feat(advice): LLM brewing advice on every observation (work in progress)
Stores a model's advice for each recorded reading, in its own field, so the brewer's own comment is never overwritten. Fire and forget: the advice is generated in a background thread, so recording a reading never blocks on the model. A failure is recorded as a visible note saying the advice could not be generated, because a silent failure is indistinguishable from "still thinking". The model is `glm-5.3:cloud` on the Ollama instance at 192.168.178.45:11434. Several models on that instance are retired and fail at call time while still appearing in the model list, so the default is one that was probed. The system prompt tells the model never to call a reading impossible: a gravity below 1.000 is always a mis-entry, but the rest of the run may be a genuine long fermentation and still worth understanding. 150 tests.
This commit is contained in:
@@ -0,0 +1,211 @@
|
||||
"""Brewing advice from an LLM, generated for each recorded observation.
|
||||
|
||||
The advice is a *comment on the reading*, not a replacement for the
|
||||
brewer's own comment. Every reading gets its own advice text, stored in
|
||||
its own field, so nothing the brewer wrote is ever overwritten.
|
||||
|
||||
Design notes
|
||||
------------
|
||||
- **The LLM is never in the request path.** Recording a reading must not
|
||||
block on a model that may be slow or down, so the advice is generated in
|
||||
a background thread and written when it is ready. The page shows the
|
||||
reading immediately and the advice appears on a later visit.
|
||||
- **Failures are recorded, not raised.** If the model is unreachable the
|
||||
advice field gets a short note saying so. A silent failure would look
|
||||
identical to "no advice yet", which is confusing when you are waiting
|
||||
for a tip that is never going to arrive.
|
||||
- **The model is configurable**, with a default that is known to work on
|
||||
this homelab. Several models on the Ollama instance have been retired
|
||||
and fail at call time while still appearing in the model list, so the
|
||||
default is verified rather than assumed.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
#: The Ollama instance on the homelab. Reachable from the pod.
|
||||
DEFAULT_OLLAMA_URL = os.getenv("OLLAMA_URL", "http://192.168.178.45:11434")
|
||||
|
||||
#: A model that is known to work. `deepseek-v4-flash:cloud`,
|
||||
#: `deepseek-v3.2:cloud` and `qwen3.5:cloud` are all retired and fail at
|
||||
#: call time, so they are not safe defaults.
|
||||
DEFAULT_MODEL = os.getenv("OLLAMA_MODEL", "glm-5.3:cloud")
|
||||
|
||||
#: How long to wait for the model before giving up. The advice is
|
||||
#: generated in the background, so this only bounds the background thread.
|
||||
DEFAULT_TIMEOUT = float(os.getenv("LLM_TIMEOUT", "45"))
|
||||
|
||||
#: The advice is advice, not instruction. Keep it short - it has to be
|
||||
#: readable on the brewing page next to the brewer's own comment.
|
||||
MAX_ADVICE_CHARS = 1200
|
||||
|
||||
SYSTEM_PROMPT = """\
|
||||
You are an experienced home brewer giving practical advice to a single \
|
||||
brewer about their own beer. You know brewing science: specific gravity, \
|
||||
attenuation, yeast health, temperature, timing, and what a stalled or \
|
||||
struck-out fermentation looks like.
|
||||
|
||||
You will be given one brew's readings so far: its name, the original \
|
||||
gravity, each reading's date and specific gravity, and any comment the \
|
||||
brewer wrote.
|
||||
|
||||
Give the brewer useful, specific, practical advice about THIS reading and \
|
||||
this brew. Consider things like:
|
||||
|
||||
- Is the fermentation progressing at a normal rate for the style and \
|
||||
temperature?
|
||||
- Has it stalled, and if so what should they do about it?
|
||||
- Is the yeast likely stressed, unhealthy, or done?
|
||||
- Is the gravity drop plausible for the original gravity?
|
||||
- Should they rack, add more hops, raise the temperature, or wait?
|
||||
|
||||
Rules:
|
||||
- If everything looks normal, say so briefly and say what to expect next.
|
||||
- If something looks wrong, say what it is and what to do about it.
|
||||
- Be specific to the numbers given. Do not give generic advice.
|
||||
- If a reading looks like a typo or a mis-entry, say so and suggest \
|
||||
checking it, but do not assume it - a slow or long fermentation can be \
|
||||
genuine.
|
||||
- Never say a reading is impossible. Beer cannot be denser than water, so \
|
||||
a gravity below 1.000 is always a mis-entry or a typo, but the rest of the \
|
||||
run may still be real and worth understanding.
|
||||
- No preamble, no headings, no bullet-point templates, no "Great question!". \
|
||||
Write two to five sentences of plain prose.
|
||||
"""
|
||||
|
||||
|
||||
def _reading_lines(readings: list[dict]) -> str:
|
||||
"""The readings, as the compact list the model reads."""
|
||||
lines = []
|
||||
for r in readings:
|
||||
parts = [f"- {r.get('date')}: gravity {r.get('sg_decimal')} ({r.get('point_scale')})"]
|
||||
if r.get("comment"):
|
||||
parts.append(f"brewer's comment: {r['comment']}")
|
||||
if r.get("final"):
|
||||
parts.append("(marked as the FINAL reading)")
|
||||
lines.append(" ".join(parts))
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def build_prompt(run: dict, reading: dict, history: list[dict]) -> str:
|
||||
"""The user-message content for one observation."""
|
||||
name = run.get("canonical_name") or run.get("name") or "this brew"
|
||||
og = run.get("og_decimal")
|
||||
if og is None and run.get("og_points"):
|
||||
og = f"{run['og_points'] / 1000:.3f}"
|
||||
|
||||
parts = [
|
||||
f"Beer: {name}",
|
||||
]
|
||||
if og:
|
||||
parts.append(f"Original gravity: {og}")
|
||||
if run.get("tap_number"):
|
||||
parts.append(f"Fermenter tap: {run['tap_number']}")
|
||||
if run.get("notes"):
|
||||
parts.append(f"Brewer's notes: {run['notes']}")
|
||||
|
||||
parts.append("")
|
||||
parts.append("Readings so far (oldest first):")
|
||||
parts.append(_reading_lines(history))
|
||||
|
||||
parts.append("")
|
||||
parts.append("Give advice for the most recent reading.")
|
||||
return "\n".join(parts)
|
||||
|
||||
|
||||
def call_ollama(prompt: str, *, url: str | None = None, model: str | None = None,
|
||||
timeout: float | None = None) -> str:
|
||||
"""Ask the model for advice. Raises on failure."""
|
||||
base = (url or DEFAULT_OLLAMA_URL).rstrip("/")
|
||||
chosen_model = model or DEFAULT_MODEL
|
||||
wait = timeout if timeout is not None else DEFAULT_TIMEOUT
|
||||
|
||||
payload = json.dumps({
|
||||
"model": chosen_model,
|
||||
"messages": [
|
||||
{"role": "system", "content": SYSTEM_PROMPT},
|
||||
{"role": "user", "content": prompt},
|
||||
],
|
||||
"temperature": 0.4,
|
||||
# The reasoning models emit their thinking first, and it comes out
|
||||
# of the same budget. At 500 tokens the reasoning used the whole
|
||||
# allowance and the reply came back empty - which looked like a
|
||||
# broken model rather than a budget problem. 2000 leaves room for
|
||||
# the reasoning AND the advice.
|
||||
"max_tokens": 2000,
|
||||
"stream": False,
|
||||
}).encode("utf-8")
|
||||
|
||||
request = urllib.request.Request(
|
||||
f"{base}/v1/chat/completions",
|
||||
data=payload,
|
||||
headers={"Content-Type": "application/json"},
|
||||
method="POST",
|
||||
)
|
||||
with urllib.request.urlopen(request, timeout=wait) as response:
|
||||
body = json.loads(response.read().decode("utf-8"))
|
||||
|
||||
choices = body.get("choices") or []
|
||||
if not choices:
|
||||
raise RuntimeError("the model returned no choices")
|
||||
content = (choices[0].get("message") or {}).get("content") or ""
|
||||
content = content.strip()
|
||||
if not content:
|
||||
raise RuntimeError("the model returned an empty response")
|
||||
return content[:MAX_ADVICE_CHARS]
|
||||
|
||||
|
||||
def generate_advice(run: dict, reading: dict, history: list[dict], *,
|
||||
url: str | None = None, model: str | None = None,
|
||||
timeout: float | None = None) -> tuple[bool, str]:
|
||||
"""Generate the advice for one reading.
|
||||
|
||||
Returns ``(ok, text)``. On failure ``ok`` is False and ``text`` is a
|
||||
short note explaining what went wrong, so the reading carries a
|
||||
visible reason instead of silently having no advice.
|
||||
"""
|
||||
prompt = build_prompt(run, reading, history)
|
||||
try:
|
||||
return True, call_ollama(prompt, url=url, model=model, timeout=timeout)
|
||||
except urllib.error.HTTPError as exc:
|
||||
# HTTPError is a subclass of URLError, so it has to be caught
|
||||
# FIRST or it would be swallowed by the unreachable branch.
|
||||
detail = ""
|
||||
try:
|
||||
detail = exc.read().decode("utf-8", "replace")[:300]
|
||||
except Exception:
|
||||
pass
|
||||
log.warning("the model returned HTTP %s: %s", exc.code, detail)
|
||||
return False, (f"Advice could not be generated - the model returned "
|
||||
f"HTTP {exc.code}. {detail}".strip())
|
||||
except urllib.error.URLError as exc:
|
||||
log.warning("the model was unreachable: %s", exc)
|
||||
return False, "Advice could not be generated - the model was unreachable."
|
||||
except TimeoutError:
|
||||
log.warning("the model timed out")
|
||||
return False, "Advice could not be generated - the model timed out."
|
||||
except Exception as exc: # noqa: BLE001 - the caller must never crash
|
||||
log.warning("advice generation failed: %s", exc)
|
||||
return False, f"Advice could not be generated - {exc}"
|
||||
|
||||
|
||||
def generate_advice_in_background(run: dict, reading: dict,
|
||||
history: list[dict], writer) -> None:
|
||||
"""Generate the advice and hand it to *writer* when it is ready.
|
||||
|
||||
*writer* is called as ``writer(reading_id, ok, text)``. It runs in a
|
||||
background thread, so it must not touch the request context - the
|
||||
caller is responsible for giving it a way to reach Mongo.
|
||||
"""
|
||||
ok, text = generate_advice(run, reading, history)
|
||||
try:
|
||||
writer(reading.get("_id"), ok, text)
|
||||
except Exception: # noqa: BLE001 - never let the thread die noisily
|
||||
log.exception("could not store the generated advice")
|
||||
@@ -152,6 +152,10 @@ class Reading:
|
||||
comment: str = ""
|
||||
beer_type: str = ""
|
||||
_id: str = ""
|
||||
# The LLM's advice for this reading. It lives in its own field in
|
||||
# Mongo, so the brewer's own comment is never overwritten.
|
||||
advice: str = ""
|
||||
advice_ok: bool = True
|
||||
|
||||
@property
|
||||
def sg_decimal(self) -> float | None:
|
||||
@@ -171,6 +175,8 @@ class Reading:
|
||||
comment=(doc.get("comment") or "").strip(),
|
||||
beer_type=(doc.get("beer_type") or "").strip(),
|
||||
_id=str(doc.get("_id") or ""),
|
||||
advice=(doc.get("advice") or "").strip(),
|
||||
advice_ok=bool(doc.get("advice_ok", True)),
|
||||
)
|
||||
|
||||
|
||||
@@ -189,6 +195,25 @@ class Run:
|
||||
|
||||
# -- aggregate accessors ------------------------------------------------ #
|
||||
|
||||
def latest_advice(self) -> str:
|
||||
"""The advice for the most recent reading that has any.
|
||||
|
||||
The advice is generated in the background, so the newest reading
|
||||
may not have any yet - in which case the newest one that does is
|
||||
used, rather than showing nothing.
|
||||
"""
|
||||
for reading in reversed(self.readings):
|
||||
if reading.advice:
|
||||
return reading.advice
|
||||
return ""
|
||||
|
||||
def latest_advice_ok(self) -> bool:
|
||||
"""False when the advice is a note saying it could not be generated."""
|
||||
for reading in reversed(self.readings):
|
||||
if reading.advice:
|
||||
return reading.advice_ok
|
||||
return True
|
||||
|
||||
def sg_values(self) -> list[int]:
|
||||
"""Gravity points of every *usable* reading, in chronological order."""
|
||||
return [r.sg_points for r in self.readings if r.sg_points is not None]
|
||||
@@ -581,6 +606,10 @@ def run_summary(run: Run, today: date | None = None,
|
||||
"days_in_fermenter": run.days_in_fermenter(today),
|
||||
"comments": run.comments(),
|
||||
"last_comment": run.comments()[-1] if run.comments() else "",
|
||||
# The advice the LLM gave for the most recent reading, if it has
|
||||
# arrived yet.
|
||||
"advice": run.latest_advice(),
|
||||
"advice_ok": run.latest_advice_ok(),
|
||||
"attenuation": attenuation_percent(run),
|
||||
"curve": fermentation_curve(run),
|
||||
"outliers": [r.sg_points for r in run.outlier_readings()],
|
||||
@@ -592,6 +621,8 @@ def run_summary(run: Run, today: date | None = None,
|
||||
"final_reading": r.final_reading,
|
||||
"comment": r.comment,
|
||||
"beer_type": r.beer_type,
|
||||
"advice": r.advice,
|
||||
"advice_ok": r.advice_ok,
|
||||
}
|
||||
for r in run.readings
|
||||
],
|
||||
|
||||
@@ -188,6 +188,27 @@ class BeerRepository:
|
||||
existing = self.readings.find_one(query)
|
||||
return str(existing.get("_id")) if existing else ""
|
||||
|
||||
def set_reading_advice(self, reading_id: str, advice: str,
|
||||
ok: bool = True) -> int:
|
||||
"""Attach the LLM's advice to a reading.
|
||||
|
||||
The advice lives in its own field, so the brewer's own comment is
|
||||
never overwritten. ``ok`` says whether the advice was actually
|
||||
generated or is a note explaining that it could not be.
|
||||
"""
|
||||
doc_id = _as_doc_id(reading_id)
|
||||
if doc_id is None:
|
||||
return 0
|
||||
result = self.readings.update_one(
|
||||
{"_id": doc_id},
|
||||
{"$set": {
|
||||
"advice": str(advice),
|
||||
"advice_ok": bool(ok),
|
||||
"advice_at": _now_iso(),
|
||||
}},
|
||||
)
|
||||
return result.modified_count
|
||||
|
||||
def set_final_reading(self, beer_run_id: str, reading_date: str,
|
||||
final: bool) -> int:
|
||||
"""Flag (or unflag) a reading as the final reading of its run."""
|
||||
@@ -314,6 +335,28 @@ def _as_id(value: object) -> str:
|
||||
return ""
|
||||
|
||||
|
||||
def _as_doc_id(value: object):
|
||||
"""Coerce a reading document id to something Mongo will match.
|
||||
|
||||
The ``_id`` of a reading is an ``ObjectId``, not a run id, so the
|
||||
``_as_id`` coercion does not apply - it would turn the ObjectId into
|
||||
an empty string and the update would silently match nothing.
|
||||
|
||||
Only an ObjectId or a plain string is accepted, so a dict can never
|
||||
be injected as a query operator.
|
||||
"""
|
||||
from bson import ObjectId
|
||||
|
||||
if isinstance(value, ObjectId):
|
||||
return value
|
||||
if isinstance(value, str):
|
||||
try:
|
||||
return ObjectId(value)
|
||||
except Exception:
|
||||
return None
|
||||
return None
|
||||
|
||||
|
||||
def _as_date(value: object) -> str:
|
||||
"""Coerce a reading date to a plain ``YYYY-MM-DD`` string."""
|
||||
if isinstance(value, str):
|
||||
|
||||
@@ -689,3 +689,65 @@ table.data .comment { color: var(--text-muted); font-size: .84rem; }
|
||||
.reading-list__sg { font-family: var(--mono); font-weight: 650; flex: 0 0 4rem; }
|
||||
.reading-list__body { flex: 1; min-width: 0; }
|
||||
.reading-list__comment { color: var(--text-muted); font-size: .84rem; }
|
||||
|
||||
/* ------------------------------------------------------------- advice */
|
||||
|
||||
/* The LLM's advice. It sits next to the brewer's own comment, never
|
||||
replaces it, and is visually distinct so the two are never confused. */
|
||||
.advice {
|
||||
display: block;
|
||||
margin-top: .35rem;
|
||||
padding: .5rem .65rem;
|
||||
border-left: 2px solid var(--amber);
|
||||
border-radius: 0 4px 4px 0;
|
||||
background: var(--amber-dim);
|
||||
color: var(--text);
|
||||
font-size: .8125rem;
|
||||
line-height: 1.5;
|
||||
}
|
||||
|
||||
.advice__label {
|
||||
display: block;
|
||||
margin-bottom: .15rem;
|
||||
font-size: .625rem;
|
||||
font-weight: 600;
|
||||
letter-spacing: .08em;
|
||||
text-transform: uppercase;
|
||||
color: var(--amber-text);
|
||||
}
|
||||
|
||||
/* Advice that could not be generated - it says why. */
|
||||
.advice--failed {
|
||||
border-left-color: var(--danger);
|
||||
background: var(--danger-dim);
|
||||
color: var(--text-muted);
|
||||
}
|
||||
|
||||
.advice--failed .advice__label {
|
||||
color: var(--danger);
|
||||
}
|
||||
|
||||
.advice-cell {
|
||||
max-width: 32rem;
|
||||
}
|
||||
|
||||
/* In the table the advice is clamped to a few lines - the full text is
|
||||
on the run detail page, where there is room to read it. */
|
||||
.advice-cell .advice {
|
||||
margin-top: 0;
|
||||
font-size: .75rem;
|
||||
display: -webkit-box;
|
||||
-webkit-line-clamp: 4;
|
||||
line-clamp: 4;
|
||||
-webkit-box-orient: vertical;
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
/* The clamped text opens up on hover, so the whole thing is readable
|
||||
without leaving the page. */
|
||||
.advice-cell:hover .advice,
|
||||
.advice-cell:focus-within .advice {
|
||||
-webkit-line-clamp: unset;
|
||||
line-clamp: unset;
|
||||
overflow: visible;
|
||||
}
|
||||
|
||||
@@ -100,6 +100,13 @@
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
{% if run.advice %}
|
||||
<div class="advice advice--reading{% if not run.advice_ok %} advice--failed{% endif %}">
|
||||
<span class="advice__label">Brewing advice</span>
|
||||
{{ run.advice }}
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
<div class="btn-row">
|
||||
<a class="btn btn--ghost btn--sm"
|
||||
href="{{ url_for('brews.run_detail', run_id=run.beer_run_id) }}">Open run</a>
|
||||
|
||||
@@ -83,6 +83,7 @@
|
||||
<th class="num">Gravity</th>
|
||||
<th class="num">Est. ABV</th>
|
||||
<th>Comment</th>
|
||||
<th>Brewing advice</th>
|
||||
<th></th>
|
||||
</tr>
|
||||
</thead>
|
||||
@@ -111,6 +112,13 @@
|
||||
<span class="faint">—</span>
|
||||
{% endif %}
|
||||
</td>
|
||||
<td class="comment advice-cell">
|
||||
{% if run.advice %}
|
||||
<span class="advice{% if not run.advice_ok %} advice--failed{% endif %}">{{ run.advice }}</span>
|
||||
{% else %}
|
||||
<span class="faint">Thinking…</span>
|
||||
{% endif %}
|
||||
</td>
|
||||
<td class="right">
|
||||
<a class="btn btn--ghost btn--sm"
|
||||
href="{{ url_for('brews.run_detail', run_id=run.beer_run_id) }}">Open</a>
|
||||
|
||||
@@ -144,6 +144,12 @@
|
||||
{% else %}
|
||||
<div class="faint tiny">No comment</div>
|
||||
{% endif %}
|
||||
{% if reading.advice %}
|
||||
<div class="advice advice--reading{% if not reading.advice_ok %} advice--failed{% endif %}">
|
||||
<span class="advice__label">Brewing advice</span>
|
||||
{{ reading.advice }}
|
||||
</div>
|
||||
{% endif %}
|
||||
</div>
|
||||
{% if reading.final_reading %}
|
||||
<span class="chip chip--done">Final</span>
|
||||
|
||||
@@ -2,15 +2,22 @@
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from flask import (Blueprint, flash, jsonify, redirect, render_template,
|
||||
request, session, url_for)
|
||||
import logging
|
||||
import os
|
||||
import threading
|
||||
|
||||
from flask import (Blueprint, current_app, flash, jsonify, redirect,
|
||||
render_template, request, session, url_for)
|
||||
from flask_wtf import FlaskForm
|
||||
from wtforms import (BooleanField, DateField, IntegerField, StringField,
|
||||
SubmitField, TextAreaField)
|
||||
from wtforms.validators import DataRequired, Length, NumberRange, Optional
|
||||
|
||||
import brew_advice
|
||||
from brewing import implausible_runs, is_plausible_sg, run_summary
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
bp = Blueprint("brews", __name__)
|
||||
|
||||
|
||||
@@ -34,6 +41,82 @@ def login_required(fn):
|
||||
return wrapper
|
||||
|
||||
|
||||
def advice_enabled() -> bool:
|
||||
"""Whether the LLM advice should be generated.
|
||||
|
||||
It is off in testing, so the suite never reaches out to a model, and
|
||||
it can be turned off in production with ``LLM_ADVICE=0`` if the model
|
||||
is misbehaving.
|
||||
"""
|
||||
if current_app.config.get("TESTING"):
|
||||
return False
|
||||
return os.getenv("LLM_ADVICE", "1").strip().lower() not in {"0", "false", "no"}
|
||||
|
||||
|
||||
def _start_advice(run_id: str, reading_id: str) -> None:
|
||||
"""Generate the LLM's advice for a reading, in the background.
|
||||
|
||||
The advice is a separate field on the reading, so the brewer's own
|
||||
comment is never touched.
|
||||
|
||||
The background thread cannot use the request-scoped repository - that
|
||||
client is closed when the request ends - so it builds its own.
|
||||
"""
|
||||
if not reading_id:
|
||||
return
|
||||
if not advice_enabled():
|
||||
return
|
||||
|
||||
try:
|
||||
repository = repo()
|
||||
run = repository.run(run_id)
|
||||
if run is None:
|
||||
return
|
||||
meta = repository.run_metadata(run_id)
|
||||
summary = run_summary(run, og_override=meta.get("og_points"))
|
||||
run_info = {
|
||||
"canonical_name": meta.get("name") or run.display_name(),
|
||||
"name": run.display_name(),
|
||||
"og_points": summary.get("og_points"),
|
||||
"og_decimal": summary.get("og_decimal"),
|
||||
"tap_number": meta.get("tap_number"),
|
||||
"notes": meta.get("notes", ""),
|
||||
}
|
||||
|
||||
# The model's view of the run: every reading, with the gravity in
|
||||
# both forms a brewer would recognise.
|
||||
readings = []
|
||||
for reading in run.readings:
|
||||
points = reading.sg_points
|
||||
readings.append({
|
||||
"_id": reading._id,
|
||||
"date": reading.date.isoformat() if reading.date else "",
|
||||
"sg": points,
|
||||
"sg_decimal": reading.sg_decimal,
|
||||
"point_scale": f"{points} points" if points is not None else "",
|
||||
"comment": reading.comment or "",
|
||||
"final": bool(reading.final_reading),
|
||||
})
|
||||
|
||||
latest = dict(readings[-1]) if readings else {"date": "", "sg": None}
|
||||
latest["_id"] = reading_id
|
||||
|
||||
except Exception: # noqa: BLE001 - advice must never break the save
|
||||
log.exception("could not gather the reading for the advice")
|
||||
return
|
||||
|
||||
def write(read_id: str, ok: bool, text: str) -> None:
|
||||
from mongo.repository import BeerRepository
|
||||
BeerRepository().set_reading_advice(read_id, text, ok)
|
||||
|
||||
thread = threading.Thread(
|
||||
target=brew_advice.generate_advice_in_background,
|
||||
args=(run_info, latest, readings, write),
|
||||
daemon=True,
|
||||
)
|
||||
thread.start()
|
||||
|
||||
|
||||
def _last_reading_date(run) -> str | None:
|
||||
"""The ISO date of the most recent reading in a run."""
|
||||
last = run.last_reading()
|
||||
@@ -87,8 +170,9 @@ def index():
|
||||
"(990-1200). It was saved anyway — double-check the reading.",
|
||||
"warning",
|
||||
)
|
||||
repo().upsert_reading(
|
||||
beer_run_id=str(form.beer_run_id.data),
|
||||
run_id = str(form.beer_run_id.data)
|
||||
reading_id = repo().upsert_reading(
|
||||
beer_run_id=run_id,
|
||||
beer_type=(form.beer_run_type.data or "").strip(),
|
||||
sg=sg_points,
|
||||
reading_date=form.Date.data.isoformat(),
|
||||
@@ -96,6 +180,11 @@ def index():
|
||||
comment=(form.comment.data or "").strip(),
|
||||
)
|
||||
flash("Reading saved.", "success")
|
||||
|
||||
# The advice is generated in the background: recording a reading
|
||||
# must not block on the model. The page shows the reading straight
|
||||
# away and the advice is there on a later visit.
|
||||
_start_advice(run_id, reading_id)
|
||||
return redirect(url_for("brews.index"))
|
||||
|
||||
runs = repo().runs()
|
||||
|
||||
@@ -0,0 +1,338 @@
|
||||
"""Tests for the LLM brewing advice: the prompt, the storage and the display."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from datetime import date
|
||||
|
||||
import pytest
|
||||
|
||||
import brew_advice
|
||||
from conftest import seed_readings
|
||||
|
||||
|
||||
# ------------------------------------------------------------ the prompt #
|
||||
|
||||
def test_the_prompt_gives_the_model_the_brew_and_its_readings():
|
||||
"""The model needs the name, the OG and every reading."""
|
||||
run = {
|
||||
"canonical_name": "Nocturna Christmas beer",
|
||||
"og_decimal": 1.042,
|
||||
"tap_number": 3,
|
||||
"notes": "dark malt, 19C",
|
||||
}
|
||||
reading = {"date": "2026-01-10", "sg_decimal": 1.022,
|
||||
"point_scale": "1022 points", "comment": "no change since day 7",
|
||||
"final": False}
|
||||
history = [
|
||||
{"date": "2026-01-01", "sg_decimal": 1.042, "point_scale": "1042 points",
|
||||
"comment": "", "final": False},
|
||||
reading,
|
||||
]
|
||||
|
||||
prompt = brew_advice.build_prompt(run, reading, history)
|
||||
|
||||
assert "Nocturna Christmas beer" in prompt
|
||||
assert "1.042" in prompt
|
||||
assert "Fermenter tap: 3" in prompt
|
||||
assert "dark malt" in prompt
|
||||
# Both readings, oldest first.
|
||||
assert "2026-01-01" in prompt
|
||||
assert "2026-01-10" in prompt
|
||||
assert "no change since day 7" in prompt
|
||||
assert "1.022" in prompt
|
||||
|
||||
|
||||
def test_the_prompt_tells_the_model_not_to_call_a_reading_impossible():
|
||||
"""A reading below 1.000 is a mis-entry, but the run may still be real.
|
||||
|
||||
This matters: the brewer's own run 12 was a genuine long fermentation
|
||||
that the app flagged as impossible. The model must not repeat that
|
||||
mistake - it should point at the odd reading and keep talking about
|
||||
the brew.
|
||||
"""
|
||||
assert "Never say a reading is impossible" in brew_advice.SYSTEM_PROMPT
|
||||
assert "still be real" in brew_advice.SYSTEM_PROMPT
|
||||
|
||||
|
||||
def test_the_prompt_marks_the_final_reading():
|
||||
run = {"canonical_name": "Ale"}
|
||||
reading = {"date": "2026-01-20", "sg_decimal": 1.010, "point_scale": "1010 points",
|
||||
"comment": "", "final": True}
|
||||
prompt = brew_advice.build_prompt(run, reading, [reading])
|
||||
assert "FINAL reading" in prompt
|
||||
|
||||
|
||||
# ---------------------------------------------------------- the LLM call #
|
||||
|
||||
def test_a_successful_call_returns_the_text(monkeypatch):
|
||||
"""A normal reply comes back as the advice."""
|
||||
captured = {}
|
||||
|
||||
def fake_urlopen(request, timeout=None):
|
||||
captured["url"] = request.full_url
|
||||
captured["body"] = json.loads(request.data.decode())
|
||||
|
||||
class Response:
|
||||
def read(self):
|
||||
return json.dumps({
|
||||
"choices": [{"message": {"content": " Leave it alone, it is still fermenting. "}}]
|
||||
}).encode()
|
||||
|
||||
def __enter__(self):
|
||||
return self
|
||||
|
||||
def __exit__(self, *args):
|
||||
return False
|
||||
|
||||
return Response()
|
||||
|
||||
monkeypatch.setattr(brew_advice.urllib.request, "urlopen", fake_urlopen)
|
||||
|
||||
ok, text = brew_advice.generate_advice(
|
||||
{"canonical_name": "Ale"},
|
||||
{"date": "2026-01-01", "sg_decimal": 1.042, "point_scale": "1042 points",
|
||||
"comment": "", "final": False},
|
||||
[{"date": "2026-01-01", "sg_decimal": 1.042, "point_scale": "1042 points",
|
||||
"comment": "", "final": False}],
|
||||
model="glm-5.3:cloud",
|
||||
)
|
||||
|
||||
assert ok is True
|
||||
assert text == "Leave it alone, it is still fermenting."
|
||||
assert captured["url"].endswith("/v1/chat/completions")
|
||||
assert captured["body"]["model"] == "glm-5.3:cloud"
|
||||
|
||||
|
||||
def test_an_unreachable_model_does_not_raise(monkeypatch):
|
||||
"""A failure is recorded, not raised.
|
||||
|
||||
The reading has to be saved either way, and a silent failure would be
|
||||
indistinguishable from "the advice is still being generated".
|
||||
"""
|
||||
def boom(request, timeout=None):
|
||||
raise brew_advice.urllib.error.URLError("connection refused")
|
||||
|
||||
monkeypatch.setattr(brew_advice.urllib.request, "urlopen", boom)
|
||||
|
||||
ok, text = brew_advice.generate_advice(
|
||||
{"canonical_name": "Ale"},
|
||||
{"date": "2026-01-01", "sg_decimal": 1.042, "point_scale": "1042 points",
|
||||
"comment": "", "final": False},
|
||||
[],
|
||||
)
|
||||
|
||||
assert ok is False
|
||||
assert "could not be generated" in text
|
||||
|
||||
|
||||
def test_an_empty_reply_is_a_failure(monkeypatch):
|
||||
"""A model that returns nothing has not given advice."""
|
||||
|
||||
class Response:
|
||||
def read(self):
|
||||
return json.dumps({"choices": [{"message": {"content": " "}}]}).encode()
|
||||
|
||||
def __enter__(self):
|
||||
return self
|
||||
|
||||
def __exit__(self, *args):
|
||||
return False
|
||||
|
||||
monkeypatch.setattr(brew_advice.urllib.request, "urlopen",
|
||||
lambda request, timeout=None: Response())
|
||||
|
||||
ok, text = brew_advice.generate_advice({"canonical_name": "Ale"},
|
||||
{"date": "2026-01-01"}, [])
|
||||
assert ok is False
|
||||
assert "could not be generated" in text
|
||||
|
||||
|
||||
def test_the_token_budget_leaves_room_for_the_reasoning(monkeypatch):
|
||||
"""The reasoning models emit their thinking first, out of the same budget.
|
||||
|
||||
At 500 tokens the reasoning used the whole allowance and the reply
|
||||
came back EMPTY - which looks like a broken model rather than a
|
||||
budget problem. The budget has to cover the reasoning AND the advice.
|
||||
"""
|
||||
captured = {}
|
||||
|
||||
def fake_urlopen(request, timeout=None):
|
||||
captured["body"] = json.loads(request.data.decode())
|
||||
|
||||
class Response:
|
||||
def read(self):
|
||||
return json.dumps({
|
||||
"choices": [{"message": {"content": "Rouse the yeast."}}]
|
||||
}).encode()
|
||||
|
||||
def __enter__(self):
|
||||
return self
|
||||
|
||||
def __exit__(self, *args):
|
||||
return False
|
||||
|
||||
return Response()
|
||||
|
||||
monkeypatch.setattr(brew_advice.urllib.request, "urlopen", fake_urlopen)
|
||||
|
||||
brew_advice.generate_advice({"canonical_name": "Ale"},
|
||||
{"date": "2026-01-01"}, [])
|
||||
|
||||
assert captured["body"]["max_tokens"] >= 2000
|
||||
|
||||
|
||||
def test_the_advice_is_truncated():
|
||||
"""A runaway reply must not fill the reading document."""
|
||||
long_text = "x" * 5000
|
||||
|
||||
class Response:
|
||||
def read(self):
|
||||
return json.dumps({"choices": [{"message": {"content": long_text}}]}).encode()
|
||||
|
||||
def __enter__(self):
|
||||
return self
|
||||
|
||||
def __exit__(self, *args):
|
||||
return False
|
||||
|
||||
import brew_advice as ba
|
||||
original = ba.urllib.request.urlopen
|
||||
ba.urllib.request.urlopen = lambda request, timeout=None: Response()
|
||||
try:
|
||||
ok, text = ba.generate_advice({"canonical_name": "Ale"},
|
||||
{"date": "2026-01-01"}, [])
|
||||
finally:
|
||||
ba.urllib.request.urlopen = original
|
||||
|
||||
assert ok is True
|
||||
assert len(text) <= ba.MAX_ADVICE_CHARS
|
||||
|
||||
|
||||
# ------------------------------------------------------------- storage #
|
||||
|
||||
def test_the_advice_is_stored_in_its_own_field(repo):
|
||||
"""The brewer's comment is never overwritten."""
|
||||
seed_readings(repo, [("1", "Ale", "1042", "2026-01-01", False, "my own comment")])
|
||||
|
||||
doc = repo.readings.find_one({"beer_run_id": "1"})
|
||||
repo.set_reading_advice(str(doc["_id"]), "The advice", ok=True)
|
||||
|
||||
updated = repo.readings.find_one({"beer_run_id": "1"})
|
||||
assert updated["advice"] == "The advice"
|
||||
assert updated["advice_ok"] is True
|
||||
# The brewer's own comment is untouched.
|
||||
assert updated["comment"] == "my own comment"
|
||||
|
||||
|
||||
def test_a_failed_generation_is_stored_as_a_failure(repo):
|
||||
"""The note says it could not be generated, and is flagged as such."""
|
||||
seed_readings(repo, [("1", "Ale", "1042", "2026-01-01", False, "")])
|
||||
|
||||
doc = repo.readings.find_one({"beer_run_id": "1"})
|
||||
repo.set_reading_advice(str(doc["_id"]), "Advice could not be generated.", ok=False)
|
||||
|
||||
updated = repo.readings.find_one({"beer_run_id": "1"})
|
||||
assert updated["advice_ok"] is False
|
||||
|
||||
|
||||
def test_the_latest_advice_comes_from_the_newest_reading_with_one():
|
||||
"""The advice for the newest reading wins.
|
||||
|
||||
The advice is generated in the background, so the newest reading may
|
||||
not have one yet - in which case the newest that does is used.
|
||||
"""
|
||||
from brewing import Run
|
||||
|
||||
run = Run.from_docs("1", [
|
||||
{"_id": "a", "beer_run_id": "1", "sg": "1042", "date": "2026-01-01",
|
||||
"final_reading": "False", "comment": "", "advice": "first advice"},
|
||||
{"_id": "b", "beer_run_id": "1", "sg": "1030", "date": "2026-01-05",
|
||||
"final_reading": "False", "comment": "", "advice": "second advice"},
|
||||
{"_id": "c", "beer_run_id": "1", "sg": "1020", "date": "2026-01-10",
|
||||
"final_reading": "False", "comment": "", "advice": ""},
|
||||
])
|
||||
|
||||
assert run.latest_advice() == "second advice"
|
||||
assert run.latest_advice_ok() is True
|
||||
|
||||
|
||||
# ------------------------------------------------------------- the pages #
|
||||
|
||||
def test_recording_a_reading_saves_it_even_when_the_model_is_down(client, repo):
|
||||
"""The model being down must never stop a reading being saved."""
|
||||
repo.users.insert_one({"username": "beer", "password": "beer_pass"})
|
||||
client.post("/login", data={"username": "beer", "password": "beer_pass"},
|
||||
follow_redirects=True)
|
||||
|
||||
response = client.post("/brews", data={
|
||||
"beer_run_id": "99",
|
||||
"beer_run_type": "Test ale",
|
||||
"Date": "2026-01-01",
|
||||
"sg": "1042",
|
||||
"comment": "a comment",
|
||||
}, follow_redirects=True)
|
||||
|
||||
assert response.status_code == 200
|
||||
assert repo.readings.count_documents({"beer_run_id": "99"}) == 1
|
||||
|
||||
|
||||
def test_the_advice_is_shown_on_the_brewing_page(client, repo):
|
||||
"""The advice appears next to the comment, clearly labelled."""
|
||||
repo.users.insert_one({"username": "beer", "password": "beer_pass"})
|
||||
client.post("/login", data={"username": "beer", "password": "beer_pass"},
|
||||
follow_redirects=True)
|
||||
|
||||
seed_readings(repo, [("1", "Ale", "1042", "2026-01-01", False, "my comment")])
|
||||
doc = repo.readings.find_one({"beer_run_id": "1"})
|
||||
repo.set_reading_advice(str(doc["_id"]), "Rouse the yeast and wait.", ok=True)
|
||||
|
||||
response = client.get("/brews")
|
||||
body = response.get_data(as_text=True)
|
||||
|
||||
assert "Rouse the yeast and wait." in body
|
||||
# The brewer's own comment is still there.
|
||||
assert "my comment" in body
|
||||
# And it is labelled as advice, so the two are not confused.
|
||||
assert "Brewing advice" in body
|
||||
|
||||
|
||||
def test_the_advice_is_shown_on_the_active_beers_page(client, repo):
|
||||
"""The active page is where the brewer looks during a fermentation."""
|
||||
repo.users.insert_one({"username": "beer", "password": "beer_pass"})
|
||||
client.post("/login", data={"username": "beer", "password": "beer_pass"},
|
||||
follow_redirects=True)
|
||||
|
||||
seed_readings(repo, [("1", "Ale", "1042", "2026-01-01", False, "my comment")])
|
||||
doc = repo.readings.find_one({"beer_run_id": "1"})
|
||||
repo.set_reading_advice(str(doc["_id"]), "Warm it to 21C and wait.", ok=True)
|
||||
|
||||
response = client.get("/active")
|
||||
body = response.get_data(as_text=True)
|
||||
|
||||
assert "Warm it to 21C and wait." in body
|
||||
assert "Brewing advice" in body
|
||||
|
||||
|
||||
def test_a_failed_advice_is_marked_as_such(client, repo):
|
||||
"""A generation failure reads differently from real advice."""
|
||||
repo.users.insert_one({"username": "beer", "password": "beer_pass"})
|
||||
client.post("/login", data={"username": "beer", "password": "beer_pass"},
|
||||
follow_redirects=True)
|
||||
|
||||
seed_readings(repo, [("1", "Ale", "1042", "2026-01-01", False, "")])
|
||||
doc = repo.readings.find_one({"beer_run_id": "1"})
|
||||
repo.set_reading_advice(str(doc["_id"]), "Advice could not be generated.",
|
||||
ok=False)
|
||||
|
||||
response = client.get("/brews")
|
||||
body = response.get_data(as_text=True)
|
||||
assert "advice--failed" in body
|
||||
|
||||
|
||||
def test_advice_is_not_generated_in_tests(client, repo):
|
||||
"""The suite must never reach out to a real model."""
|
||||
from views.brews import advice_enabled
|
||||
|
||||
with client.application.app_context():
|
||||
assert advice_enabled() is False
|
||||
Reference in New Issue
Block a user