Select assignment-specific keyword snapshots, improve model-token recall and calendar dates, and reuse supplied originals. Keep extraction boundaries while checking compaction against the final research context.
Extract reusable literal keywords once per source revision, assign complete news packages to long-lived events, and research all event members with immutable evidence and references.
Add additive research storage, vocabulary snapshots, the two-stage workspace, isolated acceptance coverage, and a paused rollout with an initial fixed 50-news production trial.
Use BIGINT casts for JSON batch references in queue filters, retries and legacy job reconciliation. Cover real large batch references and absent 64-bit IDs in isolated PostgreSQL acceptance.
Freeze date-range previews and model settings, track per-news progress and downstream targets, and share completion-driven scheduling with realtime analysis.
Prevent overlapping retries for the same news, retain batch queue associations, and refresh selected details with session-safe pagination.
Group original news into tagged fact packages, review each package with evidence and read-only research, and build complete 72-hour reading lists with independent model selections.
Add paused RSS/Atom subscriptions, news-scoped Skills, versioned analysis records, and locked deployment support for SearXNG. Preserve original news and keep live migration and legacy AI cleanup separately authorized.
Validate with 604 backend tests, 49 frontend tests, 19 CI control tests, lint, type checks, production build, and disposable PostgreSQL migration and three-stage smoke checks.
Refresh historical previews after the local day ends and isolate retries by date without resetting browser scheduling progress.
Preserve withdrawal and restoration revisions, exclude withdrawn fallback values, and cover the behavior with isolated regression checks.
Collect macroeconomic releases, events and holidays through the official browser SDK with resumable history from 2025. Preserve evidence, revisions and observation times, and merge verified series with official fields taking priority.
Add category filters, field provenance, coverage and connection status. Verify calendar persistence and deployment recovery in isolated acceptance checks.
Collect weekly claims and precise commercial petroleum inventory changes with official schedule exceptions, distinct reporting periods, raw evidence, and revisions.
Extend explicit history backfills without changing their default source scope. Report archive gaps and reject mismatched weeks instead of filling current values into history.
Store account credentials encrypted and bind QR tasks to administrator sessions. Report calendar access as awaiting validation after login.
Prevent late polls and status responses from overwriting cancelled or newer operations, and clean up QR tasks when settings unmount. Cover authentication, cancellation races, and stale frontend responses.
Poll only visible news IDs and update ratings for matching revisions without replacing the feed, scrolling, or clearing pending-news notifications. Bind refresh results to the page and session, and cover stale responses and bounded ID queries.
Analyze news revisions with independent model settings, evidence-backed risk ratings, event grouping, and rolling market outlooks. Add a default homepage, archival history, pending-result refresh, and isolated regression coverage.
Keep analysis disabled until explicitly enabled. Require a separately authorized schema migration before deployment and preserve compatibility with the previous six-service instance.
Handle German CPI corrections, year-end wording and monthly employment titles, and accept ONS labour-market titles without a colon.
Select EA21 rows when published and verify unemployment totals against the bulletin overview. Add real archive fixtures covering the backfill failures.
Match GDP table labels without case sensitivity and accept the observed seasonally-adjusted wording. Add real 2025 announcement excerpts and verify dates, previous values, and rejection of non-GDP tables.
Exclude the independent latest-release list from archived links and date boundaries. Cover stopping before the requested year, continuing within range, and rejecting pages without a filtered result block.
Fetch annual report indexes, skip stored PDFs, and stop the source on rate limits. Match report periods, stages, and publication dates to official schedules while preserving received results and keeping revised monthly series separate.
Extract original preliminary and final results with publication dates and validated table headers. Add annual report discovery and real report fixtures covering cross-month releases and PDF text layout differences.
Keep previously captured BLS and Michigan releases valid when their rolling latest pages advance to a newer period or stage. Continue reporting missing historical releases explicitly and never substitute newer values.
Verify unchanged values, first-arrival timestamps, revisions, and cleared source errors with isolated worker tests. Run all 74 calendar and history tests against the staged snapshot.
After the first take-profit fills, cancel outstanding entry orders before calculating remaining-position protection. Missing fee records still fail explicitly and leave existing stops in place without allowing the old entry to remain open.
Cover complete and incomplete fees on Binance and Bybit, including cancellation before the recovery fetch and no duplicate cancellation. Verify the staged snapshot with 61 trading safety and plan tests.
Keep analysis and Skill detail responses bound to the selected request, reject stale publish confirmations, and clear failed position-history results with retry controls.
Reject removal of the current default provider with HTTP 409 and reflect that contract in the form. Track the OpenAPI page and API module by restricting the docs ignore rule to the repository root.
Validate the staged provider contract with four isolated tests. Reuse the matching candidate's frontend lint, type check, 26 test groups, and production build results.
Replace cookie authentication with revocable Bearer sessions, optional one-use PNG challenges, bounded login limits, and short-lived market WebSocket tickets. Keep captcha disabled by default.
Standardize ordinary JSON responses while preserving HTTP statuses, raw OpenAPI, redirects, SSE, and WebSocket semantics. Revoke long connections with their owning session.
Expose official calendar data and collector status to the frontend and research tools, support bilingual news topics, and keep summaries and forward-only labels explicit. Verify the staged snapshot with all 305 backend tests.
Calculate remaining-position break-even from actual entry fees and estimated closing fees, preserve confirmed tighter stops, and keep existing protection when fill fees are incomplete.
Build historical trade summaries from execution sizing when an acceptance fill has no setup. Clarify unverified price zones and avoid suggesting fabricated structure to satisfy validation.
Verify the staged snapshot with 57 trading safety and plan tests.
Collect official RSS and Atom summaries, preserve historical captures, and poll macro releases with bounded cadence and Retry-After handling. Separate news collectors from the economic calendar worker.
Track statistical periods, publication stages, first observations, revisions, and current official series. Include explicit migration files and isolated archive, parsing, and import tests; no migration or import is executed by this commit.
Keep dependency declarations and lockfile together for PDF archives and the upcoming captcha integration. Verify the staged snapshot with 90 focused tests.
Validate Wallstreetcn business responses and retain list provenance for historical paid articles whose detail API returns code 50000. Keep other failures explicit and cover the boundary with eight isolated tests.
Persist manual requests until exchange confirmation, preserve stop protection, and reconcile fills before settling plans. Tighten model stream, crawler, skill, research accounting, and frontend race handling, with regression coverage. Keep queued analyses pending until a fresh account snapshot is available.
List each plan filled in the last 24 hours with its zone, entry, fill and
close times, close reason and net result, so the model can apply the
skill rules on consecutive stops, re-entry after a stop and the daily
entry cap.
The trader labels crypto news published after 2026-10-16 15:00 with
the configured model (category and BTC direction) and, four hours
later, backfills BTC/ETH 1m opens at publish, +5m, +1h and +4h from
the klines table. A drawer on the trading page shows the cumulative
returns of trading the labelled direction, after fees. Nothing is
traded; this only collects an out-of-sample record.
Move running, running_changed_at and capital_usdt from the account to
each trading symbol; the migration copies the account capital to every
symbol and leaves them all stopped. Each symbol is sized against its
own capital with a 3x notional cap, and the capitals together must not
exceed account equity. Scheduling, dry-run decisions and the executor
follow the per-symbol flag. The global start/stop button is replaced by
start/stop and capital controls on each symbol's plan card.
The API queues the request in Redis and the executor applies it on its
next pass, so it never races reconciliation. Both actions cancel every
open order on the symbol, including manual ones, and market-close any
position. Plans end as manual_close or manual_cancel without queueing
a new analysis. Closing also stops trading so the engine does not
reopen right away.
Sync account fills into a new trading_fills table every 60s and
reconstruct closed positions from them, so positions opened outside
the program are included and external closes get an exit price.
Positions link to plans by order id. The history drawer gains symbol,
close-date, outcome and source filters, a summary bar and pagination.
The detail is now a persistent side panel, so quick clicks can interleave
requests: only the latest request's result is applied, and a failed load
shows an error state with a retry button instead of spinning forever.
Also correct the position history comments: only plans from before plan
3.1 could hand their position over to a replacing plan.
New GET /api/trading/positions/history lists closed plans (entry filled,
position back to zero) newest first with before/limit paging. Each row
carries the filled quantity, volume-weighted entry and exit prices from
the plan's own fills, the close reason and the realized PnL, commission
and net from the plan result.
The positions panel gets a "历史仓位" button that opens a drawer with the
table, a "load earlier" button and links to each plan's analysis.
eezd