RetainWithAudit now takes only the actor; the store builds the detail after body clearing so bodies_cleared is a real number, and still writes the row before the cap. Co-Authored-By: Paperclip <noreply@paperclip.ing>
Email Agent
Triage the family inbox from one page: all mail lands in a single Gmail account and this service classifies it, recommends actions, performs bulk actions, drafts replies, and answers the Hub.
The build spec is AGENTS.md. ORIGINAL_NOTES.md is archived
pre-planning material and is not authoritative.
Status
Phase 7 — Summary and Hub; retention. The Go skeleton, session login,
and HTMX dashboard (Phase 1), real mail over IMAP with an app password,
forced to IPv4 (Phase 2), JEV classification (Phase 3), bulk triage
actions (Phase 4), reply drafts (Phase 5), and now unsubscribe
detection and the rules editor (Phase 6). Open a message to read it, draft a
reply with the LLM through OmniRoute from a template, edit it, and send it
over Gmail SMTP (IPv4 + STARTTLS). A reply is sent as the address the mail
arrived at (X-Pm-Original-To, FR-15) and returns to the original sender; the
reply sets In-Reply-To/References so Gmail keeps the thread, and the
original is filed under its Replied-to/<address> label. Sending is a
deliberate UI action with a confirmation — there is no auto-send (§10). The
rules editor (/rules) saves and versions the plain-text rules that JEV and
the reply model read. Unsubscribe detection (/unsubscribe) finds RFC
2369/8058 links and body links, keeps a domain ignore list, and records what Sam
marks — it never follows a link. Every action, including drafts, sends,
rules edits, and unsubscribe marks, is appended to actions_log (FR-13).
Phase 7 adds the daily summary (-summary, -summary-send; delivered
by email through Apprise) and the read-only Hub API (/capabilities,
/ask, /notify). Retention (AGENTS.md §7) is enforced by the bounded
-retain job: it clears message bodies older than one month, keeps metadata,
and caps the append-only actions_log; see
docs/retention.md. See
docs/phase7-summary-hub.md for Phase 7,
docs/phase6-unsubscribe.md for the phase evidence,
docs/phase5-replies.md for Phase 5, and
docs/phase4-triage.md for Phase 4.
Layout
cmd/email-agent/ service entry point (`-fetch`, `-classify`, `-classify-all`, `-retain`)
internal/classify/ JEV (TypeSafe System One) client, rule engine, orchestration
internal/config/ environment-driven configuration
internal/mailfetch/ stdlib-only IMAP client, MIME parsing, FR-2 source address
internal/mailops/ Gmail label moves and flag changes, and SMTP reply sending
internal/reply/ LLM reply drafts through OmniRoute, reply templates
internal/session/ server-side session store + signed cookie values
internal/store/ SQLite open + schema (internal/store/schema.sql), retention
internal/server/ HTTP routes, auth middleware, HTMX handlers
internal/unsubscribe/ RFC 2369/8058 + body unsubscribe-link detection (no network)
internal/version/ build metadata (set via -ldflags)
web/static/ embedded design tokens, Inter fonts, htmx, app.css
web/templates/ embedded server-rendered HTML
Dockerfile multi-stage, CGO-free build
docker-compose.yml this project's own container and image
Configuration
All configuration is read from environment variables. Secrets live in
~/.config/environment.d/10-secrets.conf on the host and are passed into the
container by docker-compose; no secret value is ever committed. See
.env.example for the full list of names.
Key variables:
| Variable | Default | Purpose |
|---|---|---|
EMAIL_AGENT_ENV |
development |
development, production, or test |
EMAIL_AGENT_ADDR |
:8790 |
Listen address |
EMAIL_AGENT_PORT |
8790 |
Listen port (used when EMAIL_AGENT_ADDR is unset) |
EMAIL_AGENT_DB_PATH |
data/email_agent.db |
SQLite file |
EMAIL_AGENT_LOG_LEVEL |
info |
debug, info, warn, error |
EMAIL_AGENT_SESSION_SECRET |
(empty) | Session cookie signing key. If unset, an ephemeral key is used (sessions reset on restart) |
EMAIL_AGENT_PASSWORD |
(empty) | Login password for Sam. If unset, EMAIL_AGENT_SESSION_SECRET doubles as the password |
GMAIL_USER |
(empty) | Gmail account that receives the forwarded mail |
GMAIL_APP_PASSWORD |
(empty) | Gmail app password for IMAP/SMTP (no OAuth) |
EMAIL_AGENT_SMTP_HOST |
smtp.gmail.com |
SMTP submission host |
EMAIL_AGENT_SMTP_PORT |
587 |
SMTP submission port (STARTTLS, IPv4) |
EMAIL_AGENT_IMAP_HOST |
imap.gmail.com |
IMAP host |
EMAIL_AGENT_IMAP_PORT |
993 |
IMAP port (implicit TLS) |
EMAIL_AGENT_IMAP_LOOKBACK_DAYS |
14 |
First-scan window |
EMAIL_AGENT_IMAP_MAX_MESSAGES |
100 |
Per-scan message cap |
JEV_BASE_URL |
https://api.typesafe.ai |
TypeSafe System One base URL |
JEV_API_KEY |
(empty) | JEV API key (required to classify) |
JEV_MODEL |
jev-latest |
System One model alias |
EMAIL_AGENT_CLASSIFY_CONCURRENCY |
4 |
In-flight JEV requests per run |
EMAIL_AGENT_CLASSIFY_MAX_MESSAGES |
200 |
Messages per classify run |
OMNIROUTE_BASE_URL |
http://192.168.20.13:20129/v1 |
OmniRoute gateway (all non-JEV models) |
OMNIROUTE_API_KEY |
(empty) | OmniRoute API key (required to draft replies) |
OMNIROUTE_MODEL |
auto/best-chat |
Model alias for reply drafts |
EMAIL_AGENT_RETENTION_DAYS |
30 |
Message-body retention window in days (§7) |
EMAIL_AGENT_ACTIONS_LOG_MAX_ROWS |
50000 |
Newest actions_log rows kept |
Mail sync (Phase 2)
internal/mailfetch speaks the minimum IMAP needed: LOGIN, SELECT INBOX,
UID SEARCH SINCE, and UID FETCH of the full RFC822 source plus Gmail's
X-GM-MSGID/X-GM-THRID. The dialer uses tcp4 so Gmail is only ever reached
over IPv4 — IPv6 to Gmail is broken from .13 and previously caused a socket EOF.
Trigger a scan either from the dashboard (Check mail) or from the CLI:
docker exec email-agent email-agent -fetch
Each scan is bounded by the lookback and max-message settings. Gmail's
X-GM-MSGID is the stable message key; the IMAP UID and UIDVALIDITY are
stored alongside it for later label operations.
Classification (Phase 3)
internal/classify sends each message to JEV (POST /v1/systemone) as three
Choice questions — category, importance, suggested action — with the live
category list as the category options, and stores the answer plus JEV's own
confidence. One request per message, bounded concurrency, retry with backoff on
429/529/5xx.
Trigger classification from the dashboard (Classify for new mail, Re-classify all after a category or rules change) or from the CLI:
docker exec email-agent email-agent -classify # pending messages
docker exec email-agent email-agent -classify-all # every stored message
Rules (FR-4)
Rules are plain text, stored versioned in rules. One rule per line:
<condition> => <effects>
from contains "amazon.com" => category=Newsletter, action=unsubscribe
* => category=Info
Conditions join with and over from, to, subject, source, body
using contains, equals, starts_with, ends_with. The first matching rule
wins and overrides only the fields it names. Edit and version the rules at
/rules (Phase 6); the classifier and the reply model both read the newest
version.
Categories (FR-14)
GET /categories edits the category list. A category's name is the key stored
in classifications.category and the Choice option sent to JEV, so the model
always sees the current list. Renaming cascades to existing classifications;
removing a category reassigns its messages to the first remaining category.
Triage actions (Phase 4)
internal/mailops turns an app folder into a Gmail label and performs the move
over IMAP, forcing IPv4 exactly like the read path:
| App folder | Gmail label |
|---|---|
inbox |
INBOX |
delete |
Delete (recoverable; never a hard delete) |
saved |
Saved |
replied |
Replied-to/<address the mail arrived at> |
A move uses the IMAP MOVE extension (with a COPY + \Deleted + EXPUNGE
fallback). Because Gmail gives each label its own UID, a message is located by
its stable X-GM-MSGID, not by a stored UID. A message in the Delete, Saved,
or Replied-to folder has a Restore button that moves it back to INBOX.
Every action appends to actions_log: one move or mark row per message,
plus one bulk_<action> summary row.
Reply drafts (Phase 5)
Opening a message in the inbox loads the detail pane: the body, the recommended
action, the reply identity, a template picker, and the draft. The draft is
generated by an LLM through OmniRoute (the only non-JEV model path, §10)
using a built-in template (quick-ack, answer, confirm, decline) plus any
note Sam types. Sam edits the draft, then sends it.
The send path uses Gmail SMTP (smtp.gmail.com:587, STARTTLS) and, like the
IMAP read path, forces IPv4 (AGENTS.md §9).
- Reply identity (FR-15): the
Fromheader isSam Rolfe <address the mail arrived at>; when the arrived-at address is unknown it falls back toSam Rolfe <GMAIL_USER>. The SMTP envelope sender is always the authenticated Gmail account. - Threading: the reply sets
In-Reply-ToandReferencesfrom the originalMessage-ID(stored by Phase 5), so Gmail keeps the thread. After a send the service checks the[Gmail]/Sent Mailmailbox for the thread and reports whether it updated. - No auto-send (§10): sending needs a CSRF token, an explicit UI
confirmation, and the guard field
confirm=yes. The handler refuses a request without them and never runs from a schedule. A draft is sent once; a second attempt is refused. - Filing: after a successful send the original moves to its
Replied-to/<address>label (FR-9).
Verify the SMTP path without sending mail:
# inside the container
email-agent -check-smtp # IPv4 + STARTTLS + app-password login, no message sent
A real send is a UI action by Sam; it is never triggered by an agent test without explicit approval (§10, AGENTS.md §13).
Retention (AGENTS.md §7)
AGENTS.md §7 says: keep message bodies for one month. Logs are append-only and
size-capped. The bounded -retain job enforces both rules:
- Message bodies. Every message whose
received_atis older thanEMAIL_AGENT_RETENTION_DAYS(default 30) hasbody_textset toNULL. All metadata (sender, subject, source address, classification, folder, labels) stays. A second run is a no-op. - Action log. Only the newest
EMAIL_AGENT_ACTIONS_LOG_MAX_ROWS(default 50000) rows of the append-onlyactions_logare kept; older rows are deleted.
The job runs in one SQLite transaction, writes one retain row to
actions_log for the audit trail, and never touches a message inside the
window. It is the CLI -retain flag, so it can be scheduled exactly like
-fetch and -classify and is never run by an HTTP request:
# inside the container
docker exec email-agent email-agent -retain
The decision is recorded in docs/retention.md.
Run locally
go run ./cmd/email-agent
curl -s localhost:8790/health
Docker
docker compose up -d --build
curl -s localhost:8790/health
The container is email-agent, image email-agent:latest, named volume
email_agent_data mounted at /data, listening on 8790. It runs as an
unprivileged user and has a built-in healthcheck (email-agent -healthcheck).
Caddy on .35 proxies mail.lab.audasmedia.com.au to this port.
Endpoints
| Method | Path | Auth | Purpose |
|---|---|---|---|
GET |
/health |
public | Liveness + database check, JSON |
GET |
/readyz |
public | Readiness, JSON |
GET |
/login |
public | Sign-in form (deep-indigo band) |
POST |
/login |
public | CSRF-checked password sign-in, sets the session cookie |
POST |
/logout |
session | Destroys the session, returns to /login |
GET |
/ |
session | Dashboard: nav counts, real message list |
GET |
/partials/inbox |
session | HTMX fragment for the centre list |
POST |
/actions/fetch |
session + CSRF | Runs one IMAP scan, returns the refreshed list |
POST |
/actions/classify |
session + CSRF | Classifies pending messages, returns the refreshed list |
POST |
/actions/reclassify |
session + CSRF | Re-classifies every message with the current categories and rules |
POST |
/actions/bulk |
session + CSRF | Bulk delete/move/mark and restore over selected message ids (FR-6/FR-9) |
GET |
/partials/message |
session | HTMX fragment for the message detail, reply draft, and history |
POST |
/actions/draft |
session + CSRF | Generates and stores a reply draft with the LLM (FR-8) |
POST |
/actions/draft/save |
session + CSRF | Saves Sam's edits to a draft |
POST |
/actions/send |
session + CSRF + confirm | Sends a reply over SMTP (FR-8/FR-15); never automatic |
GET |
/categories |
session | Category editor (FR-14) |
POST |
/categories/add |
session + CSRF | Adds a category |
POST |
/categories/rename |
session + CSRF | Renames a category and updates existing classifications |
POST |
/categories/remove |
session + CSRF | Removes a category and reassigns its messages |
GET |
/rules |
session | Rules editor: current text, versions, parse errors (FR-11) |
POST |
/rules/save |
session + CSRF | Saves the rules text as a new version |
POST |
/rules/restore |
session + CSRF | Restores an older version as a new version |
POST |
/rules/reclassify |
session + CSRF | Re-classifies every message with the current rules |
GET |
/unsubscribe |
session | Detected unsubscribe links, ignore list, and records (FR-7) |
POST |
/unsubscribe/ignore |
session + CSRF | Adds a domain to the ignore list |
POST |
/unsubscribe/unignore |
session + CSRF | Removes a domain record |
POST |
/unsubscribe/mark |
session + CSRF + confirm | Records a domain for unsubscribe; never contacts the link |
GET |
/static/… |
public | Embedded tokens.css, app.css, Inter fonts, htmx.min.js |
Unauthenticated requests to / and /partials/… redirect to /login?next=….
Form posts use a double-submit CSRF token (email_agent_csrf cookie plus a
hidden csrf field).
Database
SQLite is opened with the pure-Go modernc.org/sqlite driver (no CGO). The
schema in internal/store/schema.sql creates the AGENTS.md §7 tables:
messages, classifications, rules, actions_log, unsubscribe, drafts,
summaries, plus categories, schema_migrations. Schema init is idempotent
and runs on every start. Migration v2 adds imap_uid and imap_uidvalidity to
messages; migration v3 seeds the first category list and a starter rules
version once, so a category removed by the user is not silently re-added;
migration v4 adds folder and mailbox to messages for the Phase 4 triage
folders; migration v5 adds messages.message_id_header (reply threading) and
drafts.sent_at; migration v6 adds messages.list_unsubscribe and
messages.list_unsubscribe_post and extends unsubscribe with url and
updated_at.