dexterm-cli 0.1.6 → 0.1.7

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.

package/dist/packages/mcp/assets/kb/docs/docs-ollama-pick-the-engine-globally-or-per-surface.md

@@ -0,0 +1,43 @@
+---
+id: docs-ollama-pick-the-engine-globally-or-per-surface
+title: Use a local model with Ollama › Pick the engine, globally or per surface
+kind: docs
+page: ollama
+page_title: Use a local model with Ollama
+heading: Pick the engine, globally or per surface
+anchor: pick-the-engine-globally-or-per-surface
+url: https://dexterm.xyz/docs/ollama#pick-the-engine-globally-or-per-surface
+tags:
+  - docs
+  - ollama
+  - pick
+  - engine
+  - globally
+  - per
+  - surface
+  - 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 engine <auto|claude|codex|ollama>` sets the engine for everything; add `--surface analyst|autotrade|agent` to set one surface only (for example the analyst on Claude and paper autotrade on the local model). `dexterm ai status` shows the engine for each surface, the local model, the profile and a quick probe; `dexterm ai status --parity` adds the full list of what runs where.
+
+For the analyst the order is: `--analyst-engine`, then `DEXTERM_ANALYST_ENGINE`, then `analyst.engine` in `config.json`, then `ai.json`, then `auto`. **`auto` is unchanged**: Claude Code when it is installed, else Codex, else the local model once you set one up (or Ollama is installed). With none of them, the analyst says how to set up an AI backend, and `dexterm doctor` lists all three ways.
+
+The settings live in `~/.dexterm/ai.json` (mode 0600). Only you write it, with `dexterm ai …` or by hand. No MCP tool, chat message, Telegram command or model output can change it.
+
+| setting | how |
+|---|---|
+| engine | `dexterm ai engine ollama` · `DEXTERM_AI_PROVIDER` · per surface `--surface S` |
+| model | `dexterm ai model <name>` · `DEXTERM_OLLAMA_MODEL` (when none is set dexterm picks the first suggested model you pulled) |
+| host | `dexterm ai host <url>` · `DEXTERM_OLLAMA_HOST` (default `http://127.0.0.1:11434`) |
+| context | `dexterm ai ctx <tokens>` |
+| profile | `dexterm ai restrictions observe|propose|paper` · `dexterm ai engine ollama --full` · `DEXTERM_AI_RESTRICTIONS` can only lower it |

package/dist/packages/mcp/assets/kb/docs/docs-ollama-restriction-profiles.md

@@ -0,0 +1,35 @@
+---
+id: docs-ollama-restriction-profiles
+title: Use a local model with Ollama › Restriction profiles
+kind: docs
+page: ollama
+page_title: Use a local model with Ollama
+heading: Restriction profiles
+anchor: restriction-profiles
+url: https://dexterm.xyz/docs/ollama#restriction-profiles
+tags:
+  - docs
+  - ollama
+  - restriction
+  - profiles
+  - 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
+---
+
+| profile | the local engine may |
+|---|---|
+| `observe` | analyse only: the read tools, no UI actions, no proposals, no orders |
+| `propose` | everything the analyst does on Claude: the read tools, the UI actions (open a coin, the screener, the watchlist, a feed, and open a PAPER ticket that you confirm), and strategy proposals you apply with a key. No orders. |
+| `paper` | `propose`, plus paper orders: the AUTOTRADE runner's paper sessions, agent paper trading (https://dexterm.xyz/docs/agents) inside a mandate you armed, starting or stopping one of your parallel strategies (https://dexterm.xyz/docs/autotrade#several-strategies-at-once), paper journal tags and backtest requests |
+| `full` | everything the Claude path may do, inside the same caps, mandate tiers and kill switch |
+
+**A new local setup starts at `propose`.** `paper` is one command: `dexterm ai restrictions paper`. **`full` needs a typed confirmation** on a real terminal: `dexterm ai engine ollama --full` explains the small-model risk and asks you to type `ENABLE FULL`. It is recorded for that one model: change the model and the engine runs at `paper` until you confirm again. Going back to a lower profile forgets the confirmation. It needs you at a real terminal: a pipe cannot confirm it.

package/dist/packages/mcp/assets/kb/docs/docs-ollama-set-it-up-in-two-minutes.md

@@ -0,0 +1,39 @@
+---
+id: docs-ollama-set-it-up-in-two-minutes
+title: Use a local model with Ollama › Set it up in two minutes
+kind: docs
+page: ollama
+page_title: Use a local model with Ollama
+heading: Set it up in two minutes
+anchor: set-it-up-in-two-minutes
+url: https://dexterm.xyz/docs/ollama#set-it-up-in-two-minutes
+tags:
+  - docs
+  - ollama
+  - set
+  - two
+  - minutes
+  - 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
+---
+
+```
+1. install Ollama            https://ollama.com/download   (open it once so it runs)
+2. ollama pull qwen3:8b      about 5 GB, once
+3. dexterm ai engine ollama  run dexterm's AI on the local engine
+4. dexterm ai model qwen3:8b
+5. dexterm doctor            the "Ollama (local AI)" line should be a ✓
+```
+
+Then press `a` on a coin, or type a question, as usual. The panel title says `ANALYST · ollama` and the caption under an answer shows `local $0`. In the chat box, `/engine ollama` switches new conversations to the local model and `/engine claude` switches back.
+
+dexterm never downloads or ships a model: you pull the one you want with Ollama.

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

@@ -0,0 +1,35 @@
+---
+id: docs-ollama-troubleshooting
+title: Use a local model with Ollama › Troubleshooting
+kind: docs
+page: ollama
+page_title: Use a local model with Ollama
+heading: Troubleshooting
+anchor: troubleshooting
+url: https://dexterm.xyz/docs/ollama#troubleshooting
+tags:
+  - docs
+  - ollama
+  - troubleshooting
+  - 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
+---
+
+| message | fix |
+|---|---|
+| `ollama is not running` | open the Ollama app or run `ollama serve`, then `dexterm doctor` |
+| `no local model pulled` | `ollama pull qwen3:8b` then `dexterm ai model qwen3:8b` |
+| `ollama model … is not pulled` | `ollama pull <model>` |
+| `the local model took too long` | a smaller model answers faster; `dexterm ai status` lists yours |
+| `… did not return the structured verdict` | ask again, or pull a larger tool-capable model |
+| `the local engine's restriction profile is propose; an autotrade run needs paper` | `dexterm ai restrictions paper` |
+| `full was confirmed for …, not …` | `dexterm ai engine ollama --full` again for the new model |

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

@@ -0,0 +1,39 @@
+---
+id: docs-ollama-what-runs-on-a-local-model
+title: Use a local model with Ollama › What runs on a local model
+kind: docs
+page: ollama
+page_title: Use a local model with Ollama
+heading: What runs on a local model
+anchor: what-runs-on-a-local-model
+url: https://dexterm.xyz/docs/ollama#what-runs-on-a-local-model
+tags:
+  - docs
+  - ollama
+  - runs
+  - 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
+---
+
+| surface | on the local model |
+|---|---|
+| analyst chat and follow-ups | the same dexterm MCP server and tools, the same firewalled context, answers streamed word by word |
+| structured skills (dossier, rug-check, larp-check, trench-scan) | the same playbook, then Ollama's structured output on the same schema |
+| AI scan mode (https://dexterm.xyz/docs/scan) | observe-only, at the tool list, the MCP server and the app |
+| Jarvis voice questions | asked through the same analyst, on whichever engine `/engine` picked |
+| `dexterm ask "…"` | a headless question on the analyst's engine |
+| tune by chat | `strategy_propose_edit` / `strategy_propose_new` at `propose`; you apply with `y` as always |
+| AUTOTRADE runner sessions | `dexterm autotrade run <strategy> --paper --engine ollama`: the same DOSSIER, DELTA and EVENT messages and the same typed decision, at `paper` |
+| an agent on the dexterm tools | `dexterm ai agent "<goal>"`, tools by profile |
+| Telegram approvals, the agent bus | engine-independent: approvals are your taps; bus agents bring their own model |
+
+The Claude usage guard does not apply to a local model (no plan limit, $0); the runner's day caps on sessions and turns still do.

package/dist/packages/mcp/assets/kb/docs/docs-ollama-what-stays-outside-the-model.md

@@ -0,0 +1,36 @@
+---
+id: docs-ollama-what-stays-outside-the-model
+title: Use a local model with Ollama › What stays outside the model
+kind: docs
+page: ollama
+page_title: Use a local model with Ollama
+heading: What stays outside the model
+anchor: what-stays-outside-the-model
+url: https://dexterm.xyz/docs/ollama#what-stays-outside-the-model
+tags:
+  - docs
+  - ollama
+  - stays
+  - outside
+  - model
+  - 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
+---
+
+Whatever profile you pick, and whichever engine runs:
+
+- your strategy and runner caps, and the kill switch (command, hotkey, the panic file);
+- mandate tiers: arming a mandate is a physical keypress, and no model or agent can arm one;
+- the strategy clamp: every size a model asks for is cut to your strategy and your runner caps, exactly as for Claude;
+- Telegram approvals, when you use them: a one-time button, bound to a nonce, a hash and an expiry and to your account, tapped by you;
+- the prompt firewall: token names, socials and page text reach a local model wrapped as `<untrusted>` data, byte for byte as they reach Claude.
+
+A model can only ask. It cannot raise a cap, arm a mandate or change its own profile. There is no live mode for it to turn on: dexterm trades on paper only.

package/dist/packages/mcp/assets/kb/docs/docs-ollama-which-model.md

@@ -0,0 +1,38 @@
+---
+id: docs-ollama-which-model
+title: Use a local model with Ollama › Which model
+kind: docs
+page: ollama
+page_title: Use a local model with Ollama
+heading: Which model
+anchor: which-model
+url: https://dexterm.xyz/docs/ollama#which-model
+tags:
+  - docs
+  - ollama
+  - which
+  - model
+  - 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
+---
+
+These are tool-capable models from Ollama's library, a good place to start. They are suggestions, not a dexterm benchmark: `dexterm ai probe` checks the copy you pulled.
+
+| model | download | note |
+|---|---|---|
+| `qwen3:8b` | ~5 GB | a good default on a 16 GB machine |
+| `qwen3:14b` | ~9 GB | steadier tool use, needs about 16 GB free |
+| `llama3.1:8b` | ~5 GB | a widely used tool caller |
+| `mistral-small3.2` | ~15 GB | strong tool use on a 32 GB machine |
+
+Smaller models answer faster and make more mistakes. A model with no tool calling still works for questions (see models without tool calling (https://dexterm.xyz/docs/ollama#models-without-tool-calling)).
+
+dexterm asks Ollama for a 32,768-token context window, or the model's own maximum when that is smaller. On a small machine lower it with `dexterm ai ctx 16384`.

package/dist/packages/mcp/assets/kb/docs/docs-ollama-your-own-agent-on-the-local-model.md

@@ -0,0 +1,28 @@
+---
+id: docs-ollama-your-own-agent-on-the-local-model
+title: Use a local model with Ollama › Your own agent, on the local model
+kind: docs
+page: ollama
+page_title: Use a local model with Ollama
+heading: Your own agent, on the local model
+anchor: your-own-agent-on-the-local-model
+url: https://dexterm.xyz/docs/ollama#your-own-agent-on-the-local-model
+tags:
+  - docs
+  - ollama
+  - own
+  - agent
+  - 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 ai agent "<goal>"` runs the local model as an agent on the dexterm MCP server, the way `claude -p` connected to `dexterm mcp` would: the read tools at every profile, proposals at `propose`, and the paper tools at `paper` (the server still refuses them unless you armed a mandate and turned on agent paper trading in the app). `--thoughts FILE` writes its words for the spectator (https://dexterm.xyz/docs/spectator)'s thought ribbon (`--spectate-thoughts FILE`).

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

@@ -0,0 +1,28 @@
+---
+id: docs-ollama
+title: Use a local model with Ollama
+kind: docs
+page: ollama
+page_title: Use a local model with Ollama
+url: https://dexterm.xyz/docs/ollama
+tags:
+  - docs
+  - ollama
+  - 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
+---
+
+Run the analyst, your agents and paper autotrade on a free model on your own machine, with no login and no key, behind a restriction profile you choose.
+
+dexterm can run its AI on **a model on your own computer** through Ollama (https://ollama.com), instead of your Claude or Codex login. There is no account, no key and no bill: the model runs on your machine and every answer costs $0. dexterm talks to Ollama on `http://127.0.0.1:11434` by default, so your questions, the screen context and the tool results stay on this machine.
+
+A local engine can do everything the Claude path does: the analyst and its skills, tune-by-chat strategy proposals, the AUTOTRADE runner's sessions, and an agent on the dexterm tools. You decide how far it may go with a **restriction profile**. The limits that protect money are not part of that choice: they are enforced outside the model and are the same for every engine (see what stays outside the model (https://dexterm.xyz/docs/ollama#what-stays-outside-the-model)).

package/dist/packages/mcp/assets/kb/docs/docs-paper-trading-letting-an-agent-paper-trade-experimental.md

@@ -1,9 +1,9 @@
 ---
 id: docs-paper-trading-letting-an-agent-paper-trade-experimental
-title: Paper trading, live trading and the safety model › Letting an agent paper trade (experimental)
+title: Paper trading and the safety model › Letting an agent paper trade (experimental)
 kind: docs
 page: paper-trading
-page_title: Paper trading, live trading and the safety model
+page_title: Paper trading and the safety model
 heading: Letting an agent paper trade (experimental)
 anchor: letting-an-agent-paper-trade-experimental
 url: https://dexterm.xyz/docs/paper-trading#letting-an-agent-paper-trade-experimental
@@ -16,7 +16,6 @@ tags:
   - trade
   - experimental
   - trading
-  - live
   - safety
   - model
 confidence: high
@@ -29,4 +28,4 @@ sources:
 date: 2026-10-16
 ---
 
-If you want to, you can let an agent connected over `dexterm mcp` run the whole PAPER loop (open, size, confirm and close) inside a **trading mandate** you armed, by starting `dexterm --spectate-mcp --agent-paper <mandate-id>`. It is paper only. The agent can never sign, send a real transaction, touch keys or raise a cap, a size over your caps is refused, and you can pause, take over or stop it at any time. See Agent paper trading (https://dexterm.xyz/docs/agents#agent-paper-trading). It is experimental and off by default, and simulated figures are not a result.
+If you want to, you can let an agent connected over `dexterm mcp` run the whole PAPER loop (open, size, confirm and close) inside a **trading mandate** you armed, by starting `dexterm --spectate-mcp --agent-paper <mandate-id>`. It is paper only. The agent can never sign, send a transaction, touch keys or raise a cap, a size over your caps is refused, and you can pause, take over or stop it at any time. See Agent paper trading (https://dexterm.xyz/docs/agents#agent-paper-trading). It is experimental and off by default, and simulated figures are not a result.

package/dist/packages/mcp/assets/kb/docs/docs-paper-trading-link-a-wallet-read-only.md

@@ -0,0 +1,30 @@
+---
+id: docs-paper-trading-link-a-wallet-read-only
+title: Paper trading and the safety model › Link a wallet (read-only)
+kind: docs
+page: paper-trading
+page_title: Paper trading and the safety model
+heading: Link a wallet (read-only)
+anchor: link-a-wallet-read-only
+url: https://dexterm.xyz/docs/paper-trading#link-a-wallet-read-only
+tags:
+  - docs
+  - paper-trading
+  - link
+  - wallet
+  - read-only
+  - paper
+  - trading
+  - safety
+  - 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/paper-trading.md
+date: 2026-10-16
+---
+
+`dexterm wallet link` (or `/wallet link` typed on the screener's `/` line or in the chat box) starts a one-shot server on `127.0.0.1:41291` (a fixed loopback port; a random one only if it is busy, and the page then says so) with a single-use token, and opens your browser to it. The page asks Phantom to **connect** and **sign a message** (a dexterm nonce): no transaction, no approval of funds. dexterm verifies the Ed25519 proof and stores **only your public key** in `~/.dexterm/wallet-link.json`, to show your address. `dexterm wallet status`, `unlink`, `/wallet`, `/wallet unlink` show or remove it. No private key, seed or password ever reaches dexterm; it has no code that could hold one, and it never asks Phantom to sign a transaction.