[KM-680] feat(report): markdown section separators + inline emphasis in summary

- Render a horizontal rule (---) between the header and each report section so it reads as a formal, sectioned document.
- Relax report_summary.md: the executive summary MAY use inline **bold**/*italic* for emphasis (kept no-headings/no-bullets so it doesn't duplicate the section structure or Key Findings).
- Tables / bold (method labels) / italic (meta + citations) were already emitted. Closes DEV_PLAN #23.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

DEV_PLAN.md

@@ -132,7 +132,7 @@ Status legend: ⬜ not started · 🔄 in progress · ✅ done · ⛔ blocked ·
 | 20 | **Help handoff:** update `handlers/help.py` + `help.md` — drop the `problem_validated` tier + `define_problem_statement` action (the skill it points at is gone as of #1) | Sofhia | ✅ | Done 2026-06-25. `help.py`: actions = `ask_analysis_question` (always) + `generate_report` (if ready); renders objective/business_questions (getattr-tolerant). `help.md` v1→v2: 3 tiers, no `/problem_statement`, `/generate report`→`/report`. Local test_help updated → 11 pass |
 | 21 | Rename `analysis_records` → **`agent_observability`** (model, `slow_path/store.py`, readers, `init_db`) | Rifqi | ⬜ new | Checkpoint: no "record" in the name (clashes w/ Go `analysis_message`). Confirm write scope: every agent call vs slow-path-only |
 | 22 | Finalize `agent_observability` schema → hand to Harry for the dedorch migration/startup | Rifqi → Harry | ⬜ new | Resolves #16 (table created post-cutover). Python still creates it locally until then |
-| 23 | Report markdown formatting: tables, **bold**, *italic*, horizontal separators | Sofhia | 🔄 new | Renderer already emits `##`/`**`/tables; verify italic + `---` separators + that the LLM summary keeps formatting. Minimum bar before charts |
+| 23 | Report markdown formatting: tables, **bold**, *italic*, horizontal separators | Sofhia | ✅ | Done 2026-06-25. Added `---` separators between header + each section in `_render_markdown`. Tables (EDA) / bold (method labels) / italic (meta + citations) already emitted. Relaxed `report_summary.md` to allow inline `**bold**`/`*italic*` for emphasis (kept no-headings/no-bullets so it doesn't duplicate the section structure / Key Findings). Compile + ruff clean |
 | 24 | Clarify report input contract: records table (+ `last_report` for edit mode?) | Rifqi/Sofhia ↔ Harry | ⬜ new | Edit-mode input left open at the checkpoint |
 | 25 | Confirm Python history source = Go `analysis_message` | Rifqi ↔ Harry | ⬜ new | New chat-room table (Q + A); replaces `chat_messages` for analyses |
 | 26 | **Charts (DEFERRED):** store Plotly JSON in a future `chart` table (not matplotlib PNG) | — | ⏸️ | After the markdown path is done end-to-end |

src/agents/report/generator.py

@@ -185,13 +185,14 @@ def _build_human_content(
 def _render_markdown(report: AnalysisReport) -> str:
     # Version is deliberately NOT in the markdown — it is assigned by the store
     # after rendering and lives in the structured `version` field / API metadata.
-    parts: list[str] = ["# Analysis Report"]
     meta = f"*Generated {report.generated_at:%Y-%m-%d}"
     author = report.user_name or report.user_id
     if author:
         meta += f" by {author}"
     meta += f" · {len(report.record_ids)} analyses · {len(report.data_sources)} source(s)*"
-    parts.append(meta)
+    # Title + meta form the header block; each subsequent section is divided by a
+    # horizontal rule (`---`) so the report reads as a formal, sectioned document.
+    parts: list[str] = ["# Analysis Report\n" + meta]
 
     ps = report.problem_statement
     if ps.objective:
@@ -248,7 +249,7 @@ def _render_markdown(report: AnalysisReport) -> str:
             lines.append(f"**{label}** — {rendered}")
         parts.append("\n".join(lines))
 
-    return "\n\n".join(parts)
+    return "\n\n---\n\n".join(parts)
 
 
 # --------------------------------------------------------------------------- #

src/config/prompts/report_summary.md

@@ -7,4 +7,5 @@ Rules:
 - Do NOT introduce any number, fact, or claim that is not present in the findings. You are summarizing, not analyzing.
 - Do NOT simply restate every finding; connect them into a narrative and say what they mean for the objective.
 - If the findings are thin or inconclusive, say so plainly rather than overstating.
-- Plain business language, prose only — no headings, no bullet lists.
+- Plain business language. Write **prose only — no headings, no bullet lists** (the report already supplies the section structure and a Key Findings list below this summary; do not duplicate them).
+- You MAY use light inline markdown for emphasis within the prose — `**bold**` for the most decision-relevant figure or term, `*italic*` sparingly. Keep it subtle; do not bold whole sentences.