wehub-resource-sync
4b6817381b
Benchmark image — build + push to ECR (any adapter) / build + push (push) Waiting to run
CI / quality (ubuntu-latest) (push) Waiting to run
CI / test (tools-runtime) (push) Waiting to run
CI / test (e2e-general) (push) Waiting to run
CI / test (cli-runtime) (push) Waiting to run
CI / test (e2e-provider-and-openclaw) (push) Waiting to run
CI / test (integrations-and-misc) (push) Waiting to run
CI / coverage-report (push) Blocked by required conditions
CI / test-kubernetes (push) Waiting to run
CI / should-run-thorough (push) Waiting to run
CI / test-thorough (cloudwatch-demo) (push) Blocked by required conditions
CI / test-thorough (flink-ecs) (push) Blocked by required conditions
CI / test-thorough (upstream-lambda) (push) Blocked by required conditions
CI / test-thorough (prefect-ecs-fargate) (push) Blocked by required conditions
CodeQL / Analyze (python) (push) Waiting to run
Release / build-binaries (zip, opensre.exe, onefile, windows-latest, windows-x64) (push) Blocked by required conditions
Release / publish-release (push) Blocked by required conditions
Release / publish-main-release (push) Blocked by required conditions
Release / prepare (push) Waiting to run
Release / verify (push) Blocked by required conditions
Release / build-python-dist (push) Blocked by required conditions
Release / build-binaries (tar.gz, opensre, onedir, macos-15-intel, darwin-x64) (push) Blocked by required conditions
Release / build-binaries (tar.gz, opensre, onedir, macos-latest, darwin-arm64) (push) Blocked by required conditions
Release / build-binaries (tar.gz, opensre, onedir, ubuntu-22.04, linux-x64) (push) Blocked by required conditions
Release / build-binaries (tar.gz, opensre, onedir, ubuntu-22.04-arm, linux-arm64) (push) Blocked by required conditions
Synthetic Deterministic Tests / Synthetic offline (deterministic) (push) Waiting to run
Interactive Shell Live (PR + post-merge) / turn-checks (no-LLM) (push) Waiting to run
Interactive Shell Live (PR + post-merge) / turn-live shard ${{ matrix.shard_index }} (push) Waiting to run
CI (OpenClaw E2E) / openclaw test (push) Has been cancelled
54 lines
3.2 KiB
Plaintext
54 lines
3.2 KiB
Plaintext
---
|
|
title: 'Assistant with Connected Tools'
|
|
description: 'How the interactive shell assistant pulls live data from your connected integrations to answer free-form questions'
|
|
---
|
|
|
|
When you ask the OpenSRE interactive shell a free-form question, the assistant can pull **live data from your connected integrations** before answering — instead of replying from text alone. If a question is answerable from an integration you have configured (GitHub, Datadog, Sentry, Grafana, cloud services, and more), the assistant transparently calls the same tools the investigation pipeline uses, gathers the results, and answers from that real data.
|
|
|
|
This happens automatically. You do not run a slash command or pick a tool — just describe what you want to know.
|
|
|
|
## Example
|
|
|
|
```text
|
|
> can you check the github issues for the windows crashes in https://github.com/Tracer-Cloud/opensre?
|
|
· gathering via GitHub · search issues — windows crashes…
|
|
There are 3 open issues mentioning Windows crashes. The most recent, #482
|
|
"App crashes on launch (Windows 11)", reports a startup segfault after the
|
|
2.4.0 update and has 6 reactions…
|
|
```
|
|
|
|
You can name the repository inline (`… in https://github.com/org/repo`), mention it in an earlier turn, rely on `GITHUB_REPOSITORY`, or let OpenSRE infer it from the current git checkout's `origin` remote when GitHub is connected.
|
|
|
|
The dim `· gathering via <source> · <tool> — <query hint>…` line shows which integration the assistant reached for while it works. When the same tool runs more than once, a `(2)`, `(3)`, … suffix and the query hint distinguish each call.
|
|
|
|
More questions that trigger live gathering:
|
|
|
|
| You ask | The assistant gathers from |
|
|
| --- | --- |
|
|
| "check the GitHub issues for the Windows crashes" | GitHub issues |
|
|
| "what do the datadog logs say about the payment service?" | Datadog logs |
|
|
| "are there recent Sentry errors on checkout?" | Sentry |
|
|
| "what's the recent error rate in grafana for prod-api?" | Grafana |
|
|
|
|
## How it works
|
|
|
|
1. You ask a question in plain language.
|
|
2. The assistant runs a short, bounded tool-gathering pass over the tools your **configured integrations** expose.
|
|
3. Tools are **read-only data fetches**, so they run autonomously — no per-call confirmation, just like an investigation.
|
|
4. The gathered results are folded into the answer the assistant writes back to you.
|
|
|
|
If gathering is interrupted (Ctrl+C) or a tool is unavailable, the assistant falls back to a normal text answer.
|
|
|
|
## When nothing is configured
|
|
|
|
If you have **no integrations configured**, behavior is unchanged: the assistant answers from text only, exactly as before. There is nothing to enable or turn on — connect an integration and the relevant questions start returning live data.
|
|
|
|
Run `/health` to see which integrations are connected, and `/tools` to list the tools currently available to the assistant.
|
|
|
|
## Related docs
|
|
|
|
- [Interactive Shell Commands](/interactive-shell-commands) — slash commands and natural-language actions
|
|
- [Integrations Overview](/integrations-overview) — connecting data sources
|
|
- [GitHub](/github) — configuring the GitHub integration used by the issues example
|
|
- [Investigation overview](/investigation-overview) — the full RCA pipeline these tools also power
|