One-call briefing at the start of a turn: spots known companies in text, recalls prior theses, claims, open alerts and ruled-out ideas about them, and returns the graph digest.

Prior theses, claims and rejected hypotheses about entities and/or a question.

Call this before starting research so you build on earlier work.

Resolve an entity and list its current relations.

Keyword search over current claims, evidence and theses.

History of one entity, oldest first: claims recorded, corrected or retracted about it, theses on it created or changed, and events (filings, news) that name it. Each change has a time, kind, object id and one-line summary. Use it to see how the view on a company evolved; use what_changed for the whole graph and get_entity for its current links.

Everything recorded or revised across the graph since a point in time.

Create an entity (or merge into the one with the same canonical_key).

Fold a duplicate entity into the one to keep; its links move over.

Record a source. Re-recording the same URI returns the existing record.

Save one finding about one or more entities, tied to its sources.

    Record the source first with `record_evidence` and pass its id. A fact or
    metric without supporting evidence_ids is rejected, as is an inference with
    neither evidence nor derived_from. Returns the new claim with its id, which
    theses (`record_thesis`) and relations (`record_relation`) can cite. To fix
    an existing claim use `supersede_claim`, not a second record_claim.

Correct a claim: the old version stays in history, the new one is current.

Withdraw a claim that turned out to be wrong (kept in history).

Link two entities, e.g. TSMC SUPPLIES NVIDIA. Re-recording an existing link updates it (confidence, backing claim, dates) instead of duplicating it.

Save a new investment thesis and the claims it rests on.

    Record the claims first with `record_claim` and pass their ids. Torus uses
    the assumptions, subject and triggers to decide which new filings and news
    threaten the thesis and raise alerts. Returns the thesis with its id and
    status (active). To change an existing thesis use `update_thesis`; to log
    an idea you rejected use `record_rejected_hypothesis`.

Revise a thesis: status, confidence, the claims it rests on, and its triggers, in one atomic step. Everything is kept in its history.

    Also tunes its alerts: a threshold of its own, and mutes (e.g. no alerts
    for a supplier's routine 10-Qs).

Record an idea that was checked and ruled out, so it isn't re-explored.

Record an event and raise alerts on theses it may affect (through the companies involved and their suppliers, customers and competitors).

Dry run: which theses would an event on these entities affect, and why? Records nothing.

Alerts raised by events on theses, highest score first. Each shows how its score was built: graph score x event materiality x (1 + trigger match).

How useful alerts have been: verdicts, and the share judged related (precision) by source, form, hops and materiality.

Judge an alert after reading the event and the thesis's claims; the thesis is updated accordingly and the change logged with the alert.

The entity's neighbourhood: companies within hops links (suppliers, customers, competitors...), the links among them, and theses about them.

How two entities are connected, e.g. ASML -SUPPLIES-> TSMC -SUPPLIES-> AMD. Shortest and most confident paths first.

Watch a company: its new SEC filings become events (on the next torus watch run). Subjects of open theses are watched automatically.

Stop watching a company you added with watch. Removes it from the explicit watchlist only: a company that is the subject or a trigger entity of an open thesis is still followed. Nothing in the graph is deleted. Returns the updated watch list, as list_watches does.

What the watchers follow: the watchlist, open-thesis entities, feeds.

Lease the oldest research session waiting to be distilled into the graph.

    Returns its transcript digest, what was already recorded (don't duplicate
    it), the sources the agent looked at, and existing theses on its entities.
    Until `complete_distillation`, new records are attributed to that session.

Finish a leased distillation job (or hand it back if it failed).

Start covering companies: add them, watch their filings, suggest starter packs, and queue a mapping job for each (run by the company-mapper subagent, which reads their annual reports and records suppliers, customers and competitors).

Add a curated starter pack of companies and supplier/competitor links. Never overrides links research recorded.

Lease the next onboarded company to map from its annual report. Until complete_mapping, links you record are marked as curator links.

Finish a leased mapping job (or hand it back if it failed).

List what the most recent research sessions recorded (claims, theses, relations, sources, ruled-out ideas), newest session first, with each session's id and whether each record can still be undone. Read-only. Use it when the user asks what Torus saved, then pass the session id and records to undo_records to revert the unwanted ones.

Revert records the user doesn't want: claims are retracted (corrections go back to the earlier version), theses the session created are archived, links retired, ruled-out ideas withdrawn. History keeps everything.

What if this happened? Which theses would it reach, through which links, and would it raise alerts. Records nothing.

Write a thesis up as a memo (Markdown and a standalone HTML page): what it rests on with sources and quotes, triggers, events and verdicts, ruled-out ideas and history. Saved under TORUS_HOME/memos.

Write the interactive graph explorer HTML file (under TORUS_HOME/explorer.html) and open it in the user's browser.

Where a thesis is weakest: thin or expiring assumptions, strong supplier or customer dependencies it never mentions, triggers that can't fire on events, and opposing views already in the graph. Input for /torus:challenge.

Put a thesis on the scorecard: its return against a benchmark from an entry price and date, in the direction of its stance.

How tracked theses have done against their benchmarks, their outcomes, and calibration: did the user's confidence match how often they were right?

Record whether a thesis turned out right, wrong or unclear (overrides the automatic outcome; used for calibration).

Health check of the research graph: expired or thinly sourced assumptions, theses past their horizon or gone stale, claims that may conflict, unconfirmed starter links, orphans. Each finding suggests a fix.

What happened in the research over the last days: new alerts by thesis, thesis status and confidence changes, theses coming due, audit counts, scorecard moves and activity. markdown is ready to show.

What changed in a section of a company's latest filing against the previous one of the same form: new, dropped and reworded sentences.

Read a company's SEC filing as text, by section, from EDGAR (cached). Long sections come in pages: pass next_offset back as offset.