twmarketdata.com

List available Taiwan-market datasets (discovery entry point).

FULL semantics of one dataset: grain (what a row is), field meanings+units, ★TIME-CORRECTNESS rules (knowledge_time_field / point_in_time_safe — read before backtesting), relations for cross-table reasoning, agent_hints (when to use), quant_use (which factors).

Query rows with built-in look-ahead protection.

Traverse the knowledge graph for cross-table / supply-chain reasoning.

Semantic search over MOPS filings, financial-statement notes and company news.

Where did this number come from, and when could anyone have known it?

Prove a row was in the snapshot TWMD published — and check it yourself.

Produce a bibliographic citation for TWMD data — APA, BibTeX, and a re-verifiable token.

Read the FULL TEXT of filings and announcements — with proof links and a knowledge cutoff.

Answer a plain-language question in Taiwanese-market vocabulary, sentence by sourced sentence.

Turn rows you already fetched into a Vega-Lite drawing your chat window can render.

Turn a spoken shortlist description into explicit numeric cut-offs, and show the cut-offs.

The Taiwan business-cycle light (NDC monitoring indicator) as a monthly series.

Sort corporate dates into what is still ahead and what has already passed.

Lay two to five named companies side by side on the same measures, gaps marked as gaps.

Emit a copy-pasteable HTTP snippet wired to the real endpoint, header and parameter names.

Replay a saved multi-step routine over rows you fetched, with every step listed.

Hand an unregistered caller a short taste of an open dataset, plus where to unlock the rest.

Run a point-in-time backtest and return its run_id, metrics, sources and honesty checks.

Retrieve a previous backtest by run_id — the full record, including why it was rejected.

Re-run a stored backtest and report whether it still produces the same numbers.

Browse an INDEX of your past backtest runs — ids and headline metrics only, no re-execution.

Remember something, with its sources and its knowledge time.

Recall your own memories — hybrid (semantic + exact-term), with provenance attached.

Read the tickers on one named watchlist, as it stands right now.

Re-run a remembered query by its `twmd_q_…` id, through the read API's own replay store.

Run a multi-agent research pass and return a structured, sourced report.

Retrieve one of YOUR previous research reports.

Financial actions proposed by your research runs that are waiting for a human decision.

Record a HUMAN's approval of a proposed action.

Show the price-trigger rules you have armed, and whether each is still armed.

Leave a standing instruction: tell me when this symbol crosses this price.

Cancel one armed price trigger permanently, by its rule id.

Measure a portfolio you state against limits you state, on official point-in-time prices.

What YOUR agents have actually done, from the durable audit trail.

Verdicts from the overnight factor search on YOUR namespace — including the rejections.

一檔股票的誠實體檢:成長、獲利品質、估值、籌碼、紅旗,每個數字可驗證。 ★ 這是**事實整理**,不是投資建議、不是預測、不是目標價。輸出帶 `does_not_prove`,轉述時請一併保留。 ★ POINT-IN-TIME:`as_of` 逐資料集尊重揭露時差 —— 月營收用法定截止日推得的 估計時點,財報用出表日,估值是當日。不給 `as_of` 就用「現在可知的最新」, **不是今天**。 ★ 沒看到的東西會列在 `cannot_see`,並說明是「查了沒有」「查詢失敗」還是 「散佈權未取得」—— 三者不同。⚠️ 不要替 `cannot_see` 裡的項目估算或補值。 ★ `checked_and_clear` 是「查過而且確認沒有」(例如近一年無裁罰), 和 `cannot_see` 的「不知道」是兩回事。 ★ 代號解析不到會回 `needs_disambiguation` 附候選 —— 請回問使用者,不要挑一個。 ★ PRECONDITIONS:這支工具**自己**去拿九個資料集,所以 rows 不需要先用 `query_dataset` 取好。它 requires 的是身分:呼叫端 must be 一個已識別的 session(X-API-Key 或已驗證的 OAuth 登入),因為體檢會寫進呼叫者的工作區 脈絡。方案沒有涵蓋某個資料集時,那一項會以 `not_licensed` 出現在 `cannot_see`,而不是讓整支工具失敗 —— 所以不需要 entitlement 先檢查。 ★ SIDE EFFECTS:read-only。does not 寫入任何資料表,不建立警示、不下單。

籌碼結構:法人分項、融資融券、借券使用率、大戶集中度、董監質押。 ★ 事實整理,不是投資建議、不是預測、不是目標價。輸出帶 `does_not_prove`。 ★ POINT-IN-TIME:`as_of` 逐資料集尊重揭露時差;不給就用「現在可知的最新」。 ★ 看不到的在 `cannot_see`,並分「查了沒有 / 查詢失敗 / 散佈權未取得」。 ⚠️ 逐券商分點進出**永遠**在 cannot_see —— 散佈權未取得,不要替它估算。 ★ PRECONDITIONS:自己取數,rows 不需要先用 `query_dataset` 備好;requires 一個 已識別的 session。方案沒涵蓋的資料集以 not_licensed 進 cannot_see,不整支失敗。 ★ Args:`ticker`(代號,例如 "2330")、`as_of`(選填的知識時間界線)。 ★ Returns:一個信封,`concerns`/`observations` 各帶觸發它的數字與驗證連結, 缺的東西 listed in `cannot_see`。 ★ SIDE EFFECTS:read-only,does not 寫入任何資料表。

總經 Regime:景氣信號、利率與殖利率曲線、匯率、資金流。 ★ 這支講的是**整個市場**,不是任何一檔個股 —— 所以它不收 ticker。 ★ 事實整理,不是投資建議、不是預測。輸出帶 `does_not_prove`。 ★ ⚠️ `macro_worldbank` 類的來源會**回溯修訂**歷史年度:今天讀到的舊年度數字 和當時看到的不是同一個,`pit_notes` 會標出來。 ★ Args:只有 `as_of`(選填)—— 它**不收 ticker**,因為主體是整個市場。 ★ Returns:同一個誠實信封;`subject` 固定是 "TW_MARKET"。 ★ 例如問「現在景氣循環在哪個位置」就是這一支,而不是問某一檔。 ★ PRECONDITIONS:自己取數;requires 一個已識別的 session。 ★ SIDE EFFECTS:read-only,does not 寫入。

供應鏈與同業:產業鏈位置、同業分組、轉投資、外銷訂單 vs 營收。 ★ 事實整理,不是投資建議、不是預測。輸出帶 `does_not_prove`。 ★ ⚠️ `company_peer_groups` 無日期欄:指定過去的 `as_of` 時,回的是**現況**分組, `pit_notes` 會標「非當時分類」。 ★ ⚠️ 質化的客戶/供應商關係與分部營收在年報附註,那條來源**尚未建置** —— 固定列在 `cannot_see`(status=no_loader),不是這次查失敗。 ★ Args:`ticker`(例如 "2330")、`as_of`(選填)。 ★ Returns:誠實信封;外銷訂單與營收的背離會 listed in `concerns`。 ★ PRECONDITIONS:自己取數;requires 一個已識別的 session。 ★ SIDE EFFECTS:read-only,does not 寫入。

事件與市場結構風險:隱含波動率、注意處置、裁罰訴訟、放空限制、因子。 ★ ⚠️ **部位集中度與回撤不在這裡** —— 那是 `risk_assess` 的職責。重算一份會產生 第二個答案,而兩個都帶著我們的名字。 ★ `checked_and_clear` 是「查過而且確認沒有」(例如近一年無裁罰),和 `cannot_see` 的「不知道」是兩回事。 ★ 事實整理,不是投資建議、不是預測。輸出帶 `does_not_prove`。 ★ Args:`ticker`(例如 "2330")、`as_of`(選填)。 ★ Returns:誠實信封;事件風險 listed in `concerns`,查過確認沒有的 listed in `checked_and_clear`。 ★ PRECONDITIONS:自己取數;requires 一個已識別的 session。 ★ SIDE EFFECTS:read-only,does not 寫入。