@lazyingart/agintiflow 0.20.242 → 0.20.244

package/docs/deep-research-engine.md

@@ -10,6 +10,15 @@ Simple questions should stay on the fast path. A deep-research run spends more
 queries and model calls only when breadth, verification, and traceability add
 real value.
 
+For a request that combines local workspace evidence with web research, the
+outer agent first receives normal inspection tools. After it has read two
+relevant files, or read one file plus inspected/searched the project, the next
+research turn is constrained to `deep_research` and `finish`. This keeps local
+notes authoritative without letting an agent silently replace a requested
+multi-source review with ad hoc browsing. Tool history is scoped to the newest
+genuine user request, so a completed research call from an older task does not
+suppress a later correction or refresh.
+
 ## Architecture
 
 The implementation follows the strongest production patterns without making
@@ -205,7 +214,10 @@ To resume a partial or completed same-query run, pass the returned
 `refresh=true` is explicit. A transient run that retrieved zero allowed sources
 is marked failed, preserves its attempts, and retries retrieval on resume
 instead of caching an empty report as success. Checkpoint schema changes
-invalidate old cached runs automatically.
+invalidate old cached runs automatically. The public tool result also carries
+the research schema version; the outer session reuses a completed result only
+when that version matches the installed engine. Versionless or older retained
+results are refreshed instead of being presented as current evidence.
 
 `outputPath` is optional and must name a Markdown file inside the active
 workspace. Repository internals such as `.git`, dependency trees such as

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lazyingart/agintiflow",
-  "version": "0.20.242",
+  "version": "0.20.244",
   "type": "module",
   "description": "AgInTiFlow is a project-aware agent workspace for hybrid wet-dry R&D, hardware-aware intelligence, software automation, and industrial workflows.",
   "license": "Apache-2.0",
@@ -66,6 +66,7 @@
     "scripts/supervision-ledger.js",
     "scripts/smoke-supervision-ledger.js",
     "scripts/smoke-integration-production-mount.js",
+    "scripts/smoke-integration-production-runtime-bundle.js",
     "scripts/smoke-integration-storage-authority.js",
     "scripts/smoke-integration-retained-durable-common.js",
     "scripts/smoke-integration-retained-file-lock.js",
@@ -203,6 +204,7 @@
     "supervision:ledger": "node scripts/supervision-ledger.js",
     "smoke:supervision-ledger": "node scripts/smoke-supervision-ledger.js",
     "smoke:integration-production-mount": "node scripts/smoke-integration-production-mount.js",
+    "smoke:integration-production-runtime-bundle": "node scripts/smoke-integration-production-runtime-bundle.js",
     "smoke:integration-storage-authority": "node scripts/smoke-integration-storage-authority.js",
     "smoke:integration-retained-durable-common": "node scripts/smoke-integration-retained-durable-common.js",
     "smoke:integration-retained-file-lock": "node scripts/smoke-integration-retained-file-lock.js",
@@ -219,7 +221,7 @@
     "storage:migrate": "node bin/aginti-cli.js storage migrate",
     "publish:env": "node scripts/npm-publish-from-env.js publish --access public",
     "publish:env:whoami": "node scripts/npm-publish-from-env.js whoami",
-    "test": "npm run check && npm run smoke:integration-production-mount && npm run smoke:integration-storage-authority && npm run smoke:integration-retained-durable-common && npm run smoke:integration-retained-file-lock && npm run smoke:integration-retained-event-ledger && npm run smoke:integration-retained-event-ledger-bundle && npm run smoke:integration-retained-repository-kernel && npm run smoke:integration-retained-session-state-store && npm run smoke:integration-retained-native-session-repository-state && npm run smoke:integration-retained-native-execution-evidence && npm run smoke:integration-retained-runtime-repository-surface && npm run smoke:integration-retained-runtime-repository-phase-b && npm run smoke:integration-runtime-repository-contract && npm run smoke:integration-runtime-authority && npm run smoke:localllm-provider && npm run smoke:localllm-model-tiers && npm run smoke:localllm-code-routing && npm run smoke:local-failure-recovery && npm run smoke:localllm-auto-max && npm run smoke:local-resource-policy && npm run smoke:context-budget-recovery && npm run smoke:session-runtime && npm run smoke:runtime-core && npm run smoke:progressive-tools && npm run smoke:truthful-completion && npm run smoke:document-artifact-quality && npm run smoke:writing-specialist-routing && npm run eval:local-first-agent && npm run eval:provider-attribution && npm run smoke:runtime-compat && npm run smoke:autoupdate && npm run smoke:web-api && npm run smoke:math-rendering && npm run smoke:web-ui && npm run smoke:web-autostart && npm run smoke:webapp-command && npm run smoke:web-port-fallback && npm run smoke:docker-command && npm run smoke:coding-tools && npm run smoke:dynamic-step-budget && npm run smoke:execution-policy && npm run smoke:aaps-adapter && npm run smoke:auxiliary-tools && npm run smoke:perception-research && npm run smoke:deep-research && npm run smoke:public-research && npm run smoke:safe-chat && npm run smoke:auth && npm run smoke:agentlink && npm run smoke:canvas-artifacts && npm run smoke:capabilities && npm run smoke:mcp && npm run smoke:model-roles && npm run smoke:platform && npm run smoke:permission-modes && npm run smoke:skills && npm run smoke:skillmesh && npm run smoke:supervision-ledger && npm run smoke:tmux-tools && npm run smoke:long-jobs && npm run smoke:run-stdin && npm run smoke:cli-chat && npm run smoke:inbox",
+    "test": "npm run check && npm run smoke:integration-production-mount && npm run smoke:integration-production-runtime-bundle && npm run smoke:integration-storage-authority && npm run smoke:integration-retained-durable-common && npm run smoke:integration-retained-file-lock && npm run smoke:integration-retained-event-ledger && npm run smoke:integration-retained-event-ledger-bundle && npm run smoke:integration-retained-repository-kernel && npm run smoke:integration-retained-session-state-store && npm run smoke:integration-retained-native-session-repository-state && npm run smoke:integration-retained-native-execution-evidence && npm run smoke:integration-retained-runtime-repository-surface && npm run smoke:integration-retained-runtime-repository-phase-b && npm run smoke:integration-runtime-repository-contract && npm run smoke:integration-runtime-authority && npm run smoke:localllm-provider && npm run smoke:localllm-model-tiers && npm run smoke:localllm-code-routing && npm run smoke:local-failure-recovery && npm run smoke:localllm-auto-max && npm run smoke:local-resource-policy && npm run smoke:context-budget-recovery && npm run smoke:session-runtime && npm run smoke:runtime-core && npm run smoke:progressive-tools && npm run smoke:truthful-completion && npm run smoke:document-artifact-quality && npm run smoke:writing-specialist-routing && npm run eval:local-first-agent && npm run eval:provider-attribution && npm run smoke:runtime-compat && npm run smoke:autoupdate && npm run smoke:web-api && npm run smoke:math-rendering && npm run smoke:web-ui && npm run smoke:web-autostart && npm run smoke:webapp-command && npm run smoke:web-port-fallback && npm run smoke:docker-command && npm run smoke:coding-tools && npm run smoke:dynamic-step-budget && npm run smoke:execution-policy && npm run smoke:aaps-adapter && npm run smoke:auxiliary-tools && npm run smoke:perception-research && npm run smoke:deep-research && npm run smoke:public-research && npm run smoke:safe-chat && npm run smoke:auth && npm run smoke:agentlink && npm run smoke:canvas-artifacts && npm run smoke:capabilities && npm run smoke:mcp && npm run smoke:model-roles && npm run smoke:platform && npm run smoke:permission-modes && npm run smoke:skills && npm run smoke:skillmesh && npm run smoke:supervision-ledger && npm run smoke:tmux-tools && npm run smoke:long-jobs && npm run smoke:run-stdin && npm run smoke:cli-chat && npm run smoke:inbox",
     "pack:dry-run": "npm pack --dry-run",
     "smoke:capabilities": "node scripts/smoke-capabilities.js"
   },

package/scripts/smoke-context-budget-recovery.js

@@ -125,57 +125,94 @@ const sentPlan = capturedPayload.messages.map((message) => message.content || ""
 assert.ok(sentPlan.includes(HEAD), "plan request lost the exact task head");
 assert.ok(sentPlan.includes(TAIL), "plan request lost the latest task tail");
 
+const compactionState = {
+  goal: hugeGoal,
+  plan: "Use the existing routine and verify its artifact.",
+  messages: [
+    { role: "system", content: "SYSTEM-HEAD\n" + "policy ".repeat(10000) + "\nSYSTEM-TAIL" },
+    { role: "user", content: "first request" },
+    {
+      role: "user",
+      content:
+        "The runtime proactively compacted a long agent history before the provider context became inefficient or unstable. OLD-COMPACTION-MUST-NOT-RECUR",
+    },
+    {
+      role: "assistant",
+      content: "",
+      tool_calls: [
+        {
+          id: "deep-research-complete",
+          type: "function",
+          function: {
+            name: "deep_research",
+            arguments: '{"query":"reliability evidence","outputPath":"reports/reliability.md"}',
+          },
+        },
+      ],
+    },
+    {
+      role: "tool",
+      tool_call_id: "deep-research-complete",
+      content: JSON.stringify({
+        ok: true,
+        toolName: "deep_research",
+        version: 14,
+        researchId: "reliability-evidence-v14",
+        status: "completed",
+        stage: "completed",
+        reportPath: "reports/reliability.md",
+        artifactPath: ".aginti/deep-research-reliability.json",
+        queryCount: 10,
+        sourceCount: 16,
+        coverage: { requiredFirstPartyVerified: true },
+        audit: { citationCoverage: 1 },
+      }),
+    },
+    {
+      role: "tool",
+      content: JSON.stringify({
+        ok: true,
+        toolName: "read_file",
+        path: "/evidence/Musia/SKILL.md",
+        bytes: 2048,
+        sha256: "1234567890abcdef1234567890abcdef1234567890abcdef1234567890abcdef",
+        contentTruncated: false,
+        content: [
+          "---",
+          "name: musia-music-production",
+          "description: Create and review songs through the established Musia production workflow.",
+          "---",
+          "# Musia Music Production",
+          "Use the existing CLI and preserve the reviewed song artifacts.",
+        ].join("\n"),
+        commandEvidence: [{ command: "node bin/musia.js doctor --json" }],
+        pathEvidence: [{ path: "bin/musia.js" }],
+      }),
+    },
+    {
+      role: "tool",
+      content: JSON.stringify({
+        ok: true,
+        toolName: "list_files",
+        path: "/evidence/LALACHAN/scripts",
+        entries: [{ path: "scripts/xyq_cdp_browser.py" }, { path: "scripts/wait_downloaded_mp4.sh" }],
+      }),
+    },
+    { role: "user", content: "latest interruption: send the finished PDF to this exact chat" },
+  ],
+};
 const runtimeMessages = buildContextBudgetCompactionMessages(
-  {
-    goal: hugeGoal,
-    plan: "Use the existing routine and verify its artifact.",
-    messages: [
-      { role: "system", content: "SYSTEM-HEAD\n" + "policy ".repeat(10000) + "\nSYSTEM-TAIL" },
-      { role: "user", content: "first request" },
-      {
-        role: "user",
-        content:
-          "The runtime proactively compacted a long agent history before the provider context became inefficient or unstable. OLD-COMPACTION-MUST-NOT-RECUR",
-      },
-      {
-        role: "tool",
-        content: JSON.stringify({
-          ok: true,
-          toolName: "read_file",
-          path: "/evidence/Musia/SKILL.md",
-          bytes: 2048,
-          sha256: "1234567890abcdef1234567890abcdef1234567890abcdef1234567890abcdef",
-          contentTruncated: false,
-          content: [
-            "---",
-            "name: musia-music-production",
-            "description: Create and review songs through the established Musia production workflow.",
-            "---",
-            "# Musia Music Production",
-            "Use the existing CLI and preserve the reviewed song artifacts.",
-          ].join("\n"),
-          commandEvidence: [{ command: "node bin/musia.js doctor --json" }],
-          pathEvidence: [{ path: "bin/musia.js" }],
-        }),
-      },
-      {
-        role: "tool",
-        content: JSON.stringify({
-          ok: true,
-          toolName: "list_files",
-          path: "/evidence/LALACHAN/scripts",
-          entries: [{ path: "scripts/xyq_cdp_browser.py" }, { path: "scripts/wait_downloaded_mp4.sh" }],
-        }),
-      },
-      { role: "user", content: "latest interruption: send the finished PDF to this exact chat" },
-    ],
-  },
+  compactionState,
   config,
   { title: "", url: "" },
   3,
   { reason: "test context recovery" }
 );
 const runtimeText = runtimeMessages.map((message) => message.content || "").join("\n");
+const retainedNativeDeepResearch = runtimeMessages.find((message) =>
+  Array.isArray(message.tool_calls) &&
+  message.tool_calls.some((call) => call?.function?.name === "deep_research")
+);
 assert.ok(
   estimateMessageTokens(runtimeMessages) <= 12288,
   "runtime compaction exceeded the bounded LocalLLM retry target"
@@ -193,8 +230,27 @@ assert.ok(runtimeText.includes("sha256=1234567890abcdef"));
 assert.ok(runtimeText.includes("content=complete"));
 assert.ok(runtimeText.includes("node bin/musia.js doctor --json"));
 assert.ok(runtimeText.includes("scripts/xyq_cdp_browser.py"));
+assert.ok(retainedNativeDeepResearch, "native compaction lost the completed deep_research call");
+assert.ok(runtimeText.includes("reliability-evidence-v14"));
+assert.ok(runtimeText.includes('"version":14'));
 assert.ok(!runtimeText.includes("OLD-COMPACTION-MUST-NOT-RECUR"));
 assert.match(runtimeText, /Do not reread a listed source solely because compaction occurred/);
 assert.match(runtimeText, /never restart a full-file read loop after compaction/);
 
+const deepSeekRuntimeMessages = buildContextBudgetCompactionMessages(
+  compactionState,
+  { ...config, provider: "deepseek", model: "deepseek-chat" },
+  { title: "", url: "" },
+  3,
+  { reason: "test DeepSeek context recovery" }
+);
+const deepSeekRuntimeText = deepSeekRuntimeMessages.map((message) => message.content || "").join("\n");
+assert.ok(deepSeekRuntimeText.includes("Tool: deep_research"));
+assert.ok(deepSeekRuntimeText.includes("reliability-evidence-v14"));
+assert.ok(deepSeekRuntimeText.includes('"version":14'));
+assert.ok(
+  estimateMessageTokens(deepSeekRuntimeMessages) <= 12288,
+  "DeepSeek runtime compaction exceeded the bounded retry target"
+);
+
 console.log("context budget recovery smoke passed");

package/scripts/smoke-deep-research.js

@@ -3,7 +3,7 @@ import fs from "node:fs/promises";
 import os from "node:os";
 import path from "node:path";
 
-import { auditResearchSynthesis, deepResearch } from "../src/deep-research.js";
+import { auditResearchSynthesis, deepResearch, RESEARCH_VERSION } from "../src/deep-research.js";
 import { checkToolUse } from "../src/guardrails.js";
 import { flushHousekeeping } from "../src/housekeeping.js";
 import { requestNextStep, toolChoiceForProvider } from "../src/model-client.js";
@@ -59,6 +59,50 @@ async function main() {
     !shouldStartWithDeepResearch(localEvidenceGoal),
     "local-source research incorrectly forced deep_research before workspace inspection"
   );
+  const inspectedLocalEvidenceMessages = [
+    { role: "user", content: localEvidenceGoal },
+    {
+      role: "assistant",
+      tool_calls: [{ id: "inspect-notes", function: { name: "read_file", arguments: '{"path":"PROJECT_NOTES.md"}' } }],
+    },
+    {
+      role: "assistant",
+      tool_calls: [{ id: "inspect-sources", function: { name: "read_file", arguments: '{"path":"sources.json"}' } }],
+    },
+  ];
+  assert(
+    shouldStartWithDeepResearch(localEvidenceGoal, inspectedLocalEvidenceMessages),
+    "local-source research did not enter bounded deep research after workspace inspection"
+  );
+  assert(
+    !shouldStartWithDeepResearch(localEvidenceGoal, [
+      ...inspectedLocalEvidenceMessages,
+      {
+        role: "assistant",
+        tool_calls: [{ id: "current-research", function: { name: "deep_research", arguments: "{}" } }],
+      },
+    ]),
+    "the current request repeated deep research after already requesting it"
+  );
+  assert(
+    shouldStartWithDeepResearch(localEvidenceGoal, [
+      ...inspectedLocalEvidenceMessages,
+      {
+        role: "assistant",
+        tool_calls: [{ id: "old-research", function: { name: "deep_research", arguments: "{}" } }],
+      },
+      { role: "user", content: "Refresh this evidence review because the current report quality is not acceptable." },
+      {
+        role: "assistant",
+        tool_calls: [{ id: "refresh-report", function: { name: "read_file", arguments: '{"path":"agent-reliability-evidence-review.md"}' } }],
+      },
+      {
+        role: "assistant",
+        tool_calls: [{ id: "refresh-sources", function: { name: "read_file", arguments: '{"path":"sources.json"}' } }],
+      },
+    ]),
+    "a completed research call from an older user intent suppressed a fresh bounded research pass"
+  );
   assert(
     shouldStartWithDeepResearch("Write a deep web research report comparing three primary papers."),
     "standalone deep research no longer starts with the bounded research workflow"
@@ -509,6 +553,7 @@ async function main() {
     },
     store
   );
+  assert(research.version === RESEARCH_VERSION, "deep research did not expose its result-schema version");
   assert(research.ok && research.sourceCount === 2, `deep research failed: ${research.error || "unknown"}`);
   assert(
     researchSearchProviders.length === 2 && researchSearchProviders.every((provider) => provider === "multi"),

package/scripts/smoke-dynamic-step-budget.js

@@ -4,6 +4,7 @@ import os from "node:os";
 import path from "node:path";
 import { fileURLToPath } from "node:url";
 import { runAgent } from "../src/agent-runner.js";
+import { RESEARCH_VERSION } from "../src/deep-research.js";
 import { resolveRuntimeConfig } from "../src/config.js";
 import { classifyCommand, evaluateCommandPolicy } from "../src/command-policy.js";
 import {
@@ -4338,6 +4339,7 @@ try {
     {
       ok: true,
       toolName: "deep_research",
+      version: RESEARCH_VERSION,
       researchId: "research-one",
       status: "completed",
       reportPath: path.join(workspace, "report.md"),
@@ -4354,6 +4356,16 @@ try {
     reusedResearch?.duplicateSuppressed && reusedResearch.reportPath === path.join(workspace, "report.md"),
     "same-goal deep research did not reuse an already completed exact report"
   );
+  completedResearchState.meta.completedDeepResearch[0].result.version = RESEARCH_VERSION - 1;
+  assert(
+    completedDeepResearchReuse(
+      completedResearchState,
+      { query: "A model-expanded query", outputPath: "report.md", refresh: true },
+      { commandCwd: workspace }
+    ) === null,
+    "a stale deep-research engine result was reused after the report contract changed"
+  );
+  completedResearchState.meta.completedDeepResearch[0].result.version = RESEARCH_VERSION;
   completedResearchState.meta.goalContract = { revision: 2, currentHash: "goal-two" };
   assert(
     completedDeepResearchReuse(

package/scripts/smoke-integration-production-mount.js

@@ -547,6 +547,7 @@ async function verifyPackagedBinAndScriptClosure() {
     "scripts/eval-provider-attribution.js",
     "scripts/smoke-context-budget-recovery.js",
     "scripts/smoke-integration-production-mount.js",
+    "scripts/smoke-integration-production-runtime-bundle.js",
   ]) {
     assert.equal(packageJson.files.includes(requiredFile), true);
   }
@@ -1087,6 +1088,38 @@ async function main() {
       "INTEGRATION_CREDENTIAL_SOURCE_FORBIDDEN"
     );
 
+    let cliCheckOutput = "";
+    await withCanonicalCredentialFixture(async () => {
+      const summary = await integrationCliMain(["check", "--config", configPath], {
+        env: { CREDENTIALS_DIRECTORY: INTEGRATION_SYSTEMD_CREDENTIALS_DIRECTORY },
+        stdout: { write(chunk) { cliCheckOutput += String(chunk); } },
+      });
+      assert.equal(summary.status, "checked-disabled");
+      assert.equal(summary.capability?.enabled, false);
+      assert.equal(summary.implementationReady, false);
+      assert.equal(typeof summary.runtimeBundle?.healthy, "boolean");
+      assert.equal(summary.runtimeBundle?.implementationReady, false);
+      assert.equal(summary.runtimeBundle?.capabilityEnabled, false);
+      assert.equal(summary.runtimeBundle?.httpServingEnabled, false);
+      if (summary.runtimeBundle.healthy) {
+        assert.equal(summary.runtimeBundle.firstBlocker?.component, "idempotencyStore");
+        assert.equal(
+          summary.runtimeBundle.firstBlocker?.code,
+          "INTEGRATION_DESCRIPTOR_BOUND_IDEMPOTENCY_UNAVAILABLE"
+        );
+      } else {
+        assert.equal(summary.runtimeBundle.firstBlocker?.component, "storageAuthority");
+        assert.match(
+          summary.runtimeBundle.firstBlocker?.code || "",
+          /^INTEGRATION_STORAGE_/u
+        );
+      }
+      assert.deepEqual(
+        JSON.parse(cliCheckOutput.trim()),
+        JSON.parse(JSON.stringify(summary))
+      );
+    });
+
     const cliServePort = await unusedLoopbackPort();
     const cliServeConfigPath = path.join(tempRoot, "integration-serve.json");
     await fs.writeFile(