Files
hermes-agent/tests/gateway/test_runtime_footer.py
T
Kyzcreig ad345a99d8 feat(gateway): add opt-in 'latency' runtime footer field
The runtime footer (`/footer`) shows what model ran and how full the context
is, but not how long the turn took. On a messaging platform there is no
progress bar and no shell timer — a turn that took 4 seconds and one that took
four minutes produce visually identical replies. Users comparing models,
providers, or reasoning levels have no at-a-glance signal for the one
dimension they most often care about, and "was that slow or did I imagine it?"
is unanswerable after the fact.

Adds a `latency` field to the existing footer machinery, rendering the
wall-clock duration of the agent run: `<1s`, `22s`, `1m05s`.

`gateway/run.py` measures with `time.monotonic()` immediately around the
`self._run_agent(...)` await in `_handle_message_with_agent` — the same
function that already builds the footer, so the value is the user-perceived
turn duration (monotonic, so it is immune to wall-clock/NTP adjustment).

`latency` is deliberately NOT in `_DEFAULT_FIELDS`. It is opt-in via
`display.runtime_footer.fields`. Every existing footer — and every footer a
user has today without touching config — renders byte-identically.

This is enforced by tests, not just asserted:

- `test_latency_not_in_default_fields` pins the default tuple.
- `test_resolve_footer_config_default_fields_exclude_latency` pins what
  config resolution produces for an untouched config.
- `test_default_footer_renders_byte_identically` pins five exact output
  strings for default-config renders **while supplying `turn_seconds`** —
  proving that even when the caller measures timing, a default-configured
  footer does not show it.
- `test_default_build_footer_line_ignores_turn_seconds` asserts
  `build_footer_line(...) == build_footer_line(..., turn_seconds=125.0)`
  under default fields.

Adding `latency` to `_DEFAULT_FIELDS` fails 11 of these tests.

No new config surface (reuses `display.runtime_footer.fields`), no new env
vars, no new core tool, no new model-facing schema. One new module-private
helper (`_format_latency`), one new keyword argument threaded through the two
existing footer functions, and 3 lines in `gateway/run.py`.

`turn_seconds` defaults to `None` and the field is skipped when it is `None`
or negative, so any call site that does not measure timing keeps working
unchanged.

`tests/gateway/test_runtime_footer.py` (+185): `_format_latency` boundary
table (sub-second, rounding at 59.4/59.6, the `m{:02d}s` zero-pad, 60m), the
render/skip/opt-in matrix, field-order placement, `build_footer_line`
threading, and the byte-stability block above.

RED-proved by mutation — each of these breaks tests:
- `latency` added to `_DEFAULT_FIELDS` → 11 failures
- dropping the `turn_seconds is not None and >= 0` guard → 2 failures
- `{sec:02d}` → `{sec}` → 6 failures
- `build_footer_line` not threading `turn_seconds` → 1 failure

51 passed in `tests/gateway/test_runtime_footer.py`; 54 passed across the
footer blast radius. `ruff check` clean.
2026-08-03 17:16:57 +05:30

320 lines
9.7 KiB
Python

"""Unit tests for gateway.runtime_footer — the opt-in runtime-metadata footer
appended to final gateway replies."""
from __future__ import annotations
import os
import pytest
from gateway.runtime_footer import (
_home_relative_cwd,
_model_short,
build_footer_line,
format_runtime_footer,
resolve_footer_config,
)
# ---------------------------------------------------------------------------
# _model_short + _home_relative_cwd
# ---------------------------------------------------------------------------
@pytest.mark.parametrize(
"model,expected",
[
("openai/gpt-5.4", "gpt-5.4"),
("anthropic/claude-sonnet-4.6", "claude-sonnet-4.6"),
("gpt-5.4", "gpt-5.4"),
("", ""),
(None, ""),
],
)
def test_model_short_drops_vendor_prefix(model, expected):
assert _model_short(model) == expected
def test_home_relative_cwd_collapses_home(tmp_path, monkeypatch):
monkeypatch.setenv("HOME", str(tmp_path))
sub = tmp_path / "projects" / "hermes"
sub.mkdir(parents=True)
result = _home_relative_cwd(str(sub))
assert result == "~/projects/hermes"
# ---------------------------------------------------------------------------
# format_runtime_footer
# ---------------------------------------------------------------------------
def test_format_footer_all_fields(monkeypatch, tmp_path):
monkeypatch.setenv("HOME", str(tmp_path))
monkeypatch.setenv("TERMINAL_CWD", str(tmp_path / "projects" / "hermes"))
(tmp_path / "projects" / "hermes").mkdir(parents=True)
out = format_runtime_footer(
model="openrouter/openai/gpt-5.4",
context_tokens=68000,
context_length=100000,
cwd=None, # falls back to TERMINAL_CWD env var
fields=("model", "context_pct", "cwd"),
)
assert out == "gpt-5.4 · 68% · ~/projects/hermes"
def test_format_footer_skips_missing_context_length():
out = format_runtime_footer(
model="openai/gpt-5.4",
context_tokens=500,
context_length=None,
cwd="/tmp/wd",
fields=("model", "context_pct", "cwd"),
)
# context_pct dropped silently; no "?%" artifact
assert "%" not in out
assert "gpt-5.4" in out
assert "/tmp/wd" in out
# ---------------------------------------------------------------------------
# resolve_footer_config
# ---------------------------------------------------------------------------
def test_resolve_platform_override_wins():
user = {
"display": {
"runtime_footer": {"enabled": True, "fields": ["model"]},
"platforms": {
"slack": {"runtime_footer": {"enabled": False}},
},
},
}
# Telegram picks up the global enable
assert resolve_footer_config(user, "telegram")["enabled"] is True
# Slack overrides to off
assert resolve_footer_config(user, "slack")["enabled"] is False
def test_resolve_platform_can_add_fields_only():
user = {
"display": {
"runtime_footer": {"enabled": True},
"platforms": {
"discord": {"runtime_footer": {"fields": ["context_pct"]}},
},
},
}
tg = resolve_footer_config(user, "telegram")
assert tg["enabled"] is True
assert tg["fields"] == ["model", "context_pct", "cwd"]
dc = resolve_footer_config(user, "discord")
assert dc["enabled"] is True
assert dc["fields"] == ["context_pct"]
# ---------------------------------------------------------------------------
# build_footer_line — top-level entry point used by gateway/run.py
# ---------------------------------------------------------------------------
def test_build_footer_per_platform_off_suppresses():
user = {
"display": {
"runtime_footer": {"enabled": True},
"platforms": {"slack": {"runtime_footer": {"enabled": False}}},
},
}
out = build_footer_line(
user_config=user,
platform_key="slack",
model="openai/gpt-5.4",
context_tokens=10, context_length=100,
cwd="/tmp",
)
assert out == ""
# ---------------------------------------------------------------------------
# latency — opt-in wall-clock turn duration
# ---------------------------------------------------------------------------
@pytest.mark.parametrize(
"seconds,expected",
[
(0.0, "<1s"),
(0.4, "<1s"),
(0.999, "<1s"),
(1.0, "1s"),
(22.0, "22s"),
(22.4, "22s"),
(59.4, "59s"),
(59.6, "1m00s"),
(60.0, "1m00s"),
(65.0, "1m05s"),
(125.0, "2m05s"),
(3600.0, "60m00s"),
],
)
def test_format_latency(seconds, expected):
from gateway.runtime_footer import _format_latency
assert _format_latency(seconds) == expected
def test_format_footer_latency_renders():
out = format_runtime_footer(
model="m",
context_tokens=0,
context_length=None,
cwd="",
turn_seconds=22.0,
fields=("latency",),
)
assert out == "22s"
def test_format_footer_latency_skipped_when_unmeasured():
"""A call site that doesn't measure timing leaves the field out entirely."""
out = format_runtime_footer(
model="m",
context_tokens=0,
context_length=None,
cwd="",
turn_seconds=None,
fields=("latency",),
)
assert out == ""
def test_format_footer_latency_skipped_when_negative():
"""A nonsensical (negative) duration is dropped rather than rendered."""
out = format_runtime_footer(
model="m",
context_tokens=0,
context_length=None,
cwd="",
turn_seconds=-1.0,
fields=("latency",),
)
assert out == ""
def test_format_footer_latency_zero_renders_sub_second():
"""Zero is a real measurement (a very fast turn), not missing data."""
out = format_runtime_footer(
model="m",
context_tokens=0,
context_length=None,
cwd="",
turn_seconds=0.0,
fields=("latency",),
)
assert out == "<1s"
def test_format_footer_latency_in_field_order(monkeypatch, tmp_path):
monkeypatch.setenv("HOME", str(tmp_path))
out = format_runtime_footer(
model="openai/gpt-5.4",
context_tokens=68_000,
context_length=100_000,
cwd=str(tmp_path),
turn_seconds=65.0,
fields=("model", "context_pct", "latency", "cwd"),
)
assert out == "gpt-5.4 · 68% · 1m05s · ~"
def test_build_footer_line_threads_turn_seconds(monkeypatch):
monkeypatch.delenv("TERMINAL_CWD", raising=False)
out = build_footer_line(
user_config={
"display": {
"runtime_footer": {
"enabled": True,
"fields": ["model", "latency"],
}
}
},
platform_key="discord",
model="gpt-5.4",
context_tokens=0,
context_length=None,
cwd="",
turn_seconds=22.0,
)
assert out == "gpt-5.4 · 22s"
# ---------------------------------------------------------------------------
# Byte-stability: `latency` is opt-in, so the DEFAULT footer is unchanged.
#
# Upstream doctrine: a system prompt / rendered surface must be byte-stable for
# the life of a conversation. Adding a field to _DEFAULT_FIELDS would silently
# change the footer text of every user who already enabled it. These tests pin
# the default set and the exact default-config output strings.
# ---------------------------------------------------------------------------
_LEGACY_DEFAULT_FIELDS = ["model", "context_pct", "cwd"]
def test_latency_not_in_default_fields():
from gateway.runtime_footer import _DEFAULT_FIELDS
assert "latency" not in _DEFAULT_FIELDS
assert list(_DEFAULT_FIELDS) == _LEGACY_DEFAULT_FIELDS
def test_resolve_footer_config_default_fields_exclude_latency():
assert resolve_footer_config({}, "telegram")["fields"] == _LEGACY_DEFAULT_FIELDS
assert resolve_footer_config(
{"display": {"runtime_footer": {"enabled": True}}}, "discord"
)["fields"] == _LEGACY_DEFAULT_FIELDS
@pytest.mark.parametrize(
"model,tokens,window,cwd,expected",
[
("openai/gpt-5.4", 50_247, 1_000_000, "/var/data", "gpt-5.4 · 5% · /var/data"),
("claude-opus-4-8", 68_000, 100_000, "/var/data", "claude-opus-4-8 · 68% · /var/data"),
("m", 0, None, "/var/data", "m · /var/data"),
("", 10, 100, "/var/data", "10% · /var/data"),
("m", 10, 100, "", "m · 10%"),
],
)
def test_default_footer_renders_byte_identically(
monkeypatch, model, tokens, window, cwd, expected
):
"""Default-config output is byte-for-byte what it was before `latency`.
Note `turn_seconds` IS supplied — proving that even when the caller
measures timing, a default-configured footer does not show it.
"""
monkeypatch.delenv("TERMINAL_CWD", raising=False)
out = format_runtime_footer(
model=model,
context_tokens=tokens,
context_length=window,
cwd=cwd,
turn_seconds=22.0,
# fields deliberately NOT passed — exercises the default.
)
assert out == expected
def test_default_build_footer_line_ignores_turn_seconds(monkeypatch):
"""build_footer_line with default fields is unaffected by turn_seconds."""
monkeypatch.delenv("TERMINAL_CWD", raising=False)
common = dict(
user_config={"display": {"runtime_footer": {"enabled": True}}},
platform_key="discord",
model="openai/gpt-5.4",
context_tokens=50_247,
context_length=1_000_000,
cwd="/var/data",
)
baseline = build_footer_line(**common)
with_timing = build_footer_line(**common, turn_seconds=125.0)
assert baseline == "gpt-5.4 · 5% · /var/data"
assert with_timing == baseline