When a human or board member posts in a thread where agents have
previously participated, those agents are now woken even without
explicit @mentions. This matches the old version's behavior where
any message in a conversation could wake the recipient, enabling
natural back-and-forth between humans and agents.
The catch block in wakeAgentMentions now records wake_state on each
mention (woken/failed) instead of silently discarding the error. Failed
mentions render with a strikethrough and muted color so the user sees
which agents could not be reached, with a tooltip on hover. Migration
044 adds the wake_state column to chat_mentions.
ChatService was 542 lines, mixing message delivery with the dispatch of
nine slash commands. Move the command cluster — /board, /approve, /deny,
/agent, /skill, /file, /runbook, /handoff, /escalate — into a
ChatSlashRouter that owns the approval and board-intervention services it
needs. ChatService keeps message delivery and delegates two calls.
Behaviour identical: chat-service 376 lines, router 196, full suite and
e2e green; the slash-routing governance test exercises every branch.
An @mention by an agent wakes the mentioned teammate by creating a task
run, and the woken agent's reply can mention back, an unbounded A->B->A
loop whose only backstop was the per-provider monthly request cap (which,
once tripped, fails every agent on that provider). Before enriching agent
conversation this had to be made safe.
Cap the agent-authored messages a thread may accumulate since its last
human/board message; past the cap, agent-triggered wakes pause until a
person re-engages. A human message always wakes mentions and resets the
budget. Counted from chat_messages, so no schema change.
Agents were deaf to @mentions — only /agent slash commands triggered a
task_run. Now ChatService.sendMessage auto-wakes every mentioned agent
(skipping self-mentions and /agent which already handles it) by creating
a queued task_run through ChatAgentWakeService.wakeFromMention.
chat-service.ts exceeded 500 lines. Move the row-shape interfaces, slash-command
parsing/validation and the small standalone helpers into chat-service-internal.ts
and import them back. Pure relocation with no behaviour change; the chat
governance suite (82 tests) and e2e remain green.
The PRD calls for company, division, department, project, pod and ad-hoc
spaces, but only company, department, project and direct were accepted. Add
division, pod and ad_hoc to the command contract, the service whitelist and the
new-space dialog. The space_type column is free text, so no migration is
needed.
Any employee in the org could send a message as the board (freeze, takeover,
force-approval), because requireSender only checked that the board sender was a
valid employee. Enforce the approval_decider role (org_admin inherits it) via
IdentityAccessService, which also records an access decision for denied
attempts, and only render the thread board-control form for principals who hold
that authority — others get a read-only view of past interventions.
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.