feat: add dreaming skill and Agent Canvas automation catalog entry

[carenthomas]

• A human has tested these changes.

---

Why

Coding sessions are full of durable knowledge - corrections the user gives, conventions discovered the hard way, environment quirks - that evaporates when the conversation ends. Dreaming captures it automatically: Letta reflects over a chosen local Agent Canvas conversation on a schedule and proposes what it learns as AGENTS.md pull requests, so every future session starts smarter.

Summary

• New skills/dreaming/ skill (/dreaming:setup): the user names a conversation, the setup flow resolves it to a conversation id from local conversation metadata, and a cron automation is registered as Dreaming: "<conversation>" -> <owner>/<repo>. Each run reflects over whatever is new in that conversation; already-reflected messages are deduplicated, so quiet runs are cheap no-ops. To dream over several conversations, set up one automation per conversation (same-repo automations share a lock and never overlap).
• The automation tarball is two small scripts; all logic lives in the published @letta-ai/openhands-dreaming npm CLI (pinned), keeping the extension thin and independently updatable.
• New Agent Canvas catalog entry (automations/catalog/dreaming.json), registered in automations/index.js and the marketplace, plus a one-line popularityRank nudge to research-brief-writer (84 -> 83) to free rank 84 - intentional, not accidental churn (ranks are integers and the card grid sorts descending).

Issue Number

n/a - Letta / OpenHands proof of concept (discussed with the OpenHands team beforehand).

How to Test

1. Repo checks: npm run build, uv run python scripts/sync_extensions.py --check, uv run pytest -q tests/ (443 pass locally).
2. Live: in Agent Canvas, add GITHUB_TOKEN (repo write) and a model provider key (e.g. OPENAI_API_KEY) as named secrets, then run /dreaming:setup and name any local conversation. It registers the automation and dispatches a first run that opens or updates an AGENTS.md PR against the chosen repo (or a clean no-op when the conversation has nothing new).
3. Reference output from full local end-to-end runs of this flow: letta-ai/openhands-dreaming#2 and letta-ai/openhands-dreaming#3.

Video/Screenshots

[neubig]

Thanks for sharing this!

On high-level suggestion -- instead of having the dreaming agent focus on a single conversation, it'd be great if it could focus on all of the conversations that were done since the last time the automation ran, which would make it possible for the agent to update memory, e.g. every week with all of the new information that was obtained over the past week. Would something like that be possible?