homelab-codex-ws/kb/services/job-mail-body-ingest.md

---
okf: "0.1"
type: service
visibility: private
status: active
updated: 2026-08-06
links:
  - ../runbooks/mail-body-ingest-run.md
  - job-mail-imap-sync.md
---

# mail-body-ingest

Module 5, faza mailowa (`kb/phases/kb-m5-faza-mailowa.md`, §5, Krok 2). Second full
pass over the gmail `.eml` archive — `gmail-bulk-import` deliberately skipped inline
`text/plain`/`text/html` parts (`_parse_attachments` does `continue` on them); this job reads
exactly the content that gap left out, chunks it, embeds it, and inserts it into
`document_chunk` alongside the existing paperless chunks.

## Why a separate job, not an extension of documents-ingest's chunk_embed

`chunk_embed.py` is wired to `source='paperless'` + `entities[type=content]` (pre-extracted
text already in the DB). Mail content isn't in the DB yet — it has to be read from `.eml`
files, MIME-walked, quote-stripped, and classified, none of which paperless chunks need. The
only thing genuinely shared is the chunker itself, which is why it was extracted to
`kb_mail.chunking` first (Krok 0) instead of being copy-pasted here.

## Where it runs

**On SOLARIA** for backfill runs (needs Ollama on `localhost` for `/api/embed`), against
`kb-postgres@PIHA` over Tailscale. The `.eml` archive is rsync'd PIHA -> SOLARIA once (plan §7,
Krok 4) rather than read live over the network — 225k small files over Tailscale would be slow
and fragile.

**Also on PIHA since 2026-08-06**, as the mail stage of `kb-ingest` (see "Two modes" below).
There it reads the canonical archive locally and calls Ollama@SOLARIA over Tailscale — which
is fine at this scale: the daily increment is ~60 chunks at 8-18 ms each, measured at 8.2 ms
round-trip from PIHA. The argument against embedding from PIHA (recon §3.1) was about 271k
backfill chunks and does not carry over.

Install (from repo root, on SOLARIA):

```bash
pip install -e packages/kb-mail/
pip install -e packages/kb-retrieval/
pip install -e jobs/mail-body-ingest/
```

## Pipeline (per envelope)

1. **Read** `archive_root / raw_ref` — `missing_file`/`read_error` counted like
   `gmail-header-backfill`.
2. **Parse**: typed (`policy.default`) with a `compat32` fallback (same ~9/225030 failure mode
   `gmail-header-backfill` documents).
3. **Body extraction**: inline `text/plain` preferred; HTML->text via a small stdlib
   `HTMLParser` when the mail is HTML-only (plan §1.3: 15% of the corpus) — zero new
   dependencies, skips `style`/`script`/`head` content.
4. **Quote-strip** (Decyzja 2): truncate at the earliest reply marker (`On ... wrote:`,
   `Dnia ... napisał(a):`, `W dniu ... pisze:`, `-----Original Message-----`, Outlook's
   underscore separator), then drop remaining `>`-quoted lines. In HTML, `blockquote` and
   `div.gmail_quote` subtrees are skipped before conversion to text. `quoted_chars_stripped`
   is tallied for calibration review (plan §7).
5. **Classification**: `newsletter` (`List-Unsubscribe`/`List-Id`/`Precedence: bulk|list`,
   read from the same parsed message); `body_empty` (after quote-strip — an empty mail is
   still counted, just produces zero chunks).
6. **Prefix** (Decyzya 3): `Temat: ... | Od: ... | Data: YYYY-MM-DD` built from the
   already-backfilled `entities[type=headers]` + `envelope.ts` — zero header re-parse.
7. **Chunk**: `kb_mail.chunking.chunk_text` (2400/600 chars, same as paperless).
8. **Embed + insert**: newsletter chunks are inserted immediately with
   `excluded_reason='newsletter'`, `embedding=NULL` (no Ollama call, reversible later);
   everything else is buffered up to `--batch-size` (default 64) and sent through
   `kb_retrieval.embed.embed_batch_resilient` (`/api/embed` with `input` as a list) before
   inserting. `ON CONFLICT (envelope_id, chunk_index, model) DO NOTHING` is checked via the
   command tag, so a silent no-op counts as `chunks_conflict_skipped`, never
   `chunks_inserted`.
9. **Threading append** (Decyzja 10): `In-Reply-To`/`References` (angle brackets stripped,
   matching `envelope.id`'s bare-Message-ID convention) appended as
   `entities[type=threading]` via the same idempotent `WHERE NOT EXISTS` UPDATE pattern as
   `gmail-header-backfill` — done for every parsed envelope regardless of newsletter/
   body_empty status, since it's the same read either way.

## Two modes: backfill slice vs cyclic queue

The job was written for supervised full-corpus slices (`--limit`/`--offset`/`--since`). Since
2026-08-06 it also runs as a stage of `kb-ingest` every 2 hours, draining what the incremental
IMAP sync fetched:

```bash
mail-body-ingest --only-unchunked --apply          # cyclic mode
```

`--only-unchunked` restricts the set to envelopes with **no `document_chunk` rows at all** —
the queue that the data itself defines (recon `kb/audits/mail-sync-2026-08-06.md` §3.2). It
needs no separate state and is self-healing: an interrupted run, a mail fetched while Ollama
was down, a message inserted with a backdated header — each stays pending until it has chunks.

`--since` was explicitly rejected for that role. It filters on `envelope.ts`, the sender's
`Date:` header, so a mail delivered today carrying a month-old date would fall outside the
window and never be chunked at all. `--since` stays what it was: a tool for staging manual runs.

`--sources` defaults to `gmail,fastmail`. The pre-fetched chunk-key set is scoped to the
working set (`WHERE model = $1 AND envelope_id = ANY($2)`); unbounded it read all 389 012 keys
(~26 MB, ~1.0 s) on every run, which is nothing once for a 50k slice and wasteful every two
hours on a node with 2.4 GB available (recon §2.5 iv).

## Stats must balance

```
mails_scanned = missing_file + read_errors + parse_errors + body_empty + mails_chunked
chunks_total  = chunks_inserted + chunks_newsletter_flagged + chunks_already_embedded
                + chunks_conflict_skipped + chunks_errors
```

Any non-zero `read_errors`/`parse_errors`/`missing_file`/`chunks_errors`/
`chunks_conflict_skipped`, or an unbalanced sum, makes the CLI exit 1 — same convention as
`gmail-header-backfill`/`documents-ingest`'s `chunk_embed`.

**Reading exit 1 on a full-corpus run**: it is a "look at this", not "the run failed". Across
225k mails a handful of `parse_errors` is expected (plan §1.5 documents ~9 mails that need the
compat32 fallback), and any one of them alone trips exit 1. The verdict is the balance and the
counters in the `summary` line, not the exit code. Exit 2 is different — see below.

## Exit codes

| Code | Meaning |
|---|---|
| 0 | Balanced, zero errors |
| 1 | Balanced-but-imperfect (any `parse_errors`/`missing_file`/`read_errors`/`chunks_errors`/`chunks_conflict_skipped`), an unbalanced sum, or an embedding-dimension abort |
| 2 | `--max-embed-failures` consecutive embed batches gave up — the embed backend is down; re-run once it is back |

## Ollama-offline tolerance and the circuit breaker

Three failure modes, three responses — the first two live in
`kb_retrieval.embed.embed_batch_resilient`, the third here:

1. **Transient blip** — the batch is retried `--embed-retries` times (default 2) with
   exponential backoff (`--embed-backoff`, default 1 s, doubled per attempt). Costs seconds,
   loses nothing.
2. **One poison chunk** — `/api/embed` is all-or-nothing, so a single pathological text used to
   cost the entire 64-chunk batch it happened to land in. When the retries are exhausted but
   `/api/tags` says the backend is alive, the batch is bisected until the bad inputs are
   isolated; the healthy remainder embeds normally and only the genuinely bad chunks count as
   `chunks_errors`. One bad chunk costs ~log2(batch) extra requests instead of 64 embeddings.
3. **Dead backend** — the probe says down, so the batch gives up *without* bisecting (splitting
   against a dead backend would burn 2n-1 requests and delay the breaker exactly when it needs
   to trip).

Tolerating a *flaky* backend is right; surviving a *dead* one is not. The archive is parsed
single-threaded ahead of the GPU, so on a full-corpus run (Etap B) a dead Ollama would let the
job chew through 200k+ mails at parse speed, mark every chunk `chunks_errors`, and throw away a
multi-hour pass. `--max-embed-failures` (default 5, `0` disables) therefore stops the run after
that many *consecutive* give-ups, with exit code 2; any successful batch resets the counter.
Ollama@SOLARIA's known failure mode is total (container vanishes, network-detached — 4
incidents, plan §1.4/§7), so the breaker trips within seconds of it. On abort, rows already
embedded in the dying batch are committed and pending `entities[type=threading]` appends are
flushed first: they don't depend on Ollama, they're idempotent, and re-deriving them would mean
re-reading the same 27 GB.

A partial failure against a *live* backend deliberately does **not** advance the breaker: those
chunks were never inserted, so the next run retries them through the ordinary idempotency path,
and letting a handful of bad chunks abort a 50k slice would be strictly worse than skipping
them. `embed_items_failed` and the `embed_requests_total`/`embed_calls` ratio in the `summary`
line are what to read — a ratio of 1.0 means a clean run with no retries or bisection.

Timeouts are part of this, not an exception to it: aiohttp raises a bare `builtins.TimeoutError`
when `ClientTimeout(total=...)` expires, and that is **not** a subclass of
`aiohttp.ClientError`. An earlier version of this job caught `ClientError` alone, so an Ollama
that accepted the connection and then hung — its actual failure mode — crashed the run outright,
with no breaker and no threading flush. `kb_retrieval.embed.TRANSIENT_EMBED_ERRORS` now names
both; catch that tuple, never `ClientError` on its own.

Only a wrong embedding dimension is more severe (`EmbeddingDimensionError`, exit 1) — it aborts
immediately, since that would otherwise silently index a vector that doesn't match
`document_chunk.embedding VECTOR(1024)`.

## No SOLARIA -> PIHA fallback here (deliberate)

`kb-query` fails a *query* over to Ollama@PIHA when SOLARIA is down (`app/embed_router.py`).
This job does not, by decision: ~271k active chunks at PIHA's ~790 ms/embed CPU is ~60 h on an
8 GB node already shared with Home Assistant, Paperless and kb-postgres, and CPU embedding does
not batch-scale the way the GPU does. A fallback would quietly turn "abort and resume the slice
once Ollama is fixed" into a two-day run suffocating the infra node. The correct answer to a
dead primary in the backfill path is to stop and resume — which costs nothing, because the job
is idempotent. The two backend paths stay separate on purpose.

## Batch-size benchmark

`mail-body-ingest-bench` (same package) sweeps batch sizes over real mail chunks and prints
ms/chunk, chunks/s and a projected wall-clock for the full corpus. Read-only — `SELECT`s and
inference, with no code path that can write — so it is safe to point at live kb-postgres@PIHA.

```bash
mail-body-ingest-bench --dsn postgresql://kb:<pw>@piha:5433/kb \
    --archive-root /home/oskar/kb/mail/archive --sample-envelopes 200
```

It warms the model up before measuring (the first call after an idle period pays the model
load) and measures the *same* chunk set at every size, since ms/chunk depends heavily on text
length. `--max-chunks` caps the set — batch=1 otherwise dominates the wall clock.

## Idempotency

Pre-fetched `(envelope_id, chunk_index)` pairs, scoped server-side to `--model` (`WHERE model
= $1`), skip chunks already inserted — the pair doesn't need `model` redundantly since the
fetch is already scoped to it. Built this way from the start per the plan's note that
`chunk_embed.py`'s otherwise-equivalent pre-fetch is easy to mis-key across runs that mix
models (not an active bug there today, since one run always uses one model, but worth not
repeating the ambiguity here).

## Definition of Done

Per `CLAUDE.md`: `pytest` passes (62/62 for the job, 22/22 for `kb-retrieval`'s embed client)
+ a `--limit 5` dry-run smoke against live
`kb-postgres@PIHA` before committing (confirms DSN/query wiring; a missing local archive
mirror correctly reports `missing_file` rather than crashing). The Etap A pilot (`--since
2025-07-01 --apply`, plan §7) is a separate, explicitly-confirmed run — not part of this
job's DoD, since it's the first real write against production data.