Wire /agent-review council=true into the review job

[gnovak]

The parser already enabled council mode for `/agent-review` (`lib/config.py:593` treats `council=true` as setting `council_models` output for review mode), but the `review:` workflow job had no council branch — it unconditionally ran the single-reviewer agentic loop. `/agent-review` with `council=true` parsed fine but produced exactly one review.

Found on bridge-analysis PR #438 (issue #436):

```
/agent-review
council = true
```

→ one review from claude-small only.

Wiring

• New "Run council code review" step in the review job, guarded `if: council_models != '[]' && council_models != ''`. Calls `run_build_council` (already used by build Stage 2 and delegate Stage 5) with /agent-review-flavored labels.
• Existing "Run review loop" and "Post review comment" steps get the opposite guard so they only run in single-reviewer mode.
• "Post cost comment (fallback)" stays unguarded; the new council step writes `/tmp/llm_usage.json` the same way single-reviewer does, so the fallback picks up cost in both modes.

Label parameterization on run_build_council

The function previously hard-coded "Build Stage 2 — Council Code Review" / "`/agent-build` Stage 2" in banner, per-reviewer attribution, and completion message. Now parameterized:

Caller	banner_label	attribution_label
Build Stage 2 (defaults)	"Build Stage 2 — Council Code Review"	"/agent-build Stage 2"
Delegate Stage 5	"Delegate Stage 5/6 — Council Code Review"	"/agent-delegate Stage 5"
/agent-review council=true	"Council Code Review"	"/agent-review council=true"

Test plan

• 664 unit tests pass (+2 for label-parameterization assertions)
• YAML syntactically valid
• Empirical: `/agent-review` + `council = true` on a PR posts 3 council reviewer comments (one per configured council model), not one single-reviewer comment

🤖 Generated with Claude Code