who previously set XIAOMI_API_KEY against the Token Plan AMS endpoint must move to xiaomi-token-plan-ams and set XIAOMI_TOKEN_PLAN_AMS_API_KEY. This also resolves the 401 reported by on #4005, where a platform.xiaomimimo.com key fails against the Token Plan endpoint.

closes #4082

Jake Jia · 2026-05-03 12:57:11 +02:00

693888ac47

feat(read): compact resource read rendering

Armin Ronacher · 2026-05-02 21:20:26 +02:00

588639fa97

fix(ai): honor codex transport option

closes #4083

Mario Zechner · 2026-05-02 14:14:22 +02:00

b8bb2411ff

fix(ai): use Xiaomi Token Plan Anthropic endpoint

closes #3912

Mario Zechner · 2026-05-02 01:36:34 +02:00

c0e046990e

feat: add model thinking level metadata

closes #3208

Mario Zechner · 2026-05-02 01:21:06 +02:00

80f06d3636

feat(ai): add Xiaomi MiMo provider (#4005 )

* fix(ai): include minimax-cn in cross-provider-handoff matrix

* feat(ai): add Xiaomi MiMo provider

Adds Xiaomi MiMo as an openai-completions-compatible provider.

- packages/ai: register provider in types/KnownProvider, env-api-keys (XIAOMI_API_KEY), generate-models, models.generated.ts, overflow util, README, CHANGELOG
- packages/ai/test: extend stream, tokens, abort, empty, context-overflow, overflow, image-tool-result, tool-call-without-result, total-tokens, unicode-surrogate, cross-provider-handoff matrices with Xiaomi
- packages/coding-agent: default model (mimo-v2.5-pro), display name (Xiaomi MiMo), CLI env var docs, README, docs/providers.md

closes #3912

---------

Co-authored-by: Mario Zechner <badlogicgames@gmail.com>

Jake Jia · 2026-05-02 00:46:05 +02:00

a44622670f

fix(coding-agent): honor registered model base urls

closes #4063

Mario Zechner · 2026-05-01 22:19:06 +02:00

ddb8ed0c73

fix(coding-agent): repair self-update detection

Fixes #3942
Fixes #3980
Fixes #3922

Armin Ronacher · 2026-05-01 18:08:02 +02:00

ade08de14c

fix(ai): finalize cloudflare gateway provider support

Mario Zechner · 2026-05-01 00:56:05 +02:00

a45577bd00

feat(ai): add Cloudflare AI Gateway as a provider (#3856 )

* feat(ai): add Cloudflare AI Gateway as a provider

Routes through Cloudflare's Unified API (`/compat`) for Workers AI and
Anthropic models, and through the provider-specific `/openai` subpath
for OpenAI models so reasoning models (gpt-5.x, o-series) can hit
`/v1/responses` natively. Once `/compat` adds Responses-API support,
the OpenAI subpath can be folded back in.

Catalog layout:
  workers-ai/@cf/...  -> openai-completions, gateway/.../compat
  anthropic/...       -> openai-completions, gateway/.../compat
  <native-id>         -> openai-responses,   gateway/.../openai
                         (gpt-5.1, claude-... no, sorry: gpt-5.x and o-series only;
                          prefix stripped because the OpenAI SDK posts native ids)

Touches:
  packages/ai/src/types.ts                       add cloudflare-ai-gateway to KnownProvider
  packages/ai/src/env-api-keys.ts                map to CLOUDFLARE_API_KEY
  packages/ai/src/providers/cloudflare.ts        add CLOUDFLARE_AI_GATEWAY_COMPAT_BASE_URL
                                                 and CLOUDFLARE_AI_GATEWAY_OPENAI_BASE_URL
  packages/ai/src/providers/openai-responses.ts  one-line dispatch through resolveCloudflareBaseUrl
                                                 (matches what openai-completions.ts already does)
  packages/ai/scripts/generate-models.ts         branch openai/* vs workers-ai/anthropic/*
  packages/ai/src/models.generated.ts            spliced 34 entries
  packages/ai/test/stream.test.ts                3 e2e blocks (one per upstream)
  packages/coding-agent/*                        defaultModelPerProvider, login, env docs,
                                                 README, providers.md

Verified end-to-end against a real Cloudflare account with unified
billing: 9/9 e2e tests pass across all three upstreams (Workers AI
Kimi K2.6, OpenAI gpt-5.1 reasoning, Anthropic claude-sonnet-4-5).

* refactor(ai): move AI Gateway User-Agent and per-route session-affinity flag to catalog

Mirrors the same per-model metadata refactor done for Workers AI in the
parent branch. All cloudflare-ai-gateway entries get the User-Agent
header. Only workers-ai/* gateway entries set
`compat.sendSessionAffinityHeaders: true` because the gateway
forwards that header to the underlying Workers AI runtime; anthropic/*
upstream and openai/* (openai-responses) don't use it.

  packages/ai/scripts/generate-models.ts: emit headers (always) and
  per-upstream compat (workers-ai only) on each cloudflare-ai-gateway
  entry.
  packages/ai/src/models.generated.ts: re-spliced 35 entries with
  headers + conditional compat.

Behavior unchanged - 9/9 e2e tests pass across all three upstream
families.

* fix(ai): align AI Gateway with telemetry-aware UA helper

Adapts to badlogic/pi-mono#3851's follow-up fix ("honor telemetry for
Cloudflare attribution headers", fbb5eed) which moved the
'User-Agent: pi-coding-agent' header out of per-model catalog metadata
and into a centralized telemetry-honoring helper
(coding-agent/src/core/sdk.ts:getAttributionHeaders).

- packages/coding-agent/src/core/sdk.ts: extend the cloudflare branch of
  getAttributionHeaders to also match cloudflare-ai-gateway and
  gateway.ai.cloudflare.com.

- packages/ai/scripts/generate-models.ts and src/models.generated.ts:
  drop 'headers' from the 35 cloudflare-ai-gateway entries (constant
  CLOUDFLARE_STATIC_HEADERS no longer exists). Per-route
  compat.sendSessionAffinityHeaders is unchanged.

End-to-end behavior unchanged: 9/9 tests still pass across all three
upstream families (Workers AI, Anthropic, OpenAI Responses).

---------

Co-authored-by: Mario Zechner <badlogicgames@gmail.com>

MC · 2026-04-30 23:29:37 +02:00

24fb6b833b

fix(coding-agent): avoid duplicate blocked edit output

closes #3830

Mario Zechner · 2026-04-30 22:50:40 +02:00

3ffc2b4306

fix(coding-agent): refresh thinking border from extensions

closes #3888

Mario Zechner · 2026-04-30 22:50:00 +02:00

95ae590279

fix(coding-agent): stop tool argument injection

closes #4018

Mario Zechner · 2026-04-30 21:31:43 +02:00

3d43d2e175

remove gemini cli and antigravity support

Mario Zechner · 2026-04-30 21:24:36 +02:00

fe66edd943

feat(coding-agent): allow message_end replacements

closes #3982

Mario Zechner · 2026-04-30 21:24:36 +02:00

40c6eabb8f

fix(coding-agent): remove detached: true on Windows to fix pwsh.exe stdio (#4013 )

On Windows, spawn(..., { detached: true }) prevents pwsh.exe (PowerShell) from
producing any stdout/stderr through pipe streams. This is because detached creates
a new process group which breaks pwsh's console host communication.

bash.exe and other cygwin/msys2 shells are unaffected by detached: true, but
they don't need it either -- on Windows, killProcessTree() already uses
taskkill /F /T /PID which kills the process tree by PID regardless of
whether the process was spawned detached.

The detached flag only matters on Unix, where kill(-pid, SIGKILL) requires a
process group that is only created via detached: true.

Fixes #4012

pica · 2026-04-30 20:59:02 +02:00

24dec9fcd5

feat(ai): add Moonshot AI provider model support

Armin Ronacher · 2026-04-30 17:21:03 +02:00

7dc1bed478

Adjusts #3955 , better error message

Mario Zechner · 2026-04-30 12:33:02 +02:00

ebdf3cf451

fix(coding-agent): report edit access failures correctly (#3955 )

* fix(coding-agent): report edit access failures correctly closes #3894

- classify edit and edit-preview access errors by errno
- add regressions for missing, permission, and fallback cases
- document the fix in the coding-agent changelog

* chore: get rid of CHANGELOG.md entry

* refactor(coding-agent): apply review suggestions - use single error msg

* refactor(coding-agent): clean up test cases

Ramiz Wachtler · 2026-04-30 12:31:29 +02:00

43ee9b77ed

fix(coding-agent): redo Bun package manager node_modules handling (#3998 )

* Revert "fix(coding-agent): use alternate logic to find Bun's node_modules (#3861)"

This reverts commit c241c6d6d0.  The logic
is faulty: the original strategy of looking for node_modules by asking
the package manager is not incorrect even on bun. Instead, it should
learn a different method of asking the package manager for node_modules
when the *package manager* is bun, not the *runtime*.

* feat(coding-agent): detect bun as package manager and use alternate root query

When `"npmCommand": ["bun"]` is configured in settings.json, pi fails to
start because it invokes `bun root -g`, which doesn't exist:

    error: Failed to run bun root -g: error: Script not found "root"

Add a (simple) check for Bun being used as package manager, and instead
build the relative path starting from Bun's bin directory.

George Hilliard · 2026-04-30 12:27:50 +02:00

0dd11898ad

feat(coding-agent): add provider display names

closes #3956

Mario Zechner · 2026-04-30 00:10:38 +02:00

cf5ec23240

fix(coding-agent): support uppercase context files closes #3949

Mario Zechner · 2026-04-29 23:47:04 +02:00

b79e7f8058

feat(coding-agent): add composable editor factory access

closes #3935

Mario Zechner · 2026-04-29 23:26:25 +02:00

d698647b12

fix(coding-agent): escape exported session metadata (#3883 )

Justin Barnett · 2026-04-28 11:46:42 +02:00

57787b6557

fix(coding-agent): use alternate logic to find Bun's node_modules (#3861 )

When `"npmCommand": ["bun"]` is configured in settings.json, pi fails to
start because it invokes `bun root -g`, which doesn't exist:

    error: Failed to run bun root -g: error: Script not found "root"

Add a check for the Bun runtime using the logic already used elsewhere,
and build the relative path starting from Bun's bin directory.

George Hilliard · 2026-04-28 08:28:37 +02:00

c241c6d6d0

fix: honor telemetry for Cloudflare attribution headers

Mario Zechner · 2026-04-27 23:49:14 +02:00

fbb5eed191

feat(ai): add Cloudflare Workers AI as a provider (#3851 )

* feat(ai): add Cloudflare Workers AI as a provider

Cloudflare Workers AI hosts open-weight LLMs (Kimi K2.6, GPT-OSS,
GLM-4.7, Llama 4, Gemma 4, Nemotron 3) on Cloudflare's GPU network with
an OpenAI-compatible endpoint. Reuses the openai-completions API
protocol; the per-account URL contains a {CLOUDFLARE_ACCOUNT_ID}
placeholder resolved at request time by a small helper.

Pi automatically sets x-session-affinity for prefix caching:
https://developers.cloudflare.com/workers-ai/features/prompt-caching/

Auth: CLOUDFLARE_API_KEY (matches pi's *_API_KEY convention) +
CLOUDFLARE_ACCOUNT_ID. The User-Agent identifies traffic as
'pi-coding-agent' in Cloudflare analytics.

Verified end-to-end against a real Cloudflare account: 17 e2e tests
pass across stream/empty/tokens/unicode/tool-call-without-result/
total-tokens against @cf/moonshotai/kimi-k2.6.

Cloudflare AI Gateway is a separate, larger change (it requires routing
through provider-specific subpaths with the matching API protocol per
upstream) and will land in a follow-up PR.

* refactor(ai): move Cloudflare User-Agent and session-affinity flag to per-model metadata

Instead of conditionally setting them in openai-completions.ts based on
provider detection, declare them as model-level fields in the catalog
(headers + compat). This is consistent with how the github-copilot and
kimi-coding entries already declare their static headers.

  packages/ai/scripts/generate-models.ts: emit headers and compat fields
  on each cloudflare-workers-ai entry (CLOUDFLARE_STATIC_HEADERS).
  packages/ai/src/providers/openai-completions.ts: drop the
  isCloudflareProvider conditional that injected User-Agent and the
  isCloudflareWorkersAI override of sendSessionAffinityHeaders.
  packages/ai/src/models.generated.ts: re-spliced 8 cloudflare-workers-ai
  entries with headers + compat.

Behavior is unchanged - verified via fetch interceptor that User-Agent
and x-session-affinity / session_id / x-client-request-id are still sent
on outbound requests. 5/5 e2e tests pass.

MC · 2026-04-27 23:41:54 +02:00

d6e08b3da0

fix(coding-agent): escape exported image data (#3819 )

Fixes #3811

Justin Barnett · 2026-04-27 23:22:06 +02:00

7617c1ad92

fix(coding-agent): prevent wrapped padding in HTML export

Mario Zechner · 2026-04-27 21:49:46 +02:00

01e2536879

fix(coding-agent): tighten HTML export tool spacing

Mario Zechner · 2026-04-27 21:18:34 +02:00

b8238a77a5

817 Commits