* 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.
supportsPromptCaching, supportsAdaptiveThinking, supportsThinkingSignature,
and the Claude detection in streamSimpleBedrock/buildAdditionalModelRequestFields
all check model.id for Claude model name patterns. Application inference profile
ARNs are opaque and do not contain the model name, so these checks silently fail.
Fix by also checking model.name (user-controlled via models.json or
registerProvider) as a fallback in all affected functions. Added a shared
isAnthropicClaudeModel helper for the common Claude detection pattern.
Fixes#2925
Co-authored-by: Your Name <you@example.com>
DashScope / Aliyun Qwen (OpenAI-compatible) rejects `tools: []`
with HTTP 400 `"[] is too short - 'tools'"`. Five providers used
a truthy check (`if (context.tools)`) that treated an empty array
as "send tools", so `pi --no-tools` produced `tools: []` in the
request body. Matching the Google provider's pattern, we now
guard on `context.tools.length > 0`:
- openai-completions.ts
- openai-responses.ts
- openai-codex-responses.ts
- azure-openai-responses.ts
- anthropic.ts
The openai-completions fallback that emits `tools: []` when the
conversation has tool history (required by LiteLLM / Anthropic
proxies) is preserved via the existing `else if (hasToolHistory)`
branch.
closes#3649
Co-authored-by: 槐聚 <huaiju@zbyte-inc.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
* 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>
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
* fix(ai): replace stale OpenRouter Llama 4 Maverick test model
- Switch OpenRouter Meta test model from `meta-llama/llama-4-maverick` to `meta-llama/llama-4-scout` in AI tests.
- CI failure body:
- packages/ai/test/context-overflow.test.ts(531,41): error TS2345: Argument of type "meta-llama/llama-4-maverick" is not assignable to parameter of type "...".
- packages/ai/test/total-tokens.test.ts(520,40): error TS2345: Argument of type "meta-llama/llama-4-maverick" is not assignable to parameter of type "...".
* chore(ai): add changelog entry for OpenRouter test model swap
- Add Unreleased Fixed entry for switching OpenRouter Meta test model to llama-4-scout
- Reference PR #3421 attribution
The openai-completions provider now calls .withResponse() on the
create() result to surface HTTP status/headers for the new onResponse
hook (d131fcd4). The FakeOpenAI test mock only returned an async
iterable, so 4 tests in openai-completions-tool-choice.test.ts that
actually consume the stream failed with "withResponse is not a function".
Updated the mock to return a Promise augmented with .withResponse()
resolving to { data: <async iterable>, response: { status, headers } }.
closes#3304
