The queue worker now also enqueues one run per actionable assigned task of a
heartbeat-enabled agent with an enabled provider and no run yet, so after the
CEO hires and delegates, its reports start their tasks on their own. Each task
is enqueued at most once. The team-building prompt is now scoped to managers
(no manager) with an empty team, so reports execute their task instead.
The new app reached a real LLM but never ran an agent: the kickoff task_run
sat queued forever and runTask was a single text completion with no tools.
This adds the missing runtime:
- provider-tool-turn: OpenAI Responses + Anthropic Messages tool-use turns
- agent-tools + deliverable-writer: hire_agent, create_task,
update_task_status, write_deliverable (workspace-scoped, traversal-safe)
- agent-run-loop: real tool-use loop, capped iterations
- task-queue-worker: claims queued runs in a transaction and executes them
task-execution now drives the loop; a background worker auto-runs the
bootstrap CEO run so it hires its team, delegates tasks, and writes the first
deliverable into the bound workspace. Autonomy is gated by AGENTCOMPANY_NEW_AUTORUN
(tests run with it off to stay hermetic).
Implement the official OAuth login flows natively (ported from pi-ai's
reference): GitHub Copilot device-code, GPT account (ChatGPT Codex) and
Google Antigravity authorization-code + PKCE via a loopback callback server.
Obtained credentials are stored as JSON through the existing secret vault.
Onboarding and Settings now run the real sign-in instead of pasting an
access token.
Onboarding only accepted a typed workspace path, which is error-prone and
diverged from the original wizard. Add a pickDirectory IPC backed by Electron's
open-directory dialog and a Choose button beside the path field, so the founder
can select a real folder for agent artifacts.
The provider step was filtered to API_KEY only, which hid GitHub
Copilot, Google Antigravity, and GPT account from the founding-CEO
runtime picker even though they are first-class providers in the
catalog. Show every non-cloud provider, render an "Access token" field
in place of the API-key field for OAuth and account auths, and surface
a button that opens the provider's official sign-in page via the new
openExternalUrl IPC (validated to http(s) only).
OnboardingService.resolveProvider now accepts any non-cloud auth type.
Cloud providers still route through Settings since their multi-field
config does not fit the linear onboarding step.
OAuth, account, and cloud providers previously fell into the same
password input as API key providers, which made them impossible to
connect properly. Split the connect dialog by auth type:
- api_key: secret + model (unchanged)
- oauth_pkce / account_subscription: button that opens the provider's
official sign-in URL in a session-partitioned BrowserWindow, then a
paste field for the access token returned by the provider
- cloud: multi-field form (base URL, region, project, deployment,
credential) serialized into the encrypted secret payload
Each catalog entry now carries signInUrl and credentialHelp so the
dialog can render the right instructions without baking copy into the
renderer.
Backed by a new launchProviderSignIn IPC method on ProviderService that
opens a hardened popup (nodeIntegration off, contextIsolation on,
sandbox on, permission denies) and records an audit event.
The sidebar org button was inert: clicking it did nothing. Add a real
dropdown menu listing every organization, a "New organization" entry
that re-enters onboarding without resetting the database, and a per-org
delete affordance with inline confirmation. Active org is now persisted
in a single-row app_state table so the snapshot keeps a stable
selection across restarts and the renderer drives switching via two new
IPC channels (setActiveOrganization, deleteOrganization).
- migration 006 adds app_state(id=1, active_org_id, updated_at)
- snapshot resolves active org from app_state with the first-org fallback
- OrganizationService gains setActive + delete + bootstrap upsert
- new OrgSwitcher renderer component keeps Shell.tsx lean
Adds chat_read_state migration (employee_id + space_id, last read
message + timestamp) wired through ChatService.markSpaceRead, IPC
markChatSpaceRead, and an effect in ChatPage that flushes the active
space whenever the latest message id changes.
Shell.computeBadges now derives the Messages badge from
(message.createdAt > read_state.last_read_at) minus messages the viewer
sent, so the sidebar shows true unread instead of total throughput.
- Port design tokens, sidebar, topbar, and icons to inline SVG set
- Rewrite each page (Home/Team/Work/Chat/Files/Approvals/Social/Settings)
to drive real snapshot data and match the bento, kanban, three-pane chat,
file tree + pinned cards, approval queue, social schedule + calendar,
and settings sub-nav layouts
- Split Chat and Settings into per-concern subcomponents so every file
stays under 500 lines
- Add schema v4 for pinned files and scheduled posts plus IPC + service
wiring; cover new behavior in unit tests
- Update onboarding labels and Hire form to remove ambiguity for the
expanded e2e suite (all settings tabs + 8 routes at 1280 and 980)
ZacharyZhang-NY
