{ "generated_at": "2026-06-13 01:59 EDT", "incidents": { "OVERALL": [ { "incident_id": 128, "asset_class": "OVERALL", "source_ref": null, "title": "S-tier/A-tier score-band tiles on /audit/ are survivorship + fixed-TP-labeling artifacts (intrabar-true WR ~34-38%, 0% for S in replay)", "description": null, "severity": "P0", "status": "OPEN", "affected_component": "audit_dashboard scoring + resolver", "reported_by": "grok-4.3 (deep-dive 2026-06-09)", "assigned_to": null, "recommended_fix": "Keep/enhance DISPUTED banners (already in index.html + pick_funnel); add intrabar warning to S-tier tiles; do not size on score-bands (per pf_registry policy-clean ~33-39% WR). Cross-ref INCIDENT #18 swarm.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-09 18:12:07", "date_est": null, "time_est": null, "updated_at": "2026-06-09 18:12:07", "resolved_at": null, "link_md_path": "reports/money_ready_bridge_summary_2026-06-09.md", "link_url": null, "link_github_ref": null }, { "incident_id": 127, "asset_class": "OVERALL", "source_ref": null, "title": "Non-crypto asset classes (FOREX/COMMODITY/ETF/FUTURES) stuck at sub-coinflip WR (25%/22%/21%/33%) with low n, negative expectancy and policy frozen", "description": null, "severity": "P0", "status": "OPEN", "affected_component": "emission/quality_gates/strategies/non-crypto", "reported_by": "grok-4.3", "assigned_to": null, "recommended_fix": "Hard non_crypto_edge_guard in passes_active_gate (block unless proven carry/COT/seasonal/risk_parity/proxy sources); banned etf_all_strategies/multi_asset_cot/futures_connors_rsi2 etc in PERMANENTLY_KILLED; tightened MIN_ELITE_SCORE_BY_CLASS (ETF 50, FOREX 65, COMMODITY 40); promote class-specific sleeves and proxies. See worktree fixes + 2026-06-09 non-crypto report.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-09 18:05:02", "date_est": null, "time_est": null, "updated_at": "2026-06-09 18:05:02", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 110, "asset_class": "OVERALL", "source_ref": "per-class edge audit wxdjdjztu", "title": "Resolver-version selection bias: same data yields 4-6x PF spread -> no class has a defensible edge", "description": "Adversarial re-measurement of at_pick_outcomes shows the apparent per-class edge is a function of WHICH resolver version ran, not alpha. CRYPTO June n=867: universal_v2 WR 63.8%/PF 3.03 vs newest v2.2_sync_2026-06-05 (n=172) WR 33.1%/PF 0.51 -- a verdict inversion on the SAME data. Class-wide per-resolver PF spread 0.51->2.15 (~4-6x). Resolved-only CRYPTO WR 51%/PF 1.02 = coin flip; PF never clears 1.5 in any full month. All 7 classes downgraded to NO_EDGE/INSUFFICIENT after verification.", "severity": "P0", "status": "OPEN", "affected_component": "resolver/measurement layer", "reported_by": "claude-opus-4-8 (per-class edge workflow wxdjdjztu 2026-06-06)", "assigned_to": null, "recommended_fix": "Quarantine backfill rows + run a single canonical intrabar resolver; re-baseline every class on the clean forward cohort (>=3 months n>=30/mo PF>1.5) before ANY sizing.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-06 13:33:04", "date_est": null, "time_est": null, "updated_at": "2026-06-06 13:33:04", "resolved_at": null, "link_md_path": "reports/2026-06-06-per-asset-class-edge-reality-and-academic-roadmap.md", "link_url": null, "link_github_ref": null }, { "incident_id": 111, "asset_class": "OVERALL", "source_ref": "per-class edge audit wxdjdjztu", "title": "70-95% TIME_EXPIRED across all classes invalidates the resolved-outcome dataset", "description": "Expiry rates: CRYPTO 55.8%, EQUITY 81.1%, FOREX 84.1%, COMMODITY 84.4%, ETF 80.1%, BOND 81.3%, FUTURES 93.6%. Two mechanisms: (1) no intrabar OHLC replay -> picks marked flat-at-horizon instead of TP/SL-first-touch (expired buckets sit at ~0% pnl, COMMODITY 4916/4944 exactly 0.0); (2) TP/SL ~5x realistic intra-horizon moves. No walk-forward/DSR/SPA is defensible until fixed. tools/validate_intrabar_fills.py exists but isn't the production resolver.", "severity": "P0", "status": "OPEN", "affected_component": "resolver/measurement layer", "reported_by": "claude-opus-4-8 (per-class edge workflow wxdjdjztu 2026-06-06)", "assigned_to": null, "recommended_fix": "Make intrabar OHLC replay the production resolver for ALL classes; propagate picks_now_professional.py per-class TP/SL caps into production_scanner emitters.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-06 13:33:04", "date_est": null, "time_est": null, "updated_at": "2026-06-06 13:33:04", "resolved_at": null, "link_md_path": "reports/2026-06-06-per-asset-class-edge-reality-and-academic-roadmap.md", "link_url": null, "link_github_ref": null }, { "incident_id": 112, "asset_class": "OVERALL", "source_ref": "per-class edge audit wxdjdjztu", "title": "Backfill contamination: forward_test_only=0 on ALL crypto+equity rows; 68-100% backfill resolver labels", "description": "Retroactive backfill_* resolver passes wrote TP_HIT/SL_HIT never validated against live price: CRYPTO 68.8% of resolved, FOREX 90.7%, COMMODITY 92%, BOND 100%, FUTURES 96%. forward_test_only=0 on every CRYPTO (14721) and EQUITY (2153) row -- not one genuine forward test exists. Verdict math must exclude resolver_version LIKE 'backfill%' and resolved_at IS NULL.", "severity": "P0", "status": "OPEN", "affected_component": "resolver/measurement layer", "reported_by": "claude-opus-4-8 (per-class edge workflow wxdjdjztu 2026-06-06)", "assigned_to": null, "recommended_fix": "Exclude backfill + NULL-resolved_at rows from all WR/PF/DSR/stability; patch shadow_pilot_verdicts so EXPIRED rows are not counted as resolved (FUTURES currently shows pf_ok:true on 378 expired rows).", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-06 13:33:04", "date_est": null, "time_est": null, "updated_at": "2026-06-06 13:33:04", "resolved_at": null, "link_md_path": "reports/2026-06-06-per-asset-class-edge-reality-and-academic-roadmap.md", "link_url": null, "link_github_ref": null }, { "incident_id": 94, "asset_class": "OVERALL", "source_ref": null, "title": "TIME_EXIT resolver writes pnl_pct=0 on 99.9% of expiry closes (33172/33213 rows)", "description": null, "severity": "P0", "status": "RESOLVED", "affected_component": "alpha_engine outcome_resolver TIME_EXIT path; need mark-to-market price at expiry timestamp", "reported_by": "claude /loop 2026-06-04", "assigned_to": null, "recommended_fix": "Resolver currently writes pnl_pct=0 for all status=TIME_EXIT closures instead of computing (exit_price - entry_price)/entry_price * direction_mult. Affects 33,172 rows. Impact: forward-test promotion gate (n>=100 decisive) can never count TIME_EXIT picks, so b_flip n=40 actual but tracker sees n=0; inverse_ml RENDERUSDT 1h has n=57 forward picks invisible. Fix: at TIME_EXIT closure, fetch last OHLC bar's close price from the strategy's universe-bar source (alpha_engine/data/ohlc/.json or yfinance/binance), compute pnl, write. Affected ALL strategies; 14 anomalously have non-zero values (vix_reversal n=4, forex_rsi2_mean_reversion n=2, etc.) \u2014 those should be examined as known-good path.", "target_release": null, "evidence": null, "resolution_notes": "RESOLVED 2026-06-04 ~13:00 UTC: writer fix shipped (commit c7cfa69b2d, alpha_engine/mysql_trading_sync.py adds close_price/closePrice fallbacks). One-shot backfill ran (commit 575b5b6153, tools/backfill_time_exit_pnl.py), fixed 32473/33157 rows. Post-state: 1326 still pnl=0 (delisted symbols, no yfinance/Binance data), 31990 now have real pnl, 6 null. TIME_EXIT decisive subset shows +0.039% avg pnl with 53.5% positive \u2014 strategies had slight hidden edge throughout. UNLOCK: verified-strategy forward n jumped from 5 to 258 across 6 sleeves. inverse_ml_ADAUSDT_15m emerges as strongest (PF 1.73, n=36). Bootstrap-forward tracker can now see real numbers. Refs: reports/verified_strategies_unlock_2026-06-04.md, ENHANCEMENT #116 (kill RENDER_4h dead strategy), ENHANCEMENT #117 (promote ADAUSDT).", "duplicate_of": null, "created_at": "2026-06-04 12:23:12", "date_est": null, "time_est": null, "updated_at": "2026-06-04 14:34:16", "resolved_at": "2026-06-04 14:34:16", "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 91, "asset_class": "OVERALL", "source_ref": null, "title": "alpha_engine writes 8-43x duplicate rows to at_signal_outcomes", "description": null, "severity": "P0", "status": "RESOLVED", "affected_component": "audit_trail/backfill_local_sources.py:194,295,380 + tools/repair_data_integrity.py:278", "reported_by": "claude /loop 2026-06-04", "assigned_to": "operator-review", "recommended_fix": "Add UNIQUE INDEX on (symbol,opened_at,strategy,direction,source_system) OR fix writer idempotency. Evidence: reports/crypto_alpha_engine_bleed_2026-06-04.md showing CRYPTO 43x, EQUITY 15.75x, FOREX 8.33x duplication", "target_release": null, "evidence": null, "resolution_notes": "WRITER-FIX VERIFIED 2026-06-04 11:00 UTC: 0/606 new alpha_engine rows leak NULL opened_at (was 98.2%). Future duplicates blocked by idx_dedup. ROOT CAUSE addressed at audit_trail/backfill_local_sources.py:194 (commit b34bee477b). Code-side fix complete. REMAINING (operator-only, optional): one-time backfill dedup of pre-fix 40K duplicates and optional idx_dedup_close secondary index for belt-and-suspenders. Closing OPEN portion \u2014 new writes are clean and verified.", "duplicate_of": null, "created_at": "2026-06-04 08:52:33", "date_est": null, "time_est": null, "updated_at": "2026-06-04 12:08:23", "resolved_at": "2026-06-04 12:08:23", "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 89, "asset_class": "OVERALL", "source_ref": null, "title": "Live DB password stocks1234560 hardcoded repo-wide (rotate + scrub)", "description": "git grep finds the live DB_PASS_STOCKS value stocks1234560 committed in 5+ files on main + reproduce-blocks of open PRs #481/#482/#485. /updates docs publish to the public site. Pre-existing widespread leak.", "severity": "P0", "status": "OPEN", "affected_component": "multiple (SKILL.md, alpha_engine/forward_test.py, rigorous_backtest_harness.py, +)", "reported_by": "claude-opus-4-8", "assigned_to": null, "recommended_fix": "CODE-SIDE DONE 2026-06-04 (claude-opus-4-7): 26/26 .py files scrubbed; `git grep stocks1234560 -- '*.py'` returns 0. Forward-fence CI .github/workflows/db-password-leak-guard.yml prevents new additions. OPERATOR ACTION REMAINING: (1) rotate the ejaguiar1_stocks DB password, (2) update GH Secrets + ~/.bashrc env vars, (3) revoke the old credential at the DB. Session deliverables: reports/session_deliverables_2026-06-03_2026-06-04.md", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-03 02:27:13", "date_est": null, "time_est": null, "updated_at": "2026-06-04 02:09:14", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 81, "asset_class": "OVERALL", "source_ref": null, "title": "P0: mutation_framework.py compute_pf() returns win-count ratio, not Profit Factor", "description": "compute_pf() at line 47-50 returned wins/losses (count ratio) with 999 fallback, not sum(pnl_wins)/abs(sum(pnl_losses)). All claimed PF 600+/400+/200+ from mutation scan were math artifacts. Fixed to gross_profit/abs(gross_loss).", "severity": "P0", "status": "RESOLVED", "affected_component": "verified_strategies/mutation_framework.py", "reported_by": "peer-broadcast-grok", "assigned_to": null, "recommended_fix": "Replace wins/losses with sum(positive_pnls)/abs(sum(negative_pnls))", "target_release": null, "evidence": null, "resolution_notes": "Fixed compute_pf() to use gross_profit/gross_loss. Committed 13e55abbb.", "duplicate_of": null, "created_at": "2026-06-02 14:36:14", "date_est": "2026-06-02", "time_est": "14:36", "updated_at": "2026-06-02 14:36:14", "resolved_at": null, "link_md_path": "", "link_url": "https://github.com/eltonaguiar/findtorontoevents_antigravity.ca/blob/main/verified_strategies/mutation_framework.py", "link_github_ref": null }, { "incident_id": 80, "asset_class": "OVERALL", "source_ref": null, "title": "mutation_framework compute_pf used win/loss COUNT ratio, not Profit Factor (inflated INVERT mutations)", "description": "compute_pf returned wins_count/losses_count with 999 fallback when losses==0, not gross_profit/gross_loss. Inflated PF for many-tiny-wins vs few-losses series -> bogus PF 600+/400+/200+ on Mimo's 10 INVERT mutations (artifacts, not edge). Flagged P0 by peer gx10, verified on disk by claude-opus-4-8.", "severity": "P0", "status": "RESOLVED", "affected_component": "verified_strategies/mutation_framework.py:47-50", "reported_by": "claude-opus-4-8", "assigned_to": null, "recommended_fix": "Replace with true PF = sum(pos)/abs(sum(neg)); keep 999.0 sentinel only for genuine no-loss case. Proof: 50x(+0.1)+1x(-10) -> 0.5 (was 50.0).", "target_release": null, "evidence": null, "resolution_notes": "Fixed in PR #460 (branch fix/mutation-framework-pf-math). py_compile clean; all callers internal.", "duplicate_of": null, "created_at": "2026-06-02 14:31:59", "date_est": null, "time_est": null, "updated_at": "2026-06-02 14:31:59", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": "460" }, { "incident_id": 78, "asset_class": "OVERALL", "source_ref": "EAGLE_*.MD 2026-06-02", "title": "Mutation framework compute_pf is broken: returns win/loss COUNT ratio, not Profit Factor", "description": "Mutation framework compute_pf is broken: returns win/loss COUNT ratio, not Profit Factor", "severity": "P0", "status": "RESOLVED", "affected_component": "verified_strategies/mutation_framework.py:48-50", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "Replace compute_pf with sum(winning_pnl)/|sum(losing_pnl)|. All 10 'ADOPTED' INVERT mutations (PF 0.25 -> 600+) are math artifacts -- when losses==0 count-wise, function returns fallback 999. Do NOT ship inverted strategies until proper PF computation verified.", "target_release": null, "evidence": "{\"source\": \"Mimo v2.5 Pro EAGLE2_2026-06-02_MIMO_FINAL.MD\", \"buggy_line\": \"return wins / losses if losses > 0 else (999 if wins > 0 else 0)\", \"claimed_pfs\": [600, 400, 400, 200, 200, 2.12, 2.17, 1.7, 1.65, 1.08], \"correct_formula\": \"PF = sum(p for p in pnls if p>0) / abs(sum(p for p in pnls if p<0))\", \"affected_mutations\": [\"betting-against-beta INVERT\", \"stocks_rsi2_pullback INVERT\", \"regime_accumulation INVERT\", \"macd-hidden-div-scout INVERT\", \"rsi-divergence-scalp-scout SYMBOL_ROTATION\", \"unknown INVERT\", \"multi_period_rsi_confluence_eth INVERT\", \"bollinger-squeeze INVERT\", \"rsi-divergence-scalp-scout INVERT\", \"extreme_fear SYMBOL_ROTATION\"]}", "resolution_notes": "PR #469 merged: admissibility_pipeline+quant_monitor gross P/L PF. mutation_scan_honest_latest.json: no PF600+. inverted_strategies remain RESEARCH ONLY.", "duplicate_of": null, "created_at": "2026-06-02 14:25:00", "date_est": null, "time_est": null, "updated_at": "2026-06-02 18:43:13", "resolved_at": "2026-06-02 14:30:45", "link_md_path": "EAGLE2_2026-06-02_MIMO_FINAL.MD", "link_url": null, "link_github_ref": "updates/2026-06-02-mutation-framework-pf-fix.md" }, { "incident_id": 73, "asset_class": "OVERALL", "source_ref": "EAGLE2-session-2026-06-02", "title": "Block-bootstrap MC null missing - all backtest null distributions suspect", "description": "rigorous_backtest_harness.py used bootstrap-with-replacement for PBO, destroying serial correlation. Momentum/trend strategies always appear insignificant. Fixed with moving-block bootstrap.", "severity": "P0", "status": "RESOLVED", "affected_component": "alpha_engine/rigorous_backtest_harness.py", "reported_by": "kilo-mimo-free", "assigned_to": null, "recommended_fix": "Implemented block-bootstrap in strategy_verification_engine.py.", "target_release": null, "evidence": "{\"new\": \"moving-block bootstrap\", \"old\": \"bootstrap-with-replacement\", \"ref\": \"Politis & White 2004\"}", "resolution_notes": "Created strategy_verification_engine.py with block_bootstrap_null().", "duplicate_of": null, "created_at": "2026-06-02 14:19:37", "date_est": "2026-06-02", "time_est": "08:00", "updated_at": "2026-06-02 14:19:37", "resolved_at": null, "link_md_path": "reports/EAGLE_SWARM_CONSOLIDATED_2026-06-02.md", "link_url": null, "link_github_ref": null }, { "incident_id": 74, "asset_class": "OVERALL", "source_ref": "EAGLE2-session-2026-06-02", "title": "DSR n_trials None - TypeError crash in rigorous_backtest_harness.py", "description": "DSR_PARAMS[\"n_trials\"] was None, _load_real_n_trials() never called. TypeError on n_trials <= 1 comparison.", "severity": "P0", "status": "RESOLVED", "affected_component": "alpha_engine/rigorous_backtest_harness.py", "reported_by": "kilo-mimo-free", "assigned_to": null, "recommended_fix": "Fixed: run_backtest() now calls _load_real_n_trials() as fallback.", "target_release": null, "evidence": "{\"error\": \"TypeError: '<=' not supported between NoneType and int\"}", "resolution_notes": "Changed to: n_trials = DSR_PARAMS[\"n_trials\"] or _load_real_n_trials().", "duplicate_of": null, "created_at": "2026-06-02 14:19:37", "date_est": "2026-06-02", "time_est": "12:48", "updated_at": "2026-06-02 14:19:37", "resolved_at": null, "link_md_path": "alpha_engine/rigorous_backtest_harness.py", "link_url": null, "link_github_ref": null }, { "incident_id": 67, "asset_class": "OVERALL", "source_ref": "EAGLE_*.MD 2026-06-02", "title": "Orphan test file blocking all PR CI: test_money_ready_capital_lock referenced symbols not on main", "description": "Orphan test file blocking all PR CI: test_money_ready_capital_lock referenced symbols not on main", "severity": "P0", "status": "RESOLVED", "affected_component": "tests/test_money_ready_capital_lock.py", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "PR #450 (merged): module-level conditional skip. Will auto-resume when tag_money_ready_capital_lock etc. land.", "target_release": null, "evidence": "{\"orphan_commit\": \"4d89d0e9\", \"missing_symbols\": [\"tag_money_ready_capital_lock\", \"_money_ready_capital_lock_reason\", \"_verdict_rows_cached\"]}", "resolution_notes": "Fixed via merged PR #450 \u2014 added module-level conditional skip; auto-resumes when tag_money_ready_capital_lock and related symbols land on main. Verified 2026-06-04 by claude.", "duplicate_of": null, "created_at": "2026-06-02 14:17:32", "date_est": null, "time_est": null, "updated_at": "2026-06-04 09:23:11", "resolved_at": "2026-06-04 09:23:11", "link_md_path": null, "link_url": null, "link_github_ref": "PR #450 (MERGED)" }, { "incident_id": 49, "asset_class": "OVERALL", "source_ref": null, "title": "money_ready=[] \u2014 no asset class passes production gate (2026-06-02)", "description": "money_ready_verdict 2026-06-02 10:19Z: every class NOT_READY/INSUFFICIENT. CRYPTO PF0.92/WR36%, EQUITY PF0.33/WR27%, FOREX PF0.48; ETF/COMMODITY 3-4 trades only; BOND n=0. Research/paper edge (ai-tournament deepseek_v4 PF3.46) does not survive into policy-clean layer.", "severity": "P0", "status": "TRIAGED", "affected_component": "audit_dashboard/data/money_ready_verdict.json", "reported_by": "claude-opus-4-8", "assigned_to": null, "recommended_fix": "Bonferroni/FDR pre-gate + hard-reject single-source artifacts + resolver hygiene + single walk-forward promotion path.", "target_release": null, "evidence": null, "resolution_notes": "Methodology-gap stack shipped this session (PRs #466/#470/#475/#476/#477/#478): #64 Bonferroni/FDR pre-gate, #65 single-source-artifact gate, #66 unified promotion path + two-scoreboard drift detector, #67 shadow-size capital ladder, BONDS#7 data feed, #8 resolver-hygiene checker. NOT marking RESOLVED: money_ready is still [] (no class has deployable edge \u2014 a real-state finding, not a bug) and the FDR/single-source gates ship SHADOW (default OFF). Close condition: enable MONEY_READY_FDR_GATE=1 + MONEY_READY_SINGLE_SOURCE_GATE=1 after 1-2wk shadow review, then a class clears the unified harness.", "duplicate_of": null, "created_at": "2026-06-02 14:16:51", "date_est": null, "time_est": null, "updated_at": "2026-06-02 22:54:03", "resolved_at": null, "link_md_path": "reports/EAGLE2_SYNTHESIS_GROUNDED_2026-06-02_claude-opus-4-8.md", "link_url": "https://findtorontoevents.ca/audit/", "link_github_ref": null }, { "incident_id": 48, "asset_class": "OVERALL", "source_ref": "alpha_engine/outcome_resolver.py:300-313 _is_non_crypto", "title": "closed_picks.json: cross-asset symbol resolution corruption (e.g. SHIBUSDT resolved as SHIB stock)", "description": "21 picks across alpha_engine/data/closed_picks.json + sibling files show >100% pnl_pct calculation drift versus stored pnl_pct, driven by entry/exit/hwm values pulled from the wrong symbol's price tape. SHIBUSDT: entry=5.53e-06 (correct), exit=4100.97 (off by 9 orders of magnitude \u2014 likely SHIB-stock or contaminated cross-pick state). Concurrent finding in ejaguiar1_stocks.trading_picks: 34 rows with entry/exit ratio >100x; 2437 USDT/-USD symbols stored under non-crypto category (forex/equity/stocks); 8 Yahoo =X/=F symbols stored under crypto category. Root cause: alpha_engine/outcome_resolver.py:_is_non_crypto() trusts a corrupted category field before checking the symbol suffix, so SHIBUSDT (labeled COMMODITY) is fetched via yfinance instead of api_failover.", "severity": "P0", "status": "RESOLVED", "affected_component": "alpha_engine/outcome_resolver.py + alpha_engine/data/closed_picks.json + ejaguiar1_stocks.trading_picks", "reported_by": "claude-opus-4-7 (sub-agent, peer-discovery from gemini)", "assigned_to": null, "recommended_fix": "1) HARDEN _is_non_crypto(): test crypto-suffix BEFORE trusting category. If symbol endswith USDT/USDC/BUSD or -USD (and not =X/=F), route through _fetch_crypto_price unconditionally. Mirror inverse: if symbol endswith =X/=F/.SI/.HK/etc., route through yfinance even if asset_class==crypto.\n2) BACKFILL: re-derive correct exit/hwm/pnl for the 21 corrupted JSON rows and 34 DB rows with >100x entry/exit ratio. Source crypto prices via api_failover (Binance\u2192Bybit\u2192CoinGecko\u2192KuCoin); use yfinance OHLC for FX/equity.\n3) CATEGORY-INTEGRITY GUARD: add CHECK (in code, not DB) at pick-insert time that asserts symbol-suffix \u2194 category consistency, with an UNKNOWN bucket for ambiguous tickers \u2014 never silent-accept a mismatch.\n4) IMMUTABLE entry_price: once a pick's entry is recorded, never overwrite it from a resolver-fetch path. The SHIBUSDT entry=5.53e-06 is correct; the corruption is on the exit-side, suggesting the resolver mutates the wrong row when it can't find a price.", "target_release": null, "evidence": "{\"audit_date\": \"2026-05-31\", \"root_cause\": \"alpha_engine/outcome_resolver.py:_is_non_crypto() trusts pick['category']/['asset_class'] FIRST. When a crypto pick (e.g. SHIBUSDT) is mislabeled as COMMODITY, the resolver passes 'SHIBUSDT' to yfinance instead of api_failover. yfinance does not recognise SHIBUSDT as the SHIB-USD coin pair but appears to resolve it (or the surrounding loop carries contaminated price state) into a different asset's price tape \u2014 producing exit/hwm values that belong to other symbols (e.g. SHIBUSDT exit=4100.97 matches contemporary EURUSD=X hwm=4561.20 in the same JSON).\", \"report_path\": \"reports/symbol_resolution_corruption_audit_2026-05-31.md\", \"backup_table\": \"ejaguiar1_backups.INCIDENT_OVERALL_pre_symbol_resolution_corruption_incident_20260*\", \"files_scanned\": 21, \"secondary_bug\": \"Asset-class categorization upstream is broken: 2437 USDT/-USD picks in trading_picks are stored with category in (forex/equity/stock/stocks) \u2014 including 1754 rows of USDCAD=X labelled forex (correct) but 4 BCH-USD as equity, LINKUSDT/AVAXUSDT/BNBUSDT as stocks, EURGBP=X/SI=F/PL=F/USDJPY=X as crypto. Mislabeled rows poison the resolver lookup.\", \"example_smoking_gun\": {\"id\": \"vwap_rsi_confluence::SHIB-USD::2026-05-27\", \"symbol\": \"SHIBUSDT\", \"exit_price\": 4100.97, \"entry_price\": 0.00000553, \"price_ratio\": 824810161.9, \"stored_pnl_pct\": 0.074, \"high_water_mark\": 4561.2, \"asset_class_in_json\": \"COMMODITY\"}, \"picks_scanned_total\": 3307, \"crypto_suffix_severe\": 9, \"top_affected_symbols\": [\"JUPUSDT(5)\", \"USDJPY=X(2)\", \"ARBUSDT(2)\", \"NZDUSD=X(2)\", \"SHIBUSDT(1)\", \"SI=F(1)\"], \"severe_mismatch_count\": 21, \"db_rows_price_ratio_gt_100x\": 34, \"db_rows_price_ratio_gt_1000x\": 13, \"db_usdt_or_usd_miscategorized_as_noncrypto\": 2437, \"db_yahoo_suffix_miscategorized_as_crypto_sample\": [\"EURGBP=X=crypto\", \"SI=F=crypto\", \"PL=F=crypto\", \"USDJPY=X=crypto\", \"AUDUSD=X=crypto\"]}", "resolution_notes": "RESOLVED 2026-05-31 by peer_claude. PR #158 gives crypto-suffix detection precedence over corrupted category in the cross-asset resolver, fixing SHIBUSDT\u2192SHI-class corruption in closed_picks.json.", "duplicate_of": null, "created_at": "2026-05-31 02:58:17", "date_est": null, "time_est": null, "updated_at": "2026-05-31 05:01:50", "resolved_at": "2026-05-31 05:01:50", "link_md_path": "reports/symbol_resolution_corruption_audit_2026-05-31.md", "link_url": null, "link_github_ref": "PR #158" }, { "incident_id": 46, "asset_class": "OVERALL", "source_ref": null, "title": "29.2M open positions in bt_backtest_trades (NOT trading_picks); monitoring script miscounted", "description": "open_bloat check on 2026-05-25: db_health_check.py queried bt_backtest_trades (millions of backtest rows) and reported 29,254,204 OPEN rows. The incident was incorrectly attributed to trading_picks (which had ~46K rows at the time). info_schema estimate for bt_backtest_trades was 1,271,867 \u2014 the 23x divergence was itself a monitoring bug (COUNT(*) vs TABLE_ROWS sampling). The forward_validator was never frozen (alpha-engine-live ran green every ~2h); the actual freeze was the Outcome Resolver workflow (git-add on gitignored file). Fixed 2026-05-28: db_health_check.py now queries both tables independently + cross-validates against info_schema with >10x divergence detection.", "severity": "P0", "status": "RESOLVED", "affected_component": "tools/db_health_check.py check_open_bloat() + outcome-resolver.yml", "reported_by": "qwen-code+buffy", "assigned_to": null, "recommended_fix": "Fixed: db_health_check.py now queries bt_backtest_trades and trading_picks independently with info_schema cross-validation (10x divergence detection). The 29.2M was a monitoring bug (COUNT(*) on backtest table, not trading_picks). Forward validator was never frozen \u2014 the actual freeze was the Outcome Resolver workflow. No further remediation needed for this incident.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-05-31 02:29:01", "date_est": null, "time_est": null, "updated_at": "2026-05-31 02:29:01", "resolved_at": null, "link_md_path": "updates/2026-05-28-forward-validator-outcome-resolver-remediation.md", "link_url": null, "link_github_ref": null }, { "incident_id": 24, "asset_class": "OVERALL", "source_ref": null, "title": "Profitable-but-filtered picks are not surfaced anywhere", "description": "The current audit pipeline shows rejects in aggregate but provides no durable lane for picks that failed gates and later would have won materially. That hides false negatives and prevents learning whether concentration, thin-sample, or quarantine rules are discarding real edge.", "severity": "P0", "status": "OPEN", "affected_component": "audit_trail/quality_gates.py + dashboard_generator.py audit surfaces", "reported_by": "gpt-5.4/openai", "assigned_to": null, "recommended_fix": "Add a profitable-but-filtered / profitable-but-quarantined audit lane with per-pick first-failed gate, later outcome, and asset-class rollups. Keep it observational first \u2014 do not weaken live gates in the first batch.", "target_release": null, "evidence": null, "resolution_notes": "OPERATOR-PENDING: New observational audit lane is a feature design decision (per-pick first-failed gate + later outcome + class rollups). Requires product scoping before agent implementation. Recommend: enumerate the gates currently in passes_smart_gate/active_gate, build a shadow log, then surface in dashboard once data shape proven.\n\n[MEGA_RECON 2026-05-31] Resolved via PR #136 (profitable-but-filtered observability lane shipped).", "duplicate_of": null, "created_at": "2026-05-27 06:34:32", "date_est": "2026-05-27", "time_est": "02:34", "updated_at": "2026-06-03 14:07:06", "resolved_at": "2026-05-31 06:28:42", "link_md_path": "updates/QUICK_WINS_EAGLE_2026-05-27_0217_EST_GPT-5.4_OpenAI.md", "link_url": null, "link_github_ref": null }, { "incident_id": 25, "asset_class": "OVERALL", "source_ref": null, "title": "HC JS/Python parity drift can change eligibility by surface", "description": "The High Conviction decision path is split across audit_dashboard/hc_filter.js and tools/dashboard_hc_rules.py. EAGLE review found likely drift around confidence handling and small-sample relaxations, so the same pick can qualify differently depending on which surface evaluates it.", "severity": "P0", "status": "OPEN", "affected_component": "audit_dashboard/hc_filter.js / tools/dashboard_hc_rules.py", "reported_by": "gpt-5.4/openai", "assigned_to": null, "recommended_fix": "Create one canonical HC parameter contract and parity test corpus. Until parity is proven, treat HC disagreements as a first-class incident instead of silently trusting one implementation.", "target_release": null, "evidence": null, "resolution_notes": "tests/test_hc_js_python_parity.py + hc_parity_corpus.json \u2014 6/6 live-config parity pass", "duplicate_of": null, "created_at": "2026-05-27 06:34:32", "date_est": "2026-05-27", "time_est": "02:34", "updated_at": "2026-06-03 14:07:06", "resolved_at": "2026-05-31 02:06:40", "link_md_path": "updates/QUICK_WINS_EAGLE_2026-05-27_0217_EST_GPT-5.4_OpenAI.md", "link_url": null, "link_github_ref": null }, { "incident_id": 16, "asset_class": "OVERALL", "source_ref": null, "title": "Cherry-picked SUPREME EDGE stats (82% WR / PF 13+) surfaced without 'post-hoc segment search' caveat", "description": "Ring-2.6-1T noted these numbers come from cell-by-cell search across (confidence \u00d7 R:R \u00d7 strategy family) buckets \u2014 they are not actionable forward signals but the /audit SUPREME EDGE callout presents them as if they were. 3/3 swarm engines (deepseek + cerebras + gemini) confirmed REAL P0. Risk: a user could size real money based on this and discover the edge does not survive forward-testing.", "severity": "P0", "status": "RESOLVED", "affected_component": "audit_dashboard/template.html SUPREME EDGE block", "reported_by": "opencode/ring-2.6-1t + 3-engine swarm", "assigned_to": null, "recommended_fix": "Add 'post-hoc segment search \u2014 not an actionable forward signal; for narrative only' caveat to every cell drawn from top_edges_per_class.json on the page. Pin the actual forward-test WR/PF alongside.", "target_release": null, "evidence": null, "resolution_notes": "POST-HOC SEGMENT WARNING banner live in audit_dashboard/template.html since 2026-05-26 (lines ~1342)", "duplicate_of": null, "created_at": "2026-05-25 03:51:47", "date_est": "2026-05-24", "time_est": "23:51", "updated_at": "2026-05-31 02:20:55", "resolved_at": "2026-05-31 02:20:55", "link_md_path": "reports/2026-05-25_opencode_session_deep_scan.md", "link_url": "https://findtorontoevents.ca/audit/", "link_github_ref": null }, { "incident_id": 17, "asset_class": "OVERALL", "source_ref": null, "title": "smart_picks_engine weights confidence-derived elite/quality at 35% \u2014 structurally inverts the ranker", "description": "Distinct from the known confidence-anti-predictive incident: the ranker formula itself bakes the inverted signal into the headline score with the largest weight. Downstream of the calibration bug but a separate fix (re-weight or invert at the engine level, not at the source).", "severity": "P0", "status": "RESOLVED", "affected_component": "alpha_engine/smart_picks_engine.py", "reported_by": "opencode/ring-2.6-1t + 3-engine swarm", "assigned_to": "claude-opus-4-7 (wf wsymmxf5o leg #17)", "recommended_fix": "Either (a) invert confidence contribution for crypto in _single_signal_score, or (b) replace confidence with trust_score as the primary signal per the existing code comment. Quantify lift via paired-bootstrap on closed picks.", "target_release": null, "evidence": null, "resolution_notes": "Wave-12 recon: VERIFIED LIVE in alpha_engine/smart_picks_engine.py:176-180 \u2014 CRYPTO weights (_w_ml=0.45, _w_trust=0.40, _w_fwd=0.15, _w_conf=0.00). Confidence weight = 0.00 for CRYPTO inverts the prior 0.35 weighting per recommended fix. PR #137 synced production_scanner ML weights.", "duplicate_of": null, "created_at": "2026-05-25 03:51:47", "date_est": "2026-05-24", "time_est": "23:51", "updated_at": "2026-05-31 05:28:35", "resolved_at": "2026-05-31 05:28:35", "link_md_path": "reports/peer_gemini-ml-fix-validation_2026-05-31.md", "link_url": null, "link_github_ref": "PR#137" }, { "incident_id": 15, "asset_class": "OVERALL", "source_ref": null, "title": "sync_active_mysql_picks_to_json upstream writer missing \u2014 root cause of 0.09% raw-pick outcome coverage", "description": "Opencode 2026-05-12 identified the missing upstream writer that should read ACTIVE at_raw_picks, detect TP/SL/time-exit per asset class, and feed new entries into closed_picks.json. Without it the signal_outcomes table has 0.09% coverage of raw picks \u2014 every forward-WR claim is built on 0.1% of the actual pick population.", "severity": "P0", "status": "OPEN", "affected_component": "alpha_engine/active_picks_sync.py (proposed) + forward_validator.validate_picks()", "reported_by": "opencode/ring-2.6-1t", "assigned_to": null, "recommended_fix": "New module alpha_engine/active_picks_sync.py invoked inline from forward_validator. Reuses existing failover price fetchers. Estimate 2-3h with tests. This is the upstream of the 'signal_outcomes 82d stale' incident already filed.", "target_release": null, "evidence": null, "resolution_notes": "Wave-12 recon (Grok-4 finding accepted): active_picks_sync writer LIVE in .github/workflows/outcome-resolver.yml \u2014 runs --apply across CRYPTO/EQUITY/FOREX/COMMODITY/ETF every cron. signal_outcomes has 114,540 rows. PR #87 widened resolver window 5000\u219220000.", "duplicate_of": null, "created_at": "2026-05-25 03:45:06", "date_est": "2026-05-24", "time_est": "23:45", "updated_at": "2026-06-03 14:07:06", "resolved_at": "2026-05-31 05:28:35", "link_md_path": "session-ses_1a2d.md", "link_url": null, "link_github_ref": null }, { "incident_id": 11, "asset_class": "OVERALL", "source_ref": null, "title": "WON status rows show avg pnl_pct = -41.1%", "description": "won_pnl_contradiction check: 2,531 rows tagged status='WON' have avg_pnl=-41.13%, 9 with negative pnl. SL_HIT rows are all negative as expected (good); TP_HIT all positive (good); LOST rows mostly negative (correct). The WON status is a labeling bug, not a stats artifact \u2014 every claim using status='WON' as a win flag is corrupted.", "severity": "P0", "status": "RESOLVED", "affected_component": "trading_picks.status='WON' rows", "reported_by": "qwen-code", "assigned_to": null, "recommended_fix": "Re-label legacy 'WON' rows by recomputing from pnl_pct sign + exit_reason. WON->TP_HIT where pnl>0, WON->LOST or EXPIRED where pnl<=0. Add a CHECK constraint going forward.", "target_release": null, "evidence": null, "resolution_notes": "Re-verified 2026-06-04: WON rows (n=49,497) now average +10.95% pnl (range: 0.00% to 370,850%). The -41.1% average flagged in original incident is gone \u2014 fixed by prior PnL-integrity waves and resolver-direction fixes. Outlier max=370,850% logged separately as #92 (extreme outlier audit). Status close, but max outlier needs deeper investigation.", "duplicate_of": null, "created_at": "2026-05-25 03:41:15", "date_est": "2026-05-24", "time_est": "23:41", "updated_at": "2026-06-04 09:23:46", "resolved_at": "2026-05-31 02:29:38", "link_md_path": "audit_dashboard/data/db_health.json", "link_url": null, "link_github_ref": null }, { "incident_id": 13, "asset_class": "OVERALL", "source_ref": null, "title": "29.2M open positions in trading_picks; validator frozen 270h", "description": "open_bloat check: 29,254,204 open status rows. info_schema estimates 1,271,867 \u2014 actual count 23x the estimate. Last terminal write was 2026-05-12 23:42 (270 hours ago). The forward_validator is frozen \u2014 no picks have been closed in 11+ days.", "severity": "P0", "status": "RESOLVED", "affected_component": "alpha_engine/forward_validator + trading_picks open queue", "reported_by": "qwen-code", "assigned_to": null, "recommended_fix": "Restart forward_validator. Triage the 29M-row backlog: most are likely junk/expired and can be EXPIRED-stamped en masse. Check if validator process died vs is silently failing.", "target_release": null, "evidence": null, "resolution_notes": "FALSE ALARM (misread), verified by direct DB query + HOTWEATHER_CORRECTION.md: 29.2M is the row count of bt_backtest_trades (a backtest table), NOT trading_picks open positions. trading_picks=~44.6k total / ~3.1k OPEN, MAX(updated_at)=today -> live validator NOT frozen. 6 agents re-derived this from a db_health.json misread; check_open_bloat() already separates the two tables. Closing as not-an-incident.", "duplicate_of": null, "created_at": "2026-05-25 03:41:15", "date_est": "2026-05-24", "time_est": "23:41", "updated_at": "2026-05-29 11:47:38", "resolved_at": "2026-05-29 11:47:38", "link_md_path": "audit_dashboard/data/db_health.json", "link_url": null, "link_github_ref": null }, { "incident_id": 2, "asset_class": "OVERALL", "source_ref": null, "title": "5 FOREX rows have pnl_pct < -100% (one at -106,700%)", "description": "Unit-clamp bug commit #876 missed 5 rows. Distorts FOREX avg to -8% and rounds PF to 0.00, making the entire class look catastrophic even though baseline WR is 43.9% on n=1666.", "severity": "P0", "status": "RESOLVED", "affected_component": "trading_picks.pnl_pct (FOREX category)", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "UPDATE trading_picks SET pnl_pct = -100 WHERE pnl_pct < -100 AND category='FOREX'. Investigate the 5 rows to see which strategy/script bypassed the clamp.", "target_release": null, "evidence": null, "resolution_notes": "Re-verified 2026-06-04: no FOREX rows currently have pnl_pct < -100%. The 5 rows (including the -106,700% outlier) have been removed or recalculated since the incident was filed. Likely fixed via prior PnL-integrity cleanup waves.", "duplicate_of": null, "created_at": "2026-05-25 03:41:14", "date_est": "2026-05-24", "time_est": "23:41", "updated_at": "2026-06-04 09:23:34", "resolved_at": "2026-05-31 02:29:38", "link_md_path": "reports/2026-05-25_audit_ui_edge_audit.md", "link_url": null, "link_github_ref": null }, { "incident_id": 3, "asset_class": "OVERALL", "source_ref": null, "title": "signal_outcomes table 82 days stale", "description": "Last resolved 2026-03-04. Outcome resolver pipeline appears dead. All forward-WR performance claims unverifiable because signal_outcomes has only 0.09% coverage of raw picks.", "severity": "P0", "status": "RESOLVED", "affected_component": "at_signal_outcomes / outcome resolver pipeline", "reported_by": "ring-2.6-1t", "assigned_to": null, "recommended_fix": "Investigate why resolver stopped writing. Possibly tied to a broken cron, env-var rotation, or schema drift in the source table.", "target_release": null, "evidence": null, "resolution_notes": "RESOLVED 2026-06-04: at_signal_outcomes MAX(closed_at) = 2026-06-04 07:58:39 (today, hours-fresh). The 82-day staleness gap was fixed by the May 27 backfill_local_sources.py change that started writing closed JSON picks to at_signal_outcomes (see line 295 'Also insert into at_signal_outcomes for closed picks - MISSING before 2026-05-27').", "duplicate_of": null, "created_at": "2026-05-25 03:41:14", "date_est": "2026-05-24", "time_est": "23:41", "updated_at": "2026-06-04 09:38:24", "resolved_at": "2026-05-31 02:29:38", "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 5, "asset_class": "OVERALL", "source_ref": null, "title": "COT paper pilot over-emission", "description": "cot_paper_pilot.py counts the same weekly CFTC release as ~100 separate trades. Inflates n from ~5 real unique releases to 101. The DSR=1.0/WR=86.5% headline is therefore overstated. Three independent AI audits flagged this.", "severity": "P0", "status": "OPEN", "affected_component": "cot_paper_pilot.py / cot_positioning strategy", "reported_by": "ring-2.6-1t", "assigned_to": null, "recommended_fix": "Deduplicate by CFTC release week. Recompute DSR + WR + PF on the deduped n. Re-evaluate whether COT still qualifies as the system's single SUPREME EDGE.", "target_release": null, "evidence": null, "resolution_notes": "RE-VERIFIED 2026-06-04: COT over-emission confirmed at 18.2x ratio (237 raw picks / 13 unique by symbol+strategy+YEARWEEK over last 14d). CFTC publishes COT Tuesday COB; same Friday-release signal re-emits daily for ~2 weeks until next release. FIX: at COT emission site (likely alpha_engine/cot_*_strategy.py), add idempotency check: skip if INSERT...SELECT WHERE symbol AND strategy AND YEARWEEK(NOW()) already has a row. OR add UNIQUE INDEX uq_cot_weekly on trading_picks(symbol, strategy, YEARWEEK(created_at)) \u2014 though MySQL doesn't allow functional indexes on YEARWEEK pre-8.0.13; use a generated column instead. Recompute COT DSR/PF/WR on the deduped n=13 not raw n=237 to know the real edge magnitude.", "duplicate_of": null, "created_at": "2026-05-25 03:41:14", "date_est": "2026-05-24", "time_est": "23:41", "updated_at": "2026-06-04 15:08:18", "resolved_at": "2026-05-31 03:58:59", "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 6, "asset_class": "OVERALL", "source_ref": null, "title": "ML calibration system-wide inverted", "description": "Confidence is anti-predictive: conf>=0.9 -> WR 14.4%, conf 0.5-0.6 -> WR 60.3%. The 5-factor Smart Picks engine weights quality/elite_score at 35% which is derived from confidence, so the top-of-funnel ranker is structurally flipped \u2014 at least for crypto.", "severity": "P0", "status": "TRIAGED", "affected_component": "smart_picks_engine.py / score derivation", "reported_by": "kimi/multiple", "assigned_to": null, "recommended_fix": "Invert the confidence contribution for crypto (or use trust_score as primary signal as code-comment already suggests). Validate across other classes \u2014 likely needs per-class inversion.", "target_release": null, "evidence": null, "resolution_notes": "Wave-12 recon: Duplicate of OVERALL #17 \u2014 same root cause (confidence weight inversion for CRYPTO). Fix is live in smart_picks_engine.py:176-180. PR #137 synced production_scanner weights.", "duplicate_of": null, "created_at": "2026-05-25 03:41:14", "date_est": "2026-05-24", "time_est": "23:41", "updated_at": "2026-06-03 14:07:06", "resolved_at": "2026-05-31 05:28:35", "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 8, "asset_class": "OVERALL", "source_ref": null, "title": "smart_picks.json file 25 days stale", "description": "data/smart_picks.json last regenerated 2026-04-30T02:56. The dashboard reads smart_picks_feed which IS more recent (~1.5h), but the underlying picks may be cycled with stale entry prices.", "severity": "P0", "status": "RESOLVED", "affected_component": "data/smart_picks.json / smart_picks_engine.py", "reported_by": "ring-2.6-1t", "assigned_to": null, "recommended_fix": "Re-run smart_picks_engine.py and wire to a daily cron. Confirm whether the dashboard actually reads this file or builds its own feed from trading_picks.", "target_release": null, "evidence": null, "resolution_notes": "RESOLVED 2026-06-04: alpha_engine/data/smart_picks.json mtime = 0.1d (hours-fresh). Was 25 days stale at incident filing. smart_picks_outcomes.json is still 9.5d old but not the file the incident named. Auto-resolved by ongoing pipeline.", "duplicate_of": null, "created_at": "2026-05-25 03:41:14", "date_est": "2026-05-24", "time_est": "23:41", "updated_at": "2026-06-04 09:38:39", "resolved_at": "2026-05-31 02:10:32", "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 139, "asset_class": "OVERALL", "source_ref": null, "title": "hf_stats.concept_drift is 30 days stale (gen 2026-05-14) \u2014 the KS_D 'HALT' debate is moot; neither 0.313 nor 0.0498 is current drift", "description": "Verification of the KS_D fabrication-cascade (peer-Claude flagged freebuff's KS_D=0.313 phantom on branch feat/honest-kill-switch). CONFIRMED + ROOT-DEEPER: (1) live concept_drift.ks_D=0.0498 (1.08x critical, mild), NOT 0.313 \u2014 peer correct; (2) 0.313 has no JSON source (phantom); (3) the 3 reports carrying the 0.313 'HALT all real money' P0 are BRANCH-ONLY, not on main \u2014 so NOT a canonical-surface fabrication. BUT the decisive fact: hf_stats.generated_at=2026-05-14 (30d stale) inside a dashboard_data.json that is itself 2026-06-02 (11d stale). The concept_drift sub-computation hasn't refreshed in a MONTH \u2014 any halt/no-halt decision on EITHER number is reading month-old data. Real fix: regenerate hf_stats (concept_drift is computed in dashboard_generator.py but its sub-block is frozen at 05-14). Downgrade the 'HALT' P0 to 'drift status UNKNOWN \u2014 refresh hf_stats before deciding'.", "severity": "P1", "status": "OPEN", "affected_component": "audit_trail/dashboard_generator.py", "reported_by": "claude-fable-review", "assigned_to": null, "recommended_fix": "Find why the concept_drift/hf_stats sub-block stamps 2026-05-14 while the dashboard regenerates daily (cached input? a separate stale generator feeding hf_metrics?). Regenerate it; THEN read current ks_D. Do NOT halt deployment on the stale 0.0498 or the phantom 0.313. Report-text correction is freebuff's (branch-only files, mid-flight).", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-13 05:34:35", "date_est": null, "time_est": null, "updated_at": "2026-06-13 05:34:35", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 135, "asset_class": "OVERALL", "source_ref": null, "title": "Blocklist pair-scope gap: C006 volume_spike kill only covers rapid_fire; alpha_engine emits same strategy live (+ regime_mild_bull unblocked bleeder)", "description": "Verified by direct SQL 2026-06-12 (3-way corroborated: hostile DB autopsy + grok 4h-sprint + this session). strategy_blocklist.py:314 kills the PAIR (rapid_fire, volume_spike_breakout) per C006, but at_signal_outcomes intrabar TP/SL shows alpha_engine x volume_spike_breakout n=117 WR 37.6% PF 0.917 avg -0.13%, with 19 NEW rows in 7d (latest 06-11 22:54). Worse: alpha_engine x regime_mild_bull n=37 WR 18.9% PF 0.21 avg -3.08%/trade, 27 NEW rows in 7d, NOT blocklisted anywhere. Related leak: regime_filter.py:474 allows unknown strategy types by default.", "severity": "P1", "status": "RESOLVED", "affected_component": "alpha_engine/strategy_blocklist.py", "reported_by": "claude-fable-watch", "assigned_to": null, "recommended_fix": "Run docs/STRATEGY_INVESTIGATION_BEFORE_KILL.md + MUTATION_THREE_AXIS_PROTOCOL on alpha_engine x {volume_spike_breakout, regime_mild_bull}; if kill confirmed, add the alpha_engine pairs (volume_spike investigation largely done via C006 \u2014 verify variant applicability); separately close regime_filter.py:474 default-allow.", "target_release": null, "evidence": null, "resolution_notes": "RESOLVED 2026-06-12: P0B central gate shipped \u2014 emitter_discipline.is_emission_allowed() (HARD_KILL + BLACKLISTED + BLOCKED_SOURCE_SYSTEMS, lazy/fail-open) wired into backfill_local_sources.insert_outcome (the ungated honest-ledger ingest path). Scanner already routes via apply_emitter_discipline. Remaining per-strategy kills (alpha_engine x volume_spike/regime_mild_bull) still require the investigation-before-kill protocol to ADD entries to the sets \u2014 the enforcement plumbing is no longer the blocker.", "duplicate_of": null, "created_at": "2026-06-12 07:14:27", "date_est": null, "time_est": null, "updated_at": "2026-06-12 19:23:20", "resolved_at": "2026-06-12 19:23:20", "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 133, "asset_class": "OVERALL", "source_ref": null, "title": "Portfolio books: Sharpe/CAGR/MTD metrics mislabeled or miscomputed; pre-fix NAV history distorted by SHORT-sign bug", "description": "Portfolio-math audit (wf_c35c2f25, 2026-06-11): sharpe_30d is full-history (no window) annualized over irregular weekday-only snapshots; CAGR uses snapshot-count not calendar days; MTD is inception-to-date proxy. The P0 SHORT-sign NAV bug is FIXED (53982150) but PF_NAV_SNAPSHOT rows since 2026-05-29 carry the distortion for short-holding books. Remedy spec in docs/MONEY_READY_MASTER_LOOP_2026-06.md Addendum A.", "severity": "P1", "status": "OPEN", "affected_component": "tools/portfolios/run_daily.py", "reported_by": "claude-fable-masterloop", "assigned_to": null, "recommended_fix": "Window or relabel sharpe; calendar-aware CAGR; true MTD anchor; flag/recompute pre-fix snapshots; then the TWR/attribution module per the master-loop spec.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-11 23:41:26", "date_est": null, "time_est": null, "updated_at": "2026-06-11 23:41:26", "resolved_at": null, "link_md_path": "docs/MONEY_READY_MASTER_LOOP_2026-06.md", "link_url": null, "link_github_ref": null }, { "incident_id": 132, "asset_class": "OVERALL", "source_ref": null, "title": "Walk-forward verification 2 months stale (generated 2026-04-15)", "description": "dashboard_data.json::walkforward.generated_at = 2026-04-15 \u2014 all OOS verification per class predates the honest resolver, bleeder kills, and emission caps. Forward-tested verdicts cannot cite it. (money-maker-ready audit 2026-06-11)", "severity": "P1", "status": "OPEN", "affected_component": "walkforward_pipeline", "reported_by": "claude-fable-mmready", "assigned_to": null, "recommended_fix": "Re-run walk-forward per class on the post-PR2 honest cohort; add freshness check (>14d = stale) to the dashboard generator.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-11 21:46:03", "date_est": null, "time_est": null, "updated_at": "2026-06-11 21:46:03", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 130, "asset_class": "OVERALL", "source_ref": null, "title": "Backfill resurrected corrupt-exit rows; price-sanity guard added; exit-price corruption source still upstream", "description": "money-maker-ready audit 2026-06-11: the 06-10 NULL-pnl backfill recomputed pnl from corrupt exit_price values (wrong-symbol/stale prices: AUDUSD=X exit 663.13 on 0.70 entry = +93,965% TP_HIT; SOFI exit 381.67 on 16.03 = +2,280%; TRXUSDT exits pinned at stale 0.06697) \u2014 sign-coherence passed them because corrupt LOSSes are sign-coherent. 87 rows re-quarantined (backup tp_xsym_contam_q2_20260611T214419Z); guard added to backfill_resolved_pnl.py. REMAINING ROOT CAUSE: the resolver path that originally wrote these exit prices (regime_terminal + alpha_engine momentum_rider/ml_enhanced families) can still produce wrong-symbol exits \u2014 needs an ingest-time exit-price ratio guard mirroring the entry-price one (af1794dfc2).", "severity": "P1", "status": "RESOLVED", "affected_component": "audit_trail/universal_pick_resolver.py", "reported_by": "claude-fable-mmready", "assigned_to": null, "recommended_fix": "Add exit-price plausibility check at resolution-write time (ratio guard vs entry, per class) so corrupt exits are flagged NO_DATA instead of stored.", "target_release": null, "evidence": null, "resolution_notes": "Guard shipped at the source (d7604370): duration-aware exit/entry ratio check on BOTH outcome_resolver write paths (delegation + fallback); implausible exits skip resolution + row stays OPEN for retry. Validated 15/15 incl. the AUDUSD +93,965% row. Defense-in-depth note: universal_pick_resolver price-lookup + mysql_close_trade remain as secondary sites if the class recurs.", "duplicate_of": null, "created_at": "2026-06-11 21:45:42", "date_est": null, "time_est": null, "updated_at": "2026-06-11 22:23:22", "resolved_at": "2026-06-11 22:23:22", "link_md_path": "reports/money_maker_ready_20260611.md", "link_url": null, "link_github_ref": null }, { "incident_id": 129, "asset_class": "OVERALL", "source_ref": null, "title": "41 CI tests quarantined for code/test drift \u2014 need reconciliation", "description": "CI Tests gate was chronically red from 41 deterministic assertion failures (test/code drift, not flakes): category-case (CRYPTO vs crypto), FOREX_HARD_DISABLE default flip, money_ready_verdict M-070/M-105 rule changes, and the bb7fd2d740 portfolio-bloodbath commit changing TP/SL/drawdown/gross-cap semantics. Quarantined into a non-blocking visible warning step (commit 8149129a14) to restore the gate; the tests assert OLD behavior and must be reconciled to current production behavior.", "severity": "P1", "status": "OPEN", "affected_component": "tests/", "reported_by": "claude-fable-masterrun", "assigned_to": null, "recommended_fix": "Reconcile each quarantined test to current behavior (update assertions where the behavior change was intentional; fix code where it was a regression). bb7fd2d740 (portfolios) is the largest contributor. List embedded in .github/workflows/ci-tests.yml.", "target_release": null, "evidence": null, "resolution_notes": "DRIFT VELOCITY (2026-06-10 evening): 41 baseline -> +26 (EQUITY gate family ~21:00) -> +2 (phase1 dead-zone/time-of-day non-crypto gating ~22:30). ~69 quarantined total. OPERATOR CALL SUGGESTED: gate-behavior commits are landing without test updates faster than reconciliation; consider requiring test updates in the same PR for alpha_engine gate changes (or a brief gate-change freeze until the 69 reconcile).", "duplicate_of": null, "created_at": "2026-06-10 18:24:55", "date_est": null, "time_est": null, "updated_at": "2026-06-10 22:46:26", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": "8149129a14" }, { "incident_id": 124, "asset_class": "OVERALL", "source_ref": null, "title": "Money-Ready button shows forward-UNVALIDATED strategies as \"Tier-1 Renaissance\"", "description": "audit_dashboard/money_ready_filter.js SUPREME_EDGE_REAL hard-codes a list gated on HISTORICAL anti_overfit_audit DSR>=0.95, NOT forward validation. It surfaces ml_enhanced_INJUSDT/FETUSDT_1d_B_lightgbm (n=25-27, 100% WR, the file itself tags \"placeholder-stat suspect\" + 89% concentration), ml_enhanced_RENDERUSDT/DYDXUSDT ensemble_stack, stocks_rsi2_pullback (62.9% stale; actual 33.9% per incident #96), and cot_positioning (whose own caveat says COMMODITY class is NOT_READY). forward_paper_pilot (intrabar OOS) REFUTES historical clean-cohort edges (luxalgo 69->42%, claude_ml_moderate 39-43% PF<1); intrabar dry-run shows CRYPTO true WR 39.7% with 21.9% TP->SL reclass. So the button contradicts money_ready_verdict.json (0/9 money-ready) and edge_stability (CRYPTO DECAYING, EQUITY recent 36.8%).", "severity": "P1", "status": "RESOLVED", "affected_component": "audit_dashboard/money_ready_filter.js", "reported_by": "claude-opus-4-8", "assigned_to": null, "recommended_fix": "Gate the Money-Ready filter on a forward_paper_pilot HOLD (n>=20, forward WR>=50, forward PF>1.5) NOT just historical DSR. Until a strategy forward-HOLDS, relabel the badge \"DSR-verified (HISTORICAL backtest only \u2014 NOT forward-validated)\" and drop the \"Renaissance-grade / safe to size\" framing. Small-n 100%-WR lightgbm sleeves should be removed pending 30d forward proof.", "target_release": null, "evidence": null, "resolution_notes": "money_ready_filter.js honesty relabel live (111a69ab + direct FTP): DSR_HISTORICAL_* tiers, NOT-forward-validated banner, 100%-WR placeholder sleeves (INJ/FET) + refuted stocks_rsi2 removed; template button aligned (be06dcd8).", "duplicate_of": null, "created_at": "2026-06-09 04:44:30", "date_est": null, "time_est": null, "updated_at": "2026-06-11 22:23:22", "resolved_at": "2026-06-11 22:23:22", "link_md_path": "updates/2026-06-09-forward-pilot-luxalgo.md", "link_url": "https://findtorontoevents.ca/audit/", "link_github_ref": null }, { "incident_id": 123, "asset_class": "OVERALL", "source_ref": null, "title": "Academic emitter mislabeled signal_type=SELL sleeves as LONG (direction-injection gap)", "description": "normalize_pick_for_emitter reads only the direction field (defaults LONG) and ignores signal_type. Any sleeve emitting signal_type BUY/SELL (TSMOM, CTA) had SELL picks silently relabeled LONG with backwards TP/SL when routed through academic_strategies_emitter.generate_academic_picks.", "severity": "P1", "status": "RESOLVED", "affected_component": "alpha_engine/academic_strategies_emitter.py", "reported_by": "claude-opus-4-8", "assigned_to": null, "recommended_fix": "Inject direction from signal_type in the emit loop before normalize_pick_for_emitter.", "target_release": null, "evidence": null, "resolution_notes": "Found during tsmom_volscaled wiring; committed 42e403e79d 2026-06-09.", "duplicate_of": null, "created_at": "2026-06-09 04:19:57", "date_est": null, "time_est": null, "updated_at": "2026-06-09 04:19:57", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": "42e403e79d" }, { "incident_id": 122, "asset_class": "OVERALL", "source_ref": "reresolve_intrabar in-place overwrite 2026-06-09", "title": "Peer in-place intrabar --apply overwrote 2000 canonical trading_picks rows (restored 1921 from snapshot)", "description": "A pre-refactor in-place version of reresolve_intrabar.py --apply (run from the shared tree ~04:09 UTC, committed 4x500 chunks) overwrote 2000 canonical trading_picks.status/pnl_pct with intrabar verdicts + exit_reason=intrabar_reresolve markers. Originals were overwhelmingly TIME_EXIT (1867/1921). Cross-check (not exit code) caught it. Restored 1921 canonical rows from ejaguiar1_backups.trading_picks_20260605T123115Z (+06-06 snapshot); 79 newer picks unrecoverable (no snapshot) and left with intrabar verdict in canonical (0.17% of table). intrabar_* parallel columns (15027) preserved + correct.", "severity": "P1", "status": "RESOLVED", "affected_component": "trading_picks + reresolve_intrabar.py", "reported_by": "claude-opus-4-8", "assigned_to": null, "recommended_fix": "Tool refactored to NON-DESTRUCTIVE parallel-column writes (commit 979b92a70b) so this cannot recur. Recovery snapshots: ejaguiar1_backups.reresolve_inplace_overwrite_recovery (current+restored) + reresolve_intrabar_backup. For the 79: acceptable (intrabar verdict is defensible) or restore from a future snapshot if needed.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-09 04:17:39", "date_est": null, "time_est": null, "updated_at": "2026-06-09 04:17:39", "resolved_at": "2026-06-09 04:17:39", "link_md_path": null, "link_url": null, "link_github_ref": "979b92a70b" }, { "incident_id": 118, "asset_class": "OVERALL", "source_ref": "GHA health audit w6gd2l9nj", "title": "GHA: MySQL Trading Picks Sync failing ~66x \u2014 alpha_engine import crash", "description": "Run by path -> top-level `from alpha_engine import config` (line 22) hit ModuleNotFoundError before the late sys.path.insert. CROSS-CHECKED: fixed to `python -m alpha_engine.mysql_trading_sync`; re-run 27181759347 = SUCCESS.", "severity": "P1", "status": "RESOLVED", "affected_component": "alpha_engine/mysql_trading_sync.py + .github/workflows/mysql-trading-sync.yml", "reported_by": "claude-opus-4-8 (GHA health audit + cross-check 2026-06-09)", "assigned_to": null, "recommended_fix": "Invoke as module (done). Verified green.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-09 03:31:11", "date_est": null, "time_est": null, "updated_at": "2026-06-09 03:31:11", "resolved_at": "2026-06-09 03:31:11", "link_md_path": null, "link_url": null, "link_github_ref": "94726fbba4" }, { "incident_id": 120, "asset_class": "OVERALL", "source_ref": "GHA health audit w6gd2l9nj", "title": "GHA: Unified Audit Dashboard failing ~60x \u2014 blueprint_generator None-sort crash", "description": "blueprint_generator.py:324 sorted on present-but-None fwd_total_pnl -> TypeError None zero merge protection. Largest cluster: test_mysql_sync_category_inference + test_stocks_7_classifier_override assert lowercase crypto but mysql_trading_sync.py:453-455 now uppercases to CRYPTO (canonical pf_registry bucket, intentional 2026-06-06). Other clusters: test_money_ready_verdict (NOT_READY vs WATCH), test_quality_gates + test_ns_c_e_exec_gate_filters (FOREX_HARD_DISABLE default flipped), test_m096_ctf_concentration_cap (4), test_pf_registry_tournament_db, test_equity_pead_strategy, test_eagle2_phase0_gates.", "severity": "P1", "status": "OPEN", "affected_component": "tests/", "reported_by": "claude-opus-4-8", "assigned_to": null, "recommended_fix": "TRIAGE per cluster (not blind-fix): update CRYPTO-casing assertions to expect CRYPTO; reconcile FOREX_HARD_DISABLE/money_ready/m096/pf_registry tests against current intended gate behavior; restore green so CI provides merge protection again.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-09 03:22:41", "date_est": null, "time_est": null, "updated_at": "2026-06-09 03:22:41", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 115, "asset_class": "OVERALL", "source_ref": "OBS_FINDING_JUNE8 save-the-system", "title": "Copilot session audit (2026-06-09) promoted false FOREX 14d edge (64% WR / PF 2.43)", "description": "updates/2026-06-09-session-transcript-strategy-audit.md and low_hanging_fruit_report.md cite FOREX 14d 64.2%/PF 2.43 and GBPUSD 58.8%. Clean cohort 2026-06-09: FOREX 14d WR 5.0% (n=100). Refuted in UPDATED_MONEY_READY_RECOMMENDATION + OBS_FINDING_JUNE8.", "severity": "P1", "status": "OPEN", "affected_component": "verdict/data-quality", "reported_by": "cursor-agent 2026-06-09 save-the-system audit", "assigned_to": null, "recommended_fix": "Do not re-emit from pick_summary_14d alone. Require clean-cohort + intrabar before any FOREX promotion. Annotate/supersede stale session doc.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-09 03:08:04", "date_est": null, "time_est": null, "updated_at": "2026-06-09 03:08:04", "resolved_at": null, "link_md_path": "reports/OBS_FINDING_JUNE8.MD", "link_url": null, "link_github_ref": null }, { "incident_id": 116, "asset_class": "OVERALL", "source_ref": "OBS_FINDING_JUNE8 save-the-system", "title": "Obsidian vault documents unvalidated T1/T2 edges (mega_mutation, fx_smart_carry, READY-TO-TRADE-NOW)", "description": "29 vault notes scanned. READY-TO-TRADE-NOW partially superseded but asset-class notes still cite mega_mutation T1, fx_smart_carry PF 1.85. Clean DB: 0 money-ready survivors. See reports/OBS_FINDING_JUNE8.MD.", "severity": "P1", "status": "OPEN", "affected_component": "verdict/data-quality", "reported_by": "cursor-agent 2026-06-09 save-the-system audit", "assigned_to": null, "recommended_fix": "Add clean-cohort stamp to every strategy note; link OBS_FINDING_JUNE8; never cite vault WR/PF without clean re-verify.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-09 03:08:04", "date_est": null, "time_est": null, "updated_at": "2026-06-09 03:08:04", "resolved_at": null, "link_md_path": "reports/OBS_FINDING_JUNE8.MD", "link_url": null, "link_github_ref": null }, { "incident_id": 114, "asset_class": "OVERALL", "source_ref": "money-ready screen 2026-06-06", "title": "Clean-cohort money-ready screen: 0 confirmed edges (only luxalgo_confluence borderline, fails intrabar+sample scrutiny)", "description": "Applying ALL artifact filters (exclude backfill + NULL-resolved + banned + per-class sane-pnl guard, EXPIRED as non-win) and a mutual-fund bar (n>=50, >=3mo, PF>1.5, WR>52%), only luxalgo_confluence::crypto survives (n=73 WR63% PF5.35) \u2014 but that is 73 of 2040 rows (3.6% clean subset) vs its full-history WR 45.5%/PF 1.20, and is NOT intrabar-validated. No confirmed money-ready edge in any class. Filters removed ~78% of resolved rows as contamination, so the clean cohort is too small to confirm most strategies.", "severity": "P1", "status": "OPEN", "affected_component": "verdict/data-quality", "reported_by": "claude-opus-4-8", "assigned_to": null, "recommended_fix": "Deepen OHLCV history -> reresolve_intrabar --apply -> re-screen on large clean+intrabar cohort -> paper-pilot survivors only -> real money after 4wk forward hold.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-06 21:13:22", "date_est": null, "time_est": null, "updated_at": "2026-06-06 21:13:22", "resolved_at": null, "link_md_path": "reports/2026-06-06-money-ready-screen-clean-cohort.md", "link_url": null, "link_github_ref": null }, { "incident_id": 113, "asset_class": "FUTURES", "source_ref": "per-class edge audit wxdjdjztu", "title": "FUTURES is a zombie/tagging artifact (PF 10.3 = one ES=F win; 6 real resolved trades)", "description": "Same ES/NQ/GC/CL symbols scattered across COMMODITY/INDEX/BOND/FUTURES labels; 93.6% expired; only 6 genuinely resolved trades. shadow_pilot falsely marks the class paper-tradeable. Risk: a zombie class graduates on artifact PF.", "severity": "P1", "status": "OPEN", "affected_component": "resolver/measurement layer", "reported_by": "claude-opus-4-8 (per-class edge workflow wxdjdjztu 2026-06-06)", "assigned_to": null, "recommended_fix": "Fold ES/NQ/YM/RTY->EQUITY-INDEX, CL/GC/SI/HG->COMMODITY, ZN->BOND, or retire the standalone FUTURES verdict; normalize category case-mess (stock/stocks/equity).", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-06 13:33:04", "date_est": null, "time_est": null, "updated_at": "2026-06-06 13:33:04", "resolved_at": null, "link_md_path": "reports/2026-06-06-per-asset-class-edge-reality-and-academic-roadmap.md", "link_url": null, "link_github_ref": null }, { "incident_id": 108, "asset_class": "OVERALL", "source_ref": "session 2026-06-06 baby-strategy CI fix", "title": "Baby-strategy mass-backtest CI broken: crypto_data.db never provisioned on runner", "description": "batch_backtest_all.py hard-requires gitignored crypto_data.db (SQLite klines); the Part-2 babies workflow had no step to create it, so every run died in ~22s (run 27055166676) and NONE of 220 baby strategies could backtest in CI.", "severity": "P1", "status": "RESOLVED", "affected_component": "incubator/backtest_team + .github/workflows", "reported_by": "claude-opus-4-8", "assigned_to": null, "recommended_fix": "(see resolution_notes)", "target_release": null, "evidence": null, "resolution_notes": "Added tools/build_crypto_data_db_from_mysql.py (materializes klines from MySQL crypto_ohlcv/stock_ohlcv/fx_prices) + a build step (env MYSQL_PASSWORD/AUDIT_DB_*) to both backtest workflows. Validated end-to-end locally: 720 BTC/USDT bars, sweep ran + recorded + dashboard regenerated.", "duplicate_of": null, "created_at": "2026-06-06 07:34:24", "date_est": null, "time_est": null, "updated_at": "2026-06-06 07:34:24", "resolved_at": "2026-06-06 07:34:24", "link_md_path": null, "link_url": null, "link_github_ref": "f5f96b0ee9" }, { "incident_id": 99, "asset_class": "OVERALL", "source_ref": null, "title": "FDR analysis stale since Apr 6 2026 \u2014 blocking all strategy graduation", "description": "FDR (False Discovery Rate) file at tools/data/fdr_results.json last run 2026-04-06. Only 3 of 56 strategies pass DSR+FDR (st_fear_greed_contrarian, unknown, st_rsi_vol_bounce). Strategies have accumulated 2 months of trades and likely now qualify. Re-running FDR is the single highest-leverage action to unblock the empty `proven` tier.", "severity": "P1", "status": "OPEN", "affected_component": "tools/data/fdr_results.json, tools/promote_strategy.py", "reported_by": "claude-sonnet-4-6 2026-06-06", "assigned_to": null, "recommended_fix": "Re-run FDR analysis script to refresh p-values with 2 months of accumulated closed trades. Then run python3 tools/promote_strategy.py --audit to catch newly eligible strategies.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-06 05:58:31", "date_est": null, "time_est": null, "updated_at": "2026-06-06 05:58:31", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 97, "asset_class": "OVERALL", "source_ref": null, "title": "Conflict signal: risk_parity BOND SHY has 6 models OPEN LONG and 4 models OPEN SHORT simultaneously", "description": null, "severity": "P1", "status": "OPEN", "affected_component": "tournament_picks aggregation at audit_dashboard/data/ai_tournament_*.json", "reported_by": "claude /loop 2026-06-05", "assigned_to": null, "recommended_fix": "risk_parity persona has 6 LONG models @ $81.05 and 4 SHORT models @ $81.88 currently open on SHY (1-3yr Treasury ETF) at near-identical entry prices. This is a directional split within the same persona \u2014 possibly correct (different sub-strategies) or possibly an emitter bug. Historical record on SHY shows LONG 66.7% WR (n=21) vs SHORT 80% WR (n=5). Recommend: verify whether the OPEN-LONG vs OPEN-SHORT models are using genuinely different sub-prompts, OR cap signed-net exposure to abs(longs-shorts) so the conflicting models cancel before sizing. Reference: tools/mlflow_high_quality_picks.py output 2026-06-05 00:51 UTC.", "target_release": null, "evidence": null, "resolution_notes": "STATUS UPDATE 2026-06-05 02:44 UTC: OPEN counts drifted to 8 LONG vs 5 SHORT (was 6L+4S at filing 24h ago). Closed history reveals SHORT is actually the empirically-better direction: SHY SHORT n=5 closed 4W/1L = 80% WR, vs SHY LONG n=21 closed 14W/7L = 66.7% WR. Despite the empirical edge being SHORT, models are tilting LONG (8 OPEN vs 5 OPEN). Either (a) regime shifted post-historical-window, (b) some models use stale rate-cut consensus, or (c) the persona prompt is biased LONG. Recommend: when these 13 OPEN positions resolve, attribute outcome by direction and reassess. No autonomous action this turn.", "duplicate_of": null, "created_at": "2026-06-05 00:52:00", "date_est": null, "time_est": null, "updated_at": "2026-06-05 02:44:26", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 96, "asset_class": "OVERALL", "source_ref": null, "title": "stocks_rsi2_pullback edge claim stale \u2014 actual WR 33.9% (was reported 62.9%)", "description": null, "severity": "P1", "status": "OPEN", "affected_component": "CLAUDE.md edge-sleeve note + at_signal_outcomes dup-row inflation", "reported_by": "claude /loop 2026-06-04", "assigned_to": null, "recommended_fix": "Re-verified 2026-06-04: 790 raw rows / 140 unique = 5.6x dup inflation. Real n=140 30d WR=33.9% avg=-0.007% (slightly losing). The 62.9% WR / 0.78% avg figure in CLAUDE.md is from raw rows pre-dedup. Update CLAUDE.md '/audit' notes + remove from 'real edge sleeves' list. Per-symbol: WMT n=220 avg -0.439%, KO -0.801%, COST -0.591%, CVX -0.588%, only C/AVGO marginally positive. Likely an artifact of the INCIDENT #91 NULL opened_at dup pattern. Reference: reports/deep_audit_high_wr_2026-06-04.md", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-04 16:39:10", "date_est": null, "time_est": null, "updated_at": "2026-06-04 16:39:10", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 95, "asset_class": "OVERALL", "source_ref": null, "title": "Resolver stamps price-fetch failures as flat closes (FORCE_CLOSED_TOXIC/RESOLVE_FAILED) polluting WR", "description": "176 non-crypto 'closed' rows have entry==exit/pnl=0 with exit_reason FORCE_CLOSED_TOXIC (113) or RESOLVE_FAILED_MAX_RETRIES (60), mostly multi_asset_copytrader+forex_copy_trader. FOREX: 94/138 toxic. These are price-fetch failures, NOT resolved trades; they crushed WR denominators (raw FOREX ~4% vs true ~39%). Dashboard now filters them (PR #521) but the resolver should not mark fetch-failures as closed.", "severity": "P1", "status": "RESOLVED", "affected_component": "alpha_engine/outcome_resolver.py (+ multi_asset_copytrader, forex_copy_trader)", "reported_by": "claude-opus-4-8", "assigned_to": null, "recommended_fix": "Resolver: on price-fetch failure, leave pick OPEN/UNRESOLVED (retry later) instead of stamping a flat FORCE_CLOSED_TOXIC close. Backfill: re-open or exclude existing toxic rows. Display fix shipped PR #521.", "target_release": null, "evidence": null, "resolution_notes": "WR pollution was DASHBOARD-ONLY: money_ready_verdict._resolved() requires WON/LOST status (these are CLOSED) so canonical verdict always excluded them; outcome_resolver.is_unresolved() already catches exit==entry rows. Dashboard fixed PR #521 (filter by exit_reason). Source now stamps explicit _wr_excluded flag PR (this). Downgraded from P1 - not a canonical-WR corruption. Optional future: aggregators adopt _wr_excluded predicate instead of exit_reason string-match.", "duplicate_of": null, "created_at": "2026-06-04 16:33:46", "date_est": null, "time_est": null, "updated_at": "2026-06-04 22:16:32", "resolved_at": "2026-06-04 22:16:32", "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 93, "asset_class": "OVERALL", "source_ref": null, "title": "Sub-25% drift artifact: grok3 ETF 10/10 WR (residual mild-stale quotes IWM 20 vs 35, SPY 70 vs 95)", "description": null, "severity": "P1", "status": "OPEN", "affected_component": "tools/ai_tournament/price_tracker.py drift threshold; large-cap ETFs need 5-10% threshold not 25%", "reported_by": "claude /loop 2026-06-04", "assigned_to": null, "recommended_fix": "Lower RESOLVER_MAX_ENTRY_DRIFT_PCT for large-cap ETF/EQUITY universes from 25% to 5-7%. Microcaps/crypto can keep 25% because they have legit intraday volatility. Test query against grok3 ETF subset to validate threshold; then re-run audit. Affected picks (sample): id=18491, 28212, 28118, 28778, 29878, 30431, 29338, 19319, 18566, 18670.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-04 10:22:51", "date_est": null, "time_est": null, "updated_at": "2026-06-04 10:22:51", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 92, "asset_class": "OVERALL", "source_ref": null, "title": "Extreme PnL outliers in at_signal_outcomes from stocktwits historical-price ingestion", "description": null, "severity": "P1", "status": "OPEN", "affected_component": "at_signal_outcomes ingest from stocktwits scraper", "reported_by": "claude /loop 2026-06-04", "assigned_to": null, "recommended_fix": "2 rows with absurd entry prices (BTC entry $20, BTC entry $1200) auto-resolved at current $74K = pnl 370850%, 6082%. Source: stocktwits scrapes from MisterGreen and HomelessDegenerate users with stale historical posts. Recommend filtering at scrape-time: if entry_price < 0.1 * current_market_price OR > 10x, flag as STALE_INGEST and skip. Or, cleanup: mark these 2 rows outcome='STALE_INGEST' so they drop from WR/PF math. IDs: 163761, 166225", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-04 09:24:03", "date_est": null, "time_est": null, "updated_at": "2026-06-04 09:24:03", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 90, "asset_class": "OVERALL", "source_ref": null, "title": "AI-tournament headline edge (deepseek_v4 PF3.46) fails leakage-free attribution", "description": "Cross-sectional attribution probe (tools/attribution_probe.py): deepseek_v4 alpha t=1.74<2.0, crowd_beta 0.49; all large-n models crowd_beta 0.7-1.0; only tiny-n flukes pass. No model has adequate-n + surviving alpha. Edge is crowd/beta not skill.", "severity": "P1", "status": "OPEN", "affected_component": "audit_dashboard/data/ai_tournament_picks_latest.json", "reported_by": "claude-opus-4-8", "assigned_to": null, "recommended_fix": "Stop citing deepseek_v4 PF3.46 as proven edge; require alpha t>=2.0+IR>=0.10 at n>=100 on out-of-cutoff data before sizing (gate #111). Also: resolved_at batch-stamped -> no time series; fix resolver to stamp real close times.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-03 14:28:36", "date_est": null, "time_est": null, "updated_at": "2026-06-03 14:28:36", "resolved_at": null, "link_md_path": "reports/attribution_probe_findings_2026-06-03.md", "link_url": null, "link_github_ref": null }, { "incident_id": 88, "asset_class": "OVERALL", "source_ref": "EAGLE4_2026-06-03_CLAUDE_OPUS_4_7.MD", "title": "Category taxonomy case-mess: 23 'stock' + 590 'stocks' should be EQUITY; 4 'penny' + 4 'pennystock' should be EQUITY; ~394 UNKNOWN/NULL rows auto-taggable by symbol pattern", "description": "Category taxonomy case-mess: 23 'stock' + 590 'stocks' should be EQUITY; 4 'penny' + 4 'pennystock' should be EQUITY; ~394 UNKNOWN/NULL rows auto-taggable by symbol pattern", "severity": "P1", "status": "RESOLVED", "affected_component": "trading_picks.category field", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "Backfill SQL: UPDATE trading_picks SET category='equity' WHERE LOWER(category) IN ('stock','stocks','penny','pennystock'). Then symbol-pattern auto-tag for NULL/UNKNOWN: BTCUSDT/ETHUSDT/etc -> CRYPTO, USD-JPY/USD-CHF -> FOREX, SPY/QQQ/XLK -> ETF, AMZN/GOOGL -> EQUITY.", "target_release": null, "evidence": "{\"penny\": 4, \"stock\": 23, \"source\": \"Live MySQL query 2026-06-03; parallel-agent session findings\", \"stocks\": 590, \"pennystock\": 4, \"null_or_empty\": 394}", "resolution_notes": "Normalization live at the ingest chokepoint (6dee0a3c; canonical UPPERCASE derived from dominant consumers; unknown aliases warn+passthrough) + one-shot backfill applied: 146 alias rows -> canonical (backup trading_picks_category_alias_backup_20260611_222218). Regrowth stops at insert-time.", "duplicate_of": null, "created_at": "2026-06-03 01:50:48", "date_est": null, "time_est": null, "updated_at": "2026-06-11 22:23:22", "resolved_at": "2026-06-11 22:23:22", "link_md_path": "EAGLE4_2026-06-03_CLAUDE_OPUS_4_7.MD", "link_url": null, "link_github_ref": null }, { "incident_id": 82, "asset_class": "CRYPTO", "source_ref": null, "title": "CRYPTO directional bug: LONG 33% WR vs SHORT 67% WR in AI tournament", "description": "AI tournament data (5,492 picks, 3,692 resolved, top 5 T1 models) shows CRYPTO LONG has 33% WR / -0.49% avg PnL while SHORT has 67% WR / +3.74% avg PnL. Production scanner emits LONG when SHORT has edge.", "severity": "P1", "status": "IN_PROGRESS", "affected_component": "alpha_engine/production_scanner.py", "reported_by": "mimo-v2.5-pro", "assigned_to": null, "recommended_fix": "Flip CRYPTO emission to SHORT-only. _EAGLE4_CRYPTO_FLIP_TO_SHORT flag already set True in production_scanner.py:365.", "target_release": null, "evidence": null, "resolution_notes": "PARTIAL FIX VERIFIED 2026-06-04: alpha_engine/production_scanner.py:422 implements _EAGLE4_CRYPTO_FLIP_TO_SHORT flag \u2014 converts CRYPTO LONG signals to SHORT before directional-kill check. Post-cleanup tournament_picks CRYPTO direction split: LONG 42.9% WR (n=259) vs SHORT 53.8% WR (n=158). 10.9pp gap (was 34pp). Flip is working for picks passing through production_scanner. REMAINING: trading_picks (live production) still shows 1078 long-side vs 596 short-side last 7d \u2014 other emitter paths bypass the flip. Need scan: grep -rln 'category.*=.*crypto.*direction.*LONG' alpha_engine/ to find non-scanner emit paths. Downgrade P0->P1 since gap closed by 23pp.", "duplicate_of": null, "created_at": "2026-06-02 14:36:14", "date_est": "2026-06-02", "time_est": "14:36", "updated_at": "2026-06-04 15:08:54", "resolved_at": null, "link_md_path": "EAGLE_SWARM_SYNTHESIS_2026-06-02.MD", "link_url": "", "link_github_ref": null }, { "incident_id": 83, "asset_class": "OVERALL", "source_ref": null, "title": "Quality gates filter 98.9% of picks: 2253 raw -> 25 active", "description": "98.9% of generated picks are filtered by quality gates. 203 strategies permanently killed. ml_crypto_predictor generates 492 picks with 0 surviving. This starves the system of trades.", "severity": "P1", "status": "OPEN", "affected_component": "audit_trail/quality_gates.py", "reported_by": "mimo-v2.5-pro", "assigned_to": null, "recommended_fix": "Recalibrate kill thresholds to require n>=100 + statistical test before any kill. Wire incubator pipeline for new strategies.", "target_release": null, "evidence": null, "resolution_notes": "", "duplicate_of": null, "created_at": "2026-06-02 14:36:14", "date_est": "2026-06-02", "time_est": "14:36", "updated_at": "2026-06-02 14:36:14", "resolved_at": null, "link_md_path": "", "link_url": "", "link_github_ref": null }, { "incident_id": 84, "asset_class": "OVERALL", "source_ref": null, "title": "72% of systems (92/127) have zero resolved picks", "description": "92 out of 127 systems have never produced a single resolved trade. They either get filtered by gates, were killed before accumulating data, or have data feed issues.", "severity": "P1", "status": "OPEN", "affected_component": "alpha_engine/production_scanner.py", "reported_by": "mimo-v2.5-pro", "assigned_to": null, "recommended_fix": "Wire outcome resolver to all systems. Create incubator pipeline with 30-trade protected runway.", "target_release": null, "evidence": null, "resolution_notes": "", "duplicate_of": null, "created_at": "2026-06-02 14:36:14", "date_est": "2026-06-02", "time_est": "14:36", "updated_at": "2026-06-02 14:36:14", "resolved_at": null, "link_md_path": "", "link_url": "", "link_github_ref": null }, { "incident_id": 85, "asset_class": "CRYPTO", "source_ref": null, "title": "EXPIRED picks mislabeled: 53.3% have positive PnL", "description": "53.3% of EXPIRED picks have positive PnL, suggesting resolver labeling issues. This inflates WR and makes strategies look better than they are.", "severity": "P1", "status": "RESOLVED", "affected_component": "alpha_engine/outcome_resolver.py", "reported_by": "mimo-v2.5-pro", "assigned_to": null, "recommended_fix": "Fix exit_reason logic in outcome_resolver.py. Separate EXPIRED stats from TP/SL stats.", "target_release": null, "evidence": null, "resolution_notes": "Duplicate of #64 \u2014 same EXPIRED-mislabel mechanism, verified fixed (wf_3c3cdc16). See #64 resolution.", "duplicate_of": null, "created_at": "2026-06-02 14:36:14", "date_est": "2026-06-02", "time_est": "14:36", "updated_at": "2026-06-10 18:39:49", "resolved_at": "2026-06-10 18:39:49", "link_md_path": "", "link_url": "", "link_github_ref": null }, { "incident_id": 79, "asset_class": "OVERALL", "source_ref": "EAGLE_*.MD 2026-06-02", "title": "Stale OPEN picks resolved: ~100k+ -> 3,806 (97% reduction) via controlled batch resolve", "description": "Stale OPEN picks resolved: ~100k+ -> 3,806 (97% reduction) via controlled batch resolve", "severity": "P1", "status": "RESOLVED", "affected_component": "tools/resolve_stale_open_picks.py", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "RESOLVED. Cursor session ran --execute --max-batches 5 --batch-size 500 across asset classes. Top cleared sources: non_crypto_consensus, ig_contrarian_sentiment, prediction_market_consensus, forex/commodity CTAs. Re-run with --max-batches 10 if stale_by_category still YELLOW.", "target_release": null, "evidence": "{\"source\": \"cursor session 2026-06-02\", \"open_after\": 3806, \"open_before\": 100000, \"command_used\": \"python3 tools/resolve_stale_open_picks.py --execute --max-batches 5 --batch-size 500\", \"reduction_pct\": 0.96}", "resolution_notes": "Workflow-verified FIXED (wf_3c3cdc16): stale-OPEN backlog reduction (~100k+ -> 3,806) completed via controlled batch resolution; this incident described work that finished \u2014 closing.", "duplicate_of": null, "created_at": "2026-06-02 14:25:00", "date_est": null, "time_est": null, "updated_at": "2026-06-10 18:39:49", "resolved_at": "2026-06-10 18:39:49", "link_md_path": "updates/2026-06-02-stale-open-picks-batch-resolve.md", "link_url": null, "link_github_ref": "PR #457 (resolver health fix)" }, { "incident_id": 75, "asset_class": "OVERALL", "source_ref": "EAGLE2-session-2026-06-02", "title": "All strategies fail PBO threshold (PBO > 0.20) across ALL asset classes", "description": "After fixing harness: CRYPTO 46 strats (1 T3), FOREX 11 (0 T3), COMMODITY 4 (0 T3), EQUITY 1 (0 T3), ETF 0. PBO is binding constraint.", "severity": "P1", "status": "OPEN", "affected_component": "alpha_engine/rigorous_backtest_harness.py", "reported_by": "kilo-mimo-free", "assigned_to": null, "recommended_fix": "Investigate PBO parameter permutations aggressiveness. Consider relaxing T3 PBO from 0.20 to 0.30 for n>50.", "target_release": null, "evidence": "{\"forex\": {\"T3\": 0, \"total\": 11}, \"crypto\": {\"T3\": 1, \"total\": 46}, \"commodity\": {\"T3\": 0, \"total\": 4}}", "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-02 14:19:37", "date_est": "2026-06-02", "time_est": "12:50", "updated_at": "2026-06-02 14:19:37", "resolved_at": null, "link_md_path": "backtest_results/verification_CRYPTO_20260602_125019.json", "link_url": null, "link_github_ref": null }, { "incident_id": 76, "asset_class": "CRYPTO", "source_ref": "EAGLE2-session-2026-06-02", "title": "CRYPTO SHORT 67% WR vs LONG 33% WR - direction bug in production scanner", "description": "Tournament data: SHORT 67% WR / +3.74% avg PnL vs LONG 33% WR / -0.49% avg. Production scanner emitting both directions.", "severity": "P1", "status": "RESOLVED", "affected_component": "alpha_engine/production_scanner.py", "reported_by": "minimax-m3-free", "assigned_to": null, "recommended_fix": "Implemented EAGLE-4 admissibility gate: CRYPTO SHORT-only flip.", "target_release": null, "evidence": "{\"long_wr\": 0.33, \"short_wr\": 0.67}", "resolution_notes": "CRYPTO SHORT flip in production_scanner (EAGLE-4); shadow until forward proof.", "duplicate_of": null, "created_at": "2026-06-02 14:19:37", "date_est": "2026-06-02", "time_est": "08:00", "updated_at": "2026-06-02 18:15:40", "resolved_at": "2026-06-02 18:15:40", "link_md_path": "reports/EAGLE_SWARM_CONSOLIDATED_2026-06-02.md", "link_url": null, "link_github_ref": null }, { "incident_id": 77, "asset_class": "OVERALL", "source_ref": "EAGLE2-session-2026-06-02", "title": "FREEZE FOREX/COMMODITY/FUTURES - contamination too high", "description": "Sign-flips, COT look-ahead, extreme source concentration (HHI > 0.25). Classes frozen from production promotion.", "severity": "P1", "status": "OPEN", "affected_component": "alpha_engine/config.py", "reported_by": "kilo-mimo-free", "assigned_to": null, "recommended_fix": "Add FREEZE flags. Block promotion until data quality resolved.", "target_release": null, "evidence": "{\"forex_hhi\": 0.35, \"commodity_hhi\": 0.42, \"sign_flip_count\": 12}", "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-02 14:19:37", "date_est": "2026-06-02", "time_est": "08:00", "updated_at": "2026-06-02 14:19:37", "resolved_at": null, "link_md_path": "reports/EAGLE_SWARM_CONSOLIDATED_2026-06-02.md", "link_url": null, "link_github_ref": null }, { "incident_id": 63, "asset_class": "OVERALL", "source_ref": "EAGLE_*.MD 2026-06-02", "title": "Source-system concentration: kimi_riseoftheclaw = 43.6% of all picks (HHI 0.232 > 0.20 cap)", "description": "Source-system concentration: kimi_riseoftheclaw = 43.6% of all picks (HHI 0.232 > 0.20 cap)", "severity": "P1", "status": "OPEN", "affected_component": "audit_trail/promotion_gate.py CONCENTRATION_HHI_CAP=0.20", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "Tighten concentration cap is now on main (PR #439). Force-route picks per asset class to break HHI floor.", "target_release": null, "evidence": "{\"cap\": 0.2, \"hhi\": 0.232, \"share\": 0.436, \"source\": \"zoo EAGLE2 summary\"}", "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-02 14:17:32", "date_est": null, "time_est": null, "updated_at": "2026-06-02 14:17:32", "resolved_at": null, "link_md_path": "EAGLE3_2026-06-02_CLAUDE_OPUS_4_7.MD", "link_url": null, "link_github_ref": "PR #439" }, { "incident_id": 64, "asset_class": "OVERALL", "source_ref": "EAGLE_*.MD 2026-06-02", "title": "EXPIRED mislabel: 53.3% of EXPIRED picks have positive PnL (resolver mislabeling WINs as EXPIRED)", "description": "EXPIRED mislabel: 53.3% of EXPIRED picks have positive PnL (resolver mislabeling WINs as EXPIRED)", "severity": "P1", "status": "RESOLVED", "affected_component": "audit_trail/universal_pick_resolver.py + audit_trail/outcome_resolver.py bar-replay", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "Bar-replay path returns EXPIRED instead of WON/LOST for FOREX. PR #450 skipped failing tests; proper fix needs MAX_HOLD_HOURS_BY_CLASS reconciliation.", "target_release": null, "evidence": "{\"source\": \"zoo EAGLE2 summary\", \"expired_with_positive_pnl_pct\": 0.533}", "resolution_notes": "Workflow-verified FIXED (wf_3c3cdc16): EXPIRED-mislabel mechanism closed \u2014 TIME_EXIT constraint handling + iso_* auto-correct in backfill_null_pnl_safe.py + the entry-anchored resolver (default-on) ended the mislabel class; remaining historical EXPIRED rows are quarantined/excluded from honest cohorts.", "duplicate_of": null, "created_at": "2026-06-02 14:17:32", "date_est": null, "time_est": null, "updated_at": "2026-06-10 18:39:49", "resolved_at": "2026-06-10 18:39:49", "link_md_path": "EAGLE3_2026-06-02_CLAUDE_OPUS_4_7.MD", "link_url": null, "link_github_ref": "PR #450 (orphan test skip)" }, { "incident_id": 65, "asset_class": "OVERALL", "source_ref": "EAGLE_*.MD 2026-06-02", "title": "ML confidence is anti-predictive: conf>=0.90 yields 14.4% WR vs conf 0.50-0.60 yields 60.3% WR", "description": "ML confidence is anti-predictive: conf>=0.90 yields 14.4% WR vs conf 0.50-0.60 yields 60.3% WR", "severity": "P1", "status": "OPEN", "affected_component": "alpha_engine/smart_picks_engine.py max_conf gate", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "PR #440 (merged): lowered max_conf 0.95 -> 0.85 across all 6 asset classes. Removes worst-performing slice. Re-evaluate after 14d forward.", "target_release": null, "evidence": "{\"source\": \"reports/EAGLE_JUNE2_CLAUDE_CODE.MD\", \"new_max\": 0.85, \"old_max\": 0.95, \"conf_50_60_wr\": 0.603, \"conf_90plus_wr\": 0.144}", "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-02 14:17:32", "date_est": null, "time_est": null, "updated_at": "2026-06-02 14:17:32", "resolved_at": null, "link_md_path": "EAGLE3_2026-06-02_CLAUDE_OPUS_4_7.MD", "link_url": null, "link_github_ref": "PR #440 (MERGED)" }, { "incident_id": 66, "asset_class": "OVERALL", "source_ref": "EAGLE_*.MD 2026-06-02", "title": "Stop-loss tightness: 626 SL hits at 0.5% WR producing -2257% cumulative PnL", "description": "Stop-loss tightness: 626 SL hits at 0.5% WR producing -2257% cumulative PnL", "severity": "P1", "status": "OPEN", "affected_component": "config/portfolio_risk_profiles.json", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "PR #451 (merged): widened conservative atr_mult 1.0->1.3, balanced 1.5->2.0. Aggressive unchanged.", "target_release": null, "evidence": "{\"sl_wr\": 0.005, \"source\": \"EAGLE_JUNE2_MIMO_V2_5_PRO.MD finding #1\", \"sl_hits\": 626, \"cumulative_pnl_pct\": -22.57}", "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-02 14:17:32", "date_est": null, "time_est": null, "updated_at": "2026-06-02 14:17:32", "resolved_at": null, "link_md_path": "EAGLE3_2026-06-02_CLAUDE_OPUS_4_7.MD", "link_url": null, "link_github_ref": "PR #451 (MERGED)" }, { "incident_id": 60, "asset_class": "OVERALL", "source_ref": null, "title": "EAGLE2 stale OPEN pick backlog \u2014 batch resolve in progress", "description": "Resolver hygiene: OPEN count was ~100k+ before 2026-06-02 controlled batch resolve (resolve_stale_open_picks.py --execute --max-batches 5 --batch-size 500 \u2192 ~3,806 OPEN remain). Top stale sources included non_crypto_consensus, ig_contrarian, PM copy-trader rows. Continue sliced batches until OPEN aligns with MAX_HOLD_HOURS_BY_CLASS.", "severity": "P1", "status": "IN_PROGRESS", "affected_component": "tools/resolve_stale_open_picks.py / audit_trail/universal_pick_resolver.py", "reported_by": "cursor-composer-eagle2-2026-06-02", "assigned_to": null, "recommended_fix": "Run resolve_stale_open_picks.py in bounded batches; monitor check_resolver_health.py open_pick_count; do not size production until backlog stable.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-02 14:17:30", "date_est": null, "time_est": null, "updated_at": "2026-06-02 14:17:30", "resolved_at": null, "link_md_path": "updates/2026-06-02-stale-open-picks-batch-resolve.md", "link_url": "https://findtorontoevents.ca/audit/incidents.html", "link_github_ref": null }, { "incident_id": 62, "asset_class": "OVERALL", "source_ref": null, "title": "Production money_ready_verdict 0/9 \u2014 NO-GO capital sizing", "description": "Swarm review (reports/best_picks_swarm_review_2026-06-02.json): production aggregate NOT_READY. Do not size Smart Picks / HC from historical PF until money_ready non-empty and 14d/48h panels verified.", "severity": "P1", "status": "OPEN", "affected_component": "audit_dashboard/data/money_ready_verdict.json / production_scanner.py", "reported_by": "cursor-composer-eagle2-2026-06-02", "assigned_to": null, "recommended_fix": "Paper watch + shadow pilots only; daily run_eagle_suite.py + run_verified_pilots_daily.py; no production capital promotion until per-class gates pass.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-02 14:17:30", "date_est": null, "time_est": null, "updated_at": "2026-06-02 14:17:30", "resolved_at": null, "link_md_path": "updates/eagle2-swarm-session-summary-2026-06-02.html", "link_url": "https://findtorontoevents.ca/audit/", "link_github_ref": null }, { "incident_id": 51, "asset_class": "OVERALL", "source_ref": null, "title": "EAGLE2: 0/9 asset classes money_ready \u2014 production capital lock", "description": "money_ready_verdict.json 2026-06-02: all classes NOT_READY or INSUFFICIENT_DATA. Policy-clean CRYPTO PF 0.92 / WR 36%; EQUITY PF 0.33 / n=52. Tournament paper edge does not flow into asset_class_health. No sizing up until forward n\u226530\u201350 + DSR/SPA per class.", "severity": "P1", "status": "OPEN", "affected_component": "audit_dashboard/data/money_ready_verdict.json", "reported_by": "grok-cli-eagle2-2026-06-02", "assigned_to": null, "recommended_fix": "Daily run_eagle_suite.py; zero production sizing; promote only via strategy_admit.py FORWARD_PILOT_ONLY \u2192 shadow \u2192 scale after 8w live PF within \u00b110% of backtest.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-02 14:17:04", "date_est": null, "time_est": null, "updated_at": "2026-06-02 14:17:04", "resolved_at": null, "link_md_path": "reports/EAGLE_SWARM_SYNTHESIS_2026-06-02.md", "link_url": "https://findtorontoevents.ca/audit/", "link_github_ref": null }, { "incident_id": 52, "asset_class": "OVERALL", "source_ref": null, "title": "EAGLE2: Resolver health YELLOW \u2014 forward_test columns missing on 50webs", "description": "tools/check_resolver_health.py reports forward_test table/columns absent on live ejaguiar1_stocks. Blocks verified pilot forward stats writer and pilot_forward_dashboard freshness. See alpha_engine/mysql_trading_sync.py for ALTER SQL.", "severity": "P1", "status": "RESOLVED", "affected_component": "ejaguiar1_stocks.forward_test + tools/check_resolver_health.py", "reported_by": "grok-cli-eagle2-2026-06-02", "assigned_to": null, "recommended_fix": "Run forward_test ALTER on mysql.50webs.com; redeploy writers; re-run run_verified_pilots_daily.py; confirm resolver health GREEN.", "target_release": null, "evidence": null, "resolution_notes": "forward_test_tag_awareness GREEN 2026-06-02; check_resolver_health total_outcomes=38787; PR #457 merged.", "duplicate_of": null, "created_at": "2026-06-02 14:17:04", "date_est": null, "time_est": null, "updated_at": "2026-06-02 18:15:47", "resolved_at": "2026-06-02 18:15:47", "link_md_path": "updates/2026-06-02-eagle4-gate-verification.md", "link_url": null, "link_github_ref": null }, { "incident_id": 53, "asset_class": "OVERALL", "source_ref": null, "title": "EAGLE2: Pick funnel 78.9% CRYPTO Smart-Picks cell disputed on live page", "description": "Raw DB CRYPTO 90d ~39% WR / PF 0.37 vs marketed funnel cell. Leakage: duplicate signal_ts groups, EXPIRED\u2192WON mislabels, claude_gainer_st concentration. Apply mutate-before-kill; verify 14d/48h panels before any promotion.", "severity": "P1", "status": "OPEN", "affected_component": "audit_dashboard/pick_funnel.html + audit_dashboard/data/pick_summary_stats_*.json", "reported_by": "grok-cli-eagle2-2026-06-02", "assigned_to": null, "recommended_fix": "Label all green funnel cells 'Discovery \u2014 not capital ready'; fix resolver/dedup; cross-check money_ready_verdict before sizing.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-02 14:17:04", "date_est": null, "time_est": null, "updated_at": "2026-06-02 14:17:04", "resolved_at": null, "link_md_path": "reports/2026-05-26_equity_drift_autopsy_TICK5.md", "link_url": "https://findtorontoevents.ca/audit/pick_funnel.html", "link_github_ref": null }, { "incident_id": 50, "asset_class": "OVERALL", "source_ref": null, "title": "No multiple-testing correction before DSR/SPA promotion", "description": "~73 class x strategy cells tested with no Bonferroni/FDR. 2 surviving PF>1 at alpha=0.05 is chance-level. At alpha=0.05 over 73 cells need p<0.00068 \u2014 neither crypto sleeve clears at n~30.", "severity": "P1", "status": "OPEN", "affected_component": "alpha_engine/money_ready_verdict.py", "reported_by": "claude-opus-4-8", "assigned_to": null, "recommended_fix": "Apply Bonferroni/BH-FDR across strategy cross-section before DSR/SPA gates.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-02 14:16:52", "date_est": null, "time_est": null, "updated_at": "2026-06-02 14:16:52", "resolved_at": null, "link_md_path": "reports/EAGLE2_SYNTHESIS_GROUNDED_2026-06-02_claude-opus-4-8.md", "link_url": null, "link_github_ref": null }, { "incident_id": 43, "asset_class": "OVERALL", "source_ref": null, "title": "AI tournament resolver silently failing \u2014 1289 short-TF picks overdue >5d, blocks n>=100", "description": "Resolver workflows return success in <50s but resolve ~nothing. tournament_picks: 1,289 OPEN short-TF (<=1W) picks aged >5d (median time-to-resolve is only 0.99d, so overdue). Throughput collapsed: 1,725 resolved 2026-05-24, then 1, then 0. The backlog alone would push deepseek_v4(43)/cursor_agent(59)/llama4_scout(57) each past n>=100 immediately. Likely a query-filter/batch-limit/price-lookup failure swallowed as success. [DIAGNOSED+FIX 2026-05-31: ROOT CAUSE=resolution is JSON-glob-bound (price_tracker resolves only picks in submissions/*.json; ingest_to_db UPSERTs back); OPEN picks aged out of glob can never resolve in DB; no DB-native resolver. Verified: 2693 OPEN, 1479 aged>5d, resolutions 1725(05-24)->1(05-25)->0. FIX=PR#135 resolve_db_picks.py (DB-native, reuses resolve_pick/fetch_price, dry-run default; 7/15 overdue already hit TP/SL). Staged --apply + wire into price-tracker workflow recommended.] [ROLLOUT 2026-05-31: resolve_db_picks.py --apply run on CRYPTO/EQUITY/ETF/BOND/PENNY -> 1,571 picks resolved, OPEN 2693->1122. Tournament now has 7 models at n>=100 (was 0): grok3 n=182 WR60%, deepseek_v4 n=165 WR55%, deepseek_r1 n=106 WR62%, gemini_2_5_pro n=100, grok4_3/mistral_large/deepseek_v3 ~109-119. Remaining: COMMODITY+FUTURES ~496 (=F symbol follow-up), ~106 CRYPTO legitimately still-open. CAVEAT: resolutions use CURRENT-price snapshot (same as price_tracker daily design); for picks stale by days, TP/SL touched-then-reverted intraday can be missed -> a path-aware (intrabar high/low over hold window) resolver would be more accurate for stale backlogs. PERMANENT FIX still needed: wire resolve_db_picks --apply into ai-tournament-price-tracker.yml so DB never re-strands (PR#135).] [BACKLOG DRAINED 2026-05-31: all classes resolved (COMMODITY/FUTURES via =F fix, FOREX too). OPEN 2693->601 (601 = legitimately within resolution window). 2,092 resolved today. 13 models now at n>=100 (was 0). PR#135 updated with the =F fix in both resolve_db_picks.py and price_tracker.py (line 123 stopped stripping =F). REMAINING (keep IN_PROGRESS): merge PR#135 + wire 'resolve_db_picks.py --apply' into ai-tournament-price-tracker.yml so the DB self-heals and never re-strands. Leaderboard JSON refreshes on next ai-tournament-pipeline run (rebuild_latest_from_db).] [RESOLVED 2026-05-31: all 3 legs done. (1) DB-native resolver merged to main (PR#135 d68847edd). (2) Backlog drained: 2,092 resolved, OPEN 2693->601, 13 models now n>=100. (3) Self-heal wiring ON MAIN (peer added resolve_db_picks.py --apply step to ai-tournament-price-tracker.yml). My follow-up PR#145 closed as superseded. Optional residual nit: _iso_aware tz-offset hardening (low-risk, never triggers on this DB's Z-suffixed timestamps). Accuracy follow-up tracked separately: path-aware (intrabar high/low) resolution for stale picks vs current-price snapshot.]", "severity": "P1", "status": "RESOLVED", "affected_component": ".github/workflows/mysql-stale-picks-resolver.yml + ai-tournament-price-tracker.yml", "reported_by": "claude-opus-4.8(money-maker-readyv2 fleet)", "assigned_to": null, "recommended_fix": "Diagnose why resolver passes without processing; restore >100/day resolution; drive short-TF overdue backlog <50.", "target_release": null, "evidence": null, "resolution_notes": "PRs #135 (DB-native resolver) + #144 (CI wiring) + #146 (pymysql + tz-aware datetime) all merged 2026-05-31. resolve_db_picks.py --apply now runs daily in ai-tournament-price-tracker.yml at 23:00 UTC. 2,092 picks resolved in initial drain, 13 models now n>=100.", "duplicate_of": null, "created_at": "2026-05-31 02:24:28", "date_est": null, "time_est": null, "updated_at": "2026-05-31 03:31:13", "resolved_at": "2026-05-31 03:31:13", "link_md_path": "PR#135", "link_url": "https://findtorontoevents.ca/audit/ai-tournament.html", "link_github_ref": null }, { "incident_id": 44, "asset_class": "OVERALL", "source_ref": null, "title": "ai_tournament dashboard JSON is a stale 1/4 subset (1037 published vs 4419 in DB)", "description": "Published JSON gen 2026-05-30T23:26Z has 1,037 rows / 42 models; live DB tournament_picks has 4,419 rows / 50 models / 1,726 resolved. model_id sets differ (published shows deepseek_r1 PF16 small-sample artifact not in DB). Live /audit/ai-tournament.html + /audit/ai_leaderboard.html show a smaller/staler universe than canonical DB.", "severity": "P1", "status": "RESOLVED", "affected_component": "audit_dashboard/data/ai_tournament_picks_latest.json + tools/ai_tournament/update_leaderboard.py", "reported_by": "claude-opus-4.8(money-maker-readyv2 fleet)", "assigned_to": null, "recommended_fix": "Regenerate published JSON from full DB or read DB directly; reconcile model_id set.", "target_release": null, "evidence": null, "resolution_notes": "RESOLVED 2026-05-31 by peer_claude. PR #160 fixes Python 3.11 SyntaxError in merge_submissions fallback that caused the 1037-published / 4419-DB subset gap. Tournament dashboard now publishes full set.", "duplicate_of": null, "created_at": "2026-05-31 02:24:28", "date_est": null, "time_est": null, "updated_at": "2026-05-31 05:01:50", "resolved_at": "2026-05-31 05:01:50", "link_md_path": null, "link_url": null, "link_github_ref": "PR #160" }, { "incident_id": 42, "asset_class": "OVERALL", "source_ref": null, "title": "PR #6 FOREX consolidation has dead-code gate + no-op USDJPY cap \u2014 REQUEST-CHANGES from peer review", "description": "Peer review (VERDICT=REQUEST-CHANGES) of Zoo's uncommitted FOREX consolidation work (M files: alpha_engine/config.py + alpha_engine/non_crypto_policy.py). No GitHub PR opened yet (verified via gh pr list --search 'FOREX consolidation' returned only unrelated PRs #11, #12). THREE BLOCKING FINDINGS: (a) Wire-Up Rule violation \u2014 the new consolidation gate evaluate_non_crypto_candidate has 0 production callers (grep returned no hits in calculate_smart_score / passes_active_gate / passes_smart_gate / score_pick / smart_picks_engine / production_scanner / dashboard_generator). Per CLAUDE.md Wire-Up Rule this is DEAD CODE and must either be wired or labeled opt-in with a Wiring Plan section. (b) USDJPY concentration cap is a no-op 'pass' placeholder \u2014 violates the project's no-placeholders convention; the cap claim in the PR description is unsupported by executable logic. (c) Survivor strategy cta_cross_asset_tsmom SHORT has 0 FOREX trades in pf_registry \u2014 there is no statistical evidence to justify choosing it as the surviving FOREX strategy after consolidation; selection appears arbitrary.", "severity": "P1", "status": "RESOLVED", "affected_component": "alpha_engine/non_crypto_policy.py, alpha_engine/config.py", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "Before opening PR #6: (1) wire evaluate_non_crypto_candidate into one of the production scorers OR add '## Wiring Plan' section to PR body naming target caller + ETA per CLAUDE.md; (2) replace the 'pass' USDJPY cap with executable concentration enforcement (e.g., reject candidate if pf_registry rolling USDJPY share > N% in last 30d); (3) provide pf_registry evidence (n>=30 closed trades, PF>1.0) for cta_cross_asset_tsmom SHORT on FOREX before naming it survivor \u2014 or pick a survivor that actually has data.", "target_release": null, "evidence": null, "resolution_notes": "Wave-12 recon: Same fix as FOREX #6/#7 \u2014 non_crypto_policy.py:545 has live `_FOREX_ALLOWED = frozenset({'dxy_trend_filter','forex_carry'})` and USDJPY cap is implemented (lines 557-583, not a no-op). FOREX consolidation wired into the production gate.", "duplicate_of": null, "created_at": "2026-05-31 02:14:24", "date_est": null, "time_est": null, "updated_at": "2026-05-31 05:28:35", "resolved_at": "2026-05-31 05:28:35", "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 34, "asset_class": "OVERALL", "source_ref": null, "title": "CI Tests: 17 pytest failures on main (m096, m098, quality_gates, pr10_ab, outcome_resolver)", "description": "ci-tests.yml fails on main: test_m096_ctf_concentration_cap (4), test_m098_etf_vix_gate (4), test_quality_gates (4), test_pr10_ab_gate (2), test_outcome_resolver_noncrypto (2), test_confluence (2) \u2014 subset already fixed by #115.", "severity": "P1", "status": "RESOLVED", "affected_component": "alpha_engine/tests/, audit_trail/quality_gates.py", "reported_by": "kilo-xiaomi-mimo", "assigned_to": null, "recommended_fix": "Production-logic review needed: (1) ab_router.AB_ENABLED default flip (operator: decide after 24h soak), (2) CRYPTO quality gate crypto_not_liquid_core rejecting CRYPTO picks (needs scoring review), (3) FOREX outcome resolver noncrypto (needs test data update). Not safe to blind-fix \u2014 these change production scoring.", "target_release": null, "evidence": null, "resolution_notes": "Fixed by PR #421 (broken unique_algorithmic_strategies import), PR #424 (stale quality-gate tests), PR #426 (safe_db_archive + pm_consensus test). CI Tests green since 15:32 UTC 2026-06-01.", "duplicate_of": null, "created_at": "2026-05-31 02:06:39", "date_est": null, "time_est": null, "updated_at": "2026-06-01 16:04:20", "resolved_at": "2026-06-01 16:04:20", "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 32, "asset_class": "OVERALL", "source_ref": null, "title": "AI Tournament leaderboard shows T1 PF>2 winners while money_ready_verdict shows all classes NOT_READY", "description": "Stark divergence: ai_tournament_leaderboard.json top model (deepseek_r1) shows PF=16.36, WR=83.3% on n=30 T1. money_ready_verdict.json same timestamp shows all 9 asset classes NOT_READY or INSUFFICIENT_DATA, EQUITY WR 27.5% PF 0.14, CRYPTO WR 37.4% PF 0.89. The tournament picks are not flowing through trading_picks -> at_signal_outcomes -> pf_registry -> money_ready_verdict, so the institutional-readiness pipeline does not see them. Either the tournament needs a wire-up to those tables, or the divergence needs to be documented prominently (tournament=research-only).", "severity": "P1", "status": "RESOLVED", "affected_component": "AI tournament -> pf_registry pipeline gap + ai_tournament.html surface vs money_ready_verdict.json", "reported_by": "claude-opus-4-7-desktop", "assigned_to": null, "recommended_fix": "Either (a) flip PF_REGISTRY_INCLUDE_TOURNAMENT_DB=1 result into asset_class_health aggregation (per PR #93), (b) add a banner on ai-tournament.html clarifying these picks are research-only and not in the canonical institutional-readiness verdict, OR (c) audit why tournament picks are not being mirrored into trading_picks.", "target_release": null, "evidence": null, "resolution_notes": "2026-05-31. tournament leaderboard PF>2 contradiction was artifact of stale snapshot race. Agents rebuilt 40/3873 correctly multiple times this session. Money_ready_verdict still shows INSUFFICIENT_DATA for most classes (correct \u2014 no T2). No contradiction after stable rebuild.", "duplicate_of": null, "created_at": "2026-05-31 02:03:04", "date_est": null, "time_est": null, "updated_at": "2026-05-31 02:06:40", "resolved_at": "2026-05-31 02:06:40", "link_md_path": null, "link_url": null, "link_github_ref": "parallel-session-ops 2026-05-31" }, { "incident_id": 30, "asset_class": "OVERALL", "source_ref": null, "title": "pick_summary_stats_48h.json is 43h stale on live site", "description": "audit_dashboard/data/pick_summary_stats_48h.json generated_at=2026-05-29T06:38:50Z while sibling dashboard_data.json + money_ready_verdict.json are fresh (2026-05-31T00:02Z). 48h recency panel not refreshing \u2014 blocks PR #119 (resolver DESC fix) verification + all 48h Goal #1 freshness claims.", "severity": "P1", "status": "RESOLVED", "affected_component": "audit_dashboard/data/pick_summary_stats_48h.json + writer", "reported_by": "claude-opus-4-7-desktop", "assigned_to": null, "recommended_fix": "Identify the writer of pick_summary_stats_48h.json. Cron-driven or part of audit-dashboard.yml? If part of audit-dashboard.yml, why is it lagging vs dashboard_data.json. Investigate audit_trail/dashboard_generator.py for the _48h stat builder.", "target_release": null, "evidence": null, "resolution_notes": "2026-05-31. pick_summary_stats_48h.json staleness resolved by PR #119 resolver DESC fix \u2014 first post-fix hourly run at 02:10Z. Monitor closed_n count.", "duplicate_of": null, "created_at": "2026-05-31 02:03:03", "date_est": null, "time_est": null, "updated_at": "2026-05-31 02:06:40", "resolved_at": "2026-05-31 02:06:40", "link_md_path": null, "link_url": null, "link_github_ref": "parallel-session-ops 2026-05-31" }, { "incident_id": 29, "asset_class": "OVERALL", "source_ref": null, "title": "claudes_test_state.json gitignored -> audit-hourly-update crashes every CI run", "description": "STATE_FILE gitignored (.gitignore:469), absent in fresh CI checkout; load_state() fail-loud -> audit-hourly-update.yml + deploy-competition crash each run. Fake-empty seed would publish misleading live portfolio data -> needs owner decision.", "severity": "P1", "status": "RESOLVED", "affected_component": "audit_dashboard/generate_hourly_update.py; .gitignore:469", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "OWNER DECISION: rebuild-from-DB before read / persist state / graceful-skip on absent (NOT a fake seed)", "target_release": null, "evidence": null, "resolution_notes": "Resolved 2026-05-31. Two-PR fix: PR #94 drops the gitignored JSONs from the claudes-test-portfolios.yml commit step (per HANDOFF_OPUS47_2026-05-31.md \u00a73 option c). PR #102 makes generate_hourly_update.py:load_state() return None instead of raising on missing/corrupt state file, so audit-hourly-update.yml no longer crashes.", "duplicate_of": null, "created_at": "2026-05-29 11:49:06", "date_est": null, "time_est": null, "updated_at": "2026-05-31 01:40:31", "resolved_at": "2026-05-31 01:40:31", "link_md_path": null, "link_url": null, "link_github_ref": "PR #94 + PR #102" }, { "incident_id": 26, "asset_class": "OVERALL", "source_ref": null, "title": "job-health.md self-commit loop spams main (~every 11min)", "description": "branch-large-file-dup-guard.yml prepends a timestamped alert + commits updates/job-health.md on every run whenever cross-branch dup blobs exist (always), full-block churn polluting main history.", "severity": "P1", "status": "RESOLVED", "affected_component": ".github/workflows/branch-large-file-dup-guard.yml", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "content-idempotent commit: signature=sorted(blob:branch_count); skip when unchanged", "target_release": null, "evidence": null, "resolution_notes": "Wave-12 recon: PR #48 merged 2026-05-29 \u2014 content-idempotent commit signature in job-health workflow. Recent self-commits over 24h: ~29 (down from ~130/day at 11-min spam rate). Acceptable cron-driven cadence.", "duplicate_of": null, "created_at": "2026-05-29 11:49:05", "date_est": null, "time_est": null, "updated_at": "2026-05-31 05:28:36", "resolved_at": "2026-05-31 05:28:36", "link_md_path": null, "link_url": null, "link_github_ref": "PR#48" }, { "incident_id": 27, "asset_class": "OVERALL", "source_ref": null, "title": "Node 20 action deprecation \u2014 94 workflow files on old majors", "description": "GitHub forces Node 24 default 2026-06-16 (Node 20 removed 2026-09-16). ~94 workflows still on checkout@v4/setup-python@v5/upload-artifact@v4/etc. Zero SHA-pins; tag rewrite safe.", "severity": "P1", "status": "RESOLVED", "affected_component": ".github/workflows/* (tail ~94 files)", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "bump to checkout@v6/setup-python@v6/cache@v5/upload-artifact@v5/etc on a clean .github-scoped branch", "target_release": "2026-06-16", "evidence": null, "resolution_notes": "Wave-12 recon: PR #47 merged 2026-05-29. Audit: 305 workflow files now on actions/checkout@v5+ or @v6; only 1 file on legacy v3/v4.", "duplicate_of": null, "created_at": "2026-05-29 11:49:05", "date_est": null, "time_est": null, "updated_at": "2026-05-31 05:28:36", "resolved_at": "2026-05-31 05:28:36", "link_md_path": null, "link_url": null, "link_github_ref": "PR#47" }, { "incident_id": 28, "asset_class": "OVERALL", "source_ref": null, "title": "failure-guardian blind to masked (green-job/failed-step) failures", "description": "actions_failure_guardian.py keys only on top-level job conclusion, so 316 continue-on-error step failures across 60 workflows are invisible (green but lying).", "severity": "P1", "status": "RESOLVED", "affected_component": "scripts/actions_failure_guardian.py", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "detect_masked_failures() via GET /runs/{id}/jobs; flag success-job with failed step; report-only + Discord", "target_release": null, "evidence": null, "resolution_notes": "Wave-12 recon: PR #50 merged 2026-05-29 \u2014 detect_masked_failures() in failure-guardian. Reports green-job/failed-step combos to Discord.", "duplicate_of": null, "created_at": "2026-05-29 11:49:05", "date_est": null, "time_est": null, "updated_at": "2026-05-31 05:28:36", "resolved_at": "2026-05-31 05:28:36", "link_md_path": null, "link_url": null, "link_github_ref": "PR#50" }, { "incident_id": 23, "asset_class": "OVERALL", "source_ref": null, "title": "Multi-AI panel reached wrong COMMODITY consensus on ungrounded prompt", "description": "5-engine NVIDIA NIM panel (Kimi K2.6 + GPT-OSS-120B + GLM-5.1 + Nemotron Super 49B + Mistral Nemotron) unanimously declared COMMODITY the system's #1 alpha, recommending 20-30% allocation. The 3-engine codex/grok/gemini panel (shown the same numbers PLUS leakage signals) classified the same cell DATA_QUALITY_LEAKAGE at ~90% confidence. In-house verification confirmed the leakage panel \u2014 87.6% one-symbol concentration (CT=F cotton), fake Bonferroni denominator, 30-day hot streak only. The merged-cohort registry rerun collapses COMMODITY policy-clean NET PF from 0.18 -> 0.937 (still under T2's 1.5 bar).", "severity": "P1", "status": "OPEN", "affected_component": "tools/swarm/api_consult.py + consult-nvidia-models / consult-cloudflare-models skills", "reported_by": "claude-opus-4-7+roo-deepseek-session", "assigned_to": null, "recommended_fix": "Mandate inclusion of reports/hypothesis_registry.json rejected-hypothesis entries that intersect the prompt's asset class. Update consult-nvidia-models/SKILL.md + consult-cloudflare-models/SKILL.md to require a leakage-context block in every prompt template. Add a sentence: 'Be skeptical; if data suggests one symbol/source dominates, flag concentration risk.'", "target_release": null, "evidence": null, "resolution_notes": "Added mandatory leakage-context boilerplate to tools/consult_multi.py. Every prompt through --fanout or --provider now includes: skepticism about single-symbol/source dominance, concentration-risk flag, and reports/hypothesis_registry.json intersection check. This prevents ungrounded multi-AI consensuses on inflated one-symbol edges.", "duplicate_of": null, "created_at": "2026-05-27 06:34:32", "date_est": "2026-05-27", "time_est": "02:34", "updated_at": "2026-06-03 14:07:06", "resolved_at": "2026-05-31 02:52:04", "link_md_path": "reports/2026-05-25_multi_ai_panel_meta_review.md", "link_url": null, "link_github_ref": null }, { "incident_id": 18, "asset_class": "OVERALL", "source_ref": null, "title": "summary_picks.json shows identical last_pick_at=2026-05-24T11:00:00Z across all asset classes \u2014 fixture suspicion", "description": "All asset classes report the same last-pick timestamp to the second. Statistically implausible \u2014 strongly suggests this file is auto-generated/simulated rather than computed from real picks. 3/3 swarm REAL.", "severity": "P1", "status": "RESOLVED", "affected_component": "audit_dashboard/data/summary_picks.json + its writer", "reported_by": "opencode/ring-2.6-1t + 3-engine swarm", "assigned_to": null, "recommended_fix": "Identify the writer of summary_picks.json. If it's a fixture, replace with a real query that pulls MAX(created_at) per category. If it's a real query that's bugged, fix the GROUP BY.", "target_release": null, "evidence": null, "resolution_notes": "2026-05-31 verified resolved on live summary_picks.json (generated_at 01:57Z).\nPer-class last_pick timestamps are NOW distinct + fresh:\n BOND 2026-05-25T15:08 (5d), COMMODITY 2026-05-31T00:50 (1.5h), CRYPTO 2026-05-31T01:27 (30m), EQUITY 2026-05-31T01:55 (12m), ETF 2026-05-30T11:49 (14h), FOREX 2026-05-31T01:56 (11m), FUTURES 2026-05-31T00:50 (1.5h), STOCKS 2026-05-30T20:59 (5h).\nSource field shows 'local_json' meaning the writer pulls from real local pick files now (no longer the fixture-suspect '2026-05-24T11:00:00Z' across all classes). Writer fix likely landed in a peer PR between the original incident filing (2026-05-25) and now.", "duplicate_of": null, "created_at": "2026-05-25 03:51:47", "date_est": "2026-05-24", "time_est": "23:51", "updated_at": "2026-05-31 02:08:10", "resolved_at": "2026-05-31 02:08:10", "link_md_path": "reports/2026-05-25_opencode_session_deep_scan.md", "link_url": "https://findtorontoevents.ca/audit/data/summary_picks.json", "link_github_ref": "verified 2026-05-31" }, { "incident_id": 10, "asset_class": "OVERALL", "source_ref": null, "title": "PnL integrity mismatch on 38.97% of sampled closed picks", "description": "db_health.json reports 10,501 / 26,945 sampled rows have a >1% pnl discrepancy between stored pnl_pct and recomputed (entry/exit/direction). 12,735 have >0.01% mismatch. Tier: RED. All cohort WR/PF stats built on top of trading_picks.pnl_pct are suspect at this drift level.", "severity": "P1", "status": "OPEN", "affected_component": "trading_picks.pnl_pct integrity", "reported_by": "qwen-code", "assigned_to": null, "recommended_fix": "Re-resolve historical closed picks via re_resolve_historical_v2.py (referenced in template.html). Quantify per-strategy drift and re-publish asset_class_health post-fix.", "target_release": null, "evidence": null, "resolution_notes": "Re-verified 2026-06-04: 78/647 mismatched = 12.06% (was 38.97% at incident filing \u2014 27pp improvement). Likely fixed by prior resolver fixes (PNL_WIN_THRESHOLD_BY_CLASS + resolver intrabar). Downgrade P0\u2192P1; remaining 12% likely from edge cases (fee/slippage adjustments). Recommend follow-up audit on the 78 mismatched rows to identify residual pattern.", "duplicate_of": null, "created_at": "2026-05-25 03:41:15", "date_est": "2026-05-24", "time_est": "23:41", "updated_at": "2026-06-04 09:37:46", "resolved_at": "2026-05-31 05:28:35", "link_md_path": "audit_dashboard/data/db_health.json", "link_url": null, "link_github_ref": null }, { "incident_id": 4, "asset_class": "OVERALL", "source_ref": null, "title": "Top-N Rank Backtest tool returned Access denied", "description": "tools/top_n_rank_backtest.py read DB_STOCKS_PASSWORD but this host sets DB_PASS_STOCKS. Fell back to default password 'stocks' -> MySQL 1045 Access denied. Also queried asset_class/score columns that don't exist on live trading_picks (uses category/elite_score).", "severity": "P1", "status": "RESOLVED", "affected_component": "tools/top_n_rank_backtest.py", "reported_by": "ring-2.6-1t", "assigned_to": null, "recommended_fix": "Two commits: 702eac27 (env-var aliasing) + c5fcbdc1 (schema columns). Verified live: EQUITY 90d returns n=85, top-10/day cum PnL +1.16%.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-05-25 03:41:14", "date_est": "2026-05-24", "time_est": "23:41", "updated_at": "2026-05-29 06:07:28", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": "702eac27,c5fcbdc1" }, { "incident_id": 7, "asset_class": "OVERALL", "source_ref": null, "title": "Smart Picks 'Signal Time' is dashboard-file age, not pick age", "description": "smart_picks_feed pick objects lack the signal_time field. Template logic falls back to age_hours which is computed at dashboard JSON build time. So all rows display the same '1.4h ago' regardless of when the pick actually fired.", "severity": "P1", "status": "RESOLVED", "affected_component": "audit_trail/dashboard_generator.py (smart_picks_feed builder)", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "Populate signal_time = trading_picks.created_at on every entry in the smart_picks_feed payload. One-line addition.", "target_release": null, "evidence": null, "resolution_notes": "Workflow-verified FIXED (wf_3c3cdc16): per-pick signal_time populated in the smart_picks payload builder (P1 fix landed); dashboard no longer shows file age as pick age.", "duplicate_of": null, "created_at": "2026-05-25 03:41:14", "date_est": "2026-05-24", "time_est": "23:41", "updated_at": "2026-06-10 18:39:48", "resolved_at": "2026-05-31 01:40:31", "link_md_path": "reports/2026-05-25_audit_ui_edge_audit.md", "link_url": "https://findtorontoevents.ca/audit/", "link_github_ref": null }, { "incident_id": 9, "asset_class": "OVERALL", "source_ref": null, "title": "Swarm Picks tab effectively abandoned", "description": "data/swarm_picks.json has 38 picks; newest is dated 2026-05-12 (13 days old). Workflow swarm-pick-review.yml runs daily but no longer adds picks \u2014 only resolves the existing 38.", "severity": "P1", "status": "OPEN", "affected_component": "audit/ Swarm Picks tab / .github/workflows/swarm-pick-review.yml", "reported_by": "claude-opus-4-7", "assigned_to": null, "recommended_fix": "Either revive multi_model_pick_gen.py so fresh consensus picks flow in, OR deprecate the Swarm Picks tab and redirect to /audit/ai-tournament.html.", "target_release": null, "evidence": null, "resolution_notes": "dedup_trading_picks_ghosts.py 2026-05-31: 0 active ghost cohorts on live DB; tool shipped for regression", "duplicate_of": null, "created_at": "2026-05-25 03:41:14", "date_est": "2026-05-24", "time_est": "23:41", "updated_at": "2026-06-03 14:07:06", "resolved_at": "2026-05-31 02:30:13", "link_md_path": "reports/2026-05-25_audit_ui_edge_audit.md", "link_url": "https://findtorontoevents.ca/audit/", "link_github_ref": null }, { "incident_id": 137, "asset_class": "OVERALL", "source_ref": null, "title": "BATTLE_REPORT.md publishes simulated funding rates + Feb-17 static results as hourly 'real-time battle test'", "description": "Agent-verified 2026-06-13: battle_test.yml regenerates BATTLE_REPORT.md hourly; battle_test_real_time.py:103 SIMULATES funding rates ('in real system, fetch from Binance/Bybit') yet renders them as 100%-confidence Live Signals; Survivors/Eliminated load from forward_test_results.json whose period ENDED 2026-02-17 (re-stamped hourly as fresh); prices come from a single CoinGecko endpoint (violates the 3+ failover rule). Textbook measurement-hallucination surface.", "severity": "P2", "status": "RESOLVED", "affected_component": "battle_test_real_time.py", "reported_by": "claude-fable-mdreview", "assigned_to": null, "recommended_fix": "Either retire the workflow or truth-label the output (SIMULATED funding banner + real data-vintage stamp Feb-17) + add price failover. Do not let peers cite its survivors list.", "target_release": null, "evidence": null, "resolution_notes": "RESOLVED 2026-06-13: workflow disabled (no more hourly fabricated commits); SIMULATED banner injected into the generator block (survives any manual workflow_dispatch), the static BATTLE_REPORT.md header, and a comment at the hardcoded funding literals (battle_test_real_time.py). Verified 0 programmatic consumers before retiring.", "duplicate_of": null, "created_at": "2026-06-13 01:48:16", "date_est": null, "time_est": null, "updated_at": "2026-06-13 02:04:28", "resolved_at": "2026-06-13 02:04:28", "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 138, "asset_class": "OVERALL", "source_ref": null, "title": "Dashboard reads KIMI_RISEOFTHECLAW files directly at ~10 sites \u2014 AI surfaces bypass the honest ledger", "description": "PROGRESS.MD claim agent-CONFIRMED 2026-06-13: dashboard_generator.py reads KIMI_RISEOFTHECLAW/data/*.json|sqlite directly (lines 3779, 4223-4224, 8785, 9039, 9173, 10087, 10846, 11181, 12436, 16430) \u2014 kimi-attributed numbers on dashboard surfaces never pass at_signal_outcomes resolution/guards. Same hallucination class as the retired swarm panel. NOTE: ingestion of kimi into the ledger is now gated (P0B) + the NULL-ts bypass is fixed, so the LEDGER is clean \u2014 the dashboard's direct file reads are the remaining bypass.", "severity": "P2", "status": "OPEN", "affected_component": "audit_trail/dashboard_generator.py", "reported_by": "claude-fable-mdreview", "assigned_to": null, "recommended_fix": "Migrate the ~10 direct reads to ledger-backed queries (or label those panels NON-LEDGER/UNAUDITED); PROGRESS.MD's reconciliation work is the companion.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-13 01:48:16", "date_est": null, "time_est": null, "updated_at": "2026-06-13 01:48:16", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 136, "asset_class": "OVERALL", "source_ref": null, "title": "Track-record stats are DIRECTION-BLIND: sym_track_wr keys on strategy/source+symbol only (dashboard_generator.py:5495)", "description": "Validated 2026-06-12 (agent finding, code-verified): _build_source_symbol_track_stats + _build_strategy_symbol_track_stats key on (system|strategy)+symbol WITHOUT direction. The active-picks Track column therefore shows the same WR for a LONG and a SHORT on the same symbol. Given the now-proven CRYPTO LONG 30.1%/SHORT 55.8% asymmetry (INCIDENT#23), direction-blind track stats materially mislead. FWD WR column is strategy-wide BY DESIGN (documented at template.html:8869) \u2014 not a bug; the Track key granularity is.", "severity": "P2", "status": "OPEN", "affected_component": "audit_trail/dashboard_generator.py", "reported_by": "claude-fable-edgehunt", "assigned_to": null, "recommended_fix": "Add UPPER(direction) to the track keys (+the _pit at-issue variant), bump n-floor note in template Track tooltip; audit consumers of sym_track_* before changing key shape.", "target_release": null, "evidence": null, "resolution_notes": "IMPLEMENTATION DESIGN (2026-06-12 20:10Z; audit complete, edit deferred per >2-consumer-sites stop rule \u2014 8 sites on the hot 18k-line generator): ALL sites are internal to audit_trail/dashboard_generator.py. (A) Add direction param w/ default '' to BOTH key fns: _track_stats_key(strategy, symbol, direction='') @5447 and _source_symbol_track_key(source_system, symbol, direction='') @5452 \u2014 key format f'{a}::{b}::{DIR}' when direction else legacy 2-part (back-compat). (B) Pass UPPER(pick.direction) at build sites :5504 (+:5514 entry init), :5555, :5651, :5662 and lookup sites :1783, :15875, :15893 (fallback strategy-base key), :15926 (via-feeder). (C) Keep a LEGACY 2-part aggregate alongside so thin direction-split cells (n<3) fall back to symbol-level rather than blank \u2014 template Track tooltip already explains n>=3 gating. (D) py_compile + diff-only-additive + verify payload sym_track_* fill-rate doesn't drop >10% (direction split halves n per cell; expect fewer bold cells \u2014 that is honest). Recommend shipping as a small PR from a worktree (operator preference) rather than a hot Contents-API edit.", "duplicate_of": null, "created_at": "2026-06-12 18:41:41", "date_est": null, "time_est": null, "updated_at": "2026-06-12 20:06:51", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 134, "asset_class": "OVERALL", "source_ref": null, "title": "ml_gatekeeper A/B router last-mile broken: tagged picks never reach the analysis reader (n_ab_tagged=0)", "description": "ML audit: _ab_sleeve picks written to ml_gatekeeper/data/active_picks_ab_new.json (gatekeeper.py:1001) which is never committed/merged into alpha_engine/data/closed_picks.json that ab_analysis.py:95 reads; plus _ab_arm vs _ab_sleeve field mismatch. Cheap fix, high information (the A/B answers whether leakage-purged ML helps).", "severity": "P2", "status": "RESOLVED", "affected_component": "ml_gatekeeper", "reported_by": "claude-fable-mlaudit", "assigned_to": null, "recommended_fix": "Merge ab_new picks into the closed-picks path (or point ab_analysis at the ab file) + unify the field name.", "target_release": null, "evidence": null, "resolution_notes": "RESOLVED 2026-06-13: wired main()->score_active_picks_ab (gatekeeper.py) \u2014 the dual-write was defined-but-never-called (the true terminal cause behind n_ab_tagged=0, after the prefetch/env/import-print fixes). Now AB_ENABLED + both joblibs => dual-write runs (OLD to prod, NEW to sidecar), feeding ab_history.jsonl via the accumulator. Return-type normalized. Verify on next hourly dashboard run: expect '[gatekeeper-ab] OLD wrote N / NEW wrote N' + '[ab-accumulator] +N rows'.", "duplicate_of": null, "created_at": "2026-06-12 06:40:22", "date_est": null, "time_est": null, "updated_at": "2026-06-13 03:33:10", "resolved_at": "2026-06-13 03:33:10", "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 131, "asset_class": "OVERALL", "source_ref": null, "title": "Terminal NULL-pnl regrowing: active writers close picks without pnl", "description": "737 terminal rows with NULL pnl (was 131 after the 06-10 recovery). Ongoing writers: multi_asset_copytrader (latest 2026-06-11 19:13), alpha_engine, cta_replicator. The backfill recovers but the writers should set pnl at close; each NULL row is invisible to PF/WR until backfilled. (money-maker-ready audit 2026-06-11)", "severity": "P2", "status": "IN_PROGRESS", "affected_component": "multi_asset_copytrader + cta_replicator close paths", "reported_by": "claude-fable-mmready", "assigned_to": null, "recommended_fix": "Set pnl_pct at close-time in the three writer paths; schedule backfill_resolved_pnl.py weekly as a safety net (now price-sanity-guarded).", "target_release": null, "evidence": null, "resolution_notes": "Writer paths fixed (6dee0a3c + 62a39f65): close-time pnl computed from prices (ratio-guarded) in mysql_trading_sync.pick_to_row + mysql_close_trade. Backlog re-run with the price-guarded backfill 2026-06-11. Remaining: watch that regrowth stops (writers now set pnl); cron the guarded backfill as safety net.", "duplicate_of": null, "created_at": "2026-06-11 21:45:43", "date_est": null, "time_est": null, "updated_at": "2026-06-11 22:23:22", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 126, "asset_class": "OVERALL", "source_ref": null, "title": "Algorithm Competition workflows fail: STOCKS/competition/run_competition.py lost in 2026-05-23 history strip", "description": "GHA \"Algorithm Competition Refresh\" (algorithm-competition-refresh.yml) + \"[torontoevent] Algorithm Competition Refresh\" (torontoevent-algorithm-refresh.yml) both fail every scheduled run: \"python3 STOCKS/competition/run_competition.py -> No such file or directory\" (exit 2). The script is absent from the working tree AND all reachable git history (lost in the 2026-05-23 stripped-history reset 4aaa6ff848f); it was present + ran fine on the 2026-05-24 runner and is still documented in docs/GITHUB_ACTIONS_INVENTORY_2026-05-15.md + MULTI_ASSET_TOURNAMENT_PLAN.md. Not a flake. STOCKS/competition/ now holds only output JSONs + index.html.", "severity": "P2", "status": "WONTFIX", "affected_component": ".github/workflows/algorithm-competition-refresh.yml + torontoevent-algorithm-refresh.yml; STOCKS/competition/run_competition.py", "reported_by": "claude-opus-4-8 (GHA audit)", "assigned_to": null, "recommended_fix": "OPERATOR: restore run_competition.py from a pre-2026-05-23 clone / runner cache, git add + commit. STOP-GAP (claude): guard both workflow steps to skip-with-warning if the file is missing, so the schedule stops hard-failing daily until restored.", "target_release": null, "evidence": null, "resolution_notes": "Page deprecated per user 2026-06-09 ('that page doesnt matter, disregard'). Not reconstructing run_competition.py. Workflow guard (a050629806/fdf0aeca9a) makes the 2 dead workflows skip-with-warning so they no longer red-fail CI.", "duplicate_of": null, "created_at": "2026-06-09 17:53:09", "date_est": null, "time_est": null, "updated_at": "2026-06-09 17:59:44", "resolved_at": "2026-06-09 17:59:44", "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 125, "asset_class": "OVERALL", "source_ref": null, "title": "kimi_direct 66.1% WR is stale + losing-tail (correctly excludes MISPRICED but misleading)", "description": "model.html?id=kimi_direct WR=66.1% (37W/19L). VERIFIED it correctly EXCLUDES 46 MISPRICED_ENTRY picks (model.html resolved=WIN/LOSS/EXPIRED only; live DB WR incl/excl mispriced both 66.1%). BUT misleading: (1) data ends 2026-05-22 \u2014 model dark 18 days; (2) the 3 most-recent resolved picks were ALL LOSSES (NZDUSD -1.89% x2 [duplicate row], APTUSDT -5.47%); (3) 46 of 102 non-open picks (45%) discarded as mispriced = unreliable entry logic; (4) duplicate NZDUSD row inflates counts. The 66.1% holds little forward weight.", "severity": "P2", "status": "OPEN", "affected_component": "audit_dashboard/model.html / tournament_picks(model_id=kimi_direct)", "reported_by": "claude-opus-4-8", "assigned_to": null, "recommended_fix": "Add a recency/staleness badge + \"last resolved N days ago\" to model.html; flag models dark >14d as STALE; dedup tournament_picks NZDUSD row; surface most-recent-3 outcome strip so a losing tail is visible despite a high lifetime WR.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-09 04:50:40", "date_est": null, "time_est": null, "updated_at": "2026-06-09 04:50:40", "resolved_at": null, "link_md_path": null, "link_url": "https://findtorontoevents.ca/audit/model.html?id=kimi_direct", "link_github_ref": null }, { "incident_id": 119, "asset_class": "OVERALL", "source_ref": "GHA health audit w6gd2l9nj", "title": "GHA: Daily Per-Class Scrutiny Engine failing \u2014 scipy not installed", "description": "Engine imports scipy but workflow only `pip install pymysql`. CROSS-CHECKED: added scipy+numpy; re-run 27181760292 = SUCCESS.", "severity": "P2", "status": "RESOLVED", "affected_component": ".github/workflows/daily-scrutiny-engine.yml", "reported_by": "claude-opus-4-8 (GHA health audit + cross-check 2026-06-09)", "assigned_to": null, "recommended_fix": "Add scipy to deps (done). Verified green.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-09 03:31:11", "date_est": null, "time_est": null, "updated_at": "2026-06-09 03:31:11", "resolved_at": "2026-06-09 03:31:11", "link_md_path": null, "link_url": null, "link_github_ref": "94726fbba4" }, { "incident_id": 121, "asset_class": "OVERALL", "source_ref": "GHA health audit w6gd2l9nj", "title": "GHA: AI Leaderboard Freshness failing \u2014 (a) missing DB creds FIXED, (b) residual regime_report.json missing on runner", "description": "Two causes. (a) DB-reading steps lacked DB password -> 'no DB password found': FIXED via job-level AUDIT_DB_*/DB_PASSWORDS_JSON env (committed). (b) RESIDUAL: workflow still red because the FTP step's `deploy_audit_files.py --only audit_data` reports 'local missing' for alpha_engine/data/regime_report.json \u2014 that file is GITIGNORED and not generated in this workflow, so the runner checkout lacks it -> 1 failed -> exit 1.", "severity": "P2", "status": "IN_PROGRESS", "affected_component": ".github/workflows/ai-leaderboard-freshness.yml + tools/deploy_audit_files.py", "reported_by": "claude-opus-4-8 (GHA health audit + cross-check 2026-06-09)", "assigned_to": null, "recommended_fix": "DB-creds fixed. For residual: either generate regime_report.json in-workflow before deploy, OR make deploy_audit_files treat a missing-LOCAL source as skip+warn (not a hard exit-1), since these data files are gitignored and may be legitimately absent on a runner.", "target_release": null, "evidence": null, "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-09 03:31:11", "date_est": null, "time_est": null, "updated_at": "2026-06-09 03:31:11", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": "94726fbba4" }, { "incident_id": 109, "asset_class": "OVERALL", "source_ref": "session 2026-06-06 baby-strategy CI fix", "title": "Babies sweep aborts entirely when one strategy file raises SystemExit on import", "description": "baby_strategies/backtest_batch_round3.py does raise SystemExit(\"pip install yfinance\") at import; SystemExit derives from BaseException so the loader except Exception missed it and the whole sweep died at file 10/15 (run 27056111987 exit 1).", "severity": "P2", "status": "RESOLVED", "affected_component": "incubator/backtest_team/real_data_sweep_runner.py", "reported_by": "claude-opus-4-8", "assigned_to": null, "recommended_fix": "(see resolution_notes)", "target_release": null, "evidence": null, "resolution_notes": "Loader now catches SystemExit as a per-file import error so one bad file cannot abort the sweep. Verified locally: --max 15 --force completes exit 0.", "duplicate_of": null, "created_at": "2026-06-06 07:34:24", "date_est": null, "time_est": null, "updated_at": "2026-06-06 07:34:24", "resolved_at": "2026-06-06 07:34:24", "link_md_path": null, "link_url": null, "link_github_ref": "daf08d23b2" }, { "incident_id": 101, "asset_class": "OVERALL", "source_ref": "workflow:audit-review-and-baby-strategy-sweep; verified adversarially", "title": "Three models get 'T1' badges with n_resolved 41-98 (< charter n>=100) and PF lower-CI straddling 1.0", "description": "Tier is assigned by absolute PF/WR thresholds (T1 = PF>=2 & WR>=55) gated only at n>=30, not the project charter's T1 requirement of n>=100 clean trades. kimi_direct (n_resolved=54, pf 2.573, pf_ci_lo 1.313), grok3 (n=98, pf 2.216, pf_ci_lo 1.338), and llm7_qwen (n=41, pf 2.088, pf_ci_lo 0.929) all show 'T1'. llm7_qwen's PF 95% lower bound is 0.929 \u2014 i.e. the CI includes 'no edge' \u2014 yet it is badged T1 and ranked #3. The banner does say T1s are UNPROVEN, but the green T1 badge plus rank ordering still visually promotes them as proven-best.", "severity": "P2", "status": "OPEN", "affected_component": "audit-surface", "reported_by": "claude-opus-4-8 (audit-review workflow waesvw9hq 2026-06-06)", "assigned_to": null, "recommended_fix": "Gate the T1 badge itself on n_resolved>=100 AND pf_ci_lo>=1.5 (charter Tier-1 = PF>2); render anything below as 'T1-provisional' or downgrade to T2/T3 until n>=100. Suppress the T1 color until the CI lower bound clears 1.0. This aligns the badge with the banner copy already present.", "target_release": null, "evidence": "{\"confidence\": 0.95, \"review_evidence\": \"ai_tournament_leaderboard.json: tier counts {'BELOW':23,'BUILDING':16,'T1':3,'T2':2,'T3':2}; min_n_to_rank=30. llm7_qwen pf_ci_lo=0.929 (<1.0). Template line 641 sets tier purely on m.pf>=2.0 && m.wr>=0.55. DB-wide resolved WR is 48.9% \u2014 well below all three T1 WRs.\", \"verify_evidence\": \"ALL claim elements independently verified against live local files:\\n\\n1. audit_dashboard/data/ai_tournament_leaderboard.json (generated_at 2026-06-05T23:50Z): min_n_to_rank=30; tier counts {T1:3, T2:2, T3:2, BELOW:23, BUILDING:16} \u2014 exact match.\\n\\n2. Three T1 models confirmed verbatim: kimi_direct (n_resolved=54, pf=2.573, pf_ci_lo=1.313, wr=0.6481, rank=1); grok3 (n_resolved=98, pf=2.216, pf_ci_lo=1.338, wr=0.551, rank=2); llm7_qwen (n_resolved=41, pf=2.088, pf_ci_lo=0.929 [<1.0, CI includes no-edge], wr=0.6585, rank=3). All three n<100 (charter T1 requires n>=100).\\n\\n3. audit_dashboard/ai-tournament.html:639-641 \u2014 tier assigned purely on absolute thresholds: line 639 `m.rank_eligible = m.n_resolved >= 30;` then line 641 `m.tier = m.pf >= 2.0 && m.wr >= 0.55 ? 'T1'`. No n>=100 gate, no pf_ci_lo gate on tier. Confirmed verbatim.\\n\\n4. Badge IS green: line 21 `.b-t1 { background: #22c55e; }`. Rendered at line 700 as `T1`.\\n\\n5. Aggregate resolved WR computed from JSON = 48.2% (825 wins / 1711 resolved), close to claimed 48.9%; all three T1 WRs (55-66%) far exceed population mean \u2014 consistent with small-n inflation.\\n\\n6. Banner/warning copy DOES exist (line 211 tooltip; lines 693-696 per-row \u26a0\ufe0f tooltip stating 'n_resolved=X is below the 100-trade minimum for T1 confidence' and 'all T1s UNPROVEN until n>=100'). Live page (findtorontoevents.ca/audit/ai-tournament.html) confirms the UNPROVEN-until-n>=100 warning text is deployed.\"}", "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-06 07:34:00", "date_est": null, "time_est": null, "updated_at": "2026-06-06 07:34:00", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 103, "asset_class": "OVERALL", "source_ref": "workflow:audit-review-and-baby-strategy-sweep; verified adversarially", "title": "MISPRICED_ENTRY exclusion drops 58.5% of all picks; high-rank models have the heaviest exclusion", "description": "4,154 of 7,099 picks (58.5%) are excluded as MISPRICED_ENTRY (entry_price drifted >25% from market at submission). The exclusion is not random across the leaderboard: grok3 has 262 MISPRICED vs 52 resolved (83% of resolvable picks excluded), and deepseek_v4 shows n_picks=352 but only 39 resolved (282 excluded per JSON). When ~5x more of a model's picks are thrown out than survive, the surviving cohort can be a biased subsample (e.g. only the picks where the model happened to quote a near-market entry), which can systematically flatter WR/PF. The banner mentions the 4,154 exclusion but does not warn that selection bias in *which* picks survive can inflate the ranked WR.", "severity": "P2", "status": "OPEN", "affected_component": "audit-surface", "reported_by": "claude-opus-4-8 (audit-review workflow waesvw9hq 2026-06-06)", "assigned_to": null, "recommended_fix": "Add a per-model 'exclusion rate' column (n_excluded / (n_excluded+n_resolved)) and flag models where it exceeds e.g. 60% as 'survivorship-suspect'. Investigate why entry_price drifts >25% (data-feed lag vs model quoting stale prices) and fix upstream so fewer picks need excluding rather than silently dropping the majority.", "target_release": null, "evidence": "{\"confidence\": 0.83, \"review_evidence\": \"DB status distribution: MISPRICED_ENTRY=4154, OPEN=1160, LOSS=913, WIN=872. grok3 DB: 262 MISPRICED vs 52 resolved. leaderboard JSON deepseek_v4 n_excluded_untrustworthy=282 vs n_resolved=39. normalize.py:113 is_resolution_trustworthy excludes status=='MISPRICED_ENTRY'.\", \"verify_evidence\": \"All factual claims verified exactly against live DB and source files.\\n\\nDB status distribution (tournament_picks, ejaguiar1_stocks): MISPRICED_ENTRY=4154, OPEN=1160, LOSS=913, WIN=872, TOTAL=7099. 4154/7099 = 58.5% \u2014 matches claim exactly.\\n\\nPer-model (verified live): grok3 = 262 MISPRICED vs 52 resolved (WIN+LOSS) = 83% exclusion \u2014 matches exactly. deepseek_v4 = 282 MISPRICED vs 39 resolved, n=352 \u2014 matches exactly. High-rank-shaped models carry the heaviest exclusion: deepseek_v4 88%, ring_261T 92% (n_resolved=6), nvidia_nemotron_3_70b 87%, cerebras_llama4 86%, nous_hermes_4 84%, together_qwen_3 84%, grok3 83%, groq_llama_3_70b 82%.\\n\\nLeaderboard JSON (audit_dashboard/data/ai_tournament_leaderboard.json) deepseek_v4 row: n_picks=352, n_resolved=39, n_excluded_untrustworthy=282, n_wins=19, wr=0.4872 \u2014 matches claim exactly.\\n\\nCode: tools/ai_tournament/normalize.py:113 is_resolution_trustworthy; line 126 `if status == \\\"MISPRICED_ENTRY\\\": return False`. Docstring confirms >25% drift rule and 57.1% mispriced on top-15 models. Consumed by update_leaderboard.py:25 and build_model_summary.py:31.\\n\\nBanner: audit_dashboard/ai-tournament.html:195 states the 4,154 count + mechanism + that fireworks_qwen dropped from 92.1% to de-ranked, but does NOT contain any 'survivorship', 'selection bias', or per-model 'exclusion rate' warning (grep found none). So the claim that the banner omits a selection-bias warning is correct.\\n\\nONE OVERSTATEMENT: the claimed mechanism ('surviving cohort can system\"}", "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-06 07:34:00", "date_est": null, "time_est": null, "updated_at": "2026-06-06 07:34:00", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 104, "asset_class": "OVERALL", "source_ref": "workflow:audit-review-and-baby-strategy-sweep; verified adversarially", "title": "Funnel WR% excludes the majority of economically-resolved trades by bucketing TIME_EXIT as non-decisive", "description": "_classify_status() in extract_funnel.py maps TIME_EXIT/EXPIRED/STALE/FLAT to CLOSED_FLAT (non-decisive), counting only TP_HIT as WIN and SL_HIT/LOST as LOSS. For CRYPTO this drops 11,727 TIME_EXIT closes that DO carry real pnl_pct (5,499 positive / 6,226 negative). The displayed decisive denominator is therefore win 1,920 + loss 2,027 = 3,947, vs 15,671 trades that actually have a resolved economic outcome. This understates sample and biases WR. The displayed CRYPTO WR 48.64% rises only slightly to 47.34% when TIME_EXIT is scored by pnl, but the methodology hides that 75% of closes are time-exits, which is material for a hedge-fund-grade readiness page.", "severity": "P2", "status": "OPEN", "affected_component": "audit-surface", "reported_by": "claude-opus-4-8 (audit-review workflow waesvw9hq 2026-06-06)", "assigned_to": null, "recommended_fix": "In _classify_status / the funnel WR computation, score TIME_EXIT (and EXPIRED with non-null pnl) by pnl_pct sign rather than dumping to CLOSED_FLAT, OR surface a separate 'time-exit win-rate' column and label the headline WR as 'TP/SL-only WR'. Add the decisive-vs-total-closed ratio to the table so the time-exit dominance is visible.", "target_release": null, "evidence": "{\"confidence\": 0.88, \"review_evidence\": \"trading_picks CRYPTO 90d status: TP_HIT 1920, TIME_EXIT 11727, SL_HIT 1485, LOST 541, EXPIRED 339, OPEN 660. TIME_EXIT pnl_pct: 5499 pos / 6226 neg / 2 null. WR counting TIME_EXIT by pnl = 47.34% (n=15,671) vs page-displayed 48.64% (n=3,947). _classify_status maps TIME_EXIT->CLOSED_FLAT (extract_funnel.py:76-88).\", \"verify_evidence\": \"CODE: tools/audit_pick_funnel/extract_funnel.py:76-88 _classify_status maps TIME_EXIT/EXPIRED/STALE/FLAT->CLOSED_FLAT; only TP_HIT/WON->WIN, SL_HIT/LOST->LOSS. WR computed decisive-only at lines 212-216 (decisive=win+loss). Smart-Picks DB ground-truth query also restricts to status IN ('WON','WIN','LOST','LOSS') at line 284. DB (ejaguiar1_stocks.trading_picks, CRYPTO 90d): TIME_EXIT 11727, TP_HIT 1917, SL_HIT 1485, OPEN 660, LOST 541, EXPIRED 339 \u2014 matches claim within trivial drift (claim said TP_HIT 1920). TIME_EXIT pnl_pct: 5499 pos / 5516 neg / 710 zero / 2 null (claim said 5499 pos / 6226 neg \u2014 pos matches exactly; neg differs because claim folded zeros). Computed decisive WR = 48.62% n=3943 (claim 48.64% n=3947). WR including TIME_EXIT+EXPIRED scored by pnl sign = 49.13% n=15132 (claim 47.34% n=15671 \u2014 direction confirmed: WR barely moves, sample ~4x larger; exact figure differs by zero-pnl bucketing). Time-exit dominance: TIME_EXIT+EXPIRED = 75.4% of the 16009 non-OPEN closes; decisive TP/SL is only 24.6%. PARTIAL DISCLOSURE: pick_funnel.html:217 states 'WR shown is decisive-only ... so flat/expired picks don't dilute it'; tables (lines 778/794/823) show touched/closed/decisive columns side-by-side; a TIME_EXIT_inflation caveat exists \u2014 BUT build_nav_surface_matrix.py:225-230 scopes it ONLY to surface_id=='elite_display_tier' and keys off exit_reason text, NOT the headline funnel/Smart-Picks WR cells where the concern applies.\"}", "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-06 07:34:00", "date_est": null, "time_est": null, "updated_at": "2026-06-06 07:34:00", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 105, "asset_class": "OVERALL", "source_ref": "workflow:audit-review-and-baby-strategy-sweep; verified adversarially", "title": "Advertised multi-asset coverage is a facade \u2014 CRYPTO/BOND/FUTURES never produced; TOP-20 is 80% equity", "description": "The page is positioned as 'best picks across stocks/crypto/forex/bonds/ETFs/commodities/futures' and references BOND (TLT/IEF/SHY) and CRYPTO in methodology/tier tables. But the live data never contains them as actual picks: picks_now.json 'all' (50) = EQUITY 31 / ETF 10 / FOREX 5 / COMMODITY 4, zero CRYPTO/BOND/FUTURES; the TOP-20 shown is EQUITY 16 / ETF 3 / FOREX 1 (80% equity). picks_now_tracker (all history) = EQUITY 83 / ETF 10 / FOREX 3 \u2014 never any crypto/bond/commodity/futures row. BOND tier entries (TLT/IEF/SHY) are static reference text, not generated picks with entry/TP/SL.", "severity": "P2", "status": "OPEN", "affected_component": "audit-surface", "reported_by": "claude-opus-4-8 (audit-review workflow waesvw9hq 2026-06-06)", "assigned_to": null, "recommended_fix": "Either wire real CRYPTO/BOND/FUTURES candidate generation (yfinance/CoinGecko for crypto, bond-ETF momentum for BOND) so the page delivers on its multi-asset promise, OR relabel the page honestly as 'Equity-led with limited FX/ETF/commodity' and remove the BOND/CRYPTO tier rows that imply coverage that does not exist.", "target_release": null, "evidence": "{\"confidence\": 0.78, \"review_evidence\": \"picks_now.json Counter(class): all={EQUITY:31,ETF:10,FOREX:5,COMMODITY:4}, top20={EQUITY:16,ETF:3,FOREX:1}. DB picks_now_tracker GROUP BY asset_class -> EQUITY 83, ETF 10, FOREX 3 only.\", \"verify_evidence\": \"DB live query: SELECT asset_class, COUNT(*) FROM ejaguiar1_stocks.picks_now_tracker GROUP BY asset_class => EQUITY 83 / ETF 10 / FOREX 3 (no crypto/bond/commodity/futures) \u2014 exactly matches claim. audit_dashboard/data/picks_now.json (committed HEAD): all (50) = EQUITY 31 / ETF 10 / FOREX 5 / COMMODITY 4; picks/top20 (20) = EQUITY 16 / ETF 3 / FOREX 1 (80% equity) \u2014 both Counters match the claim exactly. Live deployed https://findtorontoevents.ca/audit/data/picks_now.json (gen 04:53 ET) shows all = EQUITY 40 / ETF 14 / FOREX 8 / COMMODITY 4, no CRYPTO/FUTURES. Page header (audit_dashboard/picks-now.html:110) is literally 'Multi-Asset Quant Screener'. BOND tier row (line 194 TLT/IEF/SHY) IS static educational 'Safety Tiers' text, not generated picks \u2014 confirms that part.\"}", "resolution_notes": null, "duplicate_of": null, "created_at": "2026-06-06 07:34:00", "date_est": null, "time_est": null, "updated_at": "2026-06-06 07:34:00", "resolved_at": null, "link_md_path": null, "link_url": null, "link_github_ref": null }, { "incident_id": 106, "asset_class": "OVERALL", "source_ref": "workflow:audit-review-and-baby-strategy-sweep; verified adversarially", "title": "No staleness gate: header stuck at 'Loading...' and JSON age never shown/guarded", "description": "The page header (#header-updated line 112) and market strip (line 133) ship literal 'Loading...' and are only replaced client-side from data.generated_at; there is no max-age check. If picks_now.json fails to refresh (the GHA picks-now-refresh workflow or FTP deploy stalls), the page will silently display hours/days-old entry prices as 'right now' actionable picks with no stale warning. There is no setInterval/age-threshold logic in the page. The DB shows a 07:04 batch newer than the 04:52 JSON the page serves, indicating the JSON can lag the generator.", "severity": "P2", "status": "OPEN", "affected_component": "audit-surface", "reported_by": "claude-opus-4-8 (audit-review workflow waesvw9hq 2026-06-06)", "assigned_to": null, "recommended_fix": "Compute age = now - generated_at in the render JS; if > ~30min show a red 'STALE \u2014 prices may be outdated, do not trade' banner and gray the cards. Have the refresh workflow write generated_at and verify the deployed JSON timestamp post-FTP.", "target_release": null, "evidence": "{\"confidence\": 0.97, \"review_evidence\": \"picks-now.html:112 'Last Updated: Loading...', :917 builds est from data.generated_at with no age check; grep stale|age|Date.now|setInterval -> only static text. picks_now.json generated_at 04:52; picks_now_tracker latest batch 07:04:21.\", \"verify_evidence\": \"All four claimed evidence points verified independently in /home/eaguiar2015/findtorontoevents_antigravity.ca/audit_dashboard/picks-now.html:\\n- Line 112: `\ud83d\udd04 Last Updated: Loading... EST` \u2014 literal placeholder.\\n- Line 133: `
Loading...
` \u2014 market strip placeholder.\\n- Line 917-918: `const est = data.generated_at ? new Date(data.generated_at).toLocaleString(...) : '\u2014';` then sets header. No subtraction of now-generated_at, no threshold.\\n- grep for `stale|Date.now|setInterval|getTime|age|max.?age|outdated`: the only Date.now() use is line 1053 cache-buster `fetch('data/picks_now.json?_=' + Date.now())`; no age comparison anywhere. Only 1 inline