17ba5d723b
Python rewrite of the agent harness on top of deepagents 0.6.1 + langchain 1.x, replacing the abandoned TS attempt in packages/. 388 unit/integration tests pass. Steps ----- 0. Scaffolding — uv workspace, ruff/mypy/pre-commit/alembic, src/tests/docs trees with docs/schemas/ seeded from my-deepagent-seed/. 1. Core — config (pydantic-settings with MYDEEPAGENT_ env prefix and TOML source), enums (Backend, Capability, RiskLevel, ApprovalDecisionAction, ApprovalState, RunState, RunPhaseState, SessionState, ErrorClass), errors (MyDeepAgentError + BudgetExhaustedError with PEP-3134 cause + context suppression), hash (canonical JSON + sha256). 2. Persona/Workflow/Binding — pydantic v2 schemas with tuple-based deep immutability (post-construction hash drift prevented), YAML loaders, deterministic auto-select (preferred_backends → version → name → hash), override resolution with ineligibility diagnostics, PersonaConsentStore with fcntl.flock + tmp+fsync+rename atomic write. 3. Artifact schema registry — Draft202012Validator, multi-root resolution, structured ValidationFinding output. 4. Persistence — 18 SQLAlchemy 2.0 async ORM models with FK CASCADE/RESTRICT, WAL + busy_timeout + foreign_keys PRAGMA, alembic baseline + ux_active_run_repo_base partial unique index, LangGraph SqliteSaver as context manager only (lifecycle safety). 5. DeepAgent session — build_agent wires Persona → create_deep_agent with LocalShellBackend / FilesystemBackend / StateBackend / CompositeBackend, ChatOpenAI(base_url=openrouter) for openrouter: model strings, and 4 middleware classes (cost / audit-tool / safety-shell / fallback-model). Critical workarounds -------------------- - deepagents 0.6.1 rejects FilesystemPermission together with backends that implement SandboxBackendProtocol (LocalShellBackend). SafetyShellMiddleware enforces destructive-command and secret-path policy at the tool layer instead, and build_agent strips the permissions kwarg when the persona's deepagents_backend is local_shell. - FilesystemOperation in deepagents is Literal['read', 'write'] only; _map_operations collapses our richer schema (read/write/edit/ls) safely. Real OpenRouter smoke --------------------- test_openrouter_deepagents_local_shell_smoke calls DeepSeek via deepagents + LocalShellBackend + SafetyShellMiddleware end-to-end. PASS, ~$0.000001 cost, input=9 / output=1 tokens with content "OK". Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
100 lines
3.1 KiB
Python
100 lines
3.1 KiB
Python
"""OpenRouter model pricing cache + cost computation.
|
|
|
|
v0.1.0: in-process dict cache + optional DB refresh. doctor와 background refresh가
|
|
업데이트 trigger (Step 12).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
|
|
import httpx
|
|
|
|
from ..errors import MyDeepAgentError
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class ModelPrice:
|
|
model: str # OpenRouter id, e.g. "deepseek/deepseek-chat"
|
|
input_per_1k_usd: float
|
|
output_per_1k_usd: float
|
|
context_length: int
|
|
|
|
|
|
class PricingCache:
|
|
"""In-memory cache of OpenRouter pricing. Caller refreshes via fetch_openrouter_pricing()."""
|
|
|
|
def __init__(self) -> None:
|
|
self._cache: dict[str, ModelPrice] = {}
|
|
|
|
def get(self, model: str) -> ModelPrice | None:
|
|
key = model.removeprefix("openrouter:")
|
|
return self._cache.get(key)
|
|
|
|
def set(self, prices: list[ModelPrice]) -> None:
|
|
for p in prices:
|
|
self._cache[p.model] = p
|
|
|
|
def compute_cost(self, model: str, input_tokens: int, output_tokens: int) -> float:
|
|
"""Return USD cost. Returns 0.0 if model price is unknown (logged separately)."""
|
|
price = self.get(model)
|
|
if price is None:
|
|
return 0.0
|
|
return (input_tokens / 1000.0) * price.input_per_1k_usd + (
|
|
output_tokens / 1000.0
|
|
) * price.output_per_1k_usd
|
|
|
|
|
|
async def fetch_openrouter_pricing(api_key: str, base_url: str) -> list[ModelPrice]:
|
|
"""Fetch the OpenRouter /models endpoint and parse pricing."""
|
|
async with httpx.AsyncClient(timeout=10.0) as client:
|
|
try:
|
|
r = await client.get(
|
|
f"{base_url}/models",
|
|
headers={"Authorization": f"Bearer {api_key}"},
|
|
)
|
|
r.raise_for_status()
|
|
except httpx.HTTPError as e:
|
|
raise MyDeepAgentError.recoverable(
|
|
"network_blip",
|
|
message=f"failed to fetch openrouter pricing: {e}",
|
|
cause=e,
|
|
) from e
|
|
data: dict[str, object] = r.json()
|
|
return _parse_pricing_payload(data)
|
|
|
|
|
|
def _parse_pricing_payload(data: dict[str, object]) -> list[ModelPrice]:
|
|
"""Parse OpenRouter response.
|
|
|
|
Expected format::
|
|
|
|
{"data": [{"id": "...", "pricing": {"prompt": "...", "completion": "..."}, ...}]}
|
|
"""
|
|
models = data.get("data", [])
|
|
if not isinstance(models, list):
|
|
return []
|
|
out: list[ModelPrice] = []
|
|
for m in models:
|
|
if not isinstance(m, dict):
|
|
continue
|
|
model_id = m.get("id")
|
|
pricing = m.get("pricing") or {}
|
|
if not isinstance(model_id, str) or not isinstance(pricing, dict):
|
|
continue
|
|
try:
|
|
prompt_per_token = float(pricing.get("prompt", "0") or "0")
|
|
completion_per_token = float(pricing.get("completion", "0") or "0")
|
|
ctx_len = int(m.get("context_length", 0) or 0)
|
|
except (TypeError, ValueError):
|
|
continue
|
|
out.append(
|
|
ModelPrice(
|
|
model=model_id,
|
|
input_per_1k_usd=prompt_per_token * 1000.0,
|
|
output_per_1k_usd=completion_per_token * 1000.0,
|
|
context_length=ctx_len,
|
|
)
|
|
)
|
|
return out
|