agent/pi - pi - Penguin

fix(ai): update copilot claude test model

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

cf7f2e3dbb

feat(ai): add Together AI provider

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

7adb8e7634

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 · 2026-05-04 00:54:46 +02:00

b326bf1a3a

fix(ai): use Xiaomi Token Plan Anthropic endpoint

closes #3912

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

c0e046990e

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(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

remove gemini cli and antigravity support

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

fe66edd943

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(ai): refresh generated model catalog for release

Mario Zechner · 2026-04-27 21:28:21 +02:00

65fc803671

fix(ai): ignore unknown anthropic sse events

closes #3708

Mario Zechner · 2026-04-25 16:57:03 +02:00

3e7ffff184

fix(coding-agent): harden clipboard copy

closes #3639

Mario Zechner · 2026-04-24 12:55:58 +02:00

1e33492525

fix(ai): support xhigh for Codex GPT-5.5

Mario Zechner · 2026-04-23 22:49:09 +02:00

bf4aa3a601

test(ai): refresh responses and codex e2e coverage closes #3576

Mario Zechner · 2026-04-23 21:36:16 +02:00

535fdcea2c

fix(ai): coalesce malformed streamed tool calls closes #3576

Mario Zechner · 2026-04-23 16:05:21 +02:00

01509156b3

fix(typebox): migrate to v1 with extension compat (#3474 )

* fix(typebox): migrate to v1 with extension compat

Replace AJV-based validation with TypeBox-native validation, keep legacy extension imports working (including @sinclair/typebox/compiler), and restore coercion for serialized/plain JSON schemas.

This change closes #3112.

* fix(typebox): use canonical imports and harden coercion

Switch first-party code to canonical typebox imports while retaining legacy extension aliases in the loader.

Remove obsolete runtime codegen guards, expand serialized JSON-schema coercion coverage, and update related tests and fixtures.

Fixes #3112.

---------

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

Armin Ronacher · 2026-04-22 19:59:33 +02:00

35ff2689ee

Reapply "fix(ai): own Anthropic SSE parsing to avoid SDK JSON.parse hard-failures"

This reverts commit fc9220d2de.

Mario Zechner · 2026-04-21 23:42:19 +02:00

e58d631c89

Revert "fix(ai): own Anthropic SSE parsing to avoid SDK JSON.parse hard-failures"

This reverts commit 4b926a30a2.

Mario Zechner · 2026-04-21 23:19:52 +02:00

fc9220d2de

fix(ai): own Anthropic SSE parsing to avoid SDK JSON.parse hard-failures

Bypass the Anthropic SDK streaming parser entirely. Use
client.messages.create().asResponse() and decode the SSE stream
ourselves with defensive JSON parsing that repairs invalid escape
sequences and control characters inside string literals.

- Switch from SDK .stream() to .asResponse() + pi-owned SSE decoder
- Add repairJson() / parseJsonWithRepair() to json-parse.ts
- Add anthropic-sse-parsing.test.ts regression for malformed tool deltas
- Update github-copilot-anthropic.test.ts mock to match new call path
- Update deprecated claude-3-5-haiku-20241022 refs to claude-haiku-4-5
- Remove stale non-reasoning model test

fixes #3175

Mario Zechner · 2026-04-21 23:00:56 +02:00

4b926a30a2

fix(ai): sanitize Mistral tool schemas closes #3361

Mario Zechner · 2026-04-18 00:54:46 +02:00

2dddc5ba25

fix(ai): prune deprecated direct minimax models

Mario Zechner · 2026-03-25 22:44:32 +01:00

6dc43d6dd1

feat(ai): add requestMetadata support to BedrockOptions for cost allocation tagging (#2511 )

Add an optional requestMetadata field to BedrockOptions that forwards
key-value pairs to the Bedrock Converse API ConverseStreamCommand. Tags
appear in AWS Cost Explorer split cost allocation data, enabling callers
to attribute inference costs to specific applications or contexts.

Changes:
- Add requestMetadata?: Record<string, string> to BedrockOptions with
  JSDoc documenting AWS constraints (max 50 pairs, key 64 chars, value
  256 chars, no aws: prefix)
- Pass requestMetadata to commandInput via conditional spread to avoid
  sending undefined when omitted
- Export BedrockOptions from package root (consistent with other
  provider option types)
- Add E2E tests: metadata forwarded to SDK payload, and omitted when
  not provided

closes #2510

wjonaskr · 2026-03-22 19:05:55 +01:00

3bcbae490c

fix(ai): support GOOGLE_CLOUD_API_KEY for google-vertex (#1948 ) (#1976 )

Gordon Hui · 2026-03-09 13:30:22 +01:00

01f7faae9c

Merge branch 'feat/use-mistral-sdk'

Mario Zechner · 2026-03-05 23:49:29 +01:00

a31065166d

feat(ai): add github-copilot gpt-5.3-codex fallback closes #1853

Mario Zechner · 2026-03-05 21:47:52 +01:00

8f2af2ae7e

refactor(ai): migrate mistral provider to conversations sdk

Abdeslam Yassine Agmar · 2026-03-03 17:25:50 +00:00

eb9f1183ad

fix(ai,coding-agent): update antigravity gemini 3.1 models and headers

fixes #1761

Mario Zechner · 2026-03-03 14:54:43 +01:00

7bd4c45d81

Closes #1671 , switch to GLM-5 for tests

Mario Zechner · 2026-02-27 21:35:40 +01:00

afe9ae06e8

feat: add configurable transport and codex websocket session caching

Mario Zechner · 2026-02-13 23:41:49 +01:00

a26a9cfabd

refactor(ai): fix inconsistencies, trim ai code+replace tests, remove unnceccessary tool_result check

Nate Smyth · 2026-02-12 18:41:12 +01:00

2419412483

ai: update Antigravity system instruction to compact version, fix flaky tool test

- Replace verbose ANTIGRAVITY_SYSTEM_INSTRUCTION with compact version from CLIProxyAPI
- Replace bridgePrompt override with [ignore] wrapper pattern
- Switch Antigravity Gemini test model from gemini-3-flash to gemini-3-pro-high
- Rename calculator tool to math_operation (gemini-3-pro ignores schema for 'calculator')

closes #1415

Mario Zechner · 2026-02-08 23:37:09 +01:00

ed9255d3bd

fix(ai): handle bedrock opus 4.6 adaptive thinking and interleaved beta

Markus Ylisiurunen · 2026-02-06 10:27:13 +02:00

d3d3ef4155

feat(ai): add adaptive thinking support for Claude Opus 4.6

- Add adaptive thinking mode (type: 'adaptive') for Opus 4.6+
- Add effort parameter ('low', 'medium', 'high', 'max') for adaptive thinking
- thinkingEnabled now auto-detects: adaptive for 4.6+, budget-based for older
- streamSimple/completeSimple map ThinkingLevel to effort levels for Opus 4.6
- Add tests for Opus 4.6 adaptive thinking and GPT-5.3 Codex
- Update @anthropic-ai/sdk to 0.73.0
- Update @aws-sdk/client-bedrock-runtime to 3.983.0
- Update @google/genai to 1.40.0
- Remove fast-xml-parser override (no longer needed)

Mario Zechner · 2026-02-05 21:14:11 +01:00

4c4d787b1a

feat(ai): add Kimi For Coding provider support

- Add kimi-coding provider using Anthropic Messages API
- API endpoint: https://api.kimi.com/coding/v1
- Environment variable: KIMI_API_KEY
- Models: kimi-k2-thinking (text), k2p5 (text + image)
- Add context overflow detection pattern for Kimi errors
- Add tests for all standard test suites

Mario Zechner · 2026-01-29 04:12:28 +01:00

87ab5c5c3b

feat(ai): add Hugging Face provider support

- Add huggingface to KnownProvider type
- Add HF_TOKEN env var mapping
- Process huggingface models from models.dev (14 models)
- Use openai-completions API with compat settings
- Add tests for all provider test suites
- Update documentation

fixes #994

Mario Zechner · 2026-01-29 02:40:14 +01:00

c808de605a

fix: typos in comments (fixes #1016 )

mom · 2026-01-28 01:56:34 +00:00

ebd8e895ce

refactor(ai): register api providers

Mario Zechner · 2026-01-24 23:15:11 +01:00

c725135a76

add Azure deployment name map and refresh generated models

Markus Ylisiurunen · 2026-01-24 12:04:34 +01:00

085c378d34

add Azure OpenAI Responses provider with deployment-aware model mapping

Markus Ylisiurunen · 2026-01-24 12:04:34 +01:00

856012296b

fix(ai): normalize tool call ids and handoff tests fixes #821

Mario Zechner · 2026-01-19 00:10:49 +01:00

2c7c23b865

feat(ai): add strictResponsesPairing for Azure OpenAI Responses API

Split OpenAICompat into OpenAICompletionsCompat and OpenAIResponsesCompat
for type-safe API-specific compat settings. Added strictResponsesPairing
option to suppress orphaned reasoning/tool calls on incomplete turns,
fixing 400 errors on Azure's Responses API which requires strict pairing.

Closes #768

Mario Zechner · 2026-01-18 20:15:33 +01:00

d43930c818

Add more models to stream.test.ts for Vercel, set infinite timeout on OpenAI responses, closes #690

Mario Zechner · 2026-01-13 17:08:56 +01:00

28072cb31f

Add handleImage and multiTurn tests for vercel-ai-gateway in stream.test.ts

Mario Zechner · 2026-01-13 16:56:48 +01:00

1d8d5d3d88

Rename to vercel-ai-gateway for clarity

Timo Lins · 2026-01-13 16:42:34 +01:00

65eb738c90

Add Vercel AI Gateway support

Timo Lins · 2026-01-13 16:42:34 +01:00

164a69a601

Add MiniMax provider support (#656 by @dannote)

- Add minimax to KnownProvider and Api types
- Add MINIMAX_API_KEY to getEnvApiKey()
- Generate MiniMax-M2 and MiniMax-M2.1 models
- Add context overflow detection pattern
- Add tests to all required test files
- Update README and CHANGELOG with attribution

Also fixes:
- Bedrock duplicate toolResult ID when content has multiple blocks
- Sandbox extension unused parameter lint warning

Mario Zechner · 2026-01-13 02:27:09 +01:00

8af8d0d672

feat(ai): Add Amazon Bedrock provider (#494 )

Adds support for Amazon Bedrock with Claude models including:
- Full streaming support via Converse API
- Reasoning/thinking support for Claude models
- Cross-region inference model ID handling
- Multiple AWS credential sources (profile, IAM keys, API keys)
- Image support in messages and tool results
- Unicode surrogate sanitization

Also adds 'Adding a New Provider' documentation to AGENTS.md and README.

Co-authored-by: nickchan2 <nickchan2@users.noreply.github.com>

Mario Zechner · 2026-01-13 00:32:59 +01:00

fd268479a4

fix: codex thinking handling

Ben Vargas · 2026-01-05 21:55:47 +01:00

02b72b49d5

fix(ai): append system prompt to codex bridge message instead of converting to input

Previously the system prompt was converted to an input message in convertMessages,
then stripped out by filterPiSystemPrompts. Now the system prompt is passed directly
to transformRequestBody and appended after CODEX_PI_BRIDGE in the bridge message.

Mario Zechner · 2026-01-05 06:03:07 +01:00

bb50738f7e

Merge hooks and custom-tools into unified extensions system (#454 )

Breaking changes:
- Settings: 'hooks' and 'customTools' arrays replaced with 'extensions'
- CLI: '--hook' and '--tool' flags replaced with '--extension' / '-e'
- API: HookMessage renamed to CustomMessage, role 'hookMessage' to 'custom'
- API: FileSlashCommand renamed to PromptTemplate
- API: discoverSlashCommands() renamed to discoverPromptTemplates()
- Directories: commands/ renamed to prompts/ for prompt templates

Migration:
- Session version bumped to 3 (auto-migrates v2 sessions)
- Old 'hookMessage' role entries converted to 'custom'

Structural changes:
- src/core/hooks/ and src/core/custom-tools/ merged into src/core/extensions/
- src/core/slash-commands.ts renamed to src/core/prompt-templates.ts
- examples/hooks/ and examples/custom-tools/ merged into examples/extensions/
- docs/hooks.md and docs/custom-tools.md merged into docs/extensions.md

New test coverage:
- test/extensions-runner.test.ts (10 tests)
- test/extensions-discovery.test.ts (26 tests)
- test/prompt-templates.test.ts

Mario Zechner · 2026-01-05 01:43:35 +01:00

c6fc084534

67 Commits