perf(server): unblock event loop on rate-limit waits and markitdown
Two complementary changes to mitigate intermittent TLS handshake
timeouts and "notifications/cancelled: Bad Request" seen against the
single-worker uvicorn deployment.
1. bedesten rate-limiter back-pressure
- Add optional ``max_wait`` to ``_TokenBucket.acquire``: if the next
wait would exceed it, raise ``BedestenRateLimited`` immediately
instead of sleeping. After a server-side 429 the bucket pauses for
up to 30s; previously a queued request sat in ``asyncio.sleep``
for that whole window, holding the worker slot and pushing the
MCP client past its cancellation timeout.
- ``search_bedesten_unified`` / ``get_bedesten_document_markdown``
catch ``BedestenRateLimited`` and reuse the existing structured
429-style response, so callers get a fast, clean retry signal.
- Tunable via ``BEDESTEN_RATE_MAX_WAIT_S`` (default 8.0s).
2. Offload sync markitdown conversions to a thread
- Every ``markitdown.convert*`` call site is now wrapped in
``asyncio.to_thread(...)`` across 14 modules (bedesten, yargitay,
danistay, anayasa norm + bireysel, uyusmazlik, emsal, rekabet,
gib, kvkk, sayistay, bddk, sigorta_tahkim, kik_v2). PDF / large
HTML parsing was stalling the event loop for seconds, which on a
single-worker deployment delayed every other in-flight request
and queued new TLS handshakes until they timed out.
Verified locally:
- ``ast.parse`` + ``importlib.import_module`` on all 15 modified files
- ``mcp_server_main.create_app()`` constructs successfully
- New ``_TokenBucket.acquire(max_wait=...)`` smoke-tested across 6
paths: capacity-available, no-arg backward compat, max_wait raise,
max_wait wait+succeed, ``penalize_until`` + max_wait fast-raise.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 4.7
parent
26aa3dacc6
commit
96a5a538b2
@@ -1,5 +1,6 @@
|
||||
# sigorta_tahkim_mcp_module/client.py
|
||||
|
||||
import asyncio
|
||||
import httpx
|
||||
from typing import Optional
|
||||
import logging
|
||||
@@ -202,7 +203,11 @@ class SigortaTahkimApiClient:
|
||||
response.raise_for_status()
|
||||
|
||||
pdf_stream = io.BytesIO(response.content)
|
||||
result = self.markitdown.convert_stream(pdf_stream, file_extension=".pdf")
|
||||
# markitdown is sync; offload to thread so PDF parsing doesn't block
|
||||
# the event-loop / other in-flight MCP requests.
|
||||
result = await asyncio.to_thread(
|
||||
self.markitdown.convert_stream, pdf_stream, file_extension=".pdf"
|
||||
)
|
||||
return result.text_content.strip(), pdf_url
|
||||
|
||||
def _split_into_decisions(self, markdown_content: str) -> list[tuple[str, str]]:
|
||||
|
||||
Reference in New Issue
Block a user