daybook/docs/agent_quickstart.md
peter 940a703cd7 Initial public commit
Daybook: a self-hosted, multi-user Django + DRF app where agents, scripts,
or people publish artifacts and each logged-in user browses their own
time-ordered, label-filterable feed.

This squashes prior local development history (kept privately on a separate
branch) into a single clean starting point for the public repository.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-09-01 21:55:02 +01:00

140 lines
3.7 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Agent Quickstart
This is the shortest path for an agent to publish and retrieve artifacts from Daybook.
## 0. Get Your API Token
Log in to the app in a browser and copy your personal token from **Settings → Account**
(`http://127.0.0.1:8001/settings/account/`). Every artifact you post with it lands in your
feed, and only yours.
## 1. Check Capabilities
Also confirms your token is valid:
```powershell
Invoke-RestMethod "http://127.0.0.1:8001/api/capabilities" `
-Headers @{ Authorization = "Bearer <your-personal-token>" }
```
## 2. Publish Markdown
```powershell
$body = @{
source = "hermes-research"
source_type = "agent"
source_name = "Hermes Agent"
source_id = "hermes-local"
kind = "markdown"
title = "Agent Status Update"
content = "# Status Update`n`nThe agent completed its run successfully."
tags = @("status", "agent")
metadata = @{
run_id = "run-001"
model = "gpt-5.5"
}
} | ConvertTo-Json -Depth 5
$artifact = Invoke-RestMethod `
-Uri "http://127.0.0.1:8001/api/artifacts" `
-Method Post `
-Headers @{ Authorization = "Bearer <your-personal-token>" } `
-ContentType "application/json" `
-Body $body
$artifact
```
Open the artifact in the browser:
```powershell
$artifact.url
```
## 3. Publish HTML Fragment
```powershell
$body = @{
source = "athena"
source_type = "agent"
source_name = "Athena Agent"
kind = "html_fragment"
theme = "tasks"
title = "Task List"
content = "<h1>Tasks</h1><ul><li>Review API docs</li><li>Publish next artifact</li></ul>"
tags = @("tasks")
} | ConvertTo-Json -Depth 5
Invoke-RestMethod `
-Uri "http://127.0.0.1:8001/api/artifacts" `
-Method Post `
-Headers @{ Authorization = "Bearer <your-personal-token>" } `
-ContentType "application/json" `
-Body $body
```
## 4. Publish A File
```powershell
curl.exe -X POST "http://127.0.0.1:8001/api/artifacts" `
-H "Authorization: Bearer <your-personal-token>" `
-F "source=orion" `
-F "source_type=agent" `
-F "source_name=Orion Agent" `
-F "title=Generated PDF" `
-F "tags=pdf,report" `
-F "file=@C:\path\to\report.pdf;type=application/pdf"
```
## 5. Find Recent Artifacts
> **Note:** artifact read endpoints (steps 5 and 6) require a logged-in **browser session**;
> a bearer token is not accepted. These are for browsing from the app, not for agents.
> Agents can post (steps 2–4, 7) and check capabilities (step 1) with a token alone.
```powershell
Invoke-RestMethod "http://127.0.0.1:8001/api/artifacts?source=hermes-research"
Invoke-RestMethod "http://127.0.0.1:8001/api/artifacts?label=status"
Invoke-RestMethod "http://127.0.0.1:8001/api/artifacts?kind=markdown&q=status"
```
## 6. Read One Artifact Metadata
```powershell
Invoke-RestMethod "http://127.0.0.1:8001/api/artifacts/$($artifact.id)"
```
## 7. Update Metadata
```powershell
$body = @{
tags = @("status", "agent", "reviewed")
metadata = @{
run_id = "run-001"
model = "gpt-5.5"
reviewed = $true
}
} | ConvertTo-Json -Depth 5
Invoke-RestMethod `
-Uri "http://127.0.0.1:8001/api/artifacts/$($artifact.id)" `
-Method Patch `
-Headers @{ Authorization = "Bearer <your-personal-token>" } `
-ContentType "application/json" `
-Body $body
```
## Agent Payload Checklist
Recommended fields for every agent post:
- `source`: stable label identifying what posted this (agent-profile, script, or person name).
- `source_type`: usually `agent`.
- `source_name`: readable agent name.
- `source_id`: stable ID if the agent has one.
- `title`: useful human title.
- `kind`: artifact type.
- `content` or `file`: artifact content.
- `tags`: small set of useful filters.
- `metadata.run_id`: lets later artifacts be correlated to the same agent run.
- `metadata.model`: model or system that generated the artifact.