Merge the removal of must-haves: the judge reads CV, languages, prompts, likes and dislikes, the CV match is uncapped, migration 34 drops the columns (wp-musts)
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
commit
02ea191b53
19 files changed
+157
-365
No files matched your search
+13
-68
@@ -7,18 +7,14 @@ to three strengths and gaps. A model's rating is an estimate, so the scale is
|
||||
coarse. The total is `app.models.cv_score`, the three numbers under the
|
||||
agent's `cv_*` weights times 10, so 0 to 100, worked out when a role is served
|
||||
and not stored, so the weights are no part of `input_key`; it is what the
|
||||
feed's CV match sorts by. The model also reports a verdict on each of the
|
||||
agent's must-haves (one per line of its must text, numbered M1..Mn in the
|
||||
prompt); it does not apply them. The rule is code's: a "broken" one makes
|
||||
career count as at most `app.models.BROKEN_CAP` (4), when the role is
|
||||
served. Culture and location are left out: the first is guessed from ad text,
|
||||
the second is what the fetch gate does.
|
||||
feed's CV match sorts by. Culture and location are left out: the first is
|
||||
guessed from ad text, the second is what the fetch gate does.
|
||||
|
||||
The work is pairs, `(agent, role)`: an enabled agent with a CV, with or
|
||||
without a prompt, and an open role in its cut (`scores.cut`, see `app.jobs.score`: the best by
|
||||
fit, the best by CV closeness that those leave out, and the liked and saved)
|
||||
with some text, that has no judgement yet, or one read from another CV,
|
||||
prompts, languages, like, avoid or must text or role text than today's (`input_key`).
|
||||
prompts, languages, like or avoid text or role text than today's (`input_key`).
|
||||
The cut is the only selection: the pull judges it after extract and the
|
||||
rescore that follows, so it reads the cut as recomputed. A pair is named by the composite key `"<agent_id>:<uid>"`,
|
||||
which is what `desk.modeltask` hands round as a uid, so `desk/` is untouched.
|
||||
@@ -51,9 +47,7 @@ from pipeline import NULL, RunContext, Task, job
|
||||
from pipeline.task import Batch
|
||||
from app.config import Config
|
||||
from app.jobs import stages
|
||||
from app.models import (
|
||||
LANGUAGE_LEVELS, MUST_VERDICTS, Agent, CvLanguage, _language_name, cv_languages, must_lines,
|
||||
)
|
||||
from app.models import LANGUAGE_LEVELS, Agent, CvLanguage, _language_name, cv_languages
|
||||
from app.storage import Store
|
||||
|
||||
#: How much of a posting goes in one item: summarise's 8000, since the
|
||||
@@ -67,7 +61,8 @@ EXCERPT = 8000
|
||||
#: career rubric reading both.
|
||||
#: 4: the three numbers 0 to 10 rather than 0 to 100.
|
||||
#: 5: the person's languages, read into skills.
|
||||
FORMAT = 5
|
||||
#: 6: no must-haves: the profile is the CV, languages, likes and dislikes.
|
||||
FORMAT = 6
|
||||
|
||||
#: How many strengths and gaps are kept, and how long each may be.
|
||||
MOST, LONGEST = 3, 300
|
||||
@@ -76,9 +71,8 @@ SYSTEM = """You judge job postings for one person: how well each fits their CV a
|
||||
|
||||
Below the rules is the person: their CV, the languages they speak and how
|
||||
well, what they want, what they like and what they do not like (the work,
|
||||
the workplace, situations), and their must-haves and deal-breakers when they
|
||||
gave any. Each item is one posting with a key, its title, company, place
|
||||
and text. Answer one judgement per item.
|
||||
the workplace, situations). Each item is one posting with a key, its title,
|
||||
company, place and text. Answer one judgement per item.
|
||||
|
||||
Score three dimensions, each a whole number from 0 to 10:
|
||||
- skills: 8-10 the core requirements are the person's primary skills; 6-7
|
||||
@@ -99,16 +93,6 @@ Score three dimensions, each a whole number from 0 to 10:
|
||||
whether the tasks and the setting would energise them, not only whether
|
||||
they could do them.
|
||||
|
||||
Their must-haves and deal-breakers are numbered M1, M2 and so on. Give a
|
||||
verdict on every one of them, in `musts`, for each item:
|
||||
- "met": the posting text says it is met.
|
||||
- "broken": only when the posting text clearly contradicts it.
|
||||
- "unclear": the text does not say. Never infer from silence: a posting that
|
||||
is silent on a must-have is "unclear", not "broken".
|
||||
Judge a must-have by its own words, not by how well the role fits otherwise.
|
||||
Answer musts as [] when there are none. The verdicts do not change the three
|
||||
scores, which follow their rubrics; name a broken must-have as a gap.
|
||||
|
||||
Then 1 to 3 strengths and 1 to 3 gaps, each one short sentence grounded in
|
||||
the posting text. State the gaps honestly: a prestigious role that fits
|
||||
poorly scores low.
|
||||
@@ -132,21 +116,8 @@ SCHEMA: dict[str, Any] = {
|
||||
"career": {"type": "integer"},
|
||||
"strengths": {"type": "array", "items": {"type": "string"}},
|
||||
"gaps": {"type": "array", "items": {"type": "string"}},
|
||||
"musts": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {"type": "string"},
|
||||
"verdict": {"type": "string", "enum": list(MUST_VERDICTS)},
|
||||
},
|
||||
"required": ["id", "verdict"],
|
||||
"additionalProperties": False,
|
||||
},
|
||||
},
|
||||
},
|
||||
"required": ["key", "skills", "experience", "career", "strengths", "gaps",
|
||||
"musts"],
|
||||
"required": ["key", "skills", "experience", "career", "strengths", "gaps"],
|
||||
"additionalProperties": False,
|
||||
},
|
||||
},
|
||||
@@ -187,11 +158,11 @@ def _text(row: Any) -> str:
|
||||
|
||||
def input_key(agent: Agent, text: str) -> str:
|
||||
"""A hash of everything a judgement reads: the CV, the prompts, the
|
||||
languages, the like, avoid and must texts, and the role's text as sent. A judgement stored
|
||||
under another key is read again."""
|
||||
languages, the like and avoid texts, and the role's text as sent. A judgement
|
||||
stored under another key is read again."""
|
||||
blob = json.dumps([FORMAT, agent.cv_text, [[p.name, p.text] for p in agent.prompts],
|
||||
[[l.language, l.level] for l in agent.cv_languages],
|
||||
agent.like_text, agent.avoid_text, agent.must_text, text], ensure_ascii=False)
|
||||
agent.like_text, agent.avoid_text, text], ensure_ascii=False)
|
||||
return hashlib.sha1(blob.encode()).hexdigest()[:16]
|
||||
|
||||
|
||||
@@ -250,9 +221,6 @@ def system(agent: Agent) -> str:
|
||||
if agent.avoid_text.strip():
|
||||
parts.append("\n<dislikes title=\"what they do not like\">\n"
|
||||
f"{agent.avoid_text.strip()}\n</dislikes>")
|
||||
if musts := must_lines(agent.must_text):
|
||||
lines = "\n".join(f"M{n}: {line}" for n, line in enumerate(musts, start=1))
|
||||
parts.append(f"\n<must title=\"must-haves and deal-breakers\">\n{lines}\n</must>")
|
||||
return "\n".join(parts)
|
||||
|
||||
|
||||
@@ -300,25 +268,6 @@ def _lines(value: Any) -> list[str]:
|
||||
return [line for line in found if line][:MOST]
|
||||
|
||||
|
||||
def _musts(agent: Agent | None, value: Any) -> list[dict[str, str]]:
|
||||
"""The verdicts on the agent's must-haves as they are stored: one
|
||||
`{id, text, verdict}` per line of its must text, in order. A must-have
|
||||
the model left out, or gave a verdict outside "met", "broken", "unclear",
|
||||
is "unclear": nothing is broken by silence. An id that is not one of the
|
||||
agent's is ignored, the first answer for an id counts."""
|
||||
said: dict[str, str] = {}
|
||||
for one in value if isinstance(value, list) else []:
|
||||
if isinstance(one, dict):
|
||||
said.setdefault(str(one.get("id") or "").strip().upper(),
|
||||
str(one.get("verdict") or "").strip().lower())
|
||||
found = []
|
||||
for n, line in enumerate(must_lines(agent.must_text if agent else ""), start=1):
|
||||
verdict = said.get(f"M{n}", "")
|
||||
found.append({"id": f"M{n}", "text": line,
|
||||
"verdict": verdict if verdict in MUST_VERDICTS else "unclear"})
|
||||
return found
|
||||
|
||||
|
||||
def apply_batch(store: Store, answer: dict[str, Any],
|
||||
batch: dict[str, Any] | None = None,
|
||||
config: Config | None = None) -> JudgeResult:
|
||||
@@ -327,7 +276,6 @@ def apply_batch(store: Store, answer: dict[str, Any],
|
||||
all three numbers; the pair stays waiting."""
|
||||
keys: dict[str, str] = dict((batch or {}).get("keys") or {})
|
||||
stats = JudgeResult()
|
||||
agents: dict[int, Agent | None] = {}
|
||||
for one in answer.get("judgements") or []:
|
||||
key = str(one.get("key") or "")
|
||||
pair = pair_of(key)
|
||||
@@ -336,11 +284,8 @@ def apply_batch(store: Store, answer: dict[str, Any],
|
||||
stats.rejected.append(key or "?")
|
||||
continue
|
||||
skills, experience, career = (int(m) for m in marks if m is not None)
|
||||
if pair[0] not in agents:
|
||||
agents[pair[0]] = store.agent(pair[0])
|
||||
if not store.set_judgement(pair[0], pair[1], keys.pop(key), skills, experience, career,
|
||||
_lines(one.get("strengths")), _lines(one.get("gaps")),
|
||||
_musts(agents[pair[0]], one.get("musts"))):
|
||||
_lines(one.get("strengths")), _lines(one.get("gaps"))):
|
||||
stats.rejected.append(key)
|
||||
continue
|
||||
stats.judged += 1
|
||||
|
||||
+9
-62
@@ -1008,79 +1008,30 @@ def language_flag(required: list[RoleLanguage],
|
||||
return "", ""
|
||||
|
||||
|
||||
#: What career counts as at most, on the judge's 0 to 10, when a posting
|
||||
#: breaks one of the agent's must-haves: the foot of the rubric's 4-5 band,
|
||||
#: a decent job that does not build toward the person's goals. The model
|
||||
#: reports whether each must-have is met; this cap is applied in code, when a
|
||||
#: role is served (`cv_score`, `Store.judgement`, `store._cv_sql`).
|
||||
BROKEN_CAP = 4
|
||||
|
||||
#: A must-have's verdict, as the judge answers it.
|
||||
MUST_VERDICTS = ("met", "broken", "unclear")
|
||||
|
||||
_BULLET = re.compile(r"^\s*(?:[-*\u2022]+|\(?\d+[.)])\s+")
|
||||
|
||||
|
||||
def must_lines(text: str) -> list[str]:
|
||||
"""The agent's must-haves text read as one must-have per line: a leading
|
||||
bullet (`-`, `*`, `•`) or number (`1.`, `2)`) is dropped, so are empty
|
||||
lines."""
|
||||
found = []
|
||||
for line in text.splitlines():
|
||||
line = " ".join(_BULLET.sub("", line, count=1).split())
|
||||
if line:
|
||||
found.append(line)
|
||||
return found
|
||||
|
||||
|
||||
def capped_career(career: int, broken: int = 0) -> int:
|
||||
"""`career` as it counts: at most `BROKEN_CAP` when any must-have is
|
||||
broken."""
|
||||
return min(career, BROKEN_CAP) if broken else career
|
||||
|
||||
|
||||
def cv_score(skills: int, experience: int, career: int,
|
||||
weights: Weights | None = None, broken: int = 0) -> float | None:
|
||||
weights: Weights | None = None) -> float | None:
|
||||
"""The one number of a CV match, 0 to 100 for sorting and display: the
|
||||
judge's three numbers, each 0 to 10, averaged by the agent's
|
||||
`cv_skills`, `cv_experience` and `cv_career` weights (30, 25 and 30 by
|
||||
default), career as `capped_career` has it, times 10. None when all
|
||||
three weights are 0."""
|
||||
default), times 10. None when all three weights are 0."""
|
||||
w = weights or Weights()
|
||||
total = w.cv_skills + w.cv_experience + w.cv_career
|
||||
if not total:
|
||||
return None
|
||||
career = capped_career(career, broken)
|
||||
return round(10 * (w.cv_skills * skills + w.cv_experience * experience
|
||||
+ w.cv_career * career) / total, 1)
|
||||
|
||||
|
||||
class Must(Model):
|
||||
"""One must-have of an agent as the judge read it against a role: its
|
||||
`id` (`M1`, by line), the line's `text` and the `verdict`."""
|
||||
|
||||
id: str
|
||||
text: str = ""
|
||||
verdict: Literal["met", "broken", "unclear"] = "unclear"
|
||||
|
||||
|
||||
class Judgement(Model):
|
||||
"""What `judge` read of one role for one agent (`role_judgements`): the
|
||||
three dimensions 0 to 10 as the model gave them, `cv_score`
|
||||
(`cv_score`, 0 to 100) and 1 to 3 strengths and gaps grounded in the
|
||||
posting.
|
||||
`musts` is the verdict on each must-have and `broken` how many are
|
||||
broken; any makes `career_capped` the lower of `career` and
|
||||
`BROKEN_CAP`. `cv_score` and `career_capped` are not read from the
|
||||
table: `Store.judgement` sets them from the agent's weights; `cv_score`
|
||||
is None when all three are 0."""
|
||||
posting. `cv_score` is not read from the table: `Store.judgement` sets
|
||||
it from the agent's weights; it is None when all three are 0."""
|
||||
|
||||
skills: int
|
||||
experience: int
|
||||
career: int
|
||||
career_capped: int | None = None
|
||||
broken: int = 0
|
||||
musts: Annotated[list[Must], BeforeValidator(lambda v: _json(v, "[]"))] = []
|
||||
cv_score: float | None = None
|
||||
strengths: JsonStrings = []
|
||||
gaps: JsonStrings = []
|
||||
@@ -1574,14 +1525,11 @@ class Agent(Model):
|
||||
are the union over the enabled agents, and an agent with none means no
|
||||
board is narrowed by words. They decide what is fetched, not what ranks.
|
||||
|
||||
`cv_text`, `cv_languages`, `like_text`, `avoid_text` and `must_text` are
|
||||
what `judge` reads a role against: the CV, the languages it states with
|
||||
a level, what the person likes and does not like (the work, the
|
||||
workplace, situations; both feed the career score), and their
|
||||
must-haves and deal-breakers (set through the API only, not on the
|
||||
form; soft, read by the model only; a hard rule is a gate). An agent without
|
||||
a CV is not judged, and one without languages flags none
|
||||
(`language_flag`)."""
|
||||
`cv_text`, `cv_languages`, `like_text` and `avoid_text` are what `judge`
|
||||
reads a role against: the CV, the languages it states with a level, and
|
||||
what the person likes and does not like (the work, the workplace,
|
||||
situations; both feed the career score). An agent without a CV is not
|
||||
judged, and one without languages flags none (`language_flag`)."""
|
||||
|
||||
id: int
|
||||
name: str
|
||||
@@ -1594,7 +1542,6 @@ class Agent(Model):
|
||||
cv_languages: CvLanguages = []
|
||||
like_text: str = ""
|
||||
avoid_text: str = ""
|
||||
must_text: str = ""
|
||||
enabled: bool = True
|
||||
created_at: str
|
||||
|
||||
|
||||
@@ -30,10 +30,7 @@
|
||||
* text (typed, or read from a .md/.txt file by the browser), the languages it
|
||||
* states as rows of a code and a level, and the two soft texts, what the
|
||||
* person likes and what they do not like (the work, the workplace,
|
||||
* situations), which the judge reads for the career score. The must-have text
|
||||
* is no longer on the form: a save leaves `must_text` out, so the stored one
|
||||
* is kept (it is set through the API, and still caps career at 4 in code
|
||||
* when the judge reports one broken).
|
||||
* situations), which the judge reads for the career score.
|
||||
* Every save sends the CV, languages and the two texts, and the card's switch
|
||||
* re-posts the row as the server gave it, so neither drops them.
|
||||
*
|
||||
|
||||
@@ -978,14 +978,6 @@ body[data-reader="open"] .company-strip { display: none; }
|
||||
.reader-cv .cv-total { margin: 0 0 .45rem; font-variant-numeric: tabular-nums; }
|
||||
.reader-cv .cv-total b { font-size: 1.25rem; }
|
||||
.reader-cv .cv-total span { display: inline-block; margin-left: .4rem; color: var(--dim); font-size: .88rem; }
|
||||
/* The must-haves, one line each with its verdict's mark. */
|
||||
.cv-musts { list-style: none; margin: 0 0 .55rem; padding: 0; font-size: .92rem; line-height: 1.4; }
|
||||
.cv-musts li { display: flex; gap: .45rem; }
|
||||
.cv-musts li + li { margin-top: .15rem; }
|
||||
.cv-musts .mark { flex: none; width: 1rem; text-align: center; font-weight: 700; }
|
||||
.cv-musts .must-met .mark { color: var(--good); }
|
||||
.cv-musts .must-broken .mark { color: var(--error); }
|
||||
.cv-musts .must-unclear .mark { color: var(--faint); }
|
||||
.cv-lists { display: grid; grid-template-columns: 1fr 1fr; gap: .5rem 1.2rem; }
|
||||
.cv-lists ul { margin: 0; padding-left: 1.1rem; font-size: .92rem; line-height: 1.45; }
|
||||
.cv-lists li + li { margin-top: .2rem; }
|
||||
|
||||
+4
-18
@@ -1744,34 +1744,20 @@
|
||||
try { return languageNames?.of(code) || code; } catch (err) { return code; }
|
||||
}
|
||||
|
||||
const MUST_MARKS = { met: ["✓", "met"], broken: ["✗", "broken"], unclear: ["?", "unclear"] };
|
||||
|
||||
/* The agent's `judge` reading against its CV: the total and its three
|
||||
numbers, each of 10, career as the server counted it (capped at 4 when a must-have
|
||||
is broken, with what the model said), the must-haves with a verdict
|
||||
each, then the strengths and gaps it named. A box as the summary is,
|
||||
since it is the same kind of thing: a model's reading, not the posting. */
|
||||
numbers, each of 10, then the strengths and gaps it named. A box as the
|
||||
summary is, since it is the same kind of thing: a model's reading, not
|
||||
the posting. */
|
||||
function cvMatch(r) {
|
||||
const j = r.judgement;
|
||||
if (!j) return "";
|
||||
const list = (items, none) => (items?.length
|
||||
? `<ul>${items.map((x) => `<li>${esc(x)}</li>`).join("")}</ul>`
|
||||
: `<p class="muted small">${none}</p>`);
|
||||
const counted = j.career_capped ?? j.career;
|
||||
const career = counted < j.career
|
||||
? `career ${counted}/10 (capped: breaks a must-have; model said ${j.career}/10)`
|
||||
: `career ${j.career}/10`;
|
||||
const musts = Array.isArray(j.musts) && j.musts.length
|
||||
? `<ul class="cv-musts">${j.musts.map((m) => {
|
||||
const [mark, word] = MUST_MARKS[m.verdict] || MUST_MARKS.unclear;
|
||||
return `<li class="must-${word}"><span class="mark" role="img"
|
||||
aria-label="${word}" title="${word}">${mark}</span><span>${esc(m.text)}</span></li>`;
|
||||
}).join("")}</ul>` : "";
|
||||
return `<section class="reader-summary reader-cv">
|
||||
<h2 class="reader-label">CV match</h2>
|
||||
<p class="cv-total"><b>${Math.round(j.cv_score)}</b> of 100
|
||||
<span>skills ${j.skills}/10 · experience ${j.experience}/10 · ${career}</span></p>
|
||||
${musts}
|
||||
<span>skills ${j.skills}/10 · experience ${j.experience}/10 · career ${j.career}/10</span></p>
|
||||
<div class="cv-lists">
|
||||
<div><h3 class="reader-label">Strengths</h3>${list(j.strengths, "None named.")}</div>
|
||||
<div><h3 class="reader-label">Gaps</h3>${list(j.gaps, "None named.")}</div>
|
||||
|
||||
+28
-16
@@ -328,9 +328,8 @@ END;
|
||||
-- as JSON: a key it lacks means the `Limits` default. fetch_terms is a JSON
|
||||
-- list of words that narrow what big boards send (app/jobs/reach.py); empty
|
||||
-- means no narrowing. cv_text, cv_languages (a JSON list of {language,
|
||||
-- level}), like_text (what they like: the work, the workplace, situations),
|
||||
-- avoid_text (what they do not like) and must_text (must-haves and
|
||||
-- deal-breakers, set through the API only) are what judge reads a role
|
||||
-- level}), like_text (what they like: the work, the workplace, situations)
|
||||
-- and avoid_text (what they do not like) are what judge reads a role
|
||||
-- against; an agent with no CV is not judged.
|
||||
CREATE TABLE IF NOT EXISTS agents (
|
||||
id INTEGER PRIMARY KEY,
|
||||
@@ -344,7 +343,6 @@ CREATE TABLE IF NOT EXISTS agents (
|
||||
cv_text TEXT NOT NULL DEFAULT '',
|
||||
cv_languages TEXT NOT NULL DEFAULT '[]',
|
||||
avoid_text TEXT NOT NULL DEFAULT '',
|
||||
must_text TEXT NOT NULL DEFAULT '',
|
||||
like_text TEXT NOT NULL DEFAULT ''
|
||||
);
|
||||
|
||||
@@ -435,11 +433,8 @@ CREATE TABLE IF NOT EXISTS agent_cv_vectors (
|
||||
-- 100 until migration 33), cv_score their weighted total times 10 at the
|
||||
-- default weights (not read: app.models.cv_score is worked out when a role
|
||||
-- is served), strengths and gaps JSON lists. input_key
|
||||
-- is a hash of the CV, prompts, avoid text and the role's text it read: a
|
||||
-- different one is read again. musts is a JSON list of {id, text, verdict},
|
||||
-- the model's verdict on each of the agent's must-haves (one per line of its
|
||||
-- must text), broken how many are "broken": career counts as at most 4 then
|
||||
-- (app.models.BROKEN_CAP), applied when the role is served. tries counts
|
||||
-- is a hash of the CV, prompts, languages, like and avoid texts and the
|
||||
-- role's text it read: a different one is read again. tries counts
|
||||
-- replies that left the role without one since; at 3 it is given up until the agent is saved again. A
|
||||
-- row with judged_at NULL holds only tries.
|
||||
CREATE TABLE IF NOT EXISTS role_judgements (
|
||||
@@ -451,8 +446,6 @@ CREATE TABLE IF NOT EXISTS role_judgements (
|
||||
cv_score REAL,
|
||||
strengths TEXT NOT NULL DEFAULT '[]',
|
||||
gaps TEXT NOT NULL DEFAULT '[]',
|
||||
musts TEXT NOT NULL DEFAULT '[]',
|
||||
broken INTEGER NOT NULL DEFAULT 0,
|
||||
input_key TEXT NOT NULL DEFAULT '',
|
||||
tries INTEGER NOT NULL DEFAULT 0,
|
||||
judged_at TEXT,
|
||||
@@ -763,6 +756,10 @@ UPDATE roles SET seniority = COALESCE(NULLIF(seniority_model, ''),
|
||||
# A Python step: JSON limits, and a count for the log.
|
||||
(33, "the judge on 0 to 10: every judgement cleared to be made again, and summarise_top "
|
||||
"50 becomes 30", lambda conn: _judge_out_of_ten(conn)),
|
||||
# A Python step: it drops the columns only where they are there. The
|
||||
# judge reads every role again (judge.FORMAT).
|
||||
(34, "agents.must_text, role_judgements.musts and broken dropped: the profile is the "
|
||||
"CV, languages, likes and dislikes", lambda conn: _drop_musts(conn)),
|
||||
)
|
||||
|
||||
#: What a file created from `SCHEMA` today is already at.
|
||||
@@ -1203,12 +1200,14 @@ def _judge_out_of_ten(conn: sqlite3.Connection) -> None:
|
||||
old number is shown on the new scale. The rows stay, as rows of no
|
||||
judgement, and the judge reads every pair again. An agent whose
|
||||
`summarise_top` is 50, migration 32's default, takes 30, the new one.
|
||||
Runs twice without harm."""
|
||||
Runs twice without harm, also after migration 34 dropped the verdicts."""
|
||||
columns = {r[1] for r in conn.execute("PRAGMA table_info(role_judgements)")}
|
||||
verdicts = ", musts = '[]', broken = 0" if {"musts", "broken"} <= columns else ""
|
||||
cleared = conn.execute(
|
||||
"""UPDATE role_judgements
|
||||
SET skills = NULL, experience = NULL, career = NULL, cv_score = NULL,
|
||||
strengths = '[]', gaps = '[]', musts = '[]', broken = 0,
|
||||
input_key = '', tries = 0, judged_at = NULL""").rowcount
|
||||
f"""UPDATE role_judgements
|
||||
SET skills = NULL, experience = NULL, career = NULL, cv_score = NULL,
|
||||
strengths = '[]', gaps = '[]'{verdicts},
|
||||
input_key = '', tries = 0, judged_at = NULL""").rowcount
|
||||
lowered = conn.execute(
|
||||
"""UPDATE agents SET limits = json_set(limits, '$.summarise_top', 30)
|
||||
WHERE json_valid(limits) AND json_type(limits) = 'object'
|
||||
@@ -1217,6 +1216,19 @@ def _judge_out_of_ten(conn: sqlite3.Connection) -> None:
|
||||
"summarise_top 50 set to 30", cleared, lowered)
|
||||
|
||||
|
||||
def _drop_musts(conn: sqlite3.Connection) -> None:
|
||||
"""Migration 34's step: the must-haves are gone, the agent's text
|
||||
(`agents.must_text`) and the judge's verdicts on it
|
||||
(`role_judgements.musts`, `broken`), and with them the cap on career.
|
||||
Runs twice without harm."""
|
||||
for table, columns in (("agents", ("must_text",)),
|
||||
("role_judgements", ("musts", "broken"))):
|
||||
present = {r[1] for r in conn.execute(f"PRAGMA table_info({table})")}
|
||||
for column in columns:
|
||||
if column in present:
|
||||
conn.execute(f"ALTER TABLE {table} DROP COLUMN {column}")
|
||||
|
||||
|
||||
def _add_all_roles(conn: sqlite3.Connection) -> None:
|
||||
"""Migration 21's step. The column; the tag for every company that is a
|
||||
favourite of any agent, since favourite no longer widens what a pull
|
||||
|
||||
+20
-35
@@ -11,7 +11,7 @@ from __future__ import annotations
|
||||
import json
|
||||
import sqlite3
|
||||
from collections import Counter
|
||||
from collections.abc import Callable, Iterable, Iterator, Mapping, MutableMapping, Sequence
|
||||
from collections.abc import Callable, Iterable, Iterator, MutableMapping, Sequence
|
||||
from contextlib import closing, contextmanager
|
||||
from datetime import UTC, datetime, timedelta
|
||||
from pathlib import Path
|
||||
@@ -26,7 +26,7 @@ from app.models import (
|
||||
AFFINITY, HAND_REASONS, LEVELS, STATUSES, Agent, Application,
|
||||
ApplicationEvent, Candidate, Company, CvLanguage, Gate, Judgement, Limits, Prompt, Role,
|
||||
RoleCopy, RolePlace, RoleRow, SavedFilter, ScoredRole, cv_languages as normal_languages, cv_score,
|
||||
BROKEN_CAP, capped_career, language_flag, role_languages,
|
||||
language_flag, role_languages,
|
||||
Subscription, Weights, check_prompts, company_fold, company_key, country_of, excerpt, place_key,
|
||||
fetch_terms as normal_terms, host_word, iso_day, posted_at, posted_host, remote_of, title_key,
|
||||
)
|
||||
@@ -140,7 +140,7 @@ _VOTED_SCORE = ("MIN(1.0, s.score * CASE v.vote WHEN -1 THEN 0.5 "
|
||||
_WITH_VOTES = "LEFT JOIN role_votes v ON v.uid = roles.uid AND v.agent_id = ?"
|
||||
|
||||
#: The agent's `judge` readings beside every role, the same way: `j.skills`,
|
||||
#: `j.experience`, `j.career` and `j.broken` are NULL for a role not judged and with no
|
||||
#: `j.experience` and `j.career` are NULL for a role not judged and with no
|
||||
#: agent.
|
||||
_WITH_JUDGEMENTS = ("LEFT JOIN role_judgements j ON j.uid = roles.uid AND j.agent_id = ? "
|
||||
"AND j.judged_at IS NOT NULL")
|
||||
@@ -150,19 +150,15 @@ _WITH_JUDGEMENTS = ("LEFT JOIN role_judgements j ON j.uid = roles.uid AND j.agen
|
||||
def _cv_sql(weights: Weights | None) -> str:
|
||||
"""`cv_score` as SQL for one agent's weights, 0 to 100 from the judge's
|
||||
three numbers 0 to 10, unrounded (`app.models.cv_score` rounds it): NULL
|
||||
for a role not judged, and for all three weights 0. Career
|
||||
counts as at most `BROKEN_CAP` when the judgement holds a broken
|
||||
must-have (`j.broken`), as `app.models.capped_career` has it. The
|
||||
numbers are the model's validated, finite floats, so they are written in
|
||||
rather than bound, the select's placeholders being then no concern."""
|
||||
for a role not judged, and for all three weights 0. The weights are
|
||||
validated, finite floats, so they are written in rather than bound, the
|
||||
select's placeholders being then no concern."""
|
||||
w = weights or Weights()
|
||||
total = w.cv_skills + w.cv_experience + w.cv_career
|
||||
if not total:
|
||||
return "NULL"
|
||||
career = (f"(CASE WHEN j.broken > 0 AND j.career > {BROKEN_CAP} THEN {BROKEN_CAP} "
|
||||
"ELSE j.career END)")
|
||||
return (f"(10.0 * ({w.cv_skills!r} * j.skills + {w.cv_experience!r} * j.experience "
|
||||
f"+ {w.cv_career!r} * {career}) / {total!r})")
|
||||
f"+ {w.cv_career!r} * j.career) / {total!r})")
|
||||
|
||||
|
||||
def _by_cv(expression: str) -> str:
|
||||
@@ -2021,33 +2017,28 @@ class Store:
|
||||
|
||||
def set_judgement(self, agent_id: int, uid: str, input_key: str, skills: int,
|
||||
experience: int, career: int, strengths: Sequence[str],
|
||||
gaps: Sequence[str], musts: Sequence[Mapping[str, str]] = ()) -> bool:
|
||||
gaps: Sequence[str]) -> bool:
|
||||
"""Store `judge`'s reading of one role for one agent, replacing the
|
||||
one before: the three numbers as the model gave them, the verdict on
|
||||
each of the agent's must-haves (`musts`, `{id, text, verdict}`) and how
|
||||
many are broken, `cv_score` (`app.models.cv_score`, at the default
|
||||
weights and with the cap: the table's column is not read, see
|
||||
`judgement`) and its tries back at 0. False for an unknown role or
|
||||
agent."""
|
||||
broken = sum(1 for m in musts if m.get("verdict") == "broken")
|
||||
one before: the three numbers as the model gave them, `cv_score`
|
||||
(`app.models.cv_score`, at the default weights: the table's column is
|
||||
not read, see `judgement`) and its tries back at 0. False for an
|
||||
unknown role or agent."""
|
||||
try:
|
||||
with self.transaction() as conn:
|
||||
conn.execute(
|
||||
"""INSERT INTO role_judgements (uid, agent_id, skills, experience, career,
|
||||
cv_score, strengths, gaps, musts, broken,
|
||||
cv_score, strengths, gaps,
|
||||
input_key, tries, judged_at)
|
||||
VALUES (?,?,?,?,?,?,?,?,?,?,?,0,?)
|
||||
VALUES (?,?,?,?,?,?,?,?,?,0,?)
|
||||
ON CONFLICT(uid, agent_id) DO UPDATE SET
|
||||
skills=excluded.skills, experience=excluded.experience,
|
||||
career=excluded.career, cv_score=excluded.cv_score,
|
||||
strengths=excluded.strengths, gaps=excluded.gaps,
|
||||
musts=excluded.musts, broken=excluded.broken,
|
||||
input_key=excluded.input_key, tries=0, judged_at=excluded.judged_at""",
|
||||
(uid, agent_id, skills, experience, career,
|
||||
cv_score(skills, experience, career, broken=broken),
|
||||
cv_score(skills, experience, career),
|
||||
json.dumps(list(strengths), ensure_ascii=False),
|
||||
json.dumps(list(gaps), ensure_ascii=False),
|
||||
json.dumps([dict(m) for m in musts], ensure_ascii=False), broken,
|
||||
input_key, self.now()))
|
||||
except sqlite3.IntegrityError:
|
||||
return False
|
||||
@@ -2075,8 +2066,7 @@ class Store:
|
||||
def judgement(self, agent_id: int | None, uid: str) -> Judgement | None:
|
||||
"""The agent's judgement of one role, None when it has none, its
|
||||
`cv_score` the three numbers under the agent's weights as they are
|
||||
now, not as stored, and `career_capped` the model's career as the
|
||||
broken must-haves leave it (`BROKEN_CAP`)."""
|
||||
now, not as stored."""
|
||||
if agent_id is None:
|
||||
return None
|
||||
row = self._row("SELECT * FROM role_judgements WHERE agent_id = ? AND uid = ? "
|
||||
@@ -2085,9 +2075,8 @@ class Store:
|
||||
return None
|
||||
found = Judgement.from_row(row)
|
||||
agent = self.agent(agent_id)
|
||||
found.career_capped = capped_career(found.career, found.broken)
|
||||
found.cv_score = cv_score(found.skills, found.experience, found.career,
|
||||
agent.weights if agent else None, found.broken)
|
||||
agent.weights if agent else None)
|
||||
return found
|
||||
|
||||
def set_article_text(self, uid: str, text: str) -> Role | None:
|
||||
@@ -2209,14 +2198,13 @@ class Store:
|
||||
cv_text: str | None = None,
|
||||
cv_languages: Sequence[CvLanguage] | None = None,
|
||||
avoid_text: str | None = None,
|
||||
must_text: str | None = None,
|
||||
like_text: str | None = None) -> Agent:
|
||||
"""Create an agent, or with `agent_id` replace that one's fields and
|
||||
prompts. Without `prompts`, a non-empty `intent` is its one prompt,
|
||||
named after the agent. Without `fetch_terms` an update keeps the
|
||||
stored ones and a new agent has none, so a caller that does not know
|
||||
them (the CLI's prompt edit) loses none; `cv_text`, `cv_languages`,
|
||||
`like_text`, `avoid_text` and `must_text` are kept the same way. A prompt whose text is
|
||||
`like_text` and `avoid_text` are kept the same way. A prompt whose text is
|
||||
unchanged keeps its cached vector, whatever its name or place, so an
|
||||
edit re-embeds only the prompts it changed. A save gives every role
|
||||
`judge` gave up on for the agent its tries back, since what it is
|
||||
@@ -2237,7 +2225,6 @@ class Store:
|
||||
(limits or Limits()).model_dump_json(), int(enabled), terms,
|
||||
None if cv_text is None else cv_text.strip(), spoken,
|
||||
None if avoid_text is None else avoid_text.strip(),
|
||||
None if must_text is None else must_text.strip(),
|
||||
None if like_text is None else like_text.strip())
|
||||
try:
|
||||
with self.transaction() as conn:
|
||||
@@ -2245,10 +2232,9 @@ class Store:
|
||||
agent_id = conn.execute(
|
||||
"""INSERT INTO agents (name, gates, weights, limits, enabled,
|
||||
fetch_terms, cv_text, cv_languages, avoid_text,
|
||||
must_text, like_text, created_at)
|
||||
like_text, created_at)
|
||||
VALUES (?,?,?,?,?,COALESCE(?, '[]'),COALESCE(?, ''),
|
||||
COALESCE(?, '[]'),COALESCE(?, ''),COALESCE(?, ''),
|
||||
COALESCE(?, ''),?)""",
|
||||
COALESCE(?, '[]'),COALESCE(?, ''),COALESCE(?, ''),?)""",
|
||||
(*fields, self.now())).lastrowid
|
||||
elif not conn.execute(
|
||||
"""UPDATE agents SET name=?, gates=?, weights=?, limits=?, enabled=?,
|
||||
@@ -2256,7 +2242,6 @@ class Store:
|
||||
cv_text=COALESCE(?, cv_text),
|
||||
cv_languages=COALESCE(?, cv_languages),
|
||||
avoid_text=COALESCE(?, avoid_text),
|
||||
must_text=COALESCE(?, must_text),
|
||||
like_text=COALESCE(?, like_text)
|
||||
WHERE id=?""",
|
||||
(*fields, agent_id)).rowcount:
|
||||
|
||||
+2
-4
@@ -1251,7 +1251,7 @@ class AgentBody(BaseModel):
|
||||
it is stored as one prompt named after the agent. `fetch_terms` narrow
|
||||
what big boards send (`app/jobs/reach.py`); `[]` narrows nothing, and
|
||||
leaving the key out keeps an existing agent's. `cv_text`,
|
||||
`cv_languages`, `like_text`, `avoid_text` and `must_text` are what `judge` reads a
|
||||
`cv_languages`, `like_text` and `avoid_text` are what `judge` reads a
|
||||
role against (`app/jobs/judge.py`), kept the same way when left out or
|
||||
null."""
|
||||
|
||||
@@ -1267,7 +1267,6 @@ class AgentBody(BaseModel):
|
||||
cv_languages: CvLanguages | None = None
|
||||
like_text: str | None = None
|
||||
avoid_text: str | None = None
|
||||
must_text: str | None = None
|
||||
enabled: bool = True
|
||||
|
||||
|
||||
@@ -1307,8 +1306,7 @@ def save_agent(body: AgentBody, store: StoreDep, queue: QueueDep) -> Agent:
|
||||
body.enabled, agent_id=body.id, limits=body.limits,
|
||||
prompts=body.prompts, fetch_terms=body.fetch_terms,
|
||||
cv_text=body.cv_text, cv_languages=body.cv_languages,
|
||||
like_text=body.like_text, avoid_text=body.avoid_text,
|
||||
must_text=body.must_text)
|
||||
like_text=body.like_text, avoid_text=body.avoid_text)
|
||||
except ValueError as exc:
|
||||
raise HTTPException(409, str(exc)) from exc
|
||||
except KeyError:
|
||||
|
||||
Reference in new issue
Block a user