--swarm-run was declared nargs="+" but the handler silently dropped
every token after the second, and a non-JSON vars argument died with a
bare "Invalid JSON". Extra tokens now fail fast naming the dropped
values, and JSON errors report the offending string, the parser error,
correct usage, and a shell-quoting hint.
Closes#428
Reverts merge commits 0b867a7 (#405) and 474f5e4 (#416), and removes the
now-orphaned #406 artifact metadata store (src/reliability + tests, zero
references left outside its own tests).
Why: the stack wrapped the tool registry in every session path (even
governance mode=off) without exposing the registry surface AgentContext
reads, breaking all session-runtime chats within a day (#433, #431). It
also modified protected core files (src/agent/loop.py, src/session/
service.py), shipped 12 internal-convention docs/ files into the public
tree, and its enforcement layer already has reported bypass paths (#420).
Trading safety stays on the single mandate-gate design (#31, #144).
README news entries for 2026-07-07/07-06 updated accordingly.
`vibe-trading dev` previously assumed the user had already run
`vibe-trading setup`. When they hadn't, the Vite spawn failed with
npm's confusing "vite is not a command" message and the user had to
know to install dependencies separately.
Add a quick `frontend/node_modules/.bin/vite` (or vite.cmd) existence
check before spawning. If missing, fail fast with a clear panel that
points the user at `vibe-trading setup`.
Signed-off-by: digger yu <digger-yu@outlook.com>
Add ``vibe-trading setup`` and ``vibe-trading dev`` to fix the
cross-platform frontend build / dev workflow.
The Windows npx tsc footgun (npm pulls the abandoned ``tsc@2.0.4``
package from the registry) is solved by always invoking tsc via
``npm exec --package=typescript tsc -b`` on Windows. POSIX uses the
standard ``npm run build`` since npm prepends ``./node_modules/.bin``
to PATH for local scripts.
``dev`` launches the backend from ``AGENT_DIR`` (so ``python -m
cli._legacy serve`` resolves the in-repo ``cli`` package) and the
Vite dev server with the port from ``vite.config.ts`` (5899, not the
5173 we used to hardcode). Both children receive SIGINT/SIGTERM and
are force-killed after a 5 s grace period.
On Windows, ``subprocess.Popen`` does not consult ``PATHEXT``, so the
npm path is taken from ``shutil.which`` (which returns the ``.cmd``
form) and used directly — without this, ``Popen(["npm", ...])``
raises ``FileNotFoundError`` even when ``which`` succeeds.
argparse subparsers are registered in ``_legacy.py``; typer
commands ``setup`` / ``dev`` are registered in ``main.py``'s
``_build_typer_app()``. ``init`` behavior is unchanged.
Tests: ``agent/tests/test_cli_setup_dev.py`` covers platform-aware
build commands, the node/npm-missing path, the dev 5899-vs-5173
regression, and the AGENT_DIR-cwd regression. The existing
``cmd_live_authorize`` flow (OAuth handshake) is untouched.
Signed-off-by: digger yu <digger-yu@outlook.com>
The connector authorize OAuth handshake timed out before the token was
persisted (#259). Two root causes:
1. The OAuth flow is driven lazily by the list_tools discovery request,
which is bounded by the per-call tool_timeout (default 30s), not
init_timeout. The prior fix widened only init_timeout, so a Robinhood
face-scan sign-in (>30s) still tripped the handshake.
2. The 30s timeout was retried, and the retry opened a fresh client
context that started a SECOND OAuth callback server on a new port,
orphaning the sign-in the user had just completed.
Fix:
- cmd_live_authorize now raises BOTH tool_timeout and init_timeout to a
configurable authorize deadline (VIBE_LIVE_AUTHORIZE_TIMEOUT_SECONDS,
default 300s), raise-only so a larger user value is preserved.
- The authorize handshake runs a single non-retried list_tools attempt
via build_mcp_tool_wrappers(..., max_list_tools_attempts=1), so a
transient failure cannot spawn a duplicate OAuth flow.
- _run_with_retry takes a configurable attempts cap; runtime/registry
callers keep the default 2 (one transient retry) unchanged.
Closes#259
Signed-off-by: Robin1987China <41602358+Robin1987China@users.noreply.github.com>
Completes work the 2026-06-18 self-merged batch left half-applied:
- Tighten the mandate proposal_id relay/preview parsers in api_server.py
and cli/_legacy.py to the strict mp_[0-9a-f]{32} format already enforced
by commit.py (#256), so the relay and the commit gate agree on format.
- Document the MCP initTimeout config key (shipped in #263) in README and
wire its base-default passthrough in config/loader.py.
- Add the registered pytest.mark.unit marker to test_mandate_commit_security.py.
A cluster of provider reports traced to one root: every OpenAI-compatible
provider shared a single shim that applied DeepSeek/Kimi/Gemini quirks
globally and silently swallowed stream failures.
- Provider capability layer (capabilities.py): reasoning capture/replay,
Gemini thought signatures, Kimi User-Agent (version from package
metadata), OpenRouter reasoning body — gated per provider, no
cross-contamination
- Optional native DeepSeek adapter via VIBE_TRADING_DEEPSEEK_ADAPTER
(auto/native/openai-compatible) + 'deepseek' extra (langchain-deepseek)
- ChatLLM.stream_chat: silent fallback to chat() removed; failures raise
ProviderStreamError with redacted provider/model context; one retry for
transient errors in AgentLoop + swarm worker (deterministic 4xx fail fast)
- Empty model response diagnosed as empty_model_response instead of
'reached max iterations'
- reasoning_delta SSE event (throttled to 1/s, first chunk immediate) +
frontend 'Reasoning…' indicator; reasoningActive reset on safety timeout
- SSE heartbeats carry no replay id; replay falls back to full buffer on
unknown last-event-id; read-only tools get a hard timeout
(VIBE_TRADING_TOOL_TIMEOUT_SECONDS) instead of hiding behind heartbeats
- 'vibe-trading provider doctor' prints redacted provider/model/package/
proxy diagnostics; preflight includes the same hint
- kimi-k2.x temperature=1 requirement auto-applied; Kimi path verified
end-to-end against the live API (kimi-k2.6 tool calls + strict
multi-turn reasoning replay)
Refs #208#203#195#204
Tiger/Longbridge/Alpaca/OKX/Binance/Futu connectors under a new broker_sdk
transport — read-only account/positions/orders/quote/history + paper-account
order placement, plus bounded mandate-gated order placement for five of them.
Longbridge is paper + read-only only (its API exposes no runtime paper/live
discriminator). Per-broker structural paper/live guards: Tiger 17-digit account,
Alpaca/Binance host separation, OKX flag + uid pin, Futu trd_env via get_acc_list.
New trading_place_order/trading_cancel_order tools; generic period/limit wired
through the tool and CLI. News updated across all 5 READMEs.
Add MiniMax-M3 as the new default model and retain MiniMax-M2.7 as
the legacy alternative (incl. -highspeed). Update llm_providers.json
registry, cli onboard provider choices, .env.example example, and the
provider-default regression tests.
Signed-off-by: Octopus <liyuan851277048@icloud.com>
Signed-off-by: octo-patch <liyuan851277048@icloud.com>
Add unified trading connector profiles and tools for IBKR and Robinhood. Gate live runner behavior by connector capability, preserve IBKR local read-only config, and update CLI, MCP, web UI, tests, skill docs, and multilingual README news.
Add an opt-in, read-only-by-default live execution channel via Robinhood
Agentic Trading (remote MCP, OAuth). The agent trades autonomously only inside
a user-committed mandate (symbol allowlist, order size, exposure, leverage,
instrument, daily cap):
- Mandate model + read-only protected store; commit is the ONLY writer
(no set_mandate tool reachable from the agent loop)
- Pre-trade enforcement gate (fail-closed) + order-intent extractor + quote pricing
- 3-tier read/write tool classification (default-deny) + OAuth token cache
- Filesystem kill switch (LLM-independent) + preemptive flatten on trip
- Mandate auto-expiry, checked proactively every runtime tick
- Persistent autonomous runtime: scheduler, durable job store, liveness,
market/interval triggers, crash-recovery reconciliation
- Consent UX (propose/commit/adjust) across CLI and Web UI
- Compliance-grade audit ledger with credential/PII redaction
Read-only/fail-closed by default; protected agent core (src/agent, src/session)
untouched. Paper/mock-tested only; live verification is the community's
(experimental, use at your own risk). Updates all 5 README languages with the
bounded-autonomy disclaimer.
Lets swarm workers call tools from operator-approved external MCP
servers in addition to the 31 local Vibe-Trading tools. Useful for
internal knowledge bases, compliance services, or any extra MCP server
the operator wants to attach.
Trust model is preserved at the schema level: MCP server URLs, commands,
env, and allowlists are resolved from the operator's config file
(VIBE_TRADING_SWARM_AGENT_CONFIG / ~/.vibe-trading/swarm-agent.json /
~/.vibe-trading/agent.json), never from `variables` or any other
caller-supplied input. The `run_swarm` MCP entry point cannot inject
server config.
Per-worker registries are built by intersecting each agent's `tools:`
whitelist with the resolved local + remote tool pool. Whitelist entries
the operator hasn't surfaced are dropped with an operator-facing
warning rather than failing the worker. Discovery is narrowed to the
servers actually referenced by the whitelist, so local-only workers
incur no MCP spawn cost.
MCP server-name collisions (e.g. `foo-bar` / `foo_bar`) keep their hash
suffixes after pruning — `_prune_agent_config_for_swarm_tools` resolves
segments against the full config first, then passes the preserved
mapping into `build_registry` so the worker whitelist still matches.
Adds `server` + `remote_tool` metadata to `tool_call` / `tool_result`
events for audit clarity, with nested redaction of sensitive argument
and result values.
Wired into MCP server, API server, CLI live runner, and in-process
SwarmTool. 27 new tests across M1-M5 (config plumbing, registry
assembly, boot wiring, e2e, trust model); 288 broader swarm/mcp/tool
tests pass.
Follow-up to #145. The new task_blocked event was emitted without
agent_id, so the CLI live panel (cli/_legacy.py) could not attach it
to the per-agent row — blocked agents stayed visually "pending" until
the run finalized. Three small fixes:
- runtime.py: pass agent_id=task.agent_id on the task_blocked emit
- cli/_legacy.py: handle task_blocked in the live event loop
- models.py: extend SwarmEvent docstring to mention task_blocked
- test_swarm_dag_gating.py: assert agent_id is present on the event
Add the session-scoped Research Goal layer across backend, CLI, API/MCP,
SSE, and Web UI. Goals now persist claims, acceptance criteria, evidence,
budgets, and completion policy; agent tools and /goal can create goals and
attach evidence; REST/MCP expose snapshots and evidence writes; SSE keeps
chat clients fresh.
Also carry the 2026-05-24 transplant cleanup: replay-all/session-id/upload
wiring, report-worthy Full Report gating, English-only Web UI copy, and audit
fixes for verified evidence, live-trading risk tiers, CLI session linkage,
goal ledger cleanup, replay-all hookup, and frontend snapshot races.
Refresh the interactive terminal transcript, activity rail, and prompt visuals. Document the 2026-05-23 CLI update in README and keep generated CLI screenshots out of git.
Co-authored-by: ykykj <140159248+ykykj@users.noreply.github.com>
Restructures the 3216-line agent/cli.py into a focused package
while preserving every existing surface verbatim.
Legacy compatibility:
- _legacy.py shim keeps every subcommand (serve, run, hypothesis,
alpha, memory, provider, swarm, sessions, ...) reachable through
the same CLI flags and console-script entry.
- Public symbols (cmd_*, _INIT_ENV_PATH, Confirm, AGENT_DIR, ...)
re-exported through cli.<name>; `from cli import *` exposes 76
symbols (was 1).
- Package-level cli.RUNS_DIR / cli.SESSIONS_DIR monkeypatches now
propagate into _legacy before any cmd_* runs.
New scaffolding:
- agent/cli/main.py interactive REPL front door
- agent/cli/commands/ slash router + handlers (15 commands)
- agent/cli/components/ reusable Rich UI building blocks
- agent/cli/{theme,intro,onboard,input,completer,stream}.py
- agent/cli/__main__.py restores `python -m cli`
- agent/cli/_version.py reads importlib.metadata.version() so
--version output and the banner stay aligned with pyproject.toml
Production wiring:
- New FastAPI middleware in api_server.py serves
frontend/dist/index.html on browser navigation to /runs/{id}
and /correlation, regex-narrowed so /runs/{id}/code and
/runs/{id}/pine API routes stay reachable.
- frontend/vite.config.ts dev proxy mirrors the same narrowing.
- scripts/dev backend starts via package-safe
`python -c 'import cli; cli.main(...)'`.
Chat-gate narrowed: chat --help / chat -h / chat --max-iter <bad> /
chat extra correctly reach legacy argparse instead of being
swallowed by the new REPL.
Tests: 2271 passed, 43 skipped (focused CLI/SPA test files:
test_cli_interactive.py 67 + test_spa_deep_link.py 13 + existing
CLI memory/init/hypothesis 48 = 128).
shadowinlife