JSONLExtension#

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

class zett_agent.extensions.jsonl.JSONLExtension(directory)[源代码]#

Append each complete Agent turn as one line in a session JSONL file.

A turn begins with the request's finalized UserMessage and includes every assistant, tool, internal-agent, and steering message appended before the terminal outcome. Model retries and tool loops remain inside that one line; history from earlier turns is not copied again.

Each record also contains AgentRunContext metadata and tags. Message attributes remain attached to their messages. Completed, failed, and cancelled turns are recorded, while raw exception objects and provider credentials are not.

参数:

directory (str | Path) -- Directory that owns the per-session .jsonl files. Session IDs are URL-safe Base64 encoded for canonical, traversal-safe names.

示例

Usage:

history = JSONLExtension(".agent-turns")
agent = await Agent.create(
    model,
    config=AgentRunConfig("session-42"),
    extensions=[history],
)

await agent.run(
    "Inspect the failing test",
    metadata={"source": "editor"},
    tags={"intent": "debug"},
)

print(history.session_path("session-42"))

备注

Writes from one extension instance are serialized with a lock. The extension does not coordinate independent processes writing the same directory.

session_path(session_id)[源代码]#

Return the canonical JSONL path for one session without creating it.

参数:

session_id (str)

返回类型:

Path

async before_run(context)[源代码]#

Remember the finalized input that marks the start of this turn.

参数:

context (AgentRunContext)

返回类型:

None

async on_success(context, result)[源代码]#

Append one completed turn after the final assistant response exists.

参数:
返回类型:

None

async on_error(context, error)[源代码]#

Append one failed turn with a safe error summary.

参数:
返回类型:

None

async on_event(context, event)[源代码]#

Append a cancelled turn from its dedicated terminal notification.

参数:
返回类型:

None

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_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_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_model_request(context, request, call_next)#

Wrap one provider request and its complete streamed response.

Pass request (or a dataclass replacement) to call_next. The default closes the inner stream so cancellation reaches the provider.

参数:
返回类型:

AsyncIterator[ModelEvent]

async on_state(context)#

Restore history and initialize state before any input conversion.

示例

Usage:

async def on_state(self, context):
    context.add_message(SystemMessage(content="Use concise answers."), index=0)
参数:

context (AgentRunContext)

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.