litellm/ci_cd/cost_map_guard.py
devin-ai-integration[bot] 7dc7f101d9
feat(decisions): bill decisions and systemone from _decisions cost map fields (#45904)
* feat(decisions): bill decisions and systemone from <provider>/decisions/<model> cost map rows

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat(decisions): mark decisions pricing rows with mode decisions

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(ui): sync generated API types for decisions mode

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(decisions): update pricing expectations in proxy tests

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(decisions): price classifier calls from decision rows

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(health): drop redundant evaluation handler after main merge

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(decisions): inject pricing row for deployed classifier

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor(decisions): ship the decisions pricing lookup without cost map rows

Restore both cost maps to main. Tests inject their own
<provider>/decisions/<model> rows. The Add Model dropdown hides those
pricing keys and offers mode decisions instead of evaluation.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(ui): expect the Decisions mode option in the Add Model form

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* feat(decisions): bill decisions and systemone from _decisions cost map fields

Replace the provider/decisions/model pricing rows with <field>_decisions
fields on the model's own row. cost_per_token overlays them for the
decisions, adecisions, systemone and asystemone call types and prices
through generic_cost_per_token; chat, responses and batch keep the plain
fields. gpt-6-luna gains its Decisions rates (input 1e-07, output 0,
cached and cache-write input 1e-07, 2x above 272k tokens).

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(decisions): satisfy type gate, schema sync and test_utils schema for _decisions fields

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(decisions): import cost_calculator module to keep basedpyright unknown-variable count flat

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(decisions): drop stray fireworks import from __init__ and annotate test cost rows for the type gate

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): cover gpt-6-luna decisions and systemone above the 272k tier

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor(decisions): keep the decisions pricing block clear of main's stale azure comment

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore(cost_calculator): drop stale azure models doc comment

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-12 14:31:12 -07:00

217 lines
7.7 KiB
Python

"""Guard the cost map on pull requests.
Every pull request whose diff against its merge base touches one of the three cost map files gets the file
checks: the files parse, the backup copy matches the root file, and the JSON schema is in sync and validates the
map. A pull request that leaves all three untouched skips them, since merging it keeps the base branch's copies
and its head tree only carries whatever state the branch was cut from. Pull requests from the cost map sync bot
(branches named litellm_cost_map_sync_*) always get the file checks and additionally may only touch those three
files and may only add or update models.
"""
from __future__ import annotations
import argparse
import json
import subprocess
import sys
from collections.abc import Mapping, Sequence
from dataclasses import dataclass
from types import MappingProxyType
from typing import Final
from generate_model_prices_schema import SPECIAL_ROOT_KEYS, build_schema, render, validation_errors
COST_MAP_PATH: Final = "model_prices_and_context_window.json"
BACKUP_PATH: Final = "litellm/model_prices_and_context_window_backup.json"
SCHEMA_PATH: Final = "model_prices_and_context_window.schema.json"
GUARDED_PATHS: Final = (COST_MAP_PATH, BACKUP_PATH, SCHEMA_PATH)
BOT_BRANCH_PREFIX: Final = "litellm_cost_map_sync_"
EVALUATION_OUTPUT_PRICE_SOURCES: Final[Mapping[str, str]] = MappingProxyType({})
CostMap = dict[str, object]
@dataclass(frozen=True, slots=True)
class Snapshot:
cost_map: str
backup: str
schema: str
def _parse_object(text: str, path: str) -> CostMap | str:
try:
parsed: Final = json.loads(text)
except json.JSONDecodeError as error:
return f"{path} is not valid JSON: {error}"
return parsed if isinstance(parsed, dict) else f"{path} must be a JSON object at the root"
def _rendered_schema(cost_map: CostMap) -> str:
try:
return render(build_schema(cost_map))
except SystemExit as error:
return str(error)
def _evaluation_output_price_failure(
key: str, entry: object, evaluation_output_price_sources: Mapping[str, str]
) -> str | None:
if not isinstance(entry, dict) or entry.get("mode") not in ("evaluation", "decisions"):
return None
output_cost: Final = entry.get("output_cost_per_token")
if (
not isinstance(output_cost, (int, float))
or isinstance(output_cost, bool)
or output_cost <= 0
or key in evaluation_output_price_sources
):
return None
return (
f"{key}: mode evaluation and decisions rows bill input only; output_cost_per_token must be 0 unless the vendor "
"prices output tokens for this model (add the source to EVALUATION_OUTPUT_PRICE_SOURCES)"
)
def _file_failures(
head: Snapshot,
head_map: CostMap,
*,
evaluation_output_price_sources: Mapping[str, str] = EVALUATION_OUTPUT_PRICE_SOURCES,
) -> tuple[str, ...]:
schema_text: Final = _rendered_schema(head_map)
if not schema_text.startswith("{"):
return (schema_text,)
backup_failure: Final = (
()
if head.backup == head.cost_map
else (f"{BACKUP_PATH} differs from {COST_MAP_PATH}; copy the root file over it",)
)
schema_failure: Final = (
()
if head.schema == schema_text
else (
f"{SCHEMA_PATH} is out of sync with {COST_MAP_PATH}; "
"run `python ci_cd/generate_model_prices_schema.py` and commit the result",
)
)
return (
*backup_failure,
*schema_failure,
*(
f"{COST_MAP_PATH} does not validate against its schema: {error}"
for error in validation_errors(head_map, json.loads(schema_text))[:20]
),
*(
failure
for key, entry in head_map.items()
if (
failure := _evaluation_output_price_failure(
key, entry, evaluation_output_price_sources
)
)
is not None
),
)
def _entries(cost_map: CostMap) -> dict[str, dict[str, object]]:
return {key: entry for key, entry in cost_map.items() if isinstance(entry, dict)}
def _bot_failures(base: Snapshot, head_map: CostMap, changed_files: Sequence[str]) -> tuple[str, ...]:
base_map: Final = _parse_object(base.cost_map, COST_MAP_PATH)
if isinstance(base_map, str):
return (f"merge base: {base_map}",)
base_entries: Final = _entries(base_map)
head_entries: Final = _entries(head_map)
removed_fields: Final = tuple(
f"{key}.{field}"
for key, entry in base_entries.items()
if key in head_entries
for field in entry
if field not in head_entries[key]
)
return (
*(
f"bot PRs may only change the cost map files, not {path}"
for path in changed_files
if path not in GUARDED_PATHS
),
*(f"bot PRs may not remove models: {key}" for key in base_map if key not in head_map),
*(f"bot PRs may not remove fields: {ref}" for ref in removed_fields),
*(
f"bot PRs may not change {key}"
for key in sorted(SPECIAL_ROOT_KEYS)
if base_map.get(key) != head_map.get(key)
),
)
def touches_cost_map(changed_files: Sequence[str]) -> bool:
return any(path in GUARDED_PATHS for path in changed_files)
def contract_for(bot: bool, changed_files: Sequence[str]) -> str:
if bot:
return "bot contract enforced"
return "human PR, file checks only" if touches_cost_map(changed_files) else "human PR, cost map untouched"
def guard_failures(
base: Snapshot,
head: Snapshot,
changed_files: Sequence[str],
bot: bool,
*,
evaluation_output_price_sources: Mapping[str, str] = EVALUATION_OUTPUT_PRICE_SOURCES,
) -> tuple[str, ...]:
if not bot and not touches_cost_map(changed_files):
return ()
head_map: Final = _parse_object(head.cost_map, COST_MAP_PATH)
if isinstance(head_map, str):
return (head_map,)
return (
*_file_failures(
head, head_map, evaluation_output_price_sources=evaluation_output_price_sources
),
*(_bot_failures(base, head_map, changed_files) if bot else ()),
)
def _git(*args: str) -> str | None:
result: Final = subprocess.run(("git", *args), check=False, capture_output=True, text=True)
return result.stdout if result.returncode == 0 else None
def snapshot(revision: str) -> Snapshot:
return Snapshot(*(_git("show", f"{revision}:{path}") or "" for path in GUARDED_PATHS))
def changed_files(base: str, head: str) -> tuple[str, ...] | None:
diff: Final = _git("diff", "--name-only", "--no-renames", base, head)
return None if diff is None else tuple(diff.splitlines())
def main(argv: Sequence[str]) -> int:
parser: Final = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--base", required=True, help="merge base of the pull request")
parser.add_argument("--head", required=True, help="head commit of the pull request")
parser.add_argument("--head-ref", required=True, help="head branch name of the pull request")
args: Final = parser.parse_args(argv)
bot: Final = args.head_ref.startswith(BOT_BRANCH_PREFIX)
changed: Final = changed_files(args.base, args.head)
if changed is None:
print(f"cost map guard failed: git diff {args.base} {args.head} failed, so the changed files are unknown")
return 1
failures: Final = guard_failures(snapshot(args.base), snapshot(args.head), changed, bot)
contract: Final = contract_for(bot, changed)
if failures:
print(f"cost map guard failed ({contract}):")
print("\n".join(f"- {failure}" for failure in failures))
return 1
print(f"cost map guard passed ({contract})")
return 0
if __name__ == "__main__":
sys.exit(main(sys.argv[1:]))