slack-channel-monitor

What this skill does

# Slack Channel Monitor

Create a cron automation that polls up to 10 Slack channels every minute.
When a message containing the **trigger phrase** (default: `@openhands`) is
detected it:

1. Adds a 👀 reaction to the triggering message.
2. Opens an OpenHands conversation with the message and recent channel context.
3. Posts a reply in the Slack thread with a link to the conversation.

On every subsequent run:
- Replies in the thread are forwarded to the running conversation.
- When the conversation finishes (or errors), the agent's final response is
  posted back to the Slack thread.

> **Local mode only.** This automation targets the local OpenHands setup
> (`dev:automation` stack). A cloud/webhook-based variant is out of scope here.

---

## Prerequisites

### Required secrets

Verify that at least one of the following secrets is set in
**OpenHands Settings → Secrets** before proceeding:

| Secret name | Token type | Minimum scopes |
|---|---|---|
| `SLACK_BOT_TOKEN` | Bot (`xoxb-…`) | `channels:history`, `channels:read`, `reactions:write`, `chat:write` |
| `SLACK_USER_TOKEN` | User (`xoxp-…`) | Same as bot, plus `search:read` for multi-channel efficiency |

Check with:
```bash
# For bot token:
curl -s https://slack.com/api/auth.test -H "Authorization: Bearer $SLACK_BOT_TOKEN" \
  | python3 -c "import json,sys; d=json.load(sys.stdin); print('ok' if d.get('ok') else d.get('error'))"

# For user token:
curl -s https://slack.com/api/auth.test -H "Authorization: Bearer $SLACK_USER_TOKEN" \
  | python3 -c "import json,sys; d=json.load(sys.stdin); print('ok' if d.get('ok') else d.get('error'))"
```

If neither token is present, inform the user and stop  -  the automation cannot
function without Slack credentials.

### Optional secret

| Secret name | Default | Purpose |
|---|---|---|
| `OPENHANDS_URL` | `http://localhost:8000` | Base URL used to build conversation links posted in Slack |

---

## Setup Workflow

Follow these steps in order.

### Step 1  -  Collect channels

Ask the user: *"Which Slack channels should be monitored? You can provide
channel names (e.g. `#general`) or IDs (e.g. `C0123456789`)."*

**If the user provides channel names**, resolve them to IDs:

```bash
SLACK_TOKEN="${SLACK_BOT_TOKEN:-$SLACK_USER_TOKEN}"
curl -s "https://slack.com/api/conversations.list?types=public_channel,private_channel&limit=200&exclude_archived=true" \
  -H "Authorization: Bearer $SLACK_TOKEN" \
  | python3 -c "
import json, sys
data = json.load(sys.stdin)
if not data.get('ok'):
    print('ERROR:', data.get('error'))
    exit(1)
names = set(n.lstrip('#') for n in ['CHANNEL_NAMES_HERE'.split(',')])
for ch in data.get('channels', []):
    if ch['name'] in names:
        print(f\"{ch['name']} → {ch['id']}\")
"
```

Replace `CHANNEL_NAMES_HERE` with the comma-separated names the user provided.

**If `conversations.list` returns `missing_scope` or `not_authed`:**
Inform the user: *"The token doesn't have permission to list channels. Please
provide the channel IDs directly (right-click a channel in Slack → Copy link  - 
the last path segment starting with `C` is the ID)."*

**If the bot token lacks `channels:read`** for private channels, the user can
either invite the bot first (`/invite @botname`) or switch to a user token.

Collect up to 10 channel IDs. Record them as a Python list literal, e.g.:
```python
["C0123456789", "C9876543210"]
```

### Step 2  -  Collect trigger phrase

Ask the user: *"What trigger phrase should OpenHands respond to?
(Press Enter to use the default: `@openhands`)"*

Accepted values: any non-empty string unlikely to appear accidentally, e.g.
`@openhands`, `jazz hands`, `take-me-to-funky-town`.

### Step 3  -  Generate the automation script

Read `scripts/main.py` from this skill's directory and **copy it verbatim**.
Apply exactly three constant substitutions near the top of the file:

> **Do not reimplement, simplify, or hand-write a replacement script.**
> The template already contains the correct secret-loading, state-path,
> conversation-creation, and context-forwarding logic. Only the three
> configuration constants below should change unless syntax validation fails.

| Placeholder | Replace with |
|---|---|
| `TRIGGER_PHRASE = "@openhands"` | `TRIGGER_PHRASE = "{user_phrase}"` |
| `CHANNEL_IDS: list[str] = []` | `CHANNEL_IDS: list[str] = {channel_id_list}` |
| `DEFAULT_OPENHANDS_URL = "http://localhost:8000"` | `DEFAULT_OPENHANDS_URL = "{url}"` (keep default if user has no preference) |

Write the customised script to a temporary directory:
```bash
mkdir -p /tmp/slack-monitor-build
# copy scripts/main.py to /tmp/slack-monitor-build/main.py
# then replace only the three constants above
```

Validate syntax before packaging:
```bash
python3 -m py_compile /tmp/slack-monitor-build/main.py && echo "Syntax OK"
```

Then run a quick integrity check to confirm the template structure is still
present and only the configuration block was customised:
```bash
grep -n 'TRIGGER_PHRASE = "' /tmp/slack-monitor-build/main.py
grep -n 'CHANNEL_IDS: list\[str\] =' /tmp/slack-monitor-build/main.py
grep -n 'DEFAULT_OPENHANDS_URL = "' /tmp/slack-monitor-build/main.py
grep -n 'def get_secret' /tmp/slack-monitor-build/main.py
grep -n 'def _state_file_path' /tmp/slack-monitor-build/main.py
grep -n 'def create_conversation' /tmp/slack-monitor-build/main.py
```

If any of those checks fail, stop and re-copy the template instead of trying to
repair a hand-written variant.

### Step 4  -  Package and upload

Determine the Automation backend URL and auth from the `<RUNTIME_SERVICES>`
block in your system context:
- Use the **Automation backend** `url_from_agent` as `OPENHANDS_HOST`
- Auth: `X-Session-API-Key: $OPENHANDS_AUTOMATION_API_KEY`

If no Automation backend is listed in `<RUNTIME_SERVICES>`, stop and tell
the user to start the full automation stack.

```bash
tar -czf /tmp/slack-monitor.tar.gz -C /tmp/slack-monitor-build .

# OPENHANDS_HOST: read from <RUNTIME_SERVICES> Automation backend url_from_agent
OPENHANDS_HOST="<automation-url-from-runtime-services>"

TARBALL_PATH=$(curl -s -X POST \
  "${OPENHANDS_HOST}/api/automation/v1/uploads?name=slack-channel-monitor" \
  -H "X-Session-API-Key: $OPENHANDS_AUTOMATION_API_KEY" \
  -H "Content-Type: application/gzip" \
  --data-binary @/tmp/slack-monitor.tar.gz \
  | python3 -c "import json,sys; print(json.load(sys.stdin)['tarball_path'])")

echo "Uploaded: $TARBALL_PATH"
```

If the upload fails with a size error, the tarball must be under 1 MB.
`main.py` is under 15 KB so this should never trigger.

### Step 5  -  Create the automation

```bash
curl -s -X POST "${OPENHANDS_HOST}/api/automation/v1" \
  -H "X-Session-API-Key: $OPENHANDS_AUTOMATION_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{
    \"name\": \"Slack Channel Monitor\",
    \"trigger\": {\"type\": \"cron\", \"schedule\": \"* * * * *\"},
    \"tarball_path\": \"$TARBALL_PATH\",
    \"entrypoint\": \"python3 main.py\",
    \"timeout\": 55
  }" | python3 -m json.tool
```

A 55-second timeout keeps runs well within the 60-second cron window.

Record the returned `id`  -  share it with the user as confirmation.

### Step 6  -  Confirm

Tell the user:

> ✅ **Slack Channel Monitor** is running!
>
> - Automation ID: `{id}`
> - Channels: `{channel list}`
> - Trigger phrase: `{phrase}`
> - Polling every minute via cron `* * * * *`
> - State file: `~/.openhands/workspaces/automation-state/slack_poller_{id}.json`
>
> Send a message containing `{phrase}` in any monitored channel to test it.
> The bot will react with 👀 and reply with a link to the new conversation.

---

## Runtime Behaviour (per poll)

Each cron run executes `main.py`, which runs **10 polling iterations** (every
5 seconds) within the 55-second timeout window. Each iteration:

1. **Loads state** from the JSON file (see `references/state-schema.md`).
2. **Resolves the Slack token**  -  checks `SLACK_USER_TOKEN` then `SLACK_BOT_TOKEN`.
3. **Fetches new messages:**
   - User token