Dobromir Popov b95e25a5c3 fix: silence BrokenPipeError on slow CPU inference, raise downstream timeout ...

BrokenPipeError on wfile.write is harmless — the client disconnected
before the response arrived. Suppress it instead of printing a full
traceback to stderr.

Raise the downstream pipeline timeout from 10s to 120s so the Windows
node (or any caller) waits long enough for CPU-mode inference to
complete before giving up.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-06-30 10:01:37 +03:00

.3rdparty

iinit

2026-06-28 23:49:11 +03:00

.agents/skills

iinit

2026-06-28 23:49:11 +03:00

.claude

inference working

2026-06-29 23:54:35 +03:00

.scratch/distributed-inference-network

feat(us-019): distributed tracker consensus — Raft assignments + CRDT gossip

2026-06-30 09:05:21 +03:00

docs

feat(us-018): WSL2 install guide, two-machine LAN test docs, and test script

2026-06-30 01:37:33 +03:00

packages

fix: silence BrokenPipeError on slow CPU inference, raise downstream timeout

2026-06-30 10:01:37 +03:00

scripts

feat(us-018): WSL2 install guide, two-machine LAN test docs, and test script

2026-06-30 01:37:33 +03:00

tests

feat(us-019): distributed tracker consensus — Raft assignments + CRDT gossip

2026-06-30 09:05:21 +03:00

.env.testnet

feat: add settlement contract boundary

2026-06-29 02:46:25 +03:00

.gitignore

feat: scaffold meshnet monorepo

2026-06-29 00:28:29 +03:00

AGENTS.md

iinit

2026-06-28 23:49:11 +03:00

conftest.py

feat: add fraud detection validator

2026-06-29 09:46:22 +03:00

CONTEXT.md

docs: add ADRs and user stories for real model inference stack (US-011–014)

2026-06-29 14:43:54 +03:00

pyproject.toml

feat: add real PyTorch model backend

2026-06-29 15:54:40 +03:00

QUICKSTART.md

docs: update QUICKSTART to reflect auto-shard detection

2026-06-29 18:28:23 +03:00

skills-lock.json

iinit

2026-06-28 23:49:11 +03:00

Description

No description provided

1.2 GiB

Languages

Python 94.7%

HTML 4.1%

C++ 0.7%

Shell 0.2%

JavaScript 0.2%

Other 0.1%