marek/creator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
Team3
2026-07-05 00:25:53 +02:00
parent 4105146c59
commit d25824229e
15 changed files with 392 additions and 402 deletions
Download Patch File Download Diff File Expand all files Collapse all files

139
backend/tests/test_guide_board.py
View File

@@ -30,19 +30,32 @@ def test_gate_schema():
assert [c["text"] for c in claims] == ["B"]
def test_coverage_schema():
res = gb._coverage_schema({"ziele": {"z1": True, "z2": "false"},
"luecken": [{"ziel": "z2", "fehlt": "Beweis"}],
"ballast": ["Abschweifung"]}, {"z1", "z2"})
def test_pruefer_schema():
"""Verschmolzenes Verdikt: ok-Kurzform, Claims-Normalisierung, Ziel-Vollständigkeit."""
assert gb._pruefer_schema({"ok": True}, {"z1"}) == {
"claims": [], "ziele": {}, "luecken": [], "ballast": [], "lese_probleme": []}
res = gb._pruefer_schema({"claims": [{"text": "A", "grund": "x", "urteil": "FALSCH"}],
"ziele": {"z1": True, "z2": "false"},
"luecken": [{"ziel": "z2", "fehlt": "Beweis"}],
"ballast": ["Abschweifung"],
"lese_probleme": [{"problem": "zu lang"}]}, {"z1", "z2"})
assert res["claims"] == [{"text": "A", "grund": "x", "urteil": "falsch"}]
assert res["ziele"] == {"z1": True, "z2": False}
assert res["luecken"][0]["fehlt"] == "Beweis"
assert gb._coverage_schema({"ziele": {"z1": True}}, {"z1", "z2"}) is None # z2 missing
assert res["luecken"][0]["fehlt"] == "Beweis" and res["lese_probleme"] == ["zu lang"]
assert gb._pruefer_schema({"ziele": {"z1": True}}, {"z1", "z2"}) is None # z2 fehlt
assert gb._pruefer_schema({"lese_probleme": []}, set()) is not None # leeres Verdikt ok
assert gb._pruefer_schema("quatsch", set()) is None
def test_problems_schema():
assert gb._problems_schema({"ok": True}) == []
assert gb._problems_schema({"problems": [{"section": "S", "problem": "zu lang"}]}) == ["zu lang"]
assert gb._problems_schema({"problems": []}) is None
def test_auftraege_schwelle_und_kritisch():
"""1–2 nur-unbelegt-Claims verfallen (GATE_FIX_MIN); falsch/Lücken sind kritisch."""
leer = {"claims": [], "ziele": {}, "luecken": [], "ballast": [], "lese_probleme": []}
z, k = gb._auftraege({**leer, "claims": [{"text": "c", "grund": "", "urteil": "unbelegt"}] * 2}, [])
assert z == [] and k is False
z, k = gb._auftraege({**leer, "claims": [{"text": "c", "grund": "w", "urteil": "falsch"}]}, [])
assert len(z) == 1 and k is True
z, k = gb._auftraege({**leer, "luecken": [{"ziel": "z1", "fehlt": "X"}]}, ["Länge 2000"])
assert len(z) == 2 and k is True
async def test_reset_from_stage(testdb):
@@ -50,7 +63,7 @@ async def test_reset_from_stage(testdb):
await db.upsert_guide_card(TOPIC, FMT, "a", "A")
await db.upsert_guide_card(TOPIC, FMT, "b", "B")
await db.set_guide_card(TOPIC, FMT, "a", stage="done", md="text", writer_rounds=2)
await db.set_guide_card(TOPIC, FMT, "b", stage="coverage", md="text")
await db.set_guide_card(TOPIC, FMT, "b", stage="pruefer", md="text")
await db.put_lernziel(TOPIC, "a", "z1", "Ziel")
# reset ab writer (idx 2): beide Karten zurück, md geleert, Ziele bleiben
moved = await gb.reset_from_stage(TOPIC, FMT, 2)
@@ -70,8 +83,8 @@ async def test_done_step(testdb):
assert await gb.done_step(TOPIC, FMT) == -1
await db.upsert_guide_card(TOPIC, FMT, "a", "A")
assert await gb.done_step(TOPIC, FMT) == -1 # alles in lernziele
await db.set_guide_card(TOPIC, FMT, "a", stage="coverage")
assert await gb.done_step(TOPIC, FMT) == 3 # bis fakten_gate fertig
await db.set_guide_card(TOPIC, FMT, "a", stage="pruefer")
assert await gb.done_step(TOPIC, FMT) == 2 # bis writer fertig
await db.set_guide_card(TOPIC, FMT, "a", stage="done")
assert await gb.done_step(TOPIC, FMT) == len(gb.GUIDE_STAGES)
@@ -162,8 +175,8 @@ def test_writer_template_has_examples_placeholder():
assert "VERIFIED FACTS" in text and "2000 characters" in text
async def test_fakten_gate_counts_examples_as_facts(testdb, monkeypatch, tmp_path):
"""Gate-Prompt enthält die Beispiele als verifizierte Fakten — sonst fliegen
async def test_pruefer_counts_examples_as_facts(testdb, monkeypatch, tmp_path):
"""Prüfer-Prompt enthält die Beispiele als verifizierte Fakten — sonst fliegen
gerechnete Beispielwerte als „nicht belegt" raus."""
import json as _json
import guide_board as gb
@@ -177,18 +190,19 @@ async def test_fakten_gate_counts_examples_as_facts(testdb, monkeypatch, tmp_pat
async def fake_slot(ctx, label, *, key, prompt, role, capabilities, payload, timeout, on_line=None):
captured["prompt"] = prompt
return "ok", []
return "ok", payload((0, '{"ok": true}', ""))
monkeypatch.setattr(gb, "run_single_slot", fake_slot)
monkeypatch.setattr(gb, "_card_facts", lambda e, b: "FAKT X")
monkeypatch.setattr(gb, "READABILITY_ACTIVE", False)
env = SimpleNamespace(ctx=SimpleNamespace(topic="t", provider="p", is_cancelled=lambda: False),
guide_id="g", topic="t", format="Guide", instructions="",
subs_by_title={"Gross": [{"title": "Sub Eins", "level": "beginner"}]},
spec="", slot=lambda name: tmp_path / name)
card = {"block_norm": "gross", "block": "Gross", "stage": "fakten_gate", "status": "open",
"writer_rounds": 0, "gate_info": "",
"md": "<!-- section: Gross -->\n<!-- ausführlich -->\nText."}
ok = await gb._stage_fakten_gate(env, card)
md = ("<!-- section: Gross -->\n<!-- ausführlich -->\n" + "Text im Rahmen. " * 20)
card = {"block_norm": "gross", "block": "Gross", "stage": "pruefer", "status": "open",
"writer_rounds": 0, "gate_info": "", "md": md}
ok = await gb._stage_pruefer(env, card)
assert ok is True
assert "VERIFIED WORKED EXAMPLES" in captured["prompt"] and "P1" in captured["prompt"]
@@ -229,7 +243,7 @@ async def test_writer_splits_oversized_first_draft(testdb, monkeypatch, tmp_path
from textkit import _parse_fragment
secs = _parse_fragment(card["md"])
assert len(secs) == 1 and [s["title"] for s in secs[0]["subs"]] == ["Sub 1", "Sub 2"]
assert card["stage"] == "fakten_gate"
assert card["stage"] == "pruefer"
async def test_lernziele_retry_bei_leerer_liste(testdb, tmp_path, monkeypatch):
@@ -268,8 +282,8 @@ async def test_lernziele_zweimal_leer_laeuft_weiter(testdb, tmp_path, monkeypatc
assert not await db.list_lernziele(TOPIC, "alpha")
async def test_lese_check_text_sink(testdb, tmp_path, monkeypatch):
"""Lese-Check antwortet als Text, Engine-Sink persistiert; capabilities none."""
async def test_pruefer_text_sink_ohne_befund_done(testdb, tmp_path, monkeypatch):
"""Prüfer antwortet als Text (Engine-Sink, capabilities none); ohne Befund → done."""
db = testdb
await db.upsert_guide_card(TOPIC, FMT, "alpha", "Alpha")
env = gb._Env(None, "g-l", TOPIC, FMT, "", tmp_path / "Guide.json", {"Alpha": []}, {}, "(q)", "spec")
@@ -284,7 +298,7 @@ async def test_lese_check_text_sink(testdb, tmp_path, monkeypatch):
monkeypatch.setattr(gb, "run_single_slot", fake_slot)
monkeypatch.setattr(gb, "READABILITY_ACTIVE", False)
assert await gb._stage_lesbarkeit(env, card)
assert await gb._stage_pruefer(env, card)
assert seen["caps"] == "none"
assert (await db.list_guide_cards(TOPIC, FMT))[0]["stage"] == "done"
@@ -307,24 +321,22 @@ async def test_writer_prompt_traegt_budget(testdb, tmp_path, monkeypatch):
assert str(gb._writer_budget(2)) in seen["prompt"] # 800 + 2×400
async def test_fakten_gate_schwelle(testdb, tmp_path, monkeypatch):
"""1–2 Claims → kein Fix-Rewrite (nur Log); ab GATE_FIX_MIN läuft der Fix."""
async def test_pruefer_claims_schwelle(testdb, tmp_path, monkeypatch):
"""1–2 nur-unbelegt-Claims → kein Fix (Karte direkt done); die Schwelle lebt in _auftraege."""
db = testdb
await db.upsert_guide_card(TOPIC, FMT, "alpha", "Alpha")
env = gb._Env(None, "g-g", TOPIC, FMT, "", tmp_path / "Guide.json", {"Alpha": []}, {}, "(q)", "spec")
md = "<!-- section: Alpha -->\n<!-- ausführlich -->\nText."
md = "<!-- section: Alpha -->\n<!-- ausführlich -->\n" + "Text im Rahmen. " * 20
card = {"block_norm": "alpha", "block": "Alpha", "writer_rounds": 0, "md": md}
keys = []
async def fake_slot(ctx, label, *, key, prompt, role, capabilities, payload, timeout):
keys.append(key)
if "-gate-" in key:
return gb.OK, [{"text": "c1", "grund": ""}, {"text": "c2", "grund": ""}]
raise AssertionError("Fix darf unter der Schwelle nicht laufen")
antwort = '{"claims": [{"text": "c1", "grund": ""}, {"text": "c2", "grund": ""}]}'
return gb.OK, payload((0, antwort, ""))
monkeypatch.setattr(gb, "run_single_slot", fake_slot)
assert await gb._stage_fakten_gate(env, card)
assert all("-gate-" in k for k in keys)
monkeypatch.setattr(gb, "READABILITY_ACTIVE", False)
assert await gb._stage_pruefer(env, card)
assert (await db.list_guide_cards(TOPIC, FMT))[0]["stage"] == "done"
async def test_load_subblocks_defaultet_levellose(testdb):
@@ -340,30 +352,46 @@ async def test_load_subblocks_defaultet_levellose(testdb):
assert by_title == {"Mit Level": "beginner", "Ohne Level": "advanced"}
async def test_fakten_gate_falsch_claim_erzwingt_fix(testdb, tmp_path, monkeypatch):
"""Ein einzelner FALSCH-Claim läuft in den Fix, auch unter GATE_FIX_MIN —
ein durchgerutschter kostete den Guide 1.5 QA-Punkte."""
async def test_falsch_claim_erzwingt_fix_und_repruefer(testdb, tmp_path, monkeypatch):
"""Ein einzelner FALSCH-Claim läuft in den Fix, auch unter GATE_FIX_MIN; nach
angewandtem Fix läuft GENAU EIN Re-Prüfer-Pass (der alte Lese-Fix blieb ungeprüft)."""
db = testdb
await db.upsert_guide_card(TOPIC, FMT, "alpha", "Alpha")
env = gb._Env(None, "g-gf", TOPIC, FMT, "", tmp_path / "Guide.json", {"Alpha": []}, {}, "(q)", "spec")
md = "<!-- section: Alpha -->\n<!-- ausführlich -->\nText."
card = {"block_norm": "alpha", "block": "Alpha", "writer_rounds": 0, "md": md}
md = "<!-- section: Alpha -->\n<!-- ausführlich -->\n" + "Text im Rahmen. " * 20
card = {"block_norm": "alpha", "block": "Alpha", "writer_rounds": 0, "md": md, "gate_info": ""}
keys = []
async def fake_slot(ctx, label, *, key, prompt, role, capabilities, payload, timeout):
keys.append(key)
if "-gate-" in key:
return gb.OK, [{"text": "c1", "grund": "widerspricht", "urteil": "falsch"}]
return gb.FAILED, None # Fix-Agent liefert nichts — Text bleibt, aber der Call MUSS kommen
if "-pruef-" in key and key.endswith("-re"):
return gb.OK, payload((0, '{"ok": true}', ""))
if "-pruef-" in key:
return gb.OK, payload((0, '{"claims": [{"text": "c1", "grund": "widerspricht", "urteil": "falsch"}]}', ""))
if "-gfix-" in key: # Fix liefert eine valide Section über die Slot-Datei
import re as _re
m = _re.search(r"(/\S+\.md)", prompt)
with open(m.group(1), "w", encoding="utf-8") as f:
f.write(md.replace("Text im Rahmen.", "Korrigiert."))
return gb.OK, payload(None)
raise AssertionError(key)
monkeypatch.setattr(gb, "run_single_slot", fake_slot)
assert await gb._stage_fakten_gate(env, card)
assert any("-gatefix-" in k for k in keys)
monkeypatch.setattr(gb, "READABILITY_ACTIVE", False)
assert await gb._stage_pruefer(env, card)
karte = (await db.list_guide_cards(TOPIC, FMT))[0]
assert karte["stage"] == "fix" and karte["gate_info"].startswith("KRITISCH")
card.update(stage="fix", gate_info=karte["gate_info"])
assert await gb._stage_fix(env, card)
assert any("-gfix-" in k for k in keys)
assert any(k.endswith("-re") for k in keys) # Re-Prüfer lief
karte = (await db.list_guide_cards(TOPIC, FMT))[0]
assert karte["stage"] == "done" and "Korrigiert." in karte["md"]
async def test_laengen_trigger_startet_lesefix(testdb, tmp_path, monkeypatch):
"""Ausführlich-Teil über der Obergrenze → deterministisches Längen-Problem
mit hartem Zeichenziel landet im Lese-Fix-Auftrag."""
async def test_laengen_trigger_startet_fix(testdb, tmp_path, monkeypatch):
"""Ausführlich-Teil über der Obergrenze → deterministisches Längen-Problem mit hartem
Zeichenziel landet als Auftrag in der Fix-Stage (unkritisch → kein Re-Prüfer)."""
db = testdb
await db.upsert_guide_card(TOPIC, FMT, "alpha", "Alpha")
env = gb._Env(None, "g-lz", TOPIC, FMT, "", tmp_path / "Guide.json",
@@ -371,16 +399,21 @@ async def test_laengen_trigger_startet_lesefix(testdb, tmp_path, monkeypatch):
{}, "(q)", "spec")
md = ("<!-- section: Alpha -->\n<!-- compact -->\n- x\n<!-- ausführlich -->\n"
+ "Viel zu langer Sockeltext. " * 80) # ~2160 Z./Sub > 1200×0.9
card = {"block_norm": "alpha", "block": "Alpha", "writer_rounds": 0, "md": md}
card = {"block_norm": "alpha", "block": "Alpha", "writer_rounds": 0, "md": md, "gate_info": ""}
seen = {}
async def fake_slot(ctx, label, *, key, prompt, role, capabilities, payload, timeout):
if "-lesefix-" in key:
seen["tasks"] = prompt
if "-gfix-" in key:
seen["auftraege"] = prompt
return gb.FAILED, None
return gb.OK, payload((0, '{"ok": true}', "")) # Lese-Check: keine Probleme
if key.endswith("-re"):
raise AssertionError("unkritischer Befund darf keinen Re-Prüfer starten")
return gb.OK, payload((0, '{"ok": true}', "")) # Prüfer: keine LLM-Befunde
monkeypatch.setattr(gb, "run_single_slot", fake_slot)
monkeypatch.setattr(gb, "READABILITY_ACTIVE", False)
assert await gb._stage_lesbarkeit(env, card)
assert "Länge" in seen["tasks"] and str(gb._writer_budget(1)) in seen["tasks"]
assert await gb._stage_pruefer(env, card)
assert (await db.list_guide_cards(TOPIC, FMT))[0]["stage"] == "fix"
card.update(stage="fix", gate_info=(await db.list_guide_cards(TOPIC, FMT))[0]["gate_info"])
assert await gb._stage_fix(env, card)
assert "Länge" in seen["auftraege"] and str(gb._writer_budget(1)) in seen["auftraege"]