Release Roomote 0.45.0

[roomote-roomote]

​Opened on behalf of @mrubens. Follow up by mentioning @roomote-roomote, in the web UI, or in Slack.

Release

• Previous version: 0.44.0
• Next version: 0.45.0
• Bump: minor

Changelog

Minor changes

• Expand GLM 5.3 and GLM 5.3 Flash availability and recommendations across OpenRouter, Vercel AI Gateway, Requesty, OpenCode Go, Z.AI, and Z.AI Coding Plan.
• Offer secure, spend-capped Roomote trial inference during hosted setup, record its real model costs in task and cost analytics, and present the option with clearer onboarding copy.
• Let self-hosted deployments run Brain embeddings and reranking through their own OpenAI-compatible upstream, including an opt-in bundled CPU service with multilingual model defaults.

Patch changes

• Include the Brain's memory volume and database state in supported self-hosted backup and restore bundles so memories survive host recovery consistently.
• Treat temporary Brain network outages as queue backpressure so infrastructure restarts do not exhaust individual memory write retries or require manual repair.
• Render Fast replies as rich Markdown in Discord guild channels instead of falling back to plain unformatted messages.
• Make suggested tasks in Fast automation reports launch reliably across Slack, Discord, Microsoft Teams, and Telegram while keeping each suggestion card's state in sync.
• Preserve the full Fast conversation context across resumed turns so follow-up answers continue from the existing thread instead of losing earlier messages.
• Keep Fast session sidebars and information panels usable on mobile by switching them to the same single-panel layout as task workspaces.
• Discover Notion pages and database rows that inherit integration access through shared parents, even when Notion search does not return them.
• Keep automatic pull-request re-reviews running after their previous sandbox shuts down and anchor each sync review on the head commit that was actually reviewed.
• Keep Standard tasks and Fast web sessions running through retryable inference-provider failures instead of ending the work prematurely.
• Briefly name the recalled insight that materially influenced an agent's approach without exposing internal memory provenance or identifiers.
• Keep Fast and standard agents identified as Roomote by removing OpenCode's conflicting injected identity prefix from their system prompts.
• Render automation report Markdown correctly in Slack while preserving the report's replyable thread footer.
• Use task-specific wording in Slack inline status updates so progress messages describe the work instead of exposing generic agent terminology.
• Make transcript tool activity easier to inspect by showing sanitized inputs and readable YAML details without hiding the corresponding tool results.

Documentation coverage

• Hosted trial inference: apps/docs/models.mdx documents hosting-provisioned availability, spend caps, Cost Analytics visibility, credit limits, and removal behavior; apps/docs/self-hosting.mdx distinguishes managed inference from self-hosted credentials.
• Self-run Brain embeddings and reranking: apps/docs/memory.mdx documents the Compose profile, upstreams, exact bare self-run model IDs, model/dimension pairing, multilingual defaults, and create-time constraints; apps/docs/environment-variables.mdx and .env.production.example keep provider and bundled Infinity naming accurate.
• Brain backup and restore: apps/docs/memory.mdx and apps/docs/self-hosting.mdx document the required two-store backup consistency and supported bundle contents.
• GLM 5.3 provider expansion: existing provider guides remain accurate because model catalogs are dynamic; affected provider pages retain source-backed provider marks.
• Remaining included changes are fixes or minor UX behavior and require no additional discoverability or configuration guidance.

Validation

• node --test scripts/release/__tests__/*.test.mjs
• mise exec -- pnpm --filter @roomote/docs check
• pnpm lint
• pnpm check-types
• pre-push oxlint, residual lint, fast type checks, and knip
• git diff --check
• node scripts/release/extract-changelog-section.mjs 0.45.0

Squash-merging this PR cuts Roomote 0.45.0 and automatically opens the frozen Promote v0.45.0 to production PR against main.

[roomote-community]

No new code issues found. See task

• apps/docs/memory.mdx:108: The local reranker example sends an openrouter:-prefixed model id to Infinity, which forwards unchanged and fails model lookup.

_{Reviewed a867759}

[roomote-roomote]

Fixed the local Infinity reranker guidance in a867759d. Self-run model IDs are now documented as bare upstream IDs in the Memory guide, environment-variable reference, and production environment example. Docs validation, broken-link checks, and pre-push checks passed; the review thread is resolved.