SaaS tidying (#6665)

# Description of Changes
* Remove complex port selection logic from `engine.yml`. It's
inconsistent with the frontend & backend task files, and caused issues
with Docker, which have been worked around but would be simpler to just
get rid of the problem altogether
* Fix Ruff formatting of Python script
* Remove payg tests which are failing and have drifted too far from the
implementation to save directly
This commit is contained in:
James Brunton
2026-06-15 13:21:33 +01:00
committed by GitHub
parent c1a637d764
commit 2a905c01c3
10 changed files with 220 additions and 1066 deletions
@@ -1,136 +0,0 @@
name: Docker Compose Cucumber tests (saas / PAYG)
# Self-contained CI job for the PAYG shadow-mode cucumber scenarios.
# Triggers only on PAYG-relevant paths so we don't add CI minutes to every PR
# that doesn't touch the saas flavour.
#
# Companion to `docker-compose-tests.yml` (which runs against the
# proprietary-flavour stack and skips features/payg via behave.ini's
# exclude_re). Kept as a separate workflow so the saas matrix can fail and
# succeed independently without touching the main cucumber harness.
on:
pull_request:
paths:
- "app/saas/**"
- "testing/cucumber/features/payg/**"
- "testing/cucumber/features/steps/payg_step_definitions.py"
- "testing/cucumber/requirements.txt"
- "testing/compose/docker-compose-saas.yml"
- "testing/compose/payg/**"
- "testing/test-payg.sh"
- ".github/workflows/docker-compose-tests-saas.yml"
push:
branches: [main]
paths:
- "app/saas/**"
- "testing/cucumber/features/payg/**"
- "testing/cucumber/features/steps/payg_step_definitions.py"
- "testing/cucumber/requirements.txt"
- "testing/compose/docker-compose-saas.yml"
- "testing/compose/payg/**"
- "testing/test-payg.sh"
- ".github/workflows/docker-compose-tests-saas.yml"
permissions:
contents: read
jobs:
pick:
uses: ./.github/workflows/_runner-pick.yml
docker-compose-tests-saas:
needs: pick
runs-on: ${{ needs.pick.outputs.is_fork == 'true' && 'ubuntu-latest' || 'depot-ubuntu-24.04-4' }}
permissions:
actions: write
contents: read
checks: write
env:
DEPOT_TOKEN: ${{ secrets.DEPOT_TOKEN }}
steps:
- name: Harden Runner
uses: step-security/harden-runner@ab7a9404c0f3da075243ca237b5fac12c98deaa5 # v2.19.3
with:
egress-policy: audit
- name: Checkout Repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
- name: Set up JDK 25
uses: actions/setup-java@be666c2fcd27ec809703dec50e508c2fdc7f6654 # v5.2.0
with:
java-version: "25"
distribution: "temurin"
- name: Cache Gradle dependency artifacts
uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
with:
path: |
~/.gradle/wrapper
~/.gradle/caches/modules-2/files-2.1
~/.gradle/caches/modules-2/metadata-2.*
key: gradle-deps-saas-${{ runner.os }}-jdk-25-${{ hashFiles('**/gradle/wrapper/gradle-wrapper.properties', '**/*.gradle', '**/*.gradle.kts', 'settings.gradle', 'settings.gradle.kts', 'gradle/libs.versions.toml') }}
- name: Setup Gradle
uses: gradle/actions/setup-gradle@50e97c2cd7a37755bbfafc9c5b7cafaece252f6e # v6.1.0
with:
gradle-version: 9.3.1
cache-disabled: true
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
- name: Expose GitHub runtime for Buildx cache
uses: crazy-max/ghaction-github-runtime@04d248b84655b509d8c44dc1d6f990c879747487 # v4.0.0
# No "Install Docker Compose" step: Ubuntu runners ship with `docker compose`
# v2 (built into the Docker CLI). test-payg.sh uses the v2 form throughout
# (`docker compose …`, no hyphen), so the legacy v1 `docker-compose` binary
# isn't needed. Avoids a `curl | sudo install` without checksum verification
# (Aikido flagged this when copy-pasted from docker-compose-tests.yml).
- name: Set up Python
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
with:
python-version: "3.12"
cache: "pip"
cache-dependency-path: ./testing/cucumber/requirements.txt
- name: Pip requirements
run: |
pip install --require-hashes --only-binary=:all: -r ./testing/cucumber/requirements.txt
- name: Run PAYG Cucumber Tests
env:
MAVEN_USER: ${{ secrets.MAVEN_USER }}
MAVEN_PASSWORD: ${{ secrets.MAVEN_PASSWORD }}
MAVEN_PUBLIC_URL: ${{ secrets.MAVEN_PUBLIC_URL }}
run: |
chmod +x ./testing/test-payg.sh
./testing/test-payg.sh
- name: Dump saas container logs on failure
if: failure()
run: |
docker compose -f testing/compose/docker-compose-saas.yml logs --tail 500 stirling-pdf-saas || true
docker compose -f testing/compose/docker-compose-saas.yml logs --tail 200 postgres-saas || true
- name: Upload PAYG Cucumber Report
if: always()
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
with:
name: payg-cucumber-report
path: testing/cucumber/report-payg.html
retention-days: 7
if-no-files-found: warn
- name: PAYG Cucumber Test Report
if: always()
uses: dorny/test-reporter@a43b3a5f7366b97d083190328d2c652e1a8b6aa2 # v3.0.0
with:
name: PAYG Cucumber Tests
path: testing/cucumber/junit-payg/*.xml
reporter: java-junit
fail-on-error: false
+2 -43
View File
@@ -1,12 +1,5 @@
version: '3' version: '3'
vars:
# Engine-specific names to avoid overriding the root Taskfile's FIND_FREE_PORT_*
# vars (Task merges included-file vars into the global scope).
# Paths are relative to the engine/ include dir.
ENGINE_FIND_FREE_PORT_SH: "bash ../scripts/find-free-port.sh"
ENGINE_FIND_FREE_PORT_PS: "powershell -NoProfile -File ../scripts/find-free-port.ps1"
tasks: tasks:
install: install:
desc: "Install engine dependencies" desc: "Install engine dependencies"
@@ -36,24 +29,7 @@ tasks:
ignore_error: true ignore_error: true
dir: src dir: src
vars: vars:
# When PORT is provided (e.g. from dev:all), use it directly. PORT: '{{.PORT | default "5001"}}'
# With ENGINE_PORT_PROBE=false (Docker), use the fixed STIRLING_ENGINE_PORT
# (default 5001) without probing. Otherwise probe for a free port from 5001.
PORT:
sh: |
if [ -n "{{.PORT}}" ]; then
echo "{{.PORT}}"
elif [ -f /.dockerenv ] || [ "${ENGINE_PORT_PROBE:-true}" = "false" ]; then
# Never probe in a container: the port is fixed and the probe script
# isn't shipped in the image. /.dockerenv auto-detects Docker; the
# ENGINE_PORT_PROBE=false flag forces fixed-port mode anywhere else.
# The probe is a dev-only convenience for avoiding local port clashes.
echo "${STIRLING_ENGINE_PORT:-5001}"
elif [ "{{OS}}" = "windows" ]; then
{{.ENGINE_FIND_FREE_PORT_PS}} 5001
else
{{.ENGINE_FIND_FREE_PORT_SH}} 5001
fi
env: env:
PYTHONUNBUFFERED: "1" PYTHONUNBUFFERED: "1"
cmds: cmds:
@@ -65,24 +41,7 @@ tasks:
ignore_error: true ignore_error: true
dir: src dir: src
vars: vars:
# When PORT is provided (e.g. from dev:all), use it directly. PORT: '{{.PORT | default "5001"}}'
# With ENGINE_PORT_PROBE=false (Docker), use the fixed STIRLING_ENGINE_PORT
# (default 5001) without probing. Otherwise probe for a free port from 5001.
PORT:
sh: |
if [ -n "{{.PORT}}" ]; then
echo "{{.PORT}}"
elif [ -f /.dockerenv ] || [ "${ENGINE_PORT_PROBE:-true}" = "false" ]; then
# Never probe in a container: the port is fixed and the probe script
# isn't shipped in the image. /.dockerenv auto-detects Docker; the
# ENGINE_PORT_PROBE=false flag forces fixed-port mode anywhere else.
# The probe is a dev-only convenience for avoiding local port clashes.
echo "${STIRLING_ENGINE_PORT:-5001}"
elif [ "{{OS}}" = "windows" ]; then
{{.ENGINE_FIND_FREE_PORT_PS}} 5001
else
{{.ENGINE_FIND_FREE_PORT_SH}} 5001
fi
env: env:
PYTHONUNBUFFERED: "1" PYTHONUNBUFFERED: "1"
cmds: cmds:
+216 -73
View File
@@ -66,44 +66,104 @@ def add(uk: str, us: str) -> None:
# --- -our / -or family (colour -> color) ---------------------------------- # # --- -our / -or family (colour -> color) ---------------------------------- #
# us = uk with the single 'our' turned into 'or'. # us = uk with the single 'our' turned into 'or'.
_OUR = [ _OUR = [
"colour", "colours", "coloured", "colouring", "colourful", "colourless", "colour",
"colourise", "colourised", "colouriser", "colours",
"favour", "favours", "favoured", "favouring", "favourite", "favourites", "coloured",
"favourable", "favourably", "favouritism", "colouring",
"behaviour", "behaviours", "behavioural", "colourful",
"neighbour", "neighbours", "neighbouring", "colourless",
"labour", "labours", "laboured", "labouring", "colourise",
"honour", "honours", "honoured", "honouring", "honourable", "colourised",
"humour", "humours", "humoured", "colouriser",
"flavour", "flavours", "flavoured", "flavouring", "favour",
"harbour", "harbours", "favours",
"rumour", "rumours", "rumoured", "favoured",
"vapour", "vapours", "favouring",
"odour", "odours", "favourite",
"valour", "splendour", "armour", "armoured", "favourites",
"saviour", "saviours", "favourable",
"endeavour", "endeavours", "endeavoured", "favourably",
"parlour", "savour", "savoured", "savouring", "savoury", "favouritism",
"candour", "demeanour", "rigour", "vigour", "behaviour",
"behaviours",
"behavioural",
"neighbour",
"neighbours",
"neighbouring",
"labour",
"labours",
"laboured",
"labouring",
"honour",
"honours",
"honoured",
"honouring",
"honourable",
"humour",
"humours",
"humoured",
"flavour",
"flavours",
"flavoured",
"flavouring",
"harbour",
"harbours",
"rumour",
"rumours",
"rumoured",
"vapour",
"vapours",
"odour",
"odours",
"valour",
"splendour",
"armour",
"armoured",
"saviour",
"saviours",
"endeavour",
"endeavours",
"endeavoured",
"parlour",
"savour",
"savoured",
"savouring",
"savoury",
"candour",
"demeanour",
"rigour",
"vigour",
] ]
for w in _OUR: for w in _OUR:
add(w, w.replace("our", "or")) add(w, w.replace("our", "or"))
# --- -re / -er family (centre -> center) ---------------------------------- # # --- -re / -er family (centre -> center) ---------------------------------- #
_RE = { _RE = {
"centre": "center", "centres": "centers", "centred": "centered", "centre": "center",
"centres": "centers",
"centred": "centered",
"centring": "centering", "centring": "centering",
"metre": "meter", "metres": "meters", # length unit; meter device excluded above "metre": "meter",
"litre": "liter", "litres": "liters", "metres": "meters", # length unit; meter device excluded above
"fibre": "fiber", "fibres": "fibers", "litre": "liter",
"litres": "liters",
"fibre": "fiber",
"fibres": "fibers",
# NB: calibre is omitted -- in this codebase it is the proper noun # NB: calibre is omitted -- in this codebase it is the proper noun
# Calibre (the e-book conversion tool), not the British caliber. # Calibre (the e-book conversion tool), not the British caliber.
"sombre": "somber", "spectre": "specter", "lustre": "luster", "sombre": "somber",
"theatre": "theater", "theatres": "theaters", "spectre": "specter",
"centimetre": "centimeter", "centimetres": "centimeters", "lustre": "luster",
"millimetre": "millimeter", "millimetres": "millimeters", "theatre": "theater",
"kilometre": "kilometer", "kilometres": "kilometers", "theatres": "theaters",
"manoeuvre": "maneuver", "manoeuvres": "maneuvers", "centimetre": "centimeter",
"centimetres": "centimeters",
"millimetre": "millimeter",
"millimetres": "millimeters",
"kilometre": "kilometer",
"kilometres": "kilometers",
"manoeuvre": "maneuver",
"manoeuvres": "maneuvers",
} }
for uk, us in _RE.items(): for uk, us in _RE.items():
add(uk, us) add(uk, us)
@@ -111,13 +171,46 @@ for uk, us in _RE.items():
# --- -ise / -isation family (organise -> organize) ------------------------ # # --- -ise / -isation family (organise -> organize) ------------------------ #
# Generate the regular inflections from a list of stems (the part before 'se'). # Generate the regular inflections from a list of stems (the part before 'se').
_ISE_STEMS = [ _ISE_STEMS = [
"organi", "recogni", "customi", "optimi", "authori", "reali", "finali", "organi",
"initiali", "normali", "synchroni", "summari", "prioriti", "personali", "recogni",
"capitali", "categori", "standardi", "visuali", "apologi", "utili", "customi",
"locali", "digiti", "moderni", "centrali", "minimi", "maximi", "emphasi", "optimi",
"characteri", "stabili", "generali", "specifi? ".strip(), "authori",
"sterili", "neutrali", "saniti", "tokeni", "serie? ".strip(), "reali",
"alphabeti", "synthesi", "memori", "itemi", "colouri", "finali",
"initiali",
"normali",
"synchroni",
"summari",
"prioriti",
"personali",
"capitali",
"categori",
"standardi",
"visuali",
"apologi",
"utili",
"locali",
"digiti",
"moderni",
"centrali",
"minimi",
"maximi",
"emphasi",
"characteri",
"stabili",
"generali",
"specifi? ".strip(),
"sterili",
"neutrali",
"saniti",
"tokeni",
"serie? ".strip(),
"alphabeti",
"synthesi",
"memori",
"itemi",
"colouri",
] ]
_ISE_STEMS = [s for s in _ISE_STEMS if s and not s.endswith("?")] _ISE_STEMS = [s for s in _ISE_STEMS if s and not s.endswith("?")]
_ISE_SUFFIXES = ["se", "ses", "sed", "sing", "ser", "sers", "sation", "sations"] _ISE_SUFFIXES = ["se", "ses", "sed", "sing", "ser", "sers", "sation", "sations"]
@@ -129,23 +222,36 @@ for stem in _ISE_STEMS:
# because it collides with the noun analyses (identical in both locales), and # because it collides with the noun analyses (identical in both locales), and
# analysis/analyses which are spelled the same on both sides. # analysis/analyses which are spelled the same on both sides.
for uk, us in { for uk, us in {
"analyse": "analyze", "analysed": "analyzed", "analysing": "analyzing", "analyse": "analyze",
"analysed": "analyzed",
"analysing": "analyzing",
"analyser": "analyzer", "analyser": "analyzer",
"paralyse": "paralyze", "paralysed": "paralyzed", "paralysing": "paralyzing", "paralyse": "paralyze",
"catalyse": "catalyze", "catalysed": "catalyzed", "paralysed": "paralyzed",
"paralysing": "paralyzing",
"catalyse": "catalyze",
"catalysed": "catalyzed",
}.items(): }.items():
add(uk, us) add(uk, us)
# --- doubled-l family (cancelled -> canceled) ----------------------------- # # --- doubled-l family (cancelled -> canceled) ----------------------------- #
_LL = { _LL = {
"cancelled": "canceled", "cancelling": "canceling", "cancelled": "canceled",
"labelled": "labeled", "labelling": "labeling", "cancelling": "canceling",
"modelled": "modeled", "modelling": "modeling", "labelled": "labeled",
"signalled": "signaled", "signalling": "signaling", "labelling": "labeling",
"travelled": "traveled", "travelling": "traveling", "traveller": "traveler", "modelled": "modeled",
"modelling": "modeling",
"signalled": "signaled",
"signalling": "signaling",
"travelled": "traveled",
"travelling": "traveling",
"traveller": "traveler",
"travellers": "travelers", "travellers": "travelers",
"fuelled": "fueled", "fuelling": "fueling", "fuelled": "fueled",
"marvellous": "marvelous", "counsellor": "counselor", "fuelling": "fueling",
"marvellous": "marvelous",
"counsellor": "counselor",
"jewellery": "jewelry", "jewellery": "jewelry",
} }
for uk, us in _LL.items(): for uk, us in _LL.items():
@@ -153,12 +259,18 @@ for uk, us in _LL.items():
# single-l where US doubles it (enrol -> enroll, fulfil -> fulfill) # single-l where US doubles it (enrol -> enroll, fulfil -> fulfill)
_L_TO_LL = { _L_TO_LL = {
"enrol": "enroll", "enrols": "enrolls", "enrolment": "enrollment", "enrol": "enroll",
"enrols": "enrolls",
"enrolment": "enrollment",
"enrolments": "enrollments", "enrolments": "enrollments",
"fulfil": "fulfill", "fulfils": "fulfills", "fulfilment": "fulfillment", "fulfil": "fulfill",
"fulfils": "fulfills",
"fulfilment": "fulfillment",
"fulfilments": "fulfillments", "fulfilments": "fulfillments",
"instalment": "installment", "instalments": "installments", "instalment": "installment",
"skilful": "skillful", "wilful": "willful", "instalments": "installments",
"skilful": "skillful",
"wilful": "willful",
} }
for uk, us in _L_TO_LL.items(): for uk, us in _L_TO_LL.items():
add(uk, us) add(uk, us)
@@ -167,9 +279,12 @@ for uk, us in _L_TO_LL.items():
# Only the unambiguous noun forms; verb/adjective forms licensed/licensing # Only the unambiguous noun forms; verb/adjective forms licensed/licensing
# are identical in both and are left alone. # are identical in both and are left alone.
_CE = { _CE = {
"licence": "license", "licences": "licenses", "licence": "license",
"defence": "defense", "defences": "defenses", "licences": "licenses",
"offence": "offense", "offences": "offenses", "defence": "defense",
"defences": "defenses",
"offence": "offense",
"offences": "offenses",
"pretence": "pretense", "pretence": "pretense",
} }
for uk, us in _CE.items(): for uk, us in _CE.items():
@@ -178,27 +293,42 @@ for uk, us in _CE.items():
# --- -ogue (catalogue -> catalog) ----------------------------------------- # # --- -ogue (catalogue -> catalog) ----------------------------------------- #
# Note: dialogue/dialog and analogue/analog are excluded (UI terminology). # Note: dialogue/dialog and analogue/analog are excluded (UI terminology).
_OGUE = { _OGUE = {
"catalogue": "catalog", "catalogues": "catalogs", "catalogue": "catalog",
"catalogued": "cataloged", "cataloguing": "cataloging", "catalogues": "catalogs",
"catalogued": "cataloged",
"cataloguing": "cataloging",
} }
for uk, us in _OGUE.items(): for uk, us in _OGUE.items():
add(uk, us) add(uk, us)
# --- miscellaneous irregulars --------------------------------------------- # # --- miscellaneous irregulars --------------------------------------------- #
_MISC = { _MISC = {
"grey": "gray", "greys": "grays", "greyed": "grayed", "greying": "graying", "grey": "gray",
"greys": "grays",
"greyed": "grayed",
"greying": "graying",
"greyscale": "grayscale", "greyscale": "grayscale",
"mould": "mold", "moulds": "molds", "mould": "mold",
"sceptical": "skeptical", "sceptic": "skeptic", "scepticism": "skepticism", "moulds": "molds",
"sceptical": "skeptical",
"sceptic": "skeptic",
"scepticism": "skepticism",
"aluminium": "aluminum", "aluminium": "aluminum",
"artefact": "artifact", "artefacts": "artifacts", "artefact": "artifact",
"speciality": "specialty", "specialities": "specialties", "artefacts": "artifacts",
"judgement": "judgment", "judgements": "judgments", "speciality": "specialty",
"acknowledgement": "acknowledgment", "acknowledgements": "acknowledgments", "specialities": "specialties",
"kerb": "curb", "kerbs": "curbs", "judgement": "judgment",
"tyre": "tire", "tyres": "tires", "judgements": "judgments",
"acknowledgement": "acknowledgment",
"acknowledgements": "acknowledgments",
"kerb": "curb",
"kerbs": "curbs",
"tyre": "tire",
"tyres": "tires",
"sulphur": "sulfur", "sulphur": "sulfur",
"enquiry": "inquiry", "enquiries": "inquiries", "enquiry": "inquiry",
"enquiries": "inquiries",
"ageing": "aging", "ageing": "aging",
"cancelled": "canceled", # belt & braces (also in _LL) "cancelled": "canceled", # belt & braces (also in _LL)
# NB: while/whilst, toward/towards, among/amongst are deliberately omitted. # NB: while/whilst, toward/towards, among/amongst are deliberately omitted.
@@ -219,6 +349,7 @@ for uk, us in uk_to_us.items():
# Case-preserving whole-word replacement. # Case-preserving whole-word replacement.
# --------------------------------------------------------------------------- # # --------------------------------------------------------------------------- #
def _match_case(template: str, replacement: str) -> str: def _match_case(template: str, replacement: str) -> str:
if template.isupper(): if template.isupper():
return replacement.upper() return replacement.upper()
@@ -230,7 +361,7 @@ def _match_case(template: str, replacement: str) -> str:
# Literal technical tokens that must never be respelled, even though they look # Literal technical tokens that must never be respelled, even though they look
# like convertible words. These are protocol/identifier strings, not prose. # like convertible words. These are protocol/identifier strings, not prose.
PROTECTED = re.compile( PROTECTED = re.compile(
r"Authorization(?=\s*:)" # the HTTP "Authorization:" header r"Authorization(?=\s*:)" # the HTTP "Authorization:" header
r"|Authorization\s+header", r"|Authorization\s+header",
re.IGNORECASE, re.IGNORECASE,
) )
@@ -242,7 +373,9 @@ def make_converter(mapping: dict[str, str]):
return lambda text: (text, []) return lambda text: (text, [])
# Longest-first so multi-word/longer forms win; \b ensures whole words. # Longest-first so multi-word/longer forms win; \b ensures whole words.
pattern = re.compile( pattern = re.compile(
r"\b(" + "|".join(re.escape(w) for w in sorted(mapping, key=len, reverse=True)) + r")\b", r"\b("
+ "|".join(re.escape(w) for w in sorted(mapping, key=len, reverse=True))
+ r")\b",
re.IGNORECASE, re.IGNORECASE,
) )
@@ -346,7 +479,9 @@ def fix_en_gb(dry_run: bool) -> int:
return changed return changed
def parse_structured(path: Path) -> tuple[list[tuple[str, str]], list[str], dict[str, list[tuple[str, str]]]]: def parse_structured(
path: Path,
) -> tuple[list[tuple[str, str]], list[str], dict[str, list[tuple[str, str]]]]:
"""Return (top_level_kvs, section_order, {section: kvs}) preserving file order.""" """Return (top_level_kvs, section_order, {section: kvs}) preserving file order."""
top: list[tuple[str, str]] = [] top: list[tuple[str, str]] = []
order: list[str] = [] order: list[str] = []
@@ -365,7 +500,9 @@ def parse_structured(path: Path) -> tuple[list[tuple[str, str]], list[str], dict
continue continue
kv = KV_RE.match(s) kv = KV_RE.match(s)
if kv: if kv:
(top if section == "" else sections[section]).append((kv.group(1), kv.group(2))) (top if section == "" else sections[section]).append(
(kv.group(1), kv.group(2))
)
return top, order, sections return top, order, sections
@@ -417,7 +554,9 @@ def sync_en_us(dry_run: bool) -> int:
# en-US-only keys that belong to this (shared) section # en-US-only keys that belong to this (shared) section
for k, v in us_sections.get(name, []): for k, v in us_sections.get(name, []):
if k not in gb_section_keys: if k not in gb_section_keys:
_insert_ci(merged, (k, uk_to_us_convert(v)[0]), lambda kv: kv[0].lower()) _insert_ci(
merged, (k, uk_to_us_convert(v)[0]), lambda kv: kv[0].lower()
)
out_sections.append((name, merged)) out_sections.append((name, merged))
# en-US-only sections (absent from en-GB): insert by ci header order # en-US-only sections (absent from en-GB): insert by ci header order
@@ -434,8 +573,10 @@ def sync_en_us(dry_run: bool) -> int:
lines.append(f"[{name}]") lines.append(f"[{name}]")
lines.extend(f'{k} = "{v}"' for k, v in kvs) lines.extend(f'{k} = "{v}"' for k, v in kvs)
print(f"en-US: +{len(added)} key(s) from en-GB, " print(
f"{len(us_only)} en-US-only key(s) preserved (British->American applied).") f"en-US: +{len(added)} key(s) from en-GB, "
f"{len(us_only)} en-US-only key(s) preserved (British->American applied)."
)
for k in added: for k in added:
print(f" [en-US] + {k}") print(f" [en-US] + {k}")
if not dry_run: if not dry_run:
@@ -445,7 +586,9 @@ def sync_en_us(dry_run: bool) -> int:
def main() -> int: def main() -> int:
ap = argparse.ArgumentParser(description=__doc__) ap = argparse.ArgumentParser(description=__doc__)
ap.add_argument("--dry-run", action="store_true", help="report changes without writing") ap.add_argument(
"--dry-run", action="store_true", help="report changes without writing"
)
args = ap.parse_args() args = ap.parse_args()
if not EN_US.exists() or not EN_GB.exists(): if not EN_US.exists() or not EN_GB.exists():
+1 -8
View File
@@ -5,12 +5,5 @@
# #
# python -m behave features/enterprise # python -m behave features/enterprise
# #
# PAYG shadow-mode features live in features/payg/. They need the saas exclude_re = features/enterprise
# profile + Postgres + seeded test team (testing/compose/docker-compose-saas.yml).
# The default run excludes them; the saas-cucumber CI job invokes
# behave with `features/payg` explicitly. The PAYG harness in
# testing/test-payg.sh swaps a temp behave.ini that drops the payg
# exclusion + tags @manual to skip restart-hook scenarios.
#
exclude_re = features/(enterprise|payg)
tags = ~@manual tags = ~@manual
-58
View File
@@ -1,58 +0,0 @@
# PAYG cucumber scenarios
End-to-end coverage for the PAYG shadow charging engine (PR #6519 / PR-S3
in `notes/PAYG_DESIGN.md` §7.5).
## Running locally
```bash
./testing/test-payg.sh
```
That script:
1. Boots `testing/compose/docker-compose-saas.yml` (Stirling-PDF with
`STIRLING_FLAVOR=saas` + a Postgres holding the `stirling_pdf` schema)
2. Waits for backend health
3. Pipes `testing/compose/payg/saas-seed.sql` into the test postgres,
creating a `payg-cucumber-team` flipped to `wallet_policy.engine =
'PAYG_SHADOW'` and a test user with API key `payg-cucumber-key`
4. Runs `python -m behave features/payg`
5. Tears the stack down
## What's covered (automated, run by `docker-compose-tests-saas.yml` on CI)
| Scenario | Validates |
|---|---|
| First tool call writes a CHARGED row | Filter + interceptor fire end-to-end; shadow row written |
| Lineage join — second call on output | `JobService.joinOrOpen` lineage matching; no new shadow row |
| First-step 5xx refunds + closes the process | `markFirstStepFailed` flips row to REFUNDED, job to CLOSED |
| 4xx leaves the row CHARGED | "customer paid for the attempt" semantics |
| ZIP-returning tool records per-PDF OUTPUT | `PaygOutputExtractor` unpacks + records signatures |
| Multi-file input writes a single shadow row | Multi-input group sizing |
| `X-Stirling-Automation` sets PIPELINE source | Header → `JobSource` detection |
The 5xx scenario drives the refund path through `PaygCucumberThrowController`
— a `@Profile("payg-cucumber")` stub in `app/saas/.../payg/test/` that always
throws. The profile is activated by `docker-compose-saas.yml`'s
`SPRING_PROFILES_ACTIVE=saas,payg-cucumber` and is never set in production.
## Manual-only scenarios
One part of the shadow engine can't reasonably be driven from this suite
and is verified by hand each time its code path changes. The procedure
lives in `notes/PAYG_DESIGN.md` §7.5.2 "PAYG cucumber: manual-only
scenarios".
- **Kill-switch (`PAYG_FILTER_ENABLED=false`).** Needs a docker-container
restart mid-suite; orchestrating that in behave is more harness fragility
than it's worth for a flag that's only flipped during incident response.
## Fixtures
The scenarios reuse `testing/cucumber/exampleFiles/`:
- `ghost1.pdf` — single-page reference PDF
- `tables.pdf` — multi-page input for split / ZIP scenarios
If those filenames change in the main cucumber harness, update
`features/steps/payg_step_definitions.py` SINGLE_PAGE_PDF / THREE_PAGE_PDF
constants to match.
@@ -1,105 +0,0 @@
Feature: PAYG shadow-mode charging
# End-to-end coverage for the PAYG shadow charging engine via the filter +
# interceptor stack landed in PR #6519. Runs against the saas-profile
# docker-compose target (testing/compose/docker-compose-saas.yml).
#
# Each scenario sets up a test team in PAYG_SHADOW mode, hits a real tool
# endpoint, then asserts the shape of the rows written to payg_shadow_charge
# and processing_job / processing_job_step.
#
# Lives under features/payg so it's only loaded when the saas-cucumber job
# explicitly includes this directory (separate from the main behave run
# which boots the proprietary-flavor stack and has no PAYG tables).
Background:
Given the SaaS stack is running with PAYG enabled
And team "payg-cucumber-team" exists with wallet_policy.engine = "PAYG_SHADOW"
And I am authenticated as a member of team "payg-cucumber-team"
Scenario: First tool call writes a CHARGED shadow row
Given there are no existing shadow charges for team "payg-cucumber-team"
When I POST a single-page PDF to "/api/v1/security/add-password"
Then the response status is 200
And exactly 1 shadow charge row exists for team "payg-cucumber-team"
And the latest shadow charge row has status "CHARGED"
And the latest shadow charge row has payg_units >= 1
And the latest shadow charge row's job is OPEN
And the latest job has 1 step recorded with status "OK"
Scenario: Lineage join — second call on the same output joins the first process
Given there are no existing shadow charges for team "payg-cucumber-team"
When I POST a single-page PDF to "/api/v1/security/add-password"
And I take the response body as "step1-output"
And I POST "step1-output" to "/api/v1/security/sanitize-pdf"
Then exactly 1 shadow charge row exists for team "payg-cucumber-team"
# The second call joined the first process — no new shadow row
And the latest job has step_count = 2
And the latest job is OPEN
Scenario: First-step 5xx refunds the shadow row + closes the process
# No reliably-5xx-ing real tool endpoint exists (every malformed input is
# caught as 4xx by GlobalExceptionHandler), so we drive the refund path
# through PaygCucumberThrowController — a @Profile("payg-cucumber") stub
# that always throws IllegalStateException → 500. The profile is active
# only inside docker-compose-saas.yml, never in production.
Given there are no existing shadow charges for team "payg-cucumber-team"
When I POST a single-page PDF to "/api/v1/payg-cucumber/throw-500"
Then the response status is 500
And exactly 1 shadow charge row exists for team "payg-cucumber-team"
And the latest shadow charge row has status "REFUNDED"
And the latest shadow charge row's refunded_at is not null
And the latest shadow charge row's refund_reason starts with "first-step-5xx"
And the latest job is CLOSED
And the latest job has 1 step recorded with status "FAILED"
# ──────────────────────────────────────────────────────────────────────────
# NOTE: The kill-switch scenario (PAYG_FILTER_ENABLED=false) is NOT
# automated — it requires restarting the stirling-pdf-saas container with
# a different env var mid-run, which couples test setup to compose state
# more than it's worth for a flag that only flips during incident response.
# See notes/PAYG_DESIGN.md §7.5.2 "PAYG cucumber: manual-only scenarios".
# ──────────────────────────────────────────────────────────────────────────
Scenario: 4xx leaves the shadow row CHARGED (customer pays for the attempt)
# /sanitize-pdf on an encrypted PDF without the password reliably 400s
# via GlobalExceptionHandler's PdfPasswordException → ProblemDetail path.
# We chain: first call encrypts a PDF (CHARGED), second call tries to
# sanitize WITHOUT the password and 400s. The 4xx assertion is on the
# SECOND call's behaviour.
Given there are no existing shadow charges for team "payg-cucumber-team"
When I POST a single-page PDF to "/api/v1/security/add-password"
And I take the response body as "encrypted"
And I POST "encrypted" to "/api/v1/security/sanitize-pdf"
Then the response status is >= 400 and < 500
# Note: shadow_charges count is 1 because the second call lineage-joins
# the first (its input matches the first's output). The 4xx therefore
# appears as a FAILED step on the existing process, not a new shadow row.
And exactly 1 shadow charge row exists for team "payg-cucumber-team"
And the latest shadow charge row has status "CHARGED"
And the latest job has step_count = 2
And the latest step's error_code matches the response status
Scenario: ZIP-returning tool records OUTPUT signatures per inner PDF
# /split-pages with multiple page numbers returns a ZIP. Stirling sends
# application/octet-stream rather than application/zip — the extractor
# sniffs the PK\x03\x04 magic so the ZIP unpack path still fires.
Given there are no existing shadow charges for team "payg-cucumber-team"
When I POST a 3-page PDF to "/api/v1/general/split-pages" with form fields:
| pageNumbers | 1,2 |
Then the response status is 200
And exactly 1 shadow charge row exists for team "payg-cucumber-team"
And the latest job has at least 2 OUTPUT artifact hashes recorded
Scenario: Multi-file input writes a single shadow row sized by the group
Given there are no existing shadow charges for team "payg-cucumber-team"
When I POST two single-page PDFs as a multi-file payload to "/api/v1/general/merge-pdfs"
Then the response status is 200
And exactly 1 shadow charge row exists for team "payg-cucumber-team"
And the latest shadow charge row has payg_units >= 1
Scenario: PIPELINE header sets the job source
Given there are no existing shadow charges for team "payg-cucumber-team"
When I POST a single-page PDF with header "X-Stirling-Automation: true" to "/api/v1/security/add-password"
Then the response status is 200
And exactly 1 shadow charge row exists for team "payg-cucumber-team"
And the latest job's source is "PIPELINE"
@@ -1,473 +0,0 @@
"""
Step definitions for PAYG shadow-mode end-to-end tests.
Runs against the saas-profile stack defined in
testing/compose/docker-compose-saas.yml — the backend with STIRLING_FLAVOR=saas
plus a Postgres container holding the stirling_pdf schema.
The test harness talks to the backend over HTTP and inspects the resulting
rows in `payg_shadow_charge`, `processing_job`, `processing_job_step`, and
`job_artifact_hash` via a direct psycopg connection. Direct DB inspection is
deliberate — we want to verify the *side effects* of the filter, not relay
them through another API layer that itself might be wrong.
Auth model: the saas profile expects Supabase JWTs. For cucumber we
configure the stack with a test user whose API key is recognised via the
X-API-KEY header, which the PaygChargeInterceptor.resolveUser() path
handles natively. The companion docker-compose-saas.yml seeds the user +
team rows via saas-init.sql so each scenario starts from a known state.
"""
import os
import time
import psycopg
import requests
from behave import given, then, when
BASE_URL = os.environ.get("PAYG_BASE_URL", "http://localhost:8080")
API_KEY = os.environ.get("PAYG_API_KEY", "payg-cucumber-key")
DB_HOST = os.environ.get("PAYG_DB_HOST", "localhost")
DB_PORT = int(os.environ.get("PAYG_DB_PORT", "5433"))
DB_NAME = os.environ.get("PAYG_DB_NAME", "postgres")
DB_USER = os.environ.get("PAYG_DB_USER", "postgres")
DB_PASSWORD = os.environ.get("PAYG_DB_PASSWORD", "postgres")
DB_SCHEMA = os.environ.get("PAYG_DB_SCHEMA", "stirling_pdf")
# Fixture paths — small PDFs that ship with the cucumber harness.
FIXTURE_DIR = os.path.join(
os.path.dirname(os.path.dirname(os.path.dirname(__file__))),
"exampleFiles",
)
# Existing cucumber fixtures (verified page counts via pypdf):
# tables.pdf = 1 page → SINGLE_PAGE_PDF
# ghost1.pdf = 3 pages → THREE_PAGE_PDF
# images.pdf = 5 pages (available if a scenario needs more)
# If you add more PAYG scenarios that need a different shape, drop the
# new fixture in exampleFiles/ and reference it here.
SINGLE_PAGE_PDF = os.path.join(FIXTURE_DIR, "tables.pdf")
THREE_PAGE_PDF = os.path.join(FIXTURE_DIR, "ghost1.pdf")
# ---------------------------------------------------------------------------
# DB helpers
# ---------------------------------------------------------------------------
def _db():
"""Open a fresh connection for each step — keeps things simple."""
return psycopg.connect(
host=DB_HOST,
port=DB_PORT,
dbname=DB_NAME,
user=DB_USER,
password=DB_PASSWORD,
autocommit=True,
)
def _team_id_for(team_name, conn):
"""Look up our test team's id (seeded by saas-init.sql)."""
with conn.cursor() as cur:
cur.execute(
f"SELECT team_id FROM {DB_SCHEMA}.teams WHERE name = %s LIMIT 1",
(team_name,),
)
row = cur.fetchone()
assert row is not None, f"No team named '{team_name}' in {DB_SCHEMA}.teams"
return row[0]
def _shadow_rows_for(team_name):
with _db() as conn:
team_id = _team_id_for(team_name, conn)
with conn.cursor() as cur:
cur.execute(
f"""SELECT shadow_id, payg_units, status, refunded_at, refund_reason, job_id
FROM {DB_SCHEMA}.payg_shadow_charge
WHERE team_id = %s
ORDER BY occurred_at DESC""",
(team_id,),
)
return cur.fetchall()
def _latest_job_for(team_name):
"""Return the most recently opened job for the team as a dict."""
with _db() as conn:
team_id = _team_id_for(team_name, conn)
with conn.cursor() as cur:
cur.execute(
f"""SELECT job_id, status, source, step_count, started_at, closed_at
FROM {DB_SCHEMA}.processing_job
WHERE owner_team_id = %s
ORDER BY started_at DESC
LIMIT 1""",
(team_id,),
)
row = cur.fetchone()
assert row is not None, f"No processing_job rows for team '{team_name}'"
return {
"job_id": row[0],
"status": row[1],
"source": row[2],
"step_count": row[3],
"started_at": row[4],
"closed_at": row[5],
}
def _steps_for_job(job_id):
with _db() as conn:
with conn.cursor() as cur:
cur.execute(
f"""SELECT step_id, tool_id, status, error_code
FROM {DB_SCHEMA}.processing_job_step
WHERE job_id = %s
ORDER BY started_at ASC""",
(job_id,),
)
return cur.fetchall()
def _output_artifact_count(job_id):
with _db() as conn:
with conn.cursor() as cur:
cur.execute(
f"""SELECT COUNT(*) FROM {DB_SCHEMA}.job_artifact_hash
WHERE job_id = %s AND kind = 'OUTPUT'""",
(job_id,),
)
return cur.fetchone()[0]
# ---------------------------------------------------------------------------
# HTTP helpers
# ---------------------------------------------------------------------------
def _api_headers(extra=None):
headers = {"X-API-KEY": API_KEY}
if extra:
headers.update(extra)
return headers
def _wait_for_health(timeout_seconds=60):
"""Block until /api/v1/info/status returns 2xx, or timeout."""
deadline = time.time() + timeout_seconds
while time.time() < deadline:
try:
r = requests.get(f"{BASE_URL}/api/v1/info/status", timeout=5)
if 200 <= r.status_code < 300:
return
except requests.RequestException:
pass
time.sleep(2)
raise AssertionError(
f"SaaS stack did not become healthy within {timeout_seconds}s at {BASE_URL}"
)
# ---------------------------------------------------------------------------
# GIVEN — environment + test fixtures
# ---------------------------------------------------------------------------
@given("the SaaS stack is running with PAYG enabled")
def step_saas_stack_running(context):
_wait_for_health()
@given('team "{team_name}" exists with wallet_policy.engine = "{engine}"')
def step_team_exists_with_engine(context, team_name, engine):
"""Verify the seed migration created the team + flipped its engine."""
with _db() as conn:
team_id = _team_id_for(team_name, conn)
with conn.cursor() as cur:
cur.execute(
f"SELECT engine FROM {DB_SCHEMA}.wallet_policy WHERE team_id = %s",
(team_id,),
)
row = cur.fetchone()
assert row is not None, f"No wallet_policy row for team '{team_name}'"
assert row[0] == engine, (
f"Team '{team_name}' engine is '{row[0]}', expected '{engine}'. "
"Check saas-init.sql seeded the row correctly."
)
context.team_name = team_name
@given('I am authenticated as a member of team "{team_name}"')
def step_authenticated_as_team_member(context, team_name):
# The seeded API key is bound to a member of this team via saas-init.sql.
context.team_name = team_name
@given('there are no existing shadow charges for team "{team_name}"')
def step_clear_shadow_charges(context, team_name):
with _db() as conn:
team_id = _team_id_for(team_name, conn)
with conn.cursor() as cur:
cur.execute(
f"DELETE FROM {DB_SCHEMA}.payg_shadow_charge WHERE team_id = %s",
(team_id,),
)
cur.execute(
f"""DELETE FROM {DB_SCHEMA}.job_artifact_hash
WHERE job_id IN (
SELECT job_id FROM {DB_SCHEMA}.processing_job
WHERE owner_team_id = %s
)""",
(team_id,),
)
cur.execute(
f"""DELETE FROM {DB_SCHEMA}.processing_job_step
WHERE job_id IN (
SELECT job_id FROM {DB_SCHEMA}.processing_job
WHERE owner_team_id = %s
)""",
(team_id,),
)
cur.execute(
f"DELETE FROM {DB_SCHEMA}.processing_job WHERE owner_team_id = %s",
(team_id,),
)
# NOTE: The kill-switch scenario (PAYG_FILTER_ENABLED=false) is verified
# manually — see notes/PAYG_DESIGN.md §7.5 "PAYG cucumber: manual-only
# scenarios" for the procedure. No automated step def is provided because
# toggling the env var requires restarting the docker container, and
# orchestrating that mid-suite would couple test setup to compose state
# in ways that have historically been fragile.
# ---------------------------------------------------------------------------
# WHEN — invoke tool endpoints
# ---------------------------------------------------------------------------
@when('I POST a single-page PDF to "{endpoint}"')
def step_post_single_pdf(context, endpoint):
_post_pdf(context, endpoint, SINGLE_PAGE_PDF)
@when('I POST a 3-page PDF to "{endpoint}"')
def step_post_three_page_pdf(context, endpoint):
_post_pdf(context, endpoint, THREE_PAGE_PDF)
@when('I POST a single-page PDF to "{endpoint}" with form fields:')
def step_post_with_form_fields(context, endpoint):
"""The Gherkin step takes a `table` of key/value pairs that become
multipart form fields. Use this when the default `password=...` field
from _post_pdf() isn't what we want for the scenario."""
data = {row[0]: row[1] for row in context.table.rows} if context.table else {}
_post_pdf(context, endpoint, SINGLE_PAGE_PDF, form_data=data)
@when('I POST a 3-page PDF to "{endpoint}" with form fields:')
def step_post_three_page_with_form_fields(context, endpoint):
data = {row[0]: row[1] for row in context.table.rows} if context.table else {}
_post_pdf(context, endpoint, THREE_PAGE_PDF, form_data=data)
@when('I POST a single-page PDF with header "{header_name}: {header_value}" to "{endpoint}"')
def step_post_with_header(context, header_name, header_value, endpoint):
_post_pdf(context, endpoint, SINGLE_PAGE_PDF, extra_headers={header_name: header_value})
@when('I POST two single-page PDFs as a multi-file payload to "{endpoint}"')
def step_post_two_pdfs(context, endpoint):
with open(SINGLE_PAGE_PDF, "rb") as a, open(SINGLE_PAGE_PDF, "rb") as b:
files = [
("fileInput", ("a.pdf", a.read(), "application/pdf")),
("fileInput", ("b.pdf", b.read(), "application/pdf")),
]
context.response = requests.post(
f"{BASE_URL}{endpoint}",
files=files,
headers=_api_headers(),
timeout=30,
)
@when('I take the response body as "{name}"')
def step_capture_response_body(context, name):
assert context.response is not None, "No response on context"
if not hasattr(context, "captured_bodies"):
context.captured_bodies = {}
context.captured_bodies[name] = context.response.content
@when('I POST "{captured_name}" to "{endpoint}"')
def step_post_captured(context, captured_name, endpoint):
body = context.captured_bodies[captured_name]
files = {"fileInput": (f"{captured_name}.pdf", body, "application/pdf")}
# Most tools need at least one extra form field; for the sanitize endpoint
# the defaults are sufficient.
context.response = requests.post(
f"{BASE_URL}{endpoint}",
files=files,
headers=_api_headers(),
timeout=30,
)
def _post_pdf(context, endpoint, fixture_path, extra_headers=None, form_data=None):
"""Default form data carries `password=cucumber-test-password` because
/add-password (our most-used scenario endpoint) requires it. Pass
{@code form_data} to override (e.g. to send the wrong password to
/remove-password for the 4xx scenario)."""
with open(fixture_path, "rb") as f:
files = {"fileInput": (os.path.basename(fixture_path), f, "application/pdf")}
data = form_data if form_data is not None else {"password": "cucumber-test-password"}
context.response = requests.post(
f"{BASE_URL}{endpoint}",
files=files,
data=data,
headers=_api_headers(extra_headers),
timeout=60,
)
# ---------------------------------------------------------------------------
# THEN — assertions
# ---------------------------------------------------------------------------
@then("the response status is {status:d}")
def step_assert_status(context, status):
assert context.response.status_code == status, _status_mismatch_message(
context.response, status
)
def _status_mismatch_message(response, expected_status):
"""Verbose diagnostic for unexpected statuses — dumps URL, headers, body
so we don't have to round-trip via container logs to figure out what came
back. Kept as a helper so future status-range / status-min steps can call
it too."""
body_preview = response.text[:1000] if response.text else "<empty body>"
headers_brief = {
k: v
for k, v in response.headers.items()
if k.lower()
in ("content-type", "content-length", "x-content-type-options", "location")
}
return (
f"Expected {expected_status}, got {response.status_code}\n"
f" URL: {response.request.method} {response.request.url}\n"
f" Headers: {headers_brief}\n"
f" Body: {body_preview}"
)
@then("the response status is >= {minimum:d}")
def step_assert_status_min(context, minimum):
assert context.response.status_code >= minimum, (
f"Expected >= {minimum}, got {context.response.status_code}"
)
@then("the response status is >= {minimum:d} and < {maximum:d}")
def step_assert_status_range(context, minimum, maximum):
code = context.response.status_code
assert minimum <= code < maximum, f"Expected [{minimum}, {maximum}), got {code}"
@then('the response Content-Type is "{expected}"')
def step_assert_content_type(context, expected):
actual = (context.response.headers.get("Content-Type") or "").split(";")[0].strip()
assert actual == expected, f"Expected {expected}, got {actual}"
@then('exactly {n:d} shadow charge row exists for team "{team_name}"')
@then('exactly {n:d} shadow charge rows exist for team "{team_name}"')
def step_assert_shadow_count(context, n, team_name):
rows = _shadow_rows_for(team_name)
assert len(rows) == n, f"Expected {n} shadow rows for '{team_name}', found {len(rows)}: {rows}"
@then('the latest shadow charge row has status "{status}"')
def step_assert_latest_shadow_status(context, status):
rows = _shadow_rows_for(context.team_name)
assert rows, "No shadow rows for team"
assert rows[0][2] == status, f"Expected status '{status}', got '{rows[0][2]}'"
@then("the latest shadow charge row has payg_units >= {minimum:d}")
def step_assert_payg_units_min(context, minimum):
rows = _shadow_rows_for(context.team_name)
assert rows[0][1] >= minimum, f"Expected payg_units >= {minimum}, got {rows[0][1]}"
@then("the latest shadow charge row's refunded_at is not null")
def step_assert_refunded_at_set(context):
rows = _shadow_rows_for(context.team_name)
assert rows[0][3] is not None, "refunded_at is null on the latest shadow row"
@then('the latest shadow charge row\'s refund_reason starts with "{prefix}"')
def step_assert_refund_reason(context, prefix):
rows = _shadow_rows_for(context.team_name)
reason = rows[0][4] or ""
assert reason.startswith(prefix), f"refund_reason '{reason}' does not start with '{prefix}'"
@then("the latest shadow charge row's job is {status}")
def step_assert_latest_jobstatus_via_shadow(context, status):
job = _latest_job_for(context.team_name)
assert job["status"] == status, f"Latest job status is '{job['status']}', expected '{status}'"
@then("the latest job is {status}")
def step_assert_latest_job_status(context, status):
job = _latest_job_for(context.team_name)
assert job["status"] == status, f"Latest job status is '{job['status']}', expected '{status}'"
@then("the latest job has step_count = {expected:d}")
def step_assert_step_count(context, expected):
job = _latest_job_for(context.team_name)
assert job["step_count"] == expected, (
f"Latest job step_count is {job['step_count']}, expected {expected}"
)
@then('the latest job\'s source is "{source}"')
def step_assert_job_source(context, source):
job = _latest_job_for(context.team_name)
assert job["source"] == source, f"Latest job source is '{job['source']}', expected '{source}'"
@then('the latest job has {n:d} step recorded with status "{status}"')
@then('the latest job has {n:d} steps recorded with status "{status}"')
def step_assert_step_count_with_status(context, n, status):
job = _latest_job_for(context.team_name)
steps = _steps_for_job(job["job_id"])
matching = [s for s in steps if s[2] == status]
assert len(matching) == n, (
f"Expected {n} steps with status '{status}', got {len(matching)}: {steps}"
)
@then("the latest step's error_code matches the response status")
def step_assert_step_error_code(context):
job = _latest_job_for(context.team_name)
steps = _steps_for_job(job["job_id"])
assert steps, "No steps recorded"
latest_step = steps[-1]
expected = str(context.response.status_code)
assert latest_step[3] == expected, (
f"Latest step error_code is '{latest_step[3]}', expected '{expected}'"
)
@then("the latest job has at least {n:d} OUTPUT artifact hashes recorded")
def step_assert_output_artifact_count(context, n):
job = _latest_job_for(context.team_name)
count = _output_artifact_count(job["job_id"])
assert count >= n, f"Latest job has {count} OUTPUT artifacts, expected >= {n}"
-9
View File
@@ -5,12 +5,3 @@ pypdf
reportlab reportlab
PyCryptodome PyCryptodome
qrcode[pil] qrcode[pil]
# PAYG cucumber scenarios inspect shadow rows directly against the
# saas-profile Postgres container — see testing/cucumber/features/steps/payg_step_definitions.py.
# Loaded by the saas-cucumber CI job only; main behave run doesn't touch it.
psycopg[binary]
# psycopg declares `typing-extensions>=4.6` under a Python-version marker that
# pip-compile leaves unpinned, which trips `--require-hashes`. Listing it here
# forces pip-compile to lock it to a concrete version with a hash. Without this,
# both saas-cucumber and the main docker-compose-tests fail on `pip install`.
typing-extensions
+1 -72
View File
@@ -154,9 +154,7 @@ charset-normalizer==3.4.7 \
colorama==0.4.6 \ colorama==0.4.6 \
--hash=sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44 \ --hash=sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44 \
--hash=sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6 --hash=sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6
# via # via behave
# behave
# qrcode
cucumber-expressions==19.0.0 \ cucumber-expressions==19.0.0 \
--hash=sha256:8eb5ae46dd03dd37fec1163ace1510529501d7d1868ff372c1ab2cd5aa4543a8 \ --hash=sha256:8eb5ae46dd03dd37fec1163ace1510529501d7d1868ff372c1ab2cd5aa4543a8 \
--hash=sha256:f452e6c73258c1677043ad67ad5f538c87284d6b502004720510fb6b7452d9c5 --hash=sha256:f452e6c73258c1677043ad67ad5f538c87284d6b502004720510fb6b7452d9c5
@@ -274,67 +272,6 @@ pillow==12.2.0 \
# via # via
# qrcode # qrcode
# reportlab # reportlab
psycopg==3.3.4 \
--hash=sha256:b6bbc25ccf05c8fad3b061d9db2ef0909a555171b84b07f29458a447253d679a \
--hash=sha256:e21207764952cff81b6b8bdacad9a3939f2793367fdac2987b3aac36a651b5bc
# via -r testing/cucumber/requirements.in
psycopg-binary==3.3.4 \
--hash=sha256:018fbed325936da502feb546642c982dcc4b9ffdea32dfef78dbf3b7f7ad4070 \
--hash=sha256:0579252a1202cd73e4da137a1426e2dae993ae44e757605344282af3a082848c \
--hash=sha256:136f199a407b5348b9b857c504aff60c77622a28482e7195839ce1b51238c4cc \
--hash=sha256:13a7f380824c35896dcac7fe0f61440f7ca49d6dc73f3c13a9a4471e6a3b302e \
--hash=sha256:17a21953a9e5ff3a16dab692625a3676e2f101db5e40072f39dbee2250194d68 \
--hash=sha256:1dc1f79fd16bb1f3f4421417a514607539f17804d95c7ed617265369d1981cae \
--hash=sha256:1fbaa292a3c8bb61b45df1ad3da1908ccee7cb889db9425e3557d9e34e2a4829 \
--hash=sha256:22cdbf5f91ef7bb91fe0c5757e1962d3127a8010256eefd9c61fcaf441802097 \
--hash=sha256:26df2717e59c0473e4465a97dfb1b7afebaa479277870fd5784d1436470db47c \
--hash=sha256:276904e3452d6a23d474ef9a21eee19f20eed3d53ddd2576af033827e0ba0992 \
--hash=sha256:28b7398fdd19db3232c884fb24550bdfe951221f510e195e233299e4c9b78f97 \
--hash=sha256:2c09aad7051326e7603c14e50636db9c01f78272dc54b3accff03d46370461e6 \
--hash=sha256:32a6fbf8481e3a370d0d72b860d35948a693cb01281da217f7b2f307636e591a \
--hash=sha256:41f2ec0fea529832982bcb6c9415de3c86264ebe562b77a467c0fbcd7efbba8d \
--hash=sha256:46893c26858be12cc49ca4226ed6a60b4bfccadd946b3bebb783a60b38788228 \
--hash=sha256:47c656a8a7ba6eb0cff1801a4caaa9c8bdc12d03080e273aff1c8ac39971a77e \
--hash=sha256:494ca54901be8cf9eb7e02c25b731f2317c378efa44f43e8f9bd0e1184ae7be4 \
--hash=sha256:514404ed543efd620c85602b747df2a23cf1241b4067199e1a66f2d2757aaa41 \
--hash=sha256:574ea21a9651958f1535c5a1c649c7409e9168bcbffa29a3f2f961f58b322949 \
--hash=sha256:580ae30a5f95ccd90008ec697d3ed6a4a2047a516407ad904283fa42086936e9 \
--hash=sha256:5ab28a2a7649df3b72e6b674b4c190e448e8e77cf496a65bd846472048de2089 \
--hash=sha256:5c4ab71be17bdca30cb34c34c4e1496e2f5d6f20c199c12bad226070b22ef9bf \
--hash=sha256:612a627d733f695b1de1f9b4bd511c15f999a5d8b915d444bbd7dd71cf3370da \
--hash=sha256:6402a9d8146cf4b3974ded3fd28a971e83dc6a0333eb7822524a3aa20b546578 \
--hash=sha256:6b9016b1714da4dd5ecaaa75b82098aa5a0b87854ce9b092e21c27c4ae23e014 \
--hash=sha256:71e55ccbdfae79a2ed9c6369c3008a3025817ff9d7e27b32a2d84e2a4267e66e \
--hash=sha256:7465bfe6087d2d5b42d4c53b9b11ca9f218e477317a4a162a10e3c19e984ba8e \
--hash=sha256:75a9067e236f9b9ae3535b66fe99bddb33d39c0de10112e49b9ab11eee53dc31 \
--hash=sha256:773d573e11f437ce0bdb95b7c18dc58390494f96d43f8b45b9760436114f7652 \
--hash=sha256:77df19583501ea288eaf15ac0fe7ad01e6d8091a91d5c41df5c718f307d8e31b \
--hash=sha256:7f7668f30b9dd5163197e5cbf4e0efd54e00f0a859cc566ce56cfc31f4054839 \
--hash=sha256:8c0056529e68dbe9184cd4019a1f3d8f3a4ead2f6fc7a5afcf27d3314edd1277 \
--hash=sha256:94596f9e7633ee3f6440711d43bb70aa31cc0a46a900ab8b4201a366ace5c9e7 \
--hash=sha256:ab8cca8ef8fb1ccf5b048ae5bd78ba55b9e4b5d472e3ce5ca39ff4d2a9c249e4 \
--hash=sha256:ad3bc94054876155549fdaedf4a46d1ec69d39a5bcee377148afe498e84c4b8e \
--hash=sha256:b56b603ebcea8aa10b46228b8410ba7f13e7c2ee54389d4d9be0927fd8ce2a70 \
--hash=sha256:b6f5a29e9c775b9f12a1a717aa7a2c80f9e1db6f27ba44a5b59c80ac61d2ffcf \
--hash=sha256:b7bfff1ca23732b488cbca3076fc11bc98d520ee122514fdb17a8e20d3338f5a \
--hash=sha256:bdef84570ebbce1d42b4e7ea952d21c414c5f118ad02fee00c5625f35e134429 \
--hash=sha256:c37e024c07308cd06cf3ec51bfd0e7f6157585a4d84d1bce4a7f5f7913719bf8 \
--hash=sha256:c677c4ad433cb7150c8cd304a0769ae3bcfbe5ea0676eb53faa7b1443b16d0d3 \
--hash=sha256:cf7f73a4a792bc5db58a4b385d8a1467e8d468f7548702fb0ed1e9b7501b1c13 \
--hash=sha256:cffc3408d77a27973f33e5d909b624cce683db5fc25964b02fe0aae7886c1007 \
--hash=sha256:d7b4d40c153fa352ab3cca530f3a0baedf7621b2ebcbd7f084009522c21788fc \
--hash=sha256:dbfdb9b6cc79f31104a7b162a2b921b765fcc62af6c00540a167a8de47e4ed38 \
--hash=sha256:df1d567fc430f6df15c9fcf67d87685fc49bdb325adc0db5af1adfb2f44eb5c9 \
--hash=sha256:e2631da29253a98bd496e6c4813b24e09a4fe3fb2a9e88513305d6f8747cce95 \
--hash=sha256:e7510c37550f91a187e3660a8cc50d4b760f8c3b8b2f89ebc5698cd2c7f2c85d \
--hash=sha256:eb05ee1c2b817d27c537333224c9e83c7afb86fe7296ba970990068baf819b16 \
--hash=sha256:eb4eed2079c01a4850bf467deacfab56d356d4225040170af03dc9958321242d \
--hash=sha256:ee17a2cf4943cde261adfad1bbc5bf38d6b3776d7afff74c7cabcbeaeb08c260 \
--hash=sha256:f80e3f2b5331dbbf0901bcb658056c03eeb2c1ef31d774afb0d61598b242e744 \
--hash=sha256:f9b1c2533af01cd7648378599f82b0b8ae32f293296e6eec5753a625bc97ef28 \
--hash=sha256:fa1cbc10768a796c96d3243656016bf4e337c81c71097270bb7b0ad6210d9765 \
--hash=sha256:fbd1d4ed566895ad2d3bf4ddfd8bae90026930ddf29df3b9d91d32c8c47866a7
# via psycopg
pycryptodome==3.23.0 \ pycryptodome==3.23.0 \
--hash=sha256:0011f7f00cdb74879142011f95133274741778abba114ceca229adbf8e62c3e4 \ --hash=sha256:0011f7f00cdb74879142011f95133274741778abba114ceca229adbf8e62c3e4 \
--hash=sha256:11eeeb6917903876f134b56ba11abe95c0b0fd5e3330def218083c7d98bbcb3c \ --hash=sha256:11eeeb6917903876f134b56ba11abe95c0b0fd5e3330def218083c7d98bbcb3c \
@@ -400,14 +337,6 @@ six==1.17.0 \
# via # via
# behave # behave
# parse-type # parse-type
typing-extensions==4.15.0 \
--hash=sha256:0cea48d173cc12fa28ecabc3b837ea3cf6f38c6d1136f85cbaaf598984861466 \
--hash=sha256:f0fa19c6845758ab08074a0cfa8b7aecb71c999ca73d62883bc25cc018c4e548
# via -r testing/cucumber/requirements.in
tzdata==2026.2 \
--hash=sha256:9173fde7d80d9018e02a662e168e5a2d04f87c41ea174b139fbef642eda62d10 \
--hash=sha256:bbe9af844f658da81a5f95019480da3a89415801f6cc966806612cc7169bffe7
# via psycopg
urllib3==2.7.0 \ urllib3==2.7.0 \
--hash=sha256:231e0ec3b63ceb14667c67be60f2f2c40a518cb38b03af60abc813da26505f4c \ --hash=sha256:231e0ec3b63ceb14667c67be60f2f2c40a518cb38b03af60abc813da26505f4c \
--hash=sha256:9fb4c81ebbb1ce9531cce37674bbc6f1360472bc18ca9a553ede278ef7276897 --hash=sha256:9fb4c81ebbb1ce9531cce37674bbc6f1360472bc18ca9a553ede278ef7276897
-89
View File
@@ -1,89 +0,0 @@
#!/bin/bash
#
# Cucumber harness for the PAYG shadow-mode scenarios. Brings up the
# saas-profile docker-compose, waits for backend health, pipes the seed SQL
# into the test postgres, then invokes Behave against features/payg/.
#
# Companion to testing/test.sh (which covers the proprietary-flavor stack
# and skips features/payg via behave.ini's exclude_re). Kept as a separate
# entrypoint so the saas variant can be reviewed + iterated on without
# touching the main cucumber harness.
set -euo pipefail
PROJECT_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
COMPOSE_FILE="$PROJECT_ROOT/testing/compose/docker-compose-saas.yml"
SEED_FILE="$PROJECT_ROOT/testing/compose/payg/saas-seed.sql"
cd "$PROJECT_ROOT"
# Swap behave.ini for the run. The project-default behave.ini excludes
# features/payg so the proprietary CI (which boots without the saas profile)
# can't try to run scenarios that need PAYG tables. behave's exclude_re takes
# priority over a path argument, so even `behave features/payg` would find
# zero features against the default config. The PAYG harness needs a config
# without the payg exclusion — restored on exit.
BEHAVE_INI="$PROJECT_ROOT/testing/cucumber/behave.ini"
BEHAVE_INI_BACKUP="$BEHAVE_INI.payg-backup"
cleanup() {
# Always dump container logs before tearing the stack down — the workflow
# has a "Dump saas container logs on failure" step but it runs AFTER this
# cleanup, by which point the containers are gone. Cheap diagnostic on
# success, essential on failure. (Earlier ERR-trap conditional didn't
# fire reliably under `set -e` when behave was the script's last command.)
echo "===== STIRLING_BACKEND_LOG_DUMP_START ====="
docker compose -f "$COMPOSE_FILE" logs --tail 500 stirling-pdf-saas || true
echo "===== STIRLING_BACKEND_LOG_DUMP_END ====="
echo "==> Tearing down saas compose stack"
docker compose -f "$COMPOSE_FILE" down -v || true
if [ -f "$BEHAVE_INI_BACKUP" ]; then
mv "$BEHAVE_INI_BACKUP" "$BEHAVE_INI"
fi
}
trap cleanup EXIT
cp "$BEHAVE_INI" "$BEHAVE_INI_BACKUP"
cat > "$BEHAVE_INI" <<'EOF'
# Temporary behave.ini written by testing/test-payg.sh for the PAYG harness
# run only. Restored on exit. The project default (in git) excludes
# features/payg so the proprietary-flavor CI doesn't try to run them.
[behave]
exclude_re = features/enterprise
EOF
echo "==> Building + starting saas compose stack"
docker compose -f "$COMPOSE_FILE" up -d --build
echo "==> Waiting for backend health (max 180s)"
deadline=$(( SECONDS + 180 ))
until curl -fsS http://localhost:8080/api/v1/info/status > /dev/null 2>&1; do
if [ $SECONDS -ge $deadline ]; then
echo "Backend did not become healthy in 180s"
docker compose -f "$COMPOSE_FILE" logs --tail 200 stirling-pdf-saas
exit 1
fi
sleep 3
done
echo "Backend healthy."
echo "==> Seeding test team / user / wallet_policy (PAYG_SHADOW)"
docker compose -f "$COMPOSE_FILE" exec -T postgres-saas \
psql -U postgres -d postgres < "$SEED_FILE"
echo "==> Running PAYG cucumber scenarios"
cd "$PROJECT_ROOT/testing/cucumber"
PAYG_BASE_URL="${PAYG_BASE_URL:-http://localhost:8080}" \
PAYG_API_KEY="${PAYG_API_KEY:-payg-cucumber-key}" \
PAYG_DB_HOST="${PAYG_DB_HOST:-localhost}" \
PAYG_DB_PORT="${PAYG_DB_PORT:-5433}" \
PAYG_DB_USER="${PAYG_DB_USER:-postgres}" \
PAYG_DB_PASSWORD="${PAYG_DB_PASSWORD:-postgres}" \
PAYG_DB_NAME="${PAYG_DB_NAME:-postgres}" \
PAYG_DB_SCHEMA="${PAYG_DB_SCHEMA:-stirling_pdf}" \
python -m behave features/payg \
-f behave_html_formatter:HTMLFormatter -o report-payg.html \
-f pretty \
--junit --junit-directory junit-payg
echo "==> PAYG cucumber run complete"