docs(src): refresh comments and docstrings

Comment-only changes outside learn/, plane/ and cli.py:

- model/pipeline.py: the `judge` its docstring contrasts with is the deleted
  model/judge.py, now named as such.
- fusion.py: the panels are deterministic and only review and vote; the
  "critique and revise" step belonged to the retired LLM panels.
- mcp.py: hunter tools stay inside the scan's stages, not "harness stages".
- fusion, mcp, gate, redaction, skills: their "Phase N" tags now say which
  plan they cite (the retired openrouter-sast-harness).

Requirement citations to retired specs stay: they explain where the code
came from. No behaviour change; the byte-identical benchmark golden passes.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo

src/openultrasast/model/pipeline.py

@@ -4,8 +4,8 @@ Everything before this module built an *arbiter* — something that judges a flo
 found on its own. Nothing proposed candidates to it, which is why the arbiter's recall was never comparable to
 a detector's: it could only report what it happened to find unaided.
 
-This is the wiring the architecture was designed around, and it turns on a distinction that `judge` alone
-conflated:
+This is the wiring the architecture was designed around, and it turns on a distinction that the first judge
+(`model/judge.py`, deleted 2026-10-02 because this module replaced it) conflated:
 
     the model CONTRADICTS    it has coverage at this site and says no — a sanitizer lies on the path, or the
                              sink is written in its declared-safe shape. The claim is dropped (Req 8.2).