mirror of
https://github.com/andrewyng/openworker.git
synced 2026-11-20 20:37:44 +00:00
* engine: report window occupancy as a context snapshot Estimated system/tools/conversation split + resolved window, on ready and each assistant_message; provider-reported prompt total wins when present. * gui: right rail glance layer — environment, context meter, header summaries Environment block (machine/folder/sandbox) atop the rail; Context section with proportional breakdown and compaction note; collapsed headers carry muted summary values (amber only for attention); header actions show on hover. * engine: async subagents — spawn_agent family, human-only approvals, expiry note Background children (read_only/inherit) with parent-stream approvals and a fail-closed spawn-time deadline whose tool result says the ask expired; reports steer or wake the parent; child tokens fold via the agent_task notice. * gui: Subagents section in the right rail Active + done runs with seeded icon chips and ages, amber while one waits on approval; fed by agent_task events + the sessions/tasks endpoint. * engine: persist subagent runs in a supplemental store agent_tasks.json beside the wake store, written on transitions: last 50 finished per session, 8KB report cap, live-at-restart runs marked lost. Also fixes report delivery through call_soon_threadsafe (kwargs crash). * gui: animal identity glyphs for subagents Ten one-color silhouettes with punched-out eyes, eight color families per theme; header chips on the collapsed section; done history compresses to a glyph grid past ten runs. * e2e: unshadow the compaction flow; align team/machine specs with the new rail One compact-the-context handler (signal, divider, context stamp); team header asserts the attention summary; machine-group locator scoped past the env block.
74 lines
2.5 KiB
Python
74 lines
2.5 KiB
Python
"""`context_snapshot` — the window-occupancy readout behind the GUI's Context panel (FB-015).
|
|
|
|
The split (system / tools / messages) is always a chars/4 estimate; `used` prefers the
|
|
provider-reported prompt-side total from the latest round trip and says when it had to
|
|
fall back to the estimate.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from coworker.engine import EventType, TurnEngine
|
|
from coworker.permissions import Mode, PermissionEngine
|
|
from coworker.providers import (
|
|
AssistantTurn,
|
|
ModelCapabilities,
|
|
ProviderClient,
|
|
)
|
|
from coworker.providers.base import TokenUsage
|
|
from coworker.tools import ToolRegistry
|
|
|
|
|
|
class OneReplyProvider(ProviderClient):
|
|
def __init__(self, usage: TokenUsage | None = None):
|
|
self.usage = usage
|
|
|
|
def complete(self, *, model, messages, tools=None, **settings):
|
|
return AssistantTurn(text="done", tool_calls=[], usage=self.usage)
|
|
|
|
def capabilities(self, model):
|
|
return ModelCapabilities(tools=True)
|
|
|
|
|
|
def _engine(tmp_path, provider):
|
|
return TurnEngine(
|
|
provider=provider,
|
|
registry=ToolRegistry(),
|
|
permissions=PermissionEngine(workspace_root=tmp_path, mode=Mode.INTERACTIVE),
|
|
model="m",
|
|
)
|
|
|
|
|
|
def test_estimate_fallback_splits_system_tools_and_messages(tmp_path):
|
|
engine = _engine(tmp_path, OneReplyProvider())
|
|
engine.messages.append({"role": "system", "content": "s" * 400})
|
|
engine.messages.append({"role": "user", "content": "u" * 800})
|
|
|
|
snap = engine.context_snapshot()
|
|
|
|
assert snap["estimated"] is True
|
|
b = snap["breakdown"]
|
|
# chars/4 over the serialized message: at least the content's share, in each bucket.
|
|
assert b["system"] >= 100
|
|
assert b["messages"] >= 200
|
|
assert b["tools"] == 0 # a bare registry carries no schemas
|
|
assert snap["used"] == b["system"] + b["tools"] + b["messages"]
|
|
# An unlisted model has no window; the GUI shows "window unknown" (UX-048).
|
|
assert snap["window"] is None
|
|
assert "compaction" not in snap # never compacted
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_reported_usage_wins_and_rides_the_assistant_message(tmp_path):
|
|
usage = TokenUsage(input=900, output=10, cache_read=2100, cache_write=0)
|
|
engine = _engine(tmp_path, OneReplyProvider(usage))
|
|
|
|
events = [e async for e in engine.run("hello")]
|
|
|
|
replies = [e for e in events if e.type is EventType.ASSISTANT_MESSAGE]
|
|
snap = replies[-1].data["context"]
|
|
assert snap["used"] == usage.context_tokens # 900 + 2100
|
|
assert snap["estimated"] is False
|
|
assert set(snap["breakdown"]) == {"system", "tools", "messages"}
|