fix(security): prevent ReDoS in verdict-prose and continuation matchers (#4943)

Two py/polynomial-redos sinks ran regexes with two adjacent \s-matching
quantifiers over untrusted model text, backtracking O(n^2) when the tail failed
on a whitespace flood:

  - routes/skills_routes.py: the last-resort verdict-from-prose extractor used
    `["\'\s:]*\s*` — the class already matches \s, so the trailing \s* was a
    redundant second quantifier. Dropped it (extracted to a documented module
    constant _VERDICT_PROSE_RE); the matched text is identical, the scan linear.
  - src/agent_loop.py _EXPLICIT_CONTINUATION_RE: `\s*[.!?]*\s*$` put two \s*
    around `[.!?]*`. Rewrote as `\s*(?:[.!?]+\s*)?$` — same accepted tails (no
    two \s* adjacent), linear. Portable form (no possessive quantifiers).

Both verified output-equivalent to the originals across a fuzz corpus. Adds
tests/test_redos_verdict_continuation.py pinning the unchanged match sets and
bounding the flood inputs (old patterns took seconds at 40k whitespace chars).

src/agent_loop.py

@@ -845,7 +845,12 @@ _EXPLICIT_CONTINUATION_RE = re.compile(
     r"run it|launch it|start it|use that|that one|same|the same|"
     r"first|second|third|the first one|the second one|the third one|"
     r"[123]|[abc]"
-    r")\s*[.!?]*\s*$",
+    # `\s*[.!?]*\s*$` put two \s-matching quantifiers around `[.!?]*`, which
+    # backtracks O(n^2) on a terse reply + whitespace flood (py/polynomial-redos).
+    # `\s*(?:[.!?]+\s*)?$` accepts the same "trailing space/punctuation" tails
+    # (the inner \s* only engages after `[.!?]+`, so no two \s* are adjacent) and
+    # is linear.
+    r")\s*(?:[.!?]+\s*)?$",
     re.IGNORECASE,
 )
 _RETRY_CONTINUATION_RE = re.compile(