deer-flow/backend/tests/test_thread_token_usage.py
Amorend 85c3909c2e
feat: show real-time context window usage (#3125) (#3183)
* feat: show real-time context window usage in chat UI (#3125)

Adds a `context_usage` block to `GET /api/threads/{id}/token-usage`
(token count from the live checkpoint, the thread model's
`context_window`, and a percentage), introduces a new
`ModelConfig.context_window` distinct from the per-call `max_tokens`
output cap, and surfaces the percentage in the chat header — inside
`TokenUsageIndicator` when token-usage tracking is on, or as a
standalone badge when it's off so context capacity stays visible
independent of cost tracking.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat: per-category breakdown for context window usage

Replace the single-number context_usage payload with a Claude-Code-style
breakdown — messages, system prompt, skills, system/MCP tools (active +
deferred), custom agents, memory injection, autocompact buffer, and free
space — and surface it in the chat UI with a segmented progress bar and
per-row table.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* docs(config): document context_window across model examples

Add `context_window` to every example model in config.example.yaml so the
new chat-UI "% context used" indicator works out of the box for whichever
example a user adopts. Each value is the published default at the time of
writing; users are pointed at the official model spec to verify. Bumps
config_version to 11 so `make config-upgrade` flags outdated user configs.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* style: ruff format (line-length 240)

No behavior change — collapses two multi-line expressions that fit on
one line under the project's 240-char limit. Picked up by `make format`.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* review: address Copilot bot comments on #3183

- token-usage-indicator: switch `{contextPercentage && (...)}` to an
  explicit `!= null` check. (The string `"0"` is actually truthy in JS so
  the original code wasn't buggy, but the explicit check is clearer.)
- context-usage-breakdown: drop the `useMemo` around segments/totals — the
  computation is O(n) over a handful of rows and the previous memo deps
  omitted `t.contextUsage.categories`, so the bar's tooltips/aria-labels
  could stay in the old language after a locale switch.
- context_usage._split_tools: snapshot MCP names from
  `get_cached_mcp_tools()` directly instead of re-reading
  `extensions_config.json` after `get_available_tools()` already loaded
  it. Removes redundant file I/O on every `/token-usage` poll.
  (`get_available_tools()` still emits its own INFO logs — silencing
  those is out of scope here.)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* style(frontend): prettier --write context-usage-breakdown

CI's `pnpm format` (prettier --check) caught two lines previously
formatted by hand. Collapses one comma to fit on one line; no behavior
change.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix(gateway): correct context-usage breakdown + add exact token counting

The context-usage indicator shipped two bugs that silently zeroed whole
breakdown rows (both caught by try/except, so the feature looked alive but
produced wrong numbers):

1. _count_system_prompt passed app_config= to get_deferred_tools_prompt_section,
   which only accepts deferred_names -> TypeError swallowed -> system_prompt
   row always 0, and used_tokens/percentage undercounted by the full prompt.
   Also subtracted the deferred section twice (the rendered prompt already
   excluded it). Fix: derive deferred names deterministically and pass them to
   apply_prompt_template; drop the redundant subtraction.

2. _split_tools imported a non-existent get_deferred_registry -> ImportError
   swallowed -> all four tool-category rows always 0. Fix: classify via the
   public is_mcp_tool predicate + tool_search.enabled (mirrors
   build_deferred_tool_setup); the MCP tag is set by get_available_tools.

Added token_usage.counting (approximate|exact). 'exact' routes text/schema/
message counting through the model tokenizer (tiktoken cl100k_base) via the
existing memory-module machinery (lazy load + cache + cooldown + CJK-aware
fallback), so CJK-heavy threads stop being undercounted by chars//4.

Regression + e2e tests added; 6621 backend tests pass.

* fix(gateway): harden context usage accounting

* fix(gateway): count promoted MCP tools as active in context usage

Promoted tools (deferred MCP tools the thread has fetched via tool_search)
have their full schema bound on every subsequent turn by
DeferredToolFilterMiddleware, so they consume context like any active tool.
The breakdown previously left them in the reserved *_deferred rows, under-
counting the thread's used_tokens.

Classification now treats a tool as deferred only when tool_search is enabled,
it is MCP-sourced, AND it has not been promoted. The promoted set is read from
the checkpoint's channel_values and scoped by catalog hash — matching the
runtime middleware, so a stale promotion from MCP-config drift cannot inflate
the active count.

The static system prompt still lists all deferred tool names (promotions only
affect schema binding, not the prompt), so _count_system_prompt's deferred
rendering is intentionally left unchanged.

8 new tests cover classification, catalog-hash scoping (match / drift /
compute-failure / malformed), and checkpoint extraction.

* fix(context): address review feedback

* fix(context): count structured message payloads

* fix(context): harden usage accounting

* fix(config): bump schema for context usage fields

* refactor: narrow context usage to core indicator

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-07-31 21:57:22 +08:00

183 lines
6.2 KiB
Python

"""Tests for thread-level token usage and context-window usage."""
from __future__ import annotations
from types import SimpleNamespace
from unittest.mock import AsyncMock, MagicMock
import pytest
from _router_auth_helpers import make_authed_test_app
from fastapi.testclient import TestClient
from app.gateway import context_usage
from app.gateway.routers import thread_runs
def _aggregate_result() -> dict:
return {
"total_tokens": 150,
"total_input_tokens": 90,
"total_output_tokens": 60,
"total_runs": 2,
"by_model": {"unknown": {"tokens": 150, "runs": 2}},
"by_caller": {
"lead_agent": 120,
"subagent": 25,
"middleware": 5,
},
}
def _make_run_store(*, model_name: str | None = None) -> MagicMock:
run_store = MagicMock()
run_store.aggregate_tokens_by_thread = AsyncMock(return_value=_aggregate_result())
runs = [{"model_name": model_name}] if model_name else []
run_store.list_by_thread = AsyncMock(return_value=runs)
return run_store
def _make_app(run_store: MagicMock):
app = make_authed_test_app()
app.include_router(thread_runs.router)
app.state.run_store = run_store
return app
def test_thread_token_usage_returns_stable_shape(monkeypatch: pytest.MonkeyPatch) -> None:
run_store = _make_run_store()
build_context_usage = AsyncMock(return_value=None)
monkeypatch.setattr(thread_runs, "build_context_usage", build_context_usage)
app = _make_app(run_store)
with TestClient(app) as client:
response = client.get("/api/threads/thread-1/token-usage")
assert response.status_code == 200
assert response.json() == {
"thread_id": "thread-1",
**_aggregate_result(),
"context_usage": None,
}
run_store.aggregate_tokens_by_thread.assert_awaited_once_with("thread-1")
build_context_usage.assert_awaited_once()
def test_thread_token_usage_can_include_active_runs(monkeypatch: pytest.MonkeyPatch) -> None:
run_store = _make_run_store()
build_context_usage = AsyncMock(return_value=None)
monkeypatch.setattr(thread_runs, "build_context_usage", build_context_usage)
app = _make_app(run_store)
with TestClient(app) as client:
response = client.get("/api/threads/thread-1/token-usage?include_active=true")
assert response.status_code == 200
run_store.aggregate_tokens_by_thread.assert_awaited_once_with("thread-1", include_active=True)
def test_thread_token_usage_serializes_context_percentage(monkeypatch: pytest.MonkeyPatch) -> None:
run_store = _make_run_store()
monkeypatch.setattr(
thread_runs,
"build_context_usage",
AsyncMock(
return_value={
"token_count": 350,
"max_context_tokens": 1000,
"percentage": 35.0,
}
),
)
app = _make_app(run_store)
with TestClient(app) as client:
response = client.get("/api/threads/thread-1/token-usage")
assert response.status_code == 200
assert response.json()["context_usage"] == {
"token_count": 350,
"max_context_tokens": 1000,
"percentage": 35.0,
}
def test_build_context_usage_payload_computes_percentage() -> None:
assert context_usage.build_context_usage_payload(token_count=350, max_context_tokens=1000) == {
"token_count": 350,
"max_context_tokens": 1000,
"percentage": 35.0,
}
def test_build_context_usage_payload_handles_unknown_capacity() -> None:
assert context_usage.build_context_usage_payload(token_count=350, max_context_tokens=None) == {
"token_count": 350,
"max_context_tokens": None,
"percentage": None,
}
@pytest.mark.asyncio
async def test_resolve_thread_model_prefers_latest_run() -> None:
run_store = _make_run_store(model_name="thread-model")
app_config = SimpleNamespace(models=[SimpleNamespace(name="fallback-model")])
assert await context_usage._resolve_thread_model_name(run_store, "thread-1", app_config) == "thread-model"
@pytest.mark.asyncio
async def test_resolve_thread_model_falls_back_to_first_configured_model() -> None:
run_store = _make_run_store()
app_config = SimpleNamespace(models=[SimpleNamespace(name="fallback-model")])
assert await context_usage._resolve_thread_model_name(run_store, "thread-1", app_config) == "fallback-model"
@pytest.mark.asyncio
async def test_build_context_usage_counts_materialized_messages(monkeypatch: pytest.MonkeyPatch) -> None:
messages = [SimpleNamespace(content="hello")]
snapshot = SimpleNamespace(values={"messages": messages})
accessor = SimpleNamespace(aget=AsyncMock(return_value=snapshot))
monkeypatch.setattr(
context_usage,
"build_thread_checkpoint_state_accessor",
AsyncMock(return_value=(accessor, {"configurable": {"thread_id": "thread-1"}})),
)
model_config = SimpleNamespace(context_window=1000)
app_config = SimpleNamespace(
models=[SimpleNamespace(name="fallback-model")],
get_model_config=lambda name: model_config if name == "thread-model" else None,
)
monkeypatch.setattr(context_usage, "get_config", lambda: app_config)
monkeypatch.setattr(context_usage, "_count_messages_approximately", lambda value: 250 if value == messages else 0)
result = await context_usage.build_context_usage(
request=SimpleNamespace(app=SimpleNamespace()),
thread_id="thread-1",
run_store=_make_run_store(model_name="thread-model"),
)
assert result == {
"token_count": 250,
"max_context_tokens": 1000,
"percentage": 25.0,
}
@pytest.mark.asyncio
async def test_build_context_usage_returns_none_when_checkpoint_read_fails(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setattr(
context_usage,
"build_thread_checkpoint_state_accessor",
AsyncMock(side_effect=RuntimeError("checkpoint unavailable")),
)
monkeypatch.setattr(context_usage, "get_config", lambda: SimpleNamespace())
result = await context_usage.build_context_usage(
request=SimpleNamespace(app=SimpleNamespace()),
thread_id="thread-1",
run_store=_make_run_store(),
)
assert result is None