feat(replay): R1 replay core — clock injection + replay of archived cycles

Re-executes BayesianStrategy.evaluate() over the R0 archive and stores
results in replay_runs/replay_decisions, tagged with git sha + a hash of
the strategy constants (same hash vs archive = determinism check,
different hash = counterfactual run).

- bayesian.py: optional as_of param on evaluate()/_days_to_resolution()
  (clock injection; default None = wall clock, prod behavior unchanged —
  the only touch to frozen code, purely additive)
- bot/replay.py: replay engine + CLI (python -m bot.replay --from --to);
  ReplayNews feeds archived sentiment back (GNews never called, per-cycle
  budget bypassed — archived sentiment already encodes it); manifold/db
  not wired (observational-only in prod); recorded-vs-replayed compare
  at 1e-9 tolerance
- schema.sql: replay_runs + replay_decisions (+ indexes), idempotent
- db.py: 6 replay accessors/writers
- tests: 19 new round-trip fidelity tests (104 total green)

Validated against a real prod cycle (2026-07-02T14:03:15Z, 46 markets,
4 skip paths incl. the Georgia confidence record): 46/46 matched,
max float delta 0.0.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

bot/data/db.py

@@ -747,6 +747,85 @@ class Database:
         except (ValueError, IndexError):
             return 0
 
+    # ── Replay R1: replay core ───────────────────────────────────────────────
+
+    async def get_replay_cycles(self, from_ts, to_ts) -> list:
+        """Return the cycle_ts values with archived decisions in [from_ts, to_ts)."""
+        async with self._pool.acquire() as conn:
+            rows = await conn.fetch("""
+                SELECT DISTINCT cycle_ts FROM signals
+                WHERE cycle_ts >= $1 AND cycle_ts < $2
+                ORDER BY cycle_ts
+            """, from_ts, to_ts)
+        return [r["cycle_ts"] for r in rows]
+
+    async def get_ext_snapshot(self, cycle_ts) -> Optional[dict]:
+        """Return one cycle's ExternalSignals snapshot, or None if missing."""
+        async with self._pool.acquire() as conn:
+            row = await conn.fetchrow(
+                "SELECT * FROM ext_snapshots WHERE cycle_ts = $1", cycle_ts
+            )
+        return dict(row) if row else None
+
+    async def get_cycle_signal_rows(self, cycle_ts) -> list[dict]:
+        """Return one cycle's archived decision rows in original evaluation
+        order (id = insertion order = the order main.py evaluated them)."""
+        async with self._pool.acquire() as conn:
+            rows = await conn.fetch(
+                "SELECT * FROM signals WHERE cycle_ts = $1 ORDER BY id", cycle_ts
+            )
+        return [dict(r) for r in rows]
+
+    async def get_markets_by_ids(self, market_ids: list[str]) -> dict[str, dict]:
+        """Return market metadata rows keyed by id (for Market reconstruction)."""
+        if not market_ids:
+            return {}
+        async with self._pool.acquire() as conn:
+            rows = await conn.fetch(
+                "SELECT * FROM markets WHERE id = ANY($1::text[])", market_ids
+            )
+        return {r["id"]: dict(r) for r in rows}
+
+    async def save_replay_run(self, run: dict) -> None:
+        async with self._pool.acquire() as conn:
+            await conn.execute("""
+                INSERT INTO replay_runs (
+                    run_id, git_sha, config_hash, config_json,
+                    from_ts, to_ts, cycles, decisions, matched, mismatched, note
+                ) VALUES ($1,$2,$3,$4,$5,$6,$7,$8,$9,$10,$11)
+            """,
+                run["run_id"], run["git_sha"], run["config_hash"],
+                run["config_json"], run["from_ts"], run["to_ts"],
+                run["cycles"], run["decisions"], run["matched"],
+                run["mismatched"], run["note"],
+            )
+
+    async def save_replay_decisions(self, run_id: str, decisions: list[dict]) -> None:
+        if not decisions:
+            return
+        rows = [
+            (
+                run_id, d["cycle_ts"], d["market_id"],
+                d["skip_reason"], d["prior_prob"], d["estimated_prob"],
+                d["raw_final_prob"], d["edge_gross"], d["edge_net"],
+                d["regime_min_edge"], d["days_to_resolution"],
+                d["confidence"], d["direction"], d["would_trade"],
+                d["recorded_skip_reason"], d["matched"], d["mismatch_field"],
+            )
+            for d in decisions
+        ]
+        async with self._pool.acquire() as conn:
+            await conn.executemany("""
+                INSERT INTO replay_decisions (
+                    run_id, cycle_ts, market_id,
+                    skip_reason, prior_prob, estimated_prob,
+                    raw_final_prob, edge_gross, edge_net,
+                    regime_min_edge, days_to_resolution,
+                    confidence, direction, would_trade,
+                    recorded_skip_reason, matched, mismatch_field
+                ) VALUES ($1,$2,$3,$4,$5,$6,$7,$8,$9,$10,$11,$12,$13,$14,$15,$16,$17)
+            """, rows)
+
     async def mark_manifold_audit_used(self, audit_id: str) -> None:
         async with self._pool.acquire() as conn:
             await conn.execute(

bot/data/schema.sql

@@ -370,3 +370,64 @@ CREATE TABLE IF NOT EXISTS ext_snapshots (
     total_market_cap_change DOUBLE PRECISION,
     valid                   BOOLEAN
 );
+
+-- ─────────────────────────────────────────────────────────────────────────────
+-- Replay R1: replay core — re-execute evaluate() over the R0 archive
+--
+-- A replay run reads cycles from signals + ext_snapshots + markets, rebuilds
+-- the exact inputs (including archived news_sentiment — GNews is never called),
+-- re-runs BayesianStrategy.evaluate() with the archived cycle_ts as clock, and
+-- writes one replay_decisions row per (cycle, market).
+--
+-- replay_runs tags every run with the code (git_sha) and strategy constants
+-- (config_hash) that produced it: two runs over the same window with different
+-- config_hash values are a counterfactual comparison; same config_hash against
+-- the recorded rows is a determinism check (mismatches should be 0, modulo
+-- day-boundary crossings between cycle_ts and the original wall-clock).
+--
+-- matched: replayed decision equals the recorded one (skip_reason, probs,
+--   confidence, direction).  NULL when not comparable — e.g. reentry_guard
+--   rows, recorded outside evaluate() with no decision fields to compare;
+--   the replay still re-evaluates them, which is extra calibration data.
+-- mismatch_field: first field that differed, for triage.
+-- ─────────────────────────────────────────────────────────────────────────────
+CREATE TABLE IF NOT EXISTS replay_runs (
+    run_id      TEXT PRIMARY KEY,
+    created_at  TIMESTAMPTZ DEFAULT NOW(),
+    git_sha     TEXT,
+    config_hash TEXT,
+    config_json TEXT,
+    from_ts     TIMESTAMPTZ,
+    to_ts       TIMESTAMPTZ,
+    cycles      INTEGER,
+    decisions   INTEGER,
+    matched     INTEGER,
+    mismatched  INTEGER,
+    note        TEXT
+);
+
+CREATE TABLE IF NOT EXISTS replay_decisions (
+    id                   SERIAL PRIMARY KEY,
+    run_id               TEXT NOT NULL,
+    cycle_ts             TIMESTAMPTZ NOT NULL,
+    market_id            TEXT NOT NULL,
+    -- replayed outputs (same semantics as the signals columns)
+    skip_reason          TEXT,
+    prior_prob           DOUBLE PRECISION,
+    estimated_prob       DOUBLE PRECISION,
+    raw_final_prob       DOUBLE PRECISION,
+    edge_gross           DOUBLE PRECISION,
+    edge_net             DOUBLE PRECISION,
+    regime_min_edge      DOUBLE PRECISION,
+    days_to_resolution   INTEGER,
+    confidence           DOUBLE PRECISION,
+    direction            TEXT,
+    would_trade          BOOLEAN,
+    -- fidelity vs the recorded signals row
+    recorded_skip_reason TEXT,
+    matched              BOOLEAN,
+    mismatch_field       TEXT
+);
+
+CREATE INDEX IF NOT EXISTS idx_replay_decisions_run ON replay_decisions(run_id);
+CREATE INDEX IF NOT EXISTS idx_replay_decisions_mkt ON replay_decisions(market_id);