mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
49dfcbb58c
Three selection defects, all measured against real counters on identical text. 1. HuggingFace-routed models counted a whole conversation as 2 tokens. transformers >= 5 defaults `apply_chat_template(tokenize=True)` to `return_dict=True` and returns a BatchEncoding, so `len(formatted)` counted DICT KEYS — input_ids and attention_mask — instead of tokens. Measured on Qwen2.5-72B with a 6,000-char message: count_messages returned 2 and count_message returned -1 (BaseTokenizer subtracts a 3-token reply overhead from it), against a true 1,003. After the fix: 1,020 and 1,017. That is a ~99.8% undercount on every HF-routed family whose resolved tokenizer carries a chat template — llama, qwen, deepseek, phi, yi, falcon, starcoder. pyproject pins transformers>=5.5.0,<6.0, so the affected version is the only installable one, and no test covered count_messages. It hid behind a second bug while I was reproducing it: DeepSeek-V3 mis-resolves to deepseek-llm-7b-base, a 2023 model with no chat template, which falls back to the estimator and looks correct. That mis-resolution is left for a follow-up. 2. The current OpenAI flagships had no pattern. MODEL_PATTERNS stopped at ^gpt-4 / ^o1 / ^o3, so gpt-5, gpt-5.1, gpt-5-mini, gpt-5.1-codex and o4-mini all fell through to the char estimator. Deviation vs the correct o200k encoding: +20% English, -33% JSON, -44% logs. Added ^gpt-5 and ^o4. 3. Every pattern is ^-anchored, so gateway-wrapped ids matched nothing. bedrock/anthropic.claude-*, vertex_ai/claude-*, openrouter/anthropic/claude-*, anthropic/claude-*, azure/gpt-4o, us.anthropic.claude-*-v1:0 and friends all resolved to the estimator instead of their family's counter. Deviation: +15% English, -33% JSON, -38% logs. handlers/openai.py already documents that LiteLLM's `headroom` guardrail passes exactly these forms. `_detect_backend` now tries progressively-unwrapped candidates — path segments stripped left to right, then Bedrock's dotted [region.]vendor.model — with the FULL name first, so no currently-correct resolution can move and an unknown alias still falls back to estimation rather than matching by accident. 20 new tests covering all three, plus the no-regression cases: bare names unchanged, unknown aliases still estimated, wrapped Gemini matching its bare form exactly, and candidate ordering. ruff check + format clean (0.15.17). tests/test_huggingface_tokenizer_timeout.py + tests/test_tokenizers/: 12 passed on this branch and 12 on clean upstream/main. tests/test_evals_cjk_tokenization.py cannot collect in this env (ModuleNotFoundError: headroom._core, the compiled extension this machine cannot build) — identical on baseline, so CI is the check there.
108 lines
3.9 KiB
Python
108 lines
3.9 KiB
Python
"""Model names must resolve to the tokenizer their model actually uses.
|
|
|
|
Two selection gaps, both measured against real counters on identical text:
|
|
|
|
1. ``MODEL_PATTERNS`` stopped at ``^gpt-4``/``^o1``/``^o3``, so the current
|
|
flagships — ``gpt-5``, ``gpt-5.1``, ``o4-mini`` — fell through to the char
|
|
estimator. Deviation vs the correct o200k encoding: +20% English, -33% JSON,
|
|
-44% logs.
|
|
|
|
2. Every pattern is ``^``-anchored, which is right for a bare model id and wrong
|
|
for the wrapped ids gateways send. ``bedrock/anthropic.claude-3-5-sonnet``,
|
|
``vertex_ai/claude-…``, ``openrouter/anthropic/claude-…``, ``azure/gpt-4o``
|
|
and Bedrock's ``us.anthropic.claude-…`` all matched nothing. LiteLLM's
|
|
``headroom`` guardrail passes exactly these forms.
|
|
|
|
The estimator is a legitimate FALLBACK; the bug is reaching it when a real
|
|
tokenizer for that family exists.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from headroom.tokenizers import get_tokenizer
|
|
from headroom.tokenizers.registry import _name_candidates
|
|
|
|
_TIKTOKEN = "TiktokenCounter"
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"model",
|
|
[
|
|
"gpt-5",
|
|
"gpt-5.1",
|
|
"gpt-5-mini",
|
|
"gpt-5.1-codex",
|
|
"o4-mini",
|
|
],
|
|
)
|
|
def test_current_openai_flagships_get_a_real_tokenizer(model: str) -> None:
|
|
"""These fell to EstimatingTokenCounter before ^gpt-5 / ^o4 were added."""
|
|
assert type(get_tokenizer(model)).__name__ == _TIKTOKEN
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"model",
|
|
[
|
|
# gateway path prefixes
|
|
"bedrock/anthropic.claude-3-5-sonnet",
|
|
"vertex_ai/claude-sonnet-4-6",
|
|
"openrouter/anthropic/claude-sonnet-4-6",
|
|
"anthropic/claude-opus-4",
|
|
"litellm/claude-sonnet-4-6",
|
|
# Bedrock dotted ids, with and without a region segment
|
|
"anthropic.claude-3-5-sonnet-20241022-v2:0",
|
|
"us.anthropic.claude-sonnet-4-6-v1:0",
|
|
"eu.anthropic.claude-sonnet-4-6-v1:0",
|
|
# OpenAI behind a gateway
|
|
"azure/gpt-4o",
|
|
"openrouter/openai/gpt-4o",
|
|
],
|
|
)
|
|
def test_gateway_wrapped_names_resolve_like_their_bare_form(model: str) -> None:
|
|
assert type(get_tokenizer(model)).__name__ == _TIKTOKEN
|
|
|
|
|
|
def test_wrapped_gemini_matches_the_bare_form_exactly() -> None:
|
|
"""Prefix stripping must reach the google backend, not the generic fallback."""
|
|
text = "hello world " * 200
|
|
assert get_tokenizer("vertex_ai/gemini-2.5-pro").count_text(text) == get_tokenizer(
|
|
"gemini-2.5-pro"
|
|
).count_text(text)
|
|
|
|
|
|
def test_bare_names_are_unaffected() -> None:
|
|
"""The exact-match candidate is tried first, so nothing already-correct moves."""
|
|
for model, expected in (
|
|
("gpt-4o", _TIKTOKEN),
|
|
("gpt-3.5-turbo", _TIKTOKEN),
|
|
("o1-preview", _TIKTOKEN),
|
|
("o3-mini", _TIKTOKEN),
|
|
("claude-sonnet-4-6", _TIKTOKEN),
|
|
):
|
|
assert type(get_tokenizer(model)).__name__ == expected, model
|
|
|
|
|
|
def test_unknown_alias_still_falls_back_to_estimation() -> None:
|
|
"""Prefix stripping must not invent a match for a genuinely unknown model."""
|
|
assert type(get_tokenizer("my-gateway/big-model")).__name__ == "EstimatingTokenCounter"
|
|
assert type(get_tokenizer("totally-unknown-xyz")).__name__ == "EstimatingTokenCounter"
|
|
|
|
|
|
def test_name_candidates_orders_most_specific_first() -> None:
|
|
"""The full name must be candidate 0 so exact registrations always win."""
|
|
got = _name_candidates("openrouter/anthropic/claude-sonnet-4-6")
|
|
assert got[0] == "openrouter/anthropic/claude-sonnet-4-6"
|
|
assert "anthropic/claude-sonnet-4-6" in got
|
|
assert "claude-sonnet-4-6" in got
|
|
|
|
dotted = _name_candidates("us.anthropic.claude-sonnet-4-6-v1:0")
|
|
assert dotted[0] == "us.anthropic.claude-sonnet-4-6-v1:0"
|
|
assert "claude-sonnet-4-6-v1:0" in dotted
|
|
|
|
|
|
def test_name_candidates_is_deduplicated_and_finite() -> None:
|
|
got = _name_candidates("a/b/c.d.e")
|
|
assert len(got) == len(set(got))
|
|
assert got[0] == "a/b/c.d.e"
|