_parse_classification_response receives raw model output (with thinking
tags, markdown fences, etc.) but was calling json.loads directly.
Now uses _strip_markdown_fences + _repair_json from the client module
before parsing, matching what _call_ollama does for extractions.
_call_ollama validates against the document extraction schema, which
doesn't match event classification output. The event classifier was
checking 'if attempt.error is None' before trying its own parsing,
so it never got to parse the valid event JSON — 956 consecutive
failures.
Now tries _parse_classification_response whenever raw_output exists,
regardless of the extraction validation error.
Redis uses separate env vars, not a single REDIS_URL. Script now
builds the connection string from REDIS_HOST, REDIS_PORT, REDIS_DB,
and REDIS_PASSWORD — matching how services/shared/config.py does it.
No more hardcoded passwords — pulls POSTGRES_HOST, POSTGRES_USER,
POSTGRES_PASSWORD, POSTGRES_DB, and REDIS_URL from the pod's
environment (injected by k8s secrets).
The repo is now private (BSL license), so pods need valid GHCR
credentials to pull images. runmefirst.sh now:
- Verifies the token can authenticate with GHCR
- Force-recreates the ghcr-credentials secret before Helm deploy
- Warns if the token is expired or missing scopes
- scripts/test_saved_queries.py: tests all 24 saved SQL explorer queries
against the live Trino API (all 24 pass)
- scripts/run_reclassify_and_reaggregate.sh: self-contained script to
re-classify macro events with updated prompts and re-aggregate all
tickers. Scales aggregation to 16 pods, monitors queues, scales back.
Licensed under Business Source License 1.1.
Copyright (c) 2025-2026 Celes Hillyerd. All rights reserved.
Production use requires written approval from the author.
Change Date: 2030-04-17 (converts to GPL v2+ after that).
Migration 028: For each recommendation with no evidence rows, finds
the closest matching trend_window (by ticker + time_horizon + timestamp)
and re-inserts evidence from top_supporting/opposing_evidence arrays.
Filters out non-UUID pattern IDs and verifies documents exist.
This fixes 'No evidence linked' on recommendations created before the
UUID filtering fix in persist_recommendation.
Backend: assemble_trend_with_evidence now deduplicates document IDs
via dict.fromkeys() (the rollup code already did this, but the base
assembly didn't — same doc could appear multiple times from different
intelligence extractions).
Frontend: Trends.tsx deduplicates via Set before rendering as a safety
net for existing data already stored with duplicates.
- EvidenceRef component now fetches document details via useDocument()
hook and displays the title instead of 'doc:43156423…'
- TanStack Query deduplicates and caches lookups for repeated doc IDs
- Pattern IDs still render as before (e.g. 'pattern META other (1d)')
- Override Trade button changed from brand-600 to red-600
The handler for /api/macro/impacts/:ticker was returning the impacts
array directly instead of { exposure_profile, impacts }. The frontend
destructures macroData.impacts which was undefined, falling back to
an empty array — so the Macro tab always showed 'No active macro impacts'
even with mock data present.
- recommendation worker: filter out non-UUID document IDs (synthetic
pattern:* IDs from competitive signals) before inserting into
recommendation_evidence table — the uuid cast was failing and
silently dropping all evidence rows
- wrap executemany in try/except so partial failures don't lose all evidence
- SqlExplorer: wrap Lucide icons in <span title=...> instead of passing
title prop directly (not supported by lucide-react, broke CI build)
- Add GET/PUT /api/admin/trading/approval-config endpoints
- Add POST/DELETE /api/admin/trading/lockouts endpoints
- Add useApprovalConfig, useUpdateApprovalConfig, useCreateLockout, useDeleteLockout hooks
- Add Paper Order Approval toggle card with confirmation dialog
- Add lockout creation form and delete button to Active Lockouts card
- Add MSW handlers for all new endpoints
- Add property-based tests for bug condition exploration and preservation
- Pattern IDs (pattern:META:other:1d) shown as 'pattern META other (1d)'
- Document UUIDs shown as clickable 'doc:43156423…' links to document detail
- Unknown formats shown truncated as fallback
API was returning a flat array but frontend expects CompanyMacroImpacts
wrapper with exposure_profile and impacts fields. Also queries the
exposure_profiles table for the company's active profile.
- Trading page: added conservative/moderate/aggressive selector that
updates the trading engine config via PUT /api/trading/config
- Recommendations page: added risk tier dropdown that defaults to the
engine's current tier and filters recs by the tier's min_confidence
- Backend: added min_confidence query param to GET /api/recommendations
- Risk tier thresholds: conservative ≥0.75, moderate ≥0.55, aggressive ≥0.40
- Removed PUT /api/trading/capital (set capital) — only touched in-memory state
- Removed POST /api/trading/capital/adjust (add/withdraw) — same problem
- Reset endpoint now: liquidates Alpaca positions, cancels orders, clears DB,
then queries Alpaca for real portfolio_value to set engine capital
- Frontend: replaced CapitalCard with simple ResetCard (one button)
- Removed useSetTradingCapital and useAdjustCapital hooks
- Added cancel_all_orders() and close_all_positions() to AlpacaBrokerAdapter
- Reset endpoint creates a temporary adapter to call Alpaca DELETE /v2/orders
and DELETE /v2/positions before clearing DB and engine state
- Also clears positions table and processed_recommendation_ids on reset
- Broker reset is best-effort — DB/engine reset proceeds even if Alpaca fails
Agreement of 1-2 signals was inflating confidence to paper-eligible
levels (0.575) even with low credibility sources. Added log2-based
dampener that scales agreement contribution by unique source count,
saturating at n=7. Single signals now cap at 0.39 confidence,
2 signals at 0.49 — both correctly below paper threshold (0.50).
- Recommendation worker now resolves thesis-rewriter config from DB
and passes ollama_config to generate_recommendation. Thesis rewriting
is now active when the thesis-rewriter agent exists in ai_agents.
Refreshes config every 50 jobs.
- Event classifier now resolves its own config separately from the
document extractor via 'event-classifier' slug. Uses a separate
OllamaClient when the model differs from the extractor. Refreshes
alongside the extractor every 100 jobs.
- Document extractor was already wired (existing code).
- Added 8 unit tests for AgentConfigResolver covering: DB resolution,
variant override, not-found, DB errors, TTL caching, cache refresh,
and invalidation.
- Migration 026 and OllamaConfig now default to qwen3.5:9b instead of
llama3.1:8b. Existing deployments keep their current model (qwen3.5:9b-fast)
since the migration uses WHERE NOT EXISTS on slug.
- Event classifier system prompt expanded with macro-vs-company filtering:
explicitly instructs the model to NOT classify single-company news
(lawsuits, earnings, management changes, debt crises) as macro events.
Sets severity=low and confidence<0.3 for company-specific articles.
Reserves 'critical' severity for multi-country/global market events.
Prevents over-tagging event_types by requiring direct description.
- Updated test_system_prompt_is_concise threshold to accommodate the
expanded prompt (300 → 1000 chars).
Three distinct capital operations on the Trading Controls page:
- Set Capital: overwrites pool balances to a new amount (existing)
- Add/Withdraw: adjusts active pool by a delta without touching
positions, orders, or history. Validates sufficient balance for
withdrawals. Logged to reserve_pool_ledger as manual_adjustment.
- Reset Everything: nuclear option — deletes all positions, orders,
trading decisions, stop levels, snapshots, backtests, notifications,
and circuit breaker events, then resets capital fresh. Red button
with double-confirmation dialog.
Backend: POST /api/trading/capital/adjust and POST /api/trading/reset
Frontend: CapitalCard rebuilt with three sections and confirmation UIs
New Agents tab in the sidebar (Ops group) for viewing, editing, and
creating AI agent configurations:
Database (migration 026):
- ai_agents table: editable configs for each LLM agent (model, prompts,
temperature, tokens, retries). source='system' for built-in,
source='user' for custom. Seeds 3 system agents (Document Extractor,
Event Classifier, Thesis Rewriter) using WHERE NOT EXISTS to never
overwrite user edits across reinstalls.
- agent_performance_log table: per-invocation metrics (duration,
confidence, retries, tokens, errors) linked to agent config.
API endpoints:
- GET/POST /api/agents — list and create agents
- GET/PUT/DELETE /api/agents/{id} — view, edit, delete (system agents
can be edited but not deleted)
- GET /api/agents/{id}/performance — aggregated metrics (success rate,
avg/p95 latency, confidence, token usage)
- GET /api/agents/{id}/performance/history — hourly time series
Frontend:
- AgentsPage with sidebar list + detail panel
- Agent detail: config display, system prompt viewer, performance
dashboard with metrics cards and time-series chart
- Edit form: all config fields editable including system prompt,
model, temperature, tokens, retries
- Create form: new user-defined agents with auto-slug generation
- System agents show blue badge, user agents show green badge
Migration 023 was deleting all but the latest trend_windows row per
entity before 024 could save them to trend_history. On reinstall,
this wiped the entire history every time.
Fixed by restructuring:
- 023 now creates trend_history FIRST and copies all trend_windows
rows into it before deduplicating trend_windows down to latest-only.
Uses NOT EXISTS to avoid duplicating rows on re-runs.
- 024 is now idempotent: ensures table/indexes exist and backfills
from recommendations (last 7 days, 1 point per ticker/window/hour)
to reconstruct approximate history even if trend_windows was sparse.
Both migrations are safe to re-run on existing databases.
- New 'intraday_bars' endpoint in PolygonMarketAdapter: fetches hourly
bars for today using range_bars URL with timespan=hour, sort=asc
- Scheduler expands intraday_bars global source into per-ticker jobs
for all active companies (every 15 minutes via polling_interval)
- Migration 025 inserts the intraday source with 900s cadence
- Frontend price matching uses closest-timestamp instead of date-string
matching, with 2h tolerance for intraday and 36h for daily windows
- Bumped market price fetch limit to 200 for intraday granularity
- New GET /api/market/prices/{ticker} endpoint serving OHLCV data from
market_snapshots, deduped by bar_timestamp
- New useMarketPrices hook in frontend
- Trend chart now shows price (purple line) on a right Y axis ($)
alongside trend metrics (%) on the left Y axis
- Custom tooltip formats price as dollars, metrics as percentages
- Price line uses connectNulls for days with missing bar data
Replaced Recharts default Tooltip with formatter prop (broken in
Recharts v3 with explicit type annotations) with a custom
TrendTooltip component matching the SQL Explorer pattern. Shows
each series name, value, and color on hover.
/api/patterns/{ticker} returns {ticker, patterns, count} but
useHistoricalPatterns typed its response as HistoricalPattern[].
The .map() call on the object caused 'e.map is not a function'.
Fixed by unwrapping resp.patterns in the hook's queryFn.
Trend charts blank:
- trend_windows uses upsert (1 row per ticker/window), so charts had
at most 1 data point. Added trend_history table (migration 024) that
appends every snapshot. New /api/trends/history endpoint serves the
time series. Frontend now uses useTrendHistory for charts and
useTrends for the latest summary card.
Competitor GUIDs:
- list_competitors query returned raw company_b_id UUIDs without
joining companies table. Added LEFT JOIN with CASE to resolve the
other company's ticker and legal_name. Updated Pydantic model to
include enriched fields. Frontend fallback changed from truncated
UUID to ticker/legal_name/Unknown.
- ID mismatch: API generated a throwaway UUID while BacktestReplay
generated its own internally. Frontend polled with wrong ID and
never found the DB row. Now pre-generate ID in endpoint and pass
it to BacktestReplay.
- Field name: API returned 'backtest_id' but frontend read 'data.id'.
Unified to 'id' everywhere.
- No polling: useBacktestResult fired once and never refreshed.
Added refetchInterval that polls every 2s while status is running.
- Response shape: GET endpoint nested results under 'result' object
but frontend expected flat fields. Flattened response to match
BacktestResult type.
- Added running/failed/completed status indicators in BacktestPanel.
Celes Renata