a-stock-data
A股全栈数据工具包:行情K线·当日逐笔·研报·信号·资金面·新闻·财务·公告·打板·ETF期权·舆情·宏观利率·期货大宗(含大商所日K)·事件驱动·可转债 | 15层·87端点·34数据源·除iwencai外免Key | A-share data for AI agents: K-lines, ticks, reports, fund flow, news, financials, filings, options, macro, futures, events, convertibles | 15 layers·87 endpoints·34 sources
Runssource: GitHubPythonApache-2.0commit f814dcfe209d
Python, Apache-2.0 licensed. The project labels itself: a share, ai agent, ai skill, china stocks, claude code, financial data, fintech and investment research.
a-stock-data runs. An Argusic agent installed it in 12 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Fresh-venv install of the README dependency list succeeds; the bundled offline suite passes 168/168 (3 opt-in live skipped by default), and the three opt-in live suites now pass against real Tencent/eastmoney/SSE/SZSE/BSE/央行 sources with no credentials after I fixed three source-drift bugs in SKILL.md (SSE margin pagination, BJ ST dedupe, SSE-e relative timestamps).
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- SSE margin API now caps each page at 2000 rows while reporting total=2017, so the shipped single-page checker raised '上交所该日数据未发布或分页不完整'20 minutes
- st_stock_list raised 'ST 名单为空或代码重复' because eastmoney's risk-warning board now includes 195 BJ 920xxx stocks that also appear in the BJ universe list, creating duplicate codes15 minutes
- sse_e_interaction raised '回复时间认不出: 1分钟前' because SSE-e now emits relative timestamps (1分钟前/5小时前/昨天 14:31) for recent items12 minutes
- Install time
- 12 minutes
- Cold machine to finish
- 28 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- python3 -m unittest discover -s tests -> Ran 168 tests OK (3 opt-in live skipped); ASTOCK_LIVE_TRADE_DATE=2026-11-04 ASTOCK_LIVE_MARGIN_DATE=2026-10-30 python3 -m unittest tests.test_official_data.LiveOfficialDataTests -> OK (SH margin 2017 rows, SZ 2118, BSE 354, CSI300 300); ASTOCK_LIVE_V39=2026-11-03 python3 -m unittest tests.test_v39_sources.LiveV39Tests -> OK (31 real endpoints); ASTOCK_LIVE_V310=1 python3 -m unittest tests.test_v310_sources.LiveV310Tests -> OK
- Model tokens used
- 622,900
- Exact commit tested
- f814dcfe209d
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- Standard install: fresh `.venv`, `pip install` of the README's 8 packages — succeeded, all import… - Offline suite: `python3 -m unittest discover -s tests` → 168 tests, OK (3 skipped are opt-in live… - Live official-data suite (`ASTOCK_LIVE_TRADE_DATE/MARGIN_DATE`) → now OK after a fix; verified re… - Live V3.9 suite (`ASTOCK_LIVE_V39=2026-11-03`, 31 real endpoints: Tencent klines, eastmoney, CCTB… - Live V3.10 suite (`ASTOCK_LIVE_V310=1`, Tencent ticks + futures klines) → OK with zero keys. **3 errors found and fixed in the shipped `SKILL.md` (the repo's source of truth)** 1. `margin_trading_backup` SH: SSE now caps pagination at 2000 rows while `total=2017`, so the sing… 2. `st_stock_list`: eastmoney's risk-warning board now includes BJ 920xxx stocks (195 of 393), whic… 3. `sse_e_interaction`: SSE-e now renders recent answer times as relative strings (`1分钟前`, `5小时前`, … Also added `.venv/` to `.gitignore` (untracked venv would otherwise pollute status). No third-party… ``` ```
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 12 minutes to install, slower than the median of the 5 comparable projects Argusic has measured.
Of the 6 a-share projects Argusic has installed and timed, a-stock-data was the 6th fastest to reach a running state, and 4 of 6 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
a-shareai-agentai-skillchina-stocksclaude-codefinancial-datafintechinvestment-researchllm-toolsmarket-datapythonquantitative-financestock-markettrading
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/a-stock-data)Questions
- Does a-stock-data run?
- Yes. a-stock-data runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test a-stock-data?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit f814dcfe209d. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test a-stock-data?
- The run that produced this verdict cost $0.17: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does a-stock-data take to install?
- 12 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does a-stock-data need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing a-stock-data?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does a-stock-data compare with the alternatives?
- Of the 6 a-share projects Argusic has installed and timed, a-stock-data was the 6th fastest to reach a running state, and 4 of 6 reached one at all.
- Where is the evidence for a-stock-data?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.