agent/pi - pi - Penguin

Clarify hardware cursor docs

closes #5200

Mario Zechner · 2026-05-30 01:20:14 +02:00

c1633e609d

Add startup session name flag

closes #5153

Mario Zechner · 2026-05-29 11:40:58 +02:00

ce554ad3de

feat(coding-agent): add exclude tools option closes #5109

Mario Zechner · 2026-05-28 23:49:18 +02:00

9380d5f2e4

Fix Anthropic empty thinking signature replay

closes #4464

Mario Zechner · 2026-05-28 12:04:33 +02:00

458a7bc27c

fix(coding-agent): make config env references explicit

closes #5095

Armin Ronacher · 2026-05-28 11:58:38 +02:00

3e9f717445

Expose tool prompt guidelines to extensions

closes #4879

Mario Zechner · 2026-05-28 11:03:25 +02:00

edd26444af

Merge pull request #5115 from DanielThomas/dannyt/sendUserMessage-agent-end

fix(coding-agent): drain follow-ups queued during agent_end

Mario Zechner · 2026-05-28 10:47:31 +02:00

8e77f8797b

fix(coding-agent): drain follow-ups queued during agent_end

When an extension queues a follow-up during `agent_end` it
gets stuck on the follow-up queue until after the next user
message.

Add a hasQueuedMessages() check to _handlePostAgentRun
so the existing while/continue loop drains them.

- One-line fix in _handlePostAgentRun
- Integration test in agent-session-queue
- git-merge-and-resolve example extension with tests

Danny Thomas · 2026-05-28 18:27:39 +10:00

a29a7902e9

feat(coding-agent): expose streamingBehavior on InputEvent

Add streamingBehavior to InputEvent so extensions can distinguish
idle prompts from mid-stream steers and queued follow-ups.

- Add streamingBehavior field to InputEvent type
- Thread it through ExtensionRunner.emitInput() and AgentSession.prompt()
- Add streaming-aware input gate example with tests
- Document in extensions.md

Danny Thomas · 2026-05-28 15:52:38 +10:00

bcea4b2e27

docs(coding-agent): fix development AGENTS link

Closes #5041

Armin Ronacher · 2026-05-27 22:51:30 +02:00

1e168a89c5

fix(codex): timeouts for websockets (#4979 )

Armin Ronacher · 2026-05-27 12:11:29 +02:00

493efd422d

fix(ai): disable hidden provider 429 retries (#4991 )

Armin Ronacher · 2026-05-26 23:41:58 +02:00

8fb1e877cd

revert: fix rpc stdout backpressure

This reverts commit d0d1d8edca.

Armin Ronacher · 2026-05-24 11:50:53 +02:00

9600ded922

fix(rpc): respect stdout backpressure

closes #4897

Armin Ronacher · 2026-05-24 11:28:02 +02:00

d0d1d8edca

fix(tui): detect Apple Terminal Shift+Enter

Armin Ronacher · 2026-05-23 15:09:01 +02:00

c5181a266e

fix(coding-agent): reconcile pinned git update refs

closes #4869

Armin Ronacher · 2026-05-23 00:16:07 +02:00

c85dbb1620

Support adaptive thinking for Anthropic-compatible aliases

closes #4790

Mario Zechner · 2026-05-22 18:30:51 +02:00

d801d88a11

Clean up OAuth device-code callbacks

Mario Zechner · 2026-05-22 15:51:36 +02:00

c841a6c78f

fix(coding-agent): reconcile git package refs

closes #4870

Mario Zechner · 2026-05-22 11:13:26 +02:00

bf56a86e1e

feat(coding-agent): expose edit tool unified patch

closes #4821

Mario Zechner · 2026-05-21 12:15:39 +02:00

60a55a2399

docs: recommend scriptless npm installs

Mario Zechner · 2026-05-20 14:47:18 +02:00

5b7c5d2157

docs(coding-agent): add uninstall instructions

Armin Ronacher · 2026-05-18 12:47:33 +02:00

137547a470

fix(coding-agent): install npm packages in managed root closes #4587

Armin Ronacher · 2026-05-17 20:48:00 +02:00

6f931797ca

fix(coding-agent): allow skill names to differ from directories

closes #4534

Mario Zechner · 2026-05-16 23:38:46 +02:00

5d31e70b8a

Merge pull request #4567 from julien-c/fix/extensions-docs-notify-type

docs(coding-agent): fix invalid notify type in extensions example

Mario Zechner · 2026-05-16 22:52:31 +02:00

943236c9e6

docs(coding-agent): document overflow normalization for custom providers

Adds a Context Overflow Errors subsection to custom-provider.md showing how a custom provider extension can rewrite unrecognized overflow errors via a message_end handler so pi's native compact-and-retry path triggers. Includes guard rails for provider scoping, idempotency, and avoiding rate-limit phrases.

Aliou Diallo · 2026-05-16 01:50:12 +02:00

b9ae2590f5

docs(coding-agent): fix invalid notify type in extensions example

The notify() API only accepts "info" | "warning" | "error" — "success"
was a copy-paste error in the example.

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

Julien Chaumond · 2026-05-15 20:23:34 +02:00

656bd2cadf

fix(coding-agent): fix Termux docs code fence

closes #4503

Mario Zechner · 2026-05-15 01:02:36 +02:00

3ca474b15b

minor fix in body

Maximilian · 2026-05-11 00:45:30 +02:00

68deecfb4f

fix tool config in SDK docs

Maximilian · 2026-05-11 00:32:19 +02:00

74739567b9

docs(coding-agent): update theme schema URLs

Armin Ronacher · 2026-05-09 23:03:58 +02:00

76131673d3

feat(ai): add Together AI provider

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

7adb8e7634

docs(coding-agent): fix termux-open chooser flag

PriNova · 2026-05-07 23:32:31 +02:00

323abaea06

doc: Update readmes

Armin Ronacher · 2026-05-07 20:02:19 +02:00

f4fc04cd75

chore: migrate pi packages to earendil works scope

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

3e5ad67e0f

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

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

docs(coding-agent): update subscription provider notes

Mario Zechner · 2026-05-01 01:32:13 +02:00

8040dd6ded

chore(coding-agent): remove Qwen CLI extension example

Mario Zechner · 2026-05-01 01:01:54 +02:00

8db0d28389

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): refresh thinking border from extensions

closes #3888

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

95ae590279

feat(coding-agent): support session dir env

closes #4027

Mario Zechner · 2026-04-30 21:37:53 +02:00

8191d59c17

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): 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

docs(coding-agent): clarify telemetry update checks

Armin Ronacher · 2026-04-30 11:04:20 +02:00

904b843fee

526 Commits