@tiangong-ai/cli 0.0.43 → 0.0.44

package/AGENTS.md

@@ -52,6 +52,7 @@ This repository owns the Tiangong AI command-line interface.
 - `tiangong-ai research policy`
 - `tiangong-ai research publication`
 - `tiangong-ai research workspace`
+- `tiangong-ai research reviewer`
 - `tiangong-ai research capability`
 - `tiangong-ai research project`
 - `tiangong-ai research status`

package/README.md

@@ -376,7 +376,7 @@ binds the manifest and every document by SHA-256; edits, manifest tampering, or
 expiry block preflight and all later stages until the Policy is reviewed and
 approved again.
 
-Before search, the current native Codex or Claude host must author a
+Before search, the current native Codex, Claude, WorkBuddy, or CodeBuddy host must author a
 project-specific scientific design. The CLI owns the closed schema and rejects
 designs that confuse model-to-model disagreement with observed truth, inflate
 independent sample size through resampling, omit quantity/threshold semantics,
@@ -602,13 +602,19 @@ The workspace stores its current protocol state under `.tiangong-research/`.
 Each project follows the evidence-first sequence: broad discovery, strict
 admission, acquisition audit, immutable evidence freeze, analysis, synthesis,
 independent review, and mechanical closure. Discover, acquire, analyze, and
-synthesize run in the current interactive Codex app/session or Claude Code
-session. The CLI never launches a nested producer process. Independent review
+synthesize run in the current interactive Codex, Claude Code, WorkBuddy, or
+CodeBuddy session. The CLI never launches a nested producer process. Independent review
 runs through the other configured agent family's CLI, and execution is blocked
 when the two roles use the same family.
 
-Independent reviewer execution requires `/usr/bin/sandbox-exec` on macOS or
-Bubblewrap (`bwrap`) on Linux. Windows can inspect and configure workspaces but
+Independent reviewer execution always requires `/usr/bin/sandbox-exec` on macOS
+or Bubblewrap (`bwrap`) on Linux. `reviewerExecution.transport=native-direct`
+creates that capsule in the current process. `sandbox-bridge` sends one
+hash-bound request to an owner-started, exact-version sidecar outside an IDE
+sandbox; the sidecar creates the same capsule and returns an Ed25519-signed
+attestation bound to workspace/config/runtime/capsule/request/result/model and
+policy hashes. The two transports are explicit and never fall back to each
+other. Windows can inspect and configure workspaces but
 does not launch reviewer packages; smoke-test setup reports a non-blocking
 warning there, while production readiness fails closed. The current native producer remains governed
 by its host application's own permissions; the CLI supplies a hash-bound packet
@@ -628,7 +634,7 @@ tiangong-ai research run --workspace /absolute/path/to/workspace \
   --project gpu-resource-impact --progress-jsonl
 # When stopReason is native-stage-required, perform the returned stage here:
 tiangong-ai research project stage prepare gpu-resource-impact \
-  --stage discover --host-agent codex \
+  --stage discover --host-agent workbuddy \
   --workspace /absolute/path/to/workspace --json
 tiangong-ai research project stage submit gpu-resource-impact \
   --session SESSION_ID --output /absolute/path/to/discover.json \
@@ -637,6 +643,36 @@ tiangong-ai research project stage submit gpu-resource-impact \
 tiangong-ai research status --workspace /absolute/path/to/workspace --json
 ```
 
+For WorkBuddy/CodeBuddy, keep Default Permission and start the sidecar from a
+separate native terminal with a private non-symlink state directory outside the
+workspace:
+
+```bash
+tiangong-ai research reviewer serve \
+  --workspace /absolute/path/to/workspace \
+  --state-dir /absolute/private/reviewer-sidecar --json
+
+# From the sandboxed IDE:
+tiangong-ai research reviewer status --workspace /absolute/path/to/workspace --json
+tiangong-ai research reviewer doctor --confirm-agent-smoke-cost \
+  --workspace /absolute/path/to/workspace --json
+```
+
+Sidecar readiness includes real filesystem negative probes and a fixed
+`execute|fingerprint|status` protocol. It has no arbitrary-command endpoint;
+reviewer shell, browser, web, undeclared MCP, and Skill tools remain disabled.
+Do not use Full Access, sandbox-disable flags, unsandboxed-command exceptions,
+or silent transport fallback.
+
+WorkBuddy/CodeBuddy capsule teardown never requests recursive bulk deletion
+inside the outer IDE. Native stages remove only the single active-session
+binding, while completed, aborted, handed-off, and reviewer/work-package
+capsules are retained. The journal records
+`capsuleDisposition=retained-outer-sandbox` plus a non-sensitive capsule ID.
+Native Codex/Claude hosts keep the existing automatic capsule deletion behavior.
+No path silently falls back to Full Access, and retained capsules are never
+reported as active sessions.
+
 The discover packet derives a bounded multi-channel plan from reviewed evidence
 requirements. Required channels run first; exact repeated requests reuse the
 project cache without another provider call but still consume a bounded context

package/dist/research/orchestration.js

@@ -6,6 +6,7 @@ import { parseStrictArgs, strictBoolean, strictString } from "../strict-args.js"
 import { researchSetupHelp, runResearchSetupCommand } from "./setup-command.js";
 import { loadCapabilityDeclarations, lockCapabilities, verifyCapabilities, } from "./workspace/capabilities.js";
 import { inspectResearchContext } from "./workspace/context.js";
+import { packageVersion } from "./workspace/constants.js";
 import { setCapabilityCredentialFromEnvironment } from "./workspace/credentials.js";
 import { configureExternalSkillProfile, doctorExternalCapabilities, EXTERNAL_SKILL_CONTEXT_PROFILE, EXTERNAL_SKILL_MEDIA_PROFILE, EXTERNAL_SKILL_PROFILE, importExternalCapability, inspectExternalSkillCatalog, } from "./workspace/external-skills.js";
 import { appendJournalEvent } from "./workspace/journal.js";
@@ -20,6 +21,7 @@ import { recordDiscoveryAssessmentBatch } from "./workspace/discovery.js";
 import { bindEvidenceDownload } from "./workspace/downloads.js";
 import { registerNativeDiscoveryCandidate } from "./workspace/evidence-ledger.js";
 import { recordNativeResearchActivity } from "./workspace/native-activity.js";
+import { inspectReviewerBridgeStatus, startReviewerBridgeSidecar, } from "./workspace/review-executor.js";
 import { readAndVerifyProjectInputPlan } from "./workspace/input-plan.js";
 import { loadCurrentClaimEvidenceGraph, loadCurrentInferenceSnapshot, } from "./workspace/inference.js";
 import { addProjectInput, createProjectAddendum, initializeProject, forkProject, listProjects, loadProject, nextReadyPackage, normalizeEvidenceRequirements, refreshProject, retryProjectPackage, setProjectDisposition, } from "./workspace/projects.js";
@@ -32,7 +34,7 @@ import { schemaForStage } from "./workspace/schemas.js";
 import { readAndVerifyScientificDesign, scientificDesignSchema, } from "./workspace/scientific-design.js";
 import { inspectScientificReviewStatus, prepareScientificReview, scientificGateAssessmentSchema, scientificReviewSchema, submitScientificReview, } from "./workspace/scientific-review.js";
 import { isObject, pathExists, sha256Text, workspacePaths } from "./workspace/storage.js";
-import { doctorResearchWorkspace, initializeResearchWorkspace, requireResearchWorkspace, withWorkspaceLock, } from "./workspace/workspace.js";
+import { doctorResearchWorkspace, initializeResearchWorkspace, loadWorkspaceConfig, requireResearchWorkspace, withWorkspaceLock, } from "./workspace/workspace.js";
 const COMMON_OPTIONS = { help: "boolean", json: "boolean" };
 const WORKSPACE_OPTIONS = { ...COMMON_OPTIONS, workspace: "string" };
 export async function runResearchOrchestrationCommand(subcommand, argv, io) {
@@ -42,6 +44,8 @@ export async function runResearchOrchestrationCommand(subcommand, argv, io) {
         return runResearchSetupCommand(argv, io);
     if (subcommand === "workspace")
         return runWorkspace(argv, io);
+    if (subcommand === "reviewer")
+        return runReviewer(argv, io);
     if (subcommand === "capability")
         return runCapability(argv, io);
     if (subcommand === "policy")
@@ -65,6 +69,9 @@ export function researchOrchestrationHelp() {
   tiangong-ai research context inspect [--path <absolute-path>] [--json]
   tiangong-ai research workspace init <absolute-path> [--name <name>] [--mode smoke-test|production-research] [--json]
   tiangong-ai research workspace doctor [--workspace <absolute-path>] [--agent-smoke] [--capability-smoke] [--json]
+  tiangong-ai research reviewer serve --state-dir <absolute-private-directory> [--workspace <absolute-path>] [--json]
+  tiangong-ai research reviewer status [--workspace <absolute-path>] [--json]
+  tiangong-ai research reviewer doctor --confirm-agent-smoke-cost [--workspace <absolute-path>] [--json]
   tiangong-ai research capability catalog [--path <absolute-path>] [--workspace <absolute-path>] [--skill-root <absolute-path>] [--json]
   tiangong-ai research capability configure [--profile ${EXTERNAL_SKILL_PROFILE}|${EXTERNAL_SKILL_CONTEXT_PROFILE}|${EXTERNAL_SKILL_MEDIA_PROFILE}] [--skill-root <absolute-path>] [--workspace <absolute-path>] [--json]
   tiangong-ai research capability import --definition <absolute-json> [--workspace <absolute-path>] [--json]
@@ -79,7 +86,7 @@ export function researchOrchestrationHelp() {
   tiangong-ai research policy validate <project-id> [--workspace <path>] [--json]
   tiangong-ai research policy approve <project-id> --confirm [--acknowledge-defaults] [--workspace <path>] [--json]
   tiangong-ai research policy resolve <project-id> [--workspace <path>] [--json]
-  tiangong-ai research publication freeze <project-id> --manuscript <absolute-file> --assessment <absolute-json> --submission <absolute-json> --producer-agent codex|claude --producer-session <opaque-id> [--supplements <absolute-json-array>] [--workspace <path>] [--json]
+  tiangong-ai research publication freeze <project-id> --manuscript <absolute-file> --assessment <absolute-json> --submission <absolute-json> --producer-agent codex|claude|workbuddy|codebuddy --producer-session <opaque-id> [--supplements <absolute-json-array>] [--workspace <path>] [--json]
   tiangong-ai research publication review prepare <project-id> --role evidence|methods-reproducibility|domain-novelty|journal-editor --reviewer-agent codex|claude --reviewer-session <opaque-id> [--workspace <path>] [--json]
   tiangong-ai research publication review submit <project-id> --role evidence|methods-reproducibility|domain-novelty|journal-editor --review <absolute-json> [--workspace <path>] [--json]
   tiangong-ai research publication status <project-id> [--workspace <path>] [--json]
@@ -100,7 +107,7 @@ export function researchOrchestrationHelp() {
   tiangong-ai research project scientific status <project-id> [--workspace <path>] [--json]
   tiangong-ai research project audit export <project-id> --output <absolute-new-directory> [--workspace <path>] [--json]
   tiangong-ai research project audit verify --bundle <absolute-directory> [--json]
-  tiangong-ai research project stage prepare <project-id> --stage discover|acquire|analyze|synthesize --host-agent codex|claude [--workspace <path>] [--json]
+  tiangong-ai research project stage prepare <project-id> --stage discover|acquire|analyze|synthesize --host-agent codex|claude|workbuddy|codebuddy [--workspace <path>] [--json]
   tiangong-ai research project stage submit <project-id> --session <id> --output <absolute-json> [--confirm-model <id>] [--workspace <path>] [--json]
   tiangong-ai research project stage abort <project-id> --session <id> [--workspace <path>] [--json]
   tiangong-ai research project evidence fetch <project-id> --request <absolute-json> [--workspace <path>] [--json]
@@ -120,6 +127,92 @@ export function researchOrchestrationHelp() {
 ${researchSetupHelp()}
 `;
 }
+async function runReviewer(argv, io) {
+    const [action, ...rest] = argv;
+    if (!action || action === "--help" || action === "-h")
+        return writeHelp(io);
+    if (action === "status") {
+        const args = parseStrictArgs(rest, WORKSPACE_OPTIONS, "research reviewer status");
+        if (strictBoolean(args, "help"))
+            return writeHelp(io);
+        if (args.positionals.length)
+            throw unknownAction("research reviewer status", args.positionals[0]);
+        const root = await workspaceFromArgs(args);
+        writeJson(io, await inspectReviewerBridgeStatus(root), args);
+        return 0;
+    }
+    if (action === "doctor") {
+        const args = parseStrictArgs(rest, { ...WORKSPACE_OPTIONS, "confirm-agent-smoke-cost": "boolean" }, "research reviewer doctor");
+        if (strictBoolean(args, "help"))
+            return writeHelp(io);
+        if (args.positionals.length)
+            throw unknownAction("research reviewer doctor", args.positionals[0]);
+        if (!strictBoolean(args, "confirm-agent-smoke-cost")) {
+            throw new CliError("Reviewer doctor requires explicit model-cost confirmation.", {
+                code: "RESEARCH_REVIEW_BRIDGE_CONFIRMATION_REQUIRED",
+                exitCode: 3,
+                details: {
+                    minimumAction: "Rerun with --confirm-agent-smoke-cost after reviewing reviewer provider quota and cost.",
+                },
+            });
+        }
+        const root = await workspaceFromArgs(args);
+        const result = await doctorResearchWorkspace(root, {
+            agentSmoke: true,
+            environment: io.env,
+        });
+        writeJson(io, result, args);
+        return result.status === "ready" ? 0 : 3;
+    }
+    if (action === "serve") {
+        const args = parseStrictArgs(rest, { ...WORKSPACE_OPTIONS, "state-dir": "string" }, "research reviewer serve");
+        if (strictBoolean(args, "help"))
+            return writeHelp(io);
+        if (args.positionals.length)
+            throw unknownAction("research reviewer serve", args.positionals[0]);
+        const stateDirectory = strictString(args, "state-dir");
+        if (!stateDirectory ||
+            !isAbsolute(stateDirectory) ||
+            resolve(stateDirectory) !== stateDirectory) {
+            throw new CliError("Reviewer sidecar --state-dir must be an explicit absolute directory.", {
+                code: "RESEARCH_REVIEW_BRIDGE_STATE_INVALID",
+                exitCode: 2,
+            });
+        }
+        const root = await workspaceFromArgs(args);
+        const sidecar = await startReviewerBridgeSidecar({
+            root,
+            stateDirectory,
+            environment: io.env,
+        });
+        writeJson(io, {
+            status: "ready",
+            workspaceId: sidecar.workspaceId,
+            packageVersion: packageVersion(),
+            keyFingerprint: sidecar.keyFingerprint,
+            supportedActions: ["execute", "fingerprint", "status"],
+        }, args);
+        try {
+            await waitForReviewerSidecarTermination();
+        }
+        finally {
+            await sidecar.close();
+        }
+        return 0;
+    }
+    throw unknownAction("research reviewer", action);
+}
+async function waitForReviewerSidecarTermination() {
+    await new Promise((resolvePromise) => {
+        const stop = () => {
+            process.off("SIGINT", stop);
+            process.off("SIGTERM", stop);
+            resolvePromise();
+        };
+        process.once("SIGINT", stop);
+        process.once("SIGTERM", stop);
+    });
+}
 async function runPublication(argv, io) {
     const [action, ...rest] = argv;
     if (!action || action === "--help" || action === "-h")
@@ -1314,6 +1407,7 @@ async function runStatus(argv, io) {
         return writeHelp(io);
     rejectPositionals(args.positionals, "research status");
     const root = await workspaceFromArgs(args);
+    const config = await loadWorkspaceConfig(root);
     const selectedProject = strictString(args, "project");
     const workspaceProjects = await listProjects(root);
     const allProjects = selectedProject
@@ -1329,6 +1423,20 @@ async function runStatus(argv, io) {
             project.status !== "abandoned");
     const result = {
         workspace: root,
+        execution: {
+            producer: {
+                host: config.producer.agent,
+                model: config.producer.model,
+                mode: config.producer.executionMode,
+            },
+            reviewer: {
+                agent: config.reviewer.agent,
+                model: config.reviewer.model,
+                mode: config.reviewer.executionMode,
+                transport: config.reviewerExecution.transport,
+                isolationProvider: config.reviewerExecution.isolationProvider,
+            },
+        },
         hiddenSupersededProjects: selectedProject || strictBoolean(args, "all")
             ? 0
             : workspaceProjects.filter((project) => project.lineage.supersededBy !== null).length,
@@ -1610,7 +1718,7 @@ function projectRecommendedAction(root, project, readyPackage, nativeStage, scie
             : "Inspect the blocking package and use explicit retry or fork recovery.";
     }
     if (readyPackage && ["discover", "acquire", "analyze", "synthesize"].includes(readyPackage)) {
-        return `Prepare native ${readyPackage}: tiangong-ai research project stage prepare ${project.id} --stage ${readyPackage} --host-agent <codex|claude> --workspace ${root}`;
+        return `Prepare native ${readyPackage}: tiangong-ai research project stage prepare ${project.id} --stage ${readyPackage} --host-agent <codex|claude|workbuddy|codebuddy> --workspace ${root}`;
     }
     return readyPackage === "review"
         ? `Run the independent reviewer package: tiangong-ai research run --project ${project.id} --workspace ${root}`
@@ -1731,9 +1839,10 @@ function nativeProducerStage(value) {
     });
 }
 function nativeHostAgent(value) {
-    if (value === "codex" || value === "claude")
+    if (value === "codex" || value === "claude" || value === "workbuddy" || value === "codebuddy") {
         return value;
-    throw new CliError("--host-agent must be codex or claude.", {
+    }
+    throw new CliError("--host-agent must be codex, claude, workbuddy, or codebuddy.", {
         code: "RESEARCH_NATIVE_HOST_INVALID",
         exitCode: 2,
     });
@@ -1846,9 +1955,13 @@ function scientificReviewRole(value) {
     });
 }
 function publicationAgent(value, label) {
-    if (value === "codex" || value === "claude")
+    const producer = label.includes("producer");
+    if (value === "codex" ||
+        value === "claude" ||
+        (producer && (value === "workbuddy" || value === "codebuddy"))) {
         return value;
-    throw new CliError(`--${label}-agent must be codex or claude.`, {
+    }
+    throw new CliError(`--${label}-agent must be ${producer ? "codex, claude, workbuddy, or codebuddy" : "codex or claude"}.`, {
         code: "RESEARCH_PUBLICATION_AGENT_INVALID",
         exitCode: 2,
     });