@lazyingart/agintiflow 0.20.50 → 0.20.52

package/README.md

@@ -97,7 +97,7 @@ For larger repositories, use `--profile large-codebase` or choose **Large codeba
 
 AgInTiFlow can also spend cheap DeepSeek calls on parallel scout notes before the main executor starts a complicated task. It first writes a bounded project map to `.aginti/codebase-map.json`, then runs scouts for architecture, implementation, review, research, context mapping, tests, git workflow, integration, symbol tracing, and dependency risks. A coordinator Swarm Board is injected for the main agent and saved as `artifacts/scout-blackboard.json` in the session. The executor still does the real file/shell/browser work itself. Disable with `--no-parallel-scouts` or set `--scout-count 1..10`.
 
-For complicated tasks that need stricter quality control, enable Student-Committee-Supervisor mode with `/enabless`, `--enabless`, or `--enabless auto`. SCS uses the main model for a typed gate: committee drafts the next phase, student approves/monitors/rejects weak evidence, and supervisor executes with the normal guarded tools. It disables duplicate scout advice by default, logs typed `scs.*` events, caps retries to avoid deadlock, and stays off unless you opt in or choose auto mode. See [docs/student-committee-supervisor.md](docs/student-committee-supervisor.md).
+For complicated tasks that need stricter quality control, enable Student-Committee-Supervisor mode with `/scs`, `--scs`, or `--scs auto`. SCS uses the main model for a typed gate: committee drafts the next phase, student approves/monitors/rejects weak evidence, and supervisor executes with the normal guarded tools. It disables duplicate scout advice by default, logs typed `scs.*` events, caps retries to avoid deadlock, and stays off unless you opt in or choose auto mode. See [docs/student-committee-supervisor.md](docs/student-committee-supervisor.md).
 
 The next productive-agent roadmap is tracked in [docs/productive-agent-roadmap.md](docs/productive-agent-roadmap.md): durable codebase maps, stronger scout blackboards, long-run checkpoints, LSP/symbol tools, test triage, and release automation. Runtime choices, Docker persistence, host full-access tradeoffs, tmux sessions, and rolling-plan autonomy are documented in [docs/runtime-modes-and-autonomy.md](docs/runtime-modes-and-autonomy.md). The supervised self-development protocol is in [docs/self-development-supervision.md](docs/self-development-supervision.md).
 
@@ -156,10 +156,10 @@ aginti aaps init "Project Workflow"
 aginti aaps validate
 aginti chat
 # then in chat: /review [focus]
-# then in chat: /enabless auto
+# then in chat: /scs auto
 # then in chat: /aaps validate
 aginti --profile code "write a small Python CLI app with tests"
-aginti --enabless auto "fix this complicated project and verify it"
+aginti --scs auto "fix this complicated project and verify it"
 aginti --latex "draw a figure, write a short LaTeX report, and compile the PDF"
 aginti "set up this project and run the tests"
 ```
@@ -170,7 +170,7 @@ Session cleanup is cwd-scoped by default. `aginti --remove-empty-sessions` shows
 
 In interactive chat, `/review [focus]` starts a bounded repository review. It begins from git status/diff and project instructions, reads manifests/entry points/tests/changed files first, avoids generated or binary folders, limits discovery passes, and reports findings before any summary.
 
-In interactive chat, `/enabless` turns on SCS for the session, `/enabless auto` activates it only for complex/risky work, `/enabless off` restores the normal fast pipeline, and `/enabless status` explains the current mode.
+In interactive chat, `/scs` toggles SCS on or off for the session, `/scs auto` activates it only for complex/risky work, `/scs on` forces it on, `/scs off` restores the normal fast pipeline, and `/scs status` explains the current mode.
 
 Run from a source checkout:
 

package/docs/student-committee-supervisor.md

@@ -7,21 +7,22 @@ It is intentionally separate from the normal fast pipeline. Small requests shoul
 ## Commands
 
 ```bash
-aginti --enabless "fix this complicated project and verify it"
-aginti --enabless auto "migrate this app and run the checks"
-aginti --no-enabless "answer this simple question"
+aginti --scs "fix this complicated project and verify it"
+aginti --scs auto "migrate this app and run the checks"
+aginti --no-scs "answer this simple question"
 ```
 
 Inside interactive chat:
 
 ```text
-/enabless
-/enabless auto
-/enabless off
-/enabless status
+/scs
+/scs auto
+/scs on
+/scs off
+/scs status
 ```
 
-`/scs` is also accepted as a serious alias.
+`/scs` without arguments toggles the feature: off becomes on, and on/auto becomes off. The old `/enabless` spelling is accepted only as a compatibility alias for older sessions and scripts.
 
 ## Role Contract
 
@@ -57,7 +58,7 @@ The current implementation is deliberately bounded:
 
 ## Auto Mode
 
-`/enabless auto` and `--enabless auto` activate SCS for complex, risky, or long-running work. Signals include:
+`/scs auto` and `--scs auto` activate SCS for complex, risky, or long-running work. Signals include:
 
 - high smart-routing complexity score;
 - profiles such as code, app, Android/iOS, large-codebase, GitHub, maintenance, security, LaTeX, research, and supervision;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lazyingart/agintiflow",
-  "version": "0.20.50",
+  "version": "0.20.52",
   "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/student-committee-supervisor-mode.md

@@ -1,6 +1,6 @@
 # Student-Committee-Supervisor Mode
 
-This note researches the current AgInTiFlow execution pipeline and proposes a standalone `/enabless` mode: Student-Committee-Supervisor, abbreviated `SCS`.
+This note researches the current AgInTiFlow execution pipeline and proposes a standalone `/scs` mode: Student-Committee-Supervisor, abbreviated `SCS`.
 
 The name intentionally keeps the reversed-role joke: the "student" supervises, the "supervisor" executes, and the "committee" drafts but cannot decide.
 
@@ -40,7 +40,7 @@ Relevant implementation files:
 
 ## Proposed SCS Contract
 
-`/enabless` enables a stricter internal workflow for the current interactive session.
+`/scs` enables a stricter internal workflow for the current interactive session.
 
 Roles:
 
@@ -50,7 +50,7 @@ Roles:
 | Committee | Main model | Draft candidate plans and alternatives. | Cannot approve, veto, replan after execution starts, or call tools. |
 | Supervisor | Main model | Execute the approved plan with the existing tool loop. | Cannot draft its own initial plan, cannot approve its own plan, cannot declare strategic replans without student permission. |
 
-The user asked that once `/enabless` is enabled, all SCS work uses the main model. This is sensible for determinism: no route/main mismatch, no cheap planner producing a plan that a stronger executor dislikes, and no confusing cross-model responsibility. It also makes cost predictable because the feature is opt-in.
+The user asked that once `/scs` is enabled, all SCS work uses the main model. This is sensible for determinism: no route/main mismatch, no cheap planner producing a plan that a stronger executor dislikes, and no confusing cross-model responsibility. It also makes cost predictable because the feature is opt-in.
 
 ## Pros
 
@@ -133,7 +133,7 @@ New config/state:
 
 - `AGINTI_SCS_MODE=true`
 - CLI flag: `--enable-scs`
-- interactive command: `/enabless`, `/enabless off`, `/enabless status`
+- interactive command: `/scs`, `/scs on`, `/scs auto`, `/scs off`, `/scs status`
 - state fields:
   - `state.enableScs`
   - `state.scs.phase`
@@ -189,7 +189,7 @@ Recommended modes:
 | `on` | SCS gates all non-trivial work in the session. |
 | `auto` | SCS only activates for complex tasks, write actions, multi-step shell work, GitHub, system maintenance, Android/iOS, LaTeX/PDF, and long-running tasks. |
 
-`/enabless` should toggle `on` in interactive CLI for the joke and speed. `/enabless auto` can be the mature default later.
+`/scs` should toggle SCS on/off in interactive CLI. `/scs auto` keeps the mature complex-task gate for users who want quality control without paying the SCS cost on simple turns.
 
 ## Model Policy
 
@@ -215,10 +215,11 @@ Possible future improvement:
 CLI:
 
 ```text
-/enabless
-/enabless off
-/enabless auto
-/enabless status
+/scs
+/scs on
+/scs off
+/scs auto
+/scs status
 ```
 
 Status output:
@@ -283,8 +284,8 @@ Implemented first slice:
 
 - `src/scs-controller.js` provides mode normalization, auto activation, committee/student JSON calls, evidence packs, supervisor instructions, tool-failure monitoring, periodic progress review, and final finish gates.
 - `src/config.js` adds `enableScs`/`scsActive` and switches active execution to the main model role when SCS is active.
-- `src/interactive-cli.js` adds `/enabless`, `/enabless auto`, `/enabless off`, `/enabless status`, and `/scs` alias.
-- `src/cli.js` adds `--enabless`, `--enabless auto`, `--no-enabless`, and aliases.
+- `src/interactive-cli.js` adds `/scs`, `/scs auto`, `/scs on`, `/scs off`, and `/scs status`. `/enabless` remains a compatibility alias only.
+- `src/cli.js` adds `--scs`, `--scs auto`, and `--no-scs`. The older `--enabless` flags remain compatibility aliases only.
 - `src/agent-runner.js` persists typed `scs.*` events, saves `scs-phase-001.json`, injects the approved supervisor phase, reviews failed tools, and gates finish.
 
 Remaining roadmap:
@@ -317,12 +318,12 @@ Phase 5: auto mode
 - Should SCS approval be required before any write tool, or only before the first phase starts?
 - Should the student be allowed to require specific checks, or only accept/reject evidence?
 - Should committee be one call or multiple candidate calls synthesized into one plan?
-- Should `/enabless` be hidden as a playful alias while `/scs` is the serious public command?
+- Should `/enabless` remain as a hidden compatibility alias now that `/scs` is the serious public command?
 - Should SCS decisions be shared through Skill Mesh as learned supervision skills?
 
 ## Recommendation
 
-Implement `/enabless` as a serious opt-in quality mode with a playful name.
+Implement `/scs` as the serious opt-in quality mode.
 
 Start with one-main-model SCS and only gate the initial plan plus final finish. Then add failure-triggered student monitoring. Avoid per-tool approval in the first version; existing command and file guardrails already protect the dangerous paths, and too many monitor calls will make the product feel slow.
 

package/scripts/smoke-cli-chat.js

@@ -15,6 +15,7 @@ import {
   formatWorkspaceChange,
   stripMarkdown,
 } from "../src/interactive-cli.js";
+import { parseArgs } from "../src/cli.js";
 import { dockerPolicyTimeoutMs, dockerUserCommand } from "../src/docker-sandbox.js";
 
 const repoRoot = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..");
@@ -263,11 +264,20 @@ try {
   if (
     canonicalSlashPromptBuffer("/ve") !== "/venice" ||
     canonicalSlashPromptBuffer("/v") !== "/venice" ||
+    canonicalSlashPromptBuffer("/sc") !== "/scs" ||
     canonicalSlashPromptBuffer("/not-a-command") !== "/not-a-command" ||
     canonicalSlashPromptBuffer("/venice off") !== "/venice off"
   ) {
     throw new Error("slash command prompt canonicalization did not preserve final submitted command correctly");
   }
+  const scsBooleanArgs = parseArgs(["--scs", "fix this project"]);
+  if (scsBooleanArgs.enableScs !== "on" || scsBooleanArgs.goal !== "fix this project") {
+    throw new Error("--scs should behave as a boolean flag when followed by a task");
+  }
+  const scsAutoArgs = parseArgs(["--scs", "auto", "fix this project"]);
+  if (scsAutoArgs.enableScs !== "auto" || scsAutoArgs.goal !== "fix this project") {
+    throw new Error("--scs auto should consume auto and preserve the task");
+  }
 
   await runCli(["init"], "");
   const instructions = await fs.readFile(path.join(tempRoot, "AGINTI.md"), "utf8");
@@ -280,8 +290,14 @@ try {
   }
   const helpResult = await runChat("/help\n/exit\n");
   const misspelledAuxiliary = "/auxil" + "liary";
-  if (!helpResult.stdout.includes("/auxiliary") || !helpResult.stdout.includes("/review") || helpResult.stdout.includes(misspelledAuxiliary)) {
-    throw new Error("interactive help did not expose only the correctly spelled /auxiliary command");
+  if (
+    !helpResult.stdout.includes("/auxiliary") ||
+    !helpResult.stdout.includes("/review") ||
+    !helpResult.stdout.includes("/scs") ||
+    helpResult.stdout.includes("/enabless") ||
+    helpResult.stdout.includes(misspelledAuxiliary)
+  ) {
+    throw new Error("interactive help did not expose the expected slash commands");
   }
   const zhHelpResult = await runCli(["chat", "--language", "zh-Hans"], "/help\n/exit\n");
   if (!zhHelpResult.stdout.includes("命令:") || !zhHelpResult.stdout.includes("输入普通任务")) {
@@ -295,6 +311,22 @@ try {
   if (!reviewResult.stdout.includes("Review focus: changed files only") || !reviewResult.stdout.includes("Mock run complete")) {
     throw new Error("interactive /review did not launch the bounded review workflow");
   }
+  const scsOnResult = await runChat("/scs\n");
+  if (!scsOnResult.stdout.includes("scs=on")) {
+    throw new Error("interactive /scs did not toggle SCS on");
+  }
+  const scsOffResult = await runCli(["chat", "--provider", "mock", "--routing", "manual", "--profile", "code", "--scs"], "/scs\n");
+  if (!scsOffResult.stdout.includes("scs=off")) {
+    throw new Error("interactive /scs did not toggle SCS off");
+  }
+  const scsStatusResult = await runChat("/scs status\n");
+  if (!scsStatusResult.stdout.includes("SCS mode: off")) {
+    throw new Error("interactive /scs status did not show current mode");
+  }
+  const scsAutoResult = await runChat("/scs auto\n");
+  if (!scsAutoResult.stdout.includes("scs=auto")) {
+    throw new Error("interactive /scs auto did not enable auto mode");
+  }
   const abbreviatedSkillsResult = await runChat("/sk website\n/ex\n");
   if (abbreviatedSkillsResult.stdout.includes("Unknown command") || !abbreviatedSkillsResult.stdout.includes("website-app")) {
     throw new Error("interactive slash command prefix did not auto-select the first matching command");
@@ -372,6 +404,7 @@ try {
           "auxiliary-command-spelling",
           "skills-command",
           "review-command",
+          "scs-command-toggle",
           "slash-prefix-autoselect",
           "slash-prefix-canonical-history",
           "instructions-chat-edit",

package/scripts/smoke-coding-tools.js

@@ -85,6 +85,52 @@ try {
     !staleDeepSeekState.messages.some((message) => message.role === "tool" && message.tool_call_id === "stale-call"),
     "repaired DeepSeek history retained an orphan stale tool message"
   );
+  const interruptedDeepSeekState = {
+    messages: [
+      { role: "system", content: "system" },
+      { role: "user", content: "old request" },
+      {
+        role: "assistant",
+        content: "Running checks.",
+        reasoning_content: "Need shell evidence.",
+        tool_calls: [
+          { id: "call-a", type: "function", function: { name: "run_command", arguments: "{}" } },
+          { id: "call-b", type: "function", function: { name: "run_command", arguments: "{}" } },
+        ],
+      },
+      { role: "tool", tool_call_id: "call-a", content: "{\"ok\":true}" },
+      { role: "user", content: "Continue with this new request: /review" },
+    ],
+  };
+  const interruptedRepair = repairModelMessageHistory(interruptedDeepSeekState, { provider: "deepseek" });
+  assert(interruptedRepair.changed, "interrupted tool-call history was not repaired");
+  assert(interruptedRepair.incompleteToolCallMessages === 1, "interrupted repair did not count the incomplete tool call");
+  assert(
+    !interruptedDeepSeekState.messages.some((message) => Array.isArray(message.tool_calls) && message.tool_calls.length > 0),
+    "interrupted repair retained incomplete assistant tool calls"
+  );
+  assert(
+    !interruptedDeepSeekState.messages.some((message) => message.role === "tool"),
+    "interrupted repair retained orphan partial tool result"
+  );
+  assert(
+    interruptedDeepSeekState.messages.at(-1)?.content === "Continue with this new request: /review",
+    "interrupted repair dropped the new user request"
+  );
+  const completeToolState = {
+    messages: [
+      { role: "system", content: "system" },
+      {
+        role: "assistant",
+        content: "Using a tool.",
+        tool_calls: [{ id: "call-ok", type: "function", function: { name: "list_files", arguments: "{}" } }],
+      },
+      { role: "tool", tool_call_id: "call-ok", content: "{\"ok\":true}" },
+      { role: "user", content: "next" },
+    ],
+  };
+  const completeRepair = repairModelMessageHistory(completeToolState, { provider: "openai" });
+  assert(!completeRepair.changed, "complete OpenAI-format tool history should not be modified");
   const patchRoute = selectModelRoute({
     routingMode: "smart",
     provider: "deepseek",

package/src/agent-runner.js

@@ -190,32 +190,68 @@ function preserveAssistantMessage(message) {
 }
 
 export function repairModelMessageHistory(state, config = {}) {
-  if (config.provider !== "deepseek" || !Array.isArray(state?.messages)) {
-    return { changed: false, droppedAssistantMessages: 0, convertedAssistantMessages: 0, droppedToolMessages: 0 };
+  if (!Array.isArray(state?.messages)) {
+    return {
+      changed: false,
+      droppedAssistantMessages: 0,
+      convertedAssistantMessages: 0,
+      droppedToolMessages: 0,
+      incompleteToolCallMessages: 0,
+    };
   }
 
   const repaired = [];
-  const droppedToolCallIds = new Set();
   let droppedAssistantMessages = 0;
   let convertedAssistantMessages = 0;
   let droppedToolMessages = 0;
+  let incompleteToolCallMessages = 0;
 
-  for (const message of state.messages) {
+  for (let index = 0; index < state.messages.length; index += 1) {
+    const message = state.messages[index];
     if (message.role === "assistant") {
       const hasReasoningContent = Boolean(message.reasoning_content || message.reasoningContent);
       const toolCalls = Array.isArray(message.tool_calls) ? message.tool_calls : [];
       const content = String(message.content || "");
+      const requiresDeepSeekReasoning = config.provider === "deepseek" && !hasReasoningContent;
+
+      if (toolCalls.length > 0) {
+        const expectedIds = toolCalls.map((call) => String(call?.id || "")).filter(Boolean);
+        const expected = new Set(expectedIds);
+        const followingToolMessages = [];
+        const duplicateOrUnexpectedToolMessages = [];
+        const seen = new Set();
+        let cursor = index + 1;
+
+        while (cursor < state.messages.length && state.messages[cursor]?.role === "tool") {
+          const toolMessage = state.messages[cursor];
+          const toolCallId = String(toolMessage.tool_call_id || "");
+          if (expected.has(toolCallId) && !seen.has(toolCallId)) {
+            followingToolMessages.push(toolMessage);
+            seen.add(toolCallId);
+          } else {
+            duplicateOrUnexpectedToolMessages.push(toolMessage);
+          }
+          cursor += 1;
+        }
 
-      if (!hasReasoningContent) {
-        if (content.startsWith("Execution plan:")) {
+        const completeToolResults = expectedIds.length > 0 && expectedIds.every((id) => seen.has(id));
+        if (requiresDeepSeekReasoning || !completeToolResults) {
           droppedAssistantMessages += 1;
+          droppedToolMessages += followingToolMessages.length + duplicateOrUnexpectedToolMessages.length;
+          if (!completeToolResults) incompleteToolCallMessages += 1;
+          index = cursor - 1;
           continue;
         }
 
-        if (toolCalls.length > 0) {
-          for (const call of toolCalls) {
-            if (call?.id) droppedToolCallIds.add(call.id);
-          }
+        repaired.push(preserveAssistantMessage(message));
+        repaired.push(...followingToolMessages);
+        droppedToolMessages += duplicateOrUnexpectedToolMessages.length;
+        index = cursor - 1;
+        continue;
+      }
+
+      if (requiresDeepSeekReasoning) {
+        if (content.startsWith("Execution plan:")) {
           droppedAssistantMessages += 1;
           continue;
         }
@@ -236,7 +272,7 @@ export function repairModelMessageHistory(state, config = {}) {
       continue;
     }
 
-    if (message.role === "tool" && droppedToolCallIds.has(message.tool_call_id)) {
+    if (message.role === "tool") {
       droppedToolMessages += 1;
       continue;
     }
@@ -259,6 +295,7 @@ export function repairModelMessageHistory(state, config = {}) {
     droppedAssistantMessages,
     convertedAssistantMessages,
     droppedToolMessages,
+    incompleteToolCallMessages,
   };
 }
 
@@ -1314,6 +1351,13 @@ export async function runAgent(config) {
 
   ensureChatState(state);
 
+  const initialRepair = repairModelMessageHistory(state, config);
+  if (initialRepair.changed) {
+    await store.appendEvent("history.repaired", initialRepair);
+    observers.event("history.repaired", initialRepair);
+    await store.saveState(state);
+  }
+
   observers.log("session.ready", {
     sessionId,
     provider: config.provider,

package/src/cli.js

@@ -55,6 +55,15 @@ function readOption(argv, index) {
   return value;
 }
 
+function readOptionalScsMode(argv, index) {
+  const value = readOption(argv, index);
+  const normalized = String(value || "").trim().toLowerCase();
+  if (!["on", "off", "auto", "smart", "true", "false", "yes", "no", "enable", "disable", "enabled", "disabled", "1", "0"].includes(normalized)) {
+    return { mode: "on", consumed: false };
+  }
+  return { mode: value, consumed: true };
+}
+
 export function parseArgs(argv) {
   const result = {
     goal: "",
@@ -151,9 +160,9 @@ export function parseArgs(argv) {
       continue;
     }
     if (arg === "--enabless" || arg === "--enable-scs" || arg === "--scs") {
-      const value = readOption(argv, i);
-      result.enableScs = value || "on";
-      if (value) i += 1;
+      const { mode, consumed } = readOptionalScsMode(argv, i);
+      result.enableScs = mode;
+      if (consumed) i += 1;
       continue;
     }
     if (arg === "--no-enabless" || arg === "--disable-scs" || arg === "--no-scs") {
@@ -395,7 +404,7 @@ export function parseArgs(argv) {
 
 function printUsage() {
   console.log(
-    'Usage: aginti [chat] OR aginti web [--port 3210] OR aginti update OR aginti models OR aginti aaps [status|init|files|validate|compile|check|run] OR aginti skills [query] OR aginti skillmesh [status|off|record|share|sync|serve|service] OR aginti housekeeping [--json] OR aginti auth [deepseek|openai|qwen|venice|grsai] OR aginti resume [--all-sessions] [latest|<session-id>] ["prompt"] OR aginti --remove-empty-sessions OR aginti --remove-sessions OR aginti queue <session-id> "message" OR aginti [--no-auto-update] [--language en|ja|zh-Hans|zh-Hant|ko|fr|es|ar|vi|de|ru] [--image] [--latex] [--enabless|--enabless auto|--no-enabless] [--routing smart|fast|complex|manual] [--provider deepseek|openai|qwen|venice|mock] [--model MODEL] [--route-model MODEL] [--main-model MODEL] [--spare-model MODEL --spare-reasoning medium] [--aux-provider grsai|venice --aux-model MODEL] [--sandbox-mode host|docker-readonly|docker-workspace] [--package-install-policy block|prompt|allow] [--approve-package-installs] [--allow-shell|--no-shell] [--allow-file-tools|--no-file-tools] [--web-search|--no-web-search] [--parallel-scouts|--no-parallel-scouts --scout-count 1..10] [--allow-auxiliary-tools|--no-auxiliary-tools] [--allow-wrappers --wrapper codex --wrapper-model gpt-5.5] [--list-models|--list-routes] "your task"'
+    'Usage: aginti [chat] OR aginti web [--port 3210] OR aginti update OR aginti models OR aginti aaps [status|init|files|validate|compile|check|run] OR aginti skills [query] OR aginti skillmesh [status|off|record|share|sync|serve|service] OR aginti housekeeping [--json] OR aginti auth [deepseek|openai|qwen|venice|grsai] OR aginti resume [--all-sessions] [latest|<session-id>] ["prompt"] OR aginti --remove-empty-sessions OR aginti --remove-sessions OR aginti queue <session-id> "message" OR aginti [--no-auto-update] [--language en|ja|zh-Hans|zh-Hant|ko|fr|es|ar|vi|de|ru] [--image] [--latex] [--scs|--scs auto|--no-scs] [--routing smart|fast|complex|manual] [--provider deepseek|openai|qwen|venice|mock] [--model MODEL] [--route-model MODEL] [--main-model MODEL] [--spare-model MODEL --spare-reasoning medium] [--aux-provider grsai|venice --aux-model MODEL] [--sandbox-mode host|docker-readonly|docker-workspace] [--package-install-policy block|prompt|allow] [--approve-package-installs] [--allow-shell|--no-shell] [--allow-file-tools|--no-file-tools] [--web-search|--no-web-search] [--parallel-scouts|--no-parallel-scouts --scout-count 1..10] [--allow-auxiliary-tools|--no-auxiliary-tools] [--allow-wrappers --wrapper codex --wrapper-model gpt-5.5] [--list-models|--list-routes] "your task"'
   );
   console.log(`Languages: ${["en", "ja", "zh-Hans", "zh-Hant", "ko", "fr", "es", "ar", "vi", "de", "ru"].map((code) => `${code}=${languageLabel(code)}`).join(", ")}`);
 }

package/src/i18n.js

@@ -138,6 +138,7 @@ const TRANSLATIONS = {
     helpSkillMesh: "Manage strict reviewed skill sharing.",
     helpProfile: "Set task profile, e.g. code, website, latex, maintenance.",
     helpWebSearch: "Enable or disable the web_search tool.",
+    helpEnableScs: "Toggle Student-Committee-Supervisor gated execution.",
     helpScouts: "Enable parallel DeepSeek scouts and set scout count.",
     helpRouting: "Set routing: smart, fast, complex, manual.",
     helpProvider: "Open provider selector, or set deepseek/openai/qwen/venice/mock.",

package/src/interactive-cli.js

@@ -87,9 +87,8 @@ const SLASH_COMMANDS = [
   "/skillsync",
   "/profile",
   "/web-search",
-  "/scouts",
-  "/enabless",
   "/scs",
+  "/scouts",
   "/models",
   "/venice",
   "/route",
@@ -667,8 +666,8 @@ function printHelp() {
       `  ${command("/skillmesh [status|off|record|share|sync]", "Manage strict reviewed skill sharing.", "helpSkillMesh")}`,
       `  ${command("/profile <name>", "Set task profile, e.g. code, website, latex, maintenance.", "helpProfile")}`,
       `  ${command("/web-search on|off", "Enable or disable the web_search tool.", "helpWebSearch")}`,
+      `  ${command("/scs [on|auto|off|status]", "Toggle Student-Committee-Supervisor gated execution.", "helpEnableScs")}`,
       `  ${command("/scouts on|off|<1-10>", "Enable parallel DeepSeek scouts and set scout count.", "helpScouts")}`,
-      `  ${command("/enabless [auto|off|status]", "Enable Student-Committee-Supervisor gated execution.", "helpEnableScs")}`,
       `  ${command("/routing <mode>", "Set routing: smart, fast, complex, manual.", "helpRouting")}`,
       `  ${command("/provider [name]", "Open provider selector, or set deepseek/openai/qwen/venice/mock.", "helpProvider")}`,
       `  ${command("/docker on", "Use docker-workspace with approved package installs.", "helpDockerOn")}`,
@@ -2808,14 +2807,40 @@ async function handleCommand(line, state, packageDir) {
   }
   if (command === "enabless" || command === "scs") {
     const rawMode = String(value || "").trim().toLowerCase();
-    const mode = value ? normalizeScsMode(value) : "on";
+    const currentMode = normalizeScsMode(state.enableScs || "off");
+    const mode =
+      rawMode === "toggle" || !rawMode
+        ? command === "scs"
+          ? currentMode === "off"
+            ? "on"
+            : "off"
+          : "on"
+        : normalizeScsMode(value);
     const knownMode =
       !rawMode ||
-      ["on", "off", "auto", "smart", "status", "?", "true", "false", "yes", "no", "y", "n", "1", "0", "enable", "disable", "enabled", "disabled"].includes(
-        rawMode
-      );
+      [
+        "on",
+        "off",
+        "auto",
+        "smart",
+        "status",
+        "?",
+        "toggle",
+        "true",
+        "false",
+        "yes",
+        "no",
+        "y",
+        "n",
+        "1",
+        "0",
+        "enable",
+        "disable",
+        "enabled",
+        "disabled",
+      ].includes(rawMode);
     if (!knownMode) {
-      printAgentMessage("Usage: /enabless [auto|off|status]. `/enabless` turns SCS on for the session.");
+      printAgentMessage("Usage: /scs [on|auto|off|status]. `/scs` toggles SCS on/off for the session.");
       return true;
     }
     if (value === "status" || value === "?") {
@@ -2823,7 +2848,7 @@ async function handleCommand(line, state, packageDir) {
         [
           `SCS mode: ${state.enableScs || "off"}`,
           "Student-Committee-Supervisor gates complex work with one main model: committee drafts, student approves/monitors, supervisor executes.",
-          "Use `/enabless` for on, `/enabless auto` for complex-task auto mode, or `/enabless off` for the normal fast pipeline.",
+          "Use `/scs` to toggle, `/scs auto` for complex-task auto mode, `/scs on` to force it on, or `/scs off` for the normal fast pipeline.",
         ].join("\n")
       );
       return true;
@@ -2837,6 +2862,8 @@ async function handleCommand(line, state, packageDir) {
       printAgentMessage("SCS enabled. Next run uses the main model for committee planning, student gates, and supervisor execution.");
     } else if (state.enableScs === "auto") {
       printAgentMessage("SCS auto enabled. It activates for complex, risky, or long-running tasks and stays off for simple turns.");
+    } else {
+      printAgentMessage("SCS disabled. Next run uses the normal routing pipeline.");
     }
     return true;
   }