Two unrelated features bundled because they ship together and share
migration 0028.
Strategic-log feedback (thumb up/down):
- New strategic_log_feedback table with UNIQUE(log_id, user_id) so each
user has one vote per log, flippable in place (up -> down -> clear).
UI shows aggregate counts only.
- app/services/log_feedback.py: set_vote, get_counts, sign/verify
feedback tokens (same itsdangerous pattern as auth.sign_pending,
30-day TTL for email links).
- POST /api/log/{id}/feedback: web vote, auth required, returns counts
+ the requesting user's own vote.
- GET /feedback?token=...&vote=...: email-link target, no auth, signed
token encodes (user, log, vote), renders feedback_thanks.html.
- partials/log.html: thumbs row below content, JS-driven swap via the
POST endpoint. Dashboard latest-log card and /log page both render
this partial via htmx, so the buttons appear in all three surfaces.
- digest emails: a "How was today's read?" row above the unsub footer,
with signed-token URLs against the latest StrategicLog at send time.
Plain-text fallback included.
Reviewer self-score (0-10):
- _SYSTEM_PROMPT asks for an integer score with anchors (10 exemplary,
5 borderline, 0 unfit). Verdict gains score: int | None.
- Deterministic-layer hits get score=0 (hard rule, no nuance);
error rows get None; LLM rows get the model's score clamped 0..10.
- ReviewerVerdict.score, StrategicLog.reviewer_score, and
IndicatorSummary.reviewer_score all new SMALLINT NULL columns.
- ai_log_job + indicator_summary_job persist verdict.score onto their
content rows when committing the row alongside content.
Tests:
- tests/test_strategic_log_feedback.py: vote, flip, clear, aggregate
across users, invalid vote, token round-trip + tamper + garbage +
'clear' not signable for email path.
- tests/test_output_review.py: score parsing, clamping (>10, <0),
missing/non-numeric -> None, deterministic-layer score=0.
Full suite: 427 passed (was 412), 5 skipped, no regressions.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Implements docs/read-markets-compliance-changes.md as flag-gated changes
(no deletions) so paused features stay in the tree for future re-enable.
All four flags default False so a fresh deploy is compliance-safe.
- New env flags: PORTFOLIO_AI_ENABLED, PORTFOLIO_SYNC_ENABLED,
TICKER_UNIVERSE_AGGREGATE_ENABLED, SUBSCRIPTIONS_ENABLED.
- Gates: /api/analyze, /api/portfolio/sync*, /api/stripe/*, /pricing,
ticker_universe writes, portfolio_analysis.analyse(). is_paid_active()
returns True for any auth'd user when subscriptions are paused.
- Prompts (PROMPT_VERSION 10): universal _COMPLIANCE_RIDER prepended to
every system prompt; watch list removed; price-target / close-above-below
/ trigger / forward-state-as-description rules added; SPECULATIVE
pivoted to regime-only scenarios; daily + weekly digests tightened.
- Reviewer: deterministic regex/lexicon pre-check fail-closed under the
Haiku call; portfolio rider gated by PORTFOLIO_AI_ENABLED; base prompt
sharpened for forward-state and MAR forward-opinion patterns;
ReviewerVerdict audit table; generate_with_review retry helper.
- Migration 0026: purge portfolio_sync + ticker_universe; create
reviewer_verdicts.
- Copy: MAR cite fixed to Art 3(1)(35) + Art 20 + Del Reg 2016/958;
portfolio reframed as browser-only viewer in disclaimer / privacy /
terms / about / pricing / landing (en + it). TODO(legal) marker for
lawyer sign-off on disclaimer.
- Tests: 13 lexicon + 6 reviewer compliance regressions; conftest enables
all flags so existing 402 tests still cover their code paths.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Extends the reviewer agent — previously only protecting indicator
summaries — to every AI-generated surface that reaches a user. The
reviewer's prompt already rejects scratchpad, truncation,
meta-commentary, and (since a6e476b) financial advice; wiring it in
turns those rules from prompt-level "asks" into structural gates.
Four call sites updated:
- ai_log_job.run() : after each tone/analysis variant is generated,
pass through review_read. On reject, log the reason and skip the
StrategicLog insert; the API's existing "latest StrategicLog" lookup
falls back to the previous clean log.
- services/portfolio_analysis.analyse() : on reject, raise a clean
RuntimeError that the /api/analyze router already maps to HTTP 502
with a retry-able message. Portfolio analysis isn't cached server-
side, so the user retries; the reviewer's verdict reason goes into
the AICall ledger as the leaked-status row's error column.
- routers/chat.chat() : on reject, instead of returning the raw
assistant content we return a short refusal explaining the limit
and inviting a rephrase. Adds ~1-2 s of latency per turn (one extra
LLM call to Haiku) — the only user-facing latency tax.
- jobs/email_digest_job._generate_variants() : on reject, the variant
is dropped for the cycle. Recipients on the rejected tone get no
digest email this run, which is better than delivering inbox copy
that drifts into advice (emails are unrecallable once sent).
In every case the AICall ledger row records the reviewer cost so
month_spend stays accurate across all paths.
The reviewer system prompt is slightly generalised to cover both the
indicator-summary case and the longer-form log/digest/chat case:
- removes "short interpretive read" framing
- softens the "any question" rule so genuine rhetorical structure in
a long-form log doesn't trigger a reject
tests/conftest.py grows an autouse fixture that stubs review_read to
clean=True in every consumer module. Tests that mock the generator
shouldn't have to also mock the safety gate behind it; tests that
specifically want the reject branch can override with their own
monkeypatch. test_output_review.py is unaffected — it imports
review_read directly.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Previously translate_log_for_active_languages and
translate_summary_for_active_languages added every successful
translation to the session and called session.commit() once at the
end. A single bad row (DB error, constraint violation, encoding
mismatch) rolled back the whole batch — losing all the languages that
had succeeded.
Wrap each row in session.begin_nested() so a per-row failure only
loses that one row. Track succeeded/failed counts and log them at the
end — escalating to error if zero succeeded out of N attempted, so
total failure surfaces in monitoring instead of just N warning lines.
openrouter.py was 790 lines mixing two orthogonal concerns:
- Prompt engineering (build_system_prompt, build_summary_*,
build_chat_*, build_daily_digest_*, etc.) — ~400 lines, changes
weekly as PROMPT_VERSION bumps
- LLM transport (call_llm, _provider_chain, _call_provider, retry
+ fallback machinery) — ~250 lines, rarely changes
Extracted the prompt-engineering surface to app/services/llm_prompts.py.
Transport stays in openrouter.py (consistent with the filename — the
OpenRouter URL is the transport's anchor).
All import sites (jobs, routers, services, tests) split their
multi-import lines into two: prompt-things from llm_prompts, transport
from openrouter. PROMPT_VERSION constant, _TONE_ALIASES, _resolve_tone,
and SYSTEM_PROMPT moved with the prompt functions.
No behaviour change — pure relocation. Function signatures, body, and
naming all preserved.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Three recently-added tables (strategic_log_translations,
indicator_summary_translations, csv_format_templates) drifted from
the codebase's existing naming convention:
- llm_model -> model
- llm_cost_usd -> cost_usd
- content_md -> content (on the two translation tables; csv_format
doesn't have a content field)
Also added prompt_tokens and completion_tokens to the three tables;
they were silently dropped at write time despite LogResult exposing
them.
All writer call sites (ai_log_job, indicator_summary_job,
llm_csv_parser) and reader call sites (api.py localized helpers)
updated to match. Tests realigned.
Migration 0025 uses batch_alter_table for SQLite compatibility.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Server no longer holds portfolios. Holdings live in the browser
(localStorage); the server publishes an anonymous ticker_universe and a
gzipped /api/universe payload identical for every authenticated user, so
access patterns can't betray which tickers a user holds. AI commentary
is generated ephemerally from the browser-supplied pie and the cost
ledger row records no positions. Migrations 0009-0011 added the
universe table and dropped positions / portfolio_snapshots /
portfolios.
Authentication is now e-mail OTP only. Migration 0010 dropped
password_hash and email_verified (every active session is by
construction proof of email control). The /signup endpoint is gone;
signup and login share a single email-entry page. Email rendering is
HTML+plain-text multipart with a shared brand palette (app/branding.py)
asserted in sync with the CSS by a drift-detection test.
LLM provider defaults to DeepSeek-direct (cheaper, api.deepseek.com)
with OpenRouter as automatic fallback if DeepSeek fails. ai_log_job and
indicator_summary_job now iterate the two tones (NOVICE, INTERMEDIATE)
per cycle so the dashboard's tone toggle is instant; PROMPT_VERSION
bumped to 6 with an educational anti-TA / anti-gambling stance baked
into _CORE. NOVICE mode renders a curated glossary inline (CBOE VIX,
yield curve, HY OAS, etc.) with JS-positioned tooltips that survive
viewport edges and sticky bars. Model name and tokens hidden from the
user UI; still recorded in StrategicLog.model and AICall for admin.
Layout adds a sticky top nav, a sticky bottom markets bar (one chip per
exchange with status LED + headline index + 1d change), and
Phase H feedback reporting is queued in tasks/todo.md.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two changes that together cut OpenRouter spend ~50% and give the daily
log temporal awareness.
1. CadencePolicy (app/services/cadence.py): expensive AI jobs only
fire hourly during the EU/US active window (Mon-Fri 07-21 UTC).
Off-hours weekdays throttle to every 4h; weekends to every 12h.
ai_log_job and indicator_summary_job both consult the policy before
doing real work; market/news/portfolio ingest jobs stay hourly
(cheap, no API cost). Skipped runs land in job_runs with status
'skipped' and the throttle reason in error.
2. Update mode for ai_log_job: when an earlier log exists for the
current UTC day, it's passed to the model as 'Earlier log from
today (generated HH:MM UTC)'. The system prompt grows an Update
mode section instructing the model to revise — not restart — and
anchor on what has CHANGED since the earlier draft. The TL;DR
leads with intra-day change when meaningful, the watch list evolves
rather than restarts. PROMPT_VERSION bumped to 5.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Containerised macro-strategy dashboard: 4-panel web UI (indicators,
portfolio, flash news, AI strategic log), MariaDB store, hourly
ingestion jobs, OpenRouter-backed AI analysis.
Ports the four prototype scripts in the parent dir (market_pulse,
flash_news, trading212, strategic_log) into async services backed by a
persistent DB and served via FastAPI + Jinja2 + HTMX. APScheduler runs
as a separate compose service for crash-safety and easier restarts.
Portfolio composition + position names come live from Trading 212;
news per-ticker headlines reuse those names. Tone (NOVICE/INTERMEDIATE/
PRO) and analysis style (DRY/SPECULATIVE) are env-configurable and
stored on each log row so historical entries show what produced them.
Default model is deepseek/deepseek-v4-flash (overridable via env).
Light/dark theme toggle, sans-serif for prose surfaces, monospace for
data. Bearer-token auth, OpenRouter monthly cost cap, RSS feeds auto-
disabled on consecutive failures.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
