KimiProvider#

Connect a provider and configure retries, credentials, and transport. See the guide.

class zett_agent.providers.kimi.KimiProvider(model, api_key, transport=None, *, base_url=None, temperature=None, retry=RetryOptions(base_delay=0.25, max_delay=8.0, max_retries=3), timeout=TimeoutOptions(connect=5.0, first_byte=60.0, idle=600.0), send_prompt_cache_key=True, extra_headers=None, extra_query=None, extra_body=None)[源代码]#

Stream Kimi through its OpenAI-compatible protocol.

参数:

  • model (str) -- Kimi model identifier, such as kimi-k3 or kimi-k2.6.

  • api_key (str) -- Moonshot API key.

  • transport (httpx.AsyncBaseTransport | None) -- Optional HTTPX transport for custom routing or tests.

  • base_url (str | None) -- API root; None uses https://api.moonshot.ai/v1. Accounts on the China platform use https://api.moonshot.cn/v1.

  • temperature (float | None) -- Optional sampling temperature.

  • retry (RetryOptions) -- Model-owned retry/backoff policy; never restarts an emitted stream.

  • timeout (TimeoutOptions) -- How long the provider may stay silent before the request is given up on. See TimeoutOptions.

  • send_prompt_cache_key (bool) -- Declare the run's prompt cache key on every request.

  • extra_headers (Mapping[str, str] | None) -- HTTP headers sent on every request after the adapter's own.

  • extra_query (Mapping[str, str] | None) -- URL query parameters sent on every request.

  • extra_body (Mapping[str, JsonValue] | None) -- JSON fields merged into every request body last, so they add an option the adapter does not model and may override one it does, such as thinking.

备注

Reasoning fields are sent only to the models that document them: reasoning_effort for kimi-k3, thinking for kimi-k2.6 and kimi-k2.7-code. Any other model gets none, and extra_body is the way to give it one. kimi-k3 always reasons and kimi-k2.7-code cannot switch thinking off, so an OFF effort is not sent to them.

示例

Stream a Kimi model:

model = KimiProvider(model="kimi-k3", api_key=os.environ["MOONSHOT_API_KEY"])
try:
    client = await create_agent(model)
    print((await client.run("Explain this function")).content)
finally:
    await model.aclose()
provider_name = 'kimi'#

Name stored on messages this provider produced and compared before reasoning is replayed.

request_fields(request)[源代码]#

Spell the reasoning level the way this model takes it.

参数:

request (ModelRequest)

返回类型:

dict[str, JsonValue]

async aclose()#

Close the SDK's owned HTTP connection pool.

返回类型:

None

chat_stop(finish_reason, *, has_tool_calls, refusal_text, stream_error, native_finish_reason)#

Say why the response ended. Override it for a service with finish reasons of its own.

参数:

  • finish_reason (str | None)

  • has_tool_calls (bool)

  • refusal_text (str)

  • stream_error (Mapping[str, JsonValue])

  • native_finish_reason (str | None)

返回类型:

StopInfo

merge_replay(blocks, fragment)#

Add one streamed opaque block (ChatDelta.replay) to the ones collected so far.

The default appends. A service that streams one block in pieces overrides this to join them, and blocks is what finally becomes replay_blocks.

参数:
返回类型:

None

native_deferred_tools = False#

See zett_agent.model.NativeDeferredToolsModel.native_deferred_tools. A provider opts in by overriding this on its class; the default keeps Responses, Chat Completions, Google, and Ollama on the withhold-and-search path.

read_delta(delta)#

Read one streamed delta.

The default reads content, refusal, tool_calls, and the first of reasoning_keys that has text. A service with fields of its own returns a ChatDelta that also carries them, usually by extending super().read_delta.

参数:

delta (Mapping[str, JsonValue])

返回类型:

ChatDelta

read_usage(usage)#

Read the usage object of a chunk.

The default accepts every spelling of the cache and reasoning counters that the compatible services use.

参数:

usage (Mapping[str, JsonValue])

返回类型:

ModelUsage

reasoning_keys = ('reasoning_content', 'reasoning')#

Fields of a streamed delta that carry reasoning text, in order of preference. Services differ on the name (reasoning_content and reasoning are the two in use), and reading both is harmless because only the first one that has text is used.

replay_reasoning(message, payload)#

Add what this service needs of an earlier assistant turn to its rendered payload.

The default returns the reasoning as reasoning_content, which reasoning services expect to see again on later requests. A message from another provider is skipped, because reasoning from one model is not context for another.

参数:
返回类型:

None

response = False#

Whether this adapter uses a Responses-style endpoint instead of its provider's traditional message or chat-completions endpoint. Only the providers read it; the runtime does not.

status_error(error)#

Turn an HTTP failure into the typed error the runtime reports.

The default reports a refusal the service sent as an HTTP error, a rejected credential, and everything else as ProviderHTTPError. A service that explains failures in a body of its own overrides this and falls back to super().

参数:

error (APIStatusError)

返回类型:

ProviderError

sync(*, runtime=None)#

Return a context-managed synchronous view; optionally share a runtime.

Omitting runtime creates a new background thread for this view. Passing an existing runtime reuses its loop and leaves its shutdown to the caller. This API is for service entry points, not Extension lifecycle hooks.

示例

Use a model or tool from a plain function:

with read_file.sync() as read:
    result = read({"path": "README.md"})
参数:

runtime (SyncRuntime | None)

返回类型:

SyncObject[Self]

vendor_headers()#

Return the headers this service wants on every request.

They are sent before extra_headers, so the application can still replace one.

返回类型:

dict[str, str]