dexterm-cli 0.1.5 → 0.1.7

package/dist/packages/mcp/assets/kb/docs/docs-copy-trading-what-is-proven-what-is-not.md

@@ -29,7 +29,7 @@ date: 2026-10-16
 
 Proven on fixtures and a fake clock: the decoder on synthetic histories and the three spike recordings; the tracker's backfill-then-alert replay; every mirror refusal and the size rule; the proposal's inertness; the auto path end to end on the paper executor (enable, ¼-size arming, fill, cooldown, max-open, daily cap, the engine's own refusal of a hand-armed extra plan); the kill paths; the restart rule; and a compromised-model suite in which spoken, agent and forged gestures, a spoofed alert, a widened policy and a plan the service did not create all fail to enable, widen or auto-arm anything.
 
-Not built or not proven: **mirror-sell** (you close every mirror yourself, so auto-disarm counts refusals and failed fills, not realised losses); an early-entry score with the "reached 3×" filter; a live run against real Helius history on this machine; and any mirror on devnet or mainnet.
+Not built or not proven: **mirror-sell** (you close every mirror yourself, so auto-disarm counts refusals and failed fills, not realised losses); an early-entry score with the "reached 3×" filter; and a live run against real Helius history on this machine. Mirrors never trade real funds.
 
 **Confirmation provenance:** the engine rejects fabricated, copied, modified, cross-engine and reused proof objects. Copy automation receives a private operation scoped to its physically armed mandate; it can create new copy buys, never adopt an existing voice or agent proposal. Automation proofs stay inside the engine. The engine re-checks the less-safe opt-in, mandate lifetime, panic and existing caps. These are in-process checks: the trusted terminal captures physical input; this is not isolation against arbitrary code execution inside that trusted process.
 

package/dist/packages/mcp/assets/kb/docs/docs-copy-trading.md

@@ -26,6 +26,6 @@ date: 2026-10-16
 
 Follow a wallet and see its decoded swaps and PnL; turn its buys into a mirror PROPOSAL with one key; or let a capped, keypress-armed auto-mirror propose and arm them for you. Your wallet, your caps, your keys.
 
-Copy trading in dexterm is a **personal tool for your own wallet**. You pick the wallets, you set the caps, your own keys sign (or the paper wallet simulates). dexterm never holds funds, never copies for anyone else, never offers pooled or hosted copying, never publishes a leader list, and takes no fee on a mirrored trade. The whole feature is labelled **in progress**: it is on main and tested on fixtures and the task-1286 spike recordings, but no mirror has moved real funds, and the auto tier fires through the paper executor unless the plans fire path is switched to the devnet fast wallet (see the live fire path (https://dexterm.xyz/docs/paper-trading#the-live-fire-path-devnet-the-fast-wallet)).
+Copy trading in dexterm is a **personal tool for your own wallet**. You pick the wallets, you set the caps, and the paper wallet simulates every mirror. dexterm never holds funds or keys, never signs, never copies for anyone else, never offers pooled or hosted copying, never publishes a leader list, and takes no fee on a mirrored trade. The whole feature is labelled **in progress**: it is on main and tested on fixtures and the task-1286 spike recordings, and every mirror, the auto tier included, fills through the paper executor. No mirror moves real funds.
 
 It is built in three stages, each behind the previous one's gate.

package/dist/packages/mcp/assets/kb/docs/docs-data-sources-recorded-history-and-retention.md

@@ -0,0 +1,36 @@
+---
+id: docs-data-sources-recorded-history-and-retention
+title: Data sources and rate limits › Recorded history and retention
+kind: docs
+page: data-sources
+page_title: Data sources and rate limits
+heading: Recorded history and retention
+anchor: recorded-history-and-retention
+url: https://dexterm.xyz/docs/data-sources#recorded-history-and-retention
+tags:
+  - docs
+  - data-sources
+  - recorded
+  - history
+  - retention
+  - data
+  - sources
+  - rate
+  - limits
+confidence: high
+owner: maintainers
+origin: docs-generated
+reviewed_by: generated@2026-10-16
+generated_from: dexterm/site content/docs (task-1420)
+sources:
+  - site/content/docs/data-sources.md
+date: 2026-10-16
+---
+
+What the local recorder keeps, all in your own `--db` file and never uploaded (see the recorder (https://dexterm.xyz/docs/configuration#history-recorder)):
+
+- **Snapshots**: a row per coin when its price, liquidity, holders or volume moved materially (about 5%), or every 30 minutes, while a screen listed it, plus outcome re-checks at 1 h to 72 h after it left. Raw JSON goes after 7 days, rows thin to one per coin per minute after 24 hours, and rows expire after 90 days (`--retention-days D` sets that age).
+- **Autotrade ticks** (`autotrade_ticks`, opt-in with `dexterm record run --focus-ticks`): a sample every 5 seconds for coins you hold on paper or have open, every 10 seconds for your watchlist and autotrade candidates: price, liquidity, market cap, 5-minute and 1-hour volume, buys and sells, and price change. At most 60 coins, in DexScreener batches of 30 (never one call per coin, and no Jupiter calls), queued inside the app's own limiter, skipped while DexScreener is rate-limiting, with a daily ceiling of 36,000 calls. Kept 14 days.
+- **1m candles** (`autotrade_candles_1m`): open, high, low and close per minute for the same coins, built from those samples, so a high or low is the highest or lowest sample, not every trade. Kept 90 days.
+- **Outcome labels**, verdicts and coin creators: kept.
+- **Size cap** (opt-in, `dexterm record run --retention-mb N`): when the database's used space reaches the cap, cached answers more than a day past their expiry are cleared first; if that is not enough, the oldest history (ticks, candles and snapshots, outcome re-checks included) is removed first until it is back under, and recording never pauses; the newest hour is always kept. Without it, the older `--max-db-mb` cap pauses new snapshots instead. SQLite reuses the freed space rather than shrinking the file.

package/dist/packages/mcp/assets/kb/docs/docs-data-sources-sources.md

@@ -35,6 +35,7 @@ date: 2026-10-16
 | security checks | RugCheck + GoPlus | none | one may be `unavailable`, the other covers |
 | new pairs | PumpPortal `subscribeNewToken` + `subscribeMigration`, Jupiter `recent` poll, RugCheck `new_tokens` | Helius: per-curve bonding % | rows from the poll; bonding is a create-time estimate |
 | watchlist prices | DexScreener + Jupiter, persisted in SQLite | Jupiter free key: higher rate | fully keyless |
+| autotrade ticks and 1m candles (opt-in, `dexterm record run --focus-ticks`) | DexScreener `tokens/v1`, batches of 30 coins per call | none | backtests use the coarser recorder snapshots only |
 | fast-lane live price | public RPC WebSocket `accountSubscribe` on the pump.fun bonding curve, price computed on-chain | free Helius key: lower latency, higher limits (used first) | the polled price (POLL badge) |
 | paper quotes | Jupiter `swap/v1/quote` (quote only; no build, no execute) | Jupiter free key: lower latency | fully keyless |
 | product vetting | the token's own site, RDAP, the GitHub API | none | a claim stays unverifiable |

package/dist/packages/mcp/assets/kb/docs/docs-getting-started-first-run.md

@@ -24,7 +24,7 @@ sources:
 date: 2026-10-16
 ---
 
-The first launch shows the full glitch boot and then a one-screen welcome card: what dexterm is, the keys that get you around, and the safety stance (non-custodial, your keys never enter dexterm, trading is PAPER by default, not financial advice). Press any key to enter the live screener. Later launches boot in about a second.
+The first launch shows the full glitch boot and then a one-screen welcome card: what dexterm is, the keys that get you around, and the safety stance (non-custodial, no wallet and no keys, trading is PAPER, not financial advice). Press any key to enter the live screener. Later launches boot in about a second.
 
 - `?` on any screen shows every key for that screen.
 - `q` quits. The terminal is always restored, even after a crash or a signal.

package/dist/packages/mcp/assets/kb/docs/docs-getting-started-install.md

@@ -41,10 +41,10 @@ $ dexterm doctor
 The package is named `dexterm-cli` because npm refuses the name `dexterm` as too similar to `xterm`. The command it installs is `dexterm`. The package ships compiled JavaScript, so it needs no build step. Every GitHub release carries a build-provenance attestation and `SHA256SUMS` you can verify (see the trust page (https://dexterm.xyz/trust/)).
 
 ```sh install from the release
-$ # download dexterm-0.1.5-src.tar.gz and SHA256SUMS from the releases page, then:
+$ # download dexterm-0.1.7-src.tar.gz and SHA256SUMS from the releases page, then:
 $ shasum -a 256 -c SHA256SUMS --ignore-missing
-$ gh attestation verify dexterm-0.1.5-src.tar.gz --repo dexterm-xyz/dexterm
-$ tar -xzf dexterm-0.1.5-src.tar.gz && cd dexterm-0.1.5
+$ gh attestation verify dexterm-0.1.7-src.tar.gz --repo dexterm-xyz/dexterm
+$ tar -xzf dexterm-0.1.7-src.tar.gz && cd dexterm-0.1.7
 $ ./install.sh
 $ dexterm doctor
 ```

package/dist/packages/mcp/assets/kb/docs/docs-getting-started-requirements.md

@@ -32,4 +32,4 @@ date: 2026-10-16
 | optional: a free RPC key | the ranked top-20 holder list and faster chain reads | Helius, Alchemy, QuickNode or Ankr free tier; see configuration (https://dexterm.xyz/docs/configuration). |
 | optional: Rust (`cargo`) | the native docked chart window | without it the chart popup opens in your browser; see popup chart (https://dexterm.xyz/docs/popup-chart). |
 
-> note: dexterm 0.1.5 is out (2026-10-18), open source under AGPL-3.0-only at github.com/dexterm-xyz/dexterm (https://github.com/dexterm-xyz/dexterm). It is early: trading is experimental and has known bugs. The release ships checksums, a build-provenance attestation and an SBOM, and its VirusTotal result (including flags we explain) is on the trust page (https://dexterm.xyz/trust/). It is also on npm as `dexterm-cli` (https://www.npmjs.com/package/dexterm-cli); the command it installs is still `dexterm`.
+> note: dexterm 0.1.7 is out (2026-10-22), open source under AGPL-3.0-only at github.com/dexterm-xyz/dexterm (https://github.com/dexterm-xyz/dexterm). It is early: trading is experimental and has known bugs. The release ships checksums, a build-provenance attestation and an SBOM, and its VirusTotal result (including flags we explain) is on the trust page (https://dexterm.xyz/trust/). It is also on npm as `dexterm-cli` (https://www.npmjs.com/package/dexterm-cli); the command it installs is still `dexterm`.

package/dist/packages/mcp/assets/kb/docs/docs-getting-started-running-the-tests.md

@@ -25,7 +25,7 @@ sources:
 date: 2026-10-16
 ---
 
-From a source checkout, `npm install` and then `npm test` runs the typecheck and three test lanes, in order (from 0.1.4, not in a release yet):
+From a source checkout, `npm install` and then `npm test` runs the typecheck and three test lanes, in order (since 0.1.4):
 
 - **parallel**: every `packages/*/test/*.test.ts` file at once, one process each.
 - **serial** (`npm run test:serial`, `packages/*/test/serial/`): the tests that drive a real terminal through a pty, run the real binary, or assert a wall-clock bound (the under-a-second quit, the 50 ms filter fuzz). They run one file at a time after the parallel lane, so they never share the CPU with it.

package/dist/packages/mcp/assets/kb/docs/docs-getting-started.md

@@ -22,6 +22,6 @@ date: 2026-10-16
 
 Requirements, install, first run and dexterm doctor.
 
-dexterm is a terminal screener for Solana memecoins with a local Claude analyst. It runs on your machine, reads public data with no key and never holds a wallet key. Trading is PAPER by default; any live swap is signed in your own Phantom wallet after you approve it (see paper trading (https://dexterm.xyz/docs/paper-trading)). This page gets you from nothing to the live screener.
+dexterm is a terminal screener for Solana memecoins with a local Claude analyst. It runs on your machine, reads public data with no key and never holds a wallet key. Trading in dexterm is PAPER (see paper trading (https://dexterm.xyz/docs/paper-trading)); dexterm signs nothing, and live trading happens in a Telegram trading bot of your choice (see live trading (https://dexterm.xyz/docs/live-trading)). This page gets you from nothing to the live screener.
 
 > note: Never used a terminal before? Start with the complete beginner guide (https://dexterm.xyz/docs/beginners). It defines every term, shows exactly what to copy on macOS, Linux and Windows, and ends with a ten-minute read-only coin review.

package/dist/packages/mcp/assets/kb/docs/docs-larp-measured-accuracy.md

@@ -29,6 +29,7 @@ date: 2026-10-16
 
 - **LARP check, links only.** The links-based baseline is a weak signal: MCC 0.039 before tuning, 0.054 after. Its tuned `LARP` grade caught 4 of 14 bad coins, too few to rate. `EARLY_BUT_REAL` coins still went bad 10.3 % of the time, and coins with no website 29.2 %. The skill now treats the baseline as a weak prior and never calls `LARP` from links alone.
 - **Rug check.** The verdict rules improved from MCC 0.043 to 0.159. Liquidity under $5k is the one strong signal (`SPECULATIVE` coins went bad 54.8 % of the time, `WATCH` 14.4 %). Dev percentage, organic score and top-10 share did not predict a worse 72 h outcome and now only lower confidence.
+- **LARP score, link-shape part** (`dexterm backtest --subject larp-score`, task-1471). Points fitted on the train split only. On the 328 held-out coins its AUROC is 0.69 (0.73 on train): a modest ranking signal. 27 of 218 low-band coins went bad (12.4 %), 34 of 110 medium-band coins (30.9 %), against 18.6 % overall; no coin reaches the high band from link shape alone. The page, domain, GitHub and X points are not measured: that evidence was not recorded at the time, and looking it up now would leak the outcome (dead coins' sites and accounts disappear).
 - **Not measured.** The model stage (fetched pages, RDAP, GitHub) cannot be replayed: a past page cannot be fetched as it was. It is measured going forward with `dexterm backtest --subject larp`, below.
 
 The method, every number and the limits are in the repository at `packages/packs/eval/README.md`. A grade is a risk flag, not a certificate.

package/dist/packages/mcp/assets/kb/docs/docs-larp-the-larp-score.md

@@ -0,0 +1,60 @@
+---
+id: docs-larp-the-larp-score
+title: LARP detector › The LARP score
+kind: docs
+page: larp
+page_title: LARP detector
+heading: The LARP score
+anchor: the-larp-score
+url: https://dexterm.xyz/docs/larp#the-larp-score
+tags:
+  - docs
+  - larp
+  - score
+  - detector
+confidence: high
+owner: maintainers
+origin: docs-generated
+reviewed_by: generated@2026-10-16
+generated_from: dexterm/site content/docs (task-1420)
+sources:
+  - site/content/docs/larp.md
+date: 2026-10-16
+---
+
+`larp_check` also returns a **LARP score from 0 to 100**: the sum of named flags, each with its points and the evidence that raised it. Higher means more of the things that went with LARP coins showed up. It summarises the flags; it is not a verdict and does not replace the one above.
+
+| band | score | |
+|---|---|---|
+| low | under 25 | few flags |
+| medium | 25 to 49 | several flags; link shape alone tops out here |
+| high | 50 or more | needs page, domain, GitHub or X evidence, not link shape alone |
+
+| flag | points | weight |
+|---|---|---|
+| no Telegram advertised | 12 | fitted |
+| no X account advertised | 10 | fitted |
+| no website advertised | 9 | fitted |
+| X link is a single post or a community, not an account | 5 | fitted |
+| the "website" is a social page | 1 | fitted |
+| the domain does not name the token · throwaway-priced TLD | 0 | fitted (did not go with bad outcomes, so not listed) |
+| launchpad / link-hub / free-host page as the website | 4 / 2 / 2 | prior (too rare to fit) |
+| sources advertise different sites or X accounts | 8 | prior |
+| wallet-drainer markers on the page | 30 | prior |
+| default or placeholder page | 15 | prior |
+| asks to connect a wallet · never names the token | 8 · 8 | prior |
+| domain under 30 days old · registrant privacy | 8 · 2 | prior |
+| no GitHub advertised · archived · a fork · no push in 180 days | 2 · 4 · 4 · 4 | prior |
+| X account suspended · does not exist | 20 · 15 | prior |
+| X account under 7 days old (or under 30 days) | 12 (6) | prior |
+| under 50 followers · no posts in 30 days | 5 · 6 | prior |
+| the website's X link and the advertised account differ | 10 | prior |
+| a linked post now shows another handle · the account does not link the site | 5 · 3 | prior |
+
+**Fitted** points come from the recorded history below (link shape is the only part of the check that history can replay). **Prior** points were written from the skill's rules before any data and are labelled `prior` in every result.
+
+**Missing data never lowers the score.** A page that could not be read, an RDAP or X lookup that failed, goes to a `missing` list with the points it could have added, and the result shows the range: "37, could be up to 58". Nothing unread is scored as clean.
+
+Where it shows: the `larp_check` MCP result (`score`, `band`, and `larp_score` with every flag, its points, its weight and its evidence, the range and the `missing` list; the existing fields are unchanged), the analyst panel after a LARP check (a gauge with the three biggest reasons, drawn from the tool's own result, never from the model's text).
+
+> warn: a LARP verdict is a risk flag, not a certificate. Public HTML cannot prove a working product, a team's identity or who owns an account; domain age, a clean script scan and a GitHub with commits are evidence, not proof, and a real product can still go to zero.

package/dist/packages/mcp/assets/kb/docs/docs-larp-the-verdict.md

@@ -25,5 +25,3 @@ date: 2026-10-16
 The `larp-check` skill returns a structured assessment: `REAL_PRODUCT` · `EARLY_BUT_REAL` · `LARP` · `UNVERIFIABLE` · `AMBIGUOUS`, with a confidence, a status per claim (supported, contradicted, unverifiable), `missing_data`, the facts and flags it used, `injection_detected` and a short summary. It is separate from the dossier's risk verdict and does not replace it.
 
 Once computed, a badge appears in the screener's FLAGS column and in the token screen's title strip for that mint only: **LARP** (red), **REAL** (green), **REAL?** (mixed), **UNKNOWN** for unverifiable or ambiguous. Nothing shows before you vet a coin. A `LARP` verdict also vetoes an AI scan (https://dexterm.xyz/docs/scan) lock on that coin.
-
-> warn: a LARP verdict is a risk flag, not a certificate. Public HTML cannot prove a working product, a team's identity or who owns an account; domain age, a clean script scan and a GitHub with commits are evidence, not proof, and a real product can still go to zero.

package/dist/packages/mcp/assets/kb/docs/docs-larp-what-it-looks-at.md

@@ -29,5 +29,8 @@ date: 2026-10-16
 | the domain | RDAP lookup of the exact advertised domain (`check_domain`) | registration age, registrar, registrant privacy. A days-old domain behind privacy is a mild signal, not proof. Novelty TLDs without an RDAP server come back as unverifiable. |
 | GitHub | the keyless GitHub API (`check_github`) for a `github.com/owner/repo` link | created and last-push dates, stars, open issues, archived or fork, up to five real commit hashes with dates |
 | pump.fun metadata | the metadata URI GoPlus reports, through the same safe fetch | the advertised description and links, when they exist |
+| the X account | a keyless public lookup (`check_x`): FxTwitter, then vxtwitter's cached copy, then X's own oEmbed. No login, no API key, one handle per check, cached 30 minutes, at least a second between calls to each host | whether the account exists, is suspended or is gone; when it was created; followers, following and posts; the last post date; whether the bio names the token and links the site; whether the website's own X link matches the advertised one; and, for a link to a single post, whether that post now shows another handle |
 
-X is usually login-walled keyless, so account age and follower counts are reported as unverifiable rather than guessed. Every fetched string reaches the model through the prompt firewall: normalised, control and bidi characters stripped, URLs and addresses masked, wrapped as untrusted data, tags stripped so a planted closing tag cannot break out.
+**How the X lookup decides.** No single source is trusted on its own. On 2026-10-19 FxTwitter answered "user not found" for accounts that exist on roughly one call in six, so one "not found" is never enough: an account is `not_found` only when two independent sources (vxtwitter and X oEmbed) agree, `suspended` when a source says so, and otherwise `unavailable`. vxtwitter serves a cached copy, so its counts carry the time it was taken. Nitter-style mirrors and the X embed timeline were down or rate-limited every time and are not used. Each source has a circuit breaker and backs off when it keeps failing. Anything the lookup could not read is listed as unavailable, never guessed and never counted as clean. The bio is untrusted text like any page.
+
+Every fetched string reaches the model through the prompt firewall: normalised, control and bidi characters stripped, URLs and addresses masked, wrapped as untrusted data, tags stripped so a planted closing tag cannot break out.

package/dist/packages/mcp/assets/kb/docs/docs-larp.md

@@ -19,6 +19,6 @@ sources:
 date: 2026-10-16
 ---
 
-Vet the product behind a coin: its website, domain registration and GitHub, read-only, only when you ask.
+Vet the product behind a coin: its website, domain registration, GitHub and X account, read-only, only when you ask, with a 0-100 LARP score that shows every point.
 
 A memecoin's advertised website, X and Telegram are claims. The LARP detector fetches what it can, reads it mechanically, and lets the analyst grade the claims against what it found. It runs only when you press `V` on a live token; nothing is fetched automatically.

package/dist/packages/mcp/assets/kb/docs/docs-live-trading-changed-in-0-1-7.md

@@ -0,0 +1,26 @@
+---
+id: docs-live-trading-changed-in-0-1-7
+title: Live trading › Changed in 0.1.7
+kind: docs
+page: live-trading
+page_title: Live trading
+heading: Changed in 0.1.7
+anchor: changed-in-0-1-7
+url: https://dexterm.xyz/docs/live-trading#changed-in-0-1-7
+tags:
+  - docs
+  - live-trading
+  - changed
+  - live
+  - trading
+confidence: high
+owner: maintainers
+origin: docs-generated
+reviewed_by: generated@2026-10-16
+generated_from: dexterm/site content/docs (task-1420)
+sources:
+  - site/content/docs/live-trading.md
+date: 2026-10-16
+---
+
+Earlier 0.1.7 test builds had an experimental local live signer with a dedicated trading wallet, and a LIVE trade ticket signed in Phantom. Both were removed before release, because dexterm should not hold a key. Sending orders to a trading bot of your choice automatically is next (0.1.8, see the roadmap (https://dexterm.xyz/roadmap/)), still with no key in dexterm.

package/dist/packages/mcp/assets/kb/docs/docs-live-trading-stopping.md

@@ -0,0 +1,28 @@
+---
+id: docs-live-trading-stopping
+title: Live trading › Stopping
+kind: docs
+page: live-trading
+page_title: Live trading
+heading: Stopping
+anchor: stopping
+url: https://dexterm.xyz/docs/live-trading#stopping
+tags:
+  - docs
+  - live-trading
+  - stopping
+  - live
+  - trading
+confidence: high
+owner: maintainers
+origin: docs-generated
+reviewed_by: generated@2026-10-16
+generated_from: dexterm/site content/docs (task-1420)
+sources:
+  - site/content/docs/live-trading.md
+date: 2026-10-16
+---
+
+- `/kill` from your paired chat, `dexterm autotrade stop`, or Ctrl-C in the runner stops a paper run.
+- `dexterm wallet panic` engages the kill switch: every autotrade run and the paper agent desk halt, and nothing starts again until `dexterm wallet resume` (a keypress on a real terminal).
+- To stop live trades, use your trading bot's own controls. dexterm cannot stop them.

package/dist/packages/mcp/assets/kb/docs/docs-live-trading-the-short-version.md

@@ -0,0 +1,34 @@
+---
+id: docs-live-trading-the-short-version
+title: Live trading › The short version
+kind: docs
+page: live-trading
+page_title: Live trading
+heading: The short version
+anchor: the-short-version
+url: https://dexterm.xyz/docs/live-trading#the-short-version
+tags:
+  - docs
+  - live-trading
+  - short
+  - version
+  - live
+  - trading
+confidence: high
+owner: maintainers
+origin: docs-generated
+reviewed_by: generated@2026-10-16
+generated_from: dexterm/site content/docs (task-1420)
+sources:
+  - site/content/docs/live-trading.md
+date: 2026-10-16
+---
+
+> **0.1.7, experimental:** dexterm never holds a key and never signs; live trading happens in the Telegram trading bot of your choice; dexterm 0.1.7 sends alerts and signals to your own bot and does not place orders in it yet; automated order forwarding is next (0.1.8). This path has not been exercised end to end on mainnet yet; testing continues.
+
+- **dexterm never holds a key and never signs a transaction.** It has no trading wallet, no signer and no place to keep a private key. It builds no transaction and sends none.
+- **Live trading happens in a Telegram trading bot of your choice.** That bot holds its own wallet and places the orders. You pick it, you fund it, and its rules and fees are its own.
+- **dexterm's part is the Telegram connector (https://dexterm.xyz/docs/telegram).** Through your own bot, dexterm sends alerts, signals and run control to your chat. You read them and act in the trading bot yourself.
+- **Everything else in dexterm is paper or read-only:** the screener, the analyst, MCP, paper trading (https://dexterm.xyz/docs/paper-trading) and autotrade (https://dexterm.xyz/docs/autotrade) on paper.
+
+> **Not financial advice.** Memecoins rug, pools drain and quotes move. Whatever you trade live, you trade in your trading bot, with money you are ready to lose.

package/dist/packages/mcp/assets/kb/docs/docs-live-trading-using-a-trading-bot-with-dexterm.md

@@ -0,0 +1,33 @@
+---
+id: docs-live-trading-using-a-trading-bot-with-dexterm
+title: Live trading › Using a trading bot with dexterm
+kind: docs
+page: live-trading
+page_title: Live trading
+heading: Using a trading bot with dexterm
+anchor: using-a-trading-bot-with-dexterm
+url: https://dexterm.xyz/docs/live-trading#using-a-trading-bot-with-dexterm
+tags:
+  - docs
+  - live-trading
+  - using
+  - trading
+  - bot
+  - dexterm
+  - live
+confidence: high
+owner: maintainers
+origin: docs-generated
+reviewed_by: generated@2026-10-16
+generated_from: dexterm/site content/docs (task-1420)
+sources:
+  - site/content/docs/live-trading.md
+date: 2026-10-16
+---
+
+1. Pick a Telegram trading bot you trust, and read its own terms, fees and security advice. Fund its wallet with only what you are ready to lose.
+2. Set up dexterm's own bot for your chat: `dexterm telegram setup`, then `dexterm telegram pair`. See Telegram (https://dexterm.xyz/docs/telegram). This is a separate bot that only talks to you.
+3. Run a strategy on paper (`dexterm autotrade run <id> --paper`). Its alerts arrive in your chat.
+4. When you want to act on one, do it in your trading bot.
+
+dexterm has not been tested with any particular trading bot.

package/dist/packages/mcp/assets/kb/docs/docs-live-trading-what-dexterm-does-not-do.md

@@ -0,0 +1,30 @@
+---
+id: docs-live-trading-what-dexterm-does-not-do
+title: Live trading › What dexterm does not do
+kind: docs
+page: live-trading
+page_title: Live trading
+heading: What dexterm does not do
+anchor: what-dexterm-does-not-do
+url: https://dexterm.xyz/docs/live-trading#what-dexterm-does-not-do
+tags:
+  - docs
+  - live-trading
+  - dexterm
+  - does
+  - live
+  - trading
+confidence: high
+owner: maintainers
+origin: docs-generated
+reviewed_by: generated@2026-10-16
+generated_from: dexterm/site content/docs (task-1420)
+sources:
+  - site/content/docs/live-trading.md
+date: 2026-10-16
+---
+
+- It does not place an order in your trading bot for you. In this version you act in the bot yourself.
+- It does not hold, import, create, decrypt or ask for a private key or seed phrase. Anything that asks you for one is not dexterm.
+- It does not sign or send a transaction. `dexterm wallet link` only proves which wallet is yours with a signed **message** in Phantom; dexterm keeps the public key to show your address. It never asks Phantom to sign a transaction.
+- It does not know what your trading bot did. Positions, fills and P/L in dexterm are paper.

package/dist/packages/mcp/assets/kb/docs/docs-live-trading-what-dexterm-does.md

@@ -0,0 +1,29 @@
+---
+id: docs-live-trading-what-dexterm-does
+title: Live trading › What dexterm does
+kind: docs
+page: live-trading
+page_title: Live trading
+heading: What dexterm does
+anchor: what-dexterm-does
+url: https://dexterm.xyz/docs/live-trading#what-dexterm-does
+tags:
+  - docs
+  - live-trading
+  - dexterm
+  - does
+  - live
+  - trading
+confidence: high
+owner: maintainers
+origin: docs-generated
+reviewed_by: generated@2026-10-16
+generated_from: dexterm/site content/docs (task-1420)
+sources:
+  - site/content/docs/live-trading.md
+date: 2026-10-16
+---
+
+- **Finds and explains.** The screener, the token screen, the LARP check (https://dexterm.xyz/docs/larp) and the analyst (https://dexterm.xyz/docs/analyst) read public data. None of them can trade.
+- **Practises on paper.** The paper ticket, paper accounts (https://dexterm.xyz/docs/autotrade#paper-accounts) and paper autotrade runs (the yolo preset (https://dexterm.xyz/docs/yolo) included) fill on a simulated book on your machine.
+- **Tells you in Telegram.** With Telegram (https://dexterm.xyz/docs/telegram) set up and paired, a paper run sends candidates, entries, exits, halts and a daily summary to your chat, and takes `/status`, `/pause`, `/resume`, `/kill`, `/flatten` and `/use` from it.

package/dist/packages/mcp/assets/kb/docs/docs-live-trading.md

@@ -0,0 +1,23 @@
+---
+id: docs-live-trading
+title: Live trading
+kind: docs
+page: live-trading
+page_title: Live trading
+url: https://dexterm.xyz/docs/live-trading
+tags:
+  - docs
+  - live-trading
+  - live
+  - trading
+confidence: high
+owner: maintainers
+origin: docs-generated
+reviewed_by: generated@2026-10-16
+generated_from: dexterm/site content/docs (task-1420)
+sources:
+  - site/content/docs/live-trading.md
+date: 2026-10-16
+---
+
+dexterm never holds a key and never signs a transaction. Live trading happens in a Telegram trading bot of your choice; dexterm's part is the Telegram connector, which sends alerts, signals and run control to your chat. Not financial advice.

package/dist/packages/mcp/assets/kb/docs/docs-ollama-another-machine.md

@@ -0,0 +1,28 @@
+---
+id: docs-ollama-another-machine
+title: Use a local model with Ollama › Another machine
+kind: docs
+page: ollama
+page_title: Use a local model with Ollama
+heading: Another machine
+anchor: another-machine
+url: https://dexterm.xyz/docs/ollama#another-machine
+tags:
+  - docs
+  - ollama
+  - another
+  - machine
+  - use
+  - local
+  - model
+confidence: high
+owner: maintainers
+origin: docs-generated
+reviewed_by: generated@2026-10-16
+generated_from: dexterm/site content/docs (task-1420)
+sources:
+  - site/content/docs/ollama.md
+date: 2026-10-16
+---
+
+`dexterm ai host http://<machine>:11434` points dexterm at an Ollama on another computer you control. Prompts, screen context and tool results then travel over your network, and `dexterm ai status`, `dexterm doctor` and each chat answer say so. dexterm contacts no other host for the local engine. It never follows a redirect: if the host answers with one, dexterm sends nothing on, and `dexterm doctor` and the chat answer say the host redirected.

package/dist/packages/mcp/assets/kb/docs/docs-ollama-autotrade-on-a-local-model.md

@@ -0,0 +1,29 @@
+---
+id: docs-ollama-autotrade-on-a-local-model
+title: Use a local model with Ollama › Autotrade on a local model
+kind: docs
+page: ollama
+page_title: Use a local model with Ollama
+heading: Autotrade on a local model
+anchor: autotrade-on-a-local-model
+url: https://dexterm.xyz/docs/ollama#autotrade-on-a-local-model
+tags:
+  - docs
+  - ollama
+  - autotrade
+  - local
+  - model
+  - use
+confidence: high
+owner: maintainers
+origin: docs-generated
+reviewed_by: generated@2026-10-16
+generated_from: dexterm/site content/docs (task-1420)
+sources:
+  - site/content/docs/ollama.md
+date: 2026-10-16
+---
+
+`dexterm autotrade run <strategy> --paper --engine ollama` (or `dexterm ai engine ollama --surface autotrade`) runs each candidate's session on your local model. The session has no tools: the request to Ollama never carries any, so the model can only answer. Its reply is constrained to `{comment, decision}` and turned into the same `DECISION {…}` line a Claude session writes, so the same closed schema, clamp, caps and run file apply. A reply later than the strategy's decision window is no answer. `--model <name>` picks another local model for the run. The run file records `agent: ollama`, the model and $0.
+
+The runner needs the `paper` profile and refuses to start below it, with the command that raises it.

package/dist/packages/mcp/assets/kb/docs/docs-ollama-check-your-model-dexterm-ai-probe.md

@@ -0,0 +1,38 @@
+---
+id: docs-ollama-check-your-model-dexterm-ai-probe
+title: Use a local model with Ollama › Check your model: dexterm ai probe
+kind: docs
+page: ollama
+page_title: Use a local model with Ollama
+heading: Check your model: dexterm ai probe
+anchor: check-your-model-dexterm-ai-probe
+url: https://dexterm.xyz/docs/ollama#check-your-model-dexterm-ai-probe
+tags:
+  - docs
+  - ollama
+  - check
+  - model
+  - dexterm
+  - probe
+  - use
+  - local
+confidence: high
+owner: maintainers
+origin: docs-generated
+reviewed_by: generated@2026-10-16
+generated_from: dexterm/site content/docs (task-1420)
+sources:
+  - site/content/docs/ollama.md
+date: 2026-10-16
+---
+
+`dexterm ai probe` checks that Ollama answers, the model is pulled, it can call tools, and how much context it has. `dexterm ai probe --json` also asks it three short trading questions and checks it answers in the decision format the AUTOTRADE runner needs. It warns when the model is below the bar for your profile:
+
+| profile | tool calling | context | decision format |
+|---|---|---|---|
+| `observe` | optional | ≥ 4,096 | not needed |
+| `propose` | yes | ≥ 8,192 | not needed |
+| `paper` | yes | ≥ 8,192 | 2 of 3 |
+| `full` | yes | ≥ 16,384 | 3 of 3 |
+
+A decision a model cannot format is refused by the engine, which means fewer trades, never bigger ones.

package/dist/packages/mcp/assets/kb/docs/docs-ollama-how-we-checked.md

@@ -0,0 +1,27 @@
+---
+id: docs-ollama-how-we-checked
+title: Use a local model with Ollama › How we checked
+kind: docs
+page: ollama
+page_title: Use a local model with Ollama
+heading: How we checked
+anchor: how-we-checked
+url: https://dexterm.xyz/docs/ollama#how-we-checked
+tags:
+  - docs
+  - ollama
+  - checked
+  - use
+  - local
+  - model
+confidence: high
+owner: maintainers
+origin: docs-generated
+reviewed_by: generated@2026-10-16
+generated_from: dexterm/site content/docs (task-1420)
+sources:
+  - site/content/docs/ollama.md
+date: 2026-10-16
+---
+
+Offline tests drive a fake Ollama server through the real app paths and the real dexterm MCP server: tool round trips, the tool list each profile offers, refused calls that never run, the no-tools mode, structured verdicts, the typed `full` confirmation, and the doctor lines. The firewall test checks the local model receives exactly the text the Claude CLI receives. The caps test runs the same decisions through the Claude path's session interface and a local session over a recorded tape and gets identical clamps, refusals and fills. Answer quality and speed of local models against Claude have not been benchmarked.

package/dist/packages/mcp/assets/kb/docs/docs-ollama-models-without-tool-calling.md

@@ -0,0 +1,32 @@
+---
+id: docs-ollama-models-without-tool-calling
+title: Use a local model with Ollama › Models without tool calling
+kind: docs
+page: ollama
+page_title: Use a local model with Ollama
+heading: Models without tool calling
+anchor: models-without-tool-calling
+url: https://dexterm.xyz/docs/ollama#models-without-tool-calling
+tags:
+  - docs
+  - ollama
+  - models
+  - without
+  - tool
+  - calling
+  - use
+  - local
+  - model
+confidence: high
+owner: maintainers
+origin: docs-generated
+reviewed_by: generated@2026-10-16
+generated_from: dexterm/site content/docs (task-1420)
+sources:
+  - site/content/docs/ollama.md
+date: 2026-10-16
+---
+
+If the model cannot call tools, dexterm fetches the selected coin's dossier itself and the model answers from it, and the answer starts with `(… has no tool calling: answering from the dossier without tools)`. Structured verdicts carry a `no_tools_mode` flag. For tool use pull a tool-capable model (the table above).
+
+A local model that keeps asking for a tool it does not have is refused each time (the call never runs); after three refusals the turn stops and says so.