The v3 cutover run scored 2/4 corrections warned against v2's 3/4, which reads
like a regression and is not one. Only 4 of the 11 detected corrections fall in
the holdout, so recall is one event from a different headline -- and the event
that flips is decided by threshold placement, not by what the score saw. "v3
without the credit sensor" catches 2025-02-21 at a *higher* threshold (35.5)
than shipped v3 misses it at (32.3), because the alarm rule needs a rising edge
and a lower threshold can fire outside the horizon then never reset below.
Two caveats are now computed and surfaced rather than left for the reader to
infer:
- Holdout event count against MIN_EVENTS_FOR_CONFIDENCE. The summary sentence
states how many of the detected corrections actually fall in the test period.
- Warning-sensor coverage across the split. The score renormalises over what is
available, so a training window predating a sensor's history freezes the
threshold on a different construct than the holdout is measured against. At
the cutover that is 39% of training sessions with all three sensors versus
100% of the test period, credit history beginning 2023-07-25.
Restricting the threshold to sensor-matched training sessions was tested and
rejected: those sessions are a calm recent stretch, so the threshold falls from
32.3 to 22.5 and false alarms rise from 3.3 to 8.6/yr. It swaps a coverage bias
for a regime-selection bias. The report states its limits instead.
_warning_series now returns per-session sensor counts alongside the scores.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The LLM-sourced capex/earnings observations carried 12+8 of 100 Warning points,
so both pegged at 100 produced a Warning of 20.0 -- below the event study's 25.3
alarm threshold and still inside the "stable" band. The reading was
arithmetically incapable of changing anything on screen, which is why refreshing
it appeared to do nothing. They are now a qualitative overlay reported beside
the scores rather than diluted into them.
Calibrated against the 408 v2 sessions to 2026-07-24, reproduced offline from
Alpaca + FRED; the harness matched the stored prod distribution exactly before
any parameter was changed.
State:
- P3 used dd_pct * 5, reaching 100 at a 20% drawdown -- the 90th percentile of
the observed distribution -- so 39/408 sessions sat at exactly 100 with no
resolution left during the part of a selloff that matters most. Replaced with
anchored breakpoints keeping headroom past the observed 36% maximum, blended
2:1 like P1/P2 instead of max(). P3's realized share of State falls from 65%
to 40%, matching its nominal weight.
- Credit level is now anchors-only. ICE capped FRED's BAMLH0A0HYM2 at a rolling
3-year window in April 2026, silently turning the 10-year percentile leg into
a 3-year one that scored 20 points of stress at an OAS of 3.5 -- the level its
own anchors call "mild". The anchors already encode the long-run distribution.
Warning:
- Added HY OAS 20-session widening (25%). The level is pinned at zero below the
3.5 anchor; its rate of change is not.
- Divergence tapers to a 0.35 floor instead of a hard price_ret >= 0 gate, which
zeroed the sensor through every decline: on 2026-07-24 the basket shed 10
points of participation in 20 sessions and Warning printed exactly 0.
- The event study and the live monitor now share one sensor definition, so they
cannot silently drift apart.
Bands are per axis (State 20/50/80, Warning 20/40/60) with quadrant dividers at
50/40; v2 Warning never exceeded 64.9 against a shared 60, leaving that half of
the quadrant unreachable. Realized shares: State 73/15/8/3%, Warning 69/20/8/3%.
Snapshots now record credit_history_days and vix_history_days -- the percentile
defect went unnoticed for months because nothing asserted the window the code
claimed.
Cutover: the first run rebuilds 400 sessions automatically; the Event Study job
must be re-run, as its cached report self-invalidates on the methodology check.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The manual paper book only contains trades taken by hand, inside a 20
minute window, on days someone was available. The backtest that validated
this strategy auto-takes the top-ranked qualified setups up to capacity
every session. The forward record was therefore measuring strategy plus
discretion plus availability -- and degrading silently on busy days.
The shadow book closes that gap: it mirrors the backtest's selection rule
(top strategy_rank qualified, up to capacity, 1% fixed-fractional risk)
and shares the manual book's exit policy, so the only difference between
the two books is which setups get taken. Selection ordering reuses the
strategy_rank the scanner already stores rather than recomputing it, so
the two cannot drift apart. It runs as a near-close pipeline step right
after the scan, marking entries at the same prices a human would see.
Gate-reset re-entry state is now scoped per book -- the books diverge as
soon as their entries differ, and each must see only its own stops.
Performance view rewritten around the comparison:
- three series (shadow, manual, SPY) from a new endpoint
- SPY changes from a per-trade cost-basis counterfactual to plain
buy-and-hold %, since one line has to serve two books
- headline stats are R-multiples, not currency: the books size
differently, so only R compares across them
- configurable start date, because the strategy has been revised
repeatedly and pre-cutover trades ran under rules that no longer
exist
Migration 024 also repairs the numeric weekday crons written by 023,
rewriting only rows still holding the broken form so hand-corrected
settings survive. Its literals are inlined because bound parameters
render as NULL under 'alembic upgrade --sql'.
The shadow book is opt-in and writes nothing until enabled. Verify its
first selections match a backtest of that day's cross-section before
trusting any point on the curve.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Persist job and ingestion warnings/errors for 7 days, surface a dismissible top-nav badge, treat stale OHLCV as a warning (e.g. ticker renames), and show market bar age on the ticker freshness chip.
De-clutter setup labels (left roles, right prices; hide Entry near Now; S/R in-plot), and draw green/red arrows for paper trade entry and exit on the matching sessions.
Single-ticker fetch now attaches residual-momentum ranks so setups do not silently fail the activation gate. Exit plan is a timeline, chart labels move left of the price scale, and missing ranks surface explicitly.
The UI told a swing-trade story (entry -> target -> stop) while the engine runs
a momentum portfolio (buy strength, trail out, re-rank). The selection was
honest; everything around it was borrowed from a strategy we don't run.
The target is never an exit under `atr_trailing`: `_atr_trailing_close()` does
not even take it as a parameter. It exists only to compute the R:R and touch
odds that admit a setup through the activation gate. Backtested exit reasons for
the production strategy: 144 initial stop, 98 trailing stop, 78 max hold —
target 0. See docs/research/sr-levels-and-exits.md.
What changed:
- New ExitPlanPanel on every setup card states the rules that actually close the
trade: initial stop (1R), the price at which the 3x ATR trail takes over from
it, the trail width in R, and the max hold. Derived in lib/exitPlan.ts from the
live exit policy, so it follows Admin rather than hardcoding the default.
- New BaseRatesPanel replaces per-target "probability" as the answer to "what
usually happens": win rate, average hold, best/worst R, and how trades actually
ended — measured under the real exit, from the backtest report.
- "Target"/"target probability" relabelled to "level"/"touch odds" and grouped as
gate metrics, with the R:R. On the dashboard focus card, residual momentum
(the actual signal) takes the headline stat those two used to occupy.
- The take-trade dialog no longer offers a target dropdown whose value the exit
ignores; it states the trailing plan instead. The picker returns only when the
live policy is mode='target', where the choice is real. The stored target is
now the setup's own, not whichever row was last clicked while exploring.
- "Played out" is gone. A setup was declared dead once price reached the target —
backwards under a trailing exit, where reaching a level is the good case and
the trade keeps running. Only the stop invalidates a setup now; running past
the entry is an "extended" warning, measured in R (you'd be chasing).
The levels ladder, the price rail and the chart overlay all stay fully
explorable — clicking a level still drives them. It is framed as overhead
structure, which is what it is, rather than a menu of exits.
Adds a parity guard: the UI recovers ATR as |entry - stop| / 1.5, so the test
fails if the scanner's stop width ever moves.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- PerfChart moves into the left column under Open Positions
(half-width), balancing the radar column.
Cleanup:
- Design mockup pages (DesignMockups / DesignHorizon / DesignOrbit)
and their routes removed - the redesign has shipped; the mockups
live on in git history. Main bundle shrinks ~97 kB and the
chunk-size warning goes away.
- frontend/tsconfig.tsbuildinfo untracked and gitignored (incremental
build artifact that churned in every commit).
- Dead npm test / test:watch scripts removed - vitest was never a
dependency; CI already skips the step via its vitest guard.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The focus|radar 3/5-2/5 pairing made the top-pick card cramped and the
full-width positions panel stretched its trade charts. Back to the
layout that worked: focus card full width, account ribbons, then
positions | radar side by side, performance chart at the bottom.
Kept from the rework: radar rows still swap the focus card - and now
reliably, because the ticker symbol inside a row is no longer a
navigation link (clicking anywhere in the row, symbol included,
selects it; the ticker page is reachable via the focus card's Ticker
details button). Below-gate inspection, badges, and the reset link
unchanged.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Layout regrouped by relationship, not size: the setup-in-focus card
and the radar sit side by side (they are one decision surface), the
four account ribbons move directly above the open positions they
describe, and a new performance chart closes the page.
- Radar rows are selectable: clicking one swaps the focus card to that
setup - including below-gate rows, whose card shows a muted
"rank N / below gate" badge and the disqualify reason in the footer,
with a "back to top pick" reset. The row currently in focus is
highlighted; ticker links still deep-link without selecting.
- Performance chart (the mockup's missing piece): new
GET /paper-trades/equity-curve computes, per benchmark trading day
since the first paper trade, the book's cumulative P&L (realized +
mark-to-market from stored OHLCV) vs the same cost basis riding SPY
over each trade's window (benchmark_prices). Pure curve math in
paper_trade_service with unit tests; hidden until there are 2+
points of data. Frontend renders both lines with crosshair readout,
zero baseline, and direct end labels.
Backend unit suite: 501 passed.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The market regime banner took a full-width row on the dashboard for
ambient context. It is now a subtle status in the top bar (colored dot
+ "neutral regime", full headline and the longs/shorts caution in the
tooltip) linking to /regime - matching the mockup's nav.
The watchlist strip moves from the bottom of the dashboard (where it
got lost) into the freed spot right under the hero: a slim chip row
with today's move per symbol and the full-watchlist link. The empty
state is a one-line hint instead of a callout box.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The dashboard fingerprints sorted score dimensions alphabetically
while the ticker page rendered them in API order, so the same ticker
drew a differently-shaped polygon on each page.
New shared helper radarAxesFromDimensions() pins the axis order to the
backend's DIMENSIONS list (technical, sr_quality, sentiment,
fundamental, momentum; unknown dimensions append alphabetically) and
centralizes the label truncation. Used by the dashboard fingerprint
strip, the ticker header radar, and ScoreCard.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- The ladder target choice is lifted to the ticker page (per
direction), so selecting a target updates the candlestick overlay's
target line and zone too, with the R:R for the tooltip taken from
the ladder row.
- Price rail: the scale now always spans the entire target ladder, so
stop / entry / now hold their positions and only the target marker
moves when a different target is selected. The furthest target sits
at the right edge.
- Setup card layout: position sizing (shares / value / max loss,
details in the tooltip) and the Mark-as-taken button move to the top
right of the card header row, next to the stats they belong with -
the dangling bottom row is gone.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
selectable targets drive the rail
- Data freshness is now the very first row of the ticker panel, above
the symbol - data age is the first thing to check.
- Indicator cards: long price-level lists (pivot swing highs/lows,
volume-profile HVN/LVN) no longer clip or overwhelm. Numeric lists
are clustered into ranges (values within ~0.75% of price merge),
sorted nearest-to-price first, capped at 4 chips with a "+n more"
note; scalar values wrap instead of overflowing the card.
- Recommendation verdict: the action ("LONG (high confidence)") is set
in the display face in accent cyan with the risk level beside it;
the signal breakdown (technical/momentum/sentiment) drops to a small
muted subtitle line.
- Target ladder is open by default and selectable: clicking a row
previews that target on the price rail and updates the R:R and
probability chips, the low-probability warning, and the prefilled
target in Mark-as-taken (still overridable there). The scanner's
primary stays the default; a non-primary choice is chipped as
"custom target".
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
verdict de-dup, target picker on take
Five fixes from prod review:
1. Data freshness row moves from the panel foot to directly under the
header - data age is a first-look concern.
2. Radar fingerprint labels were clipped left ("Momentum") and right
(value digits): label padding widened to fit "momentum 100" on both
anchored sides.
3. Indicators tab: the one-at-a-time dropdown (which also clipped) is
gone; all indicators load in parallel as quiet outlined cards - EMA
cross with its colored signal, RSI/ADX with a one-line human read
(overbought / trending / ...), values formatted to 2 decimals
instead of 4, normalized score demoted to a corner note.
4. Recommendation verdict line de-duplicated: the backend reasoning
already starts with the action label, so it now replaces the
headline instead of repeating under it.
5. Mark-as-taken: the take form gains a target selector listing every
detected target with price / probability / classification (primary
preselected), and the card warns when the primary target sits below
15% probability. Why the scanner promotes such a target to primary
is a separate (backend) question.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
RecommendationPanel redesigned to match the rest of the redesign:
- Setup cards use the spatial price rail (stop -> entry -> now ->
target with live R-multiples) instead of the label/value text grid.
- One quiet chip row per card (direction, preferred marker, confidence,
R:R, target probability) replaces scattered header text.
- Position sizing is a single mono line (shares / position / max loss)
instead of a boxed 3-column mini-table; Mark-as-taken flow kept, in
the standard cyan button style.
- Full target ladder moves behind a disclosure (the primary target is
already on the rail); warnings (counter-trend, stale/invalidated
drift, earnings window, conflict flags) all kept.
- Cards are quiet outlined blocks, no glass-in-glass; the module
renders frameless inside the unified ticker panel's Analysis tab,
under the chart.
Ticker panel tabs now: Analysis, Standing, Dimensions, Indicators,
S/R Levels, Sentiment, Fundamentals - Standing and Dimensions were the
last below-the-fold sections; the whole page is now the single panel.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The previous pass kept a stack of independent glass cards (header,
recommendation, chart section, tab pills, per-tab sections), which read
as clutter. Now the page is a single casting, like the mockup:
One glass panel containing:
- header (identity, price, chips | actions + score fingerprint)
- inline hairline tab row (Analysis / Indicators / S/R Levels /
Sentiment / Fundamentals) with the chart-overlay pills riding on the
right of the row during Analysis
- tab body: Analysis = the candlestick chart; other tabs render their
panel inside via .hz-frameless, which strips the nested card chrome
(no card-in-card)
- panel foot: data freshness row (frameless now) with per-source
refresh
Below the panel, only on Analysis: the recommendation module and a
two-column Standing | Dimensions grid. Nothing removed; the standalone
Tabs bar, the separate chart card, and the duplicated section stack are
gone.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Restructures TickerDetailPage to match the Horizon mockup's ticker
drill-down while keeping every existing feature:
- Glass header card: eyebrow + big symbol/company, price with change
and freshness, chips (composite score, next earnings, top-pick /
open-trade pills) on the left; watchlist + Fetch All actions and the
score fingerprint radar on the right (hover a corner for values).
- Data freshness bar (per-source age + refresh buttons) moves to the
foot of the chart card, like the mockup's panel footer.
- Tabs extended to five: Analysis, Indicators, S/R Levels, Sentiment,
Fundamentals - sentiment and fundamentals no longer stack below the
analysis content, they are one tab away.
- ScoreCard gains showRadar prop so the fingerprint is not duplicated
in the Dimensions section.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Fixes from first prod review of the redesign:
- Top navigation bar (TopBar) replaces the sidebar, like the mockup:
wordmark + sections + ticker search + jobs/status/logout; content in
a centered max-width column. MobileNav unchanged.
- Radar panel: qualified setups lead again (the actionable list, as
the old Top Setups did); non-qualified sit behind an "N below the
gate" toggle with per-rule reasons, auto-open only when nothing
qualifies. Adds mini radar fingerprints for the top 3 qualified
(dimension scores from the rankings endpoint, fixed axis order).
- Dashboard layout: open positions and radar side by side (xl), as in
the mockup.
- ScoreCard: the radar fingerprint was inside the showComposite block,
which the ticker page disables - it never rendered. Now it shows
whenever >= 3 dimensions exist.
- TradeChart: fresh positions with < 2 bars since entry rendered no
chart; now pads with ~10 pre-entry context bars (gray) and marks the
entry point. First open position auto-expands so the chart is
visible without a click.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Replaces the citron/green glass theme with the Horizon direction
(mockup at /design-horizon): space-void background, starfield, dim
Mars horizon, rim-cyan accent, rose for negative. Palette validated
for CVD separation and contrast on the dark surface.
- tailwind.config: gray -> cool space neutrals, blue/emerald -> cyan
scale, red -> rose; display font Space Grotesk
- globals.css: Horizon tokens, atmosphere, denser glass, cyan
buttons/inputs, price-rail / R-bar / radar chart CSS
- Dashboard rebuilt: verdict hero, top-pick card with spatial price
rail, KPI tiles, open positions as diverging R-bars with expandable
detail + trade chart (OHLCV since entry, entry/stop/target levels),
radar list with per-setup disqualify reason, watchlist chips
- OpenTradesPanel: table replaced by R-bar rows; all fields kept in
the drill-down (shares, P&L, alpha, trailing stop, sell)
- qualification: disqualifyReason() mirrors qualifiesSetup rule order
- CandlestickChart: canvas colors moved to Horizon palette; S/R now
cyan/neutral so rose stays reserved for the stop level
- ScoreCard: radar score fingerprint with hover values
- Design mockup pages included (routed in App.tsx)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Store an optional company name on Ticker (migration 014) and backfill it from
Alpaca's asset list in a single Trading-API call for the whole universe — no
per-ticker fetch. Runs automatically at the end of universe bootstrap and via a
manual "Backfill Names" button (admin) / POST /admin/tickers/backfill-names.
The name ships on /tickers; a shared symbol→name map (useTickerNames) lets any view
show it without its own request. Displayed subtly next to the symbol — in the global
search, the ticker header, and as a small muted line under the symbol in Top Setups
and Open Trades (no extra column, truncated so it never widens the table).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The ticker page renders the composite via the Standing matrix (ScoreCard runs with
showComposite=false), so the "Base X · sentiment +Y" line in the ScoreCard header
was never visible there. Add a compact caption beneath the matrix — "Composite 83 =
Base 78 + Sentiment 5.0" — shown only when sentiment actually moves the score, so
the composition of the number has a visible home where the number lives.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Applies the backtest-validated trailing stop to live paper trading, and surfaces
it transparently.
Exit (A):
- New paper-trade exit policy (paper_exit_mode=trailing, paper_trailing_pct=12),
tunable in Admin → Paper-Trade Exit. resolve_open_trades runs a trailing stop
(initial stop as floor, ratchets up from the peak; target ignored — the
validated rule) and records close_reason (trailing|stop|target|manual; +migration
013).
- list_trades enriches open trades with the live trailing-stop level + distance %.
Open Trades panel shows the active tactic and a Trail Stop column.
Alerts (B):
- Daily digest now lists open trades with unrealized gain, trailing stop, and how
far away it is.
- New "trade closed" alert: one summary per auto-close (trailing/target/stop, not
manual) — direction, reason, days held, P&L abs+%/R — covering wins AND
stop-loss losses. Deduped by trade id; toggle in Admin alerts.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Three usability fixes:
1. Global ticker search in the sidebar (TickerSearch) — typeahead over the
tracked universe that opens a ticker's detail page without adding it to the
watchlist. Also wired into the mobile nav.
2. Watchlist table shows the ticker's 12-1 momentum percentile (the top-pick
selector) instead of the noisy full S/R-level list. Enriched from the setup
already loaded in watchlist_service._enrich_entry — no extra query.
3. Alpha vs the S&P 500 on paper trades (open + closed). New benchmark_prices
table + benchmark_service store SPY daily closes (a standalone series, not a
Ticker, so it never enters the scanner / momentum ranking / rankings) via a
new daily-pipeline step. paper_trade_service computes per-trade
benchmark_return / alpha_pct / alpha_usd over each holding period; the open-
trades table, dashboard, and closed-trades panel surface per-trade and total
alpha. The list read path never makes a provider call.
Deploy: alembic upgrade head, then run the benchmark/daily job once to populate
SPY closes (alpha shows "—" until then).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Replace the scattered score readouts with one hero: a quality (composite) x
momentum-percentile scatter that plots this ticker against the whole field and
reads out a verdict by quadrant — Strong Buy / Momentum / Accumulate / Pass. The
dashed divider is the activation gate's momentum percentile, so "above the line =
qualifies" is visible at a glance; peers are clickable. Reuses the regime-quadrant
visual language and is lazy-loaded so recharts stays out of the main ticker chunk.
- New StandingMatrix component (composite x momentum, field cloud, verdict).
- ScoreCard gains showComposite (default true); the ticker page now renders it
without the composite ring (composite lives in the matrix) under "Dimensions".
- Confidence + target probability stay in the recommendation panel (the trade).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Two read-only pills in the ticker header, beside the watchlist toggle:
- "Top Pick" when the ticker is the current #1 — the same ranking the dashboard
highlights, via a shared topPickSymbol() helper so the two stay in sync.
- "Open Trade" when an open paper trade exists on the ticker.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The combined score collapsed two distinct signals into one not-very-meaningful
number. Replace its gauge with a quadrant scatter that shows both axes directly:
x = regime index (coincident), y = early warning (breadth divergence), with a
trail of the last 60 sessions and today highlighted.
The four quadrants make the readings legible — ① hot & brittle (narrow melt-up,
shakeout risk), ② transition, ③ healthy & broad, ④ real downturn — and the trail
surfaces the actual tell: the ①→④ move (early warning rolling over as the regime
index climbs = divergence resolving downward). Combined still shows as a line in
the score-history chart. Frontend-only; reuses the history endpoint. Lazy-loaded.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Plots the index, early-warning, and combined scores over time beneath the live
gauges, with a 1M/3M/6M/All range toggle and band reference lines — so the trend
and any divergence between the scores is visible, not just today's snapshot.
- Backend: GET /regime/history + get_regime_history (the three scores per
snapshot date from regime_snapshots).
- Frontend: recharts line chart, lazy-loaded so recharts ships in its own
regime-tab chunk instead of nearly doubling the main bundle.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The "warned a median -18 days later" line was the median-over-1-event trap: the
coincident baseline's 60d median is a single lucky event, while breadth warned on
7. Replace it with the honest coverage framing (7/11 vs 1/11) and flag that the
median-lead comparison is unreliable when coverage differs this much.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The event study showed the breadth-divergence signal genuinely leads (warned
before 7/11 drawdowns, ~6 weeks median, where the coincident baseline almost
never did). Surface it live to observe before deciding how to embed it — kept
separate from the index, not folded into its weights.
- regime_monitor daily job now computes breadth-divergence live and attaches a
separate early_warning score plus a combined blend (weighted mean, default
0.6/0.4, configurable via combined_weights) to each snapshot, including the
backfill so the 7/30-day trends populate immediately. Stored in breakdown_json
— no schema change. Best-effort: a breadth failure can't break the index.
- get_regime_monitor returns the index, early_warning, and combined scores each
with 7/30-day deltas.
- Regime tab shows three gauges (generalized ScoreGauge): coincident index,
early warning, and a compact combined blend. Stale snapshots render "—".
Note: the daily regime job now also does a universe-wide breadth scan.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The first run gave only 2 events (N=2 is anecdote, not evidence) and an unfairly
weak coincident baseline, so the +42d lead couldn't be trusted. This makes the
measurement meaningful:
- More, cleaner events: default drawdown threshold 15%→10%, and dedup switched
from "recover to the high" to a rising-edge + cooldown (40d), so distinct
drawdowns each register instead of merging.
- Fair comparison: each indicator now warns at its OWN 80th percentile instead of
a shared absolute 60, removing the artifact that muted the coincident baseline.
- Per-event breakdown (date · depth · breadth lead · coincident lead) so a median
over a tiny sample can't hide an apples-to-oranges comparison — you see whether
both warned on the same drawdown.
- Surface precision/recall (best row) + base rate per indicator — the honest edge
read, not just lead time.
Re-run the Event Study job to regenerate the cached report in the new shape.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The overview's Hit Rate and Expectancy were static lifetime aggregates — they
barely move day to day and aren't actionable at a glance. Replace them with the
current state from open paper trades:
- Open Risk: total $ at risk to stops across open positions.
- Unrealized: summed unrealized R (mark-to-market), with $ P&L and win/loss count.
Computed in the frontend from the already-loaded open trades (tradePnl) — no
backend change. The detailed lifetime stats remain on Signals → Track Record.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Adds a leading-by-construction candidate and the harness to measure whether it
actually leads regime breaks, before any of it earns weight in the live index.
- breadth_service: % of the stored universe above its own 200-DMA + a divergence
score (benchmark price up while breadth falls, nudged by low breadth). Genuinely
leading because it keys on divergence, not level. Not wired into the live score.
- event_study_service: detect drawdown events on the benchmark, then measure each
indicator's median lead time (event-centered) and precision/recall vs. the base
rate (signal-centered). Compares breadth-divergence against the deterministic
coincident price composite (reuses the regime price sub-scores). Price/breadth
only — reproducible, no LLM/FRED.
- Manual "Event Study" job (Admin → Jobs), GET /regime/event-study, and an
inline early-warning panel on the Regime tab with an honest small-sample caveat.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A new /regime tab scoring how far the AI/Tech bull regime has deteriorated
toward a re-rating as a single 0-100 index with per-signal breakdown and a
7/30-day trend. Intentionally decoupled: nothing reads its output to gate or
score trades — the daily-pipeline membership is scheduling only.
- regime_monitor_service: price sub-scores (P1-P6 via Alpaca, like
market_regime), VIX + HY credit spreads via a small FRED helper, weighted
aggregation over available signals (missing source -> n/a, dropped from the
denominator), one snapshot row/day, and a ~90-day history backfill by
replaying the already-fetched series as-of each past day.
- F1/F3 fundamentals proposed by the configured grounded LLM (reuses
sentiment_provider_service config resolution), with a manual override + lock.
- regime_snapshots table (migration 011); endpoints on the existing market
router; admin-editable weights/threshold; standalone /regime page.
Data needs: prices via Alpaca, VIX/credit via FRED (optional key — signals show
n/a without it). No LLM needed for history.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The 5-year backtest confirmed the EV gate adds negative value (high threshold =
worst expectancy) and that 12-1 month momentum is the one price signal with a
plausible, right-signed cross-sectional IC (~0.05). So "qualified" now means:
clears the R:R + confidence floors AND the ticker ranks in the top
`min_momentum_percentile` of the universe by 12-1 momentum that week.
- qualification.py: drop expected_value_r / the EV gate; add a momentum-percentile
gate (duck-typed `momentum_percentile`, only enforced when attached + threshold
set, else defers to floors). Mirrored in frontend qualification.ts.
- activation config/schema: min_expected_value -> min_momentum_percentile
(default 80 = top quintile). ActivationSettings, DashboardPage (ranks/【shows】
momentum instead of EV), and the BacktestPanel sweep follow.
- backtest: rank each ISO week's universe by 12-1 momentum, assign a percentile,
and qualify the top slice; the sweep now sweeps the percentile cutoff.
Also offload the backtest's per-ticker compute to a worker thread so the heavy
~5y run no longer blocks the API event loop (the "backend offline" flicker).
Production setups don't carry momentum_percentile yet — wiring the scanner to
attach it (a universe momentum-rank step) is the next step; until then the live
gate defers to floors while the backtest measures the momentum selection. 330
backend tests pass; frontend build clean.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
