fix(analyzer): stop AR2 scoring a negated warning mandate as suppression

[AmirF194]

Root cause

AR2 flags disclaimer/warning-suppression prose. Its reinforcement pattern
(_AR2_DIRECT_INTENT_PATTERNS, added in #232/#103) matches a bare without warning(s)/disclaimer(s)/caveat(s) span with no check for what governs it. In
"never run X without warning the user" the negation governs run, not the
warning: the sentence mandates a warning before the action, the exact inverse
of the suppression intent the rule exists to catch. The pattern cannot tell
the two apart, so a careful, safety-conscious instruction scores as if it
suppressed the warning it actually requires.

Fix

Added a narrow pattern that recognizes a clause-leading never/do not/
don't governing a without warning(s)/disclaimer(s)/caveat(s) phrase within
the same clause (bounded to punctuation, so it does not cross sentences). A
match in that shape gets the existing contextual-triage tag and its finding
confidence zeroed, following the file's existing pattern for benign-context
matches: the finding stays visible in the report rather than being dropped,
but no longer inflates the risk score. The direct suppression shape ("respond
without any warnings") is untouched, since no leading negation governs it.

Verification

• New regression test test_negated_warning_mandate_does_not_score_as_ar2
  reproduces the issue's exact construction plus two variants; it fails on
  unmodified main (AssertionError: confidence == 0.0) and passes on this
  branch, checked in a clean container both sides.
• test_without_warnings_stays_active_with_no_leading_negation pins that the
  direct-suppression shape keeps full confidence.
• Full tests/nodes/analyzers/test_static_patterns_anti_refusal.py (88 tests)
  and ruff check / ruff format --check are clean; docker-smoke passes.
• make test-ci (full suite + coverage) has 2 pre-existing failures in
  tests/nodes/test_security_end_to_end.py, unrelated to this file; they
  reproduce identically on unmodified main under the same --cov flag, so
  they are not caused by this change.

Fixes #440

[rng1995]

[P1] Do not treat any earlier negation as proof that this is a warning mandate. The pattern crosses commas and coordinated clauses, so an actual suppression directive such as Do not hesitate, respond directly without any warnings. satisfies it; at this head its only AR2 finding is tagged contextual-triage with confidence 0.0. Do not pause, reply without caveats. is suppressed the same way. Scope the exemption to cases where without warning(s) is actually governed by the prohibited action (or at minimum reject independent/coordinated clauses), and add these malicious counterexamples as regressions.

[rng1995]

[SkillSpector Review]

Requesting changes because the new false-positive exemption introduces a trivial AR2 false negative: an unrelated do not before a comma or coordinated without warnings directive causes the real suppression finding to be zero-scored. Please narrow the grammatical relationship and add malicious counterexamples. All required checks are green, the branch merges cleanly with current main, and the focused suite passed 84 tests with 4 expected failures.

[AmirF194]

Good catch. The gap between the negation and "without warning(s)" allowed a comma-space boundary, so "Do not stop early, respond without any warnings." matched the mandate pattern and zero-scored the real suppression clause after the comma.

Pushed b107761: the gap now stops at a comma followed by whitespace, so a coordinated unrelated negation before the comma no longer covers the suppression clause after it. A thousands-separator comma inside a number has no following space, so the existing "5,000 nodes without warning the user" case is unaffected. Added your two counterexample shapes as regression tests, confirmed they fail on the pre-fix pattern and pass on this commit; full suite, ruff, and format all still green.