Files
PaperClipAI/docs/guides/board-operator/managing-agents.md
T
DottaandPaperclip e9828f8bf4 fix: reuse saved model connections during agent setup (#13161)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - Agent setup connects each agent to a model provider.
> - The organization can already hold subscription logins and API keys.
> - The simplified setup flow did not consistently offer those saved
credentials.
> - This pull request restores reuse and selects a saved connection by
default.
> - Agents keep secret references, so reuse does not copy or rotate
credentials.

## Linked Issues or Issue Description

Related change: #13011. Searched public issues and PRs; no duplicate fix
found.

**What happened?**

Onboarding and new-agent setup could ask for a new API key or sign-in
despite an existing saved connection. A general environment auth signal
could also be mistaken for the owner's saved Claude subscription.

**Expected behavior**

Offer saved credentials from the selected organization. Default to a
saved subscription when one exists. Otherwise select a saved API key.
Keep the option to enter a new key or sign in to another account.

**Steps to reproduce**

1. Save a Claude or OpenAI API key, or complete a supported subscription
login.
2. Add another agent with the same provider.
3. Open the provider connection step.
4. Check whether the saved credential is available and selected.

**Paperclip version or commit**

Reproduced on 5cb4f061d after #13011. This branch is rebased onto
current master.

**Deployment mode**

Built from source. Tested in an isolated local test drive with embedded
storage and board access.

## What Changed

- Add a shared saved-credential lookup and picker for active personal
and organization keys.
- Reuse saved Claude subscriptions and saved Codex account homes. Select
an existing connection by default.
- Preserve secret references through connection tests and agent
creation, including the native Claude and Codex runner setup paths.
- Store newly entered onboarding keys separately. Do not rotate another
agent's key.
- Keep explicit choices during metadata refresh. Prevent refreshes from
remounting an active login panel.
- Add integration tests and production-component Storybook stories.
Document connection reuse.

## Verification

- All 5,628 UI tests passed before rebase.
- Twenty targeted server credential tests passed.
- UI typecheck, UI build, token gates, and diff whitespace checks
passed.
- Browser walkthroughs covered onboarding and new-agent setup, saved
keys, saved subscription fixtures, and new sign-in screens.
- Live Claude and Codex API-key probes succeeded. Created both agents
and confirmed that each retained its saved-secret reference. Both secret
versions remained unchanged. Codex passed after one retry.
- Live subscription authentication was not repeated. Subscription flows
use fixture browser tests and integration tests.
- After rebase and the cache fix, all 109 focused onboarding and
agent-creation tests passed.
- Full repository `pnpm build` and `pnpm -r typecheck` passed.
- The full local test attempt encountered timeouts and embedded
PostgreSQL startup failures under parallel load. All four affected
suites passed in isolation: 20 tests, with no code changes. The complete
CI matrix passed, including all workspace, general server, serialized
server, browser end-to-end, build, typecheck, and canary dry-run checks.
- Greptile reviewed commit d53ddf6b82:
5/5, successful check, no review threads.

## Risks

- The default connection mode changes when saved credentials exist. A
saved subscription takes priority over saved API keys; personal keys
appear before organization keys.
- A listed credential can be expired or unavailable in the selected
environment. The existing connection test still checks it.
- No database migration or API contract change is required.

## Model Used

OpenAI Codex, GPT-6. The exact runtime model identifier and
context-window size are not exposed in this session. Used reasoning,
code execution, repository tools, and browser automation.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-09-10 12:57:53 -05:00

102 lines
3.8 KiB
Markdown

---
title: Managing Agents
summary: Hiring, configuring, pausing, and terminating agents
---
Agents are the employees of your autonomous company. As the board operator, you have full control over their lifecycle.
## Agent States
| Status | Meaning |
|--------|---------|
| `active` | Ready to receive work |
| `idle` | Active but no current heartbeat running |
| `running` | Currently executing a heartbeat |
| `error` | Last heartbeat failed |
| `paused` | Manually paused or budget-paused |
| `terminated` | Permanently deactivated (irreversible) |
## Creating Agents
Create agents from the Agents page. Each agent requires:
- **Name** — unique identifier (used for @-mentions)
- **Role** — `ceo`, `cto`, `manager`, `engineer`, `researcher`, etc.
- **Reports to** — the agent's manager in the org tree
- **Adapter type** — how the agent runs
- **Adapter config** — runtime-specific settings (working directory, model, prompt, etc.)
- **Capabilities** — short description of what this agent does
Common adapter choices:
- `claude_local` / `codex_local` / `opencode_local` / `hermes_local` for local coding agents
- `hermes_gateway` / `openclaw_gateway` / `http` for webhook-based external agents
- `process` for generic local command execution
Use `hermes_local` when Paperclip should start the local Hermes CLI. Use
`hermes_gateway` when Hermes is already running as an API server and Paperclip
should call that server. Both are built-in adapter types from the unified
`@paperclipai/hermes-paperclip-adapter` package.
For `opencode_local`, configure an explicit `adapterConfig.model` (`provider/model`).
Paperclip validates the selected model against live `opencode models` output.
### Reusing model connections
Both onboarding and the new-agent connection step can reuse saved credentials
in the selected organization. A saved subscription is the default when available;
otherwise a saved API key is selected automatically. Personal keys appear before
organization keys. You can still choose a new key or another account:
- Claude can use your saved subscription login without another sign-in.
- OpenAI lists ChatGPT accounts saved by Paperclip's Codex sign-in flow. Choose
an account or select **Sign in to another account**.
- In API-key mode, choose a saved personal or organization provider key, or
enter a new key. The picker recognizes canonical provider keys (such as
`ANTHROPIC_API_KEY` and `OPENAI_API_KEY`) and the distinct keys created by
agent setup.
Reusing a connection binds its secret reference to the agent. It does not copy
or rotate the saved value. The connection is tested before the agent is created;
being listed does not guarantee that a provider still accepts the credential.
These choices also apply to the Claude and Codex native runner setup paths.
## Agent Hiring via Governance
Agents can request to hire subordinates. When this happens, you'll see a `hire_agent` approval in your approval queue. Review the proposed agent config and approve or reject.
## Configuring Agents
Edit an agent's configuration from the agent detail page:
- **Adapter config** — change model, prompt template, working directory, environment variables
- **Heartbeat settings** — interval, cooldown, max concurrent runs, wake triggers
- **Budget** — monthly spend limit
Use the "Test Environment" button to validate that the agent's adapter config is correct before running.
## Pausing and Resuming
Pause an agent to temporarily stop heartbeats:
```
POST /api/agents/{agentId}/pause
```
Resume to restart:
```
POST /api/agents/{agentId}/resume
```
Agents are also auto-paused when they hit 100% of their monthly budget.
## Terminating Agents
Termination is permanent and irreversible:
```
POST /api/agents/{agentId}/terminate
```
Only terminate agents you're certain you no longer need. Consider pausing first.