GLMAnthropicProvider#

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

class zett_agent.providers.glm.GLMAnthropicProvider(model, api_key, transport=None, *, base_url=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), max_tokens=16384, extra_headers=None, extra_query=None, extra_body=None)[source]#

Stream GLM through its Anthropic Messages protocol.

Use it for a tool that speaks Messages, or to keep a conversation on the protocol the rest of the application uses. GLMProvider is the same service over Chat Completions.

Parameters:

  • model (str) – GLM model identifier, such as glm-5.1.

  • api_key (str) – Z.ai API key, sent as a bearer token.

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

  • base_url (str | None) – API root; None uses https://api.z.ai/api/anthropic. Accounts on the China platform use https://open.bigmodel.cn/api/anthropic.

  • 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.

  • max_tokens (int) – Output budget for one response, excluding thinking.

  • 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 (dict[str, JsonValue]) – JSON fields merged into every request body last.

Note

Thinking is requested with Anthropic’s standard thinking field, for GLM-4.6 and later; an older model gets none. GLM-5.3 always thinks, so an OFF effort sends nothing to it. Z.ai documents only how Claude Code reaches this endpoint, not which Messages fields it reads, so use extra_body if your model needs another.

Examples

Stream a GLM model over Messages:

model = GLMAnthropicProvider(model="glm-5.1", api_key=os.environ["ZAI_API_KEY"])
try:
    client = await create_agent(model)
    print((await client.run("Explain this function")).content)
finally:
    await model.aclose()
provider_name: str = 'glm-anthropic'#

Name stored on messages this provider produced. Signed blocks are sent back only to the same name and model.

bearer_auth: ClassVar[bool] = True#

Authenticate with Authorization: Bearer as well as x-api-key. The services that take only the bearer token ignore the other header.

request_fields(request)[source]#

Request thinking from the models that have it, and nothing from the ones that do not.

Parameters:

request (ModelRequest)

Return type:

dict[str, JsonValue]

async aclose()#

Close the owned SDK connection pool.

Return type:

None

finish_usage(usage, update)#

Fold the usage object of the message_delta event into usage.

The default takes the final output_tokens, which is the only count Anthropic updates.

Parameters:
Return type:

ModelUsage

mark_cache(body, client_tools)#

Put cache markers into body (and the tool definitions in client_tools).

The default marks Anthropic’s breakpoints on the largest stable request prefixes: the tool definitions, the whole system prompt, and the conversation so far. Anthropic caches only what a cache_control marker asks for, then reads each cached prefix at a fraction of the input price. A prefix shorter than the model’s minimum cacheable length is ignored silently. Nothing is marked unless prompt_cache is on.

Parameters:
Return type:

None

message_stop(finish_reason, details, *, has_tool_calls)#

Say why the response ended, from stop_reason and stop_details.

Parameters:

  • finish_reason (str | None)

  • details (Mapping[str, JsonValue])

  • has_tool_calls (bool)

Return type:

StopInfo

native_deferred_tools: bool = False#

See zett_agent.model.NativeDeferredToolsModel.native_deferred_tools. Only Anthropic itself loads a defer_loading tool when a tool_reference names it.

response: bool = 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.

start_usage(usage)#

Read the usage object of the message_start event.

Cache reads and writes are reported next to input_tokens, not inside it, so the total input is their sum.

Parameters:

usage (Mapping[str, JsonValue])

Return type:

ModelUsage

status_error(error)#

Turn an SDK failure from opening the request into the typed error the runtime reports.

Parameters:

error (AnthropicError)

Return type:

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.

Examples

Use a model or tool from a plain function:

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

runtime (SyncRuntime | None)

Return type:

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.

Return type:

dict[str, str]