Phase 5 follow-up: discover the \Sent mailbox; record the approved real send (AUD-71)

The approved real test reply was sent and the thread updated (same
X-GM-THRID as the original). The live test exposed one bug: the thread
check hardcoded Gmail's sent mailbox as "[Gmail]/Sent Mail", but this
account exposes it as "[Google Mail]/Sent Mail".

- internal/mailfetch: LIST parser, ListMailboxes, and SentMailbox that
  finds the mailbox flagged \Sent (RFC 6154) with name fallbacks.
- internal/mailops: VerifyThreadUpdated selects the discovered \Sent
  mailbox instead of a hardcoded name.
- cmd/email-agent: -check-thread <id> exercises the check against real
  Gmail without sending mail.
- Tests for LIST parsing, sent-mailbox discovery, and the discovery
  error path.
- docs/phase5-replies.md: record send-as verification, the sent reply's
  thread id, the app confirmation (sent_reply_in_thread=true), and the
  fix.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
This commit is contained in:
Paperclip Builder
2026-10-11 22:18:05 +11:00
parent 7ca888f0c6
commit 7c66e4ad31
7 changed files with 341 additions and 34 deletions

View File

@@ -1,15 +1,13 @@
# Phase 5 — Reply drafts (templates, LLM draft, edit, send)
Status: **built, tested, and deployed. The one real test send is awaiting Sam's
explicit approval** (issue interaction `080c500d-5968-49ad-9c40-0b2d3f445cc0` on
[AUD-71](/AUD/issues/AUD-71)). Parent [AUD-68](/AUD/issues/AUD-68). Phase 5 of
Status: **complete.** Built, tested, deployed, and the approved real test reply
was sent and confirmed to have updated the thread. Sam approved the test send via
issue interaction `080c500d-5968-49ad-9c40-0b2d3f445cc0` on
[AUD-71](/AUD/issues/AUD-71). Parent [AUD-68](/AUD/issues/AUD-68). Phase 5 of
AGENTS.md §11.
**DoD:** a reply is drafted, edited, and sent, and the thread updates.
Every part of the DoD except the real send is verified below. The real send needs
Sam's approval per the phase rules and AGENTS.md §10; it is the only step that
cannot be tested without sending mail.
**DoD:** a reply is drafted, edited, and sent, and the thread updates. — met
(§2.6).
## 1. What was built
@@ -84,19 +82,23 @@ and the send path is verified up to (but not including) DATA.
### 2.3 Gmail "Send mail as" verification (AGENTS.md §13 "Remaining")
AGENTS.md records send-as as "reported as already set up in Gmail … not verifiable
from the sent folder". Gmail exposes no read-only alias list over IMAP/SMTP, so
the only reliable check is a real send: Gmail accepts the `From` header only when
the address is a registered send-as alias, and rejects it otherwise during DATA.
AGENTS.md recorded send-as as "reported as already set up in Gmail … not
verifiable from the sent folder". Gmail exposes no read-only alias list over
IMAP/SMTP, so the check is a real send: Gmail accepts the `From` header only when
the address is a registered send-as alias, and rejects it during DATA otherwise.
The SMTP connection, STARTTLS upgrade, and app-password authentication are
verified (`-check-smtp`). The `From`-header/send-as check is **pending the
approved test send**.
**Result: verified.** The approved test reply was sent as
`"Sam Rolfe" <hello@where-woof.com>` (the `X-Pm-Original-To` address) from the
`samuelrolfe@gmail.com` account. Gmail accepted it and stored it in the Sent
mailbox (`[Google Mail]/Sent Mail`) with that exact `From` header, so
`hello@where-woof.com` is a working send-as alias. The SMTP connection, STARTTLS
upgrade, and app-password authentication were already verified separately with
`-check-smtp`.
### 2.4 Draft generated, edited, and stored (screenshot of the live data)
### 2.4 Draft generated, edited, and sent
Draft `2` for message `99` ("Test email", arrived at `hello@where-woof.com`),
generated through the live UI path and then edited:
generated through the live UI path, edited, and then sent after Sam's approval:
```
Thanks, got it. This came through to hello@where-woof.com. Since it's a test, no action needed on my side. If you need anything specific, let me know.
@@ -104,13 +106,44 @@ Thanks, got it. This came through to hello@where-woof.com. Since it's a test, no
Sam
```
### 2.5 Thread update after a sent reply
After the send the draft status is `sent`, the message left the inbox and now
lives under the `Replied-to/hello@where-woof.com` label (1 row in the Replied-to
view), and the message history shows `draft`, `reply_sent`, and the `move` rows
(FR-13).
Pending the approved test send. The plan is to reply to message `99` as
`"Sam Rolfe" <hello@where-woof.com>` to `samuelrolfe@gmail.com` (Sam himself — no
third party), then confirm the thread by finding the original Gmail thread id in
`[Gmail]/Sent Mail` (`X-GM-THRID` search). The exact message and draft are on the
pending approval card.
### 2.5 Thread update after the sent reply
**Result: verified — the reply joined the original thread.** Read directly from
Gmail over IMAP (read-only):
| Message | From | To | `X-GM-THRID` | `In-Reply-To` / `References` |
|---|---|---|---|---|
| Original (`99`) | `sam rolfe <samuelrolfe@gmail.com>` | `hello@where-woof.com` | `1878738835102629816` | — |
| Sent reply | `"Sam Rolfe" <hello@where-woof.com>` | `samuelrolfe@gmail.com` | `1878738835102629816` | `<CAMAgT7S04G5E=…@mail.gmail.com>` |
The reply carries the original `Message-ID` in `In-Reply-To` and `References` and
Gmail assigned it the **same thread id**, so the thread updated. The app's own
check now agrees:
```
$ docker exec email-agent email-agent -check-thread 99
message=99 thread=1878738835102629816 sent_reply_in_thread=true
```
Status code `sent_reply_in_thread=true`. No third party received the test: the
only recipient was `samuelrolfe@gmail.com`.
### 2.6 Bug found by the live test and fixed
The first send reported "Could not yet confirm the thread update". The cause was
not threading: `VerifyThreadUpdated` hardcoded Gmail's mailbox as
`[Gmail]/Sent Mail`, but this account exposes the special-use mailboxes as
`[Google Mail]/…`. The fix discovers the mailbox flagged `\Sent` (RFC 6154) with
`LIST`, falling back to the common names. New coverage:
`internal/mailfetch` (`parseList`, `ListMailboxes`, `SentMailbox`) and
`internal/mailops` (discovered sent mailbox, discovery error). `-check-thread
<id>` was added so the check can be exercised against real Gmail without sending
mail. After the fix, `-check-thread 99` returns true (above).
## 3. Configuration
@@ -129,9 +162,13 @@ docker compose up -d # migration v5 runs on start; data volume kept
docker exec email-agent email-agent -check-smtp # safe: no mail sent
```
Two commits were needed: the Phase 5 implementation and the `\Sent` mailbox
discovery fix from §2.6.
## 5. Rollback
1. `git revert <phase-5 commit>` and `docker compose up -d --build`.
1. `git revert <sent-mailbox-fix commit> <phase-5 commit>` and
`docker compose up -d --build`.
2. Migration v5 is additive (`messages.message_id_header`, `drafts.sent_at`); the
Phase 4 binary ignores the new columns.
3. A sent reply cannot be unsent. Gmail's Sent copy and the thread stay; the
@@ -139,8 +176,6 @@ docker exec email-agent email-agent -check-smtp # safe: no mail sent
## 6. Not done / deferred
- **One real send + thread confirmation** — awaiting Sam's approval (the pending
interaction above). This is the last DoD item.
- A **template editor** (user-defined templates) is not in the Phase 5
requirements; templates are built in. The Phase 6 rules editor still feeds the
classifier.