@lazyingart/agintiflow 0.19.0 → 0.19.2

package/README.md

@@ -60,7 +60,7 @@ printf '%s' "$VENICE_API_KEY" | aginti keys set venice --stdin
 
 # optional image-generation auxiliary skill:
 aginti login grsai
-# inside chat, use /auxilliary grsai or /auxiliary grsai
+# inside chat, use /auxiliary grsai
 ```
 
 Start an interactive Codex-style CLI chat from any project folder:
@@ -77,7 +77,7 @@ Inside chat, type normal requests such as `write a small Python CLI app with tes
 
 For code edits, AgInTiFlow routes patch/refactor/database-style tasks to DeepSeek v4 pro by default and exposes `apply_patch` as a deterministic workspace tool. It supports exact replacements, Codex-style patch envelopes, and unified diffs, with preflight checks, path guardrails, hashes, and compact per-file diffs. See [docs/patch-tools.md](docs/patch-tools.md).
 
-Model choice is role-based: `/route` defaults to DeepSeek V4 Flash, `/model` or `/main` defaults to DeepSeek V4 Pro, `/spare` defaults to OpenAI GPT-5.4 medium, `/wrapper` defaults to Codex GPT-5.5 medium when enabled, and `/auxilliary` defaults to GRS AI/Nano Banana for image tools. See [docs/model-selection.md](docs/model-selection.md) and run `aginti models`.
+Model choice is role-based: `/route` defaults to DeepSeek V4 Flash, `/model` or `/main` defaults to DeepSeek V4 Pro, `/spare` defaults to OpenAI GPT-5.4 medium, `/wrapper` defaults to Codex GPT-5.5 medium when enabled, and `/auxiliary` defaults to GRS AI/Nano Banana for image tools. See [docs/model-selection.md](docs/model-selection.md) and run `aginti models`.
 
 For larger repositories, use `--profile large-codebase` or choose **Large codebase engineering** in the web UI. The web default stays **Auto**, and Auto now escalates codebase/system/debugging prompts to the same engineering loop when needed. Complex work routes to DeepSeek v4 pro, starts with `inspect_project`, then uses search/read/patch/check loops inspired by Codex, Copilot SDK, Claude Code, Gemini CLI, Qwen, and Claw Code. See [docs/large-codebase-engineering.md](docs/large-codebase-engineering.md).
 

package/docs/auxiliary-image-generation.md

@@ -22,7 +22,6 @@ printf '%s' "$VENICE_API_KEY" | aginti keys set venice --stdin
 Inside interactive chat, use either spelling:
 
 ```text
-/auxilliary grsai
 /auxiliary grsai
 ```
 

package/docs/model-selection.md

@@ -10,7 +10,7 @@ AgInTiFlow treats model choice as a role-based control plane. A provider supplie
 | Main | `/model` or `/main` | `deepseek/deepseek-v4-pro` | Complex executor for coding, debugging, writing, and long tasks. |
 | Spare | `/spare` | `openai/gpt-5.4` with `medium` reasoning | Optional fallback or cross-check model. |
 | Wrapper | `/wrapper` | `codex gpt-5.5 medium` | External coding assistant when wrapper tools are enabled. |
-| Auxiliary | `/auxilliary` | `grsai/nano-banana-2` | Image/media tools; Venice image models are optional. |
+| Auxiliary | `/auxiliary` | `grsai/nano-banana-2` | Image/media tools; Venice image models are optional. |
 
 Smart routing still works as before: normal work goes to the route model, and complex work goes to the main model. Manual provider/model selection remains available for one-off runs.
 
@@ -33,13 +33,23 @@ Interactive commands:
 
 ```text
 /models
+/venice
 /route deepseek/deepseek-v4-flash
 /model deepseek/deepseek-v4-pro
 /spare openai/gpt-5.4 medium
 /wrapper codex gpt-5.5 medium
-/auxilliary model grsai/nano-banana-2
+/auxiliary model grsai/nano-banana-2
 ```
 
+`/venice` is a shortcut for:
+
+```text
+/route venice/venice-uncensored-1-2
+/main venice/venice-uncensored-1-2
+```
+
+It keeps smart routing enabled, so normal and complex tasks still use the same route/main policy, but both roles resolve to Venice Uncensored 1.2. If the Venice key is missing, run `/auth venice`.
+
 ## Provider Buckets
 
 | Bucket | Provider | Typical use |
@@ -67,4 +77,3 @@ printf '%s' "$VENICE_API_KEY" | aginti keys set venice --stdin
 ```
 
 The web UI mirrors the same roles in its **Model roles** panel. Use the top provider/model fields for manual runs; use the role fields to change how smart routing chooses route, main, spare, wrapper, and auxiliary models.
-

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lazyingart/agintiflow",
-  "version": "0.19.0",
+  "version": "0.19.2",
   "type": "module",
   "description": "AgInTiFlow is a web-first coding agent and CLI with DeepSeek routing, sandboxed tools, model providers, canvas artifacts, and optional wrappers.",
   "license": "Apache-2.0",

package/references/model-routing-provider-design.md

@@ -22,7 +22,7 @@ The UI should be role-first rather than provider-first:
 - **Main model (`/model` or `/main`):** complex executor. Default `deepseek/deepseek-v4-pro`.
 - **Spare model (`/spare`):** fallback/cross-check model. Default `openai/gpt-5.4` with `medium` reasoning.
 - **Wrapper (`/wrapper`):** external coding assistant. Default Codex with `gpt-5.5` medium reasoning, disabled unless wrapper tools are enabled.
-- **Auxiliary (`/auxilliary`):** media/image tools. Default `grsai/nano-banana-2`; Venice image models are optional.
+- **Auxiliary (`/auxiliary`):** media/image tools. Default `grsai/nano-banana-2`; Venice image models are optional.
 
 This keeps the mental model stable: providers are supply, roles are policy.
 
@@ -42,13 +42,16 @@ Interactive equivalents:
 
 ```text
 /models
+/venice
 /route deepseek/deepseek-v4-flash
 /model deepseek/deepseek-v4-pro
 /spare openai/gpt-5.4 medium
 /wrapper codex gpt-5.5 medium
-/auxilliary model grsai/nano-banana-2
+/auxiliary model grsai/nano-banana-2
 ```
 
+`/venice` keeps smart routing enabled and points both route and main roles at `venice/venice-uncensored-1-2`.
+
 ## OpenAI Model Reference
 
 | Model | Role | Reasoning |

package/scripts/smoke-auth.js

@@ -54,7 +54,7 @@ async function runCli(args, stdin = "") {
 }
 
 try {
-  assert(normalizeAuthProvider("auxilliary") === "grsai", "auxilliary alias did not normalize to grsai");
+  assert(normalizeAuthProvider("auxiliary") === "grsai", "auxiliary alias did not normalize to grsai");
   assert(normalizeAuthProvider("qwen") === "qwen", "qwen provider did not normalize");
   assert(normalizeAuthProvider("venice") === "venice", "venice provider did not normalize");
   assert(authProviderKeyUrl("deepseek") === "https://platform.deepseek.com/api_keys", "DeepSeek key URL is missing");

package/scripts/smoke-cli-chat.js

@@ -159,6 +159,11 @@ try {
   if (!instructionsResult.stdout.includes("AGINTI.md") || !instructionsResult.stdout.includes("Project instructions")) {
     throw new Error("interactive /instructions did not show AGINTI.md");
   }
+  const helpResult = await runChat("/help\n/exit\n");
+  const misspelledAuxiliary = "/auxil" + "liary";
+  if (!helpResult.stdout.includes("/auxiliary") || helpResult.stdout.includes(misspelledAuxiliary)) {
+    throw new Error("interactive help did not expose only the correctly spelled /auxiliary command");
+  }
   const skillsResult = await runChat("/skills website\n/exit\n");
   if (!skillsResult.stdout.includes("website-app") || !skillsResult.stdout.includes("Website And App Builder")) {
     throw new Error("interactive /skills did not show matching built-in skills");
@@ -217,6 +222,7 @@ try {
           "agent-response-gutter",
           "aginti-md",
           "instructions-command",
+          "auxiliary-command-spelling",
           "skills-command",
           "slash-prefix-autoselect",
           "instructions-chat-edit",

package/scripts/smoke-model-roles.js

@@ -47,6 +47,43 @@ function runCli(args) {
   });
 }
 
+function runInteractive(input) {
+  return new Promise((resolve, reject) => {
+    const child = spawn(process.execPath, [path.join(repoRoot, "bin/aginti-cli.js"), "chat"], {
+      cwd: repoRoot,
+      stdio: ["pipe", "pipe", "pipe"],
+      env: {
+        ...process.env,
+        DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY || "test-deepseek-key-not-real",
+        VENICE_API_KEY: process.env.VENICE_API_KEY || "test-venice-key-not-real",
+        AGINTIFLOW_NO_COLOR: "1",
+      },
+    });
+    let stdout = "";
+    let stderr = "";
+    const timer = setTimeout(() => {
+      child.kill("SIGTERM");
+      reject(new Error("model role interactive smoke timed out"));
+    }, 12000);
+    child.stdout.on("data", (chunk) => {
+      stdout += String(chunk);
+    });
+    child.stderr.on("data", (chunk) => {
+      stderr += String(chunk);
+    });
+    child.on("error", (error) => {
+      clearTimeout(timer);
+      reject(error);
+    });
+    child.on("close", (code) => {
+      clearTimeout(timer);
+      if (code === 0) resolve(stdout);
+      else reject(new Error(`model role interactive smoke failed ${code}\n${stdout}\n${stderr}`));
+    });
+    child.stdin.end(input);
+  });
+}
+
 const roles = getModelRoleDefaults();
 assert(roles.route.provider === "deepseek", "route provider default should be deepseek");
 assert(roles.route.model === "deepseek-v4-flash", "route model default should be deepseek-v4-flash");
@@ -76,11 +113,15 @@ assert(AUXILIARY_MODEL_CATALOG["venice-image"].some((item) => item.id === "gpt-i
 const output = await runCli(["models"]);
 assert(output.includes("/route") && output.includes("/spare") && output.includes("venice-gpt"), "aginti models output missing role details");
 
+const interactiveOutput = await runInteractive("/venice\n/status\n/exit\n");
+assert(interactiveOutput.includes("route=venice/venice-uncensored-1-2"), "/venice did not set Venice route role");
+assert(interactiveOutput.includes("main=venice/venice-uncensored-1-2"), "/venice did not set Venice main role");
+
 console.log(
   JSON.stringify(
     {
       ok: true,
-      checks: ["role-defaults", "route-overrides", "provider-groups", "auxiliary-catalog", "cli-models-command"],
+      checks: ["role-defaults", "route-overrides", "provider-groups", "auxiliary-catalog", "cli-models-command", "venice-shortcut"],
     },
     null,
     2

package/src/agent-runner.js

@@ -319,7 +319,7 @@ async function createInitialState(config, sessionId) {
           config.allowAuxiliaryTools
             ? `Auxiliary skills are available: ${listAuxiliarySkills()
                 .map((skill) => `${skill.id} via ${skill.toolName} (${skill.available ? "key available" : `needs ${skill.keyName}`})`)
-                .join(", ")}. Use generate_image for real raster image/photo/illustration/cover/poster/logo requests when appropriate; if image keys are missing, ask the user to run /auxilliary grsai, aginti login grsai, or aginti login venice.`
+                .join(", ")}. Use generate_image for real raster image/photo/illustration/cover/poster/logo requests when appropriate; if image keys are missing, ask the user to run /auxiliary grsai, aginti login grsai, or aginti login venice.`
             : "Auxiliary skills are disabled for this run.",
           config.allowWebSearch
             ? "web_search is available for current information, docs, package/toolchain errors, and source discovery. Prefer web_search over browser search-engine navigation."

package/src/auth-onboarding.js

@@ -60,7 +60,6 @@ const AUXILIARY_AUTH_PROVIDER = {
 
 const AUTH_ALIASES = {
   auxiliary: "grsai",
-  auxilliary: "grsai",
   image: "grsai",
   imagegen: "grsai",
   grs: "grsai",

package/src/auxiliary-tools.js

@@ -424,7 +424,7 @@ export async function generateImage(args = {}, config = {}) {
 
   const apiKey = grsaiKey();
   if (!apiKey) {
-    throw new Error("Missing GRSAI key. Run `aginti login grsai`, `aginti keys set grsai --stdin`, or `/auxilliary grsai`.");
+    throw new Error("Missing GRSAI key. Run `aginti login grsai`, `aginti keys set grsai --stdin`, or `/auxiliary grsai`.");
   }
 
   const submitUrl = `${host}/v1/draw/nano-banana`;

package/src/capabilities.js

@@ -165,7 +165,7 @@ export async function buildCapabilityReport(projectRoot, packageVersion, config)
     capability("venice-key", keyStatus.venice, { envVars: keyStatus.envVars.venice }),
     capability("grsai-key", keyStatus.grsai, {
       envVars: keyStatus.envVars.grsai,
-      setup: "Optional for image generation. Run `aginti login grsai` or use `/auxilliary grsai` in chat.",
+      setup: "Optional for image generation. Run `aginti login grsai` or use `/auxiliary grsai` in chat.",
     }),
     capability("file-tools", Boolean(config.allowFileTools), { workspace: config.commandCwd }),
     capability("shell-tool", Boolean(config.allowShellTool), {

package/src/cli.js

@@ -354,7 +354,7 @@ function providerLabel(provider) {
   if (normalized === "openai") return "OpenAI";
   if (normalized === "qwen") return "Qwen";
   if (normalized === "venice") return "Venice";
-  if (normalized === "grsai" || normalized === "auxiliary" || normalized === "auxilliary") return "GRSAI";
+  if (normalized === "grsai" || normalized === "auxiliary") return "GRSAI";
   return "DeepSeek";
 }
 

package/src/interactive-cli.js

@@ -56,7 +56,6 @@ const SLASH_COMMANDS = [
   "/auth",
   "/instructions",
   "/memory",
-  "/auxilliary",
   "/auxiliary",
   "/new",
   "/resume",
@@ -67,6 +66,7 @@ const SLASH_COMMANDS = [
   "/web-search",
   "/scouts",
   "/models",
+  "/venice",
   "/route",
   "/main",
   "/spare",
@@ -573,6 +573,7 @@ function printHelp() {
       "  /instructions             Show AGINTI.md project instructions status.",
       "  /memory                   Alias for /instructions.",
       "  /models                   Show route/main/spare/wrapper/auxiliary model roles.",
+      "  /venice                   Shortcut: use Venice Uncensored 1.2 for route and main roles.",
       "  /route <mode|provider/model>",
       "                            Set routing mode or fast route model, e.g. /route deepseek/deepseek-v4-flash.",
       "  /model <provider/model>   Set the active/main model, e.g. /model deepseek/deepseek-v4-pro.",
@@ -580,7 +581,7 @@ function printHelp() {
       "                            Set spare model, e.g. /spare openai/gpt-5.4 medium.",
       "  /wrapper [on|off|codex model reasoning]",
       "                            Configure optional external wrapper.",
-      "  /auxilliary [status|grsai|venice|model grsai/nano-banana-2|on|off|image]",
+      "  /auxiliary [status|grsai|venice|model grsai/nano-banana-2|on|off|image]",
       "                            Manage optional auxiliary skills, including image generation.",
       "  /new                      Start a fresh session on the next message.",
       "  /resume <session-id>      Continue a saved session.",
@@ -1586,7 +1587,7 @@ function printModelRoles(state) {
       "/model deepseek/deepseek-v4-pro",
       "/spare openai/gpt-5.4 medium",
       "/wrapper codex gpt-5.5 medium",
-      "/auxilliary model grsai/nano-banana-2",
+      "/auxiliary model grsai/nano-banana-2",
       "",
       "Provider groups",
       ...groups,
@@ -1693,7 +1694,7 @@ async function handleCommand(line, state, packageDir) {
     );
     return true;
   }
-  if (command === "auxilliary" || command === "auxiliary") {
+  if (command === "auxiliary") {
     const action = value || "status";
     if (action === "status") {
       const keys = providerKeyStatus(process.cwd());
@@ -1703,7 +1704,7 @@ async function handleCommand(line, state, packageDir) {
           `Image generation: ${keys.grsai ? "GRSAI key available" : "missing GRSAI key"}`,
           `Venice image: ${keys.venice ? "Venice key available" : "missing Venice key"}`,
           `Selected auxiliary: ${state.auxiliaryProvider || "grsai"}/${state.auxiliaryModel || "nano-banana-2"}`,
-          "Use `/auxilliary grsai` or `/auxilliary venice` to paste a key, `/auxilliary model grsai/nano-banana-2`, `/auxilliary image`, or `/auxilliary off`.",
+          "Use `/auxiliary grsai` or `/auxiliary venice` to paste a key, `/auxiliary model grsai/nano-banana-2`, `/auxiliary image`, or `/auxiliary off`.",
         ].join("\n")
       );
       return true;
@@ -1735,7 +1736,7 @@ async function handleCommand(line, state, packageDir) {
       await promptAndSaveProviderKey(action === "venice" ? "venice" : "grsai", state);
       return true;
     }
-    printAgentMessage("Usage: /auxilliary [status|grsai|venice|model grsai/nano-banana-2|on|off|image]");
+    printAgentMessage("Usage: /auxiliary [status|grsai|venice|model grsai/nano-banana-2|on|off|image]");
     return true;
   }
   if (command === "new") {
@@ -1825,6 +1826,21 @@ async function handleCommand(line, state, packageDir) {
     printModelRoles(state);
     return true;
   }
+  if (command === "venice") {
+    state.routingMode = "smart";
+    state.provider = "deepseek";
+    state.model = "";
+    state.routeProvider = "venice";
+    state.routeModel = "venice-uncensored-1-2";
+    state.mainProvider = "venice";
+    state.mainModel = "venice-uncensored-1-2";
+    const keys = providerKeyStatus(process.cwd());
+    printSystemLine("routing=smart route=venice/venice-uncensored-1-2 main=venice/venice-uncensored-1-2");
+    if (!keys.venice) {
+      printAgentMessage("Venice model roles are selected, but no Venice key is configured. Run `/auth venice` to save one.");
+    }
+    return true;
+  }
   if (command === "route") {
     if (!value) {
       printAgentMessage(

package/src/model-client.js

@@ -241,7 +241,7 @@ export async function createPlan(client, config, state) {
           config.allowAuxiliaryTools
             ? `Auxiliary skills are enabled: ${listAuxiliarySkills()
                 .map((skill) => `${skill.id} via ${skill.toolName} (${skill.available ? "key available" : `needs ${skill.keyName}`})`)
-                .join(", ")}. For raster image generation requests, plan to use generate_image when a GRSAI or Venice image key is available; otherwise ask the user to run /auxilliary grsai, aginti login grsai, or aginti login venice.`
+                .join(", ")}. For raster image generation requests, plan to use generate_image when a GRSAI or Venice image key is available; otherwise ask the user to run /auxiliary grsai, aginti login grsai, or aginti login venice.`
             : "Auxiliary skills are disabled for this run.",
           config.allowWebSearch
             ? "web_search is available for current information, docs, install errors, package/toolchain questions, and source discovery. Prefer web_search over opening a search engine in the browser."
@@ -703,7 +703,7 @@ export async function requestNextStep(client, config, messages) {
       function: {
         name: "generate_image",
         description:
-          "Generate a raster image artifact through optional GRS AI Nano Banana or Venice image-generation skills. Use for user requests that explicitly need a real image/photo/illustration/cover/poster/logo concept rather than SVG/code-native graphics. Saves prompt, redacted payload, manifest, and downloaded images in the workspace. If keys are missing, ask the user to run /auxilliary grsai, aginti login grsai, or aginti login venice.",
+          "Generate a raster image artifact through optional GRS AI Nano Banana or Venice image-generation skills. Use for user requests that explicitly need a real image/photo/illustration/cover/poster/logo concept rather than SVG/code-native graphics. Saves prompt, redacted payload, manifest, and downloaded images in the workspace. If keys are missing, ask the user to run /auxiliary grsai, aginti login grsai, or aginti login venice.",
         parameters: {
           type: "object",
           properties: {

package/src/model-routing.js

@@ -519,7 +519,7 @@ export function getModelRoleDefaults(overrides = {}) {
     auxiliary: {
       id: "auxiliary",
       label: "Auxiliary",
-      command: "/auxilliary",
+      command: "/auxiliary",
       provider: auxiliaryProvider,
       model: auxiliaryModel,
       description: "Image/media tools. Default: GRS AI/Nano Banana; Venice image is optional.",

package/src/project.js

@@ -306,7 +306,6 @@ export function providerKeyPreview(projectRoot = process.cwd(), provider = "") {
   const normalized = String(provider || "").trim().toLowerCase();
   const aliases = {
     auxiliary: "grsai",
-    auxilliary: "grsai",
     image: "grsai",
     imagegen: "grsai",
     v: "venice",
@@ -339,7 +338,6 @@ export async function setProviderKey(projectRoot, provider, value) {
   const normalizedProvider = String(provider || "").toLowerCase();
   const aliases = {
     auxiliary: "grsai",
-    auxilliary: "grsai",
     image: "grsai",
     imagegen: "grsai",
     v: "venice",

package/src/task-profiles.js

@@ -66,7 +66,7 @@ export const TASK_PROFILES = {
     id: "image",
     label: "Image generation",
     prompt:
-      "For raster image, cover, poster, illustration, photo, and logo-concept tasks, write a clear visual prompt, use generate_image when the optional GRS AI or Venice image key is available, save outputs under artifacts/images, and send the selected image to the canvas. If keys are missing, ask the user to run /auxilliary grsai, aginti login grsai, or aginti login venice.",
+      "For raster image, cover, poster, illustration, photo, and logo-concept tasks, write a clear visual prompt, use generate_image when the optional GRS AI or Venice image key is available, save outputs under artifacts/images, and send the selected image to the canvas. If keys are missing, ask the user to run /auxiliary grsai, aginti login grsai, or aginti login venice.",
     tools: ["auxiliary:image_generation", "files", "canvas"],
   },
   aaps: {