mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-23 16:36:23 +00:00
1c2faedd88
Follow-up to the salvaged #64010 (Kenmege) and #63870 (dombejar) commits, making one resolved compression.max_attempts cap govern ALL per-turn compression attempt sites: - conversation_loop: resolve max_compression_attempts ONCE at turn start (it was previously re-resolved inside the API-call loop) and route the pre-API pressure gate through it — that gate still hardcoded 'compression_attempts < 3' and logged 'attempt=%s/3'. - conversation_loop: the salvaged post-tool compaction gate now uses the resolved cap instead of a hardcoded 3. - turn_context: the preflight compaction loop was 'for _pass in range(3)'; it now sizes itself from the same resolved cap. - agent_init: harden the max_attempts parser — reject booleans (bool subclasses int; 'true' would coerce to 1), reject fractional floats instead of truncating them, keep accepting integral floats and numeric strings; anything else falls back to 3 (floor 1, ceiling 10 unchanged). - tests: replace #63870's inspect.getsource source-shape test with behavioral loop tests (post-tool compaction fires <= cap times per turn, shares its budget with the pre-API gate, resets between turns); add an e2e test proving a 4th preflight pass runs at config cap=6 while the unset default still stops at 3; extend the #64010 config tests with the bool/float parser semantics. Salvages #64010 by @Kenmege and #63870 by @dombejar.
119 lines
4.7 KiB
Python
119 lines
4.7 KiB
Python
"""compression.max_attempts — config-driven compression retry cap.
|
|
|
|
The conversation loop's compression retry cap was hardcoded to 3, stranding
|
|
sessions that legitimately need more rounds — e.g. a restart history reload
|
|
whose incompressible tool schemas keep the request estimate above the
|
|
threshold while the messages themselves compress fine (the #62605 failure
|
|
class). The cap is now parsed from ``compression.max_attempts`` in
|
|
``agent_init`` and read by the loop via
|
|
``getattr(agent, "max_compression_attempts", 3)``.
|
|
|
|
These tests pin the parse/validate/attach seam: default preserved, custom
|
|
value honored, floor and ceiling enforced, garbage tolerated.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import contextlib
|
|
import io
|
|
from pathlib import Path
|
|
|
|
from hermes_state import SessionDB
|
|
from run_agent import AIAgent
|
|
|
|
|
|
def _config(max_attempts=None) -> dict:
|
|
compression = {
|
|
"enabled": True,
|
|
"threshold": 0.50,
|
|
"target_ratio": 0.20,
|
|
"protect_first_n": 3,
|
|
"protect_last_n": 20,
|
|
}
|
|
if max_attempts is not None:
|
|
compression["max_attempts"] = max_attempts
|
|
return {
|
|
"compression": compression,
|
|
"prompt_caching": {"cache_ttl": "5m"},
|
|
"sessions": {},
|
|
"bedrock": {},
|
|
}
|
|
|
|
|
|
def _make_agent(monkeypatch, tmp_path: Path, *, max_attempts=None):
|
|
from hermes_cli import config as config_mod
|
|
|
|
monkeypatch.setattr(
|
|
config_mod, "load_config", lambda: _config(max_attempts=max_attempts)
|
|
)
|
|
db = SessionDB(db_path=tmp_path / "state.db")
|
|
with contextlib.redirect_stdout(io.StringIO()):
|
|
agent = AIAgent(
|
|
base_url="https://chatgpt.com/backend-api/codex",
|
|
api_key="test-key",
|
|
provider="openai-codex",
|
|
model="gpt-5.5",
|
|
enabled_toolsets=[],
|
|
disabled_toolsets=[],
|
|
quiet_mode=True,
|
|
skip_memory=True,
|
|
session_db=db,
|
|
session_id="max-attempts-test",
|
|
)
|
|
return agent
|
|
|
|
|
|
class TestCompressionMaxAttemptsConfig:
|
|
def test_default_is_three_when_unset(self, monkeypatch, tmp_path):
|
|
agent = _make_agent(monkeypatch, tmp_path)
|
|
assert agent.max_compression_attempts == 3
|
|
|
|
def test_custom_value_is_honored(self, monkeypatch, tmp_path):
|
|
agent = _make_agent(monkeypatch, tmp_path, max_attempts=6)
|
|
assert agent.max_compression_attempts == 6
|
|
|
|
def test_hard_capped_at_ten(self, monkeypatch, tmp_path):
|
|
agent = _make_agent(monkeypatch, tmp_path, max_attempts=25)
|
|
assert agent.max_compression_attempts == 10
|
|
|
|
def test_zero_and_negative_fall_back_to_default(self, monkeypatch, tmp_path):
|
|
agent = _make_agent(monkeypatch, tmp_path, max_attempts=0)
|
|
assert agent.max_compression_attempts == 3
|
|
agent = _make_agent(monkeypatch, tmp_path, max_attempts=-2)
|
|
assert agent.max_compression_attempts == 3
|
|
|
|
def test_non_integer_falls_back_to_default(self, monkeypatch, tmp_path):
|
|
agent = _make_agent(monkeypatch, tmp_path, max_attempts="lots")
|
|
assert agent.max_compression_attempts == 3
|
|
|
|
def test_boolean_is_rejected_not_coerced(self, monkeypatch, tmp_path):
|
|
# bool subclasses int: int(True) == 1 would silently near-disable
|
|
# compression retries. YAML `max_attempts: true` must fall back to 3.
|
|
agent = _make_agent(monkeypatch, tmp_path, max_attempts=True)
|
|
assert agent.max_compression_attempts == 3
|
|
agent = _make_agent(monkeypatch, tmp_path, max_attempts=False)
|
|
assert agent.max_compression_attempts == 3
|
|
|
|
def test_fractional_float_is_rejected_not_truncated(self, monkeypatch, tmp_path):
|
|
# "4.7 attempts" is a config mistake, not a request for 4.
|
|
agent = _make_agent(monkeypatch, tmp_path, max_attempts=4.7)
|
|
assert agent.max_compression_attempts == 3
|
|
|
|
def test_integral_float_and_numeric_string_are_accepted(
|
|
self, monkeypatch, tmp_path
|
|
):
|
|
agent = _make_agent(monkeypatch, tmp_path, max_attempts=5.0)
|
|
assert agent.max_compression_attempts == 5
|
|
agent = _make_agent(monkeypatch, tmp_path, max_attempts="6")
|
|
assert agent.max_compression_attempts == 6
|
|
|
|
def test_loop_pickup_degrades_to_default_when_attribute_missing(
|
|
self, monkeypatch, tmp_path
|
|
):
|
|
# The loop reads getattr(agent, "max_compression_attempts", 3): a
|
|
# configured agent exposes its value, and an object without the
|
|
# attribute (older pickle / minimal stub) degrades to the prior
|
|
# hardcoded behavior.
|
|
agent = _make_agent(monkeypatch, tmp_path, max_attempts=7)
|
|
assert getattr(agent, "max_compression_attempts", 3) == 7
|
|
assert getattr(object(), "max_compression_attempts", 3) == 3
|