@vtxmacro/cli 2026.6.22 → 2026.8.11

package/README.md

@@ -2,16 +2,21 @@
 
 Command-line and MCP access for VTX Macro automation.
 
-## Install
+## Install or update
 
 ```bash
 npm install -g @vtxmacro/cli
+vtx --version
 ```
 
+The host supports Windows x64 and Linux x64, including WSL. The package installs
+the exact supported OpenAI Codex runtime for those platforms.
+The VTX host verifies that native runtime's version and digest before use; it
+does not borrow a Codex binary from PATH or an editor extension.
+
 ## Configure
 
 ```bash
-export VTX_API_URL="https://api.vtxmacro.com"
 export VTX_PROFILE_ID="<profile-id>"
 vtx auth login --scopes read,bot:control
 ```
@@ -22,14 +27,8 @@ vtx auth login --scopes read,bot:control
 vtx --json auth whoami
 vtx --json bots status
 vtx --profile <profile-id> runtime run --follow
-vtx auth login --scopes read,insights:connect
-vtx --profile <profile-id> insights connect
 ```
 
-The Insights connector talks only to a loopback OpenAI-compatible model server.
-It defaults to LM Studio at `http://127.0.0.1:1234/v1` and reads its optional
-API key from `LM_STUDIO_API_KEY`. The key and local URL never leave the device.
-
 ## MCP
 
 Configure your MCP-compatible agent app to start:
@@ -39,3 +38,81 @@ vtx-mcp
 ```
 
 The CLI and MCP server use the same saved token and environment variables.
+
+## Agent inference hosts
+
+Both paths use a separate least-privilege `insights:inference` OAuth grant.
+VTX never receives an agent vendor password, OAuth token, or subscription
+credential.
+
+### Automated Codex host
+
+```bash
+vtx inference-host login
+vtx inference-host codex-login
+vtx inference-host doctor --json
+vtx inference-host run
+vtx inference-host status --json
+vtx inference-host logout
+vtx inference-host codex-logout
+vtx inference-host revoke
+```
+
+This foreground host uses a separate least-privilege `insights:inference`
+OAuth grant. It also keeps its ChatGPT subscription login in a dedicated private
+Codex home. Neither credential is copied from or widens the ordinary CLI or Codex
+session. VTX logout/revoke and Codex logout are intentionally separate operations.
+
+### Any compatible agent harness
+
+Codex, Claude Code, Cursor, GitHub Copilot, Antigravity, and other agents that can
+run shell commands can use their existing first-party session without a
+VTX-owned vendor adapter:
+
+```bash
+vtx inference-host login
+vtx inference-host agent-connect \
+  --adapter <lowercase-harness-id> \
+  --model <exact-model-id> \
+  --model-label "<display label>" \
+  --effort <reasoning-effort> \
+  --json
+vtx inference-host agent-next --wait-seconds 50 --json
+```
+
+`agent-next` returns separate exact `system_prompt`, `user_prompt`,
+`context_json`, and `output_schema_json` fields. The agent reasons in its own
+session, then writes one JSON object to `agent-complete` stdin. At minimum that
+object contains a `result` string. If the harness exposes exact token usage,
+include the published usage object; otherwise VTX records usage as explicitly
+unavailable. For `agent-fail`, choose the truthful dispatch state and set
+`retryable` true only when a fresh attempt is safe:
+
+```json
+{"dispatch_outcome":"not_dispatched","failure_category":"adapter","failure_code":"harness_unavailable","retryable":true}
+{"dispatch_outcome":"confirmed_dispatched","failure_category":"adapter","failure_code":"no_reliable_result","retryable":false}
+{"dispatch_outcome":"outcome_unknown","failure_category":"transport","failure_code":"dispatch_confirmation_lost","retryable":false}
+```
+
+Use `not_dispatched` only when no harness inference began,
+`confirmed_dispatched` when it began but returned no trustworthy result, and
+`outcome_unknown` when dispatch itself cannot be confirmed. Pipe exactly one
+object to `vtx inference-host agent-fail --json`.
+
+Keep calling `agent-next` while the host should remain available. This same loop
+supports Main, Review, and Screener; Provider response and Decision candidate;
+and normally running VTX Client Mode or Server Mode bots. Server Mode keeps the
+normal VTX call fee. Client Mode has no VTX platform fee. Neither mode falls back
+to another model when the agent host is unavailable.
+
+## Remove
+
+First revoke the VTX inference grant, then uninstall the package. Automated
+Codex users should also remove the dedicated Codex login:
+
+```bash
+vtx inference-host revoke
+# Automated Codex host only:
+vtx inference-host codex-logout
+npm uninstall -g @vtxmacro/cli
+```

package/bin/vtx-mcp.js

@@ -256,33 +256,6 @@ var VtxAgentClient = class _VtxAgentClient {
   getLlmConfig(profileId) {
     return this.request("/llm/config", { profileId });
   }
-  registerInsightConnector(profileId, payload) {
-    return this.request("/insights/connectors/register", {
-      method: "POST",
-      profileId,
-      body: payload
-    });
-  }
-  claimInsightConnectorJob(profileId, connectorId, deviceId) {
-    return this.request(
-      `/insights/connectors/${encodeURIComponent(connectorId)}/jobs:claim`,
-      { method: "POST", profileId, body: { device_id: deviceId } }
-    );
-  }
-  completeInsightConnectorJob(profileId, connectorId, jobId, deviceId, payload) {
-    const params = new URLSearchParams({ device_id: deviceId });
-    return this.request(
-      `/insights/connectors/${encodeURIComponent(connectorId)}/jobs/${encodeURIComponent(jobId)}:complete?${params}`,
-      { method: "POST", profileId, body: payload }
-    );
-  }
-  heartbeatInsightConnectorJob(profileId, connectorId, jobId, deviceId, claimToken) {
-    const params = new URLSearchParams({ device_id: deviceId });
-    return this.request(
-      `/insights/connectors/${encodeURIComponent(connectorId)}/jobs/${encodeURIComponent(jobId)}:heartbeat?${params}`,
-      { method: "POST", profileId, body: { claim_token: claimToken } }
-    );
-  }
   heartbeatRuntime(profileId, payload, leaseToken) {
     return this.request("/trading/ai/runtime/heartbeat", {
       method: "POST",
@@ -995,7 +968,7 @@ async function handleMcpJsonRpcRequest(request, clientFactory = createDefaultMcp
       },
       serverInfo: {
         name: "vtx-macro",
-        version: "2026.6.22"
+        version: "2026.6.23"
       }
     });
   }