feat(triage): add auto mode for unattended monitoring

Add an auto mode to the triage-intake engine: a self-running variant for when Craig is away but wants tight awareness. It runs the standard sweep on a short interval (default 20 min) as an in-session loop, accumulates findings instead of mutating state, and gates the mutations behind "close the triage" (flush the batch, keep looping) and "stop the triage" (flush, then stop).

A sweep advances nothing — no sentinel write, no todos, no mail actions, no commit. The scan window grows from the last close to the next, so nothing between sweeps is dropped, and the sentinel still means "everything before this timestamp has been scanned" — it just advances once per close. Each sweep reports deltas plus a running "responses awaiting your acknowledgment" list, the primitive an away user needs that a delta-only sweep loses.

The unacked list is durable in .ai/triage-intake-unacked.org so it survives a crash, a clear, or a restart — the away-from-desk case the mode exists for. Delivery is an in-session loop so MCP auth is inherited; a detached cron schedule stays out of scope and belongs to the morning-ops orchestrator, which can reuse this accumulate behavior as its triage limb.

Source proposal from the work project, design decisions ratified 2026-06-15.

1 files changed, 43 insertions, 0 deletions

diff --git a/docs/design/2026-06-15-auto-triage-intake-spec.org b/docs/design/2026-06-15-auto-triage-intake-spec.org
new file mode 100644
index 0000000..1c7cd94
--- /dev/null
+++ b/docs/design/2026-06-15-auto-triage-intake-spec.org
@@ -0,0 +1,43 @@
+#+TITLE: Proposed engine addition — Auto mode (auto triage-intake)
+#+DATE: 2026-06-15
+
+* What this adds
+
+A new *mode* of the triage-intake engine: *auto mode* (auto triage-intake). It's a self-running monitor for when Craig is away from the desk but wants tight awareness — a loop that runs the standard triage on a short interval, accumulates rather than mutating, and hands Craig a controlled checkpoint to commit the batch.
+
+Origin: 2026-06-15, the morning Craig had to clear his day for a family emergency and wanted the desk watched while he was in and out. He asked for 20-minute sweeps that summarize what's come in for him, with an explicit command to process and commit the batch.
+
+* The mode
+
+** Cadence
+A loop (CronCreate / =/loop=) fires the triage on an interval — default *20 minutes*. Craig sets the interval.
+
+** Accumulate, don't mutate (the core difference from a normal run)
+A normal triage run writes the sentinel, creates =:quick:reactive:= todos, takes mail actions on confirmation, and is a one-shot. An auto-mode *sweep* does none of the mutations:
+
+- Does NOT advance the sentinel — the scan window grows from the last *close* until the next close, so nothing is dropped between sweeps.
+- Does NOT create todo.org tasks — accumulates them (in the session log) for the close.
+- Does NOT take mail actions (trash / mark-read / star).
+- Does NOT commit.
+- DOES run the full plugin scan, DOES update an active daily-prep (Update mode) and re-open it on change, DOES report.
+
+** End-of-sweep output
+Each sweep ends with two short sections:
+1. *Deltas* — what changed since the last sweep (one line if nothing).
+2. *Responses awaiting your acknowledgment* — every Slack reply, email, or message directed at the user that he hasn't explicitly acknowledged or had the agent answer. This is a *running list carried forward* across sweeps until the user acks each item or closes the triage. It exists because an away user's main need is "who's waiting to hear back from me," which a delta-only sweep loses the moment it scrolls past.
+
+** Close / stop commands (the checkpoint)
+The mutations are gated behind two user commands:
+
+- *"close the triage"* — finish the mail + sentinel processing, add all accumulated todos (asking the user questions along the way), commit and push, then *keep looping* (next sweep on the normal interval). This is the "flush the batch and carry on" checkpoint.
+- *"stop the triage"* — the same close processing, then *stop the loop* and revert to manual triage (run only when asked).
+
+* Why it's worth adding to the engine
+
+The standard engine is one-shot and mutating, which is right for an at-the-desk "what's new?" glance. It's wrong for unattended monitoring: running it every 20 minutes would spray reactive todos, advance the sentinel past unprocessed items, and commit noise without review. Auto mode separates the cheap, frequent *watching* from the deliberate, gated *committing* — and adds the away-user's missing primitive, the running unacknowledged-responses list.
+
+* Companion notes
+
+- The interval loop is the delivery mechanism (CronCreate session-only, or a durable schedule); the mode is the behavior. They compose.
+- "Responses awaiting acknowledgment" tracking needs a small piece of state. In a session it can live in the session-context log; if the engine wants it durable across sessions, a tiny =.ai/triage-unacked.org= (or similar) is the natural home — flagged as a design choice for the rulesets side to decide.
+- Deltas-only reporting (the 2026-06-11 ruling) and loud scan-failure surfacing both still apply inside each sweep.