UI:
- Embed the real APEX logo PNG (transparent mark) in dashboard sidebar,
cmd-header, landing nav, and landing hero (replaces SVG approximations).
- Add favicon.png across all six templates.
- Nudge color palette to brand cyan→blue→purple gradient and silver-white
wordmark; word-by-word coloring on the cmd-header tagline.
- Drop-shadow glow on logo marks tuned to the brand-blue.
Demo:
- python -m demo.run_demo now defaults to an auto-running showcase: opens
the dashboard, kicks off a ~3-4 min optimization that exercises every
phase, and lands on a verdict modal — no manual setup needed.
- Tight per-iteration targets so Phase 2 actually iterates (visible AI loop).
- Skip per-run AI analysis during Phase 1 exploration via APEX_DEMO_SKIP_PHASE1_AI=1
to keep total runtime down without losing the headline AI loop in Phase 2.
- --quick flag opts back to the original fast/manual flow.
- --loop auto-restarts for unattended screen recording.
Docs:
- README + SUBMISSION updated to describe the new auto-running default.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three issues caused the dashboard to look frozen during the long Phase 1
exploration phase, even when 2+ runs had completed:
1. AI Thinking feed only got ONE entry (the phase-start banner) and then
went silent until Phase 2. Phase 1 is LHS sampling so there are no AI
calls — but we can still narrate observations rule-based. Added
_narrate_phase1_run() that emits a per-result message tuned to what
actually happened: 'PF 1.8, DD 14% — strong region, worth refining'
(success), '$-734 loss with 191 trades — skipping' (warning), 'only
3 trades — params too restrictive' (info), etc. Mediocre runs are
throttled to 1-in-5 to avoid feed spam
2. Parameter Changes panel showed 'No iterations yet — AI-driven param
edits appear per iteration' which is misleading during Phase 1
(where there are no iterations YET, by design). Empty-state message
now phase-aware: shows 'Exploration phase — changes appear in Phase
2' during phase1, 'Waiting for first AI iteration' if autonomous, or
'Random-neighbor refinement — enable Autonomous AI for AI changes'
if not autonomous
3. AI Summary still said 'Waiting for optimization to start...' even
while the optimization was actively running. New refreshAIWaitingState()
updates the message based on (a) whether a run is active and (b)
whether the API key is set. When running with no key, shows 'AI
insights are off — no Anthropic API key set' with a 'Configure API
key in Settings →' link
Frontend now also tracks state.phase and state.autonomous from
phase_start events so all empty-state messages stay in sync.
- AIReasoner default model now claude-opus-4-7 (was sonnet-4-6); pipeline
reads ai.model from config and passes to constructor. The reasoner
class attribute is also Opus 4.7 so any caller without explicit model
defaults to the hackathon model
- README hero gains a "Built with Claude Opus 4.7" badge + a line linking
to the Cerebral Valley × Anthropic hackathon page
- New SUBMISSION.md — copy-paste blocks for every field of the
submission form: name, taglines, short / long description, "how Claude
is used" detail, GitHub URL, demo instructions, tags, tech stack,
team, license, and a final pre-submission checklist
Demo + assets
- Synthetic backtests now occasionally fail (regime failures, OOS degradation)
so verdicts span RECOMMENDED / RISKY / NOT_RELIABLE realistically. Phase 1
has ~35% failure rate, Phase 2 AI loop ~10%, OOS has 30% chance of severe
degradation — matches what real markets look like
- screenshots/dashboard.png + best_result_modal.png regenerated against the
current UI; screenshots/apex_demo.gif (6-frame autonomous-run timelapse)
embedded in the README
FEATURE 1 — Live AI token streaming
- AIReasoner._call_claude() now streams via SSE when a callback is
registered. Each text delta forwards to the dashboard as
`ai_thinking_chunk` events
- The Live AI Thinking Feed renders a single growing bubble with a blinking
cursor while text streams in, finalising on `end`. Looks and feels like
watching the AI type
FEATURE 2 — Pre-flight check on /setup
- New /api/preflight endpoint runs 5–7 probes: config readable, API key
set, MT5 paths exist (skipped in demo), EA registered, reports folder
writable. Returns {ok, blocking_count, checks[]}
- Setup page renders a colour-coded checklist on load and refocus.
Replaces "click Start, wait 5s, see generic error"
FEATURE 3 — Hot-reload settings into the running pipeline
- pipeline.reload_config() applies AI model / timeout / API-key swaps to
the live reasoner mid-run. Threshold changes surface for next run
- /api/settings POST detects a running pipeline and calls reload_config(),
returning the changed keys plus a "hot-reloaded into the running
optimization" note
FEATURE 4 — Replay scrubber on Best Result
- Evolution path now renders as an interactive scrubber: range slider +
prev/next/play buttons. Each step shows the run ID, phase, score, full
metrics grid, parameter changes for that step, and the AI's analysis
text — auto-plays at 700ms/step
FEATURE 5 — Compare runs on /reports
- Each card has a checkbox; selecting 2–4 reveals a floating Compare bar.
Compare modal renders a side-by-side table with metric winners
highlighted (Calmar / PF / profit favour higher; DD favours lower)
and a parameter-diff section showing changed values
FEATURE 6 — Discord / Slack / generic webhook on completion
- New `notifications.webhook_url` + `webhook_style` config keys
- Auto-detects Discord vs Slack from the URL host. Posts a one-line
summary on `optimization_complete`: verdict + best run + PF/Calmar/DD/
profit/trades/elapsed
Refresh-during-run no longer wipes the dashboard
- pipeline now keeps in-memory rolling logs of ai_thinking, param_changes,
validation events, and the current early-termination state. Logs reset at
the start of each new run (capped: 200 thinking / 50 param-change records /
40 validation events)
- new GET /api/live_activity returns those logs + current phase + running
state in one shot — the dashboard hits it on page load
- restoreHistory() in dashboard.js now replays each event into addThinking /
addParamChanges / validationRunStart-Complete-Done / showEarlyTermination,
and re-applies the active phase via setPhaseActive. Reload F5 mid-run no
longer shows a fresh empty dashboard
- addThinking() preserves the original ts on replay (was using nowStr() so
every replayed entry got the refresh time)
Reports page (/reports) rebuilt
- previous template crashed with 500 on legacy summary.json files that
pre-date the win_rate / drawdown_pct fields. Server now backfills sane
defaults for every metric the template touches
- runs now sorted by ts (was filesystem-iterdir order)
- new template: search bar + filter chips (All / Exploration / AI Iteration
/ Validation / AI insight / Has .set), phase tags, AI/.set badges, three
action buttons per card (View Params / Download .set / Full Report)
- per-card detail modal shows metrics grid + full parameters table +
AI reasoning + Download .set button — the missing "click to see params
+ download" path the user reported
- has_set detected per-run by globbing run_dir/*.set; AI insight tag shown
when ai_insight.json exists on disk
API + data integrity
- /api/settings GET no longer leaks the active Anthropic API key — returns a
masked preview (sk-ant-XX…YYYY) plus a boolean `anthropic_api_key_set` flag
- /api/settings POST won't overwrite a real key with the masked placeholder
the client receives back on GET (length<30 / "…" / "..." / "***" markers
trigger a preserve-existing path)
- /api/best_result, /api/status, _make_run_dict, _result_to_dict, all AI-loop
emits, validation_run_complete, optimization_complete, ai_iteration_complete,
ai_targets_met, run_complete: max_drawdown and win_rate are now consistently
emitted as PERCENTAGES (0–100), matching the dashboard's existing display
formatters. They were previously emitted as fractions (0.13 = 13%) so the UI
rendered "0.13%" instead of "13%"
- ResultRanker.make_result() now sets `passing` and `raw_score` on every result
it produces. Previously these were only set during a full ranker.rank() pass,
so individual Phase 2 / Phase 3 runs hit _make_run_dict with passing=False
even when they cleared all gates (history showed "0 passing" when 22/22
actually passed)
Major upgrade making the AI loop visible and the project ready for public release.
UI / UX
- Live AI Thinking Feed: streams reasoning, decisions, and outcomes per iteration
- Parameter Changes panel: prev → new + reason for every AI-driven edit
- Validation Activity panel: out-of-sample + sensitivity runs with live metrics
- Early Termination banner: surfaces why optimization stopped (targets met, no profit, budget, stuck, user stop)
- 3-phase tracker renamed Exploration / Iteration / Validation with live N/total
- Best Result modal exposes Evolution Path showing how the AI arrived at the winner
- Run-detail modal accessible from every recent run row
- Setup form validation (dates, walk-forward order, params selection, AI targets)
- Pause button removed; misleading sidebar nav consolidated to Dashboard / New Run / Reports / Source
Backend
- AIGuidedLoop streams ai_thinking, param_changes, ai_targets_met, ai_stuck
- Pipeline emits validation_start / validation_run_start / validation_run_complete / validation_done
- Pipeline emits early_termination on every early-stop path
- /api/best_result returns best run + full evolution chain
- /api/run/<id> + /api/runs sorted by ts
- AIReasoner falls back to ANTHROPIC_API_KEY env var when config is a placeholder
- Demo mode (APEX_DEMO_MODE=1) generates deterministic synthetic backtests so judges can run end-to-end without MT5
Open-source readiness
- README.md with pitch, demo flow, architecture diagram, quickstart, event reference
- LICENSE (MIT)
- config.example.yaml template (config.yaml now git-ignored)
- requirements.txt: added anthropic / requests / psutil / beautifulsoup4, capped majors
- .gitignore: secrets, *.set, scratch screenshots, ea_registry.yaml
- demo/run_demo.py: one-command offline demo runner
- 10 polished screenshots for README + judge review
PROBLEM: Old system repeated identical params, all scores flat at 0.2500,
user had zero control over symbol/TF/dates. Not smart, not dynamic.
NEW ARCHITECTURE:
optimizer/ (NEW package)
├── __init__.py
├── session_config.py User choices (EA, symbol, TF, dates, budget, objective)
├── lhs_sampler.py Latin Hypercube Sampling — diverse exploration
├── result_ranker.py Relative scoring (best in session=1.0, worst=0.0)
├── budget.py Time budget tracker
└── pipeline.py 3-phase orchestrator
Phase 1 — Broad Discovery (LHS, 20-26 runs):
Samples FULL parameter space, not just defaults±tiny step
LHS guarantees coverage: all 17 optimizable LEGSTECH params explored
Relative ranking: profitable configs float top, losers score 0
Phase 2 — Refinement (9 runs):
Neighbor search around top 3 configs at ±20% range (not ±0.5 step)
Keeps best of Phase1 vs Phase2 — never regresses
Phase 3 — Validation (5 runs):
OOS backtest on unseen data period
Sensitivity test: nudge params ±20%, detect fragility
Verdict: RECOMMENDED / RISKY / NOT_RELIABLE
Output: Clean downloadable .set file via /download_set/<run_id>
UI REDESIGN:
ui/templates/landing.html New / homepage (was old dashboard)
ui/templates/setup.html New /setup — EA, symbol, TF, dates, budget, objective
ui/templates/dashboard.html Updated /dashboard with:
- 5-step phase indicator
- Real progress bar per run
- Phase 1 results table (top 5 after phase1)
- Verdict banner with download button
- No-profitable-config warning
ui/static/js/dashboard.js Handles 8 new pipeline SocketIO events
app.py New routes: /, /setup, /dashboard
/api/start accepts full SessionConfig JSON
/download_set/<id> serves optimized .set
ea/registry.py +list_all() for setup page dropdown
ui/templates/reports_index.html Back to Dashboard → /dashboard (was /)
ui/static/css/style.css +dot-warn, dot-done, profit-pos/neg, aliases
FIXES:
Score no longer flat 0.2500 (was: absolute thresholds on losing EA)
User now controls: symbol, timeframe, dates, budget, objective
Parameters now span full range (was: tiny step from defaults)
Verdict is actionable: RECOMMENDED / RISKY / NOT_RELIABLE with reason
TESTED:
8/8 pre-flight checks pass
Browser test: landing ✓, setup form ✓, /dashboard ✓,
phase indicator active ✓, /reports ✓, back link ✓
LEGSTECH Optimizer