mcaxl/tests/test_cti_failsafe_reachability.py
Ryan Malloy 1b92f83dc4 route_plan: fix Python-comment-in-f-string regression in translation_chain
Live re-run after the c995bc2 Device-DN fix returned "A syntax error
has occurred" from Informix. Cause: the explanatory comment block
documenting why tkpatternusage=2 was added landed *inside* the
translation_chain f-string instead of above it. Python's `#` line
comments only work outside string literals — inside an f-string,
each `#` is literal text. Informix received SQL with `#` lines after
the JOIN clauses, parsed them as illegal tokens, and rejected.

Offline tests didn't catch this because the FakeAxlClient dispatches
on substring matches without actually parsing the SQL. The bug only
manifested when the SQL hit a real Informix engine.

Fix: move the comment block ABOVE the `sql = f"""` assignment so it
becomes a real Python comment instead of literal SQL text.

Sentinel test added (test_no_python_comment_chars_leak_into_sql):
captures all SQL emitted by a cti_failsafe_reachability call and
asserts no `#` character appears anywhere. CUCM's data dictionary
doesn't use `#` in any table or column name, and Informix uses
`--` / `/* */` for comments — so a `#` in any captured query is
almost certainly an escaped Python comment. Catches this exact
class of regression for any future contributor.

Tests: cti suite 33 → 34; full mcaxl suite 271 → 272 passing.

Operational impact: this regression made cti_failsafe_reachability
unrunnable against any live cluster between c995bc2 and this fix.
The Bingham 6→4 finding-reduction verification queued in 008 is
unblocked once the MCP server reloads with this commit.
2026-05-09 05:09:20 -06:00

534 lines
23 KiB
Python

"""Tests for cti_failsafe_reachability — find broken CFNA/CFUR forwards.
Source: cucx-docs handoff at
``axl/agent-threads/cti-audit-prompts/001-cucx-cfna-reachability-audit.md``
documenting a real life-safety bug at Bingham (912-CTI-RP CFNA →
'10911' under 911CER-CSS, where '10.911' lives in CER911-PT which
911CER-CSS doesn't reach).
The tool composes three SQL queries per broken forward:
1. Top-level forwards SQL (fetch CTI RPs with CFNA/CFUR set)
2. translation_chain's SQL (per-forward reachability check)
3. _suggest_failsafe_fix's partition-lookup SQL (one per finding)
The FakeAxlClient dispatches by query content rather than sequence
because the order of (2) and (3) interleaves across multiple findings.
"""
import pytest
from mcaxl.route_plan import (
_LIFE_SAFETY_TOKENS,
_is_life_safety_cti,
cti_failsafe_reachability,
)
class FakeAxlClient:
"""Dispatching fake — returns canned responses keyed on SQL content.
Constructor takes:
- cti_rp_rows: rows for the top-level "find CTI RPs with forwards" query
- reachable_destinations: set of (destination, css) pairs that have a
matching pattern (translation_chain returns match_count > 0 for these)
- destination_partitions: dict {destination: [partition_name, ...]}
for the exact-literal partition-lookup query in _suggest_failsafe_fix
- dotted_patterns: list of (pattern, partition) tuples for the
dot-stripped lookup. The pattern includes literal dots (e.g.
``"10.911"``); _suggest_failsafe_fix strips dots and compares to
the destination
"""
def __init__(
self,
cti_rp_rows: list[dict],
reachable_destinations: set[tuple[str, str]] | None = None,
destination_partitions: dict[str, list[str]] | None = None,
dotted_patterns: list[tuple[str, str]] | None = None,
):
self._cti_rows = cti_rp_rows
self._reachable = reachable_destinations or set()
self._dest_partitions = destination_partitions or {}
self._dotted_patterns = dotted_patterns or []
self.queries: list[str] = []
def execute_sql_query(self, sql: str) -> dict:
self.queries.append(sql)
# Dispatch 1: top-level "find CTI RPs with CFNA/CFUR" query
if "tc.name = 'CTI Route Point'" in sql and "cfnadestination" in sql:
return {"row_count": len(self._cti_rows), "rows": self._cti_rows}
# Dispatch 2: translation_chain's reachability check
# Recognizable by `tkpatternusage IN (2, 3, 5, 7)` from route_plan.py
# (tkpatternusage = 2 / Device DN was added 2026-05-09 after
# cucx-docs's empirical proof in cti-audit-prompts/007 that
# excluding Device DNs caused false-positive HIGH findings on
# CTI-RP-to-CTI-RP failsafe chains)
if "tkpatternusage IN (2, 3, 5, 7)" in sql:
for dest, css in self._reachable:
if f"name = '{css}'" in sql:
return {
"row_count": 1,
"rows": [{
"pattern": dest,
"pattern_type": "Translation",
"partition_name": "Reachable-PT",
"calling_party_xform_mask": None,
"called_party_xform_mask": None,
"prefix_digits_out": None,
"digit_discard_instructions": None,
"route_filter": None,
"description": "fake-reachable",
}],
}
return {"row_count": 0, "rows": []}
# Dispatch 3a: _suggest_failsafe_fix's dot-stripped lookup
# (Stage 2 of the fix-suggestion logic — pulls all dot-containing
# patterns and filters Python-side)
if "np.dnorpattern LIKE '%.%'" in sql:
rows = [
{"pattern": pat, "partition": part}
for pat, part in self._dotted_patterns
]
return {"row_count": len(rows), "rows": rows}
# Dispatch 3b: _suggest_failsafe_fix's exact-literal lookup
# (Stage 1 — exact match on np.dnorpattern)
if "rp.name IS NOT NULL" in sql and "np.dnorpattern" in sql:
for dest, parts in self._dest_partitions.items():
if f"np.dnorpattern = '{dest}'" in sql:
rows = [{"partition": p} for p in parts]
return {"row_count": len(rows), "rows": rows}
return {"row_count": 0, "rows": []}
# Anything else — empty (unexpected query path; fail loud later)
return {"row_count": 0, "rows": []}
def _cti_row(name, description, cfna=None, cfur=None, cfna_css=None, cfur_css=None):
return {
"name": name,
"description": description,
"cfnadestination": cfna,
"cfurdestination": cfur,
"cfna_css_name": cfna_css,
"cfur_css_name": cfur_css,
}
# ─── Life-safety token detection (helper in isolation) ────────────────
class TestLifeSafetyDetection:
@pytest.mark.parametrize("description", [
"Primary CER Server",
"911 CTI Route Point",
"Emergency CER",
"PSAP gateway",
"PANIC button receiver",
"Code BLUE Alert",
])
def test_life_safety_tokens_match(self, description):
assert _is_life_safety_cti("some-name", description) is True
@pytest.mark.parametrize("name", [
"911-CTI-RP",
"EMERGENCY-RP",
"CER-Primary",
"psap-gateway",
])
def test_token_matched_in_name_field(self, name):
# Tokens match against name OR description — some clusters tag
# the role in the name field rather than the description
assert _is_life_safety_cti(name, "Generic CTI Route Point") is True
@pytest.mark.parametrize("description", [
"Patient Intake CTI Route Point",
"Voicemail Pilot",
"Receptionist Hunt Pilot",
"Generic application route point",
])
def test_non_life_safety_descriptions(self, description):
assert _is_life_safety_cti("regular-rp", description) is False
def test_null_name_and_description_does_not_match(self):
assert _is_life_safety_cti(None, None) is False
assert _is_life_safety_cti("", "") is False
def test_advertised_token_list_is_what_we_implement(self):
# If the token list grows or shrinks, the docstring + agent-thread
# reply must be updated alongside. Catches accidental drift.
assert _LIFE_SAFETY_TOKENS == (
"emergency", "911", "cer", "psap", "panic", "alert",
)
# ─── Tool-level integration ──────────────────────────────────────────
class TestCtiFailsafeReachability:
def test_no_cti_route_points_returns_empty_findings(self):
client = FakeAxlClient(cti_rp_rows=[])
result = cti_failsafe_reachability(client)
assert result["total_cti_route_points"] == 0
assert result["broken_cfna"] == 0
assert result["broken_cfur"] == 0
assert result["findings"] == []
def test_working_cfna_produces_no_finding(self):
client = FakeAxlClient(
cti_rp_rows=[
_cti_row("Working-RP", "Patient intake", cfna="5550100", cfna_css="Internal-CSS"),
],
reachable_destinations={("5550100", "Internal-CSS")},
)
result = cti_failsafe_reachability(client)
assert result["broken_cfna"] == 0
assert result["findings"] == []
def test_broken_cfna_non_life_safety_is_medium(self):
client = FakeAxlClient(
cti_rp_rows=[
_cti_row("Generic-RP", "Patient intake", cfna="5550100", cfna_css="BadCSS"),
],
reachable_destinations=set(), # nothing reachable
destination_partitions={"5550100": ["Internal-PT"]},
)
result = cti_failsafe_reachability(client)
assert result["broken_cfna"] == 1
assert len(result["findings"]) == 1
finding = result["findings"][0]
assert finding["device"] == "Generic-RP"
assert finding["forward_kind"] == "cfna"
assert finding["destination"] == "5550100"
assert finding["css"] == "BadCSS"
assert finding["match_count"] == 0
assert finding["severity"] == "MEDIUM"
assert "Internal-PT" in finding["suggested_fix"]
assert "BadCSS" in finding["suggested_fix"]
def test_broken_cfna_life_safety_is_high(self):
client = FakeAxlClient(
cti_rp_rows=[
_cti_row("911-CTI-RP", "Emergency dispatch", cfna="10911", cfna_css="911CER-CSS"),
],
destination_partitions={"10911": ["CER911-PT"]},
)
result = cti_failsafe_reachability(client)
assert result["findings"][0]["severity"] == "HIGH"
def test_broken_cfna_and_cfur_produce_two_findings(self):
# Same device with both forwards broken — should produce TWO entries
# (per-forward, not per-device, per the design decision)
client = FakeAxlClient(
cti_rp_rows=[
_cti_row(
"912-CTI-RP", "CTI RP for Secondary CER Server",
cfna="10911", cfna_css="911CER-CSS",
cfur="10911", cfur_css="911CER-CSS",
),
],
destination_partitions={"10911": ["CER911-PT"]},
)
result = cti_failsafe_reachability(client)
assert result["broken_cfna"] == 1
assert result["broken_cfur"] == 1
assert len(result["findings"]) == 2
kinds = {f["forward_kind"] for f in result["findings"]}
assert kinds == {"cfna", "cfur"}
# Both should be HIGH (description contains "CER")
assert all(f["severity"] == "HIGH" for f in result["findings"])
def test_only_cfna_set_does_not_check_cfur(self):
# CFUR null → don't check it (not a finding)
client = FakeAxlClient(
cti_rp_rows=[
_cti_row("Half-RP", "Generic", cfna="9999", cfna_css="BadCSS"),
],
destination_partitions={"9999": ["Some-PT"]},
)
result = cti_failsafe_reachability(client)
assert result["broken_cfna"] == 1
assert result["broken_cfur"] == 0
def test_canonical_bingham_bug_reproduced(self):
"""The canary scenario from cucx-docs's 001 — verifies the tool
produces exactly the expected output for the motivating bug."""
client = FakeAxlClient(
cti_rp_rows=[
_cti_row(
"912-CTI-RP", "CTI RP for Secondary CER Server",
cfna="10911", cfna_css="911CER-CSS",
cfur="10911", cfur_css="911CER-CSS",
),
],
destination_partitions={"10911": ["CER911-PT"]},
)
result = cti_failsafe_reachability(client)
cfna_finding = next(f for f in result["findings"] if f["forward_kind"] == "cfna")
assert cfna_finding == {
"device": "912-CTI-RP",
"description": "CTI RP for Secondary CER Server",
"forward_kind": "cfna",
"destination": "10911",
"css": "911CER-CSS",
"match_count": 0,
"severity": "HIGH", # description contains "CER"
"suggested_fix": (
"Pattern '10911' lives in partition 'CER911-PT'. "
"Either add 'CER911-PT' to CSS '911CER-CSS', "
"OR change the forward CSS to a CSS that already "
"contains 'CER911-PT'."
),
}
def test_suggested_fix_when_no_partition_holds_destination(self):
# Edge case: destination doesn't match any literal pattern
# OR any dot-stripped variant (might match a wildcard, but not
# something exact). Falls back to the wildcard-investigation
# generic message.
client = FakeAxlClient(
cti_rp_rows=[
_cti_row("Wild-RP", "Generic", cfna="orphan-dest", cfna_css="BadCSS"),
],
destination_partitions={}, # no partition holds 'orphan-dest'
# dotted_patterns defaults to [] → no dot-stripped match either
)
result = cti_failsafe_reachability(client)
fix = result["findings"][0]["suggested_fix"]
assert "no exact-literal or dot-stripped pattern" in fix
assert "wildcard" in fix.lower()
def test_suggested_fix_when_destination_in_multiple_partitions(self):
# Edge case: destination matches in multiple partitions; the
# fix message lists them and asks the operator to pick.
client = FakeAxlClient(
cti_rp_rows=[
_cti_row("Multi-RP", "Generic", cfna="5555", cfna_css="BadCSS"),
],
destination_partitions={"5555": ["Site-A-PT", "Site-B-PT"]},
)
result = cti_failsafe_reachability(client)
fix = result["findings"][0]["suggested_fix"]
assert "multiple partitions" in fix
assert "Site-A-PT" in fix
assert "Site-B-PT" in fix
def test_response_includes_scope_note(self):
client = FakeAxlClient(cti_rp_rows=[])
result = cti_failsafe_reachability(client)
assert "_note" in result
# Scope discipline visible at the call site — CFB exclusion is
# documented, and the life-safety token list is named.
assert "CFB" in result["_note"]
assert "emergency" in result["_note"]
# ─── Dot-stripped fix-suggestion (cti-audit-prompts/004 limitation) ────
#
# The CUCM separator-dot in patterns like `10.911` is purely visual —
# it represents access-code boundary, not a digit. A destination string
# `10911` (no dot) should match a configured pattern `10.911`. The
# original _suggest_failsafe_fix only did exact-literal lookups and
# missed this; the live Bingham smoke-test surfaced the limitation on
# `912-CTI-RP`. These tests pin the dot-stripped fallback behavior.
class TestDotStrippedFixSuggestion:
def test_dot_stripped_match_cites_dotted_pattern(self):
# Destination "10911" should match pattern "10.911" via dot-strip
client = FakeAxlClient(
cti_rp_rows=[
_cti_row("Test-RP", "Generic", cfna="10911", cfna_css="BadCSS"),
],
destination_partitions={}, # no exact-literal match
dotted_patterns=[("10.911", "CER911-PT")],
)
result = cti_failsafe_reachability(client)
fix = result["findings"][0]["suggested_fix"]
# The fix message names BOTH the pattern form and the destination
# so the operator sees what the dot-strip matched
assert "'10.911'" in fix
assert "'10911'" in fix
assert "CER911-PT" in fix
assert "BadCSS" in fix
def test_exact_literal_takes_precedence_over_dotted(self):
# If both an exact-literal match and a dotted match exist, the
# exact-literal wins — no need to mention the dotted form
client = FakeAxlClient(
cti_rp_rows=[
_cti_row("Test-RP", "Generic", cfna="912", cfna_css="BadCSS"),
],
destination_partitions={"912": ["911CER-PT"]},
dotted_patterns=[("9.12", "Decoy-PT")], # would match if dotted ran
)
result = cti_failsafe_reachability(client)
fix = result["findings"][0]["suggested_fix"]
assert "911CER-PT" in fix
# Decoy-PT shouldn't appear — exact-literal should short-circuit
assert "Decoy-PT" not in fix
def test_dotted_match_with_multiple_partitions(self):
# If the same dotted pattern exists in multiple partitions, the
# multi-partition message format applies — same as exact-literal
client = FakeAxlClient(
cti_rp_rows=[
_cti_row("Test-RP", "Generic", cfna="10911", cfna_css="BadCSS"),
],
destination_partitions={},
dotted_patterns=[
("10.911", "Site-A-PT"),
("10.911", "Site-B-PT"),
],
)
result = cti_failsafe_reachability(client)
fix = result["findings"][0]["suggested_fix"]
assert "multiple partitions" in fix
assert "Site-A-PT" in fix
assert "Site-B-PT" in fix
def test_no_exact_no_dotted_falls_back_to_generic(self):
# Neither exact-literal nor dot-stripped lookup finds a match
# → fall back to the wildcard-investigation generic message
client = FakeAxlClient(
cti_rp_rows=[
_cti_row("Test-RP", "Generic", cfna="60003", cfna_css="BadCSS"),
],
destination_partitions={},
dotted_patterns=[],
)
result = cti_failsafe_reachability(client)
fix = result["findings"][0]["suggested_fix"]
assert "no exact-literal or dot-stripped pattern" in fix
assert "wildcard pattern" in fix.lower()
def test_dotted_pattern_with_irrelevant_dot_does_not_match(self):
# Pattern "1.0911" has a dot but its dot-stripped form is "10911"
# — should match. Pattern "1.0912" stripped is "10912" — should NOT.
# This exercises the substring-equality logic.
client = FakeAxlClient(
cti_rp_rows=[
_cti_row("Test-RP", "Generic", cfna="10911", cfna_css="BadCSS"),
],
destination_partitions={},
dotted_patterns=[
("1.0911", "Match-PT"), # strips to "10911" → matches
("1.0912", "Nonmatch-PT"), # strips to "10912" → no match
("10.91", "AnotherMatch-PT"), # strips to "1091" → no match
],
)
result = cti_failsafe_reachability(client)
fix = result["findings"][0]["suggested_fix"]
assert "Match-PT" in fix
assert "Nonmatch-PT" not in fix
assert "AnotherMatch-PT" not in fix
# ─── Device-DN inclusion in translation_chain (cti-audit-prompts/007) ──
#
# cucx-docs verified empirically in 007 that `route_translation_chain`'s
# candidate filter excluded Device DNs (tkpatternusage=2), which caused
# false-positive HIGH findings on CTI-RP-to-CTI-RP failsafe chains
# (typical CER pattern). The fix: include tkpatternusage=2 in the
# candidate set so Device DNs get checked alongside translation/route/
# hunt patterns.
#
# These tests pin the regression by:
# 1. Verifying the SQL emitted by translation_chain includes
# `tkpatternusage IN (2, 3, 5, 7)` literally
# 2. Demonstrating the cti audit doesn't false-positive on a CTI-RP-
# to-CTI-RP failsafe shape
class TestDeviceDnInTranslationChainCandidates:
def test_translation_chain_sql_includes_device_dn_usage(self):
"""Lock the candidate-filter SQL down so a future contributor
can't accidentally re-narrow it to (3, 5, 7) and re-introduce
the cti-audit-prompts/007 false-positive class.
"""
client = FakeAxlClient(cti_rp_rows=[
_cti_row("Test-RP", "Generic", cfna="912", cfna_css="SomeCSS"),
])
cti_failsafe_reachability(client)
# Find the translation_chain query in the captured SQL
chain_query = next(
q for q in client.queries
if "tkpatternusage IN" in q and "callingsearchspace" in q
)
assert "(2, 3, 5, 7)" in chain_query, (
"translation_chain candidate set must include tkpatternusage=2 "
"(Device DN). Excluding Device DNs causes false-positive HIGH "
"findings on CTI-RP-to-CTI-RP failsafe chains. See "
"agent-threads/cti-audit-prompts/007 for cucx-docs's "
"empirical proof."
)
def test_no_python_comment_chars_leak_into_sql(self):
"""Sentinel — a `#` in any captured query is almost certainly a
Python comment that escaped its f-string. Informix doesn't use
`#` for comments (it uses `--` and `/* */`); CUCM's data
dictionary doesn't use `#` in table or column names either.
Caught a real regression in 2026-05-09 cti-audit-prompts
thread: a Python explanatory comment was placed *inside* the
translation_chain f-string (after the JOIN clauses, before
WHERE). Informix returned "A syntax error has occurred" on
every live call. Offline tests passed because the FakeAxlClient
dispatched on substring matches and didn't parse the SQL.
This test wouldn't have caught the original bug if it predated
the fix (the FakeAxlClient still wouldn't fail) — but adding
it now means a future contributor can't reintroduce the same
class of mistake in any cti_failsafe_reachability call path.
"""
client = FakeAxlClient(cti_rp_rows=[
_cti_row("Test-RP", "Generic", cfna="912", cfna_css="SomeCSS"),
])
cti_failsafe_reachability(client)
for q in client.queries:
# Allow `#` in column-comment-like positions in SELECT lists?
# No — CUCM's data dictionary has no such columns. A `#`
# anywhere in any query my tool emits is a defect.
assert "#" not in q, (
f"Python `#` character leaked into SQL — likely a Python "
f"comment inside an f-string. Informix will reject this "
f"with 'A syntax error has occurred'. Offending query:\n"
f"{q[:200]}..."
)
def test_cti_rp_to_cti_rp_failsafe_does_not_false_positive(self):
"""The motivating Bingham case: 911-CTI-RP CFNA → 912 (Device DN
of 912-CTI-RP) under 911CER-CSS reaching 911CER-PT.
Pre-fix: cti_failsafe_reachability flagged this as HIGH because
translation_chain excluded the Device DN from its candidate set.
Post-fix: the Device DN '912' is in the candidate set under the
reachable partition, so the forward correctly resolves and no
finding is produced.
"""
# Simulate the fix's effect: the reachable_destinations set
# captures (912, 911CER-CSS) — meaning translation_chain returns
# match_count > 0 because the Device DN is now in the candidate
# set and gets matched against the dialed number.
client = FakeAxlClient(
cti_rp_rows=[
_cti_row(
"911-CTI-RP", "CTI RP for Primary CER Server",
cfna="912", cfna_css="911CER-CSS",
cfur="912", cfur_css="911CER-CSS",
),
],
reachable_destinations={
("912", "911CER-CSS"), # Device DN now reachable
},
)
result = cti_failsafe_reachability(client)
# No findings — the Tier-1 forward correctly resolves
assert result["broken_cfna"] == 0
assert result["broken_cfur"] == 0
assert result["findings"] == []