ToolGuidelinesExtension#

Build extensions, choose hooks, and manage request-scoped state. See the guide.

class zett_agent.extensions.tool_guidelines.ToolGuidelinesExtension(*, placement=ToolGuidancePlacement.SYSTEM_PROMPT, snippets=True, guidelines=True)[源代码]#

Show registered tool snippets and guidelines to the model.

By default the guidance becomes system instructions, grouped so the model can scan every call shape first. Set placement to ToolGuidancePlacement.DESCRIPTION to attach each tool's snippet and guidelines to that tool's own description instead; the system prompt then carries nothing. Use it for endpoints and gateways that surface only tool definitions, or when the guidance should travel with the tool wherever the definition goes.

Tools marked deferred=True are skipped in both modes: their definitions reach the model through tool search, so rendering their guidance would announce a tool that is not callable yet. Tool search appends their guidelines to the definition it returns.

参数:

  • placement (ToolGuidancePlacement) -- Where the guidance goes; the system prompt by default.

  • snippets (bool) -- Include each tool's Snippet section.

  • guidelines (bool) -- Include each tool's Guidelines section. Placement into descriptions renders only the parts enabled here.

示例

Keep guidance in the tool definitions:

agent = await Agent.create(
    model,
    extensions=[
        CodingExtension(),
        ToolGuidelinesExtension(placement=ToolGuidancePlacement.DESCRIPTION),
    ],
)

备注

Description placement edits only the request sent to the provider. The registered tools, stored history, and the persisted system messages are unchanged, so switching placement between runs never rewrites a session.

property in_system_prompt: bool#

Whether this extension writes guidance into the system instructions.

async on_state(context)[源代码]#

Place guidance after existing system instructions and before dialogue.

参数:

context (AgentRunContext)

返回类型:

None

async on_model_request(context, request, call_next)[源代码]#

Fold guidance into tool descriptions when that placement is selected.

参数:
返回类型:

AsyncIterator[ModelEvent]

accept(config, event)#

Handle one external event and report whether it was accepted.

The Agent broadcasts each event to every registered extension. Override this synchronous hook when an extension waits for input from another thread, HTTP request, TUI, or Web UI. The default ignores the event. Config is passed separately and can be None before initialization. Each extension decides whether the supplied identity and payload match its protocol. Return True to include this extension's name in the broadcast result; returning False does not stop later receivers.

参数:
返回类型:

bool

async after_model(context, response)#

Run after the complete assistant message is appended.

参数:
返回类型:

None

async after_run(context, result)#

Run after a successful final answer is appended.

参数:
返回类型:

None

async after_tool(context, call, result, error)#

Inspect or modify a tool result before it is appended.

error is the original execution exception for a failed result and None after successful execution. Changes made to result are included in context, persistence, and the next model request. Raising prevents the result from being appended.

参数:
返回类型:

None

async after_turn(context, result)#

Run once the turn's assistant message and tool results are settled.

result is the assistant message that opened the turn: either the final answer, or the tool-calling message whose ToolMessages were appended. Every requested call is settled first, including calls that failed, and calls that steering skipped, which arrive as unsuccessful or skipped ToolMessages.

Steering that interrupts a turn is accepted while the runtime settles that batch, so its UserMessage is already appended when this hook runs and the steering turn follows as the next turn.

A turn that never completed, because the request failed or was cancelled, has no after_turn call; use on_error and RunCancelledEvent for those paths.

参数:
返回类型:

None

async before_model(context, request)#

Inspect the current request before preprocessing a primary model call.

Request fields are frozen. Change messages through AgentRunContext.add_message() or AgentRunContext.replace_messages(), local tools through context.tools, and provider tools through context.server_tools; the runtime rebuilds these fields before the next hook and before calling the provider. This is a shallow request view, not an immutable copy of each message or tool definition.

示例

Inspect the tools offered in this iteration:

async def before_model(self, context, request):
    offered = {definition.name for definition in request.tools}
    if "write_file" in offered:
        context.add_message(
            SystemMessage(content="Read existing files before editing."),
        )
参数:
返回类型:

None

async before_run(context)#

Run after the transformed user input is appended and published.

参数:

context (AgentRunContext)

返回类型:

None

async before_tool(context, call)#

Run before one requested tool is invoked.

参数:
返回类型:

None

async before_turn(context)#

Run before this turn's model call.

Runs after before_run() on the first turn and after the previous turn's after_turn() on later ones. Model request assembly, compaction, and before_model() follow this hook, so context edited here reaches the provider.

参数:

context (AgentRunContext)

返回类型:

None

property name: str#

Unique registration identity, defaulting to the concrete class name.

Override with a class attribute or assign an instance name to register independently configured instances of the same extension type.

async on_compact(context)#

Summarize restored context when a caller asks for compaction.

Agent.compact restores the session through on_tool and on_state exactly as a request does, appends no input message, and makes no primary model call: the only work a compaction pass does is what this hook performs. The default does nothing, so an extension with nothing to compact pays nothing.

示例

Usage:

async def on_compact(self, context):
    await self.compact(context)
参数:

context (AgentRunContext)

返回类型:

None

async on_error(context, error)#

Run before an agent error is propagated to the caller.

参数:
返回类型:

None

async on_event(context, event)#

Process a published notification; inspect its concrete type with match.

参数:
返回类型:

None

async on_message(context)#

Transform context.input_message after state restoration, before append.

Replace the pending UserMessage to implement externally selected modes. Do not append or persist it here: the runtime appends the final message exactly once after all input hooks finish. before_run sees that message through AgentRunContext.add_message() or AgentRunContext.replace_messages(), and persistence subscribers have already received it.

参数:

context (AgentRunContext)

返回类型:

None

async on_success(context, result)#

Run once after all after_run hooks succeed, before RUN_COMPLETED.

This callback observes a completed request, not an intermediate model step. Failed or cancelled requests do not trigger it. Callback errors propagate through on_error and prevent RUN_COMPLETED from being emitted.

示例

Usage:

async def on_success(self, context, result):
    await save_answer(context.session_id, result.content)
参数:
返回类型:

None

async on_tool(context)#

Register local or provider-hosted tools before context restoration.

All extensions finish this hook before the first on_state() call, so prompt extensions can reliably inspect context.tools and context.server_tools as complete request-scoped registries.

示例

Usage:

async def on_tool(self, context):
    context.register_tool(read_file)
    context.register_server_tool(ServerToolDefinition(type="web_search"))
参数:

context (AgentRunContext)

返回类型:

None

async on_tool_call(context, call, call_next)#

Wrap one registered local tool handler and return its ToolResult.

An extension may adjust call.arguments, return without calling the next layer, transform its result, or raise into normal tool-failure handling.

参数:
返回类型:

ToolResult

property pending: bool#

Return whether this extension is participating in an active request.

The Agent updates this state for every registered extension, including extensions whose hooks are currently idle. One extension instance may be shared by multiple Agents and sessions; pending remains true until all requests using that instance have finished, failed, or been cancelled. Persistent data retained between requests does not count.