Two bodies of work that touch the same files, so one commit.
Direction and setup-size campaign (2026-09-30 → 10-01, owner's RISK-FIRST rule,
written before the runs):
- SIGNAL: M15 daily-trend veto (factory override 7, xau_strategy.daily_trend_veto
"both"). A finished setup against a clear daily trend (closed D1 bars, Sunday
stubs dropped; close vs its 50-bar EMA AND vs the close 60 kept days earlier)
is removed as the last step of the core. One definition
(signal_aggregator.daily_trend_series) for live, the bar replay and the twin's
host side; D1 is a required frame of the M15 scan; mirrored in
cuda_signal_kernels.py K2. W3 824 / +205.12R / PF 1.73 / max DD 12.4R vs
1105 / +195.79R / 1.49 / 20.9R; 2019 → 2026 1473 / +223.33R / 1.42 / 41.5R vs
2091 / +192.53R / 1.24 / 64.8R; unseen holdout −4.62R vs −6.63R.
- FAILED, not shipped: the veto on M5 (W3 drawdown 10.1R → 15.2R) and on H1
(−9.7R), buy-only and sell-only on M15, the wide-stop cap
(xau_strategy.wide_stop_cap_atr stays 0.0, a research knob).
- New M15 pins: W2 dfc647ee…, OOS e87b6de1…, W3 ad3b0dbd…. M5 / H1 / H4 pins
unchanged. --set xau_strategy.daily_trend_veto=off reproduces the previous M15
pins byte for byte. Twin and reference script MD5-equal on every window;
recorder and feature-export parity re-proved; base-rate table rebuilt.
- DISPLAY (books byte-identical): exposure.py — the lot size for
trade_size.risk_per_trade (new config.json block, off by default, private to
the owner) and the count of alerted same-direction plans still open
(signals.alerted_at, read-only open_alerted_setups); the daily trend in words
on Telegram, the CLI and the dashboard; signals.daily_trend logged.
- providers/oanda: a date window with no bars is an empty page, not an error
(a D1 pad starting on a Saturday could not be fetched).
- Reports only, nothing shipped: seven context screens (no state nominated) and
eight outside data sources (none adds a forecast to gold's own daily trend).
- Independent verification (report section 5.13): every figure reproduced on
both scripts, scoring identical to the previous commit on all four
timeframes, no look-ahead. Caveats recorded there: this is a risk filter, not
a more accurate direction call; nine tenths of the 2019 → 2026 gain is 2022;
the neighbour clause is thin (a simple 100-day average misses the R line by
1.2R); "never adds a trade" is an observation, not a guarantee.
Bug review of the whole codebase (2026-10-01). Signal path clean. 17 defects
elsewhere, plus 4 found by an independent review of the fixes; all fixed, each
with a test; no trade book changed:
- telegram_bot: one _deliver_alert for the candle scan and the level break. The
row is stamped alerted_at BEFORE the send, on a one-worker alert-db pool, and
un-stamped when no chat received it or the task is cancelled mid-stamp, so
two alerts at one candle close count each other and no SQLite write runs on
the event loop. The 5-bar cooldown counts bars of the scan's own frame
(== gpu_backtest._apply_cooldown; clock time released the 22:00 UTC bar after
the settlement pause) and is restored from signals.db at start-up. The
lot-size line goes to the owner's own chat only (a group the owner ran
/autoscan in used to receive it). /status gains a news-model line and escapes
failure details.
- signal_log: mark_alerted returns the stamp it wrote; unmark_alerted;
last_alerted_bars (read-only).
- advisory_outcome: candle continuity is judged bar by bar inside the walk; a
hole after a trade's exit no longer voids it. The stored-candle replay
resolves 108 of 111 logged setups instead of 99, all equal to the live
resolver's R.
- providers/oanda: an empty date window is accepted only when it is 5 days or
shorter and no malformed candle was skipped; a longer one is retried, then
refused, instead of being cached as history with a hole.
- news_engine: blank RSS titles skipped; one unreadable headline no longer
costs the local model its whole batch (checked on the real bundle); model
health recorded; no DeepSeek audit call in a process that does not archive;
event-direction cache keyed per release; peek_week_events never fetches.
- llm_client: chat_json never raises and never logs the API key (requests
quotes the Authorization value in InvalidHeader; error bodies are redacted).
- signal_aggregator: the scan's news block is guarded; the replay path
(use_news=False) assigns exactly the values it did before.
- agent_panel: PANEL_PROMPT_VERSION v2.2 — same prompt text, corrected input
(event timing over the cached calendar week, headlines newest first).
scripts/panel_replay.py replays the logged payload per persona;
scripts/label_scan_outcomes.py counts with an ISO cutoff.
- test_all.py: no ALTER TABLE … DROP COLUMN (the live box has SQLite 3.34);
tests that write Parquet print a notice and return without pyarrow.
Verification after the last code change: suite 632 passed, 0 failed (also with
both Parquet engines blocked and FB2_BACKEND=cpu, the live box's view); the
five reference MD5s reproduce on both backtesters, 0 cache fallbacks; Module 37
green; static Python 3.9 / SQLite 3.34 check clean on every touched file.
Evidence: backtest/research/daily_trend_campaign_2026-09-30.md,
context_screens_2026-10.md, new_inputs_2026-10.md; CLAUDE.md sections 2, 4, 6,
8, 9, 10 and 11; pair_signals/xauusd.py docstring (M15 override 7).
Agent panel v2: personas return p_win anchored to the book base rates with a
code-computed decision context; verdict = equal-weight mean (verdict_source
"mean"); only the macro persona runs live (agent_panel.personas ["macro"]);
prompt version and exact payloads logged; offline replay harness
scripts/panel_replay.py; base-rate table agent_panel_base_rates.json
(scripts/build_panel_base_rates.py). Backtester `strategy` column now carries
the generator's own stamp (label-only; five reference books re-pinned, all
62 other columns identical).
News corpus (after evaluating the owner's ML-NEWS scikit model against
DeepSeek: golden set 39/78 vs 78/78, out-of-sample agreement 64% against a
90% self-agreement ceiling; verdict: fallback only, not a replacement):
- NewsSentiment.xau_score + archive column xau_score keep DeepSeek's gold
score for every headline (930 of the first 1,546 DeepSeek rows had none);
an existing newsdata.db gains the column in place on first open
- headlines naming no tracked currency are scored and archived
(currencies_json []) but never returned to the platform
- _apply_llm_sentiment sends every new headline in its cycle, 25 per call;
a failed call ends the cycle's sending
Dashboard publisher never writes a database: main() calls
app_config.set_db_writes_for_process(False), honoured by signal_log_enabled()
and news_archive_enabled() (owner decision: the bot is the single writer).
Test suite: the hermetic app config now points both writers at a
suite-private temp dir — the RSS fixture tests were writing fixture
headlines into the real logs/newsdata.db — with a Module 32 test pinning it.
529 tests.
Signal path
- A shipped setup always names a direction: grade C needs confidence
>= 45 (gate 6c grants B at >= 45) while BUY/SELL needs >= 50, so C/B
reports reached the alert gate as NEUTRAL with a full setup. The
backtester traded them (the replay never reads final_signal) while
Telegram rejected NEUTRAL first — 5/91 trades, +3.7R of +22.2R, in
the H1 12-month book. _attach_core_setup stamps the setup's direction
and repairs the pre-gate action text; no-setup reports stay NEUTRAL.
- analyze_pair fails the scan when ANY required frame is missing
("DATA UNAVAILABLE:", scan_kind='failed'); a lost confirmation frame
used to run with an unearned -15 MTF penalty.
Outcomes and labels
- advisory_outcome.resolve_locked_floor: a gap the database cannot fill
resolves at the locked trailing stop (GAP_LOCKED, result.floor) when
the stop had crossed the entry; the rebuild fires on both gap reasons
(rows 915/920: +1.14R / +0.84R floors; resolved sum -2.46R -> -0.48R).
- label_scan_outcomes: SCAN_LABEL_MAX_AGE_H = 72 h, stale rows never
anchor the shared bar stream, labeled_at bumped on re-examination,
_stream_since warns at its row cap (the Labor-Day pile would have
blinded scan_outcomes around 2026-09-14).
Providers and scheduling
- The daily settlement pause (Mon-Thu 17:00 New York) is a scheduled
closure for _has_latest_closed_bar (whole-span label walk-back) and
_is_data_fresh (closed seconds are not age); bot and dashboard skip
scans whose just-closed label sits in the pause (61 false stale rows
in three nights).
- fetch_range retries a failed page in place (three failures on one
window raise) and logs an ERROR for interior gaps of >3 unscheduled
bars.
- pd.Timestamp.utcnow() replaced in providers/base.py and engine.py;
requirements pin pandas<4, numpy<3.
- telegram_bot: boundary loops share one scan per bar with the breach
handler (_remember_scan keys on the analysed bar; breach defers 20 s
after an M15 boundary); the rotating file handler attaches in main()
only (the test suite used to write into logs/telegram.log).
- dashboard_publisher: catch_up_timeframes re-scans boundaries missed
while a cycle overran or the process was down.
Backtester and engine guards
- _replay_span returns the per-span GPU cache-miss count; run_backtest
sums, logs it (must be 0) and writes cache_fallbacks to the manifest.
- regime_weight_table raises on a partial regime_weights_override.
Verification: 519 tests; M5/M15 2-yr, M15 OOS, H1/H4 3-yr books
byte-identical before and after; live signals.db untouched (checked on
a copy). CLAUDE.md carries the dated entry and the blocked-hours union
semantics that every book was validated under.
Claude-Session: https://claude.ai/code/session_0139xz1J6YccndA2be6yFnEo
- providers: _to_oanda_instrument / _to_tiingo_ticker / _to_td_symbol no longer
guess a wire symbol for pairs that are not registered — the registries are
the only source, so an unknown symbol raises the provider's DataIntegrityError
instead of silently fetching something else. Every scanned symbol is validated
against PAIR_INFO at import, so nothing reachable changes.
- main / telegram_bot _fmt_price: the sub-$10 five-decimal branch could never
fire for gold.
- news_engine._parse_pair: BASE/QUOTE only; the Yahoo "=X" fallback was
unreachable (its test goes with it).
- dashboard_publisher.event_to_dict: drop minutes_until (frozen at publish
time, misleading) and is_high_impact — dashboard.js never read either.
- static/dashboard.html: unused id="cal-table".
Tried and reverted: trimming the LogRow fields nothing in analyze_signal_log
reads — the tests read them to verify the loader round-trips those DB columns,
so they stay.
Suite: 460 passed, 0 failed.
Claude-Session: https://claude.ai/code/session_0156YhogLytzj9P2iH1skGbL
Removed (all recoverable from git history):
- llm_provider_switch_plan.txt: 2026-08-08 DeepSeek/Anthropic multi-provider plan that
was never implemented (llm_client.py is DeepSeek-only, no `anthropic` anywhere)
- docs/superpowers/specs/2026-07-21-centralized-config-design.md: spec of the
config.json migration that merged the same day; its plan sibling was already
deleted in b936d44. app_config's docstring pointer goes with it.
- scripts/compare_oanda_tiingo.py: Phase 0 recent-tail smoke test, superseded by the
Phase 1/2 study scripts (result recorded in the test plan)
- backtest/research/fetch_oanda_m15.py + oanda_td_divergence.py + its by-hour CSV:
the 2026-07-24 Oanda-vs-Twelve-Data study, superseded by the 2026-08-14 feed
divergence report (which keeps a one-line citation)
- backtest/research/burst_profile.py and hour_analysis.py: superseded by burst_map.py
and book_report.py
- backtest/research/panel_payload_drytest_2026-08-15.py: one-off live DeepSeek probe;
its .jsonl evidence stays
Added to git: the three 2026-08-14 research reports (feed divergence, re-pin
verification, signal parity), their CSV, and docs/data_source_change_test_plan.md -
CLAUDE.md cites them as standing evidence and their driver scripts were already
committed. The test plan no longer refers to auto-execution.
Hygiene:
- .gitignore: drop oanda_state.json (daemon removed 2026-09-03) and the vanished
backtest/trailgrid dirs; ignore .coverage
- docs/architecture_diagram.py only writes the PNG when run as a script (it used
to plot on import); test box refreshed to 461 tests / 31 modules; PNG regenerated
(the committed one still drew the removed daemon)
- backtest/instructions_for_backtest.txt: manual-journal head replaced by the
actual reporting checklist; the 2026-09-06 addendum is unchanged
- doc drift: README/publisher list all six published files; news_summary.php says
4 h (not 24 h) and drops the pre-id sha1 fallback whose window closed;
analyze_signal_log lists six lenses and --scan-outcomes; agent_panel cost model
says 4 requests by default; tiingo comment cites the NY-anchored weekend;
Module 21 title no longer says "execution lifecycle"
Suite: 461 passed, 0 failed.
Claude-Session: https://claude.ai/code/session_0156YhogLytzj9P2iH1skGbL
Zero callers anywhere (tests included), verified by grep/AST:
- dashboard_publisher.DashboardPublisher.publish_all (run_cycle inlines both publishes)
- signal_log.SignalLogger.advance_with_bars (the backfill script uses
backfill_seeds / resolve_from_store / reseed_unresolvable) and the never-read
SignalLogger.path property plus its write-only self._path
- llm_client.reset_llm_client (tests reset the singleton by assignment)
- market_outlook._last_run_ts, residue of the old "now - last < 3600" dedup;
_last_run_hour (the UTC hour bucket) is the live key
- news_engine FundamentalContext.event_impact_on_pairs: written once, read by
nothing; its only feeder NewsEngine._get_affected_pairs and that helper's
unit test go with it
- position_sizing.LIVE_DEPTH_BARS (referenced only by its own docstring, which
now states the depths inline), the unused Iterable import and the unused
atr_ok parameter of _fill_geometry
- analyze_signal_log: unused `field` import and the unused `rows` parameter of
persona_scorecard / news_outcome_buckets (both read the DB directly)
The two backfill/label scripts' --db help text now names the config.json
setting it actually falls back to.
Suite: 463 passed, 0 failed (one test removed with its subject).
Claude-Session: https://claude.ai/code/session_0156YhogLytzj9P2iH1skGbL
New violent_watch.py assesses each scan from the cached Forex Factory week events, the
UTC clock and the report's own indicator states, and stamps SignalReport.watch_line
post-hoc (telegram alerts, CLI, dashboard). A standalone heads-up goes to the owner on
the fastest scanned timeframe when the level is "hot", once per UTC hour per trigger
set, capped per day. Config block `violent_watch` (enabled False, alert_line, headsup,
max_headsup_per_day, headsup_min_level); env VIOLENT_WATCH_ENABLED.
Rule chosen from a 3-year bar-by-bar sweep (backtest/research/watch_rule_eval.py,
recorded in sizing_campaign_2026-09.md): hot = high-impact USD release within 30 min
(before or after) OR a hot clock slot (weekday 12-14 UTC, 01 UTC, Sunday 22-23 UTC)
with at least one price-extreme reading (outside Bollinger bands, RSI <30/>=70, outside
Keltner); ~8.6% of bars, next-bar odds 3-5x normal, ~4 hot hours/day. watch = clock
slot alone or two price-extreme readings (~2x). Context readings (ADX rising, extreme
volatility, transitioning, MACD acceleration) are phrases only - letting them raise the
level flagged 27% of bars at ~2x and would have sent ~13 heads-ups/day (rejected).
Direction sentence: DOWN when bearish readings dominate (70-78% on both TFs), UP on M5
only. Never a gate or exit: every open-trade protection tested lost money.
Test-locked out of analyze_from_dataframes / engine / backtester. Module 30 (18 tests).
Suite: 453 passed. Guide PDFs not rebuilt.
Claude-Session: https://claude.ai/code/session_01RWV2yLt3YXHHGVYHSQU2EE
Deletes oanda_daemon.py, oanda_executor.py, their 28 tests and the daemon-only
config keys (oanda.lot_size/quality_gate/max_hold_bars). The Oanda data
provider and credentials stay — it is the live candle feed. 402 tests.
Claude-Session: https://claude.ai/code/session_01FC4s6VCURFte4dub4xKxYL
Page now uses Bootstrap 5.3 color modes (data-bs-theme), Bootstrap Icons,
and Bootstrap modals. Custom code shrinks to dashboard.css (app tokens,
score bar, signal accents) and dashboard.js (rendering/polling logic,
ported verbatim from the inline script). dashboard_publisher copies the
new css/js into the docroot; all 381 tests still green.
main.py: --panel runs the agent panel on demand (force bypasses
enabled/surface/quality toggles; daily budget + LLM cap still apply),
prints the verdict + persona takes, and report_to_dict carries the four
panel keys — which auto-propagates them into the dashboard's
snapshot.json via report_to_webapp_dict. dashboard_publisher attaches
in scan_tf gated by agent_panel.dashboard (default off); dashboard.html
renders an "AI panel (advisory)" section in the TF detail dialog.
Claude-Session: https://claude.ai/code/session_01SisdfkxnXNL9iZsXxN3T15
Three display-side fixes, no signal-logic changes:
- run_cycle publishes snapshot.json BEFORE the news refresh — news I/O
(FF + 4 RSS + possible DeepSeek calls) took 20-30 s on TTL-expired
cycles and kept fresh signals off the page (publish_all split into
publish_snapshot/publish_news, kept for boot)
- page polls every 5 s (was 20 s) using conditional GETs: dropped the
?t= cache-buster + no-store so Apache answers unchanged files with
bodyless 304s
- boundary refetch sniper re-armed: fires 2 s after next_scan_epoch
regardless of distance (the old delay<POLL_MS guard would have been
dead code at 5 s polling)
New Module 20 test locks the snapshot-before-news ordering. 352 tests.
Claude-Session: https://claude.ai/code/session_017mbXs9HRawZhD1uZ3ze7zQ
2026-08-04 Fable 5 QA audit, final code batch.
- Boundary math: removed the provably-dead `remaining <= buffer` guard
from all three scheduler copies (518,400-instant frozen-clock sweep:
never fired) and documented the exact-boundary-instant semantics.
- websockets/websockets.client loggers pinned to INFO so a DEBUG run
can never write the TD key (connect URI) or Tiingo auth frame into
the 30-day rotating log. (.env also chmod 600, untracked.)
- Cooldown pass factored into _apply_cooldown (pure, testable) — the
only sequential replay rule finally has direct tests.
- New simulator behavior tests (previously ZERO coverage of the trade
resolver): same-bar SL+TP tie → SL-first, gap-through-SL fills at
the open, TIMEOUT pricing + round-trip spread charging, trailing
ratchet arms at bar close and fills next-bar-only, cooldown ordering.
- CLAUDE.md synced to verified reality: 338 tests/21 modules; three
weekend-implementation copies caveat; throttle claim corrected
(single-flight, TD-only throttle); daemon trail/cooldown parity
caveats (once-per-OBSERVED-bar, wall-clock cooldown) + OPEN_ONLY and
reconcile notes; CP-path gate semantics documented as validated
behavior; new "known open items" section for the owner-decision
findings (weekend DST constant, spread-in-trigger rule-6 item, H4
seeding divergence, FB2_EMA_LO).
Gates: suite 338/338 green; pinned M15 book and M5 HEAD baseline both
reproduced identically after the cooldown refactor.
Claude-Session: https://claude.ai/code/session_01UnZkzeFcTu9agFg8BDh2tn
- dashboard_publisher.py: standalone candle-close daemon that atomically
writes snapshot.json/news.json/dashboard.html to an Apache-served dir
(DASHBOARD_OUT_DIR). Fully independent of telegram_bot/oanda_daemon —
local confirmation map + boundary math, no imports either way, no new
deps, no open port. Due-TF classification from the RAW wake time.
- static/dashboard.html: self-contained dark page — hero rail, four TF
cards (score bar, 3x3 indicator grid, MTF, setup, reasons), DeepSeek
market context, week economic calendar, scored newswire. Clock offset
from the HTTP Date header (publish-time epoch is stale between closes).
- news_engine.get_week_events(): additive read-only accessor over the
cached FF week; no signal path calls it.
- deploy/: systemd unit + live-server (LAMP/SELinux) checklist.
- test_all.py: Module 20 (9 tests) + get_week_events test; 296 green.
Claude-Session: https://claude.ai/code/session_01Wc9ZoqKLYBT2QJcpRWKoGm
Harwinder Sekhon