xsl
f46ecc5eb0
Two defects that only surface against the real DeepSeek API, both of which break the cost model rather than the code: deepseek-v4-flash enables thinking mode by default. The same single-turn question took 13.5s with it on and 1.8s with it off, and the thinking tokens are billed at the output rate. That misses NFR-PERF-02b (15s per turn) and inflates every conversational call. SceneConfig now carries an explicit `thinking` flag, all four V1 scenes set it to false, and the provider always sends the parameter rather than relying on the upstream default. Reasoning tokens are recorded separately in Usage.tokens_reasoning so the cost of ever turning it back on is visible. DeepSeek moves to peak/off-peak pricing on 2026-08-17, with peak (Beijing 09:00-12:00 and 14:00-18:00) at twice the off-peak rate. Reports are generated mostly during peak hours, so a single blended rate would leave ob_ai_call -- the only input to V2 pricing -- off by nearly a factor of two. PeakAwareRateTable resolves the rate at call time; cost is computed and stored then, never recomputed later at whatever the current rate happens to be. Also here: - Replace the live API key in the redaction test with a synthetic one. The test that proves we redact secrets was itself a secret leak waiting for its first commit. - Correct LLM_COST_RATES_JSON, which held placeholder rates. - Make ids.SnowflakeGenerator take an injectable clock so rollover and clock-rollback are testable without patching a slots class. - Rename exceptions to the -Error suffix (N818) and clear the remaining ruff, mypy and import-linter findings, including two dead lines: a duplicate pytestmark assignment and a no-op assert on a None return. Gates: ruff, mypy (96 files incl. tests), 4/4 import contracts, detect-secrets, 166 unit + 3 integration tests, migration up/down round-trip.
77 lines
1.9 KiB
Python
Executable File
77 lines
1.9 KiB
Python
Executable File
"""JWT access tokens (架构文档 §9.1: Bearer JWT, 15 分钟).
|
|
|
|
The revocable refresh-token half (`id_session`) is FR-ACC-05 and is deliberately
|
|
NOT implemented in this scaffold — see packages/identity/README.md.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import time
|
|
from dataclasses import dataclass
|
|
from typing import Any
|
|
|
|
import jwt
|
|
|
|
from packages.shared.errors import AppError, ErrorCode
|
|
|
|
|
|
@dataclass(frozen=True, slots=True)
|
|
class AccessTokenClaims:
|
|
user_id: int
|
|
issued_at: int
|
|
expires_at: int
|
|
issuer: str
|
|
|
|
|
|
def create_access_token(
|
|
*,
|
|
user_id: int,
|
|
secret: str,
|
|
algorithm: str = "HS256",
|
|
ttl_seconds: int = 900,
|
|
issuer: str = "meida",
|
|
now: int | None = None,
|
|
) -> str:
|
|
issued_at = int(now if now is not None else time.time())
|
|
payload: dict[str, Any] = {
|
|
"sub": str(user_id),
|
|
"iat": issued_at,
|
|
"exp": issued_at + ttl_seconds,
|
|
"iss": issuer,
|
|
"typ": "access",
|
|
}
|
|
return str(jwt.encode(payload, secret, algorithm=algorithm))
|
|
|
|
|
|
def decode_access_token(
|
|
token: str,
|
|
*,
|
|
secret: str,
|
|
algorithm: str = "HS256",
|
|
issuer: str = "meida",
|
|
) -> AccessTokenClaims:
|
|
try:
|
|
payload = jwt.decode(
|
|
token,
|
|
secret,
|
|
algorithms=[algorithm],
|
|
issuer=issuer,
|
|
options={"require": ["exp", "iat", "sub"]},
|
|
)
|
|
except jwt.ExpiredSignatureError as exc:
|
|
raise AppError(ErrorCode.TOKEN_EXPIRED) from exc
|
|
except jwt.InvalidTokenError as exc:
|
|
raise AppError(ErrorCode.TOKEN_INVALID) from exc
|
|
|
|
try:
|
|
user_id = int(payload["sub"])
|
|
except (KeyError, TypeError, ValueError) as exc:
|
|
raise AppError(ErrorCode.TOKEN_INVALID) from exc
|
|
|
|
return AccessTokenClaims(
|
|
user_id=user_id,
|
|
issued_at=int(payload["iat"]),
|
|
expires_at=int(payload["exp"]),
|
|
issuer=str(payload.get("iss", issuer)),
|
|
)
|