synapseorch-ai/synapse-ai](https:

v1.8.1 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 17d AI Agents & Assistants

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

custom-agents custom-tools directed-acyclic-graph llm-agent mcp-client mcp-server

+6 more

mcp-servers mcp-tools multi-agent multi-agent-orchestration multi-agent-systems n8n

Summary

AI summary

Updates 🧰 Notes, local, and env-driven across a mixed release.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Low	Adds configurable operational timeouts via environment variables. Adds configurable operational timeouts via environment variables. Source: llm_adapter@2026-07-16 Confidence: high	—
Feature	Low	Adds ability to import tools from OpenAPI/Swagger spec via Settings UI. Adds ability to import tools from OpenAPI/Swagger spec via Settings UI. Source: llm_adapter@2026-07-16 Confidence: low	—
Feature	Low	Allows importing an entire API as agent tools from OpenAPI/Swagger specs. Allows importing an entire API as agent tools from OpenAPI/Swagger specs. Source: granite4.1:30b@2026-07-16-audit Confidence: low	—
Dependency	Low	Adds new dependency pyyaml for YAML OpenAPI spec support. Adds new dependency pyyaml for YAML OpenAPI spec support. Source: llm_adapter@2026-07-16 Confidence: high	—

Full changelog

Synapse v1.8.1

Two quality-of-life additions: import a whole API's worth of tools from an OpenAPI spec, and tune operational timeouts without touching code.

✨ Import tools from OpenAPI / Swagger

Turn an entire API into agent tools in one step. Settings → Custom Tools → Import OpenAPI:

Paste or upload an OpenAPI 3.x or Swagger 2.0 spec (JSON or YAML)
Preview every generated tool and pick the subset you want
Optional base-URL override, name prefix, and a shared auth header
Path/query params and JSON request bodies are mapped automatically; path params stay as {templated} URL segments

⏱️ Configurable timeouts (env-driven)

Slow network or a slow local model? Tune timeouts via environment variables — each falls back to its current default when unset, so nothing changes unless you opt in:

| Variable | Default (s) |
|---|---|
| SYNAPSE_MCP_SESSION_READ_TIMEOUT | 60 |
| SYNAPSE_MCP_TOOL_CALL_TIMEOUT | 60 |
| SYNAPSE_MCP_LIST_TOOLS_TIMEOUT | 15 |
| SYNAPSE_LLM_TIMEOUT | 180 |
| SYNAPSE_HTTP_TOOL_TIMEOUT | 30 |
| SYNAPSE_ORCH_STEP_TIMEOUT | 300 |
| SYNAPSE_ORCH_GLOBAL_TIMEOUT_MINUTES | 30 |
| SYNAPSE_ORCH_HUMAN_TIMEOUT | 3600 |

Set them in .env (local) or via env_file/environment in Docker — picked up by the backend and workers. Restart to apply. See .env.example for details.

🧰 Notes

New dependency: pyyaml (for YAML specs)
New endpoints: POST /api/tools/import/openapi, POST /api/tools/custom/bulk

Full Changelog: https://github.com/synapseorch-ai/synapse-ai/compare/v1.8.0...v1.8.1

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track synapseorch-ai/synapse-ai](https:

Get notified when new releases ship.

About synapseorch-ai/synapse-ai](https:

All releases →