agent/pi - pi - Penguin

feat(ai): add Codex device code login

Vegard Stikbakke · 2026-05-20 15:31:54 +02:00

1ffeb828d3

feat(ai): add device code login callback and use for copilot

Vegard Stikbakke · 2026-05-20 12:28:12 +02:00

bf5ac0011e

fix(ai): stop defaulting max token request caps

closes #4675

Mario Zechner · 2026-05-19 11:49:44 +02:00

2787b601d7

fix(ai): clamp OpenAI prompt cache keys

closes #4720

Mario Zechner · 2026-05-19 10:51:11 +02:00

7be75baded

fix(ai): add Xiaomi reasoning replay compat

closes #4678

Mario Zechner · 2026-05-18 11:15:20 +02:00

b8f51957a0

fix(ai): skip unknown bedrock content blocks

closes #4223

Mario Zechner · 2026-05-18 01:42:18 +02:00

9e2bfc7c40

fix(ai): normalize opencode go reasoning replay

closes #4251

Mario Zechner · 2026-05-18 01:11:23 +02:00

21d80deda2

Closes #4342

Mario Zechner · 2026-05-17 23:55:25 +02:00

b256ac7d77

fix(ai): update OpenAI Codex model list

Mattia Cerutti · 2026-05-17 03:12:19 +02:00

1af823be9d

fix(ai): detect litellm context overflow errors

closes #4563

Mario Zechner · 2026-05-16 23:29:22 +02:00

7c5c3d6fd6

Merge pull request #4558 from earendil-works/fix/openai-completions-throw-on-missing-finish_reason

fix(ai): openai-completions - throw error on missing finish-reason

Mario Zechner · 2026-05-16 22:54:42 +02:00

0412f62f9e

fix(ai): preserve OpenRouter cached token semantics

Armin Ronacher · 2026-05-16 11:55:16 +02:00

87881ca686

fix(ai): openai-completions - throw error on missing finish-reason

- require \ before treating \ streams as successful
- add regression coverage for truncated streams without \
- closes #4345

Ramiz Wachtler · 2026-05-15 15:26:57 +02:00

98ffad0437

fix(ai): ignore generic GitHub tokens for Copilot auth

closes #4485

Mario Zechner · 2026-05-15 01:26:31 +02:00

a8af0b5e99

fix(ai): honor retry-after for OpenAI Codex SSE retries

- honor `retry-after-ms` and `retry-after` for OpenAI Codex SSE retries
- add SSE retry coverage for millisecond, seconds, date, and fallback delays

Ramiz Wachtler · 2026-05-13 19:44:07 +02:00

0ae909316a

refactor(ai): use HTTP proxy agents for Bedrock

Mario Zechner · 2026-05-13 16:12:48 +02:00

a5cca409d8

Merge pull request #4358 from yanirz/fix/fireworks-session-affinity-cache

fix(ai): add session affinity and compat fixes for Fireworks provider caching

Mario Zechner · 2026-05-10 18:00:52 +02:00

cb3c42ecf5

fix(ai): align copilot claude adaptive test

Mario Zechner · 2026-05-10 17:51:08 +02:00

533d37305c

fix(ai): update copilot claude test model

Mario Zechner · 2026-05-10 17:47:45 +02:00

cf7f2e3dbb

fix(ai): add session affinity and compat fixes for Fireworks provider caching

Fireworks prompt caching is enabled by default (automatic prefix matching),
but on serverless infrastructure, requests hit random replicas. Without
session affinity, the per-replica cache misses, negating cache hit rates
and the discounted cacheRead pricing.

Changes:

- Add sendSessionAffinityHeaders and supportsCacheControlOnTools
  to AnthropicMessagesCompat interface
- Send x-session-affinity header for Fireworks (and Cloudflare AI
  Gateway Anthropic) when sessionId is available and caching is enabled
- Omit cache_control on tool definitions for Fireworks (unsupported
  per https://docs.fireworks.ai/tools-sdks/anthropic-compatibility)
- Default supportsEagerToolInputStreaming to false for Fireworks
  (unsupported field)
- Default supportsLongCacheRetention to false for Fireworks
  (cache_control.ttl not supported)
- Add compat settings to Fireworks models in generate-models.ts
- Update generated models with Fireworks compat settings
- Add integration tests for session affinity and tool compat

Refs: https://docs.fireworks.ai/guides/prompt-caching
Refs: https://docs.fireworks.ai/tools-sdks/anthropic-compatibility

yanirz · 2026-05-10 00:11:36 +02:00

99dc6fcec8

feat(ai): add Together AI provider

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

7adb8e7634

Merge pull request #3887 from cristinaponcela/feat/image-outputs

feat: image content

Mario Zechner · 2026-05-08 15:57:06 +02:00

9751057be9

fix(ai): disable OpenAI reasoning where supported

Mario Zechner · 2026-05-07 22:52:54 +02:00

783e96a144

Merge remote-tracking branch 'upstream/main' into feat/image-outputs

Cristina Poncela Cubeiro · 2026-05-07 16:46:17 +02:00

ffdf426e33

delete: images()

Cristina Poncela Cubeiro · 2026-05-07 16:21:50 +02:00

32b2cd0720

chore: migrate pi packages to earendil works scope

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

3e5ad67e0f

fix(ai): handle mixed chat completion deltas

Fixes #4228

Armin Ronacher · 2026-05-07 00:12:19 +02:00

6b271842e2

fix(ai): stop Codex OAuth stderr writes

closes #4141

Mario Zechner · 2026-05-06 00:14:40 +02:00

3029836894

e2e: add images test

Cristina Poncela Cubeiro · 2026-05-05 09:47:33 +02:00

3728e4b9e6

rename: generateImages

Cristina Poncela Cubeiro · 2026-05-05 09:30:44 +02:00

0d96b9be7f

Merge branch 'main' into feat/image-outputs

Cristina Poncela Cubeiro · 2026-05-04 16:42:51 +01:00

5731e13a61

dog

Cristina Poncela Cubeiro · 2026-05-04 17:26:50 +02:00

ab14238f1d

feat: openrouter images

Cristina Poncela Cubeiro · 2026-05-04 17:00:58 +02:00

d9adc536f5

revert

Cristina Poncela Cubeiro · 2026-05-04 15:43:45 +02:00

cbf3c333ef

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

test(ai,coding-agent): stabilize env-sensitive test cases (#4119 )

myu003 · 2026-05-03 12:55:23 +02:00

7c5ef0b70e

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

feat(ai): add cached codex websocket transport

Mario Zechner · 2026-05-01 13:07:40 +02:00

4745a95898

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 google vertex unsigned tool call replay closes #4032

Mario Zechner · 2026-04-30 21:59:21 +02:00

f7df474084

remove gemini cli and antigravity support

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

fe66edd943

feat(ai): add Mistral Medium 3.5 model (#4009 )

Johannes Ebeling · 2026-04-30 12:18:17 +02:00

779d0ef39d

feat(ai): expose routed model on openai-completions (#3968 )

Adds `AssistantMessage.responseModel` on the openai-completions path:
surfaces the concrete `chunk.model` when it differs from the requested
id (e.g. OpenRouter `auto` -> `anthropic/...`).

Alejandro · 2026-04-30 00:16:12 +02:00

e354c521f4

fix(ai): enable xhigh for DeepSeek V4 Flash

closes #3944

Mario Zechner · 2026-04-29 23:32:02 +02:00

d23cf31634

fix: modalities from openrouter

Cristina Poncela Cubeiro · 2026-04-29 09:51:57 +02:00

59a89e0c1c

fix: test (openRouterImageGeneration)

Cristina Poncela Cubeiro · 2026-04-28 14:40:13 +02:00

364ac0f3ab

292 Commits