Files
stack/tests/llm/test_config.py
kert 52ce69acf1
Some checks failed
CI / notebooks-smoke (push) Successful in 1m34s
CI / test (push) Failing after 2m19s
Infra CI / zotero (push) Successful in 16s
Infra CI / docs (push) Successful in 17s
Infra CI / api (push) Successful in 1m7s
CI / lint (push) Successful in 38s
Infra CI / llm (push) Successful in 1m10s
Infra CI / mc (push) Failing after 41s
CI / test (pull_request) Failing after 2m27s
Infra CI / notebooks (push) Successful in 7m51s
CI / notebooks-smoke (pull_request) Successful in 1m25s
Infra CI / zotero (pull_request) Successful in 14s
Infra CI / docs (pull_request) Successful in 19s
Infra CI / notebooks (pull_request) Successful in 51s
CI / lint (pull_request) Successful in 32s
Infra CI / api (pull_request) Successful in 21s
Infra CI / llm (pull_request) Successful in 17s
Infra CI / mc (pull_request) Failing after 1m8s
fix(llm): size the chat prompt in tokens and refuse silent host-side truncation
The excerpt budget was a flat chat_num_ctx * 3 characters on the user
message alone. On FR/regulatory text the instruct model's tokenizer yields
2.5–2.9 chars per token, and the system prompt and the 1,200-token reply
reservation were not counted, so a routine answer rendered 9.4k–10k prompt
tokens into an 8,192-token context. Ollama's context-shift truncation keeps
the first 4 tokens and the tail half: the system prompt and the best-ranked
excerpts were dropped on every such answer, the only trace a WARN in the
ollama log. The nightly golden set has reported missing anchors since.

- prompt_budget_chars(cfg): (chat_num_ctx - chat_max_tokens - template
  reserve) * chat_chars_per_token - len(system prompt); new [llm] knob
  chat_chars_per_token = 2.4 (measured minimum 2.50 on the golden set)
- /api/chat is sent with truncate: false; the host's 400 for an over-long
  prompt (exceed_context_size_error with n_prompt_tokens / n_ctx, or the
  older bare message) rebuilds the messages under a proportionally tighter
  budget and resends; when the trimming floors cannot shorten the prompt,
  or on the final attempt, host truncation is allowed as the last resort
- stack_llm_chat_prompt_overflow_total{resolution} counts rebuilt /
  host_truncated; each overflow is logged with the host's token counts
2026-10-24 14:14:38 -04:00

146 lines
5.2 KiB
Python

"""llm.config — [llm] section parsing + env overrides."""
import pytest
from llm import config as llm_config
class TestLoad:
def test_defaults_from_stack_toml(self, monkeypatch):
monkeypatch.delenv("LLM_OLLAMA_HOSTS", raising=False)
monkeypatch.delenv("LLM_PG_HOST", raising=False)
monkeypatch.delenv("LLM_BUILD_ANN_INDEX", raising=False)
cfg = llm_config.load()
assert cfg.ollama_hosts == ("http://127.0.0.1:11434",)
assert cfg.embed_model == "nomic-embed-text"
assert cfg.embed_dim == 768
assert cfg.pg_host == "127.0.0.1"
assert cfg.pg_db == "llm"
assert cfg.build_ann_index is True
def test_env_overrides(self, monkeypatch):
monkeypatch.setenv(
"LLM_OLLAMA_HOSTS",
"http://rig:11434, http://laptop:11434",
)
monkeypatch.setenv("LLM_PG_HOST", "postgres")
cfg = llm_config.load()
assert cfg.ollama_hosts == ("http://rig:11434", "http://laptop:11434")
assert cfg.pg_host == "postgres"
def test_build_ann_index_env_override_true(self, monkeypatch):
monkeypatch.setenv("LLM_BUILD_ANN_INDEX", "1")
cfg = llm_config.load()
assert cfg.build_ann_index is True
def test_build_ann_index_env_override_false(self, monkeypatch):
monkeypatch.setenv("LLM_BUILD_ANN_INDEX", "no")
cfg = llm_config.load()
assert cfg.build_ann_index is False
class TestPgUrl:
def test_url_includes_password_from_env(self, monkeypatch):
monkeypatch.setenv("LLM_DB_PASSWORD", "s3cret")
cfg = llm_config.load()
url = llm_config.pg_url(cfg)
assert url == f"postgresql+psycopg://llm:s3cret@{cfg.pg_host}:5432/llm"
def test_missing_password_raises(self, monkeypatch):
monkeypatch.delenv("LLM_DB_PASSWORD", raising=False)
cfg = llm_config.load()
with pytest.raises(RuntimeError, match="LLM_DB_PASSWORD"):
llm_config.pg_url(cfg)
class TestParseHosts:
def test_bare_and_annotated(self):
out = llm_config.parse_hosts(
"http://ollama:11434, http://rig.local:11434@24 ,http://nb:11434@12"
)
assert out == (
("http://ollama:11434", 0.0),
("http://rig.local:11434", 24.0),
("http://nb:11434", 12.0),
)
def test_trailing_slash_stripped_and_empty_parts_dropped(self):
assert llm_config.parse_hosts("http://a:1/@8,,") == (("http://a:1", 8.0),)
class TestNewKnobs:
def test_defaults_when_section_lacks_keys(self, monkeypatch):
monkeypatch.delenv("LLM_OLLAMA_HOSTS", raising=False)
cfg = llm_config.load()
assert cfg.large_min_vram_gb == 20.0
assert cfg.chat_num_ctx == 8192
assert cfg.chat_chars_per_token == 2.4
assert cfg.recency_half_life_days == 365.0
assert cfg.recency_weight == 0.3
assert cfg.k_per_kind == {"comment": 8, "rule": 4, "corpus": 4}
assert cfg.top_n == 8
assert isinstance(cfg.instruct_model_large, str)
def test_env_hosts_populate_vram_map(self, monkeypatch):
monkeypatch.setenv(
"LLM_OLLAMA_HOSTS", "http://rig:11434@24,http://laptop:11434@12"
)
cfg = llm_config.load()
assert cfg.ollama_hosts == ("http://rig:11434", "http://laptop:11434")
assert cfg.host_vram == {"http://rig:11434": 24.0, "http://laptop:11434": 12.0}
def test_valuation_knobs_defaults(self, monkeypatch):
monkeypatch.delenv("LLM_DUCKDB_REPLICA", raising=False)
cfg = llm_config.load()
assert cfg.duckdb_replica == "data/replica/aco.ro.duckdb"
assert cfg.valuation_years == 4
assert cfg.code_cited_per_code == 3
assert cfg.code_cited_collections == ("rules", "comments", "corpus")
assert cfg.code_cited_max == 12
assert cfg.lineage_max_rows == 25
assert cfg.lineage_on_demand_max == 3
def test_duckdb_replica_env_override(self, monkeypatch):
monkeypatch.setenv("LLM_DUCKDB_REPLICA", "/app/data/replica/aco.ro.duckdb")
assert llm_config.load().duckdb_replica == "/app/data/replica/aco.ro.duckdb"
class TestStrTuple:
"""``code_cited_collections`` must never explode a bare scalar string
into a tuple of its characters (``tuple("rules")``)."""
def test_scalar_string_becomes_one_tuple(self):
assert llm_config._str_tuple("rules") == ("rules",)
def test_list_passes_through_as_tuple(self):
assert llm_config._str_tuple(["rules", "comments"]) == ("rules", "comments")
def test_code_cited_collections_scalar_string_in_toml_is_one_tuple(
self, monkeypatch
):
import conf
from conf import _Cfg
raw = dict(conf.cfg.to_dict())
raw["llm"] = dict(raw["llm"])
raw["llm"]["code_cited_collections"] = "rules"
monkeypatch.setattr(conf, "cfg", _Cfg(raw))
assert llm_config.load().code_cited_collections == ("rules",)
def test_iom_companion_max_defaults_to_four():
from llm.config import LlmConfig
cfg = LlmConfig(
ollama_hosts=("http://h",),
embed_model="e",
instruct_model="i",
embed_dim=1,
build_ann_index=False,
pg_host="h",
pg_port=1,
pg_db="d",
pg_user="u",
)
assert cfg.iom_companion_max == 4