* 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.
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>
Mutate persisted tool-call blocks in place on function_call completion,
remove partialJson, and emit the same reference on toolcall_end.
Add regression coverage for persisted block cleanup and event identity.
fixes#3078
Map unknown finish_reason values (e.g. "end" from Ollama/LM Studio) to
"stop" instead of throwing, since assistant content is already produced.
fixes#2142
Some OpenAI-compatible providers (e.g., Moonshot/Kimi) return usage
data in chunk.choices[0].usage instead of the standard chunk.usage.
Extract usage parsing into a helper and check choice.usage as fallback.
closes#2017
The OpenAI Chat Completions API standard format for assistant message
content is a plain string. Sending it as an array of
{type:"text", text:"..."} objects causes some models (notably DeepSeek
V3.2 via NVIDIA NIM) to mirror the content-block structure literally
in their output. This produces recursive nesting where each turn wraps
the previous content blocks deeper:
[{'type':'text','text':'[{\'type\':\'text\',\'text\':...}]'}]
The fix unifies the assistant content serialization to always use a
joined string — the same approach already used for the github-copilot
provider — for all openai-completions backends.
Affected models observed: deepseek-ai/deepseek-v3.2 (nvidia provider).
Models like GLM-5, GPT-4, Claude were unaffected as they tolerate
array content, but sending a standard string is safer for all.
Co-authored-by: geraldoaax <geraldoaax@users.noreply.github.com>
Z.ai uses the same enable_thinking: boolean parameter as Qwen to control reasoning, not thinking: { type: "enabled" | "disabled" }.
The wrong parameter name means Z.ai ignores the disable request and always runs with thinking enabled, wasting tokens and adding latency.
Merge the Z.ai and Qwen branches since they use the same format.
PR by @okuyam2y
* feat(ai): add Vercel AI Gateway routing support
Add vercelGatewayRouting to OpenAICompletionsCompat, parallel to
openRouterRouting. When a model targets ai-gateway.vercel.sh and has
vercelGatewayRouting configured, the openai-completions provider passes
providerOptions.gateway with only/order in the request body.
Changes:
- types.ts: VercelGatewayRouting interface + field on OpenAICompletionsCompat
- openai-completions.ts: buildParams passes providerOptions.gateway,
detectCompat/getCompat include the new field
- model-registry.ts: VercelGatewayRoutingSchema for models.json validation
- test: updated Required<OpenAICompletionsCompat> in test fixture
* docs(coding-agent): add vercelGatewayRouting to custom models documentation
- Handle pipe-separated IDs from OpenAI Responses API in openai-completions provider
- Strip trailing underscores after truncation in openai-responses-shared (OpenAI Codex rejects them)
- Add regression tests for tool call ID normalization
fixes#1022
Allows custom models to specify which upstream providers OpenRouter
should route requests to via the `openRouterRouting` field in model
definitions.
Supported fields:
- `only`: list of provider slugs to exclusively use
- `order`: list of provider slugs to try in order
- Added headers field to base StreamOptions interface
- Updated all providers to merge options.headers with defaults
- Forward headers and onPayload through streamSimple/completeSimple
- Bedrock not supported (uses AWS SDK auth)
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
Previously, OpenAI-compatible provider settings (like developer role support)
were detected only from the baseUrl. When using custom URLs (e.g., proxies),
detection failed. Now checks model.provider first, then falls back to URL.
Fixes#774
Z.ai uses thinking: { type: "enabled" | "disabled" } instead of
OpenAI's reasoning_effort. Added thinkingFormat compat flag to handle
this. Thinking is now explicitly enabled/disabled based on user setting.
