feat(ralph): rate limit budget tracking + whatsapp text-keywords

Task #1 — Rate limit budget tracking MVP:
- tools/ralph_usage.py: pure functions (extract_usage_entry, parse_usage_jsonl,
  aggregate_by_day/_project, filter_by_days, summarize) + CLI append/summarize
  subcommands. Atomic write via temp+rename.
- tools/ralph/ralph.sh: după fiecare claude -p, append usage entry
  derivat din JSON envelope la <project>/scripts/ralph/usage.jsonl. Best-effort,
  niciodată blochează rularea (|| true).
- dashboard/handlers/ralph.py: GET /api/ralph/usage[?days=N] aggregează cross-
  project și returnează {today_cost, today_runs, by_project, by_day, ...}.

Task #2 — WhatsApp text-keyword commands:
- src/router.py: helper _translate_whatsapp_text mapează "aprob"/"stop <slug>"/
  "stare [<slug>]" → /a, /k, /l. Apelat DOAR pe adapter whatsapp în
  _try_ralph_dispatch (Discord/TG nu sunt afectate). NU acoperim propose
  intentionat — descrierea liberă e prea fragilă pentru parsing text-only.

Tests: 49 noi (test_ralph_usage 28 + test_whatsapp_keywords 21) + 4 noi în
test_dashboard_ralph_endpoint pentru /api/ralph/usage. Toate trec; regression
suite (test_router, test_router_planning, test_dashboard_ralph_endpoint,
test_whatsapp) — 90/90 pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

tests/test_dashboard_ralph_endpoint.py

@@ -186,6 +186,54 @@ class TestPrd:
         assert handler.captured_code == 400
 
 
+# ── /api/ralph/usage ────────────────────────────────────────────
+
+
+class TestUsageEndpoint:
+    def test_usage_empty_workspace(self, handler):
+        handler.path = "/api/ralph/usage"
+        handler.handle_ralph_usage()
+        assert handler.captured_code == 200
+        assert handler.captured["today_runs"] == 0
+        assert handler.captured["total_runs"] == 0
+        assert handler.captured["by_project"] == {}
+
+    def test_usage_aggregates_across_projects(self, handler, tmp_path):
+        # Create two projects, each with usage.jsonl
+        for slug, cost, ts in [("proj-a", 0.5, "2026-04-26T10:00:00+00:00"),
+                                ("proj-b", 0.3, "2026-04-26T11:00:00+00:00")]:
+            ralph_dir = tmp_path / slug / "scripts" / "ralph"
+            ralph_dir.mkdir(parents=True)
+            (ralph_dir / "usage.jsonl").write_text(
+                json.dumps({"slug": slug, "ts": ts, "total_cost_usd": cost,
+                            "input_tokens": 100, "output_tokens": 50, "cache_read": 0}) + "\n",
+                encoding="utf-8",
+            )
+        handler.path = "/api/ralph/usage?days=30"
+        handler.handle_ralph_usage()
+        assert handler.captured_code == 200
+        # Should have both projects
+        assert "proj-a" in handler.captured["by_project"]
+        assert "proj-b" in handler.captured["by_project"]
+        assert handler.captured["total_runs"] == 2
+        assert handler.captured["window_runs"] == 2
+
+    def test_usage_invalid_days_falls_back(self, handler):
+        handler.path = "/api/ralph/usage?days=abc"
+        handler.handle_ralph_usage()
+        assert handler.captured_code == 200
+        assert handler.captured["window_days"] == 7
+
+    def test_usage_handles_corrupt_jsonl(self, handler, tmp_path):
+        # Project with corrupt usage.jsonl shouldn't 500
+        ralph_dir = tmp_path / "broken" / "scripts" / "ralph"
+        ralph_dir.mkdir(parents=True)
+        (ralph_dir / "usage.jsonl").write_text("not json\n", encoding="utf-8")
+        handler.path = "/api/ralph/usage"
+        handler.handle_ralph_usage()
+        assert handler.captured_code == 200
+
+
 # ── _ralph_validate_slug ───────────────────────────────────────