- analyze_pair(context=...): no caller ever supplied it (main, telegram_bot,
pair_signals, tests), so the value was always None; the parameter and the
pass-through to analyze_from_dataframes go (analyze_from_dataframes keeps
its own context parameter).
- The three specific "SELL FILTER: quality|volatility|regime" stale-prefix
entries were shadowed by the general "SELL FILTER: " entry in the same
startswith() tuple; every emitter carries the general prefix.
- chart_patterns: the detectors never read the Open series, so the `o`
parameter is dropped from the three detectors, the PATTERN_DETECTORS
lambdas and the dispatcher.
- Corrected the pb_funnel/cp_funnel comment: nothing reads those counters
(the "read by backtest tooling" claim was stale); they stay as cheap
diagnostics.
Parity: 12-month M5 and H1 books regenerated byte-identical
(md5 a28fed4becd056466c26d6a947e1a0e5 / d20405ef64f069770c258bb9bed1ac90).
Suite: 461 passed, 0 failed.
Claude-Session: https://claude.ai/code/session_0156YhogLytzj9P2iH1skGbL
result._kc_squeeze / result._kc_squeeze_released were assigned by both the live
TechnicalEngine and the backtester's GPUTechnicalEngine and read by nothing:
the only four occurrences in the repo were the assignments. The squeeze state
still feeds the Keltner signal text where it is computed. Removed from both
engines in one commit (rule 4).
Parity: 12-month M5 and H1 books regenerated byte-identical
(md5 a28fed4becd056466c26d6a947e1a0e5 / d20405ef64f069770c258bb9bed1ac90).
Suite: 461 passed, 0 failed.
Claude-Session: https://claude.ai/code/session_0156YhogLytzj9P2iH1skGbL
main.py kept a private confirmation table and passed it into the pair factory,
which honours any non-None list. For M5 that table said [M1, M15] while the
factory, telegram_bot.TF_CONFIRMATIONS and dashboard_publisher.CONFIRMATIONS
all use the validated [M15, H1] - so `main.py --timeframe M5` scanned with an
unvalidated pairing (and an extra M1 fetch) that no other surface used.
- build_config now returns PAIR_PRODUCERS[pair](tf, None): the factory map is
the single source of truth. The unreachable bare-PlatformConfig fallback is
gone here and in telegram_bot._run_signal_sync (every symbol that reaches
either is registered).
- --timeframe offers the four validated primaries (M5, M15, H1, H4). M30 and
D1 were never validated and silently fell through to the generic [M15, H4]
map; they are removed from the CLI.
- The "all valid timeframes" test now asserts each CLI timeframe's
confirmation list equals pair_signals.xauusd._CONFIRMATIONS - the check
that would have caught this.
CLI behaviour change: M5 confirmations [M1, M15] -> [M15, H1]; M30/D1 rejected.
Bot and dashboard scans are unchanged.
Suite: 461 passed, 0 failed.
Claude-Session: https://claude.ai/code/session_0156YhogLytzj9P2iH1skGbL
- telegram_bot._format_scan_summary: multi-pair "auto-scan summary" leftover;
production sends per-report format_signal_message. Its only caller was a test.
- telegram_bot.scan_keyboard: thin wrapper only a test called; main_menu_keyboard
already builds from _scan_button_rows directly.
- telegram_bot.AUTOSCAN_CONFIRMATIONS was byte-identical to TF_CONFIRMATIONS;
the candle loop now reads the one map (app_config comment updated).
- SignalLogger.news_for: one-line wrapper over the module-level read_news that
every real reader uses; the test now calls read_news like its neighbours.
- pair_signals.get_supported_pairs: PAIR_PRODUCERS is the registry; the test
lists it directly.
Suite: 461 passed, 0 failed (two helper-only tests removed).
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
- backtest/diagnose_filters: unused BacktestConfig import
- pair_signals/__init__: unused PlatformConfig import
- scripts/shadow_scan: unused pandas import
- research burst_precursors / calendar_impact / duka_spread: unused sys / COST / struct
- test_all: MagicMock, StringIO, Colors and two function-local imports that
nothing in the test bodies used
- telegram_bot: ViolentWatch is only a type hint -> imported under TYPE_CHECKING
compare_oanda_tiingo.py and oanda_td_divergence.py are left alone here because
the hygiene commit deletes them.
Suite: 464 passed, 0 failed (unchanged).
Claude-Session: https://claude.ai/code/session_0156YhogLytzj9P2iH1skGbL
The candle provider needs only oanda.api_token + base_url; account_id belonged to the
auto-execution daemon removed 2026-09-03 (31002cb). Removed from config.json.example and
the unused oanda_account_id() accessor deleted; the key stays in _KNOWN_OANDA so existing
config.json files keep loading. CLAUDE.md env-var list updated. Test locks all three.
Suite: 464 passed.
Claude-Session: https://claude.ai/code/session_01RWV2yLt3YXHHGVYHSQU2EE
- test count no longer hardcoded (463 / 31 modules as of 2026-09-06)
- main.py --outlook, backtest --set / --export-features listed
- delivery surfaces include the web dashboard; SignalReport consumers include the publisher
- scikit-learn / lightgbm are research-only venv installs, never requirements
- rule 1: owner preference (2026-09-05) that backtests go back at most 3 years, with the
3-year baseline books and where they live
- "Current state notes" header un-dated; the 2026-08-14 canonical-book line marked superseded
by the 2026-09-03 book (M15 reference unchanged since 2026-08-04)
- docs: PDF builds noted as behind the HTML guides
Claude-Session: https://claude.ai/code/session_01RWV2yLt3YXHHGVYHSQU2EE
New additive columns on every logged scan: bar_ts (primary closed-bar label, indexed with
timeframe), engine_fingerprint (hash of the scoring config incl. the regime weight table in
force - SignalAggregator.engine_config_fingerprint, twin of the gate fingerprint), code_version
(short git SHA), penalty_tags_json / penalty_total / momentum_fading / exhaustion_count, and
post-hoc watch_level / watch_kinds / watch_line written by violent_watch.attach_watch via
signal_log.update_watch. Each indicators_json entry now also carries eff_weight (base weight x
regime multiplier, the weight the composite actually used) and wscore.
engine: IndicatorSignal.effective_weight / weighted_score are stamped inside _compute_composite
(record-keeping only); regime_weight_table(config) is the single source of truth for the
multiplier table (override honoured). Composite output byte-identical (120-report hash proof).
New table scan_outcomes: model-free forward moves per scan (fwd_1h/4h/24h in $ and ATRs,
mfe/mae over 24h, burst_1h, bars_used, complete) measured on the stored candle stream with the
advisory model's continuity rule; labelled opportunistically at the end of log() (time-boxed,
throttled, idempotent) - no daemon; scripts/label_scan_outcomes.py drives the backlog
(--dry-run is read-only). analyze_signal_log --scan-outcomes: forward move + hit rate by
TF x signal/grade with a NEUTRAL baseline and burst rate by watch level. Readers dedup by the
first row per (timeframe, bar_ts).
Module 31 (10 tests). Suite: 463 passed. Backtester untouched (test-locked).
Claude-Session: https://claude.ai/code/session_01RWV2yLt3YXHHGVYHSQU2EE
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
Walk-forward "second opinion" stake multiplier (meta-labelling on 65 decision-time
features, 3yr Oanda books @ $0.65) FAILED the pre-registered rule on M5 (clean null)
and M15 (lift inside the label-shuffle null, explained by BUY-vs-SELL). Nothing that
changes numbers ships; the 12-month M5 book re-run is byte-identical to the pinned one.
Behaviour-neutral plumbing:
- position_sizing.build_features (65 features; multiplier path returns 1.0, no artifact)
- SignalReport.penalty_tags / penalty_total / momentum_fading (record-keeping)
- TradeSetup.stake_multiplier = None (reserved)
- gpu_backtest --export-features (default export stays the pinned 63 columns; extras
forced to the tail even when the first trade lacks an indicator)
Research tools (backtest/research): book_report, burst_map, burst_precursors,
open_trade_bursts, calendar_impact, burst_indicator_map, sizing_model, watch_rule_eval.
Findings recorded in backtest/research/sizing_campaign_2026-09.md: M5 stretch measures
are positive in both halves; every open-trade protection against violent bars loses on
both TFs; high-impact USD releases cause 20-31% of violent bars but trades held through
them do better; violent bars come when price is already at an extreme, not from calm.
Module 29 tests (13). Suite: 435 passed.
Claude-Session: https://claude.ai/code/session_01RWV2yLt3YXHHGVYHSQU2EE
None of these touch the signal path. The 12-month M15 book
(2024-03-31..2025-03-30, $0.65, cached Oanda bars) is byte-identical
before and after (md5 c59d3e7e685c3c880b614640adfea74b, 375 trades),
and signal/indicator logging to logs/signals.db is unchanged — verified
end to end: per-TF indicators for all 3 TFs, 14 candles each, MTF and
reasons all still persisted.
agent_panel: the >=2-take quorum guards the CHAIR's synthesizer spend,
but ran BEFORE the macro branch — so the shipped default
(verdict_source="macro", which never calls the synthesizer) silently
dropped a good macro verdict whenever the other three personas were
slow. Quorum moved below the macro path.
analyze_signal_log: _forward_return clamped to the last available bar
when the horizon had not elapsed, reporting a near-zero "forward move"
for every row logged within `hours` of the end of the data — on every
run, blended into the hit-rate/mean-move aggregate. Now returns None.
analyze_signal_log: persona_scorecard iterated raw rows through an index
that maps EVERY member row of an event, so a re-logged scan appended
the same event R twice. One vote per event, matching
news_outcome_buckets. Measured inflation on the live DB: 1.03x.
signal_log: dedup required a non-negative logged_at gap, but logged_at is
stamped before the row wins the write lock (busy_timeout 5 s), so two
processes logging one setup at a boundary can invert timestamp order
against id order and seed a second event. Now abs(gap); same in
backfill_seeds. Zero occurrences in the current 366 setup rows.
advisory_outcome: the catch-all turned real evaluator faults into the
same UNRESOLVABLE used for legitimate weekend gaps, with nothing in the
log. Still fail-safe, now logged.
llm_client: only the "cap" warn-once flag was ever reset, so in a daemon
the second and every later network/http/parse outage logged at DEBUG
only. Cleared on UTC-day roll and re-armed by a recovered call.
dashboard.js: renderCards() redraws the selector for every timeframe but
was gated on the SELECTED one changing, leaving the other buttons stale
(up to 4 h on H4) while renderHero's rail already showed the new value.
news_summary.php: atomic_write treated a short write (disk full) as
success, publishing a truncated body the cache-first branch then served
forever; and the daily cap was charged before the no-key check and
before the stampede lock re-checked the cache, so a click burst could
exhaust the 150/day budget with zero LLM calls.
migrate_signal_log_news: logged_at is ISO with 'T' while SQLite's
datetime() uses a space, so string-comparing them put the whole cutoff
calendar day on the wrong side and it never pruned. NOTE: this now
deletes one day more than before — it only runs when invoked by hand.
Tests 414 -> 422 (new Module 28, one per fix). The existing
"<2 valid takes" test was retargeted at the chair — the case it actually
protects — rather than deleted, with new coverage for macro-alone.
Not fixed, recorded for the owner:
- Gate 6c's boost condition is textually identical to the C-grade
definition, so every C in a "transitioning" regime is promoted to B
before gate 6e reads it, making sell_min_quality's exclusion of "C" a
no-op on M15/H4 (H1 and M5 are immune by other means). The backtester
runs the same code, so every pinned book already includes this —
changing it is a rule-1 revalidation event.
- Safe-haven/geopolitical headlines score exactly 0.00 in the keyword
fallback and are now dropped entirely by the ±0.1 neutral filter,
contradicting the platform's own gold doctrine. Bites only when
DeepSeek is capped/disabled/failing.
Claude-Session: https://claude.ai/code/session_01Ah5EB1goi5inQmSd37Ne6a
Verdict from the 3-week signal log (backtest/research/news_sentiment_value_2026-09-04.md):
news_sentiment is a trailing-24h echo of price (r +0.67 with the past day, +0.03 with
the next; most bullish 2 h after the 08-25 top, bearish 44 h later; most bearish at the
09-02 low, bullish 16 h later). Per-headline LLM labels are correct; the 12 h pool and
the averaging are what destroy the information. Both gating flags stay False.
- news_engine: _LLM_SUMMARY_SYSTEM rewritten for someone who has never traded (no
acronyms, two worked examples); summary payload newest-first with the platform's own
gold direction; reply cap 300 -> 400 chars.
- config: headline_max_age_seconds 43200 -> 14400; RSS items without a parsable
pubDate are dropped (they used to be stamped "now" and never aged out).
- news_engine.get_fundamental_context drops headlines whose every relevant score is
inside +-0.1 (_is_neutral_headline) before the per-currency mean; news_sentiment
from this date is a mean over directional <=4 h headlines (log comparisons split here).
- static: dashboard copy for the 4 h pool; news_summary.php prompt gets the same style rule.
- analyze_signal_log: --news (under --stored-candles) prints sentiment lead/lag with
split halves, sentiment at the window high/low with flip lags, and outcome buckets by
direction x news x macro stance; LogRow gains news_sentiment/event_risk; _row_index shared.
- tests: 406 -> 414 (age window, undated drop, neutral filter, summary prompt/payload/cap,
--news helpers, load_rows round-trip); RSS fixtures now carry a pubDate.
- docs: user/beginner guides, CLAUDE.md, deploy README.
Claude-Session: https://claude.ai/code/session_0169BgFtWjp1SEAa5392Q9jH
agent_panel.verdict_source defaults to "macro": the macro take's stance is the
verdict, the synthesizer call is skipped (4 LLM calls per panel instead of 5);
"chair" restores the four-voice consensus + OPPOSE guard. Verdict source is
cached per mode and logged (panel_verdict_source). 406 tests.
Claude-Session: https://claude.ai/code/session_01FC4s6VCURFte4dub4xKxYL
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
Add panel_verdict, panel_confidence, panel_rationale, panel_takes_json
columns to the signals table (additive, idempotent ALTER TABLE migration
for existing DBs). _report_row now reads the panel fields attach_panel
writes onto the SignalReport, so LLM panel verdicts stop evaporating on
process exit. Also documents the Oanda re-pin (round_trip_cost stays
$0.30 for cross-book comparability and the live TP gate; $0.65 is the
measured headline) and adds the feed-divergence / parity / shadow-scan
study tooling referenced by CLAUDE.md.
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.
New signal_log.py logs each SignalReport to logs/signals.db via a
fail-safe hook in SignalAggregator.analyze_pair — the live-only entry
point used by the bot, daemon, CLI and dashboard. Backtester calls
analyze_from_dataframes directly, so live==backtest parity is preserved
(test-locked). Rows carry signal/grade/price/spread, MTF + trade-setup +
reasons/warnings JSON, and news-at-scan-time (calendar events + scored
headlines JSON via NewsEngine class-level caches).
Config: signal_log block (enabled, path; env SIGNAL_LOG_ENABLED/PATH),
source tagged per consumer (telegram/oanda_daemon/cli/dashboard).
381 tests pass (24 modules).
poll() now compares raw payload text and re-renders only what a changed
file can affect, preserving selection, disclosure, and scroll state. Hero
freshness reflects publish time (STALE warning past 15 min while market
open), and countdowns resolve their wrap interval from data-interval
instead of reverse-looking shared TF boundaries in snapshot.timeframes.
Prompt-only change (static constants; plain-language output contract
byte-identical). Ported from virattt/ai-hedge-fund's persona rubric:
- _TAKE_CONTRACT hard rules: reason only from the JSON given, never
invent numbers/events/levels; thin or missing evidence -> neutral
with confidence below 30 (deferring to role-specific rules).
- Anchored confidence bands in the contract and synthesizer, replacing
the unanchored "how sure you are".
- Per-stance support/oppose/neutral criteria for macro, technical, and
risk (risk's missing-setup->oppose folded into its oppose bullet).
- One plain-language support example beside each oppose example for
macro/technical/risk, fixing the all-oppose few-shot bias.
Contrarian's designed skeptic tilt untouched.
News-engine prompts untouched (pinned by 78/78 + 18/18 validations).
374 tests green; real-DeepSeek smoke: macro correctly answered
neutral/20 on empty news context, confidences spread 20-60 across the
bands, all notes <=25 words, no jargon.
Claude-Session: https://claude.ai/code/session_01TyZx9iRJwfbPTPnCBqcwTR
Reference plan only - no code changes. Describes the BaseLLMClient
refactor, AnthropicClient on the official SDK, per-consumer routing via
a config.json "llm" block, tests, commit sequence, and effort estimate
for the day we route the agent panel to Claude while news stays on
DeepSeek.
Claude-Session: https://claude.ai/code/session_01SisdfkxnXNL9iZsXxN3T15
Owner request: panel notes and rationale must read like plain everyday
English for a non-trader. Style rule added to the shared take contract
and synthesizer prompt, all few-shot examples rewritten in the target
voice (examples carry the style), and the Telegram votes line now spells
out full stances ("macro: support") instead of "macro:sup".
Before: "BUY against Bollinger SELL and price above upper band; 4h
neutral, mixed MTF" → After: "The price is above its usual range, and
the bigger picture is not clearly rising, so buying now is risky."
Claude-Session: https://claude.ai/code/session_01SisdfkxnXNL9iZsXxN3T15
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
Auto-scan and level-breach alert paths attach the panel AFTER the
quality gate and dedup decision (no LLM spend on suppressed alerts),
via run_in_executor so the event loop stays free. Alert message gains a
two-line 🤖 AI Panel block (verdict + confidence + rationale, persona
votes); /status shows the daily panel budget when the feature is on.
Claude-Session: https://claude.ai/code/session_01SisdfkxnXNL9iZsXxN3T15
ai-hedge-fund-style panel: 4 DeepSeek personas (macro, technical, risk,
contrarian) review a finished SignalReport concurrently on a
panel-private thread pool, then a synthesizer chair issues
AGREE/NEUTRAL/OPPOSE + confidence + rationale. Advisory/display-only by
construction: consumers attach post-hoc via attach_panel; the fields
live on SignalReport with empty defaults and analyze_from_dataframes
never touches them (backtest parity, locked by test).
Spend control on top of the shared 500/day client cap: max_panels_per_day
UTC budget (default 20), exact per-bar result cache, and a reuse TTL
keyed (symbol, tf, direction) so a persisting signal re-serves its
verdict across bars instead of burning 5 requests per bar. <2 valid
takes skips the synthesizer; any failure degrades to no panel.
Claude-Session: https://claude.ai/code/session_01SisdfkxnXNL9iZsXxN3T15
End-to-end map: external services → providers/news layer → signal core
(engine + factory + aggregator) → SignalReport → four delivery surfaces,
plus the backtester replaying the same core. Regenerate with
venv/bin/python docs/architecture_diagram.py after architecture changes.
Claude-Session: https://claude.ai/code/session_01Aq1jZ6jBsBdEC2xT3u46SA
The practice API rejects ~15-20 requests/day with a spurious 401
"Insufficient authorization" while the same token succeeds on adjacent
requests; each one silently cost a full scan cycle on that timeframe.
One retry after RETRY_DELAY_S (2 s) absorbs these plus transient
5xx/network faults. Real credential failures fail both attempts and
raise as before; other 4xx (bad request, 429) are never retried.
Tests: transient-401 recovery, persistent-401 raise, 400 not retried.
Claude-Session: https://claude.ai/code/session_01Tujtmmhxj9mxKjPFSoVjmP
Owner-supplied page design replacing the dark-only v1: Bootstrap 5
colour tokens with a luma-inverted dark mode (toggle + system-pref +
localStorage), compact clickable TF cards opening a full-detail modal
(all-nine indicator table with value/conf/weight, price ladder of key
levels vs spot, per-confirmation-TF drilldowns, provenance), newswire
aggregate sentiment box, Inter/JetBrains Mono webfonts.
Re-applied the c70f58a sync fixes the source copy predated: 5 s
conditional-GET polling and the +2 s boundary refetch sniper. Data
logic otherwise unchanged; all fields verified against
report_to_webapp_dict output.
Claude-Session: https://claude.ai/code/session_017mbXs9HRawZhD1uZ3ze7zQ
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
Validation (llm_news_eval.py harness + 78-headline golden CSV + verdict
doc): headline scoring 78/78 vs keyword baseline 24/78 — validated;
event gold-direction calls misread close K/M numeric comparisons ~11%
of the time (both claims cases in sample, JOLTS 8.79M vs 8.84M).
Fix: event payload now carries code-computed "vs_forecast" (from
EconomicEvent.surprise) and the prompt gains an explicit inverted-
metrics rule + worked claims example — iteration 1 (field alone) fixed
the arithmetic but exposed a masked inversion error. 18/18 on live
re-verification (4 misreads fixed, 11 regression cases clean, 3 fresh
both-side probes).
/status: new "News & AI" section — per-source health for the calendar
chain (which of FF/MyFXBook served), each RSS feed, and DeepSeek
(daily count, last error kind), written passively by the existing
fetch paths under _cache_lock. Failures WARN once on transition
(repeats DEBUG, recovery INFO) so the rotating log carries outage
stories without 10-min spam.
test_all.py: +5 Module 19 tests (351 total); also carries the Module 22
fixed-RR-TP tests from the prior research session (shared file).
Replay artifacts dir gitignored like commit_ladder.
Claude-Session: https://claude.ai/code/session_017mbXs9HRawZhD1uZ3ze7zQ
Hard TP at N×risk beats the trail on all 2024+ windows but the grid is
monotone to 3R (trend artifact) and M15 rr20 goes negative in 2021+2023
with doubled DD — trailing exits stay. Flag is research-only; its
Module 22 tests land with the next commit (shared test_all.py).
Claude-Session: https://claude.ai/code/session_017mbXs9HRawZhD1uZ3ze7zQ
Deletion was already staged in the working tree by the owner; the
roadmap was approved 2026-07-24 as reference only and its plan file
lives outside the repo. Content remains in git history.
Claude-Session: https://claude.ai/code/session_01UnZkzeFcTu9agFg8BDh2tn
Harwinder Sekhon