v0.1.19 — research that outlives the chat2026-11-05
Rolls up 299 commits / 116 merged pull requests since 0.1.18, plus 21
pull requests whose work landed through maintainer commits, from 26
contributors.
The headline is research that outlives the chat that produced it. A finished
analysis can be saved as a versioned research artifact with its evidence
references and data-as-of date, searched later, and revised instead of
overwritten; a follow-up turn or a later session finds the backtests already
run through listbacktestruns and reads their artifacts instead of running
them again; and a research goal's objective can be edited without losing its
evidence. Paper trading adds an opt-in A-share five-minute simulation that
settles a completed session bar by bar on a new order lifecycle, with
JoinQuant's limit-fill rules; saved accounts still settle daily. Gildata
financial queries, report-period stock screening and Shannon portfolio
diagnosis arrive as separate opt-ins for Gildata account holders, Gildata
quotes are used only when named, and the QVeris integration is removed.
Argentina (BYMA shares and CEDEARs) joins as a backtest market, web_search
can use Parallel's hosted search, and Codex OAuth lists the models the
signed-in account offers. Both 0.1.18 regressions are fixed: a retried
provider error no longer halts live decisions for the day, and a research
goal's answer that crosses its token budget is delivered. Most of the rest is
correctness: formula corrections to GTJA and Qlib alphas, futures contract
specifications and fees, loader paging and ticker forms, grounding of
document figures and their units, background tasks that belong to the session
that started them and survive a restart, and chat channels that no longer
call a voice transcriber that does not exist. The Web UI gets a new welcome
screen and a warm paper palette in light and dark.
Upgrading: a stored QVeris key is no longer read, and a GILDATA_TOKEN alone
no longer enables any Gildata feature. Pick the features in Settings → Data
Sources or VIBETRADINGGILDATA_FEATURES.
Added
- Versioned research artifacts (#2079, #2159, thanks @he-yufeng; closes
#1909, #2158). A finished analysis can be saved as an immutable revision
with its subject, universe, data-as-of date, evidence references,
verification status and optional hypothesis, goal, session or run links,
through the saveresearchartifact / searchresearchartifacts /
getresearchartifact agent tools, vibe-trading research-artifact
save|search|show|revision, /api/research-artifacts and a Web page in all
eleven languages. Passing an artifact_id appends a linked revision; the
subject and universe cannot change. Repeating identical content and
provenance returns the existing revision, and changed content or evidence
defaults to unverified: saving is not verification and does not make old
data fresh. The index lives in the runtime sessions.db unless
VIBETRADINGRESEARCHARTIFACTDB_PATH names another file; the idempotency
lookup is indexed (#2159). The REST save route accepts at most 1,000
evidence objects (1,000,000 characters serialized) and ids of at most 200
characters.
- listbacktest_runs finds the backtests earlier turns and sessions
already ran** (#2074, thanks @zeus229), so a follow-up reads their artifacts
with readrunartifact instead of re-running them. It lists runs from the
req.json and run_card.json the runtime already writes, newest first and
paged, with each backtest's absolute run_dir; the agent tool defaults to
the current session, the MCP tool to every run. Assistant replies in the
history carry [prev_run: <id>]. The grounding gate adopts a prior run read
this way only when its run card and metrics.csv agree and every table it
registers matches the run card manifest hash. The session filter is not an
access control (runs have no owner), and a run the model forged in an
earlier turn is not detected.
- A research goal's objective can be edited in place (#2093, thanks
@Shizoqua). updateresearchgoal (agent tool and session-isolated MCP
tool) replaces the objective or display summary while keeping the same goal
id, criteria and evidence, with an optional expectedgoalid stale-write
guard. Replacing the goal entirely is still startresearchgoal.
- Codex OAuth model discovery (#2080, thanks @zeus229). Web Settings lists
the models the signed-in ChatGPT account returns (entries marked
visibility: list, including OAuth-only ones) with their display names,
supported reasoning efforts and default effort, retrying once with a
refreshed token on a 401. A failed catalog request keeps the configured or
default model and manual entry available.
- Opt-in five-minute A-share paper steps (#2110, #2111, #2066, thanks
@shadowinlife and @Jackzigen). papertradestep (agent and MCP),
POST /api/paper-trade/step and vibe-trading paper step accept
interval="5m", plus optional session (auto / cna), pathmodel
(barmedian / barclose) and fillmodel (allor_none only). One step
settles one completed cn_a session bar by bar over its 48 continuous
five-minute bars from Tushare stk_mins: a market order fills at the first
bar whose checks pass, zero-volume bars never fill, an order blocked by the
price limit waits for a later bar and is rejected if still blocked at the
close, and unfilled day orders are cancelled at session end and listed in
canceled_orders. The 09:30 auction print is not matched; halts and
auction-window bars are reported in events. The measured provider budget
allows one symbol per step, only ordinary Shanghai/Shenzhen stocks have a
five-minute leg (no ETFs, indices or Beijing listings), and strategy mode
needs an explicit UNIVERSE. Such a call returns schema_version pt-v1.2
with an engine_fingerprint; a call without the new fields is
byte-identical to pt-v1.1. Saved paper accounts (CLI paper advance, the
REST advance route and the Web page) stay daily-only. Matching runs on a new
bar-agnostic order book (#2066) with replay-stable order ids and day-order
cancellation. Partial fills and volume participation remain open under
#1938.
- Five-minute limit orders follow JoinQuant's bar matching (#2127, thanks
@shadowinlife). A resting buy limit fills only when a bar's low trades
strictly below the limit, a sell only when its high trades strictly above
it, and the fill is at the limit price; a bar that only touches the limit
leaves the order resting. On the first traded bar, a reference price
already better than the limit fills at that price instead. Price-limit and
cash checks use the price the fill would execute at. The matching rules are
versioned pt-rules-v2, so a v1.2 result's engine_fingerprint differs
from one computed under pt-rules-v1 with the same bars and settings.
- A gateway address per local IBKR or Futu connection (#1983, thanks
@TerryF7). A local IBKR (TWS/Gateway) or Futu OpenD connection can store its
own host and port: through Host / Port on its card in the connection
center (saved, then tested), PUT /api/connections/{id}/endpoint, or
vibe-trading connector setup ... --host H --port P (both required). The
address is used for that connection's checks, portfolio reads and quotes
and by agent read tools given its connection_id, and the connection list
shows the effective endpoint. Only a hostname or IP is accepted (no scheme,
path or credentials), and other transports refuse an endpoint. Existing
broker configuration remains the fallback; order placement and paper/live
account checks are unchanged.
- BYMA backtests for Argentine shares and CEDEARs (#2071, thanks
@zeus229). .BA codes used to resolve to their market and then fail closed
in the runner; they now select a long-only, cash-only ARS engine on their
own (do not set engine; leverage other than 1 and `
v0.1.18 — lean runtime and reliability fixes2026-10-21
Same-day follow-up to 0.1.17: 12 commits (10 non-merge), no new external pull
requests. It ships the fixes made on main after 0.1.17 — mcp>=1.30 so the
HTTP MCP transport reclaims sessions, connect-time checks for custom model
endpoints (including fake-IP proxy hosts), grounding of run_dir/… refs and
signed amounts, Beijing codes in correlation, the macOS timeout fix and the
sdist contents — together with a leaner agent runtime: tool schemas load on
demand through load_tools, oversized tool results stay readable in the run
directory, Swarm sizes its context by the model window, and usage accounting
covers compaction, cancelled responses and failed streams. On the 0.1.17
pre-release verification prompt (DeepSeek V4 Pro, a 20/60 SMA backtest on
AAPL.US) a run took 7 model calls instead of 12 and 152K input tokens instead
of 706K, and reported the same figures.
Known issues
- A retried provider error (a connection reset or rate limit) can halt live
model decisions until the next UTC day, and a research goal's final answer
that crosses its token budget is discarded. Both are fixed on main (see
Unreleased) and ship with the next release.
Changed
- Reduce agent request overhead with on-demand tool schemas while keeping the
complete tool catalog and existing execution permissions. Ordinary backtests
no longer request extra attribution automatically. Automatic summary titles
remain available after the first chat exchange.
- Preserve oversized tool results in readable run artifacts and stop Swarm from
clearing new observations before the model sees them. Context pressure uses
the model window and includes tool schemas.
- README credits cover every cycle again: contributor lines for the
0.1.13, 0.1.15, 0.1.16 and 0.1.17 cycles in all seven READMEs, each PR
attribution checked against GitHub. The data-tools list counts the 29
read-only data tools the MCP server serves (it said 22). The 0.1.13 notes
below credit ModelScope (#1011) to @yrk111222 and #676 to the session
lifecycle entry it fixed.
Fixed
- Keep the custom-endpoint guard lazy-loaded for minimal installations and align
the Windows desktop MCP lock with the updated package requirement.
- Include compaction, cancelled responses and failed streams in usage accounting;
stop further work when a research goal exhausts its token budget. Forward the
configured output cap to both DeepSeek adapters.
- Redact credentials before tool results reach model context or replay caches,
and reject incomplete compatible-provider streams instead of releasing a
truncated answer or tool call.
- vibe-trading-mcp --transport http reclaims its sessions
(CVE-2026-59951 / GHSA-84m7-p3x7-pcfv). mcp is now >=1.30.0 instead of
capped below 1.30: an idle session closes after 30 minutes, at most 10,000
exist and an ended session is dropped, so a client can no longer grow
server memory without bound. 0.1.15–0.1.17 held the cap because 1.30's
RFC 8414 issuer check refused IBKR's OAuth metadata; IBKR's
protected-resource document now names the same issuer as its metadata
(checked 2026-10-21) and Robinhood's already did. The Docker lock pins
mcp 1.30.0.
- Custom model endpoints are checked again on every connection. Saving a
profile resolved its host once; a name that later re-resolved to a private
address (DNS rebinding), or a redirect to one, was not checked again. The
provider test and the running model now resolve each direct connection
once, refuse it unless every address is public and connect to the address
they checked (TLS still verifies the host name). When an environment proxy
carries the request the proxy resolves the name, so this check does not
apply there.
- Custom providers can be saved behind fake-IP proxies. Clash, Surge and
sing-box in TUN mode answer every lookup from 198.18.0.0/15, which 0.1.17
refused, so no custom provider could be saved on such a host. A looked-up
198.18.x address is accepted now (the proxy resolves the real name); the
same address written into the URL is still refused.
- Grounding reads the run's own files under the names models use. A
figures-block ref naming the active run as run_dir/… or by its directory
name (20261021_…/artifacts/metrics.csv) resolves to that run's
engine-written file, and a sign written before a currency mark
(−$1,847.78, (−$5.00), PnL: -$3.20) is the number's sign in both prose
and declarations. A live DeepSeek backtest report had its final value,
trade count and losing trade's PnL cut for these two reasons. Model-written
files and paths outside the run still never resolve, and a hyphen joining
two figures ($10-$20) or a spaced one ($10 - $20) is not a sign.
- **Correlation analysis puts bare Beijing, Shanghai-fund and B-share codes on
their exchange**. 920xxx resolved to .SZ, as did Shanghai 5xxxxx
funds and 9xxxxx B shares; the rule now matches the Tushare fallback's
(4/8/920 → .BJ, 5/6/9 → .SH, otherwise .SZ).
- A timed-out background command is reported as a timeout on macOS.
macOS answers EPERM rather than ESRCH when a process group holds only
exited, unreaped processes, so the final kill of a timed-out tree raised
and the task was marked error on a loaded host.
- Paper accounts say when nothing can be settled yet. Advancing an
account before its first session closed reported a date range that ran
backwards ("between 2026-10-21 and 2026-10-20"); it now names the first
execution date and the settlement time in the market's time zone.
- The sdist carries what its tests need: the test packages'
init.py files and CSV / JSON fixtures, and no untracked
teste2e.py harness.
v0.1.17 — paper accounts, and a value that cannot be computed says so2026-10-21
Rolls up 638 commits / 228 merged pull requests since 0.1.16, plus 41 pull
requests whose work landed through maintainer commits, from 33 contributors.
The headline is daily paper trading. A papertradestep tool for the agent
and MCP, and saved paper accounts through vibe-trading paper,
/api/paper-accounts and a Web page, match orders or a strategy against
completed daily bars without ever reaching a broker; saved accounts move
forward only. Most of
the rest of the cycle is correctness, and much of it has one shape: a value
that cannot be computed now says so instead of turning into a plausible
number. A profit factor with no losing trade, an undefined correlation, a
factor benchmark with too few IC observations, an upside at a zero price and
an unbounded ratio come back as null or a refusal rather than 0; a missing
price no longer bridges a return pair, a VaR transition or a lag pair; an
after-close SEC filing no longer reaches the IC a bar early; and a misspelled
backtest setting is reported in the run card instead of silently ignored.
Brazil (B3) joins as a market, the Alpha Zoo grows from 462 to 478 factors,
Slack and Discord join the guided channel setup, scheduled reports can
arrive by Email as HTML or a password-protectable PDF, token usage shows in
Run Detail, chat and swarm, a claude-cli provider runs the agent on a local
Claude Code login, and the Web UI adds Persian and Turkish for 11 languages.
Added
- Daily paper trading with saved accounts (#1939, thanks @shadowinlife). A
new papertradestep agent and MCP tool matches explicit orders, or the
per-day orders of a strategy file, against completed daily bars for cn_a,
hk and us; nothing in it can reach a broker order path. The same
stateless step is served as vibe-trading paper step and
POST /api/paper-trade/step. Saved paper accounts are built on it and
reachable three ways: vibe-trading paper create|list|show|history|advance,
authenticated REST under /api/paper-accounts (list, create, read,
history, POST .../{id}/advance) and a Paper trading page in the Web
sidebar in all eleven UI languages.
An account starts from the cash and positions you enter, today or at the
next session, and moves forward only: an advance settles sessions whose
regular close is at least 30 minutes past and carries the revision it read,
so a stale or concurrent request is refused (HTTP 409 over REST) instead of
committing twice, and a failed step leaves the ledger unchanged. Ledgers
live in <runtime_root>/paper-trading/accounts.db; there is no background
scheduler. A strategy under <runtime_root>/strategies/ runs in a child
process that sees only bars strictly before the execution day and the ledger
after earlier fills; orders fill at that day's close, and any strategy
failure discards the whole call. Matching is daily-close and all-or-none,
with simplified fees, price limits, board lots and A-share T+1. Execution
prices must be raw: adjusted or unknown price calibers and non-finite prices
are rejected, A-shares need a complete ClickHouse trading calendar, and a
split-like jump returns PAPERDATANOT_READY rather than rescaling
holdings. Corporate-action reconciliation and cash dividends are not
modelled and NAV is not total return; intraday, margin, options and
cross-market phases remain open under #1938.
- Live runner model calls have their own cadence and daily budget
(closes #1854). Safety checks still run every minute, but a model
decision now defaults to every 15 minutes, each in a fresh conversation,
with at most 26 decisions and 1,000,000 reported tokens per broker per
UTC day; an optional once-daily time, timezone and operator-priced USD
limit are set in Runtime → Model schedule and spending limits, the chat
runner panel, vibe-trading connector runner-settings or
GET/PUT /live/runner/settings. Spending history survives restarts.
Limits are checked after each provider response, so one response can
overshoot; estimates ignore cache discounts and auxiliary calls and are
not a provider billing cap. Exhaustion or missing usage trips the
existing kill switch and its cancel/flatten behaviour, and a decision
left unfinished by a crash is blocked for inspection.
- Strategy adaptation runs from preparation to evidence. A registered
strategy with adequate, non-stale evidence can be adapted to a new name,
universe, date window and position sizing through adapt_strategy (agent
and MCP), vibe-trading strategy-evidence adapt, authenticated POST
/api/strategy-adaptations and a Web welcome prompt. The SDM child keeps the
parent's signal, entry and exit definitions and gets its own run directory,
SignalEngine and backtest; it never inherits parent metrics. Refreshing with
scope=strategies (strategy-evidence refresh --scope strategies, or POST
/api/strategy-adaptations/evidence) replaces only the named strategies'
evidence, and refuses an adapted run unless its config, code, metrics,
equity and trades match the hashes sealed in its run card. The hash binds
evidence to the persisted run; it does not certify that the generated code
implements its description.
- extraETF holdings exports feed the portfolio, with allocation proposals.
vibe-trading portfolio import-extraetf, POST
/api/portfolio/imports/extraetf and **Portfolio → Manage accounts → Import
extraETF Investments** store an Investments CSV as a local source. The whole
import fails on an unreadable row, a holdings count that differs from the
one you confirm, a missing price, a future file time or an export older than
the freshness limit you choose; transactions, dividend and X-Ray exports are
refused. Portfolio ID keeps accounts apart when they hold the same ISIN.
Totals are exported quantity × price and exclude cash and assets absent from
the export. EUR joins USD, CNY and HKD as a display currency, valued at
Frankfurter reference rates whose date is shown apart from the fetch time.
An allocation proposal (portfolio rebalance --snapshot-id, POST
/api/portfolio/rebalance, portfoliosummary(snapshotid=...,
target_weights=...), or the Web page) shows value changes for target
percentages that total 100%; it creates no orders, quantities, tax or fee
estimates, and an incomplete snapshot or stale cached rates cannot produce
one. Imported holdings stay out of historical risk tools until their trading
venue is resolved.
- Portfolio research can stay on one snapshot (#1769, thanks @zeus229).
portfoliosummary returns snapshotid and read_identity and accepts a
snapshot_id back, so a multi-step analysis keeps reading the same stored
observation after a later refresh. vibe-trading portfolio show
--snapshot-id ID and GET /api/portfolio/analysis-context?snapshot_id=
read the same way, and the Web Portfolio page exports the sanitized research
snapshot it displays as JSON. An unknown snapshot, one valued under an older
valuation version, or one containing a source that is no longer enabled is
reported as unavailable and never replaced by newer data.
- mStock (India) read-only connector (#1675, thanks @Jackzigen). The
mstock-live-rest-readonly profile sends only GET requests for the Type B
holdings, net-position and fund-summary resources, with the API key and
current session token kept in the connection's OS credential vault; it never
logs in, refreshes a session or calls an order endpoint, and both order
entry points refuse before any network call. Holdings and net positions stay
separate books. Fund limits are shown raw because they are not cash or net
liquidation, so the profile withholds account.read and is not a portfolio
source. connector account and connector positions gain
--connection-id. Tests replay the documented reply shapes; no real mStock
account was available.
- **Five ex
v0.1.16 — a number that can show where it came from2026-09-29
Rolls up 492 commits / 116 merged pull requests since 0.1.15, from 16
contributors.
The theme of this cycle is a number that can show where it came from. The
final-answer grounding gate stopped guessing what a number is from the words
around it: the model declares each figure's role — observed, derived,
proposed, cited or count — the gate checks that declaration against the
session's tool evidence, and a figure that fails is cut from the answer
instead of the whole answer being refused. A backtest's own output (its
Sortino, turnover, weights and Monte Carlo p-values, not only its Sharpe)
now grounds the report written about it, run cards cite a metric only where
the saved CSV agrees, and the generated broker matrix states each profile's
permissions as declarations rather than as runtime verification. Research
runs stopped losing what they fetched: compaction follows the model's real
context window instead of a fixed 40K estimate that began clearing tool
results from the third step. The missing-data sweep reached 59 more alphas:
15 qlib158 count factors, 20 that filled a missing input with a constant
and 24 comparison gates. Argentina (BYMA), weekly and monthly bars, Bahasa
Indonesia, Gildata, OpenCode, Email and WebSocket channels and four broker
connectors (KIS, Upbit, Toss Securities, Scalable Capital) land alongside.
Added
- Stock profiles carry the listing's own identity (#1577, thanks @Shizoqua).
getstockprofile returns a listing block beside the issuer's
fundamentals: Yahoo's symbol, exchange, quote type and quote currency, plus
the financial currency and underlying symbol when Yahoo declares them. A
secondary listing no longer reads as the primary one. GOOGL.BA is an ARS
line in Buenos Aires carrying Alphabet's USD financials, and GGALD.BA is a
USD line whose issuer reports in ARS. Nothing is inferred from the ticker.
- Volume statistics in technicalindicators** (#1571, thanks @zeus229). The
tool returns the latest volume, its 20-bar mean and their ratio, computed from
the bars it already fetched. The mean needs a complete 20-bar window.
volume.unit is the unit the serving source declares (board lots on the
A-share sources, shares on the Yahoo family, null when undeclared), because
the two are 100x apart and nothing in the numbers tells them apart.
- Argentina (BYMA) market data (#1543, thanks @zeus229). A .BA symbol — a
BYMA listing or a locally traded CEDEAR — is its own market ar_equity,
quoted in ARS, served by yahoo → yfinance → local, and reported as
market ar by getstockprofile. Execution is deliberately not modelled: an
Argentine backtest raises instead of borrowing US or crypto commissions, lot
sizes, settlement and short-selling rules. The Web UI carries the market too —
Settings source priority, the positions asset-class grouping and the sector
union — and with it ukequity, vietnamequity and index, which had been
missing from one or more of those three since they landed. EnvConfig.data's
per-market MARKETDATAORDER_* fields are now guarded against
FALLBACKCHAINS instead of a hand-written list, which is why ukequity
never had one.
- Weekly and monthly bars (#1479). getmarketdata and backtests take
1W and 1M (and 1w / 1wk / 1mo). Loaders are still asked for daily
bars; loaders.base.resample_bars builds the period bar at the three fetch
boundaries (runner, market data, benchmark), so a weekly bar is the same
whichever source served the days, at that source's daily caliber. A week
runs Monday to Sunday, a month is a calendar month, and each bar is dated on
the last trading day inside it: first open, highest high, lowest low, last
close, summed volume and amount, volume-weighted vwap, mean funding rate.
Annualisation is 52 / 12; a weekly perpetual bar settles 21 funding periods.
1M is matched before any case fold, which read it as one minute in
strict-100x validation and in attribution (98,280 bars a year). The
technical-indicator tool canonicalises its documented 1wk / 1mo and
fetches whole periods instead of two days per bar.
- IM channels are configured from the Web UI (#1520, #1529; #1519, #1530,
thanks @shadowinlife). The Settings panel renders each built-in channel's
fields from backend metadata, masks secrets (**** plus the last four
characters, never sent back), tests the unsaved form against the provider
(ok / invalid_credentials / network / unsupported), and hot-swaps only
the saved channel with no restart. DingTalk and QQ have guided setups; a
shared token probe backs both. Saves write channels.<name> in
~/.vibe-trading/agent.json atomically at mode 0600; a YAML config is shown
read-only. Reloads of one channel are serialized in ChannelManager, and
stop_all cancels a reload's start that is still connecting.
- Email and WebSocket join the guided Web UI channel setup (#1544, after
#1519, thanks @shadowinlife). Both channels get hand-written field metadata —
localized labels, masked secrets — plus connection tests and per-channel hot
apply. Email's test probes the real IMAP login, mailbox select and SMTP login
without ever sending a message; WebSocket is a server channel with no remote
credentials, so its test validates the TLS cert/key material and binds every
resolved address locally — an address held by the already-running server reads
as the expected state, not a failure. Saving a WebSocket config hot-swaps the
server: connected clients (including the Web UI chat) briefly disconnect and
reconnect. A hand-written field hint's secret flag is now authoritative for
the keys it covers — the regex fail-safe still masks every unhinted key — so
token-shaped non-secrets such as websocketrequirestoken stay visible and
editable instead of being masked, and a form save can no longer silently flip
the stored token requirement. The web config routes now build the WebSocket
adapter with the gateway services it requires; previously every WebSocket save
or test failed validation. Email's polling loop also skips stale-config
delete/move post-actions once a stop or hot swap begins, while the
already-fetched batch is still delivered. Both the probe and the polling loop
now send an RFC 2971 IMAP ID after login: NetEase mailboxes
(163/126/yeah.net) accept the login but reject the first SELECT with Unsafe
Login until the client identifies itself, so without this the Email channel
could not read the most common Chinese mailboxes. The identification is static
and carries no user data or secrets, and servers that ignore ID are
unaffected; verified end-to-end against a live 163.com account.
- Bahasa Indonesia UI locale and README_id.md (#1482, thanks @Yoruxyv).
The README count tests cover it, and MANIFEST.in now ships README_es.md
and README_id.md.
- Portfolio valuation accepts any ISO-4217 currency (#1510, thanks
@zeus229). A source whose currency has no FX rate fails with the currency
named and is excluded from the totals; the healthy sources stay in.
- Gildata (恒生聚源) joins the A-share fallback chain as a token-gated source
(#1474, thanks @sambazhu). The new gildata loader talks to the vendor's
raw-api MCP endpoint (one JSON-RPC POST per call, token in the Authorization
header) and serves A-share daily OHLCV through the StockDailyQuote tool with
restorationStatus=1 — forward, split-AND-dividend adjusted bars, stamped
split_dividend in the price-caliber table after being measured against a
live payload. Volume arrives in 万股 and is converted to shares (volume_units:
shares); avgprice/prevcloseprice are ignored because the vendor keeps
them on a different adjustment basis than the adjusted OHLC. An unresolvable
symbol answers rows: [] (never an error), so the chain keeps walking. Auth
is GILDATA_TOKEN (Settings page f
v0.1.15 — data that says what it is2026-09-09
Rolls up 551 commits / 162 merged pull requests since 0.1.14, from 35
contributors.
The theme of this cycle is data that says what it is. A price frame now
carries the adjustment caliber it was served under. A factor propagates the
gaps in its inputs instead of filling them. A loader that cannot serve a
market no longer claims it, and a source that fails to refresh is an error
rather than a smaller portfolio. Three of those were the same bug wearing
different clothes: a default that silently substitutes a plausible value for
a missing one, which is indistinguishable downstream from a real
observation. Three new markets, a fourteenth broker and fifteen Quant
Library additions land alongside.
Added
- UK equity market (#1206, thanks @cgycorey) — LSE .L and .IL
symbols end to end: market data, Yahoo-backed financial statements and
indicators, trade-journal inference into uk_equity, and its own engine
path. SDRT is modelled as what it actually is — a 0.5% duty on the
purchase side only, not a symmetric round-trip cost. Charging both
sides overstated the cost of every round trip by half, which is exactly
the size of edge a mean-reversion strategy lives on.
- Zerodha Kite Connect (#1193, thanks @ashutoshsinghpr7) — a fourteenth
broker connector for Indian equities. Kite exposes no runtime paper/live
discriminator — no account-id format, host separation, demo flag or trade
environment — so under the red line it is capped at paper plus read-only:
placeorder and cancelorder hard-refuse any non-paper config at the
first line, and no *-live-trade profile exists to select. That now
covers Longbridge, Dhan, Shoonya and Zerodha; Trading212 goes further and
refuses all order placement including paper.
- Read-only multi-broker portfolio (#1072, thanks @goatyyc; onboarding
contracts in #1250) — one aggregated snapshot across every enabled
connection instance, reachable four ways: the Web /portfolio page, REST
under portfolioroutes.py, the portfoliosummary agent tool, and
vibe-trading portfolio show | refresh | sources. Three design points
that are not incidental: a source that fails to refresh is an **error
excluded from the totals (status error, lastsuccess_at,
complete=false), never a carried-forward cache, so a partial snapshot
cannot read as a smaller portfolio; every remote_mcp read passes
interactive_oauth=False, so aggregation can never pop an auth prompt;
and analysiscontext() carries riskxrayargs so portfoliorisk_xray
is fed rather than reimplemented. Eligibility is one rule —
isportfolioconnectionprofile requires readonly and** account.read
and positions.read — under which the IBKR official-MCP profile, which
advertises only discovery, is correctly not a portfolio source.
- Quant Library, fifteen additions (thanks @santhreal) — Heston (1993)
stochastic volatility option pricing (#1195); Hierarchical Risk Parity
allocation (#1196); Archimedean and Gaussian copula analytics (#1197);
market-microstructure analytics — VPIN, Roll spread, Amihud illiquidity,
Kyle's lambda (#1198); analytical single-barrier options with cash-rebate
handling (#1163) plus finite-difference sensitivity Greeks for them
(#1203); an ISDA standard-model single-name CDS valuation engine with
hazard-rate conversions (#1164); Key Rate Duration decomposition across
benchmark tenors (#1165); the Vasicek credit portfolio loss model and
spread DV01 (#1167); cross-sectional factor Information Coefficient time
series (#1166); Ornstein-Uhlenbeck exact calibration with half-life
(#1161); drawdown distribution analytics with the Ulcer and Pain indices
(#1162); Corrado rank and Cowan generalized sign non-parametric
event-study tests (#1160); multi-factor risk decomposition with Euler
marginal contributions, reporting unmatched_weight rather than
normalising it away (#1159); and group-purged k-fold cross-validation for
panel data (#1168). The layer's rule holds throughout: a formula has
exactly one implementation, and skills import it rather than carrying the
source in a SKILL.md code block.
- Brazilian Portuguese locale (#1327, thanks @nandofmike) — the eighth
shipped language, landing with full key parity. The parity suite globs
locales/*.json instead of listing languages, so a new locale is covered
the day its file lands; German had previously shipped with perfect parity
and zero coverage because that list was hand-written.
- Nobitex and Wallex (#1263, thanks @Emad211) — read-only Iranian
exchange sources on keyless public UDF endpoints, explicit-source only.
Both sit in NONETWORKFALLBACKSOURCES and are barred from the crypto
fallback chain on purpose: they are the only Toman-quoted sources and
declare markets={"crypto"} purely to be reachable, so degrading an
unavailable BTCIRT request into that chain would hand back a
USDT-quoted series as if it were Toman.
- Binance USD-M evidence path (#1229, #1230, thanks @honginp; #1248,
thanks @lorenzozanee) — read-only USD-M account snapshots, drift evidence
artifacts comparing simulated fills against recorded ones, and
deterministic tolerance calibration derived from those recordings rather
than assumed. The point is that the tolerance has a provenance: it is
measured against real fills, not chosen.
- Offline evals harness (#1271, thanks @AirHua-byte) — verifies a run's
persisted artifacts (prompt preservation, tool calls and results,
identity, evidence, provider usage, iteration budget, RunManifest
integrity) against a versioned case/verdict schema, with no LLM, network,
broker or MCP call: it reads files only. Absent instrumentation emits
NOT_EVALUABLE rather than passing, which is the whole point — a missing
field must not read as good behaviour.
- Anthropic prompt caching (#1366, thanks @averatec0773) — an explicit
cache breakpoint on the system block so the static tools+system prefix is
read from cache instead of resent at full price, with cache usage recorded
in the usage envelope. Native adapter only, behind
VIBETRADINGANTHROPICPROMPTCACHE; set it to 0 if a compatible proxy
rejects the cache_control request parameter.
- Per-market data-source priority (#1231, thanks @sambazhu) — a Settings
card and MARKETDATAORDER_* env overrides that reorder a market's
fallback chain. Validated as a multiset permutation of the default, so
reordering passes while adding, dropping or duplicating a source is
refused and the default stands. The override is applied as a setitem on
the same dict object, because runner.py and market_data.py import
FALLBACK_CHAINS by name and a rebind would leave them on the old order.
- Calendar-triggered partial rebalancing (#1277, thanks @thisisjun786)
and a data window separated from the evaluation window, so warm-up
bars stop counting as evaluation and a strategy is not graded on the bars
it needed to become defined.
- Agent-confirmed scheduled research (#1187, thanks @AirHua-byte) and
each monitor's latest verdict rendered on the job list (#1156, thanks
@he-yufeng), so a recurring job's state is legible without opening it.
- Swarm replay and retry (#1158, thanks @cgycorey; vibe-trading swarm
retry --resume in #1194, thanks @SiMinus) — resume a failed or cancelled
DAG run while keeping the artifacts of tasks that already completed,
rather than paying for the whole graph again.
- Order-plan rejection reporting (#1245, thanks @lorenzozanee) — an onplan_rejected hook plus a run-level report of
the trades the engine wanted but could not take. A rejected plan
previously vanished, so a strategy that was being silently throttled by
buying power looked identical to one that simply had no signal.
- Read-only Binance-connector crypto identity (#1242, thanks
@pengpengyi92) and public venue-ca
v0.1.14 — a backtest you can read, and Intel Macs that can install2026-08-20
Rolls up 272 commits / 74 merged pull requests since 0.1.13.
Added
- Options Lab (#1096, closes #1095, thanks @shadowinlife) — a Web UI page
with four surfaces: expiry payoff diagram, spot×IV scenario P&L matrix,
portfolio Greeks cards, and a live US options chain. The math is not new: two
read-only HTTP endpoints wrap the existing options_payoff /
getoptionschain tools, so the page and the MCP surface compute from the
same test-pinned src/quantlib/options.py. Research only — it places no
orders.
- Factor Research tab in Run Detail (#1099, thanks @shadowinlife) — IC
statistics cards, the daily IC series with its mean line, quantile-group
equity curves, and an IC correlation heatmap, all rendered from the
factor_analysis artifacts a run already writes. The new read-only
GET /runs/{run_id}/factor endpoint scans the run's artifacts/ tree and
computes the pairwise IC time-series correlation matrix, which existed
nowhere before; a hasfactorartifacts flag gates the tab so runs without
factor output do not show an empty panel.
- Positions tab in Run Detail (#1097, closes #1098, thanks @shadowinlife) —
portfolio-book structure from the existing positions.csv: a per-symbol
weight pie/treemap with a date slider, sector and asset-class net-exposure
bars, and a weight-evolution stacked area. The pie is gross composition
(absolute weights including shorts and cash) while the bars are net
exposure per industry, so a long/short pair in one sector nets to zero on the
bars while both legs stay visible on the pie. The two charts answer different
questions on purpose.
- Tearsheet tab in Run Detail (#1091, closes #1090, thanks @shadowinlife) —
monthly-returns heatmap (years × months with a full-year column), annual
returns bar chart, top-5 drawdown table, and an equity curve annotated with
the ranked drawdown zones. Everything is derived client-side from the
equity.csv rows the run response already carries: no backend change, no new
dependency, and month axis labels come from Intl.DateTimeFormat rather than
per-locale month keys.
- Interactive backtest research dashboard (#1084, thanks @AndyLongest) — an
optional report-style view for a completed backtest alongside the existing
candlestick and trade-detail views: headline return/risk/trading KPIs,
normalized equity versus benchmark, drawdown with rolling Sharpe, realized
trade P&L, a trade ledger, and the complete metric table. CLI backtests get a
quiet local report-server bootstrap so Full Report routes to the dashboard
without a manual server step.
- Strategy Discovery (#978 Phase 1 and #1007 Phase 2, refs #969, thanks
@shadowinlife) — a read-only facade answering "what strategies exist and what
state are they in?" across the Alpha Zoo and the SDM strategy store, with
per-(strategy, regime) evidence rows rather than scenario tags. Ships
liststrategies / querystrategies / getstrategyevidence as agent and
MCP tools behind an evidence gate (minimum-trade, coverage and
cost-breakeven thresholds, each with an explicit warning), plus a startup
guard that drops the routing text when any advertised tool is not actually
registered. Phase 2 adds the population path — refreshstrategyevidence
as an agent tool, an MCP wrapper and
vibe-trading strategy-evidence refresh --manifest — with the
backtest-diagnose Hard-Gate Checklist as the ingestion gate (stable
hard-gate:* skip tokens) and atomic rebuilds. Freshness is computed at read
time from the evidence-window age (fresh/aging/stale); stale rows fail
closed out of default recommendations behind an include_stale opt-out, and
sdm:* rows mirror the SDM lifecycle.
- Scheduled research now delivers itself. A finished briefing leaves the
run through an outbox rather than waiting to be read: the outbox row is
claimed under a lease before sending so a crash mid-delivery cannot double
post, the send is wired to both the session and the channel runtimes, and the
push happens on the terminal event. Delivery is configured and watched from
Market Watch.
- Each monitor's latest verdict is persisted on its job (#1152, refs #943,
thanks @he-yufeng) — the run's terminal briefing is parsed server-side into a
structured last_verdict record and the /scheduled-runs list carries it
inline, so the list renders a verdict without re-parsing free text per row or
going N+1 on sessions. The five research playbooks grow a strictly additive
## Verdict tail — one - SYMBOL: STATE - reason line per tracked symbol,
each playbook declaring its own state vocabulary. Parsing is deliberately
strict: an ad-hoc prompt lands permanently at noverdictsection and renders
as nothing rather than a warning, a run that tracked nothing is a real "no
calls" answer rather than an absence, and a malformed section degrades to
contract_violation instead of showing a wrong verdict. The prior record is
embedded one level deep at write time and no deeper.
- Futu connector — seven extended read-only endpoints (#1135, thanks
@549236606-oss) closing the gap between what the SDK exposes and what the
connector consumed: get_rehab (dividend/split/rights adjustment factors, so
backtests stop reading dividend gaps as price moves), getcapitalflow
(historical super/big/mid/small inflow buckets), getcapitaldistribution
(today's in-flow versus out-flow snapshot), gethistorydeals (fill records
for true cost-basis reconstruction, capped at the SDK's 360-day window),
getacccashflow, getfinancials (income/balance/cash-flow statements),
and getearningscalendar with EPS and revenue consensus. Each routes
through the same quotectx / tradectx / assertgateway envelope as
the original five, so missing data, missing privileges and a missing OpenD all
degrade to a clean fail-closed payload instead of an SDK stack trace. The
futu-api SDK stays lazily loaded.
- Vietnam equities (HOSE) as a backtest market (#1033, thanks @ngoanpv).
.VN matched no entry in MARKETPATTERNS, so detectmarket fell back to
a_share and executed Vietnamese bars under China A-share rules — and asking
for Yahoo explicitly did not help, because both Yahoo loaders gated on suffix
and rejected .VN before building the request. .VN now resolves through the
Yahoo loaders with a ["yahoo", "yfinance", "local"] fallback chain and runs
on a dedicated VietnamEquityEngine.
- Offline USD-M account reconciliation (#1106, relates #1030, thanks
@honginp) — immutable Binance USD-M account and position snapshot contracts
that compare an exchange observation against the existing AccountState and
RiskSnapshot without mutating either, reporting numeric, structural,
missing-symbol and unexpected-symbol drift deterministically. Liquidation-engine
validation is explicitly left unassessed rather than silently assumed. This is
the Shadow 1 slice: contracts and fixture-only offline reconciliation.
- Novita AI as a built-in OpenAI-compatible provider (#1059, thanks
@jax-novita) — registered in the provider registry with NOVITAAPIKEY /
NOVITABASEURL and wired through capabilities, CLI onboarding,
.env.example and the README provider list, so it is selectable from the
built-in list instead of hand-configured as a custom endpoint.
- GitHub Copilot as a provider through the official github-copilot-sdk
(#990, supersedes #899, thanks @sykuang), with SDK-managed authentication from
COPILOTGITHUBTOKEN, GHTOKEN, GITHUBTOKEN, stored Copilot CLI
credentials or gh credentials, plus LangChain-compatible invoke, streaming,
reasoning and tool-call handling and Settings/preflight integration. This
implements the boundary #899 was closed on: no borrowed OAuth client ID and no
editor-impersonation headers.
- **tickerall
v0.1.13 — The grounding repair, a finance-math layer, and institutional research2026-08-10
v0.1.13 — The grounding repair, a finance-math layer, and institutional research
pip install -U vibe-trading-ai
408 commits and 162 merged pull requests since v0.1.12 (2026-07-22) — the largest release to date, from 35 contributors. Full detail in CHANGELOG.md.
---
🛡 The headline is a fix, not a feature
The single most user-visible defect in the 0.1.12 line: a well-formed question would spend minutes on real tool calls and then refuse to answer, returning
> 当前无法安全确认标的身份或价格证据,因此没有生成交易结论。请确认候选证券代码和交易所后再继续。
> (cannot safely confirm instrument identity or price evidence)
The identity/grounding gate was rejecting answers it already had the evidence for. Seven independent root causes, each now fixed and covered by two-sided guard tests (healthy samples must pass; bad samples must still be blocked) plus mutation tests:
| # | Root cause | Effect |
|---|-----------|--------|
| 1 | .SS and .SH treated as different instruments | Every Shanghai ticker was permanently ambiguous |
| 2 | A+H dual listings and bare HK codes collapsed to ambiguous | Dead end instead of a shortlist |
| 3 | Yahoo returns HTTP 400 for every CJK query; recorded as a source failure | Escalated to blocking invalidated instead of "not listed here" |
| 4 | A failed side query could demote an already-locked identity | Sticky aggregate status with no recovery |
| 5 | A hardcoded per-tool whitelist decided which bare tickers could match | 11 of the 17 documented argument spellings were blocked (3/14 → 14/14 after the fix) |
| 6 | Source and currency had to be written in ASCII | Chinese answers rejected for writing 雅虎/腾讯, or 元 instead of 人民币 |
| 7 | A thousands separator split the clause mid-number | ¥1,309.22 compared as 1 against the observed range → false price conflict |
Conceptual questions with no instrument at all, and comparison reports, no longer dead-end either.
A quote outside recorded OHLC evidence is still refused. The gate got more precise, not weaker — that is the point of the two-sided tests.
Verified end to end against a real LLM, real tools and real network: a 600519.SH query that previously took 6m14s and ended in the canned refusal now answers in 7–9s with zero rejections; 茅台 in 14s; a knowledge question in 14s.
This also closes the narrower cases from the 0.1.12 line — numbers that were never prices (confidence scores, indicator readings, moving-average windows, year-less dates like 8/5, percentage ranges, and a trading plan's own trigger levels, where close ≥ 6.45 is a condition rather than a quote) — and makes a many-candidate shortlist count as an answer rather than a stalled resolution (#1001, #983, #955).
---
🧮 src/quantlib — a tested finance-math layer
265 tested functions across 19 modules — every module the tool allowlists now exports. Skills now import these instead of carrying formulas inside markdown code blocks — if you find a pricing formula living in a SKILL.md, that is a bug, not a pattern.
| Module | Coverage |
|--------|----------|
| options | Black-Scholes price + greeks, implied-volatility inversion |
| fixedincome | Bond math, Nelson-Siegel / Svensson curve fitting |
| credit | Altman Z-score, Merton / KMV distance-to-default |
| timeseries | Stationarity, cointegration, GARCH, bootstrap |
| risk · var_backtest | VaR / CVaR / EVT and their backtests |
| attribution | Brinson-Fachler decomposition |
| performance · fundmath | TWR / MWR / Modified Dietz; XIRR / MOIC / DPI / TVPI |
| factormodel · eventstudy | Factor regressions, event studies |
| multipletesting · crossvalidation | Deflated significance, purged CV |
| impact | Market-impact models |
The read-only quantlibcall tool reaches all of it through one contract, so the finance math works on the CLI, the Web UI, the REST API and MCP — including deployments where bash is gated off. It is structurally not a shell — module allowlist, all-only dispatch, export refused. Econometrics needs the stats extra; those functions lazy-import and name the missing one.
---
💰 Valuation engine
A valuation engine that refuses to invent its own inputs. The one rule in contracts.py: a missing input makes a model NOT RUNNABLE and is never silently defaulted — every default in a valuation model is an opinion wearing a constant's clothes.
- rundcf** — FCFF bridge, WACC build, mid-year discounting, net-debt bridge, WACC×g sensitivity grid. Dual terminal value: each method is cross-checked against the other's implied multiple and implied g.
- runcomps — EV bridge, LTM + calendar-year calendarisation, multiple matrix. A peer with a non-positive denominator is excluded and reported**, never averaged in as a negative multiple.
- threestatement — linked projection with a hard balance assertion, an explicit revolver plug, and an iterated interest↔debt circularity that must converge or raise.
Artifacts are input-hashed and versioned, with xlsx / pptx export.
---
🏛 Institutional research
Six slash commands — /comps /dcf /attrib /memo /earnings /screen — each carrying a step skeleton and an arithmetic-consistent worked example: the Brinson decomposition sums exactly to active return, and the earnings bridge sums exactly to the EPS delta.
Investor lenses become a standalone skill: named-investor reasoning frameworks as stackable analysis overlays, decoupled from the data layer. Each lens is an operating procedure — priority signals, disqualifying conditions, typical misuse — not a biography, and names no tool.
Five ready-to-schedule research playbooks (premarket brief, earnings-season tracker, portfolio checkup, A-share money flow, institutional-holdings diff), reachable three ways: auth-gated REST routes, a vibe-trading playbook CLI subcommand, and a /playbook slash command. Templates state their data needs in natural language rather than naming tools, so coverage can grow without editing them, and every one mandates naming a missing input instead of filling it from memory.
---
📊 Four new read-only data tools — all on free public sources
- getinstitutionalholdings — SEC 13F-HR books in manager / ticker-holders / top-managers modes, with quarter-over-quarter position diffs for factor use. Cover-page totals carry value_units + basis, because pre-2023 filings report in thousands.
- etfholdings — cross-market look-through. SEC N-PORT for US; for A-shares the semi-annual/annual reports carry the full book, not the quarterly top ten: 510300 returns 342 rows covering 98.66% of net assets versus 10 rows / 22.74%. coverage separates fullportfolio from topndisclosed, and every response stamps the report period — a full book is always the older disclosure.
- predictionmarket — event-contract search / event / market / history, with prices converted to implied probability and the unit labelled**, so downstream never reads 0.63 as dollars. Read-only by construction: no order path.
- researchpapers** — arXiv + OpenAlex search/read with source-anchored claim extraction. Anything not literally present in the source is left empty and marked not stated in source, and a paper's claimed performance is never presented as our backtest result.
---
🧾 Governance wired into every run
- A run manifest hashes the prompt, the skill contents, the tool registry and the package versions — so "what methodology produced that number?" is answerable a month later.
- The audit ledger chains each record to its predecessor's hash and fsyncs. Editing or deleting a record is detectable, and an edit that recomputes its own hash is still caught one record later via prevhashmismatch. Timestamps are always caller-supplied; no module here calls `da
v0.1.12 — Correlation regime timeline, three new providers, MetaTrader 5 + reliability wave2026-07-22
🌀 v0.1.12 — Correlation regime timeline, three new providers, MetaTrader 5 + a reliability wave
v0.1.12 rolls up nearly two weeks of work since 0.1.11 (2026-07-10) — the headlines: a correlation regime timeline that answers "when did the market fuse into one bloc, and are we in that state now?", three new LLM providers plus catalog-based endpoint resolution that makes every provider work with just a key, the MetaTrader 5 (Exness) broker connector (12 brokers), the Strategy Development Manager skill, Binance USD-M perpetuals with historical funding, and a broad reliability wave — strict-JSON/finite hardening, session/journal robustness, an 80× vectorization, and the native zai streaming fix.
This release is available on PyPI, ClawHub, and GitHub Releases.
``bash
pip install -U vibe-trading-ai
or
uv tool install --reinstall vibe-trading-ai
`
Highlights
🌀 Correlation regime timeline
A new additive GET /correlation/regime endpoint and an opt-in "Regime timeline" strip on the Correlation tab (#756, closes #719, thanks @ebujinovch). It reuses the same price data /correlation already fetches: rolling pairwise correlations reduce to an edge-density scalar per bar (the fraction of asset pairs whose |ρ| clears a threshold), the series is causally smoothed (trailing window — never reads the future), and a two-threshold hysteresis state machine marks contiguous FUSED episodes, with a dead band that suppresses chatter. It shares /correlation's auth + rate-limit budget, floors the window so short timelines can't return empty, and is explicitly descriptive risk context, not a trading signal. Backed by the correlation-regime skill (#557).
🔌 Three new LLM providers + robust endpoint resolution
Native adapters for SiliconFlow (CN + Global, #565, thanks @UNHNQ), iFlytek Spark (#537, thanks @FenjuFu), and the native Anthropic Messages API (#695, thanks @jelech; pip install "vibe-trading-ai[anthropic]"), plus MiniMax regional endpoints (#731, thanks @octo-patch). Underneath, provider credentials are resolved through one centralized path (#563, thanks @shadowinlife), and two long-standing rough edges are fixed (#758): when no BASEURL is set, the backend now falls back to each provider's canonical catalog endpoint (the same default Web Settings already used) instead of silently defaulting to api.openai.com — so a provider works with just a key — and an endpoint that streams zero chunks falls back to a non-streaming invoke rather than erroring, with an HTML-error-page hint when a base URL is misconfigured.
📈 MetaTrader 5 (Exness) connector + mt5 data source — 12 brokers
A first-class MetaTrader 5 broker connector (#481, thanks @StaniellG) — full read surface plus order placement against a locally running terminal, with a bidirectional identity guard (paper profile ⇔ demo trademode, login pinned, contest rejected) and connector-level maxordervolume / maxordernotionalusd caps on demo AND live. The live mandate gate gains forex/cfd instrument vocabulary and a lot-aware sizing hook so USD caps bind on lot-sized orders (0.1 lot EURUSD ≈ $10,800, never 0.1 × quote). The mt5 loader heads the forex fallback chain (broker-exact symbols with Exness suffix discovery, 1m–1D bars). Broker connectors: 11 → 12; market-data sources → 23.
🧬 Strategy Development Manager
sdmregister / sdmstatus / sdmdecayscan turn academic papers and broker research into registered factors and strategies (#457, closes #455, thanks @shadowinlife), backed by a persistent SQLite artifact store (UNIQUE(name, universe)) and automated IC/Sharpe decay monitoring driving an active → monitoring → decayed → disabled lifecycle. Ships with pluggable OCR for read_document (local RapidOCR by default; cloud Qwen-VL is explicit opt-in only, never auto-selected).
₿ Binance USD-M perpetuals
Explicit BTC-USDT-PERP routing with execution/mark price separation (fail-closed when the two aren't timestamp-synchronized) and historical funding settlements (#470/#716, thanks @honginp). Maintenance brackets are decoupled from the live authenticated fetch and supplied as a validated, content-hashed artifact instead (#757), so a plain -PERP backtest stays zero-credential — the regression where every perp fetch required a Binance API key is gone.
👁️ Pluggable OCR + LLM-vision extraction
readdocument gains a pluggable OCR engine architecture with optional LLM-vision extraction** and a configurable text-density threshold (#548, thanks @shadowinlife) — local by default, cloud engines opt-in only, never auto-selected.
🧰 Platform & safety
- Look-ahead-bias fix across all five portfolio optimizers (#487, thanks @YZY0108) — weights executed at a bar's open no longer include that bar's close-to-close return. Plus realized portfolio turnover metrics for every optimizer (#478, thanks @Robin1987China).
- Security hardening — all 10 findings from the 2026-07-10 external audit closed (#476): AST-hardened backtest sandbox, short-lived SSE auth tickets, hardened Compose, /correlation auth + rate limiting, security headers, hash-locked dependencies, and SHA-pinned Actions.
- 80× signal-alignment vectorization (#698, thanks @shadowinlife) and swarm MCP tool-discovery caching (#704) cut wall-clock on wide panels and multi-worker runs.
- Opt-in TAP mode for Alpaca (#377, thanks @0xZKnw), IBKR thread-local connection pool + snapshot quotes (#636, thanks @MikeCer), Robinhood accountnumber wiring (#726, thanks @nareshkps), the Requesty gateway provider (#474, thanks @Thibaultjaigu), and user swarm-presets discovery** (#570, thanks @darkknight4563).
- Two new academic factors — Frazzini-Pedersen betting-against-beta (#480, thanks @YogeshModi24) and academiccorrrewire (#705, thanks @ebujinovch): Alpha Zoo 460 → 462 across 5 families.
🛠️ Reliability & correctness wave
- Strict-JSON / finite-number hardening across the backtest + tools stack (thanks @santhreal) — risk ratios stay finite when equity crosses zero (#765) or annualizes an explosive path (#739/#740); scalar metrics (#766), factor IC std (#767), and pattern trend-slope (#764) emit strict RFC-8259 JSON (null, never NaN/Infinity); Black-Scholes helpers treat non-positive spot/strike as intrinsic (#744).
- Session / journal robustness — one corrupt session.json (#762) or schema-bad messages.jsonl line (#763) no longer aborts listing/reading; Excel float-stringified A-share codes (#770), unicode-dash PDF page ranges (#769), export KEY= dotenv lines (#768), and yahoo 1m bars (#761) all parse correctly.
- Broad reliability — cancellation is honored before the first AgentLoop iteration (#641, closes #638), a frontend insertBefore streaming DOM-race is fixed (#717, thanks @Marnie0415), the composite engine falls back for unknown symbols (#734), codex stream HTTP failures are classified for correct retry (#663), and #584 (thanks @xkam7ar) closes a batch of packaging/web/scheduler/swarm/CLI issues.
🙌 Contributor cycle
~90 correctness/reliability fixes and features from a wide contributor cohort — @santhreal (a 30-PR correctness sweep), @xkam7ar (reliability + QVeris hardening), @shadowinlife (SDM, OCR, vectorization), @ebujinovch (regime timeline), @honginp (Binance perps), @StaniellG (MetaTrader 5), and many more. Full per-person credits live in the README Contributors section and the CHANGELOG. Thanks also to @GabbaTauchi for the zai bug report (#758).
Install / upgrade
| Channel | Command |
|---|---|
| PyPI | pip install -U vibe-trading-ai |
| uv tool | uv tool install --reinstall vibe-trading-ai |
| ClawHub (Claude Desktop / OpenClaw / MCP clients) | clawhub install vibe-trading` or update the
v0.1.11 — India equity, fundamental factors, IM channels + roll-up2026-07-10
🇮🇳 v0.1.11 — India equity, fundamental factors, IM channels + roll-up since 0.1.10
v0.1.11 is a roll-up of three weeks of work. The headlines: Indian equity (NSE/BSE) becomes a first-class backtesting market, a PIT-safe fundamental factor layer brings the Alpha Zoo to 460 alphas across 5 families, the IM channel runtime delivers research through 16 message adapters, and scheduled research runs end to end. Around them ship an optional QVeris premium data track, the completed apiserver modularization, centralized env config with a CI gate, a Trading 212 read-only connector (11 brokers), a turnover-aware portfolio optimizer (5 optimizers), an analyzeimage vision tool, and a long tail of contributor fixes.
This release is available on PyPI, ClawHub, and GitHub Releases.
``bash
pip install -U vibe-trading-ai
or
uv tool install --reinstall vibe-trading-ai
`
Highlights
🇮🇳 Indian equity (NSE/BSE) as a first-class market
A dedicated IndiaEquityEngine (#305, thanks @muku314115) models the market as it actually trades: T+1 delivery, no overnight shorts (opt-in intraday), configurable circuit bands, 1-share lots, and a config-driven STT / stamp-duty / exchange / SEBI / GST cost stack. .NS/.BO symbols route through yahoo → yfinance → indiabroker → local, where indiabroker is an opt-in read-only Shoonya/Dhan bar bridge, and 255 alpha101/qlib158 factors are opted into the new equityin universe. Backtest engines: 7 → 8; market-data sources: 19 free + QVeris = 20**.
💎 Fundamental factor layer, Phase 1 — PIT-safe SEC fundamentals
SEC company facts now flow into dense daily fund: factor panels the same way price data does — filed-date anchoring (you only see what was public that day), a first-filed restatement policy, true-quarter (start, end) frame selection with Q4 synthesis so YTD/annual frames can't contaminate TTM, and rolling TTM aggregation. On top: a getfundamentals tool and 4 quality/value factors in a new fundamental zoo family. With the 4 canonical academic alphas from earlier in the cycle (#277, thanks @Robin1987China — Jegadeesh reversal, George–Hwang 52-week high, Amihud illiquidity, Harvey–Siddique co-skewness), the Alpha Zoo grows 452 → 460 across 5 families.
💬 IM channel runtime — research delivery over 16 adapters
The same agent session runtime now attaches to 16 built-in message adapters — WebSocket, Telegram, Slack, Discord, Matrix, WhatsApp, Signal, QQ/NapCat, WeChat/WeCom, Feishu, DingTalk, email, MS Teams, MoChat — dependency-gated with install hints, configurable via AgentConfig.channels, and controllable from REST (/channels/*), CLI (vibe-trading channels ...), and Web Settings, in all 5 UI locales. This release also fixes the first-image papercut: inbound media now lands under ~/.vibe-trading/uploads/<channel>/, inside the agent's allowed file roots (#465, thanks @fei-moss), and NapCat private messages trigger pairing codes (#463).
⏰ Scheduled research, end to end
A default-off background executor (VIBETRADINGENABLESCHEDULER) fires due interval/cron jobs through the session runtime (#278, thanks @mvanhorn), on top of a crash-safe atomic job store, auth-gated /scheduled-runs routes (tests in #452, thanks @Robin1987China), a Reports library, and post-backtest attribution. Combined with the Research Autopilot Phase 3 loop closure (#267, thanks @Robin1987China) — scaffoldsignalengine → linkautopilot_backtest — hypothesis → signal-engine → backtest → schedule now runs without a human in the middle.
💰 Optional QVeris premium data track
The 19 free sources stay the default. An explicit-only paid mode (Settings → QVeris or vibe-trading data mode paid) unlocks 63+ providers behind 3 key-gated tools (qverissearch / qverisinspect / qveris_execute) with preview-by-default and a session budget gate. QVeris never enters auto-fallback: no key, no cost, no surprise.
🧰 Platform & safety
- apiserver modularization completed** — 1,103 → 371 lines (#424 closing #331, thanks @shadowinlife) after a cycle of route slices.
- Centralized env config — one Pydantic EnvConfig schema + an AST CI gate that rejects raw os.getenv outside the config layer (#440, thanks @shadowinlife).
- Trading 212 read-only connector (#321, thanks @mvanhorn) — 11 brokers. No runtime paper/live discriminator → placeorder/cancelorder hard-refuse every order, paper included. Plus an opt-in PreTradeAdvisoryInterface that records advisory reviews without bypassing the mandate gate.
- Security: loopback CSRF protection (#293), SSRF-guard hardening for CGNAT/mesh ranges (#389), Pillow/langchain CVE floor bumps (#390), tightened dev defaults.
- Turnover-aware optimizer (#466, thanks @Robin1987China) — 5th optimizer: mean-variance utility with an L1 penalty on weight changes, so the portfolio trades only when improvement outweighs churn.
- analyzeimage` vision tool (#464, thanks @fei-moss) — semantic chart/screenshot reads through the session model (vision-capable model required). Tools: 72 free-mode / 75 with QVeris**.
- Manifest count guards (#461, thanks @asahikiko) — packaged SKILL.md capability counts are now asserted against source in CI.
🙌 Contributor cycle
60 contributor-authored PRs merged since 0.1.10 (73 total). Full per-person credits live in the README Contributors section and the CHANGELOG — highlights: @shadowinlife (12 PRs incl. the api_server capstone), @Robin1987China (autopilot P3, academic alphas, shadow-account conditions, turnover optimizer), @muku314115 (India equity), @mvanhorn (scheduler, Trading 212), @fei-moss (vision tool + IM fixes), @sambazhu (value-investing toolkit), and many more.
Numbers at 0.1.11: 8 backtest engines · 460 alphas / 5 families · 86 skills · 30 swarm presets · 20 data sources · 72 free tools (75 paid) · 54 MCP tools · 11 broker connectors · 16 IM adapters · 5 optimizers.
v0.1.10 — Global data layer + roll-up since 0.1.92026-06-19
🌍 v0.1.10 — Global data layer + roll-up since 0.1.9
v0.1.10 is a roll-up release. The headline is the Global data layer: the market-data registry grows from 10 to 18 sources and gains 18 read-only data tools that reach past OHLCV into fundamentals and flow, all exposed over MCP. Around it ships everything accumulated since 0.1.9 — 10 broker SDK connectors, the Alpha Zoo alpha compare full stack, a provider-reliability overhaul, Research Autopilot Phase 1, an opt-in local data cache, and a community-driven security-hardening wave.
This release is available on PyPI, ClawHub, and GitHub Releases.
``bash
pip install -U vibe-trading-ai
or
uv tool install --reinstall vibe-trading-ai
`
Highlights
🌍 Global data layer — 18 sources + 18 read-only data tools
The loader registry grows from 10 to 18 market-data sources:
- Free, no key — tushare, okx, yfinance, akshare, baostock, tencent, mootdx, ccxt, futu, local, plus four new direct-API additions: Eastmoney, Sina, Stooq, and a direct-HTTP Yahoo client.
- Optional key-gated US providers — Finnhub, Alpha Vantage, Tiingo, FMP; absent keys are skipped in the fallback chain, never crash it.
Fallback chains are re-ordered by IP-ban risk (lightweight, throttle-tolerant public endpoints lead; key-gated REST trails) behind a shared throttled HTTP gate (backtest/loaders/http.py) with per-host rate buckets, jitter, and session reuse. On top sit 18 read-only data tools — fund flow, dragon-tiger board, northbound (Stock-Connect) flow, margin trading, block trades, shareholder count, lockup expiry, sector membership, research reports, news, SEC filings (EDGAR + XBRL), financial statements, options chains, institutional holdings, full-market screening, symbol search, FRED macro, and iwencai natural-language A-share search — across A-share / US / HK, all exposed over MCP. Three shared clients (eastmoney / yahoo / secedgar) back the loaders and tools, and a consolidated data-routing index plus per-source eastmoney / sec-edgar skills document the layer.
💱 10 broker SDK connectors — read + paper, mandate-gated live
Trading is connector-first: pick a profile, and paper/live is an attribute of the connector. This release brings the roster to 10 brokers — IBKR (local read-only TWS/Gateway) · Robinhood (Agentic MCP, OAuth) · Tiger · Longbridge · Alpaca · OKX · Binance · Futu · Dhan · Shoonya (India NSE/BSE + F&O). Direct-SDK connectors share a brokersdk transport and each does read + paper-account order placement; live placement passes a single fail-closed bounded-autonomy gate (sdkordergate.py: mandate + kill switch + audit). Brokers with no runtime paper/live discriminator (Longbridge, Dhan, Shoonya) are structurally capped at paper + read-only — their placeorder / cancel_order hard-refuse any non-paper config at the first line. Order-placing tools stay off MCP (agent + CLI only).
📊 Alpha compare across CLI / REST / Web / agent tool
vibe-trading alpha compare ranks any set of Alpha Zoo factors by IC / IR on your universe, sharing one comparerunner.comparealphas core behind the CLI, a POST /alpha/compare REST route with SSE-streamed progress, the Alpha Zoo Web UI Compare view, and a read-only alphacompare agent tool. A runbench(only=…) subset filter benches only the compared factors instead of the whole zoo.
🔌 Provider-reliability overhaul
A provider capability layer gates reasoning capture/replay, Gemini thought signatures, Kimi user-agent, and OpenRouter reasoning bodies per provider. vibe-trading provider doctor prints a redacted diagnostic snapshot. Streaming failures now raise an explicit, redacted ProviderStreamError (carrying statuscode + .retryable) with one retry for transients and fail-fast on 4xx; a throttled reasoningdelta SSE drives a "Reasoning…" liveness indicator in the Web UI. Also: an optional native DeepSeek adapter (VIBETRADINGDEEPSEEKADAPTER), read-only tool hard-timeouts (VIBETRADINGTOOLTIMEOUT_SECONDS), and per-provider temperature handling (Kimi-k2 forced to 1.0, MiniMax clamped > 0).
🔬 Research Autopilot Phase 1
runresearchautopilot turns a hypothesisid into a research goal (thesis as objective, backtest-relevant acceptance criteria, next-step hints), and generatebacktestconfig auto-writes a backtest config.json from the hypothesis's universe and data sources — so the agent goes straight from idea → signalengine.py → run.
🗃️ Opt-in local data cache + local loader
VIBETRADINGDATACACHE=1 caches settled bars to ~/.vibe-trading/cache (user home, never the repo); a staleness guard never caches a range ending today, and cached frames are byte-identical to live fetches. A new local loader reads OHLCV straight from your own CSV / Parquet / DuckDB** files via ~/.vibe-trading/data-bridge/config.yaml, with normal fallback-chain support.
🛡️ Security & hardening wave
A community-driven hardening pass: API settings-write auth (#245), agent shell-tool opt-in (#243), loopback-host rebinding rejection (#242), explicit local-shutdown auth (#241), and identifier containment for mandate proposal-ids (#256), persistent-memory types (#257), and MCP swarm run-ids (#258). Plus responsive Stop mid-stream + SSE reconnect on returning to a running session (#229), multi-engine web_search fallback (#231), and Gemini thoughtSignature round-trip through OpenAI-compat tool calls (#176, #184).
🪪 Version reporting is now consistent
--version, the REST API (/docs + /api), the MCP server handshake, and the Web UI footer all derive from one source — the REST API had drifted to a wrong hardcoded 5.0.0. Packaging also now ships skill example scripts in the wheel, and the Docker image installs weasyprint's native libs so PDF reports render.
Install / upgrade
| Channel | Command |
|---|---|
| PyPI | pip install -U vibe-trading-ai |
| uv tool | uv tool install --reinstall vibe-trading-ai |
| ClawHub (Claude Desktop / OpenClaw / MCP clients) | clawhub install vibe-trading or update the installed skill |
| Docker | docker compose pull && docker compose up -d |
Remote API/Web deployments should set APIAUTHKEY and explicit trusted CORS origins. Local CLI and localhost Web UI workflows remain low-friction.
By the numbers
- ~98 non-merge commits since v0.1.9
- 18 market-data sources with auto-detect + ban-risk-ordered fallback
- 66 agent tools (auto-discovered) · 54 MCP tools
- 79 bundled finance skills
- 29 swarm presets
- 10 broker connectors (read + paper, bounded-live for those with a structural paper/live guard)
- 7 backtest engines + composite cross-market engine + options portfolio
- 4167 backend tests passing (the weasyprint shadow-report PDF suite is green on CI; it segfaults only on macOS/conda without Pango)
- Clean-room verified: a fresh pip install of the 0.1.10 wheel imports all new loaders/tools, and the wheel + sdist ship the eastmoney / sec-edgar skills including UTF-8 Chinese reference filenames
🙌 Credits
Code contributors this cycle
- @warren618 / Haozhe Wu — the global data layer (8 sources + 18 read-only data tools, 3 shared clients), the 10 broker SDK connectors + bounded-autonomy order gate, the alpha-compare full stack, the provider-reliability overhaul, multi-engine web_search` fallback, responsive Stop + SSE reconnect, multi-language READMEs, integration, release.
- @Hinotoi-agent — a security-hardening wave: explicit local-shutdown auth (#241), loopback-host rebinding rejection (#242), agent shell-tool opt-in (#243), settings-write auth (#245), mandate proposal-id containment (#256), persistent-memory type validation (#257), MCP swarm run-id containment (#258)
- @mvanhorn — the opt-in local data