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.
Supply repository scripts as a named build context for the backend check stage so containerized regression tests can import the same acceptance helpers as local tests. Keep operator scripts out of the runtime image.
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.
Validate deployed image receipts and local identities before startup, ignore caller Compose and image overrides, and report success only after health checks.
Install versioned Bash entrypoints and their standalone controller under the deployment lock while preserving local customizations. Cover lifecycle and installation behavior in isolated tests.
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.
Check the current summary endpoint across all four supported windows, including 72 hours, while retaining invalid-window rejection. This fixes the obsolete events route that stopped isolated CI acceptance.
Discard the Skill list response if the session changes after draft creation, and cover the race with a regression test. Frontend lint, type checking, all 50 tests and production build pass.
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.
Use a shared SVG combining an A mark with a market pulse line for the favicon, login page, and navigation. Preserve the existing theme and page layout.
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.
Run the dedicated calendar worker, bind the web service to loopback port 21005, and match the host nginx upstream.
Trust forwarded headers only from the Docker subnet and replace untrusted forwarded client chains at the public proxy. Validate Compose without resolving production environment files; do not restart services.
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.
eezd