Parth
e7d75c3b05
* Rewrite comments in Google developer documentation style Rewrite the comments and docstrings across the backend core modules so they read plainly. The previous prose was accurate but dense and figurative, which made it slow to skim. Applies the Google developer documentation style guide: short sentences, active voice, present tense, American spelling, and no metaphors, idioms, or rhetorical asides. Replaces em-dash chains with separate sentences.
72 lines
1.8 KiB
Python
72 lines
1.8 KiB
Python
"""In-memory ring buffer of recent provider requests/responses for the debug page.
|
|
|
|
API keys never enter the log: only the request body (which carries no
|
|
credentials) and response text are recorded, both truncated.
|
|
"""
|
|
|
|
import itertools
|
|
from collections import deque
|
|
from datetime import datetime, timezone
|
|
|
|
MAX_ENTRIES = 30
|
|
MAX_TEXT = 6000
|
|
|
|
_entries: deque[dict] = deque(maxlen=MAX_ENTRIES)
|
|
_ids = itertools.count(1)
|
|
|
|
|
|
def _clip(text: str) -> str:
|
|
if len(text) <= MAX_TEXT:
|
|
return text
|
|
return text[:MAX_TEXT] + f"\n… [{len(text) - MAX_TEXT} more chars truncated]"
|
|
|
|
|
|
def _clip_obj(obj):
|
|
if isinstance(obj, str):
|
|
return _clip(obj)
|
|
if isinstance(obj, dict):
|
|
return {k: _clip_obj(v) for k, v in obj.items()}
|
|
if isinstance(obj, list):
|
|
return [_clip_obj(v) for v in obj]
|
|
return obj
|
|
|
|
|
|
def start_entry(url: str, model: str, body: dict) -> dict:
|
|
entry = {
|
|
"id": next(_ids),
|
|
"time": datetime.now(timezone.utc).isoformat(),
|
|
"url": url,
|
|
"model": model,
|
|
"request": _clip_obj(body),
|
|
"status": "pending",
|
|
"response": "",
|
|
"usage": None,
|
|
"error": None,
|
|
}
|
|
_entries.appendleft(entry)
|
|
return entry
|
|
|
|
|
|
def finish_entry(
|
|
entry: dict,
|
|
*,
|
|
response: str = "",
|
|
error: str | None = None,
|
|
usage: dict | None = None,
|
|
) -> None:
|
|
"""Finishes a log entry.
|
|
|
|
`usage` is the endpoint's own token accounting, when it reported any. On
|
|
OpenRouter it carries `prompt_tokens_details.cached_tokens`, which is the
|
|
only direct measure of whether the prompt prefix is being cached, and it is
|
|
worth seeing next to the request that produced it.
|
|
"""
|
|
entry["response"] = _clip(response)
|
|
entry["usage"] = usage
|
|
entry["error"] = error
|
|
entry["status"] = "error" if error else "ok"
|
|
|
|
|
|
def recent() -> list[dict]:
|
|
return list(_entries)
|