Files
openworker/coworker/events.py
T
Devika Verma f08a3c425b compaction: engine hook, failure policy, persistence (OPE-27 2/4)
Minimal engine footprint: a checkpoint at each iteration top (between tool
turns and before a new turn), the usage signal captured per round-trip
(context_tokens; chars/4 estimate when never reported), and
_outbound_messages consulting the boundary. The summarizer runs off-loop
through the normal provider router, so the Settings model pin is just an
id.

Failure policy per spec: retry once in both modes; attended sessions get
the Retry / Trim-oldest-10% prompt (via the ask_user plumbing, gated by an
is_attended callback the WS surface wires); unattended runs auto-trim and
continue — never parked on internal bookkeeping. Raw context-overflow 400s
from the main model route into the same policy, progress-guarded so a
still-overflowing model terminates in the error path.

CompactionState persists on the session record (new sqlite column, same
defensive parse as grants), so reloads keep the compacted view. A
persisted compacted notice + a new COMPACTED event mark the spot for
the GUI divider (rendered in commit 3).
2026-07-29 16:13:14 +05:30

41 lines
1.3 KiB
Python

"""Event model — the contract between the turn engine and any surface (TUI/GUI/IDE).
No token streaming in v1, so granularity is per-message/per-tool. Streaming later adds
`assistant_delta` / `tool_output_delta` without changing the rest.
"""
from __future__ import annotations
from dataclasses import dataclass, field
from enum import Enum
from typing import Any
class EventType(str, Enum):
TURN_START = "turn_start"
ASSISTANT_DELTA = "assistant_delta"
REASONING_DELTA = "reasoning_delta" # model thinking text (display-only, never replayed)
ASSISTANT_MESSAGE = "assistant_message"
TOOL_PROPOSED = "tool_proposed"
PERMISSION_REQUIRED = "permission_required"
DIRECTORY_REQUESTED = "directory_requested" # agent asks the user to grant a folder
QUESTION_REQUESTED = (
"question_requested" # agent asks the user a free-text/multiple-choice question
)
PLAN_PROPOSED = (
"plan_proposed" # agent presents a plan for approval (plan mode exit)
)
TOOL_STARTED = "tool_started"
TOOL_FINISHED = "tool_finished"
ITERATION_END = "iteration_end"
TURN_END = "turn_end"
ERROR = "error"
INTERRUPTED = "interrupted"
COMPACTED = "compacted" # outbound history was compacted (summary or trim)
@dataclass
class Event:
type: EventType
data: dict[str, Any] = field(default_factory=dict)