mirror of
https://github.com/usestrix/strix.git
synced 2026-08-21 18:52:47 +02:00
Ahmed Allam
a73300f840
Restore cumulative history compaction (removed in the SDK migration) so a long scan no longer replays an ever-growing transcript until it overflows the model's context window and the run fails. - strix/llm/context_budget.py: resolve the model's real input/output token limits from LiteLLM metadata (128k gpt-4o, 272k gpt-5, 1M claude-sonnet-4, 131k deepseek), with a large configurable fallback for unmapped models and a chars/4 token-count fallback. - strix/llm/compaction.py: provider-agnostic compaction via litellm. Keeps a security-focused structured summary (objective, findings, credentials, payloads, URLs/paths, work state, dead ends, next move), keeps the most recent turns by token budget, and snaps the summary boundary so no tool call is separated from its result. Both triggers: proactive before each run and reactive compact-and-retry on a real context-overflow error. - Wire both triggers into the agent run loop next to the existing image recovery; add replace_session_items() with restore-on-failure. Env-tunable via STRIX_CONTEXT_* (auto-compact on by default).
47 lines
1.4 KiB
Python
47 lines
1.4 KiB
Python
"""Tests for model-aware token budgets."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING
|
|
|
|
from strix.config import load_settings
|
|
from strix.llm import context_budget
|
|
|
|
|
|
if TYPE_CHECKING:
|
|
import pytest
|
|
|
|
|
|
def test_context_window_known_model() -> None:
|
|
# gpt-4o is mapped by LiteLLM at 128k input tokens.
|
|
assert context_budget.context_window("gpt-4o") == 128_000
|
|
|
|
|
|
def test_context_window_strips_provider_prefix() -> None:
|
|
assert context_budget.context_window("openai/gpt-4o") == 128_000
|
|
|
|
|
|
def test_context_window_unmapped_uses_fallback(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
context_budget._model_info.cache_clear()
|
|
|
|
def _raise(_model: str) -> dict[str, int]:
|
|
raise ValueError("This model isn't mapped yet.")
|
|
|
|
monkeypatch.setattr("strix.llm.context_budget.litellm.get_model_info", _raise)
|
|
expected = load_settings().context.fallback_context_tokens
|
|
assert context_budget.context_window("totally-made-up-model") == expected
|
|
context_budget._model_info.cache_clear()
|
|
|
|
|
|
def test_count_tokens_fallback_on_error(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
def _raise(**_kwargs: object) -> int:
|
|
raise RuntimeError("no tokenizer")
|
|
|
|
monkeypatch.setattr("strix.llm.context_budget.litellm.token_counter", _raise)
|
|
text = "x" * 400
|
|
assert context_budget.count_tokens("weird-model", text) == 100
|
|
|
|
|
|
def test_count_tokens_empty_is_zero() -> None:
|
|
assert context_budget.count_tokens("gpt-4o", "") == 0
|